OpenCloudOS-Kernel/net/l2tp/l2tp_ip6.c

830 lines
20 KiB
C
Raw Normal View History

/*
* L2TPv3 IP encapsulation support for IPv6
*
* Copyright (c) 2012 Katalix Systems Ltd
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/icmp.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/random.h>
#include <linux/socket.h>
#include <linux/l2tp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/tcp_states.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include "l2tp_core.h"
struct l2tp_ip6_sock {
/* inet_sock has to be the first member of l2tp_ip6_sock */
struct inet_sock inet;
u32 conn_id;
u32 peer_conn_id;
/* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see
inet6_sk_generic */
struct ipv6_pinfo inet6;
};
static DEFINE_RWLOCK(l2tp_ip6_lock);
static struct hlist_head l2tp_ip6_table;
static struct hlist_head l2tp_ip6_bind_table;
static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
{
return (struct l2tp_ip6_sock *)sk;
}
static struct sock *__l2tp_ip6_bind_lookup(const struct net *net,
const struct in6_addr *laddr,
const struct in6_addr *raddr,
int dif, u32 tunnel_id)
{
struct sock *sk;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk);
const struct in6_addr *sk_raddr = &sk->sk_v6_daddr;
const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
if (!net_eq(sock_net(sk), net))
continue;
if (sk->sk_bound_dev_if && dif && sk->sk_bound_dev_if != dif)
continue;
if (sk_laddr && !ipv6_addr_any(sk_laddr) &&
!ipv6_addr_any(laddr) && !ipv6_addr_equal(sk_laddr, laddr))
continue;
if (!ipv6_addr_any(sk_raddr) && raddr &&
!ipv6_addr_any(raddr) && !ipv6_addr_equal(sk_raddr, raddr))
continue;
if (l2tp->conn_id != tunnel_id)
continue;
goto found;
}
sk = NULL;
found:
return sk;
}
/* When processing receive frames, there are two cases to
* consider. Data frames consist of a non-zero session-id and an
* optional cookie. Control frames consist of a regular L2TP header
* preceded by 32-bits of zeros.
*
* L2TPv3 Session Header Over IP
*
* 0 1 2 3
* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Session ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Cookie (optional, maximum 64 bits)...
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* L2TPv3 Control Message Header Over IP
*
* 0 1 2 3
* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | (32 bits of zeros) |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Control Connection ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | Ns | Nr |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* All control frames are passed to userspace.
*/
static int l2tp_ip6_recv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct sock *sk;
u32 session_id;
u32 tunnel_id;
unsigned char *ptr, *optr;
struct l2tp_session *session;
struct l2tp_tunnel *tunnel = NULL;
struct ipv6hdr *iph;
int length;
if (!pskb_may_pull(skb, 4))
goto discard;
/* Point to L2TP header */
optr = ptr = skb->data;
session_id = ntohl(*((__be32 *) ptr));
ptr += 4;
/* RFC3931: L2TP/IP packets have the first 4 bytes containing
* the session_id. If it is 0, the packet is a L2TP control
* frame and the session_id value can be discarded.
*/
if (session_id == 0) {
__skb_pull(skb, 4);
goto pass_up;
}
/* Ok, this is a data packet. Lookup the session. */
session = l2tp_session_get(net, NULL, session_id);
if (!session)
goto discard;
tunnel = session->tunnel;
if (!tunnel)
goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
ptr += 4;
pr_debug("%s: ip recv\n", tunnel->name);
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
}
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
tunnel->recv_payload_hook);
l2tp_session_dec_refcount(session);
return 0;
pass_up:
/* Get the tunnel_id from the L2TP header */
if (!pskb_may_pull(skb, 12))
goto discard;
if ((skb->data[0] & 0xc0) != 0xc0)
goto discard;
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
iph = ipv6_hdr(skb);
read_lock_bh(&l2tp_ip6_lock);
sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
inet6_iif(skb), tunnel_id);
if (!sk) {
read_unlock_bh(&l2tp_ip6_lock);
goto discard;
}
sock_hold(sk);
read_unlock_bh(&l2tp_ip6_lock);
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_put;
nf_reset(skb);
return sk_receive_skb(sk, skb, 1);
discard_sess:
l2tp_session_dec_refcount(session);
goto discard;
discard_put:
sock_put(sk);
discard:
kfree_skb(skb);
return 0;
}
static int l2tp_ip6_open(struct sock *sk)
{
/* Prevent autobind. We don't have ports. */
inet_sk(sk)->inet_num = IPPROTO_L2TP;
write_lock_bh(&l2tp_ip6_lock);
sk_add_node(sk, &l2tp_ip6_table);
write_unlock_bh(&l2tp_ip6_lock);
return 0;
}
static void l2tp_ip6_close(struct sock *sk, long timeout)
{
write_lock_bh(&l2tp_ip6_lock);
hlist_del_init(&sk->sk_bind_node);
sk_del_node_init(sk);
write_unlock_bh(&l2tp_ip6_lock);
sk_common_release(sk);
}
static void l2tp_ip6_destroy_sock(struct sock *sk)
{
struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
lock_sock(sk);
ip6_flush_pending_frames(sk);
release_sock(sk);
if (tunnel) {
l2tp_tunnel_closeall(tunnel);
sock_put(sk);
}
inet6_destroy_sock(sk);
}
static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr;
struct net *net = sock_net(sk);
__be32 v4addr = 0;
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
int bound_dev_if;
int addr_type;
int err;
if (addr->l2tp_family != AF_INET6)
return -EINVAL;
if (addr_len < sizeof(*addr))
return -EINVAL;
addr_type = ipv6_addr_type(&addr->l2tp_addr);
/* l2tp_ip6 sockets are IPv6 only */
if (addr_type == IPV6_ADDR_MAPPED)
return -EADDRNOTAVAIL;
/* L2TP is point-point, not multicast */
if (addr_type & IPV6_ADDR_MULTICAST)
return -EADDRNOTAVAIL;
lock_sock(sk);
err = -EINVAL;
l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind() Lock socket before checking the SOCK_ZAPPED flag in l2tp_ip6_bind(). Without lock, a concurrent call could modify the socket flags between the sock_flag(sk, SOCK_ZAPPED) test and the lock_sock() call. This way, a socket could be inserted twice in l2tp_ip6_bind_table. Releasing it would then leave a stale pointer there, generating use-after-free errors when walking through the list or modifying adjacent entries. BUG: KASAN: use-after-free in l2tp_ip6_close+0x22e/0x290 at addr ffff8800081b0ed8 Write of size 8 by task syz-executor/10987 CPU: 0 PID: 10987 Comm: syz-executor Not tainted 4.8.0+ #39 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014 ffff880031d97838 ffffffff829f835b ffff88001b5a1640 ffff8800081b0ec0 ffff8800081b15a0 ffff8800081b6d20 ffff880031d97860 ffffffff8174d3cc ffff880031d978f0 ffff8800081b0e80 ffff88001b5a1640 ffff880031d978e0 Call Trace: [<ffffffff829f835b>] dump_stack+0xb3/0x118 lib/dump_stack.c:15 [<ffffffff8174d3cc>] kasan_object_err+0x1c/0x70 mm/kasan/report.c:156 [< inline >] print_address_description mm/kasan/report.c:194 [<ffffffff8174d666>] kasan_report_error+0x1f6/0x4d0 mm/kasan/report.c:283 [< inline >] kasan_report mm/kasan/report.c:303 [<ffffffff8174db7e>] __asan_report_store8_noabort+0x3e/0x40 mm/kasan/report.c:329 [< inline >] __write_once_size ./include/linux/compiler.h:249 [< inline >] __hlist_del ./include/linux/list.h:622 [< inline >] hlist_del_init ./include/linux/list.h:637 [<ffffffff8579047e>] l2tp_ip6_close+0x22e/0x290 net/l2tp/l2tp_ip6.c:239 [<ffffffff850b2dfd>] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415 [<ffffffff851dc5a0>] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422 [<ffffffff84c4581d>] sock_release+0x8d/0x1d0 net/socket.c:570 [<ffffffff84c45976>] sock_close+0x16/0x20 net/socket.c:1017 [<ffffffff817a108c>] __fput+0x28c/0x780 fs/file_table.c:208 [<ffffffff817a1605>] ____fput+0x15/0x20 fs/file_table.c:244 [<ffffffff813774f9>] task_work_run+0xf9/0x170 [<ffffffff81324aae>] do_exit+0x85e/0x2a00 [<ffffffff81326dc8>] do_group_exit+0x108/0x330 [<ffffffff81348cf7>] get_signal+0x617/0x17a0 kernel/signal.c:2307 [<ffffffff811b49af>] do_signal+0x7f/0x18f0 [<ffffffff810039bf>] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156 [< inline >] prepare_exit_to_usermode arch/x86/entry/common.c:190 [<ffffffff81006060>] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259 [<ffffffff85e4d726>] entry_SYSCALL_64_fastpath+0xc4/0xc6 Object at ffff8800081b0ec0, in cache L2TP/IPv6 size: 1448 Allocated: PID = 10987 [ 1116.897025] [<ffffffff811ddcb6>] save_stack_trace+0x16/0x20 [ 1116.897025] [<ffffffff8174c736>] save_stack+0x46/0xd0 [ 1116.897025] [<ffffffff8174c9ad>] kasan_kmalloc+0xad/0xe0 [ 1116.897025] [<ffffffff8174cee2>] kasan_slab_alloc+0x12/0x20 [ 1116.897025] [< inline >] slab_post_alloc_hook mm/slab.h:417 [ 1116.897025] [< inline >] slab_alloc_node mm/slub.c:2708 [ 1116.897025] [< inline >] slab_alloc mm/slub.c:2716 [ 1116.897025] [<ffffffff817476a8>] kmem_cache_alloc+0xc8/0x2b0 mm/slub.c:2721 [ 1116.897025] [<ffffffff84c4f6a9>] sk_prot_alloc+0x69/0x2b0 net/core/sock.c:1326 [ 1116.897025] [<ffffffff84c58ac8>] sk_alloc+0x38/0xae0 net/core/sock.c:1388 [ 1116.897025] [<ffffffff851ddf67>] inet6_create+0x2d7/0x1000 net/ipv6/af_inet6.c:182 [ 1116.897025] [<ffffffff84c4af7b>] __sock_create+0x37b/0x640 net/socket.c:1153 [ 1116.897025] [< inline >] sock_create net/socket.c:1193 [ 1116.897025] [< inline >] SYSC_socket net/socket.c:1223 [ 1116.897025] [<ffffffff84c4b46f>] SyS_socket+0xef/0x1b0 net/socket.c:1203 [ 1116.897025] [<ffffffff85e4d685>] entry_SYSCALL_64_fastpath+0x23/0xc6 Freed: PID = 10987 [ 1116.897025] [<ffffffff811ddcb6>] save_stack_trace+0x16/0x20 [ 1116.897025] [<ffffffff8174c736>] save_stack+0x46/0xd0 [ 1116.897025] [<ffffffff8174cf61>] kasan_slab_free+0x71/0xb0 [ 1116.897025] [< inline >] slab_free_hook mm/slub.c:1352 [ 1116.897025] [< inline >] slab_free_freelist_hook mm/slub.c:1374 [ 1116.897025] [< inline >] slab_free mm/slub.c:2951 [ 1116.897025] [<ffffffff81748b28>] kmem_cache_free+0xc8/0x330 mm/slub.c:2973 [ 1116.897025] [< inline >] sk_prot_free net/core/sock.c:1369 [ 1116.897025] [<ffffffff84c541eb>] __sk_destruct+0x32b/0x4f0 net/core/sock.c:1444 [ 1116.897025] [<ffffffff84c5aca4>] sk_destruct+0x44/0x80 net/core/sock.c:1452 [ 1116.897025] [<ffffffff84c5ad33>] __sk_free+0x53/0x220 net/core/sock.c:1460 [ 1116.897025] [<ffffffff84c5af23>] sk_free+0x23/0x30 net/core/sock.c:1471 [ 1116.897025] [<ffffffff84c5cb6c>] sk_common_release+0x28c/0x3e0 ./include/net/sock.h:1589 [ 1116.897025] [<ffffffff8579044e>] l2tp_ip6_close+0x1fe/0x290 net/l2tp/l2tp_ip6.c:243 [ 1116.897025] [<ffffffff850b2dfd>] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415 [ 1116.897025] [<ffffffff851dc5a0>] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422 [ 1116.897025] [<ffffffff84c4581d>] sock_release+0x8d/0x1d0 net/socket.c:570 [ 1116.897025] [<ffffffff84c45976>] sock_close+0x16/0x20 net/socket.c:1017 [ 1116.897025] [<ffffffff817a108c>] __fput+0x28c/0x780 fs/file_table.c:208 [ 1116.897025] [<ffffffff817a1605>] ____fput+0x15/0x20 fs/file_table.c:244 [ 1116.897025] [<ffffffff813774f9>] task_work_run+0xf9/0x170 [ 1116.897025] [<ffffffff81324aae>] do_exit+0x85e/0x2a00 [ 1116.897025] [<ffffffff81326dc8>] do_group_exit+0x108/0x330 [ 1116.897025] [<ffffffff81348cf7>] get_signal+0x617/0x17a0 kernel/signal.c:2307 [ 1116.897025] [<ffffffff811b49af>] do_signal+0x7f/0x18f0 [ 1116.897025] [<ffffffff810039bf>] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156 [ 1116.897025] [< inline >] prepare_exit_to_usermode arch/x86/entry/common.c:190 [ 1116.897025] [<ffffffff81006060>] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259 [ 1116.897025] [<ffffffff85e4d726>] entry_SYSCALL_64_fastpath+0xc4/0xc6 Memory state around the buggy address: ffff8800081b0d80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8800081b0e00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff8800081b0e80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb ^ ffff8800081b0f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8800081b0f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== The same issue exists with l2tp_ip_bind() and l2tp_ip_bind_table. Fixes: c51ce49735c1 ("l2tp: fix oops in L2TP IP sockets for connect() AF_UNSPEC case") Reported-by: Baozeng Ding <sploving1@gmail.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Baozeng Ding <sploving1@gmail.com> Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-19 05:13:00 +08:00
if (!sock_flag(sk, SOCK_ZAPPED))
goto out_unlock;
if (sk->sk_state != TCP_CLOSE)
goto out_unlock;
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
bound_dev_if = sk->sk_bound_dev_if;
/* Check if the address belongs to the host. */
rcu_read_lock();
if (addr_type != IPV6_ADDR_ANY) {
struct net_device *dev = NULL;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
if (addr->l2tp_scope_id)
bound_dev_if = addr->l2tp_scope_id;
/* Binding to link-local address requires an
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
* interface.
*/
if (!bound_dev_if)
goto out_unlock_rcu;
err = -ENODEV;
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if);
if (!dev)
goto out_unlock_rcu;
}
/* ipv4 addr of the socket is invalid. Only the
* unspecified and mapped address have a v4 equivalent.
*/
v4addr = LOOPBACK4_IPV6;
err = -EADDRNOTAVAIL;
if (!ipv6_chk_addr(sock_net(sk), &addr->l2tp_addr, dev, 0))
goto out_unlock_rcu;
}
rcu_read_unlock();
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
write_lock_bh(&l2tp_ip6_lock);
if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if,
l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-29 20:09:46 +08:00
addr->l2tp_conn_id)) {
write_unlock_bh(&l2tp_ip6_lock);
err = -EADDRINUSE;
goto out_unlock;
}
inet->inet_saddr = v4addr;
inet->inet_rcv_saddr = v4addr;
sk->sk_bound_dev_if = bound_dev_if;
sk->sk_v6_rcv_saddr = addr->l2tp_addr;
np->saddr = addr->l2tp_addr;
l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;
sk_add_bind_node(sk, &l2tp_ip6_bind_table);
sk_del_node_init(sk);
write_unlock_bh(&l2tp_ip6_lock);
sock_reset_flag(sk, SOCK_ZAPPED);
release_sock(sk);
return 0;
out_unlock_rcu:
rcu_read_unlock();
out_unlock:
release_sock(sk);
return err;
}
static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *) uaddr;
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct in6_addr *daddr;
int addr_type;
int rc;
if (addr_len < sizeof(*lsa))
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EINVAL;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -EINVAL;
if (addr_type & IPV6_ADDR_MAPPED) {
daddr = &usin->sin6_addr;
if (ipv4_is_multicast(daddr->s6_addr32[3]))
return -EINVAL;
}
lock_sock(sk);
/* Must bind first - autobinding does not work */
if (sock_flag(sk, SOCK_ZAPPED)) {
rc = -EINVAL;
goto out_sk;
}
rc = __ip6_datagram_connect(sk, uaddr, addr_len);
if (rc < 0)
goto out_sk;
l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
write_lock_bh(&l2tp_ip6_lock);
hlist_del_init(&sk->sk_bind_node);
sk_add_bind_node(sk, &l2tp_ip6_bind_table);
write_unlock_bh(&l2tp_ip6_lock);
out_sk:
release_sock(sk);
return rc;
}
static int l2tp_ip6_disconnect(struct sock *sk, int flags)
{
if (sock_flag(sk, SOCK_ZAPPED))
return 0;
return __udp_disconnect(sk, flags);
}
static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr;
struct sock *sk = sock->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
struct l2tp_ip6_sock *lsk = l2tp_ip6_sk(sk);
lsa->l2tp_family = AF_INET6;
lsa->l2tp_flowinfo = 0;
lsa->l2tp_scope_id = 0;
lsa->l2tp_unused = 0;
if (peer) {
if (!lsk->peer_conn_id)
return -ENOTCONN;
lsa->l2tp_conn_id = lsk->peer_conn_id;
lsa->l2tp_addr = sk->sk_v6_daddr;
if (np->sndflow)
lsa->l2tp_flowinfo = np->flow_label;
} else {
if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
lsa->l2tp_addr = np->saddr;
else
lsa->l2tp_addr = sk->sk_v6_rcv_saddr;
lsa->l2tp_conn_id = lsk->conn_id;
}
if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
lsa->l2tp_scope_id = sk->sk_bound_dev_if;
*uaddr_len = sizeof(*lsa);
return 0;
}
static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb)
{
int rc;
/* Charge it to the socket, dropping if the queue is full. */
rc = sock_queue_rcv_skb(sk, skb);
if (rc < 0)
goto drop;
return 0;
drop:
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
kfree_skb(skb);
return -1;
}
static int l2tp_ip6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb;
__be32 *transhdr = NULL;
int err = 0;
skb = skb_peek(&sk->sk_write_queue);
if (skb == NULL)
goto out;
transhdr = (__be32 *)skb_transport_header(skb);
*transhdr = 0;
err = ip6_push_pending_frames(sk);
out:
return err;
}
/* Userspace will call sendmsg() on the tunnel socket to send L2TP
* control frames.
*/
static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct ipv6_txoptions opt_space;
DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions *opt = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
struct flowi6 fl6;
struct sockcm_cookie sockc_unused = {0};
struct ipcm6_cookie ipc6;
int addr_len = msg->msg_namelen;
int transhdrlen = 4; /* zero session-id */
int ulen = len + transhdrlen;
int err;
/* Rough check on arithmetic overflow,
better check is made in ip6_append_data().
*/
if (len > INT_MAX)
return -EMSGSIZE;
/* Mirror BSD error message compatibility */
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
/*
* Get and verify the address.
*/
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
ipc6.dontfrag = -1;
if (lsa) {
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (lsa->l2tp_family && lsa->l2tp_family != AF_INET6)
return -EAFNOSUPPORT;
daddr = &lsa->l2tp_addr;
if (np->sndflow) {
fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK;
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
}
}
/*
* Otherwise it will be difficult to maintain
* sk->sk_dst_cache.
*/
if (sk->sk_state == TCP_ESTABLISHED &&
ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
daddr = &sk->sk_v6_daddr;
if (addr_len >= sizeof(struct sockaddr_in6) &&
lsa->l2tp_scope_id &&
ipv6_addr_type(daddr) & IPV6_ADDR_LINKLOCAL)
fl6.flowi6_oif = lsa->l2tp_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &sk->sk_v6_daddr;
fl6.flowlabel = np->flow_label;
}
if (fl6.flowi6_oif == 0)
fl6.flowi6_oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
ipc6.opt = opt;
err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6,
&sockc_unused);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
}
if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
}
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
}
if (!opt) {
opt = txopt_get(np);
opt_to_free = opt;
}
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
ipc6.opt = opt;
fl6.flowi6_proto = sk->sk_protocol;
if (!ipv6_addr_any(daddr))
fl6.daddr = *daddr;
else
fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
fl6.saddr = np->saddr;
final_p = fl6_update_dst(&fl6, opt, &final);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
if (ipc6.tclass < 0)
ipc6.tclass = np->tclass;
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto out;
}
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
if (ipc6.dontfrag < 0)
ipc6.dontfrag = np->dontfrag;
if (msg->msg_flags & MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
lock_sock(sk);
err = ip6_append_data(sk, ip_generic_getfrag, msg,
ulen, transhdrlen, &ipc6,
&fl6, (struct rt6_info *)dst,
msg->msg_flags, &sockc_unused);
if (err)
ip6_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE))
err = l2tp_ip6_push_pending_frames(sk);
release_sock(sk);
done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
txopt_put(opt_to_free);
return err < 0 ? err : len;
do_confirm:
if (msg->msg_flags & MSG_PROBE)
dst_confirm_neigh(dst, &fl6.daddr);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int noblock, int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
size_t copied = 0;
int err = -EOPNOTSUPP;
struct sk_buff *skb;
if (flags & MSG_OOB)
goto out;
if (addr_len)
*addr_len = sizeof(*lsa);
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto done;
sock_recv_timestamp(msg, sk, skb);
/* Copy the address. */
if (lsa) {
lsa->l2tp_family = AF_INET6;
lsa->l2tp_unused = 0;
lsa->l2tp_addr = ipv6_hdr(skb)->saddr;
lsa->l2tp_flowinfo = 0;
lsa->l2tp_scope_id = 0;
lsa->l2tp_conn_id = 0;
if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
lsa->l2tp_scope_id = inet6_iif(skb);
}
if (np->rxopt.all)
ip6_datagram_recv_ctl(sk, msg, skb);
if (flags & MSG_TRUNC)
copied = skb->len;
done:
skb_free_datagram(sk, skb);
out:
return err ? err : copied;
}
static struct proto l2tp_ip6_prot = {
.name = "L2TP/IPv6",
.owner = THIS_MODULE,
.init = l2tp_ip6_open,
.close = l2tp_ip6_close,
.bind = l2tp_ip6_bind,
.connect = l2tp_ip6_connect,
.disconnect = l2tp_ip6_disconnect,
.ioctl = l2tp_ioctl,
.destroy = l2tp_ip6_destroy_sock,
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.sendmsg = l2tp_ip6_sendmsg,
.recvmsg = l2tp_ip6_recvmsg,
.backlog_rcv = l2tp_ip6_backlog_recv,
.hash = inet6_hash,
.unhash = inet_unhash,
.obj_size = sizeof(struct l2tp_ip6_sock),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};
static const struct proto_ops l2tp_ip6_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.release = inet6_release,
.bind = inet6_bind,
.connect = inet_dgram_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip6_getname,
.poll = datagram_poll,
.ioctl = inet6_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
static struct inet_protosw l2tp_ip6_protosw = {
.type = SOCK_DGRAM,
.protocol = IPPROTO_L2TP,
.prot = &l2tp_ip6_prot,
.ops = &l2tp_ip6_ops,
};
static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
.handler = l2tp_ip6_recv,
};
static int __init l2tp_ip6_init(void)
{
int err;
pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n");
err = proto_register(&l2tp_ip6_prot, 1);
if (err != 0)
goto out;
err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
if (err)
goto out1;
inet6_register_protosw(&l2tp_ip6_protosw);
return 0;
out1:
proto_unregister(&l2tp_ip6_prot);
out:
return err;
}
static void __exit l2tp_ip6_exit(void)
{
inet6_unregister_protosw(&l2tp_ip6_protosw);
inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
proto_unregister(&l2tp_ip6_prot);
}
module_init(l2tp_ip6_init);
module_exit(l2tp_ip6_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Chris Elston <celston@katalix.com>");
MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6");
MODULE_VERSION("1.0");
/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like
* enums
*/
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP);
MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP);