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

[Su Hui <suhui@nfschina.com>]

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