Merge pull request 'Support {s3,web}.root_domains for the Caddy on-demand TLS endpoint (<admin>/check?domain=xx)' (#610) from bug/support-root-domains-on-demand-tls into main

Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/610

5 files changed, 157 insertions, 36 deletions

diff --git a/doc/book/cookbook/reverse-proxy.md b/doc/book/cookbook/reverse-proxy.md
index bacac2ef..b715193e 100644
--- a/doc/book/cookbook/reverse-proxy.md
+++ b/doc/book/cookbook/reverse-proxy.md
@@ -469,3 +469,6 @@ https:// {
 	reverse_proxy localhost:3902 192.168.1.2:3902 example.tld:3902
 }
 ```
+
+More information on how this endpoint is implemented in Garage is available
+in the [Admin API Reference](@/documentation/reference-manual/admin-api.md) page.
diff --git a/doc/book/reference-manual/admin-api.md b/doc/book/reference-manual/admin-api.md
index 363bc886..6932ac60 100644
--- a/doc/book/reference-manual/admin-api.md
+++ b/doc/book/reference-manual/admin-api.md
@@ -39,11 +39,95 @@ Authorization: Bearer <token>
 
 ## Administration API endpoints
 
-### Metrics-related endpoints
-
-#### Metrics `GET /metrics`
+### Metrics `GET /metrics`
 
 Returns internal Garage metrics in Prometheus format.
+The metrics are directly documented when returned by the API.
+
+**Example:**
+
+```
+$ curl -i http://localhost:3903/metrics
+HTTP/1.1 200 OK
+content-type: text/plain; version=0.0.4
+content-length: 12145
+date: Tue, 08 Aug 2023 07:25:05 GMT
+
+# HELP api_admin_error_counter Number of API calls to the various Admin API endpoints that resulted in errors
+# TYPE api_admin_error_counter counter
+api_admin_error_counter{api_endpoint="CheckWebsiteEnabled",status_code="400"} 1
+api_admin_error_counter{api_endpoint="CheckWebsiteEnabled",status_code="404"} 3
+# HELP api_admin_request_counter Number of API calls to the various Admin API endpoints
+# TYPE api_admin_request_counter counter
+api_admin_request_counter{api_endpoint="CheckWebsiteEnabled"} 7
+api_admin_request_counter{api_endpoint="Health"} 3
+# HELP api_admin_request_duration Duration of API calls to the various Admin API endpoints
+...
+```
+
+### Health `GET /health`
+
+Returns `200 OK` if enough nodes are up to have a quorum (ie. serve requests),
+otherwise returns `503 Service Unavailable`.
+
+**Example:**
+
+```
+$ curl -i http://localhost:3903/health
+HTTP/1.1 200 OK
+content-type: text/plain
+content-length: 102
+date: Tue, 08 Aug 2023 07:22:38 GMT
+
+Garage is fully operational
+Consult the full health check API endpoint at /v0/health for more details
+```
+
+### On-demand TLS `GET /check`
+
+To prevent abuses for on-demand TLS, Caddy developpers have specified an endpoint that can be queried by the reverse proxy
+to know if a given domain is allowed to get a certificate. Garage implements this endpoints to tell if a given domain is handled by Garage or is garbage.
+
+Garage responds with the following logic:
+ - If the domain matches the pattern `<bucket-name>.<s3_api.root_domain>`, returns 200 OK
+ - If the domain matches the pattern `<bucket-name>.<s3_web.root_domain>` and website is configured for `<bucket>`, returns 200 OK
+ - If the domain matches the pattern `<bucket-name>` and website is configured for `<bucket>`, returns 200 OK
+ - Otherwise, returns 404 Not Found, 400 Bad Request or 5xx requests.
+
+*Note 1: because in the path-style URL mode, there is only one domain that is not known by Garage, hence it is not supported by this API endpoint.
+You must manually declare the domain in your reverse-proxy. Idem for K2V.*
+
+*Note 2: buckets in a user's namespace are not supported yet by this endpoint. This is a limitation of this endpoint currently.*
+
+**Example:** Suppose a Garage instance configured with `s3_api.root_domain = .s3.garage.localhost` and `s3_web.root_domain = .web.garage.localhost`.
+
+With a private `media` bucket (name in the global namespace, website is disabled), the endpoint will feature the following behavior:
+
+```
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=media.s3.garage.localhost
+200
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=media
+400
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=media.web.garage.localhost
+400
+```
+
+With a public `example.com` bucket (name in the global namespace, website is activated), the endpoint will feature the following behavior:
+
+```
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=example.com.s3.garage.localhost
+200
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=example.com
+200
+$ curl -so /dev/null -w "%{http_code}" http://localhost:3903/check?domain=example.com.web.garage.localhost
+200
+```
+
+
+**References:**
+ - [Using On-Demand TLS](https://caddyserver.com/docs/automatic-https#using-on-demand-tls)
+ - [Add option for a backend check to approve use of on-demand TLS](https://github.com/caddyserver/caddy/pull/1939)
+ - [Serving tens of thousands of domains over HTTPS with Caddy](https://caddy.community/t/serving-tens-of-thousands-of-domains-over-https-with-caddy/11179)
 
 ### Cluster operations
 
diff --git a/src/api/admin/api_server.rs b/src/api/admin/api_server.rs
index b0dfdfb7..8bf467dc 100644
--- a/src/api/admin/api_server.rs
+++ b/src/api/admin/api_server.rs
@@ -26,6 +26,7 @@ use crate::admin::cluster::*;
 use crate::admin::error::*;
 use crate::admin::key::*;
 use crate::admin::router::{Authorization, Endpoint};
+use crate::helpers::host_to_bucket;
 
 pub struct AdminApiServer {
 	garage: Arc<Garage>,
@@ -78,10 +79,7 @@ impl AdminApiServer {
 			.body(Body::empty())?)
 	}
 
-	async fn handle_check_website_enabled(
-		&self,
-		req: Request<Body>,
-	) -> Result<Response<Body>, Error> {
+	async fn handle_check_domain(&self, req: Request<Body>) -> Result<Response<Body>, Error> {
 		let query_params: HashMap<String, String> = req
 			.uri()
 			.query()
@@ -102,12 +100,43 @@ impl AdminApiServer {
 			.get("domain")
 			.ok_or_internal_error("Could not parse domain query string")?;
 
+		// Resolve bucket from domain name, inferring if the website must be activated for the
+		// domain to be valid.
+		let (bucket_name, must_check_website) = if let Some(bname) = self
+			.garage
+			.config
+			.s3_api
+			.root_domain
+			.as_ref()
+			.and_then(|rd| host_to_bucket(domain, rd))
+		{
+			(bname.to_string(), false)
+		} else if let Some(bname) = self
+			.garage
+			.config
+			.s3_web
+			.as_ref()
+			.and_then(|sw| host_to_bucket(domain, sw.root_domain.as_str()))
+		{
+			(bname.to_string(), true)
+		} else {
+			(domain.to_string(), true)
+		};
+
 		let bucket_id = self
 			.garage
 			.bucket_helper()
-			.resolve_global_bucket_name(domain)
+			.resolve_global_bucket_name(&bucket_name)
 			.await?
-			.ok_or(HelperError::NoSuchBucket(domain.to_string()))?;
+			.ok_or(HelperError::NoSuchBucket(bucket_name.to_string()))?;
+
+		if !must_check_website {
+			return Ok(Response::builder()
+				.status(StatusCode::OK)
+				.body(Body::from(format!(
+					"Domain '{domain}' is managed by Garage"
+				)))?);
+		}
 
 		let bucket = self
 			.garage
@@ -123,11 +152,11 @@ impl AdminApiServer {
 				Ok(Response::builder()
 					.status(StatusCode::OK)
 					.body(Body::from(format!(
-						"Bucket '{domain}' is authorized for website hosting"
+						"Domain '{domain}' is managed by Garage"
 					)))?)
 			}
 			None => Err(Error::bad_request(format!(
-				"Bucket '{domain}' is not authorized for website hosting"
+				"Domain '{domain}' is not managed by Garage"
 			))),
 		}
 	}
@@ -229,7 +258,7 @@ impl ApiHandler for AdminApiServer {
 
 		match endpoint {
 			Endpoint::Options => self.handle_options(&req),
-			Endpoint::CheckWebsiteEnabled => self.handle_check_website_enabled(req).await,
+			Endpoint::CheckDomain => self.handle_check_domain(req).await,
 			Endpoint::Health => self.handle_health(),
 			Endpoint::Metrics => self.handle_metrics(),
 			Endpoint::GetClusterStatus => handle_get_cluster_status(&self.garage).await,
diff --git a/src/api/admin/router.rs b/src/api/admin/router.rs
index 0dcb1546..0225f18b 100644
--- a/src/api/admin/router.rs
+++ b/src/api/admin/router.rs
@@ -17,7 +17,7 @@ router_match! {@func
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum Endpoint {
 	Options,
-	CheckWebsiteEnabled,
+	CheckDomain,
 	Health,
 	Metrics,
 	GetClusterStatus,
@@ -92,7 +92,7 @@ impl Endpoint {
 
 		let res = router_match!(@gen_path_parser (req.method(), path, query) [
 			OPTIONS _ => Options,
-			GET "/check" => CheckWebsiteEnabled,
+			GET "/check" => CheckDomain,
 			GET "/health" => Health,
 			GET "/metrics" => Metrics,
 			GET "/v0/status" => GetClusterStatus,
@@ -138,7 +138,7 @@ impl Endpoint {
 	pub fn authorization_type(&self) -> Authorization {
 		match self {
 			Self::Health => Authorization::None,
-			Self::CheckWebsiteEnabled => Authorization::None,
+			Self::CheckDomain => Authorization::None,
 			Self::Metrics => Authorization::MetricsToken,
 			_ => Authorization::AdminToken,
 		}
diff --git a/src/garage/tests/s3/website.rs b/src/garage/tests/s3/website.rs
index ab9b12b9..7c2b0deb 100644
--- a/src/garage/tests/s3/website.rs
+++ b/src/garage/tests/s3/website.rs
@@ -72,7 +72,7 @@ async fn test_website() {
 		res_body,
 		json!({
 			"code": "InvalidRequest",
-			"message": "Bad request: Bucket 'my-website' is not authorized for website hosting",
+			"message": "Bad request: Domain 'my-website' is not managed by Garage",
 			"region": "garage-integ-test",
 			"path": "/check",
 		})
@@ -91,24 +91,29 @@ async fn test_website() {
 		BODY.as_ref()
 	);
 
-	let admin_req = || {
-		Request::builder()
-			.method("GET")
-			.uri(format!(
-				"http://127.0.0.1:{0}/check?domain={1}",
-				ctx.garage.admin_port,
-				BCKT_NAME.to_string()
-			))
-			.body(Body::empty())
-			.unwrap()
-	};
-
-	let mut admin_resp = client.request(admin_req()).await.unwrap();
-	assert_eq!(admin_resp.status(), StatusCode::OK);
-	assert_eq!(
-		to_bytes(admin_resp.body_mut()).await.unwrap().as_ref(),
-		format!("Bucket '{BCKT_NAME}' is authorized for website hosting").as_bytes()
-	);
+	for bname in [
+		BCKT_NAME.to_string(),
+		format!("{BCKT_NAME}.web.garage"),
+		format!("{BCKT_NAME}.s3.garage"),
+	] {
+		let admin_req = || {
+			Request::builder()
+				.method("GET")
+				.uri(format!(
+					"http://127.0.0.1:{0}/check?domain={1}",
+					ctx.garage.admin_port, bname
+				))
+				.body(Body::empty())
+				.unwrap()
+		};
+
+		let mut admin_resp = client.request(admin_req()).await.unwrap();
+		assert_eq!(admin_resp.status(), StatusCode::OK);
+		assert_eq!(
+			to_bytes(admin_resp.body_mut()).await.unwrap().as_ref(),
+			format!("Domain '{bname}' is managed by Garage").as_bytes()
+		);
+	}
 
 	ctx.garage
 		.command()
@@ -142,7 +147,7 @@ async fn test_website() {
 		res_body,
 		json!({
 			"code": "InvalidRequest",
-			"message": "Bad request: Bucket 'my-website' is not authorized for website hosting",
+			"message": "Bad request: Domain 'my-website' is not managed by Garage",
 			"region": "garage-integ-test",
 			"path": "/check",
 		})
@@ -397,7 +402,7 @@ async fn test_website_s3_api() {
 }
 
 #[tokio::test]
-async fn test_website_check_website_enabled() {
+async fn test_website_check_domain() {
 	let ctx = common::context();
 
 	let client = Client::new();