Re: [HMM 00/15] HMM (Heterogeneous Memory Management) v22

[Balbir Singh]

On Fri, Jun 2, 2017 at 8:38 AM, Jerome Glisse <jglisse@xxxxxxxxxx> wrote:
> On Thu, Jun 01, 2017 at 12:04:02PM +1000, Balbir Singh wrote:
>> On Thu, May 25, 2017 at 3:53 AM, Jerome Glisse <jglisse@xxxxxxxxxx> wrote:
>> > On Wed, May 24, 2017 at 11:55:12AM +1000, Balbir Singh wrote:
>> >> On Tue, May 23, 2017 at 2:51 AM, JÃrÃme Glisse <jglisse@xxxxxxxxxx> wrote:
>> >> > Patchset is on top of mmotm mmotm-2017-05-18, git branch:
>> >> >
>> >> > https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-v22
>> >> >
>> >> > Change since v21 is adding back special refcounting in put_page() to
>> >> > catch when a ZONE_DEVICE page is free (refcount going from 2 to 1
>> >> > unlike regular page where a refcount of 0 means the page is free).
>> >> > See patch 8 of this serie for this refcounting. I did not use static
>> >> > keys because it kind of scares me to do that for an inline function.
>> >> > If people strongly feel about this i can try to make static key works
>> >> > here. Kirill will most likely want to review this.
>> >> >
>> >> >
>> >> > Everything else is the same. Below is the long description of what HMM
>> >> > is about and why. At the end of this email i describe briefly each patch
>> >> > and suggest reviewers for each of them.
>> >> >
>> >> >
>> >> > Heterogeneous Memory Management (HMM) (description and justification)
>> >> >
>> >>
>> >> Thanks for the patches! These patches are very helpful. There are a
>> >> few additional things we would need on top of this (once HMM the base
>> >> is merged)
>> >>
>> >> 1. Support for other architectures, we'd like to make sure we can get
>> >> this working for powerpc for example. As a first step we have
>> >> ZONE_DEVICE enablement patches, but I think we need some additional
>> >> patches for iomem space searching and memory hotplug, IIRC
>> >> 2. HMM-CDM and physical address based migration bits. In a recent RFC
>> >> we decided to try and use the HMM CDM route as a route to implementing
>> >> coherent device memory as a starting point. It would be nice to have
>> >> those patches on top of these once these make it to mm -
>> >> https://lwn.net/Articles/720380/
>> >>
>> >
>> > I intend to post the updated HMM CDM patchset early next week. I am
>> > tie in couple internal backport but i should be able to resume work
>> > on that this week.
>> >
>>
>> Thanks, I am looking at the HMM CDM branch and trying to forward port
>> and see what the results look like on top of HMM-v23. Do we have a timeline
>> for the v23 merge?
>>
>
> So i am moving to new office and it has taken me more time than i thought
> to pack stuff. Attach is first step of CDM on top of lastest HMM. I hope
> to have more time tomorrow or next week to finish rebasing patches and to
> run some test with stolen ram as CDM memory.
>


No worries, thanks for the update. I forward ported some of the stuff from
HMM-CDM myself for testing on top of v23, with some assumptions and names
like MEMORY_PRIVATE_COHERENT (a new type) and arch_add_memory for
hotplug. I also modified Reza's driver (test) to see how far I can get
with HMM-CDM.

I look forward to the HMM-CDM patchset that you post.

Balbir Singh