libperf cpumap: Reduce allocations and sorting in intersect

On hybrid platforms the CPU maps are often disjoint. Rather than copy
CPUs and trim, compute the number of common CPUs, if none early exit,
otherwise copy in an sorted order. This avoids memory allocation in
the disjoint case and avoids a second malloc and useless sort in the
previous trim cases.

Signed-off-by: Ian Rogers <[e-mail]>
Signed-off-by: Namhyung Kim <[e-mail]>

tools/lib/perf/cpumap.c

···
 struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
 					     struct perf_cpu_map *other)
 {
-	struct perf_cpu *tmp_cpus;
-	int tmp_len;
 	int i, j, k;
-	struct perf_cpu_map *merged = NULL;
+	struct perf_cpu_map *merged;
 
 	if (perf_cpu_map__is_subset(other, orig))
 		return perf_cpu_map__get(orig);
 	if (perf_cpu_map__is_subset(orig, other))
 		return perf_cpu_map__get(other);
 
-	tmp_len = max(__perf_cpu_map__nr(orig), __perf_cpu_map__nr(other));
-	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
-	if (!tmp_cpus)
+	i = j = k = 0;
+	while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
+		if (__perf_cpu_map__cpu(orig, i).cpu < __perf_cpu_map__cpu(other, j).cpu)
+			i++;
+		else if (__perf_cpu_map__cpu(orig, i).cpu > __perf_cpu_map__cpu(other, j).cpu)
+			j++;
+		else { /* CPUs match. */
+			i++;
+			j++;
+			k++;
+		}
+	}
+	if (k == 0) /* Maps are completely disjoint. */
 		return NULL;
 
+	merged = perf_cpu_map__alloc(k);
+	if (!merged)
+		return NULL;
+	/* Entries are added to merged in sorted order, so no need to sort again. */
 	i = j = k = 0;
 	while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) {
 		if (__perf_cpu_map__cpu(orig, i).cpu < __perf_cpu_map__cpu(other, j).cpu)
···
 			j++;
 		else {
 			j++;
-			tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++);
+			RC_CHK_ACCESS(merged)->map[k++] = __perf_cpu_map__cpu(orig, i++);
 		}
 	}
-	if (k)
-		merged = cpu_map__trim_new(k, tmp_cpus);
-	free(tmp_cpus);
 	return merged;
 }