From: Jerome Glisse <jglisse@redhat.com>
To: Dave Hansen <dave.hansen@intel.com>
Cc: akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, John Hubbard <jhubbard@nvidia.com>,
Dan Williams <dan.j.williams@intel.com>,
Ross Zwisler <ross.zwisler@linux.intel.com>
Subject: Re: [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for un-addressable device memory
Date: Thu, 8 Dec 2016 11:39:59 -0500 (EST) [thread overview]
Message-ID: <152004793.3187283.1481215199204.JavaMail.zimbra@redhat.com> (raw)
In-Reply-To: <be2861b4-d830-fbd7-e9eb-ebc8e4d913a2@intel.com>
> 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 i can control or enforce at platform level how to choose
specific physical address for hotplug.
So right now with my patchset what happens is that the hotplug will fail
because i already registered a resource for the physical range. What i can
add is a way to migrate the device memory to a different physical range.
I am bit afraid on how complex this can be.
The ideal solution would be to increase the MAX_PHYSMEM_BITS by one and use
physical address that can never be valid. We would not need to increase the
the direct mapping size of memory (this memory is not mappable by CPU). But
i am afraid of complication this might cause.
I think for sparse memory model it should be easy enough and i already rely
on sparse for HMM.
In any case i think this is something that can be solve after. If it becomes
a real issue. Maybe i should add a debug printk that when hotplug fails
because of an existing un-addressable ZONE_DEVICE resource.
Cheers,
Jérôme
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2016-12-08 16:40 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-08 16:39 [HMM v14 00/16] HMM (Heterogeneous Memory Management) v14 Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 01/16] mm/free_hot_cold_page: catch ZONE_DEVICE pages Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 02/16] mm/memory/hotplug: convert device bool to int to allow for more flags v2 Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 03/16] mm/ZONE_DEVICE/devmem_pages_remove: allow early removal of device memory Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 04/16] mm/ZONE_DEVICE/free-page: callback when page is freed Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 05/16] mm/ZONE_DEVICE/unaddressable: add support for un-addressable device memory Jérôme Glisse
2016-12-08 16:21 ` Dave Hansen
2016-12-08 16:39 ` Jerome Glisse [this message]
2016-12-08 20:07 ` Dave Hansen
2016-12-08 20:37 ` Jerome Glisse
2016-12-26 9:12 ` Anshuman Khandual
2016-12-26 19:02 ` Jerome Glisse
2016-12-08 16:39 ` [HMM v14 06/16] mm/ZONE_DEVICE/x86: " Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 07/16] mm/hmm: heterogeneous memory management (HMM for short) Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 08/16] mm/hmm/mirror: mirror process address space on device with HMM helpers Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 09/16] mm/hmm/mirror: helper to snapshot CPU page table Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 10/16] mm/hmm/mirror: device page fault handler Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 11/16] mm/hmm/migrate: support un-addressable ZONE_DEVICE page in migration Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 12/16] mm/hmm/migrate: add new boolean copy flag to migratepage() callback Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 13/16] mm/hmm/migrate: new memory migration helper for use with device memory v2 Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 14/16] mm/hmm/migrate: optimize page map once in vma being migrated Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 15/16] mm/hmm/devmem: device driver helper to hotplug ZONE_DEVICE memory Jérôme Glisse
2016-12-08 16:39 ` [HMM v14 16/16] mm/hmm/devmem: dummy HMM device as an helper for " Jérôme Glisse
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=152004793.3187283.1481215199204.JavaMail.zimbra@redhat.com \
--to=jglisse@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ross.zwisler@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).