[PATCH V3 1/2] perf,tools: add time out to force stop proc map processing

[kan . liang]

From: Kan Liang <kan.liang@xxxxxxxxx>

System wide sampling like 'perf top' or 'perf record -a' read all
threads /proc/xxx/maps before sampling. If there are any threads which
generating a keeping growing huge maps, perf will do infinite loop
during synthesizing. Nothing will be sampled.

This patch fixes this issue by adding per-thread timeout to force stop
this kind of endless proc map processing.
PERF_RECORD_MISC_MMAP_TIME_OUT is introduced to indicate that the mmap
record are truncated by time out. User will get warning notification
when truncated mmap records are detected.

Reported-by: Huang, Ying <ying.huang@xxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
---

Changes since V1
 - Add warning message for time out.

Changes since V2
 - Handle time out warning in perf_session__warn_about_errors
 - Configurable time out (patch 2/2)

 include/uapi/linux/perf_event.h |  4 ++++
 tools/perf/util/event.c         | 18 ++++++++++++++++++
 tools/perf/util/event.h         |  1 +
 tools/perf/util/session.c       | 11 +++++++++++
 4 files changed, 34 insertions(+)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 613ed9a..b3904ba 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -566,6 +566,10 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
 
 /*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_MMAP_TIME_OUT		(1 << 12)
+/*
  * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
  * different events so can reuse the same bit position.
  */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 793b150..ac6cf2a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -213,6 +213,8 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	return 0;
 }
 
+#define MMAP_TIMEOUT	(50 * 1000000ULL)
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -222,6 +224,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 {
 	char filename[PATH_MAX];
 	FILE *fp;
+	unsigned long long t;
+	bool timeout = false;
 	int rc = 0;
 
 	if (machine__is_default_guest(machine))
@@ -240,6 +244,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	}
 
 	event->header.type = PERF_RECORD_MMAP2;
+	t = rdclock();
 
 	while (1) {
 		char bf[BUFSIZ];
@@ -253,6 +258,12 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
+		if ((rdclock() - t) > MMAP_TIMEOUT) {
+			pr_warning("Reading %s time out.\n", filename);
+			timeout = true;
+			goto out;
+		}
+
 		/* ensure null termination since stack will be reused. */
 		strcpy(execname, "");
 
@@ -301,6 +312,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
 		}
 
+out:
+		if (timeout)
+			event->header.misc |= PERF_RECORD_MISC_MMAP_TIME_OUT;
+
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
 
@@ -319,6 +334,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			rc = -1;
 			break;
 		}
+
+		if (timeout)
+			break;
 	}
 
 	fclose(fp);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5dc51ad..39868f5 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -265,6 +265,7 @@ struct events_stats {
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
 	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+	u32 nr_proc_map_timeout;
 };
 
 struct attr_event {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88d87bf..8561d8b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1041,6 +1041,8 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
+		if (event->header.misc & PERF_RECORD_MISC_MMAP_TIME_OUT)
+			++evlist->stats.nr_proc_map_timeout;
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
@@ -1337,6 +1339,15 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
 
 	events_stats__auxtrace_error_warn(stats);
+
+	if (stats->nr_proc_map_timeout != 0) {
+		ui__warning("%d map information files for pre-existing threads were\n"
+			    "not processed, if there are samples for addresses they\n"
+			    "will not be resolved, you may find out which are these\n"
+			    "threads by running with -v and redirecting the output\n"
+			    "to a file.\n",
+			    stats->nr_proc_map_timeout);
+	}
 }
 
 volatile int session_done;
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/