perf top: Add cgroup support for perf top (-G)

Added callback option (-G) to support cgroups for 'perf top'.

Added condition to make sure -cgroup and --all-cgroups aren't both enabled.

Example:

  $perf top -e cycles -G system.slice/docker-6b95a5eb649c0d671eba3835f0d93973d05a088f3ae8602246bde37affb1ba3e.scope -a --stdio

   PerfTop:    3330 irqs/sec  kernel:68.2%  exact:  0.0% lost: 0/0 drop: 0/11075 [4000Hz cpu-clock],  (all, 4 CPUs)
   -------------------------------------------------------------------------------------------------------------------------------------------------------

    27.32%  [unknown]         [.] 0x00007f8ab7b69352
    11.44%  [kernel]          [k] 0xffffffff968cd657
     3.12%  [kernel]          [k] 0xffffffff96160e96
     2.63%  [kernel]          [k] 0xffffffff96160eb0
     1.96%  [kernel]          [k] 0xffffffff9615fcf6
     1.42%  [kernel]          [k] 0xffffffff964ddfc7
     1.09%  [kernel]          [k] 0xffffffff96160e90
     0.81%  [kernel]          [k] 0xffffffff96160eb3
     0.67%  [kernel]          [k] 0xffffffff9615fec1
     0.57%  [kernel]          [k] 0xffffffff961ee1d0
     0.53%  [unknown]         [.] 0x00007f8ab7b6666c
     0.53%  [kernel]          [k] 0xffffffff96160e64
     0.52%  [kernel]          [k] 0xffffffff9616c303
     0.51%  [kernel]          [k] 0xffffffffc08e7d50
     ...
Signed-off-by: Joshua Martinez <joshuamart@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: joshua martinez <joshuamart@google.com>
Link: http://lore.kernel.org/lkml/20210616231829.3735671-1-joshuamart@google.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-top.txt

@@ -277,6 +277,18 @@ Default is to monitor all CPUS.
 	Record events of type PERF_RECORD_NAMESPACES and display it with the
 	'cgroup_id' sort key.
 
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line. If the user wants to track multiple events for a specific cgroup, the user can
+use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
+
 --all-cgroups::
 	Record events of type PERF_RECORD_CGROUP and display it with the
 	'cgroup' sort key.

tools/perf/builtin-top.c

@@ -22,6 +22,7 @@
 
 #include "util/annotate.h"
 #include "util/bpf-event.h"
+#include "util/cgroup.h"
 #include "util/config.h"
 #include "util/color.h"
 #include "util/dso.h"
@@ -1558,6 +1559,8 @@ int cmd_top(int argc, const char **argv)
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
+	OPT_CALLBACK('G', "cgroup", &top.evlist, "name",
+		     "monitor event in cgroup name only", parse_cgroups),
 	OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
 		    "Record namespaces events"),
 	OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup,
@@ -1646,6 +1649,11 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
+	if (nr_cgroups > 0 && opts->record_cgroup) {
+		pr_err("--cgroup and --all-cgroups cannot be used together\n");
+		goto out_delete_evlist;
+	}
+
 	if (opts->branch_stack && callchain_param.enabled)
 		symbol_conf.show_branchflag_count = true;