[tip:perf/core] perf script python: Fix string vs byte array resolving

[tip-bot for Jiri Olsa]

Commit-ID:  249de6e074580988d3ee4902236803098e2cda4c
Gitweb:     http://git.kernel.org/tip/249de6e074580988d3ee4902236803098e2cda4c
Author:     Jiri Olsa <jolsa@xxxxxxxxxx>
AuthorDate: Sat, 16 Jul 2016 18:11:18 +0200
Committer:  Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Mon, 18 Jul 2016 19:48:04 -0300

perf script python: Fix string vs byte array resolving

Jirka reported that python code returns all arrays as strings.  This
makes impossible to get all items for byte array tracepoint field
containing 0x00 value item.

Fixing this by scanning full length of the array and returning it as
PyByteArray object in case non printable byte is found.

Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Reported-and-Tested-by: Jiri Pirko <jiri@xxxxxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1468685480-18951-2-git-send-email-jolsa@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 .../util/scripting-engines/trace-event-python.c    | 39 ++++++++++++++++++----
 1 file changed, 33 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 6ac6b7a..7bd6da8 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -386,6 +386,21 @@ exit:
 	return pylist;
 }
 
+static int is_printable_array(char *p, unsigned int len)
+{
+	unsigned int i;
+
+	if (!p || !len || p[len - 1] != 0)
+		return 0;
+
+	len--;
+
+	for (i = 0; i < len; i++) {
+		if (!isprint(p[i]) && !isspace(p[i]))
+			return 0;
+	}
+	return 1;
+}
 
 static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
@@ -457,14 +472,26 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		pydict_set_item_string_decref(dict, "common_callchain", callchain);
 	}
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
-			int offset;
+		unsigned int offset, len;
+		unsigned long long val;
+
+		if (field->flags & FIELD_IS_ARRAY) {
+			offset = field->offset;
+			len    = field->size;
 			if (field->flags & FIELD_IS_DYNAMIC) {
-				offset = *(int *)(data + field->offset);
+				val     = pevent_read_number(scripting_context->pevent,
+							     data + offset, len);
+				offset  = val;
+				len     = offset >> 16;
 				offset &= 0xffff;
-			} else
-				offset = field->offset;
-			obj = PyString_FromString((char *)data + offset);
+			}
+			if (field->flags & FIELD_IS_STRING &&
+			    is_printable_array(data + offset, len)) {
+				obj = PyString_FromString((char *) data + offset);
+			} else {
+				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+				field->flags &= ~FIELD_IS_STRING;
+			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
 		}