1 files changed, 117 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index b6015157763a..da48b6da0107 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -98,6 +98,26 @@ static int amdgpu_mes_doorbell_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int amdgpu_mes_event_log_init(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_GTT,
+				    &adev->mes.event_log_gpu_obj,
+				    &adev->mes.event_log_gpu_addr,
+				    &adev->mes.event_log_cpu_addr);
+	if (r) {
+		dev_warn(adev->dev, "failed to create MES event log buffer (%d)", r);
+		return r;
+	}
+
+	memset(adev->mes.event_log_cpu_addr, 0, PAGE_SIZE);
+
+	return  0;
+
+}
+
 static void amdgpu_mes_doorbell_free(struct amdgpu_device *adev)
 {
 	bitmap_free(adev->mes.doorbell_bitmap);
@@ -132,7 +152,8 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 		adev->mes.gfx_hqd_mask[i] = i ? 0 : 0xfffffffe;
 
 	for (i = 0; i < AMDGPU_MES_MAX_SDMA_PIPES; i++) {
-		if (adev->ip_versions[SDMA0_HWIP][0] < IP_VERSION(6, 0, 0))
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) <
+		    IP_VERSION(6, 0, 0))
 			adev->mes.sdma_hqd_mask[i] = i ? 0 : 0x3fc;
 		/* zero sdma_hqd_mask for non-existent engine */
 		else if (adev->sdma.num_instances == 1)
@@ -181,8 +202,14 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 	if (r)
 		goto error;
 
+	r = amdgpu_mes_event_log_init(adev);
+	if (r)
+		goto error_doorbell;
+
 	return 0;
 
+error_doorbell:
+	amdgpu_mes_doorbell_free(adev);
 error:
 	amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
 	amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
@@ -198,6 +225,10 @@ error_ids:
 
 void amdgpu_mes_fini(struct amdgpu_device *adev)
 {
+	amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj,
+			      &adev->mes.event_log_gpu_addr,
+			      &adev->mes.event_log_cpu_addr);
+
 	amdgpu_device_wb_free(adev, adev->mes.sch_ctx_offs);
 	amdgpu_device_wb_free(adev, adev->mes.query_status_fence_offs);
 	amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
@@ -556,8 +587,20 @@ static void amdgpu_mes_queue_init_mqd(struct amdgpu_device *adev,
 	mqd_prop.hqd_queue_priority = p->hqd_queue_priority;
 	mqd_prop.hqd_active = false;
 
+	if (p->queue_type == AMDGPU_RING_TYPE_GFX ||
+	    p->queue_type == AMDGPU_RING_TYPE_COMPUTE) {
+		mutex_lock(&adev->srbm_mutex);
+		amdgpu_gfx_select_me_pipe_q(adev, p->ring->me, p->ring->pipe, 0, 0, 0);
+	}
+
 	mqd_mgr->init_mqd(adev, q->mqd_cpu_ptr, &mqd_prop);
 
+	if (p->queue_type == AMDGPU_RING_TYPE_GFX ||
+	    p->queue_type == AMDGPU_RING_TYPE_COMPUTE) {
+		amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
+
 	amdgpu_bo_unreserve(q->mqd_obj);
 }
 
@@ -873,6 +916,11 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 	op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER;
 	op_input.set_shader_debugger.process_context_addr = process_context_addr;
 	op_input.set_shader_debugger.flags.u32all = flags;
+
+	/* use amdgpu mes_flush_shader_debugger instead */
+	if (op_input.set_shader_debugger.flags.process_ctx_flush)
+		return -EINVAL;
+
 	op_input.set_shader_debugger.spi_gdbg_per_vmid_cntl = spi_gdbg_per_vmid_cntl;
 	memcpy(op_input.set_shader_debugger.tcp_watch_cntl, tcp_watch_cntl,
 			sizeof(op_input.set_shader_debugger.tcp_watch_cntl));
@@ -892,6 +940,32 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 	return r;
 }
 
+int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev,
+				     uint64_t process_context_addr)
+{
+	struct mes_misc_op_input op_input = {0};
+	int r;
+
+	if (!adev->mes.funcs->misc_op) {
+		DRM_ERROR("mes flush shader debugger is not supported!\n");
+		return -EINVAL;
+	}
+
+	op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER;
+	op_input.set_shader_debugger.process_context_addr = process_context_addr;
+	op_input.set_shader_debugger.flags.process_ctx_flush = true;
+
+	amdgpu_mes_lock(&adev->mes);
+
+	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	if (r)
+		DRM_ERROR("failed to set_shader_debugger\n");
+
+	amdgpu_mes_unlock(&adev->mes);
+
+	return r;
+}
+
 static void
 amdgpu_mes_ring_to_queue_props(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,
@@ -993,9 +1067,13 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id,
 	switch (queue_type) {
 	case AMDGPU_RING_TYPE_GFX:
 		ring->funcs = adev->gfx.gfx_ring[0].funcs;
+		ring->me = adev->gfx.gfx_ring[0].me;
+		ring->pipe = adev->gfx.gfx_ring[0].pipe;
 		break;
 	case AMDGPU_RING_TYPE_COMPUTE:
 		ring->funcs = adev->gfx.compute_ring[0].funcs;
+		ring->me = adev->gfx.compute_ring[0].me;
+		ring->pipe = adev->gfx.compute_ring[0].pipe;
 		break;
 	case AMDGPU_RING_TYPE_SDMA:
 		ring->funcs = adev->sdma.instance[0].ring.funcs;
@@ -1105,7 +1183,7 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
 
 	amdgpu_sync_create(&sync);
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_lock_obj(&exec,
 				      &ctx_data->meta_data_obj->tbo.base);
@@ -1176,7 +1254,7 @@ int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev,
 	struct drm_exec exec;
 	long r;
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_lock_obj(&exec,
 				      &ctx_data->meta_data_obj->tbo.base);
@@ -1335,8 +1413,10 @@ int amdgpu_mes_self_test(struct amdgpu_device *adev)
 
 	for (i = 0; i < ARRAY_SIZE(queue_types); i++) {
 		/* On GFX v10.3, fw hasn't supported to map sdma queue. */
-		if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 3, 0) &&
-		    adev->ip_versions[GC_HWIP][0] < IP_VERSION(11, 0, 0) &&
+		if (amdgpu_ip_version(adev, GC_HWIP, 0) >=
+			    IP_VERSION(10, 3, 0) &&
+		    amdgpu_ip_version(adev, GC_HWIP, 0) <
+			    IP_VERSION(11, 0, 0) &&
 		    queue_types[i][0] == AMDGPU_RING_TYPE_SDMA)
 			continue;
 
@@ -1397,7 +1477,7 @@ int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe)
 
 	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix,
 				       sizeof(ucode_prefix));
-	if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) {
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0)) {
 		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes%s.bin",
 			 ucode_prefix,
 			 pipe == AMDGPU_MES_SCHED_PIPE ? "_2" : "1");
@@ -1460,3 +1540,34 @@ out:
 	amdgpu_ucode_release(&adev->mes.fw[pipe]);
 	return r;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
+{
+	struct amdgpu_device *adev = m->private;
+	uint32_t *mem = (uint32_t *)(adev->mes.event_log_cpu_addr);
+
+	seq_hex_dump(m, "", DUMP_PREFIX_OFFSET, 32, 4,
+		     mem, PAGE_SIZE, false);
+
+	return 0;
+}
+
+
+DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_mes_event_log);
+
+#endif
+
+void amdgpu_debugfs_mes_event_log_init(struct amdgpu_device *adev)
+{
+
+#if defined(CONFIG_DEBUG_FS)
+	struct drm_minor *minor = adev_to_drm(adev)->primary;
+	struct dentry *root = minor->debugfs_root;
+
+	debugfs_create_file("amdgpu_mes_event_log", 0444, root,
+			    adev, &amdgpu_debugfs_mes_event_log_fops);
+
+#endif
+}