[RFC/PATCH v2 4/4] perf report: Add callchain value option

[Namhyung Kim <namhyung@kernel.org>]

Now -g/--call-graph option supports how to display callchain values.
Possible values are 'percent', 'period' and 'count'.  The percent is
same as before and it's the default behavior.  The period displays the
raw period value rather than the percentage.  The count displays the
number of occurrences.

  $ perf report --no-children --stdio -g percent
  ...
    39.93%  swapper  [kernel.vmlinux]  [k] intel_idel
            |
            ---intel_idle
               cpuidle_enter_state
               cpuidle_enter
               call_cpuidle
               cpu_startup_entry
               |
               |--28.63%-- start_secondary
               |
                --11.30%-- rest_init

  $ perf report --no-children --show-total-period --stdio -g period
  ...
    39.93%   13018705  swapper  [kernel.vmlinux]  [k] intel_idel
            |
            ---intel_idle
               cpuidle_enter_state
               cpuidle_enter
               call_cpuidle
               cpu_startup_entry
               |
               |--9334403-- start_secondary
               |
                --3684302-- rest_init

  $ perf report --no-children --show-nr-samples --stdio -g count
  ...
    39.93%     80  swapper  [kernel.vmlinux]  [k] intel_idel
            |
            ---intel_idle
               cpuidle_enter_state
               cpuidle_enter
               call_cpuidle
               cpu_startup_entry
               |
               |--57-- start_secondary
               |
                --23-- rest_init

Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/Documentation/perf-report.txt | 13 ++++---
 tools/perf/builtin-report.c              |  4 +--
 tools/perf/ui/stdio/hist.c               |  8 +++++
 tools/perf/util/callchain.c              | 60 +++++++++++++++++++++++++++-----
 tools/perf/util/callchain.h              | 10 +++++-
 tools/perf/util/util.c                   |  3 +-
 6 files changed, 82 insertions(+), 16 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 5ce8da1e1256..bb9fd23a105e 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -170,11 +170,11 @@ OPTIONS
         Dump raw trace in ASCII.
 
 -g::
---call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>::
+--call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>::
         Display call chains using type, min percent threshold, print limit,
-	call order, sort key and branch.  Note that ordering of parameters is not
-	fixed so any parement can be given in an arbitraty order.  One exception
-	is the print_limit which should be preceded by threshold.
+	call order, sort key, optional branch and value.  Note that ordering of
+	parameters is not fixed so any parement can be given in an arbitraty order.
+	One exception is the print_limit which should be preceded by threshold.
 
 	print_type can be either:
 	- flat: single column, linear exposure of call chains.
@@ -204,6 +204,11 @@ OPTIONS
 	- branch: include last branch information in callgraph when available.
 	          Usually more convenient to use --branch-history for this.
 
+	value can be:
+	- percent: diplay overhead percent (default)
+	- period: display event period
+	- count: display evnt count
+
 --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
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2853ad2bd435..3dd4bb4ded1a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -625,7 +625,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 	return 0;
 }
 
-#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function"
+#define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
 
 const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
 				     CALLCHAIN_REPORT_HELP
@@ -708,7 +708,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report,
-			     "print_type,threshold[,print_limit],order,sort_key[,branch]",
+			     "print_type,threshold[,print_limit],order,sort_key[,branch],value",
 			     report_callchain_help, &report_parse_callchain_opt,
 			     callchain_default_opt),
 	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index e84ca21252d3..2104b09d41a8 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -88,6 +88,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	size_t ret = 0;
 	int i;
 	uint entries_printed = 0;
+	int cumul_count = 0;
 
 	remaining = total_samples;
 
@@ -99,6 +100,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		child = rb_entry(node, struct callchain_node, rb_node);
 		cumul = callchain_cumul_hits(child);
 		remaining -= cumul;
+		cumul_count += callchain_cumul_counts(child);
 
 		/*
 		 * The depth mask manages the output of pipes that show
@@ -148,6 +150,12 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		if (!rem_sq_bracket)
 			return ret;
 
+		if (callchain_param.value == CCVAL_COUNT) {
+			rem_node.count = child->parent->children_count - cumul_count;
+			if (rem_node.count <= 0)
+				return ret;
+		}
+
 		new_depth_mask &= ~(1 << (depth - 1));
 		ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth,
 					      new_depth_mask, 0, total_samples,
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 0a97d77509bd..7f0a89584f1b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -83,6 +83,23 @@ static int parse_callchain_sort_key(const char *value)
 	return -1;
 }
 
+static int parse_callchain_value(const char *value)
+{
+	if (!strncmp(value, "percent", strlen(value))) {
+		callchain_param.value = CCVAL_PERCENT;
+		return 0;
+	}
+	if (!strncmp(value, "period", strlen(value))) {
+		callchain_param.value = CCVAL_PERIOD;
+		return 0;
+	}
+	if (!strncmp(value, "count", strlen(value))) {
+		callchain_param.value = CCVAL_COUNT;
+		return 0;
+	}
+	return -1;
+}
+
 static int
 __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 {
@@ -106,7 +123,8 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 
 		if (!parse_callchain_mode(tok) ||
 		    !parse_callchain_order(tok) ||
-		    !parse_callchain_sort_key(tok)) {
+		    !parse_callchain_sort_key(tok) ||
+		    !parse_callchain_value(tok)) {
 			/* parsing ok - move on to the next */
 			try_stack_size = false;
 			goto next;
@@ -819,12 +837,26 @@ char *callchain_node__sprintf_value(struct callchain_node *node,
 				    char *bf, size_t bfsize, u64 total)
 {
 	double percent = 0.0;
-	u64 cumul = callchain_cumul_hits(node);
+	u64 period = callchain_cumul_hits(node);
+	int count = callchain_cumul_counts(node);
 
 	if (total)
-		percent = cumul * 100.0 / total;
+		percent = period * 100.0 / total;
+	if (callchain_param.mode == CHAIN_FOLDED)
+		count = node->count;
 
-	scnprintf(bf, bfsize, "%6.2f%%", percent);
+	switch (callchain_param.value) {
+	case CCVAL_PERIOD:
+		scnprintf(bf, bfsize, "%"PRIu64, period);
+		break;
+	case CCVAL_COUNT:
+		scnprintf(bf, bfsize, "%u", count);
+		break;
+	case CCVAL_PERCENT:
+	default:
+		scnprintf(bf, bfsize, "%.2f%%", percent);
+		break;
+	}
 	return bf;
 }
 
@@ -832,12 +864,24 @@ int callchain_node__fprintf_value(struct callchain_node *node,
 				 FILE *fp, u64 total)
 {
 	double percent = 0.0;
-	u64 cumul = callchain_cumul_hits(node);
+	u64 period = callchain_cumul_hits(node);
+	int count = callchain_cumul_counts(node);
 
 	if (total)
-		percent = cumul * 100.0 / total;
-
-	return percent_color_fprintf(fp, "%.2f%%", percent);
+		percent = period * 100.0 / total;
+	if (callchain_param.mode == CHAIN_FOLDED)
+		count = node->count;
+
+	switch (callchain_param.value) {
+	case CCVAL_PERIOD:
+		return fprintf(fp, "%"PRIu64, period);
+	case CCVAL_COUNT:
+		return fprintf(fp, "%u", count);
+	case CCVAL_PERCENT:
+	default:
+		return percent_color_fprintf(fp, "%.2f%%", percent);
+	}
+	return 0;
 }
 
 static void free_callchain_node(struct callchain_node *node)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 2f948f0ff034..e8533e328a47 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -29,7 +29,8 @@
 	HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
 	HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
 	HELP_PAD "sort_key:\tcall graph sort key (function|address)\n"	\
-	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n"
+	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
+	HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
 
 enum perf_call_graph_mode {
 	CALLCHAIN_NONE,
@@ -81,6 +82,12 @@ enum chain_key {
 	CCKEY_ADDRESS
 };
 
+enum chain_value {
+	CCVAL_PERCENT,
+	CCVAL_PERIOD,
+	CCVAL_COUNT,
+};
+
 struct callchain_param {
 	bool			enabled;
 	enum perf_call_graph_mode record_mode;
@@ -93,6 +100,7 @@ struct callchain_param {
 	bool			order_set;
 	enum chain_key		key;
 	bool			branch_callstack;
+	enum chain_value	value;
 };
 
 extern struct callchain_param callchain_param;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index cd12c25e4ea4..174912f87913 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -20,7 +20,8 @@ struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_ABS,
 	.min_percent = 0.5,
 	.order  = ORDER_CALLEE,
-	.key	= CCKEY_FUNCTION
+	.key	= CCKEY_FUNCTION,
+	.value	= CCVAL_PERCENT,
 };
 
 /*
-- 
2.6.2