mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-01 01:40:44 +01:00
* s3, iceberg: record the access key a request was signed with Several access keys can belong to one identity, but nothing downstream of authentication says which one signed a request: the audit log carries the identity name only, and every table credential the Iceberg catalog vends for that identity gets the same session name. When an identity is shared (one key per person or per service), the log cannot tell the holders apart. The verifier that matched a credential now records that credential's access key id in the request's identity holder (verifyV4Signature for header, presigned, streaming and STS requests; both SigV2 verifiers). Nothing re-reads the request for a key, so a second, unverified key elsewhere in the request (a junk X-Amz-Credential on a SigV2 request, a junk SigV4 header on a SigV2 presigned URL) is never recorded. - s3err.AccessLog gains access_key_id (omitempty): a static key's id, or an STS session's temporary key id. Every other field is unchanged. - The Iceberg and Lance catalogs install the holder before authenticating a SigV4 request; a Bearer token records the key it was minted from (the token is verified with a key derived from it); a Lance x-api-key records its key. - VendTableCredentials ends the session name with "-k" and the first 12 hex digits of SHA-256 of the key id (the table part gives way within the 64-character limit; the tag is never cut), and carries the key id in the session token (src_ak, SessionInfo.SourceAccessKeyId). Tests: auth_access_key_attribution_test.go and auth_access_key_shapes_test.go (two keys on one identity, the deny path, SigV2 and presigned SigV2 with a junk key elsewhere, streaming seed, STS session, failed signatures record nothing), s3api_iceberg_session_name_test.go, iceberg and lance Auth tests, sts source_access_key_test.go. * s3: record the access key of a verified POST-policy form and of a retargeted signature Two verified signatures left access_key_id empty in the audit log: - A browser POST upload is verified in PostPolicyBucketHandler from its form fields by doesPolicySignatureV2Match / doesPolicySignatureV4Match, which did not record the key. Both now take the request context and record the credential's key once its signature verifies; a form that fails verification records nothing. - verifyV4Signature refuses a signature that verified for one virtual-hosted bucket but was routed to another. The key was recorded only after that check, so the refusal carried none. It is now recorded as soon as a host candidate verifies. Test: TestPostPolicyUploadRecordsTheSigningKey (SigV4 and SigV2 forms, and a form with a wrong signature) and TestSignedVirtualHostRetargetRecordsTheSigningKey; both fail before this change. * s3: test VendTableCredentials end to end for the caller's access key TestVendTableCredentialsRecordsTheCallersKey mints sessions through VendTableCredentials with a configured STS service, the key recorded the way the catalog's authentication records it, then validates each session token: SourceAccessKeyId and the session name's key tag match the key, and a caller without a key gets an untagged session. It fails if the vendor stops passing either field. --------- Co-authored-by: Javier de la Torre <jatorre@lakehousebox.com> Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
272 lines
9.4 KiB
Go
272 lines
9.4 KiB
Go
package sts
|
|
|
|
import (
|
|
"crypto/sha256"
|
|
"encoding/base64"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/golang-jwt/jwt/v5"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
)
|
|
|
|
// ComputeParentUser returns a stable per-identity hash derived from the OIDC
|
|
// (sub, iss) tuple. Only the (sub, iss) pair is guaranteed stable across token
|
|
// refreshes per OpenID Connect Core 1.0 §5.7, so any per-user state (audit
|
|
// logs, quotas) must key off this value rather than the access-key or session
|
|
// id. The hash is base64-rawurl-encoded SHA-256 over "openid:<sub>:<iss>" so
|
|
// it stays filesystem-safe and bounded in length for storage in audit paths.
|
|
func ComputeParentUser(sub, iss string) string {
|
|
if sub == "" || iss == "" {
|
|
return ""
|
|
}
|
|
h := sha256.Sum256([]byte("openid:" + sub + ":" + iss))
|
|
return base64.RawURLEncoding.EncodeToString(h[:])
|
|
}
|
|
|
|
// IsParentUserID reports whether s has the shape ComputeParentUser produces —
|
|
// a base64url-encoded SHA-256 — i.e. an already issuer-scoped id rather than a
|
|
// bare subject string.
|
|
func IsParentUserID(s string) bool {
|
|
b, err := base64.RawURLEncoding.DecodeString(s)
|
|
return err == nil && len(b) == sha256.Size
|
|
}
|
|
|
|
// identityClaimPriority is the order in which ResolveIdentityClaim looks for a
|
|
// human-readable, authoritative identity attribute in an STS request context.
|
|
// The context is populated at federation time from the validated OIDC token
|
|
// (see AssumeRoleWithWebIdentity), so every entry here is server-asserted and
|
|
// not client-supplied. preferred_username/email/name are conventional OIDC
|
|
// user claims; sub is the always-present stable subject identifier and the
|
|
// final fallback so a federated session never audits as fully anonymous.
|
|
var identityClaimPriority = []string{"preferred_username", "email", "name", "sub"}
|
|
|
|
// ResolveIdentityClaim returns the most human-readable authoritative identity
|
|
// claim available in ctx, or "" when none is present. ctx is the STS request
|
|
// context (sessionInfo.RequestContext) populated from the validated OIDC token
|
|
// at federation time. Non-string values are skipped so a structured claim
|
|
// never leaks into an audit-facing field. Whitespace-only values are treated
|
|
// as absent so a blank preferred claim does not mask a usable email or sub.
|
|
func ResolveIdentityClaim(ctx map[string]interface{}) string {
|
|
if len(ctx) == 0 {
|
|
return ""
|
|
}
|
|
for _, key := range identityClaimPriority {
|
|
if v, ok := ctx[key].(string); ok {
|
|
if trimmed := strings.TrimSpace(v); trimmed != "" {
|
|
return trimmed
|
|
}
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
// STSSessionClaims represents comprehensive session information embedded in JWT tokens
|
|
// This eliminates the need for separate session storage by embedding all session
|
|
// metadata directly in the token itself - enabling true stateless operation
|
|
type STSSessionClaims struct {
|
|
jwt.RegisteredClaims
|
|
|
|
// Session identification
|
|
SessionId string `json:"sid"` // session_id (abbreviated for smaller tokens)
|
|
SessionName string `json:"snam"` // session_name (abbreviated for smaller tokens)
|
|
TokenType string `json:"typ"` // token_type
|
|
|
|
// Role information
|
|
RoleArn string `json:"role"` // role_arn
|
|
RoleId string `json:"rid,omitempty"` // unique ID of the assumed role
|
|
AssumedRole string `json:"assumed"` // assumed_role_user
|
|
Principal string `json:"principal"` // principal_arn
|
|
|
|
// Authorization data
|
|
Policies []string `json:"pol,omitempty"` // policies (abbreviated)
|
|
// SessionPolicy contains inline session policy JSON (optional)
|
|
SessionPolicy string `json:"spol,omitempty"`
|
|
|
|
// Identity provider information
|
|
IdentityProvider string `json:"idp"` // identity_provider
|
|
ExternalUserId string `json:"ext_uid"` // external_user_id
|
|
ProviderIssuer string `json:"prov_iss"` // provider_issuer
|
|
|
|
// Request context (optional, for policy evaluation)
|
|
RequestContext map[string]interface{} `json:"req_ctx,omitempty"`
|
|
|
|
// Session metadata
|
|
AssumedAt time.Time `json:"assumed_at"` // when role was assumed
|
|
MaxDuration int64 `json:"max_dur,omitempty"` // maximum session duration in seconds
|
|
|
|
// ParentUser is a stable hash of (sub, iss) for tokens minted from an OIDC
|
|
// identity. It survives token rotation since only the (sub, iss) tuple is
|
|
// guaranteed stable per OpenID Connect Core 1.0. Empty for non-federated
|
|
// session types.
|
|
ParentUser string `json:"puid,omitempty"`
|
|
|
|
// SourceAccessKeyId is the access key the caller authenticated with when
|
|
// a SeaweedFS service minted the session for it (AssumeRoleForPrincipal);
|
|
// empty for every other session type.
|
|
SourceAccessKeyId string `json:"src_ak,omitempty"`
|
|
}
|
|
|
|
// NewSTSSessionClaims creates new STS session claims with all required information
|
|
func NewSTSSessionClaims(sessionId, issuer string, expiresAt time.Time) *STSSessionClaims {
|
|
now := time.Now()
|
|
return &STSSessionClaims{
|
|
RegisteredClaims: jwt.RegisteredClaims{
|
|
Issuer: issuer,
|
|
Subject: sessionId,
|
|
IssuedAt: jwt.NewNumericDate(now),
|
|
ExpiresAt: jwt.NewNumericDate(expiresAt),
|
|
NotBefore: jwt.NewNumericDate(now),
|
|
// jti = sessionId. The session id is already a unique random
|
|
// identifier, so reusing it as the JWT id avoids a second secret
|
|
// while still giving the revocation layer a stable lookup key.
|
|
ID: sessionId,
|
|
},
|
|
SessionId: sessionId,
|
|
TokenType: TokenTypeSession,
|
|
AssumedAt: now,
|
|
}
|
|
}
|
|
|
|
// ToSessionInfo converts JWT claims back to SessionInfo structure
|
|
// This enables seamless integration with existing code expecting SessionInfo
|
|
func (c *STSSessionClaims) ToSessionInfo(credGen *CredentialGenerator) *SessionInfo {
|
|
var expiresAt time.Time
|
|
if c.ExpiresAt != nil {
|
|
expiresAt = c.ExpiresAt.Time
|
|
}
|
|
|
|
var credentials *Credentials
|
|
if credGen != nil {
|
|
creds, err := credGen.GenerateTemporaryCredentials(c.SessionId, expiresAt)
|
|
if err != nil {
|
|
glog.Warningf("Failed to generate credentials for STS session %s: %v", c.SessionId, err)
|
|
} else {
|
|
credentials = creds
|
|
}
|
|
}
|
|
|
|
return &SessionInfo{
|
|
SessionId: c.SessionId,
|
|
SessionName: c.SessionName,
|
|
RoleArn: c.RoleArn,
|
|
RoleId: c.RoleId,
|
|
AssumedRoleUser: c.AssumedRole,
|
|
Principal: c.Principal,
|
|
Policies: c.Policies,
|
|
SessionPolicy: c.SessionPolicy,
|
|
ExpiresAt: expiresAt,
|
|
IdentityProvider: c.IdentityProvider,
|
|
ExternalUserId: c.ExternalUserId,
|
|
ProviderIssuer: c.ProviderIssuer,
|
|
RequestContext: c.RequestContext,
|
|
ParentUser: c.ParentUser,
|
|
// The access key the session was minted for, if recorded
|
|
SourceAccessKeyId: c.SourceAccessKeyId,
|
|
// Provide the Subject (sub) from registered claims
|
|
Subject: c.Subject,
|
|
Credentials: credentials,
|
|
}
|
|
}
|
|
|
|
// IsValid checks if the session claims are valid (not expired, etc.)
|
|
func (c *STSSessionClaims) IsValid() bool {
|
|
now := time.Now()
|
|
|
|
// Check expiration
|
|
if c.ExpiresAt != nil && c.ExpiresAt.Before(now) {
|
|
return false
|
|
}
|
|
|
|
// Check not-before
|
|
if c.NotBefore != nil && c.NotBefore.After(now) {
|
|
return false
|
|
}
|
|
|
|
// Ensure required fields are present
|
|
if c.SessionId == "" || c.RoleArn == "" || c.Principal == "" {
|
|
return false
|
|
}
|
|
|
|
return true
|
|
}
|
|
|
|
// GetSessionId returns the session identifier
|
|
func (c *STSSessionClaims) GetSessionId() string {
|
|
return c.SessionId
|
|
}
|
|
|
|
// GetExpiresAt returns the expiration time
|
|
func (c *STSSessionClaims) GetExpiresAt() time.Time {
|
|
if c.ExpiresAt != nil {
|
|
return c.ExpiresAt.Time
|
|
}
|
|
return time.Time{}
|
|
}
|
|
|
|
// WithRoleInfo sets role-related information in the claims
|
|
func (c *STSSessionClaims) WithRoleInfo(roleArn, assumedRole, principal string) *STSSessionClaims {
|
|
c.RoleArn = roleArn
|
|
c.AssumedRole = assumedRole
|
|
c.Principal = principal
|
|
return c
|
|
}
|
|
|
|
// WithPolicies sets the policies associated with this session
|
|
// WithRoleId binds the session to the assumed role's unique ID. An empty ID
|
|
// leaves the session unbound (roles that predate role IDs).
|
|
func (c *STSSessionClaims) WithRoleId(roleId string) *STSSessionClaims {
|
|
c.RoleId = roleId
|
|
return c
|
|
}
|
|
|
|
func (c *STSSessionClaims) WithPolicies(policies []string) *STSSessionClaims {
|
|
c.Policies = policies
|
|
return c
|
|
}
|
|
|
|
// WithSessionPolicy sets the inline session policy JSON for this session
|
|
func (c *STSSessionClaims) WithSessionPolicy(policy string) *STSSessionClaims {
|
|
c.SessionPolicy = policy
|
|
return c
|
|
}
|
|
|
|
// WithIdentityProvider sets identity provider information
|
|
func (c *STSSessionClaims) WithIdentityProvider(providerName, externalUserId, providerIssuer string) *STSSessionClaims {
|
|
c.IdentityProvider = providerName
|
|
c.ExternalUserId = externalUserId
|
|
c.ProviderIssuer = providerIssuer
|
|
return c
|
|
}
|
|
|
|
// WithRequestContext sets request context for policy evaluation
|
|
func (c *STSSessionClaims) WithRequestContext(ctx map[string]interface{}) *STSSessionClaims {
|
|
c.RequestContext = ctx
|
|
return c
|
|
}
|
|
|
|
// WithMaxDuration sets the maximum session duration
|
|
func (c *STSSessionClaims) WithMaxDuration(duration time.Duration) *STSSessionClaims {
|
|
c.MaxDuration = int64(duration.Seconds())
|
|
return c
|
|
}
|
|
|
|
// WithSessionName sets the session name
|
|
func (c *STSSessionClaims) WithSessionName(sessionName string) *STSSessionClaims {
|
|
c.SessionName = sessionName
|
|
return c
|
|
}
|
|
|
|
// WithSourceAccessKeyId records the access key the session was minted for.
|
|
func (c *STSSessionClaims) WithSourceAccessKeyId(accessKeyId string) *STSSessionClaims {
|
|
c.SourceAccessKeyId = accessKeyId
|
|
return c
|
|
}
|
|
|
|
// WithParentUser sets the stable per-identity hash for the session. See
|
|
// ComputeParentUser for the derivation rule.
|
|
func (c *STSSessionClaims) WithParentUser(parentUser string) *STSSessionClaims {
|
|
c.ParentUser = parentUser
|
|
return c
|
|
}
|