drm/amdgpu: enable UMSCH 4.0.6

Share same codes with 4.0.5 and enable collaborate mode for VPE.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Veerabadhran Gopalakrishnan <Veerabadhran.Gopalakrishnan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c

@@ -2246,6 +2246,7 @@ static int amdgpu_discovery_set_umsch_mm_ip_blocks(struct amdgpu_device *adev)
 {
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		if (amdgpu_umsch_mm & 0x1) {
 			amdgpu_device_ip_block_add(adev, &umsch_mm_v4_0_ip_block);
 			adev->enable_umsch_mm = true;

drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c

@@ -189,10 +189,13 @@ static void setup_vpe_queue(struct amdgpu_device *adev,
 	mqd->rptr_val = 0;
 	mqd->unmapped = 1;
 
+	if (adev->vpe.collaborate_mode)
+		memcpy(++mqd, test->mqd_data_cpu_addr, sizeof(struct MQD_INFO));
+
 	qinfo->mqd_addr = test->mqd_data_gpu_addr;
 	qinfo->csa_addr = test->ctx_data_gpu_addr +
 		offsetof(struct umsch_mm_test_ctx_data, vpe_ctx_csa);
-	qinfo->doorbell_offset_0 = (adev->doorbell_index.vpe_ring + 1) << 1;
+	qinfo->doorbell_offset_0 = 0;
 	qinfo->doorbell_offset_1 = 0;
 }
 
@@ -287,7 +290,10 @@ static int submit_vpe_queue(struct amdgpu_device *adev, struct umsch_mm_test *te
 	ring[5] = 0;
 
 	mqd->wptr_val = (6 << 2);
-	// WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
+	if (adev->vpe.collaborate_mode)
+		(++mqd)->wptr_val = (6 << 2);
+
+	WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
 
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (*fence == test_pattern)
@@ -571,6 +577,7 @@ int amdgpu_umsch_mm_init_microcode(struct amdgpu_umsch_mm *umsch)
 
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		fw_name = "amdgpu/umsch_mm_4_0_0.bin";
 		break;
 	default:
@@ -750,6 +757,7 @@ static int umsch_mm_early_init(void *handle)
 
 	switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
 	case IP_VERSION(4, 0, 5):
+	case IP_VERSION(4, 0, 6):
 		umsch_mm_v4_0_set_funcs(&adev->umsch_mm);
 		break;
 	default:

drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c

@@ -60,7 +60,7 @@ static int umsch_mm_v4_0_load_microcode(struct amdgpu_umsch_mm *umsch)
 
 	umsch->cmd_buf_curr_ptr = umsch->cmd_buf_ptr;
 
-	if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+	if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
 		WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
 			1 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
 		SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -248,7 +248,7 @@ static int umsch_mm_v4_0_ring_stop(struct amdgpu_umsch_mm *umsch)
 	data = REG_SET_FIELD(data, VCN_UMSCH_RB_DB_CTRL, EN, 0);
 	WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_DB_CTRL, data);
 
-	if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+	if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
 		WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
 			2 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
 		SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -271,6 +271,8 @@ static int umsch_mm_v4_0_set_hw_resources(struct amdgpu_umsch_mm *umsch)
 
 	set_hw_resources.vmid_mask_mm_vcn = umsch->vmid_mask_mm_vcn;
 	set_hw_resources.vmid_mask_mm_vpe = umsch->vmid_mask_mm_vpe;
+	set_hw_resources.collaboration_mask_vpe =
+		adev->vpe.collaborate_mode ? 0x3 : 0x0;
 	set_hw_resources.engine_mask = umsch->engine_mask;
 
 	set_hw_resources.vcn0_hqd_mask[0] = umsch->vcn0_hqd_mask;
@@ -346,6 +348,7 @@ static int umsch_mm_v4_0_add_queue(struct amdgpu_umsch_mm *umsch,
 	add_queue.h_queue = input_ptr->h_queue;
 	add_queue.vm_context_cntl = input_ptr->vm_context_cntl;
 	add_queue.is_context_suspended = input_ptr->is_context_suspended;
+	add_queue.collaboration_mode = adev->vpe.collaborate_mode ? 1 : 0;
 
 	add_queue.api_status.api_completion_fence_addr = umsch->ring.fence_drv.gpu_addr;
 	add_queue.api_status.api_completion_fence_value = ++umsch->ring.fence_drv.sync_seq;