All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Christian König" <ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Jay Cornwall <jay-gJmSnxjMpeIS+FvcfC7Uqw@public.gmane.org>,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH 02/12] drm/amdgpu: send IVs to the KFD only after processing them
Date: Thu, 27 Sep 2018 11:32:02 +0200	[thread overview]
Message-ID: <fa8dd071-ca32-d2d7-74c6-dd5eff132aae@gmail.com> (raw)
In-Reply-To: <1537986270.3887323.1521702048.0DEA7A63-2RFepEojUI2N1INw9kWLP6GC3tUn3ZHUQQ4Iyu8u01E@public.gmane.org>

Am 26.09.2018 um 20:24 schrieb Jay Cornwall:
> On Wed, Sep 26, 2018, at 08:53, Christian König wrote:
>> This allows us to filter out VM faults in the GMC code.
>>
>> Signed-off-by: Christian König <christian.koenig@amd.com>
> The KFD needs to receive notification of unhandled VM faults; when demand paging is disabled or the address is not pageable. It propagates this to the UMD (ROC runtime or the ROC debugger).
>
> Does this patch change that behavior?

Potentially yes. We have some code in the GMC handling for this, but I'm 
actually not sure if that is the used path.

Thanks for the comment, I will take that into account and only block 
forwarding to the KFD if the GMC really filtered the request.

Christian.

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

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

  parent reply	other threads:[~2018-09-27  9:32 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-26 13:53 [PATCH 01/12] drm/amdgpu: add missing error handling Christian König
     [not found] ` <20180926135330.2218-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-26 13:53   ` [PATCH 02/12] drm/amdgpu: send IVs to the KFD only after processing them Christian König
     [not found]     ` <20180926135330.2218-2-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-26 18:24       ` Jay Cornwall
     [not found]         ` <1537986270.3887323.1521702048.0DEA7A63-2RFepEojUI2N1INw9kWLP6GC3tUn3ZHUQQ4Iyu8u01E@public.gmane.org>
2018-09-27  9:32           ` Christian König [this message]
2018-09-26 13:53   ` [PATCH 03/12] drm/amdgpu: remove VM fault_credit handling Christian König
2018-09-26 13:53   ` [PATCH 04/12] drm/amdgpu: move IV prescreening into the GMC code Christian König
     [not found]     ` <20180926135330.2218-4-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-10-09 23:46       ` Felix Kuehling
     [not found]         ` <dcf7fd50-e453-8a9d-cdaa-c452d4716e9a-5C7GfCeVMHo@public.gmane.org>
2018-10-10  7:08           ` Christian König
2018-09-26 13:53   ` [PATCH 05/12] drm/amdgpu: remove IV prescreening Christian König
     [not found]     ` <20180926135330.2218-5-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-27 10:28       ` Huang Rui
2018-09-26 13:53   ` [PATCH 06/12] drm/amdgpu: add IH ring to ih_get_wptr/ih_set_rptr v2 Christian König
2018-09-26 13:53   ` [PATCH 07/12] drm/amdgpu: simplify IH programming Christian König
2018-09-26 13:53   ` [PATCH 08/12] drm/amdgpu: enable IH ring 1 and ring 2 v2 Christian König
2018-09-26 13:53   ` [PATCH 09/12] drm/amdgpu: add the IH to the IV trace Christian König
2018-09-26 13:53   ` [PATCH 10/12] drm/amdgpu: add support for processing IH ring 1 & 2 Christian König
2018-09-26 13:53   ` [PATCH 11/12] drm/amdgpu: add support for self irq on Vega10 Christian König
     [not found]     ` <20180926135330.2218-11-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-09-26 19:19       ` Alex Deucher
2018-09-26 13:53   ` [PATCH 12/12] drm/amdgpu: disable IH ring 2 WPTR overflow " Christian König
2018-09-27 10:00   ` [PATCH 01/12] drm/amdgpu: add missing error handling Huang Rui
2018-09-27 11:25     ` Christian König
     [not found]       ` <e3ab66c9-41b1-c0cd-8f72-07f4eebff70b-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-09-28  7:36         ` Huang, Ray
     [not found]           ` <BY2PR12MB0040E69C83DAC1B5136F95E4ECEC0-K//h7OWB4q7Zvl48JdS6+wdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2018-10-03 14:25             ` Christian König

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=fa8dd071-ca32-d2d7-74c6-dd5eff132aae@gmail.com \
    --to=ckoenig.leichtzumerken-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
    --cc=christian.koenig-5C7GfCeVMHo@public.gmane.org \
    --cc=jay-gJmSnxjMpeIS+FvcfC7Uqw@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.