From 1ab1fa5dfb429c533fbc791e524788cf0cc43775 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 26 Dec 2013 15:11:52 +0900
Subject: perf hists: Add support for showing relative percentage

When filtering by thread, dso or symbol on TUI it also update total
period so that the output shows different result than no filter - the
percentage changed to relative to filtered entries only.  Sometimes
this is not desired since users might expect same results with filter.

So new filtered_* fields to hists->stats to count them separately.
They'll be controlled/used by user later.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1397145720-8063-2-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-report.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c8f21137dfd8..2fca56c9d68a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -123,6 +123,8 @@ static int report__add_mem_hist_entry(struct report *rep, struct addr_location *
 
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	if (!he->filtered)
+		evsel->hists.stats.nr_non_filtered_samples++;
 	err = hist_entry__append_callchain(he, sample);
 out:
 	return err;
@@ -176,6 +178,8 @@ static int report__add_branch_hist_entry(struct report *rep, struct addr_locatio
 
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+			if (!he->filtered)
+				evsel->hists.stats.nr_non_filtered_samples++;
 		} else
 			goto out;
 	}
@@ -209,6 +213,8 @@ static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
 		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
 	evsel->hists.stats.total_period += sample->period;
+	if (!he->filtered)
+		evsel->hists.stats.nr_non_filtered_samples++;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 out:
 	return err;
-- 
cgit v1.2.3


From f2148330544a697481219b5bc34261f6dd049bfb Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 14 Jan 2014 11:52:48 +0900
Subject: perf report: Add --percentage option

The --percentage option is for controlling overhead percentage
displayed.  It can only receive either of "relative" or "absolute".

"relative" means it's relative to filtered entries only so that the
sum of shown entries will be always 100%.  "absolute" means it retains
the original value before and after the filter is applied.

  $ perf report -s comm
  # Overhead       Command
  # ........  ............
  #
      74.19%           cc1
       7.61%           gcc
       6.11%            as
       4.35%            sh
       4.14%          make
       1.13%        fixdep
  ...

  $ perf report -s comm -c cc1,gcc --percentage absolute
  # Overhead       Command
  # ........  ............
  #
      74.19%           cc1
       7.61%           gcc

  $ perf report -s comm -c cc1,gcc --percentage relative
  # Overhead       Command
  # ........  ............
  #
      90.69%           cc1
       9.31%           gcc

Note that it has zero effect if no filter was applied.

Suggested-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1397145720-8063-3-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/Documentation/perf-report.txt | 24 +++++++++++++++-----
 tools/perf/builtin-report.c              | 30 ++++++++++++++++++++++--
 tools/perf/ui/browsers/hists.c           | 35 +++++++++++++++++++++-------
 tools/perf/ui/gtk/hists.c                | 11 ++++-----
 tools/perf/ui/hist.c                     |  8 +++----
 tools/perf/util/hist.c                   | 39 ++++++++++++++++----------------
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/symbol.c                 |  1 +
 tools/perf/util/symbol.h                 |  3 ++-
 9 files changed, 106 insertions(+), 46 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8eab8a4bdeb8..09af66298564 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -25,10 +25,6 @@ OPTIONS
 --verbose::
         Be more verbose. (show symbol address, etc)
 
--d::
---dsos=::
-	Only consider symbols in these dsos. CSV that understands
-	file://filename entries.
 -n::
 --show-nr-samples::
 	Show the number of samples for each symbol
@@ -42,11 +38,18 @@ OPTIONS
 -c::
 --comms=::
 	Only consider symbols in these comms. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage of
+	the overhead column.  See --percentage for more info.
+-d::
+--dsos=::
+	Only consider symbols in these dsos. CSV that understands
+	file://filename entries.  This option will affect the percentage of
+	the overhead column.  See --percentage for more info.
 -S::
 --symbols=::
 	Only consider these symbols. CSV that understands
-	file://filename entries.
+	file://filename entries.  This option will affect the percentage of
+	the overhead column.  See --percentage for more info.
 
 --symbol-filter=::
 	Only show symbols that match (partially) with this filter.
@@ -237,6 +240,15 @@ OPTIONS
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
 
+--percentage::
+	Determine how to display the overhead percentage of filtered entries.
+	Filters can be applied by --comms, --dsos and/or --symbols options and
+	Zoom operations on the TUI (thread, dso, etc).
+
+	"relative" means it's relative to filtered entries only so that the
+	sum of shown entries will be always 100%.  "absolute" means it retains
+	the original value before and after the filter is applied.
+
 --header::
 	Show header information in the perf.data file.  This includes
 	various information like hostname, OS and perf version, cpu/mem
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2fca56c9d68a..7ec351bda833 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -343,6 +343,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	char buf[512];
 	size_t size = sizeof(buf);
 
+	if (symbol_conf.filter_relative) {
+		nr_samples = hists->stats.nr_non_filtered_samples;
+		nr_events = hists->stats.total_non_filtered_period;
+	}
+
 	if (perf_evsel__is_group_event(evsel)) {
 		struct perf_evsel *pos;
 
@@ -350,8 +355,13 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 		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;
+			if (symbol_conf.filter_relative) {
+				nr_samples += pos->hists.stats.nr_non_filtered_samples;
+				nr_events += pos->hists.stats.total_non_filtered_period;
+			} else {
+				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos->hists.stats.total_period;
+			}
 		}
 	}
 
@@ -707,6 +717,20 @@ parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int
+parse_percentage(const struct option *opt __maybe_unused, const char *str,
+		 int unset __maybe_unused)
+{
+	if (!strcmp(str, "relative"))
+		symbol_conf.filter_relative = true;
+	else if (!strcmp(str, "absolute"))
+		symbol_conf.filter_relative = false;
+	else
+		return -1;
+
+	return 0;
+}
+
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
@@ -829,6 +853,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
+	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+		     "how to display percentage of filtered entries", parse_percentage),
 	OPT_END()
 	};
 	struct perf_data_file file = {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7ec871af3f6f..7ad11477a0f5 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -769,12 +769,15 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		float percent = h->stat.period * 100.0 /
-					hb->hists->stats.total_period;
+		u64 total = hists__total_period(h->hists);
+		float percent = 0.0;
 
 		if (h->filtered)
 			continue;
 
+		if (total)
+			percent = h->stat.period * 100.0 / total;
+
 		if (percent < hb->min_pcnt)
 			continue;
 
@@ -792,8 +795,11 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		float percent = h->stat.period * 100.0 /
-					hists->stats.total_period;
+		u64 total = hists__total_period(hists);
+		float percent = 0.0;
+
+		if (total)
+			percent = h->stat.period * 100.0 / total;
 
 		if (percent < min_pcnt)
 			return NULL;
@@ -813,8 +819,11 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		float percent = h->stat.period * 100.0 /
-					hists->stats.total_period;
+		u64 total = hists__total_period(hists);
+		float percent = 0.0;
+
+		if (total)
+			percent = h->stat.period * 100.0 / total;
 
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
@@ -1189,6 +1198,11 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 	char buf[512];
 	size_t buflen = sizeof(buf);
 
+	if (symbol_conf.filter_relative) {
+		nr_samples = hists->stats.nr_non_filtered_samples;
+		nr_events = hists->stats.total_non_filtered_period;
+	}
+
 	if (perf_evsel__is_group_event(evsel)) {
 		struct perf_evsel *pos;
 
@@ -1196,8 +1210,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 		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;
+			if (symbol_conf.filter_relative) {
+				nr_samples += pos->hists.stats.nr_non_filtered_samples;
+				nr_events += pos->hists.stats.total_non_filtered_period;
+			} else {
+				nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos->hists.stats.total_period;
+			}
 		}
 	}
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index e395ef9b0ae0..91f10f3f6dd1 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -228,12 +228,15 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		GtkTreeIter iter;
-		float percent = h->stat.period * 100.0 /
-					hists->stats.total_period;
+		u64 total = hists__total_period(h->hists);
+		float percent = 0.0;
 
 		if (h->filtered)
 			continue;
 
+		if (total)
+			percent = h->stat.period * 100.0 / total;
+
 		if (percent < min_pcnt)
 			continue;
 
@@ -261,12 +264,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		}
 
 		if (symbol_conf.use_callchain && sort__has_sym) {
-			u64 total;
-
 			if (callchain_param.mode == CHAIN_GRAPH_REL)
 				total = h->stat.period;
-			else
-				total = hists->stats.total_period;
 
 			perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
 						sym_col, total);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 0f403b83e9d1..0912805c08f4 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -32,10 +32,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 
 	if (fmt_percent) {
 		double percent = 0.0;
+		u64 total = hists__total_period(hists);
 
-		if (hists->stats.total_period)
-			percent = 100.0 * get_field(he) /
-				  hists->stats.total_period;
+		if (total)
+			percent = 100.0 * get_field(he) / total;
 
 		ret += hpp__call_print_fn(hpp, print_fn, fmt, percent);
 	} else
@@ -50,7 +50,7 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 
 		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
 			u64 period = get_field(pair);
-			u64 total = pair->hists->stats.total_period;
+			u64 total = hists__total_period(pair->hists);
 
 			if (!total)
 				continue;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 1ed3e2b86f0b..3ebd89a28257 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -321,9 +321,11 @@ void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
 {
 	if (!h->filtered) {
 		hists__calc_col_len(hists, h);
-		++hists->nr_entries;
-		hists->stats.total_period += h->stat.period;
+		hists->nr_non_filtered_entries++;
+		hists->stats.total_non_filtered_period += h->stat.period;
 	}
+	hists->nr_entries++;
+	hists->stats.total_period += h->stat.period;
 }
 
 static u8 symbol__parent_filter(const struct symbol *parent)
@@ -674,8 +676,9 @@ void hists__output_resort(struct hists *hists)
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists->nr_entries = hists->nr_non_filtered_entries = 0;
-	hists->stats.total_period = hists->stats.total_non_filtered_period = 0;
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_period = 0;
+	hists->stats.total_non_filtered_period = 0;
 	hists__reset_col_len(hists);
 
 	while (next) {
@@ -694,16 +697,11 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 	if (h->filtered)
 		return;
 
-	++hists->nr_entries;
 	++hists->nr_non_filtered_entries;
-	if (h->ms.unfolded) {
-		hists->nr_entries += h->nr_rows;
+	if (h->ms.unfolded)
 		hists->nr_non_filtered_entries += h->nr_rows;
-	}
 	h->row_offset = 0;
-	hists->stats.total_period += h->stat.period;
 	hists->stats.total_non_filtered_period += h->stat.period;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events;
 	hists->stats.nr_non_filtered_samples += h->stat.nr_events;
 
 	hists__calc_col_len(hists, h);
@@ -726,9 +724,8 @@ void hists__filter_by_dso(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	hists->nr_entries = hists->stats.total_period = 0;
-	hists->nr_non_filtered_entries = hists->stats.total_non_filtered_period = 0;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_non_filtered_period = 0;
 	hists->stats.nr_non_filtered_samples = 0;
 	hists__reset_col_len(hists);
 
@@ -761,9 +758,8 @@ void hists__filter_by_thread(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	hists->nr_entries = hists->stats.total_period = 0;
-	hists->nr_non_filtered_entries = hists->stats.total_non_filtered_period = 0;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_non_filtered_period = 0;
 	hists->stats.nr_non_filtered_samples = 0;
 	hists__reset_col_len(hists);
 
@@ -794,9 +790,8 @@ void hists__filter_by_symbol(struct hists *hists)
 {
 	struct rb_node *nd;
 
-	hists->nr_entries = hists->stats.total_period = 0;
-	hists->nr_non_filtered_entries = hists->stats.total_non_filtered_period = 0;
-	hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+	hists->nr_non_filtered_entries = 0;
+	hists->stats.total_non_filtered_period = 0;
 	hists->stats.nr_non_filtered_samples = 0;
 	hists__reset_col_len(hists);
 
@@ -942,3 +937,9 @@ int hists__link(struct hists *leader, struct hists *other)
 
 	return 0;
 }
+
+u64 hists__total_period(struct hists *hists)
+{
+	return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
+		hists->stats.total_period;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 213551469f36..3191496bd3b7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -115,6 +115,7 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
+u64 hists__total_period(struct hists *hists);
 void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
 void events_stats__inc(struct events_stats *stats, u32 type);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 95e249779931..b2eca6c17a70 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -33,6 +33,7 @@ struct symbol_conf symbol_conf = {
 	.try_vmlinux_path = true,
 	.annotate_src	  = true,
 	.demangle	  = true,
+	.filter_relative  = true,
 	.symfs            = "",
 };
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 501e4e722e8e..ae94e006a52d 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -115,7 +115,8 @@ struct symbol_conf {
 			annotate_asm_raw,
 			annotate_src,
 			event_group,
-			demangle;
+			demangle,
+			filter_relative;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-- 
cgit v1.2.3


From 33db4568e1f41efe6d0e4695483f968fc1135bf3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 7 Feb 2014 12:06:07 +0900
Subject: perf top: Add --percentage option

The --percentage option is for controlling overhead percentage
displayed.  It can only receive either of "relative" or "absolute".
Move the parser callback function into a common location since it's
used by multiple commands now.

For more information, please see previous commit same thing done to
"perf report".

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1397145720-8063-4-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/Documentation/perf-top.txt | 18 +++++++++++++++---
 tools/perf/builtin-report.c           | 16 +---------------
 tools/perf/builtin-top.c              |  5 +++--
 tools/perf/util/hist.c                | 13 +++++++++++++
 tools/perf/util/hist.h                |  5 +++++
 5 files changed, 37 insertions(+), 20 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 976b00c6cdb1..64ed79c43639 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -123,13 +123,16 @@ Default is to monitor all CPUS.
 	Show a column with the sum of periods.
 
 --dsos::
-	Only consider symbols in these dsos.
+	Only consider symbols in these dsos.  This option will affect the
+	percentage of the overhead column.  See --percentage for more info.
 
 --comms::
-	Only consider symbols in these comms.
+	Only consider symbols in these comms.  This option will affect the
+	percentage of the overhead column.  See --percentage for more info.
 
 --symbols::
-	Only consider these symbols.
+	Only consider these symbols.  This option will affect the
+	percentage of the overhead column.  See --percentage for more info.
 
 -M::
 --disassembler-style=:: Set disassembler style for objdump.
@@ -165,6 +168,15 @@ Default is to monitor all CPUS.
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
 
+--percentage::
+	Determine how to display the overhead percentage of filtered entries.
+	Filters can be applied by --comms, --dsos and/or --symbols options and
+	Zoom operations on the TUI (thread, dso, etc).
+
+	"relative" means it's relative to filtered entries only so that the
+	sum of shown entries will be always 100%. "absolute" means it retains
+	the original value before and after the filter is applied.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7ec351bda833..af8cb7a2c9b6 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -717,20 +717,6 @@ parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
-static int
-parse_percentage(const struct option *opt __maybe_unused, const char *str,
-		 int unset __maybe_unused)
-{
-	if (!strcmp(str, "relative"))
-		symbol_conf.filter_relative = true;
-	else if (!strcmp(str, "absolute"))
-		symbol_conf.filter_relative = false;
-	else
-		return -1;
-
-	return 0;
-}
-
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
@@ -854,7 +840,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
-		     "how to display percentage of filtered entries", parse_percentage),
+		     "how to display percentage of filtered entries", parse_filter_percentage),
 	OPT_END()
 	};
 	struct perf_data_file file = {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 25269014164a..37d30460bada 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -697,8 +697,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
 		top->exact_samples++;
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0 ||
-	    al.filtered)
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0)
 		return;
 
 	if (!top->kptr_restrict_warned &&
@@ -1119,6 +1118,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_CALLBACK(0, "percent-limit", &top, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
+	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
+		     "How to display percentage of filtered entries", parse_filter_percentage),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3ebd89a28257..3c2dd233b98e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -943,3 +943,16 @@ u64 hists__total_period(struct hists *hists)
 	return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
 		hists->stats.total_period;
 }
+
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused)
+{
+	if (!strcmp(arg, "relative"))
+		symbol_conf.filter_relative = true;
+	else if (!strcmp(arg, "absolute"))
+		symbol_conf.filter_relative = false;
+	else
+		return -1;
+
+	return 0;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 3191496bd3b7..a4ec336ae3fe 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -254,4 +254,9 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+
+struct option;
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+			    const char *arg, int unset __maybe_unused);
+
 #endif	/* __PERF_HIST_H */
-- 
cgit v1.2.3


From cff6bb46d477383092f46682a0d12e323e4b84d2 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Mon, 7 Apr 2014 14:55:24 -0400
Subject: perf callchain: Add generic report parse callchain callback function

This takes the parse_callchain_opt function and copies it into the
callchain.c file.  Now the c2c tool can use it too without duplicating.

Update perf-report to use the new routine too.

Signed-off-by: Don Zickus <dzickus@redhat.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1396896924-129847-5-git-send-email-dzickus@redhat.com
[ Adding missing braces to multiline if condition ]
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-report.c | 81 ++-------------------------------------------
 tools/perf/util/callchain.c | 78 +++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/callchain.h |  1 +
 3 files changed, 82 insertions(+), 78 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index af8cb7a2c9b6..76e2bb6cf571 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -589,11 +589,9 @@ static int __cmd_report(struct report *rep)
 }
 
 static int
-parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
 	struct report *rep = (struct report *)opt->value;
-	char *tok, *tok2;
-	char *endptr;
 
 	/*
 	 * --no-call-graph
@@ -603,80 +601,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 		return 0;
 	}
 
-	symbol_conf.use_callchain = true;
-
-	if (!arg)
-		return 0;
-
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
-
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_ABS;
-
-	else if (!strncmp(tok, "flat", strlen(arg)))
-		callchain_param.mode = CHAIN_FLAT;
-
-	else if (!strncmp(tok, "fractal", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_REL;
-
-	else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
-
-		return 0;
-	}
-
-	else
-		return -1;
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
-
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
-
-	/* get the print limit */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-
-	if (tok2[0] != 'c') {
-		callchain_param.print_limit = strtoul(tok2, &endptr, 0);
-		tok2 = strtok(NULL, ",");
-		if (!tok2)
-			goto setup;
-	}
-
-	/* get the call chain order */
-	if (!strncmp(tok2, "caller", strlen("caller")))
-		callchain_param.order = ORDER_CALLER;
-	else if (!strncmp(tok2, "callee", strlen("callee")))
-		callchain_param.order = ORDER_CALLEE;
-	else
-		return -1;
-
-	/* Get the sort key */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-	if (!strncmp(tok2, "function", strlen("function")))
-		callchain_param.key = CCKEY_FUNCTION;
-	else if (!strncmp(tok2, "address", strlen("address")))
-		callchain_param.key = CCKEY_ADDRESS;
-	else
-		return -1;
-setup:
-	if (callchain_register_param(&callchain_param) < 0) {
-		pr_err("Can't register callchain params\n");
-		return -1;
-	}
-	return 0;
+	return parse_callchain_report_opt(arg);
 }
 
 int
@@ -788,7 +713,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Only display entries with parent-match"),
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
 		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
-		     "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
+		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8d9db454f1a9..9a42382b3921 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,6 +25,84 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
+int
+parse_callchain_report_opt(const char *arg)
+{
+	char *tok, *tok2;
+	char *endptr;
+
+	symbol_conf.use_callchain = true;
+
+	if (!arg)
+		return 0;
+
+	tok = strtok((char *)arg, ",");
+	if (!tok)
+		return -1;
+
+	/* get the output mode */
+	if (!strncmp(tok, "graph", strlen(arg))) {
+		callchain_param.mode = CHAIN_GRAPH_ABS;
+
+	} else if (!strncmp(tok, "flat", strlen(arg))) {
+		callchain_param.mode = CHAIN_FLAT;
+	} else if (!strncmp(tok, "fractal", strlen(arg))) {
+		callchain_param.mode = CHAIN_GRAPH_REL;
+	} else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		symbol_conf.use_callchain = false;
+		return 0;
+	} else {
+		return -1;
+	}
+
+	/* get the min percentage */
+	tok = strtok(NULL, ",");
+	if (!tok)
+		goto setup;
+
+	callchain_param.min_percent = strtod(tok, &endptr);
+	if (tok == endptr)
+		return -1;
+
+	/* get the print limit */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+
+	if (tok2[0] != 'c') {
+		callchain_param.print_limit = strtoul(tok2, &endptr, 0);
+		tok2 = strtok(NULL, ",");
+		if (!tok2)
+			goto setup;
+	}
+
+	/* get the call chain order */
+	if (!strncmp(tok2, "caller", strlen("caller")))
+		callchain_param.order = ORDER_CALLER;
+	else if (!strncmp(tok2, "callee", strlen("callee")))
+		callchain_param.order = ORDER_CALLEE;
+	else
+		return -1;
+
+	/* Get the sort key */
+	tok2 = strtok(NULL, ",");
+	if (!tok2)
+		goto setup;
+	if (!strncmp(tok2, "function", strlen("function")))
+		callchain_param.key = CCKEY_FUNCTION;
+	else if (!strncmp(tok2, "address", strlen("address")))
+		callchain_param.key = CCKEY_ADDRESS;
+	else
+		return -1;
+setup:
+	if (callchain_register_param(&callchain_param) < 0) {
+		pr_err("Can't register callchain params\n");
+		return -1;
+	}
+	return 0;
+}
+
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 		    enum chain_mode mode)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8ad97e9b119f..dda4cf8b534c 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -157,4 +157,5 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
 
 extern const char record_callchain_help[];
+int parse_callchain_report_opt(const char *arg);
 #endif	/* __PERF_CALLCHAIN_H */
-- 
cgit v1.2.3


From 58c311da9cec97d7a665156a726bd1653384c65c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 22 Apr 2014 09:47:25 +0900
Subject: perf report: Count number of entries separately

The hists->nr_entries is counted in multiple places so that they can
confuse readers of the code.  This is a preparation of later change
and do not intend any functional difference.

Note that report__collapse_hists() now changed to return nothing since
its return value (nr_samples) is only for checking if there's any data
in the input file and this can be acheived by checking ->nr_entries.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1398327843-31845-2-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-report.c | 42 ++++++++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 20 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76e2bb6cf571..aed52036468d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -57,6 +57,7 @@ struct report {
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
 	float			min_percent;
+	u64			nr_entries;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
@@ -75,6 +76,17 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
+{
+	/*
+	 * The @he is either of a newly created one or an existing one
+	 * merging current sample.  We only want to count a new one so
+	 * checking ->nr_events being 1.
+	 */
+	if (he->stat.nr_events == 1)
+		rep->nr_entries++;
+}
+
 static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
 				      struct perf_sample *sample, struct perf_evsel *evsel)
 {
@@ -121,6 +133,8 @@ static int report__add_mem_hist_entry(struct report *rep, struct addr_location *
 			goto out;
 	}
 
+	report__inc_stats(rep, he);
+
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 	if (!he->filtered)
@@ -176,6 +190,8 @@ static int report__add_branch_hist_entry(struct report *rep, struct addr_locatio
 					goto out;
 			}
 
+			report__inc_stats(rep, he);
+
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 			if (!he->filtered)
@@ -212,6 +228,8 @@ static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
 	if (ui__has_annotation())
 		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
+	report__inc_stats(rep, he);
+
 	evsel->hists.stats.total_period += sample->period;
 	if (!he->filtered)
 		evsel->hists.stats.nr_non_filtered_samples++;
@@ -486,24 +504,12 @@ static int report__browse_hists(struct report *rep)
 	return ret;
 }
 
-static u64 report__collapse_hists(struct report *rep)
+static void report__collapse_hists(struct report *rep)
 {
 	struct ui_progress prog;
 	struct perf_evsel *pos;
-	u64 nr_samples = 0;
-	/*
- 	 * Count number of histogram entries to use when showing progress,
- 	 * reusing nr_samples variable.
- 	 */
-	evlist__for_each(rep->session->evlist, pos)
-		nr_samples += pos->hists.nr_entries;
 
-	ui_progress__init(&prog, nr_samples, "Merging related events...");
-	/*
-	 * Count total number of samples, will be used to check if this
- 	 * session had any.
- 	 */
-	nr_samples = 0;
+	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
 	evlist__for_each(rep->session->evlist, pos) {
 		struct hists *hists = &pos->hists;
@@ -512,7 +518,6 @@ static u64 report__collapse_hists(struct report *rep)
 			hists->symbol_filter_str = rep->symbol_filter_str;
 
 		hists__collapse_resort(hists, &prog);
-		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
 		/* Non-group events are considered as leader */
 		if (symbol_conf.event_group &&
@@ -525,14 +530,11 @@ static u64 report__collapse_hists(struct report *rep)
 	}
 
 	ui_progress__finish();
-
-	return nr_samples;
 }
 
 static int __cmd_report(struct report *rep)
 {
 	int ret;
-	u64 nr_samples;
 	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
 	struct perf_data_file *file = session->file;
@@ -572,12 +574,12 @@ static int __cmd_report(struct report *rep)
 		}
 	}
 
-	nr_samples = report__collapse_hists(rep);
+	report__collapse_hists(rep);
 
 	if (session_done())
 		return 0;
 
-	if (nr_samples == 0) {
+	if (rep->nr_entries == 0) {
 		ui__error("The %s file has no samples!\n", file->path);
 		return 0;
 	}
-- 
cgit v1.2.3


From 820bc81f4cdaac09a8f25040d3a20d86f3da292b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 22 Apr 2014 11:44:21 +0900
Subject: perf tools: Account entry stats when it's added to the output tree

Currently, accounting each sample is done in multiple places - once
when adding them to the input tree, other when adding them to the
output tree.  It's not only confusing but also can cause a subtle
problem since concurrent processing like in perf top might see the
updated stats before adding entries into the output tree - like seeing
more (blank) lines at the end and/or slight inaccurate percentage.

To fix this, only account the entries when it's moved into the output
tree so that they cannot be seen prematurely.  There're some
exceptional cases here and there - they should be addressed separately
with comments.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1398327843-31845-7-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-annotate.c |  3 +--
 tools/perf/builtin-diff.c     | 13 +++++++++----
 tools/perf/builtin-report.c   | 24 ++++++++++--------------
 tools/perf/util/hist.c        |  1 -
 4 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 0da603b79b61..d30d2c2e2a7a 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -46,7 +46,7 @@ struct perf_annotate {
 };
 
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
-				  struct perf_sample *sample,
+				  struct perf_sample *sample __maybe_unused,
 				  struct addr_location *al,
 				  struct perf_annotate *ann)
 {
@@ -70,7 +70,6 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 	return ret;
 }
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 52d91ac4e6c8..f3b10dcf6838 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -341,11 +341,16 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	if (al.filtered == 0) {
-		evsel->hists.stats.total_non_filtered_period += sample->period;
-		evsel->hists.nr_non_filtered_entries++;
-	}
+	/*
+	 * The total_period is updated here before going to the output
+	 * tree since normally only the baseline hists will call
+	 * hists__output_resort() and precompute needs the total
+	 * period in order to sort entries by percentage delta.
+	 */
 	evsel->hists.stats.total_period += sample->period;
+	if (!al.filtered)
+		evsel->hists.stats.total_non_filtered_period += sample->period;
+
 	return 0;
 }
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index aed52036468d..89c95289fd51 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -85,6 +85,16 @@ static void report__inc_stats(struct report *rep, struct hist_entry *he)
 	 */
 	if (he->stat.nr_events == 1)
 		rep->nr_entries++;
+
+	/*
+	 * Only counts number of samples at this stage as it's more
+	 * natural to do it here and non-sample events are also
+	 * counted in perf_session_deliver_event().  The dump_trace
+	 * requires this info is ready before going to the output tree.
+	 */
+	hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
+	if (!he->filtered)
+		he->hists->stats.nr_non_filtered_samples++;
 }
 
 static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
@@ -135,10 +145,6 @@ static int report__add_mem_hist_entry(struct report *rep, struct addr_location *
 
 	report__inc_stats(rep, he);
 
-	evsel->hists.stats.total_period += cost;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
 	err = hist_entry__append_callchain(he, sample);
 out:
 	return err;
@@ -189,13 +195,7 @@ static int report__add_branch_hist_entry(struct report *rep, struct addr_locatio
 				if (err)
 					goto out;
 			}
-
 			report__inc_stats(rep, he);
-
-			evsel->hists.stats.total_period += 1;
-			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-			if (!he->filtered)
-				evsel->hists.stats.nr_non_filtered_samples++;
 		} else
 			goto out;
 	}
@@ -230,10 +230,6 @@ static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
 
 	report__inc_stats(rep, he);
 
-	evsel->hists.stats.total_period += sample->period;
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 out:
 	return err;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8d5cfcc3bc63..6d0d2d75db68 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -382,7 +382,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
-	hists->nr_entries++;
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-- 
cgit v1.2.3


From a2ce067e55e328f1a6fe3dddf77a173381ffdfe1 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 4 Mar 2014 09:06:42 +0900
Subject: perf tools: Allow hpp fields to be sort keys

Add overhead{,_sys,_us,_guest_sys,_guest_us}, sample and period sort
keys so that they can be selected with --sort/-s option.

  $ perf report -s period,comm --stdio
  ...
  # Overhead        Period          Command
  # ........  ............  ...............
  #
      47.06%           152          swapper
      13.93%            45  qemu-system-arm
      12.38%            40         synergys
       3.72%            12          firefox
       2.48%             8            xchat

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1400480762-22852-9-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/Documentation/perf-diff.txt   |  5 ++--
 tools/perf/Documentation/perf-report.txt |  9 ++++++++
 tools/perf/Documentation/perf-top.txt    |  5 ++--
 tools/perf/builtin-diff.c                |  3 ++-
 tools/perf/builtin-report.c              |  6 ++---
 tools/perf/builtin-top.c                 |  4 ++--
 tools/perf/ui/hist.c                     |  9 ++++++--
 tools/perf/util/sort.c                   | 39 ++++++++++++++++++++++++++++++++
 8 files changed, 67 insertions(+), 13 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index fbfa1192923c..b3b8abae62b8 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -50,7 +50,8 @@ OPTIONS
 
 -s::
 --sort=::
-	Sort by key(s): pid, comm, dso, symbol.
+	Sort by key(s): pid, comm, dso, symbol, cpu, parent, srcline.
+	Please see description of --sort in the perf-report man page.
 
 -t::
 --field-separator=::
@@ -202,4 +203,4 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as:
 
 SEE ALSO
 --------
-linkperf:perf-record[1]
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 09af66298564..9babe915b6c4 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -79,6 +79,15 @@ OPTIONS
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
 	- transaction: Transaction abort flags.
+	- overhead: Overhead percentage of sample
+	- overhead_sys: Overhead percentage of sample running in system mode
+	- overhead_us: Overhead percentage of sample running in user mode
+	- overhead_guest_sys: Overhead percentage of sample running in system mode
+	on guest machine
+	- overhead_guest_us: Overhead percentage of sample running in user mode on
+	guest machine
+	- sample: Number of sample
+	- period: Raw number of event count of sample
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 64ed79c43639..df863288752a 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -113,7 +113,8 @@ Default is to monitor all CPUS.
 -s::
 --sort::
 	Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight,
-	local_weight, abort, in_tx, transaction
+	local_weight, abort, in_tx, transaction, overhead, sample, period.
+	Please see description of --sort in the perf-report man page.
 
 -n::
 --show-nr-samples::
@@ -212,4 +213,4 @@ Pressing any unmapped key displays a menu, and prompts for input.
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-list[1]
+linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-report[1]
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f3b10dcf6838..b60c711d4e72 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -741,7 +741,8 @@ static const struct option options[] = {
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
 	OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 89c95289fd51..d0180d5de781 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -699,10 +699,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "header-only", &report.header_only,
 		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
-		   " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
-		   " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
-		   "snoop, locked, abort, in_tx, transaction"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 37d30460bada..4fef1e415129 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1083,8 +1083,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight,"
-		   " abort, in_tx, transaction"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
+		   " Please refer the man page for the complete list."),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
 	OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index e7ac794382c1..24116a48298f 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -346,8 +346,13 @@ void perf_hpp__init(void)
 	int i;
 
 	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		INIT_LIST_HEAD(&perf_hpp__format[i].list);
-		INIT_LIST_HEAD(&perf_hpp__format[i].sort_list);
+		struct perf_hpp_fmt *fmt = &perf_hpp__format[i];
+
+		INIT_LIST_HEAD(&fmt->list);
+
+		/* sort_list may be linked by setup_sorting() */
+		if (fmt->sort_list.next == NULL)
+			INIT_LIST_HEAD(&fmt->sort_list);
 	}
 
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b2829f947053..916652af8304 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1028,6 +1028,26 @@ static struct sort_dimension memory_sort_dimensions[] = {
 
 #undef DIM
 
+struct hpp_dimension {
+	const char		*name;
+	struct perf_hpp_fmt	*fmt;
+	int			taken;
+};
+
+#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
+
+static struct hpp_dimension hpp_sort_dimensions[] = {
+	DIM(PERF_HPP__OVERHEAD, "overhead"),
+	DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"),
+	DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
+	DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
+	DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+	DIM(PERF_HPP__SAMPLES, "sample"),
+	DIM(PERF_HPP__PERIOD, "period"),
+};
+
+#undef DIM
+
 struct hpp_sort_entry {
 	struct perf_hpp_fmt hpp;
 	struct sort_entry *se;
@@ -1115,6 +1135,16 @@ static int __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
 	return 0;
 }
 
+static int __hpp_dimension__add(struct hpp_dimension *hd)
+{
+	if (!hd->taken) {
+		hd->taken = 1;
+
+		perf_hpp__register_sort_field(hd->fmt);
+	}
+	return 0;
+}
+
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
@@ -1144,6 +1174,15 @@ int sort_dimension__add(const char *tok)
 		return __sort_dimension__add(sd, i);
 	}
 
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+		if (strncasecmp(tok, hd->name, strlen(tok)))
+			continue;
+
+		return __hpp_dimension__add(hd);
+	}
+
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
 		struct sort_dimension *sd = &bstack_sort_dimensions[i];
 
-- 
cgit v1.2.3


From 512ae1bd6acb811c72e44e2540099eccd31f773d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 18 Mar 2014 11:31:39 +0900
Subject: perf tools: Consolidate management of default sort orders

The perf uses different default sort orders for different use-cases,
and this was scattered throughout the code.  Add get_default_sort_
order() function to handle this and change initial value of sort_order
to NULL to distinguish it from user-given one.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1400480762-22852-10-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-diff.c   |  4 ++--
 tools/perf/builtin-report.c | 18 ------------------
 tools/perf/builtin-top.c    |  3 +--
 tools/perf/util/sort.c      | 28 ++++++++++++++++++++++++++--
 tools/perf/util/sort.h      |  2 ++
 5 files changed, 31 insertions(+), 24 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index b60c711d4e72..8bff543acaab 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -60,7 +60,6 @@ static int data__files_cnt;
 #define data__for_each_file(i, d) data__for_each_file_start(i, d, 0)
 #define data__for_each_file_new(i, d) data__for_each_file_start(i, d, 1)
 
-static char diff__default_sort_order[] = "dso,symbol";
 static bool force;
 static bool show_period;
 static bool show_formula;
@@ -1142,7 +1141,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	perf_config(perf_default_config, NULL);
 
-	sort_order = diff__default_sort_order;
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
 	if (symbol__init() < 0)
@@ -1153,6 +1151,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	ui_init();
 
+	sort__mode = SORT_MODE__DIFF;
+
 	if (setup_sorting() < 0)
 		usage_with_options(diff_usage, options);
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d0180d5de781..f4d640cfdf16 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -805,30 +805,12 @@ repeat:
 	if (branch_mode == -1 && has_br_stack)
 		sort__mode = SORT_MODE__BRANCH;
 
-	/* sort__mode could be NORMAL if --no-branch-stack */
-	if (sort__mode == SORT_MODE__BRANCH) {
-		/*
-		 * if no sort_order is provided, then specify
-		 * branch-mode specific order
-		 */
-		if (sort_order == default_sort_order)
-			sort_order = "comm,dso_from,symbol_from,"
-				     "dso_to,symbol_to";
-
-	}
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
 			pr_err("branch and mem mode incompatible\n");
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
-
-		/*
-		 * if no sort_order is provided, then specify
-		 * branch-mode specific order
-		 */
-		if (sort_order == default_sort_order)
-			sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
 	}
 
 	if (setup_sorting() < 0) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 4fef1e415129..34764b6eabf9 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1137,8 +1137,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (argc)
 		usage_with_options(top_usage, options);
 
-	if (sort_order == default_sort_order)
-		sort_order = "dso,symbol";
+	sort__mode = SORT_MODE__TOP;
 
 	if (setup_sorting() < 0) {
 		parse_options_usage(top_usage, options, "s", 1);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 916652af8304..d64c1e58f1b1 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -8,7 +8,11 @@ regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char	*parent_pattern = default_parent_pattern;
 const char	default_sort_order[] = "comm,dso,symbol";
-const char	*sort_order = default_sort_order;
+const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to";
+const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+const char	default_top_sort_order[] = "dso,symbol";
+const char	default_diff_sort_order[] = "dso,symbol";
+const char	*sort_order;
 regex_t		ignore_callees_regex;
 int		have_ignore_callees = 0;
 int		sort__need_collapse = 0;
@@ -1218,11 +1222,31 @@ int sort_dimension__add(const char *tok)
 	return -ESRCH;
 }
 
+static const char *get_default_sort_order(void)
+{
+	const char *default_sort_orders[] = {
+		default_sort_order,
+		default_branch_sort_order,
+		default_mem_sort_order,
+		default_top_sort_order,
+		default_diff_sort_order,
+	};
+
+	BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
+
+	return default_sort_orders[sort__mode];
+}
+
 int setup_sorting(void)
 {
-	char *tmp, *tok, *str = strdup(sort_order);
+	char *tmp, *tok, *str;
+	const char *sort_keys = sort_order;
 	int ret = 0;
 
+	if (sort_keys == NULL)
+		sort_keys = get_default_sort_order();
+
+	str = strdup(sort_keys);
 	if (str == NULL) {
 		error("Not enough memory to setup sort keys");
 		return -ENOMEM;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 43e5ff42a609..1a7295255dc9 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -133,6 +133,8 @@ enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
 	SORT_MODE__MEMORY,
+	SORT_MODE__TOP,
+	SORT_MODE__DIFF,
 };
 
 enum sort_type {
-- 
cgit v1.2.3


From 22af969e8cfc6ea46d3e1a774a16d7e19b8cf4db Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 16 Apr 2014 11:04:51 +0900
Subject: perf tools: Call perf_hpp__init() before setting up GUI browsers

So that it can be set properly prior to set up output fields.  That
makes easy to handle/warn errors during the setup since it doesn't
need to be bothered with the GUI.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1400480762-22852-11-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-report.c    | 6 +++---
 tools/perf/builtin-top.c       | 2 ++
 tools/perf/ui/browsers/hists.c | 2 --
 tools/perf/ui/gtk/hists.c      | 2 --
 tools/perf/ui/setup.c          | 2 --
 5 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f4d640cfdf16..c4dab7acbdbb 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -823,16 +823,16 @@ repeat:
 			goto error;
 	}
 
+	perf_hpp__init();
+
 	/* Force tty output for header output. */
 	if (report.header || report.header_only)
 		use_browser = 0;
 
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
-	else {
+	else
 		use_browser = 0;
-		perf_hpp__init();
-	}
 
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 34764b6eabf9..280945bab66d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1147,6 +1147,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	/* display thread wants entries to be collapsed in a different tree */
 	sort__need_collapse = 1;
 
+	perf_hpp__init();
+
 	if (top.use_stdio)
 		use_browser = 0;
 	else if (top.use_tui)
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 37c5188fd68a..92d128f3acdc 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -661,8 +661,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
 
 void hist_browser__init_hpp(void)
 {
-	perf_hpp__init();
-
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
 				hist_browser__hpp_color_overhead;
 	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 2237245bfac0..fd52669018ee 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -58,8 +58,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
 
 void perf_gtk__init_hpp(void)
 {
-	perf_hpp__init();
-
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
 				perf_gtk__hpp_color_overhead;
 	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 5df5140a9f29..ba51fa8a1176 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -86,8 +86,6 @@ void setup_browser(bool fallback_to_pager)
 		use_browser = 0;
 		if (fallback_to_pager)
 			setup_pager();
-
-		perf_hpp__init();
 		break;
 	}
 }
-- 
cgit v1.2.3


From a7d945bc91602f916d2d0c794c179d9a784859e7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 4 Mar 2014 10:46:34 +0900
Subject: perf report: Add -F option to specify output fields

The -F/--fields option is to allow user setup output field in any
order.  It can receive any sort keys and following (hpp) fields:

  overhead, overhead_sys, overhead_us, sample and period

If guest profiling is enabled, overhead_guest_{sys,us} will be
available too.

The output fields also affect sort order unless you give -s/--sort
option.  And any keys specified on -s option, will also be added to
the output field list automatically.

  $ perf report -F sym,sample,overhead
  ...
  #                     Symbol       Samples  Overhead
  # ..........................  ............  ........
  #
    [.] __cxa_atexit                       2     2.50%
    [.] __libc_csu_init                    4     5.00%
    [.] __new_exitfn                       3     3.75%
    [.] _dl_check_map_versions             1     1.25%
    [.] _dl_name_match_p                   4     5.00%
    [.] _dl_setup_hash                     1     1.25%
    [.] _dl_sysdep_start                   1     1.25%
    [.] _init                              5     6.25%
    [.] _setjmp                            6     7.50%
    [.] a                                  8    10.00%
    [.] b                                  8    10.00%
    [.] brk                                1     1.25%
    [.] c                                  8    10.00%

Note that, the example output above is captured after applying next
patch which fixes sort/comparing behavior.

Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1400480762-22852-12-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/Documentation/perf-report.txt |  10 ++
 tools/perf/builtin-report.c              |  15 ++-
 tools/perf/ui/hist.c                     |  59 ++++++++-
 tools/perf/util/hist.h                   |   4 +
 tools/perf/util/sort.c                   | 209 ++++++++++++++++++++++++++++++-
 tools/perf/util/sort.h                   |   2 +
 6 files changed, 282 insertions(+), 17 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9babe915b6c4..a1b5185402d5 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -107,6 +107,16 @@ OPTIONS
 	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 	and symbol_to, see '--branch-stack'.
 
+-F::
+--fields=::
+	Specify output field - multiple keys can be specified in CSV format.
+	Following fields are available:
+	overhead, overhead_sys, overhead_us, sample and period.
+	Also it can contain any sort key(s).
+
+	By default, every sort keys not specified in -F will be appended
+	automatically.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c4dab7acbdbb..bc0eec1ce4be 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -701,6 +701,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
 		   " Please refer the man page for the complete list."),
+	OPT_STRING('F', "fields", &field_order, "key[,keys...]",
+		   "output field(s): overhead, period, sample plus all of sort keys"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -814,17 +816,14 @@ repeat:
 	}
 
 	if (setup_sorting() < 0) {
-		parse_options_usage(report_usage, options, "s", 1);
+		if (sort_order)
+			parse_options_usage(report_usage, options, "s", 1);
+		if (field_order)
+			parse_options_usage(sort_order ? NULL : report_usage,
+					    options, "F", 1);
 		goto error;
 	}
 
-	if (parent_pattern != default_parent_pattern) {
-		if (sort_dimension__add("parent") < 0)
-			goto error;
-	}
-
-	perf_hpp__init();
-
 	/* Force tty output for header output. */
 	if (report.header || report.header_only)
 		use_browser = 0;
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 24116a48298f..b114c6668865 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -355,6 +355,12 @@ void perf_hpp__init(void)
 			INIT_LIST_HEAD(&fmt->sort_list);
 	}
 
+	/*
+	 * If user specified field order, no need to setup default fields.
+	 */
+	if (field_order)
+		return;
+
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 
 	if (symbol_conf.show_cpu_utilization) {
@@ -377,8 +383,6 @@ void perf_hpp__init(void)
 	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
 	if (list_empty(list))
 		list_add(list, &perf_hpp__sort_list);
-
-	perf_hpp__setup_output_field();
 }
 
 void perf_hpp__column_register(struct perf_hpp_fmt *format)
@@ -403,8 +407,55 @@ void perf_hpp__setup_output_field(void)
 
 	/* append sort keys to output field */
 	perf_hpp__for_each_sort_list(fmt) {
-		if (list_empty(&fmt->list))
-			perf_hpp__column_register(fmt);
+		if (!list_empty(&fmt->list))
+			continue;
+
+		/*
+		 * sort entry fields are dynamically created,
+		 * so they can share a same sort key even though
+		 * the list is empty.
+		 */
+		if (perf_hpp__is_sort_entry(fmt)) {
+			struct perf_hpp_fmt *pos;
+
+			perf_hpp__for_each_format(pos) {
+				if (perf_hpp__same_sort_entry(pos, fmt))
+					goto next;
+			}
+		}
+
+		perf_hpp__column_register(fmt);
+next:
+		continue;
+	}
+}
+
+void perf_hpp__append_sort_keys(void)
+{
+	struct perf_hpp_fmt *fmt;
+
+	/* append output fields to sort keys */
+	perf_hpp__for_each_format(fmt) {
+		if (!list_empty(&fmt->sort_list))
+			continue;
+
+		/*
+		 * sort entry fields are dynamically created,
+		 * so they can share a same sort key even though
+		 * the list is empty.
+		 */
+		if (perf_hpp__is_sort_entry(fmt)) {
+			struct perf_hpp_fmt *pos;
+
+			perf_hpp__for_each_sort_list(pos) {
+				if (perf_hpp__same_sort_entry(pos, fmt))
+					goto next;
+			}
+		}
+
+		perf_hpp__register_sort_field(fmt);
+next:
+		continue;
 	}
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 76bb72e4302b..f3713b79742d 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -197,6 +197,10 @@ void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
 void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
 void perf_hpp__setup_output_field(void);
+void perf_hpp__append_sort_keys(void);
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d64c1e58f1b1..b748b02fcb78 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -13,6 +13,7 @@ const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";
 const char	*sort_order;
+const char	*field_order;
 regex_t		ignore_callees_regex;
 int		have_ignore_callees = 0;
 int		sort__need_collapse = 0;
@@ -1057,6 +1058,20 @@ struct hpp_sort_entry {
 	struct sort_entry *se;
 };
 
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_sort_entry *hse_a;
+	struct hpp_sort_entry *hse_b;
+
+	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+		return false;
+
+	hse_a = container_of(a, struct hpp_sort_entry, hpp);
+	hse_b = container_of(b, struct hpp_sort_entry, hpp);
+
+	return hse_a->se == hse_b->se;
+}
+
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			      struct perf_evsel *evsel)
 {
@@ -1092,14 +1107,15 @@ static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
 }
 
-static int __sort_dimension__add_hpp(struct sort_dimension *sd)
+static struct hpp_sort_entry *
+__sort_dimension__alloc_hpp(struct sort_dimension *sd)
 {
 	struct hpp_sort_entry *hse;
 
 	hse = malloc(sizeof(*hse));
 	if (hse == NULL) {
 		pr_err("Memory allocation failed\n");
-		return -1;
+		return NULL;
 	}
 
 	hse->se = sd->entry;
@@ -1115,16 +1131,42 @@ static int __sort_dimension__add_hpp(struct sort_dimension *sd)
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 
+	return hse;
+}
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+	return format->header == __sort__hpp_header;
+}
+
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+{
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+	if (hse == NULL)
+		return -1;
+
 	perf_hpp__register_sort_field(&hse->hpp);
 	return 0;
 }
 
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+{
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+	if (hse == NULL)
+		return -1;
+
+	perf_hpp__column_register(&hse->hpp);
+	return 0;
+}
+
 static int __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp(sd) < 0)
+	if (__sort_dimension__add_hpp_sort(sd) < 0)
 		return -1;
 
 	if (sd->entry->se_collapse)
@@ -1149,6 +1191,28 @@ static int __hpp_dimension__add(struct hpp_dimension *hd)
 	return 0;
 }
 
+static int __sort_dimension__add_output(struct sort_dimension *sd)
+{
+	if (sd->taken)
+		return 0;
+
+	if (__sort_dimension__add_hpp_output(sd) < 0)
+		return -1;
+
+	sd->taken = 1;
+	return 0;
+}
+
+static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+{
+	if (!hd->taken) {
+		hd->taken = 1;
+
+		perf_hpp__column_register(hd->fmt);
+	}
+	return 0;
+}
+
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
@@ -1237,14 +1301,23 @@ static const char *get_default_sort_order(void)
 	return default_sort_orders[sort__mode];
 }
 
-int setup_sorting(void)
+static int __setup_sorting(void)
 {
 	char *tmp, *tok, *str;
 	const char *sort_keys = sort_order;
 	int ret = 0;
 
-	if (sort_keys == NULL)
+	if (sort_keys == NULL) {
+		if (field_order) {
+			/*
+			 * If user specified field order but no sort order,
+			 * we'll honor it and not add default sort orders.
+			 */
+			return 0;
+		}
+
 		sort_keys = get_default_sort_order();
+	}
 
 	str = strdup(sort_keys);
 	if (str == NULL) {
@@ -1331,3 +1404,129 @@ void sort__setup_elide(FILE *output)
 	list_for_each_entry(se, &hist_entry__sort_list, list)
 		se->elide = false;
 }
+
+static int output_field_add(char *tok)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+		struct sort_dimension *sd = &common_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		return __sort_dimension__add_output(sd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+		if (strncasecmp(tok, hd->name, strlen(tok)))
+			continue;
+
+		return __hpp_dimension__add_output(hd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
+		struct sort_dimension *sd = &bstack_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		return __sort_dimension__add_output(sd);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
+		struct sort_dimension *sd = &memory_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		return __sort_dimension__add_output(sd);
+	}
+
+	return -ESRCH;
+}
+
+static void reset_dimensions(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++)
+		common_sort_dimensions[i].taken = 0;
+
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++)
+		hpp_sort_dimensions[i].taken = 0;
+
+	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++)
+		bstack_sort_dimensions[i].taken = 0;
+
+	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++)
+		memory_sort_dimensions[i].taken = 0;
+}
+
+static int __setup_output_field(void)
+{
+	char *tmp, *tok, *str;
+	int ret = 0;
+
+	if (field_order == NULL)
+		return 0;
+
+	reset_dimensions();
+
+	str = strdup(field_order);
+	if (str == NULL) {
+		error("Not enough memory to setup output fields");
+		return -ENOMEM;
+	}
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = output_field_add(tok);
+		if (ret == -EINVAL) {
+			error("Invalid --fields key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
+			error("Unknown --fields key: `%s'", tok);
+			break;
+		}
+	}
+
+	free(str);
+	return ret;
+}
+
+int setup_sorting(void)
+{
+	int err;
+
+	err = __setup_sorting();
+	if (err < 0)
+		return err;
+
+	if (parent_pattern != default_parent_pattern) {
+		err = sort_dimension__add("parent");
+		if (err < 0)
+			return err;
+	}
+
+	reset_dimensions();
+
+	/*
+	 * perf diff doesn't use default hpp output fields.
+	 */
+	if (sort__mode != SORT_MODE__DIFF)
+		perf_hpp__init();
+
+	err = __setup_output_field();
+	if (err < 0)
+		return err;
+
+	/* copy sort keys to output fields */
+	perf_hpp__setup_output_field();
+	/* and then copy output fields to sort keys */
+	perf_hpp__append_sort_keys();
+
+	return 0;
+}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 1a7295255dc9..89e5057ca378 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -25,6 +25,7 @@
 
 extern regex_t parent_regex;
 extern const char *sort_order;
+extern const char *field_order;
 extern const char default_parent_pattern[];
 extern const char *parent_pattern;
 extern const char default_sort_order[];
@@ -191,6 +192,7 @@ extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
 int setup_sorting(void);
+int setup_output_field(void);
 extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
 
-- 
cgit v1.2.3


From 1844dbcbe78503e0f4a8996d69da725d5e7a5177 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 28 May 2014 14:12:18 +0900
Subject: perf tools: Introduce hists__inc_nr_samples()

There're some duplicate code for counting number of samples.  Add
hists__inc_nr_samples() and reuse it.

Suggested-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1401335910-16832-2-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-annotate.c   | 2 +-
 tools/perf/builtin-report.c     | 4 +---
 tools/perf/builtin-sched.c      | 2 +-
 tools/perf/builtin-top.c        | 5 +----
 tools/perf/tests/hists_filter.c | 4 +---
 tools/perf/util/hist.c          | 7 +++++++
 tools/perf/util/hist.h          | 1 +
 7 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index d30d2c2e2a7a..bf52461a88bd 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -70,7 +70,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 	return ret;
 }
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bc0eec1ce4be..4a3b84dd4f41 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -92,9 +92,7 @@ static void report__inc_stats(struct report *rep, struct hist_entry *he)
 	 * counted in perf_session_deliver_event().  The dump_trace
 	 * requires this info is ready before going to the output tree.
 	 */
-	hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		he->hists->stats.nr_non_filtered_samples++;
+	hists__inc_nr_samples(he->hists, he->filtered);
 }
 
 static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d7176830b9b2..c38d06c04775 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1428,7 +1428,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	int err = 0;
 
 	evsel->hists.stats.total_period += sample->period;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5b389ce4cd15..51309264d210 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -252,10 +252,7 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	if (he == NULL)
 		return NULL;
 
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
-
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
 	return he;
 }
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index c5ba924a3581..0a71ef4b9158 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -85,9 +85,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			fake_samples[i].map = al.map;
 			fake_samples[i].sym = al.sym;
 
-			hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-			if (!he->filtered)
-				he->hists->stats.nr_non_filtered_samples++;
+			hists__inc_nr_samples(he->hists, he->filtered);
 		}
 	}
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b262b44b7a65..5943ba60f193 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -800,6 +800,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
 	events_stats__inc(&hists->stats, type);
 }
 
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+	events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+	if (!filtered)
+		hists->stats.nr_non_filtered_samples++;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a8418d19808d..03ae1dbb1b15 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -119,6 +119,7 @@ u64 hists__total_period(struct hists *hists);
 void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
 void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
-- 
cgit v1.2.3


From 69bcb019fc809874f518559c8e5b0a90176f0532 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 30 Oct 2013 09:40:34 +0900
Subject: perf tools: Introduce struct hist_entry_iter

There're some duplicate code when adding hist entries.  They are
different in that some have branch info or mem info but generally do
same thing.  So introduce new struct hist_entry_iter and add callbacks
to customize each case in general way.

The new perf_evsel__add_entry() function will look like:

  iter->prepare_entry();
  iter->add_single_entry();

  while (iter->next_entry())
    iter->add_next_entry();

  iter->finish_entry();

This will help further work like the cumulative callchain patchset.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arun Sharma <asharma@fb.com>
Tested-by: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1401335910-16832-3-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-report.c     | 192 ++++----------------------
 tools/perf/tests/hists_filter.c |  16 ++-
 tools/perf/tests/hists_output.c |  11 +-
 tools/perf/util/hist.c          | 299 ++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/hist.h          |  33 +++++
 5 files changed, 372 insertions(+), 179 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4a3b84dd4f41..3201bdfa8c3f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -76,163 +76,16 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static void report__inc_stats(struct report *rep, struct hist_entry *he)
+static void report__inc_stats(struct report *rep,
+			      struct hist_entry *he __maybe_unused)
 {
 	/*
-	 * The @he is either of a newly created one or an existing one
-	 * merging current sample.  We only want to count a new one so
-	 * checking ->nr_events being 1.
+	 * We cannot access @he at this time.  Just assume it's a new entry.
+	 * It'll be fixed once we have a callback mechanism in hist_iter.
 	 */
-	if (he->stat.nr_events == 1)
-		rep->nr_entries++;
-
-	/*
-	 * Only counts number of samples at this stage as it's more
-	 * natural to do it here and non-sample events are also
-	 * counted in perf_session_deliver_event().  The dump_trace
-	 * requires this info is ready before going to the output tree.
-	 */
-	hists__inc_nr_samples(he->hists, he->filtered);
-}
-
-static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	struct mem_info *mi, *mx;
-	uint64_t cost;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	mi = sample__resolve_mem(sample, al);
-	if (!mi)
-		return -ENOMEM;
-
-	if (rep->hide_unresolved && !al->sym)
-		return 0;
-
-	cost = sample->weight;
-	if (!cost)
-		cost = 1;
-
-	/*
-	 * must pass period=weight in order to get the correct
-	 * sorting from hists__collapse_resort() which is solely
-	 * based on periods. We want sorting be done on nr_events * weight
-	 * and this is indirectly achieved by passing period=weight here
-	 * and the he_stat__add_period() function.
-	 */
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
-				cost, cost, 0);
-	if (!he)
-		return -ENOMEM;
-
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-		if (err)
-			goto out;
-	}
-
-	report__inc_stats(rep, he);
-
-	err = hist_entry__append_callchain(he, sample);
-out:
-	return err;
-}
-
-static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	unsigned i;
-	struct hist_entry *he;
-	struct branch_info *bi, *bx;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	bi = sample__resolve_bstack(sample, al);
-	if (!bi)
-		return -ENOMEM;
-
-	for (i = 0; i < sample->branch_stack->nr; i++) {
-		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
-			continue;
-
-		err = -ENOMEM;
-
-		/* overwrite the 'al' to branch-to info */
-		al->map = bi[i].to.map;
-		al->sym = bi[i].to.sym;
-		al->addr = bi[i].to.addr;
-		/*
-		 * The report shows the percentage of total branches captured
-		 * and not events sampled. Thus we use a pseudo period of 1.
-		 */
-		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
-					1, 1, 0);
-		if (he) {
-			if (ui__has_annotation()) {
-				bx = he->branch_info;
-				err = addr_map_symbol__inc_samples(&bx->from,
-								   evsel->idx);
-				if (err)
-					goto out;
-
-				err = addr_map_symbol__inc_samples(&bx->to,
-								   evsel->idx);
-				if (err)
-					goto out;
-			}
-			report__inc_stats(rep, he);
-		} else
-			goto out;
-	}
-	err = 0;
-out:
-	free(bi);
-	return err;
+	rep->nr_entries++;
 }
 
-static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
-
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	if (he == NULL)
-		return -ENOMEM;
-
-	err = hist_entry__append_callchain(he, sample);
-	if (err)
-		goto out;
-
-	if (ui__has_annotation())
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-
-	report__inc_stats(rep, he);
-
-out:
-	return err;
-}
-
-
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -241,6 +94,9 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+	};
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
@@ -255,22 +111,22 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding lbr entry, skipping event\n");
-	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding mem entry, skipping event\n");
-	} else {
-		if (al.map != NULL)
-			al.map->dso->hit = 1;
-
-		ret = report__add_hist_entry(rep, evsel, &al, sample);
-		if (ret < 0)
-			pr_debug("problem incrementing symbol period, skipping event\n");
-	}
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else
+		iter.ops = &hist_iter_normal;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	report__inc_stats(rep, NULL);
+
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
+
 	return ret;
 }
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 0a71ef4b9158..76b02e1de701 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -42,11 +42,11 @@ static struct sample fake_samples[] = {
 	{ .pid = 300, .ip = 0xf0000 + 800, },
 };
 
-static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+static int add_hist_entries(struct perf_evlist *evlist,
+			    struct machine *machine __maybe_unused)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;
-	struct hist_entry *he;
 	struct perf_sample sample = { .cpu = 0, };
 	size_t i;
 
@@ -62,6 +62,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.misc = PERF_RECORD_MISC_USER,
 				},
 			};
+			struct hist_entry_iter iter = {
+				.ops = &hist_iter_normal,
+				.hide_unresolved = false,
+			};
 
 			/* make sure it has no filter at first */
 			evsel->hists.thread_filter = NULL;
@@ -71,21 +75,19 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 			sample.pid = fake_samples[i].pid;
 			sample.tid = fake_samples[i].pid;
 			sample.ip = fake_samples[i].ip;
+			sample.period = 100;
 
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 100, 1, 0);
-			if (he == NULL)
+			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+						 PERF_MAX_STACK_DEPTH) < 0)
 				goto out;
 
 			fake_samples[i].thread = al.thread;
 			fake_samples[i].map = al.map;
 			fake_samples[i].sym = al.sym;
-
-			hists__inc_nr_samples(he->hists, he->filtered);
 		}
 	}
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a16850551797..1308f88a9169 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -46,7 +46,7 @@ static struct sample fake_samples[] = {
 static int add_hist_entries(struct hists *hists, struct machine *machine)
 {
 	struct addr_location al;
-	struct hist_entry *he;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 	struct perf_sample sample = { .period = 100, };
 	size_t i;
 
@@ -56,6 +56,10 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 				.misc = PERF_RECORD_MISC_USER,
 			},
 		};
+		struct hist_entry_iter iter = {
+			.ops = &hist_iter_normal,
+			.hide_unresolved = false,
+		};
 
 		sample.cpu = fake_samples[i].cpu;
 		sample.pid = fake_samples[i].pid;
@@ -66,9 +70,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		he = __hists__add_entry(hists, &al, NULL, NULL, NULL,
-					sample.period, 1, 0);
-		if (he == NULL)
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH) < 0)
 			goto out;
 
 		fake_samples[i].thread = al.thread;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 5943ba60f193..d8662356de20 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "session.h"
 #include "sort.h"
 #include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -429,6 +430,304 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 	return add_hist_entry(hists, &entry, al);
 }
 
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_sample *sample = iter->sample;
+	struct mem_info *mi;
+
+	mi = sample__resolve_mem(sample, al);
+	if (mi == NULL)
+		return -ENOMEM;
+
+	iter->priv = mi;
+	return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	u64 cost;
+	struct mem_info *mi = iter->priv;
+	struct hist_entry *he;
+
+	if (mi == NULL)
+		return -EINVAL;
+
+	cost = iter->sample->weight;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+				cost, cost, 0);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = iter->he;
+	struct mem_info *mx;
+	int err = -EINVAL;
+
+	if (he == NULL)
+		goto out;
+
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
+
+		mx = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+		if (err)
+			goto out;
+	}
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+	/*
+	 * We don't need to free iter->priv (mem_info) here since
+	 * the mem info was either already freed in add_hist_entry() or
+	 * passed to a new hist entry by hist_entry__new().
+	 */
+	iter->priv = NULL;
+
+	iter->he = NULL;
+	return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return -ENOMEM;
+
+	iter->curr = 0;
+	iter->total = sample->branch_stack->nr;
+
+	iter->priv = bi;
+	return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+			     struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi = iter->priv;
+	int i = iter->curr;
+
+	if (bi == NULL)
+		return 0;
+
+	if (iter->curr >= iter->total)
+		return 0;
+
+	al->map = bi[i].to.map;
+	al->sym = bi[i].to.sym;
+	al->addr = bi[i].to.addr;
+	return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi, *bx;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = NULL;
+	int i = iter->curr;
+	int err = 0;
+
+	bi = iter->priv;
+
+	if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+		goto out;
+
+	/*
+	 * The report shows the percentage of total branches captured
+	 * and not events sampled. Thus we use a pseudo period of 1.
+	 */
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+				1, 1, 0);
+	if (he == NULL)
+		return -ENOMEM;
+
+	if (ui__has_annotation()) {
+		bx = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
+		if (err)
+			goto out;
+
+		err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
+		if (err)
+			goto out;
+	}
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+	iter->he = he;
+	iter->curr++;
+	return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+			  struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	int err;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+
+	if (he == NULL)
+		return 0;
+
+	iter->he = NULL;
+
+	if (ui__has_annotation()) {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			return err;
+	}
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+	.prepare_entry 		= iter_prepare_mem_entry,
+	.add_single_entry 	= iter_add_single_mem_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+	.prepare_entry 		= iter_prepare_branch_entry,
+	.add_single_entry 	= iter_add_single_branch_entry,
+	.next_entry 		= iter_next_branch_entry,
+	.add_next_entry 	= iter_add_next_branch_entry,
+	.finish_entry 		= iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+	.prepare_entry 		= iter_prepare_normal_entry,
+	.add_single_entry 	= iter_add_single_normal_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_normal_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth)
+{
+	int err, err2;
+
+	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+					max_stack_depth);
+	if (err)
+		return err;
+
+	iter->evsel = evsel;
+	iter->sample = sample;
+
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
+
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
+			break;
+	}
+
+out:
+	err2 = iter->ops->finish_entry(iter, al);
+	if (!err)
+		err = err2;
+
+	return err;
+}
+
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 03ae1dbb1b15..8894f184357c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -96,12 +96,45 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 };
 
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+	int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+	int total;
+	int curr;
+
+	bool hide_unresolved;
+
+	struct perf_evsel *evsel;
+	struct perf_sample *sample;
+	struct hist_entry *he;
+	struct symbol *parent;
+	void *priv;
+
+	const struct hist_iter_ops *ops;
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
 				      u64 weight, u64 transaction);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth);
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
-- 
cgit v1.2.3


From 7a13aa28aa268359cee006059731f49bcd1f839e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 11 Sep 2012 14:13:04 +0900
Subject: perf hists: Accumulate hist entry stat based on the callchain

Call __hists__add_entry() for each callchain node to get an
accumulated stat for an entry.  Introduce new cumulative_iter ops to
process them properly.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arun Sharma <asharma@fb.com>
Tested-by: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1401335910-16832-6-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-report.c |  2 +
 tools/perf/util/callchain.c |  3 +-
 tools/perf/util/hist.c      | 96 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/hist.h      |  1 +
 4 files changed, 101 insertions(+), 1 deletion(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3201bdfa8c3f..e8fa9fea341f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -115,6 +115,8 @@ static int process_sample_event(struct perf_tool *tool,
 		iter.ops = &hist_iter_branch;
 	else if (rep->mem_mode)
 		iter.ops = &hist_iter_mem;
+	else if (symbol_conf.cumulate_callchain)
+		iter.ops = &hist_iter_cumulative;
 	else
 		iter.ops = &hist_iter_normal;
 
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9a42382b3921..2af69c47b725 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -616,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 	if (sample->callchain == NULL)
 		return 0;
 
-	if (symbol_conf.use_callchain || sort__has_parent) {
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+	    sort__has_parent) {
 		return machine__resolve_callchain(al->machine, evsel, al->thread,
 						  sample, parent, al, max_stack);
 	}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b9facf33b224..6079b5acfb6d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -696,6 +696,94 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
 	return hist_entry__append_callchain(he, sample);
 }
 
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+			      struct addr_location *al __maybe_unused)
+{
+	callchain_cursor_commit(&callchain_cursor);
+	return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+				 struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+	int err = 0;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+
+	/*
+	 * The iter->he will be over-written after ->add_next_entry()
+	 * called so inc stats for the original entry now.
+	 */
+	if (ui__has_annotation())
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+			   struct addr_location *al)
+{
+	struct callchain_cursor_node *node;
+
+	node = callchain_cursor_current(&callchain_cursor);
+	if (node == NULL)
+		return 0;
+
+	al->map = node->map;
+	al->sym = node->sym;
+	if (node->map)
+		al->addr = node->map->map_ip(node->map, node->ip);
+	else
+		al->addr = node->ip;
+
+	if (iter->hide_unresolved && al->sym == NULL)
+		return 0;
+
+	callchain_cursor_advance(&callchain_cursor);
+	return 1;
+}
+
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+			       struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, false);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+
+	return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+			     struct addr_location *al __maybe_unused)
+{
+	iter->he = NULL;
+	return 0;
+}
+
 const struct hist_iter_ops hist_iter_mem = {
 	.prepare_entry 		= iter_prepare_mem_entry,
 	.add_single_entry 	= iter_add_single_mem_entry,
@@ -720,6 +808,14 @@ const struct hist_iter_ops hist_iter_normal = {
 	.finish_entry 		= iter_finish_normal_entry,
 };
 
+const struct hist_iter_ops hist_iter_cumulative = {
+	.prepare_entry 		= iter_prepare_cumulative_entry,
+	.add_single_entry 	= iter_add_single_cumulative_entry,
+	.next_entry 		= iter_next_cumulative_entry,
+	.add_next_entry 	= iter_add_next_cumulative_entry,
+	.finish_entry 		= iter_finish_cumulative_entry,
+};
+
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index bedb24d3643c..78409f95d012 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -124,6 +124,7 @@ struct hist_entry_iter {
 extern const struct hist_iter_ops hist_iter_normal;
 extern const struct hist_iter_ops hist_iter_branch;
 extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
 
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
-- 
cgit v1.2.3


From 793aaaabb79803a0154fc6a98c472a29bb6d5cc9 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 30 Oct 2013 17:05:55 +0900
Subject: perf report: Add --children option

The --children option is for showing accumulated overhead (period)
value as well as self overhead.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arun Sharma <asharma@fb.com>
Tested-by: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1401335910-16832-16-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/Documentation/perf-report.txt |  7 ++++++-
 tools/perf/builtin-report.c              | 15 ++++++++++++++-
 2 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index a1b5185402d5..cefdf430d1b4 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -111,7 +111,7 @@ OPTIONS
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in -F will be appended
@@ -163,6 +163,11 @@ OPTIONS
 
 	Default: fractal,0.5,callee,function.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires callchains are recorded.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index e8fa9fea341f..f27a8aad6a3f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -185,6 +185,14 @@ static int report__setup_sample_type(struct report *rep)
 			}
 	}
 
+	if (symbol_conf.cumulate_callchain) {
+		/* Silently ignore if callchain is missing */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			symbol_conf.cumulate_callchain = false;
+			perf_hpp__cancel_cumulate();
+		}
+	}
+
 	if (sort__mode == SORT_MODE__BRANCH) {
 		if (!is_pipe &&
 		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
@@ -568,6 +576,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
 		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
 		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -660,8 +670,10 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack)
+	if (branch_mode == -1 && has_br_stack) {
 		sort__mode = SORT_MODE__BRANCH;
+		symbol_conf.cumulate_callchain = false;
+	}
 
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -669,6 +681,7 @@ repeat:
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
+		symbol_conf.cumulate_callchain = false;
 	}
 
 	if (setup_sorting() < 0) {
-- 
cgit v1.2.3


From 8d8e645ceafd726b8317949f899e4b3acfb20d29 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 22 Jan 2013 18:09:46 +0900
Subject: perf report: Add report.children config option

Add report.children config option for setting default value of
callchain accumulation.  It affects the report output only if
perf.data contains callchain info.

A user can write .perfconfig file like below to enable accumulation
by default:

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

And it can be disabled through command line:

  $ perf report --no-children

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arun Sharma <asharma@fb.com>
Tested-by: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1401335910-16832-17-git-send-email-namhyung@kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-report.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f27a8aad6a3f..6cac509212ee 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -72,6 +72,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
+	if (!strcmp(var, "report.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
-- 
cgit v1.2.3


From 9d3c02d7188866299eebe3c4a652c08140a71f40 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 7 Jan 2014 17:02:25 +0900
Subject: perf tools: Add callback function to hist_entry_iter

The new ->add_entry_cb() will be called after an entry was added to
the histogram.  It's used for code sharing between perf report and
perf top.  Note that ops->add_*_entry() should set iter->he properly
in order to call the ->add_entry_cb.

Also pass @arg to the callback function.  It'll be used by perf top
later.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arun Sharma <asharma@fb.com>
Tested-by: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/87k393g999.fsf@sejong.aot.lge.com
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-report.c     | 61 ++++++++++++++++++++++++++++++++-----
 tools/perf/tests/hists_filter.c |  2 +-
 tools/perf/tests/hists_output.c |  2 +-
 tools/perf/util/hist.c          | 67 +++++++++++++++--------------------------
 tools/perf/util/hist.h          |  5 ++-
 5 files changed, 84 insertions(+), 53 deletions(-)

(limited to 'tools/perf/builtin-report.c')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 6cac509212ee..21d830bafff3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -80,14 +80,59 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static void report__inc_stats(struct report *rep,
-			      struct hist_entry *he __maybe_unused)
+static void report__inc_stats(struct report *rep, struct hist_entry *he)
 {
 	/*
-	 * We cannot access @he at this time.  Just assume it's a new entry.
-	 * It'll be fixed once we have a callback mechanism in hist_iter.
+	 * The @he is either of a newly created one or an existing one
+	 * merging current sample.  We only want to count a new one so
+	 * checking ->nr_events being 1.
 	 */
-	rep->nr_entries++;
+	if (he->stat.nr_events == 1)
+		rep->nr_entries++;
+}
+
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
+{
+	int err = 0;
+	struct report *rep = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct mem_info *mi;
+	struct branch_info *bi;
+
+	report__inc_stats(rep, he);
+
+	if (!ui__has_annotation())
+		return 0;
+
+	if (sort__mode == SORT_MODE__BRANCH) {
+		bi = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
+		if (err)
+			goto out;
+
+		err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
+
+	} else if (rep->mem_mode) {
+		mi = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+		if (err)
+			goto out;
+
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
+	} else if (symbol_conf.cumulate_callchain) {
+		if (single)
+			err = hist_entry__inc_addr_samples(he, evsel->idx,
+							   al->addr);
+	} else {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	}
+
+out:
+	return err;
 }
 
 static int process_sample_event(struct perf_tool *tool,
@@ -100,6 +145,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct addr_location al;
 	struct hist_entry_iter iter = {
 		.hide_unresolved = rep->hide_unresolved,
+		.add_entry_cb = hist_iter__report_callback,
 	};
 	int ret;
 
@@ -127,9 +173,8 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	report__inc_stats(rep, NULL);
-
-	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack);
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
+				   rep);
 	if (ret < 0)
 		pr_debug("problem adding hist entry, skipping event\n");
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 76b02e1de701..3539403bbad4 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -82,7 +82,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
 				goto out;
 
 			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-						 PERF_MAX_STACK_DEPTH) < 0)
+						 PERF_MAX_STACK_DEPTH, NULL) < 0)
 				goto out;
 
 			fake_samples[i].thread = al.thread;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 1308f88a9169..d40461ecd210 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -71,7 +71,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			goto out;
 
 		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH) < 0)
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
 			goto out;
 
 		fake_samples[i].thread = al.thread;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index c6f5f5251aad..5a0a4b2cadc4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -517,27 +517,16 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 }
 
 static int
-iter_finish_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+		      struct addr_location *al __maybe_unused)
 {
 	struct perf_evsel *evsel = iter->evsel;
 	struct hist_entry *he = iter->he;
-	struct mem_info *mx;
 	int err = -EINVAL;
 
 	if (he == NULL)
 		goto out;
 
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
-		if (err)
-			goto out;
-	}
-
 	hists__inc_nr_samples(&evsel->hists, he->filtered);
 
 	err = hist_entry__append_callchain(he, iter->sample);
@@ -575,6 +564,9 @@ static int
 iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
 			     struct addr_location *al __maybe_unused)
 {
+	/* to avoid calling callback function */
+	iter->he = NULL;
+
 	return 0;
 }
 
@@ -599,7 +591,7 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 static int
 iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct branch_info *bi, *bx;
+	struct branch_info *bi;
 	struct perf_evsel *evsel = iter->evsel;
 	struct hist_entry *he = NULL;
 	int i = iter->curr;
@@ -619,17 +611,6 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	if (he == NULL)
 		return -ENOMEM;
 
-	if (ui__has_annotation()) {
-		bx = he->branch_info;
-		err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
-		if (err)
-			goto out;
-
-		err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
-		if (err)
-			goto out;
-	}
-
 	hists__inc_nr_samples(&evsel->hists, he->filtered);
 
 out:
@@ -673,9 +654,9 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
 }
 
 static int
-iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
 {
-	int err;
 	struct hist_entry *he = iter->he;
 	struct perf_evsel *evsel = iter->evsel;
 	struct perf_sample *sample = iter->sample;
@@ -685,12 +666,6 @@ iter_finish_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
 
 	iter->he = NULL;
 
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			return err;
-	}
-
 	hists__inc_nr_samples(&evsel->hists, he->filtered);
 
 	return hist_entry__append_callchain(he, sample);
@@ -746,13 +721,6 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	 */
 	callchain_cursor_commit(&callchain_cursor);
 
-	/*
-	 * The iter->he will be over-written after ->add_next_entry()
-	 * called so inc stats for the original entry now.
-	 */
-	if (ui__has_annotation())
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-
 	hists__inc_nr_samples(&evsel->hists, he->filtered);
 
 	return err;
@@ -802,8 +770,11 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	 * It's possible that it has cycles or recursive calls.
 	 */
 	for (i = 0; i < iter->curr; i++) {
-		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0)
+		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+			/* to avoid calling callback function */
+			iter->he = NULL;
 			return 0;
+		}
 	}
 
 	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
@@ -863,7 +834,7 @@ const struct hist_iter_ops hist_iter_cumulative = {
 
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 struct perf_evsel *evsel, struct perf_sample *sample,
-			 int max_stack_depth)
+			 int max_stack_depth, void *arg)
 {
 	int err, err2;
 
@@ -883,10 +854,22 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (err)
 		goto out;
 
+	if (iter->he && iter->add_entry_cb) {
+		err = iter->add_entry_cb(iter, al, true, arg);
+		if (err)
+			goto out;
+	}
+
 	while (iter->ops->next_entry(iter, al)) {
 		err = iter->ops->add_next_entry(iter, al);
 		if (err)
 			break;
+
+		if (iter->he && iter->add_entry_cb) {
+			err = iter->add_entry_cb(iter, al, false, arg);
+			if (err)
+				goto out;
+		}
 	}
 
 out:
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 99ad3cb433fb..82b28ff98062 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -119,6 +119,9 @@ struct hist_entry_iter {
 	void *priv;
 
 	const struct hist_iter_ops *ops;
+	/* user-defined callback function (optional) */
+	int (*add_entry_cb)(struct hist_entry_iter *iter,
+			    struct addr_location *al, bool single, void *arg);
 };
 
 extern const struct hist_iter_ops hist_iter_normal;
@@ -135,7 +138,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 struct perf_evsel *evsel, struct perf_sample *sample,
-			 int max_stack_depth);
+			 int max_stack_depth, void *arg);
 
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
-- 
cgit v1.2.3