summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c19
-rw-r--r--net/ipv6/addrconf_core.c6
-rw-r--r--net/ipv6/af_inet6.c5
-rw-r--r--net/ipv6/icmp.c4
-rw-r--r--net/ipv6/inet6_hashtables.c2
-rw-r--r--net/ipv6/ip6_fib.c182
-rw-r--r--net/ipv6/ip6_output.c340
-rw-r--r--net/ipv6/ndisc.c11
-rw-r--r--net/ipv6/netfilter.c123
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c53
-rw-r--r--net/ipv6/proc.c4
-rw-r--r--net/ipv6/reassembly.c52
-rw-r--r--net/ipv6/route.c1074
-rw-r--r--net/ipv6/sysctl_net_ipv6.c3
-rw-r--r--net/ipv6/tcp_ipv6.c29
-rw-r--r--net/ipv6/udp.c26
16 files changed, 1435 insertions, 498 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 081bb517e40d..521e3203e83a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2417,9 +2417,13 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
goto out;
for_each_fib6_node_rt_rcu(fn) {
- if (rt->fib6_nh.fib_nh_dev->ifindex != dev->ifindex)
+ /* prefix routes only use builtin fib6_nh */
+ if (rt->nh)
continue;
- if (no_gw && rt->fib6_nh.fib_nh_gw_family)
+
+ if (rt->fib6_nh->fib_nh_dev->ifindex != dev->ifindex)
+ continue;
+ if (no_gw && rt->fib6_nh->fib_nh_gw_family)
continue;
if ((rt->fib6_flags & flags) != flags)
continue;
@@ -3123,11 +3127,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
struct in_device *in_dev = __in_dev_get_rtnl(dev);
if (in_dev && (dev->flags & IFF_UP)) {
struct in_ifaddr *ifa;
-
int flag = scope;
- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
-
+ in_dev_for_each_ifa_rtnl(ifa, in_dev) {
addr.s6_addr32[3] = ifa->ifa_local;
if (ifa->ifa_scope == RT_SCOPE_LINK)
@@ -6350,16 +6352,17 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
list_for_each_entry(ifa, &idev->addr_list, if_list) {
spin_lock(&ifa->lock);
if (ifa->rt) {
- struct fib6_info *rt = ifa->rt;
+ /* host routes only use builtin fib6_nh */
+ struct fib6_nh *nh = ifa->rt->fib6_nh;
int cpu;
rcu_read_lock();
ifa->rt->dst_nopolicy = val ? true : false;
- if (rt->rt6i_pcpu) {
+ if (nh->rt6i_pcpu) {
for_each_possible_cpu(cpu) {
struct rt6_info **rtp;
- rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+ rtp = per_cpu_ptr(nh->rt6i_pcpu, cpu);
addrconf_set_nopolicy(*rtp, val);
}
}
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 5b1246635e02..783f3c1466da 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -183,6 +183,11 @@ static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
return -EAFNOSUPPORT;
}
+static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt)
+{
+ return -EAFNOSUPPORT;
+}
+
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
.ipv6_route_input = eafnosupport_ipv6_route_input,
@@ -192,6 +197,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.fib6_select_path = eafnosupport_fib6_select_path,
.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
.fib6_nh_init = eafnosupport_fib6_nh_init,
+ .ip6_del_rt = eafnosupport_ip6_del_rt,
};
EXPORT_SYMBOL_GPL(ipv6_stub);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 5352708b7b2d..7382a927d1eb 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -208,7 +208,7 @@ lookup_protocol:
np->mc_loop = 1;
np->mc_all = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->repflow = net->ipv6.sysctl.flowlabel_reflect;
+ np->repflow = net->ipv6.sysctl.flowlabel_reflect & 1;
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
@@ -922,6 +922,9 @@ static const struct ipv6_stub ipv6_stub_impl = {
.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
.fib6_nh_init = fib6_nh_init,
.fib6_nh_release = fib6_nh_release,
+ .fib6_update_sernum = fib6_update_sernum_stub,
+ .fib6_rt_update = fib6_rt_update,
+ .ip6_del_rt = ip6_del_rt,
.udpv6_encap_enable = udpv6_encap_enable,
.ndisc_send_na = ndisc_send_na,
.nd_tbl = &nd_tbl,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 375b4b4f9bf5..12906301ec7b 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -75,9 +75,9 @@
*
* On SMP we have one ICMP socket per-cpu.
*/
-static inline struct sock *icmpv6_sk(struct net *net)
+static struct sock *icmpv6_sk(struct net *net)
{
- return *this_cpu_ptr(net->ipv6.icmp_sk);
+ return this_cpu_read(*net->ipv6.icmp_sk);
}
static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b2a55f300318..cf60fae9533b 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -174,7 +174,7 @@ struct sock *inet6_lookup_listener(struct net *net,
saddr, sport, &in6addr_any, hnum,
dif, sdif);
done:
- if (unlikely(IS_ERR(result)))
+ if (IS_ERR(result))
return NULL;
return result;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9180c8b6f764..1d16a01eccf5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -143,20 +143,19 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
addr[fn_bit >> 5];
}
-struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
+struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
{
struct fib6_info *f6i;
+ size_t sz = sizeof(*f6i);
- f6i = kzalloc(sizeof(*f6i), gfp_flags);
+ if (with_fib6_nh)
+ sz += sizeof(struct fib6_nh);
+
+ f6i = kzalloc(sz, gfp_flags);
if (!f6i)
return NULL;
- f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
- if (!f6i->rt6i_pcpu) {
- kfree(f6i);
- return NULL;
- }
-
+ /* fib6_siblings is a union with nh_list, so this initializes both */
INIT_LIST_HEAD(&f6i->fib6_siblings);
refcount_set(&f6i->fib6_ref, 1);
@@ -166,36 +165,15 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
void fib6_info_destroy_rcu(struct rcu_head *head)
{
struct fib6_info *f6i = container_of(head, struct fib6_info, rcu);
- struct rt6_exception_bucket *bucket;
WARN_ON(f6i->fib6_node);
- bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
- kfree(bucket);
-
- if (f6i->rt6i_pcpu) {
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct rt6_info **ppcpu_rt;
- struct rt6_info *pcpu_rt;
-
- ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
- pcpu_rt = *ppcpu_rt;
- if (pcpu_rt) {
- dst_dev_put(&pcpu_rt->dst);
- dst_release(&pcpu_rt->dst);
- *ppcpu_rt = NULL;
- }
- }
-
- free_percpu(f6i->rt6i_pcpu);
- }
-
- fib6_nh_release(&f6i->fib6_nh);
+ if (f6i->nh)
+ nexthop_put(f6i->nh);
+ else
+ fib6_nh_release(f6i->fib6_nh);
ip_fib_metrics_put(f6i->fib6_metrics);
-
kfree(f6i);
}
EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu);
@@ -389,10 +367,10 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
return call_fib6_notifier(nb, net, event_type, &info.info);
}
-static int call_fib6_entry_notifiers(struct net *net,
- enum fib_event_type event_type,
- struct fib6_info *rt,
- struct netlink_ext_ack *extack)
+int call_fib6_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct fib6_info *rt,
+ struct netlink_ext_ack *extack)
{
struct fib6_entry_notifier_info info = {
.info.extack = extack,
@@ -403,6 +381,22 @@ static int call_fib6_entry_notifiers(struct net *net,
return call_fib6_notifiers(net, event_type, &info.info);
}
+int call_fib6_multipath_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct fib6_info *rt,
+ unsigned int nsiblings,
+ struct netlink_ext_ack *extack)
+{
+ struct fib6_entry_notifier_info info = {
+ .info.extack = extack,
+ .rt = rt,
+ .nsiblings = nsiblings,
+ };
+
+ rt->fib6_table->fib_seq++;
+ return call_fib6_notifiers(net, event_type, &info.info);
+}
+
struct fib6_dump_arg {
struct net *net;
struct notifier_block *nb;
@@ -895,16 +889,14 @@ insert_above:
return ln;
}
-static void fib6_drop_pcpu_from(struct fib6_info *f6i,
- const struct fib6_table *table)
+static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,
+ const struct fib6_info *match,
+ const struct fib6_table *table)
{
int cpu;
- /* Make sure rt6_make_pcpu_route() wont add other percpu routes
- * while we are cleaning them here.
- */
- f6i->fib6_destroying = 1;
- mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
+ if (!fib6_nh->rt6i_pcpu)
+ return;
/* release the reference to this fib entry from
* all of its cached pcpu routes
@@ -913,9 +905,15 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
- ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+ ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
- if (pcpu_rt) {
+
+ /* only dropping the 'from' reference if the cached route
+ * is using 'match'. The cached pcpu_rt->from only changes
+ * from a fib6_info to NULL (ip6_dst_destroy); it can never
+ * change from one fib6_info reference to another
+ */
+ if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) {
struct fib6_info *from;
from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
@@ -924,13 +922,53 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
}
}
+struct fib6_nh_pcpu_arg {
+ struct fib6_info *from;
+ const struct fib6_table *table;
+};
+
+static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_pcpu_arg *arg = _arg;
+
+ __fib6_drop_pcpu_from(nh, arg->from, arg->table);
+ return 0;
+}
+
+static void fib6_drop_pcpu_from(struct fib6_info *f6i,
+ const struct fib6_table *table)
+{
+ /* Make sure rt6_make_pcpu_route() wont add other percpu routes
+ * while we are cleaning them here.
+ */
+ f6i->fib6_destroying = 1;
+ mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
+
+ if (f6i->nh) {
+ struct fib6_nh_pcpu_arg arg = {
+ .from = f6i,
+ .table = table
+ };
+
+ nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from,
+ &arg);
+ } else {
+ struct fib6_nh *fib6_nh;
+
+ fib6_nh = f6i->fib6_nh;
+ __fib6_drop_pcpu_from(fib6_nh, f6i, table);
+ }
+}
+
static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
struct net *net)
{
struct fib6_table *table = rt->fib6_table;
- if (rt->rt6i_pcpu)
- fib6_drop_pcpu_from(rt, table);
+ fib6_drop_pcpu_from(rt, table);
+
+ if (rt->nh && !list_empty(&rt->nh_list))
+ list_del_init(&rt->nh_list);
if (refcount_read(&rt->fib6_ref) != 1) {
/* This route is used as dummy address holder in some split
@@ -1101,11 +1139,13 @@ next_iter:
add:
nlflags |= NLM_F_CREATE;
- err = call_fib6_entry_notifiers(info->nl_net,
- FIB_EVENT_ENTRY_ADD,
- rt, extack);
- if (err)
- return err;
+ if (!info->skip_notify_kernel) {
+ err = call_fib6_entry_notifiers(info->nl_net,
+ FIB_EVENT_ENTRY_ADD,
+ rt, extack);
+ if (err)
+ return err;
+ }
rcu_assign_pointer(rt->fib6_next, iter);
fib6_info_hold(rt);
@@ -1130,11 +1170,13 @@ add:
return -ENOENT;
}
- err = call_fib6_entry_notifiers(info->nl_net,
- FIB_EVENT_ENTRY_REPLACE,
- rt, extack);
- if (err)
- return err;
+ if (!info->skip_notify_kernel) {
+ err = call_fib6_entry_notifiers(info->nl_net,
+ FIB_EVENT_ENTRY_REPLACE,
+ rt, extack);
+ if (err)
+ return err;
+ }
fib6_info_hold(rt);
rcu_assign_pointer(rt->fib6_node, fn);
@@ -1218,6 +1260,14 @@ void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt)
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(net));
}
+/* allow ipv4 to update sernum via ipv6_stub */
+void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i)
+{
+ spin_lock_bh(&f6i->fib6_table->tb6_lock);
+ fib6_update_sernum_upto_root(net, f6i);
+ spin_unlock_bh(&f6i->fib6_table->tb6_lock);
+}
+
/*
* Add routing information to the routing tree.
* <destination addr>/<source addr>
@@ -1331,6 +1381,8 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
err = fib6_add_rt2node(fn, rt, info, extack);
if (!err) {
+ if (rt->nh)
+ list_add(&rt->nh_list, &rt->nh->f6i_list);
__fib6_update_sernum_upto_root(rt, sernum);
fib6_start_gc(info->nl_net, rt);
}
@@ -1807,9 +1859,11 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
fib6_purge_rt(rt, fn, net);
- call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
+ if (!info->skip_notify_kernel)
+ call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
if (!info->skip_notify)
inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
+
fib6_info_release(rt);
}
@@ -2292,9 +2346,13 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
{
struct fib6_info *rt = v;
struct ipv6_route_iter *iter = seq->private;
+ struct fib6_nh *fib6_nh = rt->fib6_nh;
unsigned int flags = rt->fib6_flags;
const struct net_device *dev;
+ if (rt->nh)
+ fib6_nh = nexthop_fib6_nh(rt->nh);
+
seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
#ifdef CONFIG_IPV6_SUBTREES
@@ -2302,14 +2360,14 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
#else
seq_puts(seq, "00000000000000000000000000000000 00 ");
#endif
- if (rt->fib6_nh.fib_nh_gw_family) {
+ if (fib6_nh->fib_nh_gw_family) {
flags |= RTF_GATEWAY;
- seq_printf(seq, "%pi6", &rt->fib6_nh.fib_nh_gw6);
+ seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6);
} else {
seq_puts(seq, "00000000000000000000000000000000");
}
- dev = rt->fib6_nh.fib_nh_dev;
+ dev = fib6_nh->fib_nh_dev;
seq_printf(seq, " %08x %08x %08x %08x %8s\n",
rt->fib6_metric, refcount_read(&rt->fib6_ref), 0,
flags, dev ? dev->name : "");
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 834475717110..5e3a7963b3cb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -124,16 +124,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
return -EINVAL;
}
-static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- int ret;
-
- ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
- if (ret) {
- kfree_skb(skb);
- return ret;
- }
-
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
@@ -150,6 +142,22 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
return ip6_finish_output2(net, sk, skb);
}
+static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+
+ ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+ switch (ret) {
+ case NET_XMIT_SUCCESS:
+ return __ip6_finish_output(net, sk, skb);
+ case NET_XMIT_CN:
+ return __ip6_finish_output(net, sk, skb) ? : ret;
+ default:
+ kfree_skb(skb);
+ return ret;
+ }
+}
+
int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev;
@@ -588,6 +596,169 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
skb_copy_secmark(to, from);
}
+int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr,
+ u8 nexthdr, __be32 frag_id,
+ struct ip6_fraglist_iter *iter)
+{
+ unsigned int first_len;
+ struct frag_hdr *fh;
+
+ /* BUILD HEADER */
+ *prevhdr = NEXTHDR_FRAGMENT;
+ iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
+ if (!iter->tmp_hdr)
+ return -ENOMEM;
+
+ iter->frag = skb_shinfo(skb)->frag_list;
+ skb_frag_list_init(skb);
+
+ iter->offset = 0;
+ iter->hlen = hlen;
+ iter->frag_id = frag_id;
+ iter->nexthdr = nexthdr;
+
+ __skb_pull(skb, hlen);
+ fh = __skb_push(skb, sizeof(struct frag_hdr));
+ __skb_push(skb, hlen);
+ skb_reset_network_header(skb);
+ memcpy(skb_network_header(skb), iter->tmp_hdr, hlen);
+
+ fh->nexthdr = nexthdr;
+ fh->reserved = 0;
+ fh->frag_off = htons(IP6_MF);
+ fh->identification = frag_id;
+
+ first_len = skb_pagelen(skb);
+ skb->data_len = first_len - skb_headlen(skb);
+ skb->len = first_len;
+ ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr));
+
+ return 0;
+}
+EXPORT_SYMBOL(ip6_fraglist_init);
+
+void ip6_fraglist_prepare(struct sk_buff *skb,
+ struct ip6_fraglist_iter *iter)
+{
+ struct sk_buff *frag = iter->frag;
+ unsigned int hlen = iter->hlen;
+ struct frag_hdr *fh;
+
+ frag->ip_summed = CHECKSUM_NONE;
+ skb_reset_transport_header(frag);
+ fh = __skb_push(frag, sizeof(struct frag_hdr));
+ __skb_push(frag, hlen);
+ skb_reset_network_header(frag);
+ memcpy(skb_network_header(frag), iter->tmp_hdr, hlen);
+ iter->offset += skb->len - hlen - sizeof(struct frag_hdr);
+ fh->nexthdr = iter->nexthdr;
+ fh->reserved = 0;
+ fh->frag_off = htons(iter->offset);
+ if (frag->next)
+ fh->frag_off |= htons(IP6_MF);
+ fh->identification = iter->frag_id;
+ ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr));
+ ip6_copy_metadata(frag, skb);
+}
+EXPORT_SYMBOL(ip6_fraglist_prepare);
+
+void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu,
+ unsigned short needed_tailroom, int hdr_room, u8 *prevhdr,
+ u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state)
+{
+ state->prevhdr = prevhdr;
+ state->nexthdr = nexthdr;
+ state->frag_id = frag_id;
+
+ state->hlen = hlen;
+ state->mtu = mtu;
+
+ state->left = skb->len - hlen; /* Space per frame */
+ state->ptr = hlen; /* Where to start from */
+
+ state->hroom = hdr_room;
+ state->troom = needed_tailroom;
+
+ state->offset = 0;
+}
+EXPORT_SYMBOL(ip6_frag_init);
+
+struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state)
+{
+ u8 *prevhdr = state->prevhdr, *fragnexthdr_offset;
+ struct sk_buff *frag;
+ struct frag_hdr *fh;
+ unsigned int len;
+
+ len = state->left;
+ /* IF: it doesn't fit, use 'mtu' - the data space left */
+ if (len > state->mtu)
+ len = state->mtu;
+ /* IF: we are not sending up to and including the packet end
+ then align the next start on an eight byte boundary */
+ if (len < state->left)
+ len &= ~7;
+
+ /* Allocate buffer */
+ frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) +
+ state->hroom + state->troom, GFP_ATOMIC);
+ if (!frag)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * Set up data on packet
+ */
+
+ ip6_copy_metadata(frag, skb);
+ skb_reserve(frag, state->hroom);
+ skb_put(frag, len + state->hlen + sizeof(struct frag_hdr));
+ skb_reset_network_header(frag);
+ fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen);
+ frag->transport_header = (frag->network_header + state->hlen +
+ sizeof(struct frag_hdr));
+
+ /*
+ * Charge the memory for the fragment to any owner
+ * it might possess
+ */
+ if (skb->sk)
+ skb_set_owner_w(frag, skb->sk);
+
+ /*
+ * Copy the packet header into the new buffer.
+ */
+ skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen);
+
+ fragnexthdr_offset = skb_network_header(frag);
+ fragnexthdr_offset += prevhdr - skb_network_header(skb);
+ *fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
+ /*
+ * Build fragment header.
+ */
+ fh->nexthdr = state->nexthdr;
+ fh->reserved = 0;
+ fh->identification = state->frag_id;
+
+ /*
+ * Copy a block of the IP datagram.
+ */
+ BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag),
+ len));
+ state->left -= len;
+
+ fh->frag_off = htons(state->offset);
+ if (state->left > 0)
+ fh->frag_off |= htons(IP6_MF);
+ ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr));
+
+ state->ptr += len;
+ state->offset += len;
+
+ return frag;
+}
+EXPORT_SYMBOL(ip6_frag_next);
+
int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *))
{
@@ -595,12 +766,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
inet6_sk(skb->sk) : NULL;
- struct ipv6hdr *tmp_hdr;
- struct frag_hdr *fh;
- unsigned int mtu, hlen, left, len, nexthdr_offset;
- int hroom, troom;
+ struct ip6_frag_state state;
+ unsigned int mtu, hlen, nexthdr_offset;
+ int hroom, err = 0;
__be32 frag_id;
- int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
err = ip6_find_1stfragopt(skb, &prevhdr);
@@ -647,6 +816,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
hroom = LL_RESERVED_SPACE(rt->dst.dev);
if (skb_has_frag_list(skb)) {
unsigned int first_len = skb_pagelen(skb);
+ struct ip6_fraglist_iter iter;
struct sk_buff *frag2;
if (first_len - hlen > mtu ||
@@ -674,74 +844,29 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
skb->truesize -= frag->truesize;
}
- err = 0;
- offset = 0;
- /* BUILD HEADER */
-
- *prevhdr = NEXTHDR_FRAGMENT;
- tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
- if (!tmp_hdr) {
- err = -ENOMEM;
+ err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id,
+ &iter);
+ if (err < 0)
goto fail;
- }
- frag = skb_shinfo(skb)->frag_list;
- skb_frag_list_init(skb);
-
- __skb_pull(skb, hlen);
- fh = __skb_push(skb, sizeof(struct frag_hdr));
- __skb_push(skb, hlen);
- skb_reset_network_header(skb);
- memcpy(skb_network_header(skb), tmp_hdr, hlen);
-
- fh->nexthdr = nexthdr;
- fh->reserved = 0;
- fh->frag_off = htons(IP6_MF);
- fh->identification = frag_id;
-
- first_len = skb_pagelen(skb);
- skb->data_len = first_len - skb_headlen(skb);
- skb->len = first_len;
- ipv6_hdr(skb)->payload_len = htons(first_len -
- sizeof(struct ipv6hdr));
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
- if (frag) {
- frag->ip_summed = CHECKSUM_NONE;
- skb_reset_transport_header(frag);
- fh = __skb_push(frag, sizeof(struct frag_hdr));
- __skb_push(frag, hlen);
- skb_reset_network_header(frag);
- memcpy(skb_network_header(frag), tmp_hdr,
- hlen);
- offset += skb->len - hlen - sizeof(struct frag_hdr);
- fh->nexthdr = nexthdr;
- fh->reserved = 0;
- fh->frag_off = htons(offset);
- if (frag->next)
- fh->frag_off |= htons(IP6_MF);
- fh->identification = frag_id;
- ipv6_hdr(frag)->payload_len =
- htons(frag->len -
- sizeof(struct ipv6hdr));
- ip6_copy_metadata(frag, skb);
- }
+ if (iter.frag)
+ ip6_fraglist_prepare(skb, &iter);
err = output(net, sk, skb);
if (!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
- if (err || !frag)
+ if (err || !iter.frag)
break;
- skb = frag;
- frag = skb->next;
- skb_mark_not_on_list(skb);
+ skb = ip6_fraglist_next(&iter);
}
- kfree(tmp_hdr);
+ kfree(iter.tmp_hdr);
if (err == 0) {
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -749,7 +874,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
return 0;
}
- kfree_skb_list(frag);
+ kfree_skb_list(iter.frag);
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGFAILS);
@@ -766,91 +891,26 @@ slow_path_clean:
}
slow_path:
- left = skb->len - hlen; /* Space per frame */
- ptr = hlen; /* Where to start from */
-
/*
* Fragment the datagram.
*/
- troom = rt->dst.dev->needed_tailroom;
+ ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom,
+ LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id,
+ &state);
/*
* Keep copying data until we run out.
*/
- while (left > 0) {
- u8 *fragnexthdr_offset;
-
- len = left;
- /* IF: it doesn't fit, use 'mtu' - the data space left */
- if (len > mtu)
- len = mtu;
- /* IF: we are not sending up to and including the packet end
- then align the next start on an eight byte boundary */
- if (len < left) {
- len &= ~7;
- }
- /* Allocate buffer */
- frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
- hroom + troom, GFP_ATOMIC);
- if (!frag) {
- err = -ENOMEM;
+ while (state.left > 0) {
+ frag = ip6_frag_next(skb, &state);
+ if (IS_ERR(frag)) {
+ err = PTR_ERR(frag);
goto fail;
}
/*
- * Set up data on packet
- */
-
- ip6_copy_metadata(frag, skb);
- skb_reserve(frag, hroom);
- skb_put(frag, len + hlen + sizeof(struct frag_hdr));
- skb_reset_network_header(frag);
- fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
- frag->transport_header = (frag->network_header + hlen +
- sizeof(struct frag_hdr));
-
- /*
- * Charge the memory for the fragment to any owner
- * it might possess
- */
- if (skb->sk)
- skb_set_owner_w(frag, skb->sk);
-
- /*
- * Copy the packet header into the new buffer.
- */
- skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
-
- fragnexthdr_offset = skb_network_header(frag);
- fragnexthdr_offset += prevhdr - skb_network_header(skb);
- *fragnexthdr_offset = NEXTHDR_FRAGMENT;
-
- /*
- * Build fragment header.
- */
- fh->nexthdr = nexthdr;
- fh->reserved = 0;
- fh->identification = frag_id;
-
- /*
- * Copy a block of the IP datagram.
- */
- BUG_ON(skb_copy_bits(skb, ptr, skb_transport_header(frag),
- len));
- left -= len;
-
- fh->frag_off = htons(offset);
- if (left > 0)
- fh->frag_off |= htons(IP6_MF);
- ipv6_hdr(frag)->payload_len = htons(frag->len -
- sizeof(struct ipv6hdr));
-
- ptr += len;
- offset += len;
-
- /*
* Put this fragment into the sending queue.
*/
err = output(net, sk, frag);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 09dd2edfb868..083cc1c94cd3 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1285,12 +1285,11 @@ static void ndisc_router_discovery(struct sk_buff *skb)
!in6_dev->cnf.accept_ra_rtr_pref)
pref = ICMPV6_ROUTER_PREF_MEDIUM;
#endif
-
+ /* routes added from RAs do not use nexthop objects */
rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
-
if (rt) {
- neigh = ip6_neigh_lookup(&rt->fib6_nh.fib_nh_gw6,
- rt->fib6_nh.fib_nh_dev, NULL,
+ neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
+ rt->fib6_nh->fib_nh_dev, NULL,
&ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
@@ -1319,8 +1318,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
return;
}
- neigh = ip6_neigh_lookup(&rt->fib6_nh.fib_nh_gw6,
- rt->fib6_nh.fib_nh_dev, NULL,
+ neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
+ rt->fib6_nh->fib_nh_dev, NULL,
&ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 1240ccd57f39..d9673e10c60c 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -16,6 +16,9 @@
#include <net/ip6_route.h>
#include <net/xfrm.h>
#include <net/netfilter/nf_queue.h>
+#include <net/netfilter/nf_conntrack_bridge.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include "../bridge/br_private.h"
int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
{
@@ -109,6 +112,122 @@ int __nf_ip6_route(struct net *net, struct dst_entry **dst,
}
EXPORT_SYMBOL_GPL(__nf_ip6_route);
+int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ struct nf_ct_bridge_frag_data *data,
+ int (*output)(struct net *, struct sock *sk,
+ const struct nf_ct_bridge_frag_data *data,
+ struct sk_buff *))
+{
+ int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
+ struct ip6_frag_state state;
+ u8 *prevhdr, nexthdr = 0;
+ unsigned int mtu, hlen;
+ int hroom, err = 0;
+ __be32 frag_id;
+
+ err = ip6_find_1stfragopt(skb, &prevhdr);
+ if (err < 0)
+ goto blackhole;
+ hlen = err;
+ nexthdr = *prevhdr;
+
+ mtu = skb->dev->mtu;
+ if (frag_max_size > mtu ||
+ frag_max_size < IPV6_MIN_MTU)
+ goto blackhole;
+
+ mtu = frag_max_size;
+ if (mtu < hlen + sizeof(struct frag_hdr) + 8)
+ goto blackhole;
+ mtu -= hlen + sizeof(struct frag_hdr);
+
+ frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
+ &ipv6_hdr(skb)->saddr);
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (err = skb_checksum_help(skb)))
+ goto blackhole;
+
+ hroom = LL_RESERVED_SPACE(skb->dev);
+ if (skb_has_frag_list(skb)) {
+ unsigned int first_len = skb_pagelen(skb);
+ struct ip6_fraglist_iter iter;
+ struct sk_buff *frag2;
+
+ if (first_len - hlen > mtu ||
+ skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+ goto blackhole;
+
+ if (skb_cloned(skb))
+ goto slow_path;
+
+ skb_walk_frags(skb, frag2) {
+ if (frag2->len > mtu ||
+ skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+ goto blackhole;
+
+ /* Partially cloned skb? */
+ if (skb_shared(frag2))
+ goto slow_path;
+ }
+
+ err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id,
+ &iter);
+ if (err < 0)
+ goto blackhole;
+
+ for (;;) {
+ /* Prepare header of the next frame,
+ * before previous one went down.
+ */
+ if (iter.frag)
+ ip6_fraglist_prepare(skb, &iter);
+
+ err = output(net, sk, data, skb);
+ if (err || !iter.frag)
+ break;
+
+ skb = ip6_fraglist_next(&iter);
+ }
+
+ kfree(iter.tmp_hdr);
+ if (!err)
+ return 0;
+
+ kfree_skb_list(iter.frag);
+ return err;
+ }
+slow_path:
+ /* This is a linearized skbuff, the original geometry is lost for us.
+ * This may also be a clone skbuff, we could preserve the geometry for
+ * the copies but probably not worth the effort.
+ */
+ ip6_frag_init(skb, hlen, mtu, skb->dev->needed_tailroom,
+ LL_RESERVED_SPACE(skb->dev), prevhdr, nexthdr, frag_id,
+ &state);
+
+ while (state.left > 0) {
+ struct sk_buff *skb2;
+
+ skb2 = ip6_frag_next(skb, &state);
+ if (IS_ERR(skb2)) {
+ err = PTR_ERR(skb2);
+ goto blackhole;
+ }
+
+ err = output(net, sk, data, skb2);
+ if (err)
+ goto blackhole;
+ }
+ consume_skb(skb);
+ return err;
+
+blackhole:
+ kfree_skb(skb);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(br_ip6_fragment);
+
static const struct nf_ipv6_ops ipv6ops = {
#if IS_MODULE(CONFIG_IPV6)
.chk_addr = ipv6_chk_addr,
@@ -119,6 +238,10 @@ static const struct nf_ipv6_ops ipv6ops = {
.route_input = ip6_route_input,
.fragment = ip6_fragment,
.reroute = nf_ip6_reroute,
+#if IS_MODULE(CONFIG_IPV6)
+ .br_defrag = nf_ct_frag6_gather,
+ .br_fragment = br_ip6_fragment,
+#endif
};
int __init ipv6_netfilter_init(void)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 84322ce81d70..398e1df41406 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -54,26 +54,21 @@ static struct inet_frags nf_frags;
static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
.procname = "nf_conntrack_frag6_timeout",
- .data = &init_net.nf_frag.frags.timeout,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "nf_conntrack_frag6_low_thresh",
- .data = &init_net.nf_frag.frags.low_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra2 = &init_net.nf_frag.frags.high_thresh
},
{
.procname = "nf_conntrack_frag6_high_thresh",
- .data = &init_net.nf_frag.frags.high_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &init_net.nf_frag.frags.low_thresh
},
{ }
};
@@ -89,15 +84,15 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
GFP_KERNEL);
if (table == NULL)
goto err_alloc;
-
- table[0].data = &net->nf_frag.frags.timeout;
- table[1].data = &net->nf_frag.frags.low_thresh;
- table[1].extra2 = &net->nf_frag.frags.high_thresh;
- table[2].data = &net->nf_frag.frags.high_thresh;
- table[2].extra1 = &net->nf_frag.frags.low_thresh;
- table[2].extra2 = &init_net.nf_frag.frags.high_thresh;
}
+ table[0].data = &net->nf_frag.fqdir->timeout;
+ table[1].data = &net->nf_frag.fqdir->low_thresh;
+ table[1].extra2 = &net->nf_frag.fqdir->high_thresh;
+ table[2].data = &net->nf_frag.fqdir->high_thresh;
+ table[2].extra1 = &net->nf_frag.fqdir->low_thresh;
+ table[2].extra2 = &init_net.nf_frag.fqdir->high_thresh;
+
hdr = register_net_sysctl(net, "net/netfilter", table);
if (hdr == NULL)
goto err_reg;
@@ -144,12 +139,10 @@ static void nf_ct_frag6_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
- struct net *net;
fq = container_of(frag, struct frag_queue, q);
- net = container_of(fq->q.net, struct net, nf_frag.frags);
- ip6frag_expire_frag_queue(net, fq);
+ ip6frag_expire_frag_queue(fq->q.fqdir->net, fq);
}
/* Creation primitives. */
@@ -165,7 +158,7 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
};
struct inet_frag_queue *q;
- q = inet_frag_find(&net->nf_frag.frags, &key);
+ q = inet_frag_find(net->nf_frag.fqdir, &key);
if (!q)
return NULL;
@@ -278,7 +271,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
fq->ecn |= ecn;
if (payload_len > fq->q.max_size)
fq->q.max_size = payload_len;
- add_frag_mem_limit(fq->q.net, skb->truesize);
+ add_frag_mem_limit(fq->q.fqdir, skb->truesize);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
@@ -494,29 +487,35 @@ static int nf_ct_net_init(struct net *net)
{
int res;
- net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
- net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
- net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
- net->nf_frag.frags.f = &nf_frags;
-
- res = inet_frags_init_net(&net->nf_frag.frags);
+ res = fqdir_init(&net->nf_frag.fqdir, &nf_frags, net);
if (res < 0)
return res;
+
+ net->nf_frag.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH;
+ net->nf_frag.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH;
+ net->nf_frag.fqdir->timeout = IPV6_FRAG_TIMEOUT;
+
res = nf_ct_frag6_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->nf_frag.frags);
+ fqdir_exit(net->nf_frag.fqdir);
return res;
}
+static void nf_ct_net_pre_exit(struct net *net)
+{
+ fqdir_pre_exit(net->nf_frag.fqdir);
+}
+
static void nf_ct_net_exit(struct net *net)
{
nf_ct_frags6_sysctl_unregister(net);
- inet_frags_exit_net(&net->nf_frag.frags);
+ fqdir_exit(net->nf_frag.fqdir);
}
static struct pernet_operations nf_ct_net_ops = {
- .init = nf_ct_net_init,
- .exit = nf_ct_net_exit,
+ .init = nf_ct_net_init,
+ .pre_exit = nf_ct_net_pre_exit,
+ .exit = nf_ct_net_exit,
};
static const struct rhashtable_params nfct_rhash_params = {
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 4a8da679866e..bbff3e02e302 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -44,8 +44,8 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
- atomic_read(&net->ipv6.frags.rhashtable.nelems),
- frag_mem_limit(&net->ipv6.frags));
+ atomic_read(&net->ipv6.fqdir->rhashtable.nelems),
+ frag_mem_limit(net->ipv6.fqdir));
return 0;
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index b2b2c0c38b87..ca05b16f1bb9 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -72,12 +72,10 @@ static void ip6_frag_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
- struct net *net;
fq = container_of(frag, struct frag_queue, q);
- net = container_of(fq->q.net, struct net, ipv6.frags);
- ip6frag_expire_frag_queue(net, fq);
+ ip6frag_expire_frag_queue(fq->q.fqdir->net, fq);
}
static struct frag_queue *
@@ -96,7 +94,7 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
IPV6_ADDR_LINKLOCAL)))
key.iif = 0;
- q = inet_frag_find(&net->ipv6.frags, &key);
+ q = inet_frag_find(net->ipv6.fqdir, &key);
if (!q)
return NULL;
@@ -196,7 +194,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
- add_frag_mem_limit(fq->q.net, skb->truesize);
+ add_frag_mem_limit(fq->q.fqdir, skb->truesize);
fragsize = -skb_network_offset(skb) + skb->len;
if (fragsize > fq->q.max_size)
@@ -250,7 +248,7 @@ err:
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
struct sk_buff *prev_tail, struct net_device *dev)
{
- struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
+ struct net *net = fq->q.fqdir->net;
unsigned int nhoff;
void *reasm_data;
int payload_len;
@@ -397,23 +395,18 @@ static const struct inet6_protocol frag_protocol = {
static struct ctl_table ip6_frags_ns_ctl_table[] = {
{
.procname = "ip6frag_high_thresh",
- .data = &init_net.ipv6.frags.high_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &init_net.ipv6.frags.low_thresh
},
{
.procname = "ip6frag_low_thresh",
- .data = &init_net.ipv6.frags.low_thresh,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra2 = &init_net.ipv6.frags.high_thresh
},
{
.procname = "ip6frag_time",
- .data = &init_net.ipv6.frags.timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -445,12 +438,12 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
if (!table)
goto err_alloc;
- table[0].data = &net->ipv6.frags.high_thresh;
- table[0].extra1 = &net->ipv6.frags.low_thresh;
- table[1].data = &net->ipv6.frags.low_thresh;
- table[1].extra2 = &net->ipv6.frags.high_thresh;
- table[2].data = &net->ipv6.frags.timeout;
}
+ table[0].data = &net->ipv6.fqdir->high_thresh;
+ table[0].extra1 = &net->ipv6.fqdir->low_thresh;
+ table[1].data = &net->ipv6.fqdir->low_thresh;
+ table[1].extra2 = &net->ipv6.fqdir->high_thresh;
+ table[2].data = &net->ipv6.fqdir->timeout;
hdr = register_net_sysctl(net, "net/ipv6", table);
if (!hdr)
@@ -513,30 +506,35 @@ static int __net_init ipv6_frags_init_net(struct net *net)
{
int res;
- net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
- net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
- net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
- net->ipv6.frags.f = &ip6_frags;
-
- res = inet_frags_init_net(&net->ipv6.frags);
+ res = fqdir_init(&net->ipv6.fqdir, &ip6_frags, net);
if (res < 0)
return res;
+ net->ipv6.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH;
+ net->ipv6.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH;
+ net->ipv6.fqdir->timeout = IPV6_FRAG_TIMEOUT;
+
res = ip6_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv6.frags);
+ fqdir_exit(net->ipv6.fqdir);
return res;
}
+static void __net_exit ipv6_frags_pre_exit_net(struct net *net)
+{
+ fqdir_pre_exit(net->ipv6.fqdir);
+}
+
static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&net->ipv6.frags);
+ fqdir_exit(net->ipv6.fqdir);
}
static struct pernet_operations ip6_frags_ops = {
- .init = ipv6_frags_init_net,
- .exit = ipv6_frags_exit_net,
+ .init = ipv6_frags_init_net,
+ .pre_exit = ipv6_frags_pre_exit_net,
+ .exit = ipv6_frags_exit_net,
};
static const struct rhashtable_params ip6_rhash_params = {
@@ -587,8 +585,8 @@ err_protocol:
void ipv6_frag_exit(void)
{
- inet_frags_fini(&ip6_frags);
ip6_frags_sysctl_unregister();
unregister_pernet_subsys(&ip6_frags_ops);
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+ inet_frags_fini(&ip6_frags);
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 11ad62effd56..d72bcd8cffbd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -100,7 +100,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
int strict);
-static size_t rt6_nlmsg_size(struct fib6_info *rt);
+static size_t rt6_nlmsg_size(struct fib6_info *f6i);
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
@@ -428,21 +428,27 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
struct fib6_info *sibling, *next_sibling;
struct fib6_info *match = res->f6i;
- if (!match->fib6_nsiblings || have_oif_match)
+ if ((!match->fib6_nsiblings && !match->nh) || have_oif_match)
goto out;
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
*/
- if (!fl6->mp_hash)
+ if (!fl6->mp_hash &&
+ (!match->nh || nexthop_is_multipath(match->nh)))
fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
- if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
+ if (unlikely(match->nh)) {
+ nexthop_path_fib6_result(res, fl6->mp_hash);
+ return;
+ }
+
+ 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) {
- const struct fib6_nh *nh = &sibling->fib6_nh;
+ const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
@@ -456,7 +462,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
out:
res->f6i = match;
- res->nh = &match->fib6_nh;
+ res->nh = match->fib6_nh;
}
/*
@@ -484,6 +490,45 @@ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh,
return false;
}
+struct fib6_nh_dm_arg {
+ struct net *net;
+ const struct in6_addr *saddr;
+ int oif;
+ int flags;
+ struct fib6_nh *nh;
+};
+
+static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_dm_arg *arg = _arg;
+
+ arg->nh = nh;
+ return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif,
+ arg->flags);
+}
+
+/* returns fib6_nh from nexthop or NULL */
+static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh,
+ struct fib6_result *res,
+ const struct in6_addr *saddr,
+ int oif, int flags)
+{
+ struct fib6_nh_dm_arg arg = {
+ .net = net,
+ .saddr = saddr,
+ .oif = oif,
+ .flags = flags,
+ };
+
+ if (nexthop_is_blackhole(nh))
+ return NULL;
+
+ if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg))
+ return arg.nh;
+
+ return NULL;
+}
+
static void rt6_device_match(struct net *net, struct fib6_result *res,
const struct in6_addr *saddr, int oif, int flags)
{
@@ -492,14 +537,31 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
struct fib6_nh *nh;
if (!oif && ipv6_addr_any(saddr)) {
- nh = &f6i->fib6_nh;
+ if (unlikely(f6i->nh)) {
+ nh = nexthop_fib6_nh(f6i->nh);
+ if (nexthop_is_blackhole(f6i->nh))
+ goto out_blackhole;
+ } else {
+ nh = f6i->fib6_nh;
+ }
if (!(nh->fib_nh_flags & RTNH_F_DEAD))
goto out;
}
for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
- nh = &spf6i->fib6_nh;
- if (__rt6_device_match(net, nh, saddr, oif, flags)) {
+ bool matched = false;
+
+ if (unlikely(spf6i->nh)) {
+ nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr,
+ oif, flags);
+ if (nh)
+ matched = true;
+ } else {
+ nh = spf6i->fib6_nh;
+ if (__rt6_device_match(net, nh, saddr, oif, flags))
+ matched = true;
+ }
+ if (matched) {
res->f6i = spf6i;
goto out;
}
@@ -507,19 +569,32 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
if (oif && flags & RT6_LOOKUP_F_IFACE) {
res->f6i = net->ipv6.fib6_null_entry;
- nh = &res->f6i->fib6_nh;
+ nh = res->f6i->fib6_nh;
goto out;
}
- nh = &f6i->fib6_nh;
+ if (unlikely(f6i->nh)) {
+ nh = nexthop_fib6_nh(f6i->nh);
+ if (nexthop_is_blackhole(f6i->nh))
+ goto out_blackhole;
+ } else {
+ nh = f6i->fib6_nh;
+ }
+
if (nh->fib_nh_flags & RTNH_F_DEAD) {
res->f6i = net->ipv6.fib6_null_entry;
- nh = &res->f6i->fib6_nh;
+ nh = res->f6i->fib6_nh;
}
out:
res->nh = nh;
res->fib6_type = res->f6i->fib6_type;
res->fib6_flags = res->f6i->fib6_flags;
+ return;
+
+out_blackhole:
+ res->fib6_flags |= RTF_REJECT;
+ res->fib6_type = RTN_BLACKHOLE;
+ res->nh = nh;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
@@ -690,6 +765,24 @@ out:
return rc;
}
+struct fib6_nh_frl_arg {
+ u32 flags;
+ int oif;
+ int strict;
+ int *mpri;
+ bool *do_rr;
+ struct fib6_nh *nh;
+};
+
+static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_frl_arg *arg = _arg;
+
+ arg->nh = nh;
+ return find_match(nh, arg->flags, arg->oif, arg->strict,
+ arg->mpri, arg->do_rr);
+}
+
static void __find_rr_leaf(struct fib6_info *f6i_start,
struct fib6_info *nomatch, u32 metric,
struct fib6_result *res, struct fib6_info **cont,
@@ -700,6 +793,7 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
for (f6i = f6i_start;
f6i && f6i != nomatch;
f6i = rcu_dereference(f6i->fib6_next)) {
+ bool matched = false;
struct fib6_nh *nh;
if (cont && f6i->fib6_metric != metric) {
@@ -710,8 +804,34 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
if (fib6_check_expired(f6i))
continue;
- nh = &f6i->fib6_nh;
- if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) {
+ if (unlikely(f6i->nh)) {
+ struct fib6_nh_frl_arg arg = {
+ .flags = f6i->fib6_flags,
+ .oif = oif,
+ .strict = strict,
+ .mpri = mpri,
+ .do_rr = do_rr
+ };
+
+ if (nexthop_is_blackhole(f6i->nh)) {
+ res->fib6_flags = RTF_REJECT;
+ res->fib6_type = RTN_BLACKHOLE;
+ res->f6i = f6i;
+ res->nh = nexthop_fib6_nh(f6i->nh);
+ return;
+ }
+ if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match,
+ &arg)) {
+ matched = true;
+ nh = arg.nh;
+ }
+ } else {
+ nh = f6i->fib6_nh;
+ if (find_match(nh, f6i->fib6_flags, oif, strict,
+ mpri, do_rr))
+ matched = true;
+ }
+ if (matched) {
res->f6i = f6i;
res->nh = nh;
res->fib6_flags = f6i->fib6_flags;
@@ -792,7 +912,7 @@ static void rt6_select(struct net *net, struct fib6_node *fn, int oif,
out:
if (!res->f6i) {
res->f6i = net->ipv6.fib6_null_entry;
- res->nh = &res->f6i->fib6_nh;
+ res->nh = res->f6i->fib6_nh;
res->fib6_flags = res->f6i->fib6_flags;
res->fib6_type = res->f6i->fib6_type;
}
@@ -1113,6 +1233,8 @@ restart:
rt = net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
goto out;
+ } else if (res.fib6_flags & RTF_REJECT) {
+ goto do_create;
}
fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
@@ -1124,6 +1246,7 @@ restart:
if (ip6_hold_safe(net, &rt))
dst_use_noref(&rt->dst, jiffies);
} else {
+do_create:
rt = ip6_create_rt_rcu(&res);
}
@@ -1264,10 +1387,9 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
/* It should be called with rcu_read_lock() acquired */
static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
{
- struct rt6_info *pcpu_rt, **p;
+ struct rt6_info *pcpu_rt;
- p = this_cpu_ptr(res->f6i->rt6i_pcpu);
- pcpu_rt = *p;
+ pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
if (pcpu_rt)
ip6_hold_safe(NULL, &pcpu_rt);
@@ -1287,7 +1409,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
}
dst_hold(&pcpu_rt->dst);
- p = this_cpu_ptr(res->f6i->rt6i_pcpu);
+ p = this_cpu_ptr(res->nh->rt6i_pcpu);
prev = cmpxchg(p, NULL, pcpu_rt);
BUG_ON(prev);
@@ -1457,25 +1579,74 @@ static unsigned int fib6_mtu(const struct fib6_result *res)
return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
}
+#define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL
+
+/* used when the flushed bit is not relevant, only access to the bucket
+ * (ie., all bucket users except rt6_insert_exception);
+ *
+ * called under rcu lock; sometimes called with rt6_exception_lock held
+ */
+static
+struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh,
+ spinlock_t *lock)
+{
+ struct rt6_exception_bucket *bucket;
+
+ if (lock)
+ bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
+ lockdep_is_held(lock));
+ else
+ bucket = rcu_dereference(nh->rt6i_exception_bucket);
+
+ /* remove bucket flushed bit if set */
+ if (bucket) {
+ unsigned long p = (unsigned long)bucket;
+
+ p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED;
+ bucket = (struct rt6_exception_bucket *)p;
+ }
+
+ return bucket;
+}
+
+static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket)
+{
+ unsigned long p = (unsigned long)bucket;
+
+ return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED);
+}
+
+/* called with rt6_exception_lock held */
+static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh,
+ spinlock_t *lock)
+{
+ struct rt6_exception_bucket *bucket;
+ unsigned long p;
+
+ bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
+ lockdep_is_held(lock));
+
+ p = (unsigned long)bucket;
+ p |= FIB6_EXCEPTION_BUCKET_FLUSHED;
+ bucket = (struct rt6_exception_bucket *)p;
+ rcu_assign_pointer(nh->rt6i_exception_bucket, bucket);
+}
+
static int rt6_insert_exception(struct rt6_info *nrt,
const struct fib6_result *res)
{
struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
+ struct fib6_info *f6i = res->f6i;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
- struct fib6_info *f6i = res->f6i;
+ struct fib6_nh *nh = res->nh;
int err = 0;
spin_lock_bh(&rt6_exception_lock);
- if (f6i->exception_bucket_flushed) {
- err = -EINVAL;
- goto out;
- }
-
- bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
+ bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
+ lockdep_is_held(&rt6_exception_lock));
if (!bucket) {
bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
GFP_ATOMIC);
@@ -1483,7 +1654,10 @@ static int rt6_insert_exception(struct rt6_info *nrt,
err = -ENOMEM;
goto out;
}
- rcu_assign_pointer(f6i->rt6i_exception_bucket, bucket);
+ rcu_assign_pointer(nh->rt6i_exception_bucket, bucket);
+ } else if (fib6_nh_excptn_bucket_flushed(bucket)) {
+ err = -EINVAL;
+ goto out;
}
#ifdef CONFIG_IPV6_SUBTREES
@@ -1538,7 +1712,7 @@ out:
return err;
}
-void rt6_flush_exceptions(struct fib6_info *rt)
+static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1546,25 +1720,46 @@ void rt6_flush_exceptions(struct fib6_info *rt)
int i;
spin_lock_bh(&rt6_exception_lock);
- /* Prevent rt6_insert_exception() to recreate the bucket list */
- rt->exception_bucket_flushed = 1;
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
+ bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (!bucket)
goto out;
+ /* Prevent rt6_insert_exception() to recreate the bucket list */
+ if (!from)
+ fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock);
+
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
- hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist)
- rt6_remove_exception(bucket, rt6_ex);
- WARN_ON_ONCE(bucket->depth);
+ hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) {
+ if (!from ||
+ rcu_access_pointer(rt6_ex->rt6i->from) == from)
+ rt6_remove_exception(bucket, rt6_ex);
+ }
+ WARN_ON_ONCE(!from && bucket->depth);
bucket++;
}
-
out:
spin_unlock_bh(&rt6_exception_lock);
}
+static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
+{
+ struct fib6_info *f6i = arg;
+
+ fib6_nh_flush_exceptions(nh, f6i);
+
+ return 0;
+}
+
+void rt6_flush_exceptions(struct fib6_info *f6i)
+{
+ if (f6i->nh)
+ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
+ f6i);
+ else
+ fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
+}
+
/* Find cached rt in the hash table inside passed in rt
* Caller has to hold rcu_read_lock()
*/
@@ -1593,7 +1788,7 @@ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
src_key = saddr;
find_ex:
#endif
- bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
+ bucket = fib6_nh_get_excptn_bucket(res->nh, NULL);
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
@@ -1611,25 +1806,20 @@ find_ex:
}
/* Remove the passed in cached rt from the hash table that contains it */
-static int rt6_remove_exception_rt(struct rt6_info *rt)
+static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen,
+ const struct rt6_info *rt)
{
+ const struct in6_addr *src_key = NULL;
struct rt6_exception_bucket *bucket;
- struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
- struct fib6_info *from;
int err;
- from = rcu_dereference(rt->from);
- if (!from ||
- !(rt->rt6i_flags & RTF_CACHE))
- return -EINVAL;
-
- if (!rcu_access_pointer(from->rt6i_exception_bucket))
+ if (!rcu_access_pointer(nh->rt6i_exception_bucket))
return -ENOENT;
spin_lock_bh(&rt6_exception_lock);
- bucket = rcu_dereference_protected(from->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
+ bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
+
#ifdef CONFIG_IPV6_SUBTREES
/* rt6i_src.plen != 0 indicates 'from' is in subtree
* and exception table is indexed by a hash of
@@ -1637,7 +1827,7 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
- if (from->fib6_src.plen)
+ if (plen)
src_key = &rt->rt6i_src.addr;
#endif
rt6_ex = __rt6_find_exception_spinlock(&bucket,
@@ -1654,23 +1844,60 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
return err;
}
-/* Find rt6_ex which contains the passed in rt cache and
- * refresh its stamp
- */
-static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+struct fib6_nh_excptn_arg {
+ struct rt6_info *rt;
+ int plen;
+};
+
+static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_excptn_arg *arg = _arg;
+ int err;
+
+ err = fib6_nh_remove_exception(nh, arg->plen, arg->rt);
+ if (err == 0)
+ return 1;
+
+ return 0;
+}
+
+static int rt6_remove_exception_rt(struct rt6_info *rt)
{
- struct rt6_exception_bucket *bucket;
- struct in6_addr *src_key = NULL;
- struct rt6_exception *rt6_ex;
struct fib6_info *from;
- rcu_read_lock();
from = rcu_dereference(rt->from);
if (!from || !(rt->rt6i_flags & RTF_CACHE))
- goto unlock;
+ return -EINVAL;
+
+ if (from->nh) {
+ struct fib6_nh_excptn_arg arg = {
+ .rt = rt,
+ .plen = from->fib6_src.plen
+ };
+ int rc;
- bucket = rcu_dereference(from->rt6i_exception_bucket);
+ /* rc = 1 means an entry was found */
+ rc = nexthop_for_each_fib6_nh(from->nh,
+ rt6_nh_remove_exception_rt,
+ &arg);
+ return rc ? 0 : -ENOENT;
+ }
+
+ return fib6_nh_remove_exception(from->fib6_nh,
+ from->fib6_src.plen, rt);
+}
+/* Find rt6_ex which contains the passed in rt cache and
+ * refresh its stamp
+ */
+static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen,
+ const struct rt6_info *rt)
+{
+ const struct in6_addr *src_key = NULL;
+ struct rt6_exception_bucket *bucket;
+ struct rt6_exception *rt6_ex;
+
+ bucket = fib6_nh_get_excptn_bucket(nh, NULL);
#ifdef CONFIG_IPV6_SUBTREES
/* rt6i_src.plen != 0 indicates 'from' is in subtree
* and exception table is indexed by a hash of
@@ -1678,15 +1905,63 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
- if (from->fib6_src.plen)
+ if (plen)
src_key = &rt->rt6i_src.addr;
#endif
- rt6_ex = __rt6_find_exception_rcu(&bucket,
- &rt->rt6i_dst.addr,
- src_key);
+ rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key);
if (rt6_ex)
rt6_ex->stamp = jiffies;
+}
+
+struct fib6_nh_match_arg {
+ const struct net_device *dev;
+ const struct in6_addr *gw;
+ struct fib6_nh *match;
+};
+
+/* determine if fib6_nh has given device and gateway */
+static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_match_arg *arg = _arg;
+
+ if (arg->dev != nh->fib_nh_dev ||
+ (arg->gw && !nh->fib_nh_gw_family) ||
+ (!arg->gw && nh->fib_nh_gw_family) ||
+ (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6)))
+ return 0;
+
+ arg->match = nh;
+
+ /* found a match, break the loop */
+ return 1;
+}
+
+static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+{
+ struct fib6_info *from;
+ struct fib6_nh *fib6_nh;
+
+ rcu_read_lock();
+
+ from = rcu_dereference(rt->from);
+ if (!from || !(rt->rt6i_flags & RTF_CACHE))
+ goto unlock;
+
+ if (from->nh) {
+ struct fib6_nh_match_arg arg = {
+ .dev = rt->dst.dev,
+ .gw = &rt->rt6i_gateway,
+ };
+
+ nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg);
+ if (!arg.match)
+ return;
+ fib6_nh = arg.match;
+ } else {
+ fib6_nh = from->fib6_nh;
+ }
+ fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt);
unlock:
rcu_read_unlock();
}
@@ -1714,15 +1989,13 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
}
static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
- struct fib6_info *rt, int mtu)
+ const struct fib6_nh *nh, int mtu)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
int i;
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
-
+ bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (!bucket)
return;
@@ -1744,21 +2017,19 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE)
-static void rt6_exceptions_clean_tohost(struct fib6_info *rt,
- struct in6_addr *gateway)
+static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh,
+ const struct in6_addr *gateway)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct hlist_node *tmp;
int i;
- if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+ if (!rcu_access_pointer(nh->rt6i_exception_bucket))
return;
spin_lock_bh(&rt6_exception_lock);
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
-
+ bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (bucket) {
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry_safe(rt6_ex, tmp,
@@ -1823,23 +2094,21 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
gc_args->more++;
}
-void rt6_age_exceptions(struct fib6_info *rt,
- struct fib6_gc_args *gc_args,
- unsigned long now)
+static void fib6_nh_age_exceptions(const struct fib6_nh *nh,
+ struct fib6_gc_args *gc_args,
+ unsigned long now)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
struct hlist_node *tmp;
int i;
- if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+ if (!rcu_access_pointer(nh->rt6i_exception_bucket))
return;
rcu_read_lock_bh();
spin_lock(&rt6_exception_lock);
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
-
+ bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
if (bucket) {
for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
hlist_for_each_entry_safe(rt6_ex, tmp,
@@ -1854,6 +2123,36 @@ void rt6_age_exceptions(struct fib6_info *rt,
rcu_read_unlock_bh();
}
+struct fib6_nh_age_excptn_arg {
+ struct fib6_gc_args *gc_args;
+ unsigned long now;
+};
+
+static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_age_excptn_arg *arg = _arg;
+
+ fib6_nh_age_exceptions(nh, arg->gc_args, arg->now);
+ return 0;
+}
+
+void rt6_age_exceptions(struct fib6_info *f6i,
+ struct fib6_gc_args *gc_args,
+ unsigned long now)
+{
+ if (f6i->nh) {
+ struct fib6_nh_age_excptn_arg arg = {
+ .gc_args = gc_args,
+ .now = now
+ };
+
+ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions,
+ &arg);
+ } else {
+ fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now);
+ }
+}
+
/* must be called with rcu lock held */
int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, struct fib6_result *res, int strict)
@@ -2380,10 +2679,31 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
rcu_read_unlock();
return;
}
- res.nh = &res.f6i->fib6_nh;
res.fib6_flags = res.f6i->fib6_flags;
res.fib6_type = res.f6i->fib6_type;
+ if (res.f6i->nh) {
+ struct fib6_nh_match_arg arg = {
+ .dev = dst->dev,
+ .gw = &rt6->rt6i_gateway,
+ };
+
+ nexthop_for_each_fib6_nh(res.f6i->nh,
+ fib6_nh_find_match, &arg);
+
+ /* fib6_info uses a nexthop that does not have fib6_nh
+ * using the dst->dev + gw. Should be impossible.
+ */
+ if (!arg.match) {
+ rcu_read_unlock();
+ return;
+ }
+
+ res.nh = arg.match;
+ } else {
+ res.nh = res.f6i->fib6_nh;
+ }
+
nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
@@ -2490,6 +2810,21 @@ static bool ip6_redirect_nh_match(const struct fib6_result *res,
return true;
}
+struct fib6_nh_rd_arg {
+ struct fib6_result *res;
+ struct flowi6 *fl6;
+ const struct in6_addr *gw;
+ struct rt6_info **ret;
+};
+
+static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_rd_arg *arg = _arg;
+
+ arg->res->nh = nh;
+ return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret);
+}
+
/* Handle redirects */
struct ip6rd_flowi {
struct flowi6 fl6;
@@ -2505,6 +2840,12 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
struct rt6_info *ret = NULL;
struct fib6_result res = {};
+ struct fib6_nh_rd_arg arg = {
+ .res = &res,
+ .fl6 = fl6,
+ .gw = &rdfl->gateway,
+ .ret = &ret
+ };
struct fib6_info *rt;
struct fib6_node *fn;
@@ -2529,14 +2870,24 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
restart:
for_each_fib6_node_rt_rcu(fn) {
res.f6i = rt;
- res.nh = &rt->fib6_nh;
-
if (fib6_check_expired(rt))
continue;
if (rt->fib6_flags & RTF_REJECT)
break;
- if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret))
- goto out;
+ if (unlikely(rt->nh)) {
+ if (nexthop_is_blackhole(rt->nh))
+ continue;
+ /* on match, res->nh is filled in and potentially ret */
+ if (nexthop_for_each_fib6_nh(rt->nh,
+ fib6_nh_redirect_match,
+ &arg))
+ goto out;
+ } else {
+ res.nh = rt->fib6_nh;
+ if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway,
+ &ret))
+ goto out;
+ }
}
if (!rt)
@@ -2553,7 +2904,7 @@ restart:
}
res.f6i = rt;
- res.nh = &rt->fib6_nh;
+ res.nh = rt->fib6_nh;
out:
if (ret) {
ip6_hold_safe(net, &ret);
@@ -3038,7 +3389,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
goto out;
}
}
- goto set_dev;
+ goto pcpu_alloc;
}
if (cfg->fc_flags & RTF_GATEWAY) {
@@ -3074,7 +3425,14 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
cfg->fc_encap_type, cfg, gfp_flags, extack);
if (err)
goto out;
-set_dev:
+
+pcpu_alloc:
+ fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
+ if (!fib6_nh->rt6i_pcpu) {
+ err = -ENOMEM;
+ goto out;
+ }
+
fib6_nh->fib_nh_dev = dev;
fib6_nh->fib_nh_oif = dev->ifindex;
err = 0;
@@ -3094,6 +3452,38 @@ out:
void fib6_nh_release(struct fib6_nh *fib6_nh)
{
+ struct rt6_exception_bucket *bucket;
+
+ rcu_read_lock();
+
+ fib6_nh_flush_exceptions(fib6_nh, NULL);
+ bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL);
+ if (bucket) {
+ rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL);
+ kfree(bucket);
+ }
+
+ rcu_read_unlock();
+
+ if (fib6_nh->rt6i_pcpu) {
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **ppcpu_rt;
+ struct rt6_info *pcpu_rt;
+
+ ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
+ pcpu_rt = *ppcpu_rt;
+ if (pcpu_rt) {
+ dst_dev_put(&pcpu_rt->dst);
+ dst_release(&pcpu_rt->dst);
+ *ppcpu_rt = NULL;
+ }
+ }
+
+ free_percpu(fib6_nh->rt6i_pcpu);
+ }
+
fib_nh_common_release(&fib6_nh->nh_common);
}
@@ -3103,7 +3493,9 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
{
struct net *net = cfg->fc_nlinfo.nl_net;
struct fib6_info *rt = NULL;
+ struct nexthop *nh = NULL;
struct fib6_table *table;
+ struct fib6_nh *fib6_nh;
int err = -EINVAL;
int addr_type;
@@ -3139,6 +3531,16 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
}
#endif
+ if (cfg->fc_nh_id) {
+ nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+ if (!nh) {
+ NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+ goto out;
+ }
+ err = fib6_check_nexthop(nh, cfg, extack);
+ if (err)
+ goto out;
+ }
err = -ENOBUFS;
if (cfg->fc_nlinfo.nlh &&
@@ -3156,7 +3558,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
err = -ENOMEM;
- rt = fib6_info_alloc(gfp_flags);
+ rt = fib6_info_alloc(gfp_flags, !nh);
if (!rt)
goto out;
@@ -3196,19 +3598,35 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
rt->fib6_src.plen = cfg->fc_src_len;
#endif
- err = fib6_nh_init(net, &rt->fib6_nh, cfg, gfp_flags, extack);
- if (err)
- goto out;
+ if (nh) {
+ if (!nexthop_get(nh)) {
+ NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+ goto out;
+ }
+ if (rt->fib6_src.plen) {
+ NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ goto out;
+ }
+ rt->nh = nh;
+ fib6_nh = nexthop_fib6_nh(rt->nh);
+ } else {
+ err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack);
+ if (err)
+ goto out;
- /* We cannot add true routes via loopback here,
- * they would result in kernel looping; promote them to reject routes
- */
- addr_type = ipv6_addr_type(&cfg->fc_dst);
- if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.fib_nh_dev, addr_type))
- rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
+ fib6_nh = rt->fib6_nh;
+
+ /* We cannot add true routes via loopback here, they would
+ * result in kernel looping; promote them to reject routes
+ */
+ addr_type = ipv6_addr_type(&cfg->fc_dst);
+ if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev,
+ addr_type))
+ rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
+ }
if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
- struct net_device *dev = fib6_info_nh_dev(rt);
+ struct net_device *dev = fib6_nh->fib_nh_dev;
if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
NL_SET_ERR_MSG(extack, "Invalid source address");
@@ -3300,6 +3718,12 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg)
info->skip_notify = 1;
}
+ info->skip_notify_kernel = 1;
+ call_fib6_multipath_entry_notifiers(net,
+ FIB_EVENT_ENTRY_DEL,
+ rt,
+ rt->fib6_nsiblings,
+ NULL);
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings,
fib6_siblings) {
@@ -3322,7 +3746,7 @@ out_put:
return err;
}
-static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
+static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
{
int rc = -ESRCH;
@@ -3338,10 +3762,49 @@ out:
return rc;
}
+static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt,
+ struct fib6_nh *nh)
+{
+ struct fib6_result res = {
+ .f6i = rt,
+ .nh = nh,
+ };
+ struct rt6_info *rt_cache;
+
+ rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src);
+ if (rt_cache)
+ return __ip6_del_cached_rt(rt_cache, cfg);
+
+ return 0;
+}
+
+struct fib6_nh_del_cached_rt_arg {
+ struct fib6_config *cfg;
+ struct fib6_info *f6i;
+};
+
+static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg)
+{
+ struct fib6_nh_del_cached_rt_arg *arg = _arg;
+ int rc;
+
+ rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh);
+ return rc != -ESRCH ? rc : 0;
+}
+
+static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i)
+{
+ struct fib6_nh_del_cached_rt_arg arg = {
+ .cfg = cfg,
+ .f6i = f6i
+ };
+
+ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg);
+}
+
static int ip6_route_del(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct rt6_info *rt_cache;
struct fib6_table *table;
struct fib6_info *rt;
struct fib6_node *fn;
@@ -3364,26 +3827,44 @@ static int ip6_route_del(struct fib6_config *cfg,
for_each_fib6_node_rt_rcu(fn) {
struct fib6_nh *nh;
+ if (rt->nh && rt->nh->id != cfg->fc_nh_id)
+ continue;
+
if (cfg->fc_flags & RTF_CACHE) {
- struct fib6_result res = {
- .f6i = rt,
- };
- int rc;
-
- rt_cache = rt6_find_cached_rt(&res,
- &cfg->fc_dst,
- &cfg->fc_src);
- if (rt_cache) {
- rc = ip6_del_cached_rt(rt_cache, cfg);
- if (rc != -ESRCH) {
- rcu_read_unlock();
- return rc;
- }
+ int rc = 0;
+
+ if (rt->nh) {
+ rc = ip6_del_cached_rt_nh(cfg, rt);
+ } else if (cfg->fc_nh_id) {
+ continue;
+ } else {
+ nh = rt->fib6_nh;
+ rc = ip6_del_cached_rt(cfg, rt, nh);
+ }
+ if (rc != -ESRCH) {
+ rcu_read_unlock();
+ return rc;
}
continue;
}
- nh = &rt->fib6_nh;
+ if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
+ continue;
+ if (cfg->fc_protocol &&
+ cfg->fc_protocol != rt->fib6_protocol)
+ continue;
+
+ if (rt->nh) {
+ if (!fib6_info_hold_safe(rt))
+ continue;
+ rcu_read_unlock();
+
+ return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+ }
+ if (cfg->fc_nh_id)
+ continue;
+
+ nh = rt->fib6_nh;
if (cfg->fc_ifindex &&
(!nh->fib_nh_dev ||
nh->fib_nh_dev->ifindex != cfg->fc_ifindex))
@@ -3391,10 +3872,6 @@ static int ip6_route_del(struct fib6_config *cfg,
if (cfg->fc_flags & RTF_GATEWAY &&
!ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6))
continue;
- if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
- continue;
- if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
- continue;
if (!fib6_info_hold_safe(rt))
continue;
rcu_read_unlock();
@@ -3505,7 +3982,25 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
if (!res.f6i)
goto out;
- res.nh = &res.f6i->fib6_nh;
+ if (res.f6i->nh) {
+ struct fib6_nh_match_arg arg = {
+ .dev = dst->dev,
+ .gw = &rt->rt6i_gateway,
+ };
+
+ nexthop_for_each_fib6_nh(res.f6i->nh,
+ fib6_nh_find_match, &arg);
+
+ /* fib6_info uses a nexthop that does not have fib6_nh
+ * using the dst->dev. Should be impossible
+ */
+ if (!arg.match)
+ goto out;
+ res.nh = arg.match;
+ } else {
+ res.nh = res.f6i->fib6_nh;
+ }
+
res.fib6_flags = res.f6i->fib6_flags;
res.fib6_type = res.f6i->fib6_type;
nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL);
@@ -3557,12 +4052,15 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
goto out;
for_each_fib6_node_rt_rcu(fn) {
- if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex)
+ /* these routes do not use nexthops */
+ if (rt->nh)
+ continue;
+ if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex)
continue;
if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
- !rt->fib6_nh.fib_nh_gw_family)
+ !rt->fib6_nh->fib_nh_gw_family)
continue;
- if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr))
+ if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr))
continue;
if (!fib6_info_hold_safe(rt))
continue;
@@ -3620,8 +4118,13 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
rcu_read_lock();
for_each_fib6_node_rt_rcu(&table->tb6_root) {
- struct fib6_nh *nh = &rt->fib6_nh;
+ struct fib6_nh *nh;
+
+ /* RA routes do not use nexthops */
+ if (rt->nh)
+ continue;
+ nh = rt->fib6_nh;
if (dev == nh->fib_nh_dev &&
((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
ipv6_addr_equal(&nh->fib_nh_gw6, addr))
@@ -3872,7 +4375,8 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
- if (((void *)rt->fib6_nh.fib_nh_dev == dev || !dev) &&
+ if (!rt->nh &&
+ ((void *)rt->fib6_nh->fib_nh_dev == dev || !dev) &&
rt != net->ipv6.fib6_null_entry &&
ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
spin_lock_bh(&rt6_exception_lock);
@@ -3900,18 +4404,22 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
{
struct in6_addr *gateway = (struct in6_addr *)arg;
+ struct fib6_nh *nh;
+
+ /* RA routes do not use nexthops */
+ if (rt->nh)
+ return 0;
+ nh = rt->fib6_nh;
if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
- rt->fib6_nh.fib_nh_gw_family &&
- ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) {
+ nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6))
return -1;
- }
/* Further clean up cached routes in exception table.
* This is needed because cached route may have a different
* gateway than its 'parent' in the case of an ip redirect.
*/
- rt6_exceptions_clean_tohost(rt, gateway);
+ fib6_nh_exceptions_clean_tohost(nh, gateway);
return 0;
}
@@ -3949,11 +4457,12 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
return NULL;
}
+/* only called for fib entries with builtin fib6_nh */
static bool rt6_is_dead(const struct fib6_info *rt)
{
- if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ||
- (rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
- ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev)))
+ if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD ||
+ (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN &&
+ ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev)))
return true;
return false;
@@ -3965,11 +4474,11 @@ static int rt6_multipath_total_weight(const struct fib6_info *rt)
int total = 0;
if (!rt6_is_dead(rt))
- total += rt->fib6_nh.fib_nh_weight;
+ total += rt->fib6_nh->fib_nh_weight;
list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
if (!rt6_is_dead(iter))
- total += iter->fib6_nh.fib_nh_weight;
+ total += iter->fib6_nh->fib_nh_weight;
}
return total;
@@ -3980,11 +4489,11 @@ static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total)
int upper_bound = -1;
if (!rt6_is_dead(rt)) {
- *weight += rt->fib6_nh.fib_nh_weight;
+ *weight += rt->fib6_nh->fib_nh_weight;
upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31,
total) - 1;
}
- atomic_set(&rt->fib6_nh.fib_nh_upper_bound, upper_bound);
+ atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound);
}
static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total)
@@ -4027,9 +4536,9 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg)
const struct arg_netdev_event *arg = p_arg;
struct net *net = dev_net(arg->dev);
- if (rt != net->ipv6.fib6_null_entry &&
- rt->fib6_nh.fib_nh_dev == arg->dev) {
- rt->fib6_nh.fib_nh_flags &= ~arg->nh_flags;
+ if (rt != net->ipv6.fib6_null_entry && !rt->nh &&
+ rt->fib6_nh->fib_nh_dev == arg->dev) {
+ rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags;
fib6_update_sernum_upto_root(net, rt);
rt6_multipath_rebalance(rt);
}
@@ -4052,15 +4561,16 @@ void rt6_sync_up(struct net_device *dev, unsigned char nh_flags)
fib6_clean_all(dev_net(dev), fib6_ifup, &arg);
}
+/* only called for fib entries with inline fib6_nh */
static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
const struct net_device *dev)
{
struct fib6_info *iter;
- if (rt->fib6_nh.fib_nh_dev == dev)
+ if (rt->fib6_nh->fib_nh_dev == dev)
return true;
list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
- if (iter->fib6_nh.fib_nh_dev == dev)
+ if (iter->fib6_nh->fib_nh_dev == dev)
return true;
return false;
@@ -4081,12 +4591,12 @@ static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
struct fib6_info *iter;
unsigned int dead = 0;
- if (rt->fib6_nh.fib_nh_dev == down_dev ||
- rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh->fib_nh_dev == down_dev ||
+ rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD)
dead++;
list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
- if (iter->fib6_nh.fib_nh_dev == down_dev ||
- iter->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
+ if (iter->fib6_nh->fib_nh_dev == down_dev ||
+ iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD)
dead++;
return dead;
@@ -4098,11 +4608,11 @@ static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
{
struct fib6_info *iter;
- if (rt->fib6_nh.fib_nh_dev == dev)
- rt->fib6_nh.fib_nh_flags |= nh_flags;
+ if (rt->fib6_nh->fib_nh_dev == dev)
+ rt->fib6_nh->fib_nh_flags |= nh_flags;
list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
- if (iter->fib6_nh.fib_nh_dev == dev)
- iter->fib6_nh.fib_nh_flags |= nh_flags;
+ if (iter->fib6_nh->fib_nh_dev == dev)
+ iter->fib6_nh->fib_nh_flags |= nh_flags;
}
/* called with write lock held for table with rt */
@@ -4112,17 +4622,17 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
const struct net_device *dev = arg->dev;
struct net *net = dev_net(dev);
- if (rt == net->ipv6.fib6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry || rt->nh)
return 0;
switch (arg->event) {
case NETDEV_UNREGISTER:
- return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
+ return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0;
case NETDEV_DOWN:
if (rt->should_flush)
return -1;
if (!rt->fib6_nsiblings)
- return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
+ return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0;
if (rt6_multipath_uses_dev(rt, dev)) {
unsigned int count;
@@ -4138,10 +4648,10 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
}
return -2;
case NETDEV_CHANGE:
- if (rt->fib6_nh.fib_nh_dev != dev ||
+ if (rt->fib6_nh->fib_nh_dev != dev ||
rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
break;
- rt->fib6_nh.fib_nh_flags |= RTNH_F_LINKDOWN;
+ rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
rt6_multipath_rebalance(rt);
break;
}
@@ -4175,9 +4685,36 @@ void rt6_disable_ip(struct net_device *dev, unsigned long event)
struct rt6_mtu_change_arg {
struct net_device *dev;
unsigned int mtu;
+ struct fib6_info *f6i;
};
-static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
+static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg)
+{
+ struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg;
+ struct fib6_info *f6i = arg->f6i;
+
+ /* For administrative MTU increase, there is no way to discover
+ * IPv6 PMTU increase, so PMTU increase should be updated here.
+ * Since RFC 1981 doesn't include administrative MTU increase
+ * update PMTU increase is a MUST. (i.e. jumbo frame)
+ */
+ if (nh->fib_nh_dev == arg->dev) {
+ struct inet6_dev *idev = __in6_dev_get(arg->dev);
+ u32 mtu = f6i->fib6_pmtu;
+
+ if (mtu >= arg->mtu ||
+ (mtu < arg->mtu && mtu == idev->cnf.mtu6))
+ fib6_metric_set(f6i, RTAX_MTU, arg->mtu);
+
+ spin_lock_bh(&rt6_exception_lock);
+ rt6_exceptions_update_pmtu(idev, nh, arg->mtu);
+ spin_unlock_bh(&rt6_exception_lock);
+ }
+
+ return 0;
+}
+
+static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg)
{
struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
struct inet6_dev *idev;
@@ -4192,24 +4729,17 @@ static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
if (!idev)
return 0;
- /* For administrative MTU increase, there is no way to discover
- IPv6 PMTU increase, so PMTU increase should be updated here.
- Since RFC 1981 doesn't include administrative MTU increase
- update PMTU increase is a MUST. (i.e. jumbo frame)
- */
- if (rt->fib6_nh.fib_nh_dev == arg->dev &&
- !fib6_metric_locked(rt, RTAX_MTU)) {
- u32 mtu = rt->fib6_pmtu;
-
- if (mtu >= arg->mtu ||
- (mtu < arg->mtu && mtu == idev->cnf.mtu6))
- fib6_metric_set(rt, RTAX_MTU, arg->mtu);
+ if (fib6_metric_locked(f6i, RTAX_MTU))
+ return 0;
- spin_lock_bh(&rt6_exception_lock);
- rt6_exceptions_update_pmtu(idev, rt, arg->mtu);
- spin_unlock_bh(&rt6_exception_lock);
+ arg->f6i = f6i;
+ if (f6i->nh) {
+ /* fib6_nh_mtu_change only returns 0, so this is safe */
+ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change,
+ arg);
}
- return 0;
+
+ return fib6_nh_mtu_change(f6i->fib6_nh, arg);
}
void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
@@ -4223,6 +4753,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
}
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
+ [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 },
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
[RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
@@ -4240,6 +4771,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_IP_PROTO] = { .type = NLA_U8 },
[RTA_SPORT] = { .type = NLA_U16 },
[RTA_DPORT] = { .type = NLA_U16 },
+ [RTA_NH_ID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4286,6 +4818,16 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK);
+ if (tb[RTA_NH_ID]) {
+ if (tb[RTA_GATEWAY] || tb[RTA_OIF] ||
+ tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) {
+ NL_SET_ERR_MSG(extack,
+ "Nexthop specification and nexthop id are mutually exclusive");
+ goto errout;
+ }
+ cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]);
+ }
+
if (tb[RTA_GATEWAY]) {
cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
cfg->fc_flags |= RTF_GATEWAY;
@@ -4429,6 +4971,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
{
struct fib6_info *rt_notif = NULL, *rt_last = NULL;
struct nl_info *info = &cfg->fc_nlinfo;
+ enum fib_event_type event_type;
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
struct fib6_info *rt;
@@ -4488,7 +5031,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
goto cleanup;
}
- rt->fib6_nh.fib_nh_weight = rtnh->rtnh_hops + 1;
+ rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1;
err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
rt, &r_cfg);
@@ -4506,6 +5049,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
*/
info->skip_notify = 1;
+ /* For add and replace, send one notification with all nexthops. For
+ * append, send one notification with all appended nexthops.
+ */
+ info->skip_notify_kernel = 1;
+
err_nh = NULL;
list_for_each_entry(nh, &rt6_nh_list, next) {
err = __ip6_ins_rt(nh->fib6_info, info, extack);
@@ -4542,6 +5090,15 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
nhn++;
}
+ event_type = replace ? FIB_EVENT_ENTRY_REPLACE : FIB_EVENT_ENTRY_ADD;
+ err = call_fib6_multipath_entry_notifiers(info->nl_net, event_type,
+ rt_notif, nhn - 1, extack);
+ if (err) {
+ /* Delete all the siblings that were just added */
+ err_nh = NULL;
+ goto add_errout;
+ }
+
/* success ... tell user about new route */
ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags);
goto cleanup;
@@ -4620,6 +5177,12 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ if (cfg.fc_nh_id &&
+ !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
+ NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+ return -EINVAL;
+ }
+
if (cfg.fc_mp)
return ip6_route_multipath_del(&cfg, extack);
else {
@@ -4647,17 +5210,46 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
return ip6_route_add(&cfg, GFP_KERNEL, extack);
}
-static size_t rt6_nlmsg_size(struct fib6_info *rt)
+/* add the overhead of this fib6_nh to nexthop_len */
+static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
{
- int nexthop_len = 0;
+ int *nexthop_len = arg;
- if (rt->fib6_nsiblings) {
- nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
- + NLA_ALIGN(sizeof(struct rtnexthop))
- + nla_total_size(16) /* RTA_GATEWAY */
- + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws);
+ *nexthop_len += nla_total_size(0) /* RTA_MULTIPATH */
+ + NLA_ALIGN(sizeof(struct rtnexthop))
+ + nla_total_size(16); /* RTA_GATEWAY */
- nexthop_len *= rt->fib6_nsiblings;
+ if (nh->fib_nh_lws) {
+ /* RTA_ENCAP_TYPE */
+ *nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+ /* RTA_ENCAP */
+ *nexthop_len += nla_total_size(2);
+ }
+
+ return 0;
+}
+
+static size_t rt6_nlmsg_size(struct fib6_info *f6i)
+{
+ int nexthop_len;
+
+ if (f6i->nh) {
+ nexthop_len = nla_total_size(4); /* RTA_NH_ID */
+ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
+ &nexthop_len);
+ } else {
+ struct fib6_nh *nh = f6i->fib6_nh;
+
+ nexthop_len = 0;
+ if (f6i->fib6_nsiblings) {
+ nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
+ + NLA_ALIGN(sizeof(struct rtnexthop))
+ + nla_total_size(16) /* RTA_GATEWAY */
+ + lwtunnel_get_encap_size(nh->fib_nh_lws);
+
+ nexthop_len *= f6i->fib6_nsiblings;
+ }
+ nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
}
return NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -4673,10 +5265,38 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
+ nla_total_size(sizeof(struct rta_cacheinfo))
+ nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
+ nla_total_size(1) /* RTA_PREF */
- + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws)
+ nexthop_len;
}
+static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh,
+ unsigned char *flags)
+{
+ if (nexthop_is_multipath(nh)) {
+ struct nlattr *mp;
+
+ mp = nla_nest_start(skb, RTA_MULTIPATH);
+ if (!mp)
+ goto nla_put_failure;
+
+ if (nexthop_mpath_fill_node(skb, nh))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, mp);
+ } else {
+ struct fib6_nh *fib6_nh;
+
+ fib6_nh = nexthop_fib6_nh(nh);
+ if (fib_nexthop_info(skb, &fib6_nh->nh_common,
+ flags, false) < 0)
+ goto nla_put_failure;
+ }
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
@@ -4686,6 +5306,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct rt6_info *rt6 = (struct rt6_info *)dst;
struct rt6key *rt6_dst, *rt6_src;
u32 *pmetrics, table, rt6_flags;
+ unsigned char nh_flags = 0;
struct nlmsghdr *nlh;
struct rtmsg *rtm;
long expires = 0;
@@ -4793,22 +5414,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
if (!mp)
goto nla_put_failure;
- if (fib_add_nexthop(skb, &rt->fib6_nh.nh_common,
- rt->fib6_nh.fib_nh_weight) < 0)
+ if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common,
+ rt->fib6_nh->fib_nh_weight) < 0)
goto nla_put_failure;
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings, fib6_siblings) {
- if (fib_add_nexthop(skb, &sibling->fib6_nh.nh_common,
- sibling->fib6_nh.fib_nh_weight) < 0)
+ if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
+ sibling->fib6_nh->fib_nh_weight) < 0)
goto nla_put_failure;
}
nla_nest_end(skb, mp);
- } else {
- unsigned char nh_flags = 0;
+ } else if (rt->nh) {
+ if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
+ goto nla_put_failure;
+
+ if (nexthop_is_blackhole(rt->nh))
+ rtm->rtm_type = RTN_BLACKHOLE;
- if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common,
+ if (rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
+ goto nla_put_failure;
+
+ rtm->rtm_flags |= nh_flags;
+ } else {
+ if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common,
&nh_flags, false) < 0)
goto nla_put_failure;
@@ -4835,10 +5465,28 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg)
+{
+ const struct net_device *dev = arg;
+
+ if (nh->fib_nh_dev == dev)
+ return 1;
+
+ return 0;
+}
+
static bool fib6_info_uses_dev(const struct fib6_info *f6i,
const struct net_device *dev)
{
- if (f6i->fib6_nh.fib_nh_dev == dev)
+ if (f6i->nh) {
+ struct net_device *_dev = (struct net_device *)dev;
+
+ return !!nexthop_for_each_fib6_nh(f6i->nh,
+ fib6_info_nh_uses_dev,
+ _dev);
+ }
+
+ if (f6i->fib6_nh->fib_nh_dev == dev)
return true;
if (f6i->fib6_nsiblings) {
@@ -4846,7 +5494,7 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
list_for_each_entry_safe(sibling, next_sibling,
&f6i->fib6_siblings, fib6_siblings) {
- if (sibling->fib6_nh.fib_nh_dev == dev)
+ if (sibling->fib6_nh->fib_nh_dev == dev)
return true;
}
}
@@ -5125,6 +5773,38 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
}
+void fib6_rt_update(struct net *net, struct fib6_info *rt,
+ struct nl_info *info)
+{
+ u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ /* call_fib6_entry_notifiers will be removed when in-kernel notifier
+ * is implemented and supported for nexthop objects
+ */
+ call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL);
+
+ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+ if (!skb)
+ goto errout;
+
+ err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0,
+ RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE);
+ if (err < 0) {
+ /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
+ WARN_ON(err == -EMSGSIZE);
+ kfree_skb(skb);
+ goto errout;
+ }
+ rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
+ info->nlh, gfp_any());
+ return;
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+}
+
static int ip6_route_dev_notify(struct notifier_block *this,
unsigned long event, void *ptr)
{
@@ -5135,7 +5815,7 @@ static int ip6_route_dev_notify(struct notifier_block *this,
return NOTIFY_OK;
if (event == NETDEV_REGISTER) {
- net->ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = dev;
+ net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev;
net->ipv6.ip6_null_entry->dst.dev = dev;
net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -5329,11 +6009,11 @@ static int __net_init ip6_route_net_init(struct net *net)
if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
goto out_ip6_dst_ops;
- net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template,
- sizeof(*net->ipv6.fib6_null_entry),
- GFP_KERNEL);
+ net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true);
if (!net->ipv6.fib6_null_entry)
goto out_ip6_dst_entries;
+ memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template,
+ sizeof(*net->ipv6.fib6_null_entry));
net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
sizeof(*net->ipv6.ip6_null_entry),
@@ -5470,7 +6150,7 @@ void __init ip6_route_init_special_entries(void)
/* Registering of the loopback is done before this portion of code,
* the loopback reference in rt6_info will not be taken, do it
* manually for init_net */
- init_net.ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = init_net.loopback_dev;
+ init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev;
init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index e15cd37024fd..6d86fac472e7 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -23,6 +23,7 @@
static int zero;
static int one = 1;
+static int three = 3;
static int auto_flowlabels_min;
static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
@@ -114,6 +115,8 @@ static struct ctl_table ipv6_table_template[] = {
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
+ .extra1 = &zero,
+ .extra2 = &three,
},
{
.procname = "max_dst_opts_number",
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7a14ea37d2df..408d9ec26971 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -883,9 +883,17 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
fl6.flowi6_oif = oif;
}
- if (sk)
- mark = (sk->sk_state == TCP_TIME_WAIT) ?
- inet_twsk(sk)->tw_mark : sk->sk_mark;
+ if (sk) {
+ if (sk->sk_state == TCP_TIME_WAIT) {
+ mark = inet_twsk(sk)->tw_mark;
+ /* autoflowlabel relies on buff->hash */
+ skb_set_hash(buff, inet_twsk(sk)->tw_txhash,
+ PKT_HASH_TYPE_L4);
+ } else {
+ mark = sk->sk_mark;
+ }
+ buff->tstamp = tcp_transmit_time(sk);
+ }
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark;
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
@@ -912,15 +920,17 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
{
const struct tcphdr *th = tcp_hdr(skb);
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
u32 seq = 0, ack_seq = 0;
struct tcp_md5sig_key *key = NULL;
#ifdef CONFIG_TCP_MD5SIG
const __u8 *hash_location = NULL;
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
unsigned char newhash[16];
int genhash;
struct sock *sk1 = NULL;
#endif
+ __be32 label = 0;
+ struct net *net;
int oif = 0;
if (th->rst)
@@ -932,6 +942,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
if (!sk && !ipv6_unicast_destination(skb))
return;
+ net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
#ifdef CONFIG_TCP_MD5SIG
rcu_read_lock();
hash_location = tcp_parse_md5sig_option(th);
@@ -945,7 +956,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
* Incoming packet is checked with md5 hash with finding key,
* no RST generated if md5 hash doesn't match.
*/
- sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
+ sk1 = inet6_lookup_listener(net,
&tcp_hashinfo, NULL, 0,
&ipv6h->saddr,
th->source, &ipv6h->daddr,
@@ -975,9 +986,15 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
oif = sk->sk_bound_dev_if;
if (sk_fullsock(sk))
trace_tcp_send_reset(sk, skb);
+ if (sk->sk_state == TCP_TIME_WAIT)
+ label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel);
+ } else {
+ if (net->ipv6.sysctl.flowlabel_reflect & 2)
+ label = ip6_flowlabel(ipv6h);
}
- tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
+ tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0,
+ label);
#ifdef CONFIG_TCP_MD5SIG
out:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 70b01bd95022..66ca5a4b17c4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -54,16 +54,6 @@
#include <trace/events/skb.h>
#include "udp_impl.h"
-static bool udp6_lib_exact_dif_match(struct net *net, struct sk_buff *skb)
-{
-#if defined(CONFIG_NET_L3_MASTER_DEV)
- if (!net->ipv4.sysctl_udp_l3mdev_accept &&
- skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
- return true;
-#endif
- return false;
-}
-
static u32 udp6_ehashfn(const struct net *net,
const struct in6_addr *laddr,
const u16 lport,
@@ -111,7 +101,7 @@ void udp_v6_rehash(struct sock *sk)
static int compute_score(struct sock *sk, struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned short hnum,
- int dif, int sdif, bool exact_dif)
+ int dif, int sdif)
{
int score;
struct inet_sock *inet;
@@ -155,8 +145,8 @@ static int compute_score(struct sock *sk, struct net *net,
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned int hnum,
- int dif, int sdif, bool exact_dif,
- struct udp_hslot *hslot2, struct sk_buff *skb)
+ int dif, int sdif, struct udp_hslot *hslot2,
+ struct sk_buff *skb)
{
struct sock *sk, *result;
int score, badness;
@@ -166,7 +156,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
score = compute_score(sk, net, saddr, sport,
- daddr, hnum, dif, sdif, exact_dif);
+ daddr, hnum, dif, sdif);
if (score > badness) {
if (sk->sk_reuseport) {
hash = udp6_ehashfn(net, daddr, hnum,
@@ -195,14 +185,13 @@ struct sock *__udp6_lib_lookup(struct net *net,
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
struct sock *result;
- bool exact_dif = udp6_lib_exact_dif_match(net, skb);
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
result = udp6_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif, sdif, exact_dif,
+ daddr, hnum, dif, sdif,
hslot2, skb);
if (!result) {
hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
@@ -212,10 +201,9 @@ struct sock *__udp6_lib_lookup(struct net *net,
result = udp6_lib_lookup2(net, saddr, sport,
&in6addr_any, hnum, dif, sdif,
- exact_dif, hslot2,
- skb);
+ hslot2, skb);
}
- if (unlikely(IS_ERR(result)))
+ if (IS_ERR(result))
return NULL;
return result;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-31 13:54:01 +0000