[PATCH v14 04/10] perf record --off-cpu: Dump off-cpu samples in BPF

[Howard Chu]

Collect tid, period, callchain, and cgroup id and dump them when off-cpu
time threshold is reached.

We don't collect the off-cpu time twice (the delta), it's either in
direct samples, or accumulated samples that are dumped at the end of
perf.data.

Suggested-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Signed-off-by: Howard Chu <howardchu95@xxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Ian Rogers <irogers@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: James Clark <james.clark@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20241108204137.2444151-6-howardchu95@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/bpf_skel/off_cpu.bpf.c | 88 ++++++++++++++++++++++++--
 1 file changed, 83 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 1cdd4d63ea92..77fdc9e81db3 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -19,11 +19,17 @@
 #define MAX_ENTRIES  102400
 
 #define MAX_CPUS  4096
+#define MAX_OFFCPU_LEN 37
+
+struct stack {
+	u64 array[MAX_STACKS];
+};
 
 struct tstamp_data {
 	__u32 stack_id;
 	__u32 state;
 	__u64 timestamp;
+	struct stack stack;
 };
 
 struct offcpu_key {
@@ -41,6 +47,10 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
+struct offcpu_data {
+	u64 array[MAX_OFFCPU_LEN];
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
 	__uint(key_size, sizeof(__u32));
@@ -48,6 +58,13 @@ struct {
 	__uint(max_entries, MAX_CPUS);
 } offcpu_output SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct offcpu_data));
+	__uint(max_entries, 1);
+} offcpu_payload SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
@@ -106,6 +123,8 @@ const volatile bool uses_cgroup_v1 = false;
 
 int perf_subsys_id = -1;
 
+__u64 offcpu_thresh_ns = 500000000ull;
+
 /*
  * 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:
@@ -192,6 +211,47 @@ static inline int can_record(struct task_struct *t, int state)
 	return 1;
 }
 
+static inline int copy_stack(struct stack *from, struct offcpu_data *to, int n)
+{
+	int len = 0;
+
+	for (int i = 0; i < MAX_STACKS && from->array[i]; ++i, ++len)
+		to->array[n + 2 + i] = from->array[i];
+
+	return len;
+}
+
+/**
+ * off_cpu_dump - dump off-cpu samples to ring buffer
+ * @data: payload for dumping off-cpu samples
+ * @key: off-cpu data
+ * @stack: stack trace of the task before being scheduled out
+ *
+ * If the threshold of off-cpu time is reached, acquire tid, period, callchain, and cgroup id
+ * information of the task, and dump it as a raw sample to perf ring buffer
+ */
+static int off_cpu_dump(void *ctx, struct offcpu_data *data, struct offcpu_key *key,
+			struct stack *stack, __u64 delta)
+{
+	int n = 0, len = 0;
+
+	data->array[n++] = (u64)key->tgid << 32 | key->pid;
+	data->array[n++] = delta;
+
+	/* data->array[n] is callchain->nr (updated later) */
+	data->array[n + 1] = PERF_CONTEXT_USER;
+	data->array[n + 2] = 0;
+	len = copy_stack(stack, data, n);
+
+	/* update length of callchain */
+	data->array[n] = len + 1;
+	n += len + 2;
+
+	data->array[n++] = key->cgroup_id;
+
+	return bpf_perf_event_output(ctx, &offcpu_output, BPF_F_CURRENT_CPU, data, n * sizeof(u64));
+}
+
 static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 			struct task_struct *next, int state)
 {
@@ -216,6 +276,16 @@ static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 	pelem->state = state;
 	pelem->stack_id = stack_id;
 
+	/*
+	 * If stacks are successfully collected by bpf_get_stackid(), collect them once more
+	 * in task_storage for direct off-cpu sample dumping
+	 */
+	if (stack_id > 0 && bpf_get_stack(ctx, &pelem->stack, MAX_STACKS * sizeof(u64), BPF_F_USER_STACK)) {
+		/*
+		 * This empty if block is used to avoid 'result unused warning' from bpf_get_stack().
+		 * If the collection fails, continue with the logic for the next task.
+		 */
+	}
 next:
 	pelem = bpf_task_storage_get(&tstamp, next, NULL, 0);
 
@@ -230,11 +300,19 @@ static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 		__u64 delta = ts - pelem->timestamp;
 		__u64 *total;
 
-		total = bpf_map_lookup_elem(&off_cpu, &key);
-		if (total)
-			*total += delta;
-		else
-			bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+		if (delta >= offcpu_thresh_ns) {
+			int zero = 0;
+			struct offcpu_data *data = bpf_map_lookup_elem(&offcpu_payload, &zero);
+
+			if (data)
+				off_cpu_dump(ctx, data, &key, &pelem->stack, delta);
+		} else {
+			total = bpf_map_lookup_elem(&off_cpu, &key);
+			if (total)
+				*total += delta;
+			else
+				bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+		}
 
 		/* prevent to reuse the timestamp later */
 		pelem->timestamp = 0;
-- 
2.43.0