gen6 (SNB) GPU still stalling besides latest patches
Subsystems (2)
Hi Jesse,
thanks for the infiormation. I've switched rc6 off by echo 0 > /sys/module/i915/parameters/i915_enable_rc6 this should do it, right?
cat /sys/module/i915/parameters/i915_enable_rc6 yields "0"
Are you referring to this patch? https://lkml.org/lkml/2011/6/17/371
It should be included in kernel 3.0-rc4 and didn't help here :(
regards
nico
-----Ursprüngliche Nachricht-----
Von: "Jesse Barnes" <[email protected]>
Gesendet: Jun 21, 2011 6:06:17 PM
An: "Nicolas Kalkhof" <[email protected]>, [email protected]
Betreff: Re: [Intel-gfx] gen6 (SNB) GPU still stalling besides latest patches
Quoted 48 lines
It's i915.i915_enable_rc6=0 for extra added redundancy. You might also try Daniel Blueman's IRQ fix.
Jesse
Quoted 40 lines · On Tue, 21 Jun 2011 07:57:13 +0200 (CEST) "Nicolas Kalkhof" <[email protected]>…
Hi Folks, ok, I'll give it a try this evening. Just one more thing: Should I pass
enable_rc6as a boot parameter like this: "i915.enable_rc6=0" or is it set by echoing sysfs (/sys/module/i915/parameters/...)? regards, nico-----Ursprüngliche Nachricht-----
Von: "Jesse Barnes" <[email protected]>
Gesendet: Jun 21, 2011 2:19:29 AM
An: "Ted Phelps" <[email protected]>
Betreff: Re: [Intel-gfx] gen6 (SNB) GPU still stalling besides latest patchesQuoted 29 lines
Quoted 11 lines · On Tue, 21 Jun 2011 10:01:35 +1000 Ted Phelps <[email protected]> wrote:
Hi Nicolas,
Quoted 7 lines · Nicolas Kalkhof
SNB GPU still hangs frequently with kernel patches next-20110620 raising "drm:i915_hangcheck_ring_idle *ERROR* Hangcheck timer elapsed... gen6 bsd ring idle". This happens when multiple applications (mplayer decoding vaapi stream and some openGL game) running at the same time. With either one running there is no stalling. Could someone please confirm the issue?
Quoted 8 lines
Quoted 2 lines
/sys/module/i915/parameters/semaphoresis set to 0 xf86-video-intel compiled with --enable-snaI haven't tried SNA, but I've seen GPU hangs as well (SNB 2600K). I've found that disabling RC6 (enable_rc6=0) seems to help. Can you see if that helps?
[Note to self: submit a bug report]
Please do; and please try to confirm that your GPU hangs are really rc6 related. RC6 provides a huge (multiple Watt) power savings, and we really want it to be robust.
--
Jesse Barnes, Intel Open Source Technology Center
Quoted 8 lines
Quoted 4 lines
___________________________________________________________
Schon gehört? WEB.DE hat einen genialen Phishing-Filter in die Toolbar eingebaut! http://produkte.web.de/go/toolbar--
Jesse Barnes, Intel Open Source Technology Center
___________________________________________________________
Schon gehört? WEB.DE hat einen genialen Phishing-Filter in die Toolbar eingebaut! http://produkte.web.de/go/toolbar
_______________________________________________
Intel-gfx mailing list [email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 9 lines · On Tue, 21 Jun 2011 18:12:56 +0200 (CEST) "Nicolas Kalkhof" <[email protected]>…
Hi Jesse,
thanks for the infiormation. I've switched rc6 off by echo 0 >
/sys/module/i915/parameters/i915_enable_rc6this should do it, right?
cat/sys/module/i915/parameters/i915_enable_rc6yields "0"Are you referring to this patch? https://lkml.org/lkml/2011/6/17/371
It should be included in kernel 3.0-rc4 and didn't help here :(
So there are actually a few things that could go wrong in this area. The problem may be RC6 related, but it could also be turbo related (our GPU frequency adjustment code). Can you boot without the module parameter and try this patch and see what happens (after a cold boot)?
Thanks,
Jesse
drivers/gpu/drm/i915/intel_display.c +0 -3
@@ -7788,9 +7788,6 @@ void intel_modeset_init(struct drm_device *dev)intel_init_emon (dev); } -if (IS_GEN6 (dev)) -gen6_enable_rps (dev_priv); -INIT_WORK (&dev_priv->idle_work, intel_idle_update);setup_timer (&dev_priv->idle_timer, intel_gpu_idle_timer, (unsigned long )dev);