perf record: Add cgroup support for off-cpu profiling

This covers two different use cases.  The first one is cgroup
filtering given by -G/--cgroup option which controls the off-cpu
profiling for tasks in the given cgroups only.

The other use case is cgroup sampling which is enabled by
--all-cgroups option and it adds PERF_SAMPLE_CGROUP to the sample_type
to set the cgroup id of the task in the sample data.

Example output.

  $ sudo perf record -a --off-cpu --all-cgroups sleep 1

  $ sudo perf report --stdio -s comm,cgroup --call-graph=no
  ...
  # Samples: 144  of event 'offcpu-time'
  # Event count (approx.): 48452045427
  #
  # Children      Self  Command          Cgroup
  # ........  ........  ...............  ..........................................
  #
      61.57%     5.60%  Chrome_ChildIOT  /user.slice/user-657345.slice/user@657345.service/app.slice/...
      29.51%     7.38%  Web Content      /user.slice/user-657345.slice/user@657345.service/app.slice/...
      17.48%     1.59%  Chrome_IOThread  /user.slice/user-657345.slice/user@657345.service/app.slice/...
      16.48%     4.12%  pipewire-pulse   /user.slice/user-657345.slice/user@657345.service/session.slice/...
      14.48%     2.07%  perf             /user.slice/user-657345.slice/user@657345.service/app.slice/...
      14.30%     7.15%  CompositorTileW  /user.slice/user-657345.slice/user@657345.service/app.slice/...
      13.33%     6.67%  Timer            /user.slice/user-657345.slice/user@657345.service/app.slice/...
  ...

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20220518224725.742882-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 46 insertions, 2 deletions

diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 874856c55101..b73e84a02264 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -5,10 +5,12 @@
 #include "util/evlist.h"
 #include "util/off_cpu.h"
 #include "util/perf-hooks.h"
+#include "util/record.h"
 #include "util/session.h"
 #include "util/target.h"
 #include "util/cpumap.h"
 #include "util/thread_map.h"
+#include "util/cgroup.h"
 #include <bpf/bpf.h>
 
 #include "bpf_skel/off_cpu.skel.h"
@@ -24,6 +26,7 @@ struct off_cpu_key {
 	u32 tgid;
 	u32 stack_id;
 	u32 state;
+	u64 cgroup_id;
 };
 
 union off_cpu_data {
@@ -116,10 +119,11 @@ static void check_sched_switch_args(void)
 	}
 }
 
-int off_cpu_prepare(struct evlist *evlist, struct target *target)
+int off_cpu_prepare(struct evlist *evlist, struct target *target,
+		    struct record_opts *opts)
 {
 	int err, fd, i;
-	int ncpus = 1, ntasks = 1;
+	int ncpus = 1, ntasks = 1, ncgrps = 1;
 
 	if (off_cpu_config(evlist) < 0) {
 		pr_err("Failed to config off-cpu BPF event\n");
@@ -143,6 +147,21 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target)
 		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
 	}
 
+	if (evlist__first(evlist)->cgrp) {
+		ncgrps = evlist->core.nr_entries - 1; /* excluding a dummy */
+		bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);
+
+		if (!cgroup_is_v2("perf_event"))
+			skel->rodata->uses_cgroup_v1 = true;
+	}
+
+	if (opts->record_cgroup) {
+		skel->rodata->needs_cgroup = true;
+
+		if (!cgroup_is_v2("perf_event"))
+			skel->rodata->uses_cgroup_v1 = true;
+	}
+
 	set_max_rlimit();
 	check_sched_switch_args();
 
@@ -178,6 +197,29 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target)
 		}
 	}
 
+	if (evlist__first(evlist)->cgrp) {
+		struct evsel *evsel;
+		u8 val = 1;
+
+		skel->bss->has_cgroup = 1;
+		fd = bpf_map__fd(skel->maps.cgroup_filter);
+
+		evlist__for_each_entry(evlist, evsel) {
+			struct cgroup *cgrp = evsel->cgrp;
+
+			if (cgrp == NULL)
+				continue;
+
+			if (!cgrp->id && read_cgroup_id(cgrp) < 0) {
+				pr_err("Failed to read cgroup id of %s\n",
+				       cgrp->name);
+				goto out;
+			}
+
+			bpf_map_update_elem(fd, &cgrp->id, &val, BPF_ANY);
+		}
+	}
+
 	err = off_cpu_bpf__attach(skel);
 	if (err) {
 		pr_err("Failed to attach off-cpu BPF skeleton\n");
@@ -275,6 +317,8 @@ int off_cpu_write(struct perf_session *session)
 			/* calculate sample callchain data array length */
 			n += len + 2;
 		}
+		if (sample_type & PERF_SAMPLE_CGROUP)
+			data.array[n++] = key.cgroup_id;
 		/* TODO: handle more sample types */
 
 		size = n * sizeof(u64);