[PATCH] evh_bytechan: fix out of bounds accesses

Laurentiu Tudor laurentiu.tudor at nxp.com
Wed Feb 26 20:43:11 AEDT 2020



On 25.02.2020 22:56, Stephen Rothwell wrote:
> Hi Laurentiu,
> 
> On Tue, 25 Feb 2020 11:54:17 +0200 Laurentiu Tudor <laurentiu.tudor at nxp.com> wrote:
>>
>> On 21.02.2020 01:57, Stephen Rothwell wrote:
>>>
>>> On Thu, 16 Jan 2020 11:37:14 +1100 Stephen Rothwell <sfr at canb.auug.org.au> wrote:
>>>>
>>>> On Wed, 15 Jan 2020 14:01:35 -0600 Scott Wood <swood at redhat.com> wrote:
>>>>>
>>>>> On Thu, 2020-01-16 at 06:42 +1100, Stephen Rothwell wrote:
>>>>>>
>>>>>> On Wed, 15 Jan 2020 07:25:45 -0600 Timur Tabi <timur at kernel.org> wrote:
>>>>>>> On 1/14/20 12:31 AM, Stephen Rothwell wrote:
>>>>>>>> +/**
>>>>>>>> + * ev_byte_channel_send - send characters to a byte stream
>>>>>>>> + * @handle: byte stream handle
>>>>>>>> + * @count: (input) num of chars to send, (output) num chars sent
>>>>>>>> + * @bp: pointer to chars to send
>>>>>>>> + *
>>>>>>>> + * Returns 0 for success, or an error code.
>>>>>>>> + */
>>>>>>>> +static unsigned int ev_byte_channel_send(unsigned int handle,
>>>>>>>> +	unsigned int *count, const char *bp)
>>>>>>>
>>>>>>> Well, now you've moved this into the .c file and it is no longer
>>>>>>> available to other callers.  Anything wrong with keeping it in the .h
>>>>>>> file?
>>>>>>
>>>>>> There are currently no other callers - are there likely to be in the
>>>>>> future?  Even if there are, is it time critical enough that it needs to
>>>>>> be inlined everywhere?
>>>>>
>>>>> It's not performance critical and there aren't likely to be other users --
>>>>> just a matter of what's cleaner.  FWIW I'd rather see the original patch,
>>>>> that keeps the raw asm hcall stuff as simple wrappers in one place.
>>>>
>>>> And I don't mind either way :-)
>>>>
>>>> I just want to get rid of the warnings.
>>>
>>> Any progress with this?
>>
>> I think that the consensus was to pick up the original patch that is,
>> this one: https://patchwork.ozlabs.org/patch/1220186/
>>
>> I've tested it too, so please feel free to add a:
>>
>> Tested-by: Laurentiu Tudor <laurentiu.tudor at nxp.com>
> 
> So, whose tree should his go via?
> 

Maybe Scott or Michael can help us here. And while at it maybe, take a 
look at this patch [1] too.

[1] https://patchwork.ozlabs.org/patch/1227780/

---
Best Regards, Laurentiu


More information about the Linuxppc-dev mailing list