search for: downclock

...u/nvkm/subdev/therm/temp.c @@ -83,7 +83,7 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, { struct nvkm_subdev *subdev = &therm->subdev; bool active; - const char *thresolds[] = { + static const char * const thresholds[] = { "fanboost", "downclock", "critical", "shutdown" }; int temperature = therm->func->temp_get(therm); @@ -94,10 +94,10 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, if (dir == NVKM_THERM_THRS_FALLING) nvkm_info(subdev, "temperature (%i C) w...

...rs) { case NOUVEAU_THERM_THRS_FANBOOST: - nouveau_therm_fan_set(therm, true, 100); - nouveau_therm_mode(therm, NOUVEAU_THERM_CTRL_AUTO); + if (active) { + nouveau_therm_fan_set(therm, true, 100); + nouveau_therm_mode(therm, NOUVEAU_THERM_CTRL_AUTO); + } break; case NOUVEAU_THERM_THRS_DOWNCLOCK: if (priv->emergency.downclock) @@ -126,7 +128,8 @@ void nouveau_therm_sensor_event(struct nouveau_therm *therm, priv->emergency.pause(therm, active); break; case NOUVEAU_THERM_THRS_SHUTDOWN: - orderly_poweroff(true); + if (active) + orderly_poweroff(true); break; case NO...

...> I found a list at community at lists.compiz-fusion.org, is that the > correct one > or just another stray? Also FYI, the "Team" link on the compiz site goes to > 404. (Now I know the shake-up wasn't that bad...:-) I'll test with blur and > see if the nvidia downclocking "feature" is catching me when I get to the > office. > > That seems likely though. On my Arch Linux box where 8.2 works > great, I have > an 8800 GT that seems stuck in full-power mode. If I shut the box down and > let > it cool for a few hours, then restart...

...h at googlemail.com QA Contact: xorg-team at lists.x.org Created attachment 112240 --> https://bugs.freedesktop.org/attachment.cgi?id=112240&action=edit full dmesg kernel: 3.19-rc4 hardware: Thinkpad T510, Quadro NVS 3100M full dmesg attached, nouveau parts below What I did: 1. downclocking before starting X -> '[0000:01:00.0] invalid/missing rammap entry' in dmesg 2. start X -> working fine (could run glxgears, didn't try much else) 3. returning to default performance level -> fine 4. downclocking again -> lockup, broke it with sysrq a...

...rm/nv84.c +++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nv84.c @@ -126,7 +126,7 @@ nv84_therm_intr(struct nouveau_subdev *subdev) spin_lock_irqsave(&priv->sensor.alarm_program_lock, flags); - intr = nv_rd32(therm, 0x20100); + intr = nv_rd32(therm, 0x20100) & 0x3ff; /* THRS_4: downclock */ if (intr & 0x002) { @@ -209,6 +209,19 @@ nv84_therm_ctor(struct nouveau_object *parent, return nouveau_therm_preinit(&priv->base.base); } +int +nv84_therm_fini(struct nouveau_object *object, bool suspend) +{ + /* Disable PTherm IRQs */ + nv_wr32(object, 0x20000, 0x00000000); +...

On 07/10/2014 06:50 PM, Mikko Perttunen wrote: > Does GK20A itself have any kind of thermal protection capabilities? > Upstream SOCTHERM support is not yet available (though I have a driver > in my tree), so we are thinking of disabling CPU DVFS on boards that > don't have always-on active cooling for now. Same might be necessary for > GPU as well. There is a small thermal

Hello, does this sound as a good combination, mini-itx board with Atom dual core 1.6ghz 2G ram and a sangoma USB? For a setup with PSTN for incoming and IAX2(alaw/gsm) for outgoing calls. - Would you say its a good choice from a hardware perspective? - Roughly how many concurrent calls would one of these be able to handle? Regards, Veselin K

...ct nvkm_subdev *subdev = &clk->subdev; if (clk->temp == temp) return 0; clk->temp = temp; + if (clk->max_temp && clk->relax_temp) { + if (!clk->throttled && temp > clk->max_temp) { + nvkm_warn(subdev, + "temperature (%d C) hit the 'downclock' " + "threshold\n", + temp); + clk->throttled = true; + } else if (clk->throttled && temp < clk->relax_temp) { + nvkm_warn(subdev, + "temperature (%d C) went below the " + "'relax' threshold\n", + temp)...

...ct nvkm_subdev *subdev = &clk->subdev; if (clk->temp == temp) return 0; clk->temp = temp; + if (clk->max_temp && clk->relax_temp) { + if (!clk->throttled && temp > clk->max_temp) { + nvkm_warn(subdev, + "temperature (%d C) hit the 'downclock' " + "threshold\n", + temp); + clk->throttled = true; + } else if (clk->throttled && temp < clk->relax_temp) { + nvkm_info(subdev, + "temperature (%d C) went below the " + "'relax' threshold\n", + temp)...

Hi! We (an astronomical center) are building a small cluster for our number-crunching. The problem is that we have 12 mobos A7V600 by Asus (for athlons) - 1 server + 11 diskless nodes. And here comes the trouble... hardware: mobo: a7v600 net: 1 gigabit by 3com - 3c940, integrated in mobo the problem is: dhcp - works fine tftp - works fine pxelinux.0 - downloads fine (I hope) linux kernel -

...e8803901abc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c @@ -86,7 +86,9 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, static const char * const thresholds[] = { "fanboost", "downclock", "critical", "shutdown" }; - int temperature = therm->func->temp_get(therm); + int temperature; + + WARN_ON(nvkm_therm_temp_get(therm, &temperature) < 0); if (thrs < 0 || thrs > 3) return; @@ -140,7 +142,9 @@ nvkm_therm_threshold_hyst_polling(st...

...v/therm/temp.c > > +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c > > @@ -86,7 +86,9 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, > > static const char * const thresholds[] = { > > "fanboost", "downclock", "critical", "shutdown" > > }; > > - int temperature = therm->func->temp_get(therm); > > + int temperature; > > + > > + WARN_ON(nvkm_therm_temp_get(therm, &temperature) < 0); > > > > i...

....e7b8cbe2 100644 > --- a/drm/nouveau/nvkm/subdev/therm/temp.c > +++ b/drm/nouveau/nvkm/subdev/therm/temp.c > @@ -86,7 +86,10 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, > static const char * const thresholds[] = { > "fanboost", "downclock", "critical", "shutdown" > }; > - int temperature = therm->func->temp_get(therm); > + int temperature; > + > + if (therm->func->temp_get(therm, &temperature)) > + return; > > if (thrs < 0 || thrs > 3) > return; >...

....5ec2dfb3 100644 > --- a/drm/nouveau/nvkm/subdev/therm/temp.c > +++ b/drm/nouveau/nvkm/subdev/therm/temp.c > @@ -86,7 +86,10 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, > static const char * const thresholds[] = { > "fanboost", "downclock", "critical", "shutdown" > }; > - int temperature = therm->func->temp_get(therm); > + int temperature; > + > + if (therm->func->temp_get(therm, &temperature) < 0) > + return; > > if (thrs < 0 || thrs > 3) > retur...

...rm/temp.c index ddb2b2c6..5ec2dfb3 100644 --- a/drm/nouveau/nvkm/subdev/therm/temp.c +++ b/drm/nouveau/nvkm/subdev/therm/temp.c @@ -86,7 +86,10 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, static const char * const thresholds[] = { "fanboost", "downclock", "critical", "shutdown" }; - int temperature = therm->func->temp_get(therm); + int temperature; + + if (therm->func->temp_get(therm, &temperature) < 0) + return; if (thrs < 0 || thrs > 3) return; @@ -140,7 +143,10 @@ nvkm_therm_threshold_...

...bdev/therm/temp.c >>> +++ b/drm/nouveau/nvkm/subdev/therm/temp.c >>> @@ -86,7 +86,10 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, >>> static const char * const thresholds[] = { >>> "fanboost", "downclock", "critical", "shutdown" >>> }; >>> - int temperature = therm->func->temp_get(therm); >>> + int temperature; >>> + >>> + if (therm->func->temp_get(therm, &temperature)) >>> +...

...m/nouveau/nvkm/subdev/therm/temp.c > +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c > @@ -86,7 +86,9 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, > static const char * const thresholds[] = { > "fanboost", "downclock", "critical", "shutdown" > }; > - int temperature = therm->func->temp_get(therm); > + int temperature; > + > + WARN_ON(nvkm_therm_temp_get(therm, &temperature) < 0); > > if (thrs < 0 || thrs > 3) >...

before we can let nouveau fully reclock the gpu automatically, we should have a fail safe mechanism to prevent the card from overheating. Starting with G84 GPUs the so called FSRM does the job and automatically downclocks the GPU when specific temperatures thresholds are hit. Lucky for us the needed bits are already configured through a script inside the vbios at POST time and we only need to verify the set bits. This Patch implements the verification steps for all [nvc0,nvf0) cards by printing a debug message and...

...rm/temp.c index ddb2b2c6..e7b8cbe2 100644 --- a/drm/nouveau/nvkm/subdev/therm/temp.c +++ b/drm/nouveau/nvkm/subdev/therm/temp.c @@ -86,7 +86,10 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, static const char * const thresholds[] = { "fanboost", "downclock", "critical", "shutdown" }; - int temperature = therm->func->temp_get(therm); + int temperature; + + if (therm->func->temp_get(therm, &temperature)) + return; if (thrs < 0 || thrs > 3) return; @@ -140,7 +143,10 @@ nvkm_therm_threshold_hyst_po...

...> > +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/temp.c > > > @@ -86,7 +86,9 @@ nvkm_therm_sensor_event(struct nvkm_therm *therm, enum nvkm_therm_thrs thrs, > > > static const char * const thresholds[] = { > > > "fanboost", "downclock", "critical", "shutdown" > > > }; > > > - int temperature = therm->func->temp_get(therm); > > > + int temperature; > > > + > > > + WARN_ON(nvkm_therm_temp_get(therm, &temperature) < 0); >...