rust-kernel

//! Timers that send signals (stage 17): alarm, setitimer/getitimer and
//! the POSIX timers (timer_create, timer_settime, ...).
//!
//! A timer is a deadline, maybe with an interval to repeat at, and what to
//! do when it's reached: send a signal (SIGALRM for alarm and setitimer;
//! any signal, maybe to one thread, for timer_create).
//!
//! All timers live in one table. One kernel thread, "timerd", sleeps until
//! the nearest deadline, sends the signals that are due, and goes back to
//! sleep. Why a thread and not the timer interrupt? Sending a signal takes
//! locks and may wake threads; doing that from normal thread context keeps
//! the interrupt handler tiny and follows the locking rules in thread.rs.
//! timerd is started the first time anyone arms a timer.
//!
//! Resolution: timerd sleeps in PIT ticks (~55 ms), so a timer fires up
//! to ~110 ms late, never early. A periodic timer whose signals come late
//! counts the periods it missed as "overruns" (timer_getoverrun), like
//! Linux does when a signal is still pending.
//!
//! Lifetime, as on Linux: fork doesn't copy timers; execve deletes the
//! POSIX timers but keeps the alarm / ITIMER_REAL; exit deletes them all.

use crate::errno::Errno;
use crate::process;
use crate::signal::{self, SigInfo};
use crate::thread::WaitQueue;
use crate::time;
use alloc::vec::Vec;
use core::sync::atomic::{AtomicBool, Ordering};
use spin::Mutex;
use x86_64::instructions::interrupts::without_interrupts;

/// si_code for a POSIX timer's signal.
pub const SI_TIMER: i32 = -2;

// The clocks timer_create understands.
pub const CLOCK_REALTIME: u64 = 0;
pub const CLOCK_MONOTONIC: u64 = 1;
pub const CLOCK_BOOTTIME: u64 = 7;

// sigev_notify: what to do when it fires.
pub const SIGEV_SIGNAL: i32 = 0; // send sigev_signo to the process
pub const SIGEV_NONE: i32 = 1; // nothing (the program polls timer_gettime)
pub const SIGEV_THREAD_ID: i32 = 4; // send sigev_signo to thread sigev_tid

/// At most this many POSIX timers per process: EAGAIN after that.
const MAX_TIMERS: usize = 32;
/// The id we use for a process's ITIMER_REAL (POSIX ids are 0..MAX_TIMERS).
const ITIMER_ID: i32 = -1;

#[derive(Clone, Copy)]
struct Timer {
    pid: u64,
    /// timer_create's id, or ITIMER_ID.
    id: i32,
    clock: u64,
    /// Next expiry, in `time::now_us` microseconds (None = disarmed).
    next: Option<u64>,
    /// Repeat every this many microseconds (0 = once).
    interval: u64,
    signo: u32,
    notify: i32,
    /// SIGEV_THREAD_ID's thread.
    tid: u64,
    sigval: u64,
    /// Expirations missed at the last firing (timer_getoverrun).
    overrun: u64,
}

static TIMERS: Mutex<Vec<Timer>> = Mutex::new(Vec::new());
/// timerd sleeps here; poked when the table changes.
static CHANGED_QUEUE: WaitQueue = WaitQueue::new();
static CHANGED: AtomicBool = AtomicBool::new(false);
static STARTED: AtomicBool = AtomicBool::new(false);

fn with_table<R>(f: impl FnOnce(&mut Vec<Timer>) -> R) -> R {
    without_interrupts(|| f(&mut TIMERS.lock()))
}

/// Tell timerd to look again (starting it the first time).
fn poke() {
    if !STARTED.swap(true, Ordering::AcqRel) {
        crate::thread::spawn("timerd", timerd);
    }
    CHANGED.store(true, Ordering::Release);
    CHANGED_QUEUE.wake_all();
}

/// How far CLOCK_REALTIME is ahead of the monotonic clock (µs), to turn
/// absolute wall-clock deadlines into ours.
fn realtime_offset() -> u64 {
    time::realtime_us().saturating_sub(time::now_us())
}

/// The kernel thread that fires timers (see the top).
fn timerd() {
    loop {
        let now = time::now_us();
        let mut due = Vec::new();
        let next = with_table(|t| {
            for timer in t.iter_mut() {
                let Some(at) = timer.next else { continue };
                if at > now {
                    continue;
                }
                if timer.interval > 0 {
                    let missed = (now - at) / timer.interval;
                    timer.overrun = missed;
                    timer.next = Some(at + (missed + 1) * timer.interval);
                } else {
                    timer.overrun = 0;
                    timer.next = None;
                }
                due.push(*timer);
            }
            t.iter().filter_map(|t| t.next).min()
        });
        for timer in due {
            fire(&timer);
        }
        let changed = || CHANGED.swap(false, Ordering::AcqRel).then_some(());
        match next {
            Some(at) => {
                let deadline = time::deadline_after_us(at.saturating_sub(time::now_us()));
                let _ = CHANGED_QUEUE.wait_until_deadline(deadline, changed);
            }
            None => CHANGED_QUEUE.wait_until(changed),
        }
    }
}

/// Send a due timer's signal.
fn fire(timer: &Timer) {
    if timer.notify == SIGEV_NONE {
        return;
    }
    let Some(p) = process::get(timer.pid) else { return };
    let info = if timer.id == ITIMER_ID {
        SigInfo::from_pid(timer.signo, 0) // SI_KERNEL, like Linux's itimers
    } else {
        let mut info = SigInfo::new(timer.signo, SI_TIMER);
        info.fields[0] = timer.id as u32 as u64 | (timer.overrun.min(i32::MAX as u64)) << 32; // si_tid, si_overrun
        info.fields[1] = timer.sigval; // si_value
        info
    };
    if timer.notify == SIGEV_THREAD_ID {
        if let Some(t) = p.tasks().into_iter().find(|t| t.tid() == timer.tid) {
            signal::send_thread(&t, timer.signo, info);
        }
        return;
    }
    signal::send(&p, timer.signo, info);
}

/// (value, interval) of a timer in microseconds: time left, and the period.
fn read(timer: &Timer, now: u64) -> (u64, u64) {
    (timer.next.map_or(0, |at| at.saturating_sub(now).max(1)), timer.interval)
}

// --- setitimer / getitimer / alarm ---------------------------------------

/// getitimer(ITIMER_REAL): (time left, interval), in microseconds.
pub fn get_itimer(pid: u64) -> (u64, u64) {
    let now = time::now_us();
    with_table(|t| t.iter().find(|x| x.pid == pid && x.id == ITIMER_ID).map_or((0, 0), |x| read(x, now)))
}

/// setitimer(ITIMER_REAL, value, interval) (µs; value 0 disarms). Returns
/// the old (value, interval).
pub fn set_itimer(pid: u64, value: u64, interval: u64) -> (u64, u64) {
    let now = time::now_us();
    let old = with_table(|t| {
        let old = t.iter().position(|x| x.pid == pid && x.id == ITIMER_ID).map(|i| t.remove(i));
        if value > 0 {
            t.push(Timer {
                pid,
                id: ITIMER_ID,
                clock: CLOCK_MONOTONIC,
                next: Some(now + value),
                interval,
                signo: signal::SIGALRM,
                notify: SIGEV_SIGNAL,
                tid: 0,
                sigval: 0,
                overrun: 0,
            });
        }
        old.map_or((0, 0), |x| read(&x, now))
    });
    if value > 0 {
        poke();
    }
    old
}

// --- POSIX timers --------------------------------------------------------

/// What timer_create's `struct sigevent` asked for.
pub struct SigEvent {
    pub notify: i32,
    pub signo: u32,
    pub tid: u64,
    /// None: no sigevent was given, so the value is the timer's id.
    pub sigval: Option<u64>,
}

/// timer_create: a new, disarmed timer. Returns its id.
pub fn create(pid: u64, clock: u64, ev: SigEvent) -> Result<i32, Errno> {
    with_table(|t| {
        let ids: Vec<i32> = t.iter().filter(|x| x.pid == pid && x.id != ITIMER_ID).map(|x| x.id).collect();
        if ids.len() >= MAX_TIMERS {
            return Err(Errno::EAGAIN);
        }
        let id = (0..).find(|i| !ids.contains(i)).unwrap();
        // No sigevent: SIGALRM with the timer id as the value (Linux's default).
        let sigval = ev.sigval.unwrap_or(id as u64);
        t.push(Timer { pid, id, clock, next: None, interval: 0, signo: ev.signo, notify: ev.notify, tid: ev.tid, sigval, overrun: 0 });
        Ok(id)
    })
}

/// timer_settime: arm (value > 0) or disarm. `absolute`: value is a time on
/// the timer's clock, not a delay. Returns the old (value, interval).
pub fn settime(pid: u64, id: i32, absolute: bool, value: u64, interval: u64) -> Result<(u64, u64), Errno> {
    let now = time::now_us();
    let old = with_table(|t| {
        let timer = t.iter_mut().find(|x| x.pid == pid && x.id == id && id != ITIMER_ID).ok_or(Errno::EINVAL)?;
        let old = read(timer, now);
        timer.overrun = 0;
        timer.interval = interval;
        timer.next = match (value, absolute) {
            (0, _) => None,
            (v, false) => Some(now + v),
            (v, true) if timer.clock == CLOCK_REALTIME => Some(v.saturating_sub(realtime_offset()).max(1)),
            (v, true) => Some(v.max(1)), // MONOTONIC/BOOTTIME: our own clock
        };
        Ok(old)
    })?;
    if value > 0 {
        poke();
    }
    Ok(old)
}

/// timer_gettime: (time left, interval) in microseconds.
pub fn gettime(pid: u64, id: i32) -> Result<(u64, u64), Errno> {
    let now = time::now_us();
    with_table(|t| t.iter().find(|x| x.pid == pid && x.id == id && id != ITIMER_ID).map(|x| read(x, now)).ok_or(Errno::EINVAL))
}

/// timer_getoverrun: periods missed at the last expiry.
pub fn getoverrun(pid: u64, id: i32) -> Result<u64, Errno> {
    with_table(|t| t.iter().find(|x| x.pid == pid && x.id == id && id != ITIMER_ID).map(|x| x.overrun.min(i32::MAX as u64)).ok_or(Errno::EINVAL))
}

/// timer_delete.
pub fn delete(pid: u64, id: i32) -> Result<(), Errno> {
    with_table(|t| {
        let i = t.iter().position(|x| x.pid == pid && x.id == id && id != ITIMER_ID).ok_or(Errno::EINVAL)?;
        t.remove(i);
        Ok(())
    })
}

/// execve: POSIX timers go, the alarm stays.
pub fn exec(pid: u64) {
    with_table(|t| t.retain(|x| x.pid != pid || x.id == ITIMER_ID));
}

/// The process ended: all its timers go.
pub fn process_exited(pid: u64) {
    with_table(|t| t.retain(|x| x.pid != pid));
}

/// How many timers exist (tests: nothing left behind).
pub fn count() -> usize {
    with_table(|t| t.len())
}