perf kwork top: Implements BPF-based cpu usage statistics

Use BPF to collect statistics on the CPU usage based on perf BPF skeletons.

Example usage:

  # perf kwork top -h

   Usage: perf kwork top [<options>]

      -b, --use-bpf         Use BPF to measure task cpu usage
      -C, --cpu <cpu>       list of cpus to profile
      -i, --input <file>    input file name
      -n, --name <name>     event name to profile
      -s, --sort <key[,key2...]>
                            sort by key(s): rate, runtime, tid
          --time <str>      Time span for analysis (start,stop)

  #
  # perf kwork -k sched top -b
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
  Total  : 160702.425 ms, 8 cpus
  %Cpu(s):  36.00% id,   0.00% hi,   0.00% si
  %Cpu0   [||||||||||||||||||              61.66%]
  %Cpu1   [||||||||||||||||||              61.27%]
  %Cpu2   [|||||||||||||||||||             66.40%]
  %Cpu3   [||||||||||||||||||              61.28%]
  %Cpu4   [||||||||||||||||||              61.82%]
  %Cpu5   [|||||||||||||||||||||||         77.41%]
  %Cpu6   [||||||||||||||||||              61.73%]
  %Cpu7   [||||||||||||||||||              63.25%]

        PID     SPID    %CPU           RUNTIME  COMMMAND
    -------------------------------------------------------------
          0        0   38.72       8089.463 ms  [swapper/1]
          0        0   38.71       8084.547 ms  [swapper/3]
          0        0   38.33       8007.532 ms  [swapper/0]
          0        0   38.26       7992.985 ms  [swapper/6]
          0        0   38.17       7971.865 ms  [swapper/4]
          0        0   36.74       7447.765 ms  [swapper/7]
          0        0   33.59       6486.942 ms  [swapper/2]
          0        0   22.58       3771.268 ms  [swapper/5]
       9545     9351    2.48        447.136 ms  sched-messaging
       9574     9351    2.09        418.583 ms  sched-messaging
       9724     9351    2.05        372.407 ms  sched-messaging
       9531     9351    2.01        368.804 ms  sched-messaging
       9512     9351    2.00        362.250 ms  sched-messaging
       9514     9351    1.95        357.767 ms  sched-messaging
       9538     9351    1.86        384.476 ms  sched-messaging
       9712     9351    1.84        386.490 ms  sched-messaging
       9723     9351    1.83        380.021 ms  sched-messaging
       9722     9351    1.82        382.738 ms  sched-messaging
       9517     9351    1.81        354.794 ms  sched-messaging
       9559     9351    1.79        344.305 ms  sched-messaging
       9725     9351    1.77        365.315 ms  sched-messaging
  <SNIP>

  # perf kwork -k sched top -b -n perf
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
  Total  : 151563.332 ms, 8 cpus
  %Cpu(s):  26.49% id,   0.00% hi,   0.00% si
  %Cpu0   [                                 0.01%]
  %Cpu1   [                                 0.00%]
  %Cpu2   [                                 0.00%]
  %Cpu3   [                                 0.00%]
  %Cpu4   [                                 0.00%]
  %Cpu5   [                                 0.00%]
  %Cpu6   [                                 0.00%]
  %Cpu7   [                                 0.00%]

        PID     SPID    %CPU           RUNTIME  COMMMAND
    -------------------------------------------------------------
       9754     9754    0.01          2.303 ms  perf

  #
  # perf kwork -k sched top -b -C 2,3,4
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
  Total  :  48016.721 ms, 3 cpus
  %Cpu(s):  27.82% id,   0.00% hi,   0.00% si
  %Cpu2   [||||||||||||||||||||||          74.68%]
  %Cpu3   [|||||||||||||||||||||           71.06%]
  %Cpu4   [|||||||||||||||||||||           70.91%]

        PID     SPID    %CPU           RUNTIME  COMMMAND
    -------------------------------------------------------------
          0        0   29.08       4734.998 ms  [swapper/4]
          0        0   28.93       4710.029 ms  [swapper/3]
          0        0   25.31       3912.363 ms  [swapper/2]
      10248    10158    1.62        264.931 ms  sched-messaging
      10253    10158    1.62        265.136 ms  sched-messaging
      10158    10158    1.60        263.013 ms  bash
      10360    10158    1.49        243.639 ms  sched-messaging
      10413    10158    1.48        238.604 ms  sched-messaging
      10531    10158    1.47        234.067 ms  sched-messaging
      10400    10158    1.47        240.631 ms  sched-messaging
      10355    10158    1.47        230.586 ms  sched-messaging
      10377    10158    1.43        234.835 ms  sched-messaging
      10526    10158    1.42        232.045 ms  sched-messaging
      10298    10158    1.41        222.396 ms  sched-messaging
      10410    10158    1.38        221.853 ms  sched-messaging
      10364    10158    1.38        226.042 ms  sched-messaging
      10480    10158    1.36        213.633 ms  sched-messaging
      10370    10158    1.36        223.620 ms  sched-messaging
      10553    10158    1.34        217.169 ms  sched-messaging
      10291    10158    1.34        211.516 ms  sched-messaging
      10251    10158    1.34        218.813 ms  sched-messaging
      10522    10158    1.33        218.498 ms  sched-messaging
      10288    10158    1.33        216.787 ms  sched-messaging
  <SNIP>

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Link: https://lore.kernel.org/r/20230812084917.169338-15-yangjihong1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 59 insertions, 3 deletions

diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c
index d5949ff4bd15..04b966801643 100644
--- a/tools/perf/builtin-kwork.c
+++ b/tools/perf/builtin-kwork.c
@@ -1619,8 +1619,14 @@ static void top_print_header(struct perf_kwork *kwork __maybe_unused)
 	int ret;
 
 	printf("\n ");
-	ret = printf(" %*s  %*s  %*s  %-*s",
+	ret = printf(" %*s %s%*s%s %*s  %*s  %-*s",
 		     PRINT_PID_WIDTH, "PID",
+
+		     kwork->use_bpf ? " " : "",
+		     kwork->use_bpf ? PRINT_PID_WIDTH : 0,
+		     kwork->use_bpf ? "SPID" : "",
+		     kwork->use_bpf ? " " : "",
+
 		     PRINT_CPU_USAGE_WIDTH, "%CPU",
 		     PRINT_RUNTIME_HEADER_WIDTH + RPINT_DECIMAL_WIDTH, "RUNTIME",
 		     PRINT_TASK_NAME_WIDTH, "COMMMAND");
@@ -1640,6 +1646,12 @@ static int top_print_work(struct perf_kwork *kwork __maybe_unused, struct kwork_
 	ret += printf(" %*ld ", PRINT_PID_WIDTH, work->id);
 
 	/*
+	 * tgid
+	 */
+	if (kwork->use_bpf)
+		ret += printf(" %*d ", PRINT_PID_WIDTH, work->tgid);
+
+	/*
 	 * cpu usage
 	 */
 	ret += printf(" %*.*f ",
@@ -1656,7 +1668,13 @@ static int top_print_work(struct perf_kwork *kwork __maybe_unused, struct kwork_
 	/*
 	 * command
 	 */
-	ret += printf(" %-*s", PRINT_TASK_NAME_WIDTH, work->name);
+	if (kwork->use_bpf)
+		ret += printf(" %s%s%s",
+			      work->is_kthread ? "[" : "",
+			      work->name,
+			      work->is_kthread ? "]" : "");
+	else
+		ret += printf(" %-*s", PRINT_TASK_NAME_WIDTH, work->name);
 
 	printf("\n");
 	return ret;
@@ -2153,6 +2171,36 @@ next:
 	printf("\n");
 }
 
+static int perf_kwork__top_bpf(struct perf_kwork *kwork)
+{
+	int ret;
+
+	signal(SIGINT, sig_handler);
+	signal(SIGTERM, sig_handler);
+
+	ret = perf_kwork__top_prepare_bpf(kwork);
+	if (ret)
+		return -1;
+
+	printf("Starting trace, Hit <Ctrl+C> to stop and report\n");
+
+	perf_kwork__top_start();
+
+	/*
+	 * a simple pause, wait here for stop signal
+	 */
+	pause();
+
+	perf_kwork__top_finish();
+
+	perf_kwork__top_read_bpf(kwork);
+
+	perf_kwork__top_cleanup_bpf();
+
+	return 0;
+
+}
+
 static int perf_kwork__top(struct perf_kwork *kwork)
 {
 	struct __top_cpus_runtime *cpus_runtime;
@@ -2165,7 +2213,11 @@ static int perf_kwork__top(struct perf_kwork *kwork)
 	kwork->top_stat.cpus_runtime = cpus_runtime;
 	bitmap_zero(kwork->top_stat.all_cpus_bitmap, MAX_NR_CPUS);
 
-	ret = perf_kwork__read_events(kwork);
+	if (kwork->use_bpf)
+		ret = perf_kwork__top_bpf(kwork);
+	else
+		ret = perf_kwork__read_events(kwork);
+
 	if (ret)
 		goto out;
 
@@ -2380,6 +2432,10 @@ int cmd_kwork(int argc, const char **argv)
 		   "Time span for analysis (start,stop)"),
 	OPT_STRING('i', "input", &input_name, "file",
 		   "input file name"),
+#ifdef HAVE_BPF_SKEL
+	OPT_BOOLEAN('b', "use-bpf", &kwork.use_bpf,
+		    "Use BPF to measure task cpu usage"),
+#endif
 	OPT_PARENT(kwork_options)
 	};
 	const char *kwork_usage[] = {