//! `--repair`: clean up the Pulse modules left behind by a crashed pixelpass
//! host.
//!
//! All of the judgement lives in [`plan`], which is pure. What remains here is
//! I/O plus the two rules that cannot be expressed in a plan:
//!
//! - **Re-verify immediately before destroying anything.** Pulse module indices
//!   are reused verbatim, and a host can die (or come back) between the snapshot
//!   and the unload, so the plan is treated as evidence that expires — never as a
//!   licence.
//! - **Gate the sink on what is still attached to it**, not on the plan's ordering
//!   having succeeded. An unload can fail or be skipped, and a loopback can appear
//!   after the plan was made.
//!
//! Repair never touches native PipeWire nodes. Since phase 0c the capture sink is
//! connection-owned and removes itself when its host dies, so there is nothing
//! there for repair to do and no safe way for it to help.
//!
//! # Where the observations come from
//!
//! Structured Pulse introspection over one verified-local connection — see
//! [`introspect`], which also documents the three defects that parsing `pactl`'s
//! text output turned out to have. Listing *and* unloading both go through that
//! same connection.

pub mod introspect;
pub mod plan;

use anyhow::{Context, Result, bail};
use std::path::Path;

use introspect::PulseSession;
use plan::{Fingerprint, Liveness, Shape};

pub async fn run(clean_untagged: bool) -> Result<()> {
    let liveness = LivenessProbe::new();
    if let Some(reason) = liveness.degraded_reason() {
        // Scoped deliberately: modules carrying a token that matches this machine,
        // boot and pid namespace are still cleaned, because the token establishes
        // what these signals can only guess at. Saying "refusing to unload
        // anything" here would be false in exactly the container-recovery case the
        // token was added for.
        eprintln!(
            "[pixelpass] --repair: cannot independently determine process liveness \
             ({reason}); modules WITHOUT an ownership token will be left alone."
        );
    }

    let local = local_identity().context("could not establish this process's own identity")?;
    let policy = plan::Policy {
        local,
        untagged: if clean_untagged {
            plan::UntaggedPolicy::CleanByPidAlone
        } else {
            plan::UntaggedPolicy::Refuse
        },
    };
    if clean_untagged {
        eprintln!(
            "[pixelpass] --repair: --repair-legacy-untagged given; untagged modules will be \
             judged by process id ALONE. That is only safe on the machine and in the pid \
             namespace that ran the crashed host."
        );
    }

    let mut pulse = PulseSession::connect().context("could not observe the Pulse module table")?;
    let modules = pulse
        .list_modules()
        .context("could not list Pulse modules")?;

    // Say so loudly when something names our sinks but matches no shape we know:
    // that is either a third party using our names, or a newer pixelpass whose
    // modules this build cannot recognise. The second is how repair would go
    // silently blind, so it never gets inferred from a clean exit.
    let unrecognised = plan::unrecognised_pixelpass_modules(&modules);
    if !unrecognised.is_empty() {
        eprintln!(
            "[pixelpass] --repair: {} module(s) name a pixelpass capture sink but do not match \
             any shape this build knows; they are being LEFT ALONE:",
            unrecognised.len()
        );
        for obs in &unrecognised {
            eprintln!(
                "[pixelpass] --repair:   #{} {} {}",
                obs.id, obs.name, obs.args
            );
        }
    }

    let planned = plan::plan(&modules, &policy, |pid, attribution| {
        liveness_for(&liveness, attribution, pid)
    });

    // Ours by shape, but carrying no proof of whose pid they name. Never unloaded by
    // default — listed, so an explicit legacy run has something to look at first.
    if !planned.untagged.is_empty() {
        eprintln!(
            "[pixelpass] --repair: {} module(s) are pixelpass's but carry no ownership token, so \
             the process id in their name cannot be attributed to this machine or pid namespace. \
             LEFT ALONE. Re-run with --repair-legacy-untagged to clean them by pid alone:",
            planned.untagged.len()
        );
        for fp in &planned.untagged {
            eprintln!(
                "[pixelpass] --repair:   #{} {} (claims pid {})",
                fp.id,
                fp.shape.label(),
                fp.pid
            );
        }
    }
    // Tokened, but the token belongs to another machine, boot or namespace.
    if !planned.foreign.is_empty() {
        eprintln!(
            "[pixelpass] --repair: {} module(s) belong to another machine, boot or pid namespace; \
             their process ids mean nothing here. LEFT ALONE:",
            planned.foreign.len()
        );
        for fp in &planned.foreign {
            eprintln!(
                "[pixelpass] --repair:   #{} {} (claims pid {})",
                fp.id,
                fp.shape.label(),
                fp.pid
            );
        }
    }

    if planned.is_empty() {
        let mut held = Vec::new();
        if !planned.live_pids.is_empty() {
            held.push(format!(
                "{} live pixelpass host(s)",
                planned.live_pids.len()
            ));
        }
        if !planned.unknown_pids.is_empty() {
            held.push(format!(
                "{} pid(s) of undeterminable liveness",
                planned.unknown_pids.len()
            ));
        }
        if held.is_empty() {
            println!("[pixelpass] --repair: nothing to clean up.");
        } else {
            println!(
                "[pixelpass] --repair: nothing to clean up ({} left alone).",
                held.join(", ")
            );
        }
        return Ok(());
    }

    let mut unloaded = 0u32;
    let mut skipped = 0u32;
    let mut failed = 0u32;

    for fp in &planned.unload {
        // ORDER MATTERS, and it is the opposite of what reads naturally.
        //
        // Liveness is asked FIRST, and the fresh snapshot is taken AFTER it. The
        // tempting order — verify the module, then check liveness, then unload —
        // leaves the dangerous window wide open: between `kill` returning ESRCH and
        // the unload, this process can be descheduled long enough for the planned
        // module to vanish, a new host to inherit both the pid and the module index,
        // and its differently-nonced arguments to occupy that index. Nothing would
        // re-read those arguments, so the reused index gets unloaded.
        //
        // Asking liveness first and re-verifying the fingerprint after it means a
        // replacement arriving in that window is caught by the argument comparison,
        // and only the irreducible snapshot-to-unload interval remains.
        match attributed_liveness(&liveness, fp) {
            Liveness::Dead => {}
            Liveness::Alive => {
                println!(
                    "[pixelpass] --repair: pid {} is alive again; leaving module #{} alone",
                    fp.pid, fp.id
                );
                skipped += 1;
                continue;
            }
            Liveness::Unknown => {
                eprintln!(
                    "[pixelpass] --repair: pid {}'s liveness became undeterminable; \
                     leaving module #{} alone",
                    fp.pid, fp.id
                );
                skipped += 1;
                continue;
            }
        }

        // Fresh snapshot per action, taken after the liveness answer. Deliberately
        // not hoisted out of the loop: each unload changes the module table, and the
        // point is to decide against the table as it is *now*.
        let current = pulse
            .list_modules()
            .context("could not re-list Pulse modules")?;
        let Some(obs) = current.iter().find(|m| m.id == fp.id) else {
            println!(
                "[pixelpass] --repair: module #{} is already gone; skipping",
                fp.id
            );
            skipped += 1;
            continue;
        };
        if !fp.still_matches(obs) {
            // The index now names something else, or the same module's
            // arguments changed. Either way we no longer know what we would be
            // destroying, so we do not destroy it.
            eprintln!(
                "[pixelpass] --repair: module #{} no longer matches what was planned \
                 (index reused?); refusing to unload it",
                fp.id
            );
            skipped += 1;
            continue;
        }
        // The sink goes last in the plan, but "last" is not the same as "nothing
        // is attached any more": a loopback unload may have failed or been
        // skipped, or a new one may have arrived since. Ask the fresh snapshot.
        if fp.shape == Shape::LegacyCaptureSink
            && let Some(holder) = plan::sink_still_referenced(&current, fp.pid, fp.id)
        {
            eprintln!(
                "[pixelpass] --repair: module #{} (capture sink for pid {}) is still referenced \
                 by module #{}; leaving the sink loaded",
                fp.id, fp.pid, holder
            );
            skipped += 1;
            continue;
        }

        match pulse.unload_module(fp.id) {
            Ok(()) => {
                println!("[pixelpass] --repair: {}", describe(fp));
                unloaded += 1;
            }
            Err(e) => {
                eprintln!("[pixelpass] --repair: failed to unload #{}: {e:#}", fp.id);
                failed += 1;
            }
        }
    }

    if !planned.live_pids.is_empty() {
        println!(
            "[pixelpass] --repair: left {} live pixelpass host(s) alone.",
            planned.live_pids.len()
        );
    }
    if !planned.unknown_pids.is_empty() {
        println!(
            "[pixelpass] --repair: left {} pid(s) alone whose liveness could not be determined.",
            planned.unknown_pids.len()
        );
    }
    if skipped > 0 {
        // Deliberately not "changed under us": a skip can also mean the module is
        // still referenced, or its owner's liveness stopped being decidable. The
        // per-module reason was printed above.
        println!("[pixelpass] --repair: skipped {skipped} module(s) (reasons above).");
    }
    if failed > 0 {
        bail!("--repair: {failed} module(s) failed to unload (see errors above)");
    }
    println!("[pixelpass] --repair: cleaned up {unloaded} module(s).");
    Ok(())
}

fn describe(fp: &Fingerprint) -> String {
    format!(
        "unloaded {} #{} (orphaned from pid {})",
        fp.shape.label(),
        fp.id,
        fp.pid
    )
}

/// Ask liveness with the module's *attribution* in hand.
///
/// A module whose token matches this machine, boot and pid namespace has already
/// proven that its pid is a number meaningful here — that is the token's entire
/// job. Running such a module through the probe's degradation checks would defeat
/// it in exactly the situation it exists for: a host crashing inside a container
/// leaves a token that matches perfectly, while a container marker or a multi-entry
/// `NSpid` makes the probe answer `Unknown` for everything, so token-qualified
/// repair would do nothing precisely where it is now safe.
///
/// The degradation signals therefore guard only the *untagged* path, where a bare
/// pid is all there is and those signals are the only protection left.
fn liveness_for(probe: &LivenessProbe, attribution: plan::Attribution, pid: u32) -> Liveness {
    match attribution {
        plan::Attribution::Tokened => probe.of_attributed(pid),
        plan::Attribution::Untagged => probe.of(pid),
    }
}

/// The same rule, for a fingerprint at execution time.
fn attributed_liveness(probe: &LivenessProbe, fp: &Fingerprint) -> Liveness {
    let attribution = match fp.owner {
        Some(_) => plan::Attribution::Tokened,
        None => plan::Attribution::Untagged,
    };
    liveness_for(probe, attribution, fp.pid)
}

// ──────────────────────────────────────────────────────────────────────
// Identity
// ──────────────────────────────────────────────────────────────────────

/// This process's machine, boot and pid-namespace identity.
///
/// Read from the kernel and the system, never guessed: without all three, a token
/// cannot be compared and no module can be attributed. Dashes are stripped so every
/// component is safe inside a single unquoted Pulse property value.
pub fn local_identity() -> Result<plan::LocalIdentity> {
    let machine = read_identity_file("/etc/machine-id")
        .or_else(|_| read_identity_file("/var/lib/dbus/machine-id"))
        .context("could not read a machine id")?;
    let boot = read_identity_file("/proc/sys/kernel/random/boot_id")
        .context("could not read the boot id")?;
    let pid_ns = pid_namespace_id().context("could not read this process's pid namespace")?;
    Ok(plan::LocalIdentity {
        machine,
        boot,
        pid_ns,
    })
}

fn read_identity_file(path: &str) -> Result<String> {
    let raw = std::fs::read_to_string(path).with_context(|| format!("could not read {path}"))?;
    let cleaned: String = raw
        .trim()
        .chars()
        .filter(|c| c.is_ascii_hexdigit())
        .collect();
    if cleaned.is_empty() {
        bail!("{path} held no usable identity");
    }
    Ok(cleaned)
}

/// The inode of `/proc/self/ns/pid` — the kernel's identity for a pid namespace.
///
/// This is the value that makes a pid meaningful: two processes in different pid
/// namespaces can hold the same number, and only this distinguishes them.
fn pid_namespace_id() -> Result<u64> {
    use std::os::unix::fs::MetadataExt;
    let meta =
        std::fs::metadata("/proc/self/ns/pid").context("could not stat /proc/self/ns/pid")?;
    Ok(meta.ino())
}

// ──────────────────────────────────────────────────────────────────────
// Liveness
// ──────────────────────────────────────────────────────────────────────

/// Answers "is this pid still around", and knows when it must refuse to answer.
///
/// **An error is not an absence.** `Path::exists()` folds permission errors and a
/// missing `/proc` into `false`, which here would read as "dead, go ahead and
/// unload". Liveness is asked with `kill(pid, 0)` instead, where `EPERM` *proves*
/// existence.
///
/// # The limit of what this can prove, stated rather than papered over
///
/// A pid can be alive and invisible. Inside a pid namespace — a container, a
/// distrobox — `/proc/self` is perfectly visible while every process in the
/// *parent* namespace is not, and `hidepid` has the same self-visible,
/// others-invisible shape. Repair in such a place can reach the host's Pulse
/// socket, see a live host's modules, get `ESRCH` for its pid and unload a running
/// host's audio.
///
/// The signals below are **negative** ones: they detect *some* cases where pid
/// numbers cannot be trusted, and every one of them fails closed. What they cannot
/// do is prove the converse. `NSpid` reports this process's pid in each namespace
/// that its procfs can see, and its leftmost value is relative to the pid namespace
/// that mounted that procfs — so a nested namespace with its own `/proc` reports a
/// single entry quite legitimately. `NSpid > 1` therefore means "definitely
/// nested", while `NSpid == 1` means only "not detectably nested".
///
/// Closing that properly needs the module itself to carry an owner token (machine
/// and boot identity plus pid-namespace identity) written at load time, with
/// token-less modules treated as `Unknown`. That changes what pixelpass writes into
/// the graph and how far back `--repair` can clean up, so it is a design decision
/// recorded in the impl plan rather than guessed at here.
struct LivenessProbe {
    /// `None` when no signal says pid numbers are untrustworthy; `Some(reason)`
    /// when every answer must be [`Liveness::Unknown`].
    degraded: Option<String>,
}

impl LivenessProbe {
    fn new() -> Self {
        Self {
            degraded: Self::detect_degradation(),
        }
    }

    fn detect_degradation() -> Option<String> {
        // Locality is deliberately NOT checked here. `PULSE_SERVER` is a fallback
        // *list*, so `unix:/missing tcp:remote:4713` starts with "unix:" and still
        // connects to another machine, and a remote server can be selected by client
        // configuration with the variable unset entirely. The authoritative answer
        // comes from `pa_context_is_local()` on the connection that actually got
        // established — see `introspect::PulseSession::connect`.
        match std::fs::read_to_string("/proc/self/status") {
            Ok(status) => {
                let nspid = status
                    .lines()
                    .find_map(|line| line.strip_prefix("NSpid:"))
                    .map(|rest| rest.split_whitespace().count());
                match nspid {
                    Some(n) if n > 1 => {
                        return Some(format!(
                            "this process is in a nested pid namespace (NSpid has {n} entries), \
                             so pids in module names may belong to processes it cannot see"
                        ));
                    }
                    // NB: a single entry is not proof of the initial namespace — see
                    // the type's doc comment. It only means nothing detected it.
                    // A kernel too old to report NSpid cannot rule nesting out.
                    None => {
                        return Some(
                            "/proc/self/status does not report NSpid, so pid-namespace identity \
                             cannot be established"
                                .to_string(),
                        );
                    }
                    Some(_) => {}
                }
            }
            Err(e) => return Some(format!("/proc/self/status could not be read: {e}")),
        }
        // Belt and braces: container runtimes that leave a marker.
        for marker in ["/run/.containerenv", "/.dockerenv"] {
            if Path::new(marker).try_exists().unwrap_or(false) {
                return Some(format!("{marker} exists, so this is a container"));
            }
        }
        None
    }

    fn degraded_reason(&self) -> Option<&str> {
        self.degraded.as_deref()
    }

    /// Liveness for a pid this process has **no** independent reason to trust —
    /// an untagged module. Here the degradation signals are the only protection.
    fn of(&self, pid: u32) -> Liveness {
        if self.degraded.is_some() {
            return Liveness::Unknown;
        }
        self.of_attributed(pid)
    }

    /// Liveness for a pid already proven to belong to this machine, boot and pid
    /// namespace by an [`plan::OwnerToken`].
    ///
    /// The degradation checks are deliberately skipped: they exist to guess at
    /// whether a bare pid is meaningful, and here that is not a guess any more.
    fn of_attributed(&self, pid: u32) -> Liveness {
        // `kill(0, …)` signals our whole process group and a negative pid signals
        // another group, so neither may ever reach `kill`. Neither is a pid we
        // could have written into a sink name anyway.
        if pid == 0 || pid > i32::MAX as u32 {
            return Liveness::Unknown;
        }
        match nix::sys::signal::kill(nix::unistd::Pid::from_raw(pid as i32), None) {
            Ok(()) => Liveness::Alive,
            // The process exists; we merely may not signal it.
            Err(nix::errno::Errno::EPERM) => Liveness::Alive,
            Err(nix::errno::Errno::ESRCH) => Liveness::Dead,
            Err(_) => Liveness::Unknown,
        }
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    // The `pactl`-text parser that used to live here is gone, and so are its
    // tests: `introspect` gets index, name and argument as structured fields, so
    // there is no format left to mis-parse. What replaced those tests is the live
    // field gate, since the remaining risk is in talking to the server, which no
    // unit test can exercise. The decisions all live in `plan`, which is pure and
    // tested there.

    /// The probe must never say `Dead` when it cannot see the whole pid space, and
    /// must never ask `kill` about a pid that would signal something other than one
    /// process.
    #[test]
    fn a_degraded_probe_never_reports_dead() {
        let degraded = LivenessProbe {
            degraded: Some("test".to_string()),
        };
        assert_eq!(degraded.of(1), Liveness::Unknown);
        assert_eq!(degraded.of(u32::MAX), Liveness::Unknown);

        let probe = LivenessProbe::new();
        // Our own pid is alive by construction — unless this test itself runs
        // somewhere the probe must abstain, which is exactly the other branch.
        let me = std::process::id();
        match probe.degraded_reason() {
            None => assert_eq!(probe.of(me), Liveness::Alive),
            Some(_) => assert_eq!(probe.of(me), Liveness::Unknown),
        }
        // `kill(0, …)` would signal our whole process group, and a pid past
        // `i32::MAX` cannot be expressed to `kill` at all.
        assert_eq!(probe.of(0), Liveness::Unknown);
        assert_eq!(probe.of(u32::MAX), Liveness::Unknown);
    }

    /// A token proves the pid is meaningful here, so the probe's namespace
    /// guesswork must not veto it. Without this, a host crashing inside a
    /// container leaves a perfectly matching token while a container marker makes
    /// every answer `Unknown` — and token-qualified repair does nothing in exactly
    /// the situation the token was built for.
    ///
    /// This runs against a *degraded* probe deliberately: on an ordinary desktop
    /// the two paths agree, so a test using the real probe's state would pass
    /// whether or not the distinction exists.
    #[test]
    fn a_token_beats_the_degradation_signals_but_a_bare_pid_does_not() {
        let degraded = LivenessProbe {
            degraded: Some("pretending to be in a container".to_string()),
        };
        let me = std::process::id();

        assert_eq!(
            degraded.of_attributed(me),
            Liveness::Alive,
            "an attributed pid must still be answered when the probe is degraded"
        );
        assert_eq!(
            degraded.of(me),
            Liveness::Unknown,
            "a bare pid must not be, since the signals are all it has"
        );

        // And the routing between them, which is what the caller actually uses.
        assert_eq!(
            liveness_for(&degraded, plan::Attribution::Tokened, me),
            Liveness::Alive
        );
        assert_eq!(
            liveness_for(&degraded, plan::Attribution::Untagged, me),
            Liveness::Unknown
        );
    }
}