On Fri, Aug 14, 2015 at 07:11:27PM -0700, Dan Williams wrote:
> On Fri, Aug 14, 2015 at 3:33 PM, Dan Williams <dan.j.williams@intel.com> wrote:
> > On Fri, Aug 14, 2015 at 3:06 PM, Jerome Glisse <j.glisse@gmail.com> wrote:
> >> On Fri, Aug 14, 2015 at 02:52:15PM -0700, Dan Williams wrote:
> >>> On Fri, Aug 14, 2015 at 2:37 PM, Jerome Glisse <j.glisse@gmail.com> wrote:
> >>> > On Wed, Aug 12, 2015 at 11:50:05PM -0400, Dan Williams wrote:
> > [..]
> >>> > What is the rational for not updating max_pfn, max_low_pfn, ... ?
> >>> >
> >>>
> >>> The idea is that this memory is not meant to be available to the page
> >>> allocator and should not count as new memory capacity.  We're only
> >>> hotplugging it to get struct page coverage.
> >>
> >> But this sounds bogus to me to rely on max_pfn to stay smaller than
> >> first_dev_pfn.  For instance you might plug a device that register
> >> dev memory and then some regular memory might be hotplug, effectively
> >> updating max_pfn to a value bigger than first_dev_pfn.
> >>
> >
> > True.
> >
> >> Also i do not think that the buddy allocator use max_pfn or max_low_pfn
> >> to consider page/zone for allocation or not.
> >
> > Yes, I took it out with no effects.  I'll investigate further whether
> > we should be touching those variables or not for this new usage.
> 
> Although it does not offer perfect protection if device memory is at a
> physically lower address than RAM, skipping the update of these
> variables does seem to be what we want.  For example /dev/mem would
> fail to allow write access to persistent memory if it fails a
> valid_phys_addr_range() check.  Since /dev/mem does not know how to
> write to PMEM in a reliably persistent way, it should not treat a
> PMEM-pfn like RAM.

So i attach is a patch that should keep ZONE_DEVICE out of consideration
for the buddy allocator. You might also want to keep page reserved and not
free inside the zone, you could replace the generic_online_page() using
set_online_page_callback() while hotpluging device memory.

Regarding /dev/mem i would not worry about highmem, as /dev/mem is already
broken in respect to memory hole that might exist (at least that is my
understanding). Alternatively if you really care about /dev/mem you could
add an arch valid_phys_addr_range() that could check valid zone.

Cheers,
Jérôme