perf report: Calculate the average cycles of iterations

The branch history code has a loop detection function. With this, we can
get the number of iterations by calculating the removed loops.

While it would be nice for knowing the average cycles of iterations.
This patch adds up the cycles in branch entries of removed loops and
save the result to the next branch entry (e.g. branch entry A).

Finally it will display the iteration number and average cycles at the
"from" of branch entry A.

For example:
perf record -g -j any,save_type ./div
perf report --branch-history --no-children --stdio

--22.63%--main div.c:42 (RET CROSS_2M)
          compute_flag div.c:28 (cycles:2 iter:173115 avg_cycles:2)
          |
           --10.73%--compute_flag div.c:27 (RET CROSS_2M)
                     rand rand.c:28 (cycles:1)
                     rand rand.c:28 (RET CROSS_2M)
                     __random random.c:298 (cycles:1)
                     __random random.c:297 (COND_BWD CROSS_2M)
                     __random random.c:295 (cycles:1)
                     __random random.c:295 (COND_BWD CROSS_2M)
                     __random random.c:295 (cycles:1)
                     __random random.c:295 (RET CROSS_2M)

Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1502111115-18305-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 23 insertions, 26 deletions

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index f320b0777e0d..510b513e0f01 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -588,7 +588,7 @@ 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;
+				call->iter_cycles = cursor_node->iter_cycles;
 			}
 		}
 
@@ -722,7 +722,7 @@ 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;
+				cnode->iter_cycles += node->iter_cycles;
 			}
 		}
 
@@ -998,7 +998,7 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
 			    u64 ip, struct map *map, struct symbol *sym,
 			    bool branch, struct branch_flags *flags,
-			    int nr_loop_iter, int samples, u64 branch_from)
+			    int nr_loop_iter, u64 iter_cycles, u64 branch_from)
 {
 	struct callchain_cursor_node *node = *cursor->last;
 
@@ -1016,7 +1016,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	node->sym = sym;
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
-	node->samples = samples;
+	node->iter_cycles = iter_cycles;
 
 	if (flags)
 		memcpy(&node->branch_flags, flags,
@@ -1306,7 +1306,7 @@ static int branch_to_str(char *bf, int bfsize,
 static int branch_from_str(char *bf, int bfsize,
 			   u64 branch_count,
 			   u64 cycles_count, u64 iter_count,
-			   u64 samples_count)
+			   u64 iter_cycles)
 {
 	int printed = 0, i = 0;
 	u64 cycles;
@@ -1318,9 +1318,13 @@ static int branch_from_str(char *bf, int bfsize,
 				bf + printed, bfsize - printed);
 	}
 
-	if (iter_count && samples_count) {
-		printed += count_pri64_printf(i++, "iterations",
-				iter_count / samples_count,
+	if (iter_count) {
+		printed += count_pri64_printf(i++, "iter",
+				iter_count,
+				bf + printed, bfsize - printed);
+
+		printed += count_pri64_printf(i++, "avg_cycles",
+				iter_cycles / iter_count,
 				bf + printed, bfsize - printed);
 	}
 
@@ -1333,7 +1337,7 @@ static int branch_from_str(char *bf, int bfsize,
 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 iter_cycles,
 			     struct branch_type_stat *brtype_stat)
 {
 	int printed;
@@ -1346,7 +1350,7 @@ static int counts_str_build(char *bf, int bfsize,
 				predicted_count, abort_count, brtype_stat);
 	} else {
 		printed = branch_from_str(bf, bfsize, branch_count,
-				cycles_count, iter_count, samples_count);
+				cycles_count, iter_count, iter_cycles);
 	}
 
 	if (!printed)
@@ -1358,14 +1362,14 @@ static int counts_str_build(char *bf, int bfsize,
 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 iter_cycles,
 				   struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, samples_count, brtype_stat);
+			 iter_count, iter_cycles, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1373,31 +1377,23 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 	return scnprintf(bf, bfsize, "%s", str);
 }
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-					struct callchain_list *clist,
+int callchain_list_counts__printf_value(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;
+	u64 iter_count, iter_cycles;
 
 	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;
-		}
-	}
+	iter_count = clist->iter_count;
+	iter_cycles = clist->iter_cycles;
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
-				       cycles_count, iter_count, samples_count,
+				       cycles_count, iter_count, iter_cycles,
 				       &clist->brtype_stat);
 }
 
@@ -1523,7 +1519,8 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
 		rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
 					     node->branch, &node->branch_flags,
-					     node->nr_loop_iter, node->samples,
+					     node->nr_loop_iter,
+					     node->iter_cycles,
 					     node->branch_from);
 		if (rc)
 			break;