Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <784561bb-0937-befc-3774-892d6f6a4318@mailbox.org>
Date:   Tue, 25 Apr 2023 12:27:37 +0200
MIME-Version: 1.0
Subject: Re: [PATCH] drm/amdgpu: Mark contexts guilty for any reset type
Content-Language: de-CH-frami, en-CA
To:     =?UTF-8?B?TWFyZWsgT2zFocOhaw==?= <maraeo@gmail.com>,
        =?UTF-8?Q?Christian_K=c3=b6nig?= <christian.koenig@amd.com>
Cc:     Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>,
        =?UTF-8?Q?Andr=c3=a9_Almeida?= <andrealmeid@igalia.com>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        amd-gfx mailing list <amd-gfx@lists.freedesktop.org>,
        "Tuikov, Luben" <Luben.Tuikov@amd.com>,
        dri-devel <dri-devel@lists.freedesktop.org>,
        kernel-dev@igalia.com,
        "Deucher, Alexander" <alexander.deucher@amd.com>
References: <20230424014324.218531-1-andrealmeid@igalia.com>
 <d7264c5a-29b4-0fb3-153b-673a8a73d635@amd.com>
 <CAAxE2A6Soq28ACV-m1OzG8CA-_VWp+N2wapsABzm2Nda=Qe+yA@mail.gmail.com>
From:   =?UTF-8?Q?Michel_D=c3=a4nzer?= <michel.daenzer@mailbox.org>
In-Reply-To: <CAAxE2A6Soq28ACV-m1OzG8CA-_VWp+N2wapsABzm2Nda=Qe+yA@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 4/24/23 18:45, Marek Olšák wrote:
> Soft resets are fatal just as hard resets, but no reset is "always fatal". There are cases when apps keep working depending on which features are being used. It's still unsafe.

Agreed, in theory.

In practice, from a user PoV, right now there's pretty much 0 chance of the user session surviving if the GPU context in certain critical processes (e.g. the Wayland compositor or Xwayland) hits a fatal reset. There's a > 0 chance of it surviving after a soft reset. There's ongoing work towards making user-space components more robust against fatal resets, but it's taking time. Meanwhile, I suspect most users would take the > 0 chance.


-- 
Earthling Michel Dänzer            |                  https://redhat.com
Libre software enthusiast          |         Mesa and Xwayland developer