Re: [Freedreno] [PATCH 2/2] drm/msm/a6xx: Create an A6XX GPU specific address space

From: Rob Clark
Date: Wed Jan 20 2021 - 11:17:41 EST


On Mon, Jan 11, 2021 at 4:04 AM Sai Prakash Ranjan
<saiprakash.ranjan@xxxxxxxxxxxxxx> wrote:
>
> A6XX GPUs have support for last level cache(LLC) also known
> as system cache and need to set the bus attributes to
> use it. Currently we use a generic adreno iommu address space
> implementation which are also used by older GPU generations
> which do not have LLC and might introduce issues accidentally
> and is not clean in a way that anymore additions of GPUs
> supporting LLC would have to be guarded under ifdefs. So keep
> the generic code separate and make the address space creation
> A6XX specific. We also have a helper to set the llc attributes
> so that if the newer GPU generations do support them, we can
> use it instead of open coding domain attribute setting for each
> GPU.
>
> Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@xxxxxxxxxxxxxx>
> ---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 46 ++++++++++++++++++++++++-
> drivers/gpu/drm/msm/adreno/adreno_gpu.c | 23 +++++--------
> drivers/gpu/drm/msm/adreno/adreno_gpu.h | 7 ++--
> 3 files changed, 55 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 3b798e883f82..3c7ad51732bb 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -1239,6 +1239,50 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
> return (unsigned long)busy_time;
> }
>
> +static struct msm_gem_address_space *
> +a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
> +{
> + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
> + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
> + struct iommu_domain *iommu;
> + struct msm_mmu *mmu;
> + struct msm_gem_address_space *aspace;
> + u64 start, size;
> +
> + iommu = iommu_domain_alloc(&platform_bus_type);
> + if (!iommu)
> + return NULL;
> +
> + /*
> + * This allows GPU to set the bus attributes required to use system
> + * cache on behalf of the iommu page table walker.
> + */
> + if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
> + adreno_set_llc_attributes(iommu);
> +
> + mmu = msm_iommu_new(&pdev->dev, iommu);
> + if (IS_ERR(mmu)) {
> + iommu_domain_free(iommu);
> + return ERR_CAST(mmu);
> + }
> +
> + /*
> + * Use the aperture start or SZ_16M, whichever is greater. This will
> + * ensure that we align with the allocated pagetable range while still
> + * allowing room in the lower 32 bits for GMEM and whatnot
> + */
> + start = max_t(u64, SZ_16M, iommu->geometry.aperture_start);
> + size = iommu->geometry.aperture_end - start + 1;
> +
> + aspace = msm_gem_address_space_create(mmu, "gpu",
> + start & GENMASK_ULL(48, 0), size);
> +
> + if (IS_ERR(aspace) && !IS_ERR(mmu))
> + mmu->funcs->destroy(mmu);
> +
> + return aspace;
> +}
> +
> static struct msm_gem_address_space *
> a6xx_create_private_address_space(struct msm_gpu *gpu)
> {
> @@ -1285,7 +1329,7 @@ static const struct adreno_gpu_funcs funcs = {
> .gpu_state_get = a6xx_gpu_state_get,
> .gpu_state_put = a6xx_gpu_state_put,
> #endif
> - .create_address_space = adreno_iommu_create_address_space,
> + .create_address_space = a6xx_create_address_space,
> .create_private_address_space = a6xx_create_private_address_space,
> .get_rptr = a6xx_get_rptr,
> },
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> index b35914de1b27..0f184c3dd9d9 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> @@ -186,11 +186,18 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
> return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
> }
>
> +void adreno_set_llc_attributes(struct iommu_domain *iommu)
> +{
> + struct io_pgtable_domain_attr pgtbl_cfg;
> +
> + pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;

btw, since quirks is the only field in the struct currently, this is
ok. But better practice to do something like:

struct io_pgtable_domain_attr pgtbl_cfg = {
.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA,
};

which will zero-initialize any additional fields which might be added
later, rather than inherit random garbage from the stack.

BR,
-R

> + iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
> +}
> +
> struct msm_gem_address_space *
> adreno_iommu_create_address_space(struct msm_gpu *gpu,
> struct platform_device *pdev)
> {
> - struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
> struct iommu_domain *iommu;
> struct msm_mmu *mmu;
> struct msm_gem_address_space *aspace;
> @@ -200,20 +207,6 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
> if (!iommu)
> return NULL;
>
> - if (adreno_is_a6xx(adreno_gpu)) {
> - struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
> - struct io_pgtable_domain_attr pgtbl_cfg;
> -
> - /*
> - * This allows GPU to set the bus attributes required to use system
> - * cache on behalf of the iommu page table walker.
> - */
> - if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice)) {
> - pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
> - iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
> - }
> - }
> -
> mmu = msm_iommu_new(&pdev->dev, iommu);
> if (IS_ERR(mmu)) {
> iommu_domain_free(iommu);
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> index b3d9a333591b..2a3d049b46b5 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> @@ -212,11 +212,6 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu)
> return gpu->revn == 540;
> }
>
> -static inline bool adreno_is_a6xx(struct adreno_gpu *gpu)
> -{
> - return ((gpu->revn < 700 && gpu->revn > 599));
> -}
> -
> static inline int adreno_is_a618(struct adreno_gpu *gpu)
> {
> return gpu->revn == 618;
> @@ -278,6 +273,8 @@ struct msm_gem_address_space *
> adreno_iommu_create_address_space(struct msm_gpu *gpu,
> struct platform_device *pdev);
>
> +void adreno_set_llc_attributes(struct iommu_domain *iommu);
> +
> /*
> * For a5xx and a6xx targets load the zap shader that is used to pull the GPU
> * out of secure mode
> --
> QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
> of Code Aurora Forum, hosted by The Linux Foundation
>
> _______________________________________________
> Freedreno mailing list
> Freedreno@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/freedreno