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>

1 files changed, 148 insertions, 158 deletions

diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 1889c12ca81f..a47ce98c2cb1 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)