//! Root-side file ops in agent-owned or agent-reachable directories:
//! `SetAgentPaused` (the pause marker in the agent's `harness/`),
//! `EnsureAgentSocketDir` (`/run/hive-agent/<name>`) and the legacy
//! `SyncAgentTmpfiles`, which only removes the tmpfiles file older builds
//! wrote.

use std::os::fd::AsRawFd as _;
use std::path::{Path, PathBuf};

use anyhow::{Context as _, Result, bail};
use hive_priv_sock::{AGENT_STATE_ROOT, PAUSED_MARKER_FILE};

use crate::shared::{StagedFile, ensure_plain_filename, open_dir, validate_agent_name};

/// Root of the per-agent unix-socket dirs on the host.
const SOCKET_DIR_ROOT: &str = "/run/hive-agent";

/// `SetAgentPaused`.
pub(crate) fn exec_set_agent_paused(agent_name: &str, paused: bool) -> Result<(String, String)> {
    validate_agent_name(agent_name)?;
    set_agent_paused(agent_name, paused)
}

/// Create or remove an agent's pause marker under its harness dir. The
/// marker is written empty and chowned to the harness dir's owner (the
/// agent), matching how the harness itself would have created it.
///
/// Both directions are idempotent: re-pausing truncates the existing empty
/// marker rather than failing, and a `NotFound` on removal is the
/// already-resumed case, not an error.
fn set_agent_paused(agent_name: &str, paused: bool) -> Result<(String, String)> {
    let harness_dir = PathBuf::from(AGENT_STATE_ROOT)
        .join(agent_name)
        .join("harness");
    if paused {
        return write_agent_dir_file(agent_name, &harness_dir, PAUSED_MARKER_FILE, "");
    }
    remove_marker_in(&harness_dir, PAUSED_MARKER_FILE)?;
    tracing::info!(agent = %agent_name, "cleared pause marker");
    Ok((String::new(), String::new()))
}

/// Unlink `dir/filename`, treating "already gone" as success.
///
/// `remove_file` unlinks the leaf itself and never follows a symlink, so an
/// agent-planted link at the marker path cannot redirect this root unlink
/// at another file — the same threat [`StagedFile`] closes on the create side.
fn remove_marker_in(dir: &Path, filename: &str) -> Result<()> {
    let path = dir.join(filename);
    match std::fs::remove_file(&path) {
        Ok(()) => Ok(()),
        Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(()),
        Err(e) => Err(e).with_context(|| format!("remove {}", path.display())),
    }
}

/// Write `content` to `dir/filename` as root, chowning the result to `dir`'s
/// owner so the agent process can read it back. Its caller is the pause
/// marker, in `harness/`, a directory owned by the agent, which is precisely
/// why it needs hive-priv at all.
///
/// The file is published through a [`StagedFile`], so a reader woken by its
/// appearance cannot catch it empty or half-written: several of these paths
/// have a `systemd.path` unit watching them, and one of those triggers on the
/// file existing rather than changing.
fn write_agent_dir_file(
    agent_name: &str,
    dir: &Path,
    filename: &str,
    content: &str,
) -> Result<(String, String)> {
    use std::os::fd::AsRawFd as _;
    use std::os::unix::fs::MetadataExt as _;

    // Checked before `create_dir_all`, so a bad leaf does no filesystem work.
    ensure_plain_filename("write_agent_dir_file", filename)?;

    let state_dir = dir.to_path_buf();
    // NOTE: `create_dir_all` is normally a no-op — lifecycle creates and chowns
    // the state dir during spawn. On the rare edge where the dir doesn't exist
    // yet (container being provisioned for the first time), the newly created dir
    // is root:root. The `stat state_dir` chown below will then see uid=0 and
    // leave the file root-owned (0600). The agent won't be able to read it until
    // its lifecycle completes.
    std::fs::create_dir_all(&state_dir)
        .with_context(|| format!("create state dir {}", state_dir.display()))?;

    // Security-critical: the (state/-owning) agent may plant a symlink or
    // hardlink in this dir, and `StagedFile` neither follows nor reuses one,
    // so this root-privileged create/write/chmod/chown can't be redirected at
    // an arbitrary file.
    let path = state_dir.join(filename);
    let dir_fd = open_dir(&state_dir)?;
    let staged = StagedFile::write(&dir_fd, &state_dir, filename, content.as_bytes(), 0o600)?;

    // Chown to the state dir's owner so the agent process can read the file.
    // fchown on the temp's fd — TOCTOU-immune (the inode the write hit, never a
    // swapped path). If stat fails (e.g. dir just created, owner is root), the
    // file stays root-owned and 0600 — still unreadable by others, just not
    // agent-readable. Log a warning so operators can diagnose.
    match dir_fd.metadata() {
        Ok(meta) => {
            // SAFETY: the temp's fd is open and owned by `staged` for the whole
            // call; `fchown` only mutates that inode's uid/gid.
            let rc = unsafe { libc::fchown(staged.file().as_raw_fd(), meta.uid(), meta.gid()) };
            if rc != 0 {
                let e = std::io::Error::last_os_error();
                tracing::warn!(
                    agent = %agent_name,
                    path = %path.display(),
                    error = %e,
                    "write_agent_dir_file: fchown failed"
                );
            }
        }
        Err(e) => {
            tracing::warn!(
                agent = %agent_name,
                error = %e,
                "write_agent_dir_file: stat state_dir failed, leaving file root-owned"
            );
        }
    }
    // After the chown, never before: the file must never be visible under its
    // final name while still root-owned. A failed publish drops `staged`,
    // which removes the temp and the credential in it.
    staged.publish()?;

    tracing::info!(
        agent = %agent_name,
        dir = %state_dir.display(),
        file = %filename,
        "wrote agent file"
    );
    Ok((String::new(), String::new()))
}

/// Written by older hive-priv builds. Nothing writes it now, but left on disk
/// systemd-tmpfiles would still apply it at every boot.
const LEGACY_TMPFILES_PATH: &str = "/etc/tmpfiles.d/hyperhive-agents.conf";

/// Unlink [`LEGACY_TMPFILES_PATH`]; already absent is success. Run at every
/// hive-priv start and by the legacy `SyncAgentTmpfiles` request.
pub(crate) fn remove_legacy_tmpfiles() -> Result<()> {
    match std::fs::remove_file(LEGACY_TMPFILES_PATH) {
        Ok(()) => {
            tracing::info!("removed legacy {LEGACY_TMPFILES_PATH}");
            Ok(())
        }
        Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(()),
        Err(e) => Err(e).with_context(|| format!("remove {LEGACY_TMPFILES_PATH}")),
    }
}

/// `EnsureAgentSocketDir` — create `/run/hive-agent/<name>` if missing.
pub(crate) fn ensure_agent_socket_dir(name: &str) -> Result<(String, String)> {
    ensure_socket_dir_in(Path::new(SOCKET_DIR_ROOT), name)?;
    Ok((String::new(), String::new()))
}

/// Create `<root>/<name>` as a `0751` directory owned by the caller (root in
/// production), or accept an existing directory untouched.
/// `name` must be an agent ident; it is validated here, before any path is
/// built from it.
///
/// The result is an nspawn bind source, so a symlink here would bind a host
/// path of the planter's choosing into the container. Every step is relative
/// to an `O_DIRECTORY|O_NOFOLLOW` fd for `root`, and an existing entry is
/// checked with `AT_SYMLINK_NOFOLLOW` and refused unless it is a directory.
///
/// An existing directory keeps its owner and mode: the container's activation
/// hands it to the agent user, and re-asserting root here would undo that on
/// every start.
fn ensure_socket_dir_in(root: &Path, name: &str) -> Result<()> {
    use std::os::unix::fs::OpenOptionsExt as _;

    validate_agent_name(name)?;
    let path = root.join(name);
    let c_name = std::ffi::CString::new(name)
        .with_context(|| format!("agent name {name:?} contains a NUL byte"))?;
    let root_dir = std::fs::OpenOptions::new()
        .read(true)
        .custom_flags(libc::O_DIRECTORY | libc::O_NOFOLLOW | libc::O_CLOEXEC)
        .open(root)
        .with_context(|| format!("open (no-follow) {}", root.display()))?;
    // SAFETY: `root_dir` is an open directory fd and `c_name` NUL-terminated.
    if unsafe { libc::mkdirat(root_dir.as_raw_fd(), c_name.as_ptr(), 0o751) } == 0 {
        // mkdirat's mode is masked by the umask; the mode is part of the
        // contract, so it is set explicitly.
        // SAFETY: as above.
        let rc = unsafe {
            libc::fchmodat(
                root_dir.as_raw_fd(),
                c_name.as_ptr(),
                0o751,
                libc::AT_SYMLINK_NOFOLLOW,
            )
        };
        if rc != 0 {
            return Err(std::io::Error::last_os_error())
                .with_context(|| format!("chmod 0751 {}", path.display()));
        }
        tracing::info!(path = %path.display(), "created agent socket dir");
        return Ok(());
    }
    let err = std::io::Error::last_os_error();
    if err.kind() != std::io::ErrorKind::AlreadyExists {
        return Err(err).with_context(|| format!("create {}", path.display()));
    }
    // SAFETY: `stat` is plain old data; the zeroed value is only read after
    // `fstatat` has filled it in.
    let mut st: libc::stat = unsafe { std::mem::zeroed() };
    // SAFETY: as for `mkdirat`; `st` is a valid, writable `stat`.
    let rc = unsafe {
        libc::fstatat(
            root_dir.as_raw_fd(),
            c_name.as_ptr(),
            &raw mut st,
            libc::AT_SYMLINK_NOFOLLOW,
        )
    };
    if rc != 0 {
        return Err(std::io::Error::last_os_error())
            .with_context(|| format!("stat (no-follow) {}", path.display()));
    }
    if st.st_mode & libc::S_IFMT != libc::S_IFDIR {
        bail!(
            "{} exists but is not a directory; refusing it as a bind source",
            path.display()
        );
    }
    Ok(())
}
#[cfg(test)]
mod tests {
    use super::{PAUSED_MARKER_FILE, ensure_socket_dir_in, remove_marker_in, write_agent_dir_file};
    use crate::shared::test_support::{entries, scratch};
    use crate::shared::{StagedFile, open_dir};
    use std::path::PathBuf;

    #[test]
    fn rejects_non_plain_filenames() {
        let dir = scratch();
        let dir_fd = open_dir(&dir).unwrap();
        for bad in ["", ".", "..", "a/b", "/etc/passwd", "../escape", "sub/tok"] {
            assert!(
                StagedFile::write(&dir_fd, &dir, bad, b"x", 0o600).is_err(),
                "must reject filename {bad:?}"
            );
            // The wrapper's own check runs before its `create_dir_all`.
            // Pointing it at a directory that does not exist yet is what makes
            // this arm bite: the property worth pinning is that a bad leaf
            // fails BEFORE any root-privileged filesystem work.
            let absent = dir.join("never-created");
            assert!(
                write_agent_dir_file("a", &absent, bad, "x").is_err(),
                "wrapper must reject filename {bad:?}"
            );
            assert!(
                !absent.exists(),
                "rejected write created a directory for {bad:?}"
            );
        }
        std::fs::remove_dir_all(&dir).ok();
    }

    /// A published file arrives complete and alone. The residue arm is the
    /// load-bearing one: a stranded temp holds the same secret, is owned by
    /// root, and nothing else in the system would ever remove it.
    #[test]
    fn publishing_leaves_only_the_finished_file() {
        use std::os::unix::fs::PermissionsExt as _;
        let dir = scratch();
        let names = |d: &PathBuf| {
            let mut v: Vec<String> = std::fs::read_dir(d)
                .unwrap()
                .map(|e| e.unwrap().file_name().to_string_lossy().into_owned())
                .collect();
            v.sort();
            v
        };
        assert!(names(&dir).is_empty(), "control: scratch starts empty");

        let path = dir.join("matrix-token-alice");
        for content in ["SECRET", "ROTATED"] {
            write_agent_dir_file("a", &dir, "matrix-token-alice", content).unwrap();
            assert_eq!(names(&dir), ["matrix-token-alice"], "temp left behind");
            assert_eq!(std::fs::read_to_string(&path).unwrap(), content);
        }
        let mode = std::fs::metadata(&path).unwrap().permissions().mode() & 0o777;
        assert_eq!(mode, 0o600, "credential must be 0600 once published");

        std::fs::remove_dir_all(&dir).ok();
    }

    /// A failed publish must not strand the temp.
    #[test]
    fn a_failed_publish_removes_the_temp() {
        let dir = scratch();
        // A directory at the destination fails the `rename` (EISDIR) without
        // needing to drop privileges; the write and chown ahead of it still run.
        std::fs::create_dir(dir.join("forge-token")).unwrap();

        let err = write_agent_dir_file("a", &dir, "forge-token", "SECRET")
            .expect_err("publishing onto a directory must fail");
        assert!(
            format!("{err:#}").contains("publishing"),
            "must fail AT the publish -- failing earlier leaves no temp to \
             clean up and makes the next assertion vacuous. got: {err:#}"
        );
        assert_eq!(
            entries(&dir),
            ["forge-token"],
            "temp still holds the secret after a failed publish"
        );

        std::fs::remove_dir_all(&dir).ok();
    }

    /// The agent plants a symlink where the token goes. The rename replaces
    /// the link; the root-privileged write never reaches its target.
    #[test]
    fn a_symlink_at_the_name_is_replaced_not_followed() {
        let dir = scratch();
        let target = dir.join("target");
        std::fs::write(&target, "original").unwrap();
        std::os::unix::fs::symlink(&target, dir.join("forge-token")).unwrap();

        write_agent_dir_file("a", &dir, "forge-token", "SECRET").unwrap();
        assert_eq!(
            std::fs::read_to_string(&target).unwrap(),
            "original",
            "symlink target must be untouched"
        );
        let meta = std::fs::symlink_metadata(dir.join("forge-token")).unwrap();
        assert!(meta.file_type().is_file(), "the link must be replaced");
        assert_eq!(
            std::fs::read_to_string(dir.join("forge-token")).unwrap(),
            "SECRET"
        );
        std::fs::remove_dir_all(&dir).ok();
    }

    /// A missing socket dir is created `0751`, owned by the caller (root in
    /// production), which is the mode the container's activation expects to
    /// hand over and the one dialers traverse.
    #[test]
    fn socket_dir_created_0751_when_absent() {
        use std::os::unix::fs::{MetadataExt as _, PermissionsExt as _};
        let dir = scratch();
        ensure_socket_dir_in(&dir, "probe").unwrap();
        let meta = std::fs::symlink_metadata(dir.join("probe")).unwrap();
        assert!(meta.is_dir());
        assert_eq!(meta.permissions().mode() & 0o7777, 0o751);
        // SAFETY: `geteuid` has no preconditions.
        assert_eq!(meta.uid(), unsafe { libc::geteuid() });
        std::fs::remove_dir_all(&dir).ok();
    }

    /// An existing directory keeps its mode and contents: by the second start
    /// it belongs to the agent user, and a live socket may sit inside it.
    #[test]
    fn socket_dir_existing_directory_left_alone() {
        use std::os::unix::fs::PermissionsExt as _;
        let dir = scratch();
        let sub = dir.join("probe");
        std::fs::create_dir(&sub).unwrap();
        std::fs::set_permissions(&sub, std::fs::Permissions::from_mode(0o700)).unwrap();
        std::fs::write(sub.join("web.sock"), "").unwrap();

        ensure_socket_dir_in(&dir, "probe").unwrap();
        let mode = std::fs::metadata(&sub).unwrap().permissions().mode() & 0o7777;
        assert_eq!(mode, 0o700, "an existing dir's mode must not be reset");
        assert!(sub.join("web.sock").exists());
        std::fs::remove_dir_all(&dir).ok();
    }

    /// A symlink at the leaf would make nspawn bind wherever it points; it is
    /// refused, whether it points at a directory or nowhere.
    #[test]
    fn socket_dir_refuses_symlink_leaf() {
        use std::os::unix::fs::PermissionsExt as _;
        let dir = scratch();
        let elsewhere = dir.join("elsewhere");
        std::fs::create_dir(&elsewhere).unwrap();
        std::fs::set_permissions(&elsewhere, std::fs::Permissions::from_mode(0o700)).unwrap();
        std::os::unix::fs::symlink(&elsewhere, dir.join("probe")).unwrap();
        std::os::unix::fs::symlink(dir.join("missing"), dir.join("dangling")).unwrap();

        assert!(ensure_socket_dir_in(&dir, "probe").is_err());
        assert!(ensure_socket_dir_in(&dir, "dangling").is_err());
        let mode = std::fs::metadata(&elsewhere).unwrap().permissions().mode() & 0o7777;
        assert_eq!(mode, 0o700, "the symlink target must be untouched");
        assert!(!dir.join("missing").exists());
        std::fs::remove_dir_all(&dir).ok();
    }

    /// A regular file where the dir should be is refused, not bound.
    #[test]
    fn socket_dir_refuses_non_directory_leaf() {
        let dir = scratch();
        std::fs::write(dir.join("probe"), "x").unwrap();
        let err = ensure_socket_dir_in(&dir, "probe").unwrap_err();
        assert!(format!("{err:#}").contains("not a directory"), "{err:#}");
        std::fs::remove_dir_all(&dir).ok();
    }

    /// A symlinked root would place the new dir in a tree of the planter's
    /// choosing; the `O_NOFOLLOW` open refuses it before anything is created.
    #[test]
    fn socket_dir_refuses_symlinked_root() {
        let dir = scratch();
        let elsewhere = dir.join("elsewhere");
        std::fs::create_dir(&elsewhere).unwrap();
        let root = dir.join("root");
        std::os::unix::fs::symlink(&elsewhere, &root).unwrap();

        assert!(ensure_socket_dir_in(&root, "probe").is_err());
        assert!(!elsewhere.join("probe").exists());
        std::fs::remove_dir_all(&dir).ok();
    }

    /// Names that are not a plain agent ident are refused by validation,
    /// before anything is created. Runs against a scratch parent, so the
    /// refusal cannot come from a missing `/run/hive-agent`; `.`/`..` exist
    /// as directories and `Atlas` would be created, so each bad name gets
    /// through only if validation is gone. Control: a plain name succeeds
    /// in the same parent.
    #[test]
    fn socket_dir_refuses_bogus_names() {
        let dir = scratch();
        for bad in ["", ".", "..", "../etc", "a/b", "Atlas", "a b", "a\0b"] {
            let err = ensure_socket_dir_in(&dir, bad).unwrap_err();
            assert!(
                format!("{err:#}").contains("invalid name"),
                "agent name {bad:?} must be refused by validation, got: {err:#}"
            );
        }
        assert_eq!(std::fs::read_dir(&dir).unwrap().count(), 0);
        ensure_socket_dir_in(&dir, "atlas").unwrap();
        assert!(dir.join("atlas").is_dir());
        std::fs::remove_dir_all(&dir).ok();
    }

    /// The pause marker round-trips through the same root-only path the
    /// credential writes use, and BOTH directions are idempotent — the
    /// dashboard toggle and `hivectl pause|resume` fire blind, without
    /// reading the current state first.
    #[test]
    fn pause_marker_create_and_remove_are_idempotent() {
        let dir = scratch();
        let path = dir.join(PAUSED_MARKER_FILE);

        for _ in 0..2 {
            write_agent_dir_file("a", &dir, PAUSED_MARKER_FILE, "").unwrap();
            assert!(path.exists(), "marker must exist after pause");
            assert_eq!(std::fs::read_to_string(&path).unwrap(), "");
        }
        for _ in 0..2 {
            remove_marker_in(&dir, PAUSED_MARKER_FILE).unwrap();
            assert!(!path.exists(), "marker must be gone after resume");
        }
        std::fs::remove_dir_all(&dir).ok();
    }

    /// A resume must never follow an agent-planted symlink at the marker
    /// path: this unlink runs as root, so following it would let an agent
    /// delete an arbitrary file on the host.
    #[test]
    fn resume_unlinks_the_symlink_not_its_target() {
        let dir = scratch();
        let target = dir.join("target");
        std::fs::write(&target, "original").unwrap();
        let link = dir.join(PAUSED_MARKER_FILE);
        std::os::unix::fs::symlink(&target, &link).unwrap();

        remove_marker_in(&dir, PAUSED_MARKER_FILE).unwrap();
        // `exists()` follows the link, so it can't tell "link removed" from
        // "target removed, dangling link left" — stat the link itself.
        assert!(
            std::fs::symlink_metadata(&link).is_err(),
            "the link itself must be unlinked"
        );
        assert_eq!(
            std::fs::read_to_string(&target).unwrap(),
            "original",
            "symlink target must survive the root unlink"
        );
        std::fs::remove_dir_all(&dir).ok();
    }
}