From: Hugh Dickins <hughd@google.com>
To: Jerome Glisse <jglisse@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linux MM <linux-mm@kvack.org>, John Hubbard <jhubbard@nvidia.com>,
David Nellans <dnellans@nvidia.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
Ross Zwisler <ross.zwisler@linux.intel.com>
Subject: Re: [HMM 08/15] mm/ZONE_DEVICE: special case put_page() for device private pages
Date: Mon, 22 May 2017 13:22:22 -0700 (PDT) [thread overview]
Message-ID: <alpine.LSU.2.11.1705221317280.4687@eggly.anvils> (raw)
In-Reply-To: <20170522201416.GA8168@redhat.com>
On Mon, 22 May 2017, Jerome Glisse wrote:
> On Mon, May 22, 2017 at 12:29:53PM -0700, Dan Williams wrote:
> > On Mon, May 22, 2017 at 9:51 AM, Jerome Glisse <jglisse@redhat.com> wrote:
> > > A ZONE_DEVICE page that reach a refcount of 1 is free ie no longer
> > > have any user. For device private pages this is important to catch
> > > and thus we need to special case put_page() for this.
> > >
> > > Signed-off-by: Jerome Glisse <jglisse@redhat.com>
> > > Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> > > Cc: Dan Williams <dan.j.williams@intel.com>
> > > Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
> > > ---
> > > include/linux/mm.h | 30 ++++++++++++++++++++++++++++++
> > > kernel/memremap.c | 1 -
> > > 2 files changed, 30 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > index a825dab..11f7bac 100644
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -23,6 +23,7 @@
> > > #include <linux/page_ext.h>
> > > #include <linux/err.h>
> > > #include <linux/page_ref.h>
> > > +#include <linux/memremap.h>
> > >
> > > struct mempolicy;
> > > struct anon_vma;
> > > @@ -795,6 +796,20 @@ static inline bool is_device_private_page(const struct page *page)
> > > return ((page_zonenum(page) == ZONE_DEVICE) &&
> > > (page->pgmap->type == MEMORY_DEVICE_PRIVATE));
> > > }
> > > +
> > > +static inline void put_zone_device_private_page(struct page *page)
> > > +{
> > > + int count = page_ref_dec_return(page);
> > > +
> > > + /*
> > > + * If refcount is 1 then page is freed and refcount is stable as nobody
> > > + * holds a reference on the page.
> > > + */
> > > + if (count == 1)
> > > + page->pgmap->page_free(page, page->pgmap->data);
> > > + else if (!count)
> > > + __put_page(page);
> > > +}
Is there something else in this patchset that guarantees
that get_page_unless_zero() is never used on thse pages?
We have plenty of code that knows that refcount 0 is special:
having to know that refcount 1 may be special is worrying.
Hugh
> > > #else
> > > static inline bool is_zone_device_page(const struct page *page)
> > > {
> > > @@ -805,6 +820,10 @@ static inline bool is_device_private_page(const struct page *page)
> > > {
> > > return false;
> > > }
> > > +
> > > +static inline void put_zone_device_private_page(struct page *page)
> > > +{
> > > +}
> > > #endif
> > >
> > > static inline void get_page(struct page *page)
> > > @@ -822,6 +841,17 @@ static inline void put_page(struct page *page)
> > > {
> > > page = compound_head(page);
> > >
> > > + /*
> > > + * For private device pages we need to catch refcount transition from
> > > + * 2 to 1, when refcount reach one it means the private device page is
> > > + * free and we need to inform the device driver through callback. See
> > > + * include/linux/memremap.h and HMM for details.
> > > + */
> > > + if (unlikely(is_device_private_page(page))) {
> >
> > Since I presume HMM is a niche use case can we make this a
> > "static_branch_unlikely(&hmm_key) && is_device_private_page(page))"?
> > That way non-hmm platforms see minimal overhead.
>
> Like i said in the cover letter i am bit anxious about doing for
> an inline function. I don't see any existing case for inline
> function and static key. Is that suppose to work ?
>
> How widespread HMM use will be is hard to guess. Usual chicken
> and egg plus adoption thing. If GPGPU compte keeps growing and
> it seems it does then HMM likely gonna be enable and actively
> use for large chunk of those computer that have GPGPU workload.
>
> I will test a static key of that branch and see if it explodes
> because put_page() is an inline function.
>
> Cheers,
> Jerome
--
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:[~2017-05-22 20:22 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-22 16:51 [HMM 00/15] HMM (Heterogeneous Memory Management) v22 Jérôme Glisse
2017-05-22 16:51 ` [HMM 01/15] hmm: heterogeneous memory management documentation Jérôme Glisse
2017-05-22 16:51 ` [HMM 02/15] mm/hmm: heterogeneous memory management (HMM for short) v3 Jérôme Glisse
2017-05-22 16:51 ` [HMM 03/15] mm/hmm/mirror: mirror process address space on device with HMM helpers v3 Jérôme Glisse
2017-05-22 16:51 ` [HMM 04/15] mm/hmm/mirror: helper to snapshot CPU page table v3 Jérôme Glisse
2017-05-22 16:51 ` [HMM 05/15] mm/hmm/mirror: device page fault handler Jérôme Glisse
2017-05-22 16:51 ` [HMM 06/15] mm/memory_hotplug: introduce add_pages Jérôme Glisse
2017-05-22 16:51 ` [HMM 07/15] mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory v2 Jérôme Glisse
2017-05-22 21:17 ` Dan Williams
2017-05-23 21:36 ` [HMM 07/18] mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory v3 Jérôme Glisse
2017-05-23 8:36 ` [HMM 07/15] mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory v2 kbuild test robot
2017-05-22 16:51 ` [HMM 08/15] mm/ZONE_DEVICE: special case put_page() for device private pages Jérôme Glisse
2017-05-22 19:29 ` Dan Williams
2017-05-22 20:14 ` Jerome Glisse
2017-05-22 20:19 ` Dan Williams
2017-05-22 21:14 ` Jerome Glisse
2017-05-22 20:22 ` Hugh Dickins [this message]
2017-05-22 21:17 ` Jerome Glisse
2017-05-23 9:34 ` kbuild test robot
2017-05-23 13:23 ` Kirill A. Shutemov
2017-05-23 21:37 ` [HMM 08/18] mm/ZONE_DEVICE: special case put_page() for device private pages v2 Jérôme Glisse
2017-05-22 16:52 ` [HMM 09/15] mm/hmm/devmem: device memory hotplug using ZONE_DEVICE v4 Jérôme Glisse
2017-05-23 21:37 ` [HMM 09/18] mm/hmm/devmem: device memory hotplug using ZONE_DEVICE v5 Jérôme Glisse
2017-05-22 16:52 ` [HMM 10/15] mm/hmm/devmem: dummy HMM device for ZONE_DEVICE memory v3 Jérôme Glisse
2017-05-22 16:52 ` [HMM 11/15] mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY Jérôme Glisse
2017-05-22 16:52 ` [HMM 12/15] mm/migrate: new memory migration helper for use with device memory v4 Jérôme Glisse
2017-05-23 18:07 ` Reza Arbab
2017-06-27 0:07 ` Evgeny Baskakov
2017-06-30 23:19 ` Evgeny Baskakov
2017-07-01 0:57 ` Jerome Glisse
2017-07-01 2:06 ` Evgeny Baskakov
2017-07-10 22:59 ` Evgeny Baskakov
2017-07-10 23:43 ` Jerome Glisse
2017-07-11 0:17 ` Evgeny Baskakov
2017-07-11 0:54 ` Jerome Glisse
2017-07-20 21:05 ` Evgeny Baskakov
2017-07-10 23:44 ` Evgeny Baskakov
2017-07-11 18:29 ` Jerome Glisse
2017-07-11 18:42 ` Evgeny Baskakov
2017-07-11 18:49 ` Jerome Glisse
2017-07-11 19:35 ` Evgeny Baskakov
2017-07-13 20:16 ` Jerome Glisse
2017-07-14 5:32 ` Evgeny Baskakov
2017-07-14 19:43 ` Evgeny Baskakov
2017-07-15 0:55 ` Jerome Glisse
2017-07-15 5:04 ` Evgeny Baskakov
2017-07-21 1:00 ` Evgeny Baskakov
2017-07-21 1:33 ` Jerome Glisse
2017-07-21 22:01 ` Evgeny Baskakov
2017-07-25 22:45 ` Evgeny Baskakov
2017-07-26 19:14 ` Jerome Glisse
2017-05-22 16:52 ` [HMM 13/15] mm/migrate: migrate_vma() unmap page from vma while collecting pages Jérôme Glisse
2017-05-22 16:52 ` [HMM 14/15] mm/migrate: support un-addressable ZONE_DEVICE page in migration v2 Jérôme Glisse
2017-05-22 16:52 ` [HMM 15/15] mm/migrate: allow migrate_vma() to alloc new page on empty entry v2 Jérôme Glisse
2017-05-23 22:02 ` [HMM 00/15] HMM (Heterogeneous Memory Management) v22 Jerome Glisse
2017-05-23 22:05 ` Andrew Morton
2017-05-24 1:55 ` Balbir Singh
2017-05-24 17:53 ` Jerome Glisse
2017-06-01 2:04 ` Balbir Singh
2017-06-01 22:38 ` Jerome Glisse
2017-06-03 9:18 ` Balbir Singh
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=alpine.LSU.2.11.1705221317280.4687@eggly.anvils \
--to=hughd@google.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=dnellans@nvidia.com \
--cc=jglisse@redhat.com \
--cc=jhubbard@nvidia.com \
--cc=kirill.shutemov@linux.intel.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).