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, 33 insertions, 0 deletions

diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 986d7db6e75d..792ae2847080 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -26,6 +26,7 @@ struct offcpu_key {
 	__u32 tgid;
 	__u32 stack_id;
 	__u32 state;
+	__u64 cgroup_id;
 };
 
 struct {
@@ -63,6 +64,13 @@ struct {
 	__uint(max_entries, 1);
 } task_filter SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cgroup_filter SEC(".maps");
+
 /* old kernel task_struct definition */
 struct task_struct___old {
 	long state;
@@ -71,8 +79,11 @@ struct task_struct___old {
 int enabled = 0;
 int has_cpu = 0;
 int has_task = 0;
+int has_cgroup = 0;
 
 const volatile bool has_prev_state = false;
+const volatile bool needs_cgroup = false;
+const volatile bool uses_cgroup_v1 = false;
 
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
@@ -92,6 +103,18 @@ static inline int get_task_state(struct task_struct *t)
 	return BPF_CORE_READ(t_old, state);
 }
 
+static inline __u64 get_cgroup_id(struct task_struct *t)
+{
+	struct cgroup *cgrp;
+
+	if (uses_cgroup_v1)
+		cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup);
+	else
+		cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp);
+
+	return BPF_CORE_READ(cgrp, kn, id);
+}
+
 static inline int can_record(struct task_struct *t, int state)
 {
 	/* kernel threads don't have user stack */
@@ -120,6 +143,15 @@ static inline int can_record(struct task_struct *t, int state)
 			return 0;
 	}
 
+	if (has_cgroup) {
+		__u8 *ok;
+		__u64 cgrp_id = get_cgroup_id(t);
+
+		ok = bpf_map_lookup_elem(&cgroup_filter, &cgrp_id);
+		if (!ok)
+			return 0;
+	}
+
 	return 1;
 }
 
@@ -156,6 +188,7 @@ next:
 			.tgid = next->tgid,
 			.stack_id = pelem->stack_id,
 			.state = pelem->state,
+			.cgroup_id = needs_cgroup ? get_cgroup_id(next) : 0,
 		};
 		__u64 delta = ts - pelem->timestamp;
 		__u64 *total;