linux/net/ipv6/ip6_vti.c
Eric Dumazet 0bef512012 net: add netdev_lockdep_set_classes() to virtual drivers
Based on a syzbot report, it appears many virtual
drivers do not yet use netdev_lockdep_set_classes(),
triggerring lockdep false positives.

WARNING: possible recursive locking detected
6.8.0-rc4-next-20240212-syzkaller #0 Not tainted

syz-executor.0/19016 is trying to acquire lock:
 ffff8880162cb298 (_xmit_ETHER#2){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
 ffff8880162cb298 (_xmit_ETHER#2){+.-.}-{2:2}, at: __netif_tx_lock include/linux/netdevice.h:4452 [inline]
 ffff8880162cb298 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340

but task is already holding lock:
 ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
 ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: __netif_tx_lock include/linux/netdevice.h:4452 [inline]
 ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
  lock(_xmit_ETHER#2);
  lock(_xmit_ETHER#2);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

9 locks held by syz-executor.0/19016:
  #0: ffffffff8f385208 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_lock net/core/rtnetlink.c:79 [inline]
  #0: ffffffff8f385208 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x82c/0x1040 net/core/rtnetlink.c:6603
  #1: ffffc90000a08c00 ((&in_dev->mr_ifc_timer)){+.-.}-{0:0}, at: call_timer_fn+0xc0/0x600 kernel/time/timer.c:1697
  #2: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
  #2: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
  #2: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1360 net/ipv4/ip_output.c:228
  #3: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: local_bh_disable include/linux/bottom_half.h:20 [inline]
  #3: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: rcu_read_lock_bh include/linux/rcupdate.h:802 [inline]
  #3: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x2c4/0x3b10 net/core/dev.c:4284
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: spin_trylock include/linux/spinlock.h:361 [inline]
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: qdisc_run_begin include/net/sch_generic.h:195 [inline]
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_xmit_skb net/core/dev.c:3771 [inline]
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_queue_xmit+0x1262/0x3b10 net/core/dev.c:4325
  #5: ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
  #5: ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: __netif_tx_lock include/linux/netdevice.h:4452 [inline]
  #5: ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340
  #6: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
  #6: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
  #6: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1360 net/ipv4/ip_output.c:228
  #7: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: local_bh_disable include/linux/bottom_half.h:20 [inline]
  #7: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: rcu_read_lock_bh include/linux/rcupdate.h:802 [inline]
  #7: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x2c4/0x3b10 net/core/dev.c:4284
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: spin_trylock include/linux/spinlock.h:361 [inline]
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: qdisc_run_begin include/net/sch_generic.h:195 [inline]
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_xmit_skb net/core/dev.c:3771 [inline]
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_queue_xmit+0x1262/0x3b10 net/core/dev.c:4325

stack backtrace:
CPU: 1 PID: 19016 Comm: syz-executor.0 Not tainted 6.8.0-rc4-next-20240212-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Call Trace:
 <IRQ>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
  check_deadlock kernel/locking/lockdep.c:3062 [inline]
  validate_chain+0x15c1/0x58e0 kernel/locking/lockdep.c:3856
  __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137
  lock_acquire+0x1e4/0x530 kernel/locking/lockdep.c:5754
  __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline]
  _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154
  spin_lock include/linux/spinlock.h:351 [inline]
  __netif_tx_lock include/linux/netdevice.h:4452 [inline]
  sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340
  __dev_xmit_skb net/core/dev.c:3784 [inline]
  __dev_queue_xmit+0x1912/0x3b10 net/core/dev.c:4325
  neigh_output include/net/neighbour.h:542 [inline]
  ip_finish_output2+0xe66/0x1360 net/ipv4/ip_output.c:235
  iptunnel_xmit+0x540/0x9b0 net/ipv4/ip_tunnel_core.c:82
  ip_tunnel_xmit+0x20ee/0x2960 net/ipv4/ip_tunnel.c:831
  erspan_xmit+0x9de/0x1460 net/ipv4/ip_gre.c:720
  __netdev_start_xmit include/linux/netdevice.h:4989 [inline]
  netdev_start_xmit include/linux/netdevice.h:5003 [inline]
  xmit_one net/core/dev.c:3555 [inline]
  dev_hard_start_xmit+0x242/0x770 net/core/dev.c:3571
  sch_direct_xmit+0x2b6/0x5f0 net/sched/sch_generic.c:342
  __dev_xmit_skb net/core/dev.c:3784 [inline]
  __dev_queue_xmit+0x1912/0x3b10 net/core/dev.c:4325
  neigh_output include/net/neighbour.h:542 [inline]
  ip_finish_output2+0xe66/0x1360 net/ipv4/ip_output.c:235
  igmpv3_send_cr net/ipv4/igmp.c:723 [inline]
  igmp_ifc_timer_expire+0xb71/0xd90 net/ipv4/igmp.c:813
  call_timer_fn+0x17e/0x600 kernel/time/timer.c:1700
  expire_timers kernel/time/timer.c:1751 [inline]
  __run_timers+0x621/0x830 kernel/time/timer.c:2038
  run_timer_softirq+0x67/0xf0 kernel/time/timer.c:2051
  __do_softirq+0x2bc/0x943 kernel/softirq.c:554
  invoke_softirq kernel/softirq.c:428 [inline]
  __irq_exit_rcu+0xf2/0x1c0 kernel/softirq.c:633
  irq_exit_rcu+0x9/0x30 kernel/softirq.c:645
  instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1076 [inline]
  sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1076
 </IRQ>
 <TASK>
  asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702
 RIP: 0010:resched_offsets_ok kernel/sched/core.c:10127 [inline]
 RIP: 0010:__might_resched+0x16f/0x780 kernel/sched/core.c:10142
Code: 00 4c 89 e8 48 c1 e8 03 48 ba 00 00 00 00 00 fc ff df 48 89 44 24 38 0f b6 04 10 84 c0 0f 85 87 04 00 00 41 8b 45 00 c1 e0 08 <01> d8 44 39 e0 0f 85 d6 00 00 00 44 89 64 24 1c 48 8d bc 24 a0 00
RSP: 0018:ffffc9000ee069e0 EFLAGS: 00000246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8880296a9e00
RDX: dffffc0000000000 RSI: ffff8880296a9e00 RDI: ffffffff8bfe8fa0
RBP: ffffc9000ee06b00 R08: ffffffff82326877 R09: 1ffff11002b5ad1b
R10: dffffc0000000000 R11: ffffed1002b5ad1c R12: 0000000000000000
R13: ffff8880296aa23c R14: 000000000000062a R15: 1ffff92001dc0d44
  down_write+0x19/0x50 kernel/locking/rwsem.c:1578
  kernfs_activate fs/kernfs/dir.c:1403 [inline]
  kernfs_add_one+0x4af/0x8b0 fs/kernfs/dir.c:819
  __kernfs_create_file+0x22e/0x2e0 fs/kernfs/file.c:1056
  sysfs_add_file_mode_ns+0x24a/0x310 fs/sysfs/file.c:307
  create_files fs/sysfs/group.c:64 [inline]
  internal_create_group+0x4f4/0xf20 fs/sysfs/group.c:152
  internal_create_groups fs/sysfs/group.c:192 [inline]
  sysfs_create_groups+0x56/0x120 fs/sysfs/group.c:218
  create_dir lib/kobject.c:78 [inline]
  kobject_add_internal+0x472/0x8d0 lib/kobject.c:240
  kobject_add_varg lib/kobject.c:374 [inline]
  kobject_init_and_add+0x124/0x190 lib/kobject.c:457
  netdev_queue_add_kobject net/core/net-sysfs.c:1706 [inline]
  netdev_queue_update_kobjects+0x1f3/0x480 net/core/net-sysfs.c:1758
  register_queue_kobjects net/core/net-sysfs.c:1819 [inline]
  netdev_register_kobject+0x265/0x310 net/core/net-sysfs.c:2059
  register_netdevice+0x1191/0x19c0 net/core/dev.c:10298
  bond_newlink+0x3b/0x90 drivers/net/bonding/bond_netlink.c:576
  rtnl_newlink_create net/core/rtnetlink.c:3506 [inline]
  __rtnl_newlink net/core/rtnetlink.c:3726 [inline]
  rtnl_newlink+0x158f/0x20a0 net/core/rtnetlink.c:3739
  rtnetlink_rcv_msg+0x885/0x1040 net/core/rtnetlink.c:6606
  netlink_rcv_skb+0x1e3/0x430 net/netlink/af_netlink.c:2543
  netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
  netlink_unicast+0x7ea/0x980 net/netlink/af_netlink.c:1367
  netlink_sendmsg+0xa3c/0xd70 net/netlink/af_netlink.c:1908
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x221/0x270 net/socket.c:745
  __sys_sendto+0x3a4/0x4f0 net/socket.c:2191
  __do_sys_sendto net/socket.c:2203 [inline]
  __se_sys_sendto net/socket.c:2199 [inline]
  __x64_sys_sendto+0xde/0x100 net/socket.c:2199
 do_syscall_64+0xfb/0x240
 entry_SYSCALL_64_after_hwframe+0x6d/0x75
RIP: 0033:0x7fc3fa87fa9c

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240212140700.2795436-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-13 18:45:06 -08:00

1333 lines
32 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPv6 virtual tunneling interface
*
* Copyright (C) 2013 secunet Security Networks AG
*
* Author:
* Steffen Klassert <steffen.klassert@secunet.com>
*
* Based on:
* net/ipv6/ip6_tunnel.c
*/
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/icmp.h>
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.h>
#include <linux/slab.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
#include <linux/atomic.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <linux/etherdevice.h>
#define IP6_VTI_HASH_SIZE_SHIFT 5
#define IP6_VTI_HASH_SIZE (1 << IP6_VTI_HASH_SIZE_SHIFT)
static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2)
{
u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2);
return hash_32(hash, IP6_VTI_HASH_SIZE_SHIFT);
}
static int vti6_dev_init(struct net_device *dev);
static void vti6_dev_setup(struct net_device *dev);
static struct rtnl_link_ops vti6_link_ops __read_mostly;
static unsigned int vti6_net_id __read_mostly;
struct vti6_net {
/* the vti6 tunnel fallback device */
struct net_device *fb_tnl_dev;
/* lists for storing tunnels in use */
struct ip6_tnl __rcu *tnls_r_l[IP6_VTI_HASH_SIZE];
struct ip6_tnl __rcu *tnls_wc[1];
struct ip6_tnl __rcu **tnls[2];
};
#define for_each_vti6_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
/**
* vti6_tnl_lookup - fetch tunnel matching the end-point addresses
* @net: network namespace
* @remote: the address of the tunnel exit-point
* @local: the address of the tunnel entry-point
*
* Return:
* tunnel matching given end-points if found,
* else fallback tunnel if its device is up,
* else %NULL
**/
static struct ip6_tnl *
vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
const struct in6_addr *local)
{
unsigned int hash = HASH(remote, local);
struct ip6_tnl *t;
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
struct in6_addr any;
for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
memset(&any, 0, sizeof(any));
hash = HASH(&any, local);
for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
(t->dev->flags & IFF_UP))
return t;
}
hash = HASH(remote, &any);
for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(remote, &t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
t = rcu_dereference(ip6n->tnls_wc[0]);
if (t && (t->dev->flags & IFF_UP))
return t;
return NULL;
}
/**
* vti6_tnl_bucket - get head of list matching given tunnel parameters
* @ip6n: the private data for ip6_vti in the netns
* @p: parameters containing tunnel end-points
*
* Description:
* vti6_tnl_bucket() returns the head of the list matching the
* &struct in6_addr entries laddr and raddr in @p.
*
* Return: head of IPv6 tunnel list
**/
static struct ip6_tnl __rcu **
vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p)
{
const struct in6_addr *remote = &p->raddr;
const struct in6_addr *local = &p->laddr;
unsigned int h = 0;
int prio = 0;
if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) {
prio = 1;
h = HASH(remote, local);
}
return &ip6n->tnls[prio][h];
}
static void
vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms);
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
static void
vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp;
struct ip6_tnl *iter;
for (tp = vti6_tnl_bucket(ip6n, &t->parms);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
static void vti6_dev_free(struct net_device *dev)
{
free_percpu(dev->tstats);
}
static int vti6_tnl_create2(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
int err;
dev->rtnl_link_ops = &vti6_link_ops;
err = register_netdevice(dev);
if (err < 0)
goto out;
strcpy(t->parms.name, dev->name);
vti6_tnl_link(ip6n, t);
return 0;
out:
return err;
}
static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
{
struct net_device *dev;
struct ip6_tnl *t;
char name[IFNAMSIZ];
int err;
if (p->name[0]) {
if (!dev_valid_name(p->name))
goto failed;
strscpy(name, p->name, IFNAMSIZ);
} else {
sprintf(name, "ip6_vti%%d");
}
dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
if (!dev)
goto failed;
dev_net_set(dev, net);
t = netdev_priv(dev);
t->parms = *p;
t->net = dev_net(dev);
err = vti6_tnl_create2(dev);
if (err < 0)
goto failed_free;
return t;
failed_free:
free_netdev(dev);
failed:
return NULL;
}
/**
* vti6_locate - find or create tunnel matching given parameters
* @net: network namespace
* @p: tunnel parameters
* @create: != 0 if allowed to create new tunnel if no match found
*
* Description:
* vti6_locate() first tries to locate an existing tunnel
* based on @parms. If this is unsuccessful, but @create is set a new
* tunnel device is created and registered for use.
*
* Return:
* matching tunnel or NULL
**/
static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p,
int create)
{
const struct in6_addr *remote = &p->raddr;
const struct in6_addr *local = &p->laddr;
struct ip6_tnl __rcu **tp;
struct ip6_tnl *t;
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
for (tp = vti6_tnl_bucket(ip6n, p);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr)) {
if (create)
return NULL;
return t;
}
}
if (!create)
return NULL;
return vti6_tnl_create(net, p);
}
/**
* vti6_dev_uninit - tunnel device uninitializer
* @dev: the device to be destroyed
*
* Description:
* vti6_dev_uninit() removes tunnel from its list
**/
static void vti6_dev_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
if (dev == ip6n->fb_tnl_dev)
RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
else
vti6_tnl_unlink(ip6n, t);
netdev_put(dev, &t->dev_tracker);
}
static int vti6_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
struct ip6_tnl *t;
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
rcu_read_lock();
t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
if (t) {
if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) {
rcu_read_unlock();
goto discard;
}
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
rcu_read_unlock();
goto discard;
}
ipv6h = ipv6_hdr(skb);
if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) {
DEV_STATS_INC(t->dev, rx_dropped);
rcu_read_unlock();
goto discard;
}
rcu_read_unlock();
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, encap_type);
}
rcu_read_unlock();
return -EINVAL;
discard:
kfree_skb(skb);
return 0;
}
static int vti6_rcv(struct sk_buff *skb)
{
int nexthdr = skb_network_header(skb)[IP6CB(skb)->nhoff];
return vti6_input_proto(skb, nexthdr, 0, 0);
}
static int vti6_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
struct net_device *dev;
struct xfrm_state *x;
const struct xfrm_mode *inner_mode;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
u32 orig_mark = skb->mark;
int ret;
if (!t)
return 1;
dev = t->dev;
if (err) {
DEV_STATS_INC(dev, rx_errors);
DEV_STATS_INC(dev, rx_dropped);
return 0;
}
x = xfrm_input_state(skb);
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->family;
skb->mark = be32_to_cpu(t->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
skb->mark = orig_mark;
if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
skb->dev = dev;
dev_sw_netstats_rx_add(dev, skb->len);
return 0;
}
/**
* vti6_addr_conflict - compare packet addresses to tunnel's own
* @t: the outgoing tunnel device
* @hdr: IPv6 header from the incoming packet
*
* Description:
* Avoid trivial tunneling loop by checking that tunnel exit-point
* doesn't match source of incoming packet.
*
* Return:
* 1 if conflict,
* 0 else
**/
static inline bool
vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
{
return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
}
static bool vti6_state_check(const struct xfrm_state *x,
const struct in6_addr *dst,
const struct in6_addr *src)
{
xfrm_address_t *daddr = (xfrm_address_t *)dst;
xfrm_address_t *saddr = (xfrm_address_t *)src;
/* if there is no transform then this tunnel is not functional.
* Or if the xfrm is not mode tunnel.
*/
if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
x->props.family != AF_INET6)
return false;
if (ipv6_addr_any(dst))
return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6);
if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6))
return false;
return true;
}
/**
* vti6_xmit - send a packet
* @skb: the outgoing socket buffer
* @dev: the outgoing tunnel device
* @fl: the flow informations for the xfrm_lookup
**/
static int
vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
{
struct ip6_tnl *t = netdev_priv(dev);
struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev;
struct xfrm_state *x;
int pkt_len = skb->len;
int err = -1;
int mtu;
if (!dst) {
switch (skb->protocol) {
case htons(ETH_P_IP): {
struct rtable *rt;
fl->u.ip4.flowi4_oif = dev->ifindex;
fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
if (IS_ERR(rt))
goto tx_err_link_failure;
dst = &rt->dst;
skb_dst_set(skb, dst);
break;
}
case htons(ETH_P_IPV6):
fl->u.ip6.flowi6_oif = dev->ifindex;
fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
if (dst->error) {
dst_release(dst);
dst = NULL;
goto tx_err_link_failure;
}
skb_dst_set(skb, dst);
break;
default:
goto tx_err_link_failure;
}
}
dst_hold(dst);
dst = xfrm_lookup_route(t->net, dst, fl, NULL, 0);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
goto tx_err_link_failure;
}
if (dst->flags & DST_XFRM_QUEUE)
goto xmit;
x = dst->xfrm;
if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr))
goto tx_err_link_failure;
if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr,
(const struct in6_addr *)&x->id.daddr))
goto tx_err_link_failure;
tdev = dst->dev;
if (tdev == dev) {
DEV_STATS_INC(dev, collisions);
net_warn_ratelimited("%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst);
if (skb->len > mtu) {
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IPV6)) {
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
} else {
if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
goto xmit;
icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
}
err = -EMSGSIZE;
goto tx_err_dst_release;
}
xmit:
skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
err = dst_output(t->net, skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = pkt_len;
iptunnel_xmit_stats(dev, err);
return 0;
tx_err_link_failure:
DEV_STATS_INC(dev, tx_carrier_errors);
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
return err;
}
static netdev_tx_t
vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct flowi fl;
int ret;
if (!pskb_inet_may_pull(skb))
goto tx_err;
memset(&fl, 0, sizeof(fl));
switch (skb->protocol) {
case htons(ETH_P_IPV6):
if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
vti6_addr_conflict(t, ipv6_hdr(skb)))
goto tx_err;
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6);
break;
case htons(ETH_P_IP):
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET);
break;
default:
goto tx_err;
}
/* override mark with tunnel output key */
fl.flowi_mark = be32_to_cpu(t->parms.o_key);
ret = vti6_xmit(skb, dev, &fl);
if (ret < 0)
goto tx_err;
return NETDEV_TX_OK;
tx_err:
DEV_STATS_INC(dev, tx_errors);
DEV_STATS_INC(dev, tx_dropped);
kfree_skb(skb);
return NETDEV_TX_OK;
}
static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
__be32 spi;
__u32 mark;
struct xfrm_state *x;
struct ip6_tnl *t;
struct ip_esp_hdr *esph;
struct ip_auth_hdr *ah;
struct ip_comp_hdr *ipch;
struct net *net = dev_net(skb->dev);
const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
int protocol = iph->nexthdr;
t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr);
if (!t)
return -1;
mark = be32_to_cpu(t->parms.o_key);
switch (protocol) {
case IPPROTO_ESP:
esph = (struct ip_esp_hdr *)(skb->data + offset);
spi = esph->spi;
break;
case IPPROTO_AH:
ah = (struct ip_auth_hdr *)(skb->data + offset);
spi = ah->spi;
break;
case IPPROTO_COMP:
ipch = (struct ip_comp_hdr *)(skb->data + offset);
spi = htonl(ntohs(ipch->cpi));
break;
default:
return 0;
}
if (type != ICMPV6_PKT_TOOBIG &&
type != NDISC_REDIRECT)
return 0;
x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
spi, protocol, AF_INET6);
if (!x)
return 0;
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0,
sock_net_uid(net, NULL));
else
ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
}
static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu)
{
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
struct net_device *tdev = NULL;
int mtu;
__dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV |
IP6_TNL_F_CAP_PER_PACKET);
p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr);
if (p->flags & IP6_TNL_F_CAP_XMIT && p->flags & IP6_TNL_F_CAP_RCV)
dev->flags |= IFF_POINTOPOINT;
else
dev->flags &= ~IFF_POINTOPOINT;
if (keep_mtu && dev->mtu) {
dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu);
return;
}
if (p->flags & IP6_TNL_F_CAP_XMIT) {
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
struct rt6_info *rt = rt6_lookup(t->net,
&p->raddr, &p->laddr,
p->link, NULL, strict);
if (rt)
tdev = rt->dst.dev;
ip6_rt_put(rt);
}
if (!tdev && p->link)
tdev = __dev_get_by_index(t->net, p->link);
if (tdev)
mtu = tdev->mtu - sizeof(struct ipv6hdr);
else
mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr);
dev->mtu = max_t(int, mtu, IPV4_MIN_MTU);
}
/**
* vti6_tnl_change - update the tunnel parameters
* @t: tunnel to be changed
* @p: tunnel configuration parameters
* @keep_mtu: MTU was set from userspace, don't re-compute it
*
* Description:
* vti6_tnl_change() updates the tunnel parameters
**/
static int
vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p,
bool keep_mtu)
{
t->parms.laddr = p->laddr;
t->parms.raddr = p->raddr;
t->parms.link = p->link;
t->parms.i_key = p->i_key;
t->parms.o_key = p->o_key;
t->parms.proto = p->proto;
t->parms.fwmark = p->fwmark;
dst_cache_reset(&t->dst_cache);
vti6_link_config(t, keep_mtu);
return 0;
}
static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p,
bool keep_mtu)
{
struct net *net = dev_net(t->dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
int err;
vti6_tnl_unlink(ip6n, t);
synchronize_net();
err = vti6_tnl_change(t, p, keep_mtu);
vti6_tnl_link(ip6n, t);
netdev_state_change(t->dev);
return err;
}
static void
vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u)
{
p->laddr = u->laddr;
p->raddr = u->raddr;
p->link = u->link;
p->i_key = u->i_key;
p->o_key = u->o_key;
p->proto = u->proto;
memcpy(p->name, u->name, sizeof(u->name));
}
static void
vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
{
u->laddr = p->laddr;
u->raddr = p->raddr;
u->link = p->link;
u->i_key = p->i_key;
u->o_key = p->o_key;
if (u->i_key)
u->i_flags |= GRE_KEY;
if (u->o_key)
u->o_flags |= GRE_KEY;
u->proto = p->proto;
memcpy(u->name, p->name, sizeof(u->name));
}
/**
* vti6_siocdevprivate - configure vti6 tunnels from userspace
* @dev: virtual device associated with tunnel
* @ifr: unused
* @data: parameters passed from userspace
* @cmd: command to be performed
*
* Description:
* vti6_siocdevprivate() is used for managing vti6 tunnels
* from userspace.
*
* The possible commands are the following:
* %SIOCGETTUNNEL: get tunnel parameters for device
* %SIOCADDTUNNEL: add tunnel matching given tunnel parameters
* %SIOCCHGTUNNEL: change tunnel parameters to those given
* %SIOCDELTUNNEL: delete tunnel
*
* The fallback device "ip6_vti0", created during module
* initialization, can be used for creating other tunnel devices.
*
* Return:
* 0 on success,
* %-EFAULT if unable to copy data to or from userspace,
* %-EPERM if current process hasn't %CAP_NET_ADMIN set
* %-EINVAL if passed tunnel parameters are invalid,
* %-EEXIST if changing a tunnel's parameters would cause a conflict
* %-ENODEV if attempting to change or delete a nonexisting device
**/
static int
vti6_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd)
{
int err = 0;
struct ip6_tnl_parm2 p;
struct __ip6_tnl_parm p1;
struct ip6_tnl *t = NULL;
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
memset(&p1, 0, sizeof(p1));
switch (cmd) {
case SIOCGETTUNNEL:
if (dev == ip6n->fb_tnl_dev) {
if (copy_from_user(&p, data, sizeof(p))) {
err = -EFAULT;
break;
}
vti6_parm_from_user(&p1, &p);
t = vti6_locate(net, &p1, 0);
} else {
memset(&p, 0, sizeof(p));
}
if (!t)
t = netdev_priv(dev);
vti6_parm_to_user(&p, &t->parms);
if (copy_to_user(data, &p, sizeof(p)))
err = -EFAULT;
break;
case SIOCADDTUNNEL:
case SIOCCHGTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
err = -EFAULT;
if (copy_from_user(&p, data, sizeof(p)))
break;
err = -EINVAL;
if (p.proto != IPPROTO_IPV6 && p.proto != 0)
break;
vti6_parm_from_user(&p1, &p);
t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL);
if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
if (t) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else
t = netdev_priv(dev);
err = vti6_update(t, &p1, false);
}
if (t) {
err = 0;
vti6_parm_to_user(&p, &t->parms);
if (copy_to_user(data, &p, sizeof(p)))
err = -EFAULT;
} else
err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
break;
case SIOCDELTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
if (dev == ip6n->fb_tnl_dev) {
err = -EFAULT;
if (copy_from_user(&p, data, sizeof(p)))
break;
err = -ENOENT;
vti6_parm_from_user(&p1, &p);
t = vti6_locate(net, &p1, 0);
if (!t)
break;
err = -EPERM;
if (t->dev == ip6n->fb_tnl_dev)
break;
dev = t->dev;
}
err = 0;
unregister_netdevice(dev);
break;
default:
err = -EINVAL;
}
return err;
}
static const struct net_device_ops vti6_netdev_ops = {
.ndo_init = vti6_dev_init,
.ndo_uninit = vti6_dev_uninit,
.ndo_start_xmit = vti6_tnl_xmit,
.ndo_siocdevprivate = vti6_siocdevprivate,
.ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
/**
* vti6_dev_setup - setup virtual tunnel device
* @dev: virtual device associated with tunnel
*
* Description:
* Initialize function pointers and device parameters
**/
static void vti6_dev_setup(struct net_device *dev)
{
dev->netdev_ops = &vti6_netdev_ops;
dev->header_ops = &ip_tunnel_header_ops;
dev->needs_free_netdev = true;
dev->priv_destructor = vti6_dev_free;
dev->type = ARPHRD_TUNNEL6;
dev->min_mtu = IPV4_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr);
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
netif_keep_dst(dev);
/* This perm addr will be used as interface identifier by IPv6 */
dev->addr_assign_type = NET_ADDR_RANDOM;
eth_random_addr(dev->perm_addr);
}
/**
* vti6_dev_init_gen - general initializer for all tunnel devices
* @dev: virtual device associated with tunnel
**/
static inline int vti6_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
t->net = dev_net(dev);
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
netdev_lockdep_set_classes(dev);
return 0;
}
/**
* vti6_dev_init - initializer for all non fallback tunnel devices
* @dev: virtual device associated with tunnel
**/
static int vti6_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
int err = vti6_dev_init_gen(dev);
if (err)
return err;
vti6_link_config(t, true);
return 0;
}
/**
* vti6_fb_tnl_dev_init - initializer for fallback tunnel device
* @dev: fallback device
*
* Return: 0
**/
static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
t->parms.proto = IPPROTO_IPV6;
rcu_assign_pointer(ip6n->tnls_wc[0], t);
return 0;
}
static int vti6_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
return 0;
}
static void vti6_netlink_parms(struct nlattr *data[],
struct __ip6_tnl_parm *parms)
{
memset(parms, 0, sizeof(*parms));
if (!data)
return;
if (data[IFLA_VTI_LINK])
parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
if (data[IFLA_VTI_LOCAL])
parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]);
if (data[IFLA_VTI_REMOTE])
parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]);
if (data[IFLA_VTI_IKEY])
parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]);
if (data[IFLA_VTI_OKEY])
parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]);
if (data[IFLA_VTI_FWMARK])
parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
}
static int vti6_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct net *net = dev_net(dev);
struct ip6_tnl *nt;
nt = netdev_priv(dev);
vti6_netlink_parms(data, &nt->parms);
nt->parms.proto = IPPROTO_IPV6;
if (vti6_locate(net, &nt->parms, 0))
return -EEXIST;
return vti6_tnl_create2(dev);
}
static void vti6_dellink(struct net_device *dev, struct list_head *head)
{
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
if (dev != ip6n->fb_tnl_dev)
unregister_netdevice_queue(dev, head);
}
static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip6_tnl *t;
struct __ip6_tnl_parm p;
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
if (dev == ip6n->fb_tnl_dev)
return -EINVAL;
vti6_netlink_parms(data, &p);
t = vti6_locate(net, &p, 0);
if (t) {
if (t->dev != dev)
return -EEXIST;
} else
t = netdev_priv(dev);
return vti6_update(t, &p, tb && tb[IFLA_MTU]);
}
static size_t vti6_get_size(const struct net_device *dev)
{
return
/* IFLA_VTI_LINK */
nla_total_size(4) +
/* IFLA_VTI_LOCAL */
nla_total_size(sizeof(struct in6_addr)) +
/* IFLA_VTI_REMOTE */
nla_total_size(sizeof(struct in6_addr)) +
/* IFLA_VTI_IKEY */
nla_total_size(4) +
/* IFLA_VTI_OKEY */
nla_total_size(4) +
/* IFLA_VTI_FWMARK */
nla_total_size(4) +
0;
}
static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip6_tnl *tunnel = netdev_priv(dev);
struct __ip6_tnl_parm *parm = &tunnel->parms;
if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) ||
nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) ||
nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) ||
nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) ||
nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key) ||
nla_put_u32(skb, IFLA_VTI_FWMARK, parm->fwmark))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = {
[IFLA_VTI_LINK] = { .type = NLA_U32 },
[IFLA_VTI_LOCAL] = { .len = sizeof(struct in6_addr) },
[IFLA_VTI_REMOTE] = { .len = sizeof(struct in6_addr) },
[IFLA_VTI_IKEY] = { .type = NLA_U32 },
[IFLA_VTI_OKEY] = { .type = NLA_U32 },
[IFLA_VTI_FWMARK] = { .type = NLA_U32 },
};
static struct rtnl_link_ops vti6_link_ops __read_mostly = {
.kind = "vti6",
.maxtype = IFLA_VTI_MAX,
.policy = vti6_policy,
.priv_size = sizeof(struct ip6_tnl),
.setup = vti6_dev_setup,
.validate = vti6_validate,
.newlink = vti6_newlink,
.dellink = vti6_dellink,
.changelink = vti6_changelink,
.get_size = vti6_get_size,
.fill_info = vti6_fill_info,
.get_link_net = ip6_tnl_get_link_net,
};
static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
struct list_head *list)
{
int h;
struct ip6_tnl *t;
for (h = 0; h < IP6_VTI_HASH_SIZE; h++) {
t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t) {
unregister_netdevice_queue(t->dev, list);
t = rtnl_dereference(t->next);
}
}
t = rtnl_dereference(ip6n->tnls_wc[0]);
if (t)
unregister_netdevice_queue(t->dev, list);
}
static int __net_init vti6_init_net(struct net *net)
{
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
struct ip6_tnl *t = NULL;
int err;
ip6n->tnls[0] = ip6n->tnls_wc;
ip6n->tnls[1] = ip6n->tnls_r_l;
if (!net_has_fallback_tunnels(net))
return 0;
err = -ENOMEM;
ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0",
NET_NAME_UNKNOWN, vti6_dev_setup);
if (!ip6n->fb_tnl_dev)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops;
err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
goto err_register;
err = register_netdev(ip6n->fb_tnl_dev);
if (err < 0)
goto err_register;
t = netdev_priv(ip6n->fb_tnl_dev);
strcpy(t->parms.name, ip6n->fb_tnl_dev->name);
return 0;
err_register:
free_netdev(ip6n->fb_tnl_dev);
err_alloc_dev:
return err;
}
static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list,
struct list_head *dev_to_kill)
{
struct vti6_net *ip6n;
struct net *net;
ASSERT_RTNL();
list_for_each_entry(net, net_list, exit_list) {
ip6n = net_generic(net, vti6_net_id);
vti6_destroy_tunnels(ip6n, dev_to_kill);
}
}
static struct pernet_operations vti6_net_ops = {
.init = vti6_init_net,
.exit_batch_rtnl = vti6_exit_batch_rtnl,
.id = &vti6_net_id,
.size = sizeof(struct vti6_net),
};
static struct xfrm6_protocol vti_esp6_protocol __read_mostly = {
.handler = vti6_rcv,
.input_handler = vti6_input_proto,
.cb_handler = vti6_rcv_cb,
.err_handler = vti6_err,
.priority = 100,
};
static struct xfrm6_protocol vti_ah6_protocol __read_mostly = {
.handler = vti6_rcv,
.input_handler = vti6_input_proto,
.cb_handler = vti6_rcv_cb,
.err_handler = vti6_err,
.priority = 100,
};
static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = {
.handler = vti6_rcv,
.input_handler = vti6_input_proto,
.cb_handler = vti6_rcv_cb,
.err_handler = vti6_err,
.priority = 100,
};
#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
static int vti6_rcv_tunnel(struct sk_buff *skb)
{
const xfrm_address_t *saddr;
__be32 spi;
saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr;
spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr);
return vti6_input_proto(skb, IPPROTO_IPV6, spi, 0);
}
static struct xfrm6_tunnel vti_ipv6_handler __read_mostly = {
.handler = vti6_rcv_tunnel,
.cb_handler = vti6_rcv_cb,
.err_handler = vti6_err,
.priority = 0,
};
static struct xfrm6_tunnel vti_ip6ip_handler __read_mostly = {
.handler = vti6_rcv_tunnel,
.cb_handler = vti6_rcv_cb,
.err_handler = vti6_err,
.priority = 0,
};
#endif
/**
* vti6_tunnel_init - register protocol and reserve needed resources
*
* Return: 0 on success
**/
static int __init vti6_tunnel_init(void)
{
const char *msg;
int err;
msg = "tunnel device";
err = register_pernet_device(&vti6_net_ops);
if (err < 0)
goto pernet_dev_failed;
msg = "tunnel protocols";
err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
if (err < 0)
goto xfrm_proto_esp_failed;
err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
if (err < 0)
goto xfrm_proto_ah_failed;
err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP);
if (err < 0)
goto xfrm_proto_comp_failed;
#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
msg = "ipv6 tunnel";
err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET6);
if (err < 0)
goto vti_tunnel_ipv6_failed;
err = xfrm6_tunnel_register(&vti_ip6ip_handler, AF_INET);
if (err < 0)
goto vti_tunnel_ip6ip_failed;
#endif
msg = "netlink interface";
err = rtnl_link_register(&vti6_link_ops);
if (err < 0)
goto rtnl_link_failed;
return 0;
rtnl_link_failed:
#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
err = xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET);
vti_tunnel_ip6ip_failed:
err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6);
vti_tunnel_ipv6_failed:
#endif
xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
xfrm_proto_comp_failed:
xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
xfrm_proto_esp_failed:
unregister_pernet_device(&vti6_net_ops);
pernet_dev_failed:
pr_err("vti6 init: failed to register %s\n", msg);
return err;
}
/**
* vti6_tunnel_cleanup - free resources and unregister protocol
**/
static void __exit vti6_tunnel_cleanup(void)
{
rtnl_link_unregister(&vti6_link_ops);
#if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL)
xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET);
xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6);
#endif
xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti6_net_ops);
}
module_init(vti6_tunnel_init);
module_exit(vti6_tunnel_cleanup);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti6");
MODULE_ALIAS_NETDEV("ip6_vti0");
MODULE_AUTHOR("Steffen Klassert");
MODULE_DESCRIPTION("IPv6 virtual tunnel interface");