perf/core improvements and fixes

index 322b4def8411..b7e8812ee80c 100644
@@ -3363,6 +3363,10 @@ int cmd_sched(int argc, const char **argv)
 	OPT_STRING(0, "time", &sched.time_str, "str",
 		   "Time span for analysis (start,stop)"),
 	OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
+	OPT_STRING('p', "pid", &symbol_conf.pid_list_str, "pid[,pid...]",
+		   "analyze events only for given process id(s)"),
+	OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
+		   "analyze events only for given thread id(s)"),
 	OPT_PARENT(sched_options)
 	};
 

index 69523ed55894..7cc61eb0d83b 100644
@@ -582,6 +582,32 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
+static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
+{
+	struct perf_evsel *c2, *leader;
+	bool is_open = true;
+
+	leader = evsel->leader;
+	pr_debug("Weak group for %s/%d failed\n",
+			leader->name, leader->nr_members);
+
+	/*
+	 * for_each_group_member doesn't work here because it doesn't
+	 * include the first entry.
+	 */
+	evlist__for_each_entry(evsel_list, c2) {
+		if (c2 == evsel)
+			is_open = false;
+		if (c2->leader == leader) {
+			if (is_open)
+				perf_evsel__close(c2);
+			c2->leader = c2;
+			c2->nr_members = 0;
+		}
+	}
+	return leader;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;

@@ -618,6 +644,15 @@ static int __run_perf_stat(int argc, const char **argv)
 	evlist__for_each_entry(evsel_list, counter) {
 try_again:
 		if (create_perf_stat_counter(counter) < 0) {
+
+			/* Weak group failed. Reset the group. */
+			if (errno == EINVAL &&
+			    counter->leader != counter &&
+			    counter->weak_group) {
+				counter = perf_evsel__reset_weak_group(counter);
+				goto try_again;
+			}
+
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37
 			 * (behavior changed with commit b0a873e).

index dd2c4b5112a5..db658785d828 100644
@@ -137,6 +137,7 @@ struct perf_evsel {
 	const char *		metric_name;
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
+	bool			weak_group;
 };
 
 union u64_swap {

index f6257fb4f08c..57d7acf890e0 100644
@@ -1366,6 +1366,7 @@ struct event_modifier {
 	int exclude_GH;
 	int sample_read;
 	int pinned;
+	int weak;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,

@@ -1384,6 +1385,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 
 	int exclude = eu | ek | eh;
 	int exclude_GH = evsel ? evsel->exclude_GH : 0;
+	int weak = 0;
 
 	memset(mod, 0, sizeof(*mod));
 

@@ -1421,6 +1423,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 			sample_read = 1;
 		} else if (*str == 'D') {
 			pinned = 1;
+		} else if (*str == 'W') {
+			weak = 1;
 		} else
 			break;
 

@@ -1451,6 +1455,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 	mod->exclude_GH = exclude_GH;
 	mod->sample_read = sample_read;
 	mod->pinned = pinned;
+	mod->weak = weak;
 
 	return 0;
 }

@@ -1464,7 +1469,7 @@ static int check_modifier(char *str)
 	char *p = str;
 
 	/* The sizeof includes 0 byte as well. */
-	if (strlen(str) > (sizeof("ukhGHpppPSDI") - 1))
+	if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1))
 		return -1;
 
 	while (*p) {

@@ -1504,6 +1509,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 		evsel->exclude_GH          = mod.exclude_GH;
 		evsel->sample_read         = mod.sample_read;
 		evsel->precise_max         = mod.precise_max;
+		evsel->weak_group	   = mod.weak;
 
 		if (perf_evsel__is_group_leader(evsel))
 			evsel->attr.pinned = mod.pinned;

index d51dc9ca8861..9eb7047bafe4 100644
@@ -292,7 +292,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
 				    char *desc, char *long_desc,
 				    char *pmu, char *unit, char *perpkg,
 				    char *metric_expr,
-				    char *metric_name)
+				    char *metric_name, char *metric_group)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;

@@ -304,8 +304,10 @@ static int print_events_table_entry(void *data, char *name, char *event,
 	 */
 	fprintf(outfp, "{\n");
 
-	fprintf(outfp, "\t.name = \"%s\",\n", name);
-	fprintf(outfp, "\t.event = \"%s\",\n", event);
+	if (name)
+		fprintf(outfp, "\t.name = \"%s\",\n", name);
+	if (event)
+		fprintf(outfp, "\t.event = \"%s\",\n", event);
 	fprintf(outfp, "\t.desc = \"%s\",\n", desc);
 	fprintf(outfp, "\t.topic = \"%s\",\n", topic);
 	if (long_desc && long_desc[0])

@@ -320,6 +322,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
 	if (metric_name)
 		fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
+	if (metric_group)
+		fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
 	fprintf(outfp, "},\n");
 
 	return 0;

@@ -357,6 +361,9 @@ static char *real_event(const char *name, char *event)
 {
 	int i;
 
+	if (!name)
+		return NULL;
+
 	for (i = 0; fixed[i].name; i++)
 		if (!strcasecmp(name, fixed[i].name))
 			return (char *)fixed[i].event;

@@ -369,7 +376,7 @@ int json_events(const char *fn,
 		      char *long_desc,
 		      char *pmu, char *unit, char *perpkg,
 		      char *metric_expr,
-		      char *metric_name),
+		      char *metric_name, char *metric_group),
 	  void *data)
 {
 	int err = -EIO;

@@ -397,6 +404,7 @@ int json_events(const char *fn,
 		char *unit = NULL;
 		char *metric_expr = NULL;
 		char *metric_name = NULL;
+		char *metric_group = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
 		jsmntok_t *msrval = NULL;

@@ -476,6 +484,8 @@ int json_events(const char *fn,
 				addfield(map, &perpkg, "", "", val);
 			} else if (json_streq(map, field, "MetricName")) {
 				addfield(map, &metric_name, "", "", val);
+			} else if (json_streq(map, field, "MetricGroup")) {
+				addfield(map, &metric_group, "", "", val);
 			} else if (json_streq(map, field, "MetricExpr")) {
 				addfield(map, &metric_expr, "", "", val);
 				for (s = metric_expr; *s; s++)

@@ -501,10 +511,11 @@ int json_events(const char *fn,
 			addfield(map, &event, ",", filter, NULL);
 		if (msr != NULL)
 			addfield(map, &event, ",", msr->pname, msrval);
-		fixname(name);
+		if (name)
+			fixname(name);
 
 		err = func(data, name, real_event(name, event), desc, long_desc,
-				pmu, unit, perpkg, metric_expr, metric_name);
+			   pmu, unit, perpkg, metric_expr, metric_name, metric_group);
 		free(event);
 		free(desc);
 		free(name);

@@ -516,6 +527,7 @@ int json_events(const char *fn,
 		free(unit);
 		free(metric_expr);
 		free(metric_name);
+		free(metric_group);
 		if (err)
 			break;
 		tok += j;

index 611fac01913d..557994754410 100644
@@ -6,7 +6,7 @@ int json_events(const char *fn,
 				char *long_desc,
 				char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
-				char *metric_name),
+				char *metric_name, char *metric_group),
 		void *data);
 char *get_cpu_str(void);
 

index 569eab3688dd..94fa1720f6fd 100644
@@ -15,6 +15,7 @@ struct pmu_event {
 	const char *perpkg;
 	const char *metric_expr;
 	const char *metric_name;
+	const char *metric_group;
 };
 
 /*

index a04cf56d3517..96aa6cbf24d6 100644
@@ -627,6 +627,46 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
+static void generic_metric(const char *metric_expr,
+			   struct perf_evsel **metric_events,
+			   char *name,
+			   const char *metric_name,
+			   double avg,
+			   int cpu,
+			   int ctx,
+			   struct perf_stat_output_ctx *out)
+{
+	print_metric_t print_metric = out->print_metric;
+	struct parse_ctx pctx;
+	double ratio;
+	int i;
+	void *ctxp = out->ctx;
+
+	expr__ctx_init(&pctx);
+	expr__add_id(&pctx, name, avg);
+	for (i = 0; metric_events[i]; i++) {
+		struct saved_value *v;
+
+		v = saved_value_lookup(metric_events[i], cpu, ctx, false);
+		if (!v)
+			break;
+		expr__add_id(&pctx, metric_events[i]->name, avg_stats(&v->stats));
+	}
+	if (!metric_events[i]) {
+		const char *p = metric_expr;
+
+		if (expr__parse(&ratio, &pctx, &p) == 0)
+			print_metric(ctxp, NULL, "%8.1f",
+				metric_name ?
+				metric_name :
+				out->force_header ?  name : "",
+				ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "", 0);
+	} else
+		print_metric(ctxp, NULL, NULL, "", 0);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out)

@@ -819,33 +859,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		else
 			print_metric(ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		struct parse_ctx pctx;
-		int i;
-
-		expr__ctx_init(&pctx);
-		expr__add_id(&pctx, evsel->name, avg);
-		for (i = 0; evsel->metric_events[i]; i++) {
-			struct saved_value *v;
-
-			v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
-			if (!v)
-				break;
-			expr__add_id(&pctx, evsel->metric_events[i]->name,
-					     avg_stats(&v->stats));
-		}
-		if (!evsel->metric_events[i]) {
-			const char *p = evsel->metric_expr;
-
-			if (expr__parse(&ratio, &pctx, &p) == 0)
-				print_metric(ctxp, NULL, "%8.1f",
-					evsel->metric_name ?
-					evsel->metric_name :
-					out->force_header ?  evsel->name : "",
-					ratio);
-			else
-				print_metric(ctxp, NULL, NULL, "", 0);
-		} else
-			print_metric(ctxp, NULL, NULL, "", 0);
+		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+				evsel->metric_name, avg, cpu, ctx, out);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];

index 96aa6cbf24d6..8c7ab29169b9 100644
@@ -662,7 +662,9 @@ static void generic_metric(const char *metric_expr,
 				out->force_header ?  name : "",
 				ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "", 0);
+			print_metric(ctxp, NULL, NULL,
+				     out->force_header ?
+				     (metric_name ? metric_name : name) : "", 0);
 	} else
 		print_metric(ctxp, NULL, NULL, "", 0);
 }

index ac16a9db1fb5..ed25d7f88731 100644
@@ -516,16 +516,8 @@ char * __weak get_cpuid_str(void)
 	return NULL;
 }
 
-/*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
- */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+static char *perf_pmu__getcpuid(void)
 {
-	int i;
-	struct pmu_events_map *map;
-	struct pmu_event *pe;
 	char *cpuid;
 	static bool printed;
 

@@ -535,22 +527,50 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 	if (!cpuid)
 		cpuid = get_cpuid_str();
 	if (!cpuid)
-		return;
+		return NULL;
 
 	if (!printed) {
 		pr_debug("Using CPUID %s\n", cpuid);
 		printed = true;
 	}
+	return cpuid;
+}
+
+struct pmu_events_map *perf_pmu__find_map(void)
+{
+	struct pmu_events_map *map;
+	char *cpuid = perf_pmu__getcpuid();
+	int i;
 
 	i = 0;
-	while (1) {
+	for (;;) {
 		map = &pmu_events_map[i++];
-		if (!map->table)
-			goto out;
+		if (!map->table) {
+			map = NULL;
+			break;
+		}
 
 		if (!strcmp(map->cpuid, cpuid))
 			break;
 	}
+	free(cpuid);
+	return map;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+{
+	int i;
+	struct pmu_events_map *map;
+	struct pmu_event *pe;
+
+	map = perf_pmu__find_map();
+	if (!map)
+		return;
 
 	/*
 	 * Found a matching PMU events table. Create aliases

@@ -575,9 +595,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 				(char *)pe->metric_expr,
 				(char *)pe->metric_name);
 	}
-
-out:
-	free(cpuid);
 }
 
 struct perf_event_attr * __weak

index 389e9729331f..060f6abba8ed 100644
@@ -90,4 +90,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
+struct pmu_events_map *perf_pmu__find_map(void);
+
 #endif /* __PMU_H */

index 7cc61eb0d83b..874bc6dd8d60 100644
@@ -65,6 +65,7 @@
 #include "util/tool.h"
 #include "util/group.h"
 #include "util/string2.h"
+#include "util/metricgroup.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>

@@ -133,6 +134,8 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist	*evsel_list;
 
+static struct rblist		 metric_events;
+
 static struct target target = {
 	.uid	= UINT_MAX,
 };

@@ -1234,7 +1237,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
-				&out);
+				&out, &metric_events);
 	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);

@@ -1565,7 +1568,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		os.evsel = counter;
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
-					      &out);
+					      &out,
+					      &metric_events);
 	}
 	fputc('\n', stat_config.output);
 }

@@ -1789,6 +1793,13 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int parse_metric_groups(const struct option *opt,
+			       const char *str,
+			       int unset __maybe_unused)
+{
+	return metricgroup__parse_groups(opt, str, &metric_events);
+}
+
 static const struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),

@@ -1854,6 +1865,9 @@ static const struct option stat_options[] = {
 			"measure topdown level 1 statistics"),
 	OPT_BOOLEAN(0, "smi-cost", &smi_cost,
 			"measure SMI cost"),
+	OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
+		     "monitor specified metrics or metric groups (separated by ,)",
+		     parse_metric_groups),
 	OPT_END()
 };
 

313 lines not on this page · raw message

new file mode 100644
index 000000000000..06854e125ee7
@@ -0,0 +1,31 @@
+#ifndef METRICGROUP_H
+#define METRICGROUP_H 1
+
+#include "linux/list.h"
+#include "rblist.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "strbuf.h"
+
+struct metric_event {
+	struct rb_node nd;
+	struct perf_evsel *evsel;
+	struct list_head head; /* list of metric_expr */
+};
+
+struct metric_expr {
+	struct list_head nd;
+	const char *metric_expr;
+	const char *metric_name;
+	struct perf_evsel **metric_events;
+};
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+					 struct perf_evsel *evsel,
+					 bool create);
+int metricgroup__parse_groups(const struct option *opt,
+			const char *str,
+			struct rblist *metric_events);
+
+void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+#endif

index ed25d7f88731..7070638ab600 100644
@@ -580,8 +580,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 		const char *pname;
 
 		pe = &map->table[i++];
-		if (!pe->name)
+		if (!pe->name) {
+			if (pe->metric_group || pe->metric_name)
+				continue;
 			break;
+		}
 
 		pname = pe->pmu ? pe->pmu : "cpu";
 		if (strncmp(pname, name, strlen(pname)))

index 8c7ab29169b9..42e6c17be7ff 100644
@@ -6,6 +6,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
+#include "metricgroup.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,

@@ -671,13 +672,16 @@ static void generic_metric(const char *metric_expr,
 
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out)
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events)
 {
 	void *ctxp = out->ctx;
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	const char *color = NULL;
 	int ctx = evsel_context(evsel);
+	struct metric_event *me;
+	int num = 1;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);

@@ -880,6 +884,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
 		print_smi_cost(cpu, evsel, out);
 	} else {
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		num = 0;
 	}
+
+	if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
+		struct metric_expr *mexp;
+
+		list_for_each_entry (mexp, &me->head, nd) {
+			if (num++ > 0)
+				out->new_line(ctxp);
+			generic_metric(mexp->metric_expr, mexp->metric_events,
+					evsel->name, mexp->metric_name,
+					avg, cpu, ctx, out);
+		}
+	}
+	if (num == 0)
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 }

index eacaf958e19d..47915df346fb 100644
@@ -91,9 +91,11 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
+struct rblist;
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out);
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);

index 4bf2cb4d25aa..b2d2ad3dd478 100644
@@ -15,6 +15,7 @@
 #include "util/cache.h"
 #include "util/pmu.h"
 #include "util/debug.h"
+#include "util/metricgroup.h"
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;

@@ -79,6 +80,10 @@ int cmd_list(int argc, const char **argv)
 						long_desc_flag, details_flag);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
+		else if (strcmp(argv[i], "metric") == 0)
+			metricgroup__print(true, false, NULL, raw_dump);
+		else if (strcmp(argv[i], "metricgroup") == 0)
+			metricgroup__print(false, true, NULL, raw_dump);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
 			int sep_idx;
 

@@ -96,6 +101,7 @@ int cmd_list(int argc, const char **argv)
 			s[sep_idx] = '\0';
 			print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
 			print_sdt_events(s, s + sep_idx + 1, raw_dump);
+			metricgroup__print(true, true, s, raw_dump);
 			free(s);
 		} else {
 			if (asprintf(&s, "*%s*", argv[i]) < 0) {

@@ -112,6 +118,7 @@ int cmd_list(int argc, const char **argv)
 						details_flag);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
+			metricgroup__print(true, true, NULL, raw_dump);
 			free(s);
 		}
 	}

182 lines not on this page · raw message

index 57d7acf890e0..75588920fccc 100644
@@ -28,6 +28,7 @@
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
+#include "metricgroup.h"
 
 #define MAX_NAME_LEN 100
 

@@ -2380,6 +2381,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 	print_tracepoint_events(NULL, NULL, name_only);
 
 	print_sdt_events(NULL, NULL, name_only);
+
+	metricgroup__print(true, true, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)

index 42e6c17be7ff..664f49a9b012 100644
@@ -56,7 +56,6 @@ struct saved_value {
 	struct rb_node rb_node;
 	struct perf_evsel *evsel;
 	int cpu;
-	int ctx;
 	struct stats stats;
 };
 

@@ -67,8 +66,6 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 					     rb_node);
 	const struct saved_value *b = entry;
 
-	if (a->ctx != b->ctx)
-		return a->ctx - b->ctx;
 	if (a->cpu != b->cpu)
 		return a->cpu - b->cpu;
 	if (a->evsel == b->evsel)

@@ -90,13 +87,12 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
 }
 
 static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
-					      int cpu, int ctx,
+					      int cpu,
 					      bool create)
 {
 	struct rb_node *nd;
 	struct saved_value dm = {
 		.cpu = cpu,
-		.ctx = ctx,
 		.evsel = evsel,
 	};
 	nd = rblist__find(&runtime_saved_values, &dm);

@@ -232,8 +228,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
 
 	if (counter->collect_stat) {
-		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
-							   true);
+		struct saved_value *v = saved_value_lookup(counter, cpu, true);
 		update_stats(&v->stats, count[0]);
 	}
 }

@@ -634,7 +629,6 @@ static void generic_metric(const char *metric_expr,
 			   const char *metric_name,
 			   double avg,
 			   int cpu,
-			   int ctx,
 			   struct perf_stat_output_ctx *out)
 {
 	print_metric_t print_metric = out->print_metric;

@@ -648,7 +642,7 @@ static void generic_metric(const char *metric_expr,
 	for (i = 0; metric_events[i]; i++) {
 		struct saved_value *v;
 
-		v = saved_value_lookup(metric_events[i], cpu, ctx, false);
+		v = saved_value_lookup(metric_events[i], cpu, false);
 		if (!v)
 			break;
 		expr__add_id(&pctx, metric_events[i]->name, avg_stats(&v->stats));

@@ -866,7 +860,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			print_metric(ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
 		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
-				evsel->metric_name, avg, cpu, ctx, out);
+				evsel->metric_name, avg, cpu, out);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];

@@ -895,7 +889,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				out->new_line(ctxp);
 			generic_metric(mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
-					avg, cpu, ctx, out);
+					avg, cpu, out);
 		}
 	}
 	if (num == 0)

index 664f49a9b012..a2c12d1ef32a 100644
@@ -641,11 +641,20 @@ static void generic_metric(const char *metric_expr,
 	expr__add_id(&pctx, name, avg);
 	for (i = 0; metric_events[i]; i++) {
 		struct saved_value *v;
+		struct stats *stats;
+		double scale;
 
-		v = saved_value_lookup(metric_events[i], cpu, false);
-		if (!v)
-			break;
-		expr__add_id(&pctx, metric_events[i]->name, avg_stats(&v->stats));
+		if (!strcmp(metric_events[i]->name, "duration_time")) {
+			stats = &walltime_nsecs_stats;
+			scale = 1e-9;
+		} else {
+			v = saved_value_lookup(metric_events[i], cpu, false);
+			if (!v)
+				break;
+			stats = &v->stats;
+			scale = 1.0;
+		}
+		expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
 	}
 	if (!metric_events[i]) {
 		const char *p = metric_expr;

index 874bc6dd8d60..855890e0b70b 100644
@@ -195,6 +195,11 @@ static struct perf_stat_config stat_config = {
 	.scale		= true,
 };
 
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "duration_time");
+}
+
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {

@@ -1363,6 +1368,9 @@ static void print_aggr(char *prefix)
 		ad.id = id = aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
+
 			ad.val = ad.ena = ad.run = 0;
 			ad.nr = 0;
 			if (!collect_data(counter, aggr_cb, &ad))

@@ -1506,6 +1514,8 @@ static void print_no_aggr_metric(char *prefix)
 		if (prefix)
 			fputs(prefix, stat_config.output);
 		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
 			if (first) {
 				aggr_printout(counter, cpu, 0);
 				first = false;

@@ -1560,6 +1570,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evsel_list, counter) {
+		if (is_duration_time(counter))
+			continue;
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;

@@ -1707,12 +1719,18 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		print_aggr(prefix);
 		break;
 	case AGGR_THREAD:
-		evlist__for_each_entry(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
 			print_aggr_thread(counter, prefix);
+		}
 		break;
 	case AGGR_GLOBAL:
-		evlist__for_each_entry(evsel_list, counter)
+		evlist__for_each_entry(evsel_list, counter) {
+			if (is_duration_time(counter))
+				continue;
 			print_counter_aggr(counter, prefix);
+		}
 		if (metric_only)
 			fputc('\n', stat_config.output);
 		break;

@@ -1720,8 +1738,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		if (metric_only)
 			print_no_aggr_metric(prefix);
 		else {
-			evlist__for_each_entry(evsel_list, counter)
+			evlist__for_each_entry(evsel_list, counter) {
+				if (is_duration_time(counter))
+					continue;
 				print_counter(counter, prefix);
+			}
 		}
 		break;
 	case AGGR_UNSET:

index 855890e0b70b..88f1d5fbdb48 100644
@@ -415,6 +415,8 @@ static void process_interval(void)
 			pr_err("failed to write stat round event\n");
 	}
 
+	init_stats(&walltime_nsecs_stats);
+	update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
 	print_counters(&rs, 0, NULL);
 }
 

index 56f8142ff97f..9b379f3a3d99 100644
@@ -1643,6 +1643,9 @@ static struct option __record_options[] = {
 	OPT_CALLBACK_OPTARG('I', "intr-regs", &record.opts.sample_intr_regs, NULL, "any register",
 		    "sample selected machine registers on interrupt,"
 		    " use -I ? to list register names", parse_regs),
+	OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
+		    "sample selected machine registers on interrupt,"
+		    " use -I ? to list register names", parse_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
 	OPT_CALLBACK('k', "clockid", &record.opts,

index dc442ba21bf6..fbb0a9cd0ac6 100644
@@ -65,6 +65,7 @@ struct record_opts {
 	unsigned int user_freq;
 	u64          branch_stack;
 	u64	     sample_intr_regs;
+	u64	     sample_user_regs;
 	u64	     default_interval;
 	u64	     user_interval;
 	size_t	     auxtrace_snapshot_size;

index 4bb89373eb52..7389746c0dc4 100644
@@ -678,7 +678,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 		if (!function) {
 			perf_evsel__set_sample_bit(evsel, REGS_USER);
 			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_regs_user |= PERF_REGS_MASK;
 			attr->sample_stack_user = param->dump_size;
 			attr->exclude_callchain_user = 1;
 		} else {

@@ -931,6 +931,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		perf_evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
+	if (opts->sample_user_regs) {
+		attr->sample_regs_user |= opts->sample_user_regs;
+		perf_evsel__set_sample_bit(evsel, REGS_USER);
+	}
+
 	if (target__has_cpu(&opts->target) || opts->sample_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 

index 3d4c3b5e1868..725dbd3dd104 100644
@@ -88,6 +88,7 @@ enum perf_output_field {
 	PERF_OUTPUT_BRSTACKOFF	    = 1U << 24,
 	PERF_OUTPUT_SYNTH           = 1U << 25,
 	PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
+	PERF_OUTPUT_UREGS	    = 1U << 27,
 };
 
 struct output_option {

@@ -109,6 +110,7 @@ struct output_option {
 	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 	{.str = "period", .field = PERF_OUTPUT_PERIOD},
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
+	{.str = "uregs", .field = PERF_OUTPUT_UREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},

@@ -385,6 +387,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_IREGS))
 		return -EINVAL;
 
+	if (PRINT_FIELD(UREGS) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS",
+					PERF_OUTPUT_UREGS))
+		return -EINVAL;
+
 	if (PRINT_FIELD(PHYS_ADDR) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
 					PERF_OUTPUT_PHYS_ADDR))

@@ -509,6 +516,24 @@ static void print_sample_iregs(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_uregs(struct perf_sample *sample,
+			  struct perf_event_attr *attr)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	uint64_t mask = attr->sample_regs_user;
+	unsigned i = 0, r;
+
+	if (!regs || !regs->regs)
+		return;
+
+	printf(" ABI:%" PRIu64 " ", regs->abi);
+
+	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+		u64 val = regs->regs[i++];
+		printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+	}
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)

@@ -1444,6 +1469,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(IREGS))
 		print_sample_iregs(sample, attr);
 
+	if (PRINT_FIELD(UREGS))
+		print_sample_uregs(sample, attr);
+
 	if (PRINT_FIELD(BRSTACK))
 		print_sample_brstack(sample, thread, attr);
 	else if (PRINT_FIELD(BRSTACKSYM))

@@ -2739,7 +2767,7 @@ int cmd_script(int argc, const char **argv)
 		     "+field to add and -field to remove."
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+		     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
 		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,

index ae91c8148edf..3e2b5d64c55e 100644
@@ -34,6 +34,8 @@ void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
 	p->total = total;
 	p->title = title;
 
+	if (ui_progress__ops->init)
+		ui_progress__ops->init(p);
 }
 
 void ui_progress__finish(void)

index 717d39d3052b..e5f434a2070b 100644
@@ -14,6 +14,7 @@ void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
 void ui_progress__update(struct ui_progress *p, u64 adv);
 
 struct ui_progress_ops {
+	void (*init)(struct ui_progress *p);
 	void (*update)(struct ui_progress *p);
 	void (*finish)(void);
 };

index c4b99008e2c9..f6b8f52aad7e 100644
@@ -5,6 +5,11 @@
 #include "tui.h"
 #include "../browser.h"
 
+static void __tui_progress__init(struct ui_progress *p)
+{
+	p->next = p->step = p->total / (SLtt_Screen_Cols - 2) ?: 1;
+}
+
 static void tui_progress__update(struct ui_progress *p)
 {
 	int bar, y;

@@ -49,8 +54,8 @@ static void tui_progress__finish(void)
 	pthread_mutex_unlock(&ui__lock);
 }
 
-static struct ui_progress_ops tui_progress__ops =
-{
+static struct ui_progress_ops tui_progress__ops = {
+	.init   = __tui_progress__init,
 	.update = tui_progress__update,
 	.finish = tui_progress__finish,
 };

index 3e2b5d64c55e..7ade387d511c 100644
@@ -27,12 +27,14 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
 	}
 }
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
+void __ui_progress__init(struct ui_progress *p, u64 total,
+			 const char *title, bool size)
 {
 	p->curr = 0;
 	p->next = p->step = total / 16 ?: 1;
 	p->total = total;
 	p->title = title;
+	p->size  = size;
 
 	if (ui_progress__ops->init)
 		ui_progress__ops->init(p);

index e5f434a2070b..fbaa1507ebfe 100644
@@ -8,9 +8,18 @@ void ui_progress__finish(void);
 struct ui_progress {
 	const char *title;
 	u64 curr, next, step, total;
+	bool size;
 };
 
-void ui_progress__init(struct ui_progress *p, u64 total, const char *title);
+void __ui_progress__init(struct ui_progress *p, u64 total,
+			 const char *title, bool size);
+
+#define ui_progress__init(p, total, title) \
+	__ui_progress__init(p, total, title, false)
+
+#define ui_progress__init_size(p, total, title) \
+	__ui_progress__init(p, total, title, true)
+
 void ui_progress__update(struct ui_progress *p, u64 adv);
 
 struct ui_progress_ops {

index f6b8f52aad7e..68f6144ea603 100644
@@ -1,8 +1,10 @@
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
 #include "tui.h"
+#include "units.h"
 #include "../browser.h"
 
 static void __tui_progress__init(struct ui_progress *p)

@@ -10,8 +12,22 @@ static void __tui_progress__init(struct ui_progress *p)
 	p->next = p->step = p->total / (SLtt_Screen_Cols - 2) ?: 1;
 }
 
+static int get_title(struct ui_progress *p, char *buf, size_t size)
+{
+	char buf_cur[20];
+	char buf_tot[20];
+	int ret;
+
+	ret  = unit_number__scnprintf(buf_cur, sizeof(buf_cur), p->curr);
+	ret += unit_number__scnprintf(buf_tot, sizeof(buf_tot), p->total);
+
+	return ret + scnprintf(buf, size, "%s [%s/%s]",
+			       p->title, buf_cur, buf_tot);
+}
+
 static void tui_progress__update(struct ui_progress *p)
 {
+	char buf[100], *title = (char *) p->title;
 	int bar, y;
 	/*
 	 * FIXME: We should have a per UI backend way of showing progress,

@@ -23,13 +39,18 @@ static void tui_progress__update(struct ui_progress *p)
 	if (p->total == 0)
 		return;
 
+	if (p->size) {
+		get_title(p, buf, sizeof(buf));
+		title = buf;
+	}
+
 	ui__refresh_dimensions(false);
 	pthread_mutex_lock(&ui__lock);
 	y = SLtt_Screen_Rows / 2 - 2;
 	SLsmg_set_color(0);
 	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
 	SLsmg_gotorc(y++, 1);
-	SLsmg_write_string((char *)p->title);
+	SLsmg_write_string(title);
 	SLsmg_fill_region(y, 1, 1, SLtt_Screen_Cols - 2, ' ');
 	SLsmg_set_color(HE_COLORSET_SELECTED);
 	bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;

index a7ebd9fe8e40..ceac0848469d 100644
@@ -1847,7 +1847,7 @@ static int __perf_session__process_events(struct perf_session *session,
 	if (data_offset + data_size < file_size)
 		file_size = data_offset + data_size;
 
-	ui_progress__init(&prog, file_size, "Processing events...");
+	ui_progress__init_size(&prog, file_size, "Processing events...");
 
 	mmap_size = MMAP_SIZE;
 	if (mmap_size > file_size) {

index 1c905ba3641b..17c21ea68a72 100644
@@ -683,12 +683,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 				   bool mmap_data,
 				   unsigned int proc_map_timeout)
 {
-	DIR *proc;
-	char proc_path[PATH_MAX];
-	struct dirent *dirent;
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	union perf_event *namespaces_event;
+	char proc_path[PATH_MAX];
+	struct dirent **dirent;
 	int err = -1;
+	char *end;
+	pid_t pid;
+	int n, i;
 
 	if (machine__is_default_guest(machine))
 		return 0;

@@ -712,29 +714,32 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 		goto out_free_fork;
 
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	proc = opendir(proc_path);
+	n = scandir(proc_path, &dirent, 0, alphasort);
 
-	if (proc == NULL)
+	if (n < 0)
 		goto out_free_namespaces;
 
-	while ((dirent = readdir(proc)) != NULL) {
-		char *end;
-		pid_t pid = strtol(dirent->d_name, &end, 10);
-
-		if (*end) /* only interested in proper numerical dirents */
+	for (i = 0; i < n; i++) {
+		if (!isdigit(dirent[i]->d_name[0]))
 			continue;
-		/*
- 		 * We may race with exiting thread, so don't stop just because
- 		 * one thread couldn't be synthesized.
- 		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event,
-					   namespaces_event, pid, 1, process,
-					   tool, machine, mmap_data,
-					   proc_map_timeout);
-	}
 
+		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+		/* only interested in proper numerical dirents */
+		if (!*end) {
+			/*
+			 * We may race with exiting thread, so don't stop just because
+			 * one thread couldn't be synthesized.
+			 */
+			__event__synthesize_thread(comm_event, mmap_event, fork_event,
+						   namespaces_event, pid, 1, process,
+						   tool, machine, mmap_data,
+						   proc_map_timeout);
+		}
+		free(dirent[i]);
+	}
+	free(dirent);
 	err = 0;
-	closedir(proc);
+
 out_free_namespaces:
 	free(namespaces_event);
 out_free_fork:

index a1d82e33282c..b89417d9305e 100644
@@ -34,8 +34,7 @@ static struct option config_options[] = {
 	OPT_END()
 };
 
-static int set_config(struct perf_config_set *set, const char *file_name,
-		      const char *var, const char *value)
+static int set_config(struct perf_config_set *set, const char *file_name)
 {
 	struct perf_config_section *section = NULL;
 	struct perf_config_item *item = NULL;

@@ -49,7 +48,6 @@ static int set_config(struct perf_config_set *set, const char *file_name,
 	if (!fp)
 		return -1;
 
-	perf_config_set__collect(set, file_name, var, value);
 	fprintf(fp, "%s\n", first_line);
 
 	/* overwrite configvariables */

@@ -161,6 +159,7 @@ int cmd_config(int argc, const char **argv)
 	struct perf_config_set *set;
 	char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
 	const char *config_filename;
+	bool changed = false;
 
 	argc = parse_options(argc, argv, config_options, config_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);

@@ -231,15 +230,26 @@ int cmd_config(int argc, const char **argv)
 					goto out_err;
 				}
 			} else {
-				if (set_config(set, config_filename, var, value) < 0) {
-					pr_err("Failed to set '%s=%s' on %s\n",
-					       var, value, config_filename);
+				if (perf_config_set__collect(set, config_filename,
+							     var, value) < 0) {
+					pr_err("Failed to add '%s=%s'\n",
+					       var, value);
 					free(arg);
 					goto out_err;
 				}
+				changed = true;
 			}
 			free(arg);
 		}
+
+		if (!changed)
+			break;
+
+		if (set_config(set, config_filename) < 0) {
+			pr_err("Failed to set the configs on %s\n",
+			       config_filename);
+			goto out_err;
+		}
 	}
 
 	ret = 0;

index bc75596f9e79..d2b6983b1779 100644
@@ -700,10 +700,7 @@ struct perf_config_set *perf_config_set__new(void)
 
 	if (set) {
 		INIT_LIST_HEAD(&set->sections);
-		if (perf_config_set__init(set) < 0) {
-			perf_config_set__delete(set);
-			set = NULL;
-		}
+		perf_config_set__init(set);
 	}
 
 	return set;