linux/net/ipv6/ip6_vti.c

1332 lines
32 KiB
C
Raw Normal View History

// 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;
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 01:58:21 +00:00
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
net: ipv6: For kerneldoc warnings with W=1 net/ipv6/addrconf.c:2005: warning: Function parameter or member 'dev' not described in 'ipv6_dev_find' net/ipv6/ip6_vti.c:138: warning: Function parameter or member 'ip6n' not described in 'vti6_tnl_bucket' net/ipv6/ip6_tunnel.c:218: warning: Function parameter or member 'ip6n' not described in 'ip6_tnl_bucket' net/ipv6/ip6_tunnel.c:238: warning: Function parameter or member 'ip6n' not described in 'ip6_tnl_link' net/ipv6/ip6_tunnel.c:254: warning: Function parameter or member 'ip6n' not described in 'ip6_tnl_unlink' net/ipv6/ip6_tunnel.c:427: warning: Function parameter or member 'raw' not described in 'ip6_tnl_parse_tlv_enc_lim' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'skb' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'ipproto' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'opt' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'type' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'code' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'msg' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'info' not described in 'ip6_tnl_err' net/ipv6/ip6_tunnel.c:499: warning: Function parameter or member 'offset' not described in 'ip6_tnl_err' ip6_tnl_err() is an internal function, so remove the kerneldoc. For the others, add the missing parameters. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Andrew Lunn <andrew@lunn.ch> Link: https://lore.kernel.org/r/20201031183044.1082193-1-andrew@lunn.ch Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-10-31 18:30:44 +00:00
* @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);
dev_hold(dev);
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;
strlcpy(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:
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-08 16:52:56 +00:00
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);
dev_put(dev);
}
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;
}
ipv6: tunnels: fix two use-after-free xfrm6_policy_check() might have re-allocated skb->head, we need to reload ipv6 header pointer. sysbot reported : BUG: KASAN: use-after-free in __ipv6_addr_type+0x302/0x32f net/ipv6/addrconf_core.c:40 Read of size 4 at addr ffff888191b8cb70 by task syz-executor2/1304 CPU: 0 PID: 1304 Comm: syz-executor2 Not tainted 4.20.0-rc7+ #356 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x39d lib/dump_stack.c:113 print_address_description.cold.7+0x9/0x1ff mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.8+0x242/0x309 mm/kasan/report.c:412 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:432 __ipv6_addr_type+0x302/0x32f net/ipv6/addrconf_core.c:40 ipv6_addr_type include/net/ipv6.h:403 [inline] ip6_tnl_get_cap+0x27/0x190 net/ipv6/ip6_tunnel.c:727 ip6_tnl_rcv_ctl+0xdb/0x2a0 net/ipv6/ip6_tunnel.c:757 vti6_rcv+0x336/0x8f3 net/ipv6/ip6_vti.c:321 xfrm6_ipcomp_rcv+0x1a5/0x3a0 net/ipv6/xfrm6_protocol.c:132 ip6_protocol_deliver_rcu+0x372/0x1940 net/ipv6/ip6_input.c:394 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:434 NF_HOOK include/linux/netfilter.h:289 [inline] ip6_input+0xe9/0x600 net/ipv6/ip6_input.c:443 IPVS: ftp: loaded support on port[0] = 21 ip6_mc_input+0x514/0x11c0 net/ipv6/ip6_input.c:537 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x17a/0x330 net/ipv6/ip6_input.c:76 NF_HOOK include/linux/netfilter.h:289 [inline] ipv6_rcv+0x115/0x640 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core+0x14d/0x200 net/core/dev.c:4973 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:5083 process_backlog+0x24e/0x7a0 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x7fa/0x19b0 net/core/dev.c:6412 __do_softirq+0x308/0xb7e kernel/softirq.c:292 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1027 </IRQ> do_softirq.part.14+0x126/0x160 kernel/softirq.c:337 do_softirq+0x19/0x20 kernel/softirq.c:340 netif_rx_ni+0x521/0x860 net/core/dev.c:4569 dev_loopback_xmit+0x287/0x8c0 net/core/dev.c:3576 NF_HOOK include/linux/netfilter.h:289 [inline] ip6_finish_output2+0x193a/0x2930 net/ipv6/ip6_output.c:84 ip6_fragment+0x2b06/0x3850 net/ipv6/ip6_output.c:727 ip6_finish_output+0x6b7/0xc50 net/ipv6/ip6_output.c:152 NF_HOOK_COND include/linux/netfilter.h:278 [inline] ip6_output+0x232/0x9d0 net/ipv6/ip6_output.c:171 dst_output include/net/dst.h:444 [inline] ip6_local_out+0xc5/0x1b0 net/ipv6/output_core.c:176 ip6_send_skb+0xbc/0x340 net/ipv6/ip6_output.c:1727 ip6_push_pending_frames+0xc5/0xf0 net/ipv6/ip6_output.c:1747 rawv6_push_pending_frames net/ipv6/raw.c:615 [inline] rawv6_sendmsg+0x3a3e/0x4b40 net/ipv6/raw.c:945 kobject: 'queues' (0000000089e6eea2): kobject_add_internal: parent: 'tunl0', set: '<NULL>' kobject: 'queues' (0000000089e6eea2): kobject_uevent_env inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798 kobject: 'queues' (0000000089e6eea2): kobject_uevent_env: filter function caused the event to drop! sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:631 sock_write_iter+0x35e/0x5c0 net/socket.c:900 call_write_iter include/linux/fs.h:1857 [inline] new_sync_write fs/read_write.c:474 [inline] __vfs_write+0x6b8/0x9f0 fs/read_write.c:487 kobject: 'rx-0' (00000000e2d902d9): kobject_add_internal: parent: 'queues', set: 'queues' kobject: 'rx-0' (00000000e2d902d9): kobject_uevent_env vfs_write+0x1fc/0x560 fs/read_write.c:549 ksys_write+0x101/0x260 fs/read_write.c:598 kobject: 'rx-0' (00000000e2d902d9): fill_kobj_path: path = '/devices/virtual/net/tunl0/queues/rx-0' __do_sys_write fs/read_write.c:610 [inline] __se_sys_write fs/read_write.c:607 [inline] __x64_sys_write+0x73/0xb0 fs/read_write.c:607 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 kobject: 'tx-0' (00000000443b70ac): kobject_add_internal: parent: 'queues', set: 'queues' entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457669 Code: fd b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f9bd200bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457669 RDX: 000000000000058f RSI: 00000000200033c0 RDI: 0000000000000003 kobject: 'tx-0' (00000000443b70ac): kobject_uevent_env RBP: 000000000072bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f9bd200c6d4 R13: 00000000004c2dcc R14: 00000000004da398 R15: 00000000ffffffff Allocated by task 1304: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc7/0xe0 mm/kasan/kasan.c:553 __do_kmalloc_node mm/slab.c:3684 [inline] __kmalloc_node_track_caller+0x50/0x70 mm/slab.c:3698 __kmalloc_reserve.isra.41+0x41/0xe0 net/core/skbuff.c:140 __alloc_skb+0x155/0x760 net/core/skbuff.c:208 kobject: 'tx-0' (00000000443b70ac): fill_kobj_path: path = '/devices/virtual/net/tunl0/queues/tx-0' alloc_skb include/linux/skbuff.h:1011 [inline] __ip6_append_data.isra.49+0x2f1a/0x3f50 net/ipv6/ip6_output.c:1450 ip6_append_data+0x1bc/0x2d0 net/ipv6/ip6_output.c:1619 rawv6_sendmsg+0x15ab/0x4b40 net/ipv6/raw.c:938 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:631 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2116 __sys_sendmsg+0x11d/0x280 net/socket.c:2154 __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg net/socket.c:2161 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2161 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe kobject: 'gre0' (00000000cb1b2d7b): kobject_add_internal: parent: 'net', set: 'devices' Freed by task 1304: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xcf/0x230 mm/slab.c:3817 skb_free_head+0x93/0xb0 net/core/skbuff.c:553 pskb_expand_head+0x3b2/0x10d0 net/core/skbuff.c:1498 __pskb_pull_tail+0x156/0x18a0 net/core/skbuff.c:1896 pskb_may_pull include/linux/skbuff.h:2188 [inline] _decode_session6+0xd11/0x14d0 net/ipv6/xfrm6_policy.c:150 __xfrm_decode_session+0x71/0x140 net/xfrm/xfrm_policy.c:3272 kobject: 'gre0' (00000000cb1b2d7b): kobject_uevent_env __xfrm_policy_check+0x380/0x2c40 net/xfrm/xfrm_policy.c:3322 __xfrm_policy_check2 include/net/xfrm.h:1170 [inline] xfrm_policy_check include/net/xfrm.h:1175 [inline] xfrm6_policy_check include/net/xfrm.h:1185 [inline] vti6_rcv+0x4bd/0x8f3 net/ipv6/ip6_vti.c:316 xfrm6_ipcomp_rcv+0x1a5/0x3a0 net/ipv6/xfrm6_protocol.c:132 ip6_protocol_deliver_rcu+0x372/0x1940 net/ipv6/ip6_input.c:394 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:434 NF_HOOK include/linux/netfilter.h:289 [inline] ip6_input+0xe9/0x600 net/ipv6/ip6_input.c:443 ip6_mc_input+0x514/0x11c0 net/ipv6/ip6_input.c:537 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x17a/0x330 net/ipv6/ip6_input.c:76 NF_HOOK include/linux/netfilter.h:289 [inline] ipv6_rcv+0x115/0x640 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core+0x14d/0x200 net/core/dev.c:4973 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:5083 process_backlog+0x24e/0x7a0 net/core/dev.c:5923 kobject: 'gre0' (00000000cb1b2d7b): fill_kobj_path: path = '/devices/virtual/net/gre0' napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x7fa/0x19b0 net/core/dev.c:6412 __do_softirq+0x308/0xb7e kernel/softirq.c:292 The buggy address belongs to the object at ffff888191b8cac0 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 176 bytes inside of 512-byte region [ffff888191b8cac0, ffff888191b8ccc0) The buggy address belongs to the page: page:ffffea000646e300 count:1 mapcount:0 mapping:ffff8881da800940 index:0x0 flags: 0x2fffc0000000200(slab) raw: 02fffc0000000200 ffffea0006eaaa48 ffffea00065356c8 ffff8881da800940 raw: 0000000000000000 ffff888191b8c0c0 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected kobject: 'queues' (000000005fd6226e): kobject_add_internal: parent: 'gre0', set: '<NULL>' Memory state around the buggy address: ffff888191b8ca00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888191b8ca80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb >ffff888191b8cb00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888191b8cb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888191b8cc00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 0d3c703a9d17 ("ipv6: Cleanup IPv6 tunnel receive path") Fixes: ed1efb2aefbb ("ipv6: Add support for IPsec virtual tunnel interfaces") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-21 15:47:51 +00:00
ipv6h = ipv6_hdr(skb);
if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) {
t->dev->stats.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.rx_errors++;
dev->stats.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 net_device_stats *stats = &t->dev->stats;
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 queued;
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) {
stats->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_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
} else {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
}
err = -EMSGSIZE;
goto tx_err_dst_release;
}
queued:
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:
stats->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 net_device_stats *stats = &t->dev->stats;
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;
xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
break;
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
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:
stats->tx_errors++;
stats->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;
2017-12-19 13:59:21 +00:00
struct net_device *tdev = NULL;
vti6: Properly adjust vti6 MTU from MTU of lower device If a lower device is found, we don't need to subtract LL_MAX_HEADER to calculate our MTU: just use its MTU, the link layer headers are already taken into account by it. If the lower device is not found, start from ETH_DATA_LEN instead, and only in this case subtract a worst-case LL_MAX_HEADER. We then need to subtract our additional IPv6 header from the calculation. While at it, note that vti6 doesn't have a hardware header, so it doesn't need to set dev->hard_header_len. And as vti6_link_config() now always sets the MTU, there's no need to set a default value in vti6_dev_setup(). This makes the behaviour consistent with IPv4 vti, after commit a32452366b72 ("vti4: Don't count header length twice."), which was accidentally reverted by merge commit f895f0cfbb77 ("Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec"). While commit 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") improved on the original situation, this was still not ideal. As reported in that commit message itself, if we start from an underlying veth MTU of 9000, we end up with an MTU of 8832, that is, 9000 - LL_MAX_HEADER - sizeof(ipv6hdr). This should simply be 8880, or 9000 - sizeof(ipv6hdr) instead: we found the lower device (veth) and we know we don't have any additional link layer header, so there's no need to subtract an hypothetical worst-case number. Fixes: 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2018-03-15 16:17:11 +00:00
int mtu;
memcpy(dev->dev_addr, &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;
2017-12-19 13:59:21 +00:00
if (keep_mtu && dev->mtu) {
dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu);
return;
}
2017-12-19 13:59:21 +00:00
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);
2017-12-19 13:59:21 +00:00
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)
vti6: Properly adjust vti6 MTU from MTU of lower device If a lower device is found, we don't need to subtract LL_MAX_HEADER to calculate our MTU: just use its MTU, the link layer headers are already taken into account by it. If the lower device is not found, start from ETH_DATA_LEN instead, and only in this case subtract a worst-case LL_MAX_HEADER. We then need to subtract our additional IPv6 header from the calculation. While at it, note that vti6 doesn't have a hardware header, so it doesn't need to set dev->hard_header_len. And as vti6_link_config() now always sets the MTU, there's no need to set a default value in vti6_dev_setup(). This makes the behaviour consistent with IPv4 vti, after commit a32452366b72 ("vti4: Don't count header length twice."), which was accidentally reverted by merge commit f895f0cfbb77 ("Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec"). While commit 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") improved on the original situation, this was still not ideal. As reported in that commit message itself, if we start from an underlying veth MTU of 9000, we end up with an MTU of 8832, that is, 9000 - LL_MAX_HEADER - sizeof(ipv6hdr). This should simply be 8880, or 9000 - sizeof(ipv6hdr) instead: we found the lower device (veth) and we know we don't have any additional link layer header, so there's no need to subtract an hypothetical worst-case number. Fixes: 53c81e95df17 ("ip6_vti: adjust vti mtu according to mtu of lower device") Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2018-03-15 16:17:11 +00:00
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_ioctl - configure vti6 tunnels from userspace
* @dev: virtual device associated with tunnel
* @ifr: parameters passed from userspace
* @cmd: command to be performed
*
* Description:
* vti6_ioctl() 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_ioctl(struct net_device *dev, struct ifreq *ifr, 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);
switch (cmd) {
case SIOCGETTUNNEL:
if (dev == ip6n->fb_tnl_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_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(ifr->ifr_ifru.ifru_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, ifr->ifr_ifru.ifru_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(ifr->ifr_ifru.ifru_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, ifr->ifr_ifru.ifru_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_do_ioctl = vti6_ioctl,
.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;
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-08 16:52:56 +00:00
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;
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;
dev_hold(dev);
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);
}
ip_tunnel: the lack of vti_link_ops' dellink() cause kernel panic Now the vti_link_ops do not point the .dellink, for fb tunnel device (ip_vti0), the net_device will be removed as the default .dellink is unregister_netdevice_queue,but the tunnel still in the tunnel list, then if we add a new vti tunnel, in ip_tunnel_find(): hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == t->parms.link && ==> type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } the panic will happen, cause dev of ip_tunnel *t is null: [ 3835.072977] IP: [<ffffffffa04103fd>] ip_tunnel_find+0x9d/0xc0 [ip_tunnel] [ 3835.073008] PGD b2c21067 PUD b7277067 PMD 0 [ 3835.073008] Oops: 0000 [#1] SMP ..... [ 3835.073008] Stack: [ 3835.073008] ffff8800b72d77f0 ffffffffa0411924 ffff8800bb956000 ffff8800b72d78e0 [ 3835.073008] ffff8800b72d78a0 0000000000000000 ffffffffa040d100 ffff8800b72d7858 [ 3835.073008] ffffffffa040b2e3 0000000000000000 0000000000000000 0000000000000000 [ 3835.073008] Call Trace: [ 3835.073008] [<ffffffffa0411924>] ip_tunnel_newlink+0x64/0x160 [ip_tunnel] [ 3835.073008] [<ffffffffa040b2e3>] vti_newlink+0x43/0x70 [ip_vti] [ 3835.073008] [<ffffffff8150d4da>] rtnl_newlink+0x4fa/0x5f0 [ 3835.073008] [<ffffffff812f68bb>] ? nla_strlcpy+0x5b/0x70 [ 3835.073008] [<ffffffff81508fb0>] ? rtnl_link_ops_get+0x40/0x60 [ 3835.073008] [<ffffffff8150d11f>] ? rtnl_newlink+0x13f/0x5f0 [ 3835.073008] [<ffffffff81509cf4>] rtnetlink_rcv_msg+0xa4/0x270 [ 3835.073008] [<ffffffff8126adf5>] ? sock_has_perm+0x75/0x90 [ 3835.073008] [<ffffffff81509c50>] ? rtnetlink_rcv+0x30/0x30 [ 3835.073008] [<ffffffff81529e39>] netlink_rcv_skb+0xa9/0xc0 [ 3835.073008] [<ffffffff81509c48>] rtnetlink_rcv+0x28/0x30 .... modprobe ip_vti ip link del ip_vti0 type vti ip link add ip_vti0 type vti rmmod ip_vti do that one or more times, kernel will panic. fix it by assigning ip_tunnel_dellink to vti_link_ops' dellink, in which we skip the unregister of fb tunnel device. do the same on ip6_vti. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-23 07:04:11 +00:00
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,
ip_tunnel: the lack of vti_link_ops' dellink() cause kernel panic Now the vti_link_ops do not point the .dellink, for fb tunnel device (ip_vti0), the net_device will be removed as the default .dellink is unregister_netdevice_queue,but the tunnel still in the tunnel list, then if we add a new vti tunnel, in ip_tunnel_find(): hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == t->parms.link && ==> type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } the panic will happen, cause dev of ip_tunnel *t is null: [ 3835.072977] IP: [<ffffffffa04103fd>] ip_tunnel_find+0x9d/0xc0 [ip_tunnel] [ 3835.073008] PGD b2c21067 PUD b7277067 PMD 0 [ 3835.073008] Oops: 0000 [#1] SMP ..... [ 3835.073008] Stack: [ 3835.073008] ffff8800b72d77f0 ffffffffa0411924 ffff8800bb956000 ffff8800b72d78e0 [ 3835.073008] ffff8800b72d78a0 0000000000000000 ffffffffa040d100 ffff8800b72d7858 [ 3835.073008] ffffffffa040b2e3 0000000000000000 0000000000000000 0000000000000000 [ 3835.073008] Call Trace: [ 3835.073008] [<ffffffffa0411924>] ip_tunnel_newlink+0x64/0x160 [ip_tunnel] [ 3835.073008] [<ffffffffa040b2e3>] vti_newlink+0x43/0x70 [ip_vti] [ 3835.073008] [<ffffffff8150d4da>] rtnl_newlink+0x4fa/0x5f0 [ 3835.073008] [<ffffffff812f68bb>] ? nla_strlcpy+0x5b/0x70 [ 3835.073008] [<ffffffff81508fb0>] ? rtnl_link_ops_get+0x40/0x60 [ 3835.073008] [<ffffffff8150d11f>] ? rtnl_newlink+0x13f/0x5f0 [ 3835.073008] [<ffffffff81509cf4>] rtnetlink_rcv_msg+0xa4/0x270 [ 3835.073008] [<ffffffff8126adf5>] ? sock_has_perm+0x75/0x90 [ 3835.073008] [<ffffffff81509c50>] ? rtnetlink_rcv+0x30/0x30 [ 3835.073008] [<ffffffff81529e39>] netlink_rcv_skb+0xa9/0xc0 [ 3835.073008] [<ffffffff81509c48>] rtnetlink_rcv+0x28/0x30 .... modprobe ip_vti ip link del ip_vti0 type vti ip link add ip_vti0 type vti rmmod ip_vti do that one or more times, kernel will panic. fix it by assigning ip_tunnel_dellink to vti_link_ops' dellink, in which we skip the unregister of fb tunnel device. do the same on ip6_vti. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-23 07:04:11 +00:00
.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]);
ip6_vti: fix a null pointer deference when destroy vti6 tunnel If load ip6_vti module and create a network namespace when set fb_tunnels_only_for_init_net to 1, then exit the namespace will cause following crash: [ 6601.677036] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 6601.679057] PGD 8000000425eca067 P4D 8000000425eca067 PUD 424292067 PMD 0 [ 6601.680483] Oops: 0000 [#1] SMP PTI [ 6601.681223] CPU: 7 PID: 93 Comm: kworker/u16:1 Kdump: loaded Tainted: G E 4.18.0+ #3 [ 6601.683153] Hardware name: Fedora Project OpenStack Nova, BIOS seabios-1.7.5-11.el7 04/01/2014 [ 6601.684919] Workqueue: netns cleanup_net [ 6601.685742] RIP: 0010:vti6_exit_batch_net+0x87/0xd0 [ip6_vti] [ 6601.686932] Code: 7b 08 48 89 e6 e8 b9 ea d3 dd 48 8b 1b 48 85 db 75 ec 48 83 c5 08 48 81 fd 00 01 00 00 75 d5 49 8b 84 24 08 01 00 00 48 89 e6 <48> 8b 78 08 e8 90 ea d3 dd 49 8b 45 28 49 39 c6 4c 8d 68 d8 75 a1 [ 6601.690735] RSP: 0018:ffffa897c2737de0 EFLAGS: 00010246 [ 6601.691846] RAX: 0000000000000000 RBX: 0000000000000000 RCX: dead000000000200 [ 6601.693324] RDX: 0000000000000015 RSI: ffffa897c2737de0 RDI: ffffffff9f2ea9e0 [ 6601.694824] RBP: 0000000000000100 R08: 0000000000000000 R09: 0000000000000000 [ 6601.696314] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8dc323c07e00 [ 6601.697812] R13: ffff8dc324a63100 R14: ffffa897c2737e30 R15: ffffa897c2737e30 [ 6601.699345] FS: 0000000000000000(0000) GS:ffff8dc33fdc0000(0000) knlGS:0000000000000000 [ 6601.701068] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6601.702282] CR2: 0000000000000008 CR3: 0000000424966002 CR4: 00000000001606e0 [ 6601.703791] Call Trace: [ 6601.704329] cleanup_net+0x1b4/0x2c0 [ 6601.705268] process_one_work+0x16c/0x370 [ 6601.706145] worker_thread+0x49/0x3e0 [ 6601.706942] kthread+0xf8/0x130 [ 6601.707626] ? rescuer_thread+0x340/0x340 [ 6601.708476] ? kthread_bind+0x10/0x10 [ 6601.709266] ret_from_fork+0x35/0x40 Reproduce: modprobe ip6_vti echo 1 > /proc/sys/net/core/fb_tunnels_only_for_init_net unshare -n exit This because ip6n->tnls_wc[0] point to fallback device in default, but in non-default namespace, ip6n->tnls_wc[0] will be NULL, so add the NULL check comparatively. Fixes: e2948e5af8ee ("ip6_vti: fix creating fallback tunnel device for vti6") Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-20 02:51:05 +00:00
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);
ip_tunnel: the lack of vti_link_ops' dellink() cause kernel panic Now the vti_link_ops do not point the .dellink, for fb tunnel device (ip_vti0), the net_device will be removed as the default .dellink is unregister_netdevice_queue,but the tunnel still in the tunnel list, then if we add a new vti tunnel, in ip_tunnel_find(): hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == t->parms.link && ==> type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } the panic will happen, cause dev of ip_tunnel *t is null: [ 3835.072977] IP: [<ffffffffa04103fd>] ip_tunnel_find+0x9d/0xc0 [ip_tunnel] [ 3835.073008] PGD b2c21067 PUD b7277067 PMD 0 [ 3835.073008] Oops: 0000 [#1] SMP ..... [ 3835.073008] Stack: [ 3835.073008] ffff8800b72d77f0 ffffffffa0411924 ffff8800bb956000 ffff8800b72d78e0 [ 3835.073008] ffff8800b72d78a0 0000000000000000 ffffffffa040d100 ffff8800b72d7858 [ 3835.073008] ffffffffa040b2e3 0000000000000000 0000000000000000 0000000000000000 [ 3835.073008] Call Trace: [ 3835.073008] [<ffffffffa0411924>] ip_tunnel_newlink+0x64/0x160 [ip_tunnel] [ 3835.073008] [<ffffffffa040b2e3>] vti_newlink+0x43/0x70 [ip_vti] [ 3835.073008] [<ffffffff8150d4da>] rtnl_newlink+0x4fa/0x5f0 [ 3835.073008] [<ffffffff812f68bb>] ? nla_strlcpy+0x5b/0x70 [ 3835.073008] [<ffffffff81508fb0>] ? rtnl_link_ops_get+0x40/0x60 [ 3835.073008] [<ffffffff8150d11f>] ? rtnl_newlink+0x13f/0x5f0 [ 3835.073008] [<ffffffff81509cf4>] rtnetlink_rcv_msg+0xa4/0x270 [ 3835.073008] [<ffffffff8126adf5>] ? sock_has_perm+0x75/0x90 [ 3835.073008] [<ffffffff81509c50>] ? rtnetlink_rcv+0x30/0x30 [ 3835.073008] [<ffffffff81529e39>] netlink_rcv_skb+0xa9/0xc0 [ 3835.073008] [<ffffffff81509c48>] rtnetlink_rcv+0x28/0x30 .... modprobe ip_vti ip link del ip_vti0 type vti ip link add ip_vti0 type vti rmmod ip_vti do that one or more times, kernel will panic. fix it by assigning ip_tunnel_dellink to vti_link_ops' dellink, in which we skip the unregister of fb tunnel device. do the same on ip6_vti. Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-23 07:04:11 +00:00
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:
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-08 16:52:56 +00:00
free_netdev(ip6n->fb_tnl_dev);
err_alloc_dev:
return err;
}
static void __net_exit vti6_exit_batch_net(struct list_head *net_list)
{
struct vti6_net *ip6n;
struct net *net;
LIST_HEAD(list);
rtnl_lock();
list_for_each_entry(net, net_list, exit_list) {
ip6n = net_generic(net, vti6_net_id);
vti6_destroy_tunnels(ip6n, &list);
}
unregister_netdevice_many(&list);
rtnl_unlock();
}
static struct pernet_operations vti6_net_ops = {
.init = vti6_init_net,
.exit_batch = vti6_exit_batch_net,
.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");