3 files changed, 39 insertions, 15 deletions

diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index b20a5280f2b3..4160e7d2e120 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -368,10 +368,12 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 		.cpu = -1
 	};
 
-	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
-	return __perf_cpu_map__nr(map) > 0
-		? __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1)
-		: result;
+	if (!map)
+		return result;
+
+	// The CPUs are always sorted and nr is always > 0 as 0 length map is
+	// encoded as NULL.
+	return __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1);
 }
 
 /** Is 'b' a subset of 'a'. */
@@ -453,21 +455,33 @@ int perf_cpu_map__merge(struct perf_cpu_map **orig, struct perf_cpu_map *other)
 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)
@@ -476,11 +490,8 @@ struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig,
 			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;
 }
diff --git a/tools/lib/perf/include/perf/core.h b/tools/lib/perf/include/perf/core.h
index a3f6d68edad7..06cc132d88cf 100644
--- a/tools/lib/perf/include/perf/core.h
+++ b/tools/lib/perf/include/perf/core.h
@@ -5,7 +5,7 @@
 #include <stdarg.h>
 
 #ifndef LIBPERF_API
-#define LIBPERF_API __attribute__((visibility("default")))
+#define LIBPERF_API extern __attribute__((visibility("default")))
 #endif
 
 enum libperf_print_level {
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index aa1e91c97a22..43a8cb04994f 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -151,6 +151,18 @@ struct perf_record_switch {
 	__u32			 next_prev_tid;
 };
 
+struct perf_record_callchain_deferred {
+	struct perf_event_header header;
+	/*
+	 * This is to match kernel and (deferred) user stacks together.
+	 * The kernel part will be in the sample callchain array after
+	 * the PERF_CONTEXT_USER_DEFERRED entry.
+	 */
+	__u64			 cookie;
+	__u64			 nr;
+	__u64			 ips[];
+};
+
 struct perf_record_header_attr {
 	struct perf_event_header header;
 	struct perf_event_attr	 attr;
@@ -523,6 +535,7 @@ union perf_event {
 	struct perf_record_read			read;
 	struct perf_record_throttle		throttle;
 	struct perf_record_sample		sample;
+	struct perf_record_callchain_deferred	callchain_deferred;
 	struct perf_record_bpf_event		bpf;
 	struct perf_record_ksymbol		ksymbol;
 	struct perf_record_text_poke_event	text_poke;