perf tools: Add inverted call graph report support.

Add "caller/callee" option to support inverted butterfly report,
in the inverted report (with caller option), the call graph start
from the callee's ancestor. Users can use such view to catch system's
performance bottleneck from a sysprof like view. Using this option
with specified sort order like pid gives us high level view of call
graph statistics.

Also add "-G" alias for inverted call graph.

Signed-off-by: Sam Liao <phyomh@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

3 files changed, 14 insertions, 2 deletions

diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1a79df9f739f..9b4ff16cac96 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -14,6 +14,11 @@ enum chain_mode {
         CHAIN_GRAPH_REL
 };
 
+enum chain_order {
+        ORDER_CALLER,
+        ORDER_CALLEE
+};
+
 struct callchain_node {
         struct callchain_node   *parent;
         struct list_head        siblings;
@@ -41,6 +46,7 @@ struct callchain_param {
         u32                     print_limit;
         double                  min_percent;
         sort_chain_func_t       sort;
+        enum chain_order        order;
 };
 
 struct callchain_list {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 627a02e03c57..dae4202fa65a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -14,7 +14,8 @@ enum hist_filter {
 
 struct callchain_param  callchain_param = {
         .mode   = CHAIN_GRAPH_REL,
-        .min_percent = 0.5
+        .min_percent = 0.5,
+        .order  = ORDER_CALLEE
 };
 
 u16 hists__col_len(struct hists *self, enum hist_column col)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b723f211881c..558bcf996949 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -247,9 +247,14 @@ int perf_session__resolve_callchain(struct perf_session *self,
         callchain_cursor_reset(&self->callchain_cursor);
 
         for (i = 0; i < chain->nr; i++) {
-                u64 ip = chain->ips[i];
+                u64 ip;
                 struct addr_location al;
 
+                if (callchain_param.order == ORDER_CALLEE)
+                        ip = chain->ips[i];
+                else
+                        ip = chain->ips[chain->nr - i - 1];
+
                 if (ip >= PERF_CONTEXT_MAX) {
                         switch (ip) {
                         case PERF_CONTEXT_HV: