perf record: Handle argument change in sched_switch

Recently sched_switch tracepoint added a new argument for prev_state,
but it's hard to handle the change in a BPF program.  Instead, we can
check the function prototype in BTF before loading the program.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
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/20220518224725.742882-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/bpf_off_cpu.c

@@ -89,6 +89,33 @@ static void off_cpu_finish(void *arg __maybe_unused)
 	off_cpu_bpf__destroy(skel);
 }
 
+/* v5.18 kernel added prev_state arg, so it needs to check the signature */
+static void check_sched_switch_args(void)
+{
+	const struct btf *btf = bpf_object__btf(skel->obj);
+	const struct btf_type *t1, *t2, *t3;
+	u32 type_id;
+
+	type_id = btf__find_by_name_kind(btf, "bpf_trace_sched_switch",
+					 BTF_KIND_TYPEDEF);
+	if ((s32)type_id < 0)
+		return;
+
+	t1 = btf__type_by_id(btf, type_id);
+	if (t1 == NULL)
+		return;
+
+	t2 = btf__type_by_id(btf, t1->type);
+	if (t2 == NULL || !btf_is_ptr(t2))
+		return;
+
+	t3 = btf__type_by_id(btf, t2->type);
+	if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 4) {
+		/* new format: pass prev_state as 4th arg */
+		skel->rodata->has_prev_state = true;
+	}
+}
+
 int off_cpu_prepare(struct evlist *evlist, struct target *target)
 {
 	int err, fd, i;
@@ -117,6 +144,7 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target)
 	}
 
 	set_max_rlimit();
+	check_sched_switch_args();
 
 	err = off_cpu_bpf__load(skel);
 	if (err) {

tools/perf/util/bpf_skel/off_cpu.bpf.c

@@ -72,6 +72,8 @@ int enabled = 0;
 int has_cpu = 0;
 int has_task = 0;
 
+const volatile bool has_prev_state = false;
+
 /*
  * 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:
@@ -121,22 +123,13 @@ static inline int can_record(struct task_struct *t, int state)
 	return 1;
 }
 
-SEC("tp_btf/sched_switch")
-int on_switch(u64 *ctx)
+static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
+			struct task_struct *next, int state)
 {
 	__u64 ts;
-	int state;
 	__u32 stack_id;
-	struct task_struct *prev, *next;
 	struct tstamp_data *pelem;
 
-	if (!enabled)
-		return 0;
-
-	prev = (struct task_struct *)ctx[1];
-	next = (struct task_struct *)ctx[2];
-	state = get_task_state(prev);
-
 	ts = bpf_ktime_get_ns();
 
 	if (!can_record(prev, state))
@@ -180,4 +173,24 @@ next:
 	return 0;
 }
 
+SEC("tp_btf/sched_switch")
+int on_switch(u64 *ctx)
+{
+	struct task_struct *prev, *next;
+	int prev_state;
+
+	if (!enabled)
+		return 0;
+
+	prev = (struct task_struct *)ctx[1];
+	next = (struct task_struct *)ctx[2];
+
+	if (has_prev_state)
+		prev_state = (int)ctx[3];
+	else
+		prev_state = get_task_state(prev);
+
+	return off_cpu_stat(ctx, prev, next, prev_state);
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";