Re: [PATCH 06/18] x86, barrier: stop speculation for failed access_ok

[Dan Williams]

On Fri, Jan 5, 2018 at 7:09 PM, Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Fri, Jan 5, 2018 at 6:52 PM, Linus Torvalds
> <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
>>
>> The fact is, we have to stop speculating when access_ok() does *not*
>> fail - because that's when we'll actually do the access. And it's that
>> access that needs to be non-speculative.
>
> I also suspect we should probably do this entirely differently.
>
> Maybe the whole lfence can be part of uaccess_begin() instead (ie
> currently 'stac()'). That would fit the existing structure better, I
> think. And it would avoid any confusion about the whole "when to stop
> speculation".

I assume if we put this in uaccess_begin() we also need audit for
paths that use access_ok but don't do on to call uaccess_begin()? A
quick glance shows a few places where we are open coding the stac().
Perhaps land the lfence in stac() directly?