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>

2 files changed, 20 insertions, 2 deletions

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) {