perf report/top: Add option to collapse undesired parts of call graph

For example, in an application with an expensive function implemented
with deeply nested recursive calls, the default call-graph presentation
is dominated by the different callchains within that function.  By
ignoring these callees, we can collect the callchains leading into the
function and compactly identify what to blame for expensive calls.

For example, in this report the callers of garbage_collect() are
scattered across the tree:

  $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z]
      22.03%     ruby  [.] gc_mark
                 --- gc_mark
                    |--59.40%-- mark_keyvalue
                    |          st_foreach
                    |          gc_mark_children
                    |          |--99.75%-- rb_gc_mark
                    |          |          rb_vm_mark
                    |          |          gc_mark_children
                    |          |          gc_marks
                    |          |          |--99.00%-- garbage_collect

If we ignore the callees of garbage_collect(), its callers are coalesced:

  $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z]
      72.92%     ruby  [.] garbage_collect
                 --- garbage_collect
                     vm_xmalloc
                    |--47.08%-- ruby_xmalloc
                    |          st_insert2
                    |          rb_hash_aset
                    |          |--98.45%-- features_index_add
                    |          |          rb_provide_feature
                    |          |          rb_require_safe
                    |          |          vm_call_method

Signed-off-by: Greg Price <price@mit.edu>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu
Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu
Cc: Fengguang Wu <fengguang.wu@intel.com>
[ remove spaces at beginning of line, reported by Fengguang Wu ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 25 insertions, 12 deletions

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5dd5026a82ef..f9f9d6381b9a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1058,11 +1058,10 @@ int machine__process_event(struct machine *machine, union perf_event *event)
         return ret;
 }
 
-static bool symbol__match_parent_regex(struct symbol *sym)
+static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-        if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
+        if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
                 return 1;
-
         return 0;
 }
 
@@ -1159,8 +1158,8 @@ struct branch_info *machine__resolve_bstack(struct machine *machine,
 static int machine__resolve_callchain_sample(struct machine *machine,
                                              struct thread *thread,
                                              struct ip_callchain *chain,
-                                             struct symbol **parent)
-
+                                             struct symbol **parent,
+                                             struct addr_location *root_al)
 {
         u8 cpumode = PERF_RECORD_MISC_USER;
         unsigned int i;
@@ -1211,8 +1210,15 @@ static int machine__resolve_callchain_sample(struct machine *machine,
                                            MAP__FUNCTION, ip, &al, NULL);
                 if (al.sym != NULL) {
                         if (sort__has_parent && !*parent &&
-                            symbol__match_parent_regex(al.sym))
+                            symbol__match_regex(al.sym, &parent_regex))
                                 *parent = al.sym;
+                        else if (have_ignore_callees && root_al &&
+                          symbol__match_regex(al.sym, &ignore_callees_regex)) {
+                                /* Treat this symbol as the root,
+                                   forgetting its callees. */
+                                *root_al = al;
+                                callchain_cursor_reset(&callchain_cursor);
+                        }
                         if (!symbol_conf.use_callchain)
                                 break;
                 }
@@ -1237,13 +1243,13 @@ int machine__resolve_callchain(struct machine *machine,
                                struct perf_evsel *evsel,
                                struct thread *thread,
                                struct perf_sample *sample,
-                               struct symbol **parent)
-
+                               struct symbol **parent,
+                               struct addr_location *root_al)
 {
         int ret;
 
         ret = machine__resolve_callchain_sample(machine, thread,
-                                                sample->callchain, parent);
+                                                sample->callchain, parent, root_al);
         if (ret)
                 return ret;
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e49ba01b7937..5bb6244194d5 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -5,6 +5,7 @@
 #include <linux/rbtree.h>
 #include "map.h"
 
+struct addr_location;
 struct branch_stack;
 struct perf_evsel;
 struct perf_sample;
@@ -83,7 +84,8 @@ int machine__resolve_callchain(struct machine *machine,
                                struct perf_evsel *evsel,
                                struct thread *thread,
                                struct perf_sample *sample,
-                               struct symbol **parent);
+                               struct symbol **parent,
+                               struct addr_location *root_al);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 951a1cfb317c..1eb58eedcac1 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1406,9 +1406,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 
         if (symbol_conf.use_callchain && sample->callchain) {
 
-
                 if (machine__resolve_callchain(machine, evsel, al.thread,
-                                               sample, NULL) != 0) {
+                                               sample, NULL, NULL) != 0) {
                         if (verbose)
                                 error("Failed to resolve callchain. Skipping\n");
                         return;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 8deee19d2e7f..cb2b108635ee 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -7,6 +7,8 @@ const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char      *parent_pattern = default_parent_pattern;
 const char      default_sort_order[] = "comm,dso,symbol";
 const char      *sort_order = default_sort_order;
+regex_t         ignore_callees_regex;
+int             have_ignore_callees = 0;
 int             sort__need_collapse = 0;
 int             sort__has_parent = 0;
 int             sort__has_sym = 0;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 45ac84c1e037..a4a6d0b1ea0e 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -29,6 +29,8 @@ extern const char *sort_order;
 extern const char default_parent_pattern[];
 extern const char *parent_pattern;
 extern const char default_sort_order[];
+extern regex_t ignore_callees_regex;
+extern int have_ignore_callees;
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern int sort__has_sym;
@@ -183,4 +185,6 @@ int setup_sorting(void);
 extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
 
+int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
+
 #endif  /* __PERF_SORT_H */