On Tue, Jun 25, 2024 at 08:28:06PM +0200, Konrad Dybcio wrote:
> On recent (SM8550+) Snapdragon platforms, the GPU speed bin data is
> abstracted through SMEM, instead of being directly available in a fuse.
>
> Add support for SMEM-based speed binning, which includes getting
> "feature code" and "product code" from said source and parsing them
> to form something that lets us match OPPs against.
>
> Due to the product code being ignored in the context of Adreno on
> production parts (as of SM8650), hardcode it to SOCINFO_PC_UNKNOWN.
>
> Signed-off-by: Konrad Dybcio <konrad.dybcio@xxxxxxxxxx>
> ---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 8 +++---
> drivers/gpu/drm/msm/adreno/adreno_device.c | 2 ++
> drivers/gpu/drm/msm/adreno/adreno_gpu.c | 41 +++++++++++++++++++++++++++---
> drivers/gpu/drm/msm/adreno/adreno_gpu.h | 7 ++++-
> 4 files changed, 50 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index c98cdb1e9326..8ace096bb68c 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -2124,13 +2124,15 @@ static u32 fuse_to_supp_hw(const struct adreno_info *info, u32 fuse)
> return UINT_MAX;
> }
>
> -static int a6xx_set_supported_hw(struct device *dev, const struct adreno_info *info)
> +static int a6xx_set_supported_hw(struct adreno_gpu *adreno_gpu,
> + struct device *dev,
> + const struct adreno_info *info)
> {
> u32 supp_hw;
> u32 speedbin;
> int ret;
>
> - ret = adreno_read_speedbin(dev, &speedbin);
> + ret = adreno_read_speedbin(adreno_gpu, dev, &speedbin);
> /*
> * -ENOENT means that the platform doesn't support speedbin which is
> * fine
> @@ -2290,7 +2292,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
>
> a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx);
>
> - ret = a6xx_set_supported_hw(&pdev->dev, config->info);
> + ret = a6xx_set_supported_hw(adreno_gpu, &pdev->dev, config->info);
> if (ret) {
> a6xx_llc_slices_destroy(a6xx_gpu);
> kfree(a6xx_gpu);
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
> index 1e789ff6945e..e514346088f9 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_device.c
> +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
> @@ -6,6 +6,8 @@
> * Copyright (c) 2014,2017 The Linux Foundation. All rights reserved.
> */
>
> +#include <linux/soc/qcom/socinfo.h>
> +
> #include "adreno_gpu.h"
>
> bool hang_debug = false;
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> index 1c6626747b98..6ffd02f38499 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> @@ -21,6 +21,9 @@
> #include "msm_gem.h"
> #include "msm_mmu.h"
>
> +#include <linux/soc/qcom/smem.h>
> +#include <linux/soc/qcom/socinfo.h>
> +
> static u64 address_space_size = 0;
> MODULE_PARM_DESC(address_space_size, "Override for size of processes private GPU address space");
> module_param(address_space_size, ullong, 0600);
> @@ -1061,9 +1064,39 @@ void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem)
> adreno_ocmem->hdl);
> }
>
> -int adreno_read_speedbin(struct device *dev, u32 *speedbin)
> +int adreno_read_speedbin(struct adreno_gpu *adreno_gpu,
> + struct device *dev, u32 *fuse)
> {
> - return nvmem_cell_read_variable_le_u32(dev, "speed_bin", speedbin);
> + u32 fcode;
> + int ret;
> +
> + /*
> + * Try reading the speedbin via a nvmem cell first
> + * -ENOENT means "no nvmem-cells" and essentially means "old DT" or
> + * "nvmem fuse is irrelevant", simply assume it's fine.
> + */
> + ret = nvmem_cell_read_variable_le_u32(dev, "speed_bin", fuse);
> + if (!ret)
> + return 0;
> + else if (ret != -ENOENT)
> + return dev_err_probe(dev, ret, "Couldn't read the speed bin fuse value\n");
> +
> +#ifdef CONFIG_QCOM_SMEM
> + /*
> + * Only check the feature code - the product code only matters for
> + * proto SoCs unavailable outside Qualcomm labs, as far as GPU bin
> + * matching is concerned.
> + *
> + * Ignore EOPNOTSUPP, as not all SoCs expose this info through SMEM.
> + */
> + ret = qcom_smem_get_feature_code(&fcode);
> + if (!ret)
> + *fuse = ADRENO_SKU_ID(fcode);
> + else if (ret != -EOPNOTSUPP)
> + return dev_err_probe(dev, ret, "Couldn't get feature code from SMEM\n");
> +#endif
> +
> + return 0;
> }
>
> int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
> @@ -1102,9 +1135,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
> devm_pm_opp_set_clkname(dev, "core");
> }
>
> - if (adreno_read_speedbin(dev, &speedbin) || !speedbin)
> + if (adreno_read_speedbin(adreno_gpu, dev, &speedbin) || !speedbin)
> speedbin = 0xffff;
> - adreno_gpu->speedbin = (uint16_t) (0xffff & speedbin);
> + adreno_gpu->speedbin = speedbin;
This value is exposed to userspace via MSM_PARAM_CHIP_ID. 16 bits are
reserved for speedbin, so we should ensure somewhere that we don't
accidently use more than that.
Also, what is the the max value of fcode? I think we should leave some
space for pcode too. We never know for sure if that won't be required in
future.
-Akhil
>
> gpu_name = devm_kasprintf(dev, GFP_KERNEL, "%"ADRENO_CHIPID_FMT,
> ADRENO_CHIPID_ARGS(config->chip_id));
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> index cff8ce541d2c..563c08b44624 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> @@ -79,6 +79,10 @@ struct adreno_reglist {
>
> struct adreno_speedbin {
> uint16_t fuse;
> +/* As of SM8650, PCODE on production SoCs is meaningless wrt the GPU bin */
> +#define ADRENO_SKU_ID_FCODE GENMASK(15, 0)
> +#define ADRENO_SKU_ID(fcode) (fcode)
> +
> uint16_t speedbin;
> };
>
> @@ -545,7 +549,8 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
> struct adreno_smmu_fault_info *info, const char *block,
> u32 scratch[4]);
>
> -int adreno_read_speedbin(struct device *dev, u32 *speedbin);
> +int adreno_read_speedbin(struct adreno_gpu *adreno_gpu,
> + struct device *dev, u32 *speedbin);
>
> /*
> * For a5xx and a6xx targets load the zap shader that is used to pull the GPU
>
> --
> 2.45.2
>
