[PATCH v10 03/10] perf record --off-cpu: Preparation of off-cpu BPF program

[Howard Chu <howardchu95@gmail.com>]

Set the perf_event map in BPF for dumping off-cpu samples.

Set the offcpu_thresh to specify the threshold.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
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>
Link: https://lore.kernel.org/r/20241108204137.2444151-5-howardchu95@gmail.com
[ Added some missing iteration variables to off_cpu_config() and fixed up
  a manually edited patch hunk line boundary line ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf_off_cpu.c          | 25 +++++++++++++++++++++++++
 tools/perf/util/bpf_skel/off_cpu.bpf.c | 11 +++++++++++
 2 files changed, 36 insertions(+)

diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 9275b022b2ea..2378fb5a893f 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -13,6 +13,7 @@
 #include "util/cgroup.h"
 #include "util/strlist.h"
 #include <bpf/bpf.h>
+#include <internal/xyarray.h>
 
 #include "bpf_skel/off_cpu.skel.h"
 
@@ -60,6 +61,9 @@ static int off_cpu_config(struct evlist *evlist)
 static void off_cpu_start(void *arg)
 {
 	struct evlist *evlist = arg;
+	struct evsel *evsel;
+	struct perf_cpu pcpu;
+	int i;
 
 	/* update task filter for the given workload */
 	if (skel->rodata->has_task && skel->rodata->uses_tgid &&
@@ -73,6 +77,25 @@ static void off_cpu_start(void *arg)
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
 	}
 
+	/* update BPF perf_event map */
+	evsel = evlist__find_evsel_by_str(evlist, OFFCPU_EVENT);
+	if (evsel == NULL) {
+		pr_err("%s evsel not found\n", OFFCPU_EVENT);
+		return;
+	}
+
+	perf_cpu_map__for_each_cpu(pcpu, i, evsel->core.cpus) {
+		int err;
+
+		err = bpf_map__update_elem(skel->maps.offcpu_output, &pcpu.cpu, sizeof(__u32),
+					   xyarray__entry(evsel->core.fd, i, 0),
+					   sizeof(__u32), BPF_ANY);
+		if (err) {
+			pr_err("Failed to update perf event map for direct off-cpu dumping\n");
+			return;
+		}
+	}
+
 	skel->bss->enabled = 1;
 }
 
@@ -261,6 +284,8 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target,
 		}
 	}
 
+	skel->bss->offcpu_thresh_ns = opts->off_cpu_thresh_us * 1000;
+
 	err = off_cpu_bpf__attach(skel);
 	if (err) {
 		pr_err("Failed to attach off-cpu BPF skeleton\n");
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c152116df72f..c87132e01eb3 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -18,6 +18,8 @@
 #define MAX_STACKS   32
 #define MAX_ENTRIES  102400
 
+#define MAX_CPUS  4096
+
 struct tstamp_data {
 	__u32 stack_id;
 	__u32 state;
@@ -39,6 +41,13 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, MAX_CPUS);
+} offcpu_output SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
@@ -97,6 +106,8 @@ const volatile bool uses_cgroup_v1 = false;
 
 int perf_subsys_id = -1;
 
+__u64 offcpu_thresh_ns;
+
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
  * Use BPF CO-RE "ignored suffix rule" to deal with it like below:
-- 
2.43.0