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>

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.

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)

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.

arch/powerpc/perf/power7-pmu.c

@@ -50,6 +50,18 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #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
@@ -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,

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		);

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,					\

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],

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]

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);
 }

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()
 	 */