drm/amd/display: Add profiling tools for bandwidth validation

[Why]
We used this change to investigate the performance of bandwidth validation,
it will be useful to have if we need to investigate further.

[How]
We use performance counter tick numbers to profile performance, they live
at dc->debug.bw_val_profile (set .enable in debugger to turn on measuring).
Signed-off-by: Joshua Aberback <joshua.aberback@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c

@@ -704,6 +704,12 @@ bool dcn_validate_bandwidth(
 		struct dc_state *context,
 		bool fast_validate)
 {
+	/*
+	 * we want a breakdown of the various stages of validation, which the
+	 * perf_trace macro doesn't support
+	 */
+	BW_VAL_TRACE_SETUP();
+
 	const struct resource_pool *pool = dc->res_pool;
 	struct dcn_bw_internal_vars *v = &context->dcn_bw_vars;
 	int i, input_idx;
@@ -712,6 +718,9 @@ bool dcn_validate_bandwidth(
 	float bw_limit;
 
 	PERFORMANCE_TRACE_START();
+
+	BW_VAL_TRACE_COUNT();
+
 	if (dcn_bw_apply_registry_override(dc))
 		dcn_bw_sync_calcs_and_dml(dc);
 
@@ -1014,6 +1023,8 @@ bool dcn_validate_bandwidth(
 		mode_support_and_system_configuration(v);
 	}
 
+	BW_VAL_TRACE_END_VOLTAGE_LEVEL();
+
 	if (v->voltage_level != number_of_states_plus_one && !fast_validate) {
 		float bw_consumed = v->total_bandwidth_consumed_gbyte_per_second;
 
@@ -1089,6 +1100,8 @@ bool dcn_validate_bandwidth(
 			break;
 		}
 
+		BW_VAL_TRACE_END_WATERMARKS();
+
 		for (i = 0, input_idx = 0; i < pool->pipe_count; i++) {
 			struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
@@ -1179,6 +1192,10 @@ bool dcn_validate_bandwidth(
 
 			input_idx++;
 		}
+	} else if (v->voltage_level == number_of_states_plus_one) {
+		BW_VAL_TRACE_SKIP(fail);
+	} else if (fast_validate) {
+		BW_VAL_TRACE_SKIP(fast);
 	}
 
 	if (v->voltage_level == 0) {
@@ -1198,6 +1215,7 @@ bool dcn_validate_bandwidth(
 	kernel_fpu_end();
 
 	PERFORMANCE_TRACE_END();
+	BW_VAL_TRACE_FINISH();
 
 	if (bw_limit_pass && v->voltage_level != 5)
 		return true;

drivers/gpu/drm/amd/display/dc/dc.h

@@ -246,6 +246,57 @@ struct dc_clocks {
 	bool p_state_change_support;
 };
 
+struct dc_bw_validation_profile {
+	bool enable;
+
+	unsigned long long total_ticks;
+	unsigned long long voltage_level_ticks;
+	unsigned long long watermark_ticks;
+	unsigned long long rq_dlg_ticks;
+
+	unsigned long long total_count;
+	unsigned long long skip_fast_count;
+	unsigned long long skip_pass_count;
+	unsigned long long skip_fail_count;
+};
+
+#define BW_VAL_TRACE_SETUP() \
+		unsigned long long end_tick = 0; \
+		unsigned long long voltage_level_tick = 0; \
+		unsigned long long watermark_tick = 0; \
+		unsigned long long start_tick = dc->debug.bw_val_profile.enable ? \
+				dm_get_timestamp(dc->ctx) : 0
+
+#define BW_VAL_TRACE_COUNT() \
+		if (dc->debug.bw_val_profile.enable) \
+			dc->debug.bw_val_profile.total_count++
+
+#define BW_VAL_TRACE_SKIP(status) \
+		if (dc->debug.bw_val_profile.enable) { \
+			if (!voltage_level_tick) \
+				voltage_level_tick = dm_get_timestamp(dc->ctx); \
+			dc->debug.bw_val_profile.skip_ ## status ## _count++; \
+		}
+
+#define BW_VAL_TRACE_END_VOLTAGE_LEVEL() \
+		if (dc->debug.bw_val_profile.enable) \
+			voltage_level_tick = dm_get_timestamp(dc->ctx)
+
+#define BW_VAL_TRACE_END_WATERMARKS() \
+		if (dc->debug.bw_val_profile.enable) \
+			watermark_tick = dm_get_timestamp(dc->ctx)
+
+#define BW_VAL_TRACE_FINISH() \
+		if (dc->debug.bw_val_profile.enable) { \
+			end_tick = dm_get_timestamp(dc->ctx); \
+			dc->debug.bw_val_profile.total_ticks += end_tick - start_tick; \
+			dc->debug.bw_val_profile.voltage_level_ticks += voltage_level_tick - start_tick; \
+			if (watermark_tick) { \
+				dc->debug.bw_val_profile.watermark_ticks += watermark_tick - voltage_level_tick; \
+				dc->debug.bw_val_profile.rq_dlg_ticks += end_tick - watermark_tick; \
+			} \
+		}
+
 struct dc_debug_options {
 	enum visual_confirm visual_confirm;
 	bool sanity_checks;
@@ -299,6 +350,7 @@ struct dc_debug_options {
 	unsigned int force_odm_combine; //bit vector based on otg inst
 	unsigned int force_fclk_khz;
 	bool disable_tri_buf;
+	struct dc_bw_validation_profile bw_val_profile;
 };
 
 struct dc_debug_data {