Re: [RFC PATCH 2/2] mm,drm/ttm: Use VM_PFNMAP for TTM vmas

[Thomas Hellström (Intel)]

On 3/23/21 3:04 PM, Jason Gunthorpe wrote:
> On Tue, Mar 23, 2021 at 12:47:24PM +0100, Daniel Vetter wrote:
>
> > > +static inline bool is_cow_mapping(vm_flags_t flags)
> > Bit a bikeshed, but I wonder whether the public interface shouldn't be
> > vma_is_cow_mapping. Or whether this shouldn't be rejected somewhere else,
> > since at least in drivers/gpu we have tons of cases that don't check for
> > this and get it all kinds of wrong I think.
> >
> > remap_pfn_range handles this for many cases, but by far not for all.
> >
> > Anyway patch itself lgtm:
> >
> > Reviewed-by: Daniel Vetter <daniel.vetter@xxxxxxxx>
> I would like it if io_remap_pfn_range() did not allow shared mappings
> at all.

You mean private mappings?

> IIRC it doesn't work anyway, the kernel can't reliably copy from IO
> pages eg the "_copy_from_user_inatomic()" under cow_user_page() will
> not work on s390 that requires all IO memory be accessed with special
> instructions.
>
> Unfortunately I have no idea what the long ago special case of
> allowing COW'd IO mappings is. :\

Me neither, but at some point it must have been important enough to 
introduce VM_MIXEDMAP...

/Thomas


> Jason