[PATCH 2/5] rtla: Discard trace entries with cpu >= nr_cpus

[Tomas Glozar <tglozar@redhat.com>]

The "cpu" field of trace entries processed by rtla in tracefs mode is
used as an index into an array of size nr_cpus. In case the cpu numbers
mismatch because either the kernel or rtla reporting the number
incorrectly, out-of-bounds read/write may occur.

Guard against this by dropping trace entries with cpu >= nr_cpus in
collect_registered_events(). A new counter, "invalid_events", is added
to struct trace_instance, and printed (if non zero) next to the
pre-existing missed events counter.

Signed-off-by: Tomas Glozar <tglozar@redhat.com>
---
 tools/tracing/rtla/src/common.h        |  2 --
 tools/tracing/rtla/src/osnoise.c       | 26 +++++++++++++++++++++++++-
 tools/tracing/rtla/src/osnoise.h       |  2 ++
 tools/tracing/rtla/src/osnoise_hist.c  |  1 +
 tools/tracing/rtla/src/osnoise_top.c   |  1 +
 tools/tracing/rtla/src/timerlat_hist.c |  1 +
 tools/tracing/rtla/src/timerlat_top.c  |  1 +
 tools/tracing/rtla/src/trace.c         |  7 +++++++
 tools/tracing/rtla/src/trace.h         |  1 +
 tools/tracing/rtla/src/utils.h         |  2 ++
 10 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/tools/tracing/rtla/src/common.h b/tools/tracing/rtla/src/common.h
index 04b287a03f6d4..051d56182276b 100644
--- a/tools/tracing/rtla/src/common.h
+++ b/tools/tracing/rtla/src/common.h
@@ -114,8 +114,6 @@ struct common_params {
 	struct timerlat_u_params user;
 };
 
-extern int nr_cpus;
-
 #define for_each_monitored_cpu(cpu, common) \
 	for (cpu = 0; cpu < nr_cpus; cpu++) \
 		if (!(common)->cpus || CPU_ISSET(cpu, &(common)->monitored_cpus))
diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c
index 4ff5dad013b10..b9bcbf9ee430c 100644
--- a/tools/tracing/rtla/src/osnoise.c
+++ b/tools/tracing/rtla/src/osnoise.c
@@ -1224,6 +1224,29 @@ bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record
 	return record && !tracefs_trace_is_on(record->trace.inst);
 }
 
+/*
+ * osnoise_report_invalid_events - report number of invalid events
+ */
+void
+osnoise_report_invalid_events(struct osnoise_tool *tool)
+{
+	unsigned long long total_events;
+
+	if (tool->trace.invalid_events > 0) {
+		if (tool->trace.missed_events != UINT64_MAX) {
+			total_events = tool->trace.processed_events + tool->trace.invalid_events +
+				tool->trace.missed_events;
+
+			printf("%lld (%.2f%%) invalid events, results might not be accurate\n",
+				tool->trace.invalid_events,
+				(double) tool->trace.invalid_events / total_events * 100.0);
+		} else {
+			printf("%lld invalid events, results might not be accurate\n",
+				tool->trace.invalid_events);
+		}
+	}
+}
+
 /*
  * osnoise_report_missed_events - report number of events dropped by trace
  * buffer
@@ -1236,7 +1259,8 @@ osnoise_report_missed_events(struct osnoise_tool *tool)
 	if (tool->trace.missed_events == UINT64_MAX)
 		printf("unknown number of events missed, results might not be accurate\n");
 	else if (tool->trace.missed_events > 0) {
-		total_events = tool->trace.processed_events + tool->trace.missed_events;
+		total_events = tool->trace.processed_events + tool->trace.invalid_events +
+			tool->trace.missed_events;
 
 		printf("%lld (%.2f%%) events missed, results might not be accurate\n",
 		       tool->trace.missed_events,
diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h
index 340ff5a64e6e4..b54e9ebef7f27 100644
--- a/tools/tracing/rtla/src/osnoise.h
+++ b/tools/tracing/rtla/src/osnoise.h
@@ -56,6 +56,8 @@ void osnoise_restore_timerlat_align_us(struct osnoise_context *context);
 int osnoise_set_timerlat_align(struct osnoise_context *context, bool onoff);
 
 int osnoise_set_irq_disable(struct osnoise_context *context, bool onoff);
+
+void osnoise_report_invalid_events(struct osnoise_tool *tool);
 void osnoise_report_missed_events(struct osnoise_tool *tool);
 int osnoise_apply_config(struct osnoise_tool *tool, struct osnoise_params *params);
 
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index dfa91d0681f8f..bad0b8958ddb2 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -397,6 +397,7 @@ osnoise_print_stats(struct osnoise_tool *tool)
 	trace_seq_reset(trace->seq);
 
 	osnoise_print_summary(params, trace, data);
+	osnoise_report_invalid_events(tool);
 	osnoise_report_missed_events(tool);
 }
 
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index 512a6299cb018..3c0ff82a4b5c8 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -242,6 +242,7 @@ osnoise_print_stats(struct osnoise_tool *top)
 
 	trace_seq_do_printf(trace->seq);
 	trace_seq_reset(trace->seq);
+	osnoise_report_invalid_events(top);
 	osnoise_report_missed_events(top);
 }
 
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index df7b1398a966d..b6af5ba11340d 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -682,6 +682,7 @@ timerlat_print_stats(struct osnoise_tool *tool)
 
 	timerlat_print_summary(params, trace, data);
 	timerlat_print_stats_all(params, trace, data);
+	osnoise_report_invalid_events(tool);
 	osnoise_report_missed_events(tool);
 }
 
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 6206a0a565ad3..2afd619c16059 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -456,6 +456,7 @@ timerlat_print_stats(struct osnoise_tool *top)
 
 	trace_seq_do_printf(trace->seq);
 	trace_seq_reset(trace->seq);
+	osnoise_report_invalid_events(top);
 	osnoise_report_missed_events(top);
 }
 
diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c
index e407447773d04..1c3e2b098ba81 100644
--- a/tools/tracing/rtla/src/trace.c
+++ b/tools/tracing/rtla/src/trace.c
@@ -138,6 +138,12 @@ collect_registered_events(struct tep_event *event, struct tep_record *record,
 	struct trace_instance *trace = context;
 	struct trace_seq *s = trace->seq;
 
+	if (cpu >= nr_cpus) {
+		/* Kernel reports event on CPU we don't see, corrupt data? */
+		trace->invalid_events++;
+		return 0;
+	}
+
 	trace->processed_events++;
 
 	if (!event->handler)
@@ -236,6 +242,7 @@ int trace_instance_init(struct trace_instance *trace, char *tool_name)
 				     trace);
 
 	trace->processed_events = 0;
+	trace->invalid_events = 0;
 
 	return 0;
 
diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h
index 95b911a2228b2..715a3616fe45a 100644
--- a/tools/tracing/rtla/src/trace.h
+++ b/tools/tracing/rtla/src/trace.h
@@ -18,6 +18,7 @@ struct trace_instance {
 	struct tep_handle		*tep;
 	struct trace_seq		*seq;
 	unsigned long long		missed_events;
+	unsigned long long		invalid_events;
 	unsigned long long		processed_events;
 };
 
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index c26ba8827947a..2579e7fa08be6 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -40,6 +40,8 @@ static inline bool str_has_prefix(const char *str, const char *prefix)
 }
 
 extern bool config_debug;
+extern int nr_cpus;
+
 void debug_msg(const char *fmt, ...);
 void err_msg(const char *fmt, ...);
 void fatal(const char *fmt, ...);
-- 
2.55.0