[PATCH] smb: client: fix possible double free in smb2_set_ea()

[PATCH] smb: client: fix possible double free in smb2_set_ea()

[Su Hui]

Clang static checker(scan-build) warning：
fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
 1304 |         kfree(ea);
      |         ^~~~~~~~~

There is a double free in such case:
'ea is initialized to NULL' -> 'first successful memory allocation for
ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
-> 'goto replay_again' -> 'second goto sea_exit before allocate memory
for ea' -> 'second memory release for ea resulted in double free'.

Assign NULL value to 'ea' after 'kfree(ea)', it can fix this double free
problem.

Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
Signed-off-by: Su Hui <suhui@nfschina.com>
---
 fs/smb/client/smb2ops.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 6b385fce3f2a..5b42b352b703 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1302,6 +1302,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 
  sea_exit:
 	kfree(ea);
+	ea = NULL;
 	SMB2_open_free(&rqst[0]);
 	SMB2_set_info_free(&rqst[1]);
 	SMB2_close_free(&rqst[2]);
-- 
2.30.2

Re: [PATCH] smb: client: fix possible double free in smb2_set_ea()

[Dan Carpenter]

On Mon, Oct 14, 2024 at 07:34:17PM +0800, Su Hui wrote:
> Clang static checker(scan-build) warning：
> fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
>  1304 |         kfree(ea);
>       |         ^~~~~~~~~
> 
> There is a double free in such case:
> 'ea is initialized to NULL' -> 'first successful memory allocation for
> ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
> -> 'goto replay_again' -> 'second goto sea_exit before allocate memory
> for ea' -> 'second memory release for ea resulted in double free'.
> 
> Assign NULL value to 'ea' after 'kfree(ea)', it can fix this double free
> problem.
> 
> Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
> Signed-off-by: Su Hui <suhui@nfschina.com>
> ---
>  fs/smb/client/smb2ops.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
> index 6b385fce3f2a..5b42b352b703 100644
> --- a/fs/smb/client/smb2ops.c
> +++ b/fs/smb/client/smb2ops.c
> @@ -1302,6 +1302,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
>  
>   sea_exit:
>  	kfree(ea);
> +	ea = NULL;

That's very clever.  But I think that it would be better to do the "ea = NULL"
near to the replay_again label.  There are some lines where we re-initialize
resp_buftype[], utf16_path and vars etc.

	ea = NULL;
	resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER;

regards,
dan carpenter

Re: [PATCH] smb: client: fix possible double free in smb2_set_ea()

[Su Hui]

On 2024/10/14 20:53, Dan Carpenter wrote:

> On Mon, Oct 14, 2024 at 07:34:17PM +0800, Su Hui wrote:
>> Clang static checker(scan-build) warning：
>> fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
>>   1304 |         kfree(ea);
>>        |         ^~~~~~~~~
>>
>> There is a double free in such case:
>> 'ea is initialized to NULL' -> 'first successful memory allocation for
>> ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
>> -> 'goto replay_again' -> 'second goto sea_exit before allocate memory
>> for ea' -> 'second memory release for ea resulted in double free'.
>>
>> Assign NULL value to 'ea' after 'kfree(ea)', it can fix this double free
>> problem.
>>
>> Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
>> Signed-off-by: Su Hui <suhui@nfschina.com>
>> ---
>>   fs/smb/client/smb2ops.c | 1 +
>>   1 file changed, 1 insertion(+)
>>
>> diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
>> index 6b385fce3f2a..5b42b352b703 100644
>> --- a/fs/smb/client/smb2ops.c
>> +++ b/fs/smb/client/smb2ops.c
>> @@ -1302,6 +1302,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
>>   
>>    sea_exit:
>>   	kfree(ea);
>> +	ea = NULL;
> That's very clever.  But I think that it would be better to do the "ea = NULL"
> near to the replay_again label.  There are some lines where we re-initialize
> resp_buftype[], utf16_path and vars etc.
>
> 	ea = NULL;
> 	resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER;

Yes, it's better! Thanks for your suggestions. I will send v2 patch soon.

Su Hui