This commit introduces enhancements to the handling of the cleaner shader fence in the AMDGPU MES driver: - The MES (Microcode Execution Scheduler) now sends a PM4 packet to the KIQ (Kernel Interface Queue) to request the cleaner shader, ensuring that requests are handled in a controlled manner and avoiding the race conditions. - The CP (Compute Processor) firmware has been updated to use a private bus for accessing specific registers, avoiding unnecessary operations that could lead to issues in VF (Virtual Function) mode. - The cleaner shader fence memory address is now set correctly in the `mes_set_hw_res_pkt` structure, allowing for proper synchronization of the cleaner shader execution. Cc: Christian König <christian.koenig@xxxxxxx> Cc: Srinivasan Shanmugam <srinivasan.shanmugam@xxxxxxx> Suggested-by: Shaoyun Liu <shaoyun.liu@xxxxxxx> Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx> --- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index dcbc31279f29b..8dbab3834d82d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -678,6 +678,9 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe) { + unsigned int alloc_size = AMDGPU_GPU_PAGE_SIZE; + int ret = 0; + struct amdgpu_device *adev = mes->adev; union MESAPI_SET_HW_RESOURCES_1 mes_set_hw_res_1_pkt; memset(&mes_set_hw_res_1_pkt, 0, sizeof(mes_set_hw_res_1_pkt)); @@ -687,6 +690,19 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe) mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 0xa; + ret = amdgpu_bo_create_kernel(adev, alloc_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &mes->resource_1, + &mes->resource_1_gpu_addr, + &mes->resource_1_addr); + if (ret) { + dev_err(adev->dev, "(%d) failed to create mes resource_1 bo\n", ret); + return ret; + } + + mes_set_hw_res_1_pkt.cleaner_shader_fence_mc_addr = + mes->resource_1_gpu_addr; + return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt), offsetof(union MESAPI_SET_HW_RESOURCES_1, api_status)); @@ -1770,6 +1786,12 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block) static int mes_v12_0_hw_fini(struct amdgpu_ip_block *ip_block) { + struct amdgpu_device *adev = ip_block->adev; + + if (adev->enable_uni_mes) + amdgpu_bo_free_kernel(&adev->mes.resource_1, + &adev->mes.resource_1_gpu_addr, + &adev->mes.resource_1_addr); return 0; } -- 2.48.1