[PATCH] evh_bytechan: fix out of bounds accesses

[Laurentiu Tudor]

On 21.02.2020 01:57, Stephen Rothwell wrote:
> Hi all,
> 
> 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:
>>>> Hi Timur,
>>>>
>>>> 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>

---
Best Regards, Laurentiu