perf tools: Enable grouping logic for parsed events

This patch adds a functionality that allows to create event groups
based on the way they are specified on the command line. Adding
functionality to the '{}' group syntax introduced in earlier patch.

The current '--group/-g' option behaviour remains intact. If you
specify it for record/stat/top command, all the specified events
become members of a single group with the first event as a group
leader.

With the new '{}' group syntax you can create group like:
  # perf record -e '{cycles,faults}' ls

resulting in single event group containing 'cycles' and 'faults'
events, with cycles event as group leader.

All groups are created with regards to threads and cpus. Thus
recording an event group within a 2 threads on server with
4 CPUs will create 8 separate groups.

Examples (first event in brackets is group leader):

  # 1 group (cpu-clock,task-clock)
  perf record --group -e cpu-clock,task-clock ls
  perf record -e '{cpu-clock,task-clock}' ls

  # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults)
  perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls

  # 1 group (cpu-clock,task-clock,minor-faults,major-faults)
  perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls
  perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls

  # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults)
  perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \
   -e instructions ls

  # 1 group
  # (cpu-clock,task-clock,minor-faults,major-faults,instructions)
  perf record --group -e cpu-clock,task-clock \
   -e minor-faults,major-faults -e instructions ls perf record -e
'{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls

It's possible to use standard event modifier for a group, which spans
over all events in the group and updates each event modifier settings,
for example:

  # perf record -r '{faults:k,cache-references}:p'

resulting in ':kp' modifier being used for 'faults' and ':p' modifier
being used for 'cache-references' event.

Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 34 insertions, 17 deletions

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9c54e8f..f5b68e7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -21,7 +21,6 @@
 #include "perf_regs.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
 
 static int __perf_evsel__sample_size(u64 sample_type)
 {
@@ -493,6 +492,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 {
 	perf_evsel__exit(evsel);
 	close_cgroup(evsel->cgrp);
+	free(evsel->group_name);
 	free(evsel->name);
 	free(evsel);
 }
@@ -568,9 +568,28 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	return 0;
 }
 
+static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
+{
+	struct perf_evsel *leader = evsel->leader;
+	int fd;
+
+	if (!leader)
+		return -1;
+
+	/*
+	 * Leader must be already processed/open,
+	 * if not it's a bug.
+	 */
+	BUG_ON(!leader->fd);
+
+	fd = FD(leader, cpu, thread);
+	BUG_ON(fd == -1);
+
+	return fd;
+}
+
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads, bool group,
-			      struct xyarray *group_fds)
+			      struct thread_map *threads)
 {
 	int cpu, thread;
 	unsigned long flags = 0;
@@ -586,13 +605,15 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	}
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		int group_fd = group_fds ? GROUP_FD(group_fds, cpu) : -1;
 
 		for (thread = 0; thread < threads->nr; thread++) {
+			int group_fd;
 
 			if (!evsel->cgrp)
 				pid = threads->map[thread];
 
+			group_fd = get_group_fd(evsel, cpu, thread);
+
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
 								     pid,
 								     cpus->map[cpu],
@@ -602,8 +623,9 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 				goto out_close;
 			}
 
-			if (group && group_fd == -1)
-				group_fd = FD(evsel, cpu, thread);
+			pr_debug("event cpu %d, thread %d, fd %d, group %d\n",
+				 cpu, pid, FD(evsel, cpu, thread),
+				 group_fd);
 		}
 	}
 
@@ -647,8 +669,7 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads, bool group,
-		     struct xyarray *group_fd)
+		     struct thread_map *threads)
 {
 	if (cpus == NULL) {
 		/* Work around old compiler warnings about strict aliasing */
@@ -658,23 +679,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (threads == NULL)
 		threads = &empty_thread_map.map;
 
-	return __perf_evsel__open(evsel, cpus, threads, group, group_fd);
+	return __perf_evsel__open(evsel, cpus, threads);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus, bool group,
-			     struct xyarray *group_fd)
+			     struct cpu_map *cpus)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group,
-				  group_fd);
+	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads, bool group,
-				struct xyarray *group_fd)
+				struct thread_map *threads)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group,
-				  group_fd);
+	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,