similar to: [PATCH] therm/gm200: Added

This adds support for enabling automatic clockgating on nvidia GPUs for Kepler1. While this is not technically a clockgating level, it does enable clockgating using the clockgating values initially set by the vbios (which should be safe to use). This introduces two therm helpers for controlling basic clockgating: nvkm_therm_clkgate_enable() - enables clockgating through CG_CTRL, done after

This adds support for enabling automatic clockgating on nvidia GPUs for Kepler1. While this is not technically a clockgating level, it does enable clockgating using the clockgating values initially set by the vbios (which should be safe to use). This introduces two therm helpers for controlling basic clockgating: nvkm_therm_clkgate_enable() - enables clockgating through CG_CTRL, done after

This adds support for enabling automatic clockgating on nvidia GPUs for Kepler1, referred to as "CG" throughout the driver. This is one of two powersaving levels that Kepler1 supports. This introduces two therm helpers for controlling basic clockgating: nvkm_therm_clkgate_enable() - enables clockgating through CG_CTRL, done after initializing the GPU fully nvkm_therm_clkgate_fini() -

v2: - add nv138 and drop nv13b chipsets (Ilia Mirkin) - refactor out status variable and instead mask tsensor (Ilia Mirkin) - switch SHADOWed state message away from nvkm_error() (Ilia Mirkin) - rename internal temperature variable (Karol Herbst) Signed-off-by: Rhys Kidd <rhyskidd at gmail.com> --- .../gpu/drm/nouveau/include/nvkm/subdev/therm.h | 1 +

On Fri, Jan 26, 2018 at 4:35 AM, Lyude Paul <lyude at redhat.com> wrote: > This adds support for enabling automatic clockgating on nvidia GPUs for > Kepler1. While this is not technically a clockgating level, it does > enable clockgating using the clockgating values initially set by the > vbios (which should be safe to use). > > This introduces two therm helpers for

Signed-off-by: Rhys Kidd <rhyskidd at gmail.com> --- .../gpu/drm/nouveau/include/nvkm/subdev/therm.h | 1 + drivers/gpu/drm/nouveau/nvkm/engine/device/base.c | 6 +++ drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild | 1 + drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c | 3 +- drivers/gpu/drm/nouveau/nvkm/subdev/therm/gp100.c | 57 ++++++++++++++++++++++ 5 files changed, 67

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

Add secure-boot for the dGPU set of GM20X chips, using the PMU as the high-secure falcon. This work is based on Deepak Goyal's initial port of Secure Boot to Nouveau. Signed-off-by: Alexandre Courbot <acourbot at nvidia.com> --- drm/nouveau/include/nvkm/subdev/secboot.h | 2 + drm/nouveau/nvkm/engine/device/base.c | 2 + drm/nouveau/nvkm/engine/gr/gm200.c | 8 +-

The state of the falcons was not properly updated after running the unload ACR, which caused it to be run again (and thus fail) when nvkm_secboot_fini() was called during resume. Signed-off-by: Alexandre Courbot <acourbot at nvidia.com> --- Ben, please feel free to squash this into the gm200 secboot implementation patch - this fixes a bug that should not have been here to begin with.

Use nvkm_memory_target() to know the location of the instance block used for secure boot, instead of guessing through the presence of a RAM device. Signed-off-by: Alexandre Courbot <acourbot at nvidia.com> --- Ben, feel free to squash this one into the original secboot patch since it is a really minor fix. drm/nouveau/nvkm/subdev/secboot/gm200.c | 2 +- 1 file changed, 1 insertion(+), 1

This adds support for enabling automatic clockgating on nvidia GPUs for Fermi and later generations. This saves a little bit of power, bringing my fermi GPU's power consumption from ~28.3W on idle to ~27W, and my kepler's idle power consumption from ~23.6W to ~21.65W. Similar to how the nvidia driver seems to handle this, we enable clockgating for each engine that supports it after

Hi Lyude, thanks for the great work. Just a view comments inline. 2017-04-25 20:38 GMT+02:00 Lyude <lyude at redhat.com>: > This adds support for enabling automatic clockgating on nvidia GPUs for > Fermi and later generations. This saves a little bit of power, bringing > my fermi GPU's power consumption from ~28.3W on idle to ~27W, and my > kepler's idle power

Thanks for the work so far. A quick scan through the first NVC4 trace at hand, using upstream demmio, reveals at least 20 writes to the BLCG registers of PGRAPH and a few in PXBAR prior to altering the value of register 0x20200 (see below). We know that these are related to the clock gating you enable. Are you 110% sure that fiddling with 0x20200 bits without first setting these values can

The current hwmon code doesn't check if the returned value was actually an error. Since Kepler temperature sensors are able to report negative values. Since Pascal (and maybe earlier) we have sensors with improved precision. Adjust the nvkm_get_temp method to be able to deal with those changes and let hwmon return an error properly. Signed-off-by: Karol Herbst <karolherbst at

On 29/09/16 03:41, Martin Peres wrote: > This seems to be absolutely necessary for a lot of NV40. > > Reported-by: gsgf on IRC/freenode > Signed-off-by: Martin Peres <martin.peres at free.fr> I of course forgot to tag this patch for stable. The thing has been broken on some nv40 ... forever? > --- > drm/nouveau/nvkm/subdev/therm/base.c | 22 +++++++++++++++++++--- >

This seems to be absolutely necessary for a lot of NV40. Reported-by: gsgf on IRC/freenode Signed-off-by: Martin Peres <martin.peres at free.fr> --- drm/nouveau/nvkm/subdev/therm/base.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drm/nouveau/nvkm/subdev/therm/base.c b/drm/nouveau/nvkm/subdev/therm/base.c index 8894fee..df949fa 100644 ---

The current hwmon code doesn't check if the returned value was actually an error. Since Kepler temperature sensors are able to report negative values. Those negative values are not for error reporting, but rather when you buried your GPU in snow somewhere in Antarctica and still want a valid temperature to be reported (unverified). Since Pascal (and maybe earlier) we have sensors with

On Wed, 2017-04-26 at 00:49 +0200, Karol Herbst wrote: > Hi Lyude, > > thanks for the great work. Just a view comments inline. > > 2017-04-25 20:38 GMT+02:00 Lyude <lyude at redhat.com>: > > This adds support for enabling automatic clockgating on nvidia GPUs > > for > > Fermi and later generations. This saves a little bit of power, > > bringing >

On Wed, Nov 22, 2017 at 1:32 AM, Martin Peres <martin.peres at free.fr> wrote: > On 17/11/17 02:04, Karol Herbst wrote: >> The current hwmon code doesn't check if the returned value was actually an >> error. >> >> Since Kepler temperature sensors are able to report negative values. Those >> negative values are not for error reporting, but rather when you

This enables BLCG optimization for kepler1. When using clockgating, nvidia's firmware has a set of registers which are initially programmed by the vbios with various engine delays and other mysterious settings that are safe enough to bring up the GPU. However, the values used by the vbios are more power hungry then they need to be, so the nvidia driver writes it's own more optimized set of