#!/usr/bin/bpftrace

kprobe:irq_thread+191
/curtask->prio < 99/
{
	// pre schedule()
	@allow_s_state[tid] = 1;
}

kprobe:irq_thread+196
/curtask->prio < 99/
{
	// post schedule()
	delete(@allow_s_state[tid]);
}

kprobe:smpboot_thread_fn+219
/curtask->prio < 99/
{
	// pre schedule()
	@allow_s_state[tid] = 1;
}

kprobe:smpboot_thread_fn+224
/curtask->prio < 99/
{
	// post schedule()
	delete(@allow_s_state[tid]);
}

kprobe:do_nanosleep
/curtask->prio < 99/
{
	@allow_s_state[tid] = 1;
}

kretprobe:do_nanosleep
/curtask->prio < 99/
{
	delete(@allow_s_state[tid]);
}

kprobe:futex_lock_pi
/curtask->prio < 99/
{
	@allow_s_state[tid] = 1;
}

kretprobe:futex_lock_pi
/curtask->prio < 99/
{
	delete(@allow_s_state[tid]);
}

tracepoint:sched:sched_switch
/args->prev_prio < 99 && nsecs > @starttime/
{
	if (!@ready) {
		@ready = 1;
		printf("Ready.\n");
	}

	// handle preempted run

	if (@schedout_r_state[args->next_pid]) {
		$val = @schedout_r_state[args->next_pid];
		printf("%lu: preempted run:     pid=%d prio=%d comm=%s nsecs=%ld\n", nsecs, args->next_pid, args->next_prio, args->next_comm, nsecs - $val);
		delete(@schedout_r_state[args->next_pid]);
	}

	if (args->prev_state == 0) {
		@schedout_r_state[args->prev_pid] = nsecs;
		return;
	}

	// handle sleeping

	if (args->prev_state != 1) {
		return;
	}

	if (@allow_s_state[args->prev_pid]) {
		delete(@allow_s_state[args->prev_pid]);
		return;
	}

	printf("%lu: sleeping:          pid=%d prio=%d comm=%s%s\n", nsecs, args->prev_pid, args->prev_prio, args->prev_comm, kstack);
	delete(@allow_s_state[args->prev_pid]);
}

tracepoint:exceptions:page_fault_kernel
/curtask->prio < 99/
{
	printf("%lu: kernel page fault: pid=%d prio=%d comm=%s%s\n", nsecs, tid, curtask->prio, curtask->comm, kstack);
}

tracepoint:exceptions:page_fault_user
/curtask->prio < 99/
{
	printf("%lu: user page fault:   pid=%d prio=%d comm=%s\n", nsecs, tid, curtask->prio, curtask->comm);
}

kprobe:do_futex
/curtask->prio < 99/
{
	$op = arg1 & 0x7f;
	if ($op == 0) {
		printf("%lu: non-PI futex wait:  pid=%d prio=%d comm=%s op=%d %s\n", nsecs, tid, curtask->prio, curtask->comm, $op, kstack);
	}
}

interval:s:600
{
	exit();
}

BEGIN
{
	@starttime = nsecs + 1000000000
}

END
{
	clear(@allow_s_state);
	clear(@schedout_r_state);
	clear(@starttime);
	clear(@ready);
}