11 files changed, 308 insertions, 5 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index dc8aee97a48..eddd5ebcd69 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -117,6 +117,9 @@ void __perf_evlist__set_leader(struct list_head *list)
 	struct perf_evsel *evsel, *leader;
 
 	leader = list_entry(list->next, struct perf_evsel, node);
+	evsel = list_entry(list->prev, struct perf_evsel, node);
+
+	leader->nr_members = evsel->idx - leader->idx + 1;
 
 	list_for_each_entry(evsel, list, node) {
 		if (evsel != leader)
@@ -126,8 +129,10 @@ void __perf_evlist__set_leader(struct list_head *list)
 
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
-	if (evlist->nr_entries)
+	if (evlist->nr_entries) {
+		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
 		__perf_evlist__set_leader(&evlist->entries);
+	}
 }
 
 int perf_evlist__add_default(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 457e2350d21..73579a25a93 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -21,6 +21,7 @@ struct perf_evlist {
 	struct list_head entries;
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
+	int		 nr_groups;
 	int		 nr_fds;
 	int		 nr_mmaps;
 	int		 mmap_len;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index baa26ddbcc7..a5470150460 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -434,6 +434,31 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 	return evsel->name ?: "unknown";
 }
 
+const char *perf_evsel__group_name(struct perf_evsel *evsel)
+{
+	return evsel->group_name ?: "anon group";
+}
+
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
+{
+	int ret;
+	struct perf_evsel *pos;
+	const char *group_name = perf_evsel__group_name(evsel);
+
+	ret = scnprintf(buf, size, "%s", group_name);
+
+	ret += scnprintf(buf + ret, size - ret, " { %s",
+			 perf_evsel__name(evsel));
+
+	for_each_group_member(pos, evsel)
+		ret += scnprintf(buf + ret, size - ret, ", %s",
+				 perf_evsel__name(pos));
+
+	ret += scnprintf(buf + ret, size - ret, " }");
+
+	return ret;
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1364,7 +1389,27 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 			struct perf_attr_details *details, FILE *fp)
 {
 	bool first = true;
-	int printed = fprintf(fp, "%s", perf_evsel__name(evsel));
+	int printed = 0;
+
+	if (symbol_conf.event_group) {
+		struct perf_evsel *pos;
+
+		if (!perf_evsel__is_group_leader(evsel))
+			return 0;
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
+
+		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+		for_each_group_member(pos, evsel)
+			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "}");
+		goto out;
+	}
+
+	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
 
 	if (details->verbose || details->freq) {
 		printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
@@ -1405,7 +1450,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 		if_print(bp_type);
 		if_print(branch_sample_type);
 	}
-
+out:
 	fputc('\n', fp);
 	return ++printed;
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cbf42322a27..8512f6a8a6e 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -74,10 +74,13 @@ struct perf_evsel {
 	bool 			needs_swap;
 	/* parse modifier helper */
 	int			exclude_GH;
+	int			nr_members;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
 
+#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
+
 struct cpu_map;
 struct thread_map;
 struct perf_evlist;
@@ -111,6 +114,8 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 					    char *bf, size_t size);
 const char *perf_evsel__name(struct perf_evsel *evsel);
+const char *perf_evsel__group_name(struct perf_evsel *evsel);
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
@@ -259,4 +264,15 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 int perf_evsel__open_strerror(struct perf_evsel *evsel,
 			      struct perf_target *target,
 			      int err, char *msg, size_t size);
+
+static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
+{
+	return evsel->idx - evsel->leader->idx;
+}
+
+#define for_each_group_member(_evsel, _leader) 					\
+for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
+     (_evsel) && (_evsel)->leader == (_leader);					\
+     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f6081cb3fca..8022b5254f7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1085,6 +1085,52 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
 }
 
 /*
+ * File format:
+ *
+ * struct group_descs {
+ *	u32	nr_groups;
+ *	struct group_desc {
+ *		char	name[];
+ *		u32	leader_idx;
+ *		u32	nr_members;
+ *	}[nr_groups];
+ * };
+ */
+static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+			    struct perf_evlist *evlist)
+{
+	u32 nr_groups = evlist->nr_groups;
+	struct perf_evsel *evsel;
+	int ret;
+
+	ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			const char *name = evsel->group_name ?: "{anon_group}";
+			u32 leader_idx = evsel->idx;
+			u32 nr_members = evsel->nr_members;
+
+			ret = do_write_string(fd, name);
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &nr_members, sizeof(nr_members));
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(ARCH)/util/header.c
  */
@@ -1447,6 +1493,31 @@ error:
 	fprintf(fp, "# pmu mappings: unable to read\n");
 }
 
+static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
+			     FILE *fp)
+{
+	struct perf_session *session;
+	struct perf_evsel *evsel;
+	u32 nr = 0;
+
+	session = container_of(ph, struct perf_session, header);
+
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
+				perf_evsel__name(evsel));
+
+			nr = evsel->nr_members - 1;
+		} else if (nr) {
+			fprintf(fp, ",%s", perf_evsel__name(evsel));
+
+			if (--nr == 0)
+				fprintf(fp, "}\n");
+		}
+	}
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -1961,6 +2032,98 @@ error:
 	return -1;
 }
 
+static int process_group_desc(struct perf_file_section *section __maybe_unused,
+			      struct perf_header *ph, int fd,
+			      void *data __maybe_unused)
+{
+	size_t ret = -1;
+	u32 i, nr, nr_groups;
+	struct perf_session *session;
+	struct perf_evsel *evsel, *leader = NULL;
+	struct group_desc {
+		char *name;
+		u32 leader_idx;
+		u32 nr_members;
+	} *desc;
+
+	if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
+		return -1;
+
+	if (ph->needs_swap)
+		nr_groups = bswap_32(nr_groups);
+
+	ph->env.nr_groups = nr_groups;
+	if (!nr_groups) {
+		pr_debug("group desc not available\n");
+		return 0;
+	}
+
+	desc = calloc(nr_groups, sizeof(*desc));
+	if (!desc)
+		return -1;
+
+	for (i = 0; i < nr_groups; i++) {
+		desc[i].name = do_read_string(fd, ph);
+		if (!desc[i].name)
+			goto out_free;
+
+		if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (ph->needs_swap) {
+			desc[i].leader_idx = bswap_32(desc[i].leader_idx);
+			desc[i].nr_members = bswap_32(desc[i].nr_members);
+		}
+	}
+
+	/*
+	 * Rebuild group relationship based on the group_desc
+	 */
+	session = container_of(ph, struct perf_session, header);
+	session->evlist->nr_groups = nr_groups;
+
+	i = nr = 0;
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (evsel->idx == (int) desc[i].leader_idx) {
+			evsel->leader = evsel;
+			/* {anon_group} is a dummy name */
+			if (strcmp(desc[i].name, "{anon_group}"))
+				evsel->group_name = desc[i].name;
+			evsel->nr_members = desc[i].nr_members;
+
+			if (i >= nr_groups || nr > 0) {
+				pr_debug("invalid group desc\n");
+				goto out_free;
+			}
+
+			leader = evsel;
+			nr = evsel->nr_members - 1;
+			i++;
+		} else if (nr) {
+			/* This is a group member */
+			evsel->leader = leader;
+
+			nr--;
+		}
+	}
+
+	if (i != nr_groups || nr != 0) {
+		pr_debug("invalid group desc\n");
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	while ((int) --i >= 0)
+		free(desc[i].name);
+	free(desc);
+
+	return ret;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -2000,6 +2163,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
+	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 20f0344accb..c9fc55cada6 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -29,6 +29,7 @@ enum {
 	HEADER_NUMA_TOPOLOGY,
 	HEADER_BRANCH_STACK,
 	HEADER_PMU_MAPPINGS,
+	HEADER_GROUP_DESC,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -79,6 +80,7 @@ struct perf_session_env {
 	char			*numa_nodes;
 	int			nr_pmu_mappings;
 	char			*pmu_mappings;
+	int			nr_groups;
 };
 
 struct perf_header {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8170a3d11ff..f855941bebe 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evsel.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -540,6 +541,62 @@ void hists__collapse_resort_threaded(struct hists *hists)
  * reverse the map, sort on period.
  */
 
+static int period_cmp(u64 period_a, u64 period_b)
+{
+	if (period_a > period_b)
+		return 1;
+	if (period_a < period_b)
+		return -1;
+	return 0;
+}
+
+static int hist_entry__sort_on_period(struct hist_entry *a,
+				      struct hist_entry *b)
+{
+	int ret;
+	int i, nr_members;
+	struct perf_evsel *evsel;
+	struct hist_entry *pair;
+	u64 *periods_a, *periods_b;
+
+	ret = period_cmp(a->stat.period, b->stat.period);
+	if (ret || !symbol_conf.event_group)
+		return ret;
+
+	evsel = hists_to_evsel(a->hists);
+	nr_members = evsel->nr_members;
+	if (nr_members <= 1)
+		return ret;
+
+	periods_a = zalloc(sizeof(periods_a) * nr_members);
+	periods_b = zalloc(sizeof(periods_b) * nr_members);
+
+	if (!periods_a || !periods_b)
+		goto out;
+
+	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period;
+	}
+
+	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		ret = period_cmp(periods_a[i], periods_b[i]);
+		if (ret)
+			break;
+	}
+
+out:
+	free(periods_a);
+	free(periods_b);
+
+	return ret;
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits)
@@ -556,7 +613,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-		if (he->stat.period > iter->stat.period)
+		if (hist_entry__sort_on_period(he, iter) > 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 02f6421f03a..4e0f5c2a9fd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -884,6 +884,7 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	if (!ret) {
 		int entries = data.idx - evlist->nr_entries;
 		perf_evlist__splice_list_tail(evlist, &data.list, entries);
+		evlist->nr_groups += data.nr_groups;
 		return 0;
 	}
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 2cd2c42a69c..8a4859315fd 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -64,6 +64,7 @@ struct parse_events_term {
 struct parse_events_evlist {
 	struct list_head list;
 	int idx;
+	int nr_groups;
 };
 
 struct parse_events_terms {
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9d43c86176f..4de2fdca98c 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -23,6 +23,14 @@ do { \
 		YYABORT; \
 } while (0)
 
+static inc_group_count(struct list_head *list,
+		       struct parse_events_evlist *data)
+{
+	/* Count groups only have more than 1 members */
+	if (!list_is_last(list->next, list))
+		data->nr_groups++;
+}
+
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
@@ -123,6 +131,7 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $3;
 
+	inc_group_count(list, _data);
 	parse_events__set_leader($1, list);
 	$$ = list;
 }
@@ -131,6 +140,7 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $2;
 
+	inc_group_count(list, _data);
 	parse_events__set_leader(NULL, list);
 	$$ = list;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index d97377ac2f1..b62ca37c4b7 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -96,7 +96,8 @@ struct symbol_conf {
 			initialized,
 			kptr_restrict,
 			annotate_asm_raw,
-			annotate_src;
+			annotate_src,
+			event_group;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,