[PATCH] drm/i915: Enable runtime pm

[PATCH] drm/i915: Enable runtime pm

[Daniel Vetter]

Like with every other feature that's not enabled by default we break
runtime pm support way too often by accident because the overall test
coverage isn't great. And it's been almost 2 years since we enabled
the power well code by default

commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date:   Wed Jul 3 17:12:13 2013 -0300

    drm/i915: switch disable_power_well default value to 1

It's really more than overdue for runtime pm itself to follow!

Note that in practice this wont do a hole lot yet, since we're still
gated on snd-hda-intel doing proper runtime pm. But I've discussed
this with Liam and we agreed that this needs to be done. And the audio
team is working to hold up their end of this bargain.

And the justification for updating the autosuspend delay to 100ms:
Quick measurment shows that we can do a full rpm cycle in about 5ms,
which means the delay should still be really conservative from a power
conservation pov. The only workload that would suffer from ping-pong
is also only gpu/compute with all screens off. 100ms should cover any
kind of latency with submitting follow-up batches.

Cc: Takashi Iwai <tiwai@suse.de>
Cc: Liam Girdwood <liam.r.girdwood@intel.com>
Cc: Yang, Libin <libin.yang@intel.com>
Cc: Lin, Mengdong <mengdong.lin@intel.com>
Cc: Li, Jocelyn <jocelyn.li@intel.com>
Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
---
 drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 317b9b43d1c1..36ecbe275dd9 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 		return;
 	}
 
-	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
+	pm_runtime_set_autosuspend_delay(device, 100);
 	pm_runtime_mark_last_busy(device);
 	pm_runtime_use_autosuspend(device);
+	pm_runtime_allow(device);
 
 	pm_runtime_put_autosuspend(device);
 }
-- 
2.1.0

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[shuang.he]

Tested-By: Intel Graphics QA PRTS (Patch Regression Test System Contact: shuang.he@intel.com)
Task id: 6366
-------------------------------------Summary-------------------------------------
Platform          Delta          drm-intel-nightly          Series Applied
PNV                                  276/276              276/276
ILK                                  302/302              302/302
SNB                                  316/316              316/316
IVB                                  342/342              342/342
BYT                                  286/286              286/286
BDW                                  321/321              321/321
-------------------------------------Detailed-------------------------------------
Platform  Test                                drm-intel-nightly          Series Applied
Note: You need to pay more attention to line start with '*'
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Jesse Barnes]

On 05/08/2015 11:51 AM, Daniel Vetter wrote:
> Like with every other feature that's not enabled by default we break
> runtime pm support way too often by accident because the overall test
> coverage isn't great. And it's been almost 2 years since we enabled
> the power well code by default
> 
> commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
> Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
> Date:   Wed Jul 3 17:12:13 2013 -0300
> 
>     drm/i915: switch disable_power_well default value to 1
> 
> It's really more than overdue for runtime pm itself to follow!
> 
> Note that in practice this wont do a hole lot yet, since we're still
> gated on snd-hda-intel doing proper runtime pm. But I've discussed
> this with Liam and we agreed that this needs to be done. And the audio
> team is working to hold up their end of this bargain.
> 
> And the justification for updating the autosuspend delay to 100ms:
> Quick measurment shows that we can do a full rpm cycle in about 5ms,
> which means the delay should still be really conservative from a power
> conservation pov. The only workload that would suffer from ping-pong
> is also only gpu/compute with all screens off. 100ms should cover any
> kind of latency with submitting follow-up batches.
> 
> Cc: Takashi Iwai <tiwai@suse.de>
> Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> Cc: Yang, Libin <libin.yang@intel.com>
> Cc: Lin, Mengdong <mengdong.lin@intel.com>
> Cc: Li, Jocelyn <jocelyn.li@intel.com>
> Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
> Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> ---
>  drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> index 317b9b43d1c1..36ecbe275dd9 100644
> --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> @@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>  		return;
>  	}
>  
> -	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
> +	pm_runtime_set_autosuspend_delay(device, 100);
>  	pm_runtime_mark_last_busy(device);
>  	pm_runtime_use_autosuspend(device);
> +	pm_runtime_allow(device);
>  
>  	pm_runtime_put_autosuspend(device);
>  }
> 

This also changes the timeout...  it shouldn't break anything, but it
would be good to get some numbers from Eero's team on this.  It might be
better to use a lower or higher number based on a typical desktop
workload by default (though I guess the user or distro can do their own
tuning and override the value too).

Jesse
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Daniel Vetter]

Can I get an ack on this please? The audio folks already move ahead

http://permalink.gmane.org/gmane.linux.alsa.devel/139831

Would be embarassing if we are late to the party we organized ourselves ...
-Daniel


On Fri, May 8, 2015 at 8:51 PM, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
> Like with every other feature that's not enabled by default we break
> runtime pm support way too often by accident because the overall test
> coverage isn't great. And it's been almost 2 years since we enabled
> the power well code by default
>
> commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
> Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
> Date:   Wed Jul 3 17:12:13 2013 -0300
>
>     drm/i915: switch disable_power_well default value to 1
>
> It's really more than overdue for runtime pm itself to follow!
>
> Note that in practice this wont do a hole lot yet, since we're still
> gated on snd-hda-intel doing proper runtime pm. But I've discussed
> this with Liam and we agreed that this needs to be done. And the audio
> team is working to hold up their end of this bargain.
>
> And the justification for updating the autosuspend delay to 100ms:
> Quick measurment shows that we can do a full rpm cycle in about 5ms,
> which means the delay should still be really conservative from a power
> conservation pov. The only workload that would suffer from ping-pong
> is also only gpu/compute with all screens off. 100ms should cover any
> kind of latency with submitting follow-up batches.
>
> Cc: Takashi Iwai <tiwai@suse.de>
> Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> Cc: Yang, Libin <libin.yang@intel.com>
> Cc: Lin, Mengdong <mengdong.lin@intel.com>
> Cc: Li, Jocelyn <jocelyn.li@intel.com>
> Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
> Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> ---
>  drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> index 317b9b43d1c1..36ecbe275dd9 100644
> --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> @@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>                 return;
>         }
>
> -       pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
> +       pm_runtime_set_autosuspend_delay(device, 100);
>         pm_runtime_mark_last_busy(device);
>         pm_runtime_use_autosuspend(device);
> +       pm_runtime_allow(device);
>
>         pm_runtime_put_autosuspend(device);
>  }
> --
> 2.1.0
>



-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Liam Girdwood]

On Tue, 2015-06-16 at 10:34 +0200, Daniel Vetter wrote:
> Can I get an ack on this please? The audio folks already move ahead
> 
> http://permalink.gmane.org/gmane.linux.alsa.devel/139831
> 
> Would be embarassing if we are late to the party we organized ourselves ...
> -Daniel
> 
> 

Mengdong, Libin - I assume someone has tested this ? could someone Ack.

Thanks

Liam

> On Fri, May 8, 2015 at 8:51 PM, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
> > Like with every other feature that's not enabled by default we break
> > runtime pm support way too often by accident because the overall test
> > coverage isn't great. And it's been almost 2 years since we enabled
> > the power well code by default
> >
> > commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
> > Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
> > Date:   Wed Jul 3 17:12:13 2013 -0300
> >
> >     drm/i915: switch disable_power_well default value to 1
> >
> > It's really more than overdue for runtime pm itself to follow!
> >
> > Note that in practice this wont do a hole lot yet, since we're still
> > gated on snd-hda-intel doing proper runtime pm. But I've discussed
> > this with Liam and we agreed that this needs to be done. And the audio
> > team is working to hold up their end of this bargain.
> >
> > And the justification for updating the autosuspend delay to 100ms:
> > Quick measurment shows that we can do a full rpm cycle in about 5ms,
> > which means the delay should still be really conservative from a power
> > conservation pov. The only workload that would suffer from ping-pong
> > is also only gpu/compute with all screens off. 100ms should cover any
> > kind of latency with submitting follow-up batches.
> >
> > Cc: Takashi Iwai <tiwai@suse.de>
> > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > Cc: Yang, Libin <libin.yang@intel.com>
> > Cc: Lin, Mengdong <mengdong.lin@intel.com>
> > Cc: Li, Jocelyn <jocelyn.li@intel.com>
> > Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
> > Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
> > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> > ---
> >  drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
> >  1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > index 317b9b43d1c1..36ecbe275dd9 100644
> > --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > @@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
> >                 return;
> >         }
> >
> > -       pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
> > +       pm_runtime_set_autosuspend_delay(device, 100);
> >         pm_runtime_mark_last_busy(device);
> >         pm_runtime_use_autosuspend(device);
> > +       pm_runtime_allow(device);
> >
> >         pm_runtime_put_autosuspend(device);
> >  }
> > --
> > 2.1.0
> >
> 
> 
> 


---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ
VAT No: 860 2173 47

This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Paulo Zanoni]

2015-06-16 5:34 GMT-03:00 Daniel Vetter <daniel.vetter@ffwll.ch>:
> Can I get an ack on this please? The audio folks already move ahead
>
> http://permalink.gmane.org/gmane.linux.alsa.devel/139831
>
> Would be embarassing if we are late to the party we organized ourselves ...

The situation is already embarassing for us :)

pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ sudo ./pm_rpm --quick 2>&1
| tee pm_rpm.txt
(lots of stuff)
pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ ./sumario.sh pm_rpm.txt
Subtest drm-resources-equal: FAIL (5.897s)
Subtest dpms-lpsp: FAIL (10.045s)
Subtest dpms-non-lpsp: FAIL (10.027s)
Subtest cursor-dpms: FAIL (12.693s)
Subtest legacy-planes-dpms: FAIL (12.636s)
Subtest universal-planes-dpms: FAIL (12.719s)
Subtest dpms-mode-unset-lpsp: FAIL (12.588s)
Subtest dpms-mode-unset-non-lpsp: FAIL (10.234s)
Subtest fences-dpms: FAIL (11.726s)

Total:   41
SUCCESS: 32
FAIL:    9
SKIP:    0
pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ edmesg
[  166.007957] WARNING: CPU: 1 PID: 1648 at
drivers/gpu/drm/i915/intel_uncore.c:620
hsw_unclaimed_reg_debug+0x75/0xa0 [i915]()
[  174.944917] WARNING: CPU: 1 PID: 1648 at
drivers/gpu/drm/i915/intel_uncore.c:620
hsw_unclaimed_reg_debug+0x75/0xa0 [i915]()
[  327.095531] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.096026] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.096597] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.096866] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.097089] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.097323] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.097534] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
[  327.097767] WARNING: CPU: 0 PID: 1648 at
drivers/gpu/drm/i915/i915_gem.c:5316
i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ lspci -nn | grep VGA
00:02.0 VGA compatible controller [0300]: Intel Corporation
Broadwell-U Integrated Graphics [8086:1616] (rev 09)

Please notice that, if I remember correctly, just a few weeks ago we
were passing everything, although we were having some dmesg WARNs. Now
we're not even passing the tests anymore :(

And I only see 2 pm_rpm bugs on bugzilla:
https://bugs.freedesktop.org/show_bug.cgi?id=90863
https://bugs.freedesktop.org/show_bug.cgi?id=90546

Why isn't PRTS/QA cathing stuff!?

I'm sorry, but for now, I just can't give the ACK.

> -Daniel
>
>
> On Fri, May 8, 2015 at 8:51 PM, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
>> Like with every other feature that's not enabled by default we break
>> runtime pm support way too often by accident because the overall test
>> coverage isn't great. And it's been almost 2 years since we enabled
>> the power well code by default
>>
>> commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
>> Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
>> Date:   Wed Jul 3 17:12:13 2013 -0300
>>
>>     drm/i915: switch disable_power_well default value to 1
>>
>> It's really more than overdue for runtime pm itself to follow!
>>
>> Note that in practice this wont do a hole lot yet, since we're still
>> gated on snd-hda-intel doing proper runtime pm. But I've discussed
>> this with Liam and we agreed that this needs to be done. And the audio
>> team is working to hold up their end of this bargain.
>>
>> And the justification for updating the autosuspend delay to 100ms:
>> Quick measurment shows that we can do a full rpm cycle in about 5ms,
>> which means the delay should still be really conservative from a power
>> conservation pov. The only workload that would suffer from ping-pong
>> is also only gpu/compute with all screens off. 100ms should cover any
>> kind of latency with submitting follow-up batches.
>>
>> Cc: Takashi Iwai <tiwai@suse.de>
>> Cc: Liam Girdwood <liam.r.girdwood@intel.com>
>> Cc: Yang, Libin <libin.yang@intel.com>
>> Cc: Lin, Mengdong <mengdong.lin@intel.com>
>> Cc: Li, Jocelyn <jocelyn.li@intel.com>
>> Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
>> Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
>> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
>> ---
>>  drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
>>  1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
>> index 317b9b43d1c1..36ecbe275dd9 100644
>> --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
>> +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
>> @@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>>                 return;
>>         }
>>
>> -       pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
>> +       pm_runtime_set_autosuspend_delay(device, 100);
>>         pm_runtime_mark_last_busy(device);
>>         pm_runtime_use_autosuspend(device);
>> +       pm_runtime_allow(device);
>>
>>         pm_runtime_put_autosuspend(device);
>>  }
>> --
>> 2.1.0
>>
>
>
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> +41 (0) 79 365 57 48 - http://blog.ffwll.ch
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx



-- 
Paulo Zanoni
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Paulo Zanoni]

2015-06-16 9:23 GMT-03:00 Paulo Zanoni <przanoni@gmail.com>:
> 2015-06-16 5:34 GMT-03:00 Daniel Vetter <daniel.vetter@ffwll.ch>:
>> Can I get an ack on this please? The audio folks already move ahead
>>
>> http://permalink.gmane.org/gmane.linux.alsa.devel/139831
>>
>> Would be embarassing if we are late to the party we organized ourselves ...
>
> The situation is already embarassing for us :)
>
> pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ sudo ./pm_rpm --quick 2>&1
> | tee pm_rpm.txt
> (lots of stuff)
> pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ ./sumario.sh pm_rpm.txt

For details, please see:
http://people.freedesktop.org/~pzanoni/pm_rpm.txt
http://people.freedesktop.org/~pzanoni/dmesg.txt

> Subtest drm-resources-equal: FAIL (5.897s)
> Subtest dpms-lpsp: FAIL (10.045s)
> Subtest dpms-non-lpsp: FAIL (10.027s)
> Subtest cursor-dpms: FAIL (12.693s)
> Subtest legacy-planes-dpms: FAIL (12.636s)
> Subtest universal-planes-dpms: FAIL (12.719s)
> Subtest dpms-mode-unset-lpsp: FAIL (12.588s)
> Subtest dpms-mode-unset-non-lpsp: FAIL (10.234s)
> Subtest fences-dpms: FAIL (11.726s)
>
> Total:   41
> SUCCESS: 32
> FAIL:    9
> SKIP:    0
> pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ edmesg
> [  166.007957] WARNING: CPU: 1 PID: 1648 at
> drivers/gpu/drm/i915/intel_uncore.c:620
> hsw_unclaimed_reg_debug+0x75/0xa0 [i915]()
> [  174.944917] WARNING: CPU: 1 PID: 1648 at
> drivers/gpu/drm/i915/intel_uncore.c:620
> hsw_unclaimed_reg_debug+0x75/0xa0 [i915]()
> [  327.095531] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.096026] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.096597] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.096866] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.097089] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.097323] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.097534] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> [  327.097767] WARNING: CPU: 0 PID: 1648 at
> drivers/gpu/drm/i915/i915_gem.c:5316
> i915_gem_obj_ggtt_offset_view+0xad/0x100 [i915]()
> pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ lspci -nn | grep VGA
> 00:02.0 VGA compatible controller [0300]: Intel Corporation
> Broadwell-U Integrated Graphics [8086:1616] (rev 09)
>
> Please notice that, if I remember correctly, just a few weeks ago we
> were passing everything, although we were having some dmesg WARNs. Now
> we're not even passing the tests anymore :(
>
> And I only see 2 pm_rpm bugs on bugzilla:
> https://bugs.freedesktop.org/show_bug.cgi?id=90863
> https://bugs.freedesktop.org/show_bug.cgi?id=90546
>
> Why isn't PRTS/QA cathing stuff!?
>
> I'm sorry, but for now, I just can't give the ACK.
>
>> -Daniel
>>
>>
>> On Fri, May 8, 2015 at 8:51 PM, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
>>> Like with every other feature that's not enabled by default we break
>>> runtime pm support way too often by accident because the overall test
>>> coverage isn't great. And it's been almost 2 years since we enabled
>>> the power well code by default
>>>
>>> commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
>>> Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
>>> Date:   Wed Jul 3 17:12:13 2013 -0300
>>>
>>>     drm/i915: switch disable_power_well default value to 1
>>>
>>> It's really more than overdue for runtime pm itself to follow!
>>>
>>> Note that in practice this wont do a hole lot yet, since we're still
>>> gated on snd-hda-intel doing proper runtime pm. But I've discussed
>>> this with Liam and we agreed that this needs to be done. And the audio
>>> team is working to hold up their end of this bargain.
>>>
>>> And the justification for updating the autosuspend delay to 100ms:
>>> Quick measurment shows that we can do a full rpm cycle in about 5ms,
>>> which means the delay should still be really conservative from a power
>>> conservation pov. The only workload that would suffer from ping-pong
>>> is also only gpu/compute with all screens off. 100ms should cover any
>>> kind of latency with submitting follow-up batches.
>>>
>>> Cc: Takashi Iwai <tiwai@suse.de>
>>> Cc: Liam Girdwood <liam.r.girdwood@intel.com>
>>> Cc: Yang, Libin <libin.yang@intel.com>
>>> Cc: Lin, Mengdong <mengdong.lin@intel.com>
>>> Cc: Li, Jocelyn <jocelyn.li@intel.com>
>>> Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
>>> Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
>>> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
>>> ---
>>>  drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
>>>  1 file changed, 2 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
>>> index 317b9b43d1c1..36ecbe275dd9 100644
>>> --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
>>> +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
>>> @@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>>>                 return;
>>>         }
>>>
>>> -       pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
>>> +       pm_runtime_set_autosuspend_delay(device, 100);
>>>         pm_runtime_mark_last_busy(device);
>>>         pm_runtime_use_autosuspend(device);
>>> +       pm_runtime_allow(device);
>>>
>>>         pm_runtime_put_autosuspend(device);
>>>  }
>>> --
>>> 2.1.0
>>>
>>
>>
>>
>> --
>> Daniel Vetter
>> Software Engineer, Intel Corporation
>> +41 (0) 79 365 57 48 - http://blog.ffwll.ch
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
>
>
>
> --
> Paulo Zanoni



-- 
Paulo Zanoni
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Jesse Barnes]

On 06/16/2015 05:26 AM, Paulo Zanoni wrote:
> 2015-06-16 9:23 GMT-03:00 Paulo Zanoni <przanoni@gmail.com>:
>> 2015-06-16 5:34 GMT-03:00 Daniel Vetter <daniel.vetter@ffwll.ch>:
>>> Can I get an ack on this please? The audio folks already move ahead
>>>
>>> http://permalink.gmane.org/gmane.linux.alsa.devel/139831
>>>
>>> Would be embarassing if we are late to the party we organized ourselves ...
>>
>> The situation is already embarassing for us :)
>>
>> pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ sudo ./pm_rpm --quick 2>&1
>> | tee pm_rpm.txt
>> (lots of stuff)
>> pzanoni@nhoque:~/nfs/intel-gpu-tools/tests$ ./sumario.sh pm_rpm.txt
> 
> For details, please see:
> http://people.freedesktop.org/~pzanoni/pm_rpm.txt
> http://people.freedesktop.org/~pzanoni/dmesg.txt
> 
>> Subtest drm-resources-equal: FAIL (5.897s)
>> Subtest dpms-lpsp: FAIL (10.045s)
>> Subtest dpms-non-lpsp: FAIL (10.027s)
>> Subtest cursor-dpms: FAIL (12.693s)
>> Subtest legacy-planes-dpms: FAIL (12.636s)
>> Subtest universal-planes-dpms: FAIL (12.719s)
>> Subtest dpms-mode-unset-lpsp: FAIL (12.588s)
>> Subtest dpms-mode-unset-non-lpsp: FAIL (10.234s)
>> Subtest fences-dpms: FAIL (11.726s)

Ugg...  I'd like to make sure we have bugs on these and at least some
kind of plan to fix them before enabling by default, otherwise we're
just asking for another 'disable by default' patch just before the next
release...

Jesse

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Yang, Libin]

Hi Liam,

> -----Original Message-----
> From: Girdwood, Liam R
> Sent: Tuesday, June 16, 2015 6:42 PM
> To: Daniel Vetter; Lin, Mengdong; Yang, Libin
> Cc: Intel Graphics Development; Takashi Iwai; Yang, Libin; Lin,
> Mengdong; Li, Jocelyn; Kaskinen, Tanu; Zanoni, Paulo R; Vetter, Daniel
> Subject: Re: [PATCH] drm/i915: Enable runtime pm
> 
> On Tue, 2015-06-16 at 10:34 +0200, Daniel Vetter wrote:
> > Can I get an ack on this please? The audio folks already move ahead
> >
> > http://permalink.gmane.org/gmane.linux.alsa.devel/139831
> >
> > Would be embarassing if we are late to the party we organized
> ourselves ...
> > -Daniel
> >
> >
> 
> Mengdong, Libin - I assume someone has tested this ? could someone
> Ack.

Our patches are ready for this feature. Suppose Keqiao has test this feature.

> 
> Thanks
> 
> Liam
> 
> > On Fri, May 8, 2015 at 8:51 PM, Daniel Vetter <daniel.vetter@ffwll.ch>
> wrote:
> > > Like with every other feature that's not enabled by default we
> break
> > > runtime pm support way too often by accident because the overall
> test
> > > coverage isn't great. And it's been almost 2 years since we enabled
> > > the power well code by default
> > >
> > > commit bf51d5e2cda5d36d98e4b46ac7fca9461e512c41
> > > Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
> > > Date:   Wed Jul 3 17:12:13 2013 -0300
> > >
> > >     drm/i915: switch disable_power_well default value to 1
> > >
> > > It's really more than overdue for runtime pm itself to follow!
> > >
> > > Note that in practice this wont do a hole lot yet, since we're still
> > > gated on snd-hda-intel doing proper runtime pm. But I've
> discussed
> > > this with Liam and we agreed that this needs to be done. And the
> audio
> > > team is working to hold up their end of this bargain.
> > >
> > > And the justification for updating the autosuspend delay to 100ms:
> > > Quick measurment shows that we can do a full rpm cycle in about
> 5ms,
> > > which means the delay should still be really conservative from a
> power
> > > conservation pov. The only workload that would suffer from ping-
> pong
> > > is also only gpu/compute with all screens off. 100ms should cover
> any
> > > kind of latency with submitting follow-up batches.
> > >
> > > Cc: Takashi Iwai <tiwai@suse.de>
> > > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > > Cc: Yang, Libin <libin.yang@intel.com>
> > > Cc: Lin, Mengdong <mengdong.lin@intel.com>
> > > Cc: Li, Jocelyn <jocelyn.li@intel.com>
> > > Cc: Kaskinen, Tanu <tanu.kaskinen@intel.com>
> > > Cc: Zanoni, Paulo R <paulo.r.zanoni@intel.com>
> > > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> > > ---
> > >  drivers/gpu/drm/i915/intel_runtime_pm.c | 3 ++-
> > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c
> b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > index 317b9b43d1c1..36ecbe275dd9 100644
> > > --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > @@ -1919,9 +1919,10 @@ void intel_runtime_pm_enable(struct
> drm_i915_private *dev_priv)
> > >                 return;
> > >         }
> > >
> > > -       pm_runtime_set_autosuspend_delay(device, 10000); /* 10s
> */
> > > +       pm_runtime_set_autosuspend_delay(device, 100);
> > >         pm_runtime_mark_last_busy(device);
> > >         pm_runtime_use_autosuspend(device);
> > > +       pm_runtime_allow(device);
> > >
> > >         pm_runtime_put_autosuspend(device);
> > >  }
> > > --
> > > 2.1.0
> > >
> >
> >
> >
> 

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[David Weinehall]

On Thu, Nov 16, 2017 at 08:24:02PM +0200, David Weinehall wrote:
> On Wed, Nov 08, 2017 at 04:25:42PM +0200, David Weinehall wrote:
> > On Tue, Nov 07, 2017 at 05:18:21PM +0100, Daniel Vetter wrote:
> > > Now that we have CI, and that pm_rpm fully passes (I guess the audio
> > > folks have implemented proper runtime pm for snd-hda, hooray, pls
> > > confirm) it's time to enable this again by default.
> > > 
> > > Real goal here is to have 1 configuration only that we fully support,
> > > instead of tons of different codes with every user/customer tuning it
> > > differently. And really, power stuff should work by default, and
> > > should be enabled by everywhere where it is save to do so.
> > > 
> > > v2: Completely new commit message, a few years passed since v1 ...
> > > 
> > > Cc: Takashi Iwai <tiwai@suse.de>
> > > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > > Cc: "Yang, Libin" <libin.yang@intel.com>
> > > Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> > > Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> > > Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> > > Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> > > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> > 
> > lgtm,
> > 
> > Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
> 
> Been testing a bit; test results are a bit discouraging when it comes to
> idle power consumption.
> 
> Our nightly test suite logs idle power consumption before running any
> tests, after running all tests, and then finally after running
> powertop --auto-tune.
> 
> The before and after cases are similar with and without patch,
> but not so for the auto-tune case.
> 
> Without this patch, powertop --auto-tune yields a massive improvement
> (on NUC6i5 the power consumption drops with more than a factor of 3),
> while with this patch the power consumption just drops with 10% or so.

With the 10s => 0.1s bit of the patch reverted there's no longer any
--auto-tune regression.


Kind regards, David
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Chris Wilson]

Quoting Paulo Zanoni (2017-11-16 20:45:26)
> Em Qui, 2017-11-16 às 20:24 +0200, David Weinehall escreveu:
> > On Wed, Nov 08, 2017 at 04:25:42PM +0200, David Weinehall wrote:
> > > On Tue, Nov 07, 2017 at 05:18:21PM +0100, Daniel Vetter wrote:
> > > > Now that we have CI, and that pm_rpm fully passes (I guess the
> > > > audio
> > > > folks have implemented proper runtime pm for snd-hda, hooray, pls
> > > > confirm) it's time to enable this again by default.
> > > > 
> > > > Real goal here is to have 1 configuration only that we fully
> > > > support,
> > > > instead of tons of different codes with every user/customer
> > > > tuning it
> > > > differently. And really, power stuff should work by default, and
> > > > should be enabled by everywhere where it is save to do so.
> > > > 
> > > > v2: Completely new commit message, a few years passed since v1
> > > > ...
> > > > 
> > > > Cc: Takashi Iwai <tiwai@suse.de>
> > > > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > > > Cc: "Yang, Libin" <libin.yang@intel.com>
> > > > Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> > > > Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> > > > Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> > > > Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> > > > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> > > 
> > > lgtm,
> > > 
> > > Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
> > 
> > Been testing a bit; test results are a bit discouraging when it comes
> > to
> > idle power consumption.
> > 
> > Our nightly test suite logs idle power consumption before running any
> > tests, after running all tests, and then finally after running
> > powertop --auto-tune.
> > 
> > The before and after cases are similar with and without patch,
> > but not so for the auto-tune case.
> > 
> > Without this patch, powertop --auto-tune yields a massive improvement
> > (on NUC6i5 the power consumption drops with more than a factor of 3),
> > while with this patch the power consumption just drops with 10% or
> > so.
> 
> What happens if you keep the autosuspend delay to 10000?

The problem with the extra hpd triggering a render and flip still
remains, but less frequent.

Remove compiz + desktop manager from the picture and see if that cures
it. Then obviously you have to try each of the main desktop managers /
display servers to see which have good/bad behaviour (if my hunch is
correct). And if it does, we can't proceed with an aggressive default,
but will have to recommend that the display managers set it according to
their needs.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Paulo Zanoni]

Em Qui, 2017-11-16 às 20:24 +0200, David Weinehall escreveu:
> On Wed, Nov 08, 2017 at 04:25:42PM +0200, David Weinehall wrote:
> > On Tue, Nov 07, 2017 at 05:18:21PM +0100, Daniel Vetter wrote:
> > > Now that we have CI, and that pm_rpm fully passes (I guess the
> > > audio
> > > folks have implemented proper runtime pm for snd-hda, hooray, pls
> > > confirm) it's time to enable this again by default.
> > > 
> > > Real goal here is to have 1 configuration only that we fully
> > > support,
> > > instead of tons of different codes with every user/customer
> > > tuning it
> > > differently. And really, power stuff should work by default, and
> > > should be enabled by everywhere where it is save to do so.
> > > 
> > > v2: Completely new commit message, a few years passed since v1
> > > ...
> > > 
> > > Cc: Takashi Iwai <tiwai@suse.de>
> > > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > > Cc: "Yang, Libin" <libin.yang@intel.com>
> > > Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> > > Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> > > Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> > > Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> > > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> > 
> > lgtm,
> > 
> > Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
> 
> Been testing a bit; test results are a bit discouraging when it comes
> to
> idle power consumption.
> 
> Our nightly test suite logs idle power consumption before running any
> tests, after running all tests, and then finally after running
> powertop --auto-tune.
> 
> The before and after cases are similar with and without patch,
> but not so for the auto-tune case.
> 
> Without this patch, powertop --auto-tune yields a massive improvement
> (on NUC6i5 the power consumption drops with more than a factor of 3),
> while with this patch the power consumption just drops with 10% or
> so.

What happens if you keep the autosuspend delay to 10000?


> 
> Judging by the powertop output it seems as though we're getting a lot
> of
> interrupts from i915.
> 
>  *  *  *   Top 10 Power Consumers   *  *  *
> 
> With patch:
> 
> Usage;Events/s;Category;Description
>   0,5%; 75,1;Interrupt;[124] i915
>   0,3%; 48,4;Process;/usr/lib/xorg/Xorg -core :0 -seat seat0 -auth
> /var/run/lightdm/root/:0 -nolisten tcp vt7 -novtswitch
>   0,1%; 42,8;Timer;hrtimer_wakeup
>   0,0%; 34,9;Timer;tick_sched_timer
>   4,2%;  1,1;kWork;i915_hpd_poll_init_work
>   0,1%; 14,0;Process;python2 /opt/scripts/dut/dutlaunch/launch2.py --
> workspace=/opt/jenkins/workspace/Custom_test --iterations=1
> idlepower_before un
>   0,0%; 13,3;Process;[rcu_preempt]
>   0,8%;  1,7;Process;python /opt/scripts/dut/perf-meter.py --avgskip
> 1 --name perf-meter --infofile /tmp/testname GLBenchmark testfw_app
> synmark2 he
>   0,0%;  3,0;Process;compiz
>   0,7%; 0,11;kWork;output_poll_execute
> 
> Without the patch:
> 
> Usage;Events/s;Category;Description
>   0,0%; 29,1;Timer;tick_sched_timer
>   0,1%; 19,9;Process;python2 /opt/scripts/dut/dutlaunch/launch.py --
> workspace=/opt/jenkins/workspace/Nightly_kernel_test/kernel/151077366
> 5/SKL_6260U
>   0,0%; 13,2;Process;[rcu_preempt]
>   0,8%;  1,6;Process;python /opt/scripts/dut/perf-meter.py --avgskip
> 1 --name perf-meter --infofile /tmp/testname GLBenchmark testfw_app
> synmark2 he
>   0,0%;  2,5;Process;compiz
>   0,0%;  1,5;Process;java -jar slave.jar
>   0,0%;  1,2;Interrupt;[3] net_rx(softirq)
>   0,0%;  1,0;kWork;pci_pme_list_scan
>   0,0%;  0,9;Interrupt;[121] xhci_hcd
>   0,1%;  0,5;Process;perf-meter
> 
> As can be seen the i915 driver doesn't even show up without the
> patch,
> while it's the main culprit with the patch.
> 
> Just to eliminate DMC issues I'm going to do another run, but with
> DMC
> v1.27 instead of v1.26.
> 
> 
> Kind regards, David
> 
> > 
> > > ---
> > >  drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
> > >  1 file changed, 3 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > index 8315499452dc..dc24d008d8d4 100644
> > > --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > > @@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct
> > > drm_i915_private *dev_priv)
> > >  	struct pci_dev *pdev = dev_priv->drm.pdev;
> > >  	struct device *kdev = &pdev->dev;
> > >  
> > > -	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
> > > +	pm_runtime_set_autosuspend_delay(kdev, 100);
> > >  	pm_runtime_mark_last_busy(kdev);
> > >  
> > >  	/*
> > > @@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct
> > > drm_i915_private *dev_priv)
> > >  		pm_runtime_use_autosuspend(kdev);
> > >  	}
> > >  
> > > +	pm_runtime_allow(kdev);
> > > +
> > >  	/*
> > >  	 * The core calls the driver load handler with an RPM
> > > reference held.
> > >  	 * We drop that here and will reacquire it during
> > > unloading in
> > > -- 
> > > 2.15.0.rc2
> > > 
> > > _______________________________________________
> > > Intel-gfx mailing list
> > > Intel-gfx@lists.freedesktop.org
> > > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
> > 
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[David Weinehall]

On Wed, Nov 08, 2017 at 04:25:42PM +0200, David Weinehall wrote:
> On Tue, Nov 07, 2017 at 05:18:21PM +0100, Daniel Vetter wrote:
> > Now that we have CI, and that pm_rpm fully passes (I guess the audio
> > folks have implemented proper runtime pm for snd-hda, hooray, pls
> > confirm) it's time to enable this again by default.
> > 
> > Real goal here is to have 1 configuration only that we fully support,
> > instead of tons of different codes with every user/customer tuning it
> > differently. And really, power stuff should work by default, and
> > should be enabled by everywhere where it is save to do so.
> > 
> > v2: Completely new commit message, a few years passed since v1 ...
> > 
> > Cc: Takashi Iwai <tiwai@suse.de>
> > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > Cc: "Yang, Libin" <libin.yang@intel.com>
> > Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> > Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> > Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> > Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> 
> lgtm,
> 
> Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>

Been testing a bit; test results are a bit discouraging when it comes to
idle power consumption.

Our nightly test suite logs idle power consumption before running any
tests, after running all tests, and then finally after running
powertop --auto-tune.

The before and after cases are similar with and without patch,
but not so for the auto-tune case.

Without this patch, powertop --auto-tune yields a massive improvement
(on NUC6i5 the power consumption drops with more than a factor of 3),
while with this patch the power consumption just drops with 10% or so.

Judging by the powertop output it seems as though we're getting a lot of
interrupts from i915.

 *  *  *   Top 10 Power Consumers   *  *  *

With patch:

Usage;Events/s;Category;Description
  0,5%; 75,1;Interrupt;[124] i915
  0,3%; 48,4;Process;/usr/lib/xorg/Xorg -core :0 -seat seat0 -auth /var/run/lightdm/root/:0 -nolisten tcp vt7 -novtswitch
  0,1%; 42,8;Timer;hrtimer_wakeup
  0,0%; 34,9;Timer;tick_sched_timer
  4,2%;  1,1;kWork;i915_hpd_poll_init_work
  0,1%; 14,0;Process;python2 /opt/scripts/dut/dutlaunch/launch2.py --workspace=/opt/jenkins/workspace/Custom_test --iterations=1 idlepower_before un
  0,0%; 13,3;Process;[rcu_preempt]
  0,8%;  1,7;Process;python /opt/scripts/dut/perf-meter.py --avgskip 1 --name perf-meter --infofile /tmp/testname GLBenchmark testfw_app synmark2 he
  0,0%;  3,0;Process;compiz
  0,7%; 0,11;kWork;output_poll_execute

Without the patch:

Usage;Events/s;Category;Description
  0,0%; 29,1;Timer;tick_sched_timer
  0,1%; 19,9;Process;python2 /opt/scripts/dut/dutlaunch/launch.py --workspace=/opt/jenkins/workspace/Nightly_kernel_test/kernel/1510773665/SKL_6260U
  0,0%; 13,2;Process;[rcu_preempt]
  0,8%;  1,6;Process;python /opt/scripts/dut/perf-meter.py --avgskip 1 --name perf-meter --infofile /tmp/testname GLBenchmark testfw_app synmark2 he
  0,0%;  2,5;Process;compiz
  0,0%;  1,5;Process;java -jar slave.jar
  0,0%;  1,2;Interrupt;[3] net_rx(softirq)
  0,0%;  1,0;kWork;pci_pme_list_scan
  0,0%;  0,9;Interrupt;[121] xhci_hcd
  0,1%;  0,5;Process;perf-meter

As can be seen the i915 driver doesn't even show up without the patch,
while it's the main culprit with the patch.

Just to eliminate DMC issues I'm going to do another run, but with DMC
v1.27 instead of v1.26.


Kind regards, David

> 
> > ---
> >  drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
> >  1 file changed, 3 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > index 8315499452dc..dc24d008d8d4 100644
> > --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > @@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
> >  	struct pci_dev *pdev = dev_priv->drm.pdev;
> >  	struct device *kdev = &pdev->dev;
> >  
> > -	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
> > +	pm_runtime_set_autosuspend_delay(kdev, 100);
> >  	pm_runtime_mark_last_busy(kdev);
> >  
> >  	/*
> > @@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
> >  		pm_runtime_use_autosuspend(kdev);
> >  	}
> >  
> > +	pm_runtime_allow(kdev);
> > +
> >  	/*
> >  	 * The core calls the driver load handler with an RPM reference held.
> >  	 * We drop that here and will reacquire it during unloading in
> > -- 
> > 2.15.0.rc2
> > 
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[David Weinehall]

On Tue, Nov 07, 2017 at 05:18:21PM +0100, Daniel Vetter wrote:
> Now that we have CI, and that pm_rpm fully passes (I guess the audio
> folks have implemented proper runtime pm for snd-hda, hooray, pls
> confirm) it's time to enable this again by default.
> 
> Real goal here is to have 1 configuration only that we fully support,
> instead of tons of different codes with every user/customer tuning it
> differently. And really, power stuff should work by default, and
> should be enabled by everywhere where it is save to do so.
> 
> v2: Completely new commit message, a few years passed since v1 ...
> 
> Cc: Takashi Iwai <tiwai@suse.de>
> Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> Cc: "Yang, Libin" <libin.yang@intel.com>
> Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

lgtm,

Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> index 8315499452dc..dc24d008d8d4 100644
> --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> @@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>  	struct pci_dev *pdev = dev_priv->drm.pdev;
>  	struct device *kdev = &pdev->dev;
>  
> -	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
> +	pm_runtime_set_autosuspend_delay(kdev, 100);
>  	pm_runtime_mark_last_busy(kdev);
>  
>  	/*
> @@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>  		pm_runtime_use_autosuspend(kdev);
>  	}
>  
> +	pm_runtime_allow(kdev);
> +
>  	/*
>  	 * The core calls the driver load handler with an RPM reference held.
>  	 * We drop that here and will reacquire it during unloading in
> -- 
> 2.15.0.rc2
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Daniel Vetter]

On Tue, Nov 07, 2017 at 06:45:36PM +0200, Jani Nikula wrote:
> On Tue, 07 Nov 2017, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
> > Now that we have CI, and that pm_rpm fully passes (I guess the audio
> > folks have implemented proper runtime pm for snd-hda, hooray, pls
> > confirm) it's time to enable this again by default.
> >
> > Real goal here is to have 1 configuration only that we fully support,
> > instead of tons of different codes with every user/customer tuning it
> > differently. And really, power stuff should work by default, and
> > should be enabled by everywhere where it is save to do so.
> >
> > v2: Completely new commit message, a few years passed since v1 ...
> 
> I suppose this is something that could use more than a single round of
> IGT CI before merging...?

The dedicated pm_rpm tests explicitly enable this (with a timeout of 0) on
all machines we run in shards. It's been green for a long time. So this
just tests for accidental fallout everywhere else (timing shifts
essentially), which I think is fairly low priority.

Hence I'm not terribly worried about this one here.
 
> BR,
> Jani.
> 
> 
> 
> >
> > Cc: Takashi Iwai <tiwai@suse.de>
> > Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> > Cc: "Yang, Libin" <libin.yang@intel.com>
> > Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> > Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> > Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> > Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> > Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> > ---
> >  drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
> >  1 file changed, 3 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > index 8315499452dc..dc24d008d8d4 100644
> > --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> > @@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
> >  	struct pci_dev *pdev = dev_priv->drm.pdev;
> >  	struct device *kdev = &pdev->dev;
> >  
> > -	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
> > +	pm_runtime_set_autosuspend_delay(kdev, 100);

Wrt the data requested for this here. On bxt (probably the slowest box we
have), from the pm_rpm tests, looking at dmesg I get the following values:

- device suspend: 3-4ms
- device resume: 10-11ms

So grand total is 15ms for a transition.

On top the display will keep us out of runtime pm, as will even a mildly
busy gt. I think the 100ms value isn't aggressive at all given that.
-Daniel


> >  	pm_runtime_mark_last_busy(kdev);
> >  
> >  	/*
> > @@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
> >  		pm_runtime_use_autosuspend(kdev);
> >  	}
> >  
> > +	pm_runtime_allow(kdev);
> > +
> >  	/*
> >  	 * The core calls the driver load handler with an RPM reference held.
> >  	 * We drop that here and will reacquire it during unloading in
> 
> -- 
> Jani Nikula, Intel Open Source Technology Center

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH] drm/i915: Enable runtime pm

[Jani Nikula]

On Tue, 07 Nov 2017, Daniel Vetter <daniel.vetter@ffwll.ch> wrote:
> Now that we have CI, and that pm_rpm fully passes (I guess the audio
> folks have implemented proper runtime pm for snd-hda, hooray, pls
> confirm) it's time to enable this again by default.
>
> Real goal here is to have 1 configuration only that we fully support,
> instead of tons of different codes with every user/customer tuning it
> differently. And really, power stuff should work by default, and
> should be enabled by everywhere where it is save to do so.
>
> v2: Completely new commit message, a few years passed since v1 ...

I suppose this is something that could use more than a single round of
IGT CI before merging...?

BR,
Jani.



>
> Cc: Takashi Iwai <tiwai@suse.de>
> Cc: Liam Girdwood <liam.r.girdwood@intel.com>
> Cc: "Yang, Libin" <libin.yang@intel.com>
> Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
> Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
> Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
> Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
> ---
>  drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
> index 8315499452dc..dc24d008d8d4 100644
> --- a/drivers/gpu/drm/i915/intel_runtime_pm.c
> +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
> @@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>  	struct pci_dev *pdev = dev_priv->drm.pdev;
>  	struct device *kdev = &pdev->dev;
>  
> -	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
> +	pm_runtime_set_autosuspend_delay(kdev, 100);
>  	pm_runtime_mark_last_busy(kdev);
>  
>  	/*
> @@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
>  		pm_runtime_use_autosuspend(kdev);
>  	}
>  
> +	pm_runtime_allow(kdev);
> +
>  	/*
>  	 * The core calls the driver load handler with an RPM reference held.
>  	 * We drop that here and will reacquire it during unloading in

-- 
Jani Nikula, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH] drm/i915: Enable runtime pm

[Daniel Vetter]

Now that we have CI, and that pm_rpm fully passes (I guess the audio
folks have implemented proper runtime pm for snd-hda, hooray, pls
confirm) it's time to enable this again by default.

Real goal here is to have 1 configuration only that we fully support,
instead of tons of different codes with every user/customer tuning it
differently. And really, power stuff should work by default, and
should be enabled by everywhere where it is save to do so.

v2: Completely new commit message, a few years passed since v1 ...

Cc: Takashi Iwai <tiwai@suse.de>
Cc: Liam Girdwood <liam.r.girdwood@intel.com>
Cc: "Yang, Libin" <libin.yang@intel.com>
Cc: "Lin, Mengdong" <mengdong.lin@intel.com>
Cc: "Li, Jocelyn" <jocelyn.li@intel.com>
Cc: "Kaskinen, Tanu" <tanu.kaskinen@intel.com>
Cc: "Zanoni, Paulo R" <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
---
 drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 8315499452dc..dc24d008d8d4 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -3232,7 +3232,7 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
-	pm_runtime_set_autosuspend_delay(kdev, 10000); /* 10s */
+	pm_runtime_set_autosuspend_delay(kdev, 100);
 	pm_runtime_mark_last_busy(kdev);
 
 	/*
@@ -3251,6 +3251,8 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 		pm_runtime_use_autosuspend(kdev);
 	}
 
+	pm_runtime_allow(kdev);
+
 	/*
 	 * The core calls the driver load handler with an RPM reference held.
 	 * We drop that here and will reacquire it during unloading in
-- 
2.15.0.rc2

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