perf tools: Check if callchain is corrupted

We faced segmentation fault on perf top -G at very high sampling rate
due to a corrupted callchain. While the root cause was not revealed (I
failed to figure it out), this patch tries to protect us from the
segfault on such cases.

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Namhyung Kim <namhyung.kim@lge.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sunjin Yang <fan4326@gmail.com>
Link: http://lkml.kernel.org/r/1338443007-24857-2-git-send-email-namhyung.kim@lge.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 15 insertions, 3 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f32578634d9d..1817d4015e5f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -555,6 +555,8 @@ enum perf_event_type {
         PERF_RECORD_MAX,                        /* non-ABI */
 };
 
+#define PERF_MAX_STACK_DEPTH            255
+
 enum perf_callchain_context {
         PERF_CONTEXT_HV                 = (__u64)-32,
         PERF_CONTEXT_KERNEL             = (__u64)-128,
@@ -609,8 +611,6 @@ struct perf_guest_info_callbacks {
 #include <linux/sysfs.h>
 #include <asm/local.h>
 
-#define PERF_MAX_STACK_DEPTH            255
-
 struct perf_callchain_entry {
         __u64                           nr;
         __u64                           ip[PERF_MAX_STACK_DEPTH];
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 3b6f8e460a31..04d1e33f4592 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -300,6 +300,11 @@ int machine__resolve_callchain(struct machine *self,
 
         callchain_cursor_reset(&callchain_cursor);
 
+        if (chain->nr > PERF_MAX_STACK_DEPTH) {
+                pr_warning("corrupted callchain. skipping...\n");
+                return 0;
+        }
+
         for (i = 0; i < chain->nr; i++) {
                 u64 ip;
                 struct addr_location al;
@@ -318,7 +323,14 @@ int machine__resolve_callchain(struct machine *self,
                         case PERF_CONTEXT_USER:
                                 cpumode = PERF_RECORD_MISC_USER;        break;
                         default:
-                                break;
+                                pr_debug("invalid callchain context: "
+                                         "%"PRId64"\n", (s64) ip);
+                                /*
+                                 * It seems the callchain is corrupted.
+                                 * Discard all.
+                                 */
+                                callchain_cursor_reset(&callchain_cursor);
+                                return 0;
                         }
                         continue;
                 }