fix(kms): resolve Vault auth from the environment at startup and add Kubernetes auth (#6095)

This commit is contained in:
唐小鸭
2026-08-17 14:12:39 +08:00
committed by GitHub
parent c04ee41cf0
commit d091554ffe
10 changed files with 862 additions and 104 deletions
+58
View File
@@ -293,6 +293,15 @@ enum StrictVaultAuthMethod {
#[serde(default)]
refresh_safety_window_secs: Option<u64>,
},
Kubernetes {
role: String,
#[serde(default)]
mount: Option<String>,
#[serde(default)]
jwt_path: Option<std::path::PathBuf>,
#[serde(default)]
refresh_safety_window_secs: Option<u64>,
},
TokenFile {
path: std::path::PathBuf,
#[serde(default)]
@@ -319,6 +328,17 @@ impl From<StrictVaultAuthMethod> for VaultAuthMethod {
mount: mount.unwrap_or_else(|| crate::config::DEFAULT_VAULT_APPROLE_MOUNT.to_string()),
refresh_safety_window_secs,
},
StrictVaultAuthMethod::Kubernetes {
role,
mount,
jwt_path,
refresh_safety_window_secs,
} => Self::Kubernetes {
role,
mount: mount.unwrap_or_else(|| crate::config::DEFAULT_VAULT_KUBERNETES_MOUNT.to_string()),
jwt_path: jwt_path.unwrap_or_else(|| std::path::PathBuf::from(crate::config::DEFAULT_VAULT_KUBERNETES_JWT_PATH)),
refresh_safety_window_secs,
},
StrictVaultAuthMethod::TokenFile {
path,
poll_interval_secs,
@@ -499,6 +519,7 @@ impl From<&KmsConfig> for KmsConfigSummary {
auth_method_type: match &vault_config.auth_method {
VaultAuthMethod::Token { .. } => "token".to_string(),
VaultAuthMethod::AppRole { .. } => "approle".to_string(),
VaultAuthMethod::Kubernetes { .. } => "kubernetes".to_string(),
VaultAuthMethod::TokenFile { .. } => "token_file".to_string(),
},
has_stored_credentials: true,
@@ -513,6 +534,7 @@ impl From<&KmsConfig> for KmsConfigSummary {
auth_method_type: match &vault_config.auth_method {
VaultAuthMethod::Token { .. } => "token".to_string(),
VaultAuthMethod::AppRole { .. } => "approle".to_string(),
VaultAuthMethod::Kubernetes { .. } => "kubernetes".to_string(),
VaultAuthMethod::TokenFile { .. } => "token_file".to_string(),
},
has_stored_credentials: true,
@@ -901,6 +923,42 @@ mod tests {
assert!(request.to_kms_config().validate().is_ok());
}
/// The admin API reaches Kubernetes auth with the role alone; the mount and
/// the projected token path fall back to the cluster defaults, so a Tenant
/// manifest carries no credential and no cluster-specific paths.
#[test]
fn test_deserialize_vault_configure_request_accepts_kubernetes_auth() {
let raw = serde_json::json!({
"backend_type": "vault-transit",
"address": "https://vault.example.com:8200",
"mount_path": "rustfs",
"auth_method": { "Kubernetes": { "role": "rustfs" } }
});
let request: ConfigureKmsRequest = serde_json::from_value(raw).expect("kubernetes auth should deserialize");
let config = request.to_kms_config();
config.validate().expect("kubernetes auth must validate");
let vault = config.vault_transit_config().expect("vault transit backend config");
let VaultAuthMethod::Kubernetes {
role, mount, jwt_path, ..
} = &vault.auth_method
else {
panic!("expected Kubernetes auth, got {:?}", vault.auth_method);
};
assert_eq!(role, "rustfs");
assert_eq!(mount, crate::config::DEFAULT_VAULT_KUBERNETES_MOUNT);
assert_eq!(jwt_path, std::path::Path::new(crate::config::DEFAULT_VAULT_KUBERNETES_JWT_PATH));
let unknown_field = serde_json::json!({
"backend_type": "vault-transit",
"address": "https://vault.example.com:8200",
"auth_method": { "Kubernetes": { "role": "rustfs", "service_account": "rustfs" } }
});
serde_json::from_value::<ConfigureKmsRequest>(unknown_field)
.expect_err("an unknown auth field must be rejected rather than silently dropped");
}
#[test]
fn test_deserialize_aws_configure_request_accepts_type_aliases() {
for backend_type in ["AWS", "AwsKms", "aws", "aws-kms", "aws_kms"] {
+1
View File
@@ -550,6 +550,7 @@ impl VaultKmsClient {
address: config.address.clone(),
namespace: config.namespace.clone(),
attempt_timeout: kms_config.effective_timeout(),
skip_tls_verify: config.tls.as_ref().is_some_and(|tls| tls.skip_verify),
};
let source = token_source_for(&config.auth_method, &settings)?;
let policy = VaultCredentialPolicy::from_kms_config(
+271 -5
View File
@@ -326,6 +326,97 @@ impl fmt::Debug for AppRoleLogin {
}
}
/// Token source for [`VaultAuthMethod::Kubernetes`]: exchanges the pod's
/// projected ServiceAccount token for a lease-bound Vault token.
///
/// The JWT is re-read on every login because the kubelet rotates a projected
/// token well inside the pod's lifetime; caching it would strand the source on
/// an expired assertion once the current Vault token can no longer be renewed.
///
/// Unlike [`TokenFileSource`], the file mode is not checked: the kubelet owns
/// the projected token and mounts it world-readable by default, so rejecting
/// group/other bits would refuse every standard pod rather than catch a
/// deployment error.
pub(crate) struct KubernetesLogin {
/// Unauthenticated client used only for the login exchange.
login_client: VaultClient,
mount: String,
role: String,
jwt_path: PathBuf,
}
impl KubernetesLogin {
pub(crate) fn new(settings: &VaultConnectionSettings, mount: String, role: String, jwt_path: PathBuf) -> Result<Self> {
Ok(Self {
login_client: settings.build_login_client()?,
mount,
role,
jwt_path,
})
}
/// Read the ServiceAccount token for one login attempt.
///
/// Mirrors [`AppRoleLogin::resolve_secret_id`]: a read failure is fatal for
/// the attempt but the refresh loop keeps retrying, so a token the kubelet
/// has not projected yet heals the source without a restart.
async fn resolve_jwt(&self) -> AttemptResult<SecretString> {
let mut raw = tokio::fs::read_to_string(&self.jwt_path)
.await
.map_err(|error| AttemptError {
class: ErrorClass::Fatal,
error: KmsError::configuration_error(format!(
"Failed to read Kubernetes ServiceAccount token {}: {error}",
self.jwt_path.display()
)),
})?;
let trimmed = raw.trim();
if trimmed.is_empty() {
raw.zeroize();
return Err(AttemptError {
class: ErrorClass::Fatal,
error: KmsError::configuration_error(format!(
"Kubernetes ServiceAccount token {} is empty",
self.jwt_path.display()
)),
});
}
let jwt = SecretString::new(trimmed.to_string());
raw.zeroize();
Ok(jwt)
}
}
#[async_trait]
impl TokenSource for KubernetesLogin {
async fn acquire(&self) -> AttemptResult<TokenLease> {
let jwt = self.resolve_jwt().await?;
let auth = vaultrs::auth::kubernetes::login(&self.login_client, &self.mount, &self.role, jwt.expose())
.await
.map_err(|error| attempt_error("Kubernetes login", error))?;
Ok(TokenLease::from_auth(auth))
}
async fn renew(&self, client: &VaultClient) -> AttemptResult<TokenLease> {
let auth = vaultrs::token::renew_self(client, None)
.await
.map_err(|error| attempt_error("token renewal", error))?;
Ok(TokenLease::from_auth(auth))
}
}
impl fmt::Debug for KubernetesLogin {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
// The login client embeds Vault client settings and must stay out of
// Debug output; the role name is not a secret, and the JWT is never held.
f.debug_struct("KubernetesLogin")
.field("mount", &self.mount)
.field("role", &self.role)
.field("jwt_path", &self.jwt_path)
.finish_non_exhaustive()
}
}
/// Token source for [`VaultAuthMethod::TokenFile`]: reads an agent-managed
/// token file (for example a Vault Agent auto-auth sink).
///
@@ -464,6 +555,9 @@ pub(crate) fn token_source_for(
secret_id.clone(),
secret_id_file.clone(),
)?)),
VaultAuthMethod::Kubernetes {
role, mount, jwt_path, ..
} => Ok(Box::new(KubernetesLogin::new(settings, mount.clone(), role.clone(), jwt_path.clone())?)),
VaultAuthMethod::TokenFile {
path,
poll_interval_secs,
@@ -486,6 +580,9 @@ pub(crate) struct VaultConnectionSettings {
pub(crate) namespace: Option<String>,
/// Per-attempt HTTP timeout applied to the underlying reqwest client.
pub(crate) attempt_timeout: Duration,
/// Whether to accept an unverified Vault server certificate. Gated on
/// `allow_insecure_dev_defaults` by `KmsConfig::validate`.
pub(crate) skip_tls_verify: bool,
}
impl VaultConnectionSettings {
@@ -499,6 +596,11 @@ impl VaultConnectionSettings {
// operation-level retry policy.
settings_builder.timeout(Some(self.attempt_timeout));
settings_builder.token(token);
// Always set explicitly: left unset, vaultrs derives this from its own
// VAULT_SKIP_VERIFY variable, so a stray value in the environment would
// disable certificate verification behind the KMS configuration and its
// insecure-defaults gate.
settings_builder.verify(!self.skip_tls_verify);
if let Some(namespace) = &self.namespace {
settings_builder.namespace(Some(namespace.clone()));
@@ -551,6 +653,10 @@ impl VaultCredentialPolicy {
refresh_safety_window_secs: Some(secs),
..
}
| VaultAuthMethod::Kubernetes {
refresh_safety_window_secs: Some(secs),
..
}
| VaultAuthMethod::TokenFile {
refresh_safety_window_secs: Some(secs),
..
@@ -584,15 +690,25 @@ pub(crate) struct VaultClientHandle {
impl VaultClientHandle {
/// Absolute expiry of this generation's token.
///
/// `lease.ttl` is built from the `lease_duration` the Vault server sent, so
/// a value too large to add to `issued_at` would panic on the bare `+`. A
/// TTL that cannot be represented is indistinguishable from no expiry, so it
/// collapses to `None` — the same answer already given for the zero-lease
/// tokens Vault issues, which keeps the token in use and still fully
/// validated by Vault on every call.
fn expires_at(&self) -> Option<Instant> {
self.lease.map(|lease| self.issued_at + lease.ttl)
self.lease.and_then(|lease| self.issued_at.checked_add(lease.ttl))
}
/// When the renewal task should refresh this generation: half the TTL,
/// leaving the second half as budget for retries before the fail-closed
/// window is reached.
///
/// Unrepresentable TTLs collapse to `None` as in [`Self::expires_at`],
/// leaving a token that never expires with nothing to renew.
fn renew_at(&self) -> Option<Instant> {
self.lease.map(|lease| self.issued_at + lease.ttl / 2)
self.lease.and_then(|lease| self.issued_at.checked_add(lease.ttl / 2))
}
}
@@ -662,7 +778,7 @@ impl VaultCredentialProvider {
let handle = self.current.load_full();
if let Some(expires_at) = handle.expires_at() {
let now = Instant::now();
if now + self.policy.safety_window >= expires_at {
if self.inside_safety_window(now, expires_at) {
return Err(KmsError::credentials_unavailable(format!(
"Vault token (generation {}) is within {:?} of expiry and has not been refreshed; refusing to use it",
handle.generation, self.policy.safety_window
@@ -672,6 +788,18 @@ impl VaultCredentialProvider {
Ok(handle)
}
/// Whether the token expiring at `expires_at` is close enough to refuse.
///
/// `safety_window` reaches here from persisted configuration, so it is not
/// guaranteed to have passed this version's validation: a window too large
/// to add to the current instant would panic on the bare `+`. Such a window
/// means every token is always inside it, so saturating to "refuse" is both
/// the fail-closed answer and the one the arithmetic was reaching for.
fn inside_safety_window(&self, now: Instant, expires_at: Instant) -> bool {
now.checked_add(self.policy.safety_window)
.is_none_or(|deadline| deadline >= expires_at)
}
/// Publish the credential gauges for the generation currently installed.
///
/// The fail-closed gauge re-evaluates the very gate
@@ -683,7 +811,7 @@ impl VaultCredentialProvider {
let fail_closed = match handle.expires_at() {
Some(expires_at) => {
metrics::gauge!(METRIC_TOKEN_TTL_SECONDS).set(expires_at.saturating_duration_since(now).as_secs_f64());
now + self.policy.safety_window >= expires_at
self.inside_safety_window(now, expires_at)
}
// A generation without an expiry has no remaining TTL to report
// and can never lapse, so it can never fail closed either.
@@ -860,7 +988,7 @@ impl Drop for CredentialTaskHandle {
#[cfg(test)]
mod tests {
use super::*;
use crate::config::REDACTED_SECRET;
use crate::config::{DEFAULT_VAULT_KUBERNETES_MOUNT, REDACTED_SECRET};
use std::sync::atomic::{AtomicBool, AtomicU32, Ordering};
const TEST_TOKEN: &str = "vault-token-debug-leak-canary";
@@ -871,6 +999,7 @@ mod tests {
address: "http://127.0.0.1:8200".to_string(),
namespace: Some("team-namespace".to_string()),
attempt_timeout: Duration::from_secs(30),
skip_tls_verify: false,
}
}
@@ -1057,6 +1186,143 @@ mod tests {
assert!(format!("{source:?}").contains("AppRoleLogin"));
}
#[tokio::test]
async fn test_kubernetes_auth_method_maps_to_login_source() {
let settings = test_settings();
let source = token_source_for(&VaultAuthMethod::kubernetes("rustfs".to_string()), &settings)
.expect("kubernetes auth must map to a login source");
assert!(format!("{source:?}").contains("KubernetesLogin"));
}
/// `refresh_safety_window_secs` is operator-supplied and reaches the request
/// path from persisted configuration, so the fail-closed comparison must
/// survive a window too large to add to the current instant. Before the
/// checked arithmetic this panicked with "overflow when adding duration to
/// instant" on the first request after a lease-bearing login.
#[tokio::test]
async fn test_current_refuses_rather_than_panics_on_an_unrepresentable_safety_window() {
let (provider, _state) = scripted_provider(
Duration::from_secs(60),
true,
test_policy(Duration::from_secs(u64::MAX), Duration::from_secs(5)),
)
.await;
let error = provider
.current()
.expect_err("a window wider than any lease must refuse the token");
assert!(
matches!(error, KmsError::CredentialsUnavailable { .. }),
"expected CredentialsUnavailable, got {error:?}"
);
}
/// `lease_duration` is a bare u64 straight off the Vault response and forms
/// the other side of the same comparison, so an absurd one must not panic
/// either. It is indistinguishable from a non-expiring token, which is how
/// the zero-lease case already behaves.
#[tokio::test]
async fn test_an_unrepresentable_lease_is_treated_as_non_expiring() {
let (provider, _state) = scripted_provider(
Duration::from_secs(u64::MAX),
true,
test_policy(Duration::from_secs(30), Duration::from_secs(5)),
)
.await;
provider
.current()
.expect("a token whose expiry cannot be represented must stay usable");
}
/// The configured flag has to reach the HTTP client, not just the config
/// struct: every generation (authenticated and login) builds its own client,
/// and a Vault with a self-signed certificate fails the handshake unless
/// each one carries the setting.
#[test]
fn test_skip_tls_verify_reaches_every_vault_client_generation() {
for skip_tls_verify in [false, true] {
let settings = VaultConnectionSettings {
address: "https://vault.example.com:8200".to_string(),
namespace: None,
attempt_timeout: Duration::from_secs(30),
skip_tls_verify,
};
let authenticated = settings.build_client(TEST_TOKEN).expect("authenticated client must build");
assert_eq!(authenticated.settings.verify, !skip_tls_verify);
let login = settings.build_login_client().expect("login client must build");
assert_eq!(login.settings.verify, !skip_tls_verify);
}
}
/// vaultrs derives `verify` from its own VAULT_SKIP_VERIFY variable when the
/// builder leaves it unset, which would disable certificate verification
/// without passing the KMS insecure-defaults gate.
#[test]
fn test_vaultrs_skip_verify_env_cannot_override_the_configured_setting() {
temp_env::with_var("VAULT_SKIP_VERIFY", Some("true"), || {
let client = test_settings().build_client(TEST_TOKEN).expect("client must build");
assert!(
client.settings.verify,
"a stray VAULT_SKIP_VERIFY must not disable verification behind the KMS configuration"
);
});
}
/// The projected token is read fresh per login attempt and trimmed, so a
/// kubelet rotation is picked up without a restart and a trailing newline
/// does not corrupt the assertion sent to Vault.
#[tokio::test]
async fn test_kubernetes_login_rereads_and_trims_the_service_account_token() {
let dir = tempfile::tempdir().expect("temp dir");
let path = dir.path().join("token");
tokio::fs::write(&path, " first-jwt\n").await.expect("write token");
let login = KubernetesLogin::new(
&test_settings(),
DEFAULT_VAULT_KUBERNETES_MOUNT.to_string(),
"rustfs".to_string(),
path.clone(),
)
.expect("login source must build");
assert_eq!(login.resolve_jwt().await.expect("first read").expose(), "first-jwt");
tokio::fs::write(&path, "rotated-jwt").await.expect("rotate token");
assert_eq!(
login.resolve_jwt().await.expect("second read").expose(),
"rotated-jwt",
"a rotated projected token must be picked up without a restart"
);
}
/// The ServiceAccount token is re-read per attempt, so an unreadable or
/// empty one fails that attempt without reaching Vault; the refresh loop
/// keeps retrying, which is what lets a late projection heal the source.
#[tokio::test]
async fn test_kubernetes_login_rejects_an_unusable_service_account_token() {
let dir = tempfile::tempdir().expect("temp dir");
let missing = dir.path().join("absent-token");
let empty = dir.path().join("empty-token");
tokio::fs::write(&empty, " \n").await.expect("write empty token");
for (path, expected) in [(missing, "Failed to read"), (empty, "is empty")] {
let login =
KubernetesLogin::new(&test_settings(), DEFAULT_VAULT_KUBERNETES_MOUNT.to_string(), "rustfs".to_string(), path)
.expect("login source must build");
let error = login
.acquire()
.await
.expect_err("an unusable ServiceAccount token must fail the attempt");
assert!(matches!(error.class, ErrorClass::Fatal));
assert!(error.error.to_string().contains(expected), "got {}", error.error);
}
}
#[tokio::test(start_paused = true)]
async fn test_renewal_task_renews_at_half_ttl() {
let (provider, state) = scripted_provider(
+1
View File
@@ -415,6 +415,7 @@ impl VaultTransitKmsClient {
address: config.address.clone(),
namespace: config.namespace.clone(),
attempt_timeout: kms_config.effective_timeout(),
skip_tls_verify: config.tls.as_ref().is_some_and(|tls| tls.skip_verify),
};
let source = token_source_for(&config.auth_method, &settings)?;
let policy = VaultCredentialPolicy::from_kms_config(
+4
View File
@@ -450,6 +450,10 @@ impl VaultRestoreClient {
address: target.address.clone(),
namespace: target.namespace.clone(),
attempt_timeout: kms_config.effective_timeout(),
// A restore target carries no TLS settings, so certificates are
// always verified: recovery is the last path that should accept an
// unauthenticated Vault.
skip_tls_verify: false,
};
let source = token_source_for(&target.auth_method, &settings)?;
let policy = VaultCredentialPolicy::from_kms_config(
+295 -54
View File
@@ -25,6 +25,10 @@ use url::Url;
pub const ENV_KMS_ALLOW_INSECURE_DEV_DEFAULTS: &str = "RUSTFS_KMS_ALLOW_INSECURE_DEV_DEFAULTS";
pub const ENV_KMS_ALLOW_IMMEDIATE_DELETION: &str = "RUSTFS_KMS_ALLOW_IMMEDIATE_DELETION";
pub const ENV_KMS_VAULT_ADDRESS: &str = "RUSTFS_KMS_VAULT_ADDRESS";
pub const ENV_KMS_VAULT_TOKEN: &str = "RUSTFS_KMS_VAULT_TOKEN";
pub const ENV_KMS_VAULT_NAMESPACE: &str = "RUSTFS_KMS_VAULT_NAMESPACE";
pub const ENV_KMS_VAULT_MOUNT_PATH: &str = "RUSTFS_KMS_VAULT_MOUNT_PATH";
pub const ENV_KMS_VAULT_SKIP_TLS_VERIFY: &str = "RUSTFS_KMS_VAULT_SKIP_TLS_VERIFY";
pub const ENV_KMS_VAULT_TRANSIT_METADATA_KV_MOUNT: &str = "RUSTFS_KMS_VAULT_TRANSIT_METADATA_KV_MOUNT";
pub const ENV_KMS_VAULT_TRANSIT_METADATA_PREFIX: &str = "RUSTFS_KMS_VAULT_TRANSIT_METADATA_PREFIX";
@@ -35,6 +39,9 @@ pub const ENV_KMS_VAULT_APPROLE_SECRET_ID: &str = "RUSTFS_KMS_VAULT_APPROLE_SECR
pub const ENV_KMS_VAULT_APPROLE_SECRET_ID_FILE: &str = "RUSTFS_KMS_VAULT_APPROLE_SECRET_ID_FILE";
pub const ENV_KMS_VAULT_APPROLE_MOUNT: &str = "RUSTFS_KMS_VAULT_APPROLE_MOUNT";
pub const ENV_KMS_VAULT_TOKEN_FILE: &str = "RUSTFS_KMS_VAULT_TOKEN_FILE";
pub const ENV_KMS_VAULT_KUBERNETES_ROLE: &str = "RUSTFS_KMS_VAULT_KUBERNETES_ROLE";
pub const ENV_KMS_VAULT_KUBERNETES_MOUNT: &str = "RUSTFS_KMS_VAULT_KUBERNETES_MOUNT";
pub const ENV_KMS_VAULT_KUBERNETES_JWT_PATH: &str = "RUSTFS_KMS_VAULT_KUBERNETES_JWT_PATH";
pub const ENV_KMS_AWS_REGION: &str = "RUSTFS_KMS_AWS_REGION";
pub const ENV_KMS_AWS_ENDPOINT_URL: &str = "RUSTFS_KMS_AWS_ENDPOINT_URL";
/// Age in whole seconds beyond which a key is reported as due for rotation;
@@ -45,6 +52,9 @@ pub const ENV_KMS_ROTATION_MAX_WRAPS: &str = "RUSTFS_KMS_ROTATION_MAX_WRAPS";
pub const DEFAULT_VAULT_TRANSIT_METADATA_KV_MOUNT: &str = "secret";
pub const DEFAULT_VAULT_TRANSIT_METADATA_KEY_PREFIX: &str = "rustfs/kms/transit-metadata";
pub const DEFAULT_VAULT_APPROLE_MOUNT: &str = "approle";
pub const DEFAULT_VAULT_KUBERNETES_MOUNT: &str = "kubernetes";
/// Where the kubelet projects a pod's ServiceAccount token by default.
pub const DEFAULT_VAULT_KUBERNETES_JWT_PATH: &str = "/var/run/secrets/kubernetes.io/serviceaccount/token";
/// Upper bound applied to `KmsConfig::timeout` when deriving backend behavior.
///
@@ -84,6 +94,14 @@ fn default_vault_approle_mount() -> String {
DEFAULT_VAULT_APPROLE_MOUNT.to_string()
}
fn default_vault_kubernetes_mount() -> String {
DEFAULT_VAULT_KUBERNETES_MOUNT.to_string()
}
fn default_vault_kubernetes_jwt_path() -> PathBuf {
PathBuf::from(DEFAULT_VAULT_KUBERNETES_JWT_PATH)
}
pub const KMS_CONFIG_REDACTION_RULES: &[RedactionRule] = &[
RedactionRule::new("kms.local.master_key", RedactionLevel::Secret, "local backend key encryption material"),
RedactionRule::new("kms.vault.token", RedactionLevel::Secret, "vault authentication token"),
@@ -490,6 +508,23 @@ pub enum VaultAuthMethod {
#[serde(default)]
refresh_safety_window_secs: Option<u64>,
},
/// Kubernetes authentication: the pod's ServiceAccount token is exchanged
/// for a lease-bound Vault token that is renewed in the background.
Kubernetes {
/// Vault role bound to this ServiceAccount.
role: String,
/// Kubernetes auth engine mount path.
#[serde(default = "default_vault_kubernetes_mount")]
mount: String,
/// Projected ServiceAccount token to present. Re-read on every login so
/// a token the kubelet rotates is picked up without a restart.
#[serde(default = "default_vault_kubernetes_jwt_path")]
jwt_path: PathBuf,
/// Fail-closed margin in seconds, as on `AppRole`. Defaults to the
/// per-attempt timeout.
#[serde(default)]
refresh_safety_window_secs: Option<u64>,
},
/// Agent-managed token file (for example a Vault Agent auto-auth sink):
/// the token is read from `path` and re-read periodically so a token
/// rotated by the agent is picked up without a restart.
@@ -520,6 +555,16 @@ impl VaultAuthMethod {
}
}
/// Kubernetes authentication with the default mount and projected token path.
pub fn kubernetes(role: String) -> Self {
Self::Kubernetes {
role,
mount: default_vault_kubernetes_mount(),
jwt_path: default_vault_kubernetes_jwt_path(),
refresh_safety_window_secs: None,
}
}
/// Agent-managed token file with the default poll interval.
pub fn token_file(path: PathBuf) -> Self {
Self::TokenFile {
@@ -548,6 +593,20 @@ impl fmt::Debug for VaultAuthMethod {
.field("mount", mount)
.field("refresh_safety_window_secs", refresh_safety_window_secs)
.finish(),
// No redaction: the role and mount name a Vault binding, and the
// ServiceAccount token itself is never held on this type.
Self::Kubernetes {
role,
mount,
jwt_path,
refresh_safety_window_secs,
} => f
.debug_struct("Kubernetes")
.field("role", role)
.field("mount", mount)
.field("jwt_path", jwt_path)
.field("refresh_safety_window_secs", refresh_safety_window_secs)
.finish(),
Self::TokenFile {
path,
poll_interval_secs,
@@ -1028,50 +1087,12 @@ impl KmsConfig {
});
}
KmsBackend::VaultKv2 => {
let address = get_env_str("RUSTFS_KMS_VAULT_ADDRESS", "http://localhost:8200");
let auth_method = vault_auth_method_from_env()?;
let skip_tls_verify = get_env_bool(ENV_KMS_VAULT_SKIP_TLS_VERIFY, false);
let mount_path = match get_env_opt_str("RUSTFS_KMS_VAULT_MOUNT_PATH") {
Some(path) => {
tracing::warn!(
"RUSTFS_KMS_VAULT_MOUNT_PATH is deprecated for the Vault KV2 backend: it never calls the Transit engine and the value is stored but unused"
);
path
}
None => default_vault_kv2_mount_path(),
};
config.backend_config = BackendConfig::VaultKv2(Box::new(VaultConfig {
address,
auth_method,
namespace: get_env_opt_str("RUSTFS_KMS_VAULT_NAMESPACE"),
mount_path,
kv_mount: get_env_str("RUSTFS_KMS_VAULT_KV_MOUNT", "secret"),
key_path_prefix: get_env_str("RUSTFS_KMS_VAULT_KEY_PREFIX", "rustfs/kms/keys"),
tls: vault_tls_config(skip_tls_verify),
}));
config.backend_config =
BackendConfig::VaultKv2(Box::new(vault_kv2_config_from_env(VaultCliOverrides::default())?));
}
KmsBackend::VaultTransit => {
let address = get_env_str("RUSTFS_KMS_VAULT_ADDRESS", "http://localhost:8200");
let auth_method = vault_auth_method_from_env()?;
let skip_tls_verify = get_env_bool(ENV_KMS_VAULT_SKIP_TLS_VERIFY, false);
config.backend_config = BackendConfig::VaultTransit(Box::new(VaultTransitConfig {
address,
auth_method,
namespace: get_env_opt_str("RUSTFS_KMS_VAULT_NAMESPACE"),
mount_path: get_env_str("RUSTFS_KMS_VAULT_MOUNT_PATH", "transit"),
metadata_kv_mount: get_env_str(
ENV_KMS_VAULT_TRANSIT_METADATA_KV_MOUNT,
DEFAULT_VAULT_TRANSIT_METADATA_KV_MOUNT,
),
metadata_key_prefix: get_env_str(
ENV_KMS_VAULT_TRANSIT_METADATA_PREFIX,
DEFAULT_VAULT_TRANSIT_METADATA_KEY_PREFIX,
),
tls: vault_tls_config(skip_tls_verify),
}));
config.backend_config =
BackendConfig::VaultTransit(Box::new(vault_transit_config_from_env(VaultCliOverrides::default())?));
}
KmsBackend::Static => {
// Read from file first, then fall back to direct env var
@@ -1202,6 +1223,78 @@ fn is_under_temp_dir(path: &Path) -> bool {
path.starts_with(std::env::temp_dir())
}
/// Command-line values that take precedence over the matching environment
/// variables when assembling a Vault backend configuration.
///
/// Every field has a `RUSTFS_KMS_VAULT_*` equivalent that the CLI layer already
/// reads, so these are only set when the operator passed an explicit flag.
///
/// Deliberately not `Debug`: `token` holds the raw Vault token, and the
/// redacting `Debug` impls elsewhere in this module exist because a derived one
/// would print it. Denying the derive makes a future `{overrides:?}` a compile
/// error instead of a leak.
#[derive(Default, Clone, Copy)]
pub struct VaultCliOverrides<'a> {
pub address: Option<&'a str>,
pub token: Option<&'a str>,
pub mount_path: Option<&'a str>,
}
/// Assemble the Vault KV2 backend configuration from the environment.
///
/// Shared by [`KmsConfig::from_env`] and the server's command-line startup path
/// so both resolve the same auth method, namespace, TLS and mount settings.
pub fn vault_kv2_config_from_env(overrides: VaultCliOverrides<'_>) -> Result<VaultConfig> {
let mount_path = match overrides
.mount_path
.map(str::to_string)
.or_else(|| get_env_opt_str(ENV_KMS_VAULT_MOUNT_PATH))
{
Some(path) => {
tracing::warn!(
"RUSTFS_KMS_VAULT_MOUNT_PATH is deprecated for the Vault KV2 backend: it never calls the Transit engine and the value is stored but unused"
);
path
}
None => default_vault_kv2_mount_path(),
};
Ok(VaultConfig {
address: vault_address_from_env(overrides.address),
auth_method: vault_auth_method_from_env(overrides.token)?,
namespace: get_env_opt_str(ENV_KMS_VAULT_NAMESPACE),
mount_path,
kv_mount: get_env_str("RUSTFS_KMS_VAULT_KV_MOUNT", "secret"),
key_path_prefix: get_env_str("RUSTFS_KMS_VAULT_KEY_PREFIX", "rustfs/kms/keys"),
tls: vault_tls_config(get_env_bool(ENV_KMS_VAULT_SKIP_TLS_VERIFY, false)),
})
}
/// Assemble the Vault Transit backend configuration from the environment.
///
/// Companion to [`vault_kv2_config_from_env`]; see there for why both entry
/// points share it.
pub fn vault_transit_config_from_env(overrides: VaultCliOverrides<'_>) -> Result<VaultTransitConfig> {
Ok(VaultTransitConfig {
address: vault_address_from_env(overrides.address),
auth_method: vault_auth_method_from_env(overrides.token)?,
namespace: get_env_opt_str(ENV_KMS_VAULT_NAMESPACE),
mount_path: overrides
.mount_path
.map(str::to_string)
.unwrap_or_else(|| get_env_str(ENV_KMS_VAULT_MOUNT_PATH, "transit")),
metadata_kv_mount: get_env_str(ENV_KMS_VAULT_TRANSIT_METADATA_KV_MOUNT, DEFAULT_VAULT_TRANSIT_METADATA_KV_MOUNT),
metadata_key_prefix: get_env_str(ENV_KMS_VAULT_TRANSIT_METADATA_PREFIX, DEFAULT_VAULT_TRANSIT_METADATA_KEY_PREFIX),
tls: vault_tls_config(get_env_bool(ENV_KMS_VAULT_SKIP_TLS_VERIFY, false)),
})
}
fn vault_address_from_env(override_value: Option<&str>) -> String {
override_value
.map(str::to_string)
.unwrap_or_else(|| get_env_str(ENV_KMS_VAULT_ADDRESS, "http://localhost:8200"))
}
/// Resolve the Vault auth method from environment variables.
///
/// Setting `RUSTFS_KMS_VAULT_APPROLE_ROLE_ID` selects AppRole authentication;
@@ -1209,27 +1302,59 @@ fn is_under_temp_dir(path: &Path) -> bool {
/// (re-read on every login, mirroring the `RUSTFS_KMS_STATIC_SECRET_KEY_FILE`
/// precedent) or inline from `RUSTFS_KMS_VAULT_APPROLE_SECRET_ID`, with the
/// file taking precedence. Without a role id the legacy token flow applies.
fn vault_auth_method_from_env() -> Result<VaultAuthMethod> {
///
/// `RUSTFS_KMS_VAULT_KUBERNETES_ROLE` selects Kubernetes authentication, which
/// presents the pod's projected ServiceAccount token.
///
/// `token_override` carries a token supplied on the command line; it stands in
/// for `RUSTFS_KMS_VAULT_TOKEN` everywhere below, including the conflict checks,
/// so a flag and the variable it mirrors select the same method.
fn vault_auth_method_from_env(token_override: Option<&str>) -> Result<VaultAuthMethod> {
let token = token_override
.map(str::to_string)
.or_else(|| get_env_opt_str(ENV_KMS_VAULT_TOKEN));
let role_id = get_env_opt_str(ENV_KMS_VAULT_APPROLE_ROLE_ID);
let kubernetes_role = get_env_opt_str(ENV_KMS_VAULT_KUBERNETES_ROLE);
if let Some(token_file) = get_env_opt_str(ENV_KMS_VAULT_TOKEN_FILE) {
// A token file names one authoritative credential source; combining it
// with another one would leave the effective identity ambiguous, so
// that is a configuration error rather than a precedence rule.
if get_env_opt_str(ENV_KMS_VAULT_APPROLE_ROLE_ID).is_some() {
return Err(KmsError::configuration_error(format!(
"{ENV_KMS_VAULT_TOKEN_FILE} cannot be combined with {ENV_KMS_VAULT_APPROLE_ROLE_ID}; configure exactly one Vault auth method"
)));
}
if get_env_opt_str("RUSTFS_KMS_VAULT_TOKEN").is_some() {
return Err(KmsError::configuration_error(format!(
"{ENV_KMS_VAULT_TOKEN_FILE} cannot be combined with RUSTFS_KMS_VAULT_TOKEN; configure exactly one Vault auth method"
)));
for (name, configured) in [
(ENV_KMS_VAULT_APPROLE_ROLE_ID, role_id.is_some()),
(ENV_KMS_VAULT_KUBERNETES_ROLE, kubernetes_role.is_some()),
(ENV_KMS_VAULT_TOKEN, token.is_some()),
] {
if configured {
return Err(KmsError::configuration_error(format!(
"{ENV_KMS_VAULT_TOKEN_FILE} cannot be combined with {name}; configure exactly one Vault auth method"
)));
}
}
return Ok(VaultAuthMethod::token_file(PathBuf::from(token_file)));
}
let Some(role_id) = get_env_opt_str(ENV_KMS_VAULT_APPROLE_ROLE_ID) else {
if let Some(role) = kubernetes_role {
// Unlike a leftover static token, a second login method is never a
// stale remnant: both were configured deliberately and neither can be
// ranked over the other.
if role_id.is_some() {
return Err(KmsError::configuration_error(format!(
"{ENV_KMS_VAULT_KUBERNETES_ROLE} cannot be combined with {ENV_KMS_VAULT_APPROLE_ROLE_ID}; configure exactly one Vault auth method"
)));
}
return Ok(VaultAuthMethod::Kubernetes {
role,
mount: get_env_str(ENV_KMS_VAULT_KUBERNETES_MOUNT, DEFAULT_VAULT_KUBERNETES_MOUNT),
jwt_path: get_env_opt_str(ENV_KMS_VAULT_KUBERNETES_JWT_PATH)
.map_or_else(default_vault_kubernetes_jwt_path, PathBuf::from),
refresh_safety_window_secs: None,
});
}
let Some(role_id) = role_id else {
return Ok(VaultAuthMethod::Token {
token: get_env_str("RUSTFS_KMS_VAULT_TOKEN", "dev-token"),
token: token.unwrap_or_else(|| "dev-token".to_string()),
});
};
@@ -1273,6 +1398,22 @@ fn validate_vault_auth_method(backend_name: &str, auth_method: &VaultAuthMethod)
}
Ok(())
}
VaultAuthMethod::Kubernetes {
role, mount, jwt_path, ..
} => {
if role.is_empty() {
return Err(KmsError::configuration_error(format!("{backend_name} Kubernetes role cannot be empty")));
}
if mount.is_empty() {
return Err(KmsError::configuration_error(format!("{backend_name} Kubernetes mount cannot be empty")));
}
if jwt_path.as_os_str().is_empty() {
return Err(KmsError::configuration_error(format!(
"{backend_name} Kubernetes ServiceAccount token path cannot be empty"
)));
}
Ok(())
}
VaultAuthMethod::TokenFile {
path,
poll_interval_secs,
@@ -1976,6 +2117,106 @@ mod tests {
.expect("well-formed token file auth must validate");
}
/// A Kubernetes role alone configures the method: the credential is the
/// pod's projected ServiceAccount token, so nothing secret is in the
/// environment and the mount and token path fall back to the cluster
/// defaults.
#[test]
fn test_from_env_selects_kubernetes() {
with_vars(
vec![
("RUSTFS_KMS_BACKEND", Some("vault-transit")),
(ENV_KMS_VAULT_ADDRESS, Some("https://vault.example.com")),
(ENV_KMS_VAULT_KUBERNETES_ROLE, Some("rustfs")),
(ENV_KMS_VAULT_KUBERNETES_MOUNT, None),
(ENV_KMS_VAULT_KUBERNETES_JWT_PATH, None),
(ENV_KMS_VAULT_TOKEN, None),
(ENV_KMS_VAULT_TOKEN_FILE, None),
(ENV_KMS_VAULT_APPROLE_ROLE_ID, None),
],
|| {
let config = KmsConfig::from_env().expect("kms config should load from env");
let vault = config.vault_transit_config().expect("vault transit backend config");
let VaultAuthMethod::Kubernetes {
role,
mount,
jwt_path,
refresh_safety_window_secs,
} = &vault.auth_method
else {
panic!(
"a kubernetes role in the environment must select Kubernetes auth, got {:?}",
vault.auth_method
);
};
assert_eq!(role, "rustfs");
assert_eq!(mount, DEFAULT_VAULT_KUBERNETES_MOUNT);
assert_eq!(jwt_path, Path::new(DEFAULT_VAULT_KUBERNETES_JWT_PATH));
assert_eq!(refresh_safety_window_secs, &None);
},
);
}
#[test]
fn test_from_env_kubernetes_is_mutually_exclusive_with_other_auth() {
with_vars(
vec![
("RUSTFS_KMS_BACKEND", Some("vault-transit")),
(ENV_KMS_VAULT_KUBERNETES_ROLE, Some("rustfs")),
(ENV_KMS_VAULT_APPROLE_ROLE_ID, Some("env-role-id")),
(ENV_KMS_VAULT_TOKEN, None),
(ENV_KMS_VAULT_TOKEN_FILE, None),
],
|| {
let error = KmsConfig::from_env().expect_err("kubernetes combined with approle must be rejected");
assert!(error.to_string().contains(ENV_KMS_VAULT_KUBERNETES_ROLE));
assert!(error.to_string().contains(ENV_KMS_VAULT_APPROLE_ROLE_ID));
},
);
}
#[test]
fn test_validate_rejects_bad_kubernetes_settings() {
let vault_config = |auth_method: VaultAuthMethod| KmsConfig {
backend: KmsBackend::VaultTransit,
backend_config: BackendConfig::VaultTransit(Box::new(VaultTransitConfig {
address: "https://vault.example.com:8200".to_string(),
auth_method,
..Default::default()
})),
..Default::default()
};
let error = vault_config(VaultAuthMethod::kubernetes(String::new()))
.validate()
.expect_err("an empty kubernetes role must be rejected");
assert!(error.to_string().contains("role"), "got {error}");
let error = vault_config(VaultAuthMethod::Kubernetes {
role: "rustfs".to_string(),
mount: String::new(),
jwt_path: PathBuf::from(DEFAULT_VAULT_KUBERNETES_JWT_PATH),
refresh_safety_window_secs: None,
})
.validate()
.expect_err("an empty kubernetes mount must be rejected");
assert!(error.to_string().contains("mount"), "got {error}");
let error = vault_config(VaultAuthMethod::Kubernetes {
role: "rustfs".to_string(),
mount: DEFAULT_VAULT_KUBERNETES_MOUNT.to_string(),
jwt_path: PathBuf::new(),
refresh_safety_window_secs: None,
})
.validate()
.expect_err("an empty ServiceAccount token path must be rejected");
assert!(error.to_string().contains("token path"), "got {error}");
vault_config(VaultAuthMethod::kubernetes("rustfs".to_string()))
.validate()
.expect("well-formed kubernetes auth must validate");
}
/// Every KV2 read, write and listing is routed through `kv_mount`, so an
/// empty one names a path no Vault engine answers. The Transit backend
/// already rejects its own empty mounts; this closes the same gap on the