Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

 - Free callchains when hist entries are deleted, plugging a massive leak in
   'top -g', where hist_entries (and its callchains) are decayed over time. (Namhyung Kim)

 - Fix segfault when showing callchain in the hists browser (report & top) (Namhyung Kim)

 - Fix children sort key behavior, and also the 'perf test 32' test that
   was failing due to reliance on undefined behaviour (Namhyung Kim)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 69 insertions, 33 deletions

diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 4b8226e19a91..8d110dec393e 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
          *   30.00%    10.00%     perf  perf           [.] cmd_record
          *   20.00%     0.00%     bash  libc           [.] malloc
          *   10.00%    10.00%     bash  [kernel]       [k] page_fault
-         *   10.00%    10.00%     perf  [kernel]       [k] schedule
-         *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+         *   10.00%    10.00%     bash  bash           [.] xmalloc
          *   10.00%    10.00%     perf  [kernel]       [k] page_fault
-         *   10.00%    10.00%     perf  libc           [.] free
          *   10.00%    10.00%     perf  libc           [.] malloc
-         *   10.00%    10.00%     bash  bash           [.] xmalloc
+         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *   10.00%    10.00%     perf  libc           [.] free
+         *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
          */
         struct result expected[] = {
                 { 7000, 2000, "perf", "perf",     "main" },
@@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 { 3000, 1000, "perf", "perf",     "cmd_record" },
                 { 2000,    0, "bash", "libc",     "malloc" },
                 { 1000, 1000, "bash", "[kernel]", "page_fault" },
-                { 1000, 1000, "perf", "[kernel]", "schedule" },
-                { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+                { 1000, 1000, "bash", "bash",     "xmalloc" },
                 { 1000, 1000, "perf", "[kernel]", "page_fault" },
+                { 1000, 1000, "perf", "[kernel]", "schedule" },
                 { 1000, 1000, "perf", "libc",     "free" },
                 { 1000, 1000, "perf", "libc",     "malloc" },
-                { 1000, 1000, "bash", "bash",     "xmalloc" },
+                { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
         };
 
         symbol_conf.use_callchain = false;
@@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  malloc
          *                  main
          *
-         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *   10.00%    10.00%     bash  bash           [.] xmalloc
          *              |
-         *              --- schedule
-         *                  run_command
+         *              --- xmalloc
+         *                  malloc
+         *                  xmalloc     <--- NOTE: there's a cycle
+         *                  malloc
+         *                  xmalloc
          *                  main
          *
          *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
@@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  run_command
          *                  main
          *
+         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *              |
+         *              --- schedule
+         *                  run_command
+         *                  main
+         *
          *   10.00%    10.00%     perf  libc           [.] free
          *              |
          *              --- free
@@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  run_command
          *                  main
          *
-         *   10.00%    10.00%     bash  bash           [.] xmalloc
-         *              |
-         *              --- xmalloc
-         *                  malloc
-         *                  xmalloc     <--- NOTE: there's a cycle
-         *                  malloc
-         *                  xmalloc
-         *                  main
-         *
          */
         struct result expected[] = {
                 { 7000, 2000, "perf", "perf",     "main" },
@@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 { 3000, 1000, "perf", "perf",     "cmd_record" },
                 { 2000,    0, "bash", "libc",     "malloc" },
                 { 1000, 1000, "bash", "[kernel]", "page_fault" },
-                { 1000, 1000, "perf", "[kernel]", "schedule" },
+                { 1000, 1000, "bash", "bash",     "xmalloc" },
                 { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
                 { 1000, 1000, "perf", "[kernel]", "page_fault" },
+                { 1000, 1000, "perf", "[kernel]", "schedule" },
                 { 1000, 1000, "perf", "libc",     "free" },
                 { 1000, 1000, "perf", "libc",     "malloc" },
-                { 1000, 1000, "bash", "bash",     "xmalloc" },
         };
         struct callchain_result expected_callchain[] = {
                 {
@@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "bash",     "main" }, },
                 },
                 {
-                        3, {    { "[kernel]", "schedule" },
-                                { "perf",     "run_command" },
-                                { "perf",     "main" }, },
+                        6, {    { "bash",     "xmalloc" },
+                                { "libc",     "malloc" },
+                                { "bash",     "xmalloc" },
+                                { "libc",     "malloc" },
+                                { "bash",     "xmalloc" },
+                                { "bash",     "main" }, },
                 },
                 {
                         3, {    { "[kernel]", "sys_perf_event_open" },
@@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "perf",     "main" }, },
                 },
                 {
+                        3, {    { "[kernel]", "schedule" },
+                                { "perf",     "run_command" },
+                                { "perf",     "main" }, },
+                },
+                {
                         4, {    { "libc",     "free" },
                                 { "perf",     "cmd_record" },
                                 { "perf",     "run_command" },
@@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "perf",     "run_command" },
                                 { "perf",     "main" }, },
                 },
-                {
-                        6, {    { "bash",     "xmalloc" },
-                                { "libc",     "malloc" },
-                                { "bash",     "xmalloc" },
-                                { "libc",     "malloc" },
-                                { "bash",     "xmalloc" },
-                                { "bash",     "main" }, },
-                },
         };
 
         symbol_conf.use_callchain = true;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e6bb04b5b09b..788506eef567 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -550,7 +550,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
         bool need_percent;
 
         node = rb_first(root);
-        need_percent = !!rb_next(node);
+        need_percent = node && rb_next(node);
 
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index dc0d095f318c..482adae3cc44 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
                 if (ret)
                         return ret;
 
+                if (a->thread != b->thread || !symbol_conf.use_callchain)
+                        return 0;
+
                 ret = b->callchain->max_depth - a->callchain->max_depth;
         }
         return ret;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 64b377e591e4..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 
         return bf;
 }
+
+static void free_callchain_node(struct callchain_node *node)
+{
+        struct callchain_list *list, *tmp;
+        struct callchain_node *child;
+        struct rb_node *n;
+
+        list_for_each_entry_safe(list, tmp, &node->val, list) {
+                list_del(&list->list);
+                free(list);
+        }
+
+        n = rb_first(&node->rb_root_in);
+        while (n) {
+                child = container_of(n, struct callchain_node, rb_node_in);
+                n = rb_next(n);
+                rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+                free_callchain_node(child);
+                free(child);
+        }
+}
+
+void free_callchain(struct callchain_root *root)
+{
+        if (!symbol_conf.use_callchain)
+                return;
+
+        free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index dbc08cf5f970..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 char *callchain_list__sym_name(struct callchain_list *cl,
                                char *bf, size_t bfsize, bool show_dso);
 
+void free_callchain(struct callchain_root *root);
+
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0ced178ce306..182395546ddc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -947,6 +947,7 @@ void hist_entry__free(struct hist_entry *he)
         zfree(&he->mem_info);
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
+        free_callchain(he->callchain);
         free(he);
 }