[PATCH 0/5] Freq/CPU%/CORE_BUSY% support

[PATCH 0/5] Freq/CPU%/CORE_BUSY% support

[kan.liang]

From: Kan Liang <kan.liang@intel.com>

(Re-send. Missed "From: Kan Liang <kan.liang@intel.com>" in last mail)
This patch set supports per-sample freq/CPU%/CORE_BUSY% print in perf
report -D and --stdio.
For printing these information, the perf.data file must have been obtained
by group read and using special events cycles, ref-cycles, msr/tsc/,
msr/aperf/ or msr/mperf/.

 - Freq (MHz): The frequency during the sample interval. Needs cycles
   ref-cycles event.
 - CPU%: CPU utilization during the sample interval. Needs ref-cycles and
   msr/tsc/ events.
 - CORE_BUSY%: actual percent performance (APERF/MPERF%) during the
   sample interval. Needs msr/aperf/ and msr/mperf/ events.

For printing CPU% and CORE_BUSY%, please also apply the kernel patch.
http://marc.info/?l=linux-kernel&m=143747254926369&w=2

Here is an example:

$ perf record -e
'{cycles,ref-cycles,msr/tsc/,msr/mperf/,msr/aperf/}:S' ~/tchain_edit

$ perf report --stdio --group --show-freq-perf

                                 Overhead   FREQ MHz   CPU%  CORE_BUSY%
Command      Shared Object     Symbol
 ........................................  .........  .....  ..........
...........  ................  ......................

    99.54%  99.54%  99.53%  99.53%  99.53%       2301     96         99
tchain_edit  tchain_edit       [.] f3
     0.20%   0.20%   0.20%   0.20%   0.20%       2301     98         99
tchain_edit  tchain_edit       [.] f2
     0.05%   0.05%   0.05%   0.05%   0.05%       2300     98         99
tchain_edit  [kernel.vmlinux]  [k] read_tsc

Kan Liang (5):
  perf,tools: introduce get_cpu_max_freq
  perf,tools: Dump per-sample freq/CPU%/CORE_BUSY% in report -D
  perf,tools: save misc sample read value in struct perf_sample
  perf,tools: caculate and save freq/CPU%/CORE_BUSY% in he_stat
  perf,tools: Show freq/CPU%/CORE_BUSY% in perf report --stdio

 tools/perf/Documentation/perf-report.txt | 12 ++++++
 tools/perf/builtin-annotate.c            |  2 +-
 tools/perf/builtin-diff.c                |  2 +-
 tools/perf/builtin-report.c              | 24 +++++++++++
 tools/perf/perf.h                        |  1 +
 tools/perf/tests/hists_link.c            |  4 +-
 tools/perf/ui/hist.c                     | 71 +++++++++++++++++++++++++++++---
 tools/perf/util/cpumap.c                 | 32 ++++++++++++++
 tools/perf/util/cpumap.h                 |  2 +
 tools/perf/util/event.h                  | 11 +++++
 tools/perf/util/hist.c                   | 51 ++++++++++++++++++++---
 tools/perf/util/hist.h                   |  5 +++
 tools/perf/util/pmu.h                    |  2 +
 tools/perf/util/session.c                | 50 +++++++++++++++++++---
 tools/perf/util/session.h                | 28 +++++++++++++
 tools/perf/util/sort.c                   |  3 ++
 tools/perf/util/sort.h                   |  3 ++
 tools/perf/util/symbol.h                 |  9 +++-
 tools/perf/util/util.c                   |  2 +
 19 files changed, 293 insertions(+), 21 deletions(-)

-- 
1.8.3.1

[PATCH 1/5] perf,tools: introduce get_cpu_max_freq

[kan.liang]

From: Kan Liang <kan.liang@intel.com>

Get cpu max frequency from the first online cpu, and save the MHz value
in get_cpu_max_freq.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/builtin-report.c |  2 ++
 tools/perf/util/cpumap.c    | 32 ++++++++++++++++++++++++++++++++
 tools/perf/util/cpumap.h    |  2 ++
 3 files changed, 36 insertions(+)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 95a4771..62cce98 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -818,6 +818,8 @@ repeat:
 		symbol_conf.cumulate_callchain = false;
 	}
 
+	cpu_max_freq = get_cpu_max_freq() / 1000;
+
 	if (setup_sorting() < 0) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3667e21..548ef13 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -499,3 +499,35 @@ int cpu__setup_cpunode_map(void)
 	closedir(dir1);
 	return 0;
 }
+
+unsigned int get_cpu_max_freq(void)
+{
+	const char *mnt;
+	char path[PATH_MAX], tmp;
+	FILE *fp;
+	unsigned int freq;
+	int cpu = 0;
+	int ret;
+
+	mnt = sysfs__mountpoint();
+	if (!mnt)
+		return 0;
+
+	snprintf(path, PATH_MAX, "%s/devices/system/cpu/online", mnt);
+	fp = fopen(path, "r");
+	if (fp) {
+		ret = fscanf(fp, "%u%c", &cpu, &tmp);
+		fclose(fp);
+		if (ret < 1)
+			return 0;
+	}
+
+	snprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d/cpufreq/cpuinfo_max_freq", mnt, cpu);
+	fp = fopen(path, "r");
+	if (!fp)
+		return 0;
+	ret = fscanf(fp, "%u", &freq);
+	fclose(fp);
+
+	return (ret == 1) ? freq : 0;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 0af9cec..70ac686 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -56,8 +56,10 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
 int max_cpu_num;
 int max_node_num;
 int *cpunode_map;
+unsigned int cpu_max_freq;
 
 int cpu__setup_cpunode_map(void);
+unsigned int get_cpu_max_freq(void);
 
 static inline int cpu__max_node(void)
 {
-- 
1.8.3.1

[PATCH 2/5] perf,tools: Dump per-sample freq/CPU%/CORE_BUSY% in report -D

[kan.liang]

From: Kan Liang <kan.liang@intel.com>

The group read results from cycles/ref-cycles/TSC/ASTATE/MSTATE event
can be used to calculate the frequency, CPU Utilization and percent
performance during each sampling period.
This patch shows them in report -D.

Here is an example:

$ perf record -e
'{cycles,ref-cycles,msr/tsc/,msr/mperf/,msr/aperf/}:S' ~/tchain_edit

Here is one sample from perf report -D

1972044565107 0x3498 [0x88]: PERF_RECORD_SAMPLE(IP, 0x2): 10608/10608:
0x4005fd period: 564686 addr: 0
... sample_read:
.... group nr 5
..... id 0000000000000012, value 0000000002143901
..... id 0000000000000052, value 0000000002143896
..... id 0000000000000094, value 00000000021e443d
..... id 00000000000000d4, value 00000000021db984
..... id 0000000000000114, value 00000000021db964
..... Freq 2301 MHz
..... CPU% 98%
..... CORE_BUSY% 99%

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/builtin-report.c |  3 +++
 tools/perf/util/pmu.h       |  2 ++
 tools/perf/util/session.c   | 34 +++++++++++++++++++++++++++++-----
 tools/perf/util/session.h   | 38 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 72 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 62cce98..0cd0573 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -38,6 +38,8 @@
 
 #include "util/auxtrace.h"
 
+#include "util/pmu.h"
+
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
@@ -818,6 +820,7 @@ repeat:
 		symbol_conf.cumulate_callchain = false;
 	}
 
+	msr_pmu = perf_pmu__find("msr");
 	cpu_max_freq = get_cpu_max_freq() / 1000;
 
 	if (setup_sorting() < 0) {
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 7b9c8cf..e3e67aa 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -27,6 +27,8 @@ struct perf_pmu {
 	struct list_head list;    /* ELEM */
 };
 
+struct perf_pmu *msr_pmu;
+
 struct perf_pmu_info {
 	const char *unit;
 	double scale;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ed9dc25..6dd20b5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -17,6 +17,7 @@
 #include "asm/bug.h"
 #include "auxtrace.h"
 #include "thread-stack.h"
+#include "pmu.h"
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
@@ -851,8 +852,14 @@ static void perf_evlist__print_tstamp(struct perf_evlist *evlist,
 		printf("%" PRIu64 " ", sample->time);
 }
 
-static void sample_read__printf(struct perf_sample *sample, u64 read_format)
+static void sample_read__printf(struct perf_evlist *evlist,
+				struct perf_sample *sample,
+				u64 read_format)
 {
+	struct perf_evsel *evsel;
+	struct perf_sample_id *sid;
+	u64 data[FREQ_PERF_MAX] = { 0 };
+
 	printf("... sample_read:\n");
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -875,10 +882,26 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 			printf("..... id %016" PRIx64
 			       ", value %016" PRIx64 "\n",
 			       value->id, value->value);
+
+			sid = perf_evlist__id2sid(evlist, value->id);
+			evsel = sid->evsel;
+			if (evsel != NULL)
+				SET_FREQ_PERF_VALUE(evsel, data,
+						    value->value);
 		}
 	} else
 		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
 			sample->read.one.id, sample->read.one.value);
+
+	if (HAS_FREQ(data))
+		printf("..... Freq %lu MHz\n",
+		       (data[FREQ_PERF_CYCLES] * cpu_max_freq) / data[FREQ_PERF_REF_CYCLES]);
+	if (HAS_CPU_U(data))
+		printf("..... CPU%% %lu%%\n",
+		       (100 * data[FREQ_PERF_REF_CYCLES]) / data[FREQ_PERF_TSC]);
+	if (HAS_CORE_BUSY(data))
+		printf("..... CORE_BUSY%% %lu%%\n",
+		       (100 * data[FREQ_PERF_APERF]) / data[FREQ_PERF_MPERF]);
 }
 
 static void dump_event(struct perf_evlist *evlist, union perf_event *event,
@@ -899,8 +922,8 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event,
 	       event->header.size, perf_event__name(event->header.type));
 }
 
-static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
-			struct perf_sample *sample)
+static void dump_sample(struct perf_evlist *evlist, struct perf_evsel *evsel,
+			union perf_event *event, struct perf_sample *sample)
 {
 	u64 sample_type;
 
@@ -938,7 +961,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 		printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
 	if (sample_type & PERF_SAMPLE_READ)
-		sample_read__printf(sample, evsel->attr.read_format);
+		sample_read__printf(evlist, sample, evsel->attr.read_format);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1053,11 +1076,12 @@ static int machines__deliver_event(struct machines *machines,
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
 			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
+		dump_sample(evlist, evsel, event, sample);
+
 		if (machine == NULL) {
 			++evlist->stats.nr_unprocessable_samples;
 			return 0;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b44afc7..df2094d 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -42,6 +42,44 @@ struct perf_session {
 #define PRINT_IP_OPT_ONELINE	(1<<4)
 #define PRINT_IP_OPT_SRCLINE	(1<<5)
 
+#define PERF_MSR_TSC		0
+#define PERF_MSR_APERF		1
+#define PERF_MSR_MPERF		2
+
+enum perf_freq_perf_index {
+	FREQ_PERF_TSC		= 0,
+	FREQ_PERF_APERF		= 1,
+	FREQ_PERF_MPERF		= 2,
+	FREQ_PERF_CYCLES	= 3,
+	FREQ_PERF_REF_CYCLES	= 4,
+
+	FREQ_PERF_MAX
+};
+
+#define SET_FREQ_PERF_VALUE(event, array, value)			\
+{									\
+	if (event->attr.type == msr_pmu->type) {			\
+		if (event->attr.config == PERF_MSR_TSC)			\
+			array[FREQ_PERF_TSC] = value;			\
+		if (event->attr.config == PERF_MSR_APERF)		\
+			array[FREQ_PERF_APERF] = value;			\
+		if (event->attr.config == PERF_MSR_MPERF)		\
+			array[FREQ_PERF_MPERF] = value;			\
+	}								\
+	if (event->attr.type == PERF_TYPE_HARDWARE) {			\
+		if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES)	\
+			array[FREQ_PERF_CYCLES] = value;		\
+		if (event->attr.config == PERF_COUNT_HW_REF_CPU_CYCLES)	\
+			array[FREQ_PERF_REF_CYCLES] = value;		\
+	}								\
+}
+
+#define HAS_FREQ(array)							\
+	((array[FREQ_PERF_CYCLES] > 0) && (array[FREQ_PERF_REF_CYCLES] > 0))
+#define HAS_CPU_U(array)						\
+	((array[FREQ_PERF_TSC] > 0) && (array[FREQ_PERF_REF_CYCLES] > 0))
+#define HAS_CORE_BUSY(array)						\
+	((array[FREQ_PERF_APERF] > 0) && (array[FREQ_PERF_MPERF] > 0))
 struct perf_tool;
 
 struct perf_session *perf_session__new(struct perf_data_file *file,
-- 
1.8.3.1

[PATCH 3/5] perf,tools: save misc sample read value in struct perf_sample

[kan.liang]

From: Kan Liang <kan.liang@intel.com>

Save group read results from cycles/ref-cycles/TSC/ASTATE/MSTATE in
struct perf_sample. The following sample process function can easily
use them to caculate freq/CPU%/CORE_BUSY% and add them in hists.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/util/event.h   | 11 +++++++++++
 tools/perf/util/session.c | 16 ++++++++++++++++
 tools/perf/util/session.h | 10 ----------
 3 files changed, 27 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c53f363..f7aabe3 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -176,6 +176,16 @@ enum {
 	PERF_IP_FLAG_TRACE_BEGIN	|\
 	PERF_IP_FLAG_TRACE_END)
 
+enum perf_freq_perf_index {
+	FREQ_PERF_TSC		= 0,
+	FREQ_PERF_APERF		= 1,
+	FREQ_PERF_MPERF		= 2,
+	FREQ_PERF_CYCLES	= 3,
+	FREQ_PERF_REF_CYCLES	= 4,
+
+	FREQ_PERF_MAX
+};
+
 struct perf_sample {
 	u64 ip;
 	u32 pid, tid;
@@ -191,6 +201,7 @@ struct perf_sample {
 	u64 data_src;
 	u32 flags;
 	u16 insn_len;
+	u64 freq_perf_data[FREQ_PERF_MAX];
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6dd20b5..939dfed 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -999,6 +999,8 @@ static int deliver_sample_value(struct perf_evlist *evlist,
 				struct machine *machine)
 {
 	struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id);
+	struct perf_evsel *evsel;
+	u64 nr = 0;
 
 	if (sid) {
 		sample->id     = v->id;
@@ -1011,6 +1013,20 @@ static int deliver_sample_value(struct perf_evlist *evlist,
 		return 0;
 	}
 
+	if (perf_evsel__is_group_leader(sid->evsel)) {
+		evsel = sid->evsel;
+		SET_FREQ_PERF_VALUE(evsel, sample->freq_perf_data,
+				    sample->read.group.values[nr].value);
+		evlist__for_each_continue(evlist, evsel) {
+			if ((evsel->leader != sid->evsel) ||
+			    (++nr >= sample->read.group.nr))
+				break;
+
+			SET_FREQ_PERF_VALUE(evsel, sample->freq_perf_data,
+					    sample->read.group.values[nr].value);
+		}
+	}
+
 	return tool->sample(tool, event, sample, sid->evsel, machine);
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index df2094d..8c3cae8 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,16 +46,6 @@ struct perf_session {
 #define PERF_MSR_APERF		1
 #define PERF_MSR_MPERF		2
 
-enum perf_freq_perf_index {
-	FREQ_PERF_TSC		= 0,
-	FREQ_PERF_APERF		= 1,
-	FREQ_PERF_MPERF		= 2,
-	FREQ_PERF_CYCLES	= 3,
-	FREQ_PERF_REF_CYCLES	= 4,
-
-	FREQ_PERF_MAX
-};
-
 #define SET_FREQ_PERF_VALUE(event, array, value)			\
 {									\
 	if (event->attr.type == msr_pmu->type) {			\
-- 
1.8.3.1

[PATCH 4/5] perf,tools: caculate and save freq/CPU%/CORE_BUSY% in he_stat

[kan.liang]

From: Kan Liang <kan.liang@intel.com>

Introduce a new hist_iter ops (hist_iter_freq_perf) to caculate the
freq/CPU%/CORE_BUSY% freq when processing samples, and save them in
hist_entry.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/builtin-annotate.c |  2 +-
 tools/perf/builtin-diff.c     |  2 +-
 tools/perf/tests/hists_link.c |  4 ++--
 tools/perf/util/hist.c        | 51 ++++++++++++++++++++++++++++++++++++++-----
 tools/perf/util/hist.h        |  2 ++
 tools/perf/util/sort.h        |  3 +++
 tools/perf/util/symbol.h      |  6 +++++
 7 files changed, 60 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 2c1bec3..06e2f87 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -71,7 +71,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true);
+	he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, NULL, true);
 	if (he == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index daaa7dc..2fffcc4 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -315,7 +315,7 @@ static int hists__add_entry(struct hists *hists,
 			    u64 weight, u64 transaction)
 {
 	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-			       transaction, true) != NULL)
+			       transaction, NULL, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 8c102b0..5d9f9e3 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -90,7 +90,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				goto out;
 
 			he = __hists__add_entry(hists, &al, NULL,
-						NULL, NULL, 1, 1, 0, true);
+						NULL, NULL, 1, 1, 0, NULL, true);
 			if (he == NULL) {
 				addr_location__put(&al);
 				goto out;
@@ -116,7 +116,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				goto out;
 
 			he = __hists__add_entry(hists, &al, NULL,
-						NULL, NULL, 1, 1, 0, true);
+						NULL, NULL, 1, 1, 0, NULL, true);
 			if (he == NULL) {
 				addr_location__put(&al);
 				goto out;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6f28d53..26b8eea 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -436,7 +436,9 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction,
+				      u64 period, u64 weight,
+				      u64 transaction,
+				      struct freq_perf_info *info,
 				      bool sample_self)
 {
 	struct hist_entry entry = {
@@ -454,6 +456,9 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.nr_events = 1,
 			.period	= period,
 			.weight = weight,
+			.freq = (info != NULL) ? info->freq : 0,
+			.cpu_u = (info != NULL) ? info->cpu_u : 0,
+			.core_busy = (info != NULL) ? info->core_busy : 0,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
@@ -481,6 +486,32 @@ iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
 }
 
 static int
+iter_add_single_freq_perf_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+	struct freq_perf_info info = {0};
+	u64 *data = sample->freq_perf_data;
+
+	if (data[FREQ_PERF_REF_CYCLES] > 0)
+		info.freq = (data[FREQ_PERF_CYCLES] * cpu_max_freq) / data[FREQ_PERF_REF_CYCLES];
+	if (data[FREQ_PERF_TSC] > 0)
+		info.cpu_u = (100 * data[FREQ_PERF_REF_CYCLES]) / data[FREQ_PERF_TSC];
+	if (data[FREQ_PERF_MPERF] > 0)
+		info.core_busy = (100 * data[FREQ_PERF_APERF]) / data[FREQ_PERF_MPERF];
+
+	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, &info, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
 iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
 	struct perf_sample *sample = iter->sample;
@@ -517,7 +548,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 	 * and the he_stat__add_period() function.
 	 */
 	he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
-				cost, cost, 0, true);
+				cost, cost, 0, NULL, true);
 	if (!he)
 		return -ENOMEM;
 
@@ -618,7 +649,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	 * and not events sampled. Thus we use a pseudo period of 1.
 	 */
 	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-				1, 1, 0, true);
+				1, 1, 0, NULL, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -656,7 +687,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
 
 	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
-				sample->transaction, true);
+				sample->transaction, NULL, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -718,7 +749,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 
 	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
-				sample->transaction, true);
+				sample->transaction, NULL, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -791,7 +822,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 
 	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
 				sample->period, sample->weight,
-				sample->transaction, false);
+				sample->transaction, NULL, false);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -813,6 +844,14 @@ iter_finish_cumulative_entry(struct hist_entry_iter *iter,
 	return 0;
 }
 
+const struct hist_iter_ops hist_iter_freq_perf = {
+	.prepare_entry		= iter_prepare_normal_entry,
+	.add_single_entry	= iter_add_single_freq_perf_entry,
+	.next_entry		= iter_next_nop_entry,
+	.add_next_entry		= iter_add_next_nop_entry,
+	.finish_entry		= iter_finish_normal_entry,
+};
+
 const struct hist_iter_ops hist_iter_mem = {
 	.prepare_entry 		= iter_prepare_mem_entry,
 	.add_single_entry 	= iter_add_single_mem_entry,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5ed8d9c..70bd557 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -102,6 +102,7 @@ extern const struct hist_iter_ops hist_iter_normal;
 extern const struct hist_iter_ops hist_iter_branch;
 extern const struct hist_iter_ops hist_iter_mem;
 extern const struct hist_iter_ops hist_iter_cumulative;
+extern const struct hist_iter_ops hist_iter_freq_perf;
 
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
@@ -109,6 +110,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
 				      u64 weight, u64 transaction,
+				      struct freq_perf_info *freq_perf,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index e97cd47..90422ed 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -54,6 +54,9 @@ struct he_stat {
 	u64			period_guest_us;
 	u64			weight;
 	u32			nr_events;
+	u64			freq;
+	u64			cpu_u;
+	u64			core_busy;
 };
 
 struct hist_entry_diff {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index b98ce51..fa0ccf3 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -180,6 +180,12 @@ struct mem_info {
 	union perf_mem_data_src data_src;
 };
 
+struct freq_perf_info {
+	u64	freq;
+	u64	cpu_u;
+	u64	core_busy;
+};
+
 struct addr_location {
 	struct machine *machine;
 	struct thread *thread;
-- 
1.8.3.1

[PATCH 5/5] perf,tools: Show freq/CPU%/CORE_BUSY% in perf report --stdio

[kan.liang]

From: Kan Liang <kan.liang@intel.com>

Show frequency, CPU Utilization and percent performance for each symbol
in perf report by --stdio --show-freq-perf

In sampling group, only group leader do sampling. So only need to print
group leader's freq in --group.

Here is an example.

$ perf report --stdio --group --show-freq-perf

                                 Overhead   FREQ MHz   CPU%  CORE_BUSY%
Command      Shared Object     Symbol
 ........................................  .........  .....  ..........
...........  ................  ......................

    99.54%  99.54%  99.53%  99.53%  99.53%       2301     96         99
tchain_edit  tchain_edit       [.] f3
     0.20%   0.20%   0.20%   0.20%   0.20%       2301     98         99
tchain_edit  tchain_edit       [.] f2
     0.05%   0.05%   0.05%   0.05%   0.05%       2300     98         99
tchain_edit  [kernel.vmlinux]  [k] read_tsc

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/Documentation/perf-report.txt | 12 ++++++
 tools/perf/builtin-report.c              | 19 +++++++++
 tools/perf/perf.h                        |  1 +
 tools/perf/ui/hist.c                     | 71 +++++++++++++++++++++++++++++---
 tools/perf/util/hist.h                   |  3 ++
 tools/perf/util/session.c                |  2 +-
 tools/perf/util/sort.c                   |  3 ++
 tools/perf/util/symbol.h                 |  3 +-
 tools/perf/util/util.c                   |  2 +
 9 files changed, 109 insertions(+), 7 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index c33b69f..faa8825 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -303,6 +303,18 @@ OPTIONS
 	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
 	'perf mem' for simpler access.
 
+--show-freq-perf::
+	Show CPU frequency and performance result from sample read.
+	To generate the frequency and performance output, the perf.data file
+	must have been obtained by group read and using special events cycles,
+	ref-cycles, msr/tsc/, msr/aperf/ or msr/mperf/
+	Freq MHz: The frequency during the sample interval. Needs cycles and
+		  ref-cycles event.
+	CPU%: CPU utilization during the sample interval. Needs ref-cycles and
+	      msr/tsc/ events.
+	CORE_BUSY%: actual percent performance (APERF/MPERF%) during the
+		    sample interval. Needs msr/aperf/ and msr/mperf/ events.
+
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0cd0573..961b848 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -166,6 +166,8 @@ static int process_sample_event(struct perf_tool *tool,
 		iter.ops = &hist_iter_mem;
 	else if (symbol_conf.cumulate_callchain)
 		iter.ops = &hist_iter_cumulative;
+	else if (symbol_conf.show_freq_perf)
+		iter.ops = &hist_iter_freq_perf;
 	else
 		iter.ops = &hist_iter_normal;
 
@@ -723,6 +725,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+	OPT_BOOLEAN(0, "show-freq-perf", &symbol_conf.show_freq_perf,
+		    "show CPU freqency and performance info"),
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
@@ -735,7 +739,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct perf_data_file file = {
 		.mode  = PERF_DATA_MODE_READ,
 	};
+	struct perf_evsel *pos;
 	int ret = hists__init();
+	bool freq_perf_info[FREQ_PERF_MAX] = {0};
 
 	if (ret < 0)
 		return ret;
@@ -823,6 +829,19 @@ repeat:
 	msr_pmu = perf_pmu__find("msr");
 	cpu_max_freq = get_cpu_max_freq() / 1000;
 
+	if (symbol_conf.show_freq_perf) {
+		perf_freq = perf_cpu_u = perf_core_busy = false;
+		evlist__for_each(session->evlist, pos) {
+			SET_FREQ_PERF_VALUE(pos, freq_perf_info, true);
+		}
+		if (HAS_FREQ(freq_perf_info))
+			perf_freq = true;
+		if (HAS_CPU_U(freq_perf_info))
+			perf_cpu_u = true;
+		if (HAS_CORE_BUSY(freq_perf_info))
+			perf_core_busy = true;
+	}
+
 	if (setup_sorting() < 0) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 937b16a..87daab8 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -33,6 +33,7 @@ static inline unsigned long long rdclock(void)
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
+extern bool perf_freq, perf_cpu_u, perf_core_busy;
 extern const char perf_version_string[];
 
 void pthread__unblock_sigwinch(void);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 25d6083..949bbf2 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -17,7 +17,7 @@
 
 static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		      hpp_field_fn get_field, const char *fmt, int len,
-		      hpp_snprint_fn print_fn, bool fmt_percent)
+		      hpp_snprint_fn print_fn, bool fmt_percent, bool single)
 {
 	int ret;
 	struct hists *hists = he->hists;
@@ -36,7 +36,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	} else
 		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (perf_evsel__is_group_event(evsel) && !single) {
 		int prev_idx, idx_delta;
 		struct hist_entry *pair;
 		int nr_members = evsel->nr_members;
@@ -109,10 +109,17 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	int len = fmt->user_len ?: fmt->len;
+	bool single = false;
+
+	if (symbol_conf.show_freq_perf &&
+	    ((fmt == &perf_hpp__format[PERF_HPP__FREQ]) ||
+	     (fmt == &perf_hpp__format[PERF_HPP__CPU_U]) ||
+	     (fmt == &perf_hpp__format[PERF_HPP__CORE_BUSY])))
+		single = true;
 
 	if (symbol_conf.field_sep) {
 		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
-				  print_fn, fmt_percent);
+				  print_fn, fmt_percent, single);
 	}
 
 	if (fmt_percent)
@@ -120,7 +127,7 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	else
 		len -= 1;
 
-	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent, single);
 }
 
 int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -234,6 +241,30 @@ static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
+static int hpp__single_width_fn(struct perf_hpp_fmt *fmt,
+			 struct perf_hpp *hpp __maybe_unused,
+			 struct perf_evsel *evsel)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.event_group && !symbol_conf.show_freq_perf)
+		len = max(len, evsel->nr_members * fmt->len);
+
+	if (len < (int)strlen(fmt->name))
+		len = strlen(fmt->name);
+
+	return len;
+}
+
+static int hpp__single_header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			  struct perf_evsel *evsel)
+{
+	int len = hpp__single_width_fn(fmt, hpp, evsel);
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
+}
+
+
 static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	va_list args;
@@ -363,6 +394,9 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period)
 
 HPP_RAW_FNS(samples, nr_events)
 HPP_RAW_FNS(period, period)
+HPP_RAW_FNS(freq, freq)
+HPP_RAW_FNS(cpu_u, cpu_u)
+HPP_RAW_FNS(core_busy, core_busy)
 
 static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			    struct hist_entry *a __maybe_unused,
@@ -395,6 +429,17 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.sort	= hpp__sort_ ## _fn,		\
 	}
 
+#define HPP__SINGLE_PRINT_FNS(_name, _fn)		\
+	{						\
+		.name   = _name,			\
+		.header	= hpp__single_header_fn,	\
+		.width	= hpp__single_width_fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _fn,		\
+	}
+
 #define HPP__PRINT_FNS(_name, _fn)			\
 	{						\
 		.name   = _name,			\
@@ -414,7 +459,10 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
 	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
 	HPP__PRINT_FNS("Samples", samples),
-	HPP__PRINT_FNS("Period", period)
+	HPP__PRINT_FNS("Period", period),
+	HPP__SINGLE_PRINT_FNS("FREQ MHz", freq),
+	HPP__SINGLE_PRINT_FNS("CPU%", cpu_u),
+	HPP__SINGLE_PRINT_FNS("CORE_BUSY%", core_busy)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -485,6 +533,14 @@ void perf_hpp__init(void)
 	if (symbol_conf.show_total_period)
 		perf_hpp__column_enable(PERF_HPP__PERIOD);
 
+	if (symbol_conf.show_freq_perf) {
+		if (perf_freq)
+			perf_hpp__column_enable(PERF_HPP__FREQ);
+		if (perf_cpu_u)
+			perf_hpp__column_enable(PERF_HPP__CPU_U);
+		if (perf_core_busy)
+			perf_hpp__column_enable(PERF_HPP__CORE_BUSY);
+	}
 	/* prepend overhead field for backward compatiblity.  */
 	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
 	if (list_empty(list))
@@ -652,6 +708,9 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		return;
 
 	switch (idx) {
+	case PERF_HPP__CPU_U:
+		fmt->len = 5;
+		break;
 	case PERF_HPP__OVERHEAD:
 	case PERF_HPP__OVERHEAD_SYS:
 	case PERF_HPP__OVERHEAD_US:
@@ -661,6 +720,8 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 
 	case PERF_HPP__OVERHEAD_GUEST_SYS:
 	case PERF_HPP__OVERHEAD_GUEST_US:
+	case PERF_HPP__FREQ:
+	case PERF_HPP__CORE_BUSY:
 		fmt->len = 9;
 		break;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 70bd557..ec64234 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -237,6 +237,9 @@ enum {
 	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
+	PERF_HPP__FREQ,
+	PERF_HPP__CPU_U,
+	PERF_HPP__CORE_BUSY,
 
 	PERF_HPP__MAX_INDEX
 };
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 939dfed..43551f7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1013,7 +1013,7 @@ static int deliver_sample_value(struct perf_evlist *evlist,
 		return 0;
 	}
 
-	if (perf_evsel__is_group_leader(sid->evsel)) {
+	if (symbol_conf.show_freq_perf && perf_evsel__is_group_leader(sid->evsel)) {
 		evsel = sid->evsel;
 		SET_FREQ_PERF_VALUE(evsel, sample->freq_perf_data,
 				    sample->read.group.values[nr].value);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4c65a14..690e173 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1225,6 +1225,9 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
+	DIM(PERF_HPP__FREQ, "freq"),
+	DIM(PERF_HPP__CPU_U, "cpu_u"),
+	DIM(PERF_HPP__CORE_BUSY, "core_busy"),
 };
 
 #undef DIM
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fa0ccf3..7d70c89 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -106,7 +106,8 @@ struct symbol_conf {
 			filter_relative,
 			show_hist_headers,
 			branch_callstack,
-			has_filter;
+			has_filter,
+			show_freq_perf;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index edc2d63..648b307 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -34,6 +34,8 @@ bool test_attr__enabled;
 bool perf_host  = true;
 bool perf_guest = false;
 
+bool perf_freq, perf_cpu_u, perf_core_busy;
+
 char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
 
 void event_attr_init(struct perf_event_attr *attr)
-- 
1.8.3.1

[PATCH 5/5] perf,tools: Show freq/CPU%/CORE_BUSY% in perf report --stdio

[Kan Liang]

Show frequency, CPU Utilization and percent performance for each symbol
in perf report by --stdio --show-freq-perf

In sampling group, only group leader do sampling. So only need to print
group leader's freq in --group.

Here is an example.

$ perf report --stdio --group --show-freq-perf

                                 Overhead   FREQ MHz   CPU%  CORE_BUSY%
Command      Shared Object     Symbol
 ........................................  .........  .....  ..........
...........  ................  ......................

    99.54%  99.54%  99.53%  99.53%  99.53%       2301     96         99
tchain_edit  tchain_edit       [.] f3
     0.20%   0.20%   0.20%   0.20%   0.20%       2301     98         99
tchain_edit  tchain_edit       [.] f2
     0.05%   0.05%   0.05%   0.05%   0.05%       2300     98         99
tchain_edit  [kernel.vmlinux]  [k] read_tsc

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/Documentation/perf-report.txt | 12 ++++++
 tools/perf/builtin-report.c              | 19 +++++++++
 tools/perf/perf.h                        |  1 +
 tools/perf/ui/hist.c                     | 71 +++++++++++++++++++++++++++++---
 tools/perf/util/hist.h                   |  3 ++
 tools/perf/util/session.c                |  2 +-
 tools/perf/util/sort.c                   |  3 ++
 tools/perf/util/symbol.h                 |  3 +-
 tools/perf/util/util.c                   |  2 +
 9 files changed, 109 insertions(+), 7 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index c33b69f..faa8825 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -303,6 +303,18 @@ OPTIONS
 	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
 	'perf mem' for simpler access.
 
+--show-freq-perf::
+	Show CPU frequency and performance result from sample read.
+	To generate the frequency and performance output, the perf.data file
+	must have been obtained by group read and using special events cycles,
+	ref-cycles, msr/tsc/, msr/aperf/ or msr/mperf/
+	Freq MHz: The frequency during the sample interval. Needs cycles and
+		  ref-cycles event.
+	CPU%: CPU utilization during the sample interval. Needs ref-cycles and
+	      msr/tsc/ events.
+	CORE_BUSY%: actual percent performance (APERF/MPERF%) during the
+		    sample interval. Needs msr/aperf/ and msr/mperf/ events.
+
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0cd0573..961b848 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -166,6 +166,8 @@ static int process_sample_event(struct perf_tool *tool,
 		iter.ops = &hist_iter_mem;
 	else if (symbol_conf.cumulate_callchain)
 		iter.ops = &hist_iter_cumulative;
+	else if (symbol_conf.show_freq_perf)
+		iter.ops = &hist_iter_freq_perf;
 	else
 		iter.ops = &hist_iter_normal;
 
@@ -723,6 +725,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+	OPT_BOOLEAN(0, "show-freq-perf", &symbol_conf.show_freq_perf,
+		    "show CPU freqency and performance info"),
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
@@ -735,7 +739,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct perf_data_file file = {
 		.mode  = PERF_DATA_MODE_READ,
 	};
+	struct perf_evsel *pos;
 	int ret = hists__init();
+	bool freq_perf_info[FREQ_PERF_MAX] = {0};
 
 	if (ret < 0)
 		return ret;
@@ -823,6 +829,19 @@ repeat:
 	msr_pmu = perf_pmu__find("msr");
 	cpu_max_freq = get_cpu_max_freq() / 1000;
 
+	if (symbol_conf.show_freq_perf) {
+		perf_freq = perf_cpu_u = perf_core_busy = false;
+		evlist__for_each(session->evlist, pos) {
+			SET_FREQ_PERF_VALUE(pos, freq_perf_info, true);
+		}
+		if (HAS_FREQ(freq_perf_info))
+			perf_freq = true;
+		if (HAS_CPU_U(freq_perf_info))
+			perf_cpu_u = true;
+		if (HAS_CORE_BUSY(freq_perf_info))
+			perf_core_busy = true;
+	}
+
 	if (setup_sorting() < 0) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 937b16a..87daab8 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -33,6 +33,7 @@ static inline unsigned long long rdclock(void)
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
+extern bool perf_freq, perf_cpu_u, perf_core_busy;
 extern const char perf_version_string[];
 
 void pthread__unblock_sigwinch(void);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 25d6083..949bbf2 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -17,7 +17,7 @@
 
 static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		      hpp_field_fn get_field, const char *fmt, int len,
-		      hpp_snprint_fn print_fn, bool fmt_percent)
+		      hpp_snprint_fn print_fn, bool fmt_percent, bool single)
 {
 	int ret;
 	struct hists *hists = he->hists;
@@ -36,7 +36,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	} else
 		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (perf_evsel__is_group_event(evsel) && !single) {
 		int prev_idx, idx_delta;
 		struct hist_entry *pair;
 		int nr_members = evsel->nr_members;
@@ -109,10 +109,17 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	int len = fmt->user_len ?: fmt->len;
+	bool single = false;
+
+	if (symbol_conf.show_freq_perf &&
+	    ((fmt == &perf_hpp__format[PERF_HPP__FREQ]) ||
+	     (fmt == &perf_hpp__format[PERF_HPP__CPU_U]) ||
+	     (fmt == &perf_hpp__format[PERF_HPP__CORE_BUSY])))
+		single = true;
 
 	if (symbol_conf.field_sep) {
 		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
-				  print_fn, fmt_percent);
+				  print_fn, fmt_percent, single);
 	}
 
 	if (fmt_percent)
@@ -120,7 +127,7 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	else
 		len -= 1;
 
-	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent, single);
 }
 
 int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -234,6 +241,30 @@ static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
+static int hpp__single_width_fn(struct perf_hpp_fmt *fmt,
+			 struct perf_hpp *hpp __maybe_unused,
+			 struct perf_evsel *evsel)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.event_group && !symbol_conf.show_freq_perf)
+		len = max(len, evsel->nr_members * fmt->len);
+
+	if (len < (int)strlen(fmt->name))
+		len = strlen(fmt->name);
+
+	return len;
+}
+
+static int hpp__single_header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			  struct perf_evsel *evsel)
+{
+	int len = hpp__single_width_fn(fmt, hpp, evsel);
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
+}
+
+
 static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	va_list args;
@@ -363,6 +394,9 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period)
 
 HPP_RAW_FNS(samples, nr_events)
 HPP_RAW_FNS(period, period)
+HPP_RAW_FNS(freq, freq)
+HPP_RAW_FNS(cpu_u, cpu_u)
+HPP_RAW_FNS(core_busy, core_busy)
 
 static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			    struct hist_entry *a __maybe_unused,
@@ -395,6 +429,17 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.sort	= hpp__sort_ ## _fn,		\
 	}
 
+#define HPP__SINGLE_PRINT_FNS(_name, _fn)		\
+	{						\
+		.name   = _name,			\
+		.header	= hpp__single_header_fn,	\
+		.width	= hpp__single_width_fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _fn,		\
+	}
+
 #define HPP__PRINT_FNS(_name, _fn)			\
 	{						\
 		.name   = _name,			\
@@ -414,7 +459,10 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
 	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
 	HPP__PRINT_FNS("Samples", samples),
-	HPP__PRINT_FNS("Period", period)
+	HPP__PRINT_FNS("Period", period),
+	HPP__SINGLE_PRINT_FNS("FREQ MHz", freq),
+	HPP__SINGLE_PRINT_FNS("CPU%", cpu_u),
+	HPP__SINGLE_PRINT_FNS("CORE_BUSY%", core_busy)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -485,6 +533,14 @@ void perf_hpp__init(void)
 	if (symbol_conf.show_total_period)
 		perf_hpp__column_enable(PERF_HPP__PERIOD);
 
+	if (symbol_conf.show_freq_perf) {
+		if (perf_freq)
+			perf_hpp__column_enable(PERF_HPP__FREQ);
+		if (perf_cpu_u)
+			perf_hpp__column_enable(PERF_HPP__CPU_U);
+		if (perf_core_busy)
+			perf_hpp__column_enable(PERF_HPP__CORE_BUSY);
+	}
 	/* prepend overhead field for backward compatiblity.  */
 	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
 	if (list_empty(list))
@@ -652,6 +708,9 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		return;
 
 	switch (idx) {
+	case PERF_HPP__CPU_U:
+		fmt->len = 5;
+		break;
 	case PERF_HPP__OVERHEAD:
 	case PERF_HPP__OVERHEAD_SYS:
 	case PERF_HPP__OVERHEAD_US:
@@ -661,6 +720,8 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 
 	case PERF_HPP__OVERHEAD_GUEST_SYS:
 	case PERF_HPP__OVERHEAD_GUEST_US:
+	case PERF_HPP__FREQ:
+	case PERF_HPP__CORE_BUSY:
 		fmt->len = 9;
 		break;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 70bd557..ec64234 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -237,6 +237,9 @@ enum {
 	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
+	PERF_HPP__FREQ,
+	PERF_HPP__CPU_U,
+	PERF_HPP__CORE_BUSY,
 
 	PERF_HPP__MAX_INDEX
 };
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 939dfed..43551f7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1013,7 +1013,7 @@ static int deliver_sample_value(struct perf_evlist *evlist,
 		return 0;
 	}
 
-	if (perf_evsel__is_group_leader(sid->evsel)) {
+	if (symbol_conf.show_freq_perf && perf_evsel__is_group_leader(sid->evsel)) {
 		evsel = sid->evsel;
 		SET_FREQ_PERF_VALUE(evsel, sample->freq_perf_data,
 				    sample->read.group.values[nr].value);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4c65a14..690e173 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1225,6 +1225,9 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
+	DIM(PERF_HPP__FREQ, "freq"),
+	DIM(PERF_HPP__CPU_U, "cpu_u"),
+	DIM(PERF_HPP__CORE_BUSY, "core_busy"),
 };
 
 #undef DIM
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fa0ccf3..7d70c89 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -106,7 +106,8 @@ struct symbol_conf {
 			filter_relative,
 			show_hist_headers,
 			branch_callstack,
-			has_filter;
+			has_filter,
+			show_freq_perf;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index edc2d63..648b307 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -34,6 +34,8 @@ bool test_attr__enabled;
 bool perf_host  = true;
 bool perf_guest = false;
 
+bool perf_freq, perf_cpu_u, perf_core_busy;
+
 char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
 
 void event_attr_init(struct perf_event_attr *attr)
-- 
1.8.3.1