From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
To: "Christian König" <christian.koenig@amd.com>,
"David Airlie" <airlied@linux.ie>,
"Huang Rui" <ray.huang@amd.com>,
"Daniel Vetter" <daniel@ffwll.ch>,
"Trigger Huang" <Trigger.Huang@gmail.com>,
"Gert Wollny" <gert.wollny@collabora.com>,
"Antonio Caggiano" <antonio.caggiano@collabora.com>,
"Paolo Bonzini" <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
dri-devel@lists.freedesktop.org,
virtualization@lists.linux-foundation.org,
Dmitry Osipenko <digetx@gmail.com>,
kernel@collabora.com
Subject: Re: [PATCH v1] drm/ttm: Refcount allocated tail pages
Date: Thu, 18 Aug 2022 01:57:48 +0300 [thread overview]
Message-ID: <ff28e1b4-cda2-14b8-b9bf-10706ae52cac@collabora.com> (raw)
In-Reply-To: <6effcd33-8cc3-a4e0-3608-b9cef7a76da7@collabora.com>
On 8/15/22 18:54, Dmitry Osipenko wrote:
> On 8/15/22 17:57, Dmitry Osipenko wrote:
>> On 8/15/22 16:53, Christian König wrote:
>>> Am 15.08.22 um 15:45 schrieb Dmitry Osipenko:
>>>> [SNIP]
>>>>> Well that comment sounds like KVM is doing the right thing, so I'm
>>>>> wondering what exactly is going on here.
>>>> KVM actually doesn't hold the page reference, it takes the temporal
>>>> reference during page fault and then drops the reference once page is
>>>> mapped, IIUC. Is it still illegal for TTM? Or there is a possibility for
>>>> a race condition here?
>>>>
>>>
>>> Well the question is why does KVM grab the page reference in the first
>>> place?
>>>
>>> If that is to prevent the mapping from changing then yes that's illegal
>>> and won't work. It can always happen that you grab the address, solve
>>> the fault and then immediately fault again because the address you just
>>> grabbed is invalidated.
>>>
>>> If it's for some other reason than we should probably investigate if we
>>> shouldn't stop doing this.
>>
>> CC: +Paolo Bonzini who introduced this code
>>
>> commit add6a0cd1c5ba51b201e1361b05a5df817083618
>> Author: Paolo Bonzini <pbonzini@redhat.com>
>> Date: Tue Jun 7 17:51:18 2016 +0200
>>
>> KVM: MMU: try to fix up page faults before giving up
>>
>> The vGPU folks would like to trap the first access to a BAR by setting
>> vm_ops on the VMAs produced by mmap-ing a VFIO device. The fault
>> handler
>> then can use remap_pfn_range to place some non-reserved pages in the
>> VMA.
>>
>> This kind of VM_PFNMAP mapping is not handled by KVM, but follow_pfn
>> and fixup_user_fault together help supporting it. The patch also
>> supports
>> VM_MIXEDMAP vmas where the pfns are not reserved and thus subject to
>> reference counting.
>>
>> @Paolo,
>> https://lore.kernel.org/dri-devel/73e5ed8d-0d25-7d44-8fa2-e1d61b1f5a04@amd.com/T/#m7647ce5f8c4749599d2c6bc15a2b45f8d8cf8154
>>
>
> If we need to bump the refcount only for VM_MIXEDMAP and not for
> VM_PFNMAP, then perhaps we could add a flag for that to the kvm_main
> code that will denote to kvm_release_page_clean whether it needs to put
> the page?
The other variant that kind of works is to mark TTM pages reserved using
SetPageReserved/ClearPageReserved, telling KVM not to mess with the page
struct. But the potential consequences of doing this are unclear to me.
Christian, do you think we can do it?
--
Best regards,
Dmitry
next prev parent reply other threads:[~2022-08-17 22:58 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-15 9:54 [PATCH v1] drm/ttm: Refcount allocated tail pages Dmitry Osipenko
2022-08-15 10:05 ` Christian König
2022-08-15 10:09 ` Dmitry Osipenko
2022-08-15 10:11 ` Christian König
2022-08-15 10:14 ` Christian König
2022-08-15 10:18 ` Dmitry Osipenko
2022-08-15 10:42 ` Christian König
2022-08-15 10:47 ` Dmitry Osipenko
2022-08-15 10:51 ` Christian König
2022-08-15 11:19 ` Dmitry Osipenko
2022-08-15 11:28 ` Christian König
2022-08-15 11:50 ` Dmitry Osipenko
2022-08-15 13:06 ` Christian König
2022-08-15 13:45 ` Dmitry Osipenko
2022-08-15 13:53 ` Christian König
2022-08-15 14:57 ` Dmitry Osipenko
2022-08-15 15:54 ` Dmitry Osipenko
2022-08-17 22:57 ` Dmitry Osipenko [this message]
2022-08-17 23:13 ` Dmitry Osipenko
2022-08-18 9:41 ` Christian König
2023-01-11 17:05 ` Sean Christopherson
2023-01-11 21:24 ` Dmitry Osipenko
2022-09-06 20:01 ` Daniel Vetter
2022-09-06 20:05 ` Daniel Vetter
2022-09-07 6:48 ` Christian König
2023-01-11 17:13 ` Sean Christopherson
2022-09-08 11:04 ` Rob Clark
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=ff28e1b4-cda2-14b8-b9bf-10706ae52cac@collabora.com \
--to=dmitry.osipenko@collabora.com \
--cc=Trigger.Huang@gmail.com \
--cc=airlied@linux.ie \
--cc=antonio.caggiano@collabora.com \
--cc=christian.koenig@amd.com \
--cc=daniel@ffwll.ch \
--cc=digetx@gmail.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=gert.wollny@collabora.com \
--cc=kernel@collabora.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=ray.huang@amd.com \
--cc=virtualization@lists.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).