drm/ttm: add caching state to ttm_bus_placement

And implement setting it up correctly in the drivers.

This allows getting rid of the placement flags for this.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Link: https://patchwork.freedesktop.org/patch/394254/

6 files changed, 18 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 7f41a47e7353..5b56a66063fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -769,6 +769,7 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 
 		mem->bus.offset += adev->gmc.aper_base;
 		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_write_combined;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index ad58d0af5141..b9e7ce1adf25 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -981,6 +981,7 @@ static int bo_driver_io_mem_reserve(struct ttm_bo_device *bdev,
 	case TTM_PL_VRAM:
 		mem->bus.offset = (mem->start << PAGE_SHIFT) + vmm->vram_base;
 		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_write_combined;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 0c0ca44a6802..cb878c0e8276 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1134,6 +1134,8 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *reg)
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 	struct nvkm_device *device = nvxx_device(&drm->client.device);
 	struct nouveau_mem *mem = nouveau_mem(reg);
+	struct nvif_mmu *mmu = &drm->client.mmu;
+	const u8 type = mmu->type[drm->ttm.type_vram].type;
 	int ret;
 
 	mutex_lock(&drm->ttm.io_reserve_mutex);
@@ -1149,6 +1151,7 @@ retry:
 			reg->bus.offset = (reg->start << PAGE_SHIFT) +
 				drm->agp.base;
 			reg->bus.is_iomem = !drm->agp.cma;
+			reg->bus.caching = ttm_write_combined;
 		}
 #endif
 		if (drm->client.mem->oclass < NVIF_CLASS_MEM_NV50 ||
@@ -1162,6 +1165,14 @@ retry:
 		reg->bus.offset = (reg->start << PAGE_SHIFT) +
 			device->func->resource_addr(device, 1);
 		reg->bus.is_iomem = true;
+
+		/* Some BARs do not support being ioremapped WC */
+		if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
+		    type & NVIF_MEM_UNCACHED)
+			reg->bus.caching = ttm_uncached;
+		else
+			reg->bus.caching = ttm_write_combined;
+
 		if (drm->client.mem->oclass >= NVIF_CLASS_MEM_NV50) {
 			union {
 				struct nv50_mem_map_v0 nv50;
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index f50863493f64..61eb06dbbce8 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -83,11 +83,13 @@ int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
 	case TTM_PL_VRAM:
 		mem->bus.is_iomem = true;
 		mem->bus.offset = (mem->start << PAGE_SHIFT) + qdev->vram_base;
+		mem->bus.caching = ttm_cached;
 		break;
 	case TTM_PL_PRIV:
 		mem->bus.is_iomem = true;
 		mem->bus.offset = (mem->start << PAGE_SHIFT) +
 			qdev->surfaceram_base;
+		mem->bus.caching = ttm_cached;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 130a7cea35c3..9b53a1d80632 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -372,6 +372,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 			mem->bus.offset = (mem->start << PAGE_SHIFT) +
 				rdev->mc.agp_base;
 			mem->bus.is_iomem = !rdev->ddev->agp->cant_use_aperture;
+			mem->bus.caching = ttm_write_combined;
 		}
 #endif
 		break;
@@ -382,6 +383,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 			return -EINVAL;
 		mem->bus.offset += rdev->mc.aper_base;
 		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_write_combined;
 #ifdef __alpha__
 		/*
 		 * Alpha: use bus.addr to hold the ioremap() return,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 1fa7f9438ec4..fae88969a15a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -688,6 +688,7 @@ static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resourc
 		mem->bus.offset = (mem->start << PAGE_SHIFT) +
 			dev_priv->vram_start;
 		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_cached;
 		break;
 	default:
 		return -EINVAL;