Skip to content
Sign up

flagon-io/g1t

public
0
1,633 linesCodeBlameRaw
1//! Git over HTTPS: the smart HTTP remote at `/<namespace>/<repo>.git`,
2//! proxied to the git store with a short-lived token.
3
4use std::cell::RefCell;
5use std::rc::Rc;
6
7use futures_util::StreamExt;
8use g1t_contracts::identity::GitCredentialsArgs;
9use g1t_contracts::repos::{GitAccess, GitService, RepoPath};
10use g1t_contracts::{FailureCode, Outcome, Viewer};
11use worker::js_sys::Uint8Array;
12use worker::wasm_bindgen::JsValue;
13use worker::{Fetch, Fetcher, Headers, Method, Request, RequestInit, Response, Result, Url};
14
15use crate::meters;
16use crate::pack_limits::{PackSizer, Violation};
17use crate::push_checks::{Checks, Verdict};
18use crate::resilience::{self, Busy, Failure};
19
20const ENDPOINTS: [&str; 3] = ["info/refs", "git-upload-pack", "git-receive-pack"];
21const FORWARDED_HEADERS: [&str; 5] = [
22 "accept",
23 "content-encoding",
24 "content-type",
25 "git-protocol",
26 "user-agent",
27];
28
29/// A git request, parsed from its URL.
30pub struct GitRequest {
31 pub path: RepoPath,
32 pub endpoint: &'static str,
33 pub service: GitService,
34}
35
36impl GitRequest {
37 /// The same request for the repository of the same name under
38 /// `namespace`: where a workspace alias leads.
39 pub fn under(&self, namespace: &str) -> GitRequest {
40 GitRequest {
41 path: RepoPath {
42 namespace: namespace.to_owned(),
43 name: self.path.name.clone(),
44 },
45 endpoint: self.endpoint,
46 service: self.service,
47 }
48 }
49}
50
51/// Parses `/<namespace>/<name>[.git]/<endpoint>`, or returns `None` if the
52/// request is not git's.
53pub fn parse(url: &Url) -> Option<GitRequest> {
54 let path = url.path().strip_prefix('/')?;
55 let endpoint = ENDPOINTS
56 .into_iter()
57 .find(|endpoint| path.ends_with(&format!("/{endpoint}")))?;
58 let repo = &path[..path.len() - endpoint.len() - 1];
59 let (namespace, name) = repo.split_once('/')?;
60 let name = name.strip_suffix(".git").unwrap_or(name);
61 if namespace.is_empty() || name.is_empty() || name.contains('/') {
62 return None;
63 }
64 let service = if endpoint == "info/refs" {
65 url.query_pairs()
66 .find(|(key, _)| key == "service")
67 .map(|(_, value)| value.into_owned())?
68 } else {
69 endpoint.to_owned()
70 };
71 let service = match service.as_str() {
72 "git-upload-pack" => GitService::UploadPack,
73 "git-receive-pack" => GitService::ReceivePack,
74 _ => return None,
75 };
76 Some(GitRequest {
77 path: RepoPath {
78 namespace: namespace.to_owned(),
79 name: name.to_owned(),
80 },
81 endpoint,
82 service,
83 })
84}
85
86/// How long each step of a git request took, sent back to git as a
87/// `Server-Timing` header so that a slow clone shows where its time went.
88/// Step names and whole milliseconds only. The Workers clock moves only
89/// while a request waits on something, so each step is the time spent
90/// waiting on the database, another service or the git store. A note
91/// says how a step went without a duration: `refs;desc=hit-colo`. A part
92/// is one of several things a step did at once, with its own duration: a
93/// push's `checks` step is its `read`, `rules` and `scan` parts side by side.
94pub struct Timing {
95 started: u64,
96 last: u64,
97 steps: Vec<(&'static str, u64)>,
98 parts: Vec<(&'static str, u64)>,
99 notes: Vec<(&'static str, &'static str)>,
100}
101
102impl Timing {
103 pub fn start() -> Self {
104 let now = g1t_kit::now_ms();
105 Self {
106 started: now,
107 last: now,
108 steps: Vec::new(),
109 parts: Vec::new(),
110 notes: Vec::new(),
111 }
112 }
113
114 /// Says how long `part` of the step under way took. Parts overlap, so
115 /// they are listed after the steps and are not part of the total.
116 pub fn part(&mut self, part: &'static str, ms: u64) {
117 self.parts.push((part, ms));
118 }
119
120 /// Says how `name` went: where an answer or a credential came from.
121 pub fn note(&mut self, name: &'static str, description: &'static str) {
122 self.notes.push((name, description));
123 }
124
125 /// Ends a step, named `step`, that began when the last one ended.
126 pub fn mark(&mut self, step: &'static str) {
127 let now = g1t_kit::now_ms();
128 self.steps.push((step, now.saturating_sub(self.last)));
129 self.last = now;
130 }
131
132 /// `response`, with how long each step took.
133 pub fn apply(&self, response: Response) -> Result<Response> {
134 let total = g1t_kit::now_ms().saturating_sub(self.started);
135 let headers = response.headers().clone();
136 headers.set("server-timing", &server_timing(&self.steps, &self.parts, &self.notes, total))?;
137 Ok(response.with_headers(headers))
138 }
139}
140
141/// A `Server-Timing` value: each step with its duration, then each part,
142/// the notes, and the total.
143fn server_timing(steps: &[(&str, u64)], parts: &[(&str, u64)], notes: &[(&str, &str)], total: u64) -> String {
144 steps
145 .iter()
146 .chain(parts)
147 .map(|(step, ms)| format!("{step};dur={ms}"))
148 .chain(notes.iter().map(|(name, description)| format!("{name};desc={description}")))
149 .chain(std::iter::once(format!("total;dur={total}")))
150 .collect::<Vec<_>>()
151 .join(", ")
152}
153
154/// The user named by an HTTP Basic `Authorization` header, as git sends it.
155pub async fn viewer(request: &Request, identity: &Fetcher) -> Result<Viewer> {
156 let Some(header) = request.headers().get("authorization")? else {
157 return Ok(None);
158 };
159 let Some((scheme, encoded)) = header.split_once(' ') else {
160 return Ok(None);
161 };
162 if !scheme.eq_ignore_ascii_case("basic") {
163 return Ok(None);
164 }
165 let Some(decoded) = decode_base64(encoded.trim()) else {
166 return Ok(None);
167 };
168 let Some((username, secret)) = decoded.split_once(':') else {
169 return Ok(None);
170 };
171 g1t_kit::call(
172 identity,
173 "user_for_git_credentials",
174 &GitCredentialsArgs {
175 username: username.to_owned(),
176 secret: secret.to_owned(),
177 },
178 )
179 .await
180}
181
182/// Standard base64 to a UTF-8 string, or `None` if either step fails.
183fn decode_base64(input: &str) -> Option<String> {
184 let mut bytes = Vec::with_capacity(input.len() * 3 / 4);
185 let mut buffer = 0u32;
186 let mut bits = 0;
187 for byte in input.bytes().filter(|byte| *byte != b'=') {
188 let value = match byte {
189 b'A'..=b'Z' => byte - b'A',
190 b'a'..=b'z' => byte - b'a' + 26,
191 b'0'..=b'9' => byte - b'0' + 52,
192 b'+' => 62,
193 b'/' => 63,
194 _ => return None,
195 };
196 buffer = (buffer << 6) | u32::from(value);
197 bits += 6;
198 if bits >= 8 {
199 bits -= 8;
200 bytes.push((buffer >> bits) as u8);
201 }
202 }
203 String::from_utf8(bytes).ok()
204}
205
206/// The response for a refused git request. Anonymous callers are asked to
207/// authenticate, which is what makes git prompt for credentials.
208pub fn refuse<T>(outcome: Outcome<T>) -> Result<Response> {
209 let Outcome::Fail(failure) = outcome else {
210 return Response::error("Not found", 404);
211 };
212 let mut response = Response::error(failure.message, failure.code.http_status())?;
213 if failure.code == FailureCode::Unauthenticated {
214 response
215 .headers_mut()
216 .set("www-authenticate", "Basic realm=\"g1t\"")?;
217 }
218 Ok(response)
219}
220
221/// `url` with its first path segment, the workspace, replaced by `slug`.
222pub fn with_namespace(url: &Url, slug: &str) -> Option<String> {
223 let rest = url.path().strip_prefix('/')?.split_once('/')?.1;
224 let mut moved = url.clone();
225 moved.set_path(&format!("/{slug}/{rest}"));
226 Some(moved.to_string())
227}
228
229/// Where a git request for a renamed workspace's old address should go
230/// now, if its first segment is an old slug that still redirects.
231pub async fn renamed(url: &Url, identity: &Fetcher) -> Result<Option<String>> {
232 let Some(old) = url.path().strip_prefix('/').and_then(|path| path.split('/').next()) else {
233 return Ok(None);
234 };
235 let current: Option<String> = g1t_kit::call(
236 identity,
237 "resolve_slug",
238 &g1t_contracts::identity::SlugArgs {
239 slug: old.to_owned(),
240 },
241 )
242 .await?;
243 Ok(current.and_then(|slug| with_namespace(url, &slug)))
244}
245
246/// The request under the workspace its first segment is an alias of
247/// (identity's aliases.rs: `g1t` for `flagon-io`), if it is one. Answered
248/// in place rather than redirected: a push does not follow a redirect.
249pub async fn aliased(git: &GitRequest, identity: &Fetcher) -> Result<Option<GitRequest>> {
250 let slug: Option<String> = g1t_kit::call(
251 identity,
252 "resolve_alias",
253 &g1t_contracts::identity::SlugArgs {
254 slug: git.path.namespace.clone(),
255 },
256 )
257 .await?;
258 Ok(slug.map(|slug| git.under(&slug)))
259}
260
261/// `url` with its repository, the first two path segments, replaced by
262/// `to`: where a request for a transferred repository's old path goes.
263/// Keeps whether the old address ended in `.git`.
264pub fn transferred(url: &Url, to: &RepoPath) -> Option<String> {
265 let path = url.path().strip_prefix('/')?;
266 let mut segments = path.splitn(3, '/');
267 let (_, name, rest) = (segments.next()?, segments.next()?, segments.next()?);
268 let suffix = if name.ends_with(".git") { ".git" } else { "" };
269 let mut moved = url.clone();
270 moved.set_path(&format!("/{}/{}{suffix}/{rest}", to.namespace, to.name));
271 Some(moved.to_string())
272}
273
274/// A permanent redirect: 301 for git's first request for refs, which it
275/// follows and then uses the new address for the rest; 308 for the
276/// others, so a POST stays a POST.
277pub fn moved(location: &str, get: bool) -> Result<Response> {
278 let mut response = Response::empty()?.with_status(if get { 301 } else { 308 });
279 response.headers_mut().set("location", location)?;
280 Ok(response)
281}
282
283const ZERO_ID: &str = "0000000000000000000000000000000000000000";
284const HEADS: &str = "refs/heads/";
285const TAGS: &str = "refs/tags/";
286
287/// One ref a push asks to change.
288struct Command {
289 old: String,
290 new: String,
291 name: String,
292}
293
294/// The commands at the start of a receive-pack request, and the
295/// capabilities the client sent with the first of them.
296fn commands(body: &[u8]) -> (Vec<Command>, String) {
297 let mut commands = Vec::new();
298 let mut capabilities = String::new();
299 let mut position = 0;
300 // Commands are pkt-lines; a flush packet ends them and the pack follows.
301 while let Some(length) = body
302 .get(position..position + 4)
303 .and_then(|hex| std::str::from_utf8(hex).ok())
304 .and_then(|hex| usize::from_str_radix(hex, 16).ok())
305 {
306 if length < 4 || position + length > body.len() {
307 break;
308 }
309 let line = &body[position + 4..position + length];
310 position += length;
311 // `<old> <new> <ref>`, and on the first command a NUL then capabilities.
312 let mut halves = line.splitn(2, |byte| *byte == 0);
313 let command = halves.next().unwrap_or_default();
314 if let Some(rest) = halves.next() {
315 capabilities = String::from_utf8_lossy(rest).trim().to_owned();
316 }
317 let Ok(command) = std::str::from_utf8(command) else {
318 continue;
319 };
320 let mut parts = command.trim_end().splitn(3, ' ');
321 if let (Some(old), Some(new), Some(name)) = (parts.next(), parts.next(), parts.next()) {
322 commands.push(Command {
323 old: old.to_owned(),
324 new: new.to_owned(),
325 name: name.to_owned(),
326 });
327 }
328 }
329 (commands, capabilities)
330}
331
332/// The bytes of the pack a receive-pack request carries: everything after
333/// the flush packet that ends its commands. Zero for a push that only
334/// deletes refs.
335pub(crate) fn pack_bytes(body: &[u8]) -> u64 {
336 let mut position = 0;
337 while let Some(length) = body
338 .get(position..position + 4)
339 .and_then(|hex| std::str::from_utf8(hex).ok())
340 .and_then(|hex| usize::from_str_radix(hex, 16).ok())
341 {
342 if length == 0 {
343 return (body.len() - position - 4) as u64;
344 }
345 if length < 4 || position + length > body.len() {
346 break;
347 }
348 position += length;
349 }
350 0
351}
352
353fn pkt_line(payload: &[u8]) -> Vec<u8> {
354 let mut line = format!("{:04x}", payload.len() + 4).into_bytes();
355 line.extend_from_slice(payload);
356 line
357}
358
359/// The branches and tags a push asks to change, as rules see them: the
360/// full ref, where it pointed (`None`: it is created) and where it will
361/// (`None`: it is deleted).
362pub(crate) fn ref_updates(body: &[u8]) -> Vec<(String, Option<String>, Option<String>)> {
363 commands(body)
364 .0
365 .into_iter()
366 .filter(|command| command.name.starts_with(HEADS) || command.name.starts_with(TAGS))
367 .map(|Command { old, new, name }| (name, (old != ZERO_ID).then_some(old), (new != ZERO_ID).then_some(new)))
368 .collect()
369}
370
371/// A report-status answer, as git expects it.
372pub(crate) fn report_response(report: Vec<u8>) -> Result<Response> {
373 let headers = Headers::new();
374 headers.set("content-type", "application/x-git-receive-pack-result")?;
375 headers.set("cache-control", "no-cache")?;
376 Ok(Response::from_bytes(report)?.with_headers(headers))
377}
378
379/// What git is told when a push would change a protected branch: every ref
380/// in it is declined, with the reason against the protected one, so that
381/// git prints it beside the branch. `None` if the push leaves the branch
382/// alone, or creates it in a repository that does not have it yet. Only
383/// where rulesets cannot be read (an installation without the work
384/// service); rulesets decide everywhere else (rules.rs).
385pub(crate) fn refusal(body: &[u8], protected: &str) -> Option<Vec<u8>> {
386 let (commands, capabilities) = commands(body);
387 let reference = format!("{HEADS}{protected}");
388 if !commands
389 .iter()
390 .any(|command| command.name == reference && command.old != ZERO_ID)
391 {
392 return None;
393 }
394 let mut report = pkt_line(b"unpack ok\n");
395 for command in &commands {
396 let reason = if command.name == reference {
397 format!("{protected} is protected: push a branch and open a pull request")
398 } else {
399 format!("not pushed, because the same push would change {protected}")
400 };
401 report.extend(pkt_line(
402 format!("ng {} {reason}\n", command.name).as_bytes(),
403 ));
404 }
405 report.extend_from_slice(b"0000");
406 Some(framed(report, &capabilities, &[]))
407}
408
409/// A report-status as git expects it: inside channel 1 when the client
410/// asked for side-band, after `messages` on channel 2, which git prints as
411/// `remote:` lines. Without side-band the messages cannot be shown.
412fn framed(report: Vec<u8>, capabilities: &str, messages: &[String]) -> Vec<u8> {
413 let sideband = capabilities
414 .split(' ')
415 .any(|capability| capability.starts_with("side-band"));
416 if !sideband {
417 return report;
418 }
419 let mut body = Vec::new();
420 for message in messages {
421 let mut packet = vec![2u8];
422 packet.extend_from_slice(message.as_bytes());
423 packet.push(b'\n');
424 body.extend(pkt_line(&packet));
425 }
426 // side-band (not -64k) packets carry at most 1000 bytes.
427 for chunk in report.chunks(990) {
428 let mut packet = vec![1u8];
429 packet.extend_from_slice(chunk);
430 body.extend(pkt_line(&packet));
431 }
432 body.extend_from_slice(b"0000");
433 body
434}
435
436/// Declines every ref in a push with `reason`, explaining why in
437/// `messages`: what push protection answers when a push adds a secret.
438pub fn declined(body: &[u8], reason: &str, messages: &[String]) -> Result<Response> {
439 let (commands, capabilities) = commands(body);
440 let mut report = pkt_line(b"unpack ok\n");
441 for command in &commands {
442 report.extend(pkt_line(format!("ng {} {reason}\n", command.name).as_bytes()));
443 }
444 report.extend_from_slice(b"0000");
445 let headers = Headers::new();
446 headers.set("content-type", "application/x-git-receive-pack-result")?;
447 headers.set("cache-control", "no-cache")?;
448 Ok(Response::from_bytes(framed(report, &capabilities, messages))?.with_headers(headers))
449}
450
451/// A branch or tag a push asks to move.
452#[derive(Debug, PartialEq, Eq)]
453pub struct Pushed {
454 /// The full ref: `refs/heads/main`, `refs/tags/v1`.
455 pub git_ref: String,
456 /// Where it pointed before; `None` for a new ref.
457 pub before: Option<String>,
458 pub after: String,
459}
460
461impl Pushed {
462 pub fn branch(&self) -> Option<&str> {
463 self.git_ref.strip_prefix(HEADS)
464 }
465}
466
467/// The branches and tags a push asks to move, read from the commands at the
468/// start of a receive-pack request. Deletions and other refs are left out.
469fn pushed_branches(body: &[u8]) -> Vec<Pushed> {
470 commands(body)
471 .0
472 .into_iter()
473 .filter(|command| command.new != ZERO_ID)
474 .filter(|command| command.name.starts_with(HEADS) || command.name.starts_with(TAGS))
475 .map(|Command { old, new, name }| Pushed {
476 git_ref: name,
477 before: (old != ZERO_ID).then_some(old),
478 after: new,
479 })
480 .collect()
481}
482
483/// The branches and tags a push asks to delete: each full ref, with the
484/// commit it pointed to.
485fn deleted_refs(body: &[u8]) -> Vec<(String, String)> {
486 commands(body)
487 .0
488 .into_iter()
489 .filter(|command| command.new == ZERO_ID && command.old != ZERO_ID)
490 .filter(|command| command.name.starts_with(HEADS) || command.name.starts_with(TAGS))
491 .map(|Command { old, name, .. }| (name, old))
492 .collect()
493}
494
495/// The git store's answer, and what the request asked it to change.
496pub struct Forwarded {
497 pub response: Response,
498 /// For a push: the branches and tags it asks to move, and the commits
499 /// to move them to. Whether each moved is for the caller to confirm.
500 pub pushed: Vec<Pushed>,
501 /// For a push: the branches and tags it asks to delete, each with the
502 /// commit it pointed to. Whether each went is for the caller to confirm.
503 pub deleted: Vec<(String, String)>,
504 /// For a push: the size of the pack it sent, for the storage meter.
505 pub pack_bytes: u64,
506 /// The bytes sent to the store.
507 pub sent: u64,
508 /// Whether the answer is the store's own (not g1t's, for a store that
509 /// was busy).
510 pub from_store: bool,
511 /// For a push: whether it was too large to scan for secrets first and
512 /// was streamed to the store unscanned (`LargePushes::Unscanned`). Its
513 /// `git.push` events say so, and security scans it after it lands.
514 pub unscanned: bool,
515}
516
517/// What became of a git request.
518pub enum Push {
519 Forwarded(Forwarded),
520 /// A push the rules of its branches or tags refuse (rules.rs), answered
521 /// here without reaching the store.
522 Refused(Response),
523 /// A push that adds a secret nobody allowed, answered the same way.
524 Blocked(Response),
525 /// A push the store could not hold: an object or the repository too
526 /// large, or too large to check. With the reason, for the audit log.
527 Declined(Response, String),
528}
529
530/// What a push may bring, checked as it arrives (pack_limits.rs).
531#[derive(Clone, Copy, Debug)]
532pub struct PushLimits {
533 /// The largest object the store holds.
534 pub max_object: u64,
535 /// What the repository holds now, as g1t counts it.
536 pub held: u64,
537 /// The most a repository may hold.
538 pub repo_limit: u64,
539 /// The largest push that is read whole and scanned for secrets.
540 pub scan_cap: usize,
541 /// What happens to a larger one.
542 pub large: LargePushes,
543}
544
545impl Default for PushLimits {
546 fn default() -> Self {
547 PushLimits {
548 max_object: crate::pack_limits::MAX_OBJECT_BYTES,
549 held: 0,
550 repo_limit: crate::pack_limits::DEFAULT_REPO_LIMIT_BYTES,
551 scan_cap: crate::secret_scan::MAX_SCANNED_PUSH,
552 large: LargePushes::Refuse,
553 }
554 }
555}
556
557/// What happens to a push larger than [`PushLimits::scan_cap`]: set by
558/// `LARGE_PUSHES`.
559#[derive(Clone, Copy, Debug, PartialEq, Eq)]
560pub enum LargePushes {
561 /// Declined (the default): push protection cannot read it, so it does
562 /// not let it in.
563 Refuse,
564 /// Streamed to the store without a scan for secrets; the size limits are
565 /// still checked as it passes.
566 Unscanned,
567}
568
569impl LargePushes {
570 pub fn from_var(value: Option<&str>) -> Self {
571 match value.map(str::trim) {
572 Some("unscanned") => LargePushes::Unscanned,
573 _ => LargePushes::Refuse,
574 }
575 }
576}
577
578/// A push the store could not hold.
579#[derive(Clone, Debug, PartialEq, Eq)]
580pub enum SizeViolation {
581 Object { size: u64 },
582 Repository { held: u64, incoming: u64, limit: u64 },
583 Unscannable { size: u64, cap: usize },
584}
585
586/// Why a push is declined for its size, as git shows it: the `ng` reason,
587/// and the lines printed as `remote:`.
588pub fn size_refusal(violation: &SizeViolation) -> (String, Vec<String>) {
589 use crate::pack_limits::{MAX_OBJECT_BYTES, PLATFORM_BODY_LIMIT_BYTES, megabytes};
590 match violation {
591 SizeViolation::Object { size } => (
592 format!("a file of {} is over the {} limit", megabytes(*size), megabytes(MAX_OBJECT_BYTES)),
593 vec![
594 format!("g1t stores files of up to {} each; this push has one of {}.", megabytes(MAX_OBJECT_BYTES), megabytes(*size)),
595 "Take it out of the commits (git rm --cached, then amend or rebase), and keep large".to_owned(),
596 "files elsewhere: https://docs.g1t.sh/guides/git/#size-limits. Nothing was pushed.".to_owned(),
597 ],
598 ),
599 SizeViolation::Repository { held, incoming, limit } => (
600 "the repository would be over its size limit".to_owned(),
601 vec![
602 format!(
603 "This repository holds about {} and the push adds {}, past the {} a repository may hold.",
604 megabytes(*held),
605 megabytes(*incoming),
606 megabytes(*limit)
607 ),
608 "Delete what you no longer need, or split it: https://docs.g1t.sh/guides/git/#size-limits.".to_owned(),
609 "Nothing was pushed.".to_owned(),
610 ],
611 ),
612 SizeViolation::Unscannable { size, cap } => (
613 "the push is too large to check for secrets".to_owned(),
614 vec![
615 format!(
616 "g1t checks every push for secrets and reads up to {} at once; this one is {}.",
617 megabytes(*cap as u64),
618 megabytes(*size)
619 ),
620 "Push in parts, oldest commits first, then push as usual:".to_owned(),
621 " git rev-list --reverse HEAD | awk 'NR % 500 == 0' | xargs -I{} git push origin {}:refs/heads/main".to_owned(),
622 format!("A push over {} is refused by the network before it reaches g1t (HTTP 413).", megabytes(PLATFORM_BODY_LIMIT_BYTES)),
623 "See https://docs.g1t.sh/guides/git/#size-limits. Nothing was pushed.".to_owned(),
624 ],
625 ),
626 }
627}
628
629/// Feeds the next chunk of a push to the size check; the first violation.
630fn check_size(sizer: &mut Option<PackSizer>, chunk: &[u8], limits: &PushLimits) -> Option<SizeViolation> {
631 let walker = sizer.as_mut()?;
632 match walker.feed(chunk) {
633 Ok(()) => {}
634 Err(Violation::ObjectTooLarge { size }) => return Some(SizeViolation::Object { size }),
635 Err(Violation::Malformed(why)) => {
636 // Not for g1t to judge: the store will say.
637 worker::console_error!("push not checked for size: {why}");
638 *sizer = None;
639 return None;
640 }
641 }
642 let incoming = walker.pack_bytes();
643 crate::pack_limits::over_repo_limit(limits.held, incoming, limits.repo_limit).then_some(SizeViolation::Repository {
644 held: limits.held,
645 incoming,
646 limit: limits.repo_limit,
647 })
648}
649
650/// A request body that streams from `stream`, for `fetch`.
651pub(crate) fn stream_body<S>(stream: S) -> Result<JsValue>
652where
653 S: futures_util::TryStream + 'static,
654 S::Ok: Into<Vec<u8>>,
655 S::Error: Into<worker::Error>,
656{
657 let response: worker::web_sys::Response = Response::from_stream(stream)?.into();
658 Ok(response.body().map_or(JsValue::NULL, Into::into))
659}
660
661/// What git is told when the store is busy: 429 or 503, with when to try
662/// again (resilience.rs).
663pub fn busy_response(busy: Busy) -> Result<Response> {
664 let response = Response::error(busy.message(), busy.status())?;
665 response.headers().set("retry-after", &busy.retry_after.to_string())?;
666 Ok(response)
667}
668
669/// The rest of a request's body, read and thrown away so that git hears
670/// the answer; how many bytes it was.
671async fn drain(stream: &mut worker::ByteStream) -> Result<u64> {
672 let mut size = 0;
673 while let Some(chunk) = stream.next().await {
674 size += chunk?.len() as u64;
675 }
676 Ok(size)
677}
678
679/// One packet of a pkt-line stream: data, or a flush (`0000`), delimiter
680/// (`0001`) or response-end (`0002`) packet, kept as its four bytes.
681#[derive(Debug, PartialEq, Eq)]
682enum Packet {
683 Data(Vec<u8>),
684 Special([u8; 4]),
685}
686
687/// The packets in `bytes`, or `None` if it is not a whole pkt-line stream.
688fn packets(bytes: &[u8]) -> Option<Vec<Packet>> {
689 let mut out = Vec::new();
690 let mut position = 0;
691 while position < bytes.len() {
692 let header = bytes.get(position..position + 4)?;
693 let length = usize::from_str_radix(std::str::from_utf8(header).ok()?, 16).ok()?;
694 if length < 4 {
695 out.push(Packet::Special(header.try_into().ok()?));
696 position += 4;
697 continue;
698 }
699 out.push(Packet::Data(bytes.get(position + 4..position + length)?.to_vec()));
700 position += length;
701 }
702 Some(out)
703}
704
705fn encode(packets: &[Packet]) -> Vec<u8> {
706 let mut out = Vec::new();
707 for packet in packets {
708 match packet {
709 Packet::Data(data) => out.extend(pkt_line(data)),
710 Packet::Special(bytes) => out.extend_from_slice(bytes),
711 }
712 }
713 out
714}
715
716/// A ref advertisement (`info/refs` for upload-pack) or a protocol v2
717/// `ls-refs` answer with `HEAD` pointing at `branch`, the repository's
718/// default branch as g1t keeps it, so a clone checks it out. The git store
719/// holds the HEAD it was created with; g1t can change the default branch
720/// since. `None` when there is nothing to change: no `HEAD` line, `HEAD`
721/// already names `branch`, or `branch` is not advertised.
722pub fn with_head(body: &[u8], branch: &str) -> Option<Vec<u8>> {
723 let mut packets = packets(body)?;
724 let target = format!("{HEADS}{branch}");
725 let oid = packets.iter().find_map(|packet| {
726 let Packet::Data(data) = packet else { return None };
727 let line = data.split(|byte| *byte == 0).next()?;
728 let line = std::str::from_utf8(line).ok()?.trim_end();
729 let (oid, name) = line.split_once(' ')?;
730 // v2 lines may carry attributes after the name.
731 let name = name.split(' ').next()?;
732 (name == target).then(|| oid.to_owned())
733 })?;
734 let mut changed = false;
735 for packet in &mut packets {
736 let Packet::Data(data) = packet else { continue };
737 let text = String::from_utf8_lossy(data).into_owned();
738 let Some((_, rest)) = text.split_once(' ') else { continue };
739 if !(rest.starts_with("HEAD\0") || rest.starts_with("HEAD\n") || rest.starts_with("HEAD ") || rest == "HEAD") {
740 continue;
741 }
742 let mut line = format!("{oid} {rest}");
743 // v0: `symref=HEAD:refs/heads/<old>` among the capabilities.
744 // v2: `symref-target:refs/heads/<old>` after the name.
745 for marker in ["symref=HEAD:", "symref-target:"] {
746 if let Some(at) = line.find(marker) {
747 let start = at + marker.len();
748 let end = line[start..]
749 .find([' ', '\n', '\0'])
750 .map_or(line.len(), |offset| start + offset);
751 line.replace_range(start..end, &target);
752 }
753 }
754 changed = line != text;
755 if changed {
756 *data = line.into_bytes();
757 }
758 break;
759 }
760 changed.then(|| encode(&packets))
761}
762
763/// The capability that asks git to send a push's pack whole: every delta's
764/// base inside it, none left for the receiving end to find (a "thin" pack).
765const NO_THIN: &[u8] = b"no-thin";
766
767/// The receive-pack ref advertisement (`info/refs?service=git-receive-pack`,
768/// protocol v0 or v1) with `no-thin` among its capabilities, so that git
769/// sends a pack whose deltas have their bases in it (git's `send-pack`
770/// turns thin packs off when the server says `no-thin`). Push protection
771/// and the rules then read every object from the pack, and none from the
772/// store (secret_scan.rs `supply_bases`). The capabilities follow the NUL
773/// on the first ref line, or on the `capabilities^{}` line of an empty
774/// repository. `None` when there is nothing to change or it cannot be
775/// changed safely: `no-thin` is there already, or the answer is not a whole
776/// pkt-line advertisement in that shape. Never for upload-pack.
777pub fn with_no_thin(body: &[u8]) -> Option<Vec<u8>> {
778 let mut packets = packets(body)?;
779 // Past the `# service=` line and its flush, and v1's `version 1`: the
780 // first ref line, which carries the capabilities.
781 let line = packets.iter_mut().find_map(|packet| match packet {
782 Packet::Data(data) if !data.starts_with(b"# service=") && !data.starts_with(b"version ") => Some(data),
783 _ => None,
784 })?;
785 let nul = line.iter().position(|byte| *byte == 0)?;
786 // `<oid> <ref>` before the NUL: 40 (SHA-1) or 64 (SHA-256) hex digits.
787 let (oid, name) = std::str::from_utf8(&line[..nul]).ok()?.split_once(' ')?;
788 if !matches!(oid.len(), 40 | 64) || !oid.bytes().all(|byte| byte.is_ascii_hexdigit()) || name.is_empty() {
789 return None;
790 }
791 let end = if line.ends_with(b"\n") { line.len() - 1 } else { line.len() };
792 let capabilities = &line[nul + 1..end];
793 if capabilities.split(|byte| *byte == b' ').any(|capability| capability == NO_THIN) {
794 return None;
795 }
796 let mut added = Vec::with_capacity(NO_THIN.len() + 1);
797 if !capabilities.is_empty() && !capabilities.ends_with(b" ") {
798 added.push(b' ');
799 }
800 added.extend_from_slice(NO_THIN);
801 // A pkt-line holds at most 65516 bytes of data.
802 if line.len() + added.len() > 65516 {
803 return None;
804 }
805 line.splice(end..end, added);
806 Some(encode(&packets))
807}
808
809/// Whether a request to the git store is one whose answer names `HEAD`:
810/// the ref advertisement for a fetch, or a protocol v2 `ls-refs`.
811fn names_head(git: &GitRequest, body: Option<&[u8]>) -> bool {
812 if git.service != GitService::UploadPack {
813 return false;
814 }
815 match body {
816 None => git.endpoint == "info/refs",
817 Some(body) => {
818 git.endpoint == "git-upload-pack"
819 && body.windows(b"command=ls-refs".len()).any(|window| window == b"command=ls-refs")
820 }
821 }
822}
823
824/// Whether a request is a protocol v2 `fetch` still negotiating: it sends
825/// `have` lines and no `done`, so the answer may be acknowledgments only.
826fn negotiating(body: &[u8]) -> bool {
827 let Some(packets) = packets(body) else { return false };
828 let lines: Vec<&[u8]> = packets
829 .iter()
830 .filter_map(|packet| match packet {
831 Packet::Data(data) => Some(data.strip_suffix(b"\n").unwrap_or(data)),
832 Packet::Special(_) => None,
833 })
834 .collect();
835 lines.contains(&b"command=fetch".as_slice())
836 && lines.iter().any(|line| line.starts_with(b"have "))
837 && !lines.contains(&b"done".as_slice())
838}
839
840/// What to do with the start of a store's answer to a negotiating fetch.
841#[derive(Debug, PartialEq, Eq)]
842enum Acknowledged {
843 /// Not enough of it yet to tell.
844 NeedMore,
845 /// Send it on as it is.
846 Whole,
847 /// Acknowledgments without `ready`, followed by more sections: the
848 /// store's answer to keep is these first bytes, ended by a flush.
849 CutAt(usize),
850}
851
852/// How much of the answer to keep. The git store answers a fetch whose
853/// `have`s it does not know with `acknowledgments`, `NAK`, then a pack
854/// anyway; git refuses that ("expected no other sections to be sent after
855/// no 'ready'"), since a server that is not ready must end the response
856/// there and let the client negotiate again. Lines may be `sideband-all`
857/// framed (band 1, `\x01`).
858fn acknowledged(head: &[u8]) -> Acknowledged {
859 let mut position = 0;
860 let mut first = true;
861 loop {
862 let Some(header) = head.get(position..position + 4) else { return Acknowledged::NeedMore };
863 let Some(length) = std::str::from_utf8(header).ok().and_then(|hex| usize::from_str_radix(hex, 16).ok()) else {
864 return Acknowledged::Whole;
865 };
866 if length < 4 {
867 // The acknowledgments section's end: a delimiter means more
868 // sections follow, which only `ready` allows.
869 return match (first, header) {
870 (false, b"0001") => Acknowledged::CutAt(position),
871 _ => Acknowledged::Whole,
872 };
873 }
874 let Some(payload) = head.get(position + 4..position + length) else { return Acknowledged::NeedMore };
875 let line = payload.strip_prefix(b"\x01").unwrap_or(payload);
876 let line = line.strip_suffix(b"\n").unwrap_or(line);
877 if first && line != b"acknowledgments" {
878 return Acknowledged::Whole;
879 }
880 if line == b"ready" {
881 return Acknowledged::Whole;
882 }
883 first = false;
884 position += length;
885 }
886}
887
888/// The answer to a negotiating fetch, with the sections the store sent
889/// after acknowledgments without `ready` left off (see [`acknowledged`]).
890/// Reads only the start of the answer; the rest streams through.
891async fn without_early_pack(mut response: Response) -> Result<Response> {
892 const LOOK: usize = 64 * 1024;
893 let headers = response.headers().clone();
894 headers.delete("content-length")?;
895 let mut stream = response.stream()?;
896 let mut head = Vec::new();
897 loop {
898 match acknowledged(&head) {
899 Acknowledged::CutAt(at) => {
900 head.truncate(at);
901 // A flush ends the acknowledgments and the answer. No
902 // response-end packet: git's HTTP transport adds its own
903 // and refuses one from the server.
904 head.extend_from_slice(b"0000");
905 return Ok(Response::from_bytes(head)?.with_headers(headers));
906 }
907 Acknowledged::Whole => break,
908 Acknowledged::NeedMore if head.len() >= LOOK => break,
909 Acknowledged::NeedMore => match stream.next().await {
910 Some(chunk) => head.extend_from_slice(&chunk?),
911 None => break,
912 },
913 }
914 }
915 let rest = futures_util::stream::once(async move { Ok::<Vec<u8>, worker::Error>(head) }).chain(stream);
916 Ok(Response::from_stream(rest)?.with_headers(headers))
917}
918
919/// Sends the request on to the git store and returns its response as is,
920/// unless it is a push `checks` refuse (the workflow gate, the rules, push
921/// protection: push_checks.rs), or one the store could not hold (`limits`,
922/// pack_limits.rs). `checks` is given as much of the push as was read,
923/// whether that is all of it, and whether to scan it for secrets. A
924/// fetch's ref listing has its `HEAD` pointed at `default_branch` (see
925/// [`with_head`]). A POST's body is `read` when the caller has read it
926/// already.
927///
928/// A push is read as it arrives: up to `limits.scan_cap` is kept, to be
929/// scanned and sent on whole; past it, the push is declined, or streamed
930/// to the store unscanned (`LargePushes`), never held. Reads the store
931/// fails for a moment (429, 5xx) are tried again with backoff; a push never
932/// is. A store still busy after that is answered 429 or 503 with
933/// `Retry-After`.
934#[allow(clippy::too_many_arguments)]
935pub async fn forward(
936 mut request: Request,
937 read: Option<Vec<u8>>,
938 git: &GitRequest,
939 access: &GitAccess,
940 checks: impl AsyncFnOnce(&[u8], bool, bool) -> Result<Checks>,
941 default_branch: Option<&str>,
942 limits: PushLimits,
943 timing: &mut Timing,
944) -> Result<Push> {
945 let headers = Headers::new();
946 headers.set("authorization", &format!("Bearer {}", access.token))?;
947 for name in FORWARDED_HEADERS {
948 if let Some(value) = request.headers().get(name)? {
949 headers.set(name, &value)?;
950 }
951 }
952 let query = request.url()?.query().map(|query| format!("?{query}")).unwrap_or_default();
953 let url = format!("{}/{}{query}", access.remote, git.endpoint);
954 let method = request.method();
955 // Its own health and breaker: the fallback store's apart from Artifacts'.
956 let namespace = crate::store::health_namespace(&access.remote);
957
958 if method == Method::Post && git.endpoint == "git-receive-pack" {
959 return push(request, &url, headers, checks, limits, &namespace, timing).await;
960 }
961
962 // A read: the ref advertisement, `ls-refs`, or a fetch of objects.
963 let body = match (&method, read) {
964 (Method::Post, Some(body)) => Some(body),
965 (Method::Post, None) => Some(request.bytes().await?),
966 _ => None,
967 };
968 let lists_head = match &body {
969 None => method == Method::Get && names_head(git, None),
970 Some(body) => names_head(git, Some(body)),
971 };
972 let sent = body.as_ref().map_or(0, |body| body.len() as u64);
973 let mut attempt = 0;
974 let mut response = loop {
975 let mut init = RequestInit::new();
976 init.with_method(method.clone()).with_headers(headers.clone());
977 if let Some(body) = &body {
978 init.with_body(Some(Uint8Array::from(body.as_slice()).into()));
979 }
980 let started = g1t_kit::now_ms();
981 let answered = Fetch::Request(Request::new_with_init(&url, &init)?).send().await;
982 let ms = g1t_kit::now_ms().saturating_sub(started);
983 let failure = match &answered {
984 Ok(response) => resilience::classify_status(response.status_code()),
985 Err(_) => Some(Failure::Transient),
986 };
987 let outcome = match failure {
988 None => meters::Outcome::Ok,
989 Some(Failure::RateLimited) => meters::Outcome::RateLimited,
990 Some(_) => meters::Outcome::Failed,
991 };
992 meters::record_health(&namespace, outcome, ms);
993 match (answered, failure) {
994 (Ok(response), None) => break response,
995 (answered, Some(failure)) if resilience::retry(failure, attempt) => {
996 drop(answered);
997 let wait = resilience::backoff_ms(failure, attempt, worker::js_sys::Math::random());
998 worker::Delay::from(std::time::Duration::from_millis(wait)).await;
999 attempt += 1;
1000 }
1001 (_, Some(failure)) => {
1002 let busy = Busy { rate_limited: failure == Failure::RateLimited, retry_after: 5, read_only: false };
1003 return Ok(Push::Forwarded(Forwarded {
1004 response: busy_response(busy)?,
1005 pushed: Vec::new(),
1006 deleted: Vec::new(),
1007 pack_bytes: 0,
1008 sent,
1009 from_store: false,
1010 unscanned: false,
1011 }));
1012 }
1013 (Err(error), None) => return Err(error),
1014 }
1015 };
1016 if let (true, Some(branch)) = (lists_head, default_branch)
1017 && response.status_code() == 200
1018 {
1019 let headers = response.headers().clone();
1020 headers.delete("content-length")?;
1021 let body = response.bytes().await?;
1022 let body = with_head(&body, branch).unwrap_or(body);
1023 response = Response::from_bytes(body)?.with_headers(headers);
1024 }
1025 // A push's ref advertisement asks for a pack without outside bases.
1026 if method == Method::Get
1027 && git.service == GitService::ReceivePack
1028 && git.endpoint == "info/refs"
1029 && response.status_code() == 200
1030 {
1031 let headers = response.headers().clone();
1032 headers.delete("content-length")?;
1033 let body = response.bytes().await?;
1034 let body = with_no_thin(&body).unwrap_or(body);
1035 response = Response::from_bytes(body)?.with_headers(headers);
1036 }
1037 if git.endpoint == "git-upload-pack"
1038 && response.status_code() == 200
1039 && body.as_deref().is_some_and(negotiating)
1040 {
1041 response = without_early_pack(response).await?;
1042 }
1043 Ok(Push::Forwarded(Forwarded {
1044 response,
1045 pushed: Vec::new(),
1046 deleted: Vec::new(),
1047 pack_bytes: 0,
1048 sent,
1049 from_store: true,
1050 unscanned: false,
1051 }))
1052}
1053
1054/// A receive-pack request; see [`forward`]. Its steps: `recv` (the push
1055/// read), `checks`, `upload` (the store's answer).
1056#[allow(clippy::too_many_arguments)]
1057async fn push(
1058 mut request: Request,
1059 url: &str,
1060 headers: Headers,
1061 checks: impl AsyncFnOnce(&[u8], bool, bool) -> Result<Checks>,
1062 limits: PushLimits,
1063 namespace: &str,
1064 timing: &mut Timing,
1065) -> Result<Push> {
1066 let mut stream = request.stream()?;
1067 let mut head: Vec<u8> = Vec::new();
1068 let mut sizer = Some(PackSizer::new(limits.max_object));
1069 let mut violation = None;
1070 let mut ended = false;
1071 while head.len() <= limits.scan_cap {
1072 match stream.next().await {
1073 Some(chunk) => {
1074 let chunk = chunk?;
1075 if violation.is_none() {
1076 violation = check_size(&mut sizer, &chunk, &limits);
1077 }
1078 head.extend_from_slice(&chunk);
1079 }
1080 None => {
1081 ended = true;
1082 break;
1083 }
1084 }
1085 }
1086 timing.mark("recv");
1087 // The workflow gate and the rules of the branches and tags it changes,
1088 // with push protection alongside for a push read whole that is within
1089 // the size limits (push_checks.rs). What the rules refuse is refused
1090 // whatever else is wrong with it.
1091 let checked = checks(&head, ended, ended && violation.is_none()).await?;
1092 for (part, ms) in checked.spans {
1093 timing.part(part, ms);
1094 }
1095 // Whether the pack came thin: g1t asks for whole ones (`no-thin`, see
1096 // [`with_no_thin`]), so a thin one is a client that ignored it, and its
1097 // bases were read from the store (`read`).
1098 if let Some(bases) = checked.bases {
1099 timing.note("thin", if bases.thin() { "yes" } else { "no" });
1100 if bases.thin() {
1101 let agent = request.headers().get("user-agent").ok().flatten().unwrap_or_default();
1102 worker::console_warn!(
1103 "a thin push from {agent}: {} bases outside the pack, {} asked of the store, {} left unresolved",
1104 bases.missing,
1105 bases.asked,
1106 bases.left
1107 );
1108 }
1109 }
1110 timing.mark("checks");
1111 let blocked = match checked.verdict {
1112 Verdict::Refused(response) => {
1113 if !ended {
1114 drain(&mut stream).await?;
1115 }
1116 return Ok(Push::Refused(response));
1117 }
1118 Verdict::Blocked(response) => Some(response),
1119 Verdict::Clear => None,
1120 };
1121 if !ended && limits.large == LargePushes::Refuse && violation.is_none() {
1122 let size = head.len() as u64 + drain(&mut stream).await?;
1123 violation = Some(SizeViolation::Unscannable { size, cap: limits.scan_cap });
1124 ended = true;
1125 }
1126 if let Some(violation) = violation {
1127 if !ended {
1128 drain(&mut stream).await?;
1129 }
1130 let (reason, messages) = size_refusal(&violation);
1131 return Ok(Push::Declined(declined(&head, &reason, &messages)?, reason));
1132 }
1133 let pushed = pushed_branches(&head);
1134 let deleted = deleted_refs(&head);
1135 let mut init = RequestInit::new();
1136 init.with_method(Method::Post).with_headers(headers);
1137 let started = g1t_kit::now_ms();
1138 let (answered, pack_bytes, sent, unscanned) = if ended {
1139 if let Some(response) = blocked {
1140 return Ok(Push::Blocked(response));
1141 }
1142 let pack = pack_bytes(&head);
1143 let sent = head.len() as u64;
1144 init.with_body(Some(Uint8Array::from(head.as_slice()).into()));
1145 drop(head);
1146 (Fetch::Request(Request::new_with_init(url, &init)?).send().await, pack, sent, false)
1147 } else {
1148 // Larger than can be scanned, and let through unscanned: streamed,
1149 // with the size limits checked as it passes. A violation ends the
1150 // stream before the pack does, so the store refuses it whole.
1151 worker::console_warn!("a push of more than {} bytes goes to the store unscanned", limits.scan_cap);
1152 let commands = head.iter().take(64 * 1024).copied().collect::<Vec<u8>>();
1153 let found: Rc<RefCell<Option<SizeViolation>>> = Rc::default();
1154 let walked = Rc::new(RefCell::new((sizer, 0u64)));
1155 let rest = {
1156 let found = found.clone();
1157 let walked = walked.clone();
1158 stream.map(move |chunk| {
1159 let chunk = chunk?;
1160 let mut walked = walked.borrow_mut();
1161 walked.1 += chunk.len() as u64;
1162 if let Some(violation) = check_size(&mut walked.0, &chunk, &limits) {
1163 *found.borrow_mut() = Some(violation);
1164 return Err(worker::Error::RustError("push over the size limit".into()));
1165 }
1166 Ok(chunk)
1167 })
1168 };
1169 let first = head.len() as u64;
1170 let body = futures_util::stream::once(async move { Ok::<Vec<u8>, worker::Error>(head) }).chain(rest);
1171 init.with_body(Some(stream_body(body)?));
1172 let answered = Fetch::Request(Request::new_with_init(url, &init)?).send().await;
1173 if let Some(violation) = found.borrow_mut().take() {
1174 let (reason, messages) = size_refusal(&violation);
1175 return Ok(Push::Declined(declined(&commands, &reason, &messages)?, reason));
1176 }
1177 let walked = walked.borrow();
1178 let pack = walked.0.as_ref().map_or_else(|| pack_bytes(&commands), PackSizer::pack_bytes);
1179 (answered, pack, first + walked.1, true)
1180 };
1181 let ms = g1t_kit::now_ms().saturating_sub(started);
1182 timing.mark("upload");
1183 let failure = match &answered {
1184 Ok(response) => resilience::classify_status(response.status_code()),
1185 Err(_) => Some(Failure::Transient),
1186 };
1187 meters::record_health(
1188 namespace,
1189 match failure {
1190 None => meters::Outcome::Ok,
1191 Some(Failure::RateLimited) => meters::Outcome::RateLimited,
1192 Some(_) => meters::Outcome::Failed,
1193 },
1194 ms,
1195 );
1196 // A push is never tried again: the store may have taken it.
1197 let response = match (answered, failure) {
1198 (Ok(response), None) => response,
1199 (Ok(response), Some(Failure::RateLimited)) => {
1200 drop(response);
1201 busy_response(Busy { rate_limited: true, retry_after: 5, read_only: false })?
1202 }
1203 (Ok(response), Some(_)) => response,
1204 (Err(error), _) => {
1205 worker::console_error!("a push did not reach the store: {error}");
1206 busy_response(Busy { rate_limited: false, retry_after: 5, read_only: false })?
1207 }
1208 };
1209 Ok(Push::Forwarded(Forwarded {
1210 response,
1211 pushed,
1212 deleted,
1213 pack_bytes,
1214 sent,
1215 from_store: true,
1216 unscanned,
1217 }))
1218}
1219
1220#[cfg(test)]
1221mod tests {
1222 use super::{Acknowledged, GitService, Pushed, RepoPath, Url, ZERO_ID, acknowledged, deleted_refs, framed, negotiating, pack_bytes, parse, pushed_branches, refusal, server_timing, transferred, with_head, with_namespace, with_no_thin};
1223
1224 #[test]
1225 fn server_timing_names_each_step_and_the_total() {
1226 assert_eq!(
1227 server_timing(&[("repo", 12), ("token", 0), ("store", 140)], &[], &[], 153),
1228 "repo;dur=12, token;dur=0, store;dur=140, total;dur=153"
1229 );
1230 assert_eq!(server_timing(&[], &[], &[], 3), "total;dur=3");
1231 // A push's checks run side by side: their parts come after the steps.
1232 assert_eq!(
1233 server_timing(&[("recv", 30), ("checks", 120), ("upload", 300)], &[("read", 40), ("rules", 110), ("scan", 90)], &[], 450),
1234 "recv;dur=30, checks;dur=120, upload;dur=300, read;dur=40, rules;dur=110, scan;dur=90, total;dur=450"
1235 );
1236 assert_eq!(
1237 server_timing(&[("repo", 1), ("cache", 2)], &[], &[("refs", "hit-colo")], 4),
1238 "repo;dur=1, cache;dur=2, refs;desc=hit-colo, total;dur=4"
1239 );
1240 }
1241
1242 #[test]
1243 fn a_renamed_repository_redirects_to_its_new_name() {
1244 // A rename keeps the old path in the same table as a transfer, so
1245 // the old remote is sent to the new name the same way.
1246 let to = RepoPath {
1247 namespace: "acme".into(),
1248 name: "booster".into(),
1249 };
1250 let url = Url::parse("https://g1t.sh/acme/rocket.git/info/refs?service=git-upload-pack").unwrap();
1251 assert_eq!(
1252 transferred(&url, &to).as_deref(),
1253 Some("https://g1t.sh/acme/booster.git/info/refs?service=git-upload-pack")
1254 );
1255 }
1256
1257 #[test]
1258 fn head_follows_the_default_branch_in_a_v0_advertisement() {
1259 let main = "1111111111111111111111111111111111111111";
1260 let trunk = "2222222222222222222222222222222222222222";
1261 let body = [
1262 pkt("# service=git-upload-pack\n"),
1263 b"0000".to_vec(),
1264 pkt(&format!("{main} HEAD\0multi_ack symref=HEAD:refs/heads/main agent=git/2\n")),
1265 pkt(&format!("{main} refs/heads/main\n")),
1266 pkt(&format!("{trunk} refs/heads/trunk\n")),
1267 b"0000".to_vec(),
1268 ]
1269 .concat();
1270 let changed = String::from_utf8(with_head(&body, "trunk").unwrap()).unwrap();
1271 assert!(changed.contains(&format!("{trunk} HEAD\0multi_ack symref=HEAD:refs/heads/trunk agent=git/2\n")));
1272 assert!(changed.contains(&format!("{main} refs/heads/main\n")));
1273 assert!(changed.starts_with("001e# service=git-upload-pack\n0000"));
1274 // Already right, or a branch it does not have: left alone.
1275 assert!(with_head(&body, "main").is_none());
1276 assert!(with_head(&body, "gone").is_none());
1277 }
1278
1279 #[test]
1280 fn a_push_advertisement_asks_for_a_pack_without_outside_bases() {
1281 let main = "1111111111111111111111111111111111111111";
1282 let topic = "2222222222222222222222222222222222222222";
1283 let body = [
1284 pkt("# service=git-receive-pack\n"),
1285 b"0000".to_vec(),
1286 pkt(&format!("{main} refs/heads/main\0report-status delete-refs side-band-64k quiet ofs-delta agent=git/2.45\n")),
1287 pkt(&format!("{topic} refs/heads/topic\n")),
1288 b"0000".to_vec(),
1289 ]
1290 .concat();
1291 let changed = with_no_thin(&body).unwrap();
1292 let expected = [
1293 pkt("# service=git-receive-pack\n"),
1294 b"0000".to_vec(),
1295 pkt(&format!("{main} refs/heads/main\0report-status delete-refs side-band-64k quiet ofs-delta agent=git/2.45 no-thin\n")),
1296 pkt(&format!("{topic} refs/heads/topic\n")),
1297 b"0000".to_vec(),
1298 ]
1299 .concat();
1300 assert_eq!(String::from_utf8(changed.clone()).unwrap(), String::from_utf8(expected).unwrap());
1301 // The length of the line that grew is its new one: the whole parses.
1302 assert!(super::packets(&changed).is_some());
1303 // Said once: an answer that has it already is left alone.
1304 assert!(with_no_thin(&changed).is_none());
1305
1306 // Protocol v1 begins with `version 1`.
1307 let v1 = [
1308 pkt("# service=git-receive-pack\n"),
1309 b"0000".to_vec(),
1310 pkt("version 1\n"),
1311 pkt(&format!("{main} refs/heads/main\0report-status ofs-delta\n")),
1312 b"0000".to_vec(),
1313 ]
1314 .concat();
1315 let changed = String::from_utf8(with_no_thin(&v1).unwrap()).unwrap();
1316 assert!(changed.contains(&String::from_utf8(pkt(&format!("{main} refs/heads/main\0report-status ofs-delta no-thin\n"))).unwrap()));
1317 assert!(changed.contains("000eversion 1\n"));
1318 }
1319
1320 #[test]
1321 fn an_empty_repository_advertisement_asks_for_a_whole_pack_too() {
1322 let zero = "0000000000000000000000000000000000000000";
1323 let body = [
1324 pkt("# service=git-receive-pack\n"),
1325 b"0000".to_vec(),
1326 pkt(&format!("{zero} capabilities^{{}}\0report-status delete-refs ofs-delta\n")),
1327 b"0000".to_vec(),
1328 ]
1329 .concat();
1330 let changed = String::from_utf8(with_no_thin(&body).unwrap()).unwrap();
1331 assert!(changed.contains(&String::from_utf8(pkt(&format!("{zero} capabilities^{{}}\0report-status delete-refs ofs-delta no-thin\n"))).unwrap()));
1332 // No capabilities at all, and no newline: still one list.
1333 let bare = [pkt("# service=git-receive-pack\n"), b"0000".to_vec(), pkt(&format!("{zero} capabilities^{{}}\0")), b"0000".to_vec()].concat();
1334 let changed = String::from_utf8(with_no_thin(&bare).unwrap()).unwrap();
1335 assert!(changed.contains(&String::from_utf8(pkt(&format!("{zero} capabilities^{{}}\0no-thin"))).unwrap()));
1336 }
1337
1338 #[test]
1339 fn an_advertisement_that_cannot_be_read_goes_through_untouched() {
1340 let main = "1111111111111111111111111111111111111111";
1341 // Not pkt-lines; a length past the end; an error page.
1342 assert!(with_no_thin(b"not a git answer").is_none());
1343 assert!(with_no_thin(b"00ff1111").is_none());
1344 assert!(with_no_thin(b"<html>503 Service Unavailable</html>").is_none());
1345 assert!(with_no_thin(b"").is_none());
1346 // A first ref line without capabilities, or without an object id.
1347 let without = [pkt("# service=git-receive-pack\n"), b"0000".to_vec(), pkt(&format!("{main} refs/heads/main\n")), b"0000".to_vec()].concat();
1348 assert!(with_no_thin(&without).is_none());
1349 let unnamed = [pkt("# service=git-receive-pack\n"), b"0000".to_vec(), pkt("nothing here\0report-status\n"), b"0000".to_vec()].concat();
1350 assert!(with_no_thin(&unnamed).is_none());
1351 // `no-thin` inside another capability's value is not `no-thin`.
1352 let lookalike = [pkt("# service=git-receive-pack\n"), b"0000".to_vec(), pkt(&format!("{main} refs/heads/main\0agent=no-thin-ish\n")), b"0000".to_vec()].concat();
1353 assert!(String::from_utf8(with_no_thin(&lookalike).unwrap()).unwrap().contains("agent=no-thin-ish no-thin\n"));
1354 }
1355
1356 #[test]
1357 fn head_follows_the_default_branch_in_a_v2_listing() {
1358 let main = "1111111111111111111111111111111111111111";
1359 let trunk = "2222222222222222222222222222222222222222";
1360 let body = [
1361 pkt(&format!("{main} HEAD symref-target:refs/heads/main\n")),
1362 pkt(&format!("{main} refs/heads/main\n")),
1363 pkt(&format!("{trunk} refs/heads/trunk\n")),
1364 b"0000".to_vec(),
1365 ]
1366 .concat();
1367 let changed = String::from_utf8(with_head(&body, "trunk").unwrap()).unwrap();
1368 assert!(changed.starts_with(&String::from_utf8(pkt(&format!("{trunk} HEAD symref-target:refs/heads/trunk\n"))).unwrap()));
1369 assert!(changed.ends_with("0000"));
1370 // Without symrefs asked for, only the commit changes.
1371 let plain = [pkt(&format!("{main} HEAD\n")), pkt(&format!("{trunk} refs/heads/trunk\n")), b"0000".to_vec()].concat();
1372 let changed = String::from_utf8(with_head(&plain, "trunk").unwrap()).unwrap();
1373 assert!(changed.starts_with(&format!("0032{trunk} HEAD\n")));
1374 }
1375
1376 #[test]
1377 fn a_push_is_measured_by_the_pack_after_its_commands() {
1378 let old = "c71546fcd893ef8b0f57388b65e620d759705dda";
1379 let new = "4807077b296e6edbf410d55e72749d3e1170c291";
1380 let pack = b"PACK\0\0\0\x02\0\0\0\0rest-of-pack";
1381 let body = [
1382 pkt(&format!("{old} {new} refs/heads/main\0 report-status\n")),
1383 b"0000".to_vec(),
1384 pack.to_vec(),
1385 ]
1386 .concat();
1387 assert_eq!(pack_bytes(&body), pack.len() as u64);
1388 // Only deletions: no pack.
1389 let body = [pkt(&format!("{old} {ZERO_ID} refs/heads/gone\n")), b"0000".to_vec()].concat();
1390 assert_eq!(pack_bytes(&body), 0);
1391 assert_eq!(pack_bytes(b"garbage"), 0);
1392 }
1393
1394 #[test]
1395 fn a_transferred_repository_keeps_the_rest_of_the_address() {
1396 let to = RepoPath {
1397 namespace: "flagon-io".into(),
1398 name: "g1t".into(),
1399 };
1400 let url = Url::parse("https://g1t.sh/syntaqx/g1t.git/info/refs?service=git-receive-pack").unwrap();
1401 assert_eq!(
1402 transferred(&url, &to).as_deref(),
1403 Some("https://g1t.sh/flagon-io/g1t.git/info/refs?service=git-receive-pack")
1404 );
1405 let url = Url::parse("https://g1t.sh/syntaqx/g1t/git-upload-pack").unwrap();
1406 assert_eq!(
1407 transferred(&url, &to).as_deref(),
1408 Some("https://g1t.sh/flagon-io/g1t/git-upload-pack")
1409 );
1410 }
1411
1412 #[test]
1413 fn an_alias_is_answered_as_its_workspaces_repository() {
1414 for (address, service) in [
1415 ("https://g1t.sh/g1t/g1t.git/info/refs?service=git-upload-pack", GitService::UploadPack),
1416 ("https://g1t.sh/g1t/g1t.git/git-receive-pack", GitService::ReceivePack),
1417 ("https://g1t.sh/g1t/g1t/git-upload-pack", GitService::UploadPack),
1418 ] {
1419 let git = parse(&Url::parse(address).unwrap()).unwrap();
1420 assert_eq!(git.path.namespace, "g1t", "{address}");
1421 let canonical = git.under("flagon-io");
1422 assert_eq!(
1423 canonical.path,
1424 RepoPath {
1425 namespace: "flagon-io".into(),
1426 name: "g1t".into(),
1427 },
1428 "{address}"
1429 );
1430 assert_eq!(canonical.service, service);
1431 assert_eq!(canonical.endpoint, git.endpoint);
1432 }
1433 }
1434
1435 #[test]
1436 fn a_renamed_workspace_keeps_the_rest_of_the_address() {
1437 let url = worker::Url::parse(
1438 "https://g1t.sh/acme/rocket.git/info/refs?service=git-upload-pack",
1439 )
1440 .unwrap();
1441 assert_eq!(
1442 with_namespace(&url, "acme-inc").as_deref(),
1443 Some("https://g1t.sh/acme-inc/rocket.git/info/refs?service=git-upload-pack")
1444 );
1445 let bare = worker::Url::parse("https://g1t.sh/acme").unwrap();
1446 assert_eq!(with_namespace(&bare, "acme-inc"), None);
1447 }
1448
1449 fn pkt(payload: &str) -> Vec<u8> {
1450 format!("{:04x}{payload}", payload.len() + 4).into_bytes()
1451 }
1452
1453 fn joined(parts: &[&[u8]]) -> Vec<u8> {
1454 parts.concat()
1455 }
1456
1457 #[test]
1458 fn a_fetch_with_haves_and_no_done_is_negotiating() {
1459 let request = |lines: &[&str]| {
1460 let mut body = joined(&[&pkt("command=fetch\n"), &pkt("object-format=sha1\n"), b"0001"]);
1461 for line in lines {
1462 body.extend(pkt(&format!("{line}\n")));
1463 }
1464 body.extend(b"0000");
1465 body
1466 };
1467 let want = "want 8407eba58b925619274d012258c2b474a5dbf012";
1468 let have = "have 55cd670a89a80df4fa9d9f0244c44fbd2ed1db8b";
1469 assert!(negotiating(&request(&["deepen 1", want, have])));
1470 assert!(!negotiating(&request(&[want, have, "done"])));
1471 assert!(!negotiating(&request(&[want, "done"])));
1472 let ls_refs = joined(&[&pkt("command=ls-refs\n"), b"0001", &pkt("have nothing\n"), b"0000"]);
1473 assert!(!negotiating(&ls_refs));
1474 }
1475
1476 #[test]
1477 fn acknowledgments_without_ready_end_the_answer() {
1478 // What the store sent a shallow fetch whose only `have` it did not
1479 // know, sideband-all framed: a NAK, then a pack anyway.
1480 let answer = joined(&[
1481 &pkt("\x01acknowledgments\n"),
1482 &pkt("\x01NAK\n"),
1483 b"0001",
1484 &pkt("\x01shallow-info\n"),
1485 &pkt("\x01shallow 8407eba58b925619274d012258c2b474a5dbf012\n"),
1486 b"0001",
1487 &pkt("\x01packfile\n"),
1488 ]);
1489 let cut = joined(&[&pkt("\x01acknowledgments\n"), &pkt("\x01NAK\n")]).len();
1490 assert_eq!(acknowledged(&answer), Acknowledged::CutAt(cut));
1491 // Not yet at the section's end.
1492 assert_eq!(acknowledged(&answer[..cut - 2]), Acknowledged::NeedMore);
1493 assert_eq!(acknowledged(&answer[..cut]), Acknowledged::NeedMore);
1494 // Without sideband framing too.
1495 let plain = joined(&[&pkt("acknowledgments\n"), &pkt("ACK abc\n"), b"0001", &pkt("packfile\n")]);
1496 assert!(matches!(acknowledged(&plain), Acknowledged::CutAt(_)));
1497 }
1498
1499 #[test]
1500 fn a_ready_store_or_a_plain_pack_streams_through() {
1501 let ready = joined(&[
1502 &pkt("\x01acknowledgments\n"),
1503 &pkt("\x01ACK bab14ff1b6d9c4918100098009747d776759a967\n"),
1504 &pkt("\x01ready\n"),
1505 b"0001",
1506 &pkt("\x01packfile\n"),
1507 ]);
1508 assert_eq!(acknowledged(&ready), Acknowledged::Whole);
1509 // Acknowledgments only, ended by a flush: already right.
1510 let only = joined(&[&pkt("acknowledgments\n"), &pkt("NAK\n"), b"0000"]);
1511 assert_eq!(acknowledged(&only), Acknowledged::Whole);
1512 let pack = joined(&[&pkt("\x01packfile\n"), b"0000"]);
1513 assert_eq!(acknowledged(&pack), Acknowledged::Whole);
1514 assert_eq!(acknowledged(b"00"), Acknowledged::NeedMore);
1515 }
1516
1517 #[test]
1518 fn pushed_branches_are_read_from_the_commands() {
1519 let old = "c71546fcd893ef8b0f57388b65e620d759705dda";
1520 let new = "4807077b296e6edbf410d55e72749d3e1170c291";
1521 let body = [
1522 pkt(&format!(
1523 "{old} {new} refs/heads/main\0 report-status side-band-64k\n"
1524 )),
1525 pkt(&format!("{ZERO_ID} {new} refs/heads/feature/x\n")),
1526 pkt(&format!("{old} {ZERO_ID} refs/heads/gone\n")),
1527 pkt(&format!("{ZERO_ID} {new} refs/tags/v1\n")),
1528 b"0000".to_vec(),
1529 b"PACK\0\0\0\x02\0\0\0\0".to_vec(),
1530 ]
1531 .concat();
1532 assert_eq!(
1533 pushed_branches(&body),
1534 [
1535 Pushed {
1536 git_ref: "refs/heads/main".to_owned(),
1537 before: Some(old.to_owned()),
1538 after: new.to_owned()
1539 },
1540 Pushed {
1541 git_ref: "refs/heads/feature/x".to_owned(),
1542 before: None,
1543 after: new.to_owned()
1544 },
1545 Pushed {
1546 git_ref: "refs/tags/v1".to_owned(),
1547 before: None,
1548 after: new.to_owned()
1549 },
1550 ]
1551 );
1552 assert_eq!(deleted_refs(&body), [("refs/heads/gone".to_owned(), old.to_owned())]);
1553 let tag = [pkt(&format!("{old} {ZERO_ID} refs/tags/v0\0 report-status\n")), pkt(&format!("{old} {ZERO_ID} refs/notes/x\n")), b"0000".to_vec()].concat();
1554 assert_eq!(deleted_refs(&tag), [("refs/tags/v0".to_owned(), old.to_owned())]);
1555 }
1556
1557 #[test]
1558 fn a_push_to_a_protected_branch_is_declined_with_the_reason() {
1559 let old = "c71546fcd893ef8b0f57388b65e620d759705dda";
1560 let new = "4807077b296e6edbf410d55e72749d3e1170c291";
1561 let body = [
1562 pkt(&format!("{old} {new} refs/heads/main\0 report-status\n")),
1563 pkt(&format!("{ZERO_ID} {new} refs/heads/feature\n")),
1564 b"0000".to_vec(),
1565 ]
1566 .concat();
1567 let report = String::from_utf8(refusal(&body, "main").unwrap()).unwrap();
1568 assert!(report.starts_with("000eunpack ok\n"));
1569 assert!(report.contains("ng refs/heads/main main is protected"));
1570 assert!(report.contains("ng refs/heads/feature not pushed"));
1571 assert!(report.ends_with("0000"));
1572 }
1573
1574 #[test]
1575 fn the_report_is_framed_for_a_client_that_asked_for_side_band() {
1576 let old = "c71546fcd893ef8b0f57388b65e620d759705dda";
1577 let body = [
1578 pkt(&format!(
1579 "{old} {ZERO_ID} refs/heads/main\0 report-status side-band-64k\n"
1580 )),
1581 b"0000".to_vec(),
1582 ]
1583 .concat();
1584 let report = refusal(&body, "main").unwrap();
1585 // A length, then channel 1, then the report itself.
1586 assert_eq!(report[4], 1);
1587 assert_eq!(&report[5..18], b"000eunpack ok");
1588 assert!(report.ends_with(b"00000000"));
1589 }
1590
1591 #[test]
1592 fn other_branches_and_a_first_push_are_let_through() {
1593 let old = "c71546fcd893ef8b0f57388b65e620d759705dda";
1594 let new = "4807077b296e6edbf410d55e72749d3e1170c291";
1595 let feature = [
1596 pkt(&format!("{old} {new} refs/heads/feature\0 report-status\n")),
1597 b"0000".to_vec(),
1598 ]
1599 .concat();
1600 assert!(refusal(&feature, "main").is_none());
1601 // An empty repository has to be able to receive its first commits.
1602 let first = [
1603 pkt(&format!(
1604 "{ZERO_ID} {new} refs/heads/main\0 report-status\n"
1605 )),
1606 b"0000".to_vec(),
1607 ]
1608 .concat();
1609 assert!(refusal(&first, "main").is_none());
1610 }
1611
1612 #[test]
1613 fn a_blocked_push_explains_itself_on_the_progress_channel() {
1614 let report = b"000eunpack ok\n0000".to_vec();
1615 let messages = vec!["g1t found a secret in this push, so nothing was pushed.".to_owned()];
1616 let body = framed(report.clone(), "report-status side-band-64k", &messages);
1617 // Channel 2 first, which git prints as `remote:` lines.
1618 assert_eq!(body[4], 2);
1619 assert!(String::from_utf8_lossy(&body).contains("so nothing was pushed.\n"));
1620 let at = body.windows(5).position(|w| w == b"000eu").unwrap();
1621 assert_eq!(body[at - 1], 1);
1622 assert!(body.ends_with(b"0000"));
1623 // A client without side-band gets the bare report.
1624 assert_eq!(framed(report.clone(), "report-status", &messages), report);
1625 }
1626
1627 #[test]
1628 fn a_fetch_request_names_no_branches() {
1629 assert!(
1630 pushed_branches(b"0032want c71546fcd893ef8b0f57388b65e620d759705dda\n0000").is_empty()
1631 );
1632 }
1633}