AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Vetter <daniel@ffwll.ch>
To: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>,
	daniel.vetter@ffwll.ch, michel@daenzer.net,
	amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
	Daniel Vetter <daniel@ffwll.ch>,
	ckoenig.leichtzumerken@gmail.com
Subject: Re: [PATCH 0/6] RFC Support hot device unplug in amdgpu
Date: Mon, 11 May 2020 13:03:29 +0200	[thread overview]
Message-ID: <20200511110329.GC206103@phenom.ffwll.local> (raw)
In-Reply-To: <158919237000.1729.13151635793333034320@build.alporthouse.com>

On Mon, May 11, 2020 at 11:19:30AM +0100, Chris Wilson wrote:
> Quoting Daniel Vetter (2020-05-11 10:54:33)
> >   - worse, neither vk nor gl (to my knowledge) have a concept of events
> >     for when the gpu died. The only stuff you have is things like
> >     arb_robustness which says a) everything continues as if nothing
> >     happened b) there's a function where you can ask whether your gl
> >     context and all the textures/buffers are toast.
> 
> Vulkan/DX12 arrived after eGPU, and there is at least the concept of
> VK_ERROR_DEVICE_LOST. Mainly used at the moment after a GPU hang and
> loss of context.
> 
> https://www.khronos.org/registry/vulkan/specs/1.2-extensions/html/vkspec.html#devsandqueues-lost-device

Ah cool, so -EIO on some ioctls, with silencing it in the gl driver and
passing it on for the vk driver should be ok. Assuming vk frameworks
bother to implement the *may* thing. I'm assuming if the validation
midlayer doesn't inject this, it's untested and firework will ensue.

But then more direct path to fireworks is what vk is all about :-)
-Daniel
-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  reply	other threads:[~2020-05-11 11:03 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-09 18:51 [PATCH 0/6] RFC Support hot device unplug in amdgpu Andrey Grodzovsky
2020-05-09 18:51 ` [PATCH 1/6] drm/ttm: Add unampping of the entire device address space Andrey Grodzovsky
2020-05-11  6:45   ` Christian König
2020-06-05 14:29     ` Andrey Grodzovsky
2020-06-05 18:40       ` Christian König
2020-06-09 16:37         ` Andrey Grodzovsky
2020-05-09 18:51 ` [PATCH 2/6] drm/amdgpu: Force unmap all user VMAs on device removal Andrey Grodzovsky
2020-05-11  6:47   ` Christian König
2020-05-09 18:51 ` [PATCH 3/6] drm/amdgpu: Wait for all user clients Andrey Grodzovsky
2020-05-11  6:57   ` Christian König
2020-05-09 18:51 ` [PATCH 4/6] drm/amdgpu: Wait for all clients importing out dma-bufs Andrey Grodzovsky
2020-05-09 18:51 ` [PATCH 5/6] drm/ttm: Add destroy flag in TTM BO eviction interface Andrey Grodzovsky
2020-05-11  7:05   ` Christian König
2020-06-10 10:25   ` Thomas Hellström (Intel)
2020-06-10 13:56     ` Andrey Grodzovsky
2020-05-09 18:51 ` [PATCH 6/6] drm/amdgpu: Use TTM MMs destroy interface Andrey Grodzovsky
2020-05-11  9:26 ` [PATCH 0/6] RFC Support hot device unplug in amdgpu Pekka Paalanen
2020-05-11 12:29   ` Christian König
2020-05-11 16:37   ` Andrey Grodzovsky
2020-05-11  9:54 ` Daniel Vetter
2020-05-11 10:19   ` Chris Wilson
2020-05-11 11:03     ` Daniel Vetter [this message]
2020-05-11 11:19   ` Daniel Vetter
2020-05-11 12:34     ` Christian König
2020-05-11 12:43       ` Daniel Vetter
2020-05-11 11:43   ` Lukas Wunner
2020-05-11 12:21     ` Daniel Vetter
2020-05-11 14:08       ` Lukas Wunner
2020-05-11 14:14         ` Daniel Vetter
2020-05-13 14:32   ` Andrey Grodzovsky
2020-05-13 18:05     ` Daniel Vetter

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=20200511110329.GC206103@phenom.ffwll.local \
    --to=daniel@ffwll.ch \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=andrey.grodzovsky@amd.com \
    --cc=chris@chris-wilson.co.uk \
    --cc=ckoenig.leichtzumerken@gmail.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=michel@daenzer.net \
    /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