All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <christian.koenig@amd.com>
To: "Icenowy Zheng" <uwu@icenowy.me>,
	"Christian König" <christian.koenig@amd.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Pan Xinhui" <Xinhui.Pan@amd.com>,
	"David Airlie" <airlied@gmail.com>,
	"Daniel Vetter" <daniel@ffwll.ch>,
	"Pierre-Eric Pelloux-Prayer" <pierre-eric.pelloux-prayer@amd.com>,
	"Huacai Chen" <chenhuacai@kernel.org>,
	"WANG Xuerui" <kernel@xen0n.name>
Cc: amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, loongarch@lists.linux.dev
Subject: Re: [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content
Date: Tue, 18 Jun 2024 08:20:25 +0200	[thread overview]
Message-ID: <a57fd6cd-d9e4-4ac0-8d53-06d6149e196a@amd.com> (raw)
In-Reply-To: <73597116d4f004c5f75cf4f13da1af405ea8da8b.camel@icenowy.me>

[-- Attachment #1: Type: text/plain, Size: 651 bytes --]

Am 17.06.24 um 18:09 schrieb Icenowy Zheng:
> BTW is there any operation that could be taken to examine this specific
> workaround?
>
> Is there any case possible to reproduce?

No idea, I mean that's for GFX7/8 which was released between 2013 and 2017.

My educated guess is that you could create a test where you write 
something to VRAM or GTT with a shader and than in the interrupt handler 
try to observer if you can see those values with the CPU.

If those values aren't visible with the CPU then you have either a cache 
flushing issue or your CPU and/or PCIe root complex is incorrectly 
reordering writes and interrupts.

Regards,
Christian.

[-- Attachment #2: Type: text/html, Size: 1082 bytes --]

  reply	other threads:[~2024-06-18  6:20 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-17 10:58 [PATCH 0/2] Fixes of AMD GFX7/8 hang on Loongson platforms Icenowy Zheng
2024-06-17 10:58 ` [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content Icenowy Zheng
2024-06-17 12:35   ` Christian König
2024-06-17 13:03     ` Icenowy Zheng
2024-06-17 13:09       ` Christian König
2024-06-17 13:43         ` Icenowy Zheng
2024-06-17 13:59           ` Christian König
2024-06-17 14:30             ` Icenowy Zheng
2024-06-17 14:42               ` Christian König
2024-06-17 14:57                 ` Icenowy Zheng
2024-06-17 15:07                   ` Christian König
2024-06-17 15:35               ` Xi Ruoyao
2024-06-17 15:53                 ` Christian König
2024-06-17 16:09             ` Icenowy Zheng
2024-06-18  6:20               ` Christian König [this message]
2024-06-17 10:58 ` [PATCH 2/2] drm/radeon: repeat the same EOP packet for EOP workaround on CIK Icenowy Zheng

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=a57fd6cd-d9e4-4ac0-8d53-06d6149e196a@amd.com \
    --to=christian.koenig@amd.com \
    --cc=Xinhui.Pan@amd.com \
    --cc=airlied@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=chenhuacai@kernel.org \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=kernel@xen0n.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=loongarch@lists.linux.dev \
    --cc=pierre-eric.pelloux-prayer@amd.com \
    --cc=uwu@icenowy.me \
    /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.