stack/packages/seat/src/checkout.mjs

// The project checkouts in a role workspace (#1585). At every launch the
// bus host makes sure each project of the business file has a git clone at
// `<workspace>/<project id>/`, before it builds the bundle. The host runs
// git here, outside the session's sandbox:
//
//   no clone yet        `git clone --no-hardlinks` of the project's root, at
//                       the branch the root has checked out, into a temp
//                       directory beside it and then renamed into place; a
//                       clone that fails is removed and refuses the launch
//   a clean clone on    fetched from its origin and fast-forwarded
//   the root's branch
//   a clone on another  fetched from its origin and not merged: only
//   branch, or dirty    refs/remotes moves, with the reason (#1611)
//   anything else       left exactly as it is, with the reason
//
// The host never resets, cleans, deletes or force-updates a clone, and
// never writes the root. A clone's origin is the root's path; no credential
// or forge remote goes into it.
//
// The session can write its clone, so the host treats every clone as
// hostile. A git config key, a hook or a redirected .git would otherwise
// run a command or write a file outside the sandbox when the host runs git
// there. So every git call gets an environment without the system and
// global config, hooks pointed at /dev/null, fsmonitor off and only local
// transports. And before git runs in an existing clone, the host checks
// that the clone and its .git are real directories, that nothing under
// .git is a symlink, a special file or a file with a second hard link,
// that no commondir or alternates file sends git elsewhere, that
// .git/hooks is empty, and that .git/config is a small regular file
// holding only what a clone writes (allowed() below). A clone that fails a
// check is kept, and git doesn't run in it.
//
// Those checks cover the clone's own .git and nothing else. A submodule
// has its own config, which can name a filter driver, and git status
// recurses into a populated submodule by running a second git in it. So
// a clone with a gitlink in its index or anything under .git/modules is
// kept too, and no host git recurses into a submodule: status ignores
// them and submodule.recurse is off for every call.
//
// The checks hold only while nothing else writes the clone. The launcher
// calls this for an instance only when no session of that instance runs
// (its instance-running refusal), and each workspace is one instance's.

import { spawn } from "node:child_process";
import { randomBytes } from "node:crypto";
import { lstatSync, readdirSync, renameSync, rmSync } from "node:fs";
import { dirname, join } from "node:path";

export const GIT_TIMEOUT_MS = 100_000;
// How long a git has after SIGTERM before SIGKILL.
export const GIT_GRACE_MS = 5000;
export const GIT_LIMITS = Object.freeze({ timeoutMs: GIT_TIMEOUT_MS, graceMs: GIT_GRACE_MS });
// A clone's config is a few hundred bytes, a little more per branch.
export const CONFIG_MAX_BYTES = 64 * 1024;

export class CheckoutError extends Error {
  constructor(project, message) {
    super(message);
    this.project = project;
  }
}

// Ahead of every git subcommand. Command-line config wins over any file.
const SAFE = [
  "-c", "core.hooksPath=/dev/null",
  "-c", "core.fsmonitor=false",
  "-c", "protocol.allow=never",
  "-c", "protocol.file.allow=always",
  "-c", "submodule.recurse=false",
];

// The environment git runs with: the host's PATH and nothing else of it.
// HOME doesn't exist, so no user file (attributes, ignore) is read either.
export function gitEnv(env = process.env) {
  return {
    PATH: env.PATH ?? "/usr/bin:/bin",
    HOME: "/nonexistent",
    GIT_CONFIG_NOSYSTEM: "1",
    GIT_CONFIG_GLOBAL: "/dev/null",
    GIT_TERMINAL_PROMPT: "0",
    GIT_MERGE_AUTOEDIT: "no",
    LC_ALL: "C",
  };
}

// runGit(argv, env, limits) runs git with exactly `argv` and `env`, and
// resolves { ok, out, err, why }; working.mjs runs its git through it too.
// Async, so a long clone doesn't hold up the rest of the bus host.
//
// git runs as the leader of its own process group (detached), so a timeout
// reaches what git started as well: SIGTERM to the group at
// limits.timeoutMs, on which git removes its lockfiles, then SIGKILL to the
// group limits.graceMs later. Once a git that was signalled has closed, the
// group gets SIGKILL again, for a process that ignored SIGTERM and let go of
// git's output. A git that ends on its own isn't signalled at all. One
// consequence: a Ctrl-C at the terminal of a host run by hand no longer
// reaches its git, though a systemd stop still does (it kills the cgroup).
export function runGit(argv, env, limits = GIT_LIMITS) {
  return new Promise((resolve) => {
    const child = spawn("git", argv, { env, detached: true, stdio: ["ignore", "pipe", "pipe"] });
    let out = "";
    let err = "";
    let signalled = false;
    let kill = null;
    // A git that never started has no pid; an empty group is ESRCH. Neither
    // leaves anything to signal.
    const group = (signal) => {
      try {
        process.kill(-child.pid, signal);
      } catch {}
    };
    const term = setTimeout(() => {
      signalled = true;
      group("SIGTERM");
      kill = setTimeout(() => group("SIGKILL"), limits.graceMs);
    }, limits.timeoutMs);
    const settle = (r) => {
      clearTimeout(term);
      clearTimeout(kill);
      if (signalled) group("SIGKILL");
      resolve(r);
    };
    child.stdout.setEncoding("utf8").on("data", (d) => (out += d));
    child.stderr.setEncoding("utf8").on("data", (d) => (err += d));
    // A git that can't start may not emit close, so error settles it too.
    child.on("error", (e) => settle({ ok: false, out, err, why: e.code ?? e.message }));
    child.on("close", (code, signal) => settle({ ok: code === 0, out, err, why: signal ? `killed by ${signal}` : err.trim().split("\n").pop() || `exit ${code}` }));
  });
}

// git in a clone or a root, with SAFE first. `limits` is for the tests.
const git = (args, env, extra = {}, limits = GIT_LIMITS) => runGit([...SAFE, ...args], { ...gitEnv(env), ...extra }, limits);

const inClone = (dest) => [`--git-dir=${join(dest, ".git")}`, `--work-tree=${dest}`];

// The keys `git clone` writes, and what each may hold. branch.<name>.remote
// and .merge are the ones `git checkout -b`, `git branch -u` and the like
// add. Every other key keeps the clone.
const FETCH = "+refs/heads/*:refs/remotes/origin/*";
function allowed(key, value, root) {
  const branch = /^branch\..+\.(remote|merge)$/.exec(key);
  if (branch) return branch[1] === "remote" ? value === "origin" : /^refs\/heads\/./.test(value ?? "");
  switch (key) {
    case "core.repositoryformatversion": return value === "0";
    case "core.filemode": return value === "true" || value === "false";
    case "core.bare": return value === "false";
    case "core.logallrefupdates": return value === "true";
    case "remote.origin.url": return value === root;
    case "remote.origin.fetch": return value === FETCH;
    default: return false;
  }
}

// Why the clone at `dest` isn't safe for the host to run git in, or null.
async function unsafe(dest, root, g) {
  const isDir = (p) => {
    try {
      return lstatSync(p).isDirectory();
    } catch {
      return false;
    }
  };
  if (!isDir(dest) || !isDir(join(dest, ".git"))) return "not-a-clone";
  // A second hard link would let a host write through to a file outside.
  const walk = (dir) => {
    for (const name of readdirSync(dir)) {
      const st = lstatSync(join(dir, name));
      if (st.isDirectory()) {
        if (walk(join(dir, name))) return true;
      } else if (!st.isFile() || st.nlink !== 1) return true;
    }
    return false;
  };
  try {
    if (walk(join(dest, ".git"))) return "not-a-clone";
  } catch {
    return "not-a-clone";
  }
  // A clone never has .git/modules; `git submodule` in the session makes one.
  try {
    lstatSync(join(dest, ".git", "modules"));
    return "submodule";
  } catch {}
  for (const f of ["commondir", join("objects", "info", "alternates")]) {
    try {
      lstatSync(join(dest, ".git", f));
      return "not-a-clone";
    } catch {}
  }
  try {
    if (readdirSync(join(dest, ".git", "hooks")).length > 0) return "hooks-present";
  } catch (e) {
    if (e.code !== "ENOENT") return "not-a-clone";
  }
  try {
    const st = lstatSync(join(dest, ".git", "config"));
    if (!st.isFile() || st.size > CONFIG_MAX_BYTES) return "config-changed";
  } catch {
    return "config-changed";
  }
  const list = await g(["config", "--file", join(dest, ".git", "config"), "--list", "--null"]);
  if (!list.ok) return "config-changed";
  const seen = new Set();
  for (const entry of list.out.split("\0").filter(Boolean)) {
    const nl = entry.indexOf("\n");
    const [key, value] = nl < 0 ? [entry, null] : [entry.slice(0, nl), entry.slice(nl + 1)];
    if (seen.has(key) || !allowed(key, value, root)) return "config-changed";
    seen.add(key);
  }
  if (!seen.has("remote.origin.url")) return "config-changed";
  return null;
}

// The branch the root has checked out, null when it has none, or an error.
// The ceiling stops git finding a repository above a root that isn't one.
async function rootBranch(root, g) {
  const ceiling = { GIT_CEILING_DIRECTORIES: dirname(root) };
  const r = await g(["-C", root, "symbolic-ref", "-q", "--short", "HEAD"], ceiling);
  if (r.ok) return { branch: r.out.trim() };
  // symbolic-ref -q exits 1 with no output on a detached HEAD.
  const head = await g(["-C", root, "rev-parse", "--verify", "-q", "HEAD"], ceiling);
  return head.ok ? { branch: null } : { error: r.why };
}

async function clone(project, root, workspace, dest, g) {
  const at = await rootBranch(root, g);
  if (at.error) throw new CheckoutError(project, `the root ${root} can't be read: ${at.error}`);
  if (!at.branch) throw new CheckoutError(project, `the root ${root} has no branch checked out`);
  // A project id never starts with a dot, so the temp name is no project's.
  const tmp = join(workspace, `.${project}.clone-${randomBytes(4).toString("hex")}`);
  let commit;
  try {
    const r = await g(["clone", "-q", "--no-hardlinks", "--template=", "--branch", at.branch, "--", root, tmp]);
    if (!r.ok) throw new CheckoutError(project, `git clone of ${root} failed: ${r.why}`);
    const head = await g([...inClone(tmp), "rev-parse", "--verify", "HEAD"]);
    if (!head.ok) throw new CheckoutError(project, `the new clone of ${root} has no readable HEAD: ${head.why}`);
    commit = head.out.trim();
    renameSync(tmp, dest);
  } catch (e) {
    rmSync(tmp, { recursive: true, force: true });
    if (e instanceof CheckoutError) throw e;
    throw new CheckoutError(project, `the clone of ${root} couldn't be put in place: ${e.message}`);
  }
  return { outcome: "cloned", branch: at.branch, commit };
}

async function update(root, dest, g) {
  const problem = await unsafe(dest, root, g);
  if (problem) return { outcome: "kept", reason: problem };
  // ls-files reads only the index: no filter, hook or submodule runs.
  const staged = await g([...inClone(dest), "ls-files", "--stage", "-z"]);
  if (!staged.ok) return { outcome: "kept", reason: "status-failed" };
  if (staged.out.split("\0").some((e) => e.startsWith("160000 "))) return { outcome: "kept", reason: "submodule" };
  const at = await rootBranch(root, g);
  if (at.error) return { outcome: "kept", reason: "root-unreadable" };
  if (!at.branch) return { outcome: "kept", reason: "root-detached" };
  // Row 117 (#1611): a clone on another branch, or dirty, still gets the
  // fetch, so origin/<branch> is the root's at every launch. Only the merge
  // is left out. symbolic-ref -q fails on a detached HEAD: branch null.
  const head = await g([...inClone(dest), "symbolic-ref", "-q", "--short", "HEAD"]);
  const branch = head.ok ? head.out.trim() : null;
  let reason = null;
  if (branch !== at.branch) reason = "other-branch";
  else {
    const status = await g(["--no-optional-locks", ...inClone(dest), "status", "--porcelain=v1", "-z", "--untracked-files=all", "--ignore-submodules=all"]);
    if (!status.ok) return { outcome: "kept", reason: "status-failed" };
    if (status.out !== "") reason = "dirty";
  }
  const first = await g([...inClone(dest), "rev-parse", "HEAD"]);
  const before = first.ok ? first.out.trim() : null;
  if (!(await g([...inClone(dest), "fetch", "-q", "--no-tags", "--no-recurse-submodules", "origin"])).ok) return { outcome: "kept", reason: "fetch-failed" };
  if (reason) {
    const origin = await g([...inClone(dest), "rev-parse", "--verify", "-q", `refs/remotes/origin/${at.branch}`]);
    return { outcome: "fetched", reason, branch, commit: before, origin: { branch: at.branch, commit: origin.ok ? origin.out.trim() : null } };
  }
  if (!(await g([...inClone(dest), "merge", "-q", "--ff-only", "--no-edit", `refs/remotes/origin/${at.branch}`])).ok) return { outcome: "kept", reason: "not-fast-forward" };
  const read = await g([...inClone(dest), "rev-parse", "HEAD"]);
  const after = read.out.trim();
  return { outcome: before === after ? "current" : "updated", branch: at.branch, commit: read.ok ? after : null };
}

// await ensureCheckouts({ workspace, projects, env, limits }) for the
// business file's projects ({ <id>: { root } }). Returns one { project,
// path, outcome, reason?, branch?, commit?, origin? } per project, outcome
// cloned, updated, current, fetched or kept. branch and commit are the
// clone's after this launch (commit null when git couldn't read it). A
// fetched clone also has a reason (other-branch or dirty), branch null when
// its HEAD is detached, and origin { branch, commit }: the root's branch and
// refs/remotes/origin/<branch> after the fetch, commit null when unreadable.
// A kept clone has only a reason, since git may not be safe to run there.
// Rejects with CheckoutError when a missing clone can't be made. `limits`
// ({ timeoutMs, graceMs }) is for the tests.
export async function ensureCheckouts({ workspace, projects, env = process.env, limits = GIT_LIMITS }) {
  const g = (args, extra) => git(args, env, extra, limits);
  const out = [];
  for (const [project, { root }] of Object.entries(projects)) {
    const dest = join(workspace, project);
    let exists = true;
    try {
      lstatSync(dest);
    } catch (e) {
      if (e.code !== "ENOENT") throw new CheckoutError(project, `${dest} can't be read: ${e.code}`);
      exists = false;
    }
    out.push({ project, path: dest, ...(exists ? await update(root, dest, g) : await clone(project, root, workspace, dest, g)) });
  }
  return out;
}