linux_dsm_epyc7002/net/l2tp/l2tp_ip.c

687 lines
16 KiB
C
Raw Normal View History

/*
* L2TPv3 IP encapsulation support
*
* Copyright (c) 2008,2009,2010 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 <asm/ioctls.h>
#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 <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/tcp_states.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include "l2tp_core.h"
struct l2tp_ip_sock {
/* inet_sock has to be the first member of l2tp_ip_sock */
struct inet_sock inet;
u32 conn_id;
u32 peer_conn_id;
};
static DEFINE_RWLOCK(l2tp_ip_lock);
static struct hlist_head l2tp_ip_table;
static struct hlist_head l2tp_ip_bind_table;
static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk)
{
return (struct l2tp_ip_sock *)sk;
}
static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr,
__be32 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 08:06:00 +07:00
sk_for_each_bound(sk, &l2tp_ip_bind_table) {
const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk);
const struct inet_sock *inet = inet_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 (inet->inet_rcv_saddr && laddr &&
inet->inet_rcv_saddr != laddr)
continue;
if (inet->inet_daddr && raddr && inet->inet_daddr != 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_ip_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 iphdr *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, 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);
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 = (struct iphdr *)skb_network_header(skb);
read_lock_bh(&l2tp_ip_lock);
sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb),
tunnel_id);
if (!sk) {
read_unlock_bh(&l2tp_ip_lock);
goto discard;
}
sock_hold(sk);
read_unlock_bh(&l2tp_ip_lock);
if (!xfrm4_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_ip_open(struct sock *sk)
{
/* Prevent autobind. We don't have ports. */
inet_sk(sk)->inet_num = IPPROTO_L2TP;
write_lock_bh(&l2tp_ip_lock);
sk_add_node(sk, &l2tp_ip_table);
write_unlock_bh(&l2tp_ip_lock);
return 0;
}
static void l2tp_ip_close(struct sock *sk, long timeout)
{
write_lock_bh(&l2tp_ip_lock);
hlist_del_init(&sk->sk_bind_node);
sk_del_node_init(sk);
write_unlock_bh(&l2tp_ip_lock);
sk_common_release(sk);
}
static void l2tp_ip_destroy_sock(struct sock *sk)
{
struct sk_buff *skb;
l2tp: fix races with tunnel socket close The tunnel socket tunnel->sock (struct sock) is accessed when preparing a new ppp session on a tunnel at pppol2tp_session_init. If the socket is closed by a thread while another is creating a new session, the threads race. In pppol2tp_connect, the tunnel object may be created if the pppol2tp socket is associated with the special session_id 0 and the tunnel socket is looked up using the provided fd. When handling this, pppol2tp_connect cannot sock_hold the tunnel socket to prevent it being destroyed during pppol2tp_connect since this may itself may race with the socket being destroyed. Doing sockfd_lookup in pppol2tp_connect isn't sufficient to prevent tunnel->sock going away either because a given tunnel socket fd may be reused between calls to pppol2tp_connect. Instead, have l2tp_tunnel_create sock_hold the tunnel socket before it does sockfd_put. This ensures that the tunnel's socket is always extant while the tunnel object exists. Hold a ref on the socket until the tunnel is destroyed and ensure that all tunnel destroy paths go through a common function (l2tp_tunnel_delete) since this will do the final sock_put to release the tunnel socket. Since the tunnel's socket is now guaranteed to exist if the tunnel exists, we no longer need to use sockfd_lookup via l2tp_sock_to_tunnel to derive the tunnel from the socket since this is always sk_user_data. Also, sessions no longer sock_hold the tunnel socket since sessions already hold a tunnel ref and the tunnel sock will not be freed until the tunnel is freed. Removing these sock_holds in l2tp_session_register avoids a possible sock leak in the pppol2tp_connect error path if l2tp_session_register succeeds but attaching a ppp channel fails. The pppol2tp_connect error path could have been fixed instead and have the sock ref dropped when the session is freed, but doing a sock_put of the tunnel socket when the session is freed would require a new session_free callback. It is simpler to just remove the sock_hold of the tunnel socket in l2tp_session_register, now that the tunnel socket lifetime is guaranteed. Finally, some init code in l2tp_tunnel_create is reordered to ensure that the new tunnel object's refcount is set and the tunnel socket ref is taken before the tunnel socket destructor callbacks are set. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 4360 Comm: syzbot_19c09769 Not tainted 4.16.0-rc2+ #34 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 RIP: 0010:pppol2tp_session_init+0x1d6/0x500 RSP: 0018:ffff88001377fb40 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: ffff88001636a940 RCX: ffffffff84836c1d RDX: 0000000000000045 RSI: 0000000055976744 RDI: 0000000000000228 RBP: ffff88001377fb60 R08: ffffffff84836bc8 R09: 0000000000000002 R10: ffff88001377fab8 R11: 0000000000000001 R12: 0000000000000000 R13: ffff88001636aac8 R14: ffff8800160f81c0 R15: 1ffff100026eff76 FS: 00007ffb3ea66700(0000) GS:ffff88001a400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020e77000 CR3: 0000000016261000 CR4: 00000000000006f0 Call Trace: pppol2tp_connect+0xd18/0x13c0 ? pppol2tp_session_create+0x170/0x170 ? __might_fault+0x115/0x1d0 ? lock_downgrade+0x860/0x860 ? __might_fault+0xe5/0x1d0 ? security_socket_connect+0x8e/0xc0 SYSC_connect+0x1b6/0x310 ? SYSC_bind+0x280/0x280 ? __do_page_fault+0x5d1/0xca0 ? up_read+0x1f/0x40 ? __do_page_fault+0x3c8/0xca0 SyS_connect+0x29/0x30 ? SyS_accept+0x40/0x40 do_syscall_64+0x1e0/0x730 ? trace_hardirqs_off_thunk+0x1a/0x1c entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x7ffb3e376259 RSP: 002b:00007ffeda4f6508 EFLAGS: 00000202 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000020e77012 RCX: 00007ffb3e376259 RDX: 000000000000002e RSI: 0000000020e77000 RDI: 0000000000000004 RBP: 00007ffeda4f6540 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000400b60 R13: 00007ffeda4f6660 R14: 0000000000000000 R15: 0000000000000000 Code: 80 3d b0 ff 06 02 00 0f 84 07 02 00 00 e8 13 d6 db fc 49 8d bc 24 28 02 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 f a 48 c1 ea 03 <80> 3c 02 00 0f 85 ed 02 00 00 4d 8b a4 24 28 02 00 00 e8 13 16 Fixes: 80d84ef3ff1dd ("l2tp: prevent l2tp_tunnel_delete racing with userspace close") Signed-off-by: James Chapman <jchapman@katalix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-24 00:45:45 +07:00
struct l2tp_tunnel *tunnel = sk->sk_user_data;
while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
kfree_skb(skb);
l2tp: fix races with tunnel socket close The tunnel socket tunnel->sock (struct sock) is accessed when preparing a new ppp session on a tunnel at pppol2tp_session_init. If the socket is closed by a thread while another is creating a new session, the threads race. In pppol2tp_connect, the tunnel object may be created if the pppol2tp socket is associated with the special session_id 0 and the tunnel socket is looked up using the provided fd. When handling this, pppol2tp_connect cannot sock_hold the tunnel socket to prevent it being destroyed during pppol2tp_connect since this may itself may race with the socket being destroyed. Doing sockfd_lookup in pppol2tp_connect isn't sufficient to prevent tunnel->sock going away either because a given tunnel socket fd may be reused between calls to pppol2tp_connect. Instead, have l2tp_tunnel_create sock_hold the tunnel socket before it does sockfd_put. This ensures that the tunnel's socket is always extant while the tunnel object exists. Hold a ref on the socket until the tunnel is destroyed and ensure that all tunnel destroy paths go through a common function (l2tp_tunnel_delete) since this will do the final sock_put to release the tunnel socket. Since the tunnel's socket is now guaranteed to exist if the tunnel exists, we no longer need to use sockfd_lookup via l2tp_sock_to_tunnel to derive the tunnel from the socket since this is always sk_user_data. Also, sessions no longer sock_hold the tunnel socket since sessions already hold a tunnel ref and the tunnel sock will not be freed until the tunnel is freed. Removing these sock_holds in l2tp_session_register avoids a possible sock leak in the pppol2tp_connect error path if l2tp_session_register succeeds but attaching a ppp channel fails. The pppol2tp_connect error path could have been fixed instead and have the sock ref dropped when the session is freed, but doing a sock_put of the tunnel socket when the session is freed would require a new session_free callback. It is simpler to just remove the sock_hold of the tunnel socket in l2tp_session_register, now that the tunnel socket lifetime is guaranteed. Finally, some init code in l2tp_tunnel_create is reordered to ensure that the new tunnel object's refcount is set and the tunnel socket ref is taken before the tunnel socket destructor callbacks are set. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 4360 Comm: syzbot_19c09769 Not tainted 4.16.0-rc2+ #34 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 RIP: 0010:pppol2tp_session_init+0x1d6/0x500 RSP: 0018:ffff88001377fb40 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: ffff88001636a940 RCX: ffffffff84836c1d RDX: 0000000000000045 RSI: 0000000055976744 RDI: 0000000000000228 RBP: ffff88001377fb60 R08: ffffffff84836bc8 R09: 0000000000000002 R10: ffff88001377fab8 R11: 0000000000000001 R12: 0000000000000000 R13: ffff88001636aac8 R14: ffff8800160f81c0 R15: 1ffff100026eff76 FS: 00007ffb3ea66700(0000) GS:ffff88001a400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020e77000 CR3: 0000000016261000 CR4: 00000000000006f0 Call Trace: pppol2tp_connect+0xd18/0x13c0 ? pppol2tp_session_create+0x170/0x170 ? __might_fault+0x115/0x1d0 ? lock_downgrade+0x860/0x860 ? __might_fault+0xe5/0x1d0 ? security_socket_connect+0x8e/0xc0 SYSC_connect+0x1b6/0x310 ? SYSC_bind+0x280/0x280 ? __do_page_fault+0x5d1/0xca0 ? up_read+0x1f/0x40 ? __do_page_fault+0x3c8/0xca0 SyS_connect+0x29/0x30 ? SyS_accept+0x40/0x40 do_syscall_64+0x1e0/0x730 ? trace_hardirqs_off_thunk+0x1a/0x1c entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x7ffb3e376259 RSP: 002b:00007ffeda4f6508 EFLAGS: 00000202 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000020e77012 RCX: 00007ffb3e376259 RDX: 000000000000002e RSI: 0000000020e77000 RDI: 0000000000000004 RBP: 00007ffeda4f6540 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000400b60 R13: 00007ffeda4f6660 R14: 0000000000000000 R15: 0000000000000000 Code: 80 3d b0 ff 06 02 00 0f 84 07 02 00 00 e8 13 d6 db fc 49 8d bc 24 28 02 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 f a 48 c1 ea 03 <80> 3c 02 00 0f 85 ed 02 00 00 4d 8b a4 24 28 02 00 00 e8 13 16 Fixes: 80d84ef3ff1dd ("l2tp: prevent l2tp_tunnel_delete racing with userspace close") Signed-off-by: James Chapman <jchapman@katalix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-24 00:45:45 +07:00
if (tunnel)
l2tp_tunnel_delete(tunnel);
}
static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *) uaddr;
struct net *net = sock_net(sk);
int ret;
int chk_addr_ret;
if (addr_len < sizeof(struct sockaddr_l2tpip))
return -EINVAL;
if (addr->l2tp_family != AF_INET)
return -EINVAL;
lock_sock(sk);
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 19:09:46 +07:00
ret = -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 04:13:00 +07:00
if (!sock_flag(sk, SOCK_ZAPPED))
goto out;
if (sk->sk_state != TCP_CLOSE)
goto out;
chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr);
ret = -EADDRNOTAVAIL;
if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
goto out;
if (addr->l2tp_addr.s_addr)
inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr;
if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
inet->inet_saddr = 0; /* Use device */
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 19:09:46 +07:00
write_lock_bh(&l2tp_ip_lock);
if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 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 19:09:46 +07:00
sk->sk_bound_dev_if, addr->l2tp_conn_id)) {
write_unlock_bh(&l2tp_ip_lock);
ret = -EADDRINUSE;
goto out;
}
sk_dst_reset(sk);
l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id;
sk_add_bind_node(sk, &l2tp_ip_bind_table);
sk_del_node_init(sk);
write_unlock_bh(&l2tp_ip_lock);
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 19:09:46 +07:00
ret = 0;
sock_reset_flag(sk, SOCK_ZAPPED);
out:
release_sock(sk);
return ret;
}
static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr;
int rc;
if (addr_len < sizeof(*lsa))
return -EINVAL;
if (ipv4_is_multicast(lsa->l2tp_addr.s_addr))
return -EINVAL;
lock_sock(sk);
/* Must bind first - autobinding does not work */
if (sock_flag(sk, SOCK_ZAPPED)) {
rc = -EINVAL;
goto out_sk;
}
rc = __ip4_datagram_connect(sk, uaddr, addr_len);
if (rc < 0)
goto out_sk;
l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
write_lock_bh(&l2tp_ip_lock);
hlist_del_init(&sk->sk_bind_node);
sk_add_bind_node(sk, &l2tp_ip_bind_table);
write_unlock_bh(&l2tp_ip_lock);
out_sk:
release_sock(sk);
return rc;
}
static int l2tp_ip_disconnect(struct sock *sk, int flags)
{
if (sock_flag(sk, SOCK_ZAPPED))
return 0;
return __udp_disconnect(sk, flags);
}
static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 02:00:20 +07:00
int peer)
{
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk);
struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr;
memset(lsa, 0, sizeof(*lsa));
lsa->l2tp_family = AF_INET;
if (peer) {
if (!inet->inet_dport)
return -ENOTCONN;
lsa->l2tp_conn_id = lsk->peer_conn_id;
lsa->l2tp_addr.s_addr = inet->inet_daddr;
} else {
__be32 addr = inet->inet_rcv_saddr;
if (!addr)
addr = inet->inet_saddr;
lsa->l2tp_conn_id = lsk->conn_id;
lsa->l2tp_addr.s_addr = addr;
}
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 02:00:20 +07:00
return sizeof(*lsa);
}
static int l2tp_ip_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 0;
}
/* Userspace will call sendmsg() on the tunnel socket to send L2TP
* control frames.
*/
static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct sk_buff *skb;
int rc;
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = NULL;
struct flowi4 *fl4;
int connected = 0;
__be32 daddr;
lock_sock(sk);
rc = -ENOTCONN;
if (sock_flag(sk, SOCK_DEAD))
goto out;
/* Get and verify the address. */
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name);
rc = -EINVAL;
if (msg->msg_namelen < sizeof(*lip))
goto out;
if (lip->l2tp_family != AF_INET) {
rc = -EAFNOSUPPORT;
if (lip->l2tp_family != AF_UNSPEC)
goto out;
}
daddr = lip->l2tp_addr.s_addr;
} else {
rc = -EDESTADDRREQ;
if (sk->sk_state != TCP_ESTABLISHED)
goto out;
daddr = inet->inet_daddr;
connected = 1;
}
/* Allocate a socket buffer */
rc = -ENOMEM;
skb = sock_wmalloc(sk, 2 + NET_SKB_PAD + sizeof(struct iphdr) +
4 + len, 0, GFP_KERNEL);
if (!skb)
goto error;
/* Reserve space for headers, putting IP header on 4-byte boundary. */
skb_reserve(skb, 2 + NET_SKB_PAD);
skb_reset_network_header(skb);
skb_reserve(skb, sizeof(struct iphdr));
skb_reset_transport_header(skb);
/* Insert 0 session_id */
*((__be32 *) skb_put(skb, 4)) = 0;
/* Copy user data into skb */
rc = memcpy_from_msg(skb_put(skb, len), msg, len);
if (rc < 0) {
kfree_skb(skb);
goto error;
}
fl4 = &inet->cork.fl.u.ip4;
if (connected)
rt = (struct rtable *) __sk_dst_check(sk, 0);
rcu_read_lock();
if (rt == NULL) {
const struct ip_options_rcu *inet_opt;
inet_opt = rcu_dereference(inet->inet_opt);
/* Use correct destination address if we have options. */
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
/* If this fails, retransmit mechanism of transport layer will
* keep trying until route appears or the connection times
* itself out.
*/
rt = ip_route_output_ports(sock_net(sk), fl4, sk,
daddr, inet->inet_saddr,
inet->inet_dport, inet->inet_sport,
sk->sk_protocol, RT_CONN_FLAGS(sk),
sk->sk_bound_dev_if);
if (IS_ERR(rt))
goto no_route;
if (connected) {
sk_setup_caps(sk, &rt->dst);
} else {
skb_dst_set(skb, &rt->dst);
goto xmit;
}
}
/* We dont need to clone dst here, it is guaranteed to not disappear.
* __dev_xmit_skb() might force a refcount if needed.
*/
skb_dst_set_noref(skb, &rt->dst);
xmit:
/* Queue the packet to IP for output */
rc = ip_queue_xmit(sk, skb, &inet->cork.fl);
rcu_read_unlock();
error:
if (rc >= 0)
rc = len;
out:
release_sock(sk);
return rc;
no_route:
rcu_read_unlock();
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
rc = -EHOSTUNREACH;
goto out;
}
static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg,
size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *inet = inet_sk(sk);
size_t copied = 0;
int err = -EOPNOTSUPP;
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct sk_buff *skb;
if (flags & MSG_OOB)
goto out;
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 (sin) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
if (flags & MSG_TRUNC)
copied = skb->len;
done:
skb_free_datagram(sk, skb);
out:
return err ? err : copied;
}
int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
struct sk_buff *skb;
int amount;
switch (cmd) {
case SIOCOUTQ:
amount = sk_wmem_alloc_get(sk);
break;
case SIOCINQ:
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
amount = skb ? skb->len : 0;
spin_unlock_bh(&sk->sk_receive_queue.lock);
break;
default:
return -ENOIOCTLCMD;
}
return put_user(amount, (int __user *)arg);
}
EXPORT_SYMBOL(l2tp_ioctl);
static struct proto l2tp_ip_prot = {
.name = "L2TP/IP",
.owner = THIS_MODULE,
.init = l2tp_ip_open,
.close = l2tp_ip_close,
.bind = l2tp_ip_bind,
.connect = l2tp_ip_connect,
.disconnect = l2tp_ip_disconnect,
.ioctl = l2tp_ioctl,
.destroy = l2tp_ip_destroy_sock,
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
.sendmsg = l2tp_ip_sendmsg,
.recvmsg = l2tp_ip_recvmsg,
.backlog_rcv = l2tp_ip_backlog_recv,
.hash = inet_hash,
.unhash = inet_unhash,
.obj_size = sizeof(struct l2tp_ip_sock),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
#endif
};
static const struct proto_ops l2tp_ip_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.release = inet_release,
.bind = inet_bind,
.connect = inet_dgram_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip_getname,
.poll = datagram_poll,
.ioctl = inet_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_ip_protosw = {
.type = SOCK_DGRAM,
.protocol = IPPROTO_L2TP,
.prot = &l2tp_ip_prot,
.ops = &l2tp_ip_ops,
};
static struct net_protocol l2tp_ip_protocol __read_mostly = {
.handler = l2tp_ip_recv,
.netns_ok = 1,
};
static int __init l2tp_ip_init(void)
{
int err;
pr_info("L2TP IP encapsulation support (L2TPv3)\n");
err = proto_register(&l2tp_ip_prot, 1);
if (err != 0)
goto out;
err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP);
if (err)
goto out1;
inet_register_protosw(&l2tp_ip_protosw);
return 0;
out1:
proto_unregister(&l2tp_ip_prot);
out:
return err;
}
static void __exit l2tp_ip_exit(void)
{
inet_unregister_protosw(&l2tp_ip_protosw);
inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP);
proto_unregister(&l2tp_ip_prot);
}
module_init(l2tp_ip_init);
module_exit(l2tp_ip_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
MODULE_DESCRIPTION("L2TP over IP");
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_INET, 2, IPPROTO_L2TP);
MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP);