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:

. Make some POWER7 events available in sysfs, equivalent to
  what was done on x86, from Sukadev Bhattiprolu.

. Add event group view, from Namyung Kim:

  To use it, 'perf record' should group events when recording. And then perf
  report parses the saved group relation from file header and prints them
  together if --group option is provided.  You can use 'perf evlist' command to
  see event group information:

    $ perf record -e '{ref-cycles,cycles}' noploop 1
    [ perf record: Woken up 2 times to write data ]
    [ perf record: Captured and wrote 0.385 MB perf.data (~16807 samples) ]

    $ perf evlist --group
    {ref-cycles,cycles}

  With this example, default perf report will show you each event
  separately like this:

    $ perf report
    ...
    # group: {ref-cycles,cycles}
    # ========
    # Samples: 3K of event 'ref-cycles'
    # Event count (approx.): 3153797218
    #
    # Overhead  Command      Shared Object                      Symbol
    # ........  .......  .................  ..........................
        99.84%  noploop  noploop            [.] main
         0.07%  noploop  ld-2.15.so         [.] strcmp
         0.03%  noploop  [kernel.kallsyms]  [k] timerqueue_del
         0.03%  noploop  [kernel.kallsyms]  [k] sched_clock_cpu
         0.02%  noploop  [kernel.kallsyms]  [k] account_user_time
         0.01%  noploop  [kernel.kallsyms]  [k] __alloc_pages_nodemask
         0.00%  noploop  [kernel.kallsyms]  [k] native_write_msr_safe

    # Samples: 3K of event 'cycles'
    # Event count (approx.): 3722310525
    #
    # Overhead  Command      Shared Object                     Symbol
    # ........  .......  .................  .........................
        99.76%  noploop  noploop            [.] main
         0.11%  noploop  [kernel.kallsyms]  [k] _raw_spin_lock
         0.06%  noploop  [kernel.kallsyms]  [k] find_get_page
         0.03%  noploop  [kernel.kallsyms]  [k] sched_clock_cpu
         0.02%  noploop  [kernel.kallsyms]  [k] rcu_check_callbacks
         0.02%  noploop  [kernel.kallsyms]  [k] __current_kernel_time
         0.00%  noploop  [kernel.kallsyms]  [k] native_write_msr_safe

  In this case the event group information will be shown in the end of
  header area.  So you can use --group option to enable event group view.

    $ perf report --group
    ...
    # group: {ref-cycles,cycles}
    # ========
    # Samples: 7K of event 'anon group { ref-cycles, cycles }'
    # Event count (approx.): 6876107743
    #
    #         Overhead  Command      Shared Object                      Symbol
    # ................  .......  .................  ..........................
        99.84%  99.76%  noploop  noploop            [.] main
         0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
         0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
         0.03%   0.03%  noploop  [kernel.kallsyms]  [k] sched_clock_cpu
         0.02%   0.00%  noploop  [kernel.kallsyms]  [k] account_user_time
         0.01%   0.00%  noploop  [kernel.kallsyms]  [k] __alloc_pages_nodemask
         0.00%   0.00%  noploop  [kernel.kallsyms]  [k] native_write_msr_safe
         0.00%   0.11%  noploop  [kernel.kallsyms]  [k] _raw_spin_lock
         0.00%   0.06%  noploop  [kernel.kallsyms]  [k] find_get_page
         0.00%   0.02%  noploop  [kernel.kallsyms]  [k] rcu_check_callbacks
         0.00%   0.02%  noploop  [kernel.kallsyms]  [k] __current_kernel_time

  As you can see the Overhead column now contains both of ref-cycles and
  cycles and header line shows group information also - 'anon group {
  ref-cycles, cycles }'.  The output is sorted by period of group leader
  first.

  If perf.data file doesn't contain group information, this --group
  option does nothing.  So if you want enable event group view by
  default you can set it in ~/.perfconfig file:

    $ cat ~/.perfconfig
    [report]
    group = true

  It can be overridden with command line if you want:

    $ perf report --no-group

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

28 files changed, 1059 insertions, 267 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
new file mode 100644
index 00000000000..0adeb524c0d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -0,0 +1,62 @@
+What:		/sys/devices/cpu/events/
+		/sys/devices/cpu/events/branch-misses
+		/sys/devices/cpu/events/cache-references
+		/sys/devices/cpu/events/cache-misses
+		/sys/devices/cpu/events/stalled-cycles-frontend
+		/sys/devices/cpu/events/branch-instructions
+		/sys/devices/cpu/events/stalled-cycles-backend
+		/sys/devices/cpu/events/instructions
+		/sys/devices/cpu/events/cpu-cycles
+
+Date:		2013/01/08
+
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+
+Description:	Generic performance monitoring events
+
+		A collection of performance monitoring events that may be
+		supported by many/most CPUs. These events can be monitored
+		using the 'perf(1)' tool.
+
+		The contents of each file would look like:
+
+			event=0xNNNN
+
+		where 'N' is a hex digit and the number '0xNNNN' shows the
+		"raw code" for the perf event identified by the file's
+		"basename".
+
+
+What: 		/sys/devices/cpu/events/PM_LD_MISS_L1
+		/sys/devices/cpu/events/PM_LD_REF_L1
+		/sys/devices/cpu/events/PM_CYC
+		/sys/devices/cpu/events/PM_BRU_FIN
+		/sys/devices/cpu/events/PM_GCT_NOSLOT_CYC
+		/sys/devices/cpu/events/PM_BRU_MPRED
+		/sys/devices/cpu/events/PM_INST_CMPL
+		/sys/devices/cpu/events/PM_CMPLU_STALL
+
+Date:		2013/01/08
+
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+		Linux Powerpc mailing list <linuxppc-dev@ozlabs.org>
+
+Description:	POWER-systems specific performance monitoring events
+
+		A collection of performance monitoring events that may be
+		supported by the POWER CPU. These events can be monitored
+		using the 'perf(1)' tool.
+
+		These events may not be supported by other CPUs.
+
+		The contents of each file would look like:
+
+			event=0xNNNN
+
+		where 'N' is a hex digit and the number '0xNNNN' shows the
+		"raw code" for the perf event identified by the file's
+		"basename".
+
+		Further, multiple terms like 'event=0xNNNN' can be specified
+		and separated with comma. All available terms are defined in
+		the /sys/bus/event_source/devices/<dev>/format file.
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 9710be3a2d1..b29fcc65160 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <asm/hw_irq.h>
+#include <linux/device.h>
 
 #define MAX_HWEVENTS		8
 #define MAX_EVENT_ALTERNATIVES	8
@@ -35,6 +36,7 @@ struct power_pmu {
 	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
 	int		(*limited_pmc_event)(u64 event_id);
 	u32		flags;
+	const struct attribute_group	**attr_groups;
 	int		n_generic;
 	int		*generic_events;
 	int		(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
@@ -109,3 +111,27 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
  * If an event_id is not subject to the constraint expressed by a particular
  * field, then it will have 0 in both the mask and value for that field.
  */
+
+extern ssize_t power_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page);
+
+/*
+ * EVENT_VAR() is same as PMU_EVENT_VAR with a suffix.
+ *
+ * Having a suffix allows us to have aliases in sysfs - eg: the generic
+ * event 'cpu-cycles' can have two entries in sysfs: 'cpu-cycles' and
+ * 'PM_CYC' where the latter is the name by which the event is known in
+ * POWER CPU specification.
+ */
+#define	EVENT_VAR(_id, _suffix)		event_attr_##_id##_suffix
+#define	EVENT_PTR(_id, _suffix)		&EVENT_VAR(_id, _suffix)
+
+#define	EVENT_ATTR(_name, _id, _suffix)					\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id,	\
+			power_events_sysfs_show)
+
+#define	GENERIC_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _g)
+#define	GENERIC_EVENT_PTR(_id)		EVENT_PTR(_id, _g)
+
+#define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(PM_##_name, _id, _p)
+#define	POWER_EVENT_PTR(_id)		EVENT_PTR(_id, _p)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index aa2465e21f1..fa476d50791 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1305,6 +1305,16 @@ static int power_pmu_event_idx(struct perf_event *event)
 	return event->hw.idx;
 }
 
+ssize_t power_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
 struct pmu power_pmu = {
 	.pmu_enable	= power_pmu_enable,
 	.pmu_disable	= power_pmu_disable,
@@ -1537,6 +1547,8 @@ int __cpuinit register_power_pmu(struct power_pmu *pmu)
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	power_pmu.attr_groups = ppmu->attr_groups;
+
 #ifdef MSR_HV
 	/*
 	 * Use FCHV to ignore kernel events if MSR.HV is set.
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 2ee01e38d5e..b554879bd31 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -51,6 +51,18 @@
 #define MMCR1_PMCSEL_MSK	0xff
 
 /*
+ * Power7 event codes.
+ */
+#define	PME_PM_CYC			0x1e
+#define	PME_PM_GCT_NOSLOT_CYC		0x100f8
+#define	PME_PM_CMPLU_STALL		0x4000a
+#define	PME_PM_INST_CMPL		0x2
+#define	PME_PM_LD_REF_L1		0xc880
+#define	PME_PM_LD_MISS_L1		0x400f0
+#define	PME_PM_BRU_FIN			0x10068
+#define	PME_PM_BRU_MPRED		0x400f6
+
+/*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
  * 3210987654321098765432109876543210987654321098765432109876543210
@@ -307,14 +319,14 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 }
 
 static int power7_generic_events[] = {
-	[PERF_COUNT_HW_CPU_CYCLES] = 0x1e,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a,  /* CMPLU_STALL */
-	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
-	[PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880,	/* LD_REF_L1_LSU*/
-	[PERF_COUNT_HW_CACHE_MISSES] = 0x400f0,		/* LD_MISS_L1	*/
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x10068,	/* BRU_FIN	*/
-	[PERF_COUNT_HW_BRANCH_MISSES] = 0x400f6,	/* BR_MPRED	*/
+	[PERF_COUNT_HW_CPU_CYCLES] =			PME_PM_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PME_PM_GCT_NOSLOT_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PME_PM_CMPLU_STALL,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PME_PM_INST_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PME_PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PME_PM_LD_MISS_L1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PME_PM_BRU_FIN,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PME_PM_BRU_MPRED,
 };
 
 #define C(x)	PERF_COUNT_HW_CACHE_##x
@@ -362,6 +374,57 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
+
+GENERIC_EVENT_ATTR(cpu-cycles,			CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions,		BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses,		BRU_MPRED);
+
+POWER_EVENT_ATTR(CYC,				CYC);
+POWER_EVENT_ATTR(GCT_NOSLOT_CYC,		GCT_NOSLOT_CYC);
+POWER_EVENT_ATTR(CMPLU_STALL,			CMPLU_STALL);
+POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
+POWER_EVENT_ATTR(LD_REF_L1,			LD_REF_L1);
+POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
+POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
+POWER_EVENT_ATTR(BRU_MPRED,			BRU_MPRED);
+
+static struct attribute *power7_events_attr[] = {
+	GENERIC_EVENT_PTR(CYC),
+	GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(CMPLU_STALL),
+	GENERIC_EVENT_PTR(INST_CMPL),
+	GENERIC_EVENT_PTR(LD_REF_L1),
+	GENERIC_EVENT_PTR(LD_MISS_L1),
+	GENERIC_EVENT_PTR(BRU_FIN),
+	GENERIC_EVENT_PTR(BRU_MPRED),
+
+	POWER_EVENT_PTR(CYC),
+	POWER_EVENT_PTR(GCT_NOSLOT_CYC),
+	POWER_EVENT_PTR(CMPLU_STALL),
+	POWER_EVENT_PTR(INST_CMPL),
+	POWER_EVENT_PTR(LD_REF_L1),
+	POWER_EVENT_PTR(LD_MISS_L1),
+	POWER_EVENT_PTR(BRU_FIN),
+	POWER_EVENT_PTR(BRU_MPRED),
+	NULL
+};
+
+
+static struct attribute_group power7_pmu_events_group = {
+	.name = "events",
+	.attrs = power7_events_attr,
+};
+
+static const struct attribute_group *power7_pmu_attr_groups[] = {
+	&power7_pmu_events_group,
+	NULL,
+};
+
 static struct power_pmu power7_pmu = {
 	.name			= "POWER7",
 	.n_counter		= 6,
@@ -373,6 +436,7 @@ static struct power_pmu power7_pmu = {
 	.get_alternatives	= power7_get_alternatives,
 	.disable_pmc		= power7_disable_pmc,
 	.flags			= PPMU_ALT_SIPR,
+	.attr_groups		= power7_pmu_attr_groups,
 	.n_generic		= ARRAY_SIZE(power7_generic_events),
 	.generic_events		= power7_generic_events,
 	.cache_events		= &power7_cache_events,
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6774c17a557..c0df5ed2e04 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1310,11 +1310,6 @@ static struct attribute_group x86_pmu_format_group = {
 	.attrs = NULL,
 };
 
-struct perf_pmu_events_attr {
-	struct device_attribute attr;
-	u64 id;
-};
-
 /*
  * Remove all undefined events (x86_pmu.event_map(id) == 0)
  * out of events_attr attributes.
@@ -1348,11 +1343,9 @@ static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *at
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
 
-#define EVENT_ATTR(_name, _id)					\
-static struct perf_pmu_events_attr EVENT_VAR(_id) = {		\
-	.attr = __ATTR(_name, 0444, events_sysfs_show, NULL),	\
-	.id   =  PERF_COUNT_HW_##_id,				\
-};
+#define EVENT_ATTR(_name, _id)						\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id,	\
+			events_sysfs_show)
 
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6bfb2faa0b1..42adf012145 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -817,6 +817,17 @@ do {									\
 } while (0)
 
 
+struct perf_pmu_events_attr {
+	struct device_attribute attr;
+	u64 id;
+};
+
+#define PMU_EVENT_ATTR(_name, _var, _id, _show)				\
+static struct perf_pmu_events_attr _var = {				\
+	.attr = __ATTR(_name, 0444, _show, NULL),			\
+	.id   =  _id,							\
+};
+
 #define PMU_FORMAT_ATTR(_name, _format)					\
 static ssize_t								\
 _name##_show(struct device *dev,					\
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 15217345c2f..1ceb3700ffb 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -28,6 +28,10 @@ OPTIONS
 --verbose=::
 	Show all fields.
 
+-g::
+--group::
+	Show event group information.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-list[1],
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 848a0dcb6df..02284a0067f 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -203,6 +203,9 @@ OPTIONS
 --objdump=<path>::
         Path to objdump binary.
 
+--group::
+	Show event group information together.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 1312a5e03ec..85a5e35dd14 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -39,6 +39,8 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('F', "freq", &details.freq, "Show the sample frequency"),
 	OPT_BOOLEAN('v', "verbose", &details.verbose,
 		    "Show all event attr details"),
+	OPT_BOOLEAN('g', "group", &symbol_conf.event_group,
+		    "Show event group information"),
 	OPT_END()
 	};
 	const char * const evlist_usage[] = {
@@ -50,5 +52,10 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (argc)
 		usage_with_options(evlist_usage, options);
 
+	if (symbol_conf.event_group && (details.verbose || details.freq)) {
+		pr_err("--group option is not compatible with other options\n");
+		usage_with_options(evlist_usage, options);
+	}
+
 	return __cmd_evlist(input_name, &details);
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 2ac690cad41..774c90713a5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -486,6 +486,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 		goto out_delete_session;
 	}
 
+	if (!evsel_list->nr_groups)
+		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
+
 	/*
 	 * perf_session__delete(session) will be called at perf_record__exit()
 	 */
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 47a86447854..0d221870561 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,6 +8,7 @@
 #include "builtin.h"
 
 #include "util/util.h"
+#include "util/cache.h"
 
 #include "util/annotate.h"
 #include "util/color.h"
@@ -54,6 +55,16 @@ struct perf_report {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "report.group")) {
+		symbol_conf.event_group = perf_config_bool(var, value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 					struct addr_location *al,
 					struct perf_sample *sample,
@@ -299,6 +310,21 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
 	char unit;
 	unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = self->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(self);
+	char buf[512];
+	size_t size = sizeof(buf);
+
+	if (symbol_conf.event_group && evsel->nr_members > 1) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, size);
+		evname = buf;
+
+		for_each_group_member(pos, evsel) {
+			nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+			nr_events += pos->hists.stats.total_period;
+		}
+	}
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
@@ -319,6 +345,10 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		struct hists *hists = &pos->hists;
 		const char *evname = perf_evsel__name(pos);
 
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos))
+			continue;
+
 		hists__fprintf_nr_sample_events(hists, evname, stdout);
 		hists__fprintf(hists, true, 0, 0, stdout);
 		fprintf(stdout, "\n\n");
@@ -416,8 +446,16 @@ static int __cmd_report(struct perf_report *rep)
 			hists->symbol_filter_str = rep->symbol_filter_str;
 
 		hists__collapse_resort(hists);
-		hists__output_resort(hists);
 		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+		/* Non-group events are considered as leader */
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos)) {
+			struct hists *leader_hists = &pos->leader->hists;
+
+			hists__match(leader_hists, hists);
+			hists__link(leader_hists, hists);
+		}
 	}
 
 	if (nr_samples == 0) {
@@ -425,6 +463,9 @@ static int __cmd_report(struct perf_report *rep)
 		goto out_delete;
 	}
 
+	list_for_each_entry(pos, &session->evlist->entries, node)
+		hists__output_resort(&pos->hists);
+
 	if (use_browser > 0) {
 		if (use_browser == 1) {
 			perf_evlist__tui_browse_hists(session->evlist, help,
@@ -638,6 +679,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+		    "Show event group information together"),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
 		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
@@ -645,6 +688,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_END()
 	};
 
+	perf_config(perf_report_config, NULL);
+
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
 	if (report.use_stdio)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7978c8117b7..f561757b1bf 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -68,6 +68,8 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
+static volatile int done;
+
 static void perf_top__update_print_entries(struct perf_top *top)
 {
 	if (top->print_entries > 9)
@@ -431,8 +433,10 @@ static int perf_top__key_mapped(struct perf_top *top, int c)
 	return 0;
 }
 
-static void perf_top__handle_keypress(struct perf_top *top, int c)
+static bool perf_top__handle_keypress(struct perf_top *top, int c)
 {
+	bool ret = true;
+
 	if (!perf_top__key_mapped(top, c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 		struct termios tc, save;
@@ -453,7 +457,7 @@ static void perf_top__handle_keypress(struct perf_top *top, int c)
 
 		tcsetattr(0, TCSAFLUSH, &save);
 		if (!perf_top__key_mapped(top, c))
-			return;
+			return ret;
 	}
 
 	switch (c) {
@@ -515,7 +519,8 @@ static void perf_top__handle_keypress(struct perf_top *top, int c)
 			printf("exiting.\n");
 			if (top->dump_symtab)
 				perf_session__fprintf_dsos(top->session, stderr);
-			exit(0);
+			ret = false;
+			break;
 		case 's':
 			perf_top__prompt_symbol(top, "Enter details symbol");
 			break;
@@ -538,6 +543,8 @@ static void perf_top__handle_keypress(struct perf_top *top, int c)
 		default:
 			break;
 	}
+
+	return ret;
 }
 
 static void perf_top__sort_new_samples(void *arg)
@@ -579,8 +586,7 @@ static void *display_thread_tui(void *arg)
 	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      &top->session->header.env);
 
-	exit_browser(0);
-	exit(0);
+	done = 1;
 	return NULL;
 }
 
@@ -604,7 +610,7 @@ repeat:
 	/* trash return*/
 	getc(stdin);
 
-	while (1) {
+	while (!done) {
 		perf_top__print_sym_table(top);
 		/*
 		 * Either timeout expired or we got an EINTR due to SIGWINCH,
@@ -618,15 +624,14 @@ repeat:
 				continue;
 			/* Fall trhu */
 		default:
-			goto process_hotkey;
+			c = getc(stdin);
+			tcsetattr(0, TCSAFLUSH, &save);
+
+			if (perf_top__handle_keypress(top, c))
+				goto repeat;
+			done = 1;
 		}
 	}
-process_hotkey:
-	c = getc(stdin);
-	tcsetattr(0, TCSAFLUSH, &save);
-
-	perf_top__handle_keypress(top, c);
-	goto repeat;
 
 	return NULL;
 }
@@ -705,7 +710,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	}
 
 	if (!machine) {
-		pr_err("%u unprocessable samples recorded.\n",
+		pr_err("%u unprocessable samples recorded.\r",
 		       top->session->stats.nr_unprocessable_samples++);
 		return;
 	}
@@ -868,7 +873,7 @@ static void perf_top__mmap_read(struct perf_top *top)
 		perf_top__mmap_read_idx(top, i);
 }
 
-static void perf_top__start_counters(struct perf_top *top)
+static int perf_top__start_counters(struct perf_top *top)
 {
 	char msg[512];
 	struct perf_evsel *counter;
@@ -900,11 +905,10 @@ try_again:
 		goto out_err;
 	}
 
-	return;
+	return 0;
 
 out_err:
-	exit_browser(0);
-	exit(0);
+	return -1;
 }
 
 static int perf_top__setup_sample_type(struct perf_top *top)
@@ -948,7 +952,11 @@ static int __cmd_top(struct perf_top *top)
 	else
 		perf_event__synthesize_threads(&top->tool, perf_event__process,
 					       &top->session->machines.host);
-	perf_top__start_counters(top);
+
+	ret = perf_top__start_counters(top);
+	if (ret)
+		goto out_delete;
+
 	top->session->evlist = top->evlist;
 	perf_session__set_id_hdr_size(top->session);
 
@@ -968,10 +976,11 @@ static int __cmd_top(struct perf_top *top)
 
 	perf_top__mmap_read(top);
 
+	ret = -1;
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
 		ui__error("Could not create display thread.\n");
-		exit(-1);
+		goto out_delete;
 	}
 
 	if (top->realtime_prio) {
@@ -980,11 +989,11 @@ static int __cmd_top(struct perf_top *top)
 		param.sched_priority = top->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
 			ui__error("Could not set realtime priority.\n");
-			exit(-1);
+			goto out_delete;
 		}
 	}
 
-	while (1) {
+	while (!done) {
 		u64 hits = top->samples;
 
 		perf_top__mmap_read(top);
@@ -993,11 +1002,12 @@ static int __cmd_top(struct perf_top *top)
 			ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
 	}
 
+	ret = 0;
 out_delete:
 	perf_session__delete(top->session);
 	top->session = NULL;
 
-	return 0;
+	return ret;
 }
 
 static int
@@ -1154,7 +1164,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!top.evlist->nr_entries &&
 	    perf_evlist__add_default(top.evlist) < 0) {
 		ui__error("Not enough memory for event selector list\n");
-		return -ENOMEM;
+		goto out_delete_maps;
 	}
 
 	symbol_conf.nr_events = top.evlist->nr_entries;
@@ -1177,7 +1187,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	} else {
 		ui__error("frequency and count are zero, aborting\n");
 		status = -EINVAL;
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
@@ -1210,6 +1220,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	status = __cmd_top(&top);
 
+out_delete_maps:
+	perf_evlist__delete_maps(top.evlist);
 out_delete_evlist:
 	perf_evlist__delete(top.evlist);
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 20acaff295d..80a8daf54a6 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -23,6 +23,7 @@ static int test__checkevent_tracepoint(struct perf_evlist *evlist)
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
 
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
 		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
@@ -35,6 +36,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		TEST_ASSERT_VAL("wrong type",
@@ -510,6 +512,7 @@ static int test__group1(struct perf_evlist *evlist)
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
 
 	/* instructions:k */
 	evsel = leader = perf_evlist__first(evlist);
@@ -523,6 +526,8 @@ static int test__group1(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* cycles:upp */
 	evsel = perf_evsel__next(evsel);
@@ -537,6 +542,7 @@ static int test__group1(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -546,6 +552,7 @@ static int test__group2(struct perf_evlist *evlist)
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
 
 	/* faults + :ku modifier */
 	evsel = leader = perf_evlist__first(evlist);
@@ -559,6 +566,8 @@ static int test__group2(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* cache-references + :u modifier */
 	evsel = perf_evsel__next(evsel);
@@ -572,6 +581,7 @@ static int test__group2(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* cycles:k */
 	evsel = perf_evsel__next(evsel);
@@ -594,6 +604,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
 
 	/* group1 syscalls:sys_enter_open:H */
 	evsel = leader = perf_evlist__first(evlist);
@@ -610,6 +621,8 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group1"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* group1 cycles:kppp */
 	evsel = perf_evsel__next(evsel);
@@ -625,6 +638,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* group2 cycles + G modifier */
 	evsel = leader = perf_evsel__next(evsel);
@@ -640,6 +654,8 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group2"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* group2 1:3 + G modifier */
 	evsel = perf_evsel__next(evsel);
@@ -652,6 +668,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* instructions:u */
 	evsel = perf_evsel__next(evsel);
@@ -674,6 +691,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
 
 	/* cycles:u + p */
 	evsel = leader = perf_evlist__first(evlist);
@@ -689,6 +707,8 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* instructions:kp + p */
 	evsel = perf_evsel__next(evsel);
@@ -703,6 +723,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -712,6 +733,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
 
 	/* cycles + G */
 	evsel = leader = perf_evlist__first(evlist);
@@ -726,6 +748,8 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* instructions + G */
 	evsel = perf_evsel__next(evsel);
@@ -739,6 +763,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* cycles:G */
 	evsel = leader = perf_evsel__next(evsel);
@@ -753,6 +778,8 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
 	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* instructions:G */
 	evsel = perf_evsel__next(evsel);
@@ -766,6 +793,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* cycles */
 	evsel = perf_evsel__next(evsel);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 57b82c26cd0..20ccd57753f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -567,23 +567,123 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	return row - first_row;
 }
 
-#define HPP__COLOR_FN(_name, _field)					\
-static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp,	\
-					     struct hist_entry *he)	\
+struct hpp_arg {
+	struct ui_browser *b;
+	char folded_sign;
+	bool current_entry;
+};
+
+static int __hpp__color_callchain(struct hpp_arg *arg)
+{
+	if (!symbol_conf.use_callchain)
+		return 0;
+
+	slsmg_printf("%c ", arg->folded_sign);
+	return 2;
+}
+
+static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
+			    u64 (*get_field)(struct hist_entry *),
+			    int (*callchain_cb)(struct hpp_arg *))
+{
+	int ret = 0;
+	double percent = 0.0;
+	struct hists *hists = he->hists;
+	struct hpp_arg *arg = hpp->ptr;
+
+	if (hists->stats.total_period)
+		percent = 100.0 * get_field(he) / hists->stats.total_period;
+
+	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
+
+	if (callchain_cb)
+		ret += callchain_cb(arg);
+
+	ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
+	slsmg_printf("%s", hpp->buf);
+
+	if (symbol_conf.event_group) {
+		int prev_idx, idx_delta;
+		struct perf_evsel *evsel = hists_to_evsel(hists);
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
+
+		if (nr_members <= 1)
+			goto out;
+
+		prev_idx = perf_evsel__group_idx(evsel);
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = pair->hists->stats.total_period;
+
+			if (!total)
+				continue;
+
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				ui_browser__set_percent_color(arg->b, 0.0,
+							arg->current_entry);
+				ret += scnprintf(hpp->buf, hpp->size,
+						 " %6.2f%%", 0.0);
+				slsmg_printf("%s", hpp->buf);
+			}
+
+			percent = 100.0 * period / total;
+			ui_browser__set_percent_color(arg->b, percent,
+						      arg->current_entry);
+			ret += scnprintf(hpp->buf, hpp->size,
+					 " %6.2f%%", percent);
+			slsmg_printf("%s", hpp->buf);
+
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
+
+		idx_delta = nr_members - prev_idx - 1;
+
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			ui_browser__set_percent_color(arg->b, 0.0,
+						      arg->current_entry);
+			ret += scnprintf(hpp->buf, hpp->size,
+					 " %6.2f%%", 0.0);
+			slsmg_printf("%s", hpp->buf);
+		}
+	}
+out:
+	if (!arg->current_entry || !arg->b->navkeypressed)
+		ui_browser__set_color(arg->b, HE_COLORSET_NORMAL);
+
+	return ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field, _cb)			\
+static u64 __hpp_get_##_field(struct hist_entry *he)			\
 {									\
-	struct hists *hists = he->hists;				\
-	double percent = 100.0 * he->stat._field / hists->stats.total_period; \
-	*(double *)hpp->ptr = percent;					\
-	return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent);	\
+	return he->stat._field;						\
+}									\
+									\
+static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp,	\
+					   struct hist_entry *he)	\
+{									\
+	return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb);	\
 }
 
-HPP__COLOR_FN(overhead, period)
-HPP__COLOR_FN(overhead_sys, period_sys)
-HPP__COLOR_FN(overhead_us, period_us)
-HPP__COLOR_FN(overhead_guest_sys, period_guest_sys)
-HPP__COLOR_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL)
 
-#undef HPP__COLOR_FN
+#undef __HPP_COLOR_PERCENT_FN
 
 void hist_browser__init_hpp(void)
 {
@@ -608,7 +708,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 				    unsigned short row)
 {
 	char s[256];
-	double percent;
 	int printed = 0;
 	int width = browser->b.width;
 	char folded_sign = ' ';
@@ -628,16 +727,20 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	}
 
 	if (row_offset == 0) {
+		struct hpp_arg arg = {
+			.b 		= &browser->b,
+			.folded_sign	= folded_sign,
+			.current_entry	= current_entry,
+		};
 		struct perf_hpp hpp = {
 			.buf		= s,
 			.size		= sizeof(s),
+			.ptr		= &arg,
 		};
-		int i = 0;
 
 		ui_browser__gotorc(&browser->b, row, 0);
 
 		perf_hpp__for_each_format(fmt) {
-
 			if (!first) {
 				slsmg_printf("  ");
 				width -= 2;
@@ -645,27 +748,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			first = false;
 
 			if (fmt->color) {
-				hpp.ptr = &percent;
-				/* It will set percent for us. See HPP__COLOR_FN above. */
 				width -= fmt->color(&hpp, entry);
-
-				ui_browser__set_percent_color(&browser->b, percent, current_entry);
-
-				if (!i && symbol_conf.use_callchain) {
-					slsmg_printf("%c ", folded_sign);
-					width -= 2;
-				}
-
-				slsmg_printf("%s", s);
-
-				if (!current_entry || !browser->b.navkeypressed)
-					ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
 			} else {
 				width -= fmt->entry(&hpp, entry);
 				slsmg_printf("%s", s);
 			}
-
-			i++;
 		}
 
 		/* The scroll bar isn't being used */
@@ -1102,6 +1189,21 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 	const struct thread *thread = hists->thread_filter;
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = hists->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	char buf[512];
+	size_t buflen = sizeof(buf);
+
+	if (symbol_conf.event_group && evsel->nr_members > 1) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, buflen);
+		ev_name = buf;
+
+		for_each_group_member(pos, evsel) {
+			nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+			nr_events += pos->hists.stats.total_period;
+		}
+	}
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
@@ -1498,6 +1600,16 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
 						       HE_COLORSET_NORMAL);
 
+	if (symbol_conf.event_group && evsel->nr_members > 1) {
+		struct perf_evsel *pos;
+
+		ev_name = perf_evsel__group_name(evsel);
+
+		for_each_group_member(pos, evsel) {
+			nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+		}
+	}
+
 	nr_events = convert_unit(nr_events, &unit);
 	printed = scnprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
 			   unit, unit == ' ' ? "" : " ", ev_name);
@@ -1608,8 +1720,19 @@ out:
 	return key;
 }
 
+static bool filter_group_entries(struct ui_browser *self __maybe_unused,
+				 void *entry)
+{
+	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+
+	if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel))
+		return true;
+
+	return false;
+}
+
 static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
-					   const char *help,
+					   int nr_entries, const char *help,
 					   struct hist_browser_timer *hbt,
 					   struct perf_session_env *env)
 {
@@ -1620,7 +1743,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 			.refresh    = ui_browser__list_head_refresh,
 			.seek	    = ui_browser__list_head_seek,
 			.write	    = perf_evsel_menu__write,
-			.nr_entries = evlist->nr_entries,
+			.filter	    = filter_group_entries,
+			.nr_entries = nr_entries,
 			.priv	    = evlist,
 		},
 		.env = env,
@@ -1636,20 +1760,37 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 			menu.b.width = line_len;
 	}
 
-	return perf_evsel_menu__run(&menu, evlist->nr_entries, help, hbt);
+	return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  struct perf_session_env *env)
 {
-	if (evlist->nr_entries == 1) {
+	int nr_entries = evlist->nr_entries;
+
+single_entry:
+	if (nr_entries == 1) {
 		struct perf_evsel *first = list_entry(evlist->entries.next,
 						      struct perf_evsel, node);
 		const char *ev_name = perf_evsel__name(first);
-		return perf_evsel__hists_browse(first, evlist->nr_entries, help,
+
+		return perf_evsel__hists_browse(first, nr_entries, help,
 						ev_name, false, hbt, env);
 	}
 
-	return __perf_evlist__tui_browse_hists(evlist, help, hbt, env);
+	if (symbol_conf.event_group) {
+		struct perf_evsel *pos;
+
+		nr_entries = 0;
+		list_for_each_entry(pos, &evlist->entries, node)
+			if (perf_evsel__is_group_leader(pos))
+				nr_entries++;
+
+		if (nr_entries == 1)
+			goto single_entry;
+	}
+
+	return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
+					       hbt, env);
 }
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index c03da79d524..1e764a8ad25 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -8,32 +8,105 @@
 
 #define MAX_COLUMNS			32
 
-#define HPP__COLOR_FN(_name, _field)						\
-static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp,			\
-					 struct hist_entry *he)			\
+static int __percent_color_snprintf(char *buf, size_t size, double percent)
+{
+	int ret = 0;
+	const char *markup;
+
+	markup = perf_gtk__get_percent_color(percent);
+	if (markup)
+		ret += scnprintf(buf, size, markup);
+
+	ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent);
+
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	return ret;
+}
+
+
+static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
+			    u64 (*get_field)(struct hist_entry *))
+{
+	int ret;
+	double percent = 0.0;
+	struct hists *hists = he->hists;
+
+	if (hists->stats.total_period)
+		percent = 100.0 * get_field(he) / hists->stats.total_period;
+
+	ret = __percent_color_snprintf(hpp->buf, hpp->size, percent);
+
+	if (symbol_conf.event_group) {
+		int prev_idx, idx_delta;
+		struct perf_evsel *evsel = hists_to_evsel(hists);
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
+
+		if (nr_members <= 1)
+			return ret;
+
+		prev_idx = perf_evsel__group_idx(evsel);
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = pair->hists->stats.total_period;
+
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				ret += __percent_color_snprintf(hpp->buf + ret,
+								hpp->size - ret,
+								0.0);
+			}
+
+			percent = 100.0 * period / total;
+			ret += __percent_color_snprintf(hpp->buf + ret,
+							hpp->size - ret,
+							percent);
+
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
+
+		idx_delta = nr_members - prev_idx - 1;
+
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			ret += __percent_color_snprintf(hpp->buf + ret,
+							hpp->size - ret,
+							0.0);
+		}
+	}
+	return ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
 {										\
-	struct hists *hists = he->hists;					\
-	double percent = 100.0 * he->stat._field / hists->stats.total_period;	\
-	const char *markup;							\
-	int ret = 0;								\
+	return he->stat._field;							\
+}										\
 										\
-	markup = perf_gtk__get_percent_color(percent);				\
-	if (markup)								\
-		ret += scnprintf(hpp->buf, hpp->size, "%s", markup);		\
-	ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%6.2f%%", percent); 	\
-	if (markup)								\
-		ret += scnprintf(hpp->buf + ret, hpp->size - ret, "</span>"); 	\
-										\
-	return ret;								\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return __hpp__color_fmt(hpp, he, he_get_##_field);			\
 }
 
-HPP__COLOR_FN(overhead, period)
-HPP__COLOR_FN(overhead_sys, period_sys)
-HPP__COLOR_FN(overhead_us, period_us)
-HPP__COLOR_FN(overhead_guest_sys, period_guest_sys)
-HPP__COLOR_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_PERCENT_FN(overhead, period)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
 
-#undef HPP__COLOR_FN
+#undef __HPP_COLOR_PERCENT_FN
 
 
 void perf_gtk__init_hpp(void)
@@ -70,6 +143,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 	struct perf_hpp hpp = {
 		.buf		= s,
 		.size		= sizeof(s),
+		.ptr		= hists_to_evsel(hists),
 	};
 
 	nr_cols = 0;
@@ -96,7 +170,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
 		fmt->header(&hpp);
 
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-							    -1, s,
+							    -1, ltrim(s),
 							    renderer, "markup",
 							    col_idx++, NULL);
 	}
@@ -196,6 +270,18 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 		const char *evname = perf_evsel__name(pos);
 		GtkWidget *scrolled_window;
 		GtkWidget *tab_label;
+		char buf[512];
+		size_t size = sizeof(buf);
+
+		if (symbol_conf.event_group) {
+			if (!perf_evsel__is_group_leader(pos))
+				continue;
+
+			if (pos->nr_members > 1) {
+				perf_evsel__group_desc(pos, buf, size);
+				evname = buf;
+			}
+		}
 
 		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 1889c12ca81..a47ce98c2cb 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -3,151 +3,164 @@
 #include "../util/hist.h"
 #include "../util/util.h"
 #include "../util/sort.h"
-
+#include "../util/evsel.h"
 
 /* hist period print (hpp) functions */
-static int hpp__header_overhead(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "Overhead");
-}
-
-static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused)
-{
-	return 8;
-}
-
-static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period / hists->stats.total_period;
-
-	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
-}
-
-static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
 
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
-
-static int hpp__header_overhead_sys(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "sys");
-}
-
-static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused)
-{
-	return 7;
-}
+typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...);
 
-static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he)
+static int __hpp__percent_fmt(struct perf_hpp *hpp, struct hist_entry *he,
+			      u64 (*get_field)(struct hist_entry *),
+			      const char *fmt, hpp_snprint_fn print_fn)
 {
+	int ret;
+	double percent = 0.0;
 	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_sys / hists->stats.total_period;
 
-	return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
-}
+	if (hists->stats.total_period)
+		percent = 100.0 * get_field(he) / hists->stats.total_period;
 
-static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_sys / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
+	ret = print_fn(hpp->buf, hpp->size, fmt, percent);
 
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
+	if (symbol_conf.event_group) {
+		int prev_idx, idx_delta;
+		struct perf_evsel *evsel = hists_to_evsel(hists);
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
 
-static int hpp__header_overhead_us(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
+		if (nr_members <= 1)
+			return ret;
 
-	return scnprintf(hpp->buf, hpp->size, fmt, "user");
-}
+		prev_idx = perf_evsel__group_idx(evsel);
 
-static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused)
-{
-	return 7;
-}
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = pair->hists->stats.total_period;
 
-static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_us / hists->stats.total_period;
-
-	return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
-}
-
-static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_us / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
+			if (!total)
+				continue;
 
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
-
-static int hpp__header_overhead_guest_sys(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "guest sys");
-}
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
 
-static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused)
-{
-	return 9;
-}
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				ret += print_fn(hpp->buf + ret, hpp->size - ret,
+						fmt, 0.0);
+			}
 
-static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp,
-					 struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period;
+			ret += print_fn(hpp->buf + ret, hpp->size - ret,
+					fmt, 100.0 * period / total);
 
-	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent);
-}
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
 
-static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp,
-					 struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% ";
+		idx_delta = nr_members - prev_idx - 1;
 
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			ret += print_fn(hpp->buf + ret, hpp->size - ret,
+					fmt, 0.0);
+		}
+	}
+	return ret;
 }
 
-static int hpp__header_overhead_guest_us(struct perf_hpp *hpp)
+static int __hpp__raw_fmt(struct perf_hpp *hpp, struct hist_entry *he,
+			  u64 (*get_field)(struct hist_entry *),
+			  const char *fmt, hpp_snprint_fn print_fn)
 {
-	return scnprintf(hpp->buf, hpp->size, "guest usr");
-}
+	int ret;
 
-static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused)
-{
-	return 9;
+	ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he));
+	return ret;
 }
 
-static int hpp__color_overhead_guest_us(struct perf_hpp *hpp,
-					struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period;
 
-	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent);
-}
+#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
+static int hpp__header_##_type(struct perf_hpp *hpp)			\
+{									\
+	int len = _min_width;						\
+									\
+	if (symbol_conf.event_group) {					\
+		struct perf_evsel *evsel = hpp->ptr;			\
+									\
+		len = max(len, evsel->nr_members * _unit_width);	\
+	}								\
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
+}
+
+#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
+static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused)	\
+{									\
+	int len = _min_width;						\
+									\
+	if (symbol_conf.event_group) {					\
+		struct perf_evsel *evsel = hpp->ptr;			\
+									\
+		len = max(len, evsel->nr_members * _unit_width);	\
+	}								\
+	return len;							\
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return __hpp__percent_fmt(hpp, he, he_get_##_field, " %6.2f%%",		\
+				  (hpp_snprint_fn)percent_color_snprintf); 	\
+}
+
+#define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
+static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
+	return __hpp__percent_fmt(hpp, he, he_get_##_field, fmt,		\
+				  scnprintf);					\
+}
+
+#define __HPP_ENTRY_RAW_FN(_type, _field)					\
+static u64 he_get_raw_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
+	return __hpp__raw_fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf);	\
+}
+
+#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_COLOR_PERCENT_FN(_type, _field)					\
+__HPP_ENTRY_PERCENT_FN(_type, _field)
+
+#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_ENTRY_RAW_FN(_type, _field)
+
+
+HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
+HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
+HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
+HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
+HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
+
+HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
+HPP_RAW_FNS(period, "Period", period, 12, 12)
 
-static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp,
-					struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% ";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
 
 static int hpp__header_baseline(struct perf_hpp *hpp)
 {
@@ -179,7 +192,7 @@ static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he)
 {
 	double percent = baseline_percent(he);
 
-	if (hist_entry__has_pairs(he))
+	if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
 		return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
 	else
 		return scnprintf(hpp->buf, hpp->size, "        ");
@@ -196,44 +209,6 @@ static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he)
 		return scnprintf(hpp->buf, hpp->size, "            ");
 }
 
-static int hpp__header_samples(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%11s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Samples");
-}
-
-static int hpp__width_samples(struct perf_hpp *hpp __maybe_unused)
-{
-	return 11;
-}
-
-static int hpp__entry_samples(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%11" PRIu64;
-
-	return scnprintf(hpp->buf, hpp->size, fmt, he->stat.nr_events);
-}
-
-static int hpp__header_period(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Period");
-}
-
-static int hpp__width_period(struct perf_hpp *hpp __maybe_unused)
-{
-	return 12;
-}
-
-static int hpp__entry_period(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64;
-
-	return scnprintf(hpp->buf, hpp->size, fmt, he->stat.period);
-}
-
 static int hpp__header_period_baseline(struct perf_hpp *hpp)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
@@ -254,6 +229,7 @@ static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *h
 
 	return scnprintf(hpp->buf, hpp->size, fmt, period);
 }
+
 static int hpp__header_delta(struct perf_hpp *hpp)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
@@ -408,9 +384,20 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 
 LIST_HEAD(perf_hpp__list);
 
+
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__PRINT_FNS
 
+#undef HPP_PERCENT_FNS
+#undef HPP_RAW_FNS
+
+#undef __HPP_HEADER_FN
+#undef __HPP_WIDTH_FN
+#undef __HPP_COLOR_PERCENT_FN
+#undef __HPP_ENTRY_PERCENT_FN
+#undef __HPP_ENTRY_RAW_FN
+
+
 void perf_hpp__init(void)
 {
 	if (symbol_conf.show_cpu_utilization) {
@@ -508,12 +495,15 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
 	int i = 0, ret = 0;
+	struct perf_hpp dummy_hpp = {
+		.ptr	= hists_to_evsel(hists),
+	};
 
 	perf_hpp__for_each_format(fmt) {
 		if (i)
 			ret += 2;
 
-		ret += fmt->width(NULL);
+		ret += fmt->width(&dummy_hpp);
 	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index f9798298e3e..ff1f60cf442 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -3,6 +3,7 @@
 #include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/sort.h"
+#include "../../util/evsel.h"
 
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -347,6 +348,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
 		.size	= sizeof(bf),
+		.ptr	= hists_to_evsel(hists),
 	};
 	bool first = true;
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index dc8aee97a48..eddd5ebcd69 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -117,6 +117,9 @@ void __perf_evlist__set_leader(struct list_head *list)
 	struct perf_evsel *evsel, *leader;
 
 	leader = list_entry(list->next, struct perf_evsel, node);
+	evsel = list_entry(list->prev, struct perf_evsel, node);
+
+	leader->nr_members = evsel->idx - leader->idx + 1;
 
 	list_for_each_entry(evsel, list, node) {
 		if (evsel != leader)
@@ -126,8 +129,10 @@ void __perf_evlist__set_leader(struct list_head *list)
 
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
-	if (evlist->nr_entries)
+	if (evlist->nr_entries) {
+		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
 		__perf_evlist__set_leader(&evlist->entries);
+	}
 }
 
 int perf_evlist__add_default(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 457e2350d21..73579a25a93 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -21,6 +21,7 @@ struct perf_evlist {
 	struct list_head entries;
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
+	int		 nr_groups;
 	int		 nr_fds;
 	int		 nr_mmaps;
 	int		 mmap_len;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index baa26ddbcc7..a5470150460 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -434,6 +434,31 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 	return evsel->name ?: "unknown";
 }
 
+const char *perf_evsel__group_name(struct perf_evsel *evsel)
+{
+	return evsel->group_name ?: "anon group";
+}
+
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
+{
+	int ret;
+	struct perf_evsel *pos;
+	const char *group_name = perf_evsel__group_name(evsel);
+
+	ret = scnprintf(buf, size, "%s", group_name);
+
+	ret += scnprintf(buf + ret, size - ret, " { %s",
+			 perf_evsel__name(evsel));
+
+	for_each_group_member(pos, evsel)
+		ret += scnprintf(buf + ret, size - ret, ", %s",
+				 perf_evsel__name(pos));
+
+	ret += scnprintf(buf + ret, size - ret, " }");
+
+	return ret;
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1364,7 +1389,27 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 			struct perf_attr_details *details, FILE *fp)
 {
 	bool first = true;
-	int printed = fprintf(fp, "%s", perf_evsel__name(evsel));
+	int printed = 0;
+
+	if (symbol_conf.event_group) {
+		struct perf_evsel *pos;
+
+		if (!perf_evsel__is_group_leader(evsel))
+			return 0;
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
+
+		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+		for_each_group_member(pos, evsel)
+			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "}");
+		goto out;
+	}
+
+	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
 
 	if (details->verbose || details->freq) {
 		printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
@@ -1405,7 +1450,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 		if_print(bp_type);
 		if_print(branch_sample_type);
 	}
-
+out:
 	fputc('\n', fp);
 	return ++printed;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cbf42322a27..8512f6a8a6e 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -74,10 +74,13 @@ struct perf_evsel {
 	bool 			needs_swap;
 	/* parse modifier helper */
 	int			exclude_GH;
+	int			nr_members;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
 
+#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
+
 struct cpu_map;
 struct thread_map;
 struct perf_evlist;
@@ -111,6 +114,8 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 					    char *bf, size_t size);
 const char *perf_evsel__name(struct perf_evsel *evsel);
+const char *perf_evsel__group_name(struct perf_evsel *evsel);
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
@@ -259,4 +264,15 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 int perf_evsel__open_strerror(struct perf_evsel *evsel,
 			      struct perf_target *target,
 			      int err, char *msg, size_t size);
+
+static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
+{
+	return evsel->idx - evsel->leader->idx;
+}
+
+#define for_each_group_member(_evsel, _leader) 					\
+for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
+     (_evsel) && (_evsel)->leader == (_leader);					\
+     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f6081cb3fca..8022b5254f7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1085,6 +1085,52 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
 }
 
 /*
+ * File format:
+ *
+ * struct group_descs {
+ *	u32	nr_groups;
+ *	struct group_desc {
+ *		char	name[];
+ *		u32	leader_idx;
+ *		u32	nr_members;
+ *	}[nr_groups];
+ * };
+ */
+static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+			    struct perf_evlist *evlist)
+{
+	u32 nr_groups = evlist->nr_groups;
+	struct perf_evsel *evsel;
+	int ret;
+
+	ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			const char *name = evsel->group_name ?: "{anon_group}";
+			u32 leader_idx = evsel->idx;
+			u32 nr_members = evsel->nr_members;
+
+			ret = do_write_string(fd, name);
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &nr_members, sizeof(nr_members));
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(ARCH)/util/header.c
  */
@@ -1447,6 +1493,31 @@ error:
 	fprintf(fp, "# pmu mappings: unable to read\n");
 }
 
+static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
+			     FILE *fp)
+{
+	struct perf_session *session;
+	struct perf_evsel *evsel;
+	u32 nr = 0;
+
+	session = container_of(ph, struct perf_session, header);
+
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
+				perf_evsel__name(evsel));
+
+			nr = evsel->nr_members - 1;
+		} else if (nr) {
+			fprintf(fp, ",%s", perf_evsel__name(evsel));
+
+			if (--nr == 0)
+				fprintf(fp, "}\n");
+		}
+	}
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -1961,6 +2032,98 @@ error:
 	return -1;
 }
 
+static int process_group_desc(struct perf_file_section *section __maybe_unused,
+			      struct perf_header *ph, int fd,
+			      void *data __maybe_unused)
+{
+	size_t ret = -1;
+	u32 i, nr, nr_groups;
+	struct perf_session *session;
+	struct perf_evsel *evsel, *leader = NULL;
+	struct group_desc {
+		char *name;
+		u32 leader_idx;
+		u32 nr_members;
+	} *desc;
+
+	if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
+		return -1;
+
+	if (ph->needs_swap)
+		nr_groups = bswap_32(nr_groups);
+
+	ph->env.nr_groups = nr_groups;
+	if (!nr_groups) {
+		pr_debug("group desc not available\n");
+		return 0;
+	}
+
+	desc = calloc(nr_groups, sizeof(*desc));
+	if (!desc)
+		return -1;
+
+	for (i = 0; i < nr_groups; i++) {
+		desc[i].name = do_read_string(fd, ph);
+		if (!desc[i].name)
+			goto out_free;
+
+		if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (ph->needs_swap) {
+			desc[i].leader_idx = bswap_32(desc[i].leader_idx);
+			desc[i].nr_members = bswap_32(desc[i].nr_members);
+		}
+	}
+
+	/*
+	 * Rebuild group relationship based on the group_desc
+	 */
+	session = container_of(ph, struct perf_session, header);
+	session->evlist->nr_groups = nr_groups;
+
+	i = nr = 0;
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (evsel->idx == (int) desc[i].leader_idx) {
+			evsel->leader = evsel;
+			/* {anon_group} is a dummy name */
+			if (strcmp(desc[i].name, "{anon_group}"))
+				evsel->group_name = desc[i].name;
+			evsel->nr_members = desc[i].nr_members;
+
+			if (i >= nr_groups || nr > 0) {
+				pr_debug("invalid group desc\n");
+				goto out_free;
+			}
+
+			leader = evsel;
+			nr = evsel->nr_members - 1;
+			i++;
+		} else if (nr) {
+			/* This is a group member */
+			evsel->leader = leader;
+
+			nr--;
+		}
+	}
+
+	if (i != nr_groups || nr != 0) {
+		pr_debug("invalid group desc\n");
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	while ((int) --i >= 0)
+		free(desc[i].name);
+	free(desc);
+
+	return ret;
+}
+
 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);
@@ -2000,6 +2163,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
+	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 20f0344accb..c9fc55cada6 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -29,6 +29,7 @@ enum {
 	HEADER_NUMA_TOPOLOGY,
 	HEADER_BRANCH_STACK,
 	HEADER_PMU_MAPPINGS,
+	HEADER_GROUP_DESC,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -79,6 +80,7 @@ struct perf_session_env {
 	char			*numa_nodes;
 	int			nr_pmu_mappings;
 	char			*pmu_mappings;
+	int			nr_groups;
 };
 
 struct perf_header {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8170a3d11ff..f855941bebe 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evsel.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -540,6 +541,62 @@ void hists__collapse_resort_threaded(struct hists *hists)
  * reverse the map, sort on period.
  */
 
+static int period_cmp(u64 period_a, u64 period_b)
+{
+	if (period_a > period_b)
+		return 1;
+	if (period_a < period_b)
+		return -1;
+	return 0;
+}
+
+static int hist_entry__sort_on_period(struct hist_entry *a,
+				      struct hist_entry *b)
+{
+	int ret;
+	int i, nr_members;
+	struct perf_evsel *evsel;
+	struct hist_entry *pair;
+	u64 *periods_a, *periods_b;
+
+	ret = period_cmp(a->stat.period, b->stat.period);
+	if (ret || !symbol_conf.event_group)
+		return ret;
+
+	evsel = hists_to_evsel(a->hists);
+	nr_members = evsel->nr_members;
+	if (nr_members <= 1)
+		return ret;
+
+	periods_a = zalloc(sizeof(periods_a) * nr_members);
+	periods_b = zalloc(sizeof(periods_b) * nr_members);
+
+	if (!periods_a || !periods_b)
+		goto out;
+
+	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period;
+	}
+
+	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		ret = period_cmp(periods_a[i], periods_b[i]);
+		if (ret)
+			break;
+	}
+
+out:
+	free(periods_a);
+	free(periods_b);
+
+	return ret;
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits)
@@ -556,7 +613,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-		if (he->stat.period > iter->stat.period)
+		if (hist_entry__sort_on_period(he, iter) > 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 02f6421f03a..4e0f5c2a9fd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -884,6 +884,7 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	if (!ret) {
 		int entries = data.idx - evlist->nr_entries;
 		perf_evlist__splice_list_tail(evlist, &data.list, entries);
+		evlist->nr_groups += data.nr_groups;
 		return 0;
 	}
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 2cd2c42a69c..8a4859315fd 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -64,6 +64,7 @@ struct parse_events_term {
 struct parse_events_evlist {
 	struct list_head list;
 	int idx;
+	int nr_groups;
 };
 
 struct parse_events_terms {
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9d43c86176f..4de2fdca98c 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -23,6 +23,14 @@ do { \
 		YYABORT; \
 } while (0)
 
+static inc_group_count(struct list_head *list,
+		       struct parse_events_evlist *data)
+{
+	/* Count groups only have more than 1 members */
+	if (!list_is_last(list->next, list))
+		data->nr_groups++;
+}
+
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
@@ -123,6 +131,7 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $3;
 
+	inc_group_count(list, _data);
 	parse_events__set_leader($1, list);
 	$$ = list;
 }
@@ -131,6 +140,7 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $2;
 
+	inc_group_count(list, _data);
 	parse_events__set_leader(NULL, list);
 	$$ = list;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index d97377ac2f1..b62ca37c4b7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -96,7 +96,8 @@ struct symbol_conf {
 			initialized,
 			kptr_restrict,
 			annotate_asm_raw,
-			annotate_src;
+			annotate_src,
+			event_group;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,