drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9

CWSR fails on Raven if the control stack is MTYPE_UC, which is used
for regular GART mappings. As a workaround we map it using MTYPE_NC.

The MEC firmware expects the control stack at one page offset from the
start of the MQD so it is part of the MQD allocation on GFXv9. AMDGPU
added a memory allocation flag just for this purpose.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

5 files changed, 10 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index f8bbbb3a9504..0c791e35acf0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -272,7 +272,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
 
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
-			void **cpu_ptr)
+			void **cpu_ptr, bool mqd_gfx9)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 	struct amdgpu_bo *bo = NULL;
@@ -287,6 +287,10 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
 	bp.type = ttm_bo_type_kernel;
 	bp.resv = NULL;
+
+	if (mqd_gfx9)
+		bp.flags |= AMDGPU_GEM_CREATE_MQD_GFX9;
+
 	r = amdgpu_bo_create(adev, &bp, &bo);
 	if (r) {
 		dev_err(adev->dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 2f379c183ed2..cc9aeab5468c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -136,7 +136,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
-			void **cpu_ptr);
+			void **cpu_ptr, bool mqd_gfx9);
 void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
 void get_local_mem_info(struct kgd_dev *kgd,
 			struct kfd_local_mem_info *mem_info);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 1b048715ab8a..29ac74f40dce 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -457,7 +457,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	if (kfd->kfd2kgd->init_gtt_mem_allocation(
 			kfd->kgd, size, &kfd->gtt_mem,
-			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr)){
+			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr,
+			false)) {
 		dev_err(kfd_device, "Could not allocate %d bytes\n", size);
 		goto out;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index f5fc3675f21e..0cedb37cf513 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -88,7 +88,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 				ALIGN(sizeof(struct v9_mqd), PAGE_SIZE),
 			&((*mqd_mem_obj)->gtt_mem),
 			&((*mqd_mem_obj)->gpu_addr),
-			(void *)&((*mqd_mem_obj)->cpu_ptr));
+			(void *)&((*mqd_mem_obj)->cpu_ptr), true);
 	} else
 		retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct v9_mqd),
 				mqd_mem_obj);
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 14391b06080c..43b82e14007e 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -292,7 +292,7 @@ struct tile_config {
 struct kfd2kgd_calls {
 	int (*init_gtt_mem_allocation)(struct kgd_dev *kgd, size_t size,
 					void **mem_obj, uint64_t *gpu_addr,
-					void **cpu_ptr);
+					void **cpu_ptr, bool mqd_gfx9);
 
 	void (*free_gtt_mem)(struct kgd_dev *kgd, void *mem_obj);