rtla: Discard trace entries with cpu >= nr_cpus

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.

Link: https://lore.kernel.org/r/20260814135511.2207190-3-tglozar@redhat.com
Signed-off-by: Tomas Glozar <tglozar@redhat.com>
This commit is contained in:
Tomas Glozar 2026-08-14 15:55:08 +02:00
parent b3dc9905d7
commit bdb4d4d5db
10 changed files with 41 additions and 3 deletions

View File

@ -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))

View File

@ -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,

View File

@ -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);

View File

@ -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);
}

View File

@ -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);
}

View File

@ -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);
}

View File

@ -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);
}

View File

@ -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;

View File

@ -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;
};

View File

@ -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, ...);