<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<div class="moz-cite-prefix">Ok how about this:<br>
<br>
We add a debugfs file which when read returns the GFXOFF status
and when written with a number disabled GFXOFF for N seconds with
0 meaning forever.<br>
<br>
Umr gets a new commandline option to write to that file before
reading registers.<br>
<br>
This way the user can still disable it if it causes any problems.
Does that sounds like a plan?<br>
<br>
Regards,<br>
Christian.<br>
<br>
Am 21.02.20 um 16:56 schrieb Deucher, Alexander:<br>
</div>
<blockquote type="cite"
cite="mid:CH2PR12MB39120922B0E459A5721F0A15F7120@CH2PR12MB3912.namprd12.prod.outlook.com">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
<p
style="font-family:Arial;font-size:10pt;color:#317100;margin:15pt;"
align="Left">
[AMD Public Use]<br>
</p>
<br>
<div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
Not at the moment. But we could add a debugfs file which just
wraps <font size="2">
<span style="font-size:11pt">amdgpu_gfx_off_ctrl</span></font>().
That said, maybe we just add a delay here or a use a timer to
delay turning gfxoff back on again so that we aren't turning
it on and off so rapidly.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
Alex</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font style="font-size:11pt"
face="Calibri, sans-serif" color="#000000"><b>From:</b>
Christian König <a class="moz-txt-link-rfc2396E" href="mailto:ckoenig.leichtzumerken@gmail.com"><ckoenig.leichtzumerken@gmail.com></a><br>
<b>Sent:</b> Friday, February 21, 2020 10:43 AM<br>
<b>To:</b> Deucher, Alexander
<a class="moz-txt-link-rfc2396E" href="mailto:Alexander.Deucher@amd.com"><Alexander.Deucher@amd.com></a>; Huang, Ray
<a class="moz-txt-link-rfc2396E" href="mailto:Ray.Huang@amd.com"><Ray.Huang@amd.com></a>; Liu, Monk
<a class="moz-txt-link-rfc2396E" href="mailto:Monk.Liu@amd.com"><Monk.Liu@amd.com></a><br>
<b>Cc:</b> StDenis, Tom <a class="moz-txt-link-rfc2396E" href="mailto:Tom.StDenis@amd.com"><Tom.StDenis@amd.com></a>; Alex
Deucher <a class="moz-txt-link-rfc2396E" href="mailto:alexdeucher@gmail.com"><alexdeucher@gmail.com></a>; amd-gfx list
<a class="moz-txt-link-rfc2396E" href="mailto:amd-gfx@lists.freedesktop.org"><amd-gfx@lists.freedesktop.org></a><br>
<b>Subject:</b> Re: 回复: [PATCH] drm/amd/amdgpu: disable
GFXOFF around debugfs access to MMIO</font>
<div> </div>
</div>
<div style="background-color:#FFFFFF">
<div class="x_moz-cite-prefix">Do we have a way to disable
GFXOFF on the fly?<br>
<br>
If not maybe it would be a good idea to add a separate
debugfs file to do this.<br>
<br>
Christian.<br>
<br>
Am 21.02.20 um 16:39 schrieb Deucher, Alexander:<br>
</div>
<blockquote type="cite">
<style type="text/css" style="display:none">
<!--
p
{margin-top:0;
margin-bottom:0}
-->
</style>
<p style="font-family:Arial; font-size:10pt; color:#317100;
margin:15pt" align="Left">
[AMD Public Use]<br>
</p>
<br>
<div>
<div
style="font-family:Calibri,Arial,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)">
If we are trying to debug a reproducible hang, probably
best to just to disable gfxoff before messing with it to
remove that as a factor. Otherwise, the method included
in this patch is the proper way to disable/enable GFXOFF
dynamically.</div>
<div
style="font-family:Calibri,Arial,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)">
<br>
</div>
<div
style="font-family:Calibri,Arial,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)">
Alex</div>
<div
style="font-family:Calibri,Arial,Helvetica,sans-serif;
font-size:12pt; color:rgb(0,0,0)">
<br>
</div>
<hr tabindex="-1" style="display:inline-block; width:98%">
<div id="x_divRplyFwdMsg" dir="ltr"><font
style="font-size:11pt" face="Calibri, sans-serif"
color="#000000"><b>From:</b> amd-gfx
<a class="x_moz-txt-link-rfc2396E"
href="mailto:amd-gfx-bounces@lists.freedesktop.org"
moz-do-not-send="true">
<amd-gfx-bounces@lists.freedesktop.org></a> on
behalf of Christian König <a
class="x_moz-txt-link-rfc2396E"
href="mailto:ckoenig.leichtzumerken@gmail.com"
moz-do-not-send="true">
<ckoenig.leichtzumerken@gmail.com></a><br>
<b>Sent:</b> Friday, February 21, 2020 10:27 AM<br>
<b>To:</b> Huang, Ray <a
class="x_moz-txt-link-rfc2396E"
href="mailto:Ray.Huang@amd.com"
moz-do-not-send="true">
<Ray.Huang@amd.com></a>; Liu, Monk <a
class="x_moz-txt-link-rfc2396E"
href="mailto:Monk.Liu@amd.com"
moz-do-not-send="true">
<Monk.Liu@amd.com></a><br>
<b>Cc:</b> StDenis, Tom <a
class="x_moz-txt-link-rfc2396E"
href="mailto:Tom.StDenis@amd.com"
moz-do-not-send="true">
<Tom.StDenis@amd.com></a>; Alex Deucher <a
class="x_moz-txt-link-rfc2396E"
href="mailto:alexdeucher@gmail.com"
moz-do-not-send="true">
<alexdeucher@gmail.com></a>; amd-gfx list <a
class="x_moz-txt-link-rfc2396E"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">
<amd-gfx@lists.freedesktop.org></a><br>
<b>Subject:</b> Re: 回复: [PATCH] drm/amd/amdgpu:
disable GFXOFF around debugfs access to MMIO</font>
<div> </div>
</div>
<div class="x_BodyFragment"><font size="2"><span
style="font-size:11pt">
<div class="x_PlainText">Am 21.02.20 um 16:23
schrieb Huang Rui:<br>
> On Fri, Feb 21, 2020 at 11:18:07PM +0800,
Liu, Monk wrote:<br>
>> Better not use KIQ, because when you use
debugfs to read register you usually hit a hang,
and by that case KIQ probably already die<br>
> If CP is busy, the gfx should be in "on"
state at that time, we needn't use KIQ.<br>
<br>
Yeah, but how do you detect that? Do we have a way
to wake up the CP <br>
without asking power management to do so?<br>
<br>
Cause the register debug interface is meant to be
used when the ASIC is <br>
completed locked up. Sending messages to the SMU
is not really going to <br>
work in that situation.<br>
<br>
Regards,<br>
Christian.<br>
<br>
><br>
> Thanks,<br>
> Ray<br>
><br>
>> -----邮件原件-----<br>
>> 发件人: amd-gfx <a
class="x_moz-txt-link-rfc2396E"
href="mailto:amd-gfx-bounces@lists.freedesktop.org"
moz-do-not-send="true">
<amd-gfx-bounces@lists.freedesktop.org></a>
代表 Huang Rui<br>
>> 发送时间: 2020年2月21日 22:34<br>
>> 收件人: StDenis, Tom <a
class="x_moz-txt-link-rfc2396E"
href="mailto:Tom.StDenis@amd.com"
moz-do-not-send="true">
<Tom.StDenis@amd.com></a><br>
>> 抄送: Alex Deucher <a
class="x_moz-txt-link-rfc2396E"
href="mailto:alexdeucher@gmail.com"
moz-do-not-send="true">
<alexdeucher@gmail.com></a>; amd-gfx list
<a class="x_moz-txt-link-rfc2396E"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">
<amd-gfx@lists.freedesktop.org></a><br>
>> 主题: Re: [PATCH] drm/amd/amdgpu: disable
GFXOFF around debugfs access to MMIO<br>
>><br>
>> On Wed, Feb 19, 2020 at 10:09:46AM -0500,
Tom St Denis wrote:<br>
>>> I got some messages after a while:<br>
>>><br>
>>> [ 741.788564] Failed to send Message
8.<br>
>>> [ 746.671509] Failed to send Message
8.<br>
>>> [ 748.749673] Failed to send Message
2b.<br>
>>> [ 759.245414] Failed to send Message
7.<br>
>>> [ 763.216902] Failed to send Message
2a.<br>
>>><br>
>>> Are there any additional locks that
should be held? Because some<br>
>>> commands like --top or --waves can do
a lot of distinct read<br>
>>> operations (causing a lot of
enable/disable calls).<br>
>>><br>
>>> I'm going to sit on this a bit since
I don't think the patch is ready<br>
>>> for pushing out.<br>
>>><br>
>> How about use RREG32_KIQ and WREG32_KIQ?<br>
>><br>
>> Thanks,<br>
>> Ray<br>
>><br>
>>> Tom<br>
>>><br>
>>> On 2020-02-19 10:07 a.m., Alex
Deucher wrote:<br>
>>>> On Wed, Feb 19, 2020 at 10:04 AM
Tom St Denis <a class="x_moz-txt-link-rfc2396E"
href="mailto:tom.stdenis@amd.com"
moz-do-not-send="true">
<tom.stdenis@amd.com></a> wrote:<br>
>>>>> Signed-off-by: Tom St Denis <a
class="x_moz-txt-link-rfc2396E"
href="mailto:tom.stdenis@amd.com"
moz-do-not-send="true">
<tom.stdenis@amd.com></a><br>
>>>> Please add a patch description.
With that fixed:<br>
>>>> Reviewed-by: Alex Deucher <a
class="x_moz-txt-link-rfc2396E"
href="mailto:alexander.deucher@amd.com"
moz-do-not-send="true">
<alexander.deucher@amd.com></a><br>
>>>><br>
>>>>> ---<br>
>>>>>
drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 3
+++<br>
>>>>> 1 file changed, 3
insertions(+)<br>
>>>>><br>
>>>>> diff --git
a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c<br>
>>>>>
b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c<br>
>>>>> index
7379910790c9..66f763300c96 100644<br>
>>>>> ---
a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c<br>
>>>>> +++
b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c<br>
>>>>> @@ -169,6 +169,7 @@ static
int amdgpu_debugfs_process_reg_op(bool read,
struct file *f,<br>
>>>>> if (pm_pg_lock)<br>
>>>>>
mutex_lock(&adev->pm.mutex);<br>
>>>>><br>
>>>>> +
amdgpu_gfx_off_ctrl(adev, false);<br>
>>>>> while (size) {<br>
>>>>> uint32_t
value;<br>
>>>>><br>
>>>>> @@ -192,6 +193,8 @@ static
int amdgpu_debugfs_process_reg_op(bool read,
struct file *f,<br>
>>>>> }<br>
>>>>><br>
>>>>> end:<br>
>>>>> +
amdgpu_gfx_off_ctrl(adev, true);<br>
>>>>> +<br>
>>>>> if (use_bank) {<br>
>>>>>
amdgpu_gfx_select_se_sh(adev, 0xffffffff,
0xffffffff, 0xffffffff);<br>
>>>>>
mutex_unlock(&adev->grbm_idx_mutex);<br>
>>>>> --<br>
>>>>> 2.24.1<br>
>>>>><br>
>>>>>
_______________________________________________<br>
>>>>> amd-gfx mailing list<br>
>>>>> <a
class="x_moz-txt-link-abbreviated"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">
amd-gfx@lists.freedesktop.org</a><br>
>>>>> <a
href="https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2F"
moz-do-not-send="true">
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2F</a><br>
>>>>>
lists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7<br>
>>>>>
C01%7Cmonk.liu%40amd.com%7Cba45efb26c0240ed036f08d7b6db20aa%7C3dd8<br>
>>>>>
961fe4884e608e11a82d994e183d%7C0%7C0%7C637178924605524378&sdat<br>
>>>>>
a=%2FyHkvYU5T%2F4iFxRexsg%2BIdm7sDzyXbjzNpHUGCO7h4k%3D&reserve<br>
>>>>> d=0<br>
>>>
_______________________________________________<br>
>>> amd-gfx mailing list<br>
>>> <a
class="x_moz-txt-link-abbreviated"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">
amd-gfx@lists.freedesktop.org</a><br>
>>> <a
href="https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist"
moz-do-not-send="true">
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist</a><br>
>>>
s.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Cmo<br>
>>>
nk.liu%40amd.com%7Cba45efb26c0240ed036f08d7b6db20aa%7C3dd8961fe4884e60<br>
>>>
8e11a82d994e183d%7C0%7C0%7C637178924605524378&sdata=%2FyHkvYU5T%2F<br>
>>>
4iFxRexsg%2BIdm7sDzyXbjzNpHUGCO7h4k%3D&reserved=0<br>
>>
_______________________________________________<br>
>> amd-gfx mailing list<br>
>> <a class="x_moz-txt-link-abbreviated"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">
amd-gfx@lists.freedesktop.org</a><br>
>> <a
href="https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7CAlexander.Deucher%40amd.com%7C50c08a2474b346c44c0608d7b6e4d3ff%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637178966243976347&sdata=yQgD1Ywji%2BimCVr06LD0oSnf4ZHGmoN3s8a5NybPx4E%3D&reserved=0"
originalsrc="https://lists.freedesktop.org/mailman/listinfo/amd-gfx"
shash="LqtLGEoomD1bdinw+EjRXZ2OeqKLF5oWf5aHZFEbAfd8xh8rXUIh8fVv+uoJMV9lkffB2syhnIgBLq2tJlSoZoFMbWd3pDTkmt/cpnIC/ExDYy93x3/F1MKt9QH2q0IeK+cT6UKhA+msphzGLXbA3CpORfb4qAfA9cQ6c5Sj/aw="
moz-do-not-send="true">
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Calexander.deucher%40amd.com%7Cf3762304925b4019bfed08d7b6e287e4%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637178957179179431&sdata=bY7V%2BKOF3gYu4ITGCKgAiRvXUvxPcwsz2zsEJDns3jI%3D&reserved=0</a><br>
>
_______________________________________________<br>
> amd-gfx mailing list<br>
> <a class="x_moz-txt-link-abbreviated"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">
amd-gfx@lists.freedesktop.org</a><br>
> <a
href="https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7CAlexander.Deucher%40amd.com%7C50c08a2474b346c44c0608d7b6e4d3ff%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637178966243986301&sdata=5vafv2zCFbpgaSpgcQzLaEAC3wnqkIvGbrvKH3M11s4%3D&reserved=0"
originalsrc="https://lists.freedesktop.org/mailman/listinfo/amd-gfx"
shash="sNRPT35y/6wAGc9zONfY2DSN5loMxxR+oVuiO5qrFk03ANo8/FqIdLmGd8kP4FMnklSakEDVDNeoS97JRFWxUprHaeWBQ0oR5sa7gvhRu1pOw80jjDWxuhfZlFd9xVwkCV31z4wE5g4aPUlsN7IiAfNzmJwQ3sF2RnQONHZuBF4="
moz-do-not-send="true">
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Calexander.deucher%40amd.com%7Cf3762304925b4019bfed08d7b6e287e4%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637178957179179431&sdata=bY7V%2BKOF3gYu4ITGCKgAiRvXUvxPcwsz2zsEJDns3jI%3D&reserved=0</a><br>
<br>
_______________________________________________<br>
amd-gfx mailing list<br>
<a class="x_moz-txt-link-abbreviated"
href="mailto:amd-gfx@lists.freedesktop.org"
moz-do-not-send="true">amd-gfx@lists.freedesktop.org</a><br>
<a
href="https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7CAlexander.Deucher%40amd.com%7C50c08a2474b346c44c0608d7b6e4d3ff%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637178966243986301&sdata=5vafv2zCFbpgaSpgcQzLaEAC3wnqkIvGbrvKH3M11s4%3D&reserved=0"
originalsrc="https://lists.freedesktop.org/mailman/listinfo/amd-gfx"
shash="sNRPT35y/6wAGc9zONfY2DSN5loMxxR+oVuiO5qrFk03ANo8/FqIdLmGd8kP4FMnklSakEDVDNeoS97JRFWxUprHaeWBQ0oR5sa7gvhRu1pOw80jjDWxuhfZlFd9xVwkCV31z4wE5g4aPUlsN7IiAfNzmJwQ3sF2RnQONHZuBF4="
moz-do-not-send="true">https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.freedesktop.org%2Fmailman%2Flistinfo%2Famd-gfx&data=02%7C01%7Calexander.deucher%40amd.com%7Cf3762304925b4019bfed08d7b6e287e4%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637178957179179431&sdata=bY7V%2BKOF3gYu4ITGCKgAiRvXUvxPcwsz2zsEJDns3jI%3D&reserved=0</a><br>
</div>
</span></font></div>
</div>
</blockquote>
<br>
</div>
</div>
</blockquote>
<br>
</body>
</html>