From: Oded Gabbay <oded.gabbay@amd.com>
To: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: "Andrew Lewycky" <Andrew.Lewycky@amd.com>,
"Michel Dänzer" <michel.daenzer@amd.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"dri-devel@lists.freedesktop.org"
<dri-devel@lists.freedesktop.org>, linux-mm <linux-mm@kvack.org>,
"Alexey Skidanov" <Alexey.Skidanov@amd.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Sellek, Tom" <Tom.Sellek@amd.com>
Subject: Re: [PATCH v2 00/25] AMDKFD kernel driver
Date: Tue, 22 Jul 2014 12:52:43 +0300 [thread overview]
Message-ID: <53CE346B.1080601@amd.com> (raw)
In-Reply-To: <CAKMK7uH+okhn4YGOzrXZ1LM3S2myxdu=_63LGMduwV-WZn06CA@mail.gmail.com>
On 22/07/14 12:21, Daniel Vetter wrote:
> On Tue, Jul 22, 2014 at 10:19 AM, Oded Gabbay <oded.gabbay@amd.com> wrote:
>>> Exactly, just prevent userspace from submitting more. And if you have
>>> misbehaving userspace that submits too much, reset the gpu and tell it
>>> that you're sorry but won't schedule any more work.
>>
>> I'm not sure how you intend to know if a userspace misbehaves or not. Can
>> you elaborate ?
>
> Well that's mostly policy, currently in i915 we only have a check for
> hangs, and if userspace hangs a bit too often then we stop it. I guess
> you can do that with the queue unmapping you've describe in reply to
> Jerome's mail.
> -Daniel
>
What do you mean by hang ? Like the tdr mechanism in Windows (checks if a gpu
job takes more than 2 seconds, I think, and if so, terminates the job).
Oded
WARNING: multiple messages have this Message-ID (diff)
From: Oded Gabbay <oded.gabbay@amd.com>
To: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: "Jerome Glisse" <j.glisse@gmail.com>,
"Christian König" <deathsimple@vodafone.de>,
"David Airlie" <airlied@linux.ie>,
"Alex Deucher" <alexdeucher@gmail.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"John Bridgman" <John.Bridgman@amd.com>,
"Joerg Roedel" <joro@8bytes.org>,
"Andrew Lewycky" <Andrew.Lewycky@amd.com>,
"Michel Dänzer" <michel.daenzer@amd.com>,
"Ben Goz" <Ben.Goz@amd.com>,
"Alexey Skidanov" <Alexey.Skidanov@amd.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"dri-devel@lists.freedesktop.org"
<dri-devel@lists.freedesktop.org>, linux-mm <linux-mm@kvack.org>,
"Sellek, Tom" <Tom.Sellek@amd.com>
Subject: Re: [PATCH v2 00/25] AMDKFD kernel driver
Date: Tue, 22 Jul 2014 12:52:43 +0300 [thread overview]
Message-ID: <53CE346B.1080601@amd.com> (raw)
In-Reply-To: <CAKMK7uH+okhn4YGOzrXZ1LM3S2myxdu=_63LGMduwV-WZn06CA@mail.gmail.com>
On 22/07/14 12:21, Daniel Vetter wrote:
> On Tue, Jul 22, 2014 at 10:19 AM, Oded Gabbay <oded.gabbay@amd.com> wrote:
>>> Exactly, just prevent userspace from submitting more. And if you have
>>> misbehaving userspace that submits too much, reset the gpu and tell it
>>> that you're sorry but won't schedule any more work.
>>
>> I'm not sure how you intend to know if a userspace misbehaves or not. Can
>> you elaborate ?
>
> Well that's mostly policy, currently in i915 we only have a check for
> hangs, and if userspace hangs a bit too often then we stop it. I guess
> you can do that with the queue unmapping you've describe in reply to
> Jerome's mail.
> -Daniel
>
What do you mean by hang ? Like the tdr mechanism in Windows (checks if a gpu
job takes more than 2 seconds, I think, and if so, terminates the job).
Oded
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Oded Gabbay <oded.gabbay@amd.com>
To: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: "Jerome Glisse" <j.glisse@gmail.com>,
"Christian König" <deathsimple@vodafone.de>,
"David Airlie" <airlied@linux.ie>,
"Alex Deucher" <alexdeucher@gmail.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"John Bridgman" <John.Bridgman@amd.com>,
"Joerg Roedel" <joro@8bytes.org>,
"Andrew Lewycky" <Andrew.Lewycky@amd.com>,
"Michel Dänzer" <michel.daenzer@amd.com>,
"Ben Goz" <Ben.Goz@amd.com>,
"Alexey Skidanov" <Alexey.Skidanov@amd.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"dri-devel@lists.freedesktop.org"
<dri-devel@lists.freedesktop.org>, linux-mm <linux-mm@kvack.org>,
"Sellek, Tom" <Tom.Sellek@amd.com>
Subject: Re: [PATCH v2 00/25] AMDKFD kernel driver
Date: Tue, 22 Jul 2014 12:52:43 +0300 [thread overview]
Message-ID: <53CE346B.1080601@amd.com> (raw)
In-Reply-To: <CAKMK7uH+okhn4YGOzrXZ1LM3S2myxdu=_63LGMduwV-WZn06CA@mail.gmail.com>
On 22/07/14 12:21, Daniel Vetter wrote:
> On Tue, Jul 22, 2014 at 10:19 AM, Oded Gabbay <oded.gabbay@amd.com> wrote:
>>> Exactly, just prevent userspace from submitting more. And if you have
>>> misbehaving userspace that submits too much, reset the gpu and tell it
>>> that you're sorry but won't schedule any more work.
>>
>> I'm not sure how you intend to know if a userspace misbehaves or not. Can
>> you elaborate ?
>
> Well that's mostly policy, currently in i915 we only have a check for
> hangs, and if userspace hangs a bit too often then we stop it. I guess
> you can do that with the queue unmapping you've describe in reply to
> Jerome's mail.
> -Daniel
>
What do you mean by hang ? Like the tdr mechanism in Windows (checks if a gpu
job takes more than 2 seconds, I think, and if so, terminates the job).
Oded
next prev parent reply other threads:[~2014-07-22 9:53 UTC|newest]
Thread overview: 148+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-17 13:57 [PATCH v2 00/25] AMDKFD kernel driver Oded Gabbay
2014-07-17 13:57 ` Oded Gabbay
2014-07-17 13:57 ` Oded Gabbay
2014-07-20 17:46 ` Jerome Glisse
2014-07-20 17:46 ` Jerome Glisse
2014-07-20 17:46 ` Jerome Glisse
2014-07-21 3:03 ` Jerome Glisse
2014-07-21 3:03 ` Jerome Glisse
2014-07-21 3:03 ` Jerome Glisse
2014-07-21 7:01 ` Daniel Vetter
2014-07-21 7:01 ` Daniel Vetter
2014-07-21 9:34 ` Christian König
2014-07-21 9:34 ` Christian König
2014-07-21 12:36 ` Oded Gabbay
2014-07-21 12:36 ` Oded Gabbay
2014-07-21 12:36 ` Oded Gabbay
2014-07-21 13:39 ` Christian König
2014-07-21 13:39 ` Christian König
2014-07-21 13:39 ` Christian König
2014-07-21 14:12 ` Oded Gabbay
2014-07-21 14:12 ` Oded Gabbay
2014-07-21 14:12 ` Oded Gabbay
2014-07-21 15:54 ` Jerome Glisse
2014-07-21 15:54 ` Jerome Glisse
2014-07-21 15:54 ` Jerome Glisse
2014-07-21 17:42 ` Oded Gabbay
2014-07-21 17:42 ` Oded Gabbay
2014-07-21 17:42 ` Oded Gabbay
2014-07-21 18:14 ` Jerome Glisse
2014-07-21 18:14 ` Jerome Glisse
2014-07-21 18:14 ` Jerome Glisse
2014-07-21 18:36 ` Oded Gabbay
2014-07-21 18:36 ` Oded Gabbay
2014-07-21 18:36 ` Oded Gabbay
2014-07-21 18:59 ` Jerome Glisse
2014-07-21 18:59 ` Jerome Glisse
2014-07-21 18:59 ` Jerome Glisse
2014-07-21 19:23 ` Oded Gabbay
2014-07-21 19:23 ` Oded Gabbay
2014-07-21 19:23 ` Oded Gabbay
2014-07-21 19:28 ` Jerome Glisse
2014-07-21 19:28 ` Jerome Glisse
2014-07-21 19:28 ` Jerome Glisse
2014-07-21 21:56 ` Oded Gabbay
2014-07-21 21:56 ` Oded Gabbay
2014-07-21 21:56 ` Oded Gabbay
2014-07-21 23:05 ` Jerome Glisse
2014-07-21 23:05 ` Jerome Glisse
2014-07-21 23:05 ` Jerome Glisse
2014-07-21 23:29 ` Bridgman, John
2014-07-21 23:29 ` Bridgman, John
2014-07-21 23:36 ` Jerome Glisse
2014-07-21 23:36 ` Jerome Glisse
2014-07-21 23:36 ` Jerome Glisse
2014-07-22 8:05 ` Oded Gabbay
2014-07-22 8:05 ` Oded Gabbay
2014-07-22 8:05 ` Oded Gabbay
2014-07-22 7:23 ` Daniel Vetter
2014-07-22 7:23 ` Daniel Vetter
2014-07-22 7:23 ` Daniel Vetter
2014-07-22 8:10 ` Oded Gabbay
2014-07-22 8:10 ` Oded Gabbay
2014-07-21 15:25 ` Daniel Vetter
2014-07-21 15:25 ` Daniel Vetter
2014-07-21 15:25 ` Daniel Vetter
2014-07-21 15:58 ` Jerome Glisse
2014-07-21 15:58 ` Jerome Glisse
2014-07-21 15:58 ` Jerome Glisse
2014-07-21 17:05 ` Daniel Vetter
2014-07-21 17:05 ` Daniel Vetter
2014-07-21 17:05 ` Daniel Vetter
2014-07-21 17:28 ` Oded Gabbay
2014-07-21 17:28 ` Oded Gabbay
2014-07-21 17:28 ` Oded Gabbay
2014-07-21 18:22 ` Daniel Vetter
2014-07-21 18:22 ` Daniel Vetter
2014-07-21 18:22 ` Daniel Vetter
2014-07-21 18:41 ` Oded Gabbay
2014-07-21 18:41 ` Oded Gabbay
2014-07-21 18:41 ` Oded Gabbay
2014-07-21 19:03 ` Jerome Glisse
2014-07-21 19:03 ` Jerome Glisse
2014-07-21 19:03 ` Jerome Glisse
2014-07-22 7:28 ` Daniel Vetter
2014-07-22 7:28 ` Daniel Vetter
2014-07-22 7:28 ` Daniel Vetter
2014-07-22 7:40 ` Daniel Vetter
2014-07-22 7:40 ` Daniel Vetter
2014-07-22 8:21 ` Oded Gabbay
2014-07-22 8:21 ` Oded Gabbay
2014-07-22 8:19 ` Oded Gabbay
2014-07-22 8:19 ` Oded Gabbay
2014-07-22 9:21 ` Daniel Vetter
2014-07-22 9:21 ` Daniel Vetter
2014-07-22 9:21 ` Daniel Vetter
2014-07-22 9:24 ` Daniel Vetter
2014-07-22 9:24 ` Daniel Vetter
2014-07-22 9:24 ` Daniel Vetter
2014-07-22 9:52 ` Oded Gabbay [this message]
2014-07-22 9:52 ` Oded Gabbay
2014-07-22 9:52 ` Oded Gabbay
2014-07-22 11:15 ` Daniel Vetter
2014-07-22 11:15 ` Daniel Vetter
2014-07-23 6:50 ` Oded Gabbay
2014-07-23 6:50 ` Oded Gabbay
2014-07-23 7:04 ` Christian König
2014-07-23 7:04 ` Christian König
2014-07-23 13:39 ` Bridgman, John
2014-07-23 13:39 ` Bridgman, John
2014-07-23 14:56 ` Jerome Glisse
2014-07-23 14:56 ` Jerome Glisse
2014-07-23 14:56 ` Jerome Glisse
2014-07-23 19:49 ` Alex Deucher
2014-07-23 19:49 ` Alex Deucher
2014-07-23 20:25 ` Jerome Glisse
2014-07-23 20:25 ` Jerome Glisse
2014-07-23 20:25 ` Jerome Glisse
2014-07-23 7:05 ` Daniel Vetter
2014-07-23 7:05 ` Daniel Vetter
2014-07-23 7:05 ` Daniel Vetter
2014-07-23 8:35 ` Oded Gabbay
2014-07-23 8:35 ` Oded Gabbay
2014-07-23 8:35 ` Oded Gabbay
2014-07-23 13:33 ` Bridgman, John
2014-07-23 13:33 ` Bridgman, John
2014-07-23 13:33 ` Bridgman, John
2014-07-23 14:41 ` Daniel Vetter
2014-07-23 14:41 ` Daniel Vetter
2014-07-23 14:41 ` Daniel Vetter
2014-07-23 15:06 ` Bridgman, John
2014-07-23 15:06 ` Bridgman, John
2014-07-23 15:06 ` Bridgman, John
2014-07-23 15:12 ` Bridgman, John
2014-07-23 15:12 ` Bridgman, John
2014-07-23 15:12 ` Bridgman, John
2014-07-23 20:59 ` Jesse Barnes
2014-07-23 21:46 ` Bridgman, John
2014-07-23 22:01 ` Oded Gabbay
2014-07-24 15:44 ` Jerome Glisse
2014-07-24 15:44 ` Jerome Glisse
2014-07-24 17:35 ` Alex Deucher
2014-07-24 17:35 ` Alex Deucher
2014-07-24 18:47 ` Jerome Glisse
2014-07-24 18:47 ` Jerome Glisse
2014-07-24 18:57 ` Oded Gabbay
2014-07-24 18:57 ` Oded Gabbay
2014-07-24 20:26 ` Jerome Glisse
2014-07-24 20:26 ` Jerome Glisse
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=53CE346B.1080601@amd.com \
--to=oded.gabbay@amd.com \
--cc=Alexey.Skidanov@amd.com \
--cc=Andrew.Lewycky@amd.com \
--cc=Tom.Sellek@amd.com \
--cc=akpm@linux-foundation.org \
--cc=daniel.vetter@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=michel.daenzer@amd.com \
/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.