From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Linux MM <linux-mm@kvack.org>,
Catalin Marinas <catalin.marinas@arm.com>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
Steve Capper <steve.capper@linaro.org>,
Thomas Gleixner <tglx@linutronix.de>,
Peter Zijlstra <peterz@infradead.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
"H. Peter Anvin" <hpa@zytor.com>,
Dave Hansen <dave.hansen@intel.com>,
Borislav Petkov <bp@alien8.de>, Rik van Riel <riel@redhat.com>,
Dann Frazier <dann.frazier@canonical.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Michal Hocko <mhocko@suse.cz>,
linux-tip-commits@vger.kernel.org
Subject: Re: get_zone_device_page() in get_page() and page_cache_get_speculative()
Date: Mon, 24 Apr 2017 21:01:58 +0300 [thread overview]
Message-ID: <20170424180158.y26m3kgzhpmawbhg@node.shutemov.name> (raw)
In-Reply-To: <CAPcyv4g74LT6sK2WgG6FnwQHCC5fNTwfqBPq1BY8PnZ7zwdGPw@mail.gmail.com>
On Mon, Apr 24, 2017 at 10:47:43AM -0700, Dan Williams wrote:
> On Mon, Apr 24, 2017 at 10:30 AM, Kirill A. Shutemov
> >> >> [ 35.423841] WARNING: CPU: 8 PID: 245 at lib/percpu-refcount.c:155
> >> >> percpu_ref_switch_to_atomic_rcu+0x1f5/0x200
> >> >
> >> > Okay, I've tracked it down. The issue is triggered by replacment
> >> > get_page() with page_cache_get_speculative().
> >> >
> >> > page_cache_get_speculative() doesn't have get_zone_device_page(). :-|
> >> >
> >> > And I think it's your bug, Dan: it's wrong to have
> >> > get_/put_zone_device_page() in get_/put_page(). I must be handled by
> >> > page_ref_* machinery to catch all cases where we manipulate with page
> >> > refcount.
> >>
> >> The page_ref conversion landed in 4.6 *after* the ZONE_DEVICE
> >> implementation that landed in 4.5, so there was a missed conversion of
> >> the zone-device reference counting to page_ref.
> >
> > Fair enough.
> >
> > But get_page_unless_zero() definitely predates ZONE_DEVICE. :)
> >
>
> It does, but that's deliberate. A ZONE_DEVICE page never has a zero
> reference count, it's always owned by the device, never by the page
> allocator. ZONE_DEVICE overrides the ->lru list_head to store private
> device information and we rely on the behavior that a non-zero
> reference means the page is not added to any lru or page cache list.
So, what do you propose? Use get_page() instead of
page_cache_get_speculative() in GUP_fast() if the page belong to zone
device?
I don't like it. This situation, when we only can use subset of
helpers to manipulate page refcount creates situation waiting to explode.
I think it's still better to do it on page_ref_* level.
BTW, why do we need to pin pgmap from get_page() in first place?
I don't have enough background in ZONE_DEVICE.
--
Kirill A. Shutemov
next prev parent reply other threads:[~2017-04-24 18:02 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-20 21:46 [tip:x86/mm] x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation Dan Williams
2017-04-21 14:16 ` Kirill A. Shutemov
2017-04-21 19:30 ` Dan Williams
2017-04-23 9:52 ` [PATCH] Revert "x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation" Ingo Molnar
2017-04-23 23:31 ` get_zone_device_page() in get_page() and page_cache_get_speculative() Kirill A. Shutemov
2017-04-24 17:23 ` Dan Williams
2017-04-24 17:30 ` Kirill A. Shutemov
2017-04-24 17:47 ` Dan Williams
2017-04-24 18:01 ` Kirill A. Shutemov [this message]
2017-04-24 18:25 ` Kirill A. Shutemov
2017-04-24 18:41 ` Dan Williams
2017-04-25 13:19 ` Kirill A. Shutemov
2017-04-25 16:44 ` Dan Williams
2017-04-27 0:55 ` [PATCH] mm, zone_device: replace {get, put}_zone_device_page() with a single reference Dan Williams
2017-04-27 8:33 ` Kirill A. Shutemov
2017-04-28 6:39 ` Ingo Molnar
2017-04-28 8:14 ` [PATCH] mm, zone_device: Replace " Kirill A. Shutemov
2017-04-28 17:23 ` [PATCH v2] mm, zone_device: replace " Dan Williams
2017-04-28 17:34 ` Jerome Glisse
2017-04-28 17:41 ` Dan Williams
2017-04-28 18:00 ` Jerome Glisse
2017-04-28 19:02 ` Dan Williams
2017-04-28 19:16 ` Jerome Glisse
2017-04-28 19:22 ` Dan Williams
2017-04-28 19:33 ` Jerome Glisse
2017-04-29 10:17 ` Kirill A. Shutemov
2017-04-30 23:14 ` Jerome Glisse
2017-05-01 1:42 ` Dan Williams
2017-05-01 1:54 ` Jerome Glisse
2017-05-01 2:40 ` Dan Williams
2017-05-01 3:48 ` Logan Gunthorpe
2017-05-01 10:23 ` Kirill A. Shutemov
2017-05-01 13:55 ` Jerome Glisse
2017-05-01 20:19 ` Dan Williams
2017-05-01 20:32 ` Jerome Glisse
2017-05-02 11:37 ` Kirill A. Shutemov
2017-05-02 13:22 ` Jerome Glisse
2017-04-29 14:18 ` Ingo Molnar
2017-05-01 2:45 ` Dan Williams
2017-05-01 7:12 ` Ingo Molnar
2017-05-01 9:33 ` Kirill A. Shutemov
2017-05-01 8:28 ` [tip:x86/mm] mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash tip-bot for Dan Williams
2017-04-27 16:11 ` [PATCH] mm, zone_device: replace {get, put}_zone_device_page() with a single reference Logan Gunthorpe
2017-04-27 16:14 ` Dan Williams
2017-04-27 16:33 ` Logan Gunthorpe
2017-04-27 16:38 ` Dan Williams
2017-04-27 16:45 ` Logan Gunthorpe
2017-04-27 16:46 ` Dan Williams
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=20170424180158.y26m3kgzhpmawbhg@node.shutemov.name \
--to=kirill@shutemov.name \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=dan.j.williams@intel.com \
--cc=dann.frazier@canonical.com \
--cc=dave.hansen@intel.com \
--cc=hpa@zytor.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mhocko@suse.cz \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=steve.capper@linaro.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/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).