Am 24.10.2016 um 08:31 schrieb Dave Airlie:
> This fixes a regression in all these drivers since the cache
> mode tracking was fixed for mixed mappings. It uses the new
> arch API to add the VRAM range to the PAT mapping tracking
> tables.
>
> Fixes: 87744ab3832 (mm: fix cache mode tracking in vm_insert_mixed())
> Signed-off-by: Dave Airlie <airlied at redhat.com>
Reviewed-by: Christian König <christian.koenig at amd.com>.
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 +++++
> drivers/gpu/drm/ast/ast_ttm.c | 6 ++++++
> drivers/gpu/drm/cirrus/cirrus_ttm.c | 7 +++++++
> drivers/gpu/drm/mgag200/mgag200_ttm.c | 7 +++++++
> drivers/gpu/drm/nouveau/nouveau_ttm.c | 8 ++++++++
> drivers/gpu/drm/radeon/radeon_object.c | 5 +++++
> 6 files changed, 38 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index aa074fa..f3efb1c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -754,6 +754,10 @@ static const char *amdgpu_vram_names[] = {
>
> int amdgpu_bo_init(struct amdgpu_device *adev)
> {
> + /* reserve PAT memory space to WC for VRAM */
> + arch_io_reserve_memtype_wc(adev->mc.aper_base,
> + adev->mc.aper_size);
> +
> /* Add an MTRR for the VRAM */
> adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
> adev->mc.aper_size);
> @@ -769,6 +773,7 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
> {
> amdgpu_ttm_fini(adev);
> arch_phys_wc_del(adev->mc.vram_mtrr);
> + arch_io_free_memtype_wc(adev->mc.aper_base, adev->mc.aper_size);
> }
>
> int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
> diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
> index 608df4c..0743e65 100644
> --- a/drivers/gpu/drm/ast/ast_ttm.c
> +++ b/drivers/gpu/drm/ast/ast_ttm.c
> @@ -267,6 +267,8 @@ int ast_mm_init(struct ast_private *ast)
> return ret;
> }
>
> + arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
> + pci_resource_len(dev->pdev, 0));
> ast->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
> pci_resource_len(dev->pdev, 0));
>
> @@ -275,11 +277,15 @@ int ast_mm_init(struct ast_private *ast)
>
> void ast_mm_fini(struct ast_private *ast)
> {
> + struct drm_device *dev = ast->dev;
> +
> ttm_bo_device_release(&ast->ttm.bdev);
>
> ast_ttm_global_release(ast);
>
> arch_phys_wc_del(ast->fb_mtrr);
> + arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
> + pci_resource_len(dev->pdev, 0));
> }
>
> void ast_ttm_placement(struct ast_bo *bo, int domain)
> diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c
> b/drivers/gpu/drm/cirrus/cirrus_ttm.c
> index bb2438d..5e7e63c 100644
> --- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
> +++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
> @@ -267,6 +267,9 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
> return ret;
> }
>
> + arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
> + pci_resource_len(dev->pdev, 0));
> +
> cirrus->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
> pci_resource_len(dev->pdev, 0));
>
> @@ -276,6 +279,8 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
>
> void cirrus_mm_fini(struct cirrus_device *cirrus)
> {
> + struct drm_device *dev = cirrus->dev;
> +
> if (!cirrus->mm_inited)
> return;
>
> @@ -285,6 +290,8 @@ void cirrus_mm_fini(struct cirrus_device *cirrus)
>
> arch_phys_wc_del(cirrus->fb_mtrr);
> cirrus->fb_mtrr = 0;
> + arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
> + pci_resource_len(dev->pdev, 0));
> }
>
> void cirrus_ttm_placement(struct cirrus_bo *bo, int domain)
> diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c
> b/drivers/gpu/drm/mgag200/mgag200_ttm.c
> index 919b35f..dcf7d11 100644
> --- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
> +++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
> @@ -266,6 +266,9 @@ int mgag200_mm_init(struct mga_device *mdev)
> return ret;
> }
>
> + arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
> + pci_resource_len(dev->pdev, 0));
> +
> mdev->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
> pci_resource_len(dev->pdev, 0));
>
> @@ -274,10 +277,14 @@ int mgag200_mm_init(struct mga_device *mdev)
>
> void mgag200_mm_fini(struct mga_device *mdev)
> {
> + struct drm_device *dev = mdev->dev;
> +
> ttm_bo_device_release(&mdev->ttm.bdev);
>
> mgag200_ttm_global_release(mdev);
>
> + arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
> + pci_resource_len(dev->pdev, 0));
> arch_phys_wc_del(mdev->fb_mtrr);
> mdev->fb_mtrr = 0;
> }
> diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c
> b/drivers/gpu/drm/nouveau/nouveau_ttm.c
> index 1825dbc..a6dbe82 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
> @@ -398,6 +398,9 @@ nouveau_ttm_init(struct nouveau_drm *drm)
> /* VRAM init */
> drm->gem.vram_available = drm->device.info.ram_user;
>
> + arch_io_reserve_memtype_wc(device->func->resource_addr(device, 1),
> + device->func->resource_size(device, 1));
> +
> ret = ttm_bo_init_mm(&drm->ttm.bdev, TTM_PL_VRAM,
> drm->gem.vram_available >> PAGE_SHIFT);
> if (ret) {
> @@ -430,6 +433,8 @@ nouveau_ttm_init(struct nouveau_drm *drm)
> void
> nouveau_ttm_fini(struct nouveau_drm *drm)
> {
> + struct nvkm_device *device = nvxx_device(&drm->device);
> +
> ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_VRAM);
> ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_TT);
>
> @@ -439,4 +444,7 @@ nouveau_ttm_fini(struct nouveau_drm *drm)
>
> arch_phys_wc_del(drm->ttm.mtrr);
> drm->ttm.mtrr = 0;
> + arch_io_free_memtype_wc(device->func->resource_addr(device, 1),
> + device->func->resource_size(device, 1));
> +
> }
> diff --git a/drivers/gpu/drm/radeon/radeon_object.c
> b/drivers/gpu/drm/radeon/radeon_object.c
> index be30861..41b72ce 100644
> --- a/drivers/gpu/drm/radeon/radeon_object.c
> +++ b/drivers/gpu/drm/radeon/radeon_object.c
> @@ -446,6 +446,10 @@ void radeon_bo_force_delete(struct radeon_device *rdev)
>
> int radeon_bo_init(struct radeon_device *rdev)
> {
> + /* reserve PAT memory space to WC for VRAM */
> + arch_io_reserve_memtype_wc(rdev->mc.aper_base,
> + rdev->mc.aper_size);
> +
> /* Add an MTRR for the VRAM */
> if (!rdev->fastfb_working) {
> rdev->mc.vram_mtrr = arch_phys_wc_add(rdev->mc.aper_base,
> @@ -463,6 +467,7 @@ void radeon_bo_fini(struct radeon_device *rdev)
> {
> radeon_ttm_fini(rdev);
> arch_phys_wc_del(rdev->mc.vram_mtrr);
> + arch_io_free_memtype_wc(rdev->mc.aper_base, rdev->mc.aper_size);
> }
>
> /* Returns how many bytes TTM can move per IB.
