[PATCH] perf ctf: Convert invalid chars in a string before set value

[Wang Nan]

We observed some crazy apps on Android set their comm to unprintable
string. For example:

  # cat /proc/10607/task/*/comm
  tencent.qqmusic
  ...
  Binder_2
  æåèåç  <-- Chinese word 'log output thread'
  WifiManager
  ...

'perf data convert' fails to convert perf.data with such string to CTF format.

For example:
 # cat << EOF > ./badguy.c
 #include <sys/prctl.h>
 int main(int argc, char *argv[])
 {
         prctl(PR_SET_NAME, "\xe6\x97\xa5\xe5\xbf\x97\xe8\xbe\x93\xe5\x87\xba\xe7\xba\xbf");
         while(1)
                 sleep(1);
         return 0;
 }
 # gcc ./badguy.c
 # perf record -e sched:* ./a.out
 # perf data convert --to-ctf ./bad.ctf
 CTF stream 4 flush failed
 [ perf data convert: Converted 'perf.data' into CTF data './bad.ctf' ]
 [ perf data convert: Converted and wrote 0.008 MB (78 samples)  ]
 # babeltrace ./bad.ctf/
 [error] Packet size (18446744073709551615 bits) is larger than remaining file size (262144 bits).
 [error] Stream index creation error.
 [error] Open file stream error.
 [warning] [Context] Cannot open_trace of format ctf at path ./bad.ctf.
 [warning] [Context] cannot open trace "./bad.ctf" from ./bad.ctf/ for reading.
 [error] Cannot open any trace for reading.

 [error] opening trace "./bad.ctf/" for reading.

 [error] none of the specified trace paths could be opened.

This patch converts unprintable characters to hexadecimal word.

After applying this patch the above test works correctly:

  # ~/perf data convert --to-ctf ./good.ctf
  [ perf data convert: Converted 'perf.data' into CTF data './good.ctf' ]
  [ perf data convert: Converted and wrote 0.008 MB (78 samples) ]
  # babeltrace ./good.ctf
  ..
  [23:14:35.491665268] (+0.000001100) sched:sched_wakeup: { cpu_id = 4 }, { perf_ip = 0xFFFFFFFF810AEF33, perf_tid = 0, perf_pid = 0, perf_id = 5123, perf_period = 1, common_type = 270, common_flags = 45, common_preempt_count = 4, common_pid = 0, comm = "\xe6\x97\xa5\xe5\xbf\x97\xe8\xbe\x93\xe5\x87\xba\xe7\xba\xbf", pid = 1057, prio = 120, success = 1, target_cpu = 4 }
 [23:14:35.491666230] (+0.000000962) sched:sched_wakeup: { cpu_id = 4 }, { perf_ip = 0xFFFFFFFF810AEF33, perf_tid = 0, perf_pid = 0, perf_id = 5122, perf_period = 1, common_type = 270, common_flags = 45, common_preempt_count = 4, common_pid = 0, comm = "\xe6\x97\xa5\xe5\xbf\x97\xe8\xbe\x93\xe5\x87\xba\xe7\xba\xbf", pid = 1057, prio = 120, success = 1, target_cpu = 4 }
  ..

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
---
 tools/perf/util/data-convert-bt.c | 31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index bbf69d2..c66490e 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -204,6 +204,34 @@ static unsigned long long adjust_signedness(unsigned long long value_int, int si
 	return (value_int & value_mask) | ~value_mask;
 }
 
+static int string_set_value(struct bt_ctf_field *field, const char *string)
+{
+	char *buffer;
+	size_t len = strlen(string), i, p;
+	int err;
+
+	buffer = zalloc(len * 4 + 2);
+	if (!buffer)
+		return bt_ctf_field_string_set_value(field, string);
+
+	for (i = p = 0; i < len; i++) {
+		if (isprint(string[i])) {
+			buffer[p++] = string[i];
+		} else {
+			char numstr[5];
+
+			snprintf(numstr, sizeof(numstr), "\\x%02x",
+				(unsigned int)(string[i]) & 0xff);
+			strncat(buffer, numstr, 4);
+			p = strlen(buffer);
+		}
+	}
+
+	err = bt_ctf_field_string_set_value(field, buffer);
+	free(buffer);
+	return err;
+}
+
 static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
@@ -270,8 +298,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 
 		if (flags & FIELD_IS_STRING)
-			ret = bt_ctf_field_string_set_value(field,
-					data + offset + i * len);
+			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
 
-- 
1.8.3.4