summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2016-10-20 00:10:27 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2016-10-20 00:10:27 -0300
commitd0b2f91bede3bd5e3d24dd6803e56eee959c1797 (patch)
tree7fee4ab0509879c373c4f2cbd5b8a5be5b4041ee /net/ipv6
parente914f8eb445e8f74b00303c19c2ffceaedd16a05 (diff)
Linux-libre 4.8.2-gnupck-4.8.2-gnu
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Makefile1
-rw-r--r--net/ipv6/addrconf.c325
-rw-r--r--net/ipv6/af_inet6.c15
-rw-r--r--net/ipv6/calipso.c1475
-rw-r--r--net/ipv6/exthdrs.c76
-rw-r--r--net/ipv6/exthdrs_core.c2
-rw-r--r--net/ipv6/fib6_rules.c6
-rw-r--r--net/ipv6/icmp.c78
-rw-r--r--net/ipv6/ila/ila.h3
-rw-r--r--net/ipv6/ila/ila_common.c16
-rw-r--r--net/ipv6/ila/ila_lwt.c4
-rw-r--r--net/ipv6/ila/ila_xlat.c8
-rw-r--r--net/ipv6/ip6_gre.c3
-rw-r--r--net/ipv6/ip6_icmp.c2
-rw-r--r--net/ipv6/ip6_input.c1
-rw-r--r--net/ipv6/ip6_output.c14
-rw-r--r--net/ipv6/ip6_vti.c19
-rw-r--r--net/ipv6/ip6mr.c34
-rw-r--r--net/ipv6/ipv6_sockglue.c1
-rw-r--r--net/ipv6/ndisc.c123
-rw-r--r--net/ipv6/netfilter/ip6_tables.c61
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c4
-rw-r--r--net/ipv6/netfilter/nft_chain_route_ipv6.c10
-rw-r--r--net/ipv6/netfilter/nft_reject_ipv6.c1
-rw-r--r--net/ipv6/ping.c35
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/route.c47
-rw-r--r--net/ipv6/sit.c140
-rw-r--r--net/ipv6/sysctl_net_ipv6.c19
-rw-r--r--net/ipv6/tcp_ipv6.c41
-rw-r--r--net/ipv6/udp.c9
-rw-r--r--net/ipv6/udplite.c1
-rw-r--r--net/ipv6/xfrm6_input.c15
-rw-r--r--net/ipv6/xfrm6_policy.c6
-rw-r--r--net/ipv6/xfrm6_tunnel.c2
35 files changed, 2233 insertions, 372 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 6d8ea0992..c174ccb34 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -22,6 +22,7 @@ ipv6-$(CONFIG_NETFILTER) += netfilter.o
ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
ipv6-$(CONFIG_PROC_FS) += proc.o
ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o
+ipv6-$(CONFIG_NETLABEL) += calipso.o
ipv6-objs += $(ipv6-y)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 82e367b9e..2f1f5d439 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -547,7 +547,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
struct sk_buff *skb;
int err = -ENOBUFS;
- skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC);
+ skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_KERNEL);
if (!skb)
goto errout;
@@ -559,7 +559,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_KERNEL);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err);
@@ -778,7 +778,14 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
}
if (p == &net->ipv6.devconf_all->forwarding) {
+ int old_dflt = net->ipv6.devconf_dflt->forwarding;
+
net->ipv6.devconf_dflt->forwarding = newf;
+ if ((!newf) ^ (!old_dflt))
+ inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv6.devconf_dflt);
+
addrconf_forward_change(net, newf);
if ((!newf) ^ (!old))
inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
@@ -1524,6 +1531,28 @@ out:
return hiscore_idx;
}
+static int ipv6_get_saddr_master(struct net *net,
+ const struct net_device *dst_dev,
+ const struct net_device *master,
+ struct ipv6_saddr_dst *dst,
+ struct ipv6_saddr_score *scores,
+ int hiscore_idx)
+{
+ struct inet6_dev *idev;
+
+ idev = __in6_dev_get(dst_dev);
+ if (idev)
+ hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+ scores, hiscore_idx);
+
+ idev = __in6_dev_get(master);
+ if (idev)
+ hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+ scores, hiscore_idx);
+
+ return hiscore_idx;
+}
+
int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
const struct in6_addr *daddr, unsigned int prefs,
struct in6_addr *saddr)
@@ -1577,13 +1606,39 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
if (idev)
hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
} else {
+ const struct net_device *master;
+ int master_idx = 0;
+
+ /* if dst_dev exists and is enslaved to an L3 device, then
+ * prefer addresses from dst_dev and then the master over
+ * any other enslaved devices in the L3 domain.
+ */
+ master = l3mdev_master_dev_rcu(dst_dev);
+ if (master) {
+ master_idx = master->ifindex;
+
+ hiscore_idx = ipv6_get_saddr_master(net, dst_dev,
+ master, &dst,
+ scores, hiscore_idx);
+
+ if (scores[hiscore_idx].ifa)
+ goto out;
+ }
+
for_each_netdev_rcu(net, dev) {
+ /* only consider addresses on devices in the
+ * same L3 domain
+ */
+ if (l3mdev_master_ifindex_rcu(dev) != master_idx)
+ continue;
idev = __in6_dev_get(dev);
if (!idev)
continue;
hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
}
}
+
+out:
rcu_read_unlock();
hiscore = &scores[hiscore_idx];
@@ -1824,7 +1879,6 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp)
void addrconf_dad_failure(struct inet6_ifaddr *ifp)
{
- struct in6_addr addr;
struct inet6_dev *idev = ifp->idev;
struct net *net = dev_net(ifp->idev->dev);
@@ -1886,18 +1940,6 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
in6_ifa_put(ifp2);
lock_errdad:
spin_lock_bh(&ifp->lock);
- } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
- addr.s6_addr32[0] = htonl(0xfe800000);
- addr.s6_addr32[1] = 0;
-
- if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
- ipv6_addr_equal(&ifp->addr, &addr)) {
- /* DAD failed for link-local based on MAC address */
- idev->cnf.disable_ipv6 = 1;
-
- pr_info("%s: IPv6 being disabled!\n",
- ifp->idev->dev->name);
- }
}
errdad:
@@ -2255,7 +2297,7 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
return ERR_PTR(-EACCES);
/* Add default multicast route */
- if (!(dev->flags & IFF_LOOPBACK))
+ if (!(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev))
addrconf_add_mroute(dev);
return idev;
@@ -2334,12 +2376,109 @@ static bool is_addr_mode_generate_stable(struct inet6_dev *idev)
idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
}
+int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
+ const struct prefix_info *pinfo,
+ struct inet6_dev *in6_dev,
+ const struct in6_addr *addr, int addr_type,
+ u32 addr_flags, bool sllao, bool tokenized,
+ __u32 valid_lft, u32 prefered_lft)
+{
+ struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1);
+ int create = 0, update_lft = 0;
+
+ if (!ifp && valid_lft) {
+ int max_addresses = in6_dev->cnf.max_addresses;
+
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+ if (in6_dev->cnf.optimistic_dad &&
+ !net->ipv6.devconf_all->forwarding && sllao)
+ addr_flags |= IFA_F_OPTIMISTIC;
+#endif
+
+ /* Do not allow to create too much of autoconfigured
+ * addresses; this would be too easy way to crash kernel.
+ */
+ if (!max_addresses ||
+ ipv6_count_addresses(in6_dev) < max_addresses)
+ ifp = ipv6_add_addr(in6_dev, addr, NULL,
+ pinfo->prefix_len,
+ addr_type&IPV6_ADDR_SCOPE_MASK,
+ addr_flags, valid_lft,
+ prefered_lft);
+
+ if (IS_ERR_OR_NULL(ifp))
+ return -1;
+
+ update_lft = 0;
+ create = 1;
+ spin_lock_bh(&ifp->lock);
+ ifp->flags |= IFA_F_MANAGETEMPADDR;
+ ifp->cstamp = jiffies;
+ ifp->tokenized = tokenized;
+ spin_unlock_bh(&ifp->lock);
+ addrconf_dad_start(ifp);
+ }
+
+ if (ifp) {
+ u32 flags;
+ unsigned long now;
+ u32 stored_lft;
+
+ /* update lifetime (RFC2462 5.5.3 e) */
+ spin_lock_bh(&ifp->lock);
+ now = jiffies;
+ if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
+ stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
+ else
+ stored_lft = 0;
+ if (!update_lft && !create && stored_lft) {
+ const u32 minimum_lft = min_t(u32,
+ stored_lft, MIN_VALID_LIFETIME);
+ valid_lft = max(valid_lft, minimum_lft);
+
+ /* RFC4862 Section 5.5.3e:
+ * "Note that the preferred lifetime of the
+ * corresponding address is always reset to
+ * the Preferred Lifetime in the received
+ * Prefix Information option, regardless of
+ * whether the valid lifetime is also reset or
+ * ignored."
+ *
+ * So we should always update prefered_lft here.
+ */
+ update_lft = 1;
+ }
+
+ if (update_lft) {
+ ifp->valid_lft = valid_lft;
+ ifp->prefered_lft = prefered_lft;
+ ifp->tstamp = now;
+ flags = ifp->flags;
+ ifp->flags &= ~IFA_F_DEPRECATED;
+ spin_unlock_bh(&ifp->lock);
+
+ if (!(flags&IFA_F_TENTATIVE))
+ ipv6_ifa_notify(0, ifp);
+ } else
+ spin_unlock_bh(&ifp->lock);
+
+ manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
+ create, now);
+
+ in6_ifa_put(ifp);
+ addrconf_verify();
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr);
+
void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
{
struct prefix_info *pinfo;
__u32 valid_lft;
__u32 prefered_lft;
- int addr_type;
+ int addr_type, err;
u32 addr_flags = 0;
struct inet6_dev *in6_dev;
struct net *net = dev_net(dev);
@@ -2433,10 +2572,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
/* Try to figure out our local address for this prefix */
if (pinfo->autoconf && in6_dev->cnf.autoconf) {
- struct inet6_ifaddr *ifp;
struct in6_addr addr;
- int create = 0, update_lft = 0;
- bool tokenized = false;
+ bool tokenized = false, dev_addr_generated = false;
if (pinfo->prefix_len == 64) {
memcpy(&addr, &pinfo->prefix, 8);
@@ -2454,106 +2591,36 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
goto ok;
} else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) &&
ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) {
- in6_dev_put(in6_dev);
- return;
+ goto put;
+ } else {
+ dev_addr_generated = true;
}
goto ok;
}
net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n",
pinfo->prefix_len);
- in6_dev_put(in6_dev);
- return;
+ goto put;
ok:
+ err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+ &addr, addr_type,
+ addr_flags, sllao,
+ tokenized, valid_lft,
+ prefered_lft);
+ if (err)
+ goto put;
- ifp = ipv6_get_ifaddr(net, &addr, dev, 1);
-
- if (!ifp && valid_lft) {
- int max_addresses = in6_dev->cnf.max_addresses;
-
-#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- if (in6_dev->cnf.optimistic_dad &&
- !net->ipv6.devconf_all->forwarding && sllao)
- addr_flags |= IFA_F_OPTIMISTIC;
-#endif
-
- /* Do not allow to create too much of autoconfigured
- * addresses; this would be too easy way to crash kernel.
- */
- if (!max_addresses ||
- ipv6_count_addresses(in6_dev) < max_addresses)
- ifp = ipv6_add_addr(in6_dev, &addr, NULL,
- pinfo->prefix_len,
- addr_type&IPV6_ADDR_SCOPE_MASK,
- addr_flags, valid_lft,
- prefered_lft);
-
- if (IS_ERR_OR_NULL(ifp)) {
- in6_dev_put(in6_dev);
- return;
- }
-
- update_lft = 0;
- create = 1;
- spin_lock_bh(&ifp->lock);
- ifp->flags |= IFA_F_MANAGETEMPADDR;
- ifp->cstamp = jiffies;
- ifp->tokenized = tokenized;
- spin_unlock_bh(&ifp->lock);
- addrconf_dad_start(ifp);
- }
-
- if (ifp) {
- u32 flags;
- unsigned long now;
- u32 stored_lft;
-
- /* update lifetime (RFC2462 5.5.3 e) */
- spin_lock_bh(&ifp->lock);
- now = jiffies;
- if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
- stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
- else
- stored_lft = 0;
- if (!update_lft && !create && stored_lft) {
- const u32 minimum_lft = min_t(u32,
- stored_lft, MIN_VALID_LIFETIME);
- valid_lft = max(valid_lft, minimum_lft);
-
- /* RFC4862 Section 5.5.3e:
- * "Note that the preferred lifetime of the
- * corresponding address is always reset to
- * the Preferred Lifetime in the received
- * Prefix Information option, regardless of
- * whether the valid lifetime is also reset or
- * ignored."
- *
- * So we should always update prefered_lft here.
- */
- update_lft = 1;
- }
-
- if (update_lft) {
- ifp->valid_lft = valid_lft;
- ifp->prefered_lft = prefered_lft;
- ifp->tstamp = now;
- flags = ifp->flags;
- ifp->flags &= ~IFA_F_DEPRECATED;
- spin_unlock_bh(&ifp->lock);
-
- if (!(flags&IFA_F_TENTATIVE))
- ipv6_ifa_notify(0, ifp);
- } else
- spin_unlock_bh(&ifp->lock);
-
- manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
- create, now);
-
- in6_ifa_put(ifp);
- addrconf_verify();
- }
+ /* Ignore error case here because previous prefix add addr was
+ * successful which will be notified.
+ */
+ ndisc_ops_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr,
+ addr_type, addr_flags, sllao,
+ tokenized, valid_lft,
+ prefered_lft,
+ dev_addr_generated);
}
inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
+put:
in6_dev_put(in6_dev);
}
@@ -2948,8 +3015,8 @@ static void init_loopback(struct net_device *dev)
}
}
-static void addrconf_add_linklocal(struct inet6_dev *idev,
- const struct in6_addr *addr, u32 flags)
+void addrconf_add_linklocal(struct inet6_dev *idev,
+ const struct in6_addr *addr, u32 flags)
{
struct inet6_ifaddr *ifp;
u32 addr_flags = flags | IFA_F_PERMANENT;
@@ -2968,6 +3035,7 @@ static void addrconf_add_linklocal(struct inet6_dev *idev,
in6_ifa_put(ifp);
}
}
+EXPORT_SYMBOL_GPL(addrconf_add_linklocal);
static bool ipv6_reserved_interfaceid(struct in6_addr address)
{
@@ -3551,8 +3619,7 @@ restart:
state = ifa->state;
ifa->state = INET6_IFADDR_STATE_DEAD;
- list_del(&ifa->if_list);
- list_add(&ifa->if_list, &del_list);
+ list_move(&ifa->if_list, &del_list);
}
spin_unlock_bh(&ifa->lock);
@@ -3749,6 +3816,7 @@ static void addrconf_dad_work(struct work_struct *w)
dad_work);
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
+ bool disable_ipv6 = false;
enum {
DAD_PROCESS,
@@ -3765,6 +3833,24 @@ static void addrconf_dad_work(struct work_struct *w)
} else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
action = DAD_ABORT;
ifp->state = INET6_IFADDR_STATE_POSTDAD;
+
+ if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 &&
+ !(ifp->flags & IFA_F_STABLE_PRIVACY)) {
+ struct in6_addr addr;
+
+ addr.s6_addr32[0] = htonl(0xfe800000);
+ addr.s6_addr32[1] = 0;
+
+ if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
+ ipv6_addr_equal(&ifp->addr, &addr)) {
+ /* DAD failed for link-local based on MAC */
+ idev->cnf.disable_ipv6 = 1;
+
+ pr_info("%s: IPv6 being disabled!\n",
+ ifp->idev->dev->name);
+ disable_ipv6 = true;
+ }
+ }
}
spin_unlock_bh(&ifp->lock);
@@ -3774,6 +3860,8 @@ static void addrconf_dad_work(struct work_struct *w)
} else if (action == DAD_ABORT) {
in6_ifa_hold(ifp);
addrconf_dad_stop(ifp, 1);
+ if (disable_ipv6)
+ addrconf_ifdown(idev->dev, 0);
goto out;
}
@@ -5946,7 +6034,7 @@ static const struct ctl_table addrconf_sysctl[] = {
static int __addrconf_sysctl_register(struct net *net, char *dev_name,
struct inet6_dev *idev, struct ipv6_devconf *p)
{
- int i;
+ int i, ifindex;
struct ctl_table *table;
char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
@@ -5966,6 +6054,13 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name,
if (!p->sysctl_header)
goto free;
+ if (!strcmp(dev_name, "all"))
+ ifindex = NETCONFA_IFINDEX_ALL;
+ else if (!strcmp(dev_name, "default"))
+ ifindex = NETCONFA_IFINDEX_DEFAULT;
+ else
+ ifindex = idev->dev->ifindex;
+ inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
return 0;
free:
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index bfa86f040..b454055ba 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -60,6 +60,7 @@
#ifdef CONFIG_IPV6_TUNNEL
#include <net/ip6_tunnel.h>
#endif
+#include <net/calipso.h>
#include <asm/uaccess.h>
#include <linux/mroute6.h>
@@ -92,6 +93,12 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces");
module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
+bool ipv6_mod_enabled(void)
+{
+ return disable_ipv6_mod == 0;
+}
+EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
+
static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
{
const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
@@ -977,6 +984,10 @@ static int __init inet6_init(void)
if (err)
goto pingv6_fail;
+ err = calipso_init();
+ if (err)
+ goto calipso_fail;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -987,8 +998,10 @@ out:
#ifdef CONFIG_SYSCTL
sysctl_fail:
- pingv6_exit();
+ calipso_exit();
#endif
+calipso_fail:
+ pingv6_exit();
pingv6_fail:
ipv6_packet_cleanup();
ipv6_packet_fail:
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
new file mode 100644
index 000000000..37ac9de71
--- /dev/null
+++ b/net/ipv6/calipso.c
@@ -0,0 +1,1475 @@
+/*
+ * CALIPSO - Common Architecture Label IPv6 Security Option
+ *
+ * This is an implementation of the CALIPSO protocol as specified in
+ * RFC 5570.
+ *
+ * Authors: Paul Moore <paul.moore@hp.com>
+ * Huw Davies <huw@codeweavers.com>
+ *
+ */
+
+/* (c) Copyright Hewlett-Packard Development Company, L.P., 2006, 2008
+ * (c) Copyright Huw Davies <huw@codeweavers.com>, 2015
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/jhash.h>
+#include <linux/audit.h>
+#include <linux/slab.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/tcp.h>
+#include <net/netlabel.h>
+#include <net/calipso.h>
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <asm/unaligned.h>
+#include <linux/crc-ccitt.h>
+
+/* Maximium size of the calipso option including
+ * the two-byte TLV header.
+ */
+#define CALIPSO_OPT_LEN_MAX (2 + 252)
+
+/* Size of the minimum calipso option including
+ * the two-byte TLV header.
+ */
+#define CALIPSO_HDR_LEN (2 + 8)
+
+/* Maximium size of the calipso option including
+ * the two-byte TLV header and upto 3 bytes of
+ * leading pad and 7 bytes of trailing pad.
+ */
+#define CALIPSO_OPT_LEN_MAX_WITH_PAD (3 + CALIPSO_OPT_LEN_MAX + 7)
+
+ /* Maximium size of u32 aligned buffer required to hold calipso
+ * option. Max of 3 initial pad bytes starting from buffer + 3.
+ * i.e. the worst case is when the previous tlv finishes on 4n + 3.
+ */
+#define CALIPSO_MAX_BUFFER (6 + CALIPSO_OPT_LEN_MAX)
+
+/* List of available DOI definitions */
+static DEFINE_SPINLOCK(calipso_doi_list_lock);
+static LIST_HEAD(calipso_doi_list);
+
+/* Label mapping cache */
+int calipso_cache_enabled = 1;
+int calipso_cache_bucketsize = 10;
+#define CALIPSO_CACHE_BUCKETBITS 7
+#define CALIPSO_CACHE_BUCKETS BIT(CALIPSO_CACHE_BUCKETBITS)
+#define CALIPSO_CACHE_REORDERLIMIT 10
+struct calipso_map_cache_bkt {
+ spinlock_t lock;
+ u32 size;
+ struct list_head list;
+};
+
+struct calipso_map_cache_entry {
+ u32 hash;
+ unsigned char *key;
+ size_t key_len;
+
+ struct netlbl_lsm_cache *lsm_data;
+
+ u32 activity;
+ struct list_head list;
+};
+
+static struct calipso_map_cache_bkt *calipso_cache;
+
+/* Label Mapping Cache Functions
+ */
+
+/**
+ * calipso_cache_entry_free - Frees a cache entry
+ * @entry: the entry to free
+ *
+ * Description:
+ * This function frees the memory associated with a cache entry including the
+ * LSM cache data if there are no longer any users, i.e. reference count == 0.
+ *
+ */
+static void calipso_cache_entry_free(struct calipso_map_cache_entry *entry)
+{
+ if (entry->lsm_data)
+ netlbl_secattr_cache_free(entry->lsm_data);
+ kfree(entry->key);
+ kfree(entry);
+}
+
+/**
+ * calipso_map_cache_hash - Hashing function for the CALIPSO cache
+ * @key: the hash key
+ * @key_len: the length of the key in bytes
+ *
+ * Description:
+ * The CALIPSO tag hashing function. Returns a 32-bit hash value.
+ *
+ */
+static u32 calipso_map_cache_hash(const unsigned char *key, u32 key_len)
+{
+ return jhash(key, key_len, 0);
+}
+
+/**
+ * calipso_cache_init - Initialize the CALIPSO cache
+ *
+ * Description:
+ * Initializes the CALIPSO label mapping cache, this function should be called
+ * before any of the other functions defined in this file. Returns zero on
+ * success, negative values on error.
+ *
+ */
+static int __init calipso_cache_init(void)
+{
+ u32 iter;
+
+ calipso_cache = kcalloc(CALIPSO_CACHE_BUCKETS,
+ sizeof(struct calipso_map_cache_bkt),
+ GFP_KERNEL);
+ if (!calipso_cache)
+ return -ENOMEM;
+
+ for (iter = 0; iter < CALIPSO_CACHE_BUCKETS; iter++) {
+ spin_lock_init(&calipso_cache[iter].lock);
+ calipso_cache[iter].size = 0;
+ INIT_LIST_HEAD(&calipso_cache[iter].list);
+ }
+
+ return 0;
+}
+
+/**
+ * calipso_cache_invalidate - Invalidates the current CALIPSO cache
+ *
+ * Description:
+ * Invalidates and frees any entries in the CALIPSO cache. Returns zero on
+ * success and negative values on failure.
+ *
+ */
+static void calipso_cache_invalidate(void)
+{
+ struct calipso_map_cache_entry *entry, *tmp_entry;
+ u32 iter;
+
+ for (iter = 0; iter < CALIPSO_CACHE_BUCKETS; iter++) {
+ spin_lock_bh(&calipso_cache[iter].lock);
+ list_for_each_entry_safe(entry,
+ tmp_entry,
+ &calipso_cache[iter].list, list) {
+ list_del(&entry->list);
+ calipso_cache_entry_free(entry);
+ }
+ calipso_cache[iter].size = 0;
+ spin_unlock_bh(&calipso_cache[iter].lock);
+ }
+}
+
+/**
+ * calipso_cache_check - Check the CALIPSO cache for a label mapping
+ * @key: the buffer to check
+ * @key_len: buffer length in bytes
+ * @secattr: the security attribute struct to use
+ *
+ * Description:
+ * This function checks the cache to see if a label mapping already exists for
+ * the given key. If there is a match then the cache is adjusted and the
+ * @secattr struct is populated with the correct LSM security attributes. The
+ * cache is adjusted in the following manner if the entry is not already the
+ * first in the cache bucket:
+ *
+ * 1. The cache entry's activity counter is incremented
+ * 2. The previous (higher ranking) entry's activity counter is decremented
+ * 3. If the difference between the two activity counters is geater than
+ * CALIPSO_CACHE_REORDERLIMIT the two entries are swapped
+ *
+ * Returns zero on success, -ENOENT for a cache miss, and other negative values
+ * on error.
+ *
+ */
+static int calipso_cache_check(const unsigned char *key,
+ u32 key_len,
+ struct netlbl_lsm_secattr *secattr)
+{
+ u32 bkt;
+ struct calipso_map_cache_entry *entry;
+ struct calipso_map_cache_entry *prev_entry = NULL;
+ u32 hash;
+
+ if (!calipso_cache_enabled)
+ return -ENOENT;
+
+ hash = calipso_map_cache_hash(key, key_len);
+ bkt = hash & (CALIPSO_CACHE_BUCKETS - 1);
+ spin_lock_bh(&calipso_cache[bkt].lock);
+ list_for_each_entry(entry, &calipso_cache[bkt].list, list) {
+ if (entry->hash == hash &&
+ entry->key_len == key_len &&
+ memcmp(entry->key, key, key_len) == 0) {
+ entry->activity += 1;
+ atomic_inc(&entry->lsm_data->refcount);
+ secattr->cache = entry->lsm_data;
+ secattr->flags |= NETLBL_SECATTR_CACHE;
+ secattr->type = NETLBL_NLTYPE_CALIPSO;
+ if (!prev_entry) {
+ spin_unlock_bh(&calipso_cache[bkt].lock);
+ return 0;
+ }
+
+ if (prev_entry->activity > 0)
+ prev_entry->activity -= 1;
+ if (entry->activity > prev_entry->activity &&
+ entry->activity - prev_entry->activity >
+ CALIPSO_CACHE_REORDERLIMIT) {
+ __list_del(entry->list.prev, entry->list.next);
+ __list_add(&entry->list,
+ prev_entry->list.prev,
+ &prev_entry->list);
+ }
+
+ spin_unlock_bh(&calipso_cache[bkt].lock);
+ return 0;
+ }
+ prev_entry = entry;
+ }
+ spin_unlock_bh(&calipso_cache[bkt].lock);
+
+ return -ENOENT;
+}
+
+/**
+ * calipso_cache_add - Add an entry to the CALIPSO cache
+ * @calipso_ptr: the CALIPSO option
+ * @secattr: the packet's security attributes
+ *
+ * Description:
+ * Add a new entry into the CALIPSO label mapping cache. Add the new entry to
+ * head of the cache bucket's list, if the cache bucket is out of room remove
+ * the last entry in the list first. It is important to note that there is
+ * currently no checking for duplicate keys. Returns zero on success,
+ * negative values on failure. The key stored starts at calipso_ptr + 2,
+ * i.e. the type and length bytes are not stored, this corresponds to
+ * calipso_ptr[1] bytes of data.
+ *
+ */
+static int calipso_cache_add(const unsigned char *calipso_ptr,
+ const struct netlbl_lsm_secattr *secattr)
+{
+ int ret_val = -EPERM;
+ u32 bkt;
+ struct calipso_map_cache_entry *entry = NULL;
+ struct calipso_map_cache_entry *old_entry = NULL;
+ u32 calipso_ptr_len;
+
+ if (!calipso_cache_enabled || calipso_cache_bucketsize <= 0)
+ return 0;
+
+ calipso_ptr_len = calipso_ptr[1];
+
+ entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ return -ENOMEM;
+ entry->key = kmemdup(calipso_ptr + 2, calipso_ptr_len, GFP_ATOMIC);
+ if (!entry->key) {
+ ret_val = -ENOMEM;
+ goto cache_add_failure;
+ }
+ entry->key_len = calipso_ptr_len;
+ entry->hash = calipso_map_cache_hash(calipso_ptr, calipso_ptr_len);
+ atomic_inc(&secattr->cache->refcount);
+ entry->lsm_data = secattr->cache;
+
+ bkt = entry->hash & (CALIPSO_CACHE_BUCKETS - 1);
+ spin_lock_bh(&calipso_cache[bkt].lock);
+ if (calipso_cache[bkt].size < calipso_cache_bucketsize) {
+ list_add(&entry->list, &calipso_cache[bkt].list);
+ calipso_cache[bkt].size += 1;
+ } else {
+ old_entry = list_entry(calipso_cache[bkt].list.prev,
+ struct calipso_map_cache_entry, list);
+ list_del(&old_entry->list);
+ list_add(&entry->list, &calipso_cache[bkt].list);
+ calipso_cache_entry_free(old_entry);
+ }
+ spin_unlock_bh(&calipso_cache[bkt].lock);
+
+ return 0;
+
+cache_add_failure:
+ if (entry)
+ calipso_cache_entry_free(entry);
+ return ret_val;
+}
+
+/* DOI List Functions
+ */
+
+/**
+ * calipso_doi_search - Searches for a DOI definition
+ * @doi: the DOI to search for
+ *
+ * Description:
+ * Search the DOI definition list for a DOI definition with a DOI value that
+ * matches @doi. The caller is responsible for calling rcu_read_[un]lock().
+ * Returns a pointer to the DOI definition on success and NULL on failure.
+ */
+static struct calipso_doi *calipso_doi_search(u32 doi)
+{
+ struct calipso_doi *iter;
+
+ list_for_each_entry_rcu(iter, &calipso_doi_list, list)
+ if (iter->doi == doi && atomic_read(&iter->refcount))
+ return iter;
+ return NULL;
+}
+
+/**
+ * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine
+ * @doi_def: the DOI structure
+ * @audit_info: NetLabel audit information
+ *
+ * Description:
+ * The caller defines a new DOI for use by the CALIPSO engine and calls this
+ * function to add it to the list of acceptable domains. The caller must
+ * ensure that the mapping table specified in @doi_def->map meets all of the
+ * requirements of the mapping type (see calipso.h for details). Returns
+ * zero on success and non-zero on failure.
+ *
+ */
+static int calipso_doi_add(struct calipso_doi *doi_def,
+ struct netlbl_audit *audit_info)
+{
+ int ret_val = -EINVAL;
+ u32 doi;
+ u32 doi_type;
+ struct audit_buffer *audit_buf;
+
+ doi = doi_def->doi;
+ doi_type = doi_def->type;
+
+ if (doi_def->doi == CALIPSO_DOI_UNKNOWN)
+ goto doi_add_return;
+
+ atomic_set(&doi_def->refcount, 1);
+
+ spin_lock(&calipso_doi_list_lock);
+ if (calipso_doi_search(doi_def->doi)) {
+ spin_unlock(&calipso_doi_list_lock);
+ ret_val = -EEXIST;
+ goto doi_add_return;
+ }
+ list_add_tail_rcu(&doi_def->list, &calipso_doi_list);
+ spin_unlock(&calipso_doi_list_lock);
+ ret_val = 0;
+
+doi_add_return:
+ audit_buf = netlbl_audit_start(AUDIT_MAC_CALIPSO_ADD, audit_info);
+ if (audit_buf) {
+ const char *type_str;
+
+ switch (doi_type) {
+ case CALIPSO_MAP_PASS:
+ type_str = "pass";
+ break;
+ default:
+ type_str = "(unknown)";
+ }
+ audit_log_format(audit_buf,
+ " calipso_doi=%u calipso_type=%s res=%u",
+ doi, type_str, ret_val == 0 ? 1 : 0);
+ audit_log_end(audit_buf);
+ }
+
+ return ret_val;
+}
+
+/**
+ * calipso_doi_free - Frees a DOI definition
+ * @doi_def: the DOI definition
+ *
+ * Description:
+ * This function frees all of the memory associated with a DOI definition.
+ *
+ */
+static void calipso_doi_free(struct calipso_doi *doi_def)
+{
+ kfree(doi_def);
+}
+
+/**
+ * calipso_doi_free_rcu - Frees a DOI definition via the RCU pointer
+ * @entry: the entry's RCU field
+ *
+ * Description:
+ * This function is designed to be used as a callback to the call_rcu()
+ * function so that the memory allocated to the DOI definition can be released
+ * safely.
+ *
+ */
+static void calipso_doi_free_rcu(struct rcu_head *entry)
+{
+ struct calipso_doi *doi_def;
+
+ doi_def = container_of(entry, struct calipso_doi, rcu);
+ calipso_doi_free(doi_def);
+}
+
+/**
+ * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine
+ * @doi: the DOI value
+ * @audit_secid: the LSM secid to use in the audit message
+ *
+ * Description:
+ * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will
+ * be called to release their own LSM domain mappings as well as our own
+ * domain list. Returns zero on success and negative values on failure.
+ *
+ */
+static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info)
+{
+ int ret_val;
+ struct calipso_doi *doi_def;
+ struct audit_buffer *audit_buf;
+
+ spin_lock(&calipso_doi_list_lock);
+ doi_def = calipso_doi_search(doi);
+ if (!doi_def) {
+ spin_unlock(&calipso_doi_list_lock);
+ ret_val = -ENOENT;
+ goto doi_remove_return;
+ }
+ if (!atomic_dec_and_test(&doi_def->refcount)) {
+ spin_unlock(&calipso_doi_list_lock);
+ ret_val = -EBUSY;
+ goto doi_remove_return;
+ }
+ list_del_rcu(&doi_def->list);
+ spin_unlock(&calipso_doi_list_lock);
+
+ call_rcu(&doi_def->rcu, calipso_doi_free_rcu);
+ ret_val = 0;
+
+doi_remove_return:
+ audit_buf = netlbl_audit_start(AUDIT_MAC_CALIPSO_DEL, audit_info);
+ if (audit_buf) {
+ audit_log_format(audit_buf,
+ " calipso_doi=%u res=%u",
+ doi, ret_val == 0 ? 1 : 0);
+ audit_log_end(audit_buf);
+ }
+
+ return ret_val;
+}
+
+/**
+ * calipso_doi_getdef - Returns a reference to a valid DOI definition
+ * @doi: the DOI value
+ *
+ * Description:
+ * Searches for a valid DOI definition and if one is found it is returned to
+ * the caller. Otherwise NULL is returned. The caller must ensure that
+ * calipso_doi_putdef() is called when the caller is done.
+ *
+ */
+static struct calipso_doi *calipso_doi_getdef(u32 doi)
+{
+ struct calipso_doi *doi_def;
+
+ rcu_read_lock();
+ doi_def = calipso_doi_search(doi);
+ if (!doi_def)
+ goto doi_getdef_return;
+ if (!atomic_inc_not_zero(&doi_def->refcount))
+ doi_def = NULL;
+
+doi_getdef_return:
+ rcu_read_unlock();
+ return doi_def;
+}
+
+/**
+ * calipso_doi_putdef - Releases a reference for the given DOI definition
+ * @doi_def: the DOI definition
+ *
+ * Description:
+ * Releases a DOI definition reference obtained from calipso_doi_getdef().
+ *
+ */
+static void calipso_doi_putdef(struct calipso_doi *doi_def)
+{
+ if (!doi_def)
+ return;
+
+ if (!atomic_dec_and_test(&doi_def->refcount))
+ return;
+ spin_lock(&calipso_doi_list_lock);
+ list_del_rcu(&doi_def->list);
+ spin_unlock(&calipso_doi_list_lock);
+
+ call_rcu(&doi_def->rcu, calipso_doi_free_rcu);
+}
+
+/**
+ * calipso_doi_walk - Iterate through the DOI definitions
+ * @skip_cnt: skip past this number of DOI definitions, updated
+ * @callback: callback for each DOI definition
+ * @cb_arg: argument for the callback function
+ *
+ * Description:
+ * Iterate over the DOI definition list, skipping the first @skip_cnt entries.
+ * For each entry call @callback, if @callback returns a negative value stop
+ * 'walking' through the list and return. Updates the value in @skip_cnt upon
+ * return. Returns zero on success, negative values on failure.
+ *
+ */
+static int calipso_doi_walk(u32 *skip_cnt,
+ int (*callback)(struct calipso_doi *doi_def,
+ void *arg),
+ void *cb_arg)
+{
+ int ret_val = -ENOENT;
+ u32 doi_cnt = 0;
+ struct calipso_doi *iter_doi;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(iter_doi, &calipso_doi_list, list)
+ if (atomic_read(&iter_doi->refcount) > 0) {
+ if (doi_cnt++ < *skip_cnt)
+ continue;
+ ret_val = callback(iter_doi, cb_arg);
+ if (ret_val < 0) {
+ doi_cnt--;
+ goto doi_walk_return;
+ }
+ }
+
+doi_walk_return:
+ rcu_read_unlock();
+ *skip_cnt = doi_cnt;
+ return ret_val;
+}
+
+/**
+ * calipso_validate - Validate a CALIPSO option
+ * @skb: the packet
+ * @option: the start of the option
+ *
+ * Description:
+ * This routine is called to validate a CALIPSO option.
+ * If the option is valid then %true is returned, otherwise
+ * %false is returned.
+ *
+ * The caller should have already checked that the length of the
+ * option (including the TLV header) is >= 10 and that the catmap
+ * length is consistent with the option length.
+ *
+ * We leave checks on the level and categories to the socket layer.
+ */
+bool calipso_validate(const struct sk_buff *skb, const unsigned char *option)
+{
+ struct calipso_doi *doi_def;
+ bool ret_val;
+ u16 crc, len = option[1] + 2;
+ static const u8 zero[2];
+
+ /* The original CRC runs over the option including the TLV header
+ * with the CRC-16 field (at offset 8) zeroed out. */
+ crc = crc_ccitt(0xffff, option, 8);
+ crc = crc_ccitt(crc, zero, sizeof(zero));
+ if (len > 10)
+ crc = crc_ccitt(crc, option + 10, len - 10);
+ crc = ~crc;
+ if (option[8] != (crc & 0xff) || option[9] != ((crc >> 8) & 0xff))
+ return false;
+
+ rcu_read_lock();
+ doi_def = calipso_doi_search(get_unaligned_be32(option + 2));
+ ret_val = !!doi_def;
+ rcu_read_unlock();
+
+ return ret_val;
+}
+
+/**
+ * calipso_map_cat_hton - Perform a category mapping from host to network
+ * @doi_def: the DOI definition
+ * @secattr: the security attributes
+ * @net_cat: the zero'd out category bitmap in network/CALIPSO format
+ * @net_cat_len: the length of the CALIPSO bitmap in bytes
+ *
+ * Description:
+ * Perform a label mapping to translate a local MLS category bitmap to the
+ * correct CALIPSO bitmap using the given DOI definition. Returns the minimum
+ * size in bytes of the network bitmap on success, negative values otherwise.
+ *
+ */
+static int calipso_map_cat_hton(const struct calipso_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr,
+ unsigned char *net_cat,
+ u32 net_cat_len)
+{
+ int spot = -1;
+ u32 net_spot_max = 0;
+ u32 net_clen_bits = net_cat_len * 8;
+
+ for (;;) {
+ spot = netlbl_catmap_walk(secattr->attr.mls.cat,
+ spot + 1);
+ if (spot < 0)
+ break;
+ if (spot >= net_clen_bits)
+ return -ENOSPC;
+ netlbl_bitmap_setbit(net_cat, spot, 1);
+
+ if (spot > net_spot_max)
+ net_spot_max = spot;
+ }
+
+ return (net_spot_max / 32 + 1) * 4;
+}
+
+/**
+ * calipso_map_cat_ntoh - Perform a category mapping from network to host
+ * @doi_def: the DOI definition
+ * @net_cat: the category bitmap in network/CALIPSO format
+ * @net_cat_len: the length of the CALIPSO bitmap in bytes
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Perform a label mapping to translate a CALIPSO bitmap to the correct local
+ * MLS category bitmap using the given DOI definition. Returns zero on
+ * success, negative values on failure.
+ *
+ */
+static int calipso_map_cat_ntoh(const struct calipso_doi *doi_def,
+ const unsigned char *net_cat,
+ u32 net_cat_len,
+ struct netlbl_lsm_secattr *secattr)
+{
+ int ret_val;
+ int spot = -1;
+ u32 net_clen_bits = net_cat_len * 8;
+
+ for (;;) {
+ spot = netlbl_bitmap_walk(net_cat,
+ net_clen_bits,
+ spot + 1,
+ 1);
+ if (spot < 0) {
+ if (spot == -2)
+ return -EFAULT;
+ return 0;
+ }
+
+ ret_val = netlbl_catmap_setbit(&secattr->attr.mls.cat,
+ spot,
+ GFP_ATOMIC);
+ if (ret_val != 0)
+ return ret_val;
+ }
+
+ return -EINVAL;
+}
+
+/**
+ * calipso_pad_write - Writes pad bytes in TLV format
+ * @buf: the buffer
+ * @offset: offset from start of buffer to write padding
+ * @count: number of pad bytes to write
+ *
+ * Description:
+ * Write @count bytes of TLV padding into @buffer starting at offset @offset.
+ * @count should be less than 8 - see RFC 4942.
+ *
+ */
+static int calipso_pad_write(unsigned char *buf, unsigned int offset,
+ unsigned int count)
+{
+ if (WARN_ON_ONCE(count >= 8))
+ return -EINVAL;
+
+ switch (count) {
+ case 0:
+ break;
+ case 1:
+ buf[offset] = IPV6_TLV_PAD1;
+ break;
+ default:
+ buf[offset] = IPV6_TLV_PADN;
+ buf[offset + 1] = count - 2;
+ if (count > 2)
+ memset(buf + offset + 2, 0, count - 2);
+ break;
+ }
+ return 0;
+}
+
+/**
+ * calipso_genopt - Generate a CALIPSO option
+ * @buf: the option buffer
+ * @start: offset from which to write
+ * @buf_len: the size of opt_buf
+ * @doi_def: the CALIPSO DOI to use
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Generate a CALIPSO option using the DOI definition and security attributes
+ * passed to the function. This also generates upto three bytes of leading
+ * padding that ensures that the option is 4n + 2 aligned. It returns the
+ * number of bytes written (including any initial padding).
+ */
+static int calipso_genopt(unsigned char *buf, u32 start, u32 buf_len,
+ const struct calipso_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr)
+{
+ int ret_val;
+ u32 len, pad;
+ u16 crc;
+ static const unsigned char padding[4] = {2, 1, 0, 3};
+ unsigned char *calipso;
+
+ /* CALIPSO has 4n + 2 alignment */
+ pad = padding[start & 3];
+ if (buf_len <= start + pad + CALIPSO_HDR_LEN)
+ return -ENOSPC;
+
+ if ((secattr->flags & NETLBL_SECATTR_MLS_LVL) == 0)
+ return -EPERM;
+
+ len = CALIPSO_HDR_LEN;
+
+ if (secattr->flags & NETLBL_SECATTR_MLS_CAT) {
+ ret_val = calipso_map_cat_hton(doi_def,
+ secattr,
+ buf + start + pad + len,
+ buf_len - start - pad - len);
+ if (ret_val < 0)
+ return ret_val;
+ len += ret_val;
+ }
+
+ calipso_pad_write(buf, start, pad);
+ calipso = buf + start + pad;
+
+ calipso[0] = IPV6_TLV_CALIPSO;
+ calipso[1] = len - 2;
+ *(__be32 *)(calipso + 2) = htonl(doi_def->doi);
+ calipso[6] = (len - CALIPSO_HDR_LEN) / 4;
+ calipso[7] = secattr->attr.mls.lvl,
+ crc = ~crc_ccitt(0xffff, calipso, len);
+ calipso[8] = crc & 0xff;
+ calipso[9] = (crc >> 8) & 0xff;
+ return pad + len;
+}
+
+/* Hop-by-hop hdr helper functions
+ */
+
+/**
+ * calipso_opt_update - Replaces socket's hop options with a new set
+ * @sk: the socket
+ * @hop: new hop options
+ *
+ * Description:
+ * Replaces @sk's hop options with @hop. @hop may be NULL to leave
+ * the socket with no hop options.
+ *
+ */
+static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop)
+{
+ struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts;
+
+ txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS,
+ hop, hop ? ipv6_optlen(hop) : 0);
+ txopt_put(old);
+ if (IS_ERR(txopts))
+ return PTR_ERR(txopts);
+
+ txopts = ipv6_update_options(sk, txopts);
+ if (txopts) {
+ atomic_sub(txopts->tot_len, &sk->sk_omem_alloc);
+ txopt_put(txopts);
+ }
+
+ return 0;
+}
+
+/**
+ * calipso_tlv_len - Returns the length of the TLV
+ * @opt: the option header
+ * @offset: offset of the TLV within the header
+ *
+ * Description:
+ * Returns the length of the TLV option at offset @offset within
+ * the option header @opt. Checks that the entire TLV fits inside
+ * the option header, returns a negative value if this is not the case.
+ */
+static int calipso_tlv_len(struct ipv6_opt_hdr *opt, unsigned int offset)
+{
+ unsigned char *tlv = (unsigned char *)opt;
+ unsigned int opt_len = ipv6_optlen(opt), tlv_len;
+
+ if (offset < sizeof(*opt) || offset >= opt_len)
+ return -EINVAL;
+ if (tlv[offset] == IPV6_TLV_PAD1)
+ return 1;
+ if (offset + 1 >= opt_len)
+ return -EINVAL;
+ tlv_len = tlv[offset + 1] + 2;
+ if (offset + tlv_len > opt_len)
+ return -EINVAL;
+ return tlv_len;
+}
+
+/**
+ * calipso_opt_find - Finds the CALIPSO option in an IPv6 hop options header
+ * @hop: the hop options header
+ * @start: on return holds the offset of any leading padding
+ * @end: on return holds the offset of the first non-pad TLV after CALIPSO
+ *
+ * Description:
+ * Finds the space occupied by a CALIPSO option (including any leading and
+ * trailing padding).
+ *
+ * If a CALIPSO option exists set @start and @end to the
+ * offsets within @hop of the start of padding before the first
+ * CALIPSO option and the end of padding after the first CALIPSO
+ * option. In this case the function returns 0.
+ *
+ * In the absence of a CALIPSO option, @start and @end will be
+ * set to the start and end of any trailing padding in the header.
+ * This is useful when appending a new option, as the caller may want
+ * to overwrite some of this padding. In this case the function will
+ * return -ENOENT.
+ */
+static int calipso_opt_find(struct ipv6_opt_hdr *hop, unsigned int *start,
+ unsigned int *end)
+{
+ int ret_val = -ENOENT, tlv_len;
+ unsigned int opt_len, offset, offset_s = 0, offset_e = 0;
+ unsigned char *opt = (unsigned char *)hop;
+
+ opt_len = ipv6_optlen(hop);
+ offset = sizeof(*hop);
+
+ while (offset < opt_len) {
+ tlv_len = calipso_tlv_len(hop, offset);
+ if (tlv_len < 0)
+ return tlv_len;
+
+ switch (opt[offset]) {
+ case IPV6_TLV_PAD1:
+ case IPV6_TLV_PADN:
+ if (offset_e)
+ offset_e = offset;
+ break;
+ case IPV6_TLV_CALIPSO:
+ ret_val = 0;
+ offset_e = offset;
+ break;
+ default:
+ if (offset_e == 0)
+ offset_s = offset;
+ else
+ goto out;
+ }
+ offset += tlv_len;
+ }
+
+out:
+ if (offset_s)
+ *start = offset_s + calipso_tlv_len(hop, offset_s);
+ else
+ *start = sizeof(*hop);
+ if (offset_e)
+ *end = offset_e + calipso_tlv_len(hop, offset_e);
+ else
+ *end = opt_len;
+
+ return ret_val;
+}
+
+/**
+ * calipso_opt_insert - Inserts a CALIPSO option into an IPv6 hop opt hdr
+ * @hop: the original hop options header
+ * @doi_def: the CALIPSO DOI to use
+ * @secattr: the specific security attributes of the socket
+ *
+ * Description:
+ * Creates a new hop options header based on @hop with a
+ * CALIPSO option added to it. If @hop already contains a CALIPSO
+ * option this is overwritten, otherwise the new option is appended
+ * after any existing options. If @hop is NULL then the new header
+ * will contain just the CALIPSO option and any needed padding.
+ *
+ */
+static struct ipv6_opt_hdr *
+calipso_opt_insert(struct ipv6_opt_hdr *hop,
+ const struct calipso_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr)
+{
+ unsigned int start, end, buf_len, pad, hop_len;
+ struct ipv6_opt_hdr *new;
+ int ret_val;
+
+ if (hop) {
+ hop_len = ipv6_optlen(hop);
+ ret_val = calipso_opt_find(hop, &start, &end);
+ if (ret_val && ret_val != -ENOENT)
+ return ERR_PTR(ret_val);
+ } else {
+ hop_len = 0;
+ start = sizeof(*hop);
+ end = 0;
+ }
+
+ buf_len = hop_len + start - end + CALIPSO_OPT_LEN_MAX_WITH_PAD;
+ new = kzalloc(buf_len, GFP_ATOMIC);
+ if (!new)
+ return ERR_PTR(-ENOMEM);
+
+ if (start > sizeof(*hop))
+ memcpy(new, hop, start);
+ ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def,
+ secattr);
+ if (ret_val < 0) {
+ kfree(new);
+ return ERR_PTR(ret_val);
+ }
+
+ buf_len = start + ret_val;
+ /* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */
+ pad = ((buf_len & 4) + (end & 7)) & 7;
+ calipso_pad_write((unsigned char *)new, buf_len, pad);
+ buf_len += pad;
+
+ if (end != hop_len) {
+ memcpy((char *)new + buf_len, (char *)hop + end, hop_len - end);
+ buf_len += hop_len - end;
+ }
+ new->nexthdr = 0;
+ new->hdrlen = buf_len / 8 - 1;
+
+ return new;
+}
+
+/**
+ * calipso_opt_del - Removes the CALIPSO option from an option header
+ * @hop: the original header
+ * @new: the new header
+ *
+ * Description:
+ * Creates a new header based on @hop without any CALIPSO option. If @hop
+ * doesn't contain a CALIPSO option it returns -ENOENT. If @hop contains
+ * no other non-padding options, it returns zero with @new set to NULL.
+ * Otherwise it returns zero, creates a new header without the CALIPSO
+ * option (and removing as much padding as possible) and returns with
+ * @new set to that header.
+ *
+ */
+static int calipso_opt_del(struct ipv6_opt_hdr *hop,
+ struct ipv6_opt_hdr **new)
+{
+ int ret_val;
+ unsigned int start, end, delta, pad, hop_len;
+
+ ret_val = calipso_opt_find(hop, &start, &end);
+ if (ret_val)
+ return ret_val;
+
+ hop_len = ipv6_optlen(hop);
+ if (start == sizeof(*hop) && end == hop_len) {
+ /* There's no other option in the header so return NULL */
+ *new = NULL;
+ return 0;
+ }
+
+ delta = (end - start) & ~7;
+ *new = kzalloc(hop_len - delta, GFP_ATOMIC);
+ if (!*new)
+ return -ENOMEM;
+
+ memcpy(*new, hop, start);
+ (*new)->hdrlen -= delta / 8;
+ pad = (end - start) & 7;
+ calipso_pad_write((unsigned char *)*new, start, pad);
+ if (end != hop_len)
+ memcpy((char *)*new + start + pad, (char *)hop + end,
+ hop_len - end);
+
+ return 0;
+}
+
+/**
+ * calipso_opt_getattr - Get the security attributes from a memory block
+ * @calipso: the CALIPSO option
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Inspect @calipso and return the security attributes in @secattr.
+ * Returns zero on success and negative values on failure.
+ *
+ */
+static int calipso_opt_getattr(const unsigned char *calipso,
+ struct netlbl_lsm_secattr *secattr)
+{
+ int ret_val = -ENOMSG;
+ u32 doi, len = calipso[1], cat_len = calipso[6] * 4;
+ struct calipso_doi *doi_def;
+
+ if (cat_len + 8 > len)
+ return -EINVAL;
+
+ if (calipso_cache_check(calipso + 2, calipso[1], secattr) == 0)
+ return 0;
+
+ doi = get_unaligned_be32(calipso + 2);
+ rcu_read_lock();
+ doi_def = calipso_doi_search(doi);
+ if (!doi_def)
+ goto getattr_return;
+
+ secattr->attr.mls.lvl = calipso[7];
+ secattr->flags |= NETLBL_SECATTR_MLS_LVL;
+
+ if (cat_len) {
+ ret_val = calipso_map_cat_ntoh(doi_def,
+ calipso + 10,
+ cat_len,
+ secattr);
+ if (ret_val != 0) {
+ netlbl_catmap_free(secattr->attr.mls.cat);
+ goto getattr_return;
+ }
+
+ secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+ }
+
+ secattr->type = NETLBL_NLTYPE_CALIPSO;
+
+getattr_return:
+ rcu_read_unlock();
+ return ret_val;
+}
+
+/* sock functions.
+ */
+
+/**
+ * calipso_sock_getattr - Get the security attributes from a sock
+ * @sk: the sock
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Query @sk to see if there is a CALIPSO option attached to the sock and if
+ * there is return the CALIPSO security attributes in @secattr. This function
+ * requires that @sk be locked, or privately held, but it does not do any
+ * locking itself. Returns zero on success and negative values on failure.
+ *
+ */
+static int calipso_sock_getattr(struct sock *sk,
+ struct netlbl_lsm_secattr *secattr)
+{
+ struct ipv6_opt_hdr *hop;
+ int opt_len, len, ret_val = -ENOMSG, offset;
+ unsigned char *opt;
+ struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+
+ if (!txopts || !txopts->hopopt)
+ goto done;
+
+ hop = txopts->hopopt;
+ opt = (unsigned char *)hop;
+ opt_len = ipv6_optlen(hop);
+ offset = sizeof(*hop);
+ while (offset < opt_len) {
+ len = calipso_tlv_len(hop, offset);
+ if (len < 0) {
+ ret_val = len;
+ goto done;
+ }
+ switch (opt[offset]) {
+ case IPV6_TLV_CALIPSO:
+ if (len < CALIPSO_HDR_LEN)
+ ret_val = -EINVAL;
+ else
+ ret_val = calipso_opt_getattr(&opt[offset],
+ secattr);
+ goto done;
+ default:
+ offset += len;
+ break;
+ }
+ }
+done:
+ txopt_put(txopts);
+ return ret_val;
+}
+
+/**
+ * calipso_sock_setattr - Add a CALIPSO option to a socket
+ * @sk: the socket
+ * @doi_def: the CALIPSO DOI to use
+ * @secattr: the specific security attributes of the socket
+ *
+ * Description:
+ * Set the CALIPSO option on the given socket using the DOI definition and
+ * security attributes passed to the function. This function requires
+ * exclusive access to @sk, which means it either needs to be in the
+ * process of being created or locked. Returns zero on success and negative
+ * values on failure.
+ *
+ */
+static int calipso_sock_setattr(struct sock *sk,
+ const struct calipso_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr)
+{
+ int ret_val;
+ struct ipv6_opt_hdr *old, *new;
+ struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+
+ old = NULL;
+ if (txopts)
+ old = txopts->hopopt;
+
+ new = calipso_opt_insert(old, doi_def, secattr);
+ txopt_put(txopts);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ ret_val = calipso_opt_update(sk, new);
+
+ kfree(new);
+ return ret_val;
+}
+
+/**
+ * calipso_sock_delattr - Delete the CALIPSO option from a socket
+ * @sk: the socket
+ *
+ * Description:
+ * Removes the CALIPSO option from a socket, if present.
+ *
+ */
+static void calipso_sock_delattr(struct sock *sk)
+{
+ struct ipv6_opt_hdr *new_hop;
+ struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+
+ if (!txopts || !txopts->hopopt)
+ goto done;
+
+ if (calipso_opt_del(txopts->hopopt, &new_hop))
+ goto done;
+
+ calipso_opt_update(sk, new_hop);
+ kfree(new_hop);
+
+done:
+ txopt_put(txopts);
+}
+
+/* request sock functions.
+ */
+
+/**
+ * calipso_req_setattr - Add a CALIPSO option to a connection request socket
+ * @req: the connection request socket
+ * @doi_def: the CALIPSO DOI to use
+ * @secattr: the specific security attributes of the socket
+ *
+ * Description:
+ * Set the CALIPSO option on the given socket using the DOI definition and
+ * security attributes passed to the function. Returns zero on success and
+ * negative values on failure.
+ *
+ */
+static int calipso_req_setattr(struct request_sock *req,
+ const struct calipso_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr)
+{
+ struct ipv6_txoptions *txopts;
+ struct inet_request_sock *req_inet = inet_rsk(req);
+ struct ipv6_opt_hdr *old, *new;
+ struct sock *sk = sk_to_full_sk(req_to_sk(req));
+
+ if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt)
+ old = req_inet->ipv6_opt->hopopt;
+ else
+ old = NULL;
+
+ new = calipso_opt_insert(old, doi_def, secattr);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
+ new, new ? ipv6_optlen(new) : 0);
+
+ kfree(new);
+
+ if (IS_ERR(txopts))
+ return PTR_ERR(txopts);
+
+ txopts = xchg(&req_inet->ipv6_opt, txopts);
+ if (txopts) {
+ atomic_sub(txopts->tot_len, &sk->sk_omem_alloc);
+ txopt_put(txopts);
+ }
+
+ return 0;
+}
+
+/**
+ * calipso_req_delattr - Delete the CALIPSO option from a request socket
+ * @reg: the request socket
+ *
+ * Description:
+ * Removes the CALIPSO option from a request socket, if present.
+ *
+ */
+static void calipso_req_delattr(struct request_sock *req)
+{
+ struct inet_request_sock *req_inet = inet_rsk(req);
+ struct ipv6_opt_hdr *new;
+ struct ipv6_txoptions *txopts;
+ struct sock *sk = sk_to_full_sk(req_to_sk(req));
+
+ if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt)
+ return;
+
+ if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new))
+ return; /* Nothing to do */
+
+ txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
+ new, new ? ipv6_optlen(new) : 0);
+
+ if (!IS_ERR(txopts)) {
+ txopts = xchg(&req_inet->ipv6_opt, txopts);
+ if (txopts) {
+ atomic_sub(txopts->tot_len, &sk->sk_omem_alloc);
+ txopt_put(txopts);
+ }
+ }
+ kfree(new);
+}
+
+/* skbuff functions.
+ */
+
+/**
+ * calipso_skbuff_optptr - Find the CALIPSO option in the packet
+ * @skb: the packet
+ *
+ * Description:
+ * Parse the packet's IP header looking for a CALIPSO option. Returns a pointer
+ * to the start of the CALIPSO option on success, NULL if one if not found.
+ *
+ */
+static unsigned char *calipso_skbuff_optptr(const struct sk_buff *skb)
+{
+ const struct ipv6hdr *ip6_hdr = ipv6_hdr(skb);
+ int offset;
+
+ if (ip6_hdr->nexthdr != NEXTHDR_HOP)
+ return NULL;
+
+ offset = ipv6_find_tlv(skb, sizeof(*ip6_hdr), IPV6_TLV_CALIPSO);
+ if (offset >= 0)
+ return (unsigned char *)ip6_hdr + offset;
+
+ return NULL;
+}
+
+/**
+ * calipso_skbuff_setattr - Set the CALIPSO option on a packet
+ * @skb: the packet
+ * @doi_def: the CALIPSO DOI to use
+ * @secattr: the security attributes
+ *
+ * Description:
+ * Set the CALIPSO option on the given packet based on the security attributes.
+ * Returns a pointer to the IP header on success and NULL on failure.
+ *
+ */
+static int calipso_skbuff_setattr(struct sk_buff *skb,
+ const struct calipso_doi *doi_def,
+ const struct netlbl_lsm_secattr *secattr)
+{
+ int ret_val;
+ struct ipv6hdr *ip6_hdr;
+ struct ipv6_opt_hdr *hop;
+ unsigned char buf[CALIPSO_MAX_BUFFER];
+ int len_delta, new_end, pad;
+ unsigned int start, end;
+
+ ip6_hdr = ipv6_hdr(skb);
+ if (ip6_hdr->nexthdr == NEXTHDR_HOP) {
+ hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1);
+ ret_val = calipso_opt_find(hop, &start, &end);
+ if (ret_val && ret_val != -ENOENT)
+ return ret_val;
+ } else {
+ start = 0;
+ end = 0;
+ }
+
+ memset(buf, 0, sizeof(buf));
+ ret_val = calipso_genopt(buf, start & 3, sizeof(buf), doi_def, secattr);
+ if (ret_val < 0)
+ return ret_val;
+
+ new_end = start + ret_val;
+ /* At this point new_end aligns to 4n, so (new_end & 4) pads to 8n */
+ pad = ((new_end & 4) + (end & 7)) & 7;
+ len_delta = new_end - (int)end + pad;
+ ret_val = skb_cow(skb, skb_headroom(skb) + len_delta);
+ if (ret_val < 0)
+ return ret_val;
+
+ if (len_delta) {
+ if (len_delta > 0)
+ skb_push(skb, len_delta);
+ else
+ skb_pull(skb, -len_delta);
+ memmove((char *)ip6_hdr - len_delta, ip6_hdr,
+ sizeof(*ip6_hdr) + start);
+ skb_reset_network_header(skb);
+ ip6_hdr = ipv6_hdr(skb);
+ }
+
+ hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1);
+ if (start == 0) {
+ struct ipv6_opt_hdr *new_hop = (struct ipv6_opt_hdr *)buf;
+
+ new_hop->nexthdr = ip6_hdr->nexthdr;
+ new_hop->hdrlen = len_delta / 8 - 1;
+ ip6_hdr->nexthdr = NEXTHDR_HOP;
+ } else {
+ hop->hdrlen += len_delta / 8;
+ }
+ memcpy((char *)hop + start, buf + (start & 3), new_end - start);
+ calipso_pad_write((unsigned char *)hop, new_end, pad);
+
+ return 0;
+}
+
+/**
+ * calipso_skbuff_delattr - Delete any CALIPSO options from a packet
+ * @skb: the packet
+ *
+ * Description:
+ * Removes any and all CALIPSO options from the given packet. Returns zero on
+ * success, negative values on failure.
+ *
+ */
+static int calipso_skbuff_delattr(struct sk_buff *skb)
+{
+ int ret_val;
+ struct ipv6hdr *ip6_hdr;
+ struct ipv6_opt_hdr *old_hop;
+ u32 old_hop_len, start = 0, end = 0, delta, size, pad;
+
+ if (!calipso_skbuff_optptr(skb))
+ return 0;
+
+ /* since we are changing the packet we should make a copy */
+ ret_val = skb_cow(skb, skb_headroom(skb));
+ if (ret_val < 0)
+ return ret_val;
+
+ ip6_hdr = ipv6_hdr(skb);
+ old_hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1);
+ old_hop_len = ipv6_optlen(old_hop);
+
+ ret_val = calipso_opt_find(old_hop, &start, &end);
+ if (ret_val)
+ return ret_val;
+
+ if (start == sizeof(*old_hop) && end == old_hop_len) {
+ /* There's no other option in the header so we delete
+ * the whole thing. */
+ delta = old_hop_len;
+ size = sizeof(*ip6_hdr);
+ ip6_hdr->nexthdr = old_hop->nexthdr;
+ } else {
+ delta = (end - start) & ~7;
+ if (delta)
+ old_hop->hdrlen -= delta / 8;
+ pad = (end - start) & 7;
+ size = sizeof(*ip6_hdr) + start + pad;
+ calipso_pad_write((unsigned char *)old_hop, start, pad);
+ }
+
+ if (delta) {
+ skb_pull(skb, delta);
+ memmove((char *)ip6_hdr + delta, ip6_hdr, size);
+ skb_reset_network_header(skb);
+ }
+
+ return 0;
+}
+
+static const struct netlbl_calipso_ops ops = {
+ .doi_add = calipso_doi_add,
+ .doi_free = calipso_doi_free,
+ .doi_remove = calipso_doi_remove,
+ .doi_getdef = calipso_doi_getdef,
+ .doi_putdef = calipso_doi_putdef,
+ .doi_walk = calipso_doi_walk,
+ .sock_getattr = calipso_sock_getattr,
+ .sock_setattr = calipso_sock_setattr,
+ .sock_delattr = calipso_sock_delattr,
+ .req_setattr = calipso_req_setattr,
+ .req_delattr = calipso_req_delattr,
+ .opt_getattr = calipso_opt_getattr,
+ .skbuff_optptr = calipso_skbuff_optptr,
+ .skbuff_setattr = calipso_skbuff_setattr,
+ .skbuff_delattr = calipso_skbuff_delattr,
+ .cache_invalidate = calipso_cache_invalidate,
+ .cache_add = calipso_cache_add
+};
+
+/**
+ * calipso_init - Initialize the CALIPSO module
+ *
+ * Description:
+ * Initialize the CALIPSO module and prepare it for use. Returns zero on
+ * success and negative values on failure.
+ *
+ */
+int __init calipso_init(void)
+{
+ int ret_val;
+
+ ret_val = calipso_cache_init();
+ if (!ret_val)
+ netlbl_calipso_ops_register(&ops);
+ return ret_val;
+}
+
+void calipso_exit(void)
+{
+ netlbl_calipso_ops_register(NULL);
+ calipso_cache_invalidate();
+ kfree(calipso_cache);
+}
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 8de5dd7aa..139ceb68b 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -43,6 +43,7 @@
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
+#include <net/calipso.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
@@ -603,6 +604,28 @@ drop:
return false;
}
+/* CALIPSO RFC 5570 */
+
+static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff)
+{
+ const unsigned char *nh = skb_network_header(skb);
+
+ if (nh[optoff + 1] < 8)
+ goto drop;
+
+ if (nh[optoff + 6] * 4 + 8 > nh[optoff + 1])
+ goto drop;
+
+ if (!calipso_validate(skb, nh + optoff))
+ goto drop;
+
+ return true;
+
+drop:
+ kfree_skb(skb);
+ return false;
+}
+
static const struct tlvtype_proc tlvprochopopt_lst[] = {
{
.type = IPV6_TLV_ROUTERALERT,
@@ -612,6 +635,10 @@ static const struct tlvtype_proc tlvprochopopt_lst[] = {
.type = IPV6_TLV_JUMBO,
.func = ipv6_hop_jumbo,
},
+ {
+ .type = IPV6_TLV_CALIPSO,
+ .func = ipv6_hop_calipso,
+ },
{ -1, }
};
@@ -758,6 +785,27 @@ static int ipv6_renew_option(void *ohdr,
return 0;
}
+/**
+ * ipv6_renew_options - replace a specific ext hdr with a new one.
+ *
+ * @sk: sock from which to allocate memory
+ * @opt: original options
+ * @newtype: option type to replace in @opt
+ * @newopt: new option of type @newtype to replace (user-mem)
+ * @newoptlen: length of @newopt
+ *
+ * Returns a new set of options which is a copy of @opt with the
+ * option type @newtype replaced with @newopt.
+ *
+ * @opt may be NULL, in which case a new set of options is returned
+ * containing just @newopt.
+ *
+ * @newopt may be NULL, in which case the specified option type is
+ * not copied into the new set of options.
+ *
+ * The new set of options is allocated from the socket option memory
+ * buffer of @sk.
+ */
struct ipv6_txoptions *
ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
int newtype,
@@ -830,6 +878,34 @@ out:
return ERR_PTR(err);
}
+/**
+ * ipv6_renew_options_kern - replace a specific ext hdr with a new one.
+ *
+ * @sk: sock from which to allocate memory
+ * @opt: original options
+ * @newtype: option type to replace in @opt
+ * @newopt: new option of type @newtype to replace (kernel-mem)
+ * @newoptlen: length of @newopt
+ *
+ * See ipv6_renew_options(). The difference is that @newopt is
+ * kernel memory, rather than user memory.
+ */
+struct ipv6_txoptions *
+ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt,
+ int newtype, struct ipv6_opt_hdr *newopt,
+ int newoptlen)
+{
+ struct ipv6_txoptions *ret_val;
+ const mm_segment_t old_fs = get_fs();
+
+ set_fs(KERNEL_DS);
+ ret_val = ipv6_renew_options(sk, opt, newtype,
+ (struct ipv6_opt_hdr __user *)newopt,
+ newoptlen);
+ set_fs(old_fs);
+ return ret_val;
+}
+
struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
struct ipv6_txoptions *opt)
{
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 9508a20fb..305e2ed73 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -112,7 +112,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
}
EXPORT_SYMBOL(ipv6_skip_exthdr);
-int ipv6_find_tlv(struct sk_buff *skb, int offset, int type)
+int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type)
{
const unsigned char *nh = skb_network_header(skb);
int packet_len = skb_tail_pointer(skb) - skb_network_header(skb);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index ed33abf57..5857c1fc8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -67,6 +67,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
struct net *net = rule->fr_net;
pol_lookup_t lookup = arg->lookup_ptr;
int err = 0;
+ u32 tb_id;
switch (rule->action) {
case FR_ACT_TO_TBL:
@@ -86,7 +87,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
goto discard_pkt;
}
- table = fib6_get_table(net, rule->table);
+ tb_id = fib_rule_get_table(rule, arg);
+ table = fib6_get_table(net, tb_id);
if (!table) {
err = -EAGAIN;
goto out;
@@ -199,7 +201,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct net *net = sock_net(skb->sk);
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
- if (rule->action == FR_ACT_TO_TBL) {
+ if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
if (rule->table == RT6_TABLE_UNSPEC)
goto errout;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index a4fa84076..bd59c343d 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -388,7 +388,8 @@ relookup_failed:
/*
* Send an ICMP message in response to a packet in error
*/
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+ const struct in6_addr *force_saddr)
{
struct net *net = dev_net(skb->dev);
struct inet6_dev *idev = NULL;
@@ -475,6 +476,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = hdr->saddr;
+ if (force_saddr)
+ saddr = force_saddr;
if (saddr)
fl6.saddr = *saddr;
fl6.flowi6_mark = mark;
@@ -502,12 +505,14 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
+ ipc6.tclass = np->tclass;
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
goto out;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- ipc6.tclass = np->tclass;
ipc6.dontfrag = np->dontfrag;
ipc6.opt = NULL;
@@ -549,10 +554,75 @@ out:
*/
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
- icmp6_send(skb, ICMPV6_PARAMPROB, code, pos);
+ icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
kfree_skb(skb);
}
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ * @nhs is the size of the tunnel header(s) :
+ * Either an IPv4 header for SIT encap
+ * an IPv4 header + GRE header for GRE encap
+ */
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+ unsigned int data_len)
+{
+ struct in6_addr temp_saddr;
+ struct rt6_info *rt;
+ struct sk_buff *skb2;
+ u32 info = 0;
+
+ if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
+ return 1;
+
+ /* RFC 4884 (partial) support for ICMP extensions */
+ if (data_len < 128 || (data_len & 7) || skb->len < data_len)
+ data_len = 0;
+
+ skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
+
+ if (!skb2)
+ return 1;
+
+ skb_dst_drop(skb2);
+ skb_pull(skb2, nhs);
+ skb_reset_network_header(skb2);
+
+ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+
+ if (rt && rt->dst.dev)
+ skb2->dev = rt->dst.dev;
+
+ ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
+
+ if (data_len) {
+ /* RFC 4884 (partial) support :
+ * insert 0 padding at the end, before the extensions
+ */
+ __skb_push(skb2, nhs);
+ skb_reset_network_header(skb2);
+ memmove(skb2->data, skb2->data + nhs, data_len - nhs);
+ memset(skb2->data + data_len - nhs, 0, nhs);
+ /* RFC 4884 4.5 : Length is measured in 64-bit words,
+ * and stored in reserved[0]
+ */
+ info = (data_len/8) << 24;
+ }
+ if (type == ICMP_TIME_EXCEEDED)
+ icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
+ info, &temp_saddr);
+ else
+ icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
+ info, &temp_saddr);
+ if (rt)
+ ip6_rt_put(rt);
+
+ kfree_skb(skb2);
+
+ return 0;
+}
+EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
+
static void icmpv6_echo_reply(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
@@ -585,7 +655,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.daddr = ipv6_hdr(skb)->saddr;
if (saddr)
fl6.saddr = *saddr;
- fl6.flowi6_oif = l3mdev_fib_oif(skb->dev);
+ fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
index d08fd2d48..e0170f62b 100644
--- a/net/ipv6/ila/ila.h
+++ b/net/ipv6/ila/ila.h
@@ -109,7 +109,8 @@ static inline bool ila_csum_neutral_set(struct ila_identifier ident)
return !!(ident.csum_neutral);
}
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p);
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+ bool set_csum_neutral);
void ila_init_saved_csum(struct ila_params *p);
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 0e94042d1..ec9efbcda 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -34,12 +34,12 @@ static void ila_csum_do_neutral(struct ila_addr *iaddr,
if (p->locator_match.v64) {
diff = p->csum_diff;
} else {
- diff = compute_csum_diff8((__be32 *)iaddr,
- (__be32 *)&p->locator);
+ diff = compute_csum_diff8((__be32 *)&p->locator,
+ (__be32 *)iaddr);
}
fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ?
- ~CSUM_NEUTRAL_FLAG : CSUM_NEUTRAL_FLAG);
+ CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG);
diff = csum_add(diff, fval);
@@ -103,7 +103,8 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
iaddr->loc = p->locator;
}
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+ bool set_csum_neutral)
{
struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct ila_addr *iaddr = ila_a2i(&ip6h->daddr);
@@ -114,7 +115,8 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
* is a locator being translated to a SIR address.
* Perform (receiver) checksum-neutral translation.
*/
- ila_csum_do_neutral(iaddr, p);
+ if (!set_csum_neutral)
+ ila_csum_do_neutral(iaddr, p);
} else {
switch (p->csum_mode) {
case ILA_CSUM_ADJUST_TRANSPORT:
@@ -138,8 +140,8 @@ void ila_init_saved_csum(struct ila_params *p)
return;
p->csum_diff = compute_csum_diff8(
- (__be32 *)&p->locator_match,
- (__be32 *)&p->locator);
+ (__be32 *)&p->locator,
+ (__be32 *)&p->locator_match);
}
static int __init ila_init(void)
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 1dfb64166..c8314c6b6 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -26,7 +26,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
- ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+ ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), true);
return dst->lwtstate->orig_output(net, sk, skb);
@@ -42,7 +42,7 @@ static int ila_input(struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
- ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+ ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false);
return dst->lwtstate->orig_input(skb);
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index a90e57229..e6eca5fdf 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -210,14 +210,14 @@ static void ila_free_cb(void *ptr, void *arg)
}
}
-static int ila_xlat_addr(struct sk_buff *skb);
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral);
static unsigned int
ila_nf_input(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- ila_xlat_addr(skb);
+ ila_xlat_addr(skb, false);
return NF_ACCEPT;
}
@@ -597,7 +597,7 @@ static struct pernet_operations ila_net_ops = {
.size = sizeof(struct ila_net),
};
-static int ila_xlat_addr(struct sk_buff *skb)
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral)
{
struct ila_map *ila;
struct ipv6hdr *ip6h = ipv6_hdr(skb);
@@ -616,7 +616,7 @@ static int ila_xlat_addr(struct sk_buff *skb)
ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan);
if (ila)
- ila_update_ipv6_locator(skb, &ila->xp.ip);
+ ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral);
rcu_read_unlock();
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 776d14511..edc3daab3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -519,8 +519,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));
- skb_set_inner_protocol(skb, protocol);
-
return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
NEXTHDR_GRE);
}
@@ -650,7 +648,6 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev)
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
- fl6.flowi6_proto = skb->protocol;
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 14dacc544..713676f14 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -39,7 +39,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
if (!send)
goto out;
- send(skb, type, code, info);
+ send(skb, type, code, info, NULL);
out:
rcu_read_unlock();
}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 94611e450..aacfb4bce 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -323,6 +323,7 @@ int ip6_input(struct sk_buff *skb)
dev_net(skb->dev), NULL, skb, skb->dev, NULL,
ip6_input_finish);
}
+EXPORT_SYMBOL_GPL(ip6_input);
int ip6_mc_input(struct sk_buff *skb)
{
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 635b8d340..1dfc402d9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -368,7 +368,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
if (skb->ignore_df)
return false;
- if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
return false;
return true;
@@ -910,6 +910,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
int err;
int flags = 0;
+ if (ipv6_addr_any(&fl6->saddr) && fl6->flowi6_oif &&
+ (!*dst || !(*dst)->error)) {
+ err = l3mdev_get_saddr6(net, sk, fl6);
+ if (err)
+ goto out_err;
+ }
+
/* The correct way to handle this would be to do
* ip6_route_get_saddr, and then ip6_route_output; however,
* the route-specific preferred source forces the
@@ -999,10 +1006,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
return 0;
out_err_release:
- if (err == -ENETUNREACH)
- IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
+out_err:
+ if (err == -ENETUNREACH)
+ IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
return err;
}
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index d90a11f14..5bd3afdcc 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -321,11 +321,9 @@ static int vti6_rcv(struct sk_buff *skb)
goto discard;
}
- XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
-
rcu_read_unlock();
- return xfrm6_rcv(skb);
+ return xfrm6_rcv_tnl(skb, t);
}
rcu_read_unlock();
return -EINVAL;
@@ -340,6 +338,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
+ struct xfrm_mode *inner_mode;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
u32 orig_mark = skb->mark;
int ret;
@@ -357,7 +356,19 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
}
x = xfrm_input_state(skb);
- family = x->inner_mode->afinfo->family;
+
+ inner_mode = x->inner_mode;
+
+ if (x->sel.family == AF_UNSPEC) {
+ inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+ if (inner_mode == NULL) {
+ XFRM_INC_STATS(dev_net(skb->dev),
+ LINUX_MIB_XFRMINSTATEMODEERROR);
+ return -EINVAL;
+ }
+ }
+
+ family = inner_mode->afinfo->family;
skb->mark = be32_to_cpu(t->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 487ef3bc7..7f4265b16 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -921,6 +921,7 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
cache->mfc_un.res.maxvif = vifi + 1;
}
}
+ cache->mfc_un.res.lastuse = jiffies;
}
static int mif6_add(struct net *net, struct mr6_table *mrt,
@@ -1592,14 +1593,15 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
if (likely(mrt->mroute6_sk == NULL)) {
mrt->mroute6_sk = sk;
net->ipv6.devconf_all->mc_forwarding++;
- inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
- NETCONFA_IFINDEX_ALL,
- net->ipv6.devconf_all);
- }
- else
+ } else {
err = -EADDRINUSE;
+ }
write_unlock_bh(&mrt_lock);
+ if (!err)
+ inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
rtnl_unlock();
return err;
@@ -1617,11 +1619,11 @@ int ip6mr_sk_done(struct sock *sk)
write_lock_bh(&mrt_lock);
mrt->mroute6_sk = NULL;
net->ipv6.devconf_all->mc_forwarding--;
+ write_unlock_bh(&mrt_lock);
inet6_netconf_notify_devconf(net,
NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
- write_unlock_bh(&mrt_lock);
mroute_clean_tables(mrt, false);
err = 0;
@@ -2091,6 +2093,7 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
vif = cache->mf6c_parent;
cache->mfc_un.res.pkt++;
cache->mfc_un.res.bytes += skb->len;
+ cache->mfc_un.res.lastuse = jiffies;
if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) {
struct mfc6_cache *cache_proxy;
@@ -2233,10 +2236,11 @@ int ip6_mr_input(struct sk_buff *skb)
static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
struct mfc6_cache *c, struct rtmsg *rtm)
{
- int ct;
- struct rtnexthop *nhp;
- struct nlattr *mp_attr;
struct rta_mfc_stats mfcs;
+ struct nlattr *mp_attr;
+ struct rtnexthop *nhp;
+ unsigned long lastuse;
+ int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mf6c_parent >= MAXMIFS)
@@ -2266,18 +2270,23 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
nla_nest_end(skb, mp_attr);
+ lastuse = READ_ONCE(c->mfc_un.res.lastuse);
+ lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
+
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
- if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) < 0)
+ if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
+ nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
+ RTA_PAD))
return -EMSGSIZE;
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
-int ip6mr_get_route(struct net *net,
- struct sk_buff *skb, struct rtmsg *rtm, int nowait)
+int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
+ int nowait, u32 portid)
{
int err;
struct mr6_table *mrt;
@@ -2322,6 +2331,7 @@ int ip6mr_get_route(struct net *net,
return -ENOMEM;
}
+ NETLINK_CB(skb2).portid = portid;
skb_reset_transport_header(skb2);
skb_put(skb2, sizeof(struct ipv6hdr));
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a9895e15e..5330262ab 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -98,7 +98,6 @@ int ip6_ra_control(struct sock *sk, int sel)
return 0;
}
-static
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
struct ipv6_txoptions *opt)
{
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c245895a3..fe65cdc28 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -73,15 +73,6 @@
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
-/* Set to 3 to get tracing... */
-#define ND_DEBUG 1
-
-#define ND_PRINTK(val, level, fmt, ...) \
-do { \
- if (val <= ND_DEBUG) \
- net_##level##_ratelimited(fmt, ##__VA_ARGS__); \
-} while (0)
-
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
@@ -150,11 +141,10 @@ struct neigh_table nd_tbl = {
};
EXPORT_SYMBOL_GPL(nd_tbl);
-static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+ int data_len, int pad)
{
- int pad = ndisc_addr_option_pad(skb->dev->type);
- int data_len = skb->dev->addr_len;
- int space = ndisc_opt_addr_space(skb->dev);
+ int space = __ndisc_opt_addr_space(data_len, pad);
u8 *opt = skb_put(skb, space);
opt[0] = type;
@@ -171,6 +161,23 @@ static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
if (space > 0)
memset(opt, 0, space);
}
+EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
+
+static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
+ void *data, u8 icmp6_type)
+{
+ __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
+ ndisc_addr_option_pad(skb->dev->type));
+ ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type);
+}
+
+static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb,
+ void *ha,
+ const u8 *ops_data)
+{
+ ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT);
+ ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data);
+}
static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
@@ -185,24 +192,28 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}
-static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
+static inline int ndisc_is_useropt(const struct net_device *dev,
+ struct nd_opt_hdr *opt)
{
return opt->nd_opt_type == ND_OPT_RDNSS ||
- opt->nd_opt_type == ND_OPT_DNSSL;
+ opt->nd_opt_type == ND_OPT_DNSSL ||
+ ndisc_ops_is_useropt(dev, opt->nd_opt_type);
}
-static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
+static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
+ struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
{
if (!cur || !end || cur >= end)
return NULL;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
- } while (cur < end && !ndisc_is_useropt(cur));
- return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
+ } while (cur < end && !ndisc_is_useropt(dev, cur));
+ return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL;
}
-struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+ u8 *opt, int opt_len,
struct ndisc_options *ndopts)
{
struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
@@ -217,6 +228,8 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
l = nd_opt->nd_opt_len << 3;
if (opt_len < l || l == 0)
return NULL;
+ if (ndisc_ops_parse_options(dev, nd_opt, ndopts))
+ goto next_opt;
switch (nd_opt->nd_opt_type) {
case ND_OPT_SOURCE_LL_ADDR:
case ND_OPT_TARGET_LL_ADDR:
@@ -243,7 +256,7 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
break;
#endif
default:
- if (ndisc_is_useropt(nd_opt)) {
+ if (ndisc_is_useropt(dev, nd_opt)) {
ndopts->nd_useropts_end = nd_opt;
if (!ndopts->nd_useropts)
ndopts->nd_useropts = nd_opt;
@@ -260,6 +273,7 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
nd_opt->nd_opt_len);
}
}
+next_opt:
opt_len -= l;
nd_opt = ((void *)nd_opt) + l;
}
@@ -509,7 +523,8 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
if (!dev->addr_len)
inc_opt = 0;
if (inc_opt)
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_opt_addr_space(dev,
+ NDISC_NEIGHBOUR_ADVERTISEMENT);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -528,8 +543,8 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
if (inc_opt)
ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
- dev->dev_addr);
-
+ dev->dev_addr,
+ NDISC_NEIGHBOUR_ADVERTISEMENT);
ndisc_send_skb(skb, daddr, src_addr);
}
@@ -574,7 +589,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
if (ipv6_addr_any(saddr))
inc_opt = false;
if (inc_opt)
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_opt_addr_space(dev,
+ NDISC_NEIGHBOUR_SOLICITATION);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -590,7 +606,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
if (inc_opt)
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
- dev->dev_addr);
+ dev->dev_addr,
+ NDISC_NEIGHBOUR_SOLICITATION);
ndisc_send_skb(skb, daddr, saddr);
}
@@ -626,7 +643,7 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
}
#endif
if (send_sllao)
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -641,7 +658,8 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
if (send_sllao)
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
- dev->dev_addr);
+ dev->dev_addr,
+ NDISC_ROUTER_SOLICITATION);
ndisc_send_skb(skb, daddr, saddr);
}
@@ -702,6 +720,15 @@ static int pndisc_is_router(const void *pkey,
return ret;
}
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+ const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+ struct ndisc_options *ndopts)
+{
+ neigh_update(neigh, lladdr, new, flags);
+ /* report ndisc ops about neighbour update */
+ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
+}
+
static void ndisc_recv_ns(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
@@ -738,7 +765,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
return;
}
- if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+ if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, warn, "NS: invalid ND options\n");
return;
}
@@ -856,9 +883,10 @@ have_ifp:
neigh = __neigh_lookup(&nd_tbl, saddr, dev,
!inc || lladdr || !dev->addr_len);
if (neigh)
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
- NEIGH_UPDATE_F_OVERRIDE);
+ NEIGH_UPDATE_F_OVERRIDE,
+ NDISC_NEIGHBOUR_SOLICITATION, &ndopts);
if (neigh || !dev->header_ops) {
ndisc_send_na(dev, saddr, &msg->target, !!is_router,
true, (ifp != NULL && inc), inc);
@@ -911,7 +939,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
idev->cnf.drop_unsolicited_na)
return;
- if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+ if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, warn, "NS: invalid ND option\n");
return;
}
@@ -967,12 +995,13 @@ static void ndisc_recv_na(struct sk_buff *skb)
goto out;
}
- neigh_update(neigh, lladdr,
+ ndisc_update(dev, neigh, lladdr,
msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
(msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
- (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0));
+ (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0),
+ NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts);
if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
/*
@@ -1017,7 +1046,7 @@ static void ndisc_recv_rs(struct sk_buff *skb)
goto out;
/* Parse ND options */
- if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) {
+ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
goto out;
}
@@ -1031,10 +1060,11 @@ static void ndisc_recv_rs(struct sk_buff *skb)
neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
if (neigh) {
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
- NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
+ NEIGH_UPDATE_F_OVERRIDE_ISROUTER,
+ NDISC_ROUTER_SOLICITATION, &ndopts);
neigh_release(neigh);
}
out:
@@ -1135,7 +1165,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
return;
}
- if (!ndisc_parse_options(opt, optlen, &ndopts)) {
+ if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) {
ND_PRINTK(2, warn, "RA: invalid ND options\n");
return;
}
@@ -1329,11 +1359,12 @@ skip_linkparms:
goto out;
}
}
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
- NEIGH_UPDATE_F_ISROUTER);
+ NEIGH_UPDATE_F_ISROUTER,
+ NDISC_ROUTER_ADVERTISEMENT, &ndopts);
}
if (!ipv6_accept_ra(in6_dev)) {
@@ -1421,7 +1452,8 @@ skip_routeinfo:
struct nd_opt_hdr *p;
for (p = ndopts.nd_useropts;
p;
- p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) {
+ p = ndisc_next_useropt(skb->dev, p,
+ ndopts.nd_useropts_end)) {
ndisc_ra_useropt(skb, p);
}
}
@@ -1459,7 +1491,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
return;
}
- if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts))
+ if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts))
return;
if (!ndopts.nd_opts_rh) {
@@ -1504,7 +1536,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
struct dst_entry *dst;
struct flowi6 fl6;
int rd_len;
- u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
+ u8 ha_buf[MAX_ADDR_LEN], *ha = NULL,
+ ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
int oif = l3mdev_fib_oif(dev);
bool ret;
@@ -1563,7 +1596,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
memcpy(ha_buf, neigh->ha, dev->addr_len);
read_unlock_bh(&neigh->lock);
ha = ha_buf;
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_redirect_opt_addr_space(dev, neigh,
+ ops_data_buf,
+ &ops_data);
} else
read_unlock_bh(&neigh->lock);
@@ -1594,7 +1629,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
*/
if (ha)
- ndisc_fill_addr_option(buff, ND_OPT_TARGET_LL_ADDR, ha);
+ ndisc_fill_redirect_addr_option(buff, ha, ops_data);
/*
* build redirect option and copy skb over to the new packet.
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 63e06c3dd..552fac2f3 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -73,22 +73,22 @@ ip6_packet_match(const struct sk_buff *skb,
unsigned long ret;
const struct ipv6hdr *ipv6 = ipv6_hdr(skb);
-#define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg)))
-
- if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk,
- &ip6info->src), IP6T_INV_SRCIP) ||
- FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk,
- &ip6info->dst), IP6T_INV_DSTIP))
+ if (NF_INVF(ip6info, IP6T_INV_SRCIP,
+ ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk,
+ &ip6info->src)) ||
+ NF_INVF(ip6info, IP6T_INV_DSTIP,
+ ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk,
+ &ip6info->dst)))
return false;
ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask);
- if (FWINV(ret != 0, IP6T_INV_VIA_IN))
+ if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0))
return false;
ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask);
- if (FWINV(ret != 0, IP6T_INV_VIA_OUT))
+ if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0))
return false;
/* ... might want to do something with class and flowlabel here ... */
@@ -402,23 +402,12 @@ ip6t_do_table(struct sk_buff *skb,
else return verdict;
}
-static bool find_jump_target(const struct xt_table_info *t,
- const struct ip6t_entry *target)
-{
- struct ip6t_entry *iter;
-
- xt_entry_foreach(iter, t->entries, t->size) {
- if (iter == target)
- return true;
- }
- return false;
-}
-
/* Figures out from what hook each rule can be called: returns 0 if
there are loops. Puts hook bitmask in comefrom. */
static int
mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;
@@ -487,10 +476,11 @@ mark_source_chains(const struct xt_table_info *newinfo,
XT_STANDARD_TARGET) == 0 &&
newpos >= 0) {
/* This a jump; chase it. */
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
e = (struct ip6t_entry *)
(entry0 + newpos);
- if (!find_jump_target(newinfo, e))
- return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
@@ -724,6 +714,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ip6t_replace *repl)
{
struct ip6t_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;
@@ -736,6 +727,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
newinfo->underflow[i] = 0xFFFFFFFF;
}
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;
/* Walk through entries, checking offsets. */
xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -745,15 +739,18 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- return ret;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(ip6t_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}
+ ret = -EINVAL;
if (i != repl->num_entries)
- return -EINVAL;
+ goto out_free;
/* Check hooks all assigned */
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
@@ -761,13 +758,16 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
if (!(repl->valid_hooks & (1 << i)))
continue;
if (newinfo->hook_entry[i] == 0xFFFFFFFF)
- return -EINVAL;
+ goto out_free;
if (newinfo->underflow[i] == 0xFFFFFFFF)
- return -EINVAL;
+ goto out_free;
}
- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
+ }
+ kvfree(offsets);
/* Finally, each sanity check must pass */
i = 0;
@@ -788,6 +788,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index cb2b28883..2b1a9dcdb 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -83,10 +83,6 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb,
{
if (state->hook == NF_INET_LOCAL_OUT)
return ip6t_mangle_out(skb, state);
- if (state->hook == NF_INET_POST_ROUTING)
- return ip6t_do_table(skb, state,
- state->net->ipv6.ip6table_mangle);
- /* INPUT/FORWARD */
return ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle);
}
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 71d995ff3..2535223ba 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv,
struct in6_addr saddr, daddr;
u_int8_t hop_limit;
u32 mark, flowlabel;
+ int err;
/* malformed packet, drop it */
if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0)
@@ -46,13 +47,16 @@ static unsigned int nf_route_table_hook(void *priv,
flowlabel = *((u32 *)ipv6_hdr(skb));
ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_QUEUE &&
+ if (ret != NF_DROP && ret != NF_STOLEN &&
(memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
- flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
- return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP;
+ flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
+ err = ip6_route_me_harder(state->net, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
return ret;
}
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 533cd5719..92bda9908 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -47,6 +47,7 @@ static const struct nft_expr_ops nft_reject_ipv6_ops = {
.eval = nft_reject_ipv6_eval,
.init = nft_reject_init,
.dump = nft_reject_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 408660477..0e983b694 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -55,7 +55,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
struct icmp6hdr user_icmph;
int addr_type;
struct in6_addr *daddr;
- int iif = 0;
+ int oif = 0;
struct flowi6 fl6;
int err;
struct dst_entry *dst;
@@ -78,25 +78,30 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (u->sin6_family != AF_INET6) {
return -EAFNOSUPPORT;
}
- if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != u->sin6_scope_id) {
- return -EINVAL;
- }
daddr = &(u->sin6_addr);
- iif = u->sin6_scope_id;
+ if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr)))
+ oif = u->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &sk->sk_v6_daddr;
}
- if (!iif)
- iif = sk->sk_bound_dev_if;
+ if (!oif)
+ oif = sk->sk_bound_dev_if;
+
+ if (!oif)
+ oif = np->sticky_pktinfo.ipi6_ifindex;
+
+ if (!oif && ipv6_addr_is_multicast(daddr))
+ oif = np->mcast_oif;
+ else if (!oif)
+ oif = np->ucast_oif;
addr_type = ipv6_addr_type(daddr);
- if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
- return -EINVAL;
- if (addr_type & IPV6_ADDR_MAPPED)
+ if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) ||
+ (addr_type & IPV6_ADDR_MAPPED) ||
+ (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if))
return -EINVAL;
/* TODO: use ip6_datagram_send_ctl to get options from cmsg */
@@ -106,15 +111,14 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
+ fl6.flowi6_oif = oif;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
- fl6.flowi6_oif = np->mcast_oif;
- else if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->ucast_oif;
+ ipc6.tclass = np->tclass;
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr);
if (IS_ERR(dst))
@@ -142,7 +146,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
pfh.family = AF_INET6;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- ipc6.tclass = np->tclass;
ipc6.dontfrag = np->dontfrag;
ipc6.opt = NULL;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896350df6..590dd1f77 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -878,6 +878,11 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (inet->hdrincl)
fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
+ if (ipc6.tclass < 0)
+ ipc6.tclass = np->tclass;
+
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
@@ -886,9 +891,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
if (ipc6.dontfrag < 0)
ipc6.dontfrag = np->dontfrag;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 520b7884d..269218aac 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1042,8 +1042,8 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
return pcpu_rt;
}
-static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
- struct flowi6 *fl6, int flags)
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int flags)
{
struct fib6_node *fn, *saved_fn;
struct rt6_info *rt;
@@ -1139,6 +1139,7 @@ redo_rt6_select:
}
}
+EXPORT_SYMBOL_GPL(ip6_pol_route);
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
struct flowi6 *fl6, int flags)
@@ -1985,9 +1986,18 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
if (!(gwa_type & IPV6_ADDR_UNICAST))
goto out;
- if (cfg->fc_table)
+ if (cfg->fc_table) {
grt = ip6_nh_lookup_table(net, cfg, gw_addr);
+ if (grt) {
+ if (grt->rt6i_flags & RTF_GATEWAY ||
+ (dev && dev != grt->dst.dev)) {
+ ip6_rt_put(grt);
+ grt = NULL;
+ }
+ }
+ }
+
if (!grt)
grt = rt6_lookup(net, gw_addr, NULL,
cfg->fc_ifindex, 1);
@@ -2200,7 +2210,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
* first-hop router for the specified ICMP Destination Address.
*/
- if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) {
+ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) {
net_dbg_ratelimited("rt6_redirect: invalid ND options\n");
return;
}
@@ -2235,12 +2245,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
* We have finally decided to accept it.
*/
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
(on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
- NEIGH_UPDATE_F_ISROUTER))
- );
+ NEIGH_UPDATE_F_ISROUTER)),
+ NDISC_REDIRECT, &ndopts);
nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
if (!nrt)
@@ -2585,23 +2595,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
return rt;
}
-int ip6_route_get_saddr(struct net *net,
- struct rt6_info *rt,
- const struct in6_addr *daddr,
- unsigned int prefs,
- struct in6_addr *saddr)
-{
- struct inet6_dev *idev =
- rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
- int err = 0;
- if (rt && rt->rt6i_prefsrc.plen)
- *saddr = rt->rt6i_prefsrc.addr;
- else
- err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
- daddr, prefs, saddr);
- return err;
-}
-
/* remove deleted ip from prefsrc entries */
struct arg_dev_net_ip {
struct net_device *dev;
@@ -3209,7 +3202,9 @@ static int rt6_fill_node(struct net *net,
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
- int err = ip6mr_get_route(net, skb, rtm, nowait);
+ int err = ip6mr_get_route(net, skb, rtm, nowait,
+ portid);
+
if (err <= 0) {
if (!nowait) {
if (err == 0)
@@ -3306,6 +3301,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
err = -EINVAL;
memset(&fl6, 0, sizeof(fl6));
+ rtm = nlmsg_data(nlh);
+ fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
if (tb[RTA_SRC]) {
if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0619ac708..182b6a9be 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -479,47 +479,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
dev_put(dev);
}
-/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
- * if sufficient data bytes are available
- */
-static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb)
-{
- int ihl = ((const struct iphdr *)skb->data)->ihl*4;
- struct rt6_info *rt;
- struct sk_buff *skb2;
-
- if (!pskb_may_pull(skb, ihl + sizeof(struct ipv6hdr) + 8))
- return 1;
-
- skb2 = skb_clone(skb, GFP_ATOMIC);
-
- if (!skb2)
- return 1;
-
- skb_dst_drop(skb2);
- skb_pull(skb2, ihl);
- skb_reset_network_header(skb2);
-
- rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
-
- if (rt && rt->dst.dev)
- skb2->dev = rt->dst.dev;
-
- icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-
- if (rt)
- ip6_rt_put(rt);
-
- kfree_skb(skb2);
-
- return 0;
-}
-
static int ipip6_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
+ unsigned int data_len = 0;
struct ip_tunnel *t;
int err;
@@ -544,6 +509,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return 0;
+ data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
break;
case ICMP_REDIRECT:
break;
@@ -571,11 +537,11 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
goto out;
}
- if (t->parms.iph.daddr == 0)
+ err = 0;
+ if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
goto out;
- err = 0;
- if (!ipip6_err_gen_icmpv6_unreach(skb))
+ if (t->parms.iph.daddr == 0)
goto out;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
@@ -722,12 +688,19 @@ out:
return 0;
}
-static const struct tnl_ptk_info tpi = {
+static const struct tnl_ptk_info ipip_tpi = {
/* no tunnel info required for ipip. */
.proto = htons(ETH_P_IP),
};
-static int ipip_rcv(struct sk_buff *skb)
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct tnl_ptk_info mplsip_tpi = {
+ /* no tunnel info required for mplsip. */
+ .proto = htons(ETH_P_MPLS_UC),
+};
+#endif
+
+static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
{
const struct iphdr *iph;
struct ip_tunnel *tunnel;
@@ -736,15 +709,23 @@ static int ipip_rcv(struct sk_buff *skb)
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel) {
- if (tunnel->parms.iph.protocol != IPPROTO_IPIP &&
+ const struct tnl_ptk_info *tpi;
+
+ if (tunnel->parms.iph.protocol != ipproto &&
tunnel->parms.iph.protocol != 0)
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
- if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+#if IS_ENABLED(CONFIG_MPLS)
+ if (ipproto == IPPROTO_MPLS)
+ tpi = &mplsip_tpi;
+ else
+#endif
+ tpi = &ipip_tpi;
+ if (iptunnel_pull_header(skb, 0, tpi->proto, false))
goto drop;
- return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error);
+ return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
}
return 1;
@@ -754,6 +735,18 @@ drop:
return 0;
}
+static int ipip_rcv(struct sk_buff *skb)
+{
+ return sit_tunnel_rcv(skb, IPPROTO_IPIP);
+}
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int mplsip_rcv(struct sk_buff *skb)
+{
+ return sit_tunnel_rcv(skb, IPPROTO_MPLS);
+}
+#endif
+
/*
* If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
* stores the embedded IPv4 address in v4dst and returns true.
@@ -825,9 +818,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
u8 protocol = IPPROTO_IPV6;
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
- if (skb->protocol != htons(ETH_P_IPV6))
- goto tx_error;
-
if (tos == 1)
tos = ipv6_get_dsfield(iph6);
@@ -995,7 +985,8 @@ tx_error:
return NETDEV_TX_OK;
}
-static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
+ struct net_device *dev, u8 ipproto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
@@ -1003,9 +994,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
goto tx_error;
- skb_set_inner_ipproto(skb, IPPROTO_IPIP);
+ skb_set_inner_ipproto(skb, ipproto);
- ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
+ ip_tunnel_xmit(skb, dev, tiph, ipproto);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
@@ -1018,11 +1009,16 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
{
switch (skb->protocol) {
case htons(ETH_P_IP):
- ipip_tunnel_xmit(skb, dev);
+ sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);
break;
case htons(ETH_P_IPV6):
ipip6_tunnel_xmit(skb, dev);
break;
+#if IS_ENABLED(CONFIG_MPLS)
+ case htons(ETH_P_MPLS_UC):
+ sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS);
+ break;
+#endif
default:
goto tx_err;
}
@@ -1130,6 +1126,16 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
}
#endif
+bool ipip6_valid_ip_proto(u8 ipproto)
+{
+ return ipproto == IPPROTO_IPV6 ||
+ ipproto == IPPROTO_IPIP ||
+#if IS_ENABLED(CONFIG_MPLS)
+ ipproto == IPPROTO_MPLS ||
+#endif
+ ipproto == 0;
+}
+
static int
ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
@@ -1189,9 +1195,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
goto done;
err = -EINVAL;
- if (p.iph.protocol != IPPROTO_IPV6 &&
- p.iph.protocol != IPPROTO_IPIP &&
- p.iph.protocol != 0)
+ if (!ipip6_valid_ip_proto(p.iph.protocol))
goto done;
if (p.iph.version != 4 ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
@@ -1416,9 +1420,7 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
- if (proto != IPPROTO_IPV6 &&
- proto != IPPROTO_IPIP &&
- proto != 0)
+ if (!ipip6_valid_ip_proto(proto))
return -EINVAL;
return 0;
@@ -1760,6 +1762,14 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
.priority = 2,
};
+#if IS_ENABLED(CONFIG_MPLS)
+static struct xfrm_tunnel mplsip_handler __read_mostly = {
+ .handler = mplsip_rcv,
+ .err_handler = ipip6_err,
+ .priority = 2,
+};
+#endif
+
static void __net_exit sit_destroy_tunnels(struct net *net,
struct list_head *head)
{
@@ -1855,6 +1865,9 @@ static void __exit sit_cleanup(void)
rtnl_link_unregister(&sit_link_ops);
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+#if IS_ENABLED(CONFIG_MPLS)
+ xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+#endif
unregister_pernet_device(&sit_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
@@ -1864,7 +1877,7 @@ static int __init sit_init(void)
{
int err;
- pr_info("IPv6 over IPv4 tunneling driver\n");
+ pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n");
err = register_pernet_device(&sit_net_ops);
if (err < 0)
@@ -1879,6 +1892,13 @@ static int __init sit_init(void)
pr_info("%s: can't register ip4ip4\n", __func__);
goto xfrm_tunnel4_failed;
}
+#if IS_ENABLED(CONFIG_MPLS)
+ err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS);
+ if (err < 0) {
+ pr_info("%s: can't register mplsip\n", __func__);
+ goto xfrm_tunnel_mpls_failed;
+ }
+#endif
err = rtnl_link_register(&sit_link_ops);
if (err < 0)
goto rtnl_link_failed;
@@ -1887,6 +1907,10 @@ out:
return err;
rtnl_link_failed:
+#if IS_ENABLED(CONFIG_MPLS)
+ xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+xfrm_tunnel_mpls_failed:
+#endif
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_tunnel4_failed:
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 45243bbe5..69c50e737 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -15,6 +15,9 @@
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>
+#ifdef CONFIG_NETLABEL
+#include <net/calipso.h>
+#endif
static int one = 1;
static int auto_flowlabels_min;
@@ -106,6 +109,22 @@ static struct ctl_table ipv6_rotable[] = {
.proc_handler = proc_dointvec_minmax,
.extra1 = &one
},
+#ifdef CONFIG_NETLABEL
+ {
+ .procname = "calipso_cache_enable",
+ .data = &calipso_cache_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "calipso_cache_bucket_size",
+ .data = &calipso_cache_bucketsize,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif /* CONFIG_NETLABEL */
{ }
};
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a2aaca9be..27a968b88 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -459,6 +459,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt;
struct flowi6 *fl6 = &fl->u.ip6;
struct sk_buff *skb;
int err = -ENOMEM;
@@ -479,8 +480,10 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
rcu_read_lock();
- err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
- np->tclass);
+ opt = ireq->ipv6_opt;
+ if (!opt)
+ opt = rcu_dereference(np->opt);
+ err = ip6_xmit(sk, skb, fl6, opt, np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -492,6 +495,7 @@ done:
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
+ kfree(inet_rsk(req)->ipv6_opt);
kfree_skb(inet_rsk(req)->pktopts);
}
@@ -542,26 +546,33 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval,
AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
-static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr, int nbytes)
+static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr,
+ const struct tcphdr *th, int nbytes)
{
struct tcp6_pseudohdr *bp;
struct scatterlist sg;
+ struct tcphdr *_th;
- bp = &hp->md5_blk.ip6;
+ bp = hp->scratch;
/* 1. TCP pseudo-header (RFC2460) */
bp->saddr = *saddr;
bp->daddr = *daddr;
bp->protocol = cpu_to_be32(IPPROTO_TCP);
bp->len = cpu_to_be32(nbytes);
- sg_init_one(&sg, bp, sizeof(*bp));
- ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+ _th = (struct tcphdr *)(bp + 1);
+ memcpy(_th, th, sizeof(*th));
+ _th->check = 0;
+
+ sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
+ ahash_request_set_crypt(hp->md5_req, &sg, NULL,
+ sizeof(*bp) + sizeof(*th));
return crypto_ahash_update(hp->md5_req);
}
-static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
const struct in6_addr *daddr, struct in6_addr *saddr,
const struct tcphdr *th)
{
@@ -575,9 +586,7 @@ static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
if (crypto_ahash_init(req))
goto clear_hash;
- if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
- goto clear_hash;
- if (tcp_md5_hash_header(hp, th))
+ if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(hp, key))
goto clear_hash;
@@ -622,9 +631,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
if (crypto_ahash_init(req))
goto clear_hash;
- if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
- goto clear_hash;
- if (tcp_md5_hash_header(hp, th))
+ if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
goto clear_hash;
if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
goto clear_hash;
@@ -1131,7 +1138,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
but we make one more one thing there: reattach optmem
to newsk.
*/
- opt = rcu_dereference(np->opt);
+ opt = ireq->ipv6_opt;
+ if (!opt)
+ opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 42a2edf7c..19ac3a1c3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1207,6 +1207,11 @@ do_udp_sendmsg:
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+ if (ipc6.tclass < 0)
+ ipc6.tclass = np->tclass;
+
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
@@ -1217,9 +1222,6 @@ do_udp_sendmsg:
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
@@ -1458,7 +1460,6 @@ struct proto udpv6_prot = {
.sysctl_wmem = &sysctl_udp_wmem_min,
.sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 9cf097e20..fd6ef4148 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -50,7 +50,6 @@ struct proto udplitev6_prot = {
.unhash = udp_lib_unhash,
.get_port = udp_v6_get_port,
.obj_size = sizeof(struct udp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 0eaab1fa6..b5789562a 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -21,8 +21,10 @@ int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb)
return xfrm6_extract_header(skb);
}
-int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
+int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
+ struct ip6_tnl *t)
{
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
return xfrm_input(skb, nexthdr, spi, 0);
@@ -48,13 +50,18 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
return -1;
}
-int xfrm6_rcv(struct sk_buff *skb)
+int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t)
{
return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
- 0);
+ 0, t);
}
-EXPORT_SYMBOL(xfrm6_rcv);
+EXPORT_SYMBOL(xfrm6_rcv_tnl);
+int xfrm6_rcv(struct sk_buff *skb)
+{
+ return xfrm6_rcv_tnl(skb, NULL);
+}
+EXPORT_SYMBOL(xfrm6_rcv);
int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
xfrm_address_t *saddr, u8 proto)
{
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c074771a1..70a86adad 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -36,7 +36,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
int err;
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_oif = oif;
+ fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
@@ -366,12 +366,12 @@ static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
kfree(table);
}
#else /* CONFIG_SYSCTL */
-static int inline xfrm6_net_sysctl_init(struct net *net)
+static inline int xfrm6_net_sysctl_init(struct net *net)
{
return 0;
}
-static void inline xfrm6_net_sysctl_exit(struct net *net)
+static inline void xfrm6_net_sysctl_exit(struct net *net)
{
}
#endif
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 5743044cd..e1c0bbe79 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -236,7 +236,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb)
__be32 spi;
spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr);
- return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi);
+ return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL);
}
static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt,