This is a fix for bug, introduced in 3.4 kernel by commit
1ab5ecb90cb6a3df1476e052f76a6e8f6511cb3d, which, among other things, replaced
simple sock_put() by sk_release_kernel(). Below is sequence, which leads to
oops for non-persistent devices:
tun_chr_close()
tun_detach() <== tun->socket.file = NULL
tun_free_netdev()
sk_release_sock()
sock_release(sock->file == NULL)
iput(SOCK_INODE(sock)) <== dereference on NULL pointer
This patch just removes zeroing of socket's file from __tun_detach().
sock_release() will do this.
Cc: [email protected]
Reported-by: Ruan Zhijie <[email protected]>
Tested-by: Ruan Zhijie <[email protected]>
Acked-by: Al Viro <[email protected]>
Acked-by: Eric Dumazet <[email protected]>
Acked-by: Yuchung Cheng <[email protected]>
Signed-off-by: Stanislav Kinsbursky <[email protected]>
---
drivers/net/tun.c | 1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 987aeef..c1639f3 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -185,7 +185,6 @@ static void __tun_detach(struct tun_struct *tun)
netif_tx_lock_bh(tun->dev);
netif_carrier_off(tun->dev);
tun->tfile = NULL;
- tun->socket.file = NULL;
netif_tx_unlock_bh(tun->dev);
/* Drop read queue */
From: Stanislav Kinsbursky <[email protected]>
Date: Thu, 09 Aug 2012 16:50:40 +0400
> This is a fix for bug, introduced in 3.4 kernel by commit
> 1ab5ecb90cb6a3df1476e052f76a6e8f6511cb3d, which, among other things, replaced
> simple sock_put() by sk_release_kernel(). Below is sequence, which leads to
> oops for non-persistent devices:
>
> tun_chr_close()
> tun_detach() <== tun->socket.file = NULL
> tun_free_netdev()
> sk_release_sock()
> sock_release(sock->file == NULL)
> iput(SOCK_INODE(sock)) <== dereference on NULL pointer
>
> This patch just removes zeroing of socket's file from __tun_detach().
> sock_release() will do this.
>
> Cc: [email protected]
> Reported-by: Ruan Zhijie <[email protected]>
> Tested-by: Ruan Zhijie <[email protected]>
> Acked-by: Al Viro <[email protected]>
> Acked-by: Eric Dumazet <[email protected]>
> Acked-by: Yuchung Cheng <[email protected]>
> Signed-off-by: Stanislav Kinsbursky <[email protected]>
Applied, thanks.
10.08.2012 03:16, David Miller пишет:
> From: Stanislav Kinsbursky <[email protected]>
> Date: Thu, 09 Aug 2012 16:50:40 +0400
>
>> This is a fix for bug, introduced in 3.4 kernel by commit
>> 1ab5ecb90cb6a3df1476e052f76a6e8f6511cb3d, which, among other things, replaced
>> simple sock_put() by sk_release_kernel(). Below is sequence, which leads to
>> oops for non-persistent devices:
>>
>> tun_chr_close()
>> tun_detach() <== tun->socket.file = NULL
>> tun_free_netdev()
>> sk_release_sock()
>> sock_release(sock->file == NULL)
>> iput(SOCK_INODE(sock)) <== dereference on NULL pointer
>>
>> This patch just removes zeroing of socket's file from __tun_detach().
>> sock_release() will do this.
>>
>> Cc: [email protected]
>> Reported-by: Ruan Zhijie <[email protected]>
>> Tested-by: Ruan Zhijie <[email protected]>
>> Acked-by: Al Viro <[email protected]>
>> Acked-by: Eric Dumazet <[email protected]>
>> Acked-by: Yuchung Cheng <[email protected]>
>> Signed-off-by: Stanislav Kinsbursky <[email protected]>
>
> Applied, thanks.
>
Hi, David.
I found out, that this commit: b09e786bd1dd66418b69348cb110f3a64764626a
was previous attempt to fix the problem.
I believe this commit have to be dropped.
--
Best regards,
Stanislav Kinsbursky
On Tue, Aug 21, 2012 at 12:04 PM, Stanislav Kinsbursky
<[email protected]> wrote:
> 10.08.2012 03:16, David Miller пишет:
>
>> From: Stanislav Kinsbursky <[email protected]>
>> Date: Thu, 09 Aug 2012 16:50:40 +0400
>>
>>> This is a fix for bug, introduced in 3.4 kernel by commit
>>> 1ab5ecb90cb6a3df1476e052f76a6e8f6511cb3d, which, among other things,
>>> replaced
>>> simple sock_put() by sk_release_kernel(). Below is sequence, which leads
>>> to
>>> oops for non-persistent devices:
>>>
>>> tun_chr_close()
>>> tun_detach() <== tun->socket.file = NULL
>>> tun_free_netdev()
>>> sk_release_sock()
>>> sock_release(sock->file == NULL)
>>> iput(SOCK_INODE(sock)) <== dereference on NULL pointer
>>>
>>> This patch just removes zeroing of socket's file from __tun_detach().
>>> sock_release() will do this.
>>>
>>> Cc: [email protected]
>>> Reported-by: Ruan Zhijie <[email protected]>
>>> Tested-by: Ruan Zhijie <[email protected]>
>>> Acked-by: Al Viro <[email protected]>
>>> Acked-by: Eric Dumazet <[email protected]>
>>> Acked-by: Yuchung Cheng <[email protected]>
>>> Signed-off-by: Stanislav Kinsbursky <[email protected]>
>>
>>
>> Applied, thanks.
>>
>
> Hi, David.
> I found out, that this commit: b09e786bd1dd66418b69348cb110f3a64764626a
> was previous attempt to fix the problem.
> I believe this commit have to be dropped.
Have you tried testing with that commit reverted? AFAICT from reading
the code, if you revert b09e786bd1dd66418b69348cb110f3a64764626a then
the sockets_in_use count becomes incorrect, because sock_release()
will be calling this_cpu_sub() for each tun socket teardown when there
was no corresponding this_cpu_add() for the tun socket (because the
tun socket is not allocated with sock_alloc()).
Can you sketch in more detail why that commit should be dropped?
neal
21.08.2012 21:18, Neal Cardwell пишет:
> On Tue, Aug 21, 2012 at 12:04 PM, Stanislav Kinsbursky
> <[email protected]> wrote:
>> 10.08.2012 03:16, David Miller пишет:
>>
>>> From: Stanislav Kinsbursky <[email protected]>
>>> Date: Thu, 09 Aug 2012 16:50:40 +0400
>>>
>>>> This is a fix for bug, introduced in 3.4 kernel by commit
>>>> 1ab5ecb90cb6a3df1476e052f76a6e8f6511cb3d, which, among other things,
>>>> replaced
>>>> simple sock_put() by sk_release_kernel(). Below is sequence, which leads
>>>> to
>>>> oops for non-persistent devices:
>>>>
>>>> tun_chr_close()
>>>> tun_detach() <== tun->socket.file = NULL
>>>> tun_free_netdev()
>>>> sk_release_sock()
>>>> sock_release(sock->file == NULL)
>>>> iput(SOCK_INODE(sock)) <== dereference on NULL pointer
>>>>
>>>> This patch just removes zeroing of socket's file from __tun_detach().
>>>> sock_release() will do this.
>>>>
>>>> Cc: [email protected]
>>>> Reported-by: Ruan Zhijie <[email protected]>
>>>> Tested-by: Ruan Zhijie <[email protected]>
>>>> Acked-by: Al Viro <[email protected]>
>>>> Acked-by: Eric Dumazet <[email protected]>
>>>> Acked-by: Yuchung Cheng <[email protected]>
>>>> Signed-off-by: Stanislav Kinsbursky <[email protected]>
>>>
>>>
>>> Applied, thanks.
>>>
>>
>> Hi, David.
>> I found out, that this commit: b09e786bd1dd66418b69348cb110f3a64764626a
>> was previous attempt to fix the problem.
>> I believe this commit have to be dropped.
>
> Have you tried testing with that commit reverted? AFAICT from reading
> the code, if you revert b09e786bd1dd66418b69348cb110f3a64764626a then
> the sockets_in_use count becomes incorrect, because sock_release()
> will be calling this_cpu_sub() for each tun socket teardown when there
> was no corresponding this_cpu_add() for the tun socket (because the
> tun socket is not allocated with sock_alloc()).
>
> Can you sketch in more detail why that commit should be dropped?
>
Yep, I've noticed, that first commit patch fixes two problems simultaneously.
Here are they:
1) Dereference of invalid SOCK_INODE()
2) sockets_in_use incorrect value.
But I believe, that introducing new SOCK_EXTERNALLY_ALLOCATED socket flag and
use it in generic code just to handle tun issues is overkill.
My patch solves first problem mush simpler, than mentioned commit.
About second problem...
What about this:
diff --git a/net/socket.c b/net/socket.c
index dfe5b66..dab462b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -526,8 +526,8 @@ void sock_release(struct socket *sock)
if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags))
return;
- this_cpu_sub(sockets_in_use, 1);
if (!sock->file) {
+ this_cpu_sub(sockets_in_use, 1);
iput(SOCK_INODE(sock));
return;
}
?
> neal
>
--
Best regards,
Stanislav Kinsbursky