[PATCH 13/28] perf auxtrace: Harden auxtrace_error event handling

[Arnaldo Carvalho de Melo <acme@kernel.org>]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

Fix four issues in PERF_RECORD_AUXTRACE_ERROR handling:

1. auxtrace_error_name() takes a signed int parameter, but e->type
   is __u32.  A crafted value like 0xFFFFFFFF converts to -1, passes
   the bounds check, and causes a negative array index.  Fix by
   changing the parameter to unsigned int.

2. The msg field is printed via %s without a length bound.  The
   min_size table only guarantees fields up to msg (offset 48), so
   a truncated event has zero msg bytes within the event boundary.
   Compute the available msg length from header.size, cap at
   sizeof(e->msg), and use %.*s.

3. fmt >= 2 adds machine_pid and vcpu fields after msg[64].  Older
   files may have fmt >= 2 but an event size that doesn't include
   these fields.  Add a size check in the swap handler to downgrade
   fmt before the conditional field access, and a matching size
   guard in the fprintf path for native-endian events (which are
   mmap'd read-only and can't be modified in place).

4. python_process_auxtrace_error() had the same issues: msg was
   passed to tuple_set_string() unbounded, and machine_pid/vcpu
   were accessed unconditionally without checking fmt or event
   size.  Apply the same bounds checks.

Reported-by: sashiko-bot@kernel.org # Running on a local machine
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/auxtrace.c                    | 24 +++++++++++++---
 .../scripting-engines/trace-event-python.c    | 28 +++++++++++++++++--
 tools/perf/util/session.c                     | 18 ++++++++++--
 3 files changed, 61 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a224687ffbc1b5be..d9770e1d2f959fc4 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1759,7 +1759,7 @@ static const char * const auxtrace_error_type_name[] = {
 	[PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
 };
 
-static const char *auxtrace_error_name(int type)
+static const char *auxtrace_error_name(unsigned int type)
 {
 	const char *error_type_name = NULL;
 
@@ -1775,6 +1775,7 @@ size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
 	struct perf_record_auxtrace_error *e = &event->auxtrace_error;
 	unsigned long long nsecs = e->time;
 	const char *msg = e->msg;
+	int msg_max;
 	int ret;
 
 	ret = fprintf(fp, " %s error type %u",
@@ -1792,11 +1793,26 @@ size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
 	if (!e->fmt)
 		msg = (const char *)&e->time;
 
-	if (e->fmt >= 2 && e->machine_pid)
+	/* Bound msg to the bytes actually within the event, capped at the array size */
+	msg_max = (int)((void *)event + event->header.size - (void *)msg);
+	if (msg_max < 0)
+		msg_max = 0;
+	if (msg_max > (int)sizeof(e->msg))
+		msg_max = sizeof(e->msg);
+
+	/*
+	 * Unlike the swap path which downgrades fmt in place,
+	 * native-endian events are mmap'd read-only — check size
+	 * instead to avoid accessing machine_pid/vcpu OOB.
+	 */
+	if (e->fmt >= 2 &&
+	    event->header.size >= offsetof(typeof(event->auxtrace_error), vcpu) +
+				  sizeof(event->auxtrace_error.vcpu) &&
+	    e->machine_pid)
 		ret += fprintf(fp, " machine_pid %d vcpu %d", e->machine_pid, e->vcpu);
 
-	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRI_lx64" code %u: %s\n",
-		       e->cpu, e->pid, e->tid, e->ip, e->code, msg);
+	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRI_lx64" code %u: %.*s\n",
+		       e->cpu, e->pid, e->tid, e->ip, e->code, msg_max, msg);
 	return ret;
 }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 5a30caaec73ef06b..5b8f629fd54cbe49 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1614,6 +1614,9 @@ static void python_process_auxtrace_error(struct perf_session *session __maybe_u
 	const char *handler_name = "auxtrace_error";
 	unsigned long long tm = e->time;
 	const char *msg = e->msg;
+	s32 machine_pid = 0, vcpu = 0;
+	char msg_buf[MAX_AUXTRACE_ERROR_MSG + 1];
+	int msg_max;
 	PyObject *handler, *t;
 
 	handler = get_handler(handler_name);
@@ -1625,6 +1628,25 @@ static void python_process_auxtrace_error(struct perf_session *session __maybe_u
 		msg = (const char *)&e->time;
 	}
 
+	/* Bound msg to the bytes within the event, ensure NUL-termination */
+	msg_max = (int)((void *)event + event->header.size - (void *)msg);
+	if (msg_max <= 0) {
+		msg_buf[0] = '\0';
+	} else {
+		if (msg_max > (int)sizeof(msg_buf) - 1)
+			msg_max = sizeof(msg_buf) - 1;
+		memcpy(msg_buf, msg, msg_max);
+		msg_buf[msg_max] = '\0';
+	}
+
+	/* Only access fmt >= 2 fields if the event is large enough */
+	if (e->fmt >= 2 &&
+	    event->header.size >= offsetof(typeof(event->auxtrace_error), vcpu) +
+				  sizeof(event->auxtrace_error.vcpu)) {
+		machine_pid = e->machine_pid;
+		vcpu = e->vcpu;
+	}
+
 	t = tuple_new(11);
 
 	tuple_set_u32(t, 0, e->type);
@@ -1634,10 +1656,10 @@ static void python_process_auxtrace_error(struct perf_session *session __maybe_u
 	tuple_set_s32(t, 4, e->tid);
 	tuple_set_u64(t, 5, e->ip);
 	tuple_set_u64(t, 6, tm);
-	tuple_set_string(t, 7, msg);
+	tuple_set_string(t, 7, msg_buf);
 	tuple_set_u32(t, 8, cpumode);
-	tuple_set_s32(t, 9, e->machine_pid);
-	tuple_set_s32(t, 10, e->vcpu);
+	tuple_set_s32(t, 9, machine_pid);
+	tuple_set_s32(t, 10, vcpu);
 
 	call_object(handler, t, handler_name);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c23899c42ef7af34..a2dba77c6a2b9d2f 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -747,8 +747,22 @@ static int perf_event__auxtrace_error_swap(union perf_event *event,
 	if (event->auxtrace_error.fmt)
 		event->auxtrace_error.time = bswap_64(event->auxtrace_error.time);
 	if (event->auxtrace_error.fmt >= 2) {
-		event->auxtrace_error.machine_pid = bswap_32(event->auxtrace_error.machine_pid);
-		event->auxtrace_error.vcpu = bswap_32(event->auxtrace_error.vcpu);
+		/*
+		 * fmt >= 2 adds machine_pid and vcpu after msg[64].
+		 * Older files may have fmt >= 2 but an event size
+		 * that doesn't include these fields — downgrade to
+		 * avoid swapping out of bounds.
+		 */
+		if (event->header.size < offsetof(typeof(event->auxtrace_error), vcpu) +
+					 sizeof(event->auxtrace_error.vcpu)) {
+			pr_warning("WARNING: PERF_RECORD_AUXTRACE_ERROR: fmt %u but event too small for machine_pid/vcpu (%u bytes), downgrading fmt\n",
+				   event->auxtrace_error.fmt,
+				   event->header.size);
+			event->auxtrace_error.fmt = 1;
+		} else {
+			event->auxtrace_error.machine_pid = bswap_32(event->auxtrace_error.machine_pid);
+			event->auxtrace_error.vcpu = bswap_32(event->auxtrace_error.vcpu);
+		}
 	}
 	return 0;
 }
-- 
2.54.0