Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1538861

Re: [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for un-addressable device memory

Show all headers | View raw

> On 12/08/2016 08:39 AM, Jerome Glisse wrote:
> >> On 12/08/2016 08:39 AM, Jérôme Glisse wrote:
> >>> > > Architecture that wish to support un-addressable device memory should
> >>> > > make
> >>> > > sure to never populate the kernel linar mapping for the physical
> >>> > > range.
> >> > 
> >> > Does the platform somehow provide a range of physical addresses for this
> >> > unaddressable area?  How do we know no memory will be hot-added in a
> >> > range we're using for unaddressable device memory, for instance?
> > That's what one of the big issue. No platform does not reserve any range so
> > there is a possibility that some memory get hotpluged and assign this
> > range.
> > 
> > I pushed the range decision to higher level (ie it is the device driver
> > that
> > pick one) so right now for device driver using HMM (NVidia close driver as
> > we don't have nouveau ready for that yet) it goes from the highest physical
> > address and scan down until finding an empty range big enough.
> 
> I don't think you should be stealing physical address space for things
> that don't and can't have physical addresses.  Delegating this to
> individual device drivers and hoping that they all get it right seems
> like a recipe for disaster.

Well i expected device driver to use hmm_devmem_add() which does not take
physical address but use the above logic to pick one.

> 
> Maybe worth adding to the changelog:
> 
> 	This feature potentially breaks memory hotplug unless every
> 	driver using it magically predicts the future addresses of
> 	where memory will be hotplugged.

I will add debug printk to memory hotplug in case it fails because of some
un-addressable resource. If you really dislike memory hotplug being broken
then i can go down the way of allowing to hotplug memory above the max
physical memory limit. This require more changes but i believe this is
doable for some of the memory model (sparsemem and sparsemem extreme).

> 
> BTW, how many more of these "big issues" does this set have?  I didn't
> see any mention of this in the changelogs.
 
I am not sure what to say here. If you don't use HMM ie no device that
hotplug it. Then there is no chance of having issue. If you have a device
that use it then someone might try to do something stupid (try to kmap
and access such un-addressable page for instance). So i am not sure where
to draw the line.

Cheers,
Jérôme

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[HMM v14 00/16] HMM (Heterogeneous Memory Management) v14 Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:40 +0100
  [HMM v14 12/16] mm/hmm/migrate: add new boolean copy flag to migratepage() callback Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:40 +0100
  [HMM v14 01/16] mm/free_hot_cold_page: catch ZONE_DEVICE pages Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 06/16] mm/ZONE_DEVICE/x86: add support for un-addressable device memory Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 03/16] mm/ZONE_DEVICE/devmem_pages_remove: allow early removal of device memory Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 13/16] mm/hmm/migrate: new memory migration helper for use with device memory v2 Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 07/16] mm/hmm: heterogeneous memory management (HMM for short) Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for un-addressable device memory Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
    Re: [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for  un-addressable device memory Dave Hansen <dave.hansen@intel.com> - 2016-12-08 17:30 +0100
      Re: [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for  un-addressable device memory Jerome Glisse <jglisse@redhat.com> - 2016-12-08 17:50 +0100
        Re: [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for  un-addressable device memory Dave Hansen <dave.hansen@intel.com> - 2016-12-08 21:10 +0100
          Re: [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for  un-addressable device memory Jerome Glisse <jglisse@redhat.com> - 2016-12-08 21:40 +0100
  [HMM v14 02/16] mm/memory/hotplug: convert device bool to int to allow for more flags v2 Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 16/16] mm/hmm/devmem: dummy HMM device as an helper for ZONE_DEVICE memory Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 04/16] mm/ZONE_DEVICE/free-page: callback when page is freed Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 15/16] mm/hmm/devmem: device driver helper to hotplug ZONE_DEVICE memory Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 10/16] mm/hmm/mirror: device page fault handler Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 08/16] mm/hmm/mirror: mirror process address space on device with HMM helpers Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 14/16] mm/hmm/migrate: optimize page map once in vma being migrated Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100
  [HMM v14 09/16] mm/hmm/mirror: helper to snapshot CPU page table Jérôme Glisse <jglisse@redhat.com> - 2016-12-08 16:50 +0100

csiph-web