Re: [PATCH net-next v2 01/16] l2tp: update sk_user_data while holding sk_callback_lock

[Guillaume Nault]

On Mon, Feb 12, 2018 at 10:11:05AM +, James Chapman wrote:
> Since L2TP hooks on sockets opened by userspace using sk_user_data, we
> may race with other socket families that attempt to use the same
> socket.
> 
> This problem was discovered by syzbot using AF_KCM. KCM has since been
> modified to use only TCP sockets to avoid hitting this issue but we
> should prevent such races in L2TP anyway.
> 
> Fixes: c8fffcea0a079 ("l2tp: Refactor l2tp core driver to make use of the 
> common UDP tunnel function")
> Reported-by: syzbot+8865eaff7f9acd593...@syzkaller.appspotmail.com
> 
> Kernel BUG at net/l2tp/l2tp_ppp.c:176!
> invalid opcode:  [#1] SMP KASAN
> Dumping ftrace buffer:
>(ftrace buffer empty)
> Modules linked in:
> CPU: 1 PID: 3503 Comm: syzkaller938388 Not tainted 4.15.0-rc7+ #181
> Hardware name: Google Google Compute Engine/Google Compute Engine
> RIP: 0010:pppol2tp_sock_to_session net/l2tp/l2tp_ppp.c:176 [inline]
> RIP: 0010:pppol2tp_sendmsg+0x512/0x670 net/l2tp/l2tp_ppp.c:304
> RSP: 0018:8801d4887438 EFLAGS: 00010293
> RAX: 8801bfef2180 RBX: 8801bff88440 RCX: 84ffbca2
> RDX:  RSI: 8801d4887598 RDI: 8801bff88820
> RBP: 8801d48874a8 R08:  R09: 11003a910e17
> R10: 0003 R11: 0001 R12: 8801bfff9bc0
> R13:  R14: 8000 R15: 
> FS:  01194880() GS:8801db30() knlGS:
> CS:  0010 DS:  ES:  CR0: 80050033
> CR2: 20ea CR3: 0001bfecf001 CR4: 001606e0
> DR0:  DR1:  DR2: 
> DR3:  DR6: fffe0ff0 DR7: 0400
> Call Trace:
>  sock_sendmsg_nosec net/socket.c:628 [inline]
>  sock_sendmsg+0xca/0x110 net/socket.c:638
>  kernel_sendmsg+0x47/0x60 net/socket.c:646
>  sock_no_sendpage+0x1cc/0x280 net/core/sock.c:2581
>  kernel_sendpage+0xbf/0xe0 net/socket.c:3349
>  kcm_write_msgs+0x404/0x1b80 net/kcm/kcmsock.c:646
>  kcm_sendmsg+0x148d/0x22d0 net/kcm/kcmsock.c:1035
>  sock_sendmsg_nosec net/socket.c:628 [inline]
>  sock_sendmsg+0xca/0x110 net/socket.c:638
>  ___sys_sendmsg+0x767/0x8b0 net/socket.c:2018
>  __sys_sendmsg+0xe5/0x210 net/socket.c:2052
>  SYSC_sendmsg net/socket.c:2063 [inline]
>  SyS_sendmsg+0x2d/0x50 net/socket.c:2059
>  entry_SYSCALL_64_fastpath+0x23/0x9a
> RIP: 0033:0x440159
> RSP: 002b:7ffe74df8288 EFLAGS: 0217 ORIG_RAX: 002e
> RAX: ffda RBX:  RCX: 00440159
> RDX:  RSI: 201fcfc8 RDI: 0005
> RBP: 006ca018 R08:  R09: 
> R10:  R11: 0217 R12: 00401ac0
> R13: 00401b50 R14:  R15: 
> Code: c5 61 70 fc 48 8b 7d d0 e8 7c c2 5b fd 84 c0 74 0d e8 b3 61 70 fc 48 89 
> df e8 3b 49 2f ff 41 bd f7 ff ff ff eb 86 e8 9e 61 70 fc <0f> 0b 41 bd 95 ff 
> ff ff e9 74 ff ff ff e8 ec 32 a8 fc e9 77 fb
> RIP: pppol2tp_sock_to_session net/l2tp/l2tp_ppp.c:176 [inline] RSP: 
> 8801d4887438
> RIP: pppol2tp_sendmsg+0x512/0x670 net/l2tp/l2tp_ppp.c:304 RSP: 
> 8801d4887438
> ---
>  net/l2tp/l2tp_core.c | 21 ++---
>  net/l2tp/l2tp_ppp.c  |  8 ++--
>  2 files changed, 24 insertions(+), 5 deletions(-)
> 
> diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
> index 194a7483bb93..de7dce64173f 100644
> --- a/net/l2tp/l2tp_core.c
> +++ b/net/l2tp/l2tp_core.c
> @@ -1216,6 +1216,7 @@ static void l2tp_tunnel_destruct(struct sock *sk)
>  
>  
>   /* Disable udp encapsulation */
> + write_lock_bh(>sk_callback_lock);
>   switch (tunnel->encap) {
>   case L2TP_ENCAPTYPE_UDP:
>   /* No longer an encapsulation socket. See net/ipv4/udp.c */
> @@ -1229,7 +1230,8 @@ static void l2tp_tunnel_destruct(struct sock *sk)
>  
>   /* Remove hooks into tunnel socket */
>   sk->sk_destruct = tunnel->old_sk_destruct;
> - sk->sk_user_data = NULL;
> + rcu_assign_sk_user_data(sk, NULL);
> + write_unlock_bh(>sk_callback_lock);
>  
>   /* Remove the tunnel struct from the tunnel list */
>   pn = l2tp_pernet(tunnel->l2tp_net);
> @@ -1583,6 +1585,20 @@ int l2tp_tunnel_create(struct net *net, int fd, int 
> version, u32 tunnel_id, u32
>   }
>  #endif
>  
> + /* Assign socket sk_user_data. Must be done with
> +  * sk_callback_lock. Bail if sk_user_data is already assigned.
> +  */
> + write_lock_bh(>sk_callback_lock);
> + if (sk->sk_user_data) {
> + err = -EALREADY;
> + write_unlock_bh(>sk_callback_lock);
> + kfree(tunnel);
> + tunnel = NULL;
> + goto err;
> + }
> + rcu_assign_sk_user_data(sk, tunnel);
> + write_unlock_bh(>sk_callback_lock);
> +
I'd rather use this code only to replace the direct ->sk_user_data
assignment (in the 'else' branch). It looks strange to assign it here

Re: [PATCH net-next v2 01/16] l2tp: update sk_user_data while holding sk_callback_lock

[David Miller]

From: James Chapman 
Date: Mon, 12 Feb 2018 10:11:05 +

> Since L2TP hooks on sockets opened by userspace using sk_user_data, we
> may race with other socket families that attempt to use the same
> socket.
> 
> This problem was discovered by syzbot using AF_KCM. KCM has since been
> modified to use only TCP sockets to avoid hitting this issue but we
> should prevent such races in L2TP anyway.
> 
> Fixes: c8fffcea0a079 ("l2tp: Refactor l2tp core driver to make use of the 
> common UDP tunnel function")
> Reported-by: syzbot+8865eaff7f9acd593...@syzkaller.appspotmail.com

Yikes.  Where is your signoff James?

> Kernel BUG at net/l2tp/l2tp_ppp.c:176!
> invalid opcode:  [#1] SMP KASAN
> Dumping ftrace buffer:
>(ftrace buffer empty)

And this oops dump should be before the various
fixes/reported-by/signed-off-by tags.

Thanks.

[PATCH net-next v2 01/16] l2tp: update sk_user_data while holding sk_callback_lock

[James Chapman]

Since L2TP hooks on sockets opened by userspace using sk_user_data, we
may race with other socket families that attempt to use the same
socket.

This problem was discovered by syzbot using AF_KCM. KCM has since been
modified to use only TCP sockets to avoid hitting this issue but we
should prevent such races in L2TP anyway.

Fixes: c8fffcea0a079 ("l2tp: Refactor l2tp core driver to make use of the 
common UDP tunnel function")
Reported-by: syzbot+8865eaff7f9acd593...@syzkaller.appspotmail.com

Kernel BUG at net/l2tp/l2tp_ppp.c:176!
invalid opcode:  [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 3503 Comm: syzkaller938388 Not tainted 4.15.0-rc7+ #181
Hardware name: Google Google Compute Engine/Google Compute Engine
RIP: 0010:pppol2tp_sock_to_session net/l2tp/l2tp_ppp.c:176 [inline]
RIP: 0010:pppol2tp_sendmsg+0x512/0x670 net/l2tp/l2tp_ppp.c:304
RSP: 0018:8801d4887438 EFLAGS: 00010293
RAX: 8801bfef2180 RBX: 8801bff88440 RCX: 84ffbca2
RDX:  RSI: 8801d4887598 RDI: 8801bff88820
RBP: 8801d48874a8 R08:  R09: 11003a910e17
R10: 0003 R11: 0001 R12: 8801bfff9bc0
R13:  R14: 8000 R15: 
FS:  01194880() GS:8801db30() knlGS:
CS:  0010 DS:  ES:  CR0: 80050033
CR2: 20ea CR3: 0001bfecf001 CR4: 001606e0
DR0:  DR1:  DR2: 
DR3:  DR6: fffe0ff0 DR7: 0400
Call Trace:
 sock_sendmsg_nosec net/socket.c:628 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:638
 kernel_sendmsg+0x47/0x60 net/socket.c:646
 sock_no_sendpage+0x1cc/0x280 net/core/sock.c:2581
 kernel_sendpage+0xbf/0xe0 net/socket.c:3349
 kcm_write_msgs+0x404/0x1b80 net/kcm/kcmsock.c:646
 kcm_sendmsg+0x148d/0x22d0 net/kcm/kcmsock.c:1035
 sock_sendmsg_nosec net/socket.c:628 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:638
 ___sys_sendmsg+0x767/0x8b0 net/socket.c:2018
 __sys_sendmsg+0xe5/0x210 net/socket.c:2052
 SYSC_sendmsg net/socket.c:2063 [inline]
 SyS_sendmsg+0x2d/0x50 net/socket.c:2059
 entry_SYSCALL_64_fastpath+0x23/0x9a
RIP: 0033:0x440159
RSP: 002b:7ffe74df8288 EFLAGS: 0217 ORIG_RAX: 002e
RAX: ffda RBX:  RCX: 00440159
RDX:  RSI: 201fcfc8 RDI: 0005
RBP: 006ca018 R08:  R09: 
R10:  R11: 0217 R12: 00401ac0
R13: 00401b50 R14:  R15: 
Code: c5 61 70 fc 48 8b 7d d0 e8 7c c2 5b fd 84 c0 74 0d e8 b3 61 70 fc 48 89 
df e8 3b 49 2f ff 41 bd f7 ff ff ff eb 86 e8 9e 61 70 fc <0f> 0b 41 bd 95 ff ff 
ff e9 74 ff ff ff e8 ec 32 a8 fc e9 77 fb
RIP: pppol2tp_sock_to_session net/l2tp/l2tp_ppp.c:176 [inline] RSP: 
8801d4887438
RIP: pppol2tp_sendmsg+0x512/0x670 net/l2tp/l2tp_ppp.c:304 RSP: 8801d4887438
---
 net/l2tp/l2tp_core.c | 21 ++---
 net/l2tp/l2tp_ppp.c  |  8 ++--
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 194a7483bb93..de7dce64173f 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1216,6 +1216,7 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 
 
/* Disable udp encapsulation */
+   write_lock_bh(>sk_callback_lock);
switch (tunnel->encap) {
case L2TP_ENCAPTYPE_UDP:
/* No longer an encapsulation socket. See net/ipv4/udp.c */
@@ -1229,7 +1230,8 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 
/* Remove hooks into tunnel socket */
sk->sk_destruct = tunnel->old_sk_destruct;
-   sk->sk_user_data = NULL;
+   rcu_assign_sk_user_data(sk, NULL);
+   write_unlock_bh(>sk_callback_lock);
 
/* Remove the tunnel struct from the tunnel list */
pn = l2tp_pernet(tunnel->l2tp_net);
@@ -1583,6 +1585,20 @@ int l2tp_tunnel_create(struct net *net, int fd, int 
version, u32 tunnel_id, u32
}
 #endif
 
+   /* Assign socket sk_user_data. Must be done with
+* sk_callback_lock. Bail if sk_user_data is already assigned.
+*/
+   write_lock_bh(>sk_callback_lock);
+   if (sk->sk_user_data) {
+   err = -EALREADY;
+   write_unlock_bh(>sk_callback_lock);
+   kfree(tunnel);
+   tunnel = NULL;
+   goto err;
+   }
+   rcu_assign_sk_user_data(sk, tunnel);
+   write_unlock_bh(>sk_callback_lock);
+
/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
tunnel->encap = encap;
if (encap == L2TP_ENCAPTYPE_UDP) {
@@ -1594,8 +1610,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int 
version, u32 tunnel_id, u32
udp_cfg.encap_destroy = l2tp_udp_encap_destroy;
 
setup_udp_tunnel_sock(net, sock,