[PATCH 13/15] perf report: Calculate and return the branch flag counting

[Arnaldo Carvalho de Melo <acme@kernel.org>]

From: Jin Yao <yao.jin@linux.intel.com>

Create some branch counters in per callchain list entry. Each counter
is for a branch flag. For example, predicted_count counts all the
*predicted* branches. The counters get updated by processing the
callchain cursor nodes.

It also provides functions to retrieve or print the values of counters
in callchain list.

Besides the counting for branch flags, it also counts and returns the
average number of iterations.

Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linux-kernel@vger.kernel.org
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/1477876794-30749-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/callchain.c | 189 +++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/callchain.h |  14 ++++
 2 files changed, 202 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 138a415fad0d..823befd8209a 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -438,6 +438,21 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
 		call->ms.map = cursor_node->map;
+
+		if (cursor_node->branch) {
+			call->branch_count = 1;
+
+			if (cursor_node->branch_flags.predicted)
+				call->predicted_count = 1;
+
+			if (cursor_node->branch_flags.abort)
+				call->abort_count = 1;
+
+			call->cycles_count = cursor_node->branch_flags.cycles;
+			call->iter_count = cursor_node->nr_loop_iter;
+			call->samples_count = cursor_node->samples;
+		}
+
 		list_add_tail(&call->list, &node->val);
 
 		callchain_cursor_advance(cursor);
@@ -497,8 +512,23 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 		right = node->ip;
 	}
 
-	if (left == right)
+	if (left == right) {
+		if (node->branch) {
+			cnode->branch_count++;
+
+			if (node->branch_flags.predicted)
+				cnode->predicted_count++;
+
+			if (node->branch_flags.abort)
+				cnode->abort_count++;
+
+			cnode->cycles_count += node->branch_flags.cycles;
+			cnode->iter_count += node->nr_loop_iter;
+			cnode->samples_count += node->samples;
+		}
+
 		return MATCH_EQ;
+	}
 
 	return left > right ? MATCH_GT : MATCH_LT;
 }
@@ -947,6 +977,163 @@ int callchain_node__fprintf_value(struct callchain_node *node,
 	return 0;
 }
 
+static void callchain_counts_value(struct callchain_node *node,
+				   u64 *branch_count, u64 *predicted_count,
+				   u64 *abort_count, u64 *cycles_count)
+{
+	struct callchain_list *clist;
+
+	list_for_each_entry(clist, &node->val, list) {
+		if (branch_count)
+			*branch_count += clist->branch_count;
+
+		if (predicted_count)
+			*predicted_count += clist->predicted_count;
+
+		if (abort_count)
+			*abort_count += clist->abort_count;
+
+		if (cycles_count)
+			*cycles_count += clist->cycles_count;
+	}
+}
+
+static int callchain_node_branch_counts_cumul(struct callchain_node *node,
+					      u64 *branch_count,
+					      u64 *predicted_count,
+					      u64 *abort_count,
+					      u64 *cycles_count)
+{
+	struct callchain_node *child;
+	struct rb_node *n;
+
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = rb_entry(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+
+		callchain_node_branch_counts_cumul(child, branch_count,
+						   predicted_count,
+						   abort_count,
+						   cycles_count);
+
+		callchain_counts_value(child, branch_count,
+				       predicted_count, abort_count,
+				       cycles_count);
+	}
+
+	return 0;
+}
+
+int callchain_branch_counts(struct callchain_root *root,
+			    u64 *branch_count, u64 *predicted_count,
+			    u64 *abort_count, u64 *cycles_count)
+{
+	if (branch_count)
+		*branch_count = 0;
+
+	if (predicted_count)
+		*predicted_count = 0;
+
+	if (abort_count)
+		*abort_count = 0;
+
+	if (cycles_count)
+		*cycles_count = 0;
+
+	return callchain_node_branch_counts_cumul(&root->node,
+						  branch_count,
+						  predicted_count,
+						  abort_count,
+						  cycles_count);
+}
+
+static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
+				   u64 branch_count, u64 predicted_count,
+				   u64 abort_count, u64 cycles_count,
+				   u64 iter_count, u64 samples_count)
+{
+	double predicted_percent = 0.0;
+	const char *null_str = "";
+	char iter_str[32];
+	char *str;
+	u64 cycles = 0;
+
+	if (branch_count == 0) {
+		if (fp)
+			return fprintf(fp, " (calltrace)");
+
+		return scnprintf(bf, bfsize, " (calltrace)");
+	}
+
+	if (iter_count && samples_count) {
+		scnprintf(iter_str, sizeof(iter_str),
+			 ", iterations:%" PRId64 "",
+			 iter_count / samples_count);
+		str = iter_str;
+	} else
+		str = (char *)null_str;
+
+	predicted_percent = predicted_count * 100.0 / branch_count;
+	cycles = cycles_count / branch_count;
+
+	if ((predicted_percent >= 100.0) && (abort_count == 0)) {
+		if (fp)
+			return fprintf(fp, " (cycles:%" PRId64 "%s)",
+				       cycles, str);
+
+		return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)",
+				 cycles, str);
+	}
+
+	if ((predicted_percent < 100.0) && (abort_count == 0)) {
+		if (fp)
+			return fprintf(fp,
+				" (predicted:%.1f%%, cycles:%" PRId64 "%s)",
+				predicted_percent, cycles, str);
+
+		return scnprintf(bf, bfsize,
+			" (predicted:%.1f%%, cycles:%" PRId64 "%s)",
+			predicted_percent, cycles, str);
+	}
+
+	if (fp)
+		return fprintf(fp,
+		" (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
+			predicted_percent, abort_count, cycles, str);
+
+	return scnprintf(bf, bfsize,
+		" (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
+		predicted_percent, abort_count, cycles, str);
+}
+
+int callchain_list_counts__printf_value(struct callchain_node *node,
+					struct callchain_list *clist,
+					FILE *fp, char *bf, int bfsize)
+{
+	u64 branch_count, predicted_count;
+	u64 abort_count, cycles_count;
+	u64 iter_count = 0, samples_count = 0;
+
+	branch_count = clist->branch_count;
+	predicted_count = clist->predicted_count;
+	abort_count = clist->abort_count;
+	cycles_count = clist->cycles_count;
+
+	if (node) {
+		struct callchain_list *call;
+
+		list_for_each_entry(call, &node->val, list) {
+			iter_count += call->iter_count;
+			samples_count += call->samples_count;
+		}
+	}
+
+	return callchain_counts_printf(fp, bf, bfsize, branch_count,
+				       predicted_count, abort_count,
+				       cycles_count, iter_count, samples_count);
+}
+
 static void free_callchain_node(struct callchain_node *node)
 {
 	struct callchain_list *list, *tmp;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index df6329d1c350..d9c70dccf06a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -111,6 +111,12 @@ struct callchain_list {
 		bool		unfolded;
 		bool		has_children;
 	};
+	u64			branch_count;
+	u64			predicted_count;
+	u64			abort_count;
+	u64			cycles_count;
+	u64			iter_count;
+	u64			samples_count;
 	char		       *srcline;
 	struct list_head	list;
 };
@@ -263,8 +269,16 @@ char *callchain_node__scnprintf_value(struct callchain_node *node,
 int callchain_node__fprintf_value(struct callchain_node *node,
 				  FILE *fp, u64 total);
 
+int callchain_list_counts__printf_value(struct callchain_node *node,
+					struct callchain_list *clist,
+					FILE *fp, char *bf, int bfsize);
+
 void free_callchain(struct callchain_root *root);
 void decay_callchain(struct callchain_root *root);
 int callchain_node__make_parent_list(struct callchain_node *node);
 
+int callchain_branch_counts(struct callchain_root *root,
+			    u64 *branch_count, u64 *predicted_count,
+			    u64 *abort_count, u64 *cycles_count);
+
 #endif	/* __PERF_CALLCHAIN_H */
-- 
2.7.4