# Re: \[PATCH\] evh\_bytechan: fix out of bounds accesses - From: Laurentiu Tudor \ - Date: 2020-02-25 09:56:48 - List: linuxppc-dev - Page: https://ratatoskr.run/linuxppc-dev/2020/02/9514169 - Thread: https://ratatoskr.run/linuxppc-dev/2020/01/9513607/t.md ```text On 21.02.2020 01:57, Stephen Rothwell wrote: > Hi all, > > On Thu, 16 Jan 2020 11:37:14 +1100 Stephen Rothwell [ref] wrote: >> >> On Wed, 15 Jan 2020 14:01:35 -0600 Scott Wood [ref] 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 [ref] 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 --- Best Regards, Laurentiu ```