[Nouveau] [PATCH v2 09/22] clk: add index field to nvkm_cstate

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/clk.h | 1 + drm/nouveau/nvkm/subdev/clk/base.c| 1 + 2 files changed, 2 insertions(+) diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index fb54417..6

[Nouveau] [PATCH v2 14/22] bios: add parsing of BASE CLOCK table

: the avg clock the gpu will stay boosted to. It doesn't seem to affect the behaviour of the nvidia driver at all though. v2: make clear that base/boost/tdp fields are ids Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr&

[Nouveau] [PATCH v2 21/22] nvif: add boost info and set operations

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvif/if0001.h | 15 + drm/nouveau/nvkm/engine/device/ctrl.c | 59 +++ 2 files changed, 74 insertions(+) diff --git a/drm/nouveau/include/nvif/if0001.h b/drm/nouveau/i

[Nouveau] [PATCH v2 00/22] Volting/Clocking improvements for Fermi and newer

: boost_mode can now be changed at runtime minor fixups Karol Herbst (22): bios/volt: handle voltage table version 0x50 with 0ed header volt: properly detect entry based voltage tables volt: save the voltage range we are able to set volt: add nvkm_volt_map_min function clk: don't create cstates

[Nouveau] [PATCH v2 13/22] clk: respect voltage limits in nvkm_cstate_prog with cstate = -1

we should never allow to select a cstate which current voltage (depending on the temperature) is higher than 1. the max volt entries in the voltage map table 2. what tha gpu actually can volt to this resolves all remaining volting errors on fermi and newer Signed-off-by: Karol Herbst <n

[Nouveau] [PATCH v2 18/22] volt: add coefficients I found on my gpu

task for this is to figure out which of these constants are chip specific and from where to get the chip specific factors Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/volt/base.c | 54 - 1 file changed, 48 insertions

[Nouveau] [PATCH v2 19/22] clk: save the max clock we can set

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/clk.h | 1 + drm/nouveau/nvkm/subdev/clk/base.c| 2 ++ 2 files changed, 3 insertions(+) diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index 99ee05c..6

[Nouveau] [PATCH v2 04/22] volt: add nvkm_volt_map_min function

this is a copy of nvkm_volt_map, which always returns the lowest possible voltage for a cstate nvkm_volt_map will get a temperature parameter there later and also fix the voltage calculation, so that this functions will be completly different in later commits Signed-off-by: Karol Herbst <n

[Nouveau] [PATCH v2 20/22] clk: add nvkm_clk_reclock function

this function just forces a reclock. This makes sense if some cstates get (un)available and we have to adjust to that. This can happen for various reasons: * temperature changes * user changes boost mode Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/

[Nouveau] [PATCH v2 17/22] bios/vmap: unk0 field is the mode

this selects which formula is used to calculate the voltage Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 +- drm/nouveau/nvkm/subdev/bios/vmap.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drm/n

[Nouveau] [PATCH v2 11/22] volt: add temperature parameter to nvkm_volt_map

the voltage entries actually may map to a different voltage depending on the current temperature. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- bin/nv_cmp_volt.c | 2 +- drm/nouveau/include/nvkm/subdev/volt.h | 2 +- drm/nouveau/nvkm/subdev/volt/base.c

[Nouveau] [PATCH v2 15/22] clk: allow boosting only when NvBoost is set

0: base clock from the vbios is max clock 1: boost only to boost clock from the vbios (default) 2: boost to max clock available v2: moved into nvkm_cstate_valid Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/

[Nouveau] [PATCH v2 05/22] clk: don't create cstates which voltage is higher than what the gpu can do

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Tested-by: Pierre Moreau <pierre.mor...@free.fr> --- drm/nouveau/nvkm/subdev/clk/base.c | 4 1 file changed, 4 insertions(+) diff --git a/drm/nouveau/nvkm/subdev/clk/base.c b/drm/nouveau/nvkm/subdev/clk/base.c index 889c

[Nouveau] [PATCH v2 06/22] volt: parse the both max voltage entries

these entries specify a maximum voltage nvidia never exceeds, we shouldn't do that, too. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 ++ drm/nouveau/include/nvkm/subdev/volt.h | 2 ++ drm/nouveau/nvkm/subdev/bios/

[Nouveau] [PATCH v2 10/22] add daemon to compare nouveau with blob voltage

this tool can be run alongside the nvidia driver to print information about the current p/cstate, which voltage was set by nvidia and what nouveau would set in the same situation. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- bin/nv_cmp_volt.c

[Nouveau] [PATCH v2 16/22] volt: don't require perfect fit

if we calculate the voltage in the table right, we get all kinds of values, which never fit the hardware steps, so we use the closest higher value the hardware can do Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/volt/base.c | 25 ++

[Nouveau] [PATCH v2 01/22] bios/volt: handle voltage table version 0x50 with 0ed header

hem to switch cstates Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> Tested-by: Pierre Moreau <pierre.mor...@free.fr> --- drm/nouveau/nvkm/subdev/bios/volt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drm/nouveau/nv

[Nouveau] [PATCH v2 12/22] clk: fixup cstate selection

now the cstatei parameter can be used of the nvkm_cstate_prog function to select a specific cstate -1 is a magic value, which will always select the highest currently possible cstate Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/clk/base.c | 12 +

[Nouveau] [PATCH v2 08/22] clk: export nvkm_volt_map

before clocking to a cstate, we have to check if the voltage is within the allowed range Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/volt.h | 1 + drm/nouveau/nvkm/subdev/volt/base.c| 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

[Nouveau] [PATCH v2 03/22] volt: save the voltage range we are able to set

We shouldn't set voltages below the min or above the max voltage the gpu is able to set, so save the range Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Tested-by: Pierre Moreau <pierre.mor...@free.fr> --- drm/nouveau/include/nvkm/subdev/volt.h | 3 +++ drm/nouveau/nvkm

[Nouveau] [PATCH v2 02/22] volt: properly detect entry based voltage tables

there is a field in the voltage table which tells us if the VIDs are taken from the entries or calculated through the header v2: don't break older versions Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> Tested-by: Pierre Moreau

[Nouveau] [PATCH v2 07/22] volt: add min_id parameter to nvkm_volt_set_id

min_id indicates a volt map entry which acts as a floor value, this will be used to set the lower voltage limit through pstates Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/volt.h | 2 +- drm/nouveau/nvkm/subdev/clk/base.c | 6 -- drm/n

[Nouveau] [PATCH v2 22/22] debugfs: add boost interface to change the boost_mode

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nouveau_debugfs.c | 76 +++ 1 file changed, 76 insertions(+) diff --git a/drm/nouveau/nouveau_debugfs.c b/drm/nouveau/nouveau_debugfs.c index 3d0dc19..31b309f 100644 --- a/drm/n

[Nouveau] [PATCH 2/2] volt: properly detect entry based voltage tables

there is a field in the voltage table which tells us if the VIDs are taken from the entries or calculated through the header Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/volt.h | 5 +++-- drm/nouveau/nvkm/subdev/bios/volt.c

[Nouveau] [PATCH 17/19] volt: don't require perfect fit

when we calculate the voltage in the table right, we get all kinds of values, which never fit the hardware steps, so we use the closest higher value the hardware can do Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/volt/base.c | 25 ++

[Nouveau] [PATCH 07/19] volt: add nvkm_volt_map_min function

this is a copy of nvkm_volt_map, which always returns the lowest possible voltage for a cstate nvkm_volt_map will get a temperature parameter there later and also fix the voltage calculation, so that this functions will be completly different in later commits Signed-off-by: Karol Herbst <n

[Nouveau] [PATCH 04/19] clk: print the base clocks

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/clk/base.c | 17 - 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drm/nouveau/nvkm/subdev/clk/base.c b/drm/nouveau/nvkm/subdev/clk/base.c index 889cce2..4928668 100644 ---

[Nouveau] [PATCH 02/19] volt: properly detect entry based voltage tables

there is a field in the voltage table which tells us if the VIDs are taken from the entries or calculated through the header v2: don't break older versions Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/include

[Nouveau] [PATCH 11/19] clk: export nvkm_volt_map

before clocking to a cstate, we have to check if the voltage is within the allowed range Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/volt.h | 1 + drm/nouveau/nvkm/subdev/volt/base.c| 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

[Nouveau] [PATCH 10/19] volt: add min_id parameter to nvkm_volt_set_id

min_id indicates a volt map entry which acts as a floor value, this will be used to set the lower voltage limit through pstates Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/volt.h | 2 +- drm/nouveau/nvkm/subdev/clk/base.c | 6 -- drm/n

[Nouveau] [PATCH 16/19] clk: respect voltage limits in nvkm_cstate_prog with cstate = -1

we should never allow to select a cstate which current voltage (depending on the temperature) is higher than 1. the max volt entries in the voltage map table 2. what tha gpu actually can volt to this resolves most of the remaining volting errors on fermi and newer Signed-off-by: Karol Herbst

[Nouveau] [PATCH 14/19] volt: add temperature parameter to nvkm_volt_map

the voltage entries actually may map to a different voltage depending on the current temperature. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- bin/nv_cmp_volt.c | 2 +- drm/nouveau/include/nvkm/subdev/volt.h | 2 +- drm/nouveau/nvkm/subdev/volt/base.c

[Nouveau] [PATCH 13/19] add daemon to compare nouveau with blob voltage

this tool can be run alongside the nvidia driver to print information about the current p/cstate, which voltage was set by nvidia and what nouveau would set in the same situation. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- bin/nv_cmp_volt.c

[Nouveau] [PATCH 00/19] Volting/Clocking improvements for Fermi and newer

This series fixes most of the issues regarding volting on GPUs with any form of GPU Boost inside their vbios, which is mainly Kepler and newer, but we find some boosting related tables in Fermi vbios' already In the end reclocking should work on most Kepler cards without any issues Karol Herbst

[Nouveau] [PATCH 09/19] volt: parse the both max voltage entries

these entries specify a maximum voltage nvidia never exceeds, we shouldn't do that, too. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 ++ drm/nouveau/include/nvkm/subdev/volt.h | 2 ++ drm/nouveau/nvkm/subdev/bios/

[Nouveau] [PATCH 03/19] bios: add parsing of BASE CLOCK table

: the avg clock the gpu will stay boosted to. It doesn't seem to affect the behaviour of the nvidia driver at all though. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/baseclock.h | 24 +++ drm/nouveau/nvkm/subdev/bios/

[Nouveau] [PATCH 06/19] volt: save the voltage range we are able to set

We shouldn't set voltages below the min or above the max voltage the gpu is able to set, so save the range Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/volt.h | 3 +++ drm/nouveau/nvkm/subdev/volt/base.c| 14 +- 2 files chang

[Nouveau] [PATCH 15/19] nouveau/subdev/clk: fixup cstate selection

From: Karol Herbst <g...@karolherbst.de> now the cstatei parameter can be used of the nvkm_cstate_prog function to select a specific cstate -1 is a magic value, which will always select the highest currently possible cstate Signed-off-by: Karol Herbst <nouv...@karolherbst.de> ---

[Nouveau] [PATCH 01/19] bios/volt: handle voltage table version 0x50 with 0ed header

hem to switch cstates Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/nvkm/subdev/bios/volt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drm/nouveau/nvkm/subdev/bios/volt.c b/drm/nouveau/nvkm/subdev/bi

[Nouveau] [PATCH 05/19] clk: allow boosting only when NvBoost is set

0: base clock from the vbios is max clock 1: boost only to boost clock from the vbios (default) 2: boost to max clock available Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/clk.h | 9 - drm/nouveau/nvkm/subdev/clk/base.c

[Nouveau] [PATCH 18/19] bios/vmap: unk0 field is the mode

this selects which formula is used to calculate the voltage Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 +- drm/nouveau/nvkm/subdev/bios/vmap.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drm/n

[Nouveau] [PATCH 0/2] Fix some VID parsing in the voltage table version 0x50

the entries. This Series adds two things: 1. It parses the entries 2. It decides upon a field in the voltage table to either use the base+step or entries approach This fixes volting on some GPUs Karol Herbst (2): bios/volt: handle voltage table version 0x50 with 0ed header volt: properly detect

[Nouveau] [PATCH 12/19] clk: add index field to nvkm_cstate

From: Karol Herbst <g...@karolherbst.de> Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/clk.h | 1 + drm/nouveau/nvkm/subdev/clk/base.c| 1 + 2 files changed, 2 insertions(+) diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nou

[Nouveau] [PATCH 08/19] clk: don't create cstates which voltage is higher than what the gpu can do

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/clk/base.c | 4 1 file changed, 4 insertions(+) diff --git a/drm/nouveau/nvkm/subdev/clk/base.c b/drm/nouveau/nvkm/subdev/clk/base.c index d575412..5b8e1df 100644 --- a/drm/nouveau/nvkm/subdev/clk/base.c

[Nouveau] [PATCH v2 2/2] volt: properly detect entry based voltage tables

there is a field in the voltage table which tells us if the VIDs are taken from the entries or calculated through the header v2: don't break older versions of the table Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/volt.h | 5 +-- drm/n

[Nouveau] [PATCH 19/19] volt: add coefficients I found on my gpu

task for this is to figure out which of these constants are chip specific and from where to get the chip specific factors Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/volt/base.c | 54 - 1 file changed, 48 insertions

[Nouveau] [PATCH 1/2] fb/gm107: maxwell memory reclocking looks like kepler

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/fb/gm107.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drm/nouveau/nvkm/subdev/fb/gm107.c b/drm/nouveau/nvkm/subdev/fb/gm107.c index 2a91df8..9cc7e61 100644 --- a/drm/nouveau/nvkm/sub

[Nouveau] [PATCH 0/2] enable memory reclocking on maxwell1

on. It depends on the PMU fixes for the fuc5 though, otherwise the PMU might not work as expected and does something stupid. Karol Herbst (2): fb: maxwell memory reclocking looks like kepler, so try it out fb: remove ramgm107 drm/nouveau/nvkm/subdev/fb/Kbuild | 1 - drm/nouveau/nvkm/subdev/fb

[Nouveau] [PATCH 2/2] fb: remove ramgm107

maxwell1 memory recklocking is just as kepler and if there are some tiny changes we might be able to integrate it in the kepler code. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/fb/Kbuild | 1 - drm/nouveau/nvkm/subdev/fb/ram.h | 1 - drm/n

[Nouveau] RFC: [PATCH] x86/kmmio: fix mmiotrace for hugepages

fault within the same page twice anymore. I don't know if I got this right though, so please read this change with great care v2: use page_level macros Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- arch/x86/mm/kmmio.c | 89 -

[Nouveau] [PATCH v2 0/4] fix pmu code on gk208+

this series fixes the PMU on falcons v5 which fixes memory recklocking on kepler2 and would also allow us to enable memory recklocking on maxwell Karol Herbst (4): pmu/fuc: fix imm32 for gk208+ pmu/fuc: replace mov+sethi with imm32 pmu/fuc: use the call macro instead of using the call

[Nouveau] [PATCH v2 1/4] pmu/fuc: fix imm32 for gk208+

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h | 882 +-- drm/nouveau/nvkm/subdev/pmu/fuc/macros.fuc | 2 +- 2 files changed, 442 insertions(+), 4

[Nouveau] [PATCH v2 4/4] pmu/fuc: use imm32 in ld/st macros

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/nvkm/subdev/pmu/fuc/macros.fuc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/macros.fuc b/drm/nouveau/nvk

[Nouveau] [PATCH v2 3/4] pmu/fuc: use the call macro instead of using the call instruction directly

the macro deals with target specific differences and so we should always use this Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h | 12 ++-- drm/nouveau/nvkm/subdev/pmu/fu

Re: [Nouveau] [PATCH 4/4] pmu/fuc: movw is somewhat weird on gk208, use mov instead

kin wrote: > > On Tue, Mar 1, 2016 at 4:36 PM, Martin Peres <martin.pe...@free.fr> wrote: > >> On 26/02/16 17:19, Karol Herbst wrote: > >>> currently there is no change, because nobody uses those macros yet, but > >>> they > >>> shouldn

Re: [Nouveau] Google Summer of Code 2016

Hi vignesh, sorry for the late answer. Most of the information you need you will find in here: https://nouveau.freedesktop.org/wiki/ Also I kind of looked into this a bit, so I might be able to help out a little. I would suggest to you to hang around in #nouveau on freenode IRC and ask

[Nouveau] [PATCH 1/2] pmu: fix queued messages while getting no IRQ

ause I don't need to reboot anymore Nethertheless, we shouldn't use wait_event here, because we can't guarantee any answere at all, can we? v2: moved it into a new function Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/pmu

[Nouveau] [PATCH 2/2] pmu: be more strict about locking

when we start communicating with the pmu a bit more, the current code is a real issue. I encountered a dead lock here, while testing my dynamic reclocking code Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/pmu/base.c | 8 +--- 1 file changed, 5 inse

[Nouveau] [PATCH 0/2] PMU communications improvements

Both patches should make the communicating with the PMU more stable. Karol Herbst (2): pmu: fix queued messages while getting no IRQ pmu: be more strict about locking drm/nouveau/nvkm/subdev/pmu/base.c | 49 -- 1 file changed, 42 insertions(+), 7

Re: [Nouveau] GSOC 2016 Aspirant for Kepler Accelerated Video Encoding;

Ohh completly missed that message, ignore the noise I created with my reply then :) > Ilia Mirkin hat am 1. März 2016 um 09:56 geschrieben: > > > First, make sure there's a mentor available -- I doubt I'll have time to do > it, but perhaps someone else will be able to. >

Re: [Nouveau] GSOC 2016 Aspirant for Kepler Accelerated Video Encoding;

Hi, I tried to look into that myself into the so called NVENC engine on my kepler gpu, but never got to work on that (still on my todo list), but it would be awesome if somebody else would work on that :) My first steps were to get nvenc working with ffmpeg (I think the code actually landed

[Nouveau] [PATCH 0/9] Groundwork for clocking fixes

patch, which can be ran alongside the nvidia driver to test nouveaus volting code and print the actual voltage differences nouveau would try to set and what nvidia actually set on the gpu. Karol Herbst (9): bios/volt: handle voltage table version 0x50 with 0ed header bios/vmap: unk0 field

[Nouveau] [PATCH 3/9] clk: add index field to nvkm_cstate

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/clk.h | 1 + drm/nouveau/nvkm/subdev/clk/base.c| 1 + 2 files changed, 2 insertions(+) diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index 6b33bc0..5

[Nouveau] [PATCH 6/9] volt: save the voltage range we are able to set

We shouldn't set voltages below the min or above the max voltage the gpu is able to set, so let us store the min and max voltage Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/volt.h | 3 +++ drm/nouveau/nvkm/subdev/volt/base.c

[Nouveau] [PATCH 7/9] volt: parse the both max voltage entries

these entries specify a maximum voltage nvidia never exceeds, we shouldn't do that to after finally fixing volting. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 ++ drm/nouveau/include/nvkm/subdev/volt.h | 2 ++ drm/nouvea

[Nouveau] [PATCH 4/9] bios: add parsing of BASE CLOCK table

: the avg clock the gpu will stay boosted to. It doesn't seem to affect the behaviour of the nvidia driver at all though. Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/baseclock.h | 24 +++ drm/nouveau/nvkm/subdev/bios/

[Nouveau] [PATCH 8/9] clk: export nvkm_volt_map

we need this later to see which cstate can be actually used, because the set voltage for a cstate actually exceed the maximum possible voltage of the gpu. We want to know that in the clk subdev so that we do not try to set such a cstate Signed-off-by: Karol Herbst <nouv...@karolherbst

[Nouveau] [PATCH 5/9] clk: print the base clocks

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/clk/base.c | 17 - 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drm/nouveau/nvkm/subdev/clk/base.c b/drm/nouveau/nvkm/subdev/clk/base.c index 0ef371b..0f9b8c5 100644 ---

[Nouveau] [PATCH 1/9] bios/volt: handle voltage table version 0x50 with 0ed header

hem to switch cstates Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/bios/volt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drm/nouveau/nvkm/subdev/bios/volt.c b/drm/nouveau/nvkm/subdev/bios/volt.c index 6e0a336..fd2776b 100644 --- a/drm/nou

[Nouveau] [PATCH 2/9] bios/vmap: unk0 field is the mode

this selects what affects the voltage and how the constants are used from the voltage map table entries to calculate the final voltage Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 +- drm/nouveau/nvkm/subdev/bios/vmap.c

[Nouveau] [PATCH 9/9] add daemon to compare nouveau with blob voltage

this can be run alongside the nvidia driver and it usefull to actually check that nouveau would set the right voltage with the same clocks set Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- bin/nv_cmp_volt.c | 112 ++ 1 file c

[Nouveau] [PATCH 3/4] pmu/fuc: call# seems to be broken on gk208

for some reasons these calls don't really go there where they should go leading to various corruptions of the PMU state Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h | 12 ++-- drm/nouveau/nvkm/subdev/pmu/fuc/kernel.fuc

[Nouveau] [PATCH 0/4] fix pmu code on gk208+

while trying out my pmu_counter patches on a gk208 gpu, I notived that the pmu is pretty much screwed up there. Karol Herbst (4): pmu/fuc: fix imm32 for gk208+ pmu/fuc: replace mov+sethi with imm32 pmu/fuc: call# seems to be broken on gk208 pmu/fuc: movw is somewhat weird on gk208, use

[Nouveau] [PATCH 4/4] pmu/fuc: movw is somewhat weird on gk208, use mov instead

currently there is no change, because nobody uses those macros yet, but they shouldn't stay broken Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/pmu/fuc/macros.fuc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drm/nouveau/nvkm/

[Nouveau] [PATCH 1/4] pmu/fuc: fix imm32 for gk208+

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h | 882 +-- drm/nouveau/nvkm/subdev/pmu/fuc/macros.fuc | 2 +- 2 files changed, 442 insertions(+), 442 deletions(-) diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc

[Nouveau] [PATCH v5 4/6] hwmon: add power consumption

v5: expose only if the sensor reading is valid Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/include/nvif/device.h | 1 + drm/nouveau/nouveau_hwmon.c | 36 2 files

[Nouveau] [PATCH v5 6/6] bios/extdev: also parse v4.1 table

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/nvkm/subdev/bios/extdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drm/nouveau/nvkm/subdev/bios/extdev.c b/drm/nouveau/nvkm/subdev/bios/ex

[Nouveau] [PATCH v5 3/6] iccsense: implement for ina209, ina219 and ina3221

based on Martins initial work v3: fix ina2x9 calculations v4: don't kmalloc(0), fix the lsb/pga stuff v5: add a field to tell if the power reading may be invalid add nkvm_iccsense_read_all function check for the device on the i2c bus move to oneinit Signed-off-by: Karol Herbst <n

[Nouveau] [PATCH v5 5/6] hwmon: don't require therm to be valid to get any data

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/nouveau_hwmon.c | 39 +++ 1 file changed, 19 insertions(+), 20 deletions(-) diff --git a/drm/nouveau/nouveau_hwmon.c b

[Nouveau] [PATCH v5 0/6] Suppor for various power sensors on GF100+

nges in v3: fixes ina2x9, rebase on current master changes in v4: some minor ina2x9 fixes and get it to work on maxwell gen2 changes in v5: final polishing Tested-by: Stefan Hühner <ste...@huehner.org> on gm206 Karol Herbst (4): iccsense: implement for ina209, ina219 and ina3221 hwmon: add p

[Nouveau] [PATCH v5 2/6] nvbios/iccsense: add parsing of the SENSE table

From: Martin Peres <martin.pe...@free.fr> Karol Herbst: v4: don't kmalloc(0) v5: stricter validation Signed-off-by: Karol Herbst <nouv...@karolherbst.de> Reviewed-by: Martin Peres <martin.pe...@free.fr> --- drm/nouveau/include/nvkm/subdev/bios/iccsense.h | 16 drm/nouvea

[Nouveau] [PATCH v4 6/6] bios/extdev: also parse v4.1 table

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/bios/extdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drm/nouveau/nvkm/subdev/bios/extdev.c b/drm/nouveau/nvkm/subdev/bios/extdev.c index c9e6f6f..b857835 100644 --- a/drm/nouvea

[Nouveau] [PATCH v4 5/6] hwmon: don't require therm to be valid to get any data

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nouveau_hwmon.c | 39 +++ 1 file changed, 19 insertions(+), 20 deletions(-) diff --git a/drm/nouveau/nouveau_hwmon.c b/drm/nouveau/nouveau_hwmon.c index c4f77f5..a630192 100644 ---

[Nouveau] [PATCH v4 3/6] iccsense: implement for ina209, ina219 and ina3221

based on Martins initial work v3: fix ina2x9 calculations v4: don't kmalloc(0), fix the lsb/pga stuff Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/extdev.h | 3 + drm/nouveau/include/nvkm/subdev/i2c.h | 31 ++ drm/nouveau/i

[Nouveau] [PATCH v4 4/6] hwmon: add power consumption

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvif/device.h | 1 + drm/nouveau/nouveau_hwmon.c | 39 +++ 2 files changed, 40 insertions(+) diff --git a/drm/nouveau/include/nvif/device.h b/drm/nouveau/include/nvif/de

[Nouveau] [PATCH v4 2/6] nvbios/iccsense: add parsing of the SENSE table

From: Martin Peres <martin.pe...@free.fr> v4: don't kmalloc(0) Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/iccsense.h | 16 drm/nouveau/nvkm/subdev/bios/Kbuild | 1 + drm/nouveau/nvkm/subdev/bios/iccsense.c

[Nouveau] [PATCH v4 0/6] Suppor for various power sensors on GF100+

nges in v3: fixes ina2x9, rebase on current master changes in v4: some minor ina2x9 fixes and get it to work on maxwell gen2 Tested-by: Stefan Hühner <ste...@huehner.org> on gm206 Karol Herbst (4): iccsense: implement for ina209, ina219 and ina3221 hwmon: add power consumption hwmon: don

[Nouveau] [PATCH v3 0/4] Suppor for various power sensors on GF100+

nges in v3: fixes ina2x9, rebase on current master Karol Herbst (2): iccsense: implement for ina209, ina219 and ina3221 hwmon: add power consumption Martin Peres (2): subdev/iccsense: add new subdev for power sensors nvbios/iccsense: add parsing of the SENSE table drm/nouveau/include/nvi

[Nouveau] [PATCH v3 4/4] hwmon: add power consumption

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvif/device.h | 1 + drm/nouveau/nouveau_hwmon.c | 39 +++ 2 files changed, 40 insertions(+) diff --git a/drm/nouveau/include/nvif/device.h b/drm/nouveau/include/nvif/de

[Nouveau] [PATCH v3 3/4] iccsense: implement for ina209, ina219 and ina3221

based on Martins initial work v2: fix ina2x9 calculations, add also for gm200 Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/extdev.h | 3 + drm/nouveau/include/nvkm/subdev/i2c.h | 16 +++ drm/nouveau/include/nvkm/subdev/iccs

[Nouveau] [PATCH v3 1/4] subdev/iccsense: add new subdev for power sensors

From: Martin Peres <martin.pe...@free.fr> Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/core/device.h | 83 +-- drm/nouveau/include/nvkm/subdev/iccsense.h | 10 +++ drm/nouveau/nvkm/core/subdev.c | 83 +---

[Nouveau] [PATCH v3 2/4] nvbios/iccsense: add parsing of the SENSE table

From: Martin Peres <martin.pe...@free.fr> Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/iccsense.h | 16 + drm/nouveau/nvkm/subdev/bios/Kbuild | 1 + drm/nouveau/nvkm/subdev/bios/iccsense.c | 95

[Nouveau] [PATCH v2 3/4] iccsense: implement for ina209, ina219 and ina3221

based on Martins initial work, but heavily reworked Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/extdev.h | 3 + drm/nouveau/include/nvkm/subdev/i2c.h | 16 +++ drm/nouveau/include/nvkm/subdev/iccsense.h| 5 + drm/nouvea

[Nouveau] [PATCH v2 1/4] subdev/iccsense: add new subdev for power sensors

From: Martin Peres <martin.pe...@free.fr> Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/core/device.h | 83 +-- drm/nouveau/include/nvkm/subdev/iccsense.h | 10 +++ drm/nouveau/nvkm/core/subdev.c | 83 +---

[Nouveau] [PATCH v2 2/4] nvbios/iccsense: add parsing of the SENSE table

From: Martin Peres <martin.pe...@free.fr> v2: add missing fields for proper support (mode and rail) Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/subdev/bios/iccsense.h | 16 + drm/nouveau/nvkm/subdev/bios/Kbuild | 1 + drm/

[Nouveau] [PATCH v2 4/4] hwmon: add power consumption

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvif/device.h | 1 + drm/nouveau/nouveau_hwmon.c | 39 +++ 2 files changed, 40 insertions(+) diff --git a/drm/nouveau/include/nvif/device.h b/drm/nouveau/include/nvif/de

[Nouveau] [PATCH 2/2] hwmon: add power consumption

Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvif/device.h | 1 + drm/nouveau/nouveau_hwmon.c | 30 ++ 2 files changed, 31 insertions(+) diff --git a/drm/nouveau/include/nvif/device.h b/drm/nouveau/include/nvif/device.h

[Nouveau] [PATCH 0/2] Support for INA3221 power sensor

. If not, please report to either of us. Thanks Karol Herbst (1): hwmon: add power consumption Martin Peres (1): power sensor support drm/nouveau/include/nvif/device.h | 1 + drm/nouveau/include/nvkm/core/device.h | 83 +++--- drm/nouveau/include/nvkm/subdev/bios/extdev.h

[Nouveau] [PATCH 1/2] power sensor support

From: Martin Peres <martin.pe...@free.fr> v2 (Karol Herbst <nouv...@karolherbst.de>): fix power_rail mapping for ina3221 minor code cleanups Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/include/nvkm/core/device.h | 83 +++--- d

[Nouveau] [PATCH v2 3/4] subdev/pmu/fuc: implement counter readout

v2: read and reset counters faster Signed-off-by: Karol Herbst <nouv...@karolherbst.de> --- drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h | 411 +-- drm/nouveau/nvkm/subdev/pmu/fuc/gf119.fuc4.h | 745 +++ drm/nouveau/nvkm/subdev/pmu/fuc/gk104.fuc4.h

<    5   6   7   8   9   10   11   12   >