//! The tests' own reading of this process's CPU energy, shared by the test
//! binaries of this directory that hold the cascade's figures against it.
//!
//! It shares no call and no number with the counter under test:
//! `proc_pid_rusage` is declared here and read into raw words at the SDK's
//! offset, and a read is taken only once this thread has left its core by a
//! rule of the oracle's own — the process's context-switch count rose across
//! a sleep — where the counter watches the reading thread's own energy count.
//! That rule holds only while one thread of the process runs, so each binary
//! here has one test.

#![allow(dead_code)]

use std::os::raw::{c_int, c_void};
use std::sync::atomic::{AtomicU64, Ordering};
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};

use eoc_meter::JouleCounter;

unsafe extern "C" {
    fn proc_pid_rusage(pid: c_int, flavor: c_int, buffer: *mut c_void) -> c_int;
    fn proc_pidinfo(pid: c_int, flavor: c_int, arg: u64, buffer: *mut c_void, buffersize: c_int) -> c_int;
    fn clock_gettime_nsec_np(clock_id: u32) -> u64;
}

/// `CLOCK_THREAD_CPUTIME_ID` in macOS `<time.h>`.
const CLOCK_THREAD_CPUTIME_ID: u32 = 16;

/// This thread's CPU time.
fn thread_cpu() -> Duration {
    Duration::from_nanos(unsafe { clock_gettime_nsec_np(CLOCK_THREAD_CPUTIME_ID) })
}

/// Spin this thread until it has used `d` of its own CPU time (or 20 s of
/// wall time have passed), however loaded the host is.
pub fn burn(d: Duration) {
    let (started, wall) = (thread_cpu(), Instant::now());
    let mut acc: u64 = 0;
    while thread_cpu() - started < d && wall.elapsed() < Duration::from_secs(20) {
        for _ in 0..1_000 {
            acc = std::hint::black_box(acc.wrapping_add(1));
        }
    }
}

fn me() -> c_int {
    std::process::id() as c_int
}

/// This process's `ri_energy_nj` as it stands: `proc_pid_rusage(pid,
/// RUSAGE_INFO_V6)` into 464 raw bytes, the count at byte 336.
fn energy_nj() -> u64 {
    let mut words = [0u64; 464 / 8];
    let rc = unsafe { proc_pid_rusage(me(), 6, words.as_mut_ptr() as *mut c_void) };
    assert_eq!(rc, 0, "the oracle's proc_pid_rusage");
    words[336 / 8]
}

/// How many times this process's threads have been switched off a core:
/// `pti_csw`, the `int32_t` at byte 80 of the 96-byte `proc_taskinfo` that
/// `proc_pidinfo(pid, PROC_PIDTASKINFO = 4)` fills.
fn context_switches() -> i32 {
    let mut info = [0i32; 96 / 4];
    let wrote = unsafe { proc_pidinfo(me(), 4, 0, info.as_mut_ptr() as *mut c_void, 96) };
    assert_eq!(wrote, 96, "the oracle's proc_pidinfo(PROC_PIDTASKINFO)");
    info[80 / 4]
}

/// The oracle's read of this process's energy, in nanojoules, taken once
/// this thread has left its core: a sleep of 200 µs, then 1, 2, 4 and 8 ms,
/// until the process's context-switch count rose across one. Only the test's
/// thread runs in the process, so a rise is this thread's switch, and the
/// read after it holds all the thread spent before it.
pub fn energy_nj_off_core() -> u64 {
    let left = [200, 1_000, 2_000, 4_000, 8_000].into_iter().any(|micros| {
        let before = context_switches();
        std::thread::sleep(Duration::from_micros(micros));
        context_switches() > before
    });
    assert!(left, "the oracle never saw this thread leave its core across sleeps of 0.2, 1, 2, 4 and 8 ms");
    energy_nj()
}

/// One read of a [`Watched`] counter: the oracle's reading before it, what
/// the counter read (`None` for a failed read), the oracle's after it, and
/// where the test's own count stood when the read was asked for.
#[derive(Debug, Clone, Copy)]
pub struct Read {
    pub before_nanojoules: u64,
    pub microjoules: Option<u64>,
    pub after_nanojoules: u64,
    pub count: u64,
}

/// A counter with the oracle's own read on either side of every read of it,
/// kept in order. A span between two of its reads therefore lies between two
/// windows of the oracle's: the one inside the span, from the oracle's read
/// after the opening read to its read before the closing one, and the one
/// around the span and both reads.
///
/// The oracle's reads between the two readings of a span are the span's too:
/// its sleep after the opening read and before the closing one. So a span
/// through this counter reads a little more than one through the bare
/// counter would, and both windows hold it.
pub struct Watched<C> {
    counter: C,
    reads: Mutex<Vec<Read>>,
    count: Arc<AtomicU64>,
}

impl<C: JouleCounter> Watched<C> {
    pub fn new(counter: C) -> Self {
        Self::beside(counter, Arc::new(AtomicU64::new(0)))
    }

    /// A watched counter that also notes, at each read, where `count`
    /// stood: a count the test moves, to place a read among its own steps.
    pub fn beside(counter: C, count: Arc<AtomicU64>) -> Self {
        Self { counter, reads: Mutex::new(Vec::new()), count }
    }

    /// The reads taken since the last call, in order.
    pub fn take(&self) -> Vec<Read> {
        std::mem::take(&mut *self.reads.lock().unwrap())
    }
}

impl<C: JouleCounter> JouleCounter for Watched<C> {
    fn read_microjoules(&self) -> eoc_core::Result<u64> {
        let count = self.count.load(Ordering::SeqCst);
        let before_nanojoules = energy_nj_off_core();
        let read = self.counter.read_microjoules();
        let after_nanojoules = energy_nj_off_core();
        self.reads.lock().unwrap().push(Read {
            before_nanojoules,
            microjoules: read.as_ref().ok().copied(),
            after_nanojoules,
            count,
        });
        read
    }
    fn name(&self) -> &'static str {
        self.counter.name()
    }
}

/// A span between two reads of a [`Watched`] counter, in nanojoules: what
/// the counter read, and the oracle's two windows.
#[derive(Debug, Clone, Copy)]
pub struct Span {
    /// The counter's two reads' delta; `None` when either failed or the
    /// counter did not advance.
    pub read: Option<u64>,
    /// The oracle's window inside the span.
    pub inside: u64,
    /// The oracle's window around the span and both of its reads.
    pub around: u64,
}

impl Span {
    pub fn between(open: &Read, close: &Read) -> Self {
        let read = match (open.microjoules, close.microjoules) {
            (Some(open), Some(close)) if close > open => Some((close - open) * 1_000),
            _ => None,
        };
        Self {
            read,
            inside: close.before_nanojoules - open.after_nanojoules,
            around: close.after_nanojoules - open.before_nanojoules,
        }
    }

    /// Whether `nanojoules`, a figure for this span, lies between the
    /// oracle's two windows, give or take the micro-joule the counter's two
    /// reads round away. The count only grows, so a reading of the span that
    /// does not is not this process's count.
    pub fn holds(&self, nanojoules: u64) -> bool {
        self.inside < nanojoules + 1_000 && nanojoules < self.around + 1_000
    }

    /// The window inside the span as thousandths of the one around it: how
    /// closely the oracle pins the span.
    pub fn tightness(&self) -> u64 {
        self.inside * 1_000 / self.around.max(1)
    }
}

/// A counter that counts its reads.
pub struct Counted<C> {
    counter: C,
    reads: Mutex<u64>,
}

impl<C: JouleCounter> Counted<C> {
    pub fn new(counter: C) -> Self {
        Self { counter, reads: Mutex::new(0) }
    }

    pub fn reads(&self) -> u64 {
        *self.reads.lock().unwrap()
    }
}

impl<C: JouleCounter> JouleCounter for Counted<C> {
    fn read_microjoules(&self) -> eoc_core::Result<u64> {
        *self.reads.lock().unwrap() += 1;
        self.counter.read_microjoules()
    }
    fn name(&self) -> &'static str {
        self.counter.name()
    }
}