| Message ID | 520C37DC.90902@labri.fr (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Thursday 15 August 2013 04:07:24 Martin Peres wrote: > On 14/08/2013 05:02, Pali Rohár wrote: > > On Tuesday 13 August 2013 15:55:28 Martin Peres wrote: > >> On 13/08/2013 09:53, Pali Rohár wrote: > >>> On utorok, 13. augusta 2013 15:32:45 CEST, Martin Peres > > > > wrote: > >>>> On 13/08/2013 09:23, Pali Rohár wrote: > >>>>> 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. > >> > >> 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. 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?
From abe97f1e5de0b7ae5114802fcbc99d6e3408cd00 Mon Sep 17 00:00:00 2001 From: Martin Peres <martin.peres@labri.fr> 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. Signed-off-by: Martin Peres <martin.peres@labri.fr> --- .../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(-) diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h index 083541d..11b7993 100644 --- a/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h +++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h @@ -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; diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c b/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c index 22a2057..16b763d 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c @@ -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; diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c b/drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c index 002e51b..5312bbd 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c +++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nv40.c @@ -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); diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c index dde746c..053034e 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c +++ b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c @@ -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; } -- 1.8.3.4