Skip to contentSkip to conversation

nouveau: temperature on nv40 is unavailable since ad40d73ef533ab0ad16b4a1ab2f7870c1f8ab954

DISCUSSION Pali Rohár 2 participants 12 messages Aug 13, 2013 – Aug 21, 2013

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

Hello,

after commit ad40d73ef533ab0ad16b4a1ab2f7870c1f8ab954 temperature information from lm sensors is not available on my Nvidia 6600GT graphics card. There is no nouveau hwmon entry in sysfs anymore. Why it was removed? Can I help with debugging? I'd like to see temperature sensor working again.

Signature · 2 lines
Pali Rohár
[email protected]
#1 lore raw
Quoted 7 lines · Pali Rohár

Hello,

after commit ad40d73ef533ab0ad16b4a1ab2f7870c1f8ab954 temperature information from lm sensors is not available on my Nvidia 6600GT graphics card. There is no nouveau hwmon entry in sysfs anymore. Why it was removed? Can I help with debugging? I'd like to see temperature sensor working again.

Hi,

Thanks for bisecting the issue. Can you send me your vbios and tell me if the nvidia driver shows your temperature probe (and what is its source).

To fetch your vbios, you can extract it using nvagetbios from the envytools repo: https://github.com/envytools/envytools

Cheers,
Martin

_______________________________________________
dri-devel mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/dri-devel

#2 lore raw
Quoted 15 lines · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:
Quoted 7 lines · Pali Rohár

Hello,

after commit ad40d73ef533ab0ad16b4a1ab2f7870c1f8ab954 temperature information from lm sensors is not available on my Nvidia 6600GT graphics card. There is no nouveau hwmon entry in sysfs anymore. Why it was removed? Can I help with debugging? I'd like to see temperature sensor working again.

Hi,

Thanks for bisecting the issue. Can you send me your vbios and tell me if the nvidia driver shows your temperature probe (and what is its source).

Quoted 5 lines

To fetch your vbios, you can extract it using nvagetbios from the envytools repo: https://github.com/envytools/envytools

Cheers,
Martin

How can I check source and temperature probe in nvidia binary driver?

Signature · 2 lines
Pali Rohár
[email protected]
#3 lore raw
Quoted 15 lines · Pali Rohár
Quoted 14 lines · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:
Quoted 7 lines · Pali Rohár

Hello,

after commit ad40d73ef533ab0ad16b4a1ab2f7870c1f8ab954 temperature information from lm sensors is not available on my Nvidia 6600GT graphics card. There is no nouveau hwmon entry in sysfs anymore. Why it was removed? Can I help with debugging? I'd like to see temperature sensor working again.

Hi,

Thanks for bisecting the issue. Can you send me your vbios and tell me if the nvidia driver shows your temperature probe (and what is its source).

Quoted 6 lines
Quoted 5 lines

To fetch your vbios, you can extract it using nvagetbios from the envytools repo: https://github.com/envytools/envytools

Cheers,
Martin

How can I check source and temperature probe in nvidia binary driver?

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and I'm not sure we should :s

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

#4 lore raw
Quoted 12 lines · Martin Peres
Quoted 1 line · Pali Rohár

On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:

...
You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and I'm not sure we should :s

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Signature · 2 lines
Pali Rohár
[email protected]
#5 lore raw
Quoted 16 lines · Pali Rohár
Quoted 12 lines · Martin Peres
Quoted 1 line · Pali Rohár

On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:

...
You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and I'm not sure we should :s

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Quoted 8 lines

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

#6 lore raw
Quoted 2 lines · On Tuesday 13 August 2013 15:55:28 Martin Peres wrote:
Quoted 1 line · Pali Rohár

On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres

Quoted 22 lines · wrote:
Quoted 22 lines
Quoted 12 lines · Pali Rohár
Quoted 1 line · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:

...

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and
I'm not sure we should :s

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

Quoted 8 lines
Quoted 4 lines

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

Ok, send me patch and I can try it if it will work and report similar values as windows or nvidia driver.

Signature · 2 lines
Pali Rohár
[email protected]
#7 lore raw
Quoted 29 lines · Pali Rohár
Quoted 2 lines · On Tuesday 13 August 2013 15:55:28 Martin Peres wrote:
Quoted 1 line · Pali Rohár

On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres

Quoted 25 lines · wrote:
Quoted 25 lines
Quoted 12 lines · Pali Rohár
Quoted 1 line · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:

...

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and
I'm not sure we should :s

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Quoted 6 lines
Quoted 3 lines

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

Ok, send me patch and I can try it if it will work and report similar values as windows or nvidia driver.

Sorry for the late answer.

Please test this patch. Be aware that temperature with nouveau will be higher than with the blob. I only want to see if nouveau reports a temperature.

The only way to be sure if the values are good-enough would be to use the blob and run:
nvapeek 0x15b0
Please send me the result along with the temperature reported by nvidia at the time of the peek.

Martin

PS: This patch has only be compile-tested, I don't have access to an nv4x right now.

Quoted 1 line

From abe97f1e5de0b7ae5114802fcbc99d6e3408cd00 Mon Sep 17 00:00:00 2001

From: Martin Peres <[email protected]>
Date: Wed, 14 Aug 2013 22:00:48 -0400
Subject: [PATCH] drm/nv40/therm: set default calibration values if needed

Some vbios expose a thermal sensor but do not set default calibration values. As they are almost always the same, let's set some default ones.

---
 .../drm/nouveau/core/include/subdev/bios/therm.h   |  1 +
 drivers/gpu/drm/nouveau/core/subdev/bios/therm.c   |  1 +
 drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c   | 36 ++++++++++++++++++----
 drivers/gpu/drm/nouveau/core/subdev/therm/temp.c   |  5 ++-
 4 files changed, 34 insertions(+), 9 deletions(-)
drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h +1 -0
index 083541d..11b7993 100644
@@ -10,6 +10,7 @@ struct nvbios_therm_threshold {
 
 struct nvbios_therm_sensor {
 	/* diode */
+	int has_sensor;
 	s16 slope_mult;
 	s16 slope_div;
 	s16 offset_num;
drivers/gpu/drm/nouveau/core/subdev/bios/therm.c +1 -0
index 22a2057..16b763d 100644
@@ -95,6 +95,7 @@ nvbios_therm_sensor_parse(struct nouveau_bios *bios,
 			sensor_section++;
 			if (sensor_section == 0) {
 				offset = ((s8) nv_ro08(bios, entry + 2)) / 2;
+				sensor->has_sensor = 1;
 				sensor->offset_constant = offset;
 			}
 			break;
drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c +30 -6
index 002e51b..5312bbd 100644
@@ -93,11 +93,6 @@ nv40_temp_get(struct nouveau_therm *therm)
 	} else
 		return -ENODEV;
 
-	/* if the slope or the offset is unset, do no use the sensor */
-	if (!sensor->slope_div || !sensor->slope_mult ||
-	    !sensor->offset_num || !sensor->offset_den)
-	    return -ENODEV;
-
 	core_temp = core_temp * sensor->slope_mult / sensor->slope_div;
 	core_temp = core_temp + sensor->offset_num / sensor->offset_den;
 	core_temp = core_temp + sensor->offset_constant - 8;
@@ -171,7 +166,7 @@ nv40_therm_intr(struct nouveau_subdev *subdev)
 	struct nouveau_therm *therm = nouveau_therm(subdev);
 	uint32_t stat = nv_rd32(therm, 0x1100);
 
-	/* traitement */
+	/* TODO: do something? Need more RE first */
 
 	/* ack all IRQs */
 	nv_wr32(therm, 0x1100, 0x70000);
@@ -202,11 +197,40 @@ nv40_therm_ctor(struct nouveau_object *parent,
 	return nouveau_therm_preinit(&priv->base.base);
 }
 
+static void
+nv40_therm_temp_safety_checks(struct nouveau_therm *therm)
+{
+	struct nouveau_therm_priv *priv = (void *)therm;
+	struct nvbios_therm_sensor *sensor = &priv->bios_sensor;
+	enum nv40_sensor_style style = nv40_sensor_style(therm);
+
+	/* if the slope or the offset is unset, do no use the sensor */
+	if (sensor->has_sensor && (!sensor->slope_div || !sensor->slope_mult ||
+	    !sensor->offset_num || !sensor->offset_den)) {
+
+		nv_info(therm, "Invalid sensor calibration values. "
+		               "Set default calibration values\n");
+
+		if (style == NEW_STYLE) {
+			sensor->slope_div = 10000;
+			sensor->slope_mult = 450;
+			sensor->offset_num = -25000;
+			sensor->offset_den = 100;
+		} else 	if (style == OLD_STYLE) {
+			sensor->slope_div = 1000;
+			sensor->slope_mult = 792;
+			sensor->offset_num = 2306;
+			sensor->offset_den = 100;
+		}
+	}
+}
+
 static int
 nv40_therm_init(struct nouveau_object *object)
 {
 	struct nouveau_therm *therm = (void *)object;
 
+	nv40_therm_temp_safety_checks(therm);
 	nv40_sensor_setup(therm);
 
 	return _nouveau_therm_init(object);
drivers/gpu/drm/nouveau/core/subdev/therm/temp.c +2 -3
index dde746c..053034e 100644
@@ -49,9 +49,8 @@ nouveau_therm_temp_set_defaults(struct nouveau_therm *therm)
 	priv->bios_sensor.thrs_shutdown.hysteresis = 5; /*not that it matters */
 }
 
-
 static void
-nouveau_therm_temp_safety_checks(struct nouveau_therm *therm)
+nouveau_therm_sensor_safety_checks(struct nouveau_therm *therm)
 {
 	struct nouveau_therm_priv *priv = (void *)therm;
 	struct nvbios_therm_sensor *s = &priv->bios_sensor;
@@ -239,7 +238,7 @@ nouveau_therm_sensor_ctor(struct nouveau_therm *therm)
 	if (nvbios_therm_sensor_parse(bios, NVBIOS_THERM_DOMAIN_CORE,
 				      &priv->bios_sensor))
 		nv_error(therm, "nvbios_therm_sensor_parse failed\n");
-	nouveau_therm_temp_safety_checks(therm);
+	nouveau_therm_sensor_safety_checks(therm);
 
 	return 0;
 }
Signature · 1 line
1.8.3.4
#8 lore raw
Quoted 54 lines · On Thursday 15 August 2013 04:07:24 Martin Peres wrote:
Quoted 33 lines · Pali Rohár
Quoted 2 lines · On Tuesday 13 August 2013 15:55:28 Martin Peres wrote:
Quoted 1 line · Pali Rohár

On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres

Quoted 28 lines · wrote:
Quoted 27 lines
Quoted 9 lines · Pali Rohár
Quoted 1 line · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:

...

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and
I'm not sure we should :s

Quoted 4 lines

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Quoted 7 lines
Quoted 4 lines

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

Ok, send me patch and I can try it if it will work and report similar values as windows or nvidia driver.

Sorry for the late answer.

Please test this patch. Be aware that temperature with nouveau will be higher than with the blob.
I only want to see if nouveau reports a temperature.

The only way to be sure if the values are good-enough would be to use the blob and run:
nvapeek 0x15b0
Please send me the result along with the temperature reported by nvidia at the time of the peek.

Quoted 4 lines

Martin

PS: This patch has only be compile-tested, I don't have access to an nv4x right now.

Hello,

now after patch nouveau report temperature:

$ sensors
...
nouveau-pci-0500
Adapter: PCI adapter
temp1:        +63.0°C  (high = +95.0°C, hyst =  +3.0°C)
                       (crit = +145.0°C, hyst =  +2.0°C)
                       (emerg = +135.0°C, hyst =  +5.0°C)
...

I found that nvidia binary driver has command line utility nvidia-smi which report same temperature as X utility nvidia- settings. So I will use nvidia-smi (if it is OK).

And after reboot nvidia report another temperature value:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0
    Temperature
        Gpu                     : 70 C

Immediately I called nvapeek command:

$ nvapeek 0x15b0
000015b0: 1000008e

So value reported by nouveau is lower than value reported by nvidia binary driver.

I wait some some and started nvidia-smi and nvapeek again, here are results:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0
    Temperature
        Gpu                     : 67 C
$ nvapeek 0x15b0
000015b0: 1000008e

So it looks like that nvapeek returning always same value and does not depends on temperature... It is OK?

Signature · 2 lines
Pali Rohár
[email protected]
#9 lore raw
Quoted 58 lines · Pali Rohár
Quoted 49 lines · On Thursday 15 August 2013 04:07:24 Martin Peres wrote:
Quoted 30 lines · Pali Rohár
Quoted 2 lines · On Tuesday 13 August 2013 15:55:28 Martin Peres wrote:
Quoted 1 line · Pali Rohár

On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres

Quoted 26 lines · wrote:
Quoted 26 lines
Quoted 9 lines · Pali Rohár
Quoted 1 line · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:
   ...

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and
I'm not sure we should :s

Quoted 4 lines

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Quoted 6 lines
Quoted 4 lines

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

Ok, send me patch and I can try it if it will work and report similar values as windows or nvidia driver.

Sorry for the late answer.

Please test this patch. Be aware that temperature with nouveau will be higher than with the blob.
I only want to see if nouveau reports a temperature.

The only way to be sure if the values are good-enough would be to use the blob and run:
nvapeek 0x15b0
Please send me the result along with the temperature reported by nvidia at the time of the peek.

Quoted 4 lines

Martin

PS: This patch has only be compile-tested, I don't have access to an nv4x right now.

Hello,

now after patch nouveau report temperature:

Quoted 7 lines
$ sensors
...
nouveau-pci-0500
Adapter: PCI adapter
temp1:        +63.0°C  (high = +95.0°C, hyst =  +3.0°C)
                        (crit = +145.0°C, hyst =  +2.0°C)
                        (emerg = +135.0°C, hyst =  +5.0°C)

Ok, that was expected ;)

Quoted 14 lines

...

I found that nvidia binary driver has command line utility nvidia-smi which report same temperature as X utility nvidia- settings. So I will use nvidia-smi (if it is OK).

And after reboot nvidia report another temperature value:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0
     Temperature
         Gpu                     : 70 C
Quoted 7 lines

Immediately I called nvapeek command:

$ nvapeek 0x15b0
000015b0: 1000008e

So value reported by nouveau is lower than value reported by nvidia binary driver.

As you didn't run nvapeek 15b0 when running nouveau it is hard to tell if it is due to calibration values or because the temperature was lower.

Could you please read the temperature + peek 15b0 when running nouveau?

Anyway, it is weird because I cannot find 70°C with 0x8e as an input temperature and with the current default values :o

Quoted 9 lines

I wait some some and started nvidia-smi and nvapeek again, here are results:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0
     Temperature
         Gpu                     : 67 C
Quoted 5 lines
$ nvapeek 0x15b0
000015b0: 1000008e

So it looks like that nvapeek returning always same value and does not depends on temperature... It is OK?

Well, it looks like the temperature reading is very noisy!
Could you please get the temperature + peek when the card is as hot as possible?

There is a very effective solution to get a GPU hot, use a hair drier. If you could get your GPU to at 110°C (or less, if you feel like it is too much), that could help me check the formula and default values.

PS: I attached a new version of the patch that should improve the temperature accuracy for nv43s. Could you test it and send me your kernel log?

Quoted 1 line

From 8c806fd49d87ecf57e98713537a7d23d1f7712d9 Mon Sep 17 00:00:00 2001

From: Martin Peres <[email protected]>
Date: Wed, 14 Aug 2013 22:00:48 -0400
Subject: [PATCH] drm/nv40/therm: set default calibration values if needed

Some vbios expose a thermal sensor but do not set default calibration values. As they are almost always the same, let's set some default ones.

v2:
- the nv43 requires a different offset numerator
- cosmetic changes

---
 .../drm/nouveau/core/include/subdev/bios/therm.h   |  1 +
 drivers/gpu/drm/nouveau/core/subdev/bios/therm.c   |  1 +
 drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c   | 43 +++++++++++++++++++---
 drivers/gpu/drm/nouveau/core/subdev/therm/temp.c   |  5 +--
 4 files changed, 41 insertions(+), 9 deletions(-)
drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h +1 -0
index 083541d..11b7993 100644
@@ -10,6 +10,7 @@ struct nvbios_therm_threshold {
 
 struct nvbios_therm_sensor {
 	/* diode */
+	int has_sensor;
 	s16 slope_mult;
 	s16 slope_div;
 	s16 offset_num;
drivers/gpu/drm/nouveau/core/subdev/bios/therm.c +1 -0
index 22a2057..16b763d 100644
@@ -95,6 +95,7 @@ nvbios_therm_sensor_parse(struct nouveau_bios *bios,
 			sensor_section++;
 			if (sensor_section == 0) {
 				offset = ((s8) nv_ro08(bios, entry + 2)) / 2;
+				sensor->has_sensor = 1;
 				sensor->offset_constant = offset;
 			}
 			break;
drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c +37 -6

66 lines not on this page · raw message

drivers/gpu/drm/nouveau/core/subdev/therm/temp.c +2 -3
index dde746c..053034e 100644
@@ -49,9 +49,8 @@ nouveau_therm_temp_set_defaults(struct nouveau_therm *therm)
 	priv->bios_sensor.thrs_shutdown.hysteresis = 5; /*not that it matters */
 }
 
-
 static void
-nouveau_therm_temp_safety_checks(struct nouveau_therm *therm)
+nouveau_therm_sensor_safety_checks(struct nouveau_therm *therm)
 {
 	struct nouveau_therm_priv *priv = (void *)therm;
 	struct nvbios_therm_sensor *s = &priv->bios_sensor;
@@ -239,7 +238,7 @@ nouveau_therm_sensor_ctor(struct nouveau_therm *therm)
 	if (nvbios_therm_sensor_parse(bios, NVBIOS_THERM_DOMAIN_CORE,
 				      &priv->bios_sensor))
 		nv_error(therm, "nvbios_therm_sensor_parse failed\n");
-	nouveau_therm_temp_safety_checks(therm);
+	nouveau_therm_sensor_safety_checks(therm);
 
 	return 0;
 }
Signature · 1 line
1.8.3.4
#10 lore raw
Quoted 97 lines · On Thursday 15 August 2013 18:21:51 Martin Peres wrote:
Quoted 64 lines · Pali Rohár
Quoted 54 lines · On Thursday 15 August 2013 04:07:24 Martin Peres wrote:
Quoted 33 lines · Pali Rohár
Quoted 2 lines · On Tuesday 13 August 2013 15:55:28 Martin Peres wrote:
Quoted 1 line · Pali Rohár

On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres

Quoted 28 lines · wrote:
Quoted 27 lines
Quoted 9 lines · Pali Rohár
Quoted 1 line · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:
   ...

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and
I'm not sure we should :s

Quoted 4 lines

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Quoted 7 lines
Quoted 4 lines

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

Ok, send me patch and I can try it if it will work and report similar values as windows or nvidia driver.

Sorry for the late answer.

Please test this patch. Be aware that temperature with nouveau will be higher than with the blob.
I only want to see if nouveau reports a temperature.

The only way to be sure if the values are good-enough would be to use the blob and run:
nvapeek 0x15b0
Please send me the result along with the temperature reported by nvidia at the time of the peek.

Quoted 4 lines

Martin

PS: This patch has only be compile-tested, I don't have access to an nv4x right now.

Hello,

now after patch nouveau report temperature:

Quoted 8 lines
$ sensors
...
nouveau-pci-0500
Adapter: PCI adapter
temp1:        +63.0°C  (high = +95.0°C, hyst =  +3.0°C)
                        (crit = +145.0°C, hyst =  +2.0°C)
                        (emerg = +135.0°C, hyst =  +5.0°C)

Ok, that was expected ;)

Quoted 21 lines

...

I found that nvidia binary driver has command line utility nvidia-smi which report same temperature as X utility nvidia- settings. So I will use nvidia-smi (if it is OK).

And after reboot nvidia report another temperature value:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0

Temperature

Gpu : 70 C

Immediately I called nvapeek command:

$ nvapeek 0x15b0
000015b0: 1000008e
Quoted 7 lines
Quoted 2 lines

So value reported by nouveau is lower than value reported by nvidia binary driver.

As you didn't run nvapeek 15b0 when running nouveau it is hard to tell if it is due to
calibration values or because the temperature was lower.

I run it and it always reported value 000000ff (also when temperature changed).

Quoted 6 lines

Could you please read the temperature + peek 15b0 when running nouveau?

Anyway, it is weird because I cannot find 70°C with 0x8e as an input temperature and with
the current default values :o

My idea is that register does not contains temperature. Both nouveau and nvidia driver when show different temperature it does not show different output from "nvapeek 0x15b0".

Now I started computer with nouveau driver. Temperature is incresing, but nvapeek 0x15b0 is still same.

So do you really needs other tests with nvapeek 0x15b0? Is that register correct?

Quoted 30 lines
Quoted 9 lines

I wait some some and started nvidia-smi and nvapeek again, here are results:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0

Temperature

Quoted 7 lines

Gpu : 67 C

$ nvapeek 0x15b0
000015b0: 1000008e

So it looks like that nvapeek returning always same value and does not depends on temperature... It is OK?

Well, it looks like the temperature reading is very noisy! Could you please get the temperature + peek when the card is as hot as possible?

There is a very effective solution to get a GPU hot, use a hair drier. If you could get your
GPU to at 110°C (or less, if you feel like it is too much), that could help me check the formula
and default values.

PS: I attached a new version of the patch that should improve the temperature accuracy for
nv43s. Could you test it and send me your kernel log?

Signature · 2 lines
Pali Rohár
[email protected]
#11 lore raw
Quoted 91 lines · Pali Rohár
Quoted 90 lines · On Thursday 15 August 2013 18:21:51 Martin Peres wrote:
Quoted 58 lines · Pali Rohár
Quoted 49 lines · On Thursday 15 August 2013 04:07:24 Martin Peres wrote:
Quoted 30 lines · Pali Rohár
Quoted 2 lines · On Tuesday 13 August 2013 15:55:28 Martin Peres wrote:
Quoted 1 line · Pali Rohár

On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres

Quoted 26 lines · wrote:
Quoted 26 lines
Quoted 9 lines · Pali Rohár
Quoted 1 line · On Tuesday 13 August 2013 09:01:19 Martin Peres wrote:
    ...

You can check the temperature by running nvidia-settings. If you can't see the temperature in it, then nvidia doesn't support it on your card and
I'm not sure we should :s

Quoted 4 lines

Thanks for the vbios you sent me in private. For the others, the reason why he doesn't have temperature anymore is because his vbios lacks sensor calibration values.

In nvidia-settings tab "GPU 0 - (GeForce 6600 GT)" --> "Thermal Settings" is:

Thermal Sensor Information:
ID: 0
Target: GPU
Provider: GPU Internal
Temperature: 70 C (now)

I looked in Windows program SpeedFan. It found Nvidia PCI card and reported "GPU Temp" about 68-70 C. So it looks like both nvidia driver and windows SpeedFan program reading same values.

Quoted 6 lines
Quoted 4 lines

Great, I'll cook you a patch in a bit and you'll see what the temperature is like. It won't be perfectly accurate but there is some kind of default for nvidia cards of this generation.

Ok, send me patch and I can try it if it will work and report similar values as windows or nvidia driver.

Sorry for the late answer.

Please test this patch. Be aware that temperature with nouveau will be higher than with the blob.
I only want to see if nouveau reports a temperature.

The only way to be sure if the values are good-enough would be to use the blob and run:
nvapeek 0x15b0
Please send me the result along with the temperature reported by nvidia at the time of the peek.

Quoted 4 lines

Martin

PS: This patch has only be compile-tested, I don't have access to an nv4x right now.

Hello,

now after patch nouveau report temperature:

Quoted 8 lines
$ sensors
...
nouveau-pci-0500
Adapter: PCI adapter
temp1:        +63.0°C  (high = +95.0°C, hyst =  +3.0°C)
                         (crit = +145.0°C, hyst =  +2.0°C)
                         (emerg = +135.0°C, hyst =  +5.0°C)

Ok, that was expected ;)

Quoted 21 lines

...

I found that nvidia binary driver has command line utility nvidia-smi which report same temperature as X utility nvidia- settings. So I will use nvidia-smi (if it is OK).

And after reboot nvidia report another temperature value:

$ nvidia-smi -q -d TEMPERATURE
...
GPU 0000:05:00.0

Temperature

Gpu : 70 C

Immediately I called nvapeek command:

$ nvapeek 0x15b0
000015b0: 1000008e
Quoted 7 lines
Quoted 6 lines
Quoted 2 lines

So value reported by nouveau is lower than value reported by nvidia binary driver.

As you didn't run nvapeek 15b0 when running nouveau it is hard to tell if it is due to
calibration values or because the temperature was lower.

I run it and it always reported value 000000ff (also when temperature changed).

Seems like we may not calibrate the ADC correctly, this is weird.

Quoted 11 lines
Quoted 7 lines

Could you please read the temperature + peek 15b0 when running nouveau?

Anyway, it is weird because I cannot find 70°C with 0x8e as an input temperature and with
the current default values :o

My idea is that register does not contains temperature. Both nouveau and nvidia driver when show different temperature it does not show different output from "nvapeek 0x15b0".

Quoted 5 lines

Now I started computer with nouveau driver. Temperature is incresing, but nvapeek 0x15b0 is still same.

So do you really needs other tests with nvapeek 0x15b0? Is that register correct?

I want you to be really sure that 15b0 doesn't change with temperature ON THE PROPRIETARY driver. This is very serious if this is not the case.

If this is not the case, then you must have an i2c device from which the blob is reading temperature and this device isn't detected by Nouveau.