rtla/osnoise: Better report when histogram is empty

When osnoise hist does not observe any samples above the threshold,
no entries are recorded and the final report shows empty entries
for the usual statistics (count, min, max, avg):

[~]# osnoise hist -d 5s -T 500
# RTLA osnoise histogram
# Time unit is microseconds (us)
# Duration: 0 00:00:05
Index
over:
count:
min:
avg:
max:

That could lead users to confusing interpretations of the results.

A simple solution is to report 0 for count and the statistics, making it
clear that no noise (above the defined threshold) was observed:

[~]# osnoise hist -d 5s -T 500
# RTLA osnoise histogram
# Time unit is microseconds (us)
# Duration: 0 00:00:05
Index
over: 0
count: 0
min: 0
avg: 0
max: 0

Link: https://lkml.kernel.org/r/[e-mail]

Cc: Daniel Bristot de Oliveira <[e-mail]>
Cc: John Kacur <[e-mail]>
Cc: Clark Williams <[e-mail]>
Reviewed-by: John Kacur <[e-mail]>
Signed-off-by: Luis Claudio R. Goncalves <[e-mail]>
Signed-off-by: Daniel Bristot de Oliveira <[e-mail]>

tools/tracing/rtla/src/osnoise_hist.c

···
 {
 	struct osnoise_hist_data *data = tool->data;
 	struct trace_instance *trace = &tool->trace;
+	int has_samples = 0;
 	int bucket, cpu;
 	int total;
 
···
 			continue;
 		}
 
+		/* There are samples above the threshold */
+		has_samples = 1;
 		trace_seq_printf(trace->seq, "\n");
 		trace_seq_do_printf(trace->seq);
 		trace_seq_reset(trace->seq);
+	}
+
+	/*
+	 * If no samples were recorded, skip calculations, print zeroed statistics
+	 * and return.
+	 */
+	if (!has_samples) {
+		trace_seq_reset(trace->seq);
+		trace_seq_printf(trace->seq, "over: 0\ncount: 0\nmin: 0\navg: 0\nmax: 0\n");
+		trace_seq_do_printf(trace->seq);
+		trace_seq_reset(trace->seq);
+		return;
 	}
 
 	if (!params->no_index)