diff --git a/docs/plans/DEFERRED.md b/docs/plans/DEFERRED.md index 197a29ecb..7945a6829 100644 --- a/docs/plans/DEFERRED.md +++ b/docs/plans/DEFERRED.md @@ -319,6 +319,10 @@ at every gate. Started 2026-09-12 during the control board MVP. waits 30 s before it calls a lone `sleep 30` a leak. The row 197 lanes scan only at lane end, about 15 minutes after pkg-bus, so they can't see it (mos-1169). (2026-10-21) + Closing note, row 280 (2026-10-22): both scratch sshd fixtures install a + bounded 30/60-second sleep stub that exits when its test directory is gone; + other sleep arguments exec /usr/bin/sleep unchanged. Evidence is recorded + in agents/rocko/work/queue-280/BUILD.md. - **Row 66 live checks: the unslop notice on a live managed session, both harnesses.** (mos-1186, Vikunja #454.) Row 66's gate asked for one landing session per diff --git a/packages/bus/tests/grant-executor.test.mjs b/packages/bus/tests/grant-executor.test.mjs index 1992f1525..b27d91dc4 100644 --- a/packages/bus/tests/grant-executor.test.mjs +++ b/packages/bus/tests/grant-executor.test.mjs @@ -6,9 +6,9 @@ // reaches another host. import test from 'node:test'; import assert from 'node:assert/strict'; -import { execFileSync, spawn } from 'node:child_process'; +import { execFileSync } from 'node:child_process'; import { createHash } from 'node:crypto'; -import { connect } from 'node:net'; +import { createServer } from 'node:net'; import { appendFileSync, chmodSync, existsSync, mkdirSync, mkdtempSync, readFileSync, rmSync, statSync, writeFileSync } from 'node:fs'; import { tmpdir, userInfo } from 'node:os'; import { join } from 'node:path'; @@ -19,6 +19,8 @@ import { hostExecutor, runHost } from '../src/host-run.mjs'; import { Store } from '../src/store.mjs'; import { grantDecision, hostRecord } from './host-fixtures.mjs'; +import { ephemeralRange, installSleepStub, pickPort, startScratchSshd } from './scratch-sshd.mjs'; + const SSHD = '/usr/bin/sshd'; const USER = userInfo().username; const AT = '2026-10-21T00:00:00.000Z'; @@ -35,12 +37,7 @@ const DEFINITIONS = { pm: { roleVersion: 2, credentials: [] }, ops: { roleVersion: 2, credentials: [{ service: 'host' }] }, }; -const listening = (port) => - new Promise((resolve) => { - const s = connect(port, '127.0.0.1'); - s.on('connect', () => (s.destroy(), resolve(true))); - s.on('error', () => resolve(false)); - }); + async function until(fn, ms = 10000) { const end = Date.now() + ms; while (!fn()) { @@ -54,12 +51,13 @@ async function until(fn, ms = 10000) { // Both also stop when the test dir is gone, since a held stub on the sshd side outlives its test (#1750). // wrap.sh logs every request. The sudo stub logs its arguments to sudo.log and runs the command as the // test's user. -async function sshd(t, dir) { +async function sshd(t, dir, options) { if (!existsSync(SSHD)) throw new Error(`${SSHD} is missing: the executor tests need it and fail, never skip`); keygen(join(dir, 'hostkey')); keygen(join(dir, 'installer')); writeFileSync(join(dir, 'authorized_keys'), readFileSync(join(dir, 'installer.pub')), { mode: 0o600 }); mkdirSync(join(dir, 'fake')); + installSleepStub(dir); const stub = (name, body) => writeFileSync(join(dir, 'fake', name), `#!/bin/sh\nD='${dir}'\n${body}\n`, { mode: 0o755 }); stub('list', '[ -e "$D/fail-list" ] && exit 1\n[ -e "$D/granted" ] && grep " mosaic-[0-9a-f]*$" "$D/granted"\nexit 0'); stub( @@ -76,26 +74,42 @@ async function sshd(t, dir) { `#!/bin/sh\nprintf '%s\\n' "$SSH_ORIGINAL_COMMAND" >> '${dir}/requests.log'\nPATH=${dir}/fake:/usr/bin:/bin; export PATH\nexec /bin/sh -c "$SSH_ORIGINAL_COMMAND"\n`, { mode: 0o755 }, ); - for (let attempt = 0; attempt < 5; attempt++) { - const port = 20000 + Math.floor(Math.random() * 20000); - writeFileSync( - join(dir, 'sshd_config'), - [`Port ${port}`, 'ListenAddress 127.0.0.1', `HostKey ${dir}/hostkey`, `AuthorizedKeysFile ${dir}/authorized_keys ${dir}/granted`, - `PidFile ${dir}/sshd.pid`, 'UsePAM no', 'StrictModes no', 'PasswordAuthentication no', 'KbdInteractiveAuthentication no', - `ForceCommand ${dir}/wrap.sh`, ''].join('\n'), - ); - const daemon = spawn(SSHD, ['-D', '-f', join(dir, 'sshd_config'), '-E', join(dir, 'sshd.log')], { stdio: 'ignore' }); - t.after(() => daemon.kill('SIGKILL')); - const deadline = Date.now() + 3000; - while (Date.now() < deadline && daemon.exitCode === null) { - if (await listening(port)) return port; - await sleep(30); - } - daemon.kill('SIGKILL'); - } - throw new Error('scratch sshd did not start'); + return startScratchSshd(t, dir, [ + 'ListenAddress 127.0.0.1', `HostKey ${dir}/hostkey`, + `AuthorizedKeysFile ${dir}/authorized_keys ${dir}/granted`, `PidFile ${dir}/sshd.pid`, + 'UsePAM no', 'StrictModes no', 'PasswordAuthentication no', 'KbdInteractiveAuthentication no', + `ForceCommand ${dir}/wrap.sh`, + ], options); } + +test('row 280: an occupied TCP port is attempted, refused, and retried with our sshd', async t => { + const dir = mkdtempSync(join(tmpdir(), 'sshd280-')); + t.after(() => rmSync(dir, { recursive: true, force: true })); + const server = createServer(socket => socket.end()); + await new Promise((resolve, reject) => { + server.once('error', reject); + server.listen(0, '127.0.0.1', resolve); + }); + t.after(() => new Promise(resolve => server.close(resolve))); + const occupied = server.address().port; + const port = await sshd(t, dir, { firstPort: occupied }); + assert.match(readFileSync(join(dir, 'sshd-0.conf'), 'utf8'), new RegExp(`^Port ${occupied}\\n`)); + assert.equal(readFileSync(join(dir, 'sshd-0.log'), 'utf8').includes(`Server listening on 127.0.0.1 port ${occupied}.`), false); + assert.notEqual(port, occupied); + assert.ok([1, 2, 3, 4].some(n => existsSync(join(dir, `sshd-${n}.log`)) && + readFileSync(join(dir, `sshd-${n}.log`), 'utf8').includes(`Server listening on 127.0.0.1 port ${port}.`))); +}); + +test('row 280: every injected picker sample is unprivileged and outside the ephemeral range', () => { + const [lo, hi] = ephemeralRange(); + for (const sample of [0, 0.25, 0.5, 0.6384, 0.75, 0.999999]) { + const port = pickPort(() => sample); + assert.ok(port >= 1024 && port <= 65535); + assert.ok(port < lo || port > hi, `sample ${sample}: ${port} inside ${lo}-${hi}`); + } +}); + async function setup(t, opts = {}) { const dir = mkdtempSync(join(tmpdir(), 'g235x-')); t.after(() => rmSync(dir, { recursive: true, force: true })); diff --git a/packages/bus/tests/host-run.test.mjs b/packages/bus/tests/host-run.test.mjs index 6f5949b5c..f7eebd45e 100644 --- a/packages/bus/tests/host-run.test.mjs +++ b/packages/bus/tests/host-run.test.mjs @@ -4,7 +4,7 @@ import test from 'node:test'; import assert from 'node:assert/strict'; import { execFileSync, spawn } from 'node:child_process'; -import { connect, createServer } from 'node:net'; +import { createServer } from 'node:net'; import { chmodSync, existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, rmSync, writeFileSync } from 'node:fs'; import { tmpdir, userInfo } from 'node:os'; import { join } from 'node:path'; @@ -19,6 +19,8 @@ import { hostGrant } from '../src/host-grant.mjs'; import { startBroker } from '../src/runtime.mjs'; import { businessDoc, rolesCopy, systemFor, writeJson } from '../../business/tests/helpers.mjs'; +import { ephemeralRange, installSleepStub, pickPort, startScratchSshd } from './scratch-sshd.mjs'; + const SSHD = '/usr/bin/sshd'; const REPO = fileURLToPath(new URL('../../../', import.meta.url)); const USER = userInfo().username; @@ -50,22 +52,18 @@ async function until(fn, ms = 5000) { } return true; } -const listening = (port) => - new Promise((resolve) => { - const s = connect(port, '127.0.0.1'); - s.on('connect', () => (s.destroy(), resolve(true))); - s.on('error', () => resolve(false)); - }); + // A scratch sshd. ForceCommand puts the fake sudo first on PATH and hands the command to /bin/sh, so // the remote side parses the command line the way a real host's POSIX shell does. -async function sshd(t, dir) { +async function sshd(t, dir, options) { if (!existsSync(SSHD)) throw new Error(`${SSHD} is missing: the executor tests need it and fail, never skip`); keygen(join(dir, 'hostkey')); keygen(join(dir, 'otherhost')); keygen(join(dir, 'user')); writeFileSync(join(dir, 'authorized_keys'), readFileSync(join(dir, 'user.pub')), { mode: 0o600 }); mkdirSync(join(dir, 'fake')); + installSleepStub(dir); writeFileSync( join(dir, 'fake', 'sudo'), `#!/bin/sh\n'${process.execPath}' -e 'require("fs").appendFileSync(process.argv[1], JSON.stringify(process.argv.slice(2)) + "\\n")' '${dir}/argv.json' "$@"\nshift 2\nexec "$@"\n`, @@ -75,26 +73,42 @@ async function sshd(t, dir) { writeFileSync(join(dir, 'fake', 'fail255'), '#!/bin/sh\necho "Host key verification failed." >&2\nexit 255\n', { mode: 0o755 }); writeFileSync(join(dir, 'wrap.sh'), `#!/bin/sh\nPATH=${dir}/fake:/usr/bin:/bin; export PATH\nexec /bin/sh -c "$SSH_ORIGINAL_COMMAND"\n`); chmodSync(join(dir, 'wrap.sh'), 0o755); - for (let attempt = 0; attempt < 5; attempt++) { - const port = 20000 + Math.floor(Math.random() * 20000); - writeFileSync( - join(dir, 'sshd_config'), - [`Port ${port}`, 'ListenAddress 127.0.0.1', `HostKey ${dir}/hostkey`, `AuthorizedKeysFile ${dir}/authorized_keys`, - `PidFile ${dir}/sshd.pid`, 'UsePAM no', 'StrictModes no', 'PasswordAuthentication no', 'KbdInteractiveAuthentication no', - `ForceCommand ${dir}/wrap.sh`, ''].join('\n'), - ); - const daemon = spawn(SSHD, ['-D', '-f', join(dir, 'sshd_config'), '-E', join(dir, 'sshd.log')], { stdio: 'ignore' }); - t.after(() => daemon.kill('SIGKILL')); - const deadline = Date.now() + 3000; - while (Date.now() < deadline && daemon.exitCode === null) { - if (await listening(port)) return port; - await sleep(30); - } - daemon.kill('SIGKILL'); - } - throw new Error('scratch sshd did not start'); + return startScratchSshd(t, dir, [ + 'ListenAddress 127.0.0.1', `HostKey ${dir}/hostkey`, + `AuthorizedKeysFile ${dir}/authorized_keys`, `PidFile ${dir}/sshd.pid`, + 'UsePAM no', 'StrictModes no', 'PasswordAuthentication no', 'KbdInteractiveAuthentication no', + `ForceCommand ${dir}/wrap.sh`, + ], options); } + +test('row 280: an occupied TCP port is attempted, refused, and retried with our sshd', async t => { + const dir = mkdtempSync(join(tmpdir(), 'sshd280-')); + t.after(() => rmSync(dir, { recursive: true, force: true })); + const server = createServer(socket => socket.end()); + await new Promise((resolve, reject) => { + server.once('error', reject); + server.listen(0, '127.0.0.1', resolve); + }); + t.after(() => new Promise(resolve => server.close(resolve))); + const occupied = server.address().port; + const port = await sshd(t, dir, { firstPort: occupied }); + assert.match(readFileSync(join(dir, 'sshd-0.conf'), 'utf8'), new RegExp(`^Port ${occupied}\\n`)); + assert.equal(readFileSync(join(dir, 'sshd-0.log'), 'utf8').includes(`Server listening on 127.0.0.1 port ${occupied}.`), false); + assert.notEqual(port, occupied); + assert.ok([1, 2, 3, 4].some(n => existsSync(join(dir, `sshd-${n}.log`)) && + readFileSync(join(dir, `sshd-${n}.log`), 'utf8').includes(`Server listening on 127.0.0.1 port ${port}.`))); +}); + +test('row 280: every injected picker sample is unprivileged and outside the ephemeral range', () => { + const [lo, hi] = ephemeralRange(); + for (const sample of [0, 0.25, 0.5, 0.6384, 0.75, 0.999999]) { + const port = pickPort(() => sample); + assert.ok(port >= 1024 && port <= 65535); + assert.ok(port < lo || port > hi, `sample ${sample}: ${port} inside ${lo}-${hi}`); + } +}); + const GRANT = [['true'], ['false'], ['echo'], ['sleep'], ['head'], ['cat'], ['systemctl', 'status']]; async function hostFixture(t, { commands = GRANT, reviewerHosts, wrongHostKey = false, coderWeb2 = false } = {}) { const dir = mkdtempSync(join(tmpdir(), 'h210-')); diff --git a/packages/bus/tests/scratch-sshd.mjs b/packages/bus/tests/scratch-sshd.mjs new file mode 100644 index 000000000..2dde26de3 --- /dev/null +++ b/packages/bus/tests/scratch-sshd.mjs @@ -0,0 +1,88 @@ +// Row 280: fixture-only sshd startup. A TCP connect alone does not prove ownership. +import { spawn } from 'node:child_process'; +import { once } from 'node:events'; +import { mkdirSync, readFileSync, writeFileSync } from 'node:fs'; +import { connect } from 'node:net'; +import { basename, join } from 'node:path'; + +export const ephemeralRange = () => { + const text = readFileSync('/proc/sys/net/ipv4/ip_local_port_range', 'utf8').trim(); + if (!/^\d+\s+\d+$/.test(text)) throw Error('invalid ephemeral port range'); + const range = text.split(/\s+/).map(Number); + if (range[0] < 1 || range[1] > 65535 || range[0] > range[1]) throw Error('invalid ephemeral port range'); + return range; +}; + +export function pickPort(rand = Math.random) { + const [lo, hi] = ephemeralRange(); + const below = Math.max(0, Math.min(lo, 65536) - 1024); + const above = Math.max(0, 65535 - Math.max(hi, 1023)); + const sample = rand(); + if (!below && !above) throw Error('no scratch sshd port available'); + if (!(sample >= 0 && sample < 1)) throw Error('invalid random sample'); + const offset = Math.floor(sample * (below + above)); + return offset < below ? 1024 + offset : Math.max(hi + 1, 1024) + offset - below; +} + +const sleep = ms => new Promise(resolve => setTimeout(resolve, ms)); +const listening = port => new Promise(resolve => { + const socket = connect(port, '127.0.0.1'); + const done = result => { socket.destroy(); resolve(result); }; + socket.setTimeout(200, () => done(false)); + socket.on('connect', () => done(true)); + socket.on('error', () => done(false)); +}); +const stop = async daemon => { + if (daemon.pid === undefined || daemon.exitCode !== null || daemon.signalCode !== null) return; + const exited = once(daemon, 'exit'); + daemon.kill('SIGKILL'); + await exited; +}; + +export async function startScratchSshd(t, dir, config, { firstPort } = {}) { + let lastLog; + for (let attempt = 0; attempt < 5; attempt++) { + const port = attempt === 0 && firstPort !== undefined ? firstPort : pickPort(); + const configFile = join(dir, `sshd-${attempt}.conf`); + lastLog = join(dir, `sshd-${attempt}.log`); + writeFileSync(configFile, [`Port ${port}`, ...config, ''].join('\n')); + writeFileSync(lastLog, ''); + const daemon = spawn('/usr/bin/sshd', ['-D', '-f', configFile, '-E', lastLog], { stdio: 'ignore' }); + t.after(() => stop(daemon)); + const saveLog = () => { + if (!process.env.MOSAIC_SSHD_EVIDENCE) return; + const evidence = join(process.env.MOSAIC_SSHD_EVIDENCE, basename(dir)); + mkdirSync(evidence, { recursive: true }); + writeFileSync(join(evidence, basename(lastLog)), readFileSync(lastLog)); + writeFileSync(join(evidence, basename(configFile)), readFileSync(configFile)); + }; + let spawnError; + daemon.on('error', error => { spawnError = error; }); + const deadline = Date.now() + 3000; + while (Date.now() < deadline && !spawnError && daemon.exitCode === null && daemon.signalCode === null) { + if (await listening(port) && daemon.exitCode === null && daemon.signalCode === null && + readFileSync(lastLog, 'utf8').split('\n').some(line => + (line === `Server listening on 127.0.0.1 port ${port}.` || + line === `Server listening on 127.0.0.1 port ${port}.\r`))) { saveLog(); return port; } + await sleep(30); + } + await stop(daemon); + saveLog(); + } + throw Error(`scratch sshd did not start: ${lastLog}`); +} + +// Long remote sleeps remain in flight for their original duration, but cannot outlive the fixture. +export function installSleepStub(dir) { + const script = `const fs = require("node:fs"); +const end = Date.now() + Number(process.argv[2]) * 1000; +const timer = setInterval(() => { + if (!fs.existsSync(process.argv[1]) || Date.now() >= end) { clearInterval(timer); } +}, 50);`; + writeFileSync(join(dir, 'fake', 'sleep'), `#!/bin/sh +case "$#:$1" in + 1:30|1:60) exec '${process.execPath}' -e '${script}' '${dir}' "$1" ;; + *) exec /usr/bin/sleep "$@" ;; +esac +`, { mode: 0o755 }); +}