[PATCH v1 5/5] perf report: Show branch type in callchain entry

[Jin Yao <yao.jin@linux.intel.com>]

Show branch type in callchain entry. The branch type is printed
with other LBR information (such as cycles/abort/...).

The branch types are:

 JCC forward: Conditional forward jump
JCC backward: Conditional backward jump
         JMP: Jump imm
     IND_JMP: Jump reg/mem
        CALL: Call imm
    IND_CALL: Call reg/mem
         RET: Ret
  FAR_BRANCH: SYSCALL/SYSRET, IRQ, IRET, TSX Abort

One example:
perf report --branch-history --stdio --no-children

--23.91%--main div.c:42 (RET cycles:2)
          compute_flag div.c:28 (RET cycles:2)
          compute_flag div.c:27 (RET cycles:1)
          rand rand.c:28 (RET cycles:1)
          rand rand.c:28 (RET cycles:1)
          __random random.c:298 (RET cycles:1)
          __random random.c:297 (JCC forward cycles:1)
          __random random.c:295 (JCC forward cycles:1)
          __random random.c:295 (JCC forward cycles:1)
          __random random.c:295 (JCC forward cycles:1)
          __random random.c:295 (RET cycles:9)

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
 tools/perf/util/callchain.c | 168 ++++++++++++++++++++++++++++----------------
 tools/perf/util/callchain.h |  13 ++++
 tools/perf/util/event.h     |   3 +-
 3 files changed, 124 insertions(+), 60 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 3cea1fb..f8f4c26 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -428,6 +428,44 @@ create_child(struct callchain_node *parent, bool inherit_children)
 	return new;
 }
 
+static const char *br_type_name[BR_IDX_MAX] = {
+	"JCC forward",
+	"JCC backward",
+	"JMP",
+	"IND_JMP",
+	"CALL",
+	"IND_CALL",
+	"RET",
+	"FAR_BRANCH",
+};
+
+static void
+branch_type_count(int *counts, struct branch_flags *flags)
+{
+	if ((flags->type & PERF_BR_CALL) == PERF_BR_CALL)
+		counts[BR_IDX_CALL]++;
+
+	if ((flags->type & PERF_BR_RET) == PERF_BR_RET)
+		counts[BR_IDX_RET]++;
+
+	if ((flags->type & PERF_BR_FAR_BRANCH) == PERF_BR_FAR_BRANCH)
+		counts[BR_IDX_FAR_BRANCH]++;
+
+	if ((flags->type & PERF_BR_JCC_FWD) == PERF_BR_JCC_FWD)
+		counts[BR_IDX_JCC_FWD]++;
+
+	if ((flags->type & PERF_BR_JCC_BWD) == PERF_BR_JCC_BWD)
+		counts[BR_IDX_JCC_BWD]++;
+
+	if ((flags->type & PERF_BR_JMP) == PERF_BR_JMP)
+		counts[BR_IDX_JMP]++;
+
+	if ((flags->type & PERF_BR_IND_CALL) == PERF_BR_IND_CALL)
+		counts[BR_IDX_IND_CALL]++;
+
+	if ((flags->type & PERF_BR_IND_JMP) == PERF_BR_IND_JMP)
+		counts[BR_IDX_IND_JMP]++;
+}
 
 /*
  * Fill the node with callchain values
@@ -467,6 +505,9 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 			call->cycles_count = cursor_node->branch_flags.cycles;
 			call->iter_count = cursor_node->nr_loop_iter;
 			call->samples_count = cursor_node->samples;
+
+			branch_type_count(call->brtype_count,
+					  &cursor_node->branch_flags);
 		}
 
 		list_add_tail(&call->list, &node->val);
@@ -579,6 +620,9 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->samples_count += node->samples;
+
+			branch_type_count(cnode->brtype_count,
+					  &node->branch_flags);
 		}
 
 		return MATCH_EQ;
@@ -1105,95 +1149,100 @@ int callchain_branch_counts(struct callchain_root *root,
 						  cycles_count);
 }
 
+static int branch_type_str(int *counts, char *bf, int bfsize)
+{
+	int i, printed = 0;
+
+	for (i = 0; i < BR_IDX_MAX; i++) {
+		if (printed == bfsize - 1)
+			return printed;
+
+		if (counts[i] > 0) {
+			printed += scnprintf(bf + printed, bfsize - printed,
+					     " (%s", br_type_name[i]);
+		}
+	}
+
+	return printed;
+}
+
 static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
-			     u64 iter_count, u64 samples_count)
+			     u64 iter_count, u64 samples_count,
+			     int *brtype_count)
 {
-	double predicted_percent = 0.0;
-	const char *null_str = "";
-	char iter_str[32];
-	char cycle_str[32];
-	char *istr, *cstr;
 	u64 cycles;
+	int printed, i = 0;
 
 	if (branch_count == 0)
 		return scnprintf(bf, bfsize, " (calltrace)");
 
-	cycles = cycles_count / branch_count;
+	printed = branch_type_str(brtype_count, bf, bfsize);
+	if (printed)
+		i++;
 
-	if (iter_count && samples_count) {
-		if (cycles > 0)
-			scnprintf(iter_str, sizeof(iter_str),
-				 " iterations:%" PRId64 "",
-				 iter_count / samples_count);
+	cycles = cycles_count / branch_count;
+	if (cycles) {
+		if (i++)
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" cycles:%" PRId64 "", cycles);
 		else
-			scnprintf(iter_str, sizeof(iter_str),
-				 "iterations:%" PRId64 "",
-				 iter_count / samples_count);
-		istr = iter_str;
-	} else
-		istr = (char *)null_str;
-
-	if (cycles > 0) {
-		scnprintf(cycle_str, sizeof(cycle_str),
-			  "cycles:%" PRId64 "", cycles);
-		cstr = cycle_str;
-	} else
-		cstr = (char *)null_str;
-
-	predicted_percent = predicted_count * 100.0 / branch_count;
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" (cycles:%" PRId64 "", cycles);
+	}
 
-	if ((predicted_count == branch_count) && (abort_count == 0)) {
-		if ((cycles > 0) || (istr != (char *)null_str))
-			return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
+	if (iter_count && samples_count) {
+		if (i++)
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" iterations:%" PRId64 "",
+				iter_count / samples_count);
 		else
-			return scnprintf(bf, bfsize, "%s", (char *)null_str);
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" (iterations:%" PRId64 "",
+				iter_count / samples_count);
 	}
 
-	if ((predicted_count < branch_count) && (abort_count == 0)) {
-		if ((cycles > 0) || (istr != (char *)null_str))
-			return scnprintf(bf, bfsize,
-				" (predicted:%.1f%% %s%s)",
-				predicted_percent, cstr, istr);
-		else {
-			return scnprintf(bf, bfsize,
-				" (predicted:%.1f%%)",
-				predicted_percent);
-		}
+	if (predicted_count < branch_count) {
+		if (i++)
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" predicted:%.1f%%",
+				predicted_count * 100.0 / branch_count);
+		else
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" (predicted:%.1f%%",
+				predicted_count * 100.0 / branch_count);
 	}
 
-	if ((predicted_count == branch_count) && (abort_count > 0)) {
-		if ((cycles > 0) || (istr != (char *)null_str))
-			return scnprintf(bf, bfsize,
-				" (abort:%" PRId64 " %s%s)",
-				abort_count, cstr, istr);
+	if (abort_count) {
+		if (i++)
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" abort:%.1f%%",
+				abort_count * 100.0 / branch_count);
 		else
-			return scnprintf(bf, bfsize,
-				" (abort:%" PRId64 ")",
-				abort_count);
+			printed += scnprintf(bf + printed, bfsize - printed,
+				" (abort:%.1f%%",
+				abort_count * 100.0 / branch_count);
 	}
 
-	if ((cycles > 0) || (istr != (char *)null_str))
-		return scnprintf(bf, bfsize,
-			" (predicted:%.1f%% abort:%" PRId64 " %s%s)",
-			predicted_percent, abort_count, cstr, istr);
+	if (i)
+		return scnprintf(bf + printed, bfsize - printed, ")");
 
-	return scnprintf(bf, bfsize,
-			" (predicted:%.1f%% abort:%" PRId64 ")",
-			predicted_percent, abort_count);
+	bf[0] = 0;
+	return 0;
 }
 
 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)
+				   u64 iter_count, u64 samples_count,
+				   int *brtype_count)
 {
 	char str[128];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, samples_count);
+			 iter_count, samples_count, brtype_count);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1225,7 +1274,8 @@ int callchain_list_counts__printf_value(struct callchain_node *node,
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
-				       cycles_count, iter_count, samples_count);
+				       cycles_count, iter_count, samples_count,
+				       clist->brtype_count);
 }
 
 static void free_callchain_node(struct callchain_node *node)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index c56c23d..994aa5a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -106,6 +106,18 @@ struct callchain_param {
 extern struct callchain_param callchain_param;
 extern struct callchain_param callchain_param_default;
 
+enum {
+	BR_IDX_JCC_FWD		= 0,
+	BR_IDX_JCC_BWD		= 1,
+	BR_IDX_JMP		= 2,
+	BR_IDX_IND_JMP		= 3,
+	BR_IDX_CALL		= 4,
+	BR_IDX_IND_CALL		= 5,
+	BR_IDX_RET		= 6,
+	BR_IDX_FAR_BRANCH	= 7,
+	BR_IDX_MAX,
+};
+
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
@@ -119,6 +131,7 @@ struct callchain_list {
 	u64			cycles_count;
 	u64			iter_count;
 	u64			samples_count;
+	int			brtype_count[BR_IDX_MAX];
 	char		       *srcline;
 	struct list_head	list;
 };
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index eb7a7b2..4c1a6da 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -142,7 +142,8 @@ struct branch_flags {
 	u64 in_tx:1;
 	u64 abort:1;
 	u64 cycles:16;
-	u64 reserved:44;
+	u64 type:9;
+	u64 reserved:35;
 };
 
 struct branch_entry {
-- 
2.7.4