perf kwork: Constify control data for BPF

The control knobs set before loading BPF programs should be declared as
'const volatile' so that it can be optimized by the BPF core.

Committer testing:

  root@x1:~# perf kwork report --use-bpf
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
    Kwork Name                     | Cpu  | Total Runtime | Count     | Max runtime   | Max runtime start   | Max runtime end     |
   --------------------------------------------------------------------------------------------------------------------------------
    (w)intel_atomic_commit_work [  | 0009 |     18.680 ms |         2 |     18.553 ms |     362410.681580 s |     362410.700133 s |
    (w)pm_runtime_work             | 0007 |     13.300 ms |         1 |     13.300 ms |     362410.254996 s |     362410.268295 s |
    (w)intel_atomic_commit_work [  | 0009 |      9.846 ms |         2 |      9.717 ms |     362410.172352 s |     362410.182069 s |
    (w)acpi_ec_event_processor     | 0002 |      8.106 ms |         1 |      8.106 ms |     362410.463187 s |     362410.471293 s |
    (s)SCHED:7                     | 0000 |      1.351 ms |       106 |      0.063 ms |     362410.658017 s |     362410.658080 s |
    i915:157                       | 0008 |      0.994 ms |        13 |      0.361 ms |     362411.222125 s |     362411.222486 s |
    (s)SCHED:7                     | 0001 |      0.703 ms |        98 |      0.047 ms |     362410.245004 s |     362410.245051 s |
    (s)SCHED:7                     | 0005 |      0.674 ms |        42 |      0.074 ms |     362411.483039 s |     362411.483113 s |
    (s)NET_RX:3                    | 0001 |      0.556 ms |        10 |      0.079 ms |     362411.066388 s |     362411.066467 s |
  <SNIP>

  root@x1:~# perf trace -e bpf --max-events 5 perf kwork report --use-bpf
       0.000 ( 0.016 ms): perf/2948007 bpf(cmd: 36, uattr: 0x7ffededa6660, size: 8)          = -1 EOPNOTSUPP (Operation not supported)
       0.026 ( 0.106 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6390, size: 148) = 12
       0.152 ( 0.032 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6450, size: 148) = 12
      26.247 ( 0.138 ms): perf/2948007 bpf(cmd: PROG_LOAD, uattr: 0x7ffededa6300, size: 148) = 12
      26.396 ( 0.012 ms): perf/2948007 bpf(uattr: 0x7ffededa64b0, size: 80)                  = 12
  Starting trace, Hit <Ctrl+C> to stop and report
  root@x1:~#

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Link: https://lore.kernel.org/r/20240902200515.2103769-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c
index 44f0f708a15d6a14f2f07eeed558ca26e35def3d..6c7126b7670dd0c9a2b0a5b55d74cbbc5f4ea5cd 100644 (file)
--- a/tools/perf/util/bpf_kwork.c
+++ b/tools/perf/util/bpf_kwork.c
@@ -176,8 +176,6 @@ static int setup_filters(struct perf_kwork *kwork)
                        bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY);
                }
                perf_cpu_map__put(map);
-
-               skel->bss->has_cpu_filter = 1;
        }
 
        if (kwork->profile_name != NULL) {
@@ -197,8 +195,6 @@ static int setup_filters(struct perf_kwork *kwork)
 
                key = 0;
                bpf_map_update_elem(fd, &key, kwork->profile_name, BPF_ANY);
-
-               skel->bss->has_name_filter = 1;
        }
 
        return 0;
@@ -239,6 +235,11 @@ int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork)
                        class_bpf->load_prepare(kwork);
        }
 
+       if (kwork->cpu_list != NULL)
+               skel->rodata->has_cpu_filter = 1;
+       if (kwork->profile_name != NULL)
+               skel->rodata->has_name_filter = 1;
+
        if (kwork_trace_bpf__load(skel)) {
                pr_debug("Failed to load kwork trace skeleton\n");
                goto out;

diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c
index 22a3b00a1e23f92999b835649a73b7202af5edd7..7261cad43468d7a4cfcaf4df0e1849b6fb057e67 100644 (file)
--- a/tools/perf/util/bpf_kwork_top.c
+++ b/tools/perf/util/bpf_kwork_top.c
@@ -151,14 +151,12 @@ static int setup_filters(struct perf_kwork *kwork)
                        bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY);
                }
                perf_cpu_map__put(map);
-
-               skel->bss->has_cpu_filter = 1;
        }
 
        return 0;
 }
 
-int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
+int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork)
 {
        struct bpf_program *prog;
        struct kwork_class *class;
@@ -193,6 +191,9 @@ int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
                        class_bpf->load_prepare();
        }
 
+       if (kwork->cpu_list)
+               skel->rodata->has_cpu_filter = 1;
+
        if (kwork_top_bpf__load(skel)) {
                pr_debug("Failed to load kwork top skeleton\n");
                goto out;

diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c
index 84c15ccbab44ccc9668d7b85296ab3b0482412c2..594da91965a2f6c9e082d9ef7d183fbb923a479a 100644 (file)
--- a/tools/perf/util/bpf_skel/kwork_top.bpf.c
+++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c
@@ -84,7 +84,7 @@ struct {
 
 int enabled = 0;
 
-int has_cpu_filter = 0;
+const volatile int has_cpu_filter = 0;
 
 __u64 from_timestamp = 0;
 __u64 to_timestamp = 0;

diff --git a/tools/perf/util/bpf_skel/kwork_trace.bpf.c b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
index 063c124e099938edb1879cedebf9151e41999f2a..cbd79bc4b3302d812cf569781b66f64598d62e58 100644 (file)
--- a/tools/perf/util/bpf_skel/kwork_trace.bpf.c
+++ b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
@@ -68,8 +68,9 @@ struct {
 } perf_kwork_name_filter SEC(".maps");
 
 int enabled = 0;
-int has_cpu_filter = 0;
-int has_name_filter = 0;
+
+const volatile int has_cpu_filter = 0;
+const volatile int has_name_filter = 0;
 
 static __always_inline int local_strncmp(const char *s1,
                                         unsigned int sz, const char *s2)