perf record: Add --all-cgroups option

The --all-cgroups option is to enable cgroup profiling support.  It
tells kernel to record CGROUP events in the ring buffer so that perf
report can identify task/cgroup association later.

  [root@seventh ~]# perf record --all-cgroups --namespaces /wb/cgtest
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.042 MB perf.data (558 samples) ]
  [root@seventh ~]# perf report --stdio -s cgroup_id,cgroup,pid
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 558  of event 'cycles'
  # Event count (approx.): 458017341
  #
  # Overhead  cgroup id (dev/inode)  Cgroup          Pid:Command
  # ........  .....................  ..........  ...............
  #
      33.15%  4/0xeffffffb           /sub           9615:looper0
      32.83%  4/0xf00002f5           /sub/cgrp2     9620:looper2
      32.79%  4/0xf00002f4           /sub/cgrp1     9619:looper1
       0.35%  4/0xf00002f5           /sub/cgrp2     9618:cgtest
       0.34%  4/0xf00002f4           /sub/cgrp1     9617:cgtest
       0.32%  4/0xeffffffb           /              9615:looper0
       0.11%  4/0xeffffffb           /sub           9617:cgtest
       0.10%  4/0xeffffffb           /sub           9618:cgtest

  #
  # (Tip: Sample related events with: perf record -e '{cycles,instructions}:S')
  #
  [root@seventh ~]#

Signed-off-by: Namhyung Kim <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Link: http://lore.kernel.org/lkml/[email protected]
[ Extracted the HAVE_FILE_HANDLE from the followup patch ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: namhyung

tools/perf/Documentation/perf-record.txt

@@ -391,7 +391,10 @@ displayed with the weight and local_weight sort keys.  This currently works for
 abort events and some memory events in precise mode on modern Intel CPUs.
 
 --namespaces::
-Record events of type PERF_RECORD_NAMESPACES.
+Record events of type PERF_RECORD_NAMESPACES.  This enables 'cgroup_id' sort key.
+
+--all-cgroups::
+Record events of type PERF_RECORD_CGROUP.  This enables 'cgroup' sort key.
 
 --transaction::
 Record transaction flags for transaction related events.

tools/perf/builtin-record.c

@@ -1433,6 +1433,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (rec->opts.record_namespaces)
 		tool->namespace_events = true;
 
+	if (rec->opts.record_cgroup) {
+#ifdef HAVE_FILE_HANDLE
+		tool->cgroup_events = true;
+#else
+		pr_err("cgroup tracking is not supported\n");
+		return -1;
+#endif
+	}
+
 	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
@@ -2363,6 +2372,8 @@ static struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
 		    "Record namespaces events"),
+	OPT_BOOLEAN(0, "all-cgroups", &record.opts.record_cgroup,
+		    "Record cgroup events"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
 	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,

tools/perf/util/evsel.c

@@ -1104,6 +1104,11 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
 
+	if (opts->record_cgroup) {
+		attr->cgroup = track && !perf_missing_features.cgroup;
+		perf_evsel__set_sample_bit(evsel, CGROUP);
+	}
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
@@ -1789,7 +1794,11 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.branch_hw_idx &&
+        if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
+		perf_missing_features.cgroup = true;
+		pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n");
+		goto out_close;
+        } else if (!perf_missing_features.branch_hw_idx &&
 	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
 		perf_missing_features.branch_hw_idx = true;
 		pr_debug2("switching off branch HW index support\n");

tools/perf/util/evsel.h

@@ -120,6 +120,7 @@ struct perf_missing_features {
 	bool bpf;
 	bool aux_output;
 	bool branch_hw_idx;
+	bool cgroup;
 };
 
 extern struct perf_missing_features perf_missing_features;

tools/perf/util/record.h

@@ -34,6 +34,7 @@ struct record_opts {
 	bool	      auxtrace_snapshot_on_exit;
 	bool	      auxtrace_sample_mode;
 	bool	      record_namespaces;
+	bool	      record_cgroup;
 	bool	      record_switch_events;
 	bool	      all_kernel;
 	bool	      all_user;