All of lore.kernel.org
 help / color / mirror / Atom feed
From: zhoucm1 <david1.zhou-5C7GfCeVMHo@public.gmane.org>
To: "Christian König"
	<deathsimple-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH 00/13] shadow page table support
Date: Tue, 26 Jul 2016 16:41:57 +0800	[thread overview]
Message-ID: <57972255.7000307@amd.com> (raw)
In-Reply-To: <a53d1727-796b-351e-7254-e8eed6369f2d-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>



On 2016年07月26日 16:27, Christian König wrote:
> Am 26.07.2016 um 07:33 schrieb zhoucm1:
>>
>>
>> On 2016年07月26日 10:40, zhoucm1 wrote:
>>> 1. We add an optional "shadow" flag so that when a BO in VRAM is 
>>> allocated we also allocate a shadow BO in GART.
>>>
>>> 2. We have another "backup" flag that says on the next command 
>>> submission the BO is backed up from VRAM to GART before that 
>>> submission.
>>>
>>> 3. We set the shadow flag for VM PD/PT BOs and every time we modify 
>>> them set the backup flag so they get backed up on next CS.
>>>
>>> 4. We add an IOCTL to allow setting the backup flag from userspace 
>>> so that we can trigger another backup even after the first CS. 
>> When I'm trying it and thinking more, a general shadow BO indeed be a 
>> sense way, but backup flag seems not necessary, mainly two reasons:
>> 1. we cannot make sure backup job is completed when gpu reset happens.
>
> Correct, but we can't guarantee that for VM updates either.
Since we directly fill pte info to shadow BO, not copy from VRAM to GTT. 
Which ensures shadow BO content always is right, event these jobs don't 
complete when gpu reset, but after gpu reset, we can sync these jobs, 
and then copy GTT to VRAM. The similar case is also same for shader BOs. 
So we should directly fill the shadow BOs.

Regards,
David Zhou
>
>> 2. backup flag is to copy the whole BO, which seems overhead. If we 
>> update shadow BO along with BO in real time, e.g. PD/PT, we could 
>> only update some ptes not the entire BO.
>
> How about using a begin/end range of which parts of the BO needs to be 
> backed up instead of a flag?
>
>> So can we assume shadow BO always needed to backup if shadow flag is 
>> set?
>
> For shader BOs clearly not a good idea because they are rarely update 
> and so backing them up every time would be a huge overhead.
>
> Regards,
> Christian.
>
>>
>> Regards,
>> David Zhou
>
>

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  parent reply	other threads:[~2016-07-26  8:41 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-25  7:22 [PATCH 00/13] shadow page table support Chunming Zhou
     [not found] ` <1469431353-15787-1-git-send-email-David1.Zhou-5C7GfCeVMHo@public.gmane.org>
2016-07-25  7:22   ` [PATCH 01/13] drm/amdgpu: add pd/pt bo shadow Chunming Zhou
2016-07-25  7:22   ` [PATCH 02/13] drm/amdgpu: update shadow pt bo while update pt Chunming Zhou
2016-07-25  7:22   ` [PATCH 03/13] drm/amdgpu: update pd shadow while updating pd Chunming Zhou
2016-07-25  7:22   ` [PATCH 04/13] drm/amdgpu: implement amdgpu_vm_recover_page_table_from_shadow Chunming Zhou
2016-07-25  7:22   ` [PATCH 05/13] drm/amdgpu: link all vm clients Chunming Zhou
2016-07-25  7:22   ` [PATCH 06/13] drm/amdgpu: add vm_list_lock Chunming Zhou
2016-07-25  7:22   ` [PATCH 07/13] drm/amd: add block entity function Chunming Zhou
2016-07-25  7:22   ` [PATCH 08/13] drm/amdgpu: recover page tables after gpu reset Chunming Zhou
2016-07-25  7:22   ` [PATCH 09/13] drm/amdgpu: add vm recover pt fence Chunming Zhou
2016-07-25  7:22   ` [PATCH 10/13] drm/amd: reset hw count when reset job Chunming Zhou
2016-07-25  7:22   ` [PATCH 11/13] drm/amd: fix deadlock of job_list_lock Chunming Zhou
2016-07-25  7:22   ` [PATCH 12/13] drm/amd: wait neccessary dependency before running job Chunming Zhou
2016-07-25  7:22   ` [PATCH 13/13] drm/amdgpu: fix sched deadoff Chunming Zhou
2016-07-25 10:31   ` [PATCH 00/13] shadow page table support Christian König
     [not found]     ` <b2f1e133-c7e2-88c4-1e0f-d12310d734f0-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-07-26  2:40       ` zhoucm1
     [not found]         ` <5796CD94.6080405-5C7GfCeVMHo@public.gmane.org>
2016-07-26  5:33           ` zhoucm1
     [not found]             ` <5796F610.4050204-5C7GfCeVMHo@public.gmane.org>
2016-07-26  8:27               ` Christian König
     [not found]                 ` <a53d1727-796b-351e-7254-e8eed6369f2d-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-07-26  8:41                   ` zhoucm1 [this message]
     [not found]                     ` <57972255.7000307-5C7GfCeVMHo@public.gmane.org>
2016-07-26  9:05                       ` Christian König
     [not found]                         ` <3766450b-7dd5-9632-ed0b-81e744d08f32-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-07-26  9:12                           ` zhoucm1
2016-07-26  8:51   ` Liu, Monk
2016-07-26  8:52 ` Liu, Monk
  -- strict thread matches above, loose matches on Subject: below --
2016-07-28 10:11 Chunming Zhou
     [not found] ` <1469700700-25013-1-git-send-email-David1.Zhou-5C7GfCeVMHo@public.gmane.org>
2016-08-02  2:03   ` zhoucm1
2016-08-02  7:48 Chunming Zhou
     [not found] ` <1470124147-22840-1-git-send-email-David1.Zhou-5C7GfCeVMHo@public.gmane.org>
2016-08-03 13:39   ` Christian König
     [not found]     ` <28f9e53b-5616-89e1-202b-6dba62b7f004-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-08-04  6:05       ` zhoucm1
     [not found]         ` <57A2DB2C.7050705-5C7GfCeVMHo@public.gmane.org>
2016-08-04  9:52           ` Christian König
     [not found]             ` <88f96afd-c2c2-b4e5-8b79-e09f1bf7e742-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-08-05  2:43               ` zhoucm1
     [not found]                 ` <57A3FD55.60602-5C7GfCeVMHo@public.gmane.org>
2016-08-05  8:56                   ` Christian König
     [not found]                     ` <99f20f60-11a2-9e79-728e-d7fe754d8b47-ANTagKRnAhcb1SvskN2V4Q@public.gmane.org>
2016-08-05  9:12                       ` zhoucm1
     [not found]                         ` <57A45883.6040901-5C7GfCeVMHo@public.gmane.org>
2016-08-05  9:21                           ` Christian König
2016-08-05  9:12                       ` zhoucm1

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=57972255.7000307@amd.com \
    --to=david1.zhou-5c7gfcevmho@public.gmane.org \
    --cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
    --cc=deathsimple-ANTagKRnAhcb1SvskN2V4Q@public.gmane.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.