mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-16 08:45:22 +01:00
* s3api: create a multipart upload's directory on the object's owner filer CreateMultipartUpload wrote .uploads/<id> to the gateway's own filer while the upload's completion commits on the object's write owner. With independent filer stores, a part or completion reaching another gateway before peer metadata replication caught up could not see the upload. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: look up a multipart upload on the object's owner filer UploadPart, UploadPartCopy, ListParts, CompleteMultipartUpload, AbortMultipartUpload and the bucket policy SSE lookup read .uploads/<id> from the gateway's own filer, so a request on another gateway shortly after CreateMultipartUpload answered NoSuchUpload until replication caught up. Read it preferring the object's write owner, like object reads. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: write multipart parts to the upload's owner filer UploadPart and UploadPartCopy stored part entries on the gateway's own filer, so ListParts and CompleteMultipartUpload on another gateway could miss a part that replication had not delivered yet. Store them next to the upload directory on the object's write owner. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: list and clean up a multipart upload on its owner filer ListParts, CompleteMultipartUpload and AbortMultipartUpload listed and removed part entries on the gateway's own filer. Do it where the upload and its parts now live, so completion sees every part and cleanup does not miss entries replication has not delivered yet. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: test a multipart upload against a lagging gateway filer Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: check the upload's owner before freeing a failed part's chunks A part write that the owner stored but answered with an error went to recovery with no object, so the owner was never among the filers checked. When the owner is outside the gateway's filer list, the others' not-found answers freed chunks the stored part still references. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: list an upload's parts on the prior owner after a ring change The upload record lookup already falls back to the key's prior owner while a ring change is in its cooling-off window, but the part listing read only the new owner. ListParts then reported no parts for an open upload. Fall back the same way when the new owner has nothing yet. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: find the upload record on the prior owner past a bare directory A part routed to a new owner that has not received the upload yet makes that filer create .uploads/<id> without the upload's key. The post-write check then read it as an aborted upload and removed the part. While the ring change is in its cooling-off window, a record on the prior owner now wins over such a directory. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: merge the prior owner's parts into an upload listing During a ring change's cooling-off window the new owner may have received only some of an upload's parts. Listing returned the new owner's parts alone once it had any, so ListParts dropped the rest and a completion naming them failed with InvalidPart. Both owners' pages are now merged, the owner's entry winning a shared name, and cut to the page limit. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: fail an upload listing the prior owner could not answer When the new owner has none of an upload's parts yet and the prior owner's listing fails, the parts may all be on the prior owner. That listing read as empty, so CompleteMultipartUpload answered NoSuchUpload for an upload that still exists; it now returns the error. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * s3api: fail an upload lookup the prior owner could not answer During a ring change's cooling-off window an upload the new owner has not received yet, or holds only as a bare directory, read as NoSuchUpload when the prior owner's lookup failed. That failure is now returned, so the client sees a retryable error instead of an upload that is gone. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
208 lines
7.8 KiB
Go
208 lines
7.8 KiB
Go
package s3api
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/s3api/policy_engine"
|
|
)
|
|
|
|
// BucketPolicyEngine wraps the policy_engine to provide bucket policy evaluation
|
|
type BucketPolicyEngine struct {
|
|
engine *policy_engine.PolicyEngine
|
|
// MultipartSSELookup retrieves the canonical SSE algorithm ("AES256" or
|
|
// "aws:kms") that was stored when a multipart upload was initiated.
|
|
// Returns "" when the upload had no SSE or when the entry cannot be found.
|
|
// Set by S3ApiServer after construction to give the engine filer access.
|
|
MultipartSSELookup func(bucket, object, uploadID string) string
|
|
}
|
|
|
|
// NewBucketPolicyEngine creates a new bucket policy engine
|
|
func NewBucketPolicyEngine() *BucketPolicyEngine {
|
|
return &BucketPolicyEngine{
|
|
engine: policy_engine.NewPolicyEngine(),
|
|
}
|
|
}
|
|
|
|
// LoadBucketPolicy loads a bucket policy into the engine from the filer entry
|
|
func (bpe *BucketPolicyEngine) LoadBucketPolicy(bucket string, entry *filer_pb.Entry) error {
|
|
if entry == nil || entry.Extended == nil {
|
|
return nil
|
|
}
|
|
|
|
policyJSON, exists := entry.Extended[BUCKET_POLICY_METADATA_KEY]
|
|
if !exists || len(policyJSON) == 0 {
|
|
// No policy for this bucket - remove it if it exists
|
|
bpe.engine.DeleteBucketPolicy(bucket)
|
|
return nil
|
|
}
|
|
|
|
// Set the policy in the engine
|
|
if err := bpe.engine.SetBucketPolicy(bucket, string(policyJSON)); err != nil {
|
|
glog.Errorf("Failed to load bucket policy for %s: %v", bucket, err)
|
|
return err
|
|
}
|
|
|
|
glog.V(3).Infof("Loaded bucket policy for %s into policy engine", bucket)
|
|
return nil
|
|
}
|
|
|
|
// LoadBucketPolicyFromCache loads a bucket policy from a cached BucketConfig
|
|
//
|
|
// This function loads the policy directly into the engine
|
|
func (bpe *BucketPolicyEngine) LoadBucketPolicyFromCache(bucket string, policyDoc *policy_engine.PolicyDocument) error {
|
|
if policyDoc == nil {
|
|
// No policy for this bucket - remove it if it exists
|
|
bpe.engine.DeleteBucketPolicy(bucket)
|
|
return nil
|
|
}
|
|
|
|
// Policy is already in correct format, just load it
|
|
// We need to re-marshal to string because SetBucketPolicy expects JSON string
|
|
policyJSON, err := json.Marshal(policyDoc)
|
|
if err != nil {
|
|
glog.Errorf("Failed to marshal bucket policy for %s: %v", bucket, err)
|
|
return err
|
|
}
|
|
|
|
// Set the policy in the engine
|
|
if err := bpe.engine.SetBucketPolicy(bucket, string(policyJSON)); err != nil {
|
|
glog.Errorf("Failed to load bucket policy for %s: %v", bucket, err)
|
|
return err
|
|
}
|
|
|
|
glog.V(4).Infof("Loaded bucket policy for %s into policy engine from cache", bucket)
|
|
return nil
|
|
}
|
|
|
|
// DeleteBucketPolicy removes a bucket policy from the engine
|
|
func (bpe *BucketPolicyEngine) DeleteBucketPolicy(bucket string) error {
|
|
return bpe.engine.DeleteBucketPolicy(bucket)
|
|
}
|
|
|
|
// HasPolicyForBucket checks if a bucket has a policy configured
|
|
func (bpe *BucketPolicyEngine) HasPolicyForBucket(bucket string) bool {
|
|
return bpe.engine.HasPolicyForBucket(bucket)
|
|
}
|
|
|
|
// GetBucketPolicy gets the policy for a bucket
|
|
func (bpe *BucketPolicyEngine) GetBucketPolicy(bucket string) (*policy_engine.PolicyDocument, error) {
|
|
return bpe.engine.GetBucketPolicy(bucket)
|
|
}
|
|
|
|
// ListBucketPolicies returns all buckets that have policies
|
|
func (bpe *BucketPolicyEngine) ListBucketPolicies() []string {
|
|
return bpe.engine.GetAllBucketsWithPolicies()
|
|
}
|
|
|
|
// EvaluatePolicy evaluates whether an action is allowed by bucket policy
|
|
//
|
|
// Parameters:
|
|
// - bucket: the bucket name
|
|
// - object: the object key (can be empty for bucket-level operations)
|
|
// - action: the action being performed (e.g., "Read", "Write")
|
|
// - principal: the principal ARN or identifier
|
|
// - r: the HTTP request (optional, used for condition evaluation and action resolution)
|
|
// - objectEntry: the object's metadata from entry.Extended (can be nil at auth time,
|
|
// should be passed when available for tag-based conditions like s3:ExistingObjectTag)
|
|
//
|
|
// Returns:
|
|
// - allowed: whether the policy allows the action
|
|
// - evaluated: whether a policy was found and evaluated (false = no policy exists)
|
|
// - error: any error during evaluation
|
|
func (bpe *BucketPolicyEngine) EvaluatePolicy(bucket, object, action, principal string, r *http.Request, claims map[string]interface{}, objectEntry map[string][]byte) (allowed bool, evaluated bool, err error) {
|
|
// Validate required parameters
|
|
if bucket == "" {
|
|
return false, false, fmt.Errorf("bucket cannot be empty")
|
|
}
|
|
if action == "" {
|
|
return false, false, fmt.Errorf("action cannot be empty")
|
|
}
|
|
|
|
// Convert action to S3 action format
|
|
// ResolveS3Action handles nil request internally (falls back to mapBaseActionToS3Format)
|
|
s3Action := ResolveS3Action(r, action, bucket, object)
|
|
|
|
// Build resource ARN
|
|
resource := buildResourceARN(bucket, object)
|
|
|
|
glog.V(4).Infof("EvaluatePolicy: bucket=%s, resource=%s, action=%s, principal=%s",
|
|
bucket, resource, s3Action, principal)
|
|
|
|
// Evaluate using the policy engine
|
|
args := &policy_engine.PolicyEvaluationArgs{
|
|
Action: s3Action,
|
|
Resource: resource,
|
|
Principal: principal,
|
|
ObjectEntry: objectEntry,
|
|
}
|
|
|
|
// glog.V(4).Infof("EvaluatePolicy [Wrapper]: bucket=%s, resource=%s, action=%s, principal=%s",
|
|
// bucket, resource, s3Action, principal)
|
|
|
|
// Extract conditions and claims from request if available
|
|
if r != nil {
|
|
args.OriginalGrantConditions = policy_engine.OriginalGrantConditionsFromRequest(r)
|
|
args.Conditions = bpe.engine.ExtractConditionValuesFromRequest(r)
|
|
|
|
// Extract principal-related variables (aws:username, etc.) from principal ARN
|
|
principalVars := principalVariables(principal, claims)
|
|
for k, v := range principalVars {
|
|
args.Conditions[k] = v
|
|
}
|
|
|
|
// Extract JWT claims if authenticated via JWT or STS
|
|
if claims != nil {
|
|
args.Claims = claims
|
|
} else {
|
|
// If claims were not provided directly, try to get them from context Identity?
|
|
// But the caller is responsible for passing them.
|
|
// Falling back to empty claims if not provided.
|
|
}
|
|
|
|
// For multipart continuation actions look up the SSE algorithm that was
|
|
// set at CreateMultipartUpload time. UploadPart/UploadPartCopy do not
|
|
// re-send the SSE header, so we inject the stored value so that bucket
|
|
// policy conditions on s3:x-amz-server-side-encryption evaluate correctly.
|
|
if policy_engine.IsMultipartContinuationAction(s3Action) && bpe.MultipartSSELookup != nil {
|
|
if uploadID := r.URL.Query().Get("uploadId"); uploadID != "" {
|
|
args.InheritedSSEAlgorithm = bpe.MultipartSSELookup(bucket, object, uploadID)
|
|
}
|
|
}
|
|
}
|
|
|
|
result := bpe.engine.EvaluatePolicy(bucket, args)
|
|
|
|
switch result {
|
|
case policy_engine.PolicyResultAllow:
|
|
// glog.V(4).Infof("EvaluatePolicy [Wrapper]: ALLOW - bucket=%s, action=%s, principal=%s", bucket, s3Action, principal)
|
|
return true, true, nil
|
|
case policy_engine.PolicyResultDeny:
|
|
// glog.V(4).Infof("EvaluatePolicy [Wrapper]: DENY - bucket=%s, action=%s, principal=%s", bucket, s3Action, principal)
|
|
return false, true, nil
|
|
case policy_engine.PolicyResultIndeterminate:
|
|
// No policy exists for this bucket
|
|
// glog.V(4).Infof("EvaluatePolicy [Wrapper]: INDETERMINATE (no policy) - bucket=%s", bucket)
|
|
return false, false, nil
|
|
default:
|
|
return false, false, fmt.Errorf("unknown policy result: %v", result)
|
|
}
|
|
}
|
|
|
|
// principalVariables resolves the policy variables of a principal. A role
|
|
// session's ARN ends in the session name the caller chose, so its user comes
|
|
// from the session itself: the user the session was issued to.
|
|
func principalVariables(principal string, claims map[string]interface{}) map[string][]string {
|
|
vars := policy_engine.ExtractPrincipalVariables(principal)
|
|
if types := vars["aws:principaltype"]; len(types) == 1 && types[0] == "AssumedRole" {
|
|
if user, ok := claims["aws:username"].(string); ok && user != "" {
|
|
vars["aws:username"] = []string{user}
|
|
vars["aws:userid"] = []string{user}
|
|
}
|
|
}
|
|
return vars
|
|
}
|