summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
authorJeff Garzik <jeff@garzik.org>2006-09-24 01:52:47 -0400
committerJeff Garzik <jeff@garzik.org>2006-09-24 01:52:47 -0400
commit23930fa1cebfea6f79881c588ccd1b0781e49e3f (patch)
tree36d29e3f83661c4f5f45b6f74ac0d5f9886867a8 /net/ipv6
parent36b35a5be0e4b406acd816e2122d153e875105be (diff)
parent4f5537de7c1531398e84e18a24f667e49cc94208 (diff)
Merge branch 'master' into upstream
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Kconfig45
-rw-r--r--net/ipv6/Makefile4
-rw-r--r--net/ipv6/addrconf.c663
-rw-r--r--net/ipv6/af_inet6.c21
-rw-r--r--net/ipv6/ah6.c124
-rw-r--r--net/ipv6/anycast.c8
-rw-r--r--net/ipv6/datagram.c20
-rw-r--r--net/ipv6/esp6.c106
-rw-r--r--net/ipv6/exthdrs.c233
-rw-r--r--net/ipv6/fib6_rules.c305
-rw-r--r--net/ipv6/icmp.c31
-rw-r--r--net/ipv6/inet6_connection_sock.c3
-rw-r--r--net/ipv6/ip6_fib.c463
-rw-r--r--net/ipv6/ip6_input.c2
-rw-r--r--net/ipv6/ip6_output.c106
-rw-r--r--net/ipv6/ipcomp6.c32
-rw-r--r--net/ipv6/ipv6_sockglue.c10
-rw-r--r--net/ipv6/ipv6_syms.c3
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/mip6.c519
-rw-r--r--net/ipv6/ndisc.c53
-rw-r--r--net/ipv6/netfilter.c2
-rw-r--r--net/ipv6/netfilter/Makefile2
-rw-r--r--net/ipv6/netfilter/ip6_queue.c16
-rw-r--r--net/ipv6/netfilter/ip6_tables.c24
-rw-r--r--net/ipv6/netfilter/ip6t_HL.c9
-rw-r--r--net/ipv6/netfilter/ip6t_LOG.c4
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c9
-rw-r--r--net/ipv6/netfilter/ip6t_ah.c1
-rw-r--r--net/ipv6/netfilter/ip6t_dst.c220
-rw-r--r--net/ipv6/netfilter/ip6t_frag.c1
-rw-r--r--net/ipv6/netfilter/ip6t_hbh.c49
-rw-r--r--net/ipv6/netfilter/ip6t_ipv6header.c1
-rw-r--r--net/ipv6/netfilter/ip6t_owner.c1
-rw-r--r--net/ipv6/netfilter/ip6t_rt.c1
-rw-r--r--net/ipv6/netfilter/ip6table_filter.c4
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c12
-rw-r--r--net/ipv6/netfilter/ip6table_raw.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c12
-rw-r--r--net/ipv6/raw.c49
-rw-r--r--net/ipv6/reassembly.c14
-rw-r--r--net/ipv6/route.c1059
-rw-r--r--net/ipv6/tcp_ipv6.c23
-rw-r--r--net/ipv6/udp.c104
-rw-r--r--net/ipv6/xfrm6_input.c110
-rw-r--r--net/ipv6/xfrm6_mode_ro.c93
-rw-r--r--net/ipv6/xfrm6_mode_transport.c5
-rw-r--r--net/ipv6/xfrm6_mode_tunnel.c3
-rw-r--r--net/ipv6/xfrm6_output.c18
-rw-r--r--net/ipv6/xfrm6_policy.c87
-rw-r--r--net/ipv6/xfrm6_state.c189
-rw-r--r--net/ipv6/xfrm6_tunnel.c2
54 files changed, 3414 insertions, 1469 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index e923d4dea41..a2d211da2ab 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -77,6 +77,7 @@ config INET6_ESP
select CRYPTO
select CRYPTO_HMAC
select CRYPTO_MD5
+ select CRYPTO_CBC
select CRYPTO_SHA1
select CRYPTO_DES
---help---
@@ -97,6 +98,15 @@ config INET6_IPCOMP
If unsure, say Y.
+config IPV6_MIP6
+ bool "IPv6: Mobility (EXPERIMENTAL)"
+ depends on IPV6 && EXPERIMENTAL
+ select XFRM
+ ---help---
+ Support for IPv6 Mobility described in RFC 3775.
+
+ If unsure, say N.
+
config INET6_XFRM_TUNNEL
tristate
select INET6_TUNNEL
@@ -126,6 +136,13 @@ config INET6_XFRM_MODE_TUNNEL
If unsure, say Y.
+config INET6_XFRM_MODE_ROUTEOPTIMIZATION
+ tristate "IPv6: MIPv6 route optimization mode (EXPERIMENTAL)"
+ depends on IPV6 && EXPERIMENTAL
+ select XFRM
+ ---help---
+ Support for MIPv6 route optimization mode.
+
config IPV6_TUNNEL
tristate "IPv6: IPv6-in-IPv6 tunnel"
select INET6_TUNNEL
@@ -135,3 +152,31 @@ config IPV6_TUNNEL
If unsure, say N.
+config IPV6_SUBTREES
+ bool "IPv6: source address based routing"
+ depends on IPV6 && EXPERIMENTAL
+ ---help---
+ Enable routing by source address or prefix.
+
+ The destination address is still the primary routing key, so mixing
+ normal and source prefix specific routes in the same routing table
+ may sometimes lead to unintended routing behavior. This can be
+ avoided by defining different routing tables for the normal and
+ source prefix specific routes.
+
+ If unsure, say N.
+
+config IPV6_MULTIPLE_TABLES
+ bool "IPv6: Multiple Routing Tables"
+ depends on IPV6 && EXPERIMENTAL
+ select FIB_RULES
+ ---help---
+ Support multiple routing tables.
+
+config IPV6_ROUTE_FWMARK
+ bool "IPv6: use netfilter MARK value as routing key"
+ depends on IPV6_MULTIPLE_TABLES && NETFILTER
+ ---help---
+ If you say Y here, you will be able to specify different routes for
+ packets with different mark values (see iptables(8), MARK target).
+
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 386e0a62694..0213c6612b5 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -13,6 +13,9 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \
ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \
xfrm6_output.o
ipv6-$(CONFIG_NETFILTER) += netfilter.o
+ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
+ipv6-$(CONFIG_IPV6_MIP6) += mip6.o
+
ipv6-objs += $(ipv6-y)
obj-$(CONFIG_INET6_AH) += ah6.o
@@ -22,6 +25,7 @@ obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o
obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o
obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o
obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o
+obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
obj-$(CONFIG_NETFILTER) += netfilter/
obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c7852b38e03..c1867635239 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -48,6 +48,7 @@
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
+#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/if_arcnet.h>
#include <linux/if_infiniband.h>
@@ -72,6 +73,7 @@
#include <net/addrconf.h>
#include <net/tcp.h>
#include <net/ip.h>
+#include <net/netlink.h>
#include <linux/if_tunnel.h>
#include <linux/rtnetlink.h>
@@ -117,9 +119,6 @@ static int ipv6_count_addresses(struct inet6_dev *idev);
static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE];
static DEFINE_RWLOCK(addrconf_hash_lock);
-/* Protects inet6 devices */
-DEFINE_RWLOCK(addrconf_lock);
-
static void addrconf_verify(unsigned long);
static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
@@ -144,7 +143,7 @@ static int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *de
static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
-struct ipv6_devconf ipv6_devconf = {
+struct ipv6_devconf ipv6_devconf __read_mostly = {
.forwarding = 0,
.hop_limit = IPV6_DEFAULT_HOPLIMIT,
.mtu6 = IPV6_MIN_MTU,
@@ -173,9 +172,10 @@ struct ipv6_devconf ipv6_devconf = {
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .proxy_ndp = 0,
};
-static struct ipv6_devconf ipv6_devconf_dflt = {
+static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.forwarding = 0,
.hop_limit = IPV6_DEFAULT_HOPLIMIT,
.mtu6 = IPV6_MIN_MTU,
@@ -203,6 +203,7 @@ static struct ipv6_devconf ipv6_devconf_dflt = {
.accept_ra_rt_info_max_plen = 0,
#endif
#endif
+ .proxy_ndp = 0,
};
/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
@@ -314,6 +315,12 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp,
/* Nobody refers to this device, we may destroy it. */
+static void in6_dev_finish_destroy_rcu(struct rcu_head *head)
+{
+ struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu);
+ kfree(idev);
+}
+
void in6_dev_finish_destroy(struct inet6_dev *idev)
{
struct net_device *dev = idev->dev;
@@ -328,7 +335,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
return;
}
snmp6_free_dev(idev);
- kfree(idev);
+ call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu);
}
static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
@@ -404,9 +411,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
if (netif_carrier_ok(dev))
ndev->if_flags |= IF_READY;
- write_lock_bh(&addrconf_lock);
- dev->ip6_ptr = ndev;
- write_unlock_bh(&addrconf_lock);
+ /* protected by rtnl_lock */
+ rcu_assign_pointer(dev->ip6_ptr, ndev);
ipv6_mc_init_dev(ndev);
ndev->tstamp = jiffies;
@@ -470,7 +476,7 @@ static void addrconf_forward_change(void)
read_lock(&dev_base_lock);
for (dev=dev_base; dev; dev=dev->next) {
- read_lock(&addrconf_lock);
+ rcu_read_lock();
idev = __in6_dev_get(dev);
if (idev) {
int changed = (!idev->cnf.forwarding) ^ (!ipv6_devconf.forwarding);
@@ -478,7 +484,7 @@ static void addrconf_forward_change(void)
if (changed)
dev_forward_change(idev);
}
- read_unlock(&addrconf_lock);
+ rcu_read_unlock();
}
read_unlock(&dev_base_lock);
}
@@ -539,7 +545,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
int hash;
int err = 0;
- read_lock_bh(&addrconf_lock);
+ rcu_read_lock_bh();
if (idev->dead) {
err = -ENODEV; /*XXX*/
goto out2;
@@ -608,7 +614,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
in6_ifa_hold(ifa);
write_unlock(&idev->lock);
out2:
- read_unlock_bh(&addrconf_lock);
+ rcu_read_unlock_bh();
if (likely(err == 0))
atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa);
@@ -734,7 +740,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) {
if (onlink == 0) {
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
rt = NULL;
} else if (!(rt->rt6i_flags & RTF_EXPIRES)) {
rt->rt6i_expires = expires;
@@ -911,7 +917,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
memset(&hiscore, 0, sizeof(hiscore));
read_lock(&dev_base_lock);
- read_lock(&addrconf_lock);
+ rcu_read_lock();
for (dev = dev_base; dev; dev=dev->next) {
struct inet6_dev *idev;
@@ -1032,9 +1038,27 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
continue;
}
- /* Rule 4: Prefer home address -- not implemented yet */
+ /* Rule 4: Prefer home address */
+#ifdef CONFIG_IPV6_MIP6
+ if (hiscore.rule < 4) {
+ if (ifa_result->flags & IFA_F_HOMEADDRESS)
+ hiscore.attrs |= IPV6_SADDR_SCORE_HOA;
+ hiscore.rule++;
+ }
+ if (ifa->flags & IFA_F_HOMEADDRESS) {
+ score.attrs |= IPV6_SADDR_SCORE_HOA;
+ if (!(ifa_result->flags & IFA_F_HOMEADDRESS)) {
+ score.rule = 4;
+ goto record_it;
+ }
+ } else {
+ if (hiscore.attrs & IPV6_SADDR_SCORE_HOA)
+ continue;
+ }
+#else
if (hiscore.rule < 4)
hiscore.rule++;
+#endif
/* Rule 5: Prefer outgoing interface */
if (hiscore.rule < 5) {
@@ -1123,7 +1147,7 @@ record_it:
}
read_unlock_bh(&idev->lock);
}
- read_unlock(&addrconf_lock);
+ rcu_read_unlock();
read_unlock(&dev_base_lock);
if (!ifa_result)
@@ -1147,7 +1171,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr)
struct inet6_dev *idev;
int err = -EADDRNOTAVAIL;
- read_lock(&addrconf_lock);
+ rcu_read_lock();
if ((idev = __in6_dev_get(dev)) != NULL) {
struct inet6_ifaddr *ifp;
@@ -1161,7 +1185,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr)
}
read_unlock_bh(&idev->lock);
}
- read_unlock(&addrconf_lock);
+ rcu_read_unlock();
return err;
}
@@ -1462,7 +1486,7 @@ static void ipv6_regen_rndid(unsigned long data)
struct inet6_dev *idev = (struct inet6_dev *) data;
unsigned long expires;
- read_lock_bh(&addrconf_lock);
+ rcu_read_lock_bh();
write_lock_bh(&idev->lock);
if (idev->dead)
@@ -1486,7 +1510,7 @@ static void ipv6_regen_rndid(unsigned long data)
out:
write_unlock_bh(&idev->lock);
- read_unlock_bh(&addrconf_lock);
+ rcu_read_unlock_bh();
in6_dev_put(idev);
}
@@ -1507,59 +1531,56 @@ static void
addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
unsigned long expires, u32 flags)
{
- struct in6_rtmsg rtmsg;
+ struct fib6_config cfg = {
+ .fc_table = RT6_TABLE_PREFIX,
+ .fc_metric = IP6_RT_PRIO_ADDRCONF,
+ .fc_ifindex = dev->ifindex,
+ .fc_expires = expires,
+ .fc_dst_len = plen,
+ .fc_flags = RTF_UP | flags,
+ };
- memset(&rtmsg, 0, sizeof(rtmsg));
- ipv6_addr_copy(&rtmsg.rtmsg_dst, pfx);
- rtmsg.rtmsg_dst_len = plen;
- rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF;
- rtmsg.rtmsg_ifindex = dev->ifindex;
- rtmsg.rtmsg_info = expires;
- rtmsg.rtmsg_flags = RTF_UP|flags;
- rtmsg.rtmsg_type = RTMSG_NEWROUTE;
+ ipv6_addr_copy(&cfg.fc_dst, pfx);
/* Prevent useless cloning on PtP SIT.
This thing is done here expecting that the whole
class of non-broadcast devices need not cloning.
*/
- if (dev->type == ARPHRD_SIT && (dev->flags&IFF_POINTOPOINT))
- rtmsg.rtmsg_flags |= RTF_NONEXTHOP;
+ if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT))
+ cfg.fc_flags |= RTF_NONEXTHOP;
- ip6_route_add(&rtmsg, NULL, NULL, NULL);
+ ip6_route_add(&cfg);
}
/* Create "default" multicast route to the interface */
static void addrconf_add_mroute(struct net_device *dev)
{
- struct in6_rtmsg rtmsg;
+ struct fib6_config cfg = {
+ .fc_table = RT6_TABLE_LOCAL,
+ .fc_metric = IP6_RT_PRIO_ADDRCONF,
+ .fc_ifindex = dev->ifindex,
+ .fc_dst_len = 8,
+ .fc_flags = RTF_UP,
+ };
+
+ ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0);
- memset(&rtmsg, 0, sizeof(rtmsg));
- ipv6_addr_set(&rtmsg.rtmsg_dst,
- htonl(0xFF000000), 0, 0, 0);
- rtmsg.rtmsg_dst_len = 8;
- rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF;
- rtmsg.rtmsg_ifindex = dev->ifindex;
- rtmsg.rtmsg_flags = RTF_UP;
- rtmsg.rtmsg_type = RTMSG_NEWROUTE;
- ip6_route_add(&rtmsg, NULL, NULL, NULL);
+ ip6_route_add(&cfg);
}
static void sit_route_add(struct net_device *dev)
{
- struct in6_rtmsg rtmsg;
-
- memset(&rtmsg, 0, sizeof(rtmsg));
-
- rtmsg.rtmsg_type = RTMSG_NEWROUTE;
- rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF;
+ struct fib6_config cfg = {
+ .fc_table = RT6_TABLE_MAIN,
+ .fc_metric = IP6_RT_PRIO_ADDRCONF,
+ .fc_ifindex = dev->ifindex,
+ .fc_dst_len = 96,
+ .fc_flags = RTF_UP | RTF_NONEXTHOP,
+ };
/* prefix length - 96 bits "::d.d.d.d" */
- rtmsg.rtmsg_dst_len = 96;
- rtmsg.rtmsg_flags = RTF_UP|RTF_NONEXTHOP;
- rtmsg.rtmsg_ifindex = dev->ifindex;
-
- ip6_route_add(&rtmsg, NULL, NULL, NULL);
+ ip6_route_add(&cfg);
}
static void addrconf_add_lroute(struct net_device *dev)
@@ -1660,7 +1681,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) {
if (rt->rt6i_flags&RTF_EXPIRES) {
if (valid_lft == 0) {
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
rt = NULL;
} else {
rt->rt6i_expires = jiffies + rt_expires;
@@ -1870,12 +1891,11 @@ err_exit:
* Manual configuration of address on an interface
*/
static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen,
- __u32 prefered_lft, __u32 valid_lft)
+ __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft)
{
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
struct net_device *dev;
- __u8 ifa_flags = 0;
int scope;
ASSERT_RTNL();
@@ -1887,9 +1907,6 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen,
if ((dev = __dev_get_by_index(ifindex)) == NULL)
return -ENODEV;
- if (!(dev->flags&IFF_UP))
- return -ENETDOWN;
-
if ((idev = addrconf_add_dev(dev)) == NULL)
return -ENOBUFS;
@@ -1971,7 +1988,7 @@ int addrconf_add_ifaddr(void __user *arg)
rtnl_lock();
err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen,
- INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
+ IFA_F_PERMANENT, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
rtnl_unlock();
return err;
}
@@ -2344,10 +2361,10 @@ static int addrconf_ifdown(struct net_device *dev, int how)
Do not dev_put!
*/
if (how == 1) {
- write_lock_bh(&addrconf_lock);
- dev->ip6_ptr = NULL;
idev->dead = 1;
- write_unlock_bh(&addrconf_lock);
+
+ /* protected by rtnl_lock */
+ rcu_assign_pointer(dev->ip6_ptr, NULL);
/* Step 1.5: remove snmp6 entry */
snmp6_unregister_dev(idev);
@@ -2514,7 +2531,8 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
spin_lock_bh(&ifp->lock);
if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
- !(ifp->flags&IFA_F_TENTATIVE)) {
+ !(ifp->flags&IFA_F_TENTATIVE) ||
+ ifp->flags & IFA_F_NODAD) {
ifp->flags &= ~IFA_F_TENTATIVE;
spin_unlock_bh(&ifp->lock);
read_unlock_bh(&idev->lock);
@@ -2759,6 +2777,26 @@ void if6_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
+#ifdef CONFIG_IPV6_MIP6
+/* Check if address is a home address configured on any interface. */
+int ipv6_chk_home_addr(struct in6_addr *addr)
+{
+ int ret = 0;
+ struct inet6_ifaddr * ifp;
+ u8 hash = ipv6_addr_hash(addr);
+ read_lock_bh(&addrconf_hash_lock);
+ for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) {
+ if (ipv6_addr_cmp(&ifp->addr, addr) == 0 &&
+ (ifp->flags & IFA_F_HOMEADDRESS)) {
+ ret = 1;
+ break;
+ }
+ }
+ read_unlock_bh(&addrconf_hash_lock);
+ return ret;
+}
+#endif
+
/*
* Periodic address status verification
*/
@@ -2869,66 +2907,68 @@ restart:
spin_unlock_bh(&addrconf_verify_lock);
}
+static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local)
+{
+ struct in6_addr *pfx = NULL;
+
+ if (addr)
+ pfx = nla_data(addr);
+
+ if (local) {
+ if (pfx && nla_memcmp(local, pfx, sizeof(*pfx)))
+ pfx = NULL;
+ else
+ pfx = nla_data(local);
+ }
+
+ return pfx;
+}
+
+static struct nla_policy ifa_ipv6_policy[IFA_MAX+1] __read_mostly = {
+ [IFA_ADDRESS] = { .len = sizeof(struct in6_addr) },
+ [IFA_LOCAL] = { .len = sizeof(struct in6_addr) },
+ [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
+};
+
static int
inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
- struct rtattr **rta = arg;
- struct ifaddrmsg *ifm = NLMSG_DATA(nlh);
+ struct ifaddrmsg *ifm;
+ struct nlattr *tb[IFA_MAX+1];
struct in6_addr *pfx;
+ int err;
- pfx = NULL;
- if (rta[IFA_ADDRESS-1]) {
- if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*pfx))
- return -EINVAL;
- pfx = RTA_DATA(rta[IFA_ADDRESS-1]);
- }
- if (rta[IFA_LOCAL-1]) {
- if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*pfx) ||
- (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx))))
- return -EINVAL;
- pfx = RTA_DATA(rta[IFA_LOCAL-1]);
- }
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
+ if (err < 0)
+ return err;
+
+ ifm = nlmsg_data(nlh);
+ pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
if (pfx == NULL)
return -EINVAL;
return inet6_addr_del(ifm->ifa_index, pfx, ifm->ifa_prefixlen);
}
-static int
-inet6_addr_modify(int ifindex, struct in6_addr *pfx,
- __u32 prefered_lft, __u32 valid_lft)
+static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags,
+ u32 prefered_lft, u32 valid_lft)
{
- struct inet6_ifaddr *ifp = NULL;
- struct net_device *dev;
- int ifa_flags = 0;
-
- if ((dev = __dev_get_by_index(ifindex)) == NULL)
- return -ENODEV;
-
- if (!(dev->flags&IFF_UP))
- return -ENETDOWN;
-
if (!valid_lft || (prefered_lft > valid_lft))
return -EINVAL;
- ifp = ipv6_get_ifaddr(pfx, dev, 1);
- if (ifp == NULL)
- return -ENOENT;
-
if (valid_lft == INFINITY_LIFE_TIME)
- ifa_flags = IFA_F_PERMANENT;
+ ifa_flags |= IFA_F_PERMANENT;
else if (valid_lft >= 0x7FFFFFFF/HZ)
valid_lft = 0x7FFFFFFF/HZ;
if (prefered_lft == 0)
- ifa_flags = IFA_F_DEPRECATED;
+ ifa_flags |= IFA_F_DEPRECATED;
else if ((prefered_lft >= 0x7FFFFFFF/HZ) &&
(prefered_lft != INFINITY_LIFE_TIME))
prefered_lft = 0x7FFFFFFF/HZ;
spin_lock_bh(&ifp->lock);
- ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED|IFA_F_PERMANENT)) | ifa_flags;
-
+ ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags;
ifp->tstamp = jiffies;
ifp->valid_lft = valid_lft;
ifp->prefered_lft = prefered_lft;
@@ -2936,7 +2976,6 @@ inet6_addr_modify(int ifindex, struct in6_addr *pfx,
spin_unlock_bh(&ifp->lock);
if (!(ifp->flags&IFA_F_TENTATIVE))
ipv6_ifa_notify(0, ifp);
- in6_ifa_put(ifp);
addrconf_verify(0);
@@ -2946,172 +2985,189 @@ inet6_addr_modify(int ifindex, struct in6_addr *pfx,
static int
inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
- struct rtattr **rta = arg;
- struct ifaddrmsg *ifm = NLMSG_DATA(nlh);
+ struct ifaddrmsg *ifm;
+ struct nlattr *tb[IFA_MAX+1];
struct in6_addr *pfx;
- __u32 valid_lft = INFINITY_LIFE_TIME, prefered_lft = INFINITY_LIFE_TIME;
+ struct inet6_ifaddr *ifa;
+ struct net_device *dev;
+ u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME;
+ u8 ifa_flags;
+ int err;
- pfx = NULL;
- if (rta[IFA_ADDRESS-1]) {
- if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*pfx))
- return -EINVAL;
- pfx = RTA_DATA(rta[IFA_ADDRESS-1]);
- }
- if (rta[IFA_LOCAL-1]) {
- if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*pfx) ||
- (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx))))
- return -EINVAL;
- pfx = RTA_DATA(rta[IFA_LOCAL-1]);
- }
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
+ if (err < 0)
+ return err;
+
+ ifm = nlmsg_data(nlh);
+ pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
if (pfx == NULL)
return -EINVAL;
- if (rta[IFA_CACHEINFO-1]) {
+ if (tb[IFA_CACHEINFO]) {
struct ifa_cacheinfo *ci;
- if (RTA_PAYLOAD(rta[IFA_CACHEINFO-1]) < sizeof(*ci))
- return -EINVAL;
- ci = RTA_DATA(rta[IFA_CACHEINFO-1]);
+
+ ci = nla_data(tb[IFA_CACHEINFO]);
valid_lft = ci->ifa_valid;
- prefered_lft = ci->ifa_prefered;
+ preferred_lft = ci->ifa_prefered;
+ } else {
+ preferred_lft = INFINITY_LIFE_TIME;
+ valid_lft = INFINITY_LIFE_TIME;
}
- if (nlh->nlmsg_flags & NLM_F_REPLACE) {
- int ret;
- ret = inet6_addr_modify(ifm->ifa_index, pfx,
- prefered_lft, valid_lft);
- if (ret == 0 || !(nlh->nlmsg_flags & NLM_F_CREATE))
- return ret;
+ dev = __dev_get_by_index(ifm->ifa_index);
+ if (dev == NULL)
+ return -ENODEV;
+
+ /* We ignore other flags so far. */
+ ifa_flags = ifm->ifa_flags & (IFA_F_NODAD | IFA_F_HOMEADDRESS);
+
+ ifa = ipv6_get_ifaddr(pfx, dev, 1);
+ if (ifa == NULL) {
+ /*
+ * It would be best to check for !NLM_F_CREATE here but
+ * userspace alreay relies on not having to provide this.
+ */
+ return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen,
+ ifa_flags, preferred_lft, valid_lft);
}
- return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen,
- prefered_lft, valid_lft);
+ if (nlh->nlmsg_flags & NLM_F_EXCL ||
+ !(nlh->nlmsg_flags & NLM_F_REPLACE))
+ err = -EEXIST;
+ else
+ err = inet6_addr_modify(ifa, ifa_flags, preferred_lft, valid_lft);
+
+ in6_ifa_put(ifa);
+
+ return err;
+}
+
+static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u8 flags,
+ u8 scope, int ifindex)
+{
+ struct ifaddrmsg *ifm;
+ ifm = nlmsg_data(nlh);
+ ifm->ifa_family = AF_INET6;
+ ifm->ifa_prefixlen = prefixlen;
+ ifm->ifa_flags = flags;
+ ifm->ifa_scope = scope;
+ ifm->ifa_index = ifindex;
}
-/* Maximum length of ifa_cacheinfo attributes */
-#define INET6_IFADDR_RTA_SPACE \
- RTA_SPACE(16) /* IFA_ADDRESS */ + \
- RTA_SPACE(sizeof(struct ifa_cacheinfo)) /* CACHEINFO */
+static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp,
+ unsigned long tstamp, u32 preferred, u32 valid)
+{
+ struct ifa_cacheinfo ci;
+
+ ci.cstamp = (u32)(TIME_DELTA(cstamp, INITIAL_JIFFIES) / HZ * 100
+ + TIME_DELTA(cstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
+ ci.tstamp = (u32)(TIME_DELTA(tstamp, INITIAL_JIFFIES) / HZ * 100
+ + TIME_DELTA(tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
+ ci.ifa_prefered = preferred;
+ ci.ifa_valid = valid;
+
+ return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci);
+}
+
+static inline int rt_scope(int ifa_scope)
+{
+ if (ifa_scope & IFA_HOST)
+ return RT_SCOPE_HOST;
+ else if (ifa_scope & IFA_LINK)
+ return RT_SCOPE_LINK;
+ else if (ifa_scope & IFA_SITE)
+ return RT_SCOPE_SITE;
+ else
+ return RT_SCOPE_UNIVERSE;
+}
+
+static inline int inet6_ifaddr_msgsize(void)
+{
+ return nlmsg_total_size(sizeof(struct ifaddrmsg) +
+ nla_total_size(16) +
+ nla_total_size(sizeof(struct ifa_cacheinfo)) +
+ 128);
+}
static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
u32 pid, u32 seq, int event, unsigned int flags)
{
- struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
- struct ifa_cacheinfo ci;
- unsigned char *b = skb->tail;
+ u32 preferred, valid;
+
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags);
+ if (nlh == NULL)
+ return -ENOBUFS;
+
+ put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope),
+ ifa->idev->dev->ifindex);
- nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags);
- ifm = NLMSG_DATA(nlh);
- ifm->ifa_family = AF_INET6;
- ifm->ifa_prefixlen = ifa->prefix_len;
- ifm->ifa_flags = ifa->flags;
- ifm->ifa_scope = RT_SCOPE_UNIVERSE;
- if (ifa->scope&IFA_HOST)
- ifm->ifa_scope = RT_SCOPE_HOST;
- else if (ifa->scope&IFA_LINK)
- ifm->ifa_scope = RT_SCOPE_LINK;
- else if (ifa->scope&IFA_SITE)
- ifm->ifa_scope = RT_SCOPE_SITE;
- ifm->ifa_index = ifa->idev->dev->ifindex;
- RTA_PUT(skb, IFA_ADDRESS, 16, &ifa->addr);
if (!(ifa->flags&IFA_F_PERMANENT)) {
- ci.ifa_prefered = ifa->prefered_lft;
- ci.ifa_valid = ifa->valid_lft;
- if (ci.ifa_prefered != INFINITY_LIFE_TIME) {
+ preferred = ifa->prefered_lft;
+ valid = ifa->valid_lft;
+ if (preferred != INFINITY_LIFE_TIME) {
long tval = (jiffies - ifa->tstamp)/HZ;
- ci.ifa_prefered -= tval;
- if (ci.ifa_valid != INFINITY_LIFE_TIME)
- ci.ifa_valid -= tval;
+ preferred -= tval;
+ if (valid != INFINITY_LIFE_TIME)
+ valid -= tval;
}
} else {
- ci.ifa_prefered = INFINITY_LIFE_TIME;
- ci.ifa_valid = INFINITY_LIFE_TIME;
- }
- ci.cstamp = (__u32)(TIME_DELTA(ifa->cstamp, INITIAL_JIFFIES) / HZ * 100
- + TIME_DELTA(ifa->cstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
- ci.tstamp = (__u32)(TIME_DELTA(ifa->tstamp, INITIAL_JIFFIES) / HZ * 100
- + TIME_DELTA(ifa->tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ);
- RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci);
- nlh->nlmsg_len = skb->tail - b;
- return skb->len;
+ preferred = INFINITY_LIFE_TIME;
+ valid = INFINITY_LIFE_TIME;
+ }
-nlmsg_failure:
-rtattr_failure:
- skb_trim(skb, b - skb->data);
- return -1;
+ if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0 ||
+ put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0)
+ return nlmsg_cancel(skb, nlh);
+
+ return nlmsg_end(skb, nlh);
}
static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
u32 pid, u32 seq, int event, u16 flags)
{
- struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
- struct ifa_cacheinfo ci;
- unsigned char *b = skb->tail;
-
- nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags);
- ifm = NLMSG_DATA(nlh);
- ifm->ifa_family = AF_INET6;
- ifm->ifa_prefixlen = 128;
- ifm->ifa_flags = IFA_F_PERMANENT;
- ifm->ifa_scope = RT_SCOPE_UNIVERSE;
- if (ipv6_addr_scope(&ifmca->mca_addr)&IFA_SITE)
- ifm->ifa_scope = RT_SCOPE_SITE;
- ifm->ifa_index = ifmca->idev->dev->ifindex;
- RTA_PUT(skb, IFA_MULTICAST, 16, &ifmca->mca_addr);
- ci.cstamp = (__u32)(TIME_DELTA(ifmca->mca_cstamp, INITIAL_JIFFIES) / HZ
- * 100 + TIME_DELTA(ifmca->mca_cstamp, INITIAL_JIFFIES) % HZ
- * 100 / HZ);
- ci.tstamp = (__u32)(TIME_DELTA(ifmca->mca_tstamp, INITIAL_JIFFIES) / HZ
- * 100 + TIME_DELTA(ifmca->mca_tstamp, INITIAL_JIFFIES) % HZ
- * 100 / HZ);
- ci.ifa_prefered = INFINITY_LIFE_TIME;
- ci.ifa_valid = INFINITY_LIFE_TIME;
- RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci);
- nlh->nlmsg_len = skb->tail - b;
- return skb->len;
+ u8 scope = RT_SCOPE_UNIVERSE;
+ int ifindex = ifmca->idev->dev->ifindex;
-nlmsg_failure:
-rtattr_failure:
- skb_trim(skb, b - skb->data);
- return -1;
+ if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE)
+ scope = RT_SCOPE_SITE;
+
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags);
+ if (nlh == NULL)
+ return -ENOBUFS;
+
+ put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
+ if (nla_put(skb, IFA_MULTICAST, 16, &ifmca->mca_addr) < 0 ||
+ put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp,
+ INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0)
+ return nlmsg_cancel(skb, nlh);
+
+ return nlmsg_end(skb, nlh);
}
static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
u32 pid, u32 seq, int event, unsigned int flags)
{
- struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
- struct ifa_cacheinfo ci;
- unsigned char *b = skb->tail;
-
- nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags);
- ifm = NLMSG_DATA(nlh);
- ifm->ifa_family = AF_INET6;
- ifm->ifa_prefixlen = 128;
- ifm->ifa_flags = IFA_F_PERMANENT;
- ifm->ifa_scope = RT_SCOPE_UNIVERSE;
- if (ipv6_addr_scope(&ifaca->aca_addr)&IFA_SITE)
- ifm->ifa_scope = RT_SCOPE_SITE;
- ifm->ifa_index = ifaca->aca_idev->dev->ifindex;
- RTA_PUT(skb, IFA_ANYCAST, 16, &ifaca->aca_addr);
- ci.cstamp = (__u32)(TIME_DELTA(ifaca->aca_cstamp, INITIAL_JIFFIES) / HZ
- * 100 + TIME_DELTA(ifaca->aca_cstamp, INITIAL_JIFFIES) % HZ
- * 100 / HZ);
- ci.tstamp = (__u32)(TIME_DELTA(ifaca->aca_tstamp, INITIAL_JIFFIES) / HZ
- * 100 + TIME_DELTA(ifaca->aca_tstamp, INITIAL_JIFFIES) % HZ
- * 100 / HZ);
- ci.ifa_prefered = INFINITY_LIFE_TIME;
- ci.ifa_valid = INFINITY_LIFE_TIME;
- RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci);
- nlh->nlmsg_len = skb->tail - b;
- return skb->len;
+ u8 scope = RT_SCOPE_UNIVERSE;
+ int ifindex = ifaca->aca_idev->dev->ifindex;
-nlmsg_failure:
-rtattr_failure:
- skb_trim(skb, b - skb->data);
- return -1;
+ if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE)
+ scope = RT_SCOPE_SITE;
+
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags);
+ if (nlh == NULL)
+ return -ENOBUFS;
+
+ put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
+ if (nla_put(skb, IFA_ANYCAST, 16, &ifaca->aca_addr) < 0 ||
+ put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp,
+ INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0)
+ return nlmsg_cancel(skb, nlh);
+
+ return nlmsg_end(skb, nlh);
}
enum addr_type_t
@@ -3222,79 +3278,74 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
return inet6_dump_addr(skb, cb, type);
}
-static int inet6_rtm_getaddr(struct sk_buff *in_skb,
- struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh,
+ void *arg)
{
- struct rtattr **rta = arg;
- struct ifaddrmsg *ifm = NLMSG_DATA(nlh);
+ struct ifaddrmsg *ifm;
+ struct nlattr *tb[IFA_MAX+1];
struct in6_addr *addr = NULL;
struct net_device *dev = NULL;
struct inet6_ifaddr *ifa;
struct sk_buff *skb;
- int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + INET6_IFADDR_RTA_SPACE);
int err;
- if (rta[IFA_ADDRESS-1]) {
- if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*addr))
- return -EINVAL;
- addr = RTA_DATA(rta[IFA_ADDRESS-1]);
- }
- if (rta[IFA_LOCAL-1]) {
- if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*addr) ||
- (addr && memcmp(addr, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*addr))))
- return -EINVAL;
- addr = RTA_DATA(rta[IFA_LOCAL-1]);
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
+ if (err < 0)
+ goto errout;
+
+ addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+ if (addr == NULL) {
+ err = -EINVAL;
+ goto errout;
}
- if (addr == NULL)
- return -EINVAL;
+ ifm = nlmsg_data(nlh);
if (ifm->ifa_index)
dev = __dev_get_by_index(ifm->ifa_index);
- if ((ifa = ipv6_get_ifaddr(addr, dev, 1)) == NULL)
- return -EADDRNOTAVAIL;
+ if ((ifa = ipv6_get_ifaddr(addr, dev, 1)) == NULL) {
+ err = -EADDRNOTAVAIL;
+ goto errout;
+ }
- if ((skb = alloc_skb(size, GFP_KERNEL)) == NULL) {
+ if ((skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL)) == NULL) {
err = -ENOBUFS;
- goto out;
+ goto errout_ifa;
}
- NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;
err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid,
nlh->nlmsg_seq, RTM_NEWADDR, 0);
if (err < 0) {
- err = -EMSGSIZE;
- goto out_free;
+ kfree_skb(skb);
+ goto errout_ifa;
}
- err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
- if (err > 0)
- err = 0;
-out:
+ err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid);
+errout_ifa:
in6_ifa_put(ifa);
+errout:
return err;
-out_free:
- kfree_skb(skb);
- goto out;
}
static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
{
struct sk_buff *skb;
- int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + INET6_IFADDR_RTA_SPACE);
+ int err = -ENOBUFS;
- skb = alloc_skb(size, GFP_ATOMIC);
- if (!skb) {
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, ENOBUFS);
- return;
- }
- if (inet6_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) {
+ skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0);
+ if (err < 0) {
kfree_skb(skb);
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, EINVAL);
- return;
+ goto errout;
}
- NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFADDR;
- netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFADDR, GFP_ATOMIC);
+
+ err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err);
}
static void inline ipv6_store_devconf(struct ipv6_devconf *cnf,
@@ -3329,6 +3380,7 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
#endif
#endif
+ array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
}
/* Maximum length of ifinfomsg attributes */
@@ -3435,20 +3487,23 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
{
struct sk_buff *skb;
- int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + INET6_IFINFO_RTA_SPACE);
+ int payload = sizeof(struct ifinfomsg) + INET6_IFINFO_RTA_SPACE;
+ int err = -ENOBUFS;
- skb = alloc_skb(size, GFP_ATOMIC);
- if (!skb) {
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, ENOBUFS);
- return;
- }
- if (inet6_fill_ifinfo(skb, idev, current->pid, 0, event, 0) < 0) {
+ skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0);
+ if (err < 0) {
kfree_skb(skb);
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, EINVAL);
- return;
+ goto errout;
}
- NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFINFO;
- netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFINFO, GFP_ATOMIC);
+
+ err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err);
}
/* Maximum length of prefix_cacheinfo attributes */
@@ -3500,20 +3555,23 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
struct prefix_info *pinfo)
{
struct sk_buff *skb;
- int size = NLMSG_SPACE(sizeof(struct prefixmsg) + INET6_PREFIX_RTA_SPACE);
+ int payload = sizeof(struct prefixmsg) + INET6_PREFIX_RTA_SPACE;
+ int err = -ENOBUFS;
- skb = alloc_skb(size, GFP_ATOMIC);
- if (!skb) {
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, ENOBUFS);
- return;
- }
- if (inet6_fill_prefix(skb, idev, pinfo, current->pid, 0, event, 0) < 0) {
+ skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC);
+ if (skb == NULL)
+ goto errout;
+
+ err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0);
+ if (err < 0) {
kfree_skb(skb);
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, EINVAL);
- return;
+ goto errout;
}
- NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_PREFIX;
- netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_PREFIX, GFP_ATOMIC);
+
+ err = rtnl_notify(skb, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC);
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(RTNLGRP_IPV6_PREFIX, err);
}
static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = {
@@ -3528,6 +3586,9 @@ static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = {
[RTM_DELROUTE - RTM_BASE] = { .doit = inet6_rtm_delroute, },
[RTM_GETROUTE - RTM_BASE] = { .doit = inet6_rtm_getroute,
.dumpit = inet6_dump_fib, },
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ [RTM_GETRULE - RTM_BASE] = { .dumpit = fib6_rules_dump, },
+#endif
};
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
@@ -3536,7 +3597,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
switch (event) {
case RTM_NEWADDR:
- ip6_ins_rt(ifp->rt, NULL, NULL, NULL);
+ ip6_ins_rt(ifp->rt);
if (ifp->idev->cnf.forwarding)
addrconf_join_anycast(ifp);
break;
@@ -3545,7 +3606,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
addrconf_leave_anycast(ifp);
addrconf_leave_solict(ifp->idev, &ifp->addr);
dst_hold(&ifp->rt->u.dst);
- if (ip6_del_rt(ifp->rt, NULL, NULL, NULL))
+ if (ip6_del_rt(ifp->rt))
dst_free(&ifp->rt->u.dst);
break;
}
@@ -3553,10 +3614,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
{
- read_lock_bh(&addrconf_lock);
+ rcu_read_lock_bh();
if (likely(ifp->idev->dead == 0))
__ipv6_ifa_notify(event, ifp);
- read_unlock_bh(&addrconf_lock);
+ rcu_read_unlock_bh();
}
#ifdef CONFIG_SYSCTL
@@ -3653,7 +3714,7 @@ static struct addrconf_sysctl_table
ctl_table addrconf_conf_dir[2];
ctl_table addrconf_proto_dir[2];
ctl_table addrconf_root_dir[2];
-} addrconf_sysctl = {
+} addrconf_sysctl __read_mostly = {
.sysctl_header = NULL,
.addrconf_vars = {
{
@@ -3843,6 +3904,14 @@ static struct addrconf_sysctl_table
#endif
#endif
{
+ .ctl_name = NET_IPV6_PROXY_NDP,
+ .procname = "proxy_ndp",
+ .data = &ipv6_devconf.proxy_ndp,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
.ctl_name = 0, /* sentinel */
}
},
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ac85e9c532c..bf6e8aff19d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -59,6 +59,9 @@
#ifdef CONFIG_IPV6_TUNNEL
#include <net/ip6_tunnel.h>
#endif
+#ifdef CONFIG_IPV6_MIP6
+#include <net/mip6.h>
+#endif
#include <asm/uaccess.h>
#include <asm/system.h>
@@ -67,7 +70,7 @@ MODULE_AUTHOR("Cast of dozens");
MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
MODULE_LICENSE("GPL");
-int sysctl_ipv6_bindv6only;
+int sysctl_ipv6_bindv6only __read_mostly;
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
@@ -637,6 +640,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
+ security_sk_classify_flow(sk, &fl);
if (np->opt && np->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
@@ -658,7 +662,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
return err;
}
- __ip6_dst_store(sk, dst, NULL);
+ __ip6_dst_store(sk, dst, NULL, NULL);
}
return 0;
@@ -757,6 +761,8 @@ static int __init inet6_init(void)
struct list_head *r;
int err;
+ BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb));
+
#ifdef MODULE
#if 0 /* FIXME --RR */
if (!mod_member_present(&__this_module, can_unload))
@@ -766,11 +772,6 @@ static int __init inet6_init(void)
#endif
#endif
- if (sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)) {
- printk(KERN_CRIT "inet6_proto_init: size fault\n");
- return -EINVAL;
- }
-
err = proto_register(&tcpv6_prot, 1);
if (err)
goto out;
@@ -856,6 +857,9 @@ static int __init inet6_init(void)
ipv6_frag_init();
ipv6_nodata_init();
ipv6_destopt_init();
+#ifdef CONFIG_IPV6_MIP6
+ mip6_init();
+#endif
/* Init v6 transport protocols. */
udpv6_init();
@@ -919,6 +923,9 @@ static void __exit inet6_exit(void)
tcp6_proc_exit();
raw6_proc_exit();
#endif
+#ifdef CONFIG_IPV6_MIP6
+ mip6_fini();
+#endif
/* Cleanup code parts. */
sit_cleanup();
ip6_flowlabel_cleanup();
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 9d4831bd433..b0d83e8e425 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -74,6 +74,66 @@ bad:
return 0;
}
+#ifdef CONFIG_IPV6_MIP6
+/**
+ * ipv6_rearrange_destopt - rearrange IPv6 destination options header
+ * @iph: IPv6 header
+ * @destopt: destionation options header
+ */
+static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *destopt)
+{
+ u8 *opt = (u8 *)destopt;
+ int len = ipv6_optlen(destopt);
+ int off = 0;
+ int optlen = 0;
+
+ off += 2;
+ len -= 2;
+
+ while (len > 0) {
+
+ switch (opt[off]) {
+
+ case IPV6_TLV_PAD0:
+ optlen = 1;
+ break;
+ default:
+ if (len < 2)
+ goto bad;
+ optlen = opt[off+1]+2;
+ if (len < optlen)
+ goto bad;
+
+ /* Rearrange the source address in @iph and the
+ * addresses in home address option for final source.
+ * See 11.3.2 of RFC 3775 for details.
+ */
+ if (opt[off] == IPV6_TLV_HAO) {
+ struct in6_addr final_addr;
+ struct ipv6_destopt_hao *hao;
+
+ hao = (struct ipv6_destopt_hao *)&opt[off];
+ if (hao->length != sizeof(hao->addr)) {
+ if (net_ratelimit())
+ printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length);
+ goto bad;
+ }
+ ipv6_addr_copy(&final_addr, &hao->addr);
+ ipv6_addr_copy(&hao->addr, &iph->saddr);
+ ipv6_addr_copy(&iph->saddr, &final_addr);
+ }
+ break;
+ }
+
+ off += optlen;
+ len -= optlen;
+ }
+ /* Note: ok if len == 0 */
+bad:
+ return;
+}
+#endif
+
/**
* ipv6_rearrange_rthdr - rearrange IPv6 routing header
* @iph: IPv6 header
@@ -113,7 +173,7 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr)
ipv6_addr_copy(&iph->daddr, &final_addr);
}
-static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len)
+static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
{
union {
struct ipv6hdr *iph;
@@ -128,8 +188,12 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len)
while (exthdr.raw < end) {
switch (nexthdr) {
- case NEXTHDR_HOP:
case NEXTHDR_DEST:
+#ifdef CONFIG_IPV6_MIP6
+ if (dir == XFRM_POLICY_OUT)
+ ipv6_rearrange_destopt(iph, exthdr.opth);
+#endif
+ case NEXTHDR_HOP:
if (!zero_out_mutable_opts(exthdr.opth)) {
LIMIT_NETDEBUG(
KERN_WARNING "overrun %sopts\n",
@@ -164,6 +228,9 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
u8 nexthdr;
char tmp_base[8];
struct {
+#ifdef CONFIG_IPV6_MIP6
+ struct in6_addr saddr;
+#endif
struct in6_addr daddr;
char hdrs[0];
} *tmp_ext;
@@ -188,10 +255,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
err = -ENOMEM;
goto error;
}
+#ifdef CONFIG_IPV6_MIP6
+ memcpy(tmp_ext, &top_iph->saddr, extlen);
+#else
memcpy(tmp_ext, &top_iph->daddr, extlen);
+#endif
err = ipv6_clear_mutable_options(top_iph,
extlen - sizeof(*tmp_ext) +
- sizeof(*top_iph));
+ sizeof(*top_iph),
+ XFRM_POLICY_OUT);
if (err)
goto error_free_iph;
}
@@ -213,13 +285,20 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
ah->spi = x->id.spi;
ah->seq_no = htonl(++x->replay.oseq);
xfrm_aevent_doreplay(x);
- ahp->icv(ahp, skb, ah->auth_data);
+ err = ah_mac_digest(ahp, skb, ah->auth_data);
+ if (err)
+ goto error_free_iph;
+ memcpy(ah->auth_data, ahp->work_icv, ahp->icv_trunc_len);
err = 0;
memcpy(top_iph, tmp_base, sizeof(tmp_base));
if (tmp_ext) {
+#ifdef CONFIG_IPV6_MIP6
+ memcpy(&top_iph->saddr, tmp_ext, extlen);
+#else
memcpy(&top_iph->daddr, tmp_ext, extlen);
+#endif
error_free_iph:
kfree(tmp_ext);
}
@@ -251,6 +330,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
u16 hdr_len;
u16 ah_hlen;
int nexthdr;
+ int err = -EINVAL;
if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr)))
goto out;
@@ -278,7 +358,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
if (!tmp_hdr)
goto out;
memcpy(tmp_hdr, skb->nh.raw, hdr_len);
- if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len))
+ if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len, XFRM_POLICY_IN))
goto free_out;
skb->nh.ipv6h->priority = 0;
skb->nh.ipv6h->flow_lbl[0] = 0;
@@ -292,8 +372,11 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
memset(ah->auth_data, 0, ahp->icv_trunc_len);
skb_push(skb, hdr_len);
- ahp->icv(ahp, skb, ah->auth_data);
- if (memcmp(ah->auth_data, auth_data, ahp->icv_trunc_len)) {
+ err = ah_mac_digest(ahp, skb, ah->auth_data);
+ if (err)
+ goto free_out;
+ err = -EINVAL;
+ if (memcmp(ahp->work_icv, auth_data, ahp->icv_trunc_len)) {
LIMIT_NETDEBUG(KERN_WARNING "ipsec ah authentication error\n");
x->stats.integrity_failed++;
goto free_out;
@@ -310,7 +393,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
free_out:
kfree(tmp_hdr);
out:
- return -EINVAL;
+ return err;
}
static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
@@ -338,6 +421,7 @@ static int ah6_init_state(struct xfrm_state *x)
{
struct ah_data *ahp = NULL;
struct xfrm_algo_desc *aalg_desc;
+ struct crypto_hash *tfm;
if (!x->aalg)
goto error;
@@ -355,24 +439,27 @@ static int ah6_init_state(struct xfrm_state *x)
ahp->key = x->aalg->alg_key;
ahp->key_len = (x->aalg->alg_key_len+7)/8;
- ahp->tfm = crypto_alloc_tfm(x->aalg->alg_name, 0);
- if (!ahp->tfm)
+ tfm = crypto_alloc_hash(x->aalg->alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm))
+ goto error;
+
+ ahp->tfm = tfm;
+ if (crypto_hash_setkey(tfm, ahp->key, ahp->key_len))
goto error;
- ahp->icv = ah_hmac_digest;
/*
* Lookup the algorithm description maintained by xfrm_algo,
* verify crypto transform properties, and store information
* we need for AH processing. This lookup cannot fail here
- * after a successful crypto_alloc_tfm().
+ * after a successful crypto_alloc_hash().
*/
aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
BUG_ON(!aalg_desc);
if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
- crypto_tfm_alg_digestsize(ahp->tfm)) {
+ crypto_hash_digestsize(tfm)) {
printk(KERN_INFO "AH: %s digestsize %u != %hu\n",
- x->aalg->alg_name, crypto_tfm_alg_digestsize(ahp->tfm),
+ x->aalg->alg_name, crypto_hash_digestsize(tfm),
aalg_desc->uinfo.auth.icv_fullbits/8);
goto error;
}
@@ -387,7 +474,7 @@ static int ah6_init_state(struct xfrm_state *x)
goto error;
x->props.header_len = XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_trunc_len);
- if (x->props.mode)
+ if (x->props.mode == XFRM_MODE_TUNNEL)
x->props.header_len += sizeof(struct ipv6hdr);
x->data = ahp;
@@ -396,7 +483,7 @@ static int ah6_init_state(struct xfrm_state *x)
error:
if (ahp) {
kfree(ahp->work_icv);
- crypto_free_tfm(ahp->tfm);
+ crypto_free_hash(ahp->tfm);
kfree(ahp);
}
return -EINVAL;
@@ -411,7 +498,7 @@ static void ah6_destroy(struct xfrm_state *x)
kfree(ahp->work_icv);
ahp->work_icv = NULL;
- crypto_free_tfm(ahp->tfm);
+ crypto_free_hash(ahp->tfm);
ahp->tfm = NULL;
kfree(ahp);
}
@@ -424,7 +511,8 @@ static struct xfrm_type ah6_type =
.init_state = ah6_init_state,
.destructor = ah6_destroy,
.input = ah6_input,
- .output = ah6_output
+ .output = ah6_output,
+ .hdr_offset = xfrm6_find_1stfragopt,
};
static struct inet6_protocol ah6_protocol = {
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index f6881d7a038..a9604764e01 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -56,7 +56,7 @@ ip6_onlink(struct in6_addr *addr, struct net_device *dev)
int onlink;
onlink = 0;
- read_lock(&addrconf_lock);
+ rcu_read_lock();
idev = __in6_dev_get(dev);
if (idev) {
read_lock_bh(&idev->lock);
@@ -68,7 +68,7 @@ ip6_onlink(struct in6_addr *addr, struct net_device *dev)
}
read_unlock_bh(&idev->lock);
}
- read_unlock(&addrconf_lock);
+ rcu_read_unlock();
return onlink;
}
@@ -335,7 +335,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr)
write_unlock_bh(&idev->lock);
dst_hold(&rt->u.dst);
- if (ip6_ins_rt(rt, NULL, NULL, NULL))
+ if (ip6_ins_rt(rt))
dst_release(&rt->u.dst);
addrconf_join_solict(dev, &aca->aca_addr);
@@ -378,7 +378,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr)
addrconf_leave_solict(idev, &aca->aca_addr);
dst_hold(&aca->aca_rt->u.dst);
- if (ip6_del_rt(aca->aca_rt, NULL, NULL, NULL))
+ if (ip6_del_rt(aca->aca_rt))
dst_free(&aca->aca_rt->u.dst);
else
dst_release(&aca->aca_rt->u.dst);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 3b55b4c8e2d..7206747022f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -156,6 +156,8 @@ ipv4_connected:
if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST))
fl.oif = np->mcast_oif;
+ security_sk_classify_flow(sk, &fl);
+
if (flowlabel) {
if (flowlabel->opt && flowlabel->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt;
@@ -191,7 +193,12 @@ ipv4_connected:
ip6_dst_store(sk, dst,
ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
- &np->daddr : NULL);
+ &np->daddr : NULL,
+#ifdef CONFIG_IPV6_SUBTREES
+ ipv6_addr_equal(&fl.fl6_src, &np->saddr) ?
+ &np->saddr :
+#endif
+ NULL);
sk->sk_state = TCP_ESTABLISHED;
out:
@@ -641,10 +648,13 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl,
rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg);
- /*
- * TYPE 0
- */
- if (rthdr->type) {
+ switch (rthdr->type) {
+ case IPV6_SRCRT_TYPE_0:
+#ifdef CONFIG_IPV6_MIP6
+ case IPV6_SRCRT_TYPE_2:
+#endif
+ break;
+ default:
err = -EINVAL;
goto exit_f;
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index a278d5e862f..e78680a9985 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -24,6 +24,7 @@
* This file is derived from net/ipv4/esp.c
*/
+#include <linux/err.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/xfrm.h>
@@ -44,7 +45,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
int hdr_len;
struct ipv6hdr *top_iph;
struct ipv6_esp_hdr *esph;
- struct crypto_tfm *tfm;
+ struct crypto_blkcipher *tfm;
+ struct blkcipher_desc desc;
struct esp_data *esp;
struct sk_buff *trailer;
int blksize;
@@ -67,7 +69,9 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
alen = esp->auth.icv_trunc_len;
tfm = esp->conf.tfm;
- blksize = ALIGN(crypto_tfm_alg_blocksize(tfm), 4);
+ desc.tfm = tfm;
+ desc.flags = 0;
+ blksize = ALIGN(crypto_blkcipher_blocksize(tfm), 4);
clen = ALIGN(clen + 2, blksize);
if (esp->conf.padlen)
clen = ALIGN(clen, esp->conf.padlen);
@@ -95,8 +99,13 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
esph->seq_no = htonl(++x->replay.oseq);
xfrm_aevent_doreplay(x);
- if (esp->conf.ivlen)
- crypto_cipher_set_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
+ if (esp->conf.ivlen) {
+ if (unlikely(!esp->conf.ivinitted)) {
+ get_random_bytes(esp->conf.ivec, esp->conf.ivlen);
+ esp->conf.ivinitted = 1;
+ }
+ crypto_blkcipher_set_iv(tfm, esp->conf.ivec, esp->conf.ivlen);
+ }
do {
struct scatterlist *sg = &esp->sgbuf[0];
@@ -107,24 +116,25 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
goto error;
}
skb_to_sgvec(skb, sg, esph->enc_data+esp->conf.ivlen-skb->data, clen);
- crypto_cipher_encrypt(tfm, sg, sg, clen);
+ err = crypto_blkcipher_encrypt(&desc, sg, sg, clen);
if (unlikely(sg != &esp->sgbuf[0]))
kfree(sg);
} while (0);
+ if (unlikely(err))
+ goto error;
+
if (esp->conf.ivlen) {
- memcpy(esph->enc_data, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
- crypto_cipher_get_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm));
+ memcpy(esph->enc_data, esp->conf.ivec, esp->conf.ivlen);
+ crypto_blkcipher_get_iv(tfm, esp->conf.ivec, esp->conf.ivlen);
}
if (esp->auth.icv_full_len) {
- esp->auth.icv(esp, skb, (u8*)esph-skb->data,
- sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen+clen, trailer->tail);
- pskb_put(skb, trailer, alen);
+ err = esp_mac_digest(esp, skb, (u8 *)esph - skb->data,
+ sizeof(*esph) + esp->conf.ivlen + clen);
+ memcpy(pskb_put(skb, trailer, alen), esp->auth.work_icv, alen);
}
- err = 0;
-
error:
return err;
}
@@ -134,8 +144,10 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
struct ipv6hdr *iph;
struct ipv6_esp_hdr *esph;
struct esp_data *esp = x->data;
+ struct crypto_blkcipher *tfm = esp->conf.tfm;
+ struct blkcipher_desc desc = { .tfm = tfm };
struct sk_buff *trailer;
- int blksize = ALIGN(crypto_tfm_alg_blocksize(esp->conf.tfm), 4);
+ int blksize = ALIGN(crypto_blkcipher_blocksize(tfm), 4);
int alen = esp->auth.icv_trunc_len;
int elen = skb->len - sizeof(struct ipv6_esp_hdr) - esp->conf.ivlen - alen;
@@ -155,15 +167,16 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
/* If integrity check is required, do this. */
if (esp->auth.icv_full_len) {
- u8 sum[esp->auth.icv_full_len];
- u8 sum1[alen];
+ u8 sum[alen];
- esp->auth.icv(esp, skb, 0, skb->len-alen, sum);
+ ret = esp_mac_digest(esp, skb, 0, skb->len - alen);
+ if (ret)
+ goto out;
- if (skb_copy_bits(skb, skb->len-alen, sum1, alen))
+ if (skb_copy_bits(skb, skb->len - alen, sum, alen))
BUG();
- if (unlikely(memcmp(sum, sum1, alen))) {
+ if (unlikely(memcmp(esp->auth.work_icv, sum, alen))) {
x->stats.integrity_failed++;
ret = -EINVAL;
goto out;
@@ -182,7 +195,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
/* Get ivec. This can be wrong, check against another impls. */
if (esp->conf.ivlen)
- crypto_cipher_set_iv(esp->conf.tfm, esph->enc_data, crypto_tfm_alg_ivsize(esp->conf.tfm));
+ crypto_blkcipher_set_iv(tfm, esph->enc_data, esp->conf.ivlen);
{
u8 nexthdr[2];
@@ -197,9 +210,11 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
}
}
skb_to_sgvec(skb, sg, sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen, elen);
- crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen);
+ ret = crypto_blkcipher_decrypt(&desc, sg, sg, elen);
if (unlikely(sg != &esp->sgbuf[0]))
kfree(sg);
+ if (unlikely(ret))
+ goto out;
if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
BUG();
@@ -225,9 +240,9 @@ out:
static u32 esp6_get_max_size(struct xfrm_state *x, int mtu)
{
struct esp_data *esp = x->data;
- u32 blksize = ALIGN(crypto_tfm_alg_blocksize(esp->conf.tfm), 4);
+ u32 blksize = ALIGN(crypto_blkcipher_blocksize(esp->conf.tfm), 4);
- if (x->props.mode) {
+ if (x->props.mode == XFRM_MODE_TUNNEL) {
mtu = ALIGN(mtu + 2, blksize);
} else {
/* The worst case. */
@@ -266,11 +281,11 @@ static void esp6_destroy(struct xfrm_state *x)
if (!esp)
return;
- crypto_free_tfm(esp->conf.tfm);
+ crypto_free_blkcipher(esp->conf.tfm);
esp->conf.tfm = NULL;
kfree(esp->conf.ivec);
esp->conf.ivec = NULL;
- crypto_free_tfm(esp->auth.tfm);
+ crypto_free_hash(esp->auth.tfm);
esp->auth.tfm = NULL;
kfree(esp->auth.work_icv);
esp->auth.work_icv = NULL;
@@ -280,6 +295,7 @@ static void esp6_destroy(struct xfrm_state *x)
static int esp6_init_state(struct xfrm_state *x)
{
struct esp_data *esp = NULL;
+ struct crypto_blkcipher *tfm;
/* null auth and encryption can have zero length keys */
if (x->aalg) {
@@ -298,24 +314,29 @@ static int esp6_init_state(struct xfrm_state *x)
if (x->aalg) {
struct xfrm_algo_desc *aalg_desc;
+ struct crypto_hash *hash;
esp->auth.key = x->aalg->alg_key;
esp->auth.key_len = (x->aalg->alg_key_len+7)/8;
- esp->auth.tfm = crypto_alloc_tfm(x->aalg->alg_name, 0);
- if (esp->auth.tfm == NULL)
+ hash = crypto_alloc_hash(x->aalg->alg_name, 0,
+ CRYPTO_ALG_ASYNC);
+ if (IS_ERR(hash))
+ goto error;
+
+ esp->auth.tfm = hash;
+ if (crypto_hash_setkey(hash, esp->auth.key, esp->auth.key_len))
goto error;
- esp->auth.icv = esp_hmac_digest;
aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
BUG_ON(!aalg_desc);
if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
- crypto_tfm_alg_digestsize(esp->auth.tfm)) {
- printk(KERN_INFO "ESP: %s digestsize %u != %hu\n",
- x->aalg->alg_name,
- crypto_tfm_alg_digestsize(esp->auth.tfm),
- aalg_desc->uinfo.auth.icv_fullbits/8);
- goto error;
+ crypto_hash_digestsize(hash)) {
+ NETDEBUG(KERN_INFO "ESP: %s digestsize %u != %hu\n",
+ x->aalg->alg_name,
+ crypto_hash_digestsize(hash),
+ aalg_desc->uinfo.auth.icv_fullbits/8);
+ goto error;
}
esp->auth.icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
@@ -327,24 +348,22 @@ static int esp6_init_state(struct xfrm_state *x)
}
esp->conf.key = x->ealg->alg_key;
esp->conf.key_len = (x->ealg->alg_key_len+7)/8;
- if (x->props.ealgo == SADB_EALG_NULL)
- esp->conf.tfm = crypto_alloc_tfm(x->ealg->alg_name, CRYPTO_TFM_MODE_ECB);
- else
- esp->conf.tfm = crypto_alloc_tfm(x->ealg->alg_name, CRYPTO_TFM_MODE_CBC);
- if (esp->conf.tfm == NULL)
+ tfm = crypto_alloc_blkcipher(x->ealg->alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm))
goto error;
- esp->conf.ivlen = crypto_tfm_alg_ivsize(esp->conf.tfm);
+ esp->conf.tfm = tfm;
+ esp->conf.ivlen = crypto_blkcipher_ivsize(tfm);
esp->conf.padlen = 0;
if (esp->conf.ivlen) {
esp->conf.ivec = kmalloc(esp->conf.ivlen, GFP_KERNEL);
if (unlikely(esp->conf.ivec == NULL))
goto error;
- get_random_bytes(esp->conf.ivec, esp->conf.ivlen);
+ esp->conf.ivinitted = 0;
}
- if (crypto_cipher_setkey(esp->conf.tfm, esp->conf.key, esp->conf.key_len))
+ if (crypto_blkcipher_setkey(tfm, esp->conf.key, esp->conf.key_len))
goto error;
x->props.header_len = sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen;
- if (x->props.mode)
+ if (x->props.mode == XFRM_MODE_TUNNEL)
x->props.header_len += sizeof(struct ipv6hdr);
x->data = esp;
return 0;
@@ -365,7 +384,8 @@ static struct xfrm_type esp6_type =
.destructor = esp6_destroy,
.get_max_size = esp6_get_max_size,
.input = esp6_input,
- .output = esp6_output
+ .output = esp6_output,
+ .hdr_offset = xfrm6_find_1stfragopt,
};
static struct inet6_protocol esp6_protocol = {
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 86dac106873..88c96b10684 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -43,9 +43,54 @@
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
+#ifdef CONFIG_IPV6_MIP6
+#include <net/xfrm.h>
+#endif
#include <asm/uaccess.h>
+int ipv6_find_tlv(struct sk_buff *skb, int offset, int type)
+{
+ int packet_len = skb->tail - skb->nh.raw;
+ struct ipv6_opt_hdr *hdr;
+ int len;
+
+ if (offset + 2 > packet_len)
+ goto bad;
+ hdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
+ len = ((hdr->hdrlen + 1) << 3);
+
+ if (offset + len > packet_len)
+ goto bad;
+
+ offset += 2;
+ len -= 2;
+
+ while (len > 0) {
+ int opttype = skb->nh.raw[offset];
+ int optlen;
+
+ if (opttype == type)
+ return offset;
+
+ switch (opttype) {
+ case IPV6_TLV_PAD0:
+ optlen = 1;
+ break;
+ default:
+ optlen = skb->nh.raw[offset + 1] + 2;
+ if (optlen > len)
+ goto bad;
+ break;
+ }
+ offset += optlen;
+ len -= optlen;
+ }
+ /* not_found */
+ bad:
+ return -1;
+}
+
/*
* Parsing tlv encoded headers.
*
@@ -56,7 +101,7 @@
struct tlvtype_proc {
int type;
- int (*func)(struct sk_buff *skb, int offset);
+ int (*func)(struct sk_buff **skbp, int offset);
};
/*********************
@@ -65,8 +110,10 @@ struct tlvtype_proc {
/* An unknown option is detected, decide what to do */
-static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff)
+static int ip6_tlvopt_unknown(struct sk_buff **skbp, int optoff)
{
+ struct sk_buff *skb = *skbp;
+
switch ((skb->nh.raw[optoff] & 0xC0) >> 6) {
case 0: /* ignore */
return 1;
@@ -91,8 +138,9 @@ static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff)
/* Parse tlv encoded option header (hop-by-hop or destination) */
-static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb)
+static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff **skbp)
{
+ struct sk_buff *skb = *skbp;
struct tlvtype_proc *curr;
int off = skb->h.raw - skb->nh.raw;
int len = ((skb->h.raw[1]+1)<<3);
@@ -122,13 +170,13 @@ static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb)
/* type specific length/alignment
checks will be performed in the
func(). */
- if (curr->func(skb, off) == 0)
+ if (curr->func(skbp, off) == 0)
return 0;
break;
}
}
if (curr->type < 0) {
- if (ip6_tlvopt_unknown(skb, off) == 0)
+ if (ip6_tlvopt_unknown(skbp, off) == 0)
return 0;
}
break;
@@ -147,8 +195,85 @@ bad:
Destination options header.
*****************************/
+#ifdef CONFIG_IPV6_MIP6
+static int ipv6_dest_hao(struct sk_buff **skbp, int optoff)
+{
+ struct sk_buff *skb = *skbp;
+ struct ipv6_destopt_hao *hao;
+ struct inet6_skb_parm *opt = IP6CB(skb);
+ struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->nh.raw;
+ struct in6_addr tmp_addr;
+ int ret;
+
+ if (opt->dsthao) {
+ LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n");
+ goto discard;
+ }
+ opt->dsthao = opt->dst1;
+ opt->dst1 = 0;
+
+ hao = (struct ipv6_destopt_hao *)(skb->nh.raw + optoff);
+
+ if (hao->length != 16) {
+ LIMIT_NETDEBUG(
+ KERN_DEBUG "hao invalid option length = %d\n", hao->length);
+ goto discard;
+ }
+
+ if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
+ LIMIT_NETDEBUG(
+ KERN_DEBUG "hao is not an unicast addr: " NIP6_FMT "\n", NIP6(hao->addr));
+ goto discard;
+ }
+
+ ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr,
+ (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS);
+ if (unlikely(ret < 0))
+ goto discard;
+
+ if (skb_cloned(skb)) {
+ struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC);
+ struct inet6_skb_parm *opt2;
+
+ if (skb2 == NULL)
+ goto discard;
+
+ opt2 = IP6CB(skb2);
+ memcpy(opt2, opt, sizeof(*opt2));
+
+ kfree_skb(skb);
+
+ /* update all variable using below by copied skbuff */
+ *skbp = skb = skb2;
+ hao = (struct ipv6_destopt_hao *)(skb2->nh.raw + optoff);
+ ipv6h = (struct ipv6hdr *)skb2->nh.raw;
+ }
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->ip_summed = CHECKSUM_NONE;
+
+ ipv6_addr_copy(&tmp_addr, &ipv6h->saddr);
+ ipv6_addr_copy(&ipv6h->saddr, &hao->addr);
+ ipv6_addr_copy(&hao->addr, &tmp_addr);
+
+ if (skb->tstamp.off_sec == 0)
+ __net_timestamp(skb);
+
+ return 1;
+
+ discard:
+ kfree_skb(skb);
+ return 0;
+}
+#endif
+
static struct tlvtype_proc tlvprocdestopt_lst[] = {
- /* No destination options are defined now */
+#ifdef CONFIG_IPV6_MIP6
+ {
+ .type = IPV6_TLV_HAO,
+ .func = ipv6_dest_hao,
+ },
+#endif
{-1, NULL}
};
@@ -156,6 +281,9 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp)
{
struct sk_buff *skb = *skbp;
struct inet6_skb_parm *opt = IP6CB(skb);
+#ifdef CONFIG_IPV6_MIP6
+ __u16 dstbuf;
+#endif
if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+8) ||
!pskb_may_pull(skb, (skb->h.raw-skb->data)+((skb->h.raw[1]+1)<<3))) {
@@ -166,10 +294,19 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp)
opt->lastopt = skb->h.raw - skb->nh.raw;
opt->dst1 = skb->h.raw - skb->nh.raw;
+#ifdef CONFIG_IPV6_MIP6
+ dstbuf = opt->dst1;
+#endif
- if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) {
+ if (ip6_parse_tlv(tlvprocdestopt_lst, skbp)) {
+ skb = *skbp;
skb->h.raw += ((skb->h.raw[1]+1)<<3);
+ opt = IP6CB(skb);
+#ifdef CONFIG_IPV6_MIP6
+ opt->nhoff = dstbuf;
+#else
opt->nhoff = opt->dst1;
+#endif
return 1;
}
@@ -219,7 +356,7 @@ static int ipv6_rthdr_rcv(struct sk_buff **skbp)
{
struct sk_buff *skb = *skbp;
struct inet6_skb_parm *opt = IP6CB(skb);
- struct in6_addr *addr;
+ struct in6_addr *addr = NULL;
struct in6_addr daddr;
int n, i;
@@ -244,6 +381,23 @@ static int ipv6_rthdr_rcv(struct sk_buff **skbp)
looped_back:
if (hdr->segments_left == 0) {
+ switch (hdr->type) {
+#ifdef CONFIG_IPV6_MIP6
+ case IPV6_SRCRT_TYPE_2:
+ /* Silently discard type 2 header unless it was
+ * processed by own
+ */
+ if (!addr) {
+ IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
+ kfree_skb(skb);
+ return -1;
+ }
+ break;
+#endif
+ default:
+ break;
+ }
+
opt->lastopt = skb->h.raw - skb->nh.raw;
opt->srcrt = skb->h.raw - skb->nh.raw;
skb->h.raw += (hdr->hdrlen + 1) << 3;
@@ -253,17 +407,29 @@ looped_back:
return 1;
}
- if (hdr->type != IPV6_SRCRT_TYPE_0) {
+ switch (hdr->type) {
+ case IPV6_SRCRT_TYPE_0:
+ if (hdr->hdrlen & 0x01) {
+ IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw);
+ return -1;
+ }
+ break;
+#ifdef CONFIG_IPV6_MIP6
+ case IPV6_SRCRT_TYPE_2:
+ /* Silently discard invalid RTH type 2 */
+ if (hdr->hdrlen != 2 || hdr->segments_left != 1) {
+ IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
+ kfree_skb(skb);
+ return -1;
+ }
+ break;
+#endif
+ default:
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb->nh.raw);
return -1;
}
-
- if (hdr->hdrlen & 0x01) {
- IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw);
- return -1;
- }
/*
* This is the routing header forwarding algorithm from
@@ -294,7 +460,7 @@ looped_back:
hdr = (struct ipv6_rt_hdr *) skb2->h.raw;
}
- if (skb->ip_summed == CHECKSUM_HW)
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
i = n - --hdr->segments_left;
@@ -303,6 +469,27 @@ looped_back:
addr = rthdr->addr;
addr += i - 1;
+ switch (hdr->type) {
+#ifdef CONFIG_IPV6_MIP6
+ case IPV6_SRCRT_TYPE_2:
+ if (xfrm6_input_addr(skb, (xfrm_address_t *)addr,
+ (xfrm_address_t *)&skb->nh.ipv6h->saddr,
+ IPPROTO_ROUTING) < 0) {
+ IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
+ kfree_skb(skb);
+ return -1;
+ }
+ if (!ipv6_chk_home_addr(addr)) {
+ IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
+ kfree_skb(skb);
+ return -1;
+ }
+ break;
+#endif
+ default:
+ break;
+ }
+
if (ipv6_addr_is_multicast(addr)) {
IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
kfree_skb(skb);
@@ -421,8 +608,10 @@ EXPORT_SYMBOL_GPL(ipv6_invert_rthdr);
/* Router Alert as of RFC 2711 */
-static int ipv6_hop_ra(struct sk_buff *skb, int optoff)
+static int ipv6_hop_ra(struct sk_buff **skbp, int optoff)
{
+ struct sk_buff *skb = *skbp;
+
if (skb->nh.raw[optoff+1] == 2) {
IP6CB(skb)->ra = optoff;
return 1;
@@ -435,8 +624,9 @@ static int ipv6_hop_ra(struct sk_buff *skb, int optoff)
/* Jumbo payload */
-static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
+static int ipv6_hop_jumbo(struct sk_buff **skbp, int optoff)
{
+ struct sk_buff *skb = *skbp;
u32 pkt_len;
if (skb->nh.raw[optoff+1] != 4 || (optoff&3) != 2) {
@@ -485,8 +675,9 @@ static struct tlvtype_proc tlvprochopopt_lst[] = {
{ -1, }
};
-int ipv6_parse_hopopts(struct sk_buff *skb)
+int ipv6_parse_hopopts(struct sk_buff **skbp)
{
+ struct sk_buff *skb = *skbp;
struct inet6_skb_parm *opt = IP6CB(skb);
/*
@@ -502,8 +693,10 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
}
opt->hop = sizeof(struct ipv6hdr);
- if (ip6_parse_tlv(tlvprochopopt_lst, skb)) {
+ if (ip6_parse_tlv(tlvprochopopt_lst, skbp)) {
+ skb = *skbp;
skb->h.raw += (skb->h.raw[1]+1)<<3;
+ opt = IP6CB(skb);
opt->nhoff = sizeof(struct ipv6hdr);
return 1;
}
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
new file mode 100644
index 00000000000..34f5bfaddfc
--- /dev/null
+++ b/net/ipv6/fib6_rules.c
@@ -0,0 +1,305 @@
+/*
+ * net/ipv6/fib6_rules.c IPv6 Routing Policy Rules
+ *
+ * Copyright (C)2003-2006 Helsinki University of Technology
+ * Copyright (C)2003-2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2.
+ *
+ * Authors
+ * Thomas Graf <tgraf@suug.ch>
+ * Ville Nuorvala <vnuorval@tcs.hut.fi>
+ */
+
+#include <linux/config.h>
+#include <linux/netdevice.h>
+
+#include <net/fib_rules.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/netlink.h>
+
+struct fib6_rule
+{
+ struct fib_rule common;
+ struct rt6key src;
+ struct rt6key dst;
+#ifdef CONFIG_IPV6_ROUTE_FWMARK
+ u32 fwmark;
+ u32 fwmask;
+#endif
+ u8 tclass;
+};
+
+static struct fib_rules_ops fib6_rules_ops;
+
+static struct fib6_rule main_rule = {
+ .common = {
+ .refcnt = ATOMIC_INIT(2),
+ .pref = 0x7FFE,
+ .action = FR_ACT_TO_TBL,
+ .table = RT6_TABLE_MAIN,
+ },
+};
+
+static struct fib6_rule local_rule = {
+ .common = {
+ .refcnt = ATOMIC_INIT(2),
+ .pref = 0,
+ .action = FR_ACT_TO_TBL,
+ .table = RT6_TABLE_LOCAL,
+ .flags = FIB_RULE_PERMANENT,
+ },
+};
+
+static LIST_HEAD(fib6_rules);
+
+struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
+ pol_lookup_t lookup)
+{
+ struct fib_lookup_arg arg = {
+ .lookup_ptr = lookup,
+ };
+
+ fib_rules_lookup(&fib6_rules_ops, fl, flags, &arg);
+ if (arg.rule)
+ fib_rule_put(arg.rule);
+
+ if (arg.result)
+ return (struct dst_entry *) arg.result;
+
+ dst_hold(&ip6_null_entry.u.dst);
+ return &ip6_null_entry.u.dst;
+}
+
+static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+ int flags, struct fib_lookup_arg *arg)
+{
+ struct rt6_info *rt = NULL;
+ struct fib6_table *table;
+ pol_lookup_t lookup = arg->lookup_ptr;
+
+ switch (rule->action) {
+ case FR_ACT_TO_TBL:
+ break;
+ case FR_ACT_UNREACHABLE:
+ rt = &ip6_null_entry;
+ goto discard_pkt;
+ default:
+ case FR_ACT_BLACKHOLE:
+ rt = &ip6_blk_hole_entry;
+ goto discard_pkt;
+ case FR_ACT_PROHIBIT:
+ rt = &ip6_prohibit_entry;
+ goto discard_pkt;
+ }
+
+ table = fib6_get_table(rule->table);
+ if (table)
+ rt = lookup(table, flp, flags);
+
+ if (rt != &ip6_null_entry)
+ goto out;
+ dst_release(&rt->u.dst);
+ rt = NULL;
+ goto out;
+
+discard_pkt:
+ dst_hold(&rt->u.dst);
+out:
+ arg->result = rt;
+ return rt == NULL ? -EAGAIN : 0;
+}
+
+
+static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
+{
+ struct fib6_rule *r = (struct fib6_rule *) rule;
+
+ if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen))
+ return 0;
+
+ if ((flags & RT6_LOOKUP_F_HAS_SADDR) &&
+ !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen))
+ return 0;
+
+ if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff))
+ return 0;
+
+#ifdef CONFIG_IPV6_ROUTE_FWMARK
+ if ((r->fwmark ^ fl->fl6_fwmark) & r->fwmask)
+ return 0;
+#endif
+
+ return 1;
+}
+
+static struct nla_policy fib6_rule_policy[FRA_MAX+1] __read_mostly = {
+ [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
+ [FRA_PRIORITY] = { .type = NLA_U32 },
+ [FRA_SRC] = { .len = sizeof(struct in6_addr) },
+ [FRA_DST] = { .len = sizeof(struct in6_addr) },
+ [FRA_FWMARK] = { .type = NLA_U32 },
+ [FRA_FWMASK] = { .type = NLA_U32 },
+ [FRA_TABLE] = { .type = NLA_U32 },
+};
+
+static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+ struct nlmsghdr *nlh, struct fib_rule_hdr *frh,
+ struct nlattr **tb)
+{
+ int err = -EINVAL;
+ struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+ if (frh->src_len > 128 || frh->dst_len > 128 ||
+ (frh->tos & ~IPV6_FLOWINFO_MASK))
+ goto errout;
+
+ if (rule->action == FR_ACT_TO_TBL) {
+ if (rule->table == RT6_TABLE_UNSPEC)
+ goto errout;
+
+ if (fib6_new_table(rule->table) == NULL) {
+ err = -ENOBUFS;
+ goto errout;
+ }
+ }
+
+ if (tb[FRA_SRC])
+ nla_memcpy(&rule6->src.addr, tb[FRA_SRC],
+ sizeof(struct in6_addr));
+
+ if (tb[FRA_DST])
+ nla_memcpy(&rule6->dst.addr, tb[FRA_DST],
+ sizeof(struct in6_addr));
+
+#ifdef CONFIG_IPV6_ROUTE_FWMARK
+ if (tb[FRA_FWMARK]) {
+ rule6->fwmark = nla_get_u32(tb[FRA_FWMARK]);
+ if (rule6->fwmark) {
+ /*
+ * if the mark value is non-zero,
+ * all bits are compared by default
+ * unless a mask is explicitly specified.
+ */
+ rule6->fwmask = 0xFFFFFFFF;
+ }
+ }
+
+ if (tb[FRA_FWMASK])
+ rule6->fwmask = nla_get_u32(tb[FRA_FWMASK]);
+#endif
+
+ rule6->src.plen = frh->src_len;
+ rule6->dst.plen = frh->dst_len;
+ rule6->tclass = frh->tos;
+
+ err = 0;
+errout:
+ return err;
+}
+
+static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+ struct nlattr **tb)
+{
+ struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+ if (frh->src_len && (rule6->src.plen != frh->src_len))
+ return 0;
+
+ if (frh->dst_len && (rule6->dst.plen != frh->dst_len))
+ return 0;
+
+ if (frh->tos && (rule6->tclass != frh->tos))
+ return 0;
+
+ if (tb[FRA_SRC] &&
+ nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
+ return 0;
+
+ if (tb[FRA_DST] &&
+ nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr)))
+ return 0;
+
+#ifdef CONFIG_IPV6_ROUTE_FWMARK
+ if (tb[FRA_FWMARK] && (rule6->fwmark != nla_get_u32(tb[FRA_FWMARK])))
+ return 0;
+
+ if (tb[FRA_FWMASK] && (rule6->fwmask != nla_get_u32(tb[FRA_FWMASK])))
+ return 0;
+#endif
+
+ return 1;
+}
+
+static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+ struct nlmsghdr *nlh, struct fib_rule_hdr *frh)
+{
+ struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+ frh->family = AF_INET6;
+ frh->dst_len = rule6->dst.plen;
+ frh->src_len = rule6->src.plen;
+ frh->tos = rule6->tclass;
+
+ if (rule6->dst.plen)
+ NLA_PUT(skb, FRA_DST, sizeof(struct in6_addr),
+ &rule6->dst.addr);
+
+ if (rule6->src.plen)
+ NLA_PUT(skb, FRA_SRC, sizeof(struct in6_addr),
+ &rule6->src.addr);
+
+#ifdef CONFIG_IPV6_ROUTE_FWMARK
+ if (rule6->fwmark)
+ NLA_PUT_U32(skb, FRA_FWMARK, rule6->fwmark);
+
+ if (rule6->fwmask || rule6->fwmark)
+ NLA_PUT_U32(skb, FRA_FWMASK, rule6->fwmask);
+#endif
+
+ return 0;
+
+nla_put_failure:
+ return -ENOBUFS;
+}
+
+int fib6_rules_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ return fib_rules_dump(skb, cb, AF_INET6);
+}
+
+static u32 fib6_rule_default_pref(void)
+{
+ return 0x3FFF;
+}
+
+static struct fib_rules_ops fib6_rules_ops = {
+ .family = AF_INET6,
+ .rule_size = sizeof(struct fib6_rule),
+ .action = fib6_rule_action,
+ .match = fib6_rule_match,
+ .configure = fib6_rule_configure,
+ .compare = fib6_rule_compare,
+ .fill = fib6_rule_fill,
+ .default_pref = fib6_rule_default_pref,
+ .nlgroup = RTNLGRP_IPV6_RULE,
+ .policy = fib6_rule_policy,
+ .rules_list = &fib6_rules,
+ .owner = THIS_MODULE,
+};
+
+void __init fib6_rules_init(void)
+{
+ list_add_tail(&local_rule.common.list, &fib6_rules);
+ list_add_tail(&main_rule.common.list, &fib6_rules);
+
+ fib_rules_register(&fib6_rules_ops);
+}
+
+void fib6_rules_cleanup(void)
+{
+ fib_rules_unregister(&fib6_rules_ops);
+}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 356a8a7ef22..4ec876066b3 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -151,7 +151,7 @@ static int is_ineligible(struct sk_buff *skb)
return 0;
}
-static int sysctl_icmpv6_time = 1*HZ;
+static int sysctl_icmpv6_time __read_mostly = 1*HZ;
/*
* Check the ICMP output rate limit
@@ -273,6 +273,29 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
return 0;
}
+#ifdef CONFIG_IPV6_MIP6
+static void mip6_addr_swap(struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = skb->nh.ipv6h;
+ struct inet6_skb_parm *opt = IP6CB(skb);
+ struct ipv6_destopt_hao *hao;
+ struct in6_addr tmp;
+ int off;
+
+ if (opt->dsthao) {
+ off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
+ if (likely(off >= 0)) {
+ hao = (struct ipv6_destopt_hao *)(skb->nh.raw + off);
+ ipv6_addr_copy(&tmp, &iph->saddr);
+ ipv6_addr_copy(&iph->saddr, &hao->addr);
+ ipv6_addr_copy(&hao->addr, &tmp);
+ }
+ }
+}
+#else
+static inline void mip6_addr_swap(struct sk_buff *skb) {}
+#endif
+
/*
* Send an ICMP message in response to a packet in error
*/
@@ -350,6 +373,8 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
return;
}
+ mip6_addr_swap(skb);
+
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_ICMPV6;
ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
@@ -358,6 +383,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
fl.oif = iif;
fl.fl_icmp_type = type;
fl.fl_icmp_code = code;
+ security_skb_classify_flow(skb, &fl);
if (icmpv6_xmit_lock())
return;
@@ -472,6 +498,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
ipv6_addr_copy(&fl.fl6_src, saddr);
fl.oif = skb->dev->ifindex;
fl.fl_icmp_type = ICMPV6_ECHO_REPLY;
+ security_skb_classify_flow(skb, &fl);
if (icmpv6_xmit_lock())
return;
@@ -604,7 +631,7 @@ static int icmpv6_rcv(struct sk_buff **pskb)
/* Perform checksum. */
switch (skb->ip_summed) {
- case CHECKSUM_HW:
+ case CHECKSUM_COMPLETE:
if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
skb->csum))
break;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index bf491077b82..827f41d1478 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -157,6 +157,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_sport = inet->sport;
fl.fl_ip_dport = inet->dport;
+ security_sk_classify_flow(sk, &fl);
if (np->opt && np->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
@@ -185,7 +186,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok)
return err;
}
- __ip6_dst_store(sk, dst, NULL);
+ __ip6_dst_store(sk, dst, NULL, NULL);
}
skb->dst = dst_clone(dst);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 764221220af..8fcae7a6510 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -18,6 +18,7 @@
* Yuji SEKIYA @USAGI: Support default route on router node;
* remove ip6_null_entry from the top of
* routing table.
+ * Ville Nuorvala: Fixed routing subtrees.
*/
#include <linux/errno.h>
#include <linux/types.h>
@@ -26,6 +27,7 @@
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
+#include <linux/list.h>
#ifdef CONFIG_PROC_FS
#include <linux/proc_fs.h>
@@ -68,19 +70,19 @@ struct fib6_cleaner_t
void *arg;
};
-DEFINE_RWLOCK(fib6_walker_lock);
-
+static DEFINE_RWLOCK(fib6_walker_lock);
#ifdef CONFIG_IPV6_SUBTREES
#define FWS_INIT FWS_S
-#define SUBTREE(fn) ((fn)->subtree)
#else
#define FWS_INIT FWS_L
-#define SUBTREE(fn) NULL
#endif
static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt);
+static struct rt6_info * fib6_find_prefix(struct fib6_node *fn);
static struct fib6_node * fib6_repair_tree(struct fib6_node *fn);
+static int fib6_walk(struct fib6_walker_t *w);
+static int fib6_walk_continue(struct fib6_walker_t *w);
/*
* A routing update causes an increase of the serial number on the
@@ -93,13 +95,31 @@ static __u32 rt_sernum;
static DEFINE_TIMER(ip6_fib_timer, fib6_run_gc, 0, 0);
-struct fib6_walker_t fib6_walker_list = {
+static struct fib6_walker_t fib6_walker_list = {
.prev = &fib6_walker_list,
.next = &fib6_walker_list,
};
#define FOR_WALKERS(w) for ((w)=fib6_walker_list.next; (w) != &fib6_walker_list; (w)=(w)->next)
+static inline void fib6_walker_link(struct fib6_walker_t *w)
+{
+ write_lock_bh(&fib6_walker_lock);
+ w->next = fib6_walker_list.next;
+ w->prev = &fib6_walker_list;
+ w->next->prev = w;
+ w->prev->next = w;
+ write_unlock_bh(&fib6_walker_lock);
+}
+
+static inline void fib6_walker_unlink(struct fib6_walker_t *w)
+{
+ write_lock_bh(&fib6_walker_lock);
+ w->next->prev = w->prev;
+ w->prev->next = w->next;
+ w->prev = w->next = w;
+ write_unlock_bh(&fib6_walker_lock);
+}
static __inline__ u32 fib6_new_sernum(void)
{
u32 n = ++rt_sernum;
@@ -147,6 +167,253 @@ static __inline__ void rt6_release(struct rt6_info *rt)
dst_free(&rt->u.dst);
}
+static struct fib6_table fib6_main_tbl = {
+ .tb6_id = RT6_TABLE_MAIN,
+ .tb6_lock = RW_LOCK_UNLOCKED,
+ .tb6_root = {
+ .leaf = &ip6_null_entry,
+ .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
+ },
+};
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+#define FIB_TABLE_HASHSZ 256
+#else
+#define FIB_TABLE_HASHSZ 1
+#endif
+static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
+
+static void fib6_link_table(struct fib6_table *tb)
+{
+ unsigned int h;
+
+ h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1);
+
+ /*
+ * No protection necessary, this is the only list mutatation
+ * operation, tables never disappear once they exist.
+ */
+ hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]);
+}
+
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+static struct fib6_table fib6_local_tbl = {
+ .tb6_id = RT6_TABLE_LOCAL,
+ .tb6_lock = RW_LOCK_UNLOCKED,
+ .tb6_root = {
+ .leaf = &ip6_null_entry,
+ .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
+ },
+};
+
+static struct fib6_table *fib6_alloc_table(u32 id)
+{
+ struct fib6_table *table;
+
+ table = kzalloc(sizeof(*table), GFP_ATOMIC);
+ if (table != NULL) {
+ table->tb6_id = id;
+ table->tb6_lock = RW_LOCK_UNLOCKED;
+ table->tb6_root.leaf = &ip6_null_entry;
+ table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+ }
+
+ return table;
+}
+
+struct fib6_table *fib6_new_table(u32 id)
+{
+ struct fib6_table *tb;
+
+ if (id == 0)
+ id = RT6_TABLE_MAIN;
+ tb = fib6_get_table(id);
+ if (tb)
+ return tb;
+
+ tb = fib6_alloc_table(id);
+ if (tb != NULL)
+ fib6_link_table(tb);
+
+ return tb;
+}
+
+struct fib6_table *fib6_get_table(u32 id)
+{
+ struct fib6_table *tb;
+ struct hlist_node *node;
+ unsigned int h;
+
+ if (id == 0)
+ id = RT6_TABLE_MAIN;
+ h = id & (FIB_TABLE_HASHSZ - 1);
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb6_hlist) {
+ if (tb->tb6_id == id) {
+ rcu_read_unlock();
+ return tb;
+ }
+ }
+ rcu_read_unlock();
+
+ return NULL;
+}
+
+static void __init fib6_tables_init(void)
+{
+ fib6_link_table(&fib6_main_tbl);
+ fib6_link_table(&fib6_local_tbl);
+}
+
+#else
+
+struct fib6_table *fib6_new_table(u32 id)
+{
+ return fib6_get_table(id);
+}
+
+struct fib6_table *fib6_get_table(u32 id)
+{
+ return &fib6_main_tbl;
+}
+
+struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags,
+ pol_lookup_t lookup)
+{
+ return (struct dst_entry *) lookup(&fib6_main_tbl, fl, flags);
+}
+
+static void __init fib6_tables_init(void)
+{
+ fib6_link_table(&fib6_main_tbl);
+}
+
+#endif
+
+static int fib6_dump_node(struct fib6_walker_t *w)
+{
+ int res;
+ struct rt6_info *rt;
+
+ for (rt = w->leaf; rt; rt = rt->u.next) {
+ res = rt6_dump_route(rt, w->args);
+ if (res < 0) {
+ /* Frame is full, suspend walking */
+ w->leaf = rt;
+ return 1;
+ }
+ BUG_TRAP(res!=0);
+ }
+ w->leaf = NULL;
+ return 0;
+}
+
+static void fib6_dump_end(struct netlink_callback *cb)
+{
+ struct fib6_walker_t *w = (void*)cb->args[2];
+
+ if (w) {
+ cb->args[2] = 0;
+ kfree(w);
+ }
+ cb->done = (void*)cb->args[3];
+ cb->args[1] = 3;
+}
+
+static int fib6_dump_done(struct netlink_callback *cb)
+{
+ fib6_dump_end(cb);
+ return cb->done ? cb->done(cb) : 0;
+}
+
+static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct fib6_walker_t *w;
+ int res;
+
+ w = (void *)cb->args[2];
+ w->root = &table->tb6_root;
+
+ if (cb->args[4] == 0) {
+ read_lock_bh(&table->tb6_lock);
+ res = fib6_walk(w);
+ read_unlock_bh(&table->tb6_lock);
+ if (res > 0)
+ cb->args[4] = 1;
+ } else {
+ read_lock_bh(&table->tb6_lock);
+ res = fib6_walk_continue(w);
+ read_unlock_bh(&table->tb6_lock);
+ if (res != 0) {
+ if (res < 0)
+ fib6_walker_unlink(w);
+ goto end;
+ }
+ fib6_walker_unlink(w);
+ cb->args[4] = 0;
+ }
+end:
+ return res;
+}
+
+int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ unsigned int h, s_h;
+ unsigned int e = 0, s_e;
+ struct rt6_rtnl_dump_arg arg;
+ struct fib6_walker_t *w;
+ struct fib6_table *tb;
+ struct hlist_node *node;
+ int res = 0;
+
+ s_h = cb->args[0];
+ s_e = cb->args[1];
+
+ w = (void *)cb->args[2];
+ if (w == NULL) {
+ /* New dump:
+ *
+ * 1. hook callback destructor.
+ */
+ cb->args[3] = (long)cb->done;
+ cb->done = fib6_dump_done;
+
+ /*
+ * 2. allocate and initialize walker.
+ */
+ w = kzalloc(sizeof(*w), GFP_ATOMIC);
+ if (w == NULL)
+ return -ENOMEM;
+ w->func = fib6_dump_node;
+ cb->args[2] = (long)w;
+ }
+
+ arg.skb = skb;
+ arg.cb = cb;
+ w->args = &arg;
+
+ for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
+ e = 0;
+ hlist_for_each_entry(tb, node, &fib_table_hash[h], tb6_hlist) {
+ if (e < s_e)
+ goto next;
+ res = fib6_dump_table(tb, skb, cb);
+ if (res != 0)
+ goto out;
+next:
+ e++;
+ }
+ }
+out:
+ cb->args[1] = e;
+ cb->args[0] = h;
+
+ res = res < 0 ? res : skb->len;
+ if (res <= 0)
+ fib6_dump_end(cb);
+ return res;
+}
/*
* Routing Table
@@ -343,7 +610,7 @@ insert_above:
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
- struct nlmsghdr *nlh, struct netlink_skb_parms *req)
+ struct nl_info *info)
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
@@ -398,7 +665,7 @@ out:
*ins = rt;
rt->rt6i_node = fn;
atomic_inc(&rt->rt6i_ref);
- inet6_rt_notify(RTM_NEWROUTE, rt, nlh, req);
+ inet6_rt_notify(RTM_NEWROUTE, rt, info);
rt6_stats.fib_rt_entries++;
if ((fn->fn_flags & RTN_RTINFO) == 0) {
@@ -428,10 +695,9 @@ void fib6_force_start_gc(void)
* with source addr info in sub-trees
*/
-int fib6_add(struct fib6_node *root, struct rt6_info *rt,
- struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
{
- struct fib6_node *fn;
+ struct fib6_node *fn, *pn = NULL;
int err = -ENOMEM;
fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr),
@@ -440,6 +706,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (fn == NULL)
goto out;
+ pn = fn;
+
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen) {
struct fib6_node *sn;
@@ -485,10 +753,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
/* Now link new subtree to main tree */
sfn->parent = fn;
fn->subtree = sfn;
- if (fn->leaf == NULL) {
- fn->leaf = rt;
- atomic_inc(&rt->rt6i_ref);
- }
} else {
sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
sizeof(struct in6_addr), rt->rt6i_src.plen,
@@ -498,21 +762,42 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
goto st_failure;
}
+ if (fn->leaf == NULL) {
+ fn->leaf = rt;
+ atomic_inc(&rt->rt6i_ref);
+ }
fn = sn;
}
#endif
- err = fib6_add_rt2node(fn, rt, nlh, req);
+ err = fib6_add_rt2node(fn, rt, info);
if (err == 0) {
fib6_start_gc(rt);
if (!(rt->rt6i_flags&RTF_CACHE))
- fib6_prune_clones(fn, rt);
+ fib6_prune_clones(pn, rt);
}
out:
- if (err)
+ if (err) {
+#ifdef CONFIG_IPV6_SUBTREES
+ /*
+ * If fib6_add_1 has cleared the old leaf pointer in the
+ * super-tree leaf node we have to find a new one for it.
+ */
+ if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) {
+ pn->leaf = fib6_find_prefix(pn);
+#if RT6_DEBUG >= 2
+ if (!pn->leaf) {
+ BUG_TRAP(pn->leaf != NULL);
+ pn->leaf = &ip6_null_entry;
+ }
+#endif
+ atomic_inc(&pn->leaf->rt6i_ref);
+ }
+#endif
dst_free(&rt->u.dst);
+ }
return err;
#ifdef CONFIG_IPV6_SUBTREES
@@ -543,6 +828,9 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
struct fib6_node *fn;
int dir;
+ if (unlikely(args->offset == 0))
+ return NULL;
+
/*
* Descend on a tree
*/
@@ -564,33 +852,26 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
break;
}
- while ((fn->fn_flags & RTN_ROOT) == 0) {
-#ifdef CONFIG_IPV6_SUBTREES
- if (fn->subtree) {
- struct fib6_node *st;
- struct lookup_args *narg;
-
- narg = args + 1;
-
- if (narg->addr) {
- st = fib6_lookup_1(fn->subtree, narg);
-
- if (st && !(st->fn_flags & RTN_ROOT))
- return st;
- }
- }
-#endif
-
- if (fn->fn_flags & RTN_RTINFO) {
+ while(fn) {
+ if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
struct rt6key *key;
key = (struct rt6key *) ((u8 *) fn->leaf +
args->offset);
- if (ipv6_prefix_equal(&key->addr, args->addr, key->plen))
- return fn;
+ if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
+#ifdef CONFIG_IPV6_SUBTREES
+ if (fn->subtree)
+ fn = fib6_lookup_1(fn->subtree, args + 1);
+#endif
+ if (!fn || fn->fn_flags & RTN_RTINFO)
+ return fn;
+ }
}
+ if (fn->fn_flags & RTN_ROOT)
+ break;
+
fn = fn->parent;
}
@@ -600,18 +881,24 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr,
struct in6_addr *saddr)
{
- struct lookup_args args[2];
struct fib6_node *fn;
-
- args[0].offset = offsetof(struct rt6_info, rt6i_dst);
- args[0].addr = daddr;
-
+ struct lookup_args args[] = {
+ {
+ .offset = offsetof(struct rt6_info, rt6i_dst),
+ .addr = daddr,
+ },
#ifdef CONFIG_IPV6_SUBTREES
- args[1].offset = offsetof(struct rt6_info, rt6i_src);
- args[1].addr = saddr;
+ {
+ .offset = offsetof(struct rt6_info, rt6i_src),
+ .addr = saddr,
+ },
#endif
+ {
+ .offset = 0, /* sentinel */
+ }
+ };
- fn = fib6_lookup_1(root, args);
+ fn = fib6_lookup_1(root, daddr ? args : args + 1);
if (fn == NULL || fn->fn_flags & RTN_TL_ROOT)
fn = root;
@@ -667,10 +954,8 @@ struct fib6_node * fib6_locate(struct fib6_node *root,
#ifdef CONFIG_IPV6_SUBTREES
if (src_len) {
BUG_TRAP(saddr!=NULL);
- if (fn == NULL)
- fn = fn->subtree;
- if (fn)
- fn = fib6_locate_1(fn, saddr, src_len,
+ if (fn && fn->subtree)
+ fn = fib6_locate_1(fn->subtree, saddr, src_len,
offsetof(struct rt6_info, rt6i_src));
}
#endif
@@ -699,7 +984,7 @@ static struct rt6_info * fib6_find_prefix(struct fib6_node *fn)
if(fn->right)
return fn->right->leaf;
- fn = SUBTREE(fn);
+ fn = FIB6_SUBTREE(fn);
}
return NULL;
}
@@ -730,7 +1015,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
if (fn->right) child = fn->right, children |= 1;
if (fn->left) child = fn->left, children |= 2;
- if (children == 3 || SUBTREE(fn)
+ if (children == 3 || FIB6_SUBTREE(fn)
#ifdef CONFIG_IPV6_SUBTREES
/* Subtree root (i.e. fn) may have one child */
|| (children && fn->fn_flags&RTN_ROOT)
@@ -749,9 +1034,9 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
pn = fn->parent;
#ifdef CONFIG_IPV6_SUBTREES
- if (SUBTREE(pn) == fn) {
+ if (FIB6_SUBTREE(pn) == fn) {
BUG_TRAP(fn->fn_flags&RTN_ROOT);
- SUBTREE(pn) = NULL;
+ FIB6_SUBTREE(pn) = NULL;
nstate = FWS_L;
} else {
BUG_TRAP(!(fn->fn_flags&RTN_ROOT));
@@ -799,7 +1084,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
read_unlock(&fib6_walker_lock);
node_free(fn);
- if (pn->fn_flags&RTN_RTINFO || SUBTREE(pn))
+ if (pn->fn_flags&RTN_RTINFO || FIB6_SUBTREE(pn))
return pn;
rt6_release(pn->leaf);
@@ -809,7 +1094,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn)
}
static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
- struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
+ struct nl_info *info)
{
struct fib6_walker_t *w;
struct rt6_info *rt = *rtp;
@@ -865,11 +1150,11 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
if (atomic_read(&rt->rt6i_ref) != 1) BUG();
}
- inet6_rt_notify(RTM_DELROUTE, rt, nlh, req);
+ inet6_rt_notify(RTM_DELROUTE, rt, info);
rt6_release(rt);
}
-int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
+int fib6_del(struct rt6_info *rt, struct nl_info *info)
{
struct fib6_node *fn = rt->rt6i_node;
struct rt6_info **rtp;
@@ -885,8 +1170,18 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne
BUG_TRAP(fn->fn_flags&RTN_RTINFO);
- if (!(rt->rt6i_flags&RTF_CACHE))
- fib6_prune_clones(fn, rt);
+ if (!(rt->rt6i_flags&RTF_CACHE)) {
+ struct fib6_node *pn = fn;
+#ifdef CONFIG_IPV6_SUBTREES
+ /* clones of this route might be in another subtree */
+ if (rt->rt6i_src.plen) {
+ while (!(pn->fn_flags&RTN_ROOT))
+ pn = pn->parent;
+ pn = pn->parent;
+ }
+#endif
+ fib6_prune_clones(pn, rt);
+ }
/*
* Walk the leaf entries looking for ourself
@@ -894,7 +1189,7 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne
for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.next) {
if (*rtp == rt) {
- fib6_del_route(fn, rtp, nlh, _rtattr, req);
+ fib6_del_route(fn, rtp, info);
return 0;
}
}
@@ -925,7 +1220,7 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne
* <0 -> walk is terminated by an error.
*/
-int fib6_walk_continue(struct fib6_walker_t *w)
+static int fib6_walk_continue(struct fib6_walker_t *w)
{
struct fib6_node *fn, *pn;
@@ -942,8 +1237,8 @@ int fib6_walk_continue(struct fib6_walker_t *w)
switch (w->state) {
#ifdef CONFIG_IPV6_SUBTREES
case FWS_S:
- if (SUBTREE(fn)) {
- w->node = SUBTREE(fn);
+ if (FIB6_SUBTREE(fn)) {
+ w->node = FIB6_SUBTREE(fn);
continue;
}
w->state = FWS_L;
@@ -977,7 +1272,7 @@ int fib6_walk_continue(struct fib6_walker_t *w)
pn = fn->parent;
w->node = pn;
#ifdef CONFIG_IPV6_SUBTREES
- if (SUBTREE(pn) == fn) {
+ if (FIB6_SUBTREE(pn) == fn) {
BUG_TRAP(fn->fn_flags&RTN_ROOT);
w->state = FWS_L;
continue;
@@ -999,7 +1294,7 @@ int fib6_walk_continue(struct fib6_walker_t *w)
}
}
-int fib6_walk(struct fib6_walker_t *w)
+static int fib6_walk(struct fib6_walker_t *w)
{
int res;
@@ -1023,7 +1318,7 @@ static int fib6_clean_node(struct fib6_walker_t *w)
res = c->func(rt, c->arg);
if (res < 0) {
w->leaf = rt;
- res = fib6_del(rt, NULL, NULL, NULL);
+ res = fib6_del(rt, NULL);
if (res) {
#if RT6_DEBUG >= 2
printk(KERN_DEBUG "fib6_clean_node: del failed: rt=%p@%p err=%d\n", rt, rt->rt6i_node, res);
@@ -1049,9 +1344,9 @@ static int fib6_clean_node(struct fib6_walker_t *w)
* ignoring pure split nodes) will be scanned.
*/
-void fib6_clean_tree(struct fib6_node *root,
- int (*func)(struct rt6_info *, void *arg),
- int prune, void *arg)
+static void fib6_clean_tree(struct fib6_node *root,
+ int (*func)(struct rt6_info *, void *arg),
+ int prune, void *arg)
{
struct fib6_cleaner_t c;
@@ -1064,6 +1359,25 @@ void fib6_clean_tree(struct fib6_node *root,
fib6_walk(&c.w);
}
+void fib6_clean_all(int (*func)(struct rt6_info *, void *arg),
+ int prune, void *arg)
+{
+ struct fib6_table *table;
+ struct hlist_node *node;
+ unsigned int h;
+
+ rcu_read_lock();
+ for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
+ hlist_for_each_entry_rcu(table, node, &fib_table_hash[h],
+ tb6_hlist) {
+ write_lock_bh(&table->tb6_lock);
+ fib6_clean_tree(&table->tb6_root, func, prune, arg);
+ write_unlock_bh(&table->tb6_lock);
+ }
+ }
+ rcu_read_unlock();
+}
+
static int fib6_prune_clone(struct rt6_info *rt, void *arg)
{
if (rt->rt6i_flags & RTF_CACHE) {
@@ -1142,11 +1456,8 @@ void fib6_run_gc(unsigned long dummy)
}
gc_args.more = 0;
-
- write_lock_bh(&rt6_lock);
ndisc_dst_gc(&gc_args.more);
- fib6_clean_tree(&ip6_routing_table, fib6_age, 0, NULL);
- write_unlock_bh(&rt6_lock);
+ fib6_clean_all(fib6_age, 0, NULL);
if (gc_args.more)
mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
@@ -1161,10 +1472,10 @@ void __init fib6_init(void)
{
fib6_node_kmem = kmem_cache_create("fib6_nodes",
sizeof(struct fib6_node),
- 0, SLAB_HWCACHE_ALIGN,
+ 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL, NULL);
- if (!fib6_node_kmem)
- panic("cannot create fib6_nodes cache");
+
+ fib6_tables_init();
}
void fib6_gc_cleanup(void)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 25c2a9e0389..6b8e6d76a58 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -111,7 +111,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
}
if (hdr->nexthdr == NEXTHDR_HOP) {
- if (ipv6_parse_hopopts(skb) < 0) {
+ if (ipv6_parse_hopopts(&skb) < 0) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
return 0;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4fb47a25291..66716911962 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -308,6 +308,56 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
return 0;
}
+static int ip6_forward_proxy_check(struct sk_buff *skb)
+{
+ struct ipv6hdr *hdr = skb->nh.ipv6h;
+ u8 nexthdr = hdr->nexthdr;
+ int offset;
+
+ if (ipv6_ext_hdr(nexthdr)) {
+ offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
+ if (offset < 0)
+ return 0;
+ } else
+ offset = sizeof(struct ipv6hdr);
+
+ if (nexthdr == IPPROTO_ICMPV6) {
+ struct icmp6hdr *icmp6;
+
+ if (!pskb_may_pull(skb, skb->nh.raw + offset + 1 - skb->data))
+ return 0;
+
+ icmp6 = (struct icmp6hdr *)(skb->nh.raw + offset);
+
+ switch (icmp6->icmp6_type) {
+ case NDISC_ROUTER_SOLICITATION:
+ case NDISC_ROUTER_ADVERTISEMENT:
+ case NDISC_NEIGHBOUR_SOLICITATION:
+ case NDISC_NEIGHBOUR_ADVERTISEMENT:
+ case NDISC_REDIRECT:
+ /* For reaction involving unicast neighbor discovery
+ * message destined to the proxied address, pass it to
+ * input function.
+ */
+ return 1;
+ default:
+ break;
+ }
+ }
+
+ /*
+ * The proxying router can't forward traffic sent to a link-local
+ * address, so signal the sender and discard the packet. This
+ * behavior is clarified by the MIPv6 specification.
+ */
+ if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) {
+ dst_link_failure(skb);
+ return -1;
+ }
+
+ return 0;
+}
+
static inline int ip6_forward_finish(struct sk_buff *skb)
{
return dst_output(skb);
@@ -362,6 +412,18 @@ int ip6_forward(struct sk_buff *skb)
return -ETIMEDOUT;
}
+ /* XXX: idev->cnf.proxy_ndp? */
+ if (ipv6_devconf.proxy_ndp &&
+ pneigh_lookup(&nd_tbl, &hdr->daddr, skb->dev, 0)) {
+ int proxied = ip6_forward_proxy_check(skb);
+ if (proxied > 0)
+ return ip6_input(skb);
+ else if (proxied < 0) {
+ IP6_INC_STATS(IPSTATS_MIB_INDISCARDS);
+ goto drop;
+ }
+ }
+
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS(IPSTATS_MIB_INDISCARDS);
goto drop;
@@ -475,17 +537,25 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
switch (**nexthdr) {
case NEXTHDR_HOP:
+ break;
case NEXTHDR_ROUTING:
+ found_rhdr = 1;
+ break;
case NEXTHDR_DEST:
- if (**nexthdr == NEXTHDR_ROUTING) found_rhdr = 1;
- if (**nexthdr == NEXTHDR_DEST && found_rhdr) return offset;
- offset += ipv6_optlen(exthdr);
- *nexthdr = &exthdr->nexthdr;
- exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
+#ifdef CONFIG_IPV6_MIP6
+ if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
+ break;
+#endif
+ if (found_rhdr)
+ return offset;
break;
default :
return offset;
}
+
+ offset += ipv6_optlen(exthdr);
+ *nexthdr = &exthdr->nexthdr;
+ exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
}
return offset;
@@ -726,6 +796,14 @@ fail:
return err;
}
+static inline int ip6_rt_check(struct rt6key *rt_key,
+ struct in6_addr *fl_addr,
+ struct in6_addr *addr_cache)
+{
+ return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
+ (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)));
+}
+
static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
struct dst_entry *dst,
struct flowi *fl)
@@ -741,8 +819,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
* that we do not support routing by source, TOS,
* and MSG_DONTROUTE --ANK (980726)
*
- * 1. If route was host route, check that
- * cached destination is current.
+ * 1. ip6_rt_check(): If route was host route,
+ * check that cached destination is current.
* If it is network route, we still may
* check its validity using saved pointer
* to the last used address: daddr_cache.
@@ -753,11 +831,11 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
* sockets.
* 2. oif also should be the same.
*/
- if (((rt->rt6i_dst.plen != 128 ||
- !ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr))
- && (np->daddr_cache == NULL ||
- !ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache)))
- || (fl->oif && fl->oif != dst->dev->ifindex)) {
+ if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) ||
+#ifdef CONFIG_IPV6_SUBTREES
+ ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) ||
+#endif
+ (fl->oif && fl->oif != dst->dev->ifindex)) {
dst_release(dst);
dst = NULL;
}
@@ -866,7 +944,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
/* initialize protocol header pointer */
skb->h.raw = skb->data + fragheaderlen;
- skb->ip_summed = CHECKSUM_HW;
+ skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
sk->sk_sndmsg_off = 0;
}
@@ -963,7 +1041,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
- fragheaderlen = sizeof(struct ipv6hdr) + (opt ? opt->opt_nflen : 0);
+ fragheaderlen = sizeof(struct ipv6hdr) + rt->u.dst.nfheader_len + (opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 7e4d1c17bfb..ad9c6e824e6 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -53,7 +53,7 @@
struct ipcomp6_tfms {
struct list_head list;
- struct crypto_tfm **tfms;
+ struct crypto_comp **tfms;
int users;
};
@@ -70,7 +70,7 @@ static int ipcomp6_input(struct xfrm_state *x, struct sk_buff *skb)
int plen, dlen;
struct ipcomp_data *ipcd = x->data;
u8 *start, *scratch;
- struct crypto_tfm *tfm;
+ struct crypto_comp *tfm;
int cpu;
if (skb_linearize_cow(skb))
@@ -129,7 +129,7 @@ static int ipcomp6_output(struct xfrm_state *x, struct sk_buff *skb)
struct ipcomp_data *ipcd = x->data;
int plen, dlen;
u8 *start, *scratch;
- struct crypto_tfm *tfm;
+ struct crypto_comp *tfm;
int cpu;
hdr_len = skb->h.raw - skb->data;
@@ -212,7 +212,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr));
memcpy(&t->sel, &x->sel, sizeof(t->sel));
t->props.family = AF_INET6;
- t->props.mode = 1;
+ t->props.mode = XFRM_MODE_TUNNEL;
memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr));
if (xfrm_init_state(t))
@@ -301,7 +301,7 @@ static void **ipcomp6_alloc_scratches(void)
return scratches;
}
-static void ipcomp6_free_tfms(struct crypto_tfm **tfms)
+static void ipcomp6_free_tfms(struct crypto_comp **tfms)
{
struct ipcomp6_tfms *pos;
int cpu;
@@ -323,28 +323,28 @@ static void ipcomp6_free_tfms(struct crypto_tfm **tfms)
return;
for_each_possible_cpu(cpu) {
- struct crypto_tfm *tfm = *per_cpu_ptr(tfms, cpu);
- crypto_free_tfm(tfm);
+ struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu);
+ crypto_free_comp(tfm);
}
free_percpu(tfms);
}
-static struct crypto_tfm **ipcomp6_alloc_tfms(const char *alg_name)
+static struct crypto_comp **ipcomp6_alloc_tfms(const char *alg_name)
{
struct ipcomp6_tfms *pos;
- struct crypto_tfm **tfms;
+ struct crypto_comp **tfms;
int cpu;
/* This can be any valid CPU ID so we don't need locking. */
cpu = raw_smp_processor_id();
list_for_each_entry(pos, &ipcomp6_tfms_list, list) {
- struct crypto_tfm *tfm;
+ struct crypto_comp *tfm;
tfms = pos->tfms;
tfm = *per_cpu_ptr(tfms, cpu);
- if (!strcmp(crypto_tfm_alg_name(tfm), alg_name)) {
+ if (!strcmp(crypto_comp_name(tfm), alg_name)) {
pos->users++;
return tfms;
}
@@ -358,12 +358,13 @@ static struct crypto_tfm **ipcomp6_alloc_tfms(const char *alg_name)
INIT_LIST_HEAD(&pos->list);
list_add(&pos->list, &ipcomp6_tfms_list);
- pos->tfms = tfms = alloc_percpu(struct crypto_tfm *);
+ pos->tfms = tfms = alloc_percpu(struct crypto_comp *);
if (!tfms)
goto error;
for_each_possible_cpu(cpu) {
- struct crypto_tfm *tfm = crypto_alloc_tfm(alg_name, 0);
+ struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0,
+ CRYPTO_ALG_ASYNC);
if (!tfm)
goto error;
*per_cpu_ptr(tfms, cpu) = tfm;
@@ -416,7 +417,7 @@ static int ipcomp6_init_state(struct xfrm_state *x)
goto out;
x->props.header_len = 0;
- if (x->props.mode)
+ if (x->props.mode == XFRM_MODE_TUNNEL)
x->props.header_len += sizeof(struct ipv6hdr);
mutex_lock(&ipcomp6_resource_mutex);
@@ -428,7 +429,7 @@ static int ipcomp6_init_state(struct xfrm_state *x)
goto error;
mutex_unlock(&ipcomp6_resource_mutex);
- if (x->props.mode) {
+ if (x->props.mode == XFRM_MODE_TUNNEL) {
err = ipcomp6_tunnel_attach(x);
if (err)
goto error_tunnel;
@@ -460,6 +461,7 @@ static struct xfrm_type ipcomp6_type =
.destructor = ipcomp6_destroy,
.input = ipcomp6_input,
.output = ipcomp6_output,
+ .hdr_offset = xfrm6_find_1stfragopt,
};
static struct inet6_protocol ipcomp6_protocol =
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a5eaaf693ab..4f3bb7fcc8b 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -407,8 +407,16 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
/* routing header option needs extra check */
if (optname == IPV6_RTHDR && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
- if (rthdr->type)
+ switch (rthdr->type) {
+ case IPV6_SRCRT_TYPE_0:
+#ifdef CONFIG_IPV6_MIP6
+ case IPV6_SRCRT_TYPE_2:
+#endif
+ break;
+ default:
goto sticky_done;
+ }
+
if ((rthdr->hdrlen & 1) ||
(rthdr->hdrlen >> 1) != rthdr->segments_left)
goto sticky_done;
diff --git a/net/ipv6/ipv6_syms.c b/net/ipv6/ipv6_syms.c
index dd4d1ce7776..0e8e0676a03 100644
--- a/net/ipv6/ipv6_syms.c
+++ b/net/ipv6/ipv6_syms.c
@@ -14,7 +14,6 @@ EXPORT_SYMBOL(ndisc_mc_map);
EXPORT_SYMBOL(register_inet6addr_notifier);
EXPORT_SYMBOL(unregister_inet6addr_notifier);
EXPORT_SYMBOL(ip6_route_output);
-EXPORT_SYMBOL(addrconf_lock);
EXPORT_SYMBOL(ipv6_setsockopt);
EXPORT_SYMBOL(ipv6_getsockopt);
EXPORT_SYMBOL(inet6_register_protosw);
@@ -31,6 +30,8 @@ EXPORT_SYMBOL(ipv6_chk_addr);
EXPORT_SYMBOL(in6_dev_finish_destroy);
#ifdef CONFIG_XFRM
EXPORT_SYMBOL(xfrm6_rcv);
+EXPORT_SYMBOL(xfrm6_input_addr);
+EXPORT_SYMBOL(xfrm6_find_1stfragopt);
#endif
EXPORT_SYMBOL(rt6_lookup);
EXPORT_SYMBOL(ipv6_push_nfrag_opts);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 639eb20c9f1..3b114e3fa2f 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -171,7 +171,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
#define IPV6_MLD_MAX_MSF 64
-int sysctl_mld_max_msf = IPV6_MLD_MAX_MSF;
+int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;
/*
* socket join on multicast group
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
new file mode 100644
index 00000000000..99d116caecd
--- /dev/null
+++ b/net/ipv6/mip6.c
@@ -0,0 +1,519 @@
+/*
+ * Copyright (C)2003-2006 Helsinki University of Technology
+ * Copyright (C)2003-2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+/*
+ * Authors:
+ * Noriaki TAKAMIYA @USAGI
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/time.h>
+#include <linux/ipv6.h>
+#include <linux/icmpv6.h>
+#include <net/sock.h>
+#include <net/ipv6.h>
+#include <net/ip6_checksum.h>
+#include <net/xfrm.h>
+#include <net/mip6.h>
+
+static xfrm_address_t *mip6_xfrm_addr(struct xfrm_state *x, xfrm_address_t *addr)
+{
+ return x->coaddr;
+}
+
+static inline unsigned int calc_padlen(unsigned int len, unsigned int n)
+{
+ return (n - len + 16) & 0x7;
+}
+
+static inline void *mip6_padn(__u8 *data, __u8 padlen)
+{
+ if (!data)
+ return NULL;
+ if (padlen == 1) {
+ data[0] = MIP6_OPT_PAD_1;
+ } else if (padlen > 1) {
+ data[0] = MIP6_OPT_PAD_N;
+ data[1] = padlen - 2;
+ if (padlen > 2)
+ memset(data+2, 0, data[1]);
+ }
+ return data + padlen;
+}
+
+static inline void mip6_param_prob(struct sk_buff *skb, int code, int pos)
+{
+ icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev);
+}
+
+static int mip6_mh_len(int type)
+{
+ int len = 0;
+
+ switch (type) {
+ case IP6_MH_TYPE_BRR:
+ len = 0;
+ break;
+ case IP6_MH_TYPE_HOTI:
+ case IP6_MH_TYPE_COTI:
+ case IP6_MH_TYPE_BU:
+ case IP6_MH_TYPE_BACK:
+ len = 1;
+ break;
+ case IP6_MH_TYPE_HOT:
+ case IP6_MH_TYPE_COT:
+ case IP6_MH_TYPE_BERROR:
+ len = 2;
+ break;
+ }
+ return len;
+}
+
+int mip6_mh_filter(struct sock *sk, struct sk_buff *skb)
+{
+ struct ip6_mh *mh;
+ int mhlen;
+
+ if (!pskb_may_pull(skb, (skb->h.raw - skb->data) + 8) ||
+ !pskb_may_pull(skb, (skb->h.raw - skb->data) + ((skb->h.raw[1] + 1) << 3)))
+ return -1;
+
+ mh = (struct ip6_mh *)skb->h.raw;
+
+ if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) {
+ LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n",
+ mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type));
+ mip6_param_prob(skb, 0, (&mh->ip6mh_hdrlen) - skb->nh.raw);
+ return -1;
+ }
+ mhlen = (mh->ip6mh_hdrlen + 1) << 3;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (csum_ipv6_magic(&skb->nh.ipv6h->saddr,
+ &skb->nh.ipv6h->daddr,
+ mhlen, IPPROTO_MH,
+ skb->csum)) {
+ LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH hw checksum failed\n");
+ skb->ip_summed = CHECKSUM_NONE;
+ }
+ }
+ if (skb->ip_summed == CHECKSUM_NONE) {
+ if (csum_ipv6_magic(&skb->nh.ipv6h->saddr,
+ &skb->nh.ipv6h->daddr,
+ mhlen, IPPROTO_MH,
+ skb_checksum(skb, 0, mhlen, 0))) {
+ LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH checksum failed "
+ "[" NIP6_FMT " > " NIP6_FMT "]\n",
+ NIP6(skb->nh.ipv6h->saddr),
+ NIP6(skb->nh.ipv6h->daddr));
+ return -1;
+ }
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ }
+
+ if (mh->ip6mh_proto != IPPROTO_NONE) {
+ LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n",
+ mh->ip6mh_proto);
+ mip6_param_prob(skb, 0, (&mh->ip6mh_proto) - skb->nh.raw);
+ return -1;
+ }
+
+ return 0;
+}
+
+struct mip6_report_rate_limiter {
+ spinlock_t lock;
+ struct timeval stamp;
+ int iif;
+ struct in6_addr src;
+ struct in6_addr dst;
+};
+
+static struct mip6_report_rate_limiter mip6_report_rl = {
+ .lock = SPIN_LOCK_UNLOCKED
+};
+
+static int mip6_destopt_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = skb->nh.ipv6h;
+ struct ipv6_destopt_hdr *destopt = (struct ipv6_destopt_hdr *)skb->data;
+
+ if (!ipv6_addr_equal(&iph->saddr, (struct in6_addr *)x->coaddr) &&
+ !ipv6_addr_any((struct in6_addr *)x->coaddr))
+ return -ENOENT;
+
+ return destopt->nexthdr;
+}
+
+/* Destination Option Header is inserted.
+ * IP Header's src address is replaced with Home Address Option in
+ * Destination Option Header.
+ */
+static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph;
+ struct ipv6_destopt_hdr *dstopt;
+ struct ipv6_destopt_hao *hao;
+ u8 nexthdr;
+ int len;
+
+ iph = (struct ipv6hdr *)skb->data;
+ iph->payload_len = htons(skb->len - sizeof(*iph));
+
+ nexthdr = *skb->nh.raw;
+ *skb->nh.raw = IPPROTO_DSTOPTS;
+
+ dstopt = (struct ipv6_destopt_hdr *)skb->h.raw;
+ dstopt->nexthdr = nexthdr;
+
+ hao = mip6_padn((char *)(dstopt + 1),
+ calc_padlen(sizeof(*dstopt), 6));
+
+ hao->type = IPV6_TLV_HAO;
+ hao->length = sizeof(*hao) - 2;
+ BUG_TRAP(hao->length == 16);
+
+ len = ((char *)hao - (char *)dstopt) + sizeof(*hao);
+
+ memcpy(&hao->addr, &iph->saddr, sizeof(hao->addr));
+ memcpy(&iph->saddr, x->coaddr, sizeof(iph->saddr));
+
+ BUG_TRAP(len == x->props.header_len);
+ dstopt->hdrlen = (x->props.header_len >> 3) - 1;
+
+ return 0;
+}
+
+static inline int mip6_report_rl_allow(struct timeval *stamp,
+ struct in6_addr *dst,
+ struct in6_addr *src, int iif)
+{
+ int allow = 0;
+
+ spin_lock_bh(&mip6_report_rl.lock);
+ if (mip6_report_rl.stamp.tv_sec != stamp->tv_sec ||
+ mip6_report_rl.stamp.tv_usec != stamp->tv_usec ||
+ mip6_report_rl.iif != iif ||
+ !ipv6_addr_equal(&mip6_report_rl.src, src) ||
+ !ipv6_addr_equal(&mip6_report_rl.dst, dst)) {
+ mip6_report_rl.stamp.tv_sec = stamp->tv_sec;
+ mip6_report_rl.stamp.tv_usec = stamp->tv_usec;
+ mip6_report_rl.iif = iif;
+ ipv6_addr_copy(&mip6_report_rl.src, src);
+ ipv6_addr_copy(&mip6_report_rl.dst, dst);
+ allow = 1;
+ }
+ spin_unlock_bh(&mip6_report_rl.lock);
+ return allow;
+}
+
+static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl)
+{
+ struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb;
+ struct ipv6_destopt_hao *hao = NULL;
+ struct xfrm_selector sel;
+ int offset;
+ struct timeval stamp;
+ int err = 0;
+
+ if (unlikely(fl->proto == IPPROTO_MH &&
+ fl->fl_mh_type <= IP6_MH_TYPE_MAX))
+ goto out;
+
+ if (likely(opt->dsthao)) {
+ offset = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
+ if (likely(offset >= 0))
+ hao = (struct ipv6_destopt_hao *)(skb->nh.raw + offset);
+ }
+
+ skb_get_timestamp(skb, &stamp);
+
+ if (!mip6_report_rl_allow(&stamp, &skb->nh.ipv6h->daddr,
+ hao ? &hao->addr : &skb->nh.ipv6h->saddr,
+ opt->iif))
+ goto out;
+
+ memset(&sel, 0, sizeof(sel));
+ memcpy(&sel.daddr, (xfrm_address_t *)&skb->nh.ipv6h->daddr,
+ sizeof(sel.daddr));
+ sel.prefixlen_d = 128;
+ memcpy(&sel.saddr, (xfrm_address_t *)&skb->nh.ipv6h->saddr,
+ sizeof(sel.saddr));
+ sel.prefixlen_s = 128;
+ sel.family = AF_INET6;
+ sel.proto = fl->proto;
+ sel.dport = xfrm_flowi_dport(fl);
+ if (sel.dport)
+ sel.dport_mask = ~((__u16)0);
+ sel.sport = xfrm_flowi_sport(fl);
+ if (sel.sport)
+ sel.sport_mask = ~((__u16)0);
+ sel.ifindex = fl->oif;
+
+ err = km_report(IPPROTO_DSTOPTS, &sel,
+ (hao ? (xfrm_address_t *)&hao->addr : NULL));
+
+ out:
+ return err;
+}
+
+static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb,
+ u8 **nexthdr)
+{
+ u16 offset = sizeof(struct ipv6hdr);
+ struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1);
+ unsigned int packet_len = skb->tail - skb->nh.raw;
+ int found_rhdr = 0;
+
+ *nexthdr = &skb->nh.ipv6h->nexthdr;
+
+ while (offset + 1 <= packet_len) {
+
+ switch (**nexthdr) {
+ case NEXTHDR_HOP:
+ break;
+ case NEXTHDR_ROUTING:
+ found_rhdr = 1;
+ break;
+ case NEXTHDR_DEST:
+ /*
+ * HAO MUST NOT appear more than once.
+ * XXX: It is better to try to find by the end of
+ * XXX: packet if HAO exists.
+ */
+ if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
+ LIMIT_NETDEBUG(KERN_WARNING "mip6: hao exists already, override\n");
+ return offset;
+ }
+
+ if (found_rhdr)
+ return offset;
+
+ break;
+ default:
+ return offset;
+ }
+
+ offset += ipv6_optlen(exthdr);
+ *nexthdr = &exthdr->nexthdr;
+ exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
+ }
+
+ return offset;
+}
+
+static int mip6_destopt_init_state(struct xfrm_state *x)
+{
+ if (x->id.spi) {
+ printk(KERN_INFO "%s: spi is not 0: %u\n", __FUNCTION__,
+ x->id.spi);
+ return -EINVAL;
+ }
+ if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) {
+ printk(KERN_INFO "%s: state's mode is not %u: %u\n",
+ __FUNCTION__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode);
+ return -EINVAL;
+ }
+
+ x->props.header_len = sizeof(struct ipv6_destopt_hdr) +
+ calc_padlen(sizeof(struct ipv6_destopt_hdr), 6) +
+ sizeof(struct ipv6_destopt_hao);
+ BUG_TRAP(x->props.header_len == 24);
+
+ return 0;
+}
+
+/*
+ * Do nothing about destroying since it has no specific operation for
+ * destination options header unlike IPsec protocols.
+ */
+static void mip6_destopt_destroy(struct xfrm_state *x)
+{
+}
+
+static struct xfrm_type mip6_destopt_type =
+{
+ .description = "MIP6DESTOPT",
+ .owner = THIS_MODULE,
+ .proto = IPPROTO_DSTOPTS,
+ .flags = XFRM_TYPE_NON_FRAGMENT,
+ .init_state = mip6_destopt_init_state,
+ .destructor = mip6_destopt_destroy,
+ .input = mip6_destopt_input,
+ .output = mip6_destopt_output,
+ .reject = mip6_destopt_reject,
+ .hdr_offset = mip6_destopt_offset,
+ .local_addr = mip6_xfrm_addr,
+};
+
+static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data;
+
+ if (!ipv6_addr_equal(&rt2->addr, (struct in6_addr *)x->coaddr) &&
+ !ipv6_addr_any((struct in6_addr *)x->coaddr))
+ return -ENOENT;
+
+ return rt2->rt_hdr.nexthdr;
+}
+
+/* Routing Header type 2 is inserted.
+ * IP Header's dst address is replaced with Routing Header's Home Address.
+ */
+static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph;
+ struct rt2_hdr *rt2;
+ u8 nexthdr;
+
+ iph = (struct ipv6hdr *)skb->data;
+ iph->payload_len = htons(skb->len - sizeof(*iph));
+
+ nexthdr = *skb->nh.raw;
+ *skb->nh.raw = IPPROTO_ROUTING;
+
+ rt2 = (struct rt2_hdr *)skb->h.raw;
+ rt2->rt_hdr.nexthdr = nexthdr;
+ rt2->rt_hdr.hdrlen = (x->props.header_len >> 3) - 1;
+ rt2->rt_hdr.type = IPV6_SRCRT_TYPE_2;
+ rt2->rt_hdr.segments_left = 1;
+ memset(&rt2->reserved, 0, sizeof(rt2->reserved));
+
+ BUG_TRAP(rt2->rt_hdr.hdrlen == 2);
+
+ memcpy(&rt2->addr, &iph->daddr, sizeof(rt2->addr));
+ memcpy(&iph->daddr, x->coaddr, sizeof(iph->daddr));
+
+ return 0;
+}
+
+static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb,
+ u8 **nexthdr)
+{
+ u16 offset = sizeof(struct ipv6hdr);
+ struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1);
+ unsigned int packet_len = skb->tail - skb->nh.raw;
+ int found_rhdr = 0;
+
+ *nexthdr = &skb->nh.ipv6h->nexthdr;
+
+ while (offset + 1 <= packet_len) {
+
+ switch (**nexthdr) {
+ case NEXTHDR_HOP:
+ break;
+ case NEXTHDR_ROUTING:
+ if (offset + 3 <= packet_len) {
+ struct ipv6_rt_hdr *rt;
+ rt = (struct ipv6_rt_hdr *)(skb->nh.raw + offset);
+ if (rt->type != 0)
+ return offset;
+ }
+ found_rhdr = 1;
+ break;
+ case NEXTHDR_DEST:
+ if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
+ return offset;
+
+ if (found_rhdr)
+ return offset;
+
+ break;
+ default:
+ return offset;
+ }
+
+ offset += ipv6_optlen(exthdr);
+ *nexthdr = &exthdr->nexthdr;
+ exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
+ }
+
+ return offset;
+}
+
+static int mip6_rthdr_init_state(struct xfrm_state *x)
+{
+ if (x->id.spi) {
+ printk(KERN_INFO "%s: spi is not 0: %u\n", __FUNCTION__,
+ x->id.spi);
+ return -EINVAL;
+ }
+ if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) {
+ printk(KERN_INFO "%s: state's mode is not %u: %u\n",
+ __FUNCTION__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode);
+ return -EINVAL;
+ }
+
+ x->props.header_len = sizeof(struct rt2_hdr);
+
+ return 0;
+}
+
+/*
+ * Do nothing about destroying since it has no specific operation for routing
+ * header type 2 unlike IPsec protocols.
+ */
+static void mip6_rthdr_destroy(struct xfrm_state *x)
+{
+}
+
+static struct xfrm_type mip6_rthdr_type =
+{
+ .description = "MIP6RT",
+ .owner = THIS_MODULE,
+ .proto = IPPROTO_ROUTING,
+ .flags = XFRM_TYPE_NON_FRAGMENT,
+ .init_state = mip6_rthdr_init_state,
+ .destructor = mip6_rthdr_destroy,
+ .input = mip6_rthdr_input,
+ .output = mip6_rthdr_output,
+ .hdr_offset = mip6_rthdr_offset,
+ .remote_addr = mip6_xfrm_addr,
+};
+
+int __init mip6_init(void)
+{
+ printk(KERN_INFO "Mobile IPv6\n");
+
+ if (xfrm_register_type(&mip6_destopt_type, AF_INET6) < 0) {
+ printk(KERN_INFO "%s: can't add xfrm type(destopt)\n", __FUNCTION__);
+ goto mip6_destopt_xfrm_fail;
+ }
+ if (xfrm_register_type(&mip6_rthdr_type, AF_INET6) < 0) {
+ printk(KERN_INFO "%s: can't add xfrm type(rthdr)\n", __FUNCTION__);
+ goto mip6_rthdr_xfrm_fail;
+ }
+ return 0;
+
+ mip6_rthdr_xfrm_fail:
+ xfrm_unregister_type(&mip6_destopt_type, AF_INET6);
+ mip6_destopt_xfrm_fail:
+ return -EAGAIN;
+}
+
+void __exit mip6_fini(void)
+{
+ if (xfrm_unregister_type(&mip6_rthdr_type, AF_INET6) < 0)
+ printk(KERN_INFO "%s: can't remove xfrm type(rthdr)\n", __FUNCTION__);
+ if (xfrm_unregister_type(&mip6_destopt_type, AF_INET6) < 0)
+ printk(KERN_INFO "%s: can't remove xfrm type(destopt)\n", __FUNCTION__);
+}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index b50055b9278..0304b5fe8d6 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -62,6 +62,7 @@
#include <linux/sysctl.h>
#endif
+#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
@@ -411,7 +412,8 @@ static void pndisc_destructor(struct pneigh_entry *n)
*/
static inline void ndisc_flow_init(struct flowi *fl, u8 type,
- struct in6_addr *saddr, struct in6_addr *daddr)
+ struct in6_addr *saddr, struct in6_addr *daddr,
+ int oif)
{
memset(fl, 0, sizeof(*fl));
ipv6_addr_copy(&fl->fl6_src, saddr);
@@ -419,6 +421,8 @@ static inline void ndisc_flow_init(struct flowi *fl, u8 type,
fl->proto = IPPROTO_ICMPV6;
fl->fl_icmp_type = type;
fl->fl_icmp_code = 0;
+ fl->oif = oif;
+ security_sk_classify_flow(ndisc_socket->sk, fl);
}
static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
@@ -450,7 +454,8 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
src_addr = &tmpaddr;
}
- ndisc_flow_init(&fl, NDISC_NEIGHBOUR_ADVERTISEMENT, src_addr, daddr);
+ ndisc_flow_init(&fl, NDISC_NEIGHBOUR_ADVERTISEMENT, src_addr, daddr,
+ dev->ifindex);
dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output);
if (!dst)
@@ -491,7 +496,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
msg->icmph.icmp6_unused = 0;
msg->icmph.icmp6_router = router;
msg->icmph.icmp6_solicited = solicited;
- msg->icmph.icmp6_override = !!override;
+ msg->icmph.icmp6_override = override;
/* Set the target address. */
ipv6_addr_copy(&msg->target, solicited_addr);
@@ -540,7 +545,8 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
saddr = &addr_buf;
}
- ndisc_flow_init(&fl, NDISC_NEIGHBOUR_SOLICITATION, saddr, daddr);
+ ndisc_flow_init(&fl, NDISC_NEIGHBOUR_SOLICITATION, saddr, daddr,
+ dev->ifindex);
dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output);
if (!dst)
@@ -615,7 +621,8 @@ void ndisc_send_rs(struct net_device *dev, struct in6_addr *saddr,
int len;
int err;
- ndisc_flow_init(&fl, NDISC_ROUTER_SOLICITATION, saddr, daddr);
+ ndisc_flow_init(&fl, NDISC_ROUTER_SOLICITATION, saddr, daddr,
+ dev->ifindex);
dst = ndisc_dst_alloc(dev, NULL, daddr, ip6_output);
if (!dst)
@@ -729,8 +736,10 @@ static void ndisc_recv_ns(struct sk_buff *skb)
struct inet6_ifaddr *ifp;
struct inet6_dev *idev = NULL;
struct neighbour *neigh;
+ struct pneigh_entry *pneigh = NULL;
int dad = ipv6_addr_any(saddr);
int inc;
+ int is_router;
if (ipv6_addr_is_multicast(&msg->target)) {
ND_PRINTK2(KERN_WARNING
@@ -815,7 +824,9 @@ static void ndisc_recv_ns(struct sk_buff *skb)
if (ipv6_chk_acast_addr(dev, &msg->target) ||
(idev->cnf.forwarding &&
- pneigh_lookup(&nd_tbl, &msg->target, dev, 0))) {
+ (ipv6_devconf.proxy_ndp || idev->cnf.proxy_ndp) &&
+ (pneigh = pneigh_lookup(&nd_tbl,
+ &msg->target, dev, 0)) != NULL)) {
if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
skb->pkt_type != PACKET_HOST &&
inc != 0 &&
@@ -836,12 +847,14 @@ static void ndisc_recv_ns(struct sk_buff *skb)
goto out;
}
+ is_router = !!(pneigh ? pneigh->flags & NTF_ROUTER : idev->cnf.forwarding);
+
if (dad) {
struct in6_addr maddr;
ipv6_addr_all_nodes(&maddr);
ndisc_send_na(dev, NULL, &maddr, &msg->target,
- idev->cnf.forwarding, 0, (ifp != NULL), 1);
+ is_router, 0, (ifp != NULL), 1);
goto out;
}
@@ -862,7 +875,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
NEIGH_UPDATE_F_OVERRIDE);
if (neigh || !dev->hard_header) {
ndisc_send_na(dev, neigh, saddr, &msg->target,
- idev->cnf.forwarding,
+ is_router,
1, (ifp != NULL && inc), inc);
if (neigh)
neigh_release(neigh);
@@ -945,6 +958,20 @@ static void ndisc_recv_na(struct sk_buff *skb)
if (neigh->nud_state & NUD_FAILED)
goto out;
+ /*
+ * Don't update the neighbor cache entry on a proxy NA from
+ * ourselves because either the proxied node is off link or it
+ * has already sent a NA to us.
+ */
+ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) &&
+ ipv6_devconf.forwarding && ipv6_devconf.proxy_ndp &&
+ pneigh_lookup(&nd_tbl, &msg->target, dev, 0)) {
+ /* XXX: idev->cnf.prixy_ndp */
+ WARN_ON(skb->dst != NULL &&
+ ((struct rt6_info *)skb->dst)->rt6i_idev);
+ goto out;
+ }
+
neigh_update(neigh, lladdr,
msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
@@ -959,7 +986,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
struct rt6_info *rt;
rt = rt6_get_dflt_router(saddr, dev);
if (rt)
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
}
out:
@@ -1112,7 +1139,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (rt && lifetime == 0) {
neigh_clone(neigh);
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
rt = NULL;
}
@@ -1344,7 +1371,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1);
if (neigh) {
- rt6_redirect(dest, &skb->nh.ipv6h->saddr, neigh, lladdr,
+ rt6_redirect(dest, &skb->nh.ipv6h->daddr,
+ &skb->nh.ipv6h->saddr, neigh, lladdr,
on_link);
neigh_release(neigh);
}
@@ -1380,7 +1408,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
return;
}
- ndisc_flow_init(&fl, NDISC_REDIRECT, &saddr_buf, &skb->nh.ipv6h->saddr);
+ ndisc_flow_init(&fl, NDISC_REDIRECT, &saddr_buf, &skb->nh.ipv6h->saddr,
+ dev->ifindex);
dst = ip6_route_output(NULL, &fl);
if (dst == NULL)
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 395a417ba95..580b1aba672 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -87,7 +87,7 @@ unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
unsigned int csum = 0;
switch (skb->ip_summed) {
- case CHECKSUM_HW:
+ case CHECKSUM_COMPLETE:
if (hook != NF_IP6_PRE_ROUTING && hook != NF_IP6_LOCAL_IN)
break;
if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index eeeb57d4c9c..ac1dfebde17 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -5,7 +5,7 @@
# Link order matters here.
obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o
obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
-obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o ip6t_dst.o
+obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o
obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o
obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index 968a14be0d0..9510c24ca8d 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -56,15 +56,15 @@ struct ipq_queue_entry {
typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long);
-static unsigned char copy_mode = IPQ_COPY_NONE;
-static unsigned int queue_maxlen = IPQ_QMAX_DEFAULT;
+static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE;
+static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT;
static DEFINE_RWLOCK(queue_lock);
-static int peer_pid;
-static unsigned int copy_range;
+static int peer_pid __read_mostly;
+static unsigned int copy_range __read_mostly;
static unsigned int queue_total;
static unsigned int queue_dropped = 0;
static unsigned int queue_user_dropped = 0;
-static struct sock *ipqnl;
+static struct sock *ipqnl __read_mostly;
static LIST_HEAD(queue_list);
static DEFINE_MUTEX(ipqnl_mutex);
@@ -206,9 +206,9 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp)
break;
case IPQ_COPY_PACKET:
- if (entry->skb->ip_summed == CHECKSUM_HW &&
- (*errp = skb_checksum_help(entry->skb,
- entry->info->outdev == NULL))) {
+ if ((entry->skb->ip_summed == CHECKSUM_PARTIAL ||
+ entry->skb->ip_summed == CHECKSUM_COMPLETE) &&
+ (*errp = skb_checksum_help(entry->skb))) {
read_unlock_bh(&queue_lock);
return NULL;
}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index c9d6b23cd3f..4ab368fa0b8 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -70,9 +70,6 @@ do { \
#define IP_NF_ASSERT(x)
#endif
-
-#include <linux/netfilter_ipv4/listhelp.h>
-
#if 0
/* All the better to debug you with... */
#define static
@@ -220,8 +217,7 @@ ip6t_error(struct sk_buff **pskb,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
- const void *targinfo,
- void *userinfo)
+ const void *targinfo)
{
if (net_ratelimit())
printk("ip6_tables: error: `%s'\n", (char *)targinfo);
@@ -258,8 +254,7 @@ ip6t_do_table(struct sk_buff **pskb,
unsigned int hook,
const struct net_device *in,
const struct net_device *out,
- struct xt_table *table,
- void *userdata)
+ struct xt_table *table)
{
static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
int offset = 0;
@@ -349,8 +344,7 @@ ip6t_do_table(struct sk_buff **pskb,
in, out,
hook,
t->u.kernel.target,
- t->data,
- userdata);
+ t->data);
#ifdef CONFIG_NETFILTER_DEBUG
if (((struct ip6t_entry *)table_base)->comefrom
@@ -507,8 +501,7 @@ cleanup_match(struct ip6t_entry_match *m, unsigned int *i)
return 1;
if (m->u.kernel.match->destroy)
- m->u.kernel.match->destroy(m->u.kernel.match, m->data,
- m->u.match_size - sizeof(*m));
+ m->u.kernel.match->destroy(m->u.kernel.match, m->data);
module_put(m->u.kernel.match->me);
return 0;
}
@@ -561,7 +554,6 @@ check_match(struct ip6t_entry_match *m,
if (m->u.kernel.match->checkentry
&& !m->u.kernel.match->checkentry(name, ipv6, match, m->data,
- m->u.match_size - sizeof(*m),
hookmask)) {
duprintf("ip_tables: check failed for `%s'.\n",
m->u.kernel.match->name);
@@ -618,12 +610,10 @@ check_entry(struct ip6t_entry *e, const char *name, unsigned int size,
if (t->u.kernel.target == &ip6t_standard_target) {
if (!standard_check(t, size)) {
ret = -EINVAL;
- goto cleanup_matches;
+ goto err;
}
} else if (t->u.kernel.target->checkentry
&& !t->u.kernel.target->checkentry(name, e, target, t->data,
- t->u.target_size
- - sizeof(*t),
e->comefrom)) {
duprintf("ip_tables: check failed for `%s'.\n",
t->u.kernel.target->name);
@@ -695,8 +685,7 @@ cleanup_entry(struct ip6t_entry *e, unsigned int *i)
IP6T_MATCH_ITERATE(e, cleanup_match, NULL);
t = ip6t_get_target(e);
if (t->u.kernel.target->destroy)
- t->u.kernel.target->destroy(t->u.kernel.target, t->data,
- t->u.target_size - sizeof(*t));
+ t->u.kernel.target->destroy(t->u.kernel.target, t->data);
module_put(t->u.kernel.target->me);
return 0;
}
@@ -1352,7 +1341,6 @@ icmp6_checkentry(const char *tablename,
const void *entry,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchsize,
unsigned int hook_mask)
{
const struct ip6t_icmp *icmpinfo = matchinfo;
diff --git a/net/ipv6/netfilter/ip6t_HL.c b/net/ipv6/netfilter/ip6t_HL.c
index b8eff8ee69b..435750f664d 100644
--- a/net/ipv6/netfilter/ip6t_HL.c
+++ b/net/ipv6/netfilter/ip6t_HL.c
@@ -22,11 +22,10 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
- const void *targinfo, void *userinfo)
+ const void *targinfo)
{
struct ipv6hdr *ip6h;
const struct ip6t_HL_info *info = targinfo;
- u_int16_t diffs[2];
int new_hl;
if (!skb_make_writable(pskb, (*pskb)->len))
@@ -53,11 +52,8 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb,
break;
}
- if (new_hl != ip6h->hop_limit) {
- diffs[0] = htons(((unsigned)ip6h->hop_limit) << 8) ^ 0xFFFF;
+ if (new_hl != ip6h->hop_limit)
ip6h->hop_limit = new_hl;
- diffs[1] = htons(((unsigned)ip6h->hop_limit) << 8);
- }
return IP6T_CONTINUE;
}
@@ -66,7 +62,6 @@ static int ip6t_hl_checkentry(const char *tablename,
const void *entry,
const struct xt_target *target,
void *targinfo,
- unsigned int targinfosize,
unsigned int hook_mask)
{
struct ip6t_HL_info *info = targinfo;
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index 73c6300109d..0cf537d3018 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -427,8 +427,7 @@ ip6t_log_target(struct sk_buff **pskb,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
- const void *targinfo,
- void *userinfo)
+ const void *targinfo)
{
const struct ip6t_log_info *loginfo = targinfo;
struct nf_loginfo li;
@@ -452,7 +451,6 @@ static int ip6t_log_checkentry(const char *tablename,
const void *entry,
const struct xt_target *target,
void *targinfo,
- unsigned int targinfosize,
unsigned int hook_mask)
{
const struct ip6t_log_info *loginfo = targinfo;
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 8629ba195d2..311eae82feb 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -96,6 +96,7 @@ static void send_reset(struct sk_buff *oldskb)
ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr);
fl.fl_ip_sport = otcph.dest;
fl.fl_ip_dport = otcph.source;
+ security_skb_classify_flow(oldskb, &fl);
dst = ip6_route_output(NULL, &fl);
if (dst == NULL)
return;
@@ -179,8 +180,7 @@ static unsigned int reject6_target(struct sk_buff **pskb,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
- const void *targinfo,
- void *userinfo)
+ const void *targinfo)
{
const struct ip6t_reject_info *reject = targinfo;
@@ -223,7 +223,6 @@ static int check(const char *tablename,
const void *entry,
const struct xt_target *target,
void *targinfo,
- unsigned int targinfosize,
unsigned int hook_mask)
{
const struct ip6t_reject_info *rejinfo = targinfo;
@@ -256,9 +255,7 @@ static struct ip6t_target ip6t_reject_reg = {
static int __init ip6t_reject_init(void)
{
- if (ip6t_register_target(&ip6t_reject_reg))
- return -EINVAL;
- return 0;
+ return ip6t_register_target(&ip6t_reject_reg);
}
static void __exit ip6t_reject_fini(void)
diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c
index 2f7bb20c758..ec1b1608156 100644
--- a/net/ipv6/netfilter/ip6t_ah.c
+++ b/net/ipv6/netfilter/ip6t_ah.c
@@ -102,7 +102,6 @@ checkentry(const char *tablename,
const void *entry,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchinfosize,
unsigned int hook_mask)
{
const struct ip6t_ah *ahinfo = matchinfo;
diff --git a/net/ipv6/netfilter/ip6t_dst.c b/net/ipv6/netfilter/ip6t_dst.c
deleted file mode 100644
index 9422413d057..00000000000
--- a/net/ipv6/netfilter/ip6t_dst.c
+++ /dev/null
@@ -1,220 +0,0 @@
-/* Kernel module to match Hop-by-Hop and Destination parameters. */
-
-/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/ipv6.h>
-#include <linux/types.h>
-#include <net/checksum.h>
-#include <net/ipv6.h>
-
-#include <asm/byteorder.h>
-
-#include <linux/netfilter_ipv6/ip6_tables.h>
-#include <linux/netfilter_ipv6/ip6t_opts.h>
-
-#define HOPBYHOP 0
-
-MODULE_LICENSE("GPL");
-#if HOPBYHOP
-MODULE_DESCRIPTION("IPv6 HbH match");
-#else
-MODULE_DESCRIPTION("IPv6 DST match");
-#endif
-MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
-
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(format, args...)
-#endif
-
-/*
- * (Type & 0xC0) >> 6
- * 0 -> ignorable
- * 1 -> must drop the packet
- * 2 -> send ICMP PARM PROB regardless and drop packet
- * 3 -> Send ICMP if not a multicast address and drop packet
- * (Type & 0x20) >> 5
- * 0 -> invariant
- * 1 -> can change the routing
- * (Type & 0x1F) Type
- * 0 -> Pad1 (only 1 byte!)
- * 1 -> PadN LENGTH info (total length = length + 2)
- * C0 | 2 -> JUMBO 4 x x x x ( xxxx > 64k )
- * 5 -> RTALERT 2 x x
- */
-
-static int
-match(const struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- const struct xt_match *match,
- const void *matchinfo,
- int offset,
- unsigned int protoff,
- int *hotdrop)
-{
- struct ipv6_opt_hdr _optsh, *oh;
- const struct ip6t_opts *optinfo = matchinfo;
- unsigned int temp;
- unsigned int ptr;
- unsigned int hdrlen = 0;
- unsigned int ret = 0;
- u8 _opttype, *tp = NULL;
- u8 _optlen, *lp = NULL;
- unsigned int optlen;
-
-#if HOPBYHOP
- if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP, NULL) < 0)
-#else
- if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST, NULL) < 0)
-#endif
- return 0;
-
- oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh);
- if (oh == NULL) {
- *hotdrop = 1;
- return 0;
- }
-
- hdrlen = ipv6_optlen(oh);
- if (skb->len - ptr < hdrlen) {
- /* Packet smaller than it's length field */
- return 0;
- }
-
- DEBUGP("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen);
-
- DEBUGP("len %02X %04X %02X ",
- optinfo->hdrlen, hdrlen,
- (!(optinfo->flags & IP6T_OPTS_LEN) ||
- ((optinfo->hdrlen == hdrlen) ^
- !!(optinfo->invflags & IP6T_OPTS_INV_LEN))));
-
- ret = (oh != NULL) &&
- (!(optinfo->flags & IP6T_OPTS_LEN) ||
- ((optinfo->hdrlen == hdrlen) ^
- !!(optinfo->invflags & IP6T_OPTS_INV_LEN)));
-
- ptr += 2;
- hdrlen -= 2;
- if (!(optinfo->flags & IP6T_OPTS_OPTS)) {
- return ret;
- } else if (optinfo->flags & IP6T_OPTS_NSTRICT) {
- DEBUGP("Not strict - not implemented");
- } else {
- DEBUGP("Strict ");
- DEBUGP("#%d ", optinfo->optsnr);
- for (temp = 0; temp < optinfo->optsnr; temp++) {
- /* type field exists ? */
- if (hdrlen < 1)
- break;
- tp = skb_header_pointer(skb, ptr, sizeof(_opttype),
- &_opttype);
- if (tp == NULL)
- break;
-
- /* Type check */
- if (*tp != (optinfo->opts[temp] & 0xFF00) >> 8) {
- DEBUGP("Tbad %02X %02X\n",
- *tp,
- (optinfo->opts[temp] & 0xFF00) >> 8);
- return 0;
- } else {
- DEBUGP("Tok ");
- }
- /* Length check */
- if (*tp) {
- u16 spec_len;
-
- /* length field exists ? */
- if (hdrlen < 2)
- break;
- lp = skb_header_pointer(skb, ptr + 1,
- sizeof(_optlen),
- &_optlen);
- if (lp == NULL)
- break;
- spec_len = optinfo->opts[temp] & 0x00FF;
-
- if (spec_len != 0x00FF && spec_len != *lp) {
- DEBUGP("Lbad %02X %04X\n", *lp,
- spec_len);
- return 0;
- }
- DEBUGP("Lok ");
- optlen = *lp + 2;
- } else {
- DEBUGP("Pad1\n");
- optlen = 1;
- }
-
- /* Step to the next */
- DEBUGP("len%04X \n", optlen);
-
- if ((ptr > skb->len - optlen || hdrlen < optlen) &&
- (temp < optinfo->optsnr - 1)) {
- DEBUGP("new pointer is too large! \n");
- break;
- }
- ptr += optlen;
- hdrlen -= optlen;
- }
- if (temp == optinfo->optsnr)
- return ret;
- else
- return 0;
- }
-
- return 0;
-}
-
-/* Called when user tries to insert an entry of this type. */
-static int
-checkentry(const char *tablename,
- const void *info,
- const struct xt_match *match,
- void *matchinfo,
- unsigned int matchinfosize,
- unsigned int hook_mask)
-{
- const struct ip6t_opts *optsinfo = matchinfo;
-
- if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) {
- DEBUGP("ip6t_opts: unknown flags %X\n", optsinfo->invflags);
- return 0;
- }
- return 1;
-}
-
-static struct ip6t_match opts_match = {
-#if HOPBYHOP
- .name = "hbh",
-#else
- .name = "dst",
-#endif
- .match = match,
- .matchsize = sizeof(struct ip6t_opts),
- .checkentry = checkentry,
- .me = THIS_MODULE,
-};
-
-static int __init ip6t_dst_init(void)
-{
- return ip6t_register_match(&opts_match);
-}
-
-static void __exit ip6t_dst_fini(void)
-{
- ip6t_unregister_match(&opts_match);
-}
-
-module_init(ip6t_dst_init);
-module_exit(ip6t_dst_fini);
diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c
index 06768c84bd3..78d9c8b9e28 100644
--- a/net/ipv6/netfilter/ip6t_frag.c
+++ b/net/ipv6/netfilter/ip6t_frag.c
@@ -119,7 +119,6 @@ checkentry(const char *tablename,
const void *ip,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchinfosize,
unsigned int hook_mask)
{
const struct ip6t_frag *fraginfo = matchinfo;
diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c
index 374f1be85c0..d32a205e3af 100644
--- a/net/ipv6/netfilter/ip6t_hbh.c
+++ b/net/ipv6/netfilter/ip6t_hbh.c
@@ -19,15 +19,10 @@
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/netfilter_ipv6/ip6t_opts.h>
-#define HOPBYHOP 1
-
MODULE_LICENSE("GPL");
-#if HOPBYHOP
-MODULE_DESCRIPTION("IPv6 HbH match");
-#else
-MODULE_DESCRIPTION("IPv6 DST match");
-#endif
+MODULE_DESCRIPTION("IPv6 opts match");
MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+MODULE_ALIAS("ip6t_dst");
#if 0
#define DEBUGP printk
@@ -71,11 +66,7 @@ match(const struct sk_buff *skb,
u8 _optlen, *lp = NULL;
unsigned int optlen;
-#if HOPBYHOP
- if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP, NULL) < 0)
-#else
- if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST, NULL) < 0)
-#endif
+ if (ipv6_find_hdr(skb, &ptr, match->data, NULL) < 0)
return 0;
oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh);
@@ -182,7 +173,6 @@ checkentry(const char *tablename,
const void *entry,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchinfosize,
unsigned int hook_mask)
{
const struct ip6t_opts *optsinfo = matchinfo;
@@ -194,26 +184,35 @@ checkentry(const char *tablename,
return 1;
}
-static struct ip6t_match opts_match = {
-#if HOPBYHOP
- .name = "hbh",
-#else
- .name = "dst",
-#endif
- .match = match,
- .matchsize = sizeof(struct ip6t_opts),
- .checkentry = checkentry,
- .me = THIS_MODULE,
+static struct xt_match opts_match[] = {
+ {
+ .name = "hbh",
+ .family = AF_INET6,
+ .match = match,
+ .matchsize = sizeof(struct ip6t_opts),
+ .checkentry = checkentry,
+ .me = THIS_MODULE,
+ .data = NEXTHDR_HOP,
+ },
+ {
+ .name = "dst",
+ .family = AF_INET6,
+ .match = match,
+ .matchsize = sizeof(struct ip6t_opts),
+ .checkentry = checkentry,
+ .me = THIS_MODULE,
+ .data = NEXTHDR_DEST,
+ },
};
static int __init ip6t_hbh_init(void)
{
- return ip6t_register_match(&opts_match);
+ return xt_register_matches(opts_match, ARRAY_SIZE(opts_match));
}
static void __exit ip6t_hbh_fini(void)
{
- ip6t_unregister_match(&opts_match);
+ xt_unregister_matches(opts_match, ARRAY_SIZE(opts_match));
}
module_init(ip6t_hbh_init);
diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c
index 9375eeb1369..3093c398002 100644
--- a/net/ipv6/netfilter/ip6t_ipv6header.c
+++ b/net/ipv6/netfilter/ip6t_ipv6header.c
@@ -128,7 +128,6 @@ ipv6header_checkentry(const char *tablename,
const void *ip,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchsize,
unsigned int hook_mask)
{
const struct ip6t_ipv6header_info *info = matchinfo;
diff --git a/net/ipv6/netfilter/ip6t_owner.c b/net/ipv6/netfilter/ip6t_owner.c
index 5d047990cd4..4eb9bbc4ebc 100644
--- a/net/ipv6/netfilter/ip6t_owner.c
+++ b/net/ipv6/netfilter/ip6t_owner.c
@@ -57,7 +57,6 @@ checkentry(const char *tablename,
const void *ip,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchsize,
unsigned int hook_mask)
{
const struct ip6t_owner_info *info = matchinfo;
diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index fbb0184a41d..bcb2e168a5b 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -197,7 +197,6 @@ checkentry(const char *tablename,
const void *entry,
const struct xt_match *match,
void *matchinfo,
- unsigned int matchinfosize,
unsigned int hook_mask)
{
const struct ip6t_rt *rtinfo = matchinfo;
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 60976c0c58e..2fc07c74dec 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -108,7 +108,7 @@ ip6t_hook(unsigned int hook,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL);
+ return ip6t_do_table(pskb, hook, in, out, &packet_filter);
}
static unsigned int
@@ -128,7 +128,7 @@ ip6t_local_out_hook(unsigned int hook,
}
#endif
- return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL);
+ return ip6t_do_table(pskb, hook, in, out, &packet_filter);
}
static struct nf_hook_ops ip6t_ops[] = {
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 03a13eab1da..386ea260e76 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -138,7 +138,7 @@ ip6t_route_hook(unsigned int hook,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL);
+ return ip6t_do_table(pskb, hook, in, out, &packet_mangler);
}
static unsigned int
@@ -174,18 +174,14 @@ ip6t_local_hook(unsigned int hook,
/* flowlabel and prio (includes version, which shouldn't change either */
flowlabel = *((u_int32_t *) (*pskb)->nh.ipv6h);
- ret = ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL);
+ ret = ip6t_do_table(pskb, hook, in, out, &packet_mangler);
if (ret != NF_DROP && ret != NF_STOLEN
&& (memcmp(&(*pskb)->nh.ipv6h->saddr, &saddr, sizeof(saddr))
|| memcmp(&(*pskb)->nh.ipv6h->daddr, &daddr, sizeof(daddr))
|| (*pskb)->nfmark != nfmark
- || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) {
-
- /* something which could affect routing has changed */
-
- DEBUGP("ip6table_mangle: we'd need to re-route a packet\n");
- }
+ || (*pskb)->nh.ipv6h->hop_limit != hop_limit))
+ return ip6_route_me_harder(*pskb) == 0 ? ret : NF_DROP;
return ret;
}
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 61a7c58e99f..b4154da575c 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -122,7 +122,7 @@ ip6t_hook(unsigned int hook,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip6t_do_table(pskb, hook, in, out, &packet_raw, NULL);
+ return ip6t_do_table(pskb, hook, in, out, &packet_raw);
}
static struct nf_hook_ops ip6t_ops[] = {
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index c2ab38ff46a..e5e53fff9e3 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -335,7 +335,7 @@ static struct nf_hook_ops ipv6_conntrack_ops[] = {
/* From nf_conntrack_proto_icmpv6.c */
extern unsigned int nf_ct_icmpv6_timeout;
-/* From nf_conntrack_frag6.c */
+/* From nf_conntrack_reasm.c */
extern unsigned int nf_ct_frag6_timeout;
extern unsigned int nf_ct_frag6_low_thresh;
extern unsigned int nf_ct_frag6_high_thresh;
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index ef18a7b7014..34d447208ff 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -33,7 +33,7 @@
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
-unsigned long nf_ct_icmpv6_timeout = 30*HZ;
+unsigned long nf_ct_icmpv6_timeout __read_mostly = 30*HZ;
#if 0
#define DEBUGP printk
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 00d5583807f..bf93c1ea6be 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -54,9 +54,9 @@
#define NF_CT_FRAG6_LOW_THRESH 196608 /* == 192*1024 */
#define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT
-unsigned int nf_ct_frag6_high_thresh = 256*1024;
-unsigned int nf_ct_frag6_low_thresh = 192*1024;
-unsigned long nf_ct_frag6_timeout = IPV6_FRAG_TIMEOUT;
+unsigned int nf_ct_frag6_high_thresh __read_mostly = 256*1024;
+unsigned int nf_ct_frag6_low_thresh __read_mostly = 192*1024;
+unsigned long nf_ct_frag6_timeout __read_mostly = IPV6_FRAG_TIMEOUT;
struct nf_ct_frag6_skb_cb
{
@@ -408,7 +408,7 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
return -1;
}
- if (skb->ip_summed == CHECKSUM_HW)
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum,
csum_partial(skb->nh.raw,
(u8*)(fhdr + 1) - skb->nh.raw,
@@ -640,7 +640,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_HW)
+ else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
atomic_sub(fp->truesize, &nf_ct_frag6_mem);
@@ -652,7 +652,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
head->nh.ipv6h->payload_len = htons(payload_len);
/* Yes, and fold redundant checksum back. 8) */
- if (head->ip_summed == CHECKSUM_HW)
+ if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);
fq->fragments = NULL;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 15b862d8aca..d09329ca326 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -50,6 +50,9 @@
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/tcp_states.h>
+#ifdef CONFIG_IPV6_MIP6
+#include <net/mip6.h>
+#endif
#include <net/rawv6.h>
#include <net/xfrm.h>
@@ -169,8 +172,32 @@ int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, IP6CB(skb)->iif);
while (sk) {
+ int filtered;
+
delivered = 1;
- if (nexthdr != IPPROTO_ICMPV6 || !icmpv6_filter(sk, skb)) {
+ switch (nexthdr) {
+ case IPPROTO_ICMPV6:
+ filtered = icmpv6_filter(sk, skb);
+ break;
+#ifdef CONFIG_IPV6_MIP6
+ case IPPROTO_MH:
+ /* XXX: To validate MH only once for each packet,
+ * this is placed here. It should be after checking
+ * xfrm policy, however it doesn't. The checking xfrm
+ * policy is placed in rawv6_rcv() because it is
+ * required for each socket.
+ */
+ filtered = mip6_mh_filter(sk, skb);
+ break;
+#endif
+ default:
+ filtered = 0;
+ break;
+ }
+
+ if (filtered < 0)
+ break;
+ if (filtered == 0) {
struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
/* Not releasing hash table! */
@@ -334,7 +361,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
if (!rp->checksum)
skb->ip_summed = CHECKSUM_UNNECESSARY;
- if (skb->ip_summed == CHECKSUM_HW) {
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
skb_postpull_rcsum(skb, skb->nh.raw,
skb->h.raw - skb->nh.raw);
if (!csum_ipv6_magic(&skb->nh.ipv6h->saddr,
@@ -582,6 +609,9 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
struct iovec *iov;
u8 __user *type = NULL;
u8 __user *code = NULL;
+#ifdef CONFIG_IPV6_MIP6
+ u8 len = 0;
+#endif
int probed = 0;
int i;
@@ -613,6 +643,20 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
probed = 1;
}
break;
+#ifdef CONFIG_IPV6_MIP6
+ case IPPROTO_MH:
+ if (iov->iov_base && iov->iov_len < 1)
+ break;
+ /* check if type field is readable or not. */
+ if (iov->iov_len > 2 - len) {
+ u8 __user *p = iov->iov_base;
+ get_user(fl->fl_mh_type, &p[2 - len]);
+ probed = 1;
+ } else
+ len += iov->iov_len;
+
+ break;
+#endif
default:
probed = 1;
break;
@@ -759,6 +803,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
fl.oif = np->mcast_oif;
+ security_sk_classify_flow(sk, &fl);
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 4e299c69e1c..f39bbedd132 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -53,10 +53,10 @@
#include <net/ndisc.h>
#include <net/addrconf.h>
-int sysctl_ip6frag_high_thresh = 256*1024;
-int sysctl_ip6frag_low_thresh = 192*1024;
+int sysctl_ip6frag_high_thresh __read_mostly = 256*1024;
+int sysctl_ip6frag_low_thresh __read_mostly = 192*1024;
-int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT;
+int sysctl_ip6frag_time __read_mostly = IPV6_FRAG_TIMEOUT;
struct ip6frag_skb_cb
{
@@ -152,7 +152,7 @@ static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr,
}
static struct timer_list ip6_frag_secret_timer;
-int sysctl_ip6frag_secret_interval = 10 * 60 * HZ;
+int sysctl_ip6frag_secret_interval __read_mostly = 10 * 60 * HZ;
static void ip6_frag_secret_rebuild(unsigned long dummy)
{
@@ -433,7 +433,7 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
return;
}
- if (skb->ip_summed == CHECKSUM_HW)
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum,
csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0));
@@ -647,7 +647,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_HW)
+ else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
atomic_sub(fp->truesize, &ip6_frag_mem);
@@ -662,7 +662,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
*skb_in = head;
/* Yes, and fold redundant checksum back. 8) */
- if (head->ip_summed == CHECKSUM_HW)
+ if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);
IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d9baca062d2..d6b4b4f48d1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -22,6 +22,8 @@
* routers in REACHABLE, STALE, DELAY or PROBE states).
* - always select the same router if it is (probably)
* reachable. otherwise, round-robin the list.
+ * Ville Nuorvala
+ * Fixed routing subtrees.
*/
#include <linux/capability.h>
@@ -35,7 +37,6 @@
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
-#include <linux/netlink.h>
#include <linux/if_arp.h>
#ifdef CONFIG_PROC_FS
@@ -54,6 +55,7 @@
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/netevent.h>
+#include <net/netlink.h>
#include <asm/uaccess.h>
@@ -74,9 +76,6 @@
#define CLONE_OFFLINK_ROUTE 0
-#define RT6_SELECT_F_IFACE 0x1
-#define RT6_SELECT_F_REACHABLE 0x2
-
static int ip6_rt_max_size = 4096;
static int ip6_rt_gc_min_interval = HZ / 2;
static int ip6_rt_gc_timeout = 60*HZ;
@@ -140,15 +139,49 @@ struct rt6_info ip6_null_entry = {
.rt6i_ref = ATOMIC_INIT(1),
};
-struct fib6_node ip6_routing_table = {
- .leaf = &ip6_null_entry,
- .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
-};
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-/* Protects all the ip6 fib */
+struct rt6_info ip6_prohibit_entry = {
+ .u = {
+ .dst = {
+ .__refcnt = ATOMIC_INIT(1),
+ .__use = 1,
+ .dev = &loopback_dev,
+ .obsolete = -1,
+ .error = -EACCES,
+ .metrics = { [RTAX_HOPLIMIT - 1] = 255, },
+ .input = ip6_pkt_discard,
+ .output = ip6_pkt_discard_out,
+ .ops = &ip6_dst_ops,
+ .path = (struct dst_entry*)&ip6_prohibit_entry,
+ }
+ },
+ .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_metric = ~(u32) 0,
+ .rt6i_ref = ATOMIC_INIT(1),
+};
-DEFINE_RWLOCK(rt6_lock);
+struct rt6_info ip6_blk_hole_entry = {
+ .u = {
+ .dst = {
+ .__refcnt = ATOMIC_INIT(1),
+ .__use = 1,
+ .dev = &loopback_dev,
+ .obsolete = -1,
+ .error = -EINVAL,
+ .metrics = { [RTAX_HOPLIMIT - 1] = 255, },
+ .input = ip6_pkt_discard,
+ .output = ip6_pkt_discard_out,
+ .ops = &ip6_dst_ops,
+ .path = (struct dst_entry*)&ip6_blk_hole_entry,
+ }
+ },
+ .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .rt6i_metric = ~(u32) 0,
+ .rt6i_ref = ATOMIC_INIT(1),
+};
+#endif
/* allocate dst with ip6_dst_ops */
static __inline__ struct rt6_info *ip6_dst_alloc(void)
@@ -188,8 +221,14 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt)
time_after(jiffies, rt->rt6i_expires));
}
+static inline int rt6_need_strict(struct in6_addr *daddr)
+{
+ return (ipv6_addr_type(daddr) &
+ (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
+}
+
/*
- * Route lookup. Any rt6_lock is implied.
+ * Route lookup. Any table->tb6_lock is implied.
*/
static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
@@ -298,7 +337,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
int m, n;
m = rt6_check_dev(rt, oif);
- if (!m && (strict & RT6_SELECT_F_IFACE))
+ if (!m && (strict & RT6_LOOKUP_F_IFACE))
return -1;
#ifdef CONFIG_IPV6_ROUTER_PREF
m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
@@ -306,7 +345,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
n = rt6_check_neigh(rt);
if (n > 1)
m |= 16;
- else if (!n && strict & RT6_SELECT_F_REACHABLE)
+ else if (!n && strict & RT6_LOOKUP_F_REACHABLE)
return -1;
return m;
}
@@ -346,7 +385,7 @@ static struct rt6_info *rt6_select(struct rt6_info **head, int oif,
}
if (!match &&
- (strict & RT6_SELECT_F_REACHABLE) &&
+ (strict & RT6_LOOKUP_F_REACHABLE) &&
last && last != rt0) {
/* no entries matched; do round-robin */
static DEFINE_SPINLOCK(lock);
@@ -417,7 +456,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex);
if (rt && !lifetime) {
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
rt = NULL;
}
@@ -441,44 +480,95 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
#endif
-struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
- int oif, int strict)
+#define BACKTRACK(saddr) \
+do { \
+ if (rt == &ip6_null_entry) { \
+ struct fib6_node *pn; \
+ while (fn) { \
+ if (fn->fn_flags & RTN_TL_ROOT) \
+ goto out; \
+ pn = fn->parent; \
+ if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
+ fn = fib6_lookup(pn->subtree, NULL, saddr); \
+ else \
+ fn = pn; \
+ if (fn->fn_flags & RTN_RTINFO) \
+ goto restart; \
+ } \
+ } \
+} while(0)
+
+static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table,
+ struct flowi *fl, int flags)
{
struct fib6_node *fn;
struct rt6_info *rt;
- read_lock_bh(&rt6_lock);
- fn = fib6_lookup(&ip6_routing_table, daddr, saddr);
- rt = rt6_device_match(fn->leaf, oif, strict);
+ read_lock_bh(&table->tb6_lock);
+ fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+restart:
+ rt = fn->leaf;
+ rt = rt6_device_match(rt, fl->oif, flags);
+ BACKTRACK(&fl->fl6_src);
+out:
dst_hold(&rt->u.dst);
- rt->u.dst.__use++;
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
rt->u.dst.lastuse = jiffies;
- if (rt->u.dst.error == 0)
- return rt;
- dst_release(&rt->u.dst);
+ rt->u.dst.__use++;
+
+ return rt;
+
+}
+
+struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
+ int oif, int strict)
+{
+ struct flowi fl = {
+ .oif = oif,
+ .nl_u = {
+ .ip6_u = {
+ .daddr = *daddr,
+ /* TODO: saddr */
+ },
+ },
+ };
+ struct dst_entry *dst;
+ int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
+
+ dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
+ if (dst->error == 0)
+ return (struct rt6_info *) dst;
+
+ dst_release(dst);
+
return NULL;
}
-/* ip6_ins_rt is called with FREE rt6_lock.
+/* ip6_ins_rt is called with FREE table->tb6_lock.
It takes new route entry, the addition fails by any reason the
route is freed. In any case, if caller does not hold it, it may
be destroyed.
*/
-int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh,
- void *_rtattr, struct netlink_skb_parms *req)
+static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
{
int err;
+ struct fib6_table *table;
- write_lock_bh(&rt6_lock);
- err = fib6_add(&ip6_routing_table, rt, nlh, _rtattr, req);
- write_unlock_bh(&rt6_lock);
+ table = rt->rt6i_table;
+ write_lock_bh(&table->tb6_lock);
+ err = fib6_add(&table->tb6_root, rt, info);
+ write_unlock_bh(&table->tb6_lock);
return err;
}
+int ip6_ins_rt(struct rt6_info *rt)
+{
+ return __ip6_ins_rt(rt, NULL);
+}
+
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
struct in6_addr *saddr)
{
@@ -532,51 +622,39 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d
return rt;
}
-#define BACKTRACK() \
-if (rt == &ip6_null_entry) { \
- while ((fn = fn->parent) != NULL) { \
- if (fn->fn_flags & RTN_ROOT) { \
- goto out; \
- } \
- if (fn->fn_flags & RTN_RTINFO) \
- goto restart; \
- } \
-}
-
-
-void ip6_route_input(struct sk_buff *skb)
+static struct rt6_info *ip6_pol_route_input(struct fib6_table *table,
+ struct flowi *fl, int flags)
{
struct fib6_node *fn;
struct rt6_info *rt, *nrt;
- int strict;
+ int strict = 0;
int attempts = 3;
int err;
- int reachable = RT6_SELECT_F_REACHABLE;
+ int reachable = RT6_LOOKUP_F_REACHABLE;
- strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0;
+ strict |= flags & RT6_LOOKUP_F_IFACE;
relookup:
- read_lock_bh(&rt6_lock);
+ read_lock_bh(&table->tb6_lock);
restart_2:
- fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr,
- &skb->nh.ipv6h->saddr);
+ fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
- rt = rt6_select(&fn->leaf, skb->dev->ifindex, strict | reachable);
- BACKTRACK();
+ rt = rt6_select(&fn->leaf, fl->iif, strict | reachable);
+ BACKTRACK(&fl->fl6_src);
if (rt == &ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
goto out;
dst_hold(&rt->u.dst);
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
- nrt = rt6_alloc_cow(rt, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr);
+ nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
else {
#if CLONE_OFFLINK_ROUTE
- nrt = rt6_alloc_clone(rt, &skb->nh.ipv6h->daddr);
+ nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
#else
goto out2;
#endif
@@ -587,7 +665,7 @@ restart:
dst_hold(&rt->u.dst);
if (nrt) {
- err = ip6_ins_rt(nrt, NULL, NULL, &NETLINK_CB(skb));
+ err = ip6_ins_rt(nrt);
if (!err)
goto out2;
}
@@ -596,7 +674,7 @@ restart:
goto out2;
/*
- * Race condition! In the gap, when rt6_lock was
+ * Race condition! In the gap, when table->tb6_lock was
* released someone could insert this route. Relookup.
*/
dst_release(&rt->u.dst);
@@ -608,40 +686,63 @@ out:
goto restart_2;
}
dst_hold(&rt->u.dst);
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
out2:
rt->u.dst.lastuse = jiffies;
rt->u.dst.__use++;
- skb->dst = (struct dst_entry *) rt;
- return;
+
+ return rt;
}
-struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
+void ip6_route_input(struct sk_buff *skb)
+{
+ struct ipv6hdr *iph = skb->nh.ipv6h;
+ struct flowi fl = {
+ .iif = skb->dev->ifindex,
+ .nl_u = {
+ .ip6_u = {
+ .daddr = iph->daddr,
+ .saddr = iph->saddr,
+#ifdef CONFIG_IPV6_ROUTE_FWMARK
+ .fwmark = skb->nfmark,
+#endif
+ .flowlabel = (* (u32 *) iph)&IPV6_FLOWINFO_MASK,
+ },
+ },
+ .proto = iph->nexthdr,
+ };
+ int flags = rt6_need_strict(&iph->daddr) ? RT6_LOOKUP_F_IFACE : 0;
+
+ skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input);
+}
+
+static struct rt6_info *ip6_pol_route_output(struct fib6_table *table,
+ struct flowi *fl, int flags)
{
struct fib6_node *fn;
struct rt6_info *rt, *nrt;
- int strict;
+ int strict = 0;
int attempts = 3;
int err;
- int reachable = RT6_SELECT_F_REACHABLE;
+ int reachable = RT6_LOOKUP_F_REACHABLE;
- strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0;
+ strict |= flags & RT6_LOOKUP_F_IFACE;
relookup:
- read_lock_bh(&rt6_lock);
+ read_lock_bh(&table->tb6_lock);
restart_2:
- fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src);
+ fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
rt = rt6_select(&fn->leaf, fl->oif, strict | reachable);
- BACKTRACK();
+ BACKTRACK(&fl->fl6_src);
if (rt == &ip6_null_entry ||
rt->rt6i_flags & RTF_CACHE)
goto out;
dst_hold(&rt->u.dst);
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
@@ -658,7 +759,7 @@ restart:
dst_hold(&rt->u.dst);
if (nrt) {
- err = ip6_ins_rt(nrt, NULL, NULL, NULL);
+ err = ip6_ins_rt(nrt);
if (!err)
goto out2;
}
@@ -667,7 +768,7 @@ restart:
goto out2;
/*
- * Race condition! In the gap, when rt6_lock was
+ * Race condition! In the gap, when table->tb6_lock was
* released someone could insert this route. Relookup.
*/
dst_release(&rt->u.dst);
@@ -679,11 +780,21 @@ out:
goto restart_2;
}
dst_hold(&rt->u.dst);
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
out2:
rt->u.dst.lastuse = jiffies;
rt->u.dst.__use++;
- return &rt->u.dst;
+ return rt;
+}
+
+struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
+{
+ int flags = 0;
+
+ if (rt6_need_strict(&fl->fl6_dst))
+ flags |= RT6_LOOKUP_F_IFACE;
+
+ return fib6_rule_lookup(fl, flags, ip6_pol_route_output);
}
@@ -709,7 +820,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
if (rt) {
if (rt->rt6i_flags & RTF_CACHE)
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
else
dst_release(dst);
}
@@ -747,8 +858,6 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
}
}
-/* Protected by rt6_lock. */
-static struct dst_entry *ndisc_dst_gc_list;
static int ipv6_get_mtu(struct net_device *dev);
static inline unsigned int ipv6_advmss(unsigned int mtu)
@@ -769,6 +878,9 @@ static inline unsigned int ipv6_advmss(unsigned int mtu)
return mtu;
}
+static struct dst_entry *ndisc_dst_gc_list;
+static DEFINE_SPINLOCK(ndisc_lock);
+
struct dst_entry *ndisc_dst_alloc(struct net_device *dev,
struct neighbour *neigh,
struct in6_addr *addr,
@@ -809,10 +921,10 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev,
rt->rt6i_dst.plen = 128;
#endif
- write_lock_bh(&rt6_lock);
+ spin_lock_bh(&ndisc_lock);
rt->u.dst.next = ndisc_dst_gc_list;
ndisc_dst_gc_list = &rt->u.dst;
- write_unlock_bh(&rt6_lock);
+ spin_unlock_bh(&ndisc_lock);
fib6_force_start_gc();
@@ -826,8 +938,11 @@ int ndisc_dst_gc(int *more)
int freed;
next = NULL;
+ freed = 0;
+
+ spin_lock_bh(&ndisc_lock);
pprev = &ndisc_dst_gc_list;
- freed = 0;
+
while ((dst = *pprev) != NULL) {
if (!atomic_read(&dst->__refcnt)) {
*pprev = dst->next;
@@ -839,6 +954,8 @@ int ndisc_dst_gc(int *more)
}
}
+ spin_unlock_bh(&ndisc_lock);
+
return freed;
}
@@ -899,28 +1016,24 @@ int ipv6_get_hoplimit(struct net_device *dev)
*
*/
-int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
- void *_rtattr, struct netlink_skb_parms *req)
+int ip6_route_add(struct fib6_config *cfg)
{
int err;
- struct rtmsg *r;
- struct rtattr **rta;
struct rt6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
+ struct fib6_table *table;
int addr_type;
- rta = (struct rtattr **) _rtattr;
-
- if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128)
+ if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
- if (rtmsg->rtmsg_src_len)
+ if (cfg->fc_src_len)
return -EINVAL;
#endif
- if (rtmsg->rtmsg_ifindex) {
+ if (cfg->fc_ifindex) {
err = -ENODEV;
- dev = dev_get_by_index(rtmsg->rtmsg_ifindex);
+ dev = dev_get_by_index(cfg->fc_ifindex);
if (!dev)
goto out;
idev = in6_dev_get(dev);
@@ -928,8 +1041,14 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
goto out;
}
- if (rtmsg->rtmsg_metric == 0)
- rtmsg->rtmsg_metric = IP6_RT_PRIO_USER;
+ if (cfg->fc_metric == 0)
+ cfg->fc_metric = IP6_RT_PRIO_USER;
+
+ table = fib6_new_table(cfg->fc_table);
+ if (table == NULL) {
+ err = -ENOBUFS;
+ goto out;
+ }
rt = ip6_dst_alloc();
@@ -939,14 +1058,13 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
}
rt->u.dst.obsolete = -1;
- rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info);
- if (nlh && (r = NLMSG_DATA(nlh))) {
- rt->rt6i_protocol = r->rtm_protocol;
- } else {
- rt->rt6i_protocol = RTPROT_BOOT;
- }
+ rt->rt6i_expires = jiffies + clock_t_to_jiffies(cfg->fc_expires);
- addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst);
+ if (cfg->fc_protocol == RTPROT_UNSPEC)
+ cfg->fc_protocol = RTPROT_BOOT;
+ rt->rt6i_protocol = cfg->fc_protocol;
+
+ addr_type = ipv6_addr_type(&cfg->fc_dst);
if (addr_type & IPV6_ADDR_MULTICAST)
rt->u.dst.input = ip6_mc_input;
@@ -955,24 +1073,22 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
rt->u.dst.output = ip6_output;
- ipv6_addr_prefix(&rt->rt6i_dst.addr,
- &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len);
- rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len;
+ 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)
rt->u.dst.flags = DST_HOST;
#ifdef CONFIG_IPV6_SUBTREES
- ipv6_addr_prefix(&rt->rt6i_src.addr,
- &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
- rt->rt6i_src.plen = rtmsg->rtmsg_src_len;
+ ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
+ rt->rt6i_src.plen = cfg->fc_src_len;
#endif
- rt->rt6i_metric = rtmsg->rtmsg_metric;
+ rt->rt6i_metric = cfg->fc_metric;
/* We cannot add true routes via loopback here,
they would result in kernel looping; promote them to reject routes
*/
- if ((rtmsg->rtmsg_flags&RTF_REJECT) ||
+ if ((cfg->fc_flags & RTF_REJECT) ||
(dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
/* hold loopback dev/idev if we haven't done so. */
if (dev != &loopback_dev) {
@@ -995,12 +1111,12 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
goto install_route;
}
- if (rtmsg->rtmsg_flags & RTF_GATEWAY) {
+ if (cfg->fc_flags & RTF_GATEWAY) {
struct in6_addr *gw_addr;
int gwa_type;
- gw_addr = &rtmsg->rtmsg_gateway;
- ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway);
+ gw_addr = &cfg->fc_gateway;
+ ipv6_addr_copy(&rt->rt6i_gateway, gw_addr);
gwa_type = ipv6_addr_type(gw_addr);
if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
@@ -1017,7 +1133,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
if (!(gwa_type&IPV6_ADDR_UNICAST))
goto out;
- grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1);
+ grt = rt6_lookup(gw_addr, NULL, cfg->fc_ifindex, 1);
err = -EHOSTUNREACH;
if (grt == NULL)
@@ -1049,7 +1165,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
if (dev == NULL)
goto out;
- if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) {
+ if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
if (IS_ERR(rt->rt6i_nexthop)) {
err = PTR_ERR(rt->rt6i_nexthop);
@@ -1058,24 +1174,24 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
}
}
- rt->rt6i_flags = rtmsg->rtmsg_flags;
+ rt->rt6i_flags = cfg->fc_flags;
install_route:
- if (rta && rta[RTA_METRICS-1]) {
- int attrlen = RTA_PAYLOAD(rta[RTA_METRICS-1]);
- struct rtattr *attr = RTA_DATA(rta[RTA_METRICS-1]);
-
- while (RTA_OK(attr, attrlen)) {
- unsigned flavor = attr->rta_type;
- if (flavor) {
- if (flavor > RTAX_MAX) {
+ if (cfg->fc_mx) {
+ struct nlattr *nla;
+ int remaining;
+
+ nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+ int type = nla->nla_type;
+
+ if (type) {
+ if (type > RTAX_MAX) {
err = -EINVAL;
goto out;
}
- rt->u.dst.metrics[flavor-1] =
- *(u32 *)RTA_DATA(attr);
+
+ rt->u.dst.metrics[type - 1] = nla_get_u32(nla);
}
- attr = RTA_NEXT(attr, attrlen);
}
}
@@ -1087,7 +1203,8 @@ install_route:
rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
rt->u.dst.dev = dev;
rt->rt6i_idev = idev;
- return ip6_ins_rt(rt, nlh, _rtattr, req);
+ rt->rt6i_table = table;
+ return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
out:
if (dev)
@@ -1099,51 +1216,65 @@ out:
return err;
}
-int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
+static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
{
int err;
+ struct fib6_table *table;
- write_lock_bh(&rt6_lock);
+ if (rt == &ip6_null_entry)
+ return -ENOENT;
- err = fib6_del(rt, nlh, _rtattr, req);
+ table = rt->rt6i_table;
+ write_lock_bh(&table->tb6_lock);
+
+ err = fib6_del(rt, info);
dst_release(&rt->u.dst);
- write_unlock_bh(&rt6_lock);
+ write_unlock_bh(&table->tb6_lock);
return err;
}
-static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
+int ip6_del_rt(struct rt6_info *rt)
{
+ return __ip6_del_rt(rt, NULL);
+}
+
+static int ip6_route_del(struct fib6_config *cfg)
+{
+ struct fib6_table *table;
struct fib6_node *fn;
struct rt6_info *rt;
int err = -ESRCH;
- read_lock_bh(&rt6_lock);
+ table = fib6_get_table(cfg->fc_table);
+ if (table == NULL)
+ return err;
- fn = fib6_locate(&ip6_routing_table,
- &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len,
- &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
+ read_lock_bh(&table->tb6_lock);
+
+ fn = fib6_locate(&table->tb6_root,
+ &cfg->fc_dst, cfg->fc_dst_len,
+ &cfg->fc_src, cfg->fc_src_len);
if (fn) {
for (rt = fn->leaf; rt; rt = rt->u.next) {
- if (rtmsg->rtmsg_ifindex &&
+ if (cfg->fc_ifindex &&
(rt->rt6i_dev == NULL ||
- rt->rt6i_dev->ifindex != rtmsg->rtmsg_ifindex))
+ rt->rt6i_dev->ifindex != cfg->fc_ifindex))
continue;
- if (rtmsg->rtmsg_flags&RTF_GATEWAY &&
- !ipv6_addr_equal(&rtmsg->rtmsg_gateway, &rt->rt6i_gateway))
+ if (cfg->fc_flags & RTF_GATEWAY &&
+ !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
continue;
- if (rtmsg->rtmsg_metric &&
- rtmsg->rtmsg_metric != rt->rt6i_metric)
+ if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
continue;
dst_hold(&rt->u.dst);
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
- return ip6_del_rt(rt, nlh, _rtattr, req);
+ return __ip6_del_rt(rt, &cfg->fc_nlinfo);
}
}
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
return err;
}
@@ -1151,13 +1282,18 @@ static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_r
/*
* Handle redirects
*/
-void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr,
- struct neighbour *neigh, u8 *lladdr, int on_link)
+struct ip6rd_flowi {
+ struct flowi fl;
+ struct in6_addr gateway;
+};
+
+static struct rt6_info *__ip6_route_redirect(struct fib6_table *table,
+ struct flowi *fl,
+ int flags)
{
- struct rt6_info *rt, *nrt = NULL;
- int strict;
+ struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl;
+ struct rt6_info *rt;
struct fib6_node *fn;
- struct netevent_redirect netevent;
/*
* Get the "current" route for this destination and
@@ -1169,10 +1305,9 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr,
* is a bit fuzzy and one might need to check all possible
* routes.
*/
- strict = ipv6_addr_type(dest) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL);
- read_lock_bh(&rt6_lock);
- fn = fib6_lookup(&ip6_routing_table, dest, NULL);
+ read_lock_bh(&table->tb6_lock);
+ fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
for (rt = fn->leaf; rt; rt = rt->u.next) {
/*
@@ -1187,29 +1322,60 @@ restart:
continue;
if (!(rt->rt6i_flags & RTF_GATEWAY))
continue;
- if (neigh->dev != rt->rt6i_dev)
+ if (fl->oif != rt->rt6i_dev->ifindex)
continue;
- if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway))
+ if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
continue;
break;
}
- if (rt)
- dst_hold(&rt->u.dst);
- else if (strict) {
- while ((fn = fn->parent) != NULL) {
- if (fn->fn_flags & RTN_ROOT)
- break;
- if (fn->fn_flags & RTN_RTINFO)
- goto restart;
- }
- }
- read_unlock_bh(&rt6_lock);
- if (!rt) {
+ if (!rt)
+ rt = &ip6_null_entry;
+ BACKTRACK(&fl->fl6_src);
+out:
+ dst_hold(&rt->u.dst);
+
+ read_unlock_bh(&table->tb6_lock);
+
+ return rt;
+};
+
+static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
+ struct in6_addr *src,
+ struct in6_addr *gateway,
+ struct net_device *dev)
+{
+ struct ip6rd_flowi rdfl = {
+ .fl = {
+ .oif = dev->ifindex,
+ .nl_u = {
+ .ip6_u = {
+ .daddr = *dest,
+ .saddr = *src,
+ },
+ },
+ },
+ .gateway = *gateway,
+ };
+ int flags = rt6_need_strict(dest) ? RT6_LOOKUP_F_IFACE : 0;
+
+ return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect);
+}
+
+void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
+ struct in6_addr *saddr,
+ struct neighbour *neigh, u8 *lladdr, int on_link)
+{
+ struct rt6_info *rt, *nrt = NULL;
+ struct netevent_redirect netevent;
+
+ rt = ip6_route_redirect(dest, src, saddr, neigh->dev);
+
+ if (rt == &ip6_null_entry) {
if (net_ratelimit())
printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
"for redirect target\n");
- return;
+ goto out;
}
/*
@@ -1252,7 +1418,7 @@ restart:
nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev);
nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst));
- if (ip6_ins_rt(nrt, NULL, NULL, NULL))
+ if (ip6_ins_rt(nrt))
goto out;
netevent.old = &rt->u.dst;
@@ -1260,7 +1426,7 @@ restart:
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
if (rt->rt6i_flags&RTF_CACHE) {
- ip6_del_rt(rt, NULL, NULL, NULL);
+ ip6_del_rt(rt);
return;
}
@@ -1342,7 +1508,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires);
nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;
- ip6_ins_rt(nrt, NULL, NULL, NULL);
+ ip6_ins_rt(nrt);
}
out:
dst_release(&rt->u.dst);
@@ -1378,6 +1544,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
#ifdef CONFIG_IPV6_SUBTREES
memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
+ rt->rt6i_table = ort->rt6i_table;
}
return rt;
}
@@ -1388,9 +1555,14 @@ static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixle
{
struct fib6_node *fn;
struct rt6_info *rt = NULL;
+ struct fib6_table *table;
+
+ table = fib6_get_table(RT6_TABLE_INFO);
+ if (table == NULL)
+ return NULL;
- write_lock_bh(&rt6_lock);
- fn = fib6_locate(&ip6_routing_table, prefix ,prefixlen, NULL, 0);
+ write_lock_bh(&table->tb6_lock);
+ fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
if (!fn)
goto out;
@@ -1405,7 +1577,7 @@ static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixle
break;
}
out:
- write_unlock_bh(&rt6_lock);
+ write_unlock_bh(&table->tb6_lock);
return rt;
}
@@ -1413,21 +1585,23 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle
struct in6_addr *gwaddr, int ifindex,
unsigned pref)
{
- struct in6_rtmsg rtmsg;
+ struct fib6_config cfg = {
+ .fc_table = RT6_TABLE_INFO,
+ .fc_metric = 1024,
+ .fc_ifindex = ifindex,
+ .fc_dst_len = prefixlen,
+ .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
+ RTF_UP | RTF_PREF(pref),
+ };
+
+ ipv6_addr_copy(&cfg.fc_dst, prefix);
+ ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
- memset(&rtmsg, 0, sizeof(rtmsg));
- rtmsg.rtmsg_type = RTMSG_NEWROUTE;
- ipv6_addr_copy(&rtmsg.rtmsg_dst, prefix);
- rtmsg.rtmsg_dst_len = prefixlen;
- ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr);
- rtmsg.rtmsg_metric = 1024;
- rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref);
/* We should treat it as a default route if prefix length is 0. */
if (!prefixlen)
- rtmsg.rtmsg_flags |= RTF_DEFAULT;
- rtmsg.rtmsg_ifindex = ifindex;
+ cfg.fc_flags |= RTF_DEFAULT;
- ip6_route_add(&rtmsg, NULL, NULL, NULL);
+ ip6_route_add(&cfg);
return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex);
}
@@ -1436,12 +1610,14 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle
struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
{
struct rt6_info *rt;
- struct fib6_node *fn;
+ struct fib6_table *table;
- fn = &ip6_routing_table;
+ table = fib6_get_table(RT6_TABLE_DFLT);
+ if (table == NULL)
+ return NULL;
- write_lock_bh(&rt6_lock);
- for (rt = fn->leaf; rt; rt=rt->u.next) {
+ write_lock_bh(&table->tb6_lock);
+ for (rt = table->tb6_root.leaf; rt; rt=rt->u.next) {
if (dev == rt->rt6i_dev &&
((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
ipv6_addr_equal(&rt->rt6i_gateway, addr))
@@ -1449,7 +1625,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d
}
if (rt)
dst_hold(&rt->u.dst);
- write_unlock_bh(&rt6_lock);
+ write_unlock_bh(&table->tb6_lock);
return rt;
}
@@ -1457,43 +1633,65 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref)
{
- struct in6_rtmsg rtmsg;
+ struct fib6_config cfg = {
+ .fc_table = RT6_TABLE_DFLT,
+ .fc_metric = 1024,
+ .fc_ifindex = dev->ifindex,
+ .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
+ RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
+ };
- memset(&rtmsg, 0, sizeof(struct in6_rtmsg));
- rtmsg.rtmsg_type = RTMSG_NEWROUTE;
- ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr);
- rtmsg.rtmsg_metric = 1024;
- rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES |
- RTF_PREF(pref);
+ ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
- rtmsg.rtmsg_ifindex = dev->ifindex;
+ ip6_route_add(&cfg);
- ip6_route_add(&rtmsg, NULL, NULL, NULL);
return rt6_get_dflt_router(gwaddr, dev);
}
void rt6_purge_dflt_routers(void)
{
struct rt6_info *rt;
+ struct fib6_table *table;
+
+ /* NOTE: Keep consistent with rt6_get_dflt_router */
+ table = fib6_get_table(RT6_TABLE_DFLT);
+ if (table == NULL)
+ return;
restart:
- read_lock_bh(&rt6_lock);
- for (rt = ip6_routing_table.leaf; rt; rt = rt->u.next) {
+ read_lock_bh(&table->tb6_lock);
+ for (rt = table->tb6_root.leaf; rt; rt = rt->u.next) {
if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
dst_hold(&rt->u.dst);
-
- read_unlock_bh(&rt6_lock);
-
- ip6_del_rt(rt, NULL, NULL, NULL);
-
+ read_unlock_bh(&table->tb6_lock);
+ ip6_del_rt(rt);
goto restart;
}
}
- read_unlock_bh(&rt6_lock);
+ read_unlock_bh(&table->tb6_lock);
+}
+
+static void rtmsg_to_fib6_config(struct in6_rtmsg *rtmsg,
+ struct fib6_config *cfg)
+{
+ memset(cfg, 0, sizeof(*cfg));
+
+ cfg->fc_table = RT6_TABLE_MAIN;
+ cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
+ cfg->fc_metric = rtmsg->rtmsg_metric;
+ cfg->fc_expires = rtmsg->rtmsg_info;
+ cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
+ cfg->fc_src_len = rtmsg->rtmsg_src_len;
+ cfg->fc_flags = rtmsg->rtmsg_flags;
+
+ ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
+ ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
+ ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway);
}
int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
{
+ struct fib6_config cfg;
struct in6_rtmsg rtmsg;
int err;
@@ -1506,14 +1704,16 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
sizeof(struct in6_rtmsg));
if (err)
return -EFAULT;
-
+
+ rtmsg_to_fib6_config(&rtmsg, &cfg);
+
rtnl_lock();
switch (cmd) {
case SIOCADDRT:
- err = ip6_route_add(&rtmsg, NULL, NULL, NULL);
+ err = ip6_route_add(&cfg);
break;
case SIOCDELRT:
- err = ip6_route_del(&rtmsg, NULL, NULL, NULL);
+ err = ip6_route_del(&cfg);
break;
default:
err = -EINVAL;
@@ -1587,6 +1787,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
rt->rt6i_dst.plen = 128;
+ rt->rt6i_table = fib6_get_table(RT6_TABLE_LOCAL);
atomic_set(&rt->u.dst.__refcnt, 1);
@@ -1605,9 +1806,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *arg)
void rt6_ifdown(struct net_device *dev)
{
- write_lock_bh(&rt6_lock);
- fib6_clean_tree(&ip6_routing_table, fib6_ifdown, 0, dev);
- write_unlock_bh(&rt6_lock);
+ fib6_clean_all(fib6_ifdown, 0, dev);
}
struct rt6_mtu_change_arg
@@ -1657,80 +1856,114 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
void rt6_mtu_change(struct net_device *dev, unsigned mtu)
{
- struct rt6_mtu_change_arg arg;
+ struct rt6_mtu_change_arg arg = {
+ .dev = dev,
+ .mtu = mtu,
+ };
- arg.dev = dev;
- arg.mtu = mtu;
- read_lock_bh(&rt6_lock);
- fib6_clean_tree(&ip6_routing_table, rt6_mtu_change_route, 0, &arg);
- read_unlock_bh(&rt6_lock);
+ fib6_clean_all(rt6_mtu_change_route, 0, &arg);
}
-static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta,
- struct in6_rtmsg *rtmsg)
+static struct nla_policy rtm_ipv6_policy[RTA_MAX+1] __read_mostly = {
+ [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_OIF] = { .type = NLA_U32 },
+ [RTA_IIF] = { .type = NLA_U32 },
+ [RTA_PRIORITY] = { .type = NLA_U32 },
+ [RTA_METRICS] = { .type = NLA_NESTED },
+};
+
+static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct fib6_config *cfg)
{
- memset(rtmsg, 0, sizeof(*rtmsg));
+ struct rtmsg *rtm;
+ struct nlattr *tb[RTA_MAX+1];
+ int err;
- rtmsg->rtmsg_dst_len = r->rtm_dst_len;
- rtmsg->rtmsg_src_len = r->rtm_src_len;
- rtmsg->rtmsg_flags = RTF_UP;
- if (r->rtm_type == RTN_UNREACHABLE)
- rtmsg->rtmsg_flags |= RTF_REJECT;
+ err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
+ if (err < 0)
+ goto errout;
- if (rta[RTA_GATEWAY-1]) {
- if (rta[RTA_GATEWAY-1]->rta_len != RTA_LENGTH(16))
- return -EINVAL;
- memcpy(&rtmsg->rtmsg_gateway, RTA_DATA(rta[RTA_GATEWAY-1]), 16);
- rtmsg->rtmsg_flags |= RTF_GATEWAY;
- }
- if (rta[RTA_DST-1]) {
- if (RTA_PAYLOAD(rta[RTA_DST-1]) < ((r->rtm_dst_len+7)>>3))
- return -EINVAL;
- memcpy(&rtmsg->rtmsg_dst, RTA_DATA(rta[RTA_DST-1]), ((r->rtm_dst_len+7)>>3));
+ err = -EINVAL;
+ rtm = nlmsg_data(nlh);
+ memset(cfg, 0, sizeof(*cfg));
+
+ cfg->fc_table = rtm->rtm_table;
+ cfg->fc_dst_len = rtm->rtm_dst_len;
+ cfg->fc_src_len = rtm->rtm_src_len;
+ cfg->fc_flags = RTF_UP;
+ cfg->fc_protocol = rtm->rtm_protocol;
+
+ if (rtm->rtm_type == RTN_UNREACHABLE)
+ cfg->fc_flags |= RTF_REJECT;
+
+ cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
+ cfg->fc_nlinfo.nlh = nlh;
+
+ if (tb[RTA_GATEWAY]) {
+ nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16);
+ cfg->fc_flags |= RTF_GATEWAY;
}
- if (rta[RTA_SRC-1]) {
- if (RTA_PAYLOAD(rta[RTA_SRC-1]) < ((r->rtm_src_len+7)>>3))
- return -EINVAL;
- memcpy(&rtmsg->rtmsg_src, RTA_DATA(rta[RTA_SRC-1]), ((r->rtm_src_len+7)>>3));
+
+ if (tb[RTA_DST]) {
+ int plen = (rtm->rtm_dst_len + 7) >> 3;
+
+ if (nla_len(tb[RTA_DST]) < plen)
+ goto errout;
+
+ nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen);
}
- if (rta[RTA_OIF-1]) {
- if (rta[RTA_OIF-1]->rta_len != RTA_LENGTH(sizeof(int)))
- return -EINVAL;
- memcpy(&rtmsg->rtmsg_ifindex, RTA_DATA(rta[RTA_OIF-1]), sizeof(int));
+
+ if (tb[RTA_SRC]) {
+ int plen = (rtm->rtm_src_len + 7) >> 3;
+
+ if (nla_len(tb[RTA_SRC]) < plen)
+ goto errout;
+
+ nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
}
- if (rta[RTA_PRIORITY-1]) {
- if (rta[RTA_PRIORITY-1]->rta_len != RTA_LENGTH(4))
- return -EINVAL;
- memcpy(&rtmsg->rtmsg_metric, RTA_DATA(rta[RTA_PRIORITY-1]), 4);
+
+ if (tb[RTA_OIF])
+ cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);
+
+ if (tb[RTA_PRIORITY])
+ cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]);
+
+ if (tb[RTA_METRICS]) {
+ cfg->fc_mx = nla_data(tb[RTA_METRICS]);
+ cfg->fc_mx_len = nla_len(tb[RTA_METRICS]);
}
- return 0;
+
+ if (tb[RTA_TABLE])
+ cfg->fc_table = nla_get_u32(tb[RTA_TABLE]);
+
+ err = 0;
+errout:
+ return err;
}
int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
- struct rtmsg *r = NLMSG_DATA(nlh);
- struct in6_rtmsg rtmsg;
+ struct fib6_config cfg;
+ int err;
- if (inet6_rtm_to_rtmsg(r, arg, &rtmsg))
- return -EINVAL;
- return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb));
+ err = rtm_to_fib6_config(skb, nlh, &cfg);
+ if (err < 0)
+ return err;
+
+ return ip6_route_del(&cfg);
}
int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
- struct rtmsg *r = NLMSG_DATA(nlh);
- struct in6_rtmsg rtmsg;
+ struct fib6_config cfg;
+ int err;
- if (inet6_rtm_to_rtmsg(r, arg, &rtmsg))
- return -EINVAL;
- return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb));
-}
+ err = rtm_to_fib6_config(skb, nlh, &cfg);
+ if (err < 0)
+ return err;
-struct rt6_rtnl_dump_arg
-{
- struct sk_buff *skb;
- struct netlink_callback *cb;
-};
+ return ip6_route_add(&cfg);
+}
static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
struct in6_addr *dst, struct in6_addr *src,
@@ -1738,9 +1971,9 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
int prefix, unsigned int flags)
{
struct rtmsg *rtm;
- struct nlmsghdr *nlh;
- unsigned char *b = skb->tail;
+ struct nlmsghdr *nlh;
struct rta_cacheinfo ci;
+ u32 table;
if (prefix) { /* user wants prefix routes only */
if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
@@ -1749,13 +1982,21 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
}
}
- nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags);
- rtm = NLMSG_DATA(nlh);
+ nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
+ if (nlh == NULL)
+ return -ENOBUFS;
+
+ rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET6;
rtm->rtm_dst_len = rt->rt6i_dst.plen;
rtm->rtm_src_len = rt->rt6i_src.plen;
rtm->rtm_tos = 0;
- rtm->rtm_table = RT_TABLE_MAIN;
+ if (rt->rt6i_table)
+ table = rt->rt6i_table->tb6_id;
+ else
+ table = RT6_TABLE_UNSPEC;
+ rtm->rtm_table = table;
+ NLA_PUT_U32(skb, RTA_TABLE, table);
if (rt->rt6i_flags&RTF_REJECT)
rtm->rtm_type = RTN_UNREACHABLE;
else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
@@ -1776,31 +2017,35 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
rtm->rtm_flags |= RTM_F_CLONED;
if (dst) {
- RTA_PUT(skb, RTA_DST, 16, dst);
+ NLA_PUT(skb, RTA_DST, 16, dst);
rtm->rtm_dst_len = 128;
} else if (rtm->rtm_dst_len)
- RTA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
+ NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
if (src) {
- RTA_PUT(skb, RTA_SRC, 16, src);
+ NLA_PUT(skb, RTA_SRC, 16, src);
rtm->rtm_src_len = 128;
} else if (rtm->rtm_src_len)
- RTA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
+ NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
#endif
if (iif)
- RTA_PUT(skb, RTA_IIF, 4, &iif);
+ NLA_PUT_U32(skb, RTA_IIF, iif);
else if (dst) {
struct in6_addr saddr_buf;
if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0)
- RTA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
+ NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
}
+
if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
- goto rtattr_failure;
+ goto nla_put_failure;
+
if (rt->u.dst.neighbour)
- RTA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key);
+ NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key);
+
if (rt->u.dst.dev)
- RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->rt6i_dev->ifindex);
- RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric);
+ NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);
+
+ NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);
ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse);
if (rt->rt6i_expires)
ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies);
@@ -1812,23 +2057,21 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
ci.rta_id = 0;
ci.rta_ts = 0;
ci.rta_tsage = 0;
- RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci);
- nlh->nlmsg_len = skb->tail - b;
- return skb->len;
+ NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci);
-nlmsg_failure:
-rtattr_failure:
- skb_trim(skb, b - skb->data);
- return -1;
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ return nlmsg_cancel(skb, nlh);
}
-static int rt6_dump_route(struct rt6_info *rt, void *p_arg)
+int rt6_dump_route(struct rt6_info *rt, void *p_arg)
{
struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
int prefix;
- if (arg->cb->nlh->nlmsg_len >= NLMSG_LENGTH(sizeof(struct rtmsg))) {
- struct rtmsg *rtm = NLMSG_DATA(arg->cb->nlh);
+ if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
+ struct rtmsg *rtm = nlmsg_data(arg->cb->nlh);
prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0;
} else
prefix = 0;
@@ -1838,189 +2081,108 @@ static int rt6_dump_route(struct rt6_info *rt, void *p_arg)
prefix, NLM_F_MULTI);
}
-static int fib6_dump_node(struct fib6_walker_t *w)
+int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
- int res;
+ struct nlattr *tb[RTA_MAX+1];
struct rt6_info *rt;
+ struct sk_buff *skb;
+ struct rtmsg *rtm;
+ struct flowi fl;
+ int err, iif = 0;
- for (rt = w->leaf; rt; rt = rt->u.next) {
- res = rt6_dump_route(rt, w->args);
- if (res < 0) {
- /* Frame is full, suspend walking */
- w->leaf = rt;
- return 1;
- }
- BUG_TRAP(res!=0);
- }
- w->leaf = NULL;
- return 0;
-}
-
-static void fib6_dump_end(struct netlink_callback *cb)
-{
- struct fib6_walker_t *w = (void*)cb->args[0];
-
- if (w) {
- cb->args[0] = 0;
- fib6_walker_unlink(w);
- kfree(w);
- }
- cb->done = (void*)cb->args[1];
- cb->args[1] = 0;
-}
-
-static int fib6_dump_done(struct netlink_callback *cb)
-{
- fib6_dump_end(cb);
- return cb->done ? cb->done(cb) : 0;
-}
-
-int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
-{
- struct rt6_rtnl_dump_arg arg;
- struct fib6_walker_t *w;
- int res;
+ err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
+ if (err < 0)
+ goto errout;
- arg.skb = skb;
- arg.cb = cb;
+ err = -EINVAL;
+ memset(&fl, 0, sizeof(fl));
- w = (void*)cb->args[0];
- if (w == NULL) {
- /* New dump:
- *
- * 1. hook callback destructor.
- */
- cb->args[1] = (long)cb->done;
- cb->done = fib6_dump_done;
+ if (tb[RTA_SRC]) {
+ if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
+ goto errout;
- /*
- * 2. allocate and initialize walker.
- */
- w = kzalloc(sizeof(*w), GFP_ATOMIC);
- if (w == NULL)
- return -ENOMEM;
- RT6_TRACE("dump<%p", w);
- w->root = &ip6_routing_table;
- w->func = fib6_dump_node;
- w->args = &arg;
- cb->args[0] = (long)w;
- read_lock_bh(&rt6_lock);
- res = fib6_walk(w);
- read_unlock_bh(&rt6_lock);
- } else {
- w->args = &arg;
- read_lock_bh(&rt6_lock);
- res = fib6_walk_continue(w);
- read_unlock_bh(&rt6_lock);
+ ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC]));
}
-#if RT6_DEBUG >= 3
- if (res <= 0 && skb->len == 0)
- RT6_TRACE("%p>dump end\n", w);
-#endif
- res = res < 0 ? res : skb->len;
- /* res < 0 is an error. (really, impossible)
- res == 0 means that dump is complete, but skb still can contain data.
- res > 0 dump is not complete, but frame is full.
- */
- /* Destroy walker, if dump of this table is complete. */
- if (res <= 0)
- fib6_dump_end(cb);
- return res;
-}
-
-int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
-{
- struct rtattr **rta = arg;
- int iif = 0;
- int err = -ENOBUFS;
- struct sk_buff *skb;
- struct flowi fl;
- struct rt6_info *rt;
- skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
- if (skb == NULL)
- goto out;
+ if (tb[RTA_DST]) {
+ if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
+ goto errout;
- /* Reserve room for dummy headers, this skb can pass
- through good chunk of routing engine.
- */
- skb->mac.raw = skb->data;
- skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
+ ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST]));
+ }
- memset(&fl, 0, sizeof(fl));
- if (rta[RTA_SRC-1])
- ipv6_addr_copy(&fl.fl6_src,
- (struct in6_addr*)RTA_DATA(rta[RTA_SRC-1]));
- if (rta[RTA_DST-1])
- ipv6_addr_copy(&fl.fl6_dst,
- (struct in6_addr*)RTA_DATA(rta[RTA_DST-1]));
+ if (tb[RTA_IIF])
+ iif = nla_get_u32(tb[RTA_IIF]);
- if (rta[RTA_IIF-1])
- memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));
+ if (tb[RTA_OIF])
+ fl.oif = nla_get_u32(tb[RTA_OIF]);
if (iif) {
struct net_device *dev;
dev = __dev_get_by_index(iif);
if (!dev) {
err = -ENODEV;
- goto out_free;
+ goto errout;
}
}
- fl.oif = 0;
- if (rta[RTA_OIF-1])
- memcpy(&fl.oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int));
+ skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (skb == NULL) {
+ err = -ENOBUFS;
+ goto errout;
+ }
- rt = (struct rt6_info*)ip6_route_output(NULL, &fl);
+ /* Reserve room for dummy headers, this skb can pass
+ through good chunk of routing engine.
+ */
+ skb->mac.raw = skb->data;
+ skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
+ rt = (struct rt6_info*) ip6_route_output(NULL, &fl);
skb->dst = &rt->u.dst;
- NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;
- err = rt6_fill_node(skb, rt,
- &fl.fl6_dst, &fl.fl6_src,
- iif,
+ err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
nlh->nlmsg_seq, 0, 0);
if (err < 0) {
- err = -EMSGSIZE;
- goto out_free;
+ kfree_skb(skb);
+ goto errout;
}
- err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
- if (err > 0)
- err = 0;
-out:
+ err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid);
+errout:
return err;
-out_free:
- kfree_skb(skb);
- goto out;
}
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh,
- struct netlink_skb_parms *req)
+void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
{
struct sk_buff *skb;
- int size = NLMSG_SPACE(sizeof(struct rtmsg)+256);
- u32 pid = current->pid;
- u32 seq = 0;
-
- if (req)
- pid = req->pid;
- if (nlh)
- seq = nlh->nlmsg_seq;
-
- skb = alloc_skb(size, gfp_any());
- if (!skb) {
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, ENOBUFS);
- return;
+ u32 pid = 0, seq = 0;
+ struct nlmsghdr *nlh = NULL;
+ int payload = sizeof(struct rtmsg) + 256;
+ int err = -ENOBUFS;
+
+ if (info) {
+ pid = info->pid;
+ nlh = info->nlh;
+ if (nlh)
+ seq = nlh->nlmsg_seq;
}
- if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0) < 0) {
+
+ skb = nlmsg_new(nlmsg_total_size(payload), gfp_any());
+ if (skb == NULL)
+ goto errout;
+
+ err = rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0);
+ if (err < 0) {
kfree_skb(skb);
- netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, EINVAL);
- return;
+ goto errout;
}
- NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_ROUTE;
- netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_ROUTE, gfp_any());
+
+ err = rtnl_notify(skb, pid, RTNLGRP_IPV6_ROUTE, nlh, gfp_any());
+errout:
+ if (err < 0)
+ rtnl_set_sk_err(RTNLGRP_IPV6_ROUTE, err);
}
/*
@@ -2096,16 +2258,13 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
static int rt6_proc_info(char *buffer, char **start, off_t offset, int length)
{
- struct rt6_proc_arg arg;
- arg.buffer = buffer;
- arg.offset = offset;
- arg.length = length;
- arg.skip = 0;
- arg.len = 0;
+ struct rt6_proc_arg arg = {
+ .buffer = buffer,
+ .offset = offset,
+ .length = length,
+ };
- read_lock_bh(&rt6_lock);
- fib6_clean_tree(&ip6_routing_table, rt6_info_route, 0, &arg);
- read_unlock_bh(&rt6_lock);
+ fib6_clean_all(rt6_info_route, 0, &arg);
*start = buffer;
if (offset)
@@ -2260,13 +2419,9 @@ void __init ip6_route_init(void)
{
struct proc_dir_entry *p;
- ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache",
- sizeof(struct rt6_info),
- 0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
- if (!ip6_dst_ops.kmem_cachep)
- panic("cannot create ip6_dst_cache");
-
+ ip6_dst_ops.kmem_cachep =
+ kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
fib6_init();
#ifdef CONFIG_PROC_FS
p = proc_net_create("ipv6_route", 0, rt6_proc_info);
@@ -2278,10 +2433,16 @@ void __init ip6_route_init(void)
#ifdef CONFIG_XFRM
xfrm6_init();
#endif
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ fib6_rules_init();
+#endif
}
void ip6_route_cleanup(void)
{
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ fib6_rules_cleanup();
+#endif
#ifdef CONFIG_PROC_FS
proc_net_remove("ipv6_route");
proc_net_remove("rt6_stats");
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 802a1a6b103..2546fc9f0a7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -251,6 +251,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
final_p = &final;
}
+ security_sk_classify_flow(sk, &fl);
+
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto failure;
@@ -270,7 +272,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
inet->rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
- __ip6_dst_store(sk, dst, NULL);
+ __ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
@@ -374,6 +376,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
+ security_skb_classify_flow(skb, &fl);
if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
sk->sk_err_soft = -err;
@@ -467,6 +470,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
fl.oif = treq->iif;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_sk(sk)->sport;
+ security_req_classify_flow(req, &fl);
if (dst == NULL) {
opt = np->opt;
@@ -541,7 +545,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb)
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcphdr *th = skb->h.th;
- if (skb->ip_summed == CHECKSUM_HW) {
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0);
skb->csum = offsetof(struct tcphdr, check);
} else {
@@ -566,7 +570,7 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb)
th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
IPPROTO_TCP, 0);
skb->csum = offsetof(struct tcphdr, check);
- skb->ip_summed = CHECKSUM_HW;
+ skb->ip_summed = CHECKSUM_PARTIAL;
return 0;
}
@@ -625,6 +629,7 @@ static void tcp_v6_send_reset(struct sk_buff *skb)
fl.oif = inet6_iif(skb);
fl.fl_ip_dport = t1->dest;
fl.fl_ip_sport = t1->source;
+ security_skb_classify_flow(skb, &fl);
/* sk = NULL, but it is safe for now. RST socket required. */
if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
@@ -691,6 +696,7 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32
fl.oif = inet6_iif(skb);
fl.fl_ip_dport = t1->dest;
fl.fl_ip_sport = t1->source;
+ security_skb_classify_flow(skb, &fl);
if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) {
@@ -820,6 +826,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_rsk(req)->snt_isn = isn;
+ security_inet_conn_request(sk, skb, req);
+
if (tcp_v6_send_synack(sk, req, NULL))
goto drop;
@@ -923,6 +931,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_sk(sk)->sport;
+ security_req_classify_flow(req, &fl);
if (ip6_dst_lookup(sk, &dst, &fl))
goto out;
@@ -945,7 +954,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
*/
newsk->sk_gso_type = SKB_GSO_TCPV6;
- __ip6_dst_store(newsk, dst, NULL);
+ __ip6_dst_store(newsk, dst, NULL, NULL);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
@@ -1024,7 +1033,7 @@ out:
static int tcp_v6_checksum_init(struct sk_buff *skb)
{
- if (skb->ip_summed == CHECKSUM_HW) {
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr,
&skb->nh.ipv6h->daddr,skb->csum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1066,7 +1075,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
- if (sk_filter(sk, skb, 0))
+ if (sk_filter(sk, skb))
goto discard;
/*
@@ -1223,7 +1232,7 @@ process:
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
- if (sk_filter(sk, skb, 0))
+ if (sk_filter(sk, skb))
goto discard_and_relse;
skb->dev = NULL;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3d54f246411..9662561701d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -61,81 +61,9 @@
DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;
-/* Grrr, addr_type already calculated by caller, but I don't want
- * to add some silly "cookie" argument to this method just for that.
- */
-static int udp_v6_get_port(struct sock *sk, unsigned short snum)
+static inline int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
- struct sock *sk2;
- struct hlist_node *node;
-
- write_lock_bh(&udp_hash_lock);
- if (snum == 0) {
- int best_size_so_far, best, result, i;
-
- if (udp_port_rover > sysctl_local_port_range[1] ||
- udp_port_rover < sysctl_local_port_range[0])
- udp_port_rover = sysctl_local_port_range[0];
- best_size_so_far = 32767;
- best = result = udp_port_rover;
- for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
- int size;
- struct hlist_head *list;
-
- list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)];
- if (hlist_empty(list)) {
- if (result > sysctl_local_port_range[1])
- result = sysctl_local_port_range[0] +
- ((result - sysctl_local_port_range[0]) &
- (UDP_HTABLE_SIZE - 1));
- goto gotit;
- }
- size = 0;
- sk_for_each(sk2, node, list)
- if (++size >= best_size_so_far)
- goto next;
- best_size_so_far = size;
- best = result;
- next:;
- }
- result = best;
- for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) {
- if (result > sysctl_local_port_range[1])
- result = sysctl_local_port_range[0]
- + ((result - sysctl_local_port_range[0]) &
- (UDP_HTABLE_SIZE - 1));
- if (!udp_lport_inuse(result))
- break;
- }
- if (i >= (1 << 16) / UDP_HTABLE_SIZE)
- goto fail;
-gotit:
- udp_port_rover = snum = result;
- } else {
- sk_for_each(sk2, node,
- &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) {
- if (inet_sk(sk2)->num == snum &&
- sk2 != sk &&
- (!sk2->sk_bound_dev_if ||
- !sk->sk_bound_dev_if ||
- sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
- (!sk2->sk_reuse || !sk->sk_reuse) &&
- ipv6_rcv_saddr_equal(sk, sk2))
- goto fail;
- }
- }
-
- inet_sk(sk)->num = snum;
- if (sk_unhashed(sk)) {
- sk_add_node(sk, &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]);
- sock_prot_inc_use(sk->sk_prot);
- }
- write_unlock_bh(&udp_hash_lock);
- return 0;
-
-fail:
- write_unlock_bh(&udp_hash_lock);
- return 1;
+ return udp_get_port(sk, snum, ipv6_rcv_saddr_equal);
}
static void udp_v6_hash(struct sock *sk)
@@ -345,6 +273,8 @@ out:
static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
+ int rc;
+
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
return -1;
@@ -356,7 +286,10 @@ static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
return 0;
}
- if (sock_queue_rcv_skb(sk,skb)<0) {
+ if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
+ /* Note that an ENOMEM error is charged twice */
+ if (rc == -ENOMEM)
+ UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS);
UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
kfree_skb(skb);
return 0;
@@ -475,7 +408,7 @@ static int udpv6_rcv(struct sk_buff **pskb)
uh = skb->h.uh;
}
- if (skb->ip_summed == CHECKSUM_HW &&
+ if (skb->ip_summed == CHECKSUM_COMPLETE &&
!csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum))
skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -782,6 +715,8 @@ do_udp_sendmsg:
connected = 0;
}
+ security_sk_classify_flow(sk, fl);
+
err = ip6_sk_dst_lookup(sk, &dst, fl);
if (err)
goto out;
@@ -840,7 +775,12 @@ do_append_data:
if (connected) {
ip6_dst_store(sk, dst,
ipv6_addr_equal(&fl->fl6_dst, &np->daddr) ?
- &np->daddr : NULL);
+ &np->daddr : NULL,
+#ifdef CONFIG_IPV6_SUBTREES
+ ipv6_addr_equal(&fl->fl6_src, &np->saddr) ?
+ &np->saddr :
+#endif
+ NULL);
} else {
dst_release(dst);
}
@@ -855,6 +795,16 @@ out:
UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS);
return len;
}
+ /*
+ * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting
+ * ENOBUFS might not be good (it's not tunable per se), but otherwise
+ * we don't have a good statistic (IpOutDiscards but it can be too many
+ * things). We could add another new stat but at least for now that
+ * seems like overkill.
+ */
+ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+ UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS);
+ }
return err;
do_confirm:
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 0405d74ff91..a40a0578901 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -72,7 +72,7 @@ int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi)
if (x->mode->input(x, skb))
goto drop;
- if (x->props.mode) { /* XXX */
+ if (x->props.mode == XFRM_MODE_TUNNEL) { /* XXX */
decaps = 1;
break;
}
@@ -138,3 +138,111 @@ int xfrm6_rcv(struct sk_buff **pskb)
{
return xfrm6_rcv_spi(*pskb, 0);
}
+
+int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
+ xfrm_address_t *saddr, u8 proto)
+{
+ struct xfrm_state *x = NULL;
+ int wildcard = 0;
+ struct in6_addr any;
+ xfrm_address_t *xany;
+ struct xfrm_state *xfrm_vec_one = NULL;
+ int nh = 0;
+ int i = 0;
+
+ ipv6_addr_set(&any, 0, 0, 0, 0);
+ xany = (xfrm_address_t *)&any;
+
+ for (i = 0; i < 3; i++) {
+ xfrm_address_t *dst, *src;
+ switch (i) {
+ case 0:
+ dst = daddr;
+ src = saddr;
+ break;
+ case 1:
+ /* lookup state with wild-card source address */
+ wildcard = 1;
+ dst = daddr;
+ src = xany;
+ break;
+ case 2:
+ default:
+ /* lookup state with wild-card addresses */
+ wildcard = 1; /* XXX */
+ dst = xany;
+ src = xany;
+ break;
+ }
+
+ x = xfrm_state_lookup_byaddr(dst, src, proto, AF_INET6);
+ if (!x)
+ continue;
+
+ spin_lock(&x->lock);
+
+ if (wildcard) {
+ if ((x->props.flags & XFRM_STATE_WILDRECV) == 0) {
+ spin_unlock(&x->lock);
+ xfrm_state_put(x);
+ x = NULL;
+ continue;
+ }
+ }
+
+ if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+ spin_unlock(&x->lock);
+ xfrm_state_put(x);
+ x = NULL;
+ continue;
+ }
+ if (xfrm_state_check_expire(x)) {
+ spin_unlock(&x->lock);
+ xfrm_state_put(x);
+ x = NULL;
+ continue;
+ }
+
+ nh = x->type->input(x, skb);
+ if (nh <= 0) {
+ spin_unlock(&x->lock);
+ xfrm_state_put(x);
+ x = NULL;
+ continue;
+ }
+
+ x->curlft.bytes += skb->len;
+ x->curlft.packets++;
+
+ spin_unlock(&x->lock);
+
+ xfrm_vec_one = x;
+ break;
+ }
+
+ if (!xfrm_vec_one)
+ goto drop;
+
+ /* Allocate new secpath or COW existing one. */
+ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
+ struct sec_path *sp;
+ sp = secpath_dup(skb->sp);
+ if (!sp)
+ goto drop;
+ if (skb->sp)
+ secpath_put(skb->sp);
+ skb->sp = sp;
+ }
+
+ if (1 + skb->sp->len > XFRM_MAX_DEPTH)
+ goto drop;
+
+ skb->sp->xvec[skb->sp->len] = xfrm_vec_one;
+ skb->sp->len ++;
+
+ return 1;
+drop:
+ if (xfrm_vec_one)
+ xfrm_state_put(xfrm_vec_one);
+ return -1;
+}
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
new file mode 100644
index 00000000000..6031c16d46c
--- /dev/null
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -0,0 +1,93 @@
+/*
+ * xfrm6_mode_ro.c - Route optimization mode for IPv6.
+ *
+ * Copyright (C)2003-2006 Helsinki University of Technology
+ * Copyright (C)2003-2006 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+/*
+ * Authors:
+ * Noriaki TAKAMIYA @USAGI
+ * Masahide NAKAMURA @USAGI
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/stringify.h>
+#include <net/ipv6.h>
+#include <net/xfrm.h>
+
+/* Add route optimization header space.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the route optimization header.
+ *
+ * On exit, skb->h will be set to the start of the encapsulation header to be
+ * filled in by x->type->output and skb->nh will be set to the nextheader field
+ * of the extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header. The value of skb->data will always
+ * point to the top IP header.
+ */
+static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+ struct ipv6hdr *iph;
+ u8 *prevhdr;
+ int hdr_len;
+
+ skb_push(skb, x->props.header_len);
+ iph = skb->nh.ipv6h;
+
+ hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+ skb->nh.raw = prevhdr - x->props.header_len;
+ skb->h.raw = skb->data + hdr_len;
+ memmove(skb->data, iph, hdr_len);
+ return 0;
+}
+
+/*
+ * Do nothing about routing optimization header unlike IPsec.
+ */
+static int xfrm6_ro_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+ return 0;
+}
+
+static struct xfrm_mode xfrm6_ro_mode = {
+ .input = xfrm6_ro_input,
+ .output = xfrm6_ro_output,
+ .owner = THIS_MODULE,
+ .encap = XFRM_MODE_ROUTEOPTIMIZATION,
+};
+
+static int __init xfrm6_ro_init(void)
+{
+ return xfrm_register_mode(&xfrm6_ro_mode, AF_INET6);
+}
+
+static void __exit xfrm6_ro_exit(void)
+{
+ int err;
+
+ err = xfrm_unregister_mode(&xfrm6_ro_mode, AF_INET6);
+ BUG_ON(err);
+}
+
+module_init(xfrm6_ro_init);
+module_exit(xfrm6_ro_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_ROUTEOPTIMIZATION);
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 711d713e36d..3a4b39b12ba 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -25,9 +25,8 @@
* its absence, that of the top IP header. The value of skb->data will always
* point to the top IP header.
*/
-static int xfrm6_transport_output(struct sk_buff *skb)
+static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
{
- struct xfrm_state *x = skb->dst->xfrm;
struct ipv6hdr *iph;
u8 *prevhdr;
int hdr_len;
@@ -35,7 +34,7 @@ static int xfrm6_transport_output(struct sk_buff *skb)
skb_push(skb, x->props.header_len);
iph = skb->nh.ipv6h;
- hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
+ hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
skb->nh.raw = prevhdr - x->props.header_len;
skb->h.raw = skb->data + hdr_len;
memmove(skb->data, iph, hdr_len);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 8af79be2edc..5e7d8a7d641 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -37,10 +37,9 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
* its absence, that of the top IP header. The value of skb->data will always
* point to the top IP header.
*/
-static int xfrm6_tunnel_output(struct sk_buff *skb)
+static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb->dst;
- struct xfrm_state *x = dst->xfrm;
struct ipv6hdr *iph, *top_iph;
int dsfield;
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index c8c8b44a0f5..c260ea104c5 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -17,6 +17,12 @@
#include <net/ipv6.h>
#include <net/xfrm.h>
+int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
+ u8 **prevhdr)
+{
+ return ip6_find_1stfragopt(skb, prevhdr);
+}
+
static int xfrm6_tunnel_check_size(struct sk_buff *skb)
{
int mtu, ret = 0;
@@ -41,13 +47,13 @@ static int xfrm6_output_one(struct sk_buff *skb)
struct xfrm_state *x = dst->xfrm;
int err;
- if (skb->ip_summed == CHECKSUM_HW) {
- err = skb_checksum_help(skb, 0);
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ err = skb_checksum_help(skb);
if (err)
goto error_nolock;
}
- if (x->props.mode) {
+ if (x->props.mode == XFRM_MODE_TUNNEL) {
err = xfrm6_tunnel_check_size(skb);
if (err)
goto error_nolock;
@@ -59,7 +65,7 @@ static int xfrm6_output_one(struct sk_buff *skb)
if (err)
goto error;
- err = x->mode->output(skb);
+ err = x->mode->output(x, skb);
if (err)
goto error;
@@ -69,6 +75,8 @@ static int xfrm6_output_one(struct sk_buff *skb)
x->curlft.bytes += skb->len;
x->curlft.packets++;
+ if (x->props.mode == XFRM_MODE_ROUTEOPTIMIZATION)
+ x->lastused = (u64)xtime.tv_sec;
spin_unlock_bh(&x->lock);
@@ -80,7 +88,7 @@ static int xfrm6_output_one(struct sk_buff *skb)
}
dst = skb->dst;
x = dst->xfrm;
- } while (x && !x->props.mode);
+ } while (x && (x->props.mode != XFRM_MODE_TUNNEL));
IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
err = 0;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 73cd250aecb..6a252e2134d 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -18,6 +18,9 @@
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
+#ifdef CONFIG_IPV6_MIP6
+#include <net/mip6.h>
+#endif
static struct dst_ops xfrm6_dst_ops;
static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
@@ -31,6 +34,26 @@ static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
return err;
}
+static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr)
+{
+ struct rt6_info *rt;
+ struct flowi fl_tunnel = {
+ .nl_u = {
+ .ip6_u = {
+ .daddr = *(struct in6_addr *)&daddr->a6,
+ },
+ },
+ };
+
+ if (!xfrm6_dst_lookup((struct xfrm_dst **)&rt, &fl_tunnel)) {
+ ipv6_get_saddr(&rt->u.dst, (struct in6_addr *)&daddr->a6,
+ (struct in6_addr *)&saddr->a6);
+ dst_release(&rt->u.dst);
+ return 0;
+ }
+ return -EHOSTUNREACH;
+}
+
static struct dst_entry *
__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
{
@@ -50,7 +73,9 @@ __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
xdst->u.rt6.rt6i_src.plen);
if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
- xfrm_bundle_ok(xdst, fl, AF_INET6)) {
+ xfrm_bundle_ok(xdst, fl, AF_INET6,
+ (xdst->u.rt6.rt6i_dst.plen != 128 ||
+ xdst->u.rt6.rt6i_src.plen != 128))) {
dst_clone(dst);
break;
}
@@ -59,6 +84,40 @@ __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
return dst;
}
+static inline struct in6_addr*
+__xfrm6_bundle_addr_remote(struct xfrm_state *x, struct in6_addr *addr)
+{
+ return (x->type->remote_addr) ?
+ (struct in6_addr*)x->type->remote_addr(x, (xfrm_address_t *)addr) :
+ (struct in6_addr*)&x->id.daddr;
+}
+
+static inline struct in6_addr*
+__xfrm6_bundle_addr_local(struct xfrm_state *x, struct in6_addr *addr)
+{
+ return (x->type->local_addr) ?
+ (struct in6_addr*)x->type->local_addr(x, (xfrm_address_t *)addr) :
+ (struct in6_addr*)&x->props.saddr;
+}
+
+static inline void
+__xfrm6_bundle_len_inc(int *len, int *nflen, struct xfrm_state *x)
+{
+ if (x->type->flags & XFRM_TYPE_NON_FRAGMENT)
+ *nflen += x->props.header_len;
+ else
+ *len += x->props.header_len;
+}
+
+static inline void
+__xfrm6_bundle_len_dec(int *len, int *nflen, struct xfrm_state *x)
+{
+ if (x->type->flags & XFRM_TYPE_NON_FRAGMENT)
+ *nflen -= x->props.header_len;
+ else
+ *len -= x->props.header_len;
+}
+
/* Allocate chain of dst_entry's, attach known xfrm's, calculate
* all the metrics... Shortly, bundle a bundle.
*/
@@ -83,6 +142,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int
int i;
int err = 0;
int header_len = 0;
+ int nfheader_len = 0;
int trailer_len = 0;
dst = dst_prev = NULL;
@@ -109,17 +169,18 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int
xdst = (struct xfrm_dst *)dst1;
xdst->route = &rt->u.dst;
+ xdst->genid = xfrm[i]->genid;
if (rt->rt6i_node)
xdst->route_cookie = rt->rt6i_node->fn_sernum;
dst1->next = dst_prev;
dst_prev = dst1;
- if (xfrm[i]->props.mode) {
- remote = (struct in6_addr*)&xfrm[i]->id.daddr;
- local = (struct in6_addr*)&xfrm[i]->props.saddr;
+ if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
+ remote = __xfrm6_bundle_addr_remote(xfrm[i], remote);
+ local = __xfrm6_bundle_addr_local(xfrm[i], local);
tunnel = 1;
}
- header_len += xfrm[i]->props.header_len;
+ __xfrm6_bundle_len_inc(&header_len, &nfheader_len, xfrm[i]);
trailer_len += xfrm[i]->props.trailer_len;
if (tunnel) {
@@ -154,6 +215,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int
dst_prev->flags |= DST_HOST;
dst_prev->lastuse = jiffies;
dst_prev->header_len = header_len;
+ dst_prev->nfheader_len = nfheader_len;
dst_prev->trailer_len = trailer_len;
memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics));
@@ -172,7 +234,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int
x->u.rt6.rt6i_src = rt0->rt6i_src;
x->u.rt6.rt6i_idev = rt0->rt6i_idev;
in6_dev_hold(rt0->rt6i_idev);
- header_len -= x->u.dst.xfrm->props.header_len;
+ __xfrm6_bundle_len_dec(&header_len, &nfheader_len, x->u.dst.xfrm);
trailer_len -= x->u.dst.xfrm->props.trailer_len;
}
@@ -232,6 +294,18 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl)
fl->proto = nexthdr;
return;
+#ifdef CONFIG_IPV6_MIP6
+ case IPPROTO_MH:
+ if (pskb_may_pull(skb, skb->nh.raw + offset + 3 - skb->data)) {
+ struct ip6_mh *mh;
+ mh = (struct ip6_mh *)exthdr;
+
+ fl->fl_mh_type = mh->ip6mh_type;
+ }
+ fl->proto = nexthdr;
+ return;
+#endif
+
/* XXX Why are there these headers? */
case IPPROTO_AH:
case IPPROTO_ESP:
@@ -308,6 +382,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.family = AF_INET6,
.dst_ops = &xfrm6_dst_ops,
.dst_lookup = xfrm6_dst_lookup,
+ .get_saddr = xfrm6_get_saddr,
.find_bundle = __xfrm6_find_bundle,
.bundle_create = __xfrm6_bundle_create,
.decode_session = _decode_session6,
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index b33296b3f6d..711bfafb247 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -42,102 +42,135 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl,
memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
if (ipv6_addr_any((struct in6_addr*)&x->props.saddr))
memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
- if (tmpl->mode && ipv6_addr_any((struct in6_addr*)&x->props.saddr)) {
- struct rt6_info *rt;
- struct flowi fl_tunnel = {
- .nl_u = {
- .ip6_u = {
- .daddr = *(struct in6_addr *)daddr,
- }
- }
- };
- if (!xfrm_dst_lookup((struct xfrm_dst **)&rt,
- &fl_tunnel, AF_INET6)) {
- ipv6_get_saddr(&rt->u.dst, (struct in6_addr *)daddr,
- (struct in6_addr *)&x->props.saddr);
- dst_release(&rt->u.dst);
- }
- }
x->props.mode = tmpl->mode;
x->props.reqid = tmpl->reqid;
x->props.family = AF_INET6;
}
-static struct xfrm_state *
-__xfrm6_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto)
+static int
+__xfrm6_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n)
{
- unsigned h = __xfrm6_spi_hash(daddr, spi, proto);
- struct xfrm_state *x;
-
- list_for_each_entry(x, xfrm6_state_afinfo.state_byspi+h, byspi) {
- if (x->props.family == AF_INET6 &&
- spi == x->id.spi &&
- ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) &&
- proto == x->id.proto) {
- xfrm_state_hold(x);
- return x;
+ int i;
+ int j = 0;
+
+ /* Rule 1: select IPsec transport except AH */
+ for (i = 0; i < n; i++) {
+ if (src[i]->props.mode == XFRM_MODE_TRANSPORT &&
+ src[i]->id.proto != IPPROTO_AH) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
+ }
+ if (j == n)
+ goto end;
+
+ /* Rule 2: select MIPv6 RO or inbound trigger */
+#ifdef CONFIG_IPV6_MIP6
+ for (i = 0; i < n; i++) {
+ if (src[i] &&
+ (src[i]->props.mode == XFRM_MODE_ROUTEOPTIMIZATION ||
+ src[i]->props.mode == XFRM_MODE_IN_TRIGGER)) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
+ }
+ if (j == n)
+ goto end;
+#endif
+
+ /* Rule 3: select IPsec transport AH */
+ for (i = 0; i < n; i++) {
+ if (src[i] &&
+ src[i]->props.mode == XFRM_MODE_TRANSPORT &&
+ src[i]->id.proto == IPPROTO_AH) {
+ dst[j++] = src[i];
+ src[i] = NULL;
}
}
- return NULL;
+ if (j == n)
+ goto end;
+
+ /* Rule 4: select IPsec tunnel */
+ for (i = 0; i < n; i++) {
+ if (src[i] &&
+ src[i]->props.mode == XFRM_MODE_TUNNEL) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
+ }
+ if (likely(j == n))
+ goto end;
+
+ /* Final rule */
+ for (i = 0; i < n; i++) {
+ if (src[i]) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
+ }
+
+ end:
+ return 0;
}
-static struct xfrm_state *
-__xfrm6_find_acq(u8 mode, u32 reqid, u8 proto,
- xfrm_address_t *daddr, xfrm_address_t *saddr,
- int create)
+static int
+__xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n)
{
- struct xfrm_state *x, *x0;
- unsigned h = __xfrm6_dst_hash(daddr);
-
- x0 = NULL;
-
- list_for_each_entry(x, xfrm6_state_afinfo.state_bydst+h, bydst) {
- if (x->props.family == AF_INET6 &&
- ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) &&
- mode == x->props.mode &&
- proto == x->id.proto &&
- ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)x->props.saddr.a6) &&
- reqid == x->props.reqid &&
- x->km.state == XFRM_STATE_ACQ &&
- !x->id.spi) {
- x0 = x;
- break;
- }
+ int i;
+ int j = 0;
+
+ /* Rule 1: select IPsec transport */
+ for (i = 0; i < n; i++) {
+ if (src[i]->mode == XFRM_MODE_TRANSPORT) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
}
- if (!x0 && create && (x0 = xfrm_state_alloc()) != NULL) {
- ipv6_addr_copy((struct in6_addr *)x0->sel.daddr.a6,
- (struct in6_addr *)daddr);
- ipv6_addr_copy((struct in6_addr *)x0->sel.saddr.a6,
- (struct in6_addr *)saddr);
- x0->sel.prefixlen_d = 128;
- x0->sel.prefixlen_s = 128;
- ipv6_addr_copy((struct in6_addr *)x0->props.saddr.a6,
- (struct in6_addr *)saddr);
- x0->km.state = XFRM_STATE_ACQ;
- ipv6_addr_copy((struct in6_addr *)x0->id.daddr.a6,
- (struct in6_addr *)daddr);
- x0->id.proto = proto;
- x0->props.family = AF_INET6;
- x0->props.mode = mode;
- x0->props.reqid = reqid;
- x0->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES;
- xfrm_state_hold(x0);
- x0->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ;
- add_timer(&x0->timer);
- xfrm_state_hold(x0);
- list_add_tail(&x0->bydst, xfrm6_state_afinfo.state_bydst+h);
- wake_up(&km_waitq);
+ if (j == n)
+ goto end;
+
+ /* Rule 2: select MIPv6 RO or inbound trigger */
+#ifdef CONFIG_IPV6_MIP6
+ for (i = 0; i < n; i++) {
+ if (src[i] &&
+ (src[i]->mode == XFRM_MODE_ROUTEOPTIMIZATION ||
+ src[i]->mode == XFRM_MODE_IN_TRIGGER)) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
}
- if (x0)
- xfrm_state_hold(x0);
- return x0;
+ if (j == n)
+ goto end;
+#endif
+
+ /* Rule 3: select IPsec tunnel */
+ for (i = 0; i < n; i++) {
+ if (src[i] &&
+ src[i]->mode == XFRM_MODE_TUNNEL) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
+ }
+ if (likely(j == n))
+ goto end;
+
+ /* Final rule */
+ for (i = 0; i < n; i++) {
+ if (src[i]) {
+ dst[j++] = src[i];
+ src[i] = NULL;
+ }
+ }
+
+ end:
+ return 0;
}
static struct xfrm_state_afinfo xfrm6_state_afinfo = {
.family = AF_INET6,
.init_tempsel = __xfrm6_init_tempsel,
- .state_lookup = __xfrm6_state_lookup,
- .find_acq = __xfrm6_find_acq,
+ .tmpl_sort = __xfrm6_tmpl_sort,
+ .state_sort = __xfrm6_state_sort,
};
void __init xfrm6_state_init(void)
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index c8f9369c2a8..59685ee8f70 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -307,7 +307,7 @@ static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
static int xfrm6_tunnel_init_state(struct xfrm_state *x)
{
- if (!x->props.mode)
+ if (x->props.mode != XFRM_MODE_TUNNEL)
return -EINVAL;
if (x->encap)