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


Groups > linux.kernel > #1552953

Re: [HMM v15 13/16] mm/hmm/migrate: new memory migration helper for use with device memory v2

From David Nellans <dnellans@nvidia.com>
Newsgroups linux.kernel
Subject Re: [HMM v15 13/16] mm/hmm/migrate: new memory migration helper for use with device memory v2
Date 2017-01-06 17:50 +0100
Message-ID <sWFSi-4A4-23@gated-at.bofh.it> (permalink)
References <sWEWd-3VU-3@gated-at.bofh.it> <sWEWe-3VU-9@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw



On 01/06/2017 10:46 AM, Jérôme Glisse wrote:
> This patch add a new memory migration helpers, which migrate memory
> backing a range of virtual address of a process to different memory
> (which can be allocated through special allocator). It differs from
> numa migration by working on a range of virtual address and thus by
> doing migration in chunk that can be large enough to use DMA engine
> or special copy offloading engine.
>
> Expected users are any one with heterogeneous memory where different
> memory have different characteristics (latency, bandwidth, ...). As
> an example IBM platform with CAPI bus can make use of this feature
> to migrate between regular memory and CAPI device memory. New CPU
> architecture with a pool of high performance memory not manage as
> cache but presented as regular memory (while being faster and with
> lower latency than DDR) will also be prime user of this patch.
Why should the normal page migration path (where neither src nor dest are
device private), use the hmm_migrate functionality?  11-14 are
replicating a lot of the
normal migration functionality but with special casing for HMM
requirements.  When migrating
THP's or a list of pages (your use case above), normal NUMA migration
is going to want to do this as fast as possible too (see Zi Yan's
patches for multi-threading normal
migrations & prototype of using intel IOAT for transfers, he sees 3-5x
speedup).

If the intention is to provide a common interface hook for migration to
use DMA acceleration
(which is a good idea), it probably shouldn't be special cased inside
HMM functionality.
For example, using the intel IOAT for migration DMA has nothing to do
with HMM
whatsoever. We need a normal migration path interface to allow DMA that
isn't tied
to HMM.

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


Thread

[HMM v15 13/16] mm/hmm/migrate: new memory migration helper for use with device memory v2 Jérôme Glisse <jglisse@redhat.com> - 2017-01-06 16:50 +0100
  Re: [HMM v15 13/16] mm/hmm/migrate: new memory migration helper for  use with device memory v2 David Nellans <dnellans@nvidia.com> - 2017-01-06 17:50 +0100
    Re: [HMM v15 13/16] mm/hmm/migrate: new memory migration helper for  use with device memory v2 Jerome Glisse <jglisse@redhat.com> - 2017-01-06 18:20 +0100
      Re: [HMM v15 13/16] mm/hmm/migrate: new memory migration helper for  use with device memory v2 David Nellans <dnellans@nvidia.com> - 2017-01-10 16:40 +0100
        Re: [HMM v15 13/16] mm/hmm/migrate: new memory migration helper for  use with device memory v2 Jerome Glisse <jglisse@redhat.com> - 2017-01-10 18:00 +0100

csiph-web