Re: [PATCH v5 1/7] mce: fix set_mce_nospec to always unmap the whole page

[Dan Williams]

On Thu, Feb 3, 2022 at 5:42 AM Christoph Hellwig <hch@xxxxxxxxxxxxx> wrote:
>
> On Wed, Feb 02, 2022 at 11:07:37PM +0000, Jane Chu wrote:
> > On 2/2/2022 1:20 PM, Jane Chu wrote:
> > >> Wouldn't it make more sense to move these helpers out of line rather
> > >> than exporting _set_memory_present?
> > >
> > > Do you mean to move
> > >     return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
> > > into clear_mce_nospec() for the x86 arch and get rid of _set_memory_present?
> > > If so, sure I'll do that.
> >
> > Looks like I can't do that.  It's either exporting
> > _set_memory_present(), or exporting change_page_attr_set().  Perhaps the
> > former is more conventional?
>
> These helpers above means set_mce_nospec and clear_mce_nospec.  If they
> are moved to normal functions instead of inlines, there is no need to
> export the internals at all.

Agree, {set,clear}_mce_nospec() can just move to arch/x86/mm/pat/set_memory.c.