summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Makefile1
-rw-r--r--net/ipv6/addrconf.c2
-rw-r--r--net/ipv6/af_inet6.c6
-rw-r--r--net/ipv6/datagram.c12
-rw-r--r--net/ipv6/icmp.c6
-rw-r--r--net/ipv6/inet6_hashtables.c8
-rw-r--r--net/ipv6/ip6_fib.c25
-rw-r--r--net/ipv6/ip6_flowlabel.c4
-rw-r--r--net/ipv6/ip6_output.c60
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6_udp_tunnel.c6
-rw-r--r--net/ipv6/mcast_snoop.c213
-rw-r--r--net/ipv6/ndisc.c2
-rw-r--r--net/ipv6/netfilter.c2
-rw-r--r--net/ipv6/netfilter/Kconfig3
-rw-r--r--net/ipv6/netfilter/ip6_tables.c100
-rw-r--r--net/ipv6/output_core.c14
-rw-r--r--net/ipv6/raw.c11
-rw-r--r--net/ipv6/route.c561
-rw-r--r--net/ipv6/syncookies.c19
-rw-r--r--net/ipv6/sysctl_net_ipv6.c8
-rw-r--r--net/ipv6/tcp_ipv6.c16
-rw-r--r--net/ipv6/xfrm6_policy.c20
23 files changed, 767 insertions, 334 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 2e8c06108ab9..0f3f1999719a 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -48,4 +48,5 @@ obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o
ifneq ($(CONFIG_IPV6),)
obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
+obj-y += mcast_snoop.o
endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 37b70e82bff8..21c2c818df3b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2121,6 +2121,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
if (!fn)
goto out;
+
+ noflags |= RTF_CACHE;
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
if (rt->dst.dev->ifindex != dev->ifindex)
continue;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index eef63b394c5a..7de52b65173f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -167,7 +167,7 @@ lookup_protocol:
WARN_ON(!answer_prot->slab);
err = -ENOBUFS;
- sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot);
+ sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot, kern);
if (!sk)
goto out;
@@ -362,7 +362,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
np->saddr = addr->sin6_addr;
/* Make sure we are allowed to bind here. */
- if (sk->sk_prot->get_port(sk, snum)) {
+ if ((snum || !inet->bind_address_no_port) &&
+ sk->sk_prot->get_port(sk, snum)) {
inet_reset_saddr(sk);
err = -EADDRINUSE;
goto out;
@@ -768,6 +769,7 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.auto_flowlabels = 0;
net->ipv6.sysctl.idgen_retries = 3;
net->ipv6.sysctl.idgen_delay = 1 * HZ;
+ net->ipv6.sysctl.flowlabel_state_ranges = 1;
atomic_set(&net->ipv6.fib6_sernum, 1);
err = ipv6_init_mibs(net);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 762a58c772b8..62d908e64eeb 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -325,6 +325,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
kfree_skb(skb);
}
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+ return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 ||
+ serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+ serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
/* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
*
* At one point, excluding local errors was a quick test to identify icmp/icmp6
@@ -389,7 +399,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
serr = SKB_EXT_ERR(skb);
- if (sin && serr->port) {
+ if (sin && ipv6_datagram_support_addr(serr)) {
const unsigned char *nh = skb_network_header(skb);
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 2c2b5d51f15c..713d7434c911 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -207,7 +207,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
struct inet_peer *peer;
peer = inet_getpeer_v6(net->ipv6.peers,
- &rt->rt6i_dst.addr, 1);
+ &fl6->daddr, 1);
res = inet_peer_xrlim_allow(peer, tmo);
if (peer)
inet_putpeer(peer);
@@ -337,7 +337,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
* We won't send icmp if the destination is known
* anycast.
*/
- if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
+ if (ipv6_anycast_destination(dst, &fl6->daddr)) {
net_dbg_ratelimited("icmp6_send: acast source\n");
dst_release(dst);
return ERR_PTR(-EINVAL);
@@ -564,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
if (!ipv6_unicast_destination(skb) &&
!(net->ipv6.sysctl.anycast_src_echo_reply &&
- ipv6_anycast_destination(skb)))
+ ipv6_anycast_destination(skb_dst(skb), saddr)))
saddr = NULL;
memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 871641bc1ed4..b4fd96de97e6 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -257,7 +257,7 @@ not_unique:
return -EADDRNOTAVAIL;
}
-static inline u32 inet6_sk_port_offset(const struct sock *sk)
+static u32 inet6_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
@@ -269,7 +269,11 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk)
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk),
+ u32 port_offset = 0;
+
+ if (!inet_sk(sk)->inet_num)
+ port_offset = inet6_sk_port_offset(sk);
+ return __inet_hash_connect(death_row, sk, port_offset,
__inet6_check_established);
}
EXPORT_SYMBOL_GPL(inet6_hash_connect);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index bde57b113009..55d19861ab20 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -154,10 +154,32 @@ static void node_free(struct fib6_node *fn)
kmem_cache_free(fib6_node_kmem, fn);
}
+static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
+{
+ int cpu;
+
+ if (!non_pcpu_rt->rt6i_pcpu)
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **ppcpu_rt;
+ struct rt6_info *pcpu_rt;
+
+ ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
+ pcpu_rt = *ppcpu_rt;
+ if (pcpu_rt) {
+ dst_free(&pcpu_rt->dst);
+ *ppcpu_rt = NULL;
+ }
+ }
+}
+
static void rt6_release(struct rt6_info *rt)
{
- if (atomic_dec_and_test(&rt->rt6i_ref))
+ if (atomic_dec_and_test(&rt->rt6i_ref)) {
+ rt6_free_pcpu(rt);
dst_free(&rt->dst);
+ }
}
static void fib6_link_table(struct net *net, struct fib6_table *tb)
@@ -738,6 +760,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
+ iter->rt6i_pmtu = rt->rt6i_pmtu;
return -EEXIST;
}
/* If we have the same destination and the same metric,
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index d491125011c4..1f9ebe3cbb4a 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -595,6 +595,10 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
return -EINVAL;
+ if (net->ipv6.sysctl.flowlabel_state_ranges &&
+ (freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
+ return -ERANGE;
+
fl = fl_create(net, sk, &freq, optval, optlen, &err);
if (!fl)
return err;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bc09cb97b840..d5f7716662db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = rt6_nexthop((struct rt6_info *)dst);
+ nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
@@ -459,7 +459,7 @@ int ip6_forward(struct sk_buff *skb)
else
target = &hdr->daddr;
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+ peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
@@ -551,7 +551,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
int hroom, troom;
- __be32 frag_id = 0;
+ __be32 frag_id;
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
struct net *net = dev_net(skb_dst(skb)->dev);
@@ -564,18 +564,17 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket.
*/
- if (unlikely(!skb->ignore_df && skb->len > mtu) ||
- (IP6CB(skb)->frag_max_size &&
- IP6CB(skb)->frag_max_size > mtu)) {
- if (skb->sk && dst_allfrag(skb_dst(skb)))
- sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+ if (unlikely(!skb->ignore_df && skb->len > mtu))
+ goto fail_toobig;
- skb->dev = skb_dst(skb)->dev;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_FRAGFAILS);
- kfree_skb(skb);
- return -EMSGSIZE;
+ if (IP6CB(skb)->frag_max_size) {
+ if (IP6CB(skb)->frag_max_size > mtu)
+ goto fail_toobig;
+
+ /* don't send fragments larger than what we received */
+ mtu = IP6CB(skb)->frag_max_size;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
}
if (np && np->frag_size < mtu) {
@@ -584,6 +583,9 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
}
mtu -= hlen + sizeof(struct frag_hdr);
+ frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
+ &ipv6_hdr(skb)->saddr);
+
if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
struct sk_buff *frag2;
@@ -632,11 +634,10 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
- ipv6_select_ident(net, fh, rt);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
- frag_id = fh->identification;
+ fh->identification = frag_id;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
@@ -778,11 +779,7 @@ slow_path:
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
- if (!frag_id) {
- ipv6_select_ident(net, fh, rt);
- frag_id = fh->identification;
- } else
- fh->identification = frag_id;
+ fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
@@ -815,6 +812,14 @@ slow_path:
consume_skb(skb);
return err;
+fail_toobig:
+ if (skb->sk && dst_allfrag(skb_dst(skb)))
+ sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+
+ skb->dev = skb_dst(skb)->dev;
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ err = -EMSGSIZE;
+
fail:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
@@ -936,7 +941,8 @@ static int ip6_dst_lookup_tail(struct sock *sk,
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
- n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev,
+ rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
@@ -1060,11 +1066,10 @@ static inline int ip6_ufo_append_data(struct sock *sk,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int transhdrlen, int mtu, unsigned int flags,
- struct rt6_info *rt)
+ const struct flowi6 *fl6)
{
struct sk_buff *skb;
- struct frag_hdr fhdr;
int err;
/* There is support for UDP large send offload by network
@@ -1106,8 +1111,9 @@ static inline int ip6_ufo_append_data(struct sock *sk,
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
- ipv6_select_ident(sock_net(sk), &fhdr, rt);
- skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
+ skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk),
+ &fl6->daddr,
+ &fl6->saddr);
append:
return skb_append_datato_frags(sk, skb, getfrag, from,
@@ -1332,7 +1338,7 @@ emsgsize:
(sk->sk_type == SOCK_DGRAM)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen,
- transhdrlen, mtu, flags, rt);
+ transhdrlen, mtu, flags, fl6);
if (err)
goto error;
return 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5cafd92c2312..2e67b660118b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -151,7 +151,7 @@ EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *) dst;
- t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+ t->dst_cookie = rt6_get_cookie(rt);
dst_release(t->dst_cache);
t->dst_cache = dst;
}
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index bba8903e871f..e1a1136bda7c 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -19,12 +19,10 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
int err;
struct socket *sock = NULL;
- err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
+ err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock);
if (err < 0)
goto error;
- sk_change_net(sock->sk, net);
-
udp6_addr.sin6_family = AF_INET6;
memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
sizeof(udp6_addr.sin6_addr));
@@ -55,7 +53,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
error:
if (sock) {
kernel_sock_shutdown(sock, SHUT_RDWR);
- sk_release_kernel(sock->sk);
+ sock_release(sock);
}
*sockp = NULL;
return err;
diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c
new file mode 100644
index 000000000000..df8afe5ab31e
--- /dev/null
+++ b/net/ipv6/mcast_snoop.c
@@ -0,0 +1,213 @@
+/* Copyright (C) 2010: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ * Copyright (C) 2015: Linus Lüssing <linus.luessing@c0d3.blue>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ *
+ * Based on the MLD support added to br_multicast.c by YOSHIFUJI Hideaki.
+ */
+
+#include <linux/skbuff.h>
+#include <net/ipv6.h>
+#include <net/mld.h>
+#include <net/addrconf.h>
+#include <net/ip6_checksum.h>
+
+static int ipv6_mc_check_ip6hdr(struct sk_buff *skb)
+{
+ const struct ipv6hdr *ip6h;
+ unsigned int len;
+ unsigned int offset = skb_network_offset(skb) + sizeof(*ip6h);
+
+ if (!pskb_may_pull(skb, offset))
+ return -EINVAL;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->version != 6)
+ return -EINVAL;
+
+ len = offset + ntohs(ip6h->payload_len);
+ if (skb->len < len || len <= offset)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ipv6_mc_check_exthdrs(struct sk_buff *skb)
+{
+ const struct ipv6hdr *ip6h;
+ int offset;
+ u8 nexthdr;
+ __be16 frag_off;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->nexthdr != IPPROTO_HOPOPTS)
+ return -ENOMSG;
+
+ nexthdr = ip6h->nexthdr;
+ offset = skb_network_offset(skb) + sizeof(*ip6h);
+ offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+
+ if (offset < 0)
+ return -EINVAL;
+
+ if (nexthdr != IPPROTO_ICMPV6)
+ return -ENOMSG;
+
+ skb_set_transport_header(skb, offset);
+
+ return 0;
+}
+
+static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb)
+{
+ unsigned int len = skb_transport_offset(skb);
+
+ len += sizeof(struct mld2_report);
+
+ return pskb_may_pull(skb, len) ? 0 : -EINVAL;
+}
+
+static int ipv6_mc_check_mld_query(struct sk_buff *skb)
+{
+ struct mld_msg *mld;
+ unsigned int len = skb_transport_offset(skb);
+
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL))
+ return -EINVAL;
+
+ len += sizeof(struct mld_msg);
+ if (skb->len < len)
+ return -EINVAL;
+
+ /* MLDv1? */
+ if (skb->len != len) {
+ /* or MLDv2? */
+ len += sizeof(struct mld2_query) - sizeof(struct mld_msg);
+ if (skb->len < len || !pskb_may_pull(skb, len))
+ return -EINVAL;
+ }
+
+ mld = (struct mld_msg *)skb_transport_header(skb);
+
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
+ * all-nodes destination address (ff02::1) for general queries
+ */
+ if (ipv6_addr_any(&mld->mld_mca) &&
+ !ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ipv6_mc_check_mld_msg(struct sk_buff *skb)
+{
+ struct mld_msg *mld = (struct mld_msg *)skb_transport_header(skb);
+
+ switch (mld->mld_type) {
+ case ICMPV6_MGM_REDUCTION:
+ case ICMPV6_MGM_REPORT:
+ /* fall through */
+ return 0;
+ case ICMPV6_MLD2_REPORT:
+ return ipv6_mc_check_mld_reportv2(skb);
+ case ICMPV6_MGM_QUERY:
+ return ipv6_mc_check_mld_query(skb);
+ default:
+ return -ENOMSG;
+ }
+}
+
+static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb)
+{
+ return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo);
+}
+
+static int __ipv6_mc_check_mld(struct sk_buff *skb,
+ struct sk_buff **skb_trimmed)
+
+{
+ struct sk_buff *skb_chk = NULL;
+ unsigned int transport_len;
+ unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg);
+ int ret;
+
+ transport_len = ntohs(ipv6_hdr(skb)->payload_len);
+ transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr);
+
+ skb_get(skb);
+ skb_chk = skb_checksum_trimmed(skb, transport_len,
+ ipv6_mc_validate_checksum);
+ if (!skb_chk)
+ return -EINVAL;
+
+ if (!pskb_may_pull(skb_chk, len)) {
+ kfree_skb(skb_chk);
+ return -EINVAL;
+ }
+
+ ret = ipv6_mc_check_mld_msg(skb_chk);
+ if (ret) {
+ kfree_skb(skb_chk);
+ return ret;
+ }
+
+ if (skb_trimmed)
+ *skb_trimmed = skb_chk;
+ else
+ kfree_skb(skb_chk);
+
+ return 0;
+}
+
+/**
+ * ipv6_mc_check_mld - checks whether this is a sane MLD packet
+ * @skb: the skb to validate
+ * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional)
+ *
+ * Checks whether an IPv6 packet is a valid MLD packet. If so sets
+ * skb network and transport headers accordingly and returns zero.
+ *
+ * -EINVAL: A broken packet was detected, i.e. it violates some internet
+ * standard
+ * -ENOMSG: IP header validation succeeded but it is not an MLD packet.
+ * -ENOMEM: A memory allocation failure happened.
+ *
+ * Optionally, an skb pointer might be provided via skb_trimmed (or set it
+ * to NULL): After parsing an MLD packet successfully it will point to
+ * an skb which has its tail aligned to the IP packet end. This might
+ * either be the originally provided skb or a trimmed, cloned version if
+ * the skb frame had data beyond the IP packet. A cloned skb allows us
+ * to leave the original skb and its full frame unchanged (which might be
+ * desirable for layer 2 frame jugglers).
+ *
+ * The caller needs to release a reference count from any returned skb_trimmed.
+ */
+int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed)
+{
+ int ret;
+
+ ret = ipv6_mc_check_ip6hdr(skb);
+ if (ret < 0)
+ return ret;
+
+ ret = ipv6_mc_check_exthdrs(skb);
+ if (ret < 0)
+ return ret;
+
+ return __ipv6_mc_check_mld(skb, skb_trimmed);
+}
+EXPORT_SYMBOL(ipv6_mc_check_mld);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 96f153c0846b..0a05b35a90fc 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1506,7 +1506,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
"Redirect: destination is not a neighbour\n");
goto release;
}
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
+ peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
if (peer)
inet_putpeer(peer);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d958718b5031..b4de08a83e0b 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -191,6 +191,8 @@ static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
static const struct nf_ipv6_ops ipv6ops = {
.chk_addr = ipv6_chk_addr,
+ .route_input = ip6_route_input,
+ .fragment = ip6_fragment
};
static const struct nf_afinfo nf_ip6_afinfo = {
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ca6998345b42..b552cf0d6198 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -186,7 +186,8 @@ config IP6_NF_MATCH_MH
config IP6_NF_MATCH_RPFILTER
tristate '"rpfilter" reverse path filter match support'
- depends on NETFILTER_ADVANCED && (IP6_NF_MANGLE || IP6_NF_RAW)
+ depends on NETFILTER_ADVANCED
+ depends on IP6_NF_MANGLE || IP6_NF_RAW
---help---
This option allows you to match packets whose replies would
go out via the interface the packet came in.
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 62f5b0d0bc9b..3c35ced39b42 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -283,15 +283,13 @@ static void trace_packet(const struct sk_buff *skb,
const struct xt_table_info *private,
const struct ip6t_entry *e)
{
- const void *table_base;
const struct ip6t_entry *root;
const char *hookname, *chainname, *comment;
const struct ip6t_entry *iter;
unsigned int rulenum = 0;
struct net *net = dev_net(in ? in : out);
- table_base = private->entries[smp_processor_id()];
- root = get_entry(table_base, private->hook_entry[hook]);
+ root = get_entry(private->entries, private->hook_entry[hook]);
hookname = chainname = hooknames[hook];
comment = comments[NF_IP6_TRACE_COMMENT_RULE];
@@ -357,7 +355,7 @@ ip6t_do_table(struct sk_buff *skb,
*/
smp_read_barrier_depends();
cpu = smp_processor_id();
- table_base = private->entries[cpu];
+ table_base = private->entries;
jumpstack = (struct ip6t_entry **)private->jumpstack[cpu];
stackptr = per_cpu_ptr(private->stackptr, cpu);
origptr = *stackptr;
@@ -367,6 +365,7 @@ ip6t_do_table(struct sk_buff *skb,
do {
const struct xt_entry_target *t;
const struct xt_entry_match *ematch;
+ struct xt_counters *counter;
IP_NF_ASSERT(e);
acpar.thoff = 0;
@@ -384,7 +383,8 @@ ip6t_do_table(struct sk_buff *skb,
goto no_match;
}
- ADD_COUNTER(e->counters, skb->len, 1);
+ counter = xt_get_this_cpu_counter(&e->counters);
+ ADD_COUNTER(*counter, skb->len, 1);
t = ip6t_get_target_c(e);
IP_NF_ASSERT(t->u.kernel.target);
@@ -679,6 +679,10 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
if (ret)
return ret;
+ e->counters.pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(e->counters.pcnt))
+ return -ENOMEM;
+
j = 0;
mtpar.net = net;
mtpar.table = name;
@@ -714,6 +718,9 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
break;
cleanup_match(ematch, net);
}
+
+ xt_percpu_counter_free(e->counters.pcnt);
+
return ret;
}
@@ -797,6 +804,8 @@ static void cleanup_entry(struct ip6t_entry *e, struct net *net)
if (par.target->destroy != NULL)
par.target->destroy(&par);
module_put(par.target->me);
+
+ xt_percpu_counter_free(e->counters.pcnt);
}
/* Checks and translates the user-supplied table segment (held in
@@ -879,12 +888,6 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
return ret;
}
- /* And one copy for every other CPU */
- for_each_possible_cpu(i) {
- if (newinfo->entries[i] && newinfo->entries[i] != entry0)
- memcpy(newinfo->entries[i], entry0, newinfo->size);
- }
-
return ret;
}
@@ -900,14 +903,16 @@ get_counters(const struct xt_table_info *t,
seqcount_t *s = &per_cpu(xt_recseq, cpu);
i = 0;
- xt_entry_foreach(iter, t->entries[cpu], t->size) {
+ xt_entry_foreach(iter, t->entries, t->size) {
+ struct xt_counters *tmp;
u64 bcnt, pcnt;
unsigned int start;
+ tmp = xt_get_per_cpu_counter(&iter->counters, cpu);
do {
start = read_seqcount_begin(s);
- bcnt = iter->counters.bcnt;
- pcnt = iter->counters.pcnt;
+ bcnt = tmp->bcnt;
+ pcnt = tmp->pcnt;
} while (read_seqcount_retry(s, start));
ADD_COUNTER(counters[i], bcnt, pcnt);
@@ -952,11 +957,7 @@ copy_entries_to_user(unsigned int total_size,
if (IS_ERR(counters))
return PTR_ERR(counters);
- /* choose the copy that is on our node/cpu, ...
- * This choice is lazy (because current thread is
- * allowed to migrate to another cpu)
- */
- loc_cpu_entry = private->entries[raw_smp_processor_id()];
+ loc_cpu_entry = private->entries;
if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
ret = -EFAULT;
goto free_counters;
@@ -1064,16 +1065,16 @@ static int compat_table_info(const struct xt_table_info *info,
struct xt_table_info *newinfo)
{
struct ip6t_entry *iter;
- void *loc_cpu_entry;
+ const void *loc_cpu_entry;
int ret;
if (!newinfo || !info)
return -EINVAL;
- /* we dont care about newinfo->entries[] */
+ /* we dont care about newinfo->entries */
memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
newinfo->initial_entries = 0;
- loc_cpu_entry = info->entries[raw_smp_processor_id()];
+ loc_cpu_entry = info->entries;
xt_compat_init_offsets(AF_INET6, info->number);
xt_entry_foreach(iter, loc_cpu_entry, info->size) {
ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo);
@@ -1194,7 +1195,6 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
struct xt_table *t;
struct xt_table_info *oldinfo;
struct xt_counters *counters;
- const void *loc_cpu_old_entry;
struct ip6t_entry *iter;
ret = 0;
@@ -1237,8 +1237,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
get_counters(oldinfo, counters);
/* Decrease module usage counts and free resource */
- loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
- xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size)
+ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size)
cleanup_entry(iter, net);
xt_free_table_info(oldinfo);
@@ -1284,8 +1283,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
if (!newinfo)
return -ENOMEM;
- /* choose the copy that is on our node/cpu */
- loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
+ loc_cpu_entry = newinfo->entries;
if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
tmp.size) != 0) {
ret = -EFAULT;
@@ -1316,7 +1314,7 @@ static int
do_add_counters(struct net *net, const void __user *user, unsigned int len,
int compat)
{
- unsigned int i, curcpu;
+ unsigned int i;
struct xt_counters_info tmp;
struct xt_counters *paddc;
unsigned int num_counters;
@@ -1326,7 +1324,6 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
struct xt_table *t;
const struct xt_table_info *private;
int ret = 0;
- const void *loc_cpu_entry;
struct ip6t_entry *iter;
unsigned int addend;
#ifdef CONFIG_COMPAT
@@ -1374,7 +1371,6 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
goto free;
}
-
local_bh_disable();
private = t->private;
if (private->number != num_counters) {
@@ -1383,16 +1379,15 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
}
i = 0;
- /* Choose the copy that is on our node */
- curcpu = smp_processor_id();
addend = xt_write_recseq_begin();
- loc_cpu_entry = private->entries[curcpu];
- xt_entry_foreach(iter, loc_cpu_entry, private->size) {
- ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt);
+ xt_entry_foreach(iter, private->entries, private->size) {
+ struct xt_counters *tmp;
+
+ tmp = xt_get_this_cpu_counter(&iter->counters);
+ ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt);
++i;
}
xt_write_recseq_end(addend);
-
unlock_up_free:
local_bh_enable();
xt_table_unlock(t);
@@ -1459,7 +1454,6 @@ static int
compat_find_calc_match(struct xt_entry_match *m,
const char *name,
const struct ip6t_ip6 *ipv6,
- unsigned int hookmask,
int *size)
{
struct xt_match *match;
@@ -1528,8 +1522,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
entry_offset = (void *)e - (void *)base;
j = 0;
xt_ematch_foreach(ematch, e) {
- ret = compat_find_calc_match(ematch, name,
- &e->ipv6, e->comefrom, &off);
+ ret = compat_find_calc_match(ematch, name, &e->ipv6, &off);
if (ret != 0)
goto release_matches;
++j;
@@ -1623,6 +1616,9 @@ static int compat_check_entry(struct ip6t_entry *e, struct net *net,
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
+ e->counters.pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(e->counters.pcnt))
+ return -ENOMEM;
j = 0;
mtpar.net = net;
mtpar.table = name;
@@ -1647,6 +1643,9 @@ static int compat_check_entry(struct ip6t_entry *e, struct net *net,
break;
cleanup_match(ematch, net);
}
+
+ xt_percpu_counter_free(e->counters.pcnt);
+
return ret;
}
@@ -1731,7 +1730,7 @@ translate_compat_table(struct net *net,
newinfo->hook_entry[i] = info->hook_entry[i];
newinfo->underflow[i] = info->underflow[i];
}
- entry1 = newinfo->entries[raw_smp_processor_id()];
+ entry1 = newinfo->entries;
pos = entry1;
size = total_size;
xt_entry_foreach(iter0, entry0, total_size) {
@@ -1783,11 +1782,6 @@ translate_compat_table(struct net *net,
return ret;
}
- /* And one copy for every other CPU */
- for_each_possible_cpu(i)
- if (newinfo->entries[i] && newinfo->entries[i] != entry1)
- memcpy(newinfo->entries[i], entry1, newinfo->size);
-
*pinfo = newinfo;
*pentry0 = entry1;
xt_free_table_info(info);
@@ -1834,8 +1828,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
if (!newinfo)
return -ENOMEM;
- /* choose the copy that is on our node/cpu */
- loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
+ loc_cpu_entry = newinfo->entries;
if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
tmp.size) != 0) {
ret = -EFAULT;
@@ -1906,7 +1899,6 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
void __user *pos;
unsigned int size;
int ret = 0;
- const void *loc_cpu_entry;
unsigned int i = 0;
struct ip6t_entry *iter;
@@ -1914,14 +1906,9 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
if (IS_ERR(counters))
return PTR_ERR(counters);
- /* choose the copy that is on our node/cpu, ...
- * This choice is lazy (because current thread is
- * allowed to migrate to another cpu)
- */
- loc_cpu_entry = private->entries[raw_smp_processor_id()];
pos = userptr;
size = total_size;
- xt_entry_foreach(iter, loc_cpu_entry, total_size) {
+ xt_entry_foreach(iter, private->entries, total_size) {
ret = compat_copy_entry_to_user(iter, &pos,
&size, counters, i++);
if (ret != 0)
@@ -2096,8 +2083,7 @@ struct xt_table *ip6t_register_table(struct net *net,
goto out;
}
- /* choose the copy on our node/cpu, but dont care about preemption */
- loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
+ loc_cpu_entry = newinfo->entries;
memcpy(loc_cpu_entry, repl->entries, repl->size);
ret = translate_table(net, newinfo, loc_cpu_entry, repl);
@@ -2127,7 +2113,7 @@ void ip6t_unregister_table(struct net *net, struct xt_table *table)
private = xt_unregister_table(table);
/* Decrease module usage counts and free resources */
- loc_cpu_entry = private->entries[raw_smp_processor_id()];
+ loc_cpu_entry = private->entries;
xt_entry_foreach(iter, loc_cpu_entry, private->size)
cleanup_entry(iter, net);
if (private->number > private->initial_entries)
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 85892af57364..928a0fb0b744 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -8,9 +8,11 @@
#include <net/ip6_fib.h>
#include <net/addrconf.h>
#include <net/secure_seq.h>
+#include <linux/netfilter.h>
static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
- struct in6_addr *dst, struct in6_addr *src)
+ const struct in6_addr *dst,
+ const struct in6_addr *src)
{
u32 hash, id;
@@ -60,17 +62,17 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
-void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr,
- struct rt6_info *rt)
+__be32 ipv6_select_ident(struct net *net,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
static u32 ip6_idents_hashrnd __read_mostly;
u32 id;
net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
- id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr,
- &rt->rt6i_src.addr);
- fhdr->identification = htonl(id);
+ id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr);
+ return htonl(id);
}
EXPORT_SYMBOL(ipv6_select_ident);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8072bd4139b7..ca4700cb26c4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -865,6 +865,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = np->ucast_oif;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+ if (inet->hdrincl)
+ fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
+
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
@@ -1324,13 +1327,7 @@ static struct inet_protosw rawv6_protosw = {
int __init rawv6_init(void)
{
- int ret;
-
- ret = inet6_register_protosw(&rawv6_protosw);
- if (ret)
- goto out;
-out:
- return ret;
+ return inet6_register_protosw(&rawv6_protosw);
}
void rawv6_exit(void)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c73ae5039e46..1a1122a6bbf5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -72,8 +72,7 @@ enum rt6_nud_state {
RT6_NUD_SUCCEED = 1
};
-static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
- const struct in6_addr *dest);
+static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
static unsigned int ip6_mtu(const struct dst_entry *dst);
@@ -92,6 +91,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
+static void rt6_dst_from_metrics_check(struct rt6_info *rt);
static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -104,65 +104,82 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *gwaddr, int ifindex);
#endif
-static void rt6_bind_peer(struct rt6_info *rt, int create)
+struct uncached_list {
+ spinlock_t lock;
+ struct list_head head;
+};
+
+static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
+
+static void rt6_uncached_list_add(struct rt6_info *rt)
{
- struct inet_peer_base *base;
- struct inet_peer *peer;
+ struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
- base = inetpeer_base_ptr(rt->_rt6i_peer);
- if (!base)
- return;
+ rt->dst.flags |= DST_NOCACHE;
+ rt->rt6i_uncached_list = ul;
+
+ spin_lock_bh(&ul->lock);
+ list_add_tail(&rt->rt6i_uncached, &ul->head);
+ spin_unlock_bh(&ul->lock);
+}
- peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
- if (peer) {
- if (!rt6_set_peer(rt, peer))
- inet_putpeer(peer);
+static void rt6_uncached_list_del(struct rt6_info *rt)
+{
+ if (!list_empty(&rt->rt6i_uncached)) {
+ struct uncached_list *ul = rt->rt6i_uncached_list;
+
+ spin_lock_bh(&ul->lock);
+ list_del(&rt->rt6i_uncached);
+ spin_unlock_bh(&ul->lock);
}
}
-static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create)
+static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
{
- if (rt6_has_peer(rt))
- return rt6_peer_ptr(rt);
+ struct net_device *loopback_dev = net->loopback_dev;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
+ struct rt6_info *rt;
+
+ spin_lock_bh(&ul->lock);
+ list_for_each_entry(rt, &ul->head, rt6i_uncached) {
+ struct inet6_dev *rt_idev = rt->rt6i_idev;
+ struct net_device *rt_dev = rt->dst.dev;
+
+ if (rt_idev && (rt_idev->dev == dev || !dev) &&
+ rt_idev->dev != loopback_dev) {
+ rt->rt6i_idev = in6_dev_get(loopback_dev);
+ in6_dev_put(rt_idev);
+ }
- rt6_bind_peer(rt, create);
- return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL);
+ if (rt_dev && (rt_dev == dev || !dev) &&
+ rt_dev != loopback_dev) {
+ rt->dst.dev = loopback_dev;
+ dev_hold(rt->dst.dev);
+ dev_put(rt_dev);
+ }
+ }
+ spin_unlock_bh(&ul->lock);
+ }
}
-static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt)
+static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt)
{
- return __rt6_get_peer(rt, 1);
+ return dst_metrics_write_ptr(rt->dst.from);
}
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
{
- struct rt6_info *rt = (struct rt6_info *) dst;
- struct inet_peer *peer;
- u32 *p = NULL;
+ struct rt6_info *rt = (struct rt6_info *)dst;
- if (!(rt->dst.flags & DST_HOST))
+ if (rt->rt6i_flags & RTF_PCPU)
+ return rt6_pcpu_cow_metrics(rt);
+ else if (rt->rt6i_flags & RTF_CACHE)
+ return NULL;
+ else
return dst_cow_metrics_generic(dst, old);
-
- peer = rt6_get_peer_create(rt);
- if (peer) {
- u32 *old_p = __DST_METRICS_PTR(old);
- unsigned long prev, new;
-
- p = peer->metrics;
- if (inet_metrics_new(peer) ||
- (old & DST_METRICS_FORCE_OVERWRITE))
- memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
-
- new = (unsigned long) p;
- prev = cmpxchg(&dst->_metrics, old, new);
-
- if (prev != old) {
- p = __DST_METRICS_PTR(prev);
- if (prev & DST_METRICS_READ_ONLY)
- p = NULL;
- }
- }
- return p;
}
static inline const void *choose_neigh_daddr(struct rt6_info *rt,
@@ -299,10 +316,10 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct net *net,
- struct net_device *dev,
- int flags,
- struct fib6_table *table)
+static struct rt6_info *__ip6_dst_alloc(struct net *net,
+ struct net_device *dev,
+ int flags,
+ struct fib6_table *table)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
@@ -311,21 +328,54 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct dst_entry *dst = &rt->dst;
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
- rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
INIT_LIST_HEAD(&rt->rt6i_siblings);
+ INIT_LIST_HEAD(&rt->rt6i_uncached);
+ }
+ return rt;
+}
+
+static struct rt6_info *ip6_dst_alloc(struct net *net,
+ struct net_device *dev,
+ int flags,
+ struct fib6_table *table)
+{
+ struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table);
+
+ if (rt) {
+ rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
+ if (rt->rt6i_pcpu) {
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **p;
+
+ p = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+ /* no one shares rt */
+ *p = NULL;
+ }
+ } else {
+ dst_destroy((struct dst_entry *)rt);
+ return NULL;
+ }
}
+
return rt;
}
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
- struct inet6_dev *idev = rt->rt6i_idev;
struct dst_entry *from = dst->from;
+ struct inet6_dev *idev;
+
+ dst_destroy_metrics_generic(dst);
- if (!(rt->dst.flags & DST_HOST))
- dst_destroy_metrics_generic(dst);
+ if (rt->rt6i_pcpu)
+ free_percpu(rt->rt6i_pcpu);
+ rt6_uncached_list_del(rt);
+
+ idev = rt->rt6i_idev;
if (idev) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
@@ -333,11 +383,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
dst->from = NULL;
dst_release(from);
-
- if (rt6_has_peer(rt)) {
- struct inet_peer *peer = rt6_peer_ptr(rt);
- inet_putpeer(peer);
- }
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -652,15 +697,33 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
u32 metric, int oif, int strict,
bool *do_rr)
{
- struct rt6_info *rt, *match;
+ struct rt6_info *rt, *match, *cont;
int mpri = -1;
match = NULL;
- for (rt = rr_head; rt && rt->rt6i_metric == metric;
- rt = rt->dst.rt6_next)
+ cont = NULL;
+ for (rt = rr_head; rt; rt = rt->dst.rt6_next) {
+ if (rt->rt6i_metric != metric) {
+ cont = rt;
+ break;
+ }
+
match = find_match(rt, oif, strict, &mpri, match, do_rr);
- for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
- rt = rt->dst.rt6_next)
+ }
+
+ for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
+ if (rt->rt6i_metric != metric) {
+ cont = rt;
+ break;
+ }
+
+ match = find_match(rt, oif, strict, &mpri, match, do_rr);
+ }
+
+ if (match || !cont)
+ return match;
+
+ for (rt = cont; rt; rt = rt->dst.rt6_next)
match = find_match(rt, oif, strict, &mpri, match, do_rr);
return match;
@@ -694,6 +757,11 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
return match ? match : net->ipv6.ip6_null_entry;
}
+static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
+{
+ return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
+}
+
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
@@ -872,9 +940,9 @@ int ip6_ins_rt(struct rt6_info *rt)
return __ip6_ins_rt(rt, &info, &mxc);
}
-static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr)
+static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
struct rt6_info *rt;
@@ -882,15 +950,26 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
* Clone the route.
*/
- rt = ip6_rt_copy(ort, daddr);
+ if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
+ ort = (struct rt6_info *)ort->dst.from;
- if (rt) {
+ rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
+ 0, ort->rt6i_table);
+
+ if (!rt)
+ return NULL;
+
+ ip6_rt_copy_init(rt, ort);
+ rt->rt6i_flags |= RTF_CACHE;
+ rt->rt6i_metric = 0;
+ rt->dst.flags |= DST_HOST;
+ rt->rt6i_dst.addr = *daddr;
+ rt->rt6i_dst.plen = 128;
+
+ if (!rt6_is_gw_or_nonexthop(ort)) {
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
-
- rt->rt6i_flags |= RTF_CACHE;
-
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
rt->rt6i_src.addr = *saddr;
@@ -902,30 +981,65 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
return rt;
}
-static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
- const struct in6_addr *daddr)
+static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
{
- struct rt6_info *rt = ip6_rt_copy(ort, daddr);
+ struct rt6_info *pcpu_rt;
- if (rt)
- rt->rt6i_flags |= RTF_CACHE;
- return rt;
+ pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev),
+ rt->dst.dev, rt->dst.flags,
+ rt->rt6i_table);
+
+ if (!pcpu_rt)
+ return NULL;
+ ip6_rt_copy_init(pcpu_rt, rt);
+ pcpu_rt->rt6i_protocol = rt->rt6i_protocol;
+ pcpu_rt->rt6i_flags |= RTF_PCPU;
+ return pcpu_rt;
+}
+
+/* It should be called with read_lock_bh(&tb6_lock) acquired */
+static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
+{
+ struct rt6_info *pcpu_rt, *prev, **p;
+
+ p = this_cpu_ptr(rt->rt6i_pcpu);
+ pcpu_rt = *p;
+
+ if (pcpu_rt)
+ goto done;
+
+ pcpu_rt = ip6_rt_pcpu_alloc(rt);
+ if (!pcpu_rt) {
+ struct net *net = dev_net(rt->dst.dev);
+
+ pcpu_rt = net->ipv6.ip6_null_entry;
+ goto done;
+ }
+
+ prev = cmpxchg(p, NULL, pcpu_rt);
+ if (prev) {
+ /* If someone did it before us, return prev instead */
+ dst_destroy(&pcpu_rt->dst);
+ pcpu_rt = prev;
+ }
+
+done:
+ dst_hold(&pcpu_rt->dst);
+ rt6_dst_from_metrics_check(pcpu_rt);
+ return pcpu_rt;
}
static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, int flags)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *rt, *nrt;
+ struct rt6_info *rt;
int strict = 0;
- int attempts = 3;
- int err;
strict |= flags & RT6_LOOKUP_F_IFACE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
-redo_fib6_lookup_lock:
read_lock_bh(&table->tb6_lock);
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
@@ -944,51 +1058,52 @@ redo_rt6_select:
strict &= ~RT6_LOOKUP_F_REACHABLE;
fn = saved_fn;
goto redo_rt6_select;
- } else {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- goto out2;
}
}
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- if (rt->rt6i_flags & RTF_CACHE)
- goto out2;
+ if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) {
+ dst_use(&rt->dst, jiffies);
+ read_unlock_bh(&table->tb6_lock);
- if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)))
- nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
- else if (!(rt->dst.flags & DST_HOST))
- nrt = rt6_alloc_clone(rt, &fl6->daddr);
- else
- goto out2;
+ rt6_dst_from_metrics_check(rt);
+ return rt;
+ } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
+ !(rt->rt6i_flags & RTF_GATEWAY))) {
+ /* Create a RTF_CACHE clone which will not be
+ * owned by the fib6 tree. It is for the special case where
+ * the daddr in the skb during the neighbor look-up is different
+ * from the fl6->daddr used to look-up route here.
+ */
- ip6_rt_put(rt);
- rt = nrt ? : net->ipv6.ip6_null_entry;
+ struct rt6_info *uncached_rt;
- dst_hold(&rt->dst);
- if (nrt) {
- err = ip6_ins_rt(nrt);
- if (!err)
- goto out2;
- }
+ dst_use(&rt->dst, jiffies);
+ read_unlock_bh(&table->tb6_lock);
- if (--attempts <= 0)
- goto out2;
+ uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
+ dst_release(&rt->dst);
- /*
- * Race condition! In the gap, when table->tb6_lock was
- * released someone could insert this route. Relookup.
- */
- ip6_rt_put(rt);
- goto redo_fib6_lookup_lock;
+ if (uncached_rt)
+ rt6_uncached_list_add(uncached_rt);
+ else
+ uncached_rt = net->ipv6.ip6_null_entry;
-out2:
- rt->dst.lastuse = jiffies;
- rt->dst.__use++;
+ dst_hold(&uncached_rt->dst);
+ return uncached_rt;
- return rt;
+ } else {
+ /* Get a percpu copy */
+
+ struct rt6_info *pcpu_rt;
+
+ rt->dst.lastuse = jiffies;
+ rt->dst.__use++;
+ pcpu_rt = rt6_get_pcpu_route(rt);
+ read_unlock_bh(&table->tb6_lock);
+
+ return pcpu_rt;
+ }
}
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
@@ -1059,7 +1174,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
new = &rt->dst;
memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
- rt6_init_peer(rt, net->ipv6.peers);
new->__use = 1;
new->input = dst_discard;
@@ -1093,6 +1207,33 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
+static void rt6_dst_from_metrics_check(struct rt6_info *rt)
+{
+ if (rt->dst.from &&
+ dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(rt->dst.from))
+ dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true);
+}
+
+static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
+{
+ if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+ return NULL;
+
+ if (rt6_check_expired(rt))
+ return NULL;
+
+ return &rt->dst;
+}
+
+static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
+{
+ if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+ rt6_check((struct rt6_info *)(rt->dst.from), cookie))
+ return &rt->dst;
+ else
+ return NULL;
+}
+
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
struct rt6_info *rt;
@@ -1103,13 +1244,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
- if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
- return NULL;
- if (rt6_check_expired(rt))
- return NULL;
+ rt6_dst_from_metrics_check(rt);
- return dst;
+ if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+ return rt6_dst_from_check(rt, cookie);
+ else
+ return rt6_check(rt, cookie);
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -1148,24 +1289,63 @@ static void ip6_link_failure(struct sk_buff *skb)
}
}
-static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu)
+static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
+{
+ struct net *net = dev_net(rt->dst.dev);
+
+ rt->rt6i_flags |= RTF_MODIFIED;
+ rt->rt6i_pmtu = mtu;
+ rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+}
+
+static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
+ const struct ipv6hdr *iph, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info *)dst;
- dst_confirm(dst);
- if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
- struct net *net = dev_net(dst->dev);
+ if (rt6->rt6i_flags & RTF_LOCAL)
+ return;
- rt6->rt6i_flags |= RTF_MODIFIED;
- if (mtu < IPV6_MIN_MTU)
- mtu = IPV6_MIN_MTU;
+ dst_confirm(dst);
+ mtu = max_t(u32, mtu, IPV6_MIN_MTU);
+ if (mtu >= dst_mtu(dst))
+ return;
- dst_metric_set(dst, RTAX_MTU, mtu);
- rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
+ if (rt6->rt6i_flags & RTF_CACHE) {
+ rt6_do_update_pmtu(rt6, mtu);
+ } else {
+ const struct in6_addr *daddr, *saddr;
+ struct rt6_info *nrt6;
+
+ if (iph) {
+ daddr = &iph->daddr;
+ saddr = &iph->saddr;
+ } else if (sk) {
+ daddr = &sk->sk_v6_daddr;
+ saddr = &inet6_sk(sk)->saddr;
+ } else {
+ return;
+ }
+ nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
+ if (nrt6) {
+ rt6_do_update_pmtu(nrt6, mtu);
+
+ /* ip6_ins_rt(nrt6) will bump the
+ * rt6->rt6i_node->fn_sernum
+ * which will fail the next rt6_check() and
+ * invalidate the sk->sk_dst_cache.
+ */
+ ip6_ins_rt(nrt6);
+ }
}
}
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu)
+{
+ __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+}
+
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
int oif, u32 mark)
{
@@ -1182,7 +1362,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
- ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
+ __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
@@ -1341,12 +1521,17 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
static unsigned int ip6_mtu(const struct dst_entry *dst)
{
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+ unsigned int mtu = rt->rt6i_pmtu;
struct inet6_dev *idev;
- unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
goto out;
+ mtu = dst_metric_raw(dst, RTAX_MTU);
+ if (mtu)
+ goto out;
+
mtu = IPV6_MIN_MTU;
rcu_read_lock();
@@ -1590,10 +1775,8 @@ int ip6_route_add(struct fib6_config *cfg)
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
- if (rt->rt6i_dst.plen == 128) {
+ if (rt->rt6i_dst.plen == 128)
rt->dst.flags |= DST_HOST;
- dst_metrics_set_force_overwrite(&rt->dst);
- }
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
@@ -1651,6 +1834,16 @@ int ip6_route_add(struct fib6_config *cfg)
int gwa_type;
gw_addr = &cfg->fc_gateway;
+
+ /* if gw_addr is local we will fail to detect this in case
+ * address is still TENTATIVE (DAD in progress). rt6_lookup()
+ * will return already-added prefix route via interface that
+ * prefix route was assigned to, which might be non-loopback.
+ */
+ err = -EINVAL;
+ if (ipv6_chk_addr_and_flags(net, gw_addr, NULL, 0, 0))
+ goto out;
+
rt->rt6i_gateway = *gw_addr;
gwa_type = ipv6_addr_type(gw_addr);
@@ -1664,7 +1857,6 @@ int ip6_route_add(struct fib6_config *cfg)
(SIT, PtP, NBMA NOARP links) it is handy to allow
some exceptions. --ANK
*/
- err = -EINVAL;
if (!(gwa_type & IPV6_ADDR_UNICAST))
goto out;
@@ -1785,6 +1977,9 @@ static int ip6_route_del(struct fib6_config *cfg)
if (fn) {
for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+ if ((rt->rt6i_flags & RTF_CACHE) &&
+ !(cfg->fc_flags & RTF_CACHE))
+ continue;
if (cfg->fc_ifindex &&
(!rt->dst.dev ||
rt->dst.dev->ifindex != cfg->fc_ifindex))
@@ -1894,7 +2089,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NEIGH_UPDATE_F_ISROUTER))
);
- nrt = ip6_rt_copy(rt, &msg->dest);
+ nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
if (!nrt)
goto out;
@@ -1926,42 +2121,35 @@ out:
* Misc support functions
*/
-static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
- const struct in6_addr *dest)
+static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
{
- struct net *net = dev_net(ort->dst.dev);
- struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
- ort->rt6i_table);
+ BUG_ON(from->dst.from);
- if (rt) {
- rt->dst.input = ort->dst.input;
- rt->dst.output = ort->dst.output;
- rt->dst.flags |= DST_HOST;
-
- rt->rt6i_dst.addr = *dest;
- rt->rt6i_dst.plen = 128;
- dst_copy_metrics(&rt->dst, &ort->dst);
- rt->dst.error = ort->dst.error;
- rt->rt6i_idev = ort->rt6i_idev;
- if (rt->rt6i_idev)
- in6_dev_hold(rt->rt6i_idev);
- rt->dst.lastuse = jiffies;
-
- if (ort->rt6i_flags & RTF_GATEWAY)
- rt->rt6i_gateway = ort->rt6i_gateway;
- else
- rt->rt6i_gateway = *dest;
- rt->rt6i_flags = ort->rt6i_flags;
- rt6_set_from(rt, ort);
- rt->rt6i_metric = 0;
+ rt->rt6i_flags &= ~RTF_EXPIRES;
+ dst_hold(&from->dst);
+ rt->dst.from = &from->dst;
+ dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
+}
+static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
+{
+ rt->dst.input = ort->dst.input;
+ rt->dst.output = ort->dst.output;
+ rt->rt6i_dst = ort->rt6i_dst;
+ rt->dst.error = ort->dst.error;
+ rt->rt6i_idev = ort->rt6i_idev;
+ if (rt->rt6i_idev)
+ in6_dev_hold(rt->rt6i_idev);
+ rt->dst.lastuse = jiffies;
+ rt->rt6i_gateway = ort->rt6i_gateway;
+ rt->rt6i_flags = ort->rt6i_flags;
+ rt6_set_from(rt, ort);
+ rt->rt6i_metric = ort->rt6i_metric;
#ifdef CONFIG_IPV6_SUBTREES
- memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
+ rt->rt6i_src = ort->rt6i_src;
#endif
- memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key));
- rt->rt6i_table = ort->rt6i_table;
- }
- return rt;
+ rt->rt6i_prefsrc = ort->rt6i_prefsrc;
+ rt->rt6i_table = ort->rt6i_table;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -2336,6 +2524,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
fib6_clean_all(net, fib6_ifdown, &adn);
icmp6_clean_all(fib6_ifdown, &adn);
+ rt6_uncached_list_flush_dev(net, dev);
}
struct rt6_mtu_change_arg {
@@ -2373,11 +2562,20 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
- !dst_metric_locked(&rt->dst, RTAX_MTU) &&
- (dst_mtu(&rt->dst) >= arg->mtu ||
- (dst_mtu(&rt->dst) < arg->mtu &&
- dst_mtu(&rt->dst) == idev->cnf.mtu6))) {
- dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
+ !dst_metric_locked(&rt->dst, RTAX_MTU)) {
+ if (rt->rt6i_flags & RTF_CACHE) {
+ /* For RTF_CACHE with rt6i_pmtu == 0
+ * (i.e. a redirected route),
+ * the metrics of its rt->dst.from has already
+ * been updated.
+ */
+ if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu)
+ rt->rt6i_pmtu = arg->mtu;
+ } else if (dst_mtu(&rt->dst) >= arg->mtu ||
+ (dst_mtu(&rt->dst) < arg->mtu &&
+ dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+ dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
+ }
}
return 0;
}
@@ -2434,6 +2632,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (rtm->rtm_type == RTN_LOCAL)
cfg->fc_flags |= RTF_LOCAL;
+ if (rtm->rtm_flags & RTM_F_CLONED)
+ cfg->fc_flags |= RTF_CACHE;
+
cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
@@ -2608,6 +2809,7 @@ static int rt6_fill_node(struct net *net,
int iif, int type, u32 portid, u32 seq,
int prefix, int nowait, unsigned int flags)
{
+ u32 metrics[RTAX_MAX];
struct rtmsg *rtm;
struct nlmsghdr *nlh;
long expires;
@@ -2721,7 +2923,10 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
}
- if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
+ memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
+ if (rt->rt6i_pmtu)
+ metrics[RTAX_MTU - 1] = rt->rt6i_pmtu;
+ if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
if (rt->rt6i_flags & RTF_GATEWAY) {
@@ -3216,6 +3421,7 @@ static struct notifier_block ip6_route_dev_notifier = {
int __init ip6_route_init(void)
{
int ret;
+ int cpu;
ret = -ENOMEM;
ip6_dst_ops_template.kmem_cachep =
@@ -3275,6 +3481,13 @@ int __init ip6_route_init(void)
if (ret)
goto out_register_late_subsys;
+ for_each_possible_cpu(cpu) {
+ struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
+
+ INIT_LIST_HEAD(&ul->head);
+ spin_lock_init(&ul->lock);
+ }
+
out:
return ret;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 21bc2eb53c57..0909f4e0d53c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -41,23 +41,6 @@ static __u16 const msstab[] = {
9000 - 60,
};
-static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
- struct request_sock *req,
- struct dst_entry *dst)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
- struct sock *child;
-
- child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
- if (child) {
- atomic_set(&req->rsk_refcnt, 1);
- inet_csk_reqsk_queue_add(sk, req, child);
- } else {
- reqsk_free(req);
- }
- return child;
-}
-
static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
ipv6_cookie_scratch);
@@ -264,7 +247,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
- ret = get_cookie_sock(sk, skb, req, dst);
+ ret = tcp_get_cookie_sock(sk, skb, req, dst);
out:
return ret;
out_free:
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index abcc79f649b3..4e705add4f18 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -68,6 +68,13 @@ static struct ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "flowlabel_state_ranges",
+ .data = &init_net.ipv6.sysctl.flowlabel_state_ranges,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
@@ -109,6 +116,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect;
ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries;
ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay;
+ ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges;
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3adffb300238..6748c4277aff 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -99,8 +99,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
dst_hold(dst);
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
- if (rt->rt6i_node)
- inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+ inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
}
}
@@ -121,7 +120,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
- struct rt6_info *rt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -259,10 +257,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
sk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
- rt = (struct rt6_info *) dst;
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
- ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr))
+ ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
@@ -1251,7 +1248,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
return 0;
}
- if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb))
+ if (tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
@@ -1421,6 +1418,7 @@ process:
skb->dev = NULL;
bh_lock_sock_nested(sk);
+ tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
ret = 0;
if (!sock_owned_by_user(sk)) {
if (!tcp_prequeue(sk, skb))
@@ -1442,7 +1440,7 @@ no_tcp_socket:
tcp_v6_fill_cb(skb, hdr, th);
- if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
+ if (tcp_checksum_complete(skb)) {
csum_error:
TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
bad_packet:
@@ -1467,10 +1465,6 @@ do_time_wait:
tcp_v6_fill_cb(skb, hdr, th);
- if (skb->len < (th->doff<<2)) {
- inet_twsk_put(inet_twsk(sk));
- goto bad_packet;
- }
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f337a908a76a..ed0583c1b9fc 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -71,20 +71,12 @@ static int xfrm6_get_tos(const struct flowi *fl)
return 0;
}
-static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst)
-{
- struct rt6_info *rt = (struct rt6_info *)xdst;
-
- rt6_init_peer(rt, net->ipv6.peers);
-}
-
static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
if (dst->ops->family == AF_INET6) {
struct rt6_info *rt = (struct rt6_info *)dst;
- if (rt->rt6i_node)
- path->path_cookie = rt->rt6i_node->fn_sernum;
+ path->path_cookie = rt6_get_cookie(rt);
}
path->u.rt6.rt6i_nfheader_len = nfheader_len;
@@ -106,16 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
return -ENODEV;
}
- rt6_transfer_peer(&xdst->u.rt6, rt);
-
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
xdst->u.rt6.rt6i_node = rt->rt6i_node;
- if (rt->rt6i_node)
- xdst->route_cookie = rt->rt6i_node->fn_sernum;
+ xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
@@ -255,10 +244,6 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
- if (rt6_has_peer(&xdst->u.rt6)) {
- struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
- inet_putpeer(peer);
- }
xfrm_dst_destroy(xdst);
}
@@ -308,7 +293,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
- .init_dst = xfrm6_init_dst,
.init_path = xfrm6_init_path,
.fill_dst = xfrm6_fill_dst,
.blackhole_route = ip6_blackhole_route,