1 files changed, 106 insertions, 474 deletions

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 1c5c3eeba4cf..9c83f7d96caa 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
 #include <math.h>
 #include <stdio.h>
 #include "evsel.h"
@@ -15,413 +16,88 @@
 #include <linux/zalloc.h>
 #include "iostat.h"
 #include "util/hashmap.h"
+#include "tool_pmu.h"
 
-struct stats walltime_nsecs_stats;
-struct rusage_stats ru_stats;
-
-enum {
-	CTX_BIT_USER	= 1 << 0,
-	CTX_BIT_KERNEL	= 1 << 1,
-	CTX_BIT_HV	= 1 << 2,
-	CTX_BIT_HOST	= 1 << 3,
-	CTX_BIT_IDLE	= 1 << 4,
-	CTX_BIT_MAX	= 1 << 5,
-};
-
-enum stat_type {
-	STAT_NONE = 0,
-	STAT_NSECS,
-	STAT_CYCLES,
-	STAT_INSTRUCTIONS,
-	STAT_STALLED_CYCLES_FRONT,
-	STAT_STALLED_CYCLES_BACK,
-	STAT_BRANCHES,
-	STAT_BRANCH_MISS,
-	STAT_CACHE_REFS,
-	STAT_CACHE_MISSES,
-	STAT_L1_DCACHE,
-	STAT_L1_ICACHE,
-	STAT_LL_CACHE,
-	STAT_ITLB_CACHE,
-	STAT_DTLB_CACHE,
-	STAT_L1D_MISS,
-	STAT_L1I_MISS,
-	STAT_LL_MISS,
-	STAT_DTLB_MISS,
-	STAT_ITLB_MISS,
-	STAT_MAX
-};
-
-static int evsel_context(const struct evsel *evsel)
+static bool tool_pmu__is_time_event(const struct perf_stat_config *config,
+				   const struct evsel *evsel, int *tool_aggr_idx)
 {
-	int ctx = 0;
-
-	if (evsel->core.attr.exclude_kernel)
-		ctx |= CTX_BIT_KERNEL;
-	if (evsel->core.attr.exclude_user)
-		ctx |= CTX_BIT_USER;
-	if (evsel->core.attr.exclude_hv)
-		ctx |= CTX_BIT_HV;
-	if (evsel->core.attr.exclude_host)
-		ctx |= CTX_BIT_HOST;
-	if (evsel->core.attr.exclude_idle)
-		ctx |= CTX_BIT_IDLE;
-
-	return ctx;
-}
-
-void perf_stat__reset_shadow_stats(void)
-{
-	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
-	memset(&ru_stats, 0, sizeof(ru_stats));
-}
-
-static enum stat_type evsel__stat_type(const struct evsel *evsel)
-{
-	/* Fake perf_hw_cache_op_id values for use with evsel__match. */
-	u64 PERF_COUNT_hw_cache_l1d_miss = PERF_COUNT_HW_CACHE_L1D |
-		((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-		((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16);
-	u64 PERF_COUNT_hw_cache_l1i_miss = PERF_COUNT_HW_CACHE_L1I |
-		((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-		((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16);
-	u64 PERF_COUNT_hw_cache_ll_miss = PERF_COUNT_HW_CACHE_LL |
-		((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-		((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16);
-	u64 PERF_COUNT_hw_cache_dtlb_miss = PERF_COUNT_HW_CACHE_DTLB |
-		((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-		((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16);
-	u64 PERF_COUNT_hw_cache_itlb_miss = PERF_COUNT_HW_CACHE_ITLB |
-		((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-		((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16);
-
-	if (evsel__is_clock(evsel))
-		return STAT_NSECS;
-	else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES))
-		return STAT_CYCLES;
-	else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS))
-		return STAT_INSTRUCTIONS;
-	else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-		return STAT_STALLED_CYCLES_FRONT;
-	else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-		return STAT_STALLED_CYCLES_BACK;
-	else if (evsel__match(evsel, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		return STAT_BRANCHES;
-	else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES))
-		return STAT_BRANCH_MISS;
-	else if (evsel__match(evsel, HARDWARE, HW_CACHE_REFERENCES))
-		return STAT_CACHE_REFS;
-	else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES))
-		return STAT_CACHE_MISSES;
-	else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1D))
-		return STAT_L1_DCACHE;
-	else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1I))
-		return STAT_L1_ICACHE;
-	else if (evsel__match(evsel, HW_CACHE, HW_CACHE_LL))
-		return STAT_LL_CACHE;
-	else if (evsel__match(evsel, HW_CACHE, HW_CACHE_DTLB))
-		return STAT_DTLB_CACHE;
-	else if (evsel__match(evsel, HW_CACHE, HW_CACHE_ITLB))
-		return STAT_ITLB_CACHE;
-	else if (evsel__match(evsel, HW_CACHE, hw_cache_l1d_miss))
-		return STAT_L1D_MISS;
-	else if (evsel__match(evsel, HW_CACHE, hw_cache_l1i_miss))
-		return STAT_L1I_MISS;
-	else if (evsel__match(evsel, HW_CACHE, hw_cache_ll_miss))
-		return STAT_LL_MISS;
-	else if (evsel__match(evsel, HW_CACHE, hw_cache_dtlb_miss))
-		return STAT_DTLB_MISS;
-	else if (evsel__match(evsel, HW_CACHE, hw_cache_itlb_miss))
-		return STAT_ITLB_MISS;
-	return STAT_NONE;
-}
-
-static const char *get_ratio_color(const double ratios[3], double val)
-{
-	const char *color = PERF_COLOR_NORMAL;
-
-	if (val > ratios[0])
-		color = PERF_COLOR_RED;
-	else if (val > ratios[1])
-		color = PERF_COLOR_MAGENTA;
-	else if (val > ratios[2])
-		color = PERF_COLOR_YELLOW;
-
-	return color;
-}
-
-static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type type)
-{
-	const struct evsel *cur;
-	int evsel_ctx = evsel_context(evsel);
-
-	evlist__for_each_entry(evsel->evlist, cur) {
-		struct perf_stat_aggr *aggr;
-
-		/* Ignore the evsel that is being searched from. */
-		if (evsel == cur)
-			continue;
-
-		/* Ignore evsels that are part of different groups. */
-		if (evsel->core.leader->nr_members > 1 &&
-		    evsel->core.leader != cur->core.leader)
-			continue;
-		/* Ignore evsels with mismatched modifiers. */
-		if (evsel_ctx != evsel_context(cur))
-			continue;
-		/* Ignore if not the cgroup we're looking for. */
-		if (evsel->cgrp != cur->cgrp)
-			continue;
-		/* Ignore if not the stat we're looking for. */
-		if (type != evsel__stat_type(cur))
-			continue;
-
-		aggr = &cur->stats->aggr[aggr_idx];
-		if (type == STAT_NSECS)
-			return aggr->counts.val;
-		return aggr->counts.val * cur->scale;
-	}
-	return 0.0;
-}
-
-static void print_ratio(struct perf_stat_config *config,
-			const struct evsel *evsel, int aggr_idx,
-			double numerator, struct perf_stat_output_ctx *out,
-			enum stat_type denominator_type,
-			const double color_ratios[3], const char *unit)
-{
-	double denominator = find_stat(evsel, aggr_idx, denominator_type);
-
-	if (numerator && denominator) {
-		double ratio = numerator / denominator * 100.0;
-		const char *color = get_ratio_color(color_ratios, ratio);
-
-		out->print_metric(config, out->ctx, color, "%7.2f%%", unit, ratio);
-	} else
-		out->print_metric(config, out->ctx, NULL, NULL, unit, 0);
-}
-
-static void print_stalled_cycles_front(struct perf_stat_config *config,
-				const struct evsel *evsel,
-				int aggr_idx, double stalled,
-				struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {50.0, 30.0, 10.0};
-
-	print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios,
-		    "frontend cycles idle");
-}
-
-static void print_stalled_cycles_back(struct perf_stat_config *config,
-				const struct evsel *evsel,
-				int aggr_idx, double stalled,
-				struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {75.0, 50.0, 20.0};
-
-	print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios,
-		    "backend cycles idle");
-}
-
-static void print_branch_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_BRANCHES, color_ratios,
-		    "of all branches");
-}
-
-static void print_l1d_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_DCACHE, color_ratios,
-		    "of all L1-dcache accesses");
-}
-
-static void print_l1i_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_ICACHE, color_ratios,
-		    "of all L1-icache accesses");
-}
-
-static void print_ll_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios,
-		    "of all L1-icache accesses");
-}
+	enum tool_pmu_event event = evsel__tool_event(evsel);
+	int aggr_idx;
 
-static void print_dtlb_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_DTLB_CACHE, color_ratios,
-		    "of all dTLB cache accesses");
-}
-
-static void print_itlb_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_ITLB_CACHE, color_ratios,
-		    "of all iTLB cache accesses");
-}
-
-static void print_cache_miss(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double misses,
-			struct perf_stat_output_ctx *out)
-{
-	static const double color_ratios[3] = {20.0, 10.0, 5.0};
-
-	print_ratio(config, evsel, aggr_idx, misses, out, STAT_CACHE_REFS, color_ratios,
-		    "of all cache refs");
-}
+	if (event != TOOL_PMU__EVENT_DURATION_TIME &&
+	    event != TOOL_PMU__EVENT_USER_TIME &&
+	    event != TOOL_PMU__EVENT_SYSTEM_TIME)
+		return false;
 
-static void print_instructions(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double instructions,
-			struct perf_stat_output_ctx *out)
-{
-	print_metric_t print_metric = out->print_metric;
-	void *ctxp = out->ctx;
-	double cycles = find_stat(evsel, aggr_idx, STAT_CYCLES);
-	double max_stalled = max(find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_FRONT),
-				find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_BACK));
-
-	if (cycles) {
-		print_metric(config, ctxp, NULL, "%7.2f ", "insn per cycle",
-			instructions / cycles);
-	} else
-		print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
-
-	if (max_stalled && instructions) {
-		out->new_line(config, ctxp);
-		print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn",
-			max_stalled / instructions);
+	if (config) {
+		cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
+			if (config->aggr_map->map[aggr_idx].cpu.cpu == 0) {
+				*tool_aggr_idx = aggr_idx;
+				return true;
+			}
+		}
+		pr_debug("Unexpected CPU0 missing in aggregation for tool event.\n");
 	}
+	*tool_aggr_idx = 0; /* Assume the first aggregation index works. */
+	return true;
 }
 
-static void print_cycles(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx, double cycles,
-			struct perf_stat_output_ctx *out)
-{
-	double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS);
-
-	if (cycles && nsecs) {
-		double ratio = cycles / nsecs;
-
-		out->print_metric(config, out->ctx, NULL, "%8.3f", "GHz", ratio);
-	} else
-		out->print_metric(config, out->ctx, NULL, NULL, "GHz", 0);
-}
-
-static void print_nsecs(struct perf_stat_config *config,
-			const struct evsel *evsel,
-			int aggr_idx __maybe_unused, double nsecs,
-			struct perf_stat_output_ctx *out)
-{
-	print_metric_t print_metric = out->print_metric;
-	void *ctxp = out->ctx;
-	double wall_time = avg_stats(&walltime_nsecs_stats);
-
-	if (wall_time) {
-		print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
-			nsecs / (wall_time * evsel->scale));
-	} else
-		print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
-}
-
-static int prepare_metric(struct evsel **metric_events,
-			  struct metric_ref *metric_refs,
+static int prepare_metric(struct perf_stat_config *config,
+			  const struct metric_expr *mexp,
+			  const struct evsel *evsel,
 			  struct expr_parse_ctx *pctx,
 			  int aggr_idx)
 {
+	struct evsel * const *metric_events = mexp->metric_events;
+	struct metric_ref *metric_refs = mexp->metric_refs;
 	int i;
 
 	for (i = 0; metric_events[i]; i++) {
+		int source_count = 0, tool_aggr_idx;
+		bool is_tool_time =
+			tool_pmu__is_time_event(config, metric_events[i], &tool_aggr_idx);
+		struct perf_stat_evsel *ps = metric_events[i]->stats;
+		struct perf_stat_aggr *aggr;
 		char *n;
 		double val;
-		int source_count = 0;
-
-		if (evsel__is_tool(metric_events[i])) {
-			struct stats *stats;
-			double scale;
 
-			switch (metric_events[i]->tool_event) {
-			case PERF_TOOL_DURATION_TIME:
-				stats = &walltime_nsecs_stats;
-				scale = 1e-9;
+		/*
+		 * If there are multiple uncore PMUs and we're not reading the
+		 * leader's stats, determine the stats for the appropriate
+		 * uncore PMU.
+		 */
+		if (evsel && evsel->metric_leader &&
+		    evsel->pmu != evsel->metric_leader->pmu &&
+		    mexp->metric_events[i]->pmu == evsel->metric_leader->pmu) {
+			struct evsel *pos;
+
+			evlist__for_each_entry(evsel->evlist, pos) {
+				if (pos->pmu != evsel->pmu)
+					continue;
+				if (pos->metric_leader != mexp->metric_events[i])
+					continue;
+				ps = pos->stats;
+				source_count = 1;
 				break;
-			case PERF_TOOL_USER_TIME:
-				stats = &ru_stats.ru_utime_usec_stat;
-				scale = 1e-6;
-				break;
-			case PERF_TOOL_SYSTEM_TIME:
-				stats = &ru_stats.ru_stime_usec_stat;
-				scale = 1e-6;
-				break;
-			case PERF_TOOL_NONE:
-				pr_err("Invalid tool event 'none'");
-				abort();
-			case PERF_TOOL_MAX:
-				pr_err("Invalid tool event 'max'");
-				abort();
-			default:
-				pr_err("Unknown tool event '%s'", evsel__name(metric_events[i]));
-				abort();
 			}
-			val = avg_stats(stats) * scale;
-			source_count = 1;
+		}
+		/* Time events are always on CPU0, the first aggregation index. */
+		aggr = &ps->aggr[is_tool_time ? tool_aggr_idx : aggr_idx];
+		if (!aggr || !metric_events[i]->supported) {
+			/*
+			 * Not supported events will have a count of 0, which
+			 * can be confusing in a metric. Explicitly set the
+			 * value to NAN. Not counted events (enable time of 0)
+			 * are read as 0.
+			 */
+			val = NAN;
+			source_count = 0;
 		} else {
-			struct perf_stat_evsel *ps = metric_events[i]->stats;
-			struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx];
-
-			if (!aggr)
-				break;
-
-                        if (!metric_events[i]->supported) {
-				/*
-				 * Not supported events will have a count of 0,
-				 * which can be confusing in a
-				 * metric. Explicitly set the value to NAN. Not
-				 * counted events (enable time of 0) are read as
-				 * 0.
-				 */
-				val = NAN;
-				source_count = 0;
-			} else {
-				/*
-				 * If an event was scaled during stat gathering,
-				 * reverse the scale before computing the
-				 * metric.
-				 */
-				val = aggr->counts.val * (1.0 / metric_events[i]->scale);
+			val = aggr->counts.val;
+			if (is_tool_time)
+				val *= 1e-9; /* Convert time event nanoseconds to seconds. */
+			if (!source_count)
 				source_count = evsel__source_count(metric_events[i]);
-			}
 		}
 		n = strdup(evsel__metric_id(metric_events[i]));
 		if (!n)
@@ -441,23 +117,23 @@ static int prepare_metric(struct evsel **metric_events,
 }
 
 static void generic_metric(struct perf_stat_config *config,
-			   const char *metric_expr,
-			   const char *metric_threshold,
-			   struct evsel **metric_events,
-			   struct metric_ref *metric_refs,
-			   char *name,
-			   const char *metric_name,
-			   const char *metric_unit,
-			   int runtime,
+			   struct metric_expr *mexp,
+			   struct evsel *evsel,
 			   int aggr_idx,
 			   struct perf_stat_output_ctx *out)
 {
 	print_metric_t print_metric = out->print_metric;
+	const char *metric_name = mexp->metric_name;
+	const char *metric_expr = mexp->metric_expr;
+	const char *metric_threshold = mexp->metric_threshold;
+	const char *metric_unit = mexp->metric_unit;
+	struct evsel * const *metric_events = mexp->metric_events;
+	int runtime = mexp->runtime;
 	struct expr_parse_ctx *pctx;
 	double ratio, scale, threshold;
 	int i;
 	void *ctxp = out->ctx;
-	const char *color = NULL;
+	enum metric_threshold_classify thresh = METRIC_THRESHOLD_UNKNOWN;
 
 	pctx = expr__ctx_new();
 	if (!pctx)
@@ -467,7 +143,7 @@ static void generic_metric(struct perf_stat_config *config,
 		pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list);
 	pctx->sctx.runtime = runtime;
 	pctx->sctx.system_wide = config->system_wide;
-	i = prepare_metric(metric_events, metric_refs, pctx, aggr_idx);
+	i = prepare_metric(config, mexp, evsel, pctx, aggr_idx);
 	if (i < 0) {
 		expr__ctx_free(pctx);
 		return;
@@ -475,13 +151,13 @@ static void generic_metric(struct perf_stat_config *config,
 	if (!metric_events[i]) {
 		if (expr__parse(&ratio, pctx, metric_expr) == 0) {
 			char *unit;
-			char metric_bf[64];
+			char metric_bf[128];
 
 			if (metric_threshold &&
 			    expr__parse(&threshold, pctx, metric_threshold) == 0 &&
 			    !isnan(threshold)) {
-				color = fpclassify(threshold) == FP_ZERO
-					? PERF_COLOR_GREEN : PERF_COLOR_RED;
+				thresh = fpclassify(threshold) == FP_ZERO
+					? METRIC_THRESHOLD_GOOD : METRIC_THRESHOLD_BAD;
 			}
 
 			if (metric_unit && metric_name) {
@@ -496,24 +172,24 @@ static void generic_metric(struct perf_stat_config *config,
 					scnprintf(metric_bf, sizeof(metric_bf),
 					  "%s  %s", unit, metric_name);
 
-				print_metric(config, ctxp, color, "%8.1f",
+				print_metric(config, ctxp, thresh, "%8.1f",
 					     metric_bf, ratio);
 			} else {
-				print_metric(config, ctxp, color, "%8.2f",
+				print_metric(config, ctxp, thresh, "%8.2f",
 					metric_name ?
 					metric_name :
-					out->force_header ?  name : "",
+					out->force_header ?  evsel->name : "",
 					ratio);
 			}
 		} else {
-			print_metric(config, ctxp, color, /*unit=*/NULL,
+			print_metric(config, ctxp, thresh, /*fmt=*/NULL,
 				     out->force_header ?
-				     (metric_name ? metric_name : name) : "", 0);
+				     (metric_name ?: evsel->name) : "", 0);
 		}
 	} else {
-		print_metric(config, ctxp, color, /*unit=*/NULL,
+		print_metric(config, ctxp, thresh, /*fmt=*/NULL,
 			     out->force_header ?
-			     (metric_name ? metric_name : name) : "", 0);
+			     (metric_name ?: evsel->name) : "", 0);
 	}
 
 	expr__ctx_free(pctx);
@@ -528,7 +204,7 @@ double test_generic_metric(struct metric_expr *mexp, int aggr_idx)
 	if (!pctx)
 		return NAN;
 
-	if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, aggr_idx) < 0)
+	if (prepare_metric(/*config=*/NULL, mexp, /*evsel=*/NULL, pctx, aggr_idx) < 0)
 		goto out;
 
 	if (expr__parse(&ratio, pctx, mexp->metric_expr))
@@ -547,7 +223,7 @@ static void perf_stat__print_metricgroup_header(struct perf_stat_config *config,
 {
 	bool need_full_name = perf_pmus__num_core_pmus() > 1;
 	static const char *last_name;
-	static const char *last_pmu;
+	static const struct perf_pmu *last_pmu;
 	char full_name[64];
 
 	/*
@@ -557,22 +233,20 @@ static void perf_stat__print_metricgroup_header(struct perf_stat_config *config,
 	 * event. Only align with other metics from
 	 * different metric events.
 	 */
-	if (last_name && !strcmp(last_name, name)) {
-		if (!need_full_name || !strcmp(last_pmu, evsel->pmu_name)) {
-			out->print_metricgroup_header(config, ctxp, NULL);
-			return;
-		}
+	if (last_name && !strcmp(last_name, name) && last_pmu == evsel->pmu) {
+		out->print_metricgroup_header(config, ctxp, NULL);
+		return;
 	}
 
-	if (need_full_name)
-		scnprintf(full_name, sizeof(full_name), "%s (%s)", name, evsel->pmu_name);
+	if (need_full_name && evsel->pmu)
+		scnprintf(full_name, sizeof(full_name), "%s (%s)", name, evsel->pmu->name);
 	else
 		scnprintf(full_name, sizeof(full_name), "%s", name);
 
 	out->print_metricgroup_header(config, ctxp, full_name);
 
 	last_name = name;
-	last_pmu = evsel->pmu_name;
+	last_pmu = evsel->pmu;
 }
 
 /**
@@ -591,14 +265,14 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
 						int aggr_idx,
 						int *num,
 						void *from,
-						struct perf_stat_output_ctx *out,
-						struct rblist *metric_events)
+						struct perf_stat_output_ctx *out)
 {
 	struct metric_event *me;
 	struct metric_expr *mexp = from;
 	void *ctxp = out->ctx;
 	bool header_printed = false;
 	const char *name = NULL;
+	struct rblist *metric_events = &evsel->evlist->metric_events;
 
 	me = metricgroup__lookup(metric_events, evsel, false);
 	if (me == NULL)
@@ -621,19 +295,16 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
 			if (strcmp(name, mexp->default_metricgroup_name))
 				return (void *)mexp;
 			/* Only print the name of the metricgroup once */
-			if (!header_printed) {
+			if (!header_printed && !evsel->default_show_events) {
 				header_printed = true;
 				perf_stat__print_metricgroup_header(config, evsel, ctxp,
 								    name, out);
 			}
 		}
 
-		if ((*num)++ > 0)
+		if ((*num)++ > 0 && out->new_line)
 			out->new_line(config, ctxp);
-		generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
-			       mexp->metric_events, mexp->metric_refs, evsel->name,
-			       mexp->metric_name, mexp->metric_unit, mexp->runtime,
-			       aggr_idx, out);
+		generic_metric(config, mexp, evsel, aggr_idx, out);
 	}
 
 	return NULL;
@@ -641,61 +312,23 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
 
 void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				   struct evsel *evsel,
-				   double avg, int aggr_idx,
-				   struct perf_stat_output_ctx *out,
-				   struct rblist *metric_events)
+				   int aggr_idx,
+				   struct perf_stat_output_ctx *out)
 {
-	typedef void (*stat_print_function_t)(struct perf_stat_config *config,
-					const struct evsel *evsel,
-					int aggr_idx, double misses,
-					struct perf_stat_output_ctx *out);
-	static const stat_print_function_t stat_print_function[STAT_MAX] = {
-		[STAT_INSTRUCTIONS] = print_instructions,
-		[STAT_BRANCH_MISS] = print_branch_miss,
-		[STAT_L1D_MISS] = print_l1d_miss,
-		[STAT_L1I_MISS] = print_l1i_miss,
-		[STAT_DTLB_MISS] = print_dtlb_miss,
-		[STAT_ITLB_MISS] = print_itlb_miss,
-		[STAT_LL_MISS] = print_ll_miss,
-		[STAT_CACHE_MISSES] = print_cache_miss,
-		[STAT_STALLED_CYCLES_FRONT] = print_stalled_cycles_front,
-		[STAT_STALLED_CYCLES_BACK] = print_stalled_cycles_back,
-		[STAT_CYCLES] = print_cycles,
-		[STAT_NSECS] = print_nsecs,
-	};
 	print_metric_t print_metric = out->print_metric;
 	void *ctxp = out->ctx;
-	int num = 1;
+	int num = 0;
 
-	if (config->iostat_run) {
+	if (config->iostat_run)
 		iostat_print_metric(config, evsel, out);
-	} else {
-		stat_print_function_t fn = stat_print_function[evsel__stat_type(evsel)];
-
-		if (fn)
-			fn(config, evsel, aggr_idx, avg, out);
-		else {
-			double nsecs =	find_stat(evsel, aggr_idx, STAT_NSECS);
-
-			if (nsecs) {
-				char unit = ' ';
-				char unit_buf[10] = "/sec";
-				double ratio = convert_unit_double(1000000000.0 * avg / nsecs,
-								   &unit);
-
-				if (unit != ' ')
-					snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-				print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
-			} else
-				num = 0;
-		}
-	}
 
 	perf_stat__print_shadow_stats_metricgroup(config, evsel, aggr_idx,
-						  &num, NULL, out, metric_events);
+						  &num, NULL, out);
 
-	if (num == 0)
-		print_metric(config, ctxp, NULL, NULL, NULL, 0);
+	if (num == 0) {
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN,
+			     /*fmt=*/NULL, /*unit=*/NULL, 0);
+	}
 }
 
 /**
@@ -703,7 +336,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
  *				  if it's not running or not the metric event.
  */
 bool perf_stat__skip_metric_event(struct evsel *evsel,
-				  struct rblist *metric_events,
 				  u64 ena, u64 run)
 {
 	if (!evsel->default_metricgroup)
@@ -712,5 +344,5 @@ bool perf_stat__skip_metric_event(struct evsel *evsel,
 	if (!ena || !run)
 		return true;
 
-	return !metricgroup__lookup(metric_events, evsel, false);
+	return !metricgroup__lookup(&evsel->evlist->metric_events, evsel, false);
 }