search for: nvbios_baseclock_entry

...e *device, nvkm_subdev_ctor(&nvkm_clk, device, index, 0, subdev); + clk->boost_mode = nvkm_longopt(device->cfgopt, "NvBoost", + NVKM_CLK_BOOST_AVG); if (bios && !nvbios_baseclock_parse(bios, &h)) { struct nvbios_baseclk_entry base, boost; - if (!nvbios_baseclock_entry(bios, &h, h.boost, &boost)) + if (!nvbios_baseclock_entry(bios, &h, h.boost, &boost)) { + clk->boost_khz = boost.clock_mhz * 1000; nvkm_info(subdev, "boost: %i MHz\n", boost.clock_mhz / 2); - if (!nvbios_baseclock_entry(bios, &h, h.base, &base)) +...

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 (19): bios/volt: handle voltage table version 0x50 with 0ed header volt: properly detect entry

this series solves different issues we encounter on kepler cards while reclocking: 1. core clock doesn't change at all and produces a volting error (patch 1) this can happen when the voltage table has only 0ed values in the header so we have to parse the entries itself, which contain the right voltages 2. kepler won't clock to highest cstates (patch 2) this happens, because there are

...et, idx, arglen; > const char *mode; > + struct nvbios_baseclock_header header; > > nvkm_subdev_ctor(&nvkm_clk, device, index, 0, &clk->subdev); > + bios = device->bios; > + > + if (bios && !nvbios_baseclock_parse(bios, &header)) { > + struct nvbios_baseclock_entry base_entry, boost_entry; > + if (nvbios_baseclock_get_entry(bios, &header, header.base_entry, &base_entry)) > + nvkm_error(&clk->subdev, "couldn't parse base clock\n"); > + else if (nvbios_baseclock_get_entry(bios, &header, header.boost_entry, &boos...

...struct nvkm_bios *bios = device->bios; int ret, idx, arglen; const char *mode; + struct nvbios_baseclk_header h; + + nvkm_subdev_ctor(&nvkm_clk, device, index, 0, subdev); + + if (bios && !nvbios_baseclock_parse(bios, &h)) { + struct nvbios_baseclk_entry base, boost; + if (!nvbios_baseclock_entry(bios, &h, h.boost, &boost)) + nvkm_info(subdev, "boost: %i MHz\n", + boost.clock_mhz / 2); + if (!nvbios_baseclock_entry(bios, &h, h.base, &base)) + nvkm_info(subdev, "base: %i MHz\n", + base.clock_mhz / 2); + } - nvkm_subdev_ctor(&nvkm_clk,...

...clk_header h; + + nvkm_subdev_ctor(&nvkm_clk, device, index, subdev); + + clk->boost_mode = nvkm_longopt(device->cfgopt, "NvBoost", + NVKM_CLK_BOOST_AVG); + if (bios && !nvbios_baseclock_parse(bios, &h)) { + struct nvbios_baseclk_entry base, boost; + if (!nvbios_baseclock_entry(bios, &h, h.boost_id, &boost)) + clk->boost_khz = boost.clock_mhz * 1000; + if (!nvbios_baseclock_entry(bios, &h, h.base_id, &base)) + clk->base_khz = base.clock_mhz * 1000; + } - nvkm_subdev_ctor(&nvkm_clk, device, index, &clk->subdev); clk->func = func...

...os_baseclk_header { + u16 offset; + + u8 version; + u8 hlen; + u8 ecount; + u8 elen; + u8 scount; + u8 slen; + + u8 base; + u8 boost; + u8 tdp; +}; +struct nvbios_baseclk_entry { + u8 pstate; + u16 clock_mhz; +}; +int nvbios_baseclock_parse(struct nvkm_bios *, struct nvbios_baseclk_header *); +int nvbios_baseclock_entry(struct nvkm_bios *, struct nvbios_baseclk_header *, + u8 idx, struct nvbios_baseclk_entry *); +#endif diff --git a/drm/nouveau/nvkm/subdev/bios/Kbuild b/drm/nouveau/nvkm/subdev/bios/Kbuild index dbcb0ef..6cb3beb 100644 --- a/drm/nouveau/nvkm/subdev/bios/Kbuild +++ b/drm/nouveau/nvkm/subdev/bio...

this series solves different issues we encounter on kepler cards while reclocking: 1. core clock doesn't change at all and produces a volting error (patch 1) this can happen when the voltage table has only 0ed values in the header so we have to parse the entries itself, which contain the right voltages 2. kepler won't clock to highest cstates (patch 2) this happens, because there are

This series contains a lot of groundwork to finally fix reclocking issues on Kepler+ gpus. There shouldn't be any functional changes with the first patch being the only exception (fixes some voltage table parsing issues with of few kepler gpus) The most interessting thing is the tool in the last patch, which can be ran alongside the nvidia driver to test nouveaus volting code and print the

...> } > > /****************************************************************************** > @@ -573,13 +582,19 @@ nvkm_clk_ctor(const struct nvkm_clk_func *func, struct nvkm_device *device, > > if (bios && !nvbios_baseclock_parse(bios, &header)) { > struct nvbios_baseclock_entry base_entry, boost_entry; > + clk->boost_mode = nvkm_longopt(device->cfgopt, "NvBoost", 0); > if (nvbios_baseclock_get_entry(bios, &header, header.base_entry, &base_entry)) If `boost_mode == -1` is some "went wrong, don't use" value, shouldn't you...

...lk) { + struct nvkm_bios *bios; int ret, idx, arglen; const char *mode; + struct nvbios_baseclock_header header; nvkm_subdev_ctor(&nvkm_clk, device, index, 0, &clk->subdev); + bios = device->bios; + + if (bios && !nvbios_baseclock_parse(bios, &header)) { + struct nvbios_baseclock_entry base_entry, boost_entry; + if (nvbios_baseclock_get_entry(bios, &header, header.base_entry, &base_entry)) + nvkm_error(&clk->subdev, "couldn't parse base clock\n"); + else if (nvbios_baseclock_get_entry(bios, &header, header.boost_entry, &boost_entry)) + n...

...+ struct nvbios_baseclock_header header; > > > > nvkm_subdev_ctor(&nvkm_clk, device, index, 0, &clk->subdev); > > + bios = device->bios; > > + > > + if (bios && !nvbios_baseclock_parse(bios, &header)) { > > + struct nvbios_baseclock_entry base_entry, boost_entry; > > + if (nvbios_baseclock_get_entry(bios, &header, header.base_entry, > > &base_entry)) > > + nvkm_error(&clk->subdev, "couldn't parse base clock\n"); > > + else if (nvbios_baseclock_get_entry(bios, &...

...+ kfree(cstate); + return -EINVAL; } /****************************************************************************** @@ -573,13 +582,19 @@ nvkm_clk_ctor(const struct nvkm_clk_func *func, struct nvkm_device *device, if (bios && !nvbios_baseclock_parse(bios, &header)) { struct nvbios_baseclock_entry base_entry, boost_entry; + clk->boost_mode = nvkm_longopt(device->cfgopt, "NvBoost", 0); if (nvbios_baseclock_get_entry(bios, &header, header.base_entry, &base_entry)) nvkm_error(&clk->subdev, "couldn't parse base clock\n"); else if (nvbios_ba...

...***************************************************************** > > @@ -573,13 +582,19 @@ nvkm_clk_ctor(const struct nvkm_clk_func *func, struct > > nvkm_device *device, > > > > if (bios && !nvbios_baseclock_parse(bios, &header)) { > > struct nvbios_baseclock_entry base_entry, boost_entry; > > + clk->boost_mode = nvkm_longopt(device->cfgopt, "NvBoost", 0); > > if (nvbios_baseclock_get_entry(bios, &header, header.base_entry, > > &base_entry)) > > If `boost_mode == -1` is some "went wrong, don't...

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 v2: boost_mode can now be changed at runtime minor fixups Karol Herbst (22): bios/volt: handle voltage

This is an updated series for the old clocking improvement one. I think I got everything needed in place and also a simple update mechanism for updating the cstates/voltage on temperature changes. If anything is unclear how I REed or got the information, please leave a note so that I can provide additional information in the commits. Besides that I think we are pretty close now and only some

We are slowly getting there! v4 of the series with some realy good improvements, so I am sure this is like 95% done and only needs some proper polishing and proper Reviews! I also added the NvVoltOffsetmV module parameter, so that a user is able to over and !under!-volt the GPU. Overvolting makes sense, when there are still some reclocking issues left, which might be solved by a higher voltage.