Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

 - Make 'perf record' collect CPU cache info in the perf.data file header:

  $ perf record usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.017 MB perf.data (7 samples) ]
  $ perf report --header-only -I | tail -10 | head -8
  # CPU cache info:
  #  L1 Data                 32K [0-1]
  #  L1 Instruction          32K [0-1]
  #  L1 Data                 32K [2-3]
  #  L1 Instruction          32K [2-3]
  #  L2 Unified             256K [0-1]
  #  L2 Unified             256K [2-3]
  #  L3 Unified            4096K [0-3]
  $

  Will be used in 'perf c2c' and eventually in 'perf diff' to allow, for instance
  running the same workload in multiple machines and then when using 'diff' show
  the hardware difference. (Jiri Olsa)

 - 'perf stat' now shows shadow metrics (insn per cycle, etc) in
   interval mode too. E.g:

    # perf stat -I 1000 -e instructions,cycles sleep 1
    #         time   counts unit events
       1.000215928  519,620      instructions     #  0.69 insn per cycle
       1.000215928  752,003      cycles
    <SNIP>

Infrastructure changes:

 - libapi now can also use pr_{warning,info,debug}() and that can be
   set by tools using it (Jiri Olsa)

 - libapi adopts filename__read_str() from perf, adds sysfs__read_str() (Jiri Olsa)

 - Add check for java alternatives cmd in jvmti Makefile, so that it manages
   to automatically find the right path for the JDK devel files in Ubuntu like
   systems in addition to Fedora like ones (Stephane Eranian)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 694 insertions, 255 deletions

diff --git a/tools/lib/api/Build b/tools/lib/api/Build
index e8b8a23b9bf4..954c644f7ad9 100644
--- a/tools/lib/api/Build
+++ b/tools/lib/api/Build
@@ -1,3 +1,4 @@
 libapi-y += fd/
 libapi-y += fs/
 libapi-y += cpu.o
+libapi-y += debug.o
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index d85904dc9b38..bbc82c614bee 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -18,6 +18,7 @@ LIBFILE = $(OUTPUT)libapi.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+CFLAGS += -I$(srctree)/tools/lib/api
 
 RM = rm -f
 
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
new file mode 100644
index 000000000000..188f7880eafe
--- /dev/null
+++ b/tools/lib/api/debug-internal.h
@@ -0,0 +1,20 @@
+#ifndef __API_DEBUG_INTERNAL_H__
+#define __API_DEBUG_INTERNAL_H__
+
+#include "debug.h"
+
+#define __pr(func, fmt, ...)	\
+do {				\
+	if ((func))		\
+		(func)("libapi: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+extern libapi_print_fn_t __pr_warning;
+extern libapi_print_fn_t __pr_info;
+extern libapi_print_fn_t __pr_debug;
+
+#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
+
+#endif /* __API_DEBUG_INTERNAL_H__ */
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
new file mode 100644
index 000000000000..5fa5cf500a1f
--- /dev/null
+++ b/tools/lib/api/debug.c
@@ -0,0 +1,28 @@
+#include <stdio.h>
+#include <stdarg.h>
+#include "debug.h"
+#include "debug-internal.h"
+
+static int __base_pr(const char *format, ...)
+{
+	va_list args;
+	int err;
+
+	va_start(args, format);
+	err = vfprintf(stderr, format, args);
+	va_end(args);
+	return err;
+}
+
+libapi_print_fn_t __pr_warning = __base_pr;
+libapi_print_fn_t __pr_info    = __base_pr;
+libapi_print_fn_t __pr_debug;
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug)
+{
+	__pr_warning = warn;
+	__pr_info    = info;
+	__pr_debug   = debug;
+}
diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h
new file mode 100644
index 000000000000..a0872f68fc56
--- /dev/null
+++ b/tools/lib/api/debug.h
@@ -0,0 +1,10 @@
+#ifndef __API_DEBUG_H__
+#define __API_DEBUG_H__
+
+typedef int (*libapi_print_fn_t)(const char *, ...);
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug);
+
+#endif /* __API_DEBUG_H__ */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 459599d1b6c4..ef78c22ff44d 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -13,6 +13,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "debug-internal.h"
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -300,6 +301,56 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return err;
 }
 
+#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	size_t size = 0, alloc_size = 0;
+	void *bf = NULL, *nbf;
+	int fd, n, err = 0;
+	char sbuf[STRERR_BUFSIZE];
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (!nbf) {
+				err = -ENOMEM;
+				break;
+			}
+
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, alloc_size - size);
+		if (n < 0) {
+			if (size) {
+				pr_warning("read failed %d: %s\n", errno,
+					 strerror_r(errno, sbuf, sizeof(sbuf)));
+				err = 0;
+			} else
+				err = -errno;
+
+			break;
+		}
+
+		size += n;
+	} while (n > 0);
+
+	if (!err) {
+		*sizep = size;
+		*buf   = bf;
+	} else
+		free(bf);
+
+	close(fd);
+	return err;
+}
+
 int sysfs__read_ull(const char *entry, unsigned long long *value)
 {
 	char path[PATH_MAX];
@@ -326,6 +377,19 @@ int sysfs__read_int(const char *entry, int *value)
 	return filename__read_int(path, value);
 }
 
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+	return filename__read_str(path, buf, sizep);
+}
+
 int sysctl__read_int(const char *sysctl, int *value)
 {
 	char path[PATH_MAX];
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index d024a7f682f6..9f6598098dc5 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -2,6 +2,7 @@
 #define __API_FS__
 
 #include <stdbool.h>
+#include <unistd.h>
 
 /*
  * On most systems <limits.h> would have given us this, but  not on some systems
@@ -26,8 +27,10 @@ FS(tracefs)
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
 
 int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
 #endif /* __API_FS__ */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 038e877081b6..15e4fcf34e0c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -735,6 +735,60 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	if (stat_config.aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	if (stat_config.aggr_mode == AGGR_CORE)
+		fprintf(os->fh, "                  ");
+	if (stat_config.aggr_mode == AGGR_SOCKET)
+		fprintf(os->fh, "            ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -793,22 +847,60 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise)
 {
-	int cpu = cpu_map__id_to_cpu(id);
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = stat_config.output,
+		.prefix = prefix ? prefix : ""
+	};
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
+
+	nl = new_line_std;
+
+	if (run == 0 || ena == 0) {
+		aggr_printout(counter, id, nr);
+
+		fprintf(stat_config.output, "%*s%s",
+			csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			csv_sep);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
+		fprintf(stat_config.output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+
+		fprintf(stat_config.output, "%*s",
+			csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(stat_config.output, "%s%s",
+				csv_sep, counter->cgrp->name);
+
+		print_running(run, ena);
+		return;
+	}
 
 	if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
 
-	if (!csv_output && !stat_config.interval)
-		perf_stat__print_shadow_stats(stat_config.output, counter,
-					      uval, cpu,
-					      stat_config.aggr_mode);
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+
+	if (!csv_output)
+		perf_stat__print_shadow_stats(counter, uval,
+				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+				cpu_map__id_to_cpu(id),
+				&out);
+
+	print_noise(counter, noise);
+	print_running(run, ena);
 }
 
 static void print_aggr(char *prefix)
@@ -839,36 +931,8 @@ static void print_aggr(char *prefix)
 			if (prefix)
 				fprintf(output, "%s", prefix);
 
-			if (run == 0 || ena == 0) {
-				aggr_printout(counter, id, nr);
-
-				fprintf(output, "%*s%s",
-					csv_output ? 0 : 18,
-					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-					csv_sep);
-
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
-
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
-
-				if (counter->cgrp)
-					fprintf(output, "%s%s",
-						csv_sep, counter->cgrp->name);
-
-				print_running(run, ena);
-				fputc('\n', output);
-				continue;
-			}
 			uval = val * counter->scale;
-			printout(id, nr, counter, uval);
-			if (!csv_output)
-				print_noise(counter, 1.0);
-
-			print_running(run, ena);
+			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
 			fputc('\n', output);
 		}
 	}
@@ -895,12 +959,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval);
-
-		if (!csv_output)
-			print_noise(counter, 1.0);
-
-		print_running(run, ena);
+		printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
 		fputc('\n', output);
 	}
 }
@@ -914,7 +973,6 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	FILE *output = stat_config.output;
 	struct perf_stat_evsel *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
-	int scaled = counter->counts->scaled;
 	double uval;
 	double avg_enabled, avg_running;
 
@@ -924,32 +982,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	if (prefix)
 		fprintf(output, "%s", prefix);
 
-	if (scaled == -1 || !counter->supported) {
-		fprintf(output, "%*s%s",
-			csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
-		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
-		fprintf(output, "%*s",
-			csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
-		print_running(avg_running, avg_enabled);
-		fputc('\n', output);
-		return;
-	}
-
 	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval);
-
-	print_noise(counter, avg);
-
-	print_running(avg_running, avg_enabled);
+	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
 	fprintf(output, "\n");
 }
 
@@ -972,36 +1006,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		if (prefix)
 			fprintf(output, "%s", prefix);
 
-		if (run == 0 || ena == 0) {
-			fprintf(output, "CPU%*d%s%*s%s",
-				csv_output ? 0 : -4,
-				perf_evsel__cpus(counter)->map[cpu], csv_sep,
-				csv_output ? 0 : 18,
-				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-				csv_sep);
-
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
-
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
-
-			if (counter->cgrp)
-				fprintf(output, "%s%s",
-					csv_sep, counter->cgrp->name);
-
-			print_running(run, ena);
-			fputc('\n', output);
-			continue;
-		}
-
 		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval);
-		if (!csv_output)
-			print_noise(counter, 1.0);
-		print_running(run, ena);
+		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 
 		fputc('\n', output);
 	}
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
index 5968f8332a28..0277a64b391b 100644
--- a/tools/perf/jvmti/Makefile
+++ b/tools/perf/jvmti/Makefile
@@ -35,8 +35,12 @@ SOLIBEXT=so
 
 # The following works at least on fedora 23, you may need the next
 # line for other distros.
+ifeq (,$(wildcard /usr/sbin/update-java-alternatives))
 JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
-#JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+else
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+endif
+
 # -lrt required in 32-bit mode for clock_gettime()
 LIBS=-lelf -lrt
 INCDIR=-I $(JDIR)/include -I $(JDIR)/include/linux
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index a929618b8eb6..144047c396f0 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -613,6 +613,8 @@ int main(int argc, const char **argv)
 	 */
 	pthread__block_sigwinch();
 
+	perf_debug_setup();
+
 	while (1) {
 		static int done_help;
 		int was_alias = run_argv(&argc, &argv);
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 86d9c7302598..ff7e86ad1b06 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <api/debug.h>
 
 #include "cache.h"
 #include "color.h"
@@ -22,7 +23,7 @@ int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
 
-static int _eprintf(int level, int var, const char *fmt, va_list args)
+int veprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
@@ -36,24 +37,19 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)
 	return ret;
 }
 
-int veprintf(int level, int var, const char *fmt, va_list args)
-{
-	return _eprintf(level, var, fmt, args);
-}
-
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret;
 
 	va_start(args, fmt);
-	ret = _eprintf(level, var, fmt, args);
+	ret = veprintf(level, var, fmt, args);
 	va_end(args);
 
 	return ret;
 }
 
-static int __eprintf_time(u64 t, const char *fmt, va_list args)
+static int veprintf_time(u64 t, const char *fmt, va_list args)
 {
 	int ret = 0;
 	u64 secs, usecs, nsecs = t;
@@ -75,7 +71,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
 
 	if (var >= level) {
 		va_start(args, fmt);
-		ret = __eprintf_time(t, fmt, args);
+		ret = veprintf_time(t, fmt, args);
 		va_end(args);
 	}
 
@@ -91,7 +87,7 @@ void pr_stat(const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	_eprintf(1, verbose, fmt, args);
+	veprintf(1, verbose, fmt, args);
 	va_end(args);
 	eprintf(1, verbose, "\n");
 }
@@ -192,3 +188,23 @@ int perf_debug_option(const char *str)
 	free(s);
 	return 0;
 }
+
+#define DEBUG_WRAPPER(__n, __l)				\
+static int pr_ ## __n ## _wrapper(const char *fmt, ...)	\
+{							\
+	va_list args;					\
+	int ret;					\
+							\
+	va_start(args, fmt);				\
+	ret = veprintf(__l, verbose, fmt, args);	\
+	va_end(args);					\
+	return ret;					\
+}
+
+DEBUG_WRAPPER(warning, 0);
+DEBUG_WRAPPER(debug, 1);
+
+void perf_debug_setup(void)
+{
+	libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8b9a088c32ab..14bafda79eda 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -53,5 +53,6 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__(
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+void perf_debug_setup(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 7dd5939dea2e..49a11d9d8b8f 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -6,6 +6,8 @@ struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env)
 {
+	int i;
+
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);
@@ -19,6 +21,10 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->numa_nodes);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
+
+	for (i = 0; i < env->caches_cnt; i++)
+		cpu_cache_level__free(&env->caches[i]);
+	zfree(&env->caches);
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
@@ -75,3 +81,10 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	env->nr_cpus_avail = nr_cpus;
 	return 0;
 }
+
+void cpu_cache_level__free(struct cpu_cache_level *cache)
+{
+	free(cache->type);
+	free(cache->map);
+	free(cache->size);
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 0132b9557c02..56cffb60a0b4 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -1,11 +1,23 @@
 #ifndef __PERF_ENV_H
 #define __PERF_ENV_H
 
+#include <linux/types.h>
+
 struct cpu_topology_map {
 	int	socket_id;
 	int	core_id;
 };
 
+struct cpu_cache_level {
+	u32	level;
+	u32	line_size;
+	u32	sets;
+	u32	ways;
+	char	*type;
+	char	*size;
+	char	*map;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -31,6 +43,8 @@ struct perf_env {
 	char			*numa_nodes;
 	char			*pmu_mappings;
 	struct cpu_topology_map	*cpu;
+	struct cpu_cache_level	*caches;
+	int			 caches_cnt;
 };
 
 extern struct perf_env perf_env;
@@ -41,4 +55,5 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
+void cpu_cache_level__free(struct cpu_cache_level *cache);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f50b7235ecb6..73e38e472ecd 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -23,6 +23,8 @@
 #include "strbuf.h"
 #include "build-id.h"
 #include "data.h"
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 
 /*
  * magic2 = "PERFILE2"
@@ -868,6 +870,199 @@ static int write_auxtrace(int fd, struct perf_header *h,
 	return err;
 }
 
+static int cpu_cache_level__sort(const void *a, const void *b)
+{
+	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
+	struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b;
+
+	return cache_a->level - cache_b->level;
+}
+
+static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b)
+{
+	if (a->level != b->level)
+		return false;
+
+	if (a->line_size != b->line_size)
+		return false;
+
+	if (a->sets != b->sets)
+		return false;
+
+	if (a->ways != b->ways)
+		return false;
+
+	if (strcmp(a->type, b->type))
+		return false;
+
+	if (strcmp(a->size, b->size))
+		return false;
+
+	if (strcmp(a->map, b->map))
+		return false;
+
+	return true;
+}
+
+static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level)
+{
+	char path[PATH_MAX], file[PATH_MAX];
+	struct stat st;
+	size_t len;
+
+	scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level);
+	scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path);
+
+	if (stat(file, &st))
+		return 1;
+
+	scnprintf(file, PATH_MAX, "%s/level", path);
+	if (sysfs__read_int(file, (int *) &cache->level))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/coherency_line_size", path);
+	if (sysfs__read_int(file, (int *) &cache->line_size))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/number_of_sets", path);
+	if (sysfs__read_int(file, (int *) &cache->sets))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path);
+	if (sysfs__read_int(file, (int *) &cache->ways))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/type", path);
+	if (sysfs__read_str(file, &cache->type, &len))
+		return -1;
+
+	cache->type[len] = 0;
+	cache->type = rtrim(cache->type);
+
+	scnprintf(file, PATH_MAX, "%s/size", path);
+	if (sysfs__read_str(file, &cache->size, &len)) {
+		free(cache->type);
+		return -1;
+	}
+
+	cache->size[len] = 0;
+	cache->size = rtrim(cache->size);
+
+	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
+	if (sysfs__read_str(file, &cache->map, &len)) {
+		free(cache->map);
+		free(cache->type);
+		return -1;
+	}
+
+	cache->map[len] = 0;
+	cache->map = rtrim(cache->map);
+	return 0;
+}
+
+static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
+{
+	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+{
+	u32 i, cnt = 0;
+	long ncpus;
+	u32 nr, cpu;
+	u16 level;
+
+	ncpus = sysconf(_SC_NPROCESSORS_CONF);
+	if (ncpus < 0)
+		return -1;
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		for (level = 0; level < 10; level++) {
+			struct cpu_cache_level c;
+			int err;
+
+			err = cpu_cache_level__read(&c, cpu, level);
+			if (err < 0)
+				return err;
+
+			if (err == 1)
+				break;
+
+			for (i = 0; i < cnt; i++) {
+				if (cpu_cache_level__cmp(&c, &caches[i]))
+					break;
+			}
+
+			if (i == cnt)
+				caches[cnt++] = c;
+			else
+				cpu_cache_level__free(&c);
+
+			if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
+				goto out;
+		}
+	}
+ out:
+	*cntp = cnt;
+	return 0;
+}
+
+#define MAX_CACHES 2000
+
+static int write_cache(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct cpu_cache_level caches[MAX_CACHES];
+	u32 cnt = 0, i, version = 1;
+	int ret;
+
+	ret = build_caches(caches, MAX_CACHES, &cnt);
+	if (ret)
+		goto out;
+
+	qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
+
+	ret = do_write(fd, &version, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(fd, &cnt, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level *c = &caches[i];
+
+		#define _W(v)					\
+			ret = do_write(fd, &c->v, sizeof(u32));	\
+			if (ret < 0)				\
+				goto out;
+
+		_W(level)
+		_W(line_size)
+		_W(sets)
+		_W(ways)
+		#undef _W
+
+		#define _W(v)						\
+			ret = do_write_string(fd, (const char *) c->v);	\
+			if (ret < 0)					\
+				goto out;
+
+		_W(type)
+		_W(size)
+		_W(map)
+		#undef _W
+	}
+
+out:
+	for (i = 0; i < cnt; i++)
+		cpu_cache_level__free(&caches[i]);
+	return ret;
+}
+
 static int write_stat(int fd __maybe_unused,
 		      struct perf_header *h __maybe_unused,
 		      struct perf_evlist *evlist __maybe_unused)
@@ -1172,6 +1367,18 @@ static void print_stat(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains stat data\n");
 }
 
+static void print_cache(struct perf_header *ph __maybe_unused,
+			int fd __maybe_unused, FILE *fp __maybe_unused)
+{
+	int i;
+
+	fprintf(fp, "# CPU cache info:\n");
+	for (i = 0; i < ph->env.caches_cnt; i++) {
+		fprintf(fp, "#  ");
+		cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+	}
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1920,6 +2127,68 @@ static int process_auxtrace(struct perf_file_section *section,
 	return err;
 }
 
+static int process_cache(struct perf_file_section *section __maybe_unused,
+			 struct perf_header *ph __maybe_unused, int fd __maybe_unused,
+			 void *data __maybe_unused)
+{
+	struct cpu_cache_level *caches;
+	u32 cnt, i, version;
+
+	if (readn(fd, &version, sizeof(version)) != sizeof(version))
+		return -1;
+
+	if (ph->needs_swap)
+		version = bswap_32(version);
+
+	if (version != 1)
+		return -1;
+
+	if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+		return -1;
+
+	if (ph->needs_swap)
+		cnt = bswap_32(cnt);
+
+	caches = zalloc(sizeof(*caches) * cnt);
+	if (!caches)
+		return -1;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level c;
+
+		#define _R(v)						\
+			if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+				goto out_free_caches;			\
+			if (ph->needs_swap)				\
+				c.v = bswap_32(c.v);			\
+
+		_R(level)
+		_R(line_size)
+		_R(sets)
+		_R(ways)
+		#undef _R
+
+		#define _R(v)				\
+			c.v = do_read_string(fd, ph);	\
+			if (!c.v)			\
+				goto out_free_caches;
+
+		_R(type)
+		_R(size)
+		_R(map)
+		#undef _R
+
+		caches[i] = c;
+	}
+
+	ph->env.caches = caches;
+	ph->env.caches_cnt = cnt;
+	return 0;
+out_free_caches:
+	free(caches);
+	return -1;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1962,6 +2231,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 	FEAT_OPA(HEADER_STAT,		stat),
+	FEAT_OPF(HEADER_CACHE,		cache),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index cff9892452ee..3d87ca823c0a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -32,6 +32,7 @@ enum {
 	HEADER_GROUP_DESC,
 	HEADER_AUXTRACE,
 	HEADER_STAT,
+	HEADER_CACHE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac03146889d..4d8f18581b9b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+					  __maybe_unused, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +153,17 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	if (ratio)
+		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+				  ratio);
+	else
+		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
 					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+					 __maybe_unused, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +176,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
 				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +195,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +214,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +232,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +250,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +268,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
 				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +286,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,119 +302,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
+		out->new_line(ctxp);
 		if (total && avg) {
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
 		else
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +450,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 2af63c9cb59f..f02af68adc04 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 802bb868d446..8ae051e0ec79 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
+#include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index b9e2843cfbe7..35b20dd454de 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -507,54 +507,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 	return ret;
 }
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep)
-{
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warning("read failed %d: %s\n", errno,
-					 strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
-	} else
-		free(bf);
-
-	close(fd);
-	return err;
-}
-
 const char *get_filename_for_perf_kvm(void)
 {
 	const char *filename;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index a8615816a00d..3dd04089e8be 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -303,7 +303,6 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
 void mem_bswap_64(void *src, int byte_size);