ci(release): unset synthetic RELEASE_TAG for Helm check in test-release

Signed-off-by: Feng Ruohang <rh@vonng.com>

.github/workflows/dco.yml

@@ -1,6 +1,9 @@
 name: DCO
 
 on:
+  push:
+    branches:
+      - main
   pull_request:
     branches:
       - main
@@ -17,18 +20,29 @@ jobs:
         with:
           fetch-depth: 0
 
-      # Every non-merge commit in the pull request must carry a Signed-off-by
+      # Every non-merge commit in the pull request or push must carry a Signed-off-by
       # trailer matching the commit author's email, certifying the Developer
       # Certificate of Origin 1.1 (https://developercertificate.org/).
       # Only commits authored from a GitHub-issued bot address are exempt; a
       # display name is attacker-controlled and must never grant the exemption.
       - name: Check Signed-off-by trailers
         env:
-          BASE_SHA: ${{ github.event.pull_request.base.sha }}
-          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
+          EVENT_NAME: ${{ github.event_name }}
+          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
+          PR_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
+          PUSH_BEFORE_SHA: ${{ github.event.before }}
+          PUSH_AFTER_SHA: ${{ github.sha }}
         run: |
+          if [ "${EVENT_NAME}" = "pull_request" ]; then
+            rev_range="${PR_BASE_SHA}..${PR_HEAD_SHA}"
+          elif [ -n "${PUSH_BEFORE_SHA}" ] && [ "${PUSH_BEFORE_SHA}" != "0000000000000000000000000000000000000000" ] && git cat-file -e "${PUSH_BEFORE_SHA}^{commit}" 2>/dev/null; then
+            rev_range="${PUSH_BEFORE_SHA}..${PUSH_AFTER_SHA}"
+          else
+            rev_range="${PUSH_AFTER_SHA}^..${PUSH_AFTER_SHA}"
+          fi
           fail=0
           while read -r sha; do
+            [ -n "${sha}" ] || continue
             author_name="$(git log -1 --format='%an' "${sha}")"
             author_email="$(git log -1 --format='%ae' "${sha}")"
             case "${author_email}" in
@@ -39,5 +53,5 @@ jobs:
               echo "::error::commit ${sha} by ${author_name} <${author_email}> lacks a matching Signed-off-by trailer; sign with 'git commit -s', repair with 'git rebase --signoff'"
               fail=1
             fi
-          done < <(git rev-list --no-merges "${BASE_SHA}..${HEAD_SHA}")
+          done < <(git rev-list --no-merges "${rev_range}")
           exit "${fail}"

.github/workflows/go.yml

@@ -35,7 +35,8 @@ jobs:
       - name: Check gofmt
         run: |
           mapfile -t unformatted < <(gofmt -l main.go cmd internal \
-            buildscripts/rebrand-guard buildscripts/helm-migration-guard)
+            buildscripts/rebrand-guard buildscripts/helm-migration-guard \
+            buildscripts/release-dependency-guard)
           if [ "${#unformatted[@]}" -ne 0 ]; then
             echo "The following files are not gofmt-formatted:"
             printf '%s\n' "${unformatted[@]}"

.github/workflows/release.yml

@@ -20,6 +20,7 @@ permissions:
   id-token: write
   attestations: write
   artifact-metadata: write
+  actions: read
 
 concurrency:
   group: release-${{ github.event_name == 'workflow_dispatch' && inputs.tag || github.ref_name }}
@@ -102,6 +103,12 @@ jobs:
             echo "Release tag ${TAG} resolves to ${TAG_COMMIT}, checkout is ${HEAD_COMMIT}" >&2
             exit 1
           fi
+          CHART_APP_VERSION="$(sed -n 's/^appVersion: *//p' helm/silo/Chart.yaml)"
+          CHART_IMAGE_TAG="$(sed -n '/^image:/,/^[^ ]/s/^  tag: *//p' helm/silo/values.yaml)"
+          if [ "${CHART_APP_VERSION}" != "${TAG}" ] || [ "${CHART_IMAGE_TAG}" != "${TAG}" ]; then
+            echo "helm/silo Chart.yaml appVersion (${CHART_APP_VERSION}) and values.yaml image.tag (${CHART_IMAGE_TAG}) must match release tag ${TAG}" >&2
+            exit 1
+          fi
           VERSION_HYPHEN="${TAG#RELEASE.}"
           PKG_VERSION="$(echo "${VERSION_HYPHEN}" | sed -E 's/^([0-9]{4})-([0-9]{2})-([0-9]{2})T([0-9]{2})-([0-9]{2})-([0-9]{2})Z$/\1\2\3\4\5\6.0.0/')"
           VERSION_COLON="$(echo "${VERSION_HYPHEN}" | sed -E 's/T([0-9]{2})-([0-9]{2})-([0-9]{2})Z$/T\1:\2:\3Z/')"
@@ -109,14 +116,29 @@ jobs:
 
           {
             echo "RELEASE_TAG=${TAG}"
+            echo "RELEASE_COMMIT=${HEAD_COMMIT}"
             echo "PKG_VERSION=${PKG_VERSION}"
             echo "LDFLAGS=${LDFLAGS}"
           } >> "${GITHUB_ENV}"
 
           echo "Release tag: ${TAG}"
+          echo "Release commit: ${HEAD_COMMIT}"
           echo "Package version: ${PKG_VERSION}"
           echo "LDFLAGS: ${LDFLAGS}"
 
+      - name: Check release commit is the tip of main with green CI
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+          buildscripts/check-release-commit.sh "${RELEASE_COMMIT}"
+
+      - name: Verify coordinated release dependencies
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GOWORK: "off"
+        run: go run ./buildscripts/release-dependency-guard
+
       - name: Check existing release state
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -140,7 +162,7 @@ jobs:
       - name: Build Draft release with GoReleaser
         uses: goreleaser/goreleaser-action@f06c13b6b1a9625abc9e6e439d9c05a8f2190e94 # v7.2.3
         with:
-          version: v2.18.3
+          version: v2.20.1
           args: release --clean --skip=validate --config .github/goreleaser.yml
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-release.yml

@@ -25,6 +25,9 @@ on:
       - "buildscripts/minio-upgrade.sh"
       - "buildscripts/sign-release-rpms.sh"
       - "buildscripts/verify-build-provenance.sh"
+      - "buildscripts/check-release-commit.sh"
+      - "buildscripts/check-release-commit_test.sh"
+      - "buildscripts/release-dependency-guard/**"
       - "buildscripts/check-release-state.sh"
       - "buildscripts/check-release-state_test.sh"
       - "buildscripts/verify-rebrand.sh"
@@ -97,10 +100,14 @@ jobs:
       - name: GoReleaser config check
         uses: goreleaser/goreleaser-action@f06c13b6b1a9625abc9e6e439d9c05a8f2190e94 # v7.2.3
         with:
-          version: v2.18.3
+          version: v2.20.1
           args: check --config .github/goreleaser.yml
 
       - name: Validate Helm chart and legacy upgrade identity
+        env:
+          # Compute test variables sets a synthetic GoReleaser fixture tag;
+          # real tag equality is enforced in release.yml.
+          RELEASE_TAG: ""
         run: buildscripts/verify-helm-migration.sh
 
       - name: Install Syft
@@ -111,7 +118,7 @@ jobs:
       - name: Build snapshot artifacts
         uses: goreleaser/goreleaser-action@f06c13b6b1a9625abc9e6e439d9c05a8f2190e94 # v7.2.3
         with:
-          version: v2.18.3
+          version: v2.20.1
           # A pull-request snapshot has no trusted release identity. Exercise
           # the SBOM/checksum pipeline here, and reserve keyless signing for
           # the tag-triggered release workflow with GitHub OIDC.
@@ -537,6 +544,8 @@ jobs:
           bash -n buildscripts/minio-upgrade.sh
           bash -n buildscripts/sign-release-rpms.sh
           bash -n buildscripts/verify-build-provenance.sh
+          bash -n buildscripts/check-release-commit.sh
+          bash -n buildscripts/check-release-commit_test.sh
           bash -n buildscripts/check-release-state.sh
           bash -n buildscripts/check-release-state_test.sh
           bash -n buildscripts/verify-rebrand.sh
@@ -553,6 +562,8 @@ jobs:
           test -x buildscripts/package-release.sh
           test -x buildscripts/sign-release-rpms.sh
           test -x buildscripts/verify-build-provenance.sh
+          test -x buildscripts/check-release-commit.sh
+          test -x buildscripts/check-release-commit_test.sh
           test -x buildscripts/check-release-state.sh
           test -x buildscripts/check-release-state_test.sh
           test -x buildscripts/verify-rebrand.sh
@@ -561,4 +572,6 @@ jobs:
           test -x buildscripts/package/preremove.sh
           test -x buildscripts/package/lifecycle_test.sh
           test -x dockerscripts/docker-entrypoint_test.sh
+          buildscripts/check-release-commit_test.sh
+          GOWORK=off go test ./buildscripts/release-dependency-guard
           buildscripts/check-release-state_test.sh

CHANGELOG.md

@@ -1,12 +1,194 @@
 # Changelog
 
+## RELEASE.2026-11-12T00-00-00Z
+
+Package version: `20261112000000.0.0`. Publication status and artifacts are
+listed in [GitHub Releases](https://github.com/pgsty/silo/releases). This
+section covers the changes after the published 20261109 source `d998292387cc`,
+adopting Go `1.27.4`, `silo-pkg v3.16.1`, embedded Console `v2.7.2`, and
+bundled `mcli 20261112`. See the
+[server compatibility notes](https://silo.pgsty.com/compatibility/server/)
+for behavior and upgrade boundaries.
+
+- Release checks verify the selected pkg and embedded Console versions and
+  match the bundled mcli release to its source module, independently of local
+  workspaces, before building release artifacts. Deploy SILO and mcli
+  `RELEASE.2026-11-12T00-00-00Z` by default from Helm chart `7.0.5`.
+- Replica writes and copies use the destination version's retention, legal
+  hold and tags under its mutation lock, verify staged replica content and
+  SSE-C/compressed metadata against stored locked versions before committing,
+  and prevent newer peer timestamps from weakening unexpired COMPLIANCE
+  retention. Cross-pool reconciliation preserves COMPLIANCE protection
+  regardless of pool order, while authorized changes to GOVERNANCE retention
+  and legal hold remain possible. Local lock revisions advance past stored
+  revisions, unaddressed deletes under versioning suspension or excluded
+  prefixes enforce Object Lock across single-pool and multi-pool deployments
+  and fail closed when versioning or Object Lock metadata cannot be read,
+  bucket metadata imports require versioning across prefix exclusions as well
+  as suspension, and peer replication-trust headers must be signed with
+  header-based SigV4 ([#336](https://github.com/pgsty/silo/issues/336)).
+- Tagging proxies (`GET`, `PUT` and `DELETE`) authenticate and authorize every
+  present replica, including its stored tags, fail closed on unreadable targets,
+  and skip missing replicas caused by replication lag unless all targets are
+  absent; active-active `GET` and `HEAD` proxies enforce `s3:ExistingObjectTag`
+  and `s3:versionid` before returning peer responses, forward
+  `X-Amz-Tagging-Directive: ACCESS` on `HEAD`, gate proxied
+  `x-amz-tagging-count` and `X-Amz-Tagging` headers on tag-read authorization
+  without emitting duplicate headers, and filter canonical-case peer
+  `X-Amz-Object-Lock-*` headers when `s3:GetObjectRetention` or
+  `s3:GetObjectLegalHold` is denied. Authenticated unsigned-trailer
+  uploads enforce the request time window and header signatures, SigV4 header,
+  presigned, streaming and POST policy verifiers bind the credential-scope date
+  to the signed request timestamp, streaming trailer readers bound trailer memory
+  and surface non-EOF stream errors without hanging on negative
+  `X-Amz-Decoded-Content-Length`, and bucket metadata cache loads no longer
+  overwrite fresher concurrent updates
+  ([#337](https://github.com/pgsty/silo/issues/337),
+  [#338](https://github.com/pgsty/silo/issues/338)).
+- Object tag and version authorization now applies consistently across read,
+  copy, list and archive endpoints: `GetObject`, `HeadObject` and
+  `SelectObjectContent` evaluate `s3:ExistingObjectTag` and `s3:versionid`
+  (preserving retryable `5xx` server errors for callers authorized by tag
+  conditions when storage is unreadable, resolving the 20261109 limitation in
+  [#293](https://github.com/pgsty/silo/issues/293) via
+  [PR #294](https://github.com/pgsty/silo/pull/294)); `CopyObject` and
+  `UploadPartCopy` authorize source `s3:ExistingObjectTag` and `s3:versionid`
+  as well as destination `s3:RequestObjectTag` on copied tags; both
+  `x-amz-tagging-count` and `X-Amz-Tagging` (`X-Amz-Tagging-Directive: ACCESS`)
+  are omitted on `GET`/`HEAD` (including versioned reads, STS sessions,
+  presigned/anonymous requests and replication proxies) unless
+  `s3:GetObjectTagging` / `s3:GetObjectVersionTagging` (with no explicit `Deny`)
+  or signed `s3:ReplicateTags` permits; `ListObjectsV2` / `ListObjectVersions` with `metadata=true` evaluate
+  current-object and per-version metadata permissions respectively, using stored tags; and `GetObjectAttributes`,
+  tagging handlers (`GET`/`PUT`/`DELETE`) and ZIP `GET`/`HEAD`/member listings
+  authorize stored tags and version actions without mutating unindexed archives
+  ([#342](https://github.com/pgsty/silo/issues/342)).
+- Policy parsing rejects unknown JSON fields, trailing tokens and malformed
+  principals across admin IAM policy/user/service-account endpoints, STS
+  session policies, IAM imports/replication, bucket policies and bucket metadata
+  imports instead of silently accepting empty or wildcard fallbacks. Validate
+  the complete imported policy file before applying entries; retain supported
+  historical snapshot semantics and explicit null bucket-policy replication
+  tombstones. New session policies retain strict resource validation.
+- Every explicit version removal in S3 `DeleteObjects`, including in buckets
+  without Object Lock, now uses the sequential single-object path to check
+  metadata, retention and replication under the mutation lock. Large version
+  purges can take longer. Unaddressed deletes that can replace a locked null
+  version also use the single-object path; other unaddressed deletes retain
+  bulk execution.
+- Decommission rescans keys hidden below another key only while source
+  versions are actually removed, resolving the 20261109 limitation recorded
+  in [#334](https://github.com/pgsty/silo/issues/334)
+  ([PR #335](https://github.com/pgsty/silo/pull/335)). Decommission and rebalance
+  clean up successfully migrated sibling versions after concurrent deletion
+  of another version. Source-removal and final empty verification check every
+  online drive and tolerate offline drives within the erasure set's read quorum,
+  while rejecting online metadata remnants, corrupt metadata, directory errors
+  and drive outages beyond parity. Cancellation returns an error, and a scan
+  without physical progress stops. Free-version tier ownership and the final
+  physical-empty check remain protected
+  ([#340](https://github.com/pgsty/silo/issues/340)). See the
+  [decommission procedure](https://silo.pgsty.com/operations/deployments/baremetal-decommission-server-pool/).
+- Site-replication bucket healing, metadata healing, status collection and
+  replication hooks snapshot site topology and release the state read lock
+  before storage I/O and peer RPCs, avoiding deadlocks and state-map races
+  when a configuration writer is waiting
+  ([#341](https://github.com/pgsty/silo/issues/341)). IAM import preserves
+  disabled service accounts and groups, reports group failures, and excludes
+  derived session-policy claims from exported and replicated credentials
+  ([#345](https://github.com/pgsty/silo/issues/345)).
+- Lifecycle history revision counting treats old and healed `xl.meta` headers
+  for the same version as one revision ([#332](https://github.com/pgsty/silo/issues/332)),
+  and restore expiry no longer turns a time-derived data-directory flag into a
+  different version revision; mixed healed headers can reach quorum and expired
+  local restore data can be cleaned up ([#344](https://github.com/pgsty/silo/issues/344)).
+  Historical-version self-copy plans its destination pool and data rewrite
+  before encryption or compression, preserving multi-block compression seek
+  indexes so a source version in another pool creates a readable new version.
+  In-place metadata updates locate the exact requested version and preserve
+  authoritative content on moving pools, while copies that require encryption
+  or checksum recomputation select an active pool
+  ([#343](https://github.com/pgsty/silo/issues/343)). Indexed `Range` reads into
+  compressed, server-side encrypted (`SSE-S3`, `SSE-KMS`, `SSE-C`) objects also
+  succeed when the target compressed block starts inside the first 64 KiB
+  encrypted frame (`decryptSkip > 0`), without rewriting stored objects.
+- Batch KMS rotation decodes and validates the configured encryption context
+  as strict UTF-8 JSON before changing an object key and without adding
+  validation-probe fields to object metadata, supports `SSE-S3` to `SSE-KMS`
+  key migration and multipart metadata preservation, and rewrites legacy `XLV1`
+  objects onto `XLv2` streams instead of failing in-place metadata updates
+  ([#346](https://github.com/pgsty/silo/issues/346)). Incoming HTTP
+  `X-Amz-Server-Side-Encryption-Context` headers on `PutObject`, `CopyObject`,
+  `CreateMultipartUpload` and browser `POST` uploads reject empty values,
+  malformed Base64/UTF-8/JSON, trailing tokens and non-string/non-`null` member
+  values with `400 InvalidArgument` instead of `500 InternalError`. Batch variable
+  preflight follows the pinned policy evaluator's literal and substitution
+  rules, including BinaryEquals, while retaining refusal of unavailable
+  request context. This does not add AWS special-variable escape semantics
+  ([#347](https://github.com/pgsty/silo/issues/347)).
+- Service-account and access-key create/edit normalize a missing policy Version
+  to `2012-10-17`, reject malformed or unknown policy fields, and distinguish an
+  omitted or `null` policy (preserve existing inline policy) from an explicit
+  empty policy document such as `{}` or `{"Statement":[]}` (reset to parent
+  inheritance), while keeping historical deny-all accounts carrying an empty
+  embedded policy restricted until explicitly reset
+  ([#339](https://github.com/pgsty/silo/issues/339),
+  [Console #89](https://github.com/pgsty/silo-console/issues/89),
+  [mcli #78](https://github.com/pgsty/mc/issues/78)). Previously,
+  `mcli admin user svcacct disable`, `enable` and `edit` without `--policy`,
+  the matching `admin accesskey` and `idp ldap/openid accesskey` commands, and
+  any other `update-service-account` request without `newPolicy` removed the
+  inline policy on the receiving site and on site-replication peers for
+  non-root parent users. In the matching Console (`v2.7.2`), turn off **Restrict
+  beyond user policy** or enter `{}` to remove an inline policy; clearing the
+  editor while restriction is enabled prevents saving, save errors render inside
+  the edit modal, and HTTP-to-HTTPS browser redirects preserve the request host
+  or `CONSOLE_SECURE_TLS_HOST` when bound to `--host 0.0.0.0`
+  (`unrolled/secure v1.18.0`). Freeze service-account edits on un-upgraded
+  `20261109` nodes during rollout; after upgrading every site, review accounts
+  that `svcacct info` reports with `Policy: implied` and re-apply restrictions
+  where needed.
+
+- S3 `DeleteObjects` on a single pool stops at an entry whose name fails the
+  object name check: the entry returns `XMinioInvalidObjectName` and is not
+  locked or sent to a drive, as with a single-object DELETE and with more than
+  one pool. Until now such an entry still reached the drives of the node, where
+  a name with a `..` segment was joined to the request bucket. A caller allowed
+  to delete in one bucket could remove a version in another bucket, including
+  one under Object Lock retention, and from a versioned bucket could put a
+  delete marker on an object of another bucket or on stored system metadata
+  such as a bucket's configuration. The other entries of a request are deleted
+  as before.
+
+- Site replication sends a service account or access key as the record its
+  site has stored, whole: for a create, for every edit, at the first sync of a
+  new site and when healing. IAM export writes that record too. Until now an
+  edit was sent as the fields it changed. A peer that an earlier edit had not
+  reached, or reached late, kept the old secret key, status or inline policy
+  under the revision of the later edit, and healing took the sites for equal:
+  a key that was rotated, disabled or restricted on one site stayed as it was
+  on the other. Sync, heal and export took the claims and the inline policy, and
+  heal the secret key and status as well, from the cache of the server that ran
+  them, which can predate an edit made through another server of the site, and
+  sent them under the revision of the stored record. A service account created
+  for a user that had been deleted and created again did not reach the peers
+  before healing. Peers on 20261109 and 20261026 apply the new items as they
+  apply a healed account, and an edit that names no policy no longer removes the
+  inline policy on such a peer; a site that is not upgraded still sends its own
+  edits the old way. An edit now gives every site the whole account of the site
+  that took it, so accounts that already differ between sites are not repaired
+  by the upgrade, but by the next edit: after upgrading every site, review such
+  accounts and edit each one at a site that has it right.
+
 ## RELEASE.2026-11-09T00-00-00Z
 
-Package version: `20261109000000.0.0`. Publication status and artifacts are
-listed in [GitHub Releases](https://github.com/pgsty/silo/releases). This
-section covers the changes after the published 20261026 source `c3ad836aed0d`.
-Most fixes come from reports and patches by
-[@botdeniska](https://github.com/botdeniska); see [CONTRIBUTORS.md](CONTRIBUTORS.md).
+Package version: `20261109000000.0.0`; published from source `d998292387cc`.
+Artifacts are listed in the [GitHub release](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-11-09T00-00-00Z).
+The coordinated [English release notes](https://silo.pgsty.com/blog/release/silo-20261109/)
+and [Chinese release notes](https://silo.pgsty.com/zh/blog/release/silo-20261109/)
+cover all components, upgrade guidance, and validation scope since the
+published 20261026 source `c3ad836aed0d`. Most fixes come from reports and
+patches by [@botdeniska](https://github.com/botdeniska); see [CONTRIBUTORS.md](CONTRIBUTORS.md).
 
 Lifecycle, multi-pool and tiering:
 
@@ -21,7 +203,8 @@ Lifecycle, multi-pool and tiering:
   `retainVersions: 0`) on the expired key instead of the keys below it; a key
   with a tiered or Object Lock protected version is refused
   ([#297](https://github.com/pgsty/silo/issues/297)).
-- Stop taking the free version of a deleted tiered version for a version
+- Exclude the internal free-version marker of a deleted tiered version from
+  visible version history and lifecycle decisions
   ([#263](https://github.com/pgsty/silo/issues/263)), apply rules whose only
   action is `DelMarkerExpiration` ([#268](https://github.com/pgsty/silo/issues/268)),
   and report and account only the removals that happened
@@ -167,7 +350,7 @@ Known issues: `ListMultipartUploads` prefix and paging
 ([#217](https://github.com/pgsty/silo/issues/217)), replayed bucket creation
 under site replication ([PR #241](https://github.com/pgsty/silo/pull/241)), and
 `403` instead of the server error for reads allowed only by object tags while
-the object is unreadable ([#293](https://github.com/pgsty/silo/issues/293)).
+the object is unreadable ([PR #294](https://github.com/pgsty/silo/pull/294)).
 
 ## RELEASE.2026-10-26T00-00-00Z
 

CONTRIBUTING.md

@@ -165,8 +165,11 @@ license grant to SILO or upstream MinIO maintainers is required.
 
 ### How does Silo manage dependencies?
 
-Silo uses Go modules. Preserve the compatibility module and import paths in
-`go.mod`; downstream forks are selected with explicit `replace` directives.
+Silo uses Go modules. Shared packages in `github.com/pgsty/silo-pkg/v3` are
+required and imported directly under their own module path, upstream
+`github.com/minio/minio-go/v7` is pinned to a verified commit, and Console
+(`github.com/minio/console`) and MC (`github.com/minio/mc`) are selected with
+explicit `replace` directives in `go.mod`.
 
 - Run `go get foo/bar` in the source folder to add the dependency to `go.mod` file.
 

Dockerfile.distroless

@@ -14,7 +14,7 @@ RUN mkdir -p /prep/data && chmod 0777 /prep/data
 # Debian's bundle in distroless still trusts the roots the classic image
 # blocklists. Build the same bundle as Dockerfile.goreleaser so both variants
 # trust the same roots; it is architecture-neutral, so build it natively.
-FROM --platform=$BUILDPLATFORM registry.access.redhat.com/ubi9/ubi:latest@sha256:16e9e43d99e181463513cc84a514859b1abb9460f1c4d9e208da4b4e51cd5cc3 AS certs
+FROM --platform=$BUILDPLATFORM registry.access.redhat.com/ubi9/ubi:latest@sha256:8b212f75a0e5a156ac28b1c5c030d2e8a07715254e19d522286118279399af81 AS certs
 # Native root blocklist mitigation: https://access.redhat.com/security/vulnerabilities/RHSB-2026-012
 RUN dnf -y install ca-certificates && \
     if [ -d /etc/pki/ca-trust/source/blocklist ]; then \

Dockerfile.goreleaser

@@ -1,4 +1,4 @@
-FROM golang:1.27.3-alpine@sha256:d530cf60723abf1ffae0cd16bb546b379ec0550d2f3815e5b16ed69dbc00fba4 AS curl-build
+FROM golang:1.27.4-alpine@sha256:0a5f7fe796599ff487605987432e7619ae45beeb2fba4c2ce0b907879932aebf AS curl-build
 ARG TARGETARCH
 COPY dockerscripts/build-static-curl.sh /build/build-static-curl
 RUN /bin/sh /build/build-static-curl
@@ -9,7 +9,7 @@ COPY --from=curl-build /go/bin/curl /curl
 COPY --from=curl-build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
 ENTRYPOINT ["/curl"]
 
-FROM golang:1.27.3-alpine@sha256:d530cf60723abf1ffae0cd16bb546b379ec0550d2f3815e5b16ed69dbc00fba4 AS build
+FROM golang:1.27.4-alpine@sha256:0a5f7fe796599ff487605987432e7619ae45beeb2fba4c2ce0b907879932aebf AS build
 
 ARG TARGETARCH
 
@@ -17,9 +17,9 @@ ENV GOPATH=/go
 ENV CGO_ENABLED=0
 
 ARG MC_REPO=pgsty/mc
-ARG MC_VERSION=RELEASE.2026-11-09T00-00-00Z
-ARG MC_AMD64_SHA256=79e6cf4ad00a9e5eb2e7ceccc6e6496e4af4ec096e59695515ea8f223c287e4a
-ARG MC_ARM64_SHA256=5473c4b39a31dd66478f5c44686a09f3e9e37861a30f1faf18564fbe66118387
+ARG MC_VERSION=RELEASE.2026-11-12T00-00-00Z
+ARG MC_AMD64_SHA256=68875c7fdd06a76af12b74753506df65226d1bec65a405d2617d76448c229ba2
+ARG MC_ARM64_SHA256=4ea59d2f278c96b25e380289fd2ee9bc49faa342687074f031805cb7b34fbe1a
 
 RUN apk add -U --no-cache \
     ca-certificates \
@@ -69,7 +69,7 @@ RUN apk add -U --no-cache \
     mkdir -p /go/share/mcli && \
     cp /tmp/mcli-extract/LICENSE /tmp/mcli-extract/NOTICE /tmp/mcli-extract/CREDITS /go/share/mcli/
 
-FROM registry.access.redhat.com/ubi9/ubi:latest@sha256:16e9e43d99e181463513cc84a514859b1abb9460f1c4d9e208da4b4e51cd5cc3 AS certs
+FROM registry.access.redhat.com/ubi9/ubi:latest@sha256:8b212f75a0e5a156ac28b1c5c030d2e8a07715254e19d522286118279399af81 AS certs
 # Native root blocklist mitigation: https://access.redhat.com/security/vulnerabilities/RHSB-2026-012
 RUN dnf -y install ca-certificates && \
     if [ -d /etc/pki/ca-trust/source/blocklist ]; then \
@@ -88,7 +88,7 @@ RUN dnf -y install ca-certificates && \
     dnf clean all && \
     rm -rf /var/cache/dnf
 
-FROM registry.access.redhat.com/ubi9/ubi-micro:latest@sha256:5be877a2a280ae36eb9ab80ca4efb28bbf77c57abbba38137cdc37a03b8465e6
+FROM registry.access.redhat.com/ubi9/ubi-micro:latest@sha256:b59ac4f291d86027c2681f7a7b1cbf7448972fc55a6cb8e25cab5aa5eef5ce5f
 
 LABEL org.opencontainers.image.title="Silo" \
       org.opencontainers.image.description="S3-Interface Libre Object Storage" \

PULL_REQUESTS_ETIQUETTE.md

@@ -42,7 +42,8 @@ PRs must flow smoothly through review to reach production. Large PRs should be s
    - Document testing steps in the PR summary if manual testing was performed.
 
 4. **Before Submitting**:
-   - Run `make verify` to check formatting, linting, and tests.
+   - Sign off every commit under the Developer Certificate of Origin (`git commit -s`).
+   - Run `make verifiers` to check formatting, linting, code generation, and `rebrand-guard`.
    - Reference related issues (e.g., “Closes #1234”).
    - Notify team members via GitHub `@mentions` if urgent or complex.
 

README.md

@@ -36,7 +36,7 @@
 
 PGSTY SILO keeps one maintained release line of the open-source MinIO server alive after upstream ended community distribution: builds, packages, multi-arch images, security fixes, and the full web console. Pigsty runs it in production as its PostgreSQL backup repository.
 
-It follows one rule — **the product and its delivery surfaces are renamed; the protocol and your data are not.** Everything else lives on [silo.pgsty.com](https://silo.pgsty.com/).
+It follows one rule: **the product and its delivery surfaces are renamed; the protocol and your data are not.** Full documentation is published at [silo.pgsty.com](https://silo.pgsty.com/).
 
 **Related:** [`pgsty/mc`](https://github.com/pgsty/mc) · [`pgsty/silo-console`](https://github.com/pgsty/silo-console) · [`pgsty/silo-pkg`](https://github.com/pgsty/silo-pkg) · [`pgsty/kes`](https://github.com/pgsty/kes) · [`pgsty/pigsty`](https://github.com/pgsty/pigsty)
 
@@ -44,10 +44,10 @@ It follows one rule — **the product and its delivery surfaces are renamed; the
   <img src="https://silo.pgsty.com/images/silo-console/console-metrics-simple.webp" alt="Silo Console">
 </p>
 
-#### SILO 20261109
+### SILO 20261109
 
 > [!WARNING]
-> [SILO 20261109](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-11-09T00-00-00Z) fixes bugs and security vulnerabilities. We strongly recommend scheduling an upgrade to reduce security risks.
+> [SILO 20261109](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-11-09T00-00-00Z) (`20261109000000.0.0`, source `d998292387cc`) fixes storage, lifecycle, native restore, Object Lock, batch authorization, and IAM defects, embedding Console `v2.7.0` with `mcli 20261109`, `silo-pkg v3.16.0`, and Go `1.27.3`. Review the [release notes and upgrade requirements](https://silo.pgsty.com/blog/release/silo-20261109/) before upgrading.
 
 > [!NOTE]
 > On 2026-08-06, `pgsty/minio` became `pgsty/silo`, and the default branch changed from `master` to `main`. The last MinIO-branded release is [`20260804`](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-08-04T00-00-00Z) on the [`minio`](https://github.com/pgsty/silo/tree/minio) branch.
@@ -86,7 +86,7 @@ docker exec silo mcli mb local/demo && docker exec silo mcli ls local
 | Kubernetes | Helm chart, see [Download & Install](https://silo.pgsty.com/download/) |
 | Source | `go build -o silo . && ./silo --version` |
 
-Every release ships checksums, SPDX SBOMs, Sigstore-signed manifests, and GitHub build attestations. Installation methods and verification commands are documented at [Download & Install](https://silo.pgsty.com/download/); migrating from upstream MinIO — taking over an existing `minio.service` and its `/etc/default/minio`, and keeping data ownership stable with a `/etc/systemd/system/silo.service.d/10-legacy-user.conf` drop-in — is covered by the [migration guide](https://silo.pgsty.com/compatibility/migration/) and the [binary & service notes](https://silo.pgsty.com/compatibility/binary/).
+Every release ships checksums, SPDX SBOMs, Sigstore-signed manifests, and GitHub build attestations. Installation methods and verification commands are documented at [Download & Install](https://silo.pgsty.com/download/). To migrate from upstream MinIO, take over `minio.service` and `/etc/default/minio`, and preserve data ownership with a `/etc/systemd/system/silo.service.d/10-legacy-user.conf` drop-in. See the [migration guide](https://silo.pgsty.com/compatibility/migration/) and [binary & service notes](https://silo.pgsty.com/compatibility/binary/).
 
 ## Compatibility
 
@@ -98,7 +98,7 @@ Every divergence from upstream is listed in the code-verified [compatibility aud
 
 ### TLS and Go upgrades
 
-Server 20260916 restored Go's default key exchange; Server 20261018 retains it with Go 1.27.2.
+Server 20260916 restored Go's default key exchange; Server 20261109 retains it with Go 1.27.3.
 TLS key exchange follows Go's defaults across the S3 listener, node links,
 replication, identity providers, etcd, and external HTTP services. If an endpoint
 cannot accept ML-KEM, `GODEBUG=tlsmlkem=0` disables the default hybrid exchanges

README_ZH.md

@@ -36,7 +36,7 @@
 
 上游停止社区发行后，Silo 为开源 MinIO 服务端维护一条持续可用的版本线：构建、软件包、多架构镜像、安全修复与完整 Web 控制台。Pigsty 在生产环境中用它承载 PostgreSQL 备份存储。
 
-它只遵循一条原则：**改名的是产品与交付物，不是协议与你的数据。** 其余内容都在 [silo.pgsty.com](https://silo.pgsty.com/zh/)。
+它只遵循一条原则：**改名的是产品与交付物，不是协议与你的数据。** 完整文档发布在 [silo.pgsty.com](https://silo.pgsty.com/zh/)。
 
 **相关项目：**[`pgsty/mc`](https://github.com/pgsty/mc) · [`pgsty/silo-console`](https://github.com/pgsty/silo-console) · [`pgsty/silo-pkg`](https://github.com/pgsty/silo-pkg) · [`pgsty/kes`](https://github.com/pgsty/kes) · [`pgsty/pigsty`](https://github.com/pgsty/pigsty)
 
@@ -44,10 +44,10 @@
   <img src="https://silo.pgsty.com/images/silo-console/console-metrics-simple.webp" alt="Silo 控制台">
 </p>
 
-#### SILO 20261109
+### SILO 20261109
 
 > [!WARNING]
-> [SILO 20261109](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-11-09T00-00-00Z) 修复了缺陷与安全漏洞，强烈建议尽快安排升级，以降低安全风险。
+> [SILO 20261109](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-11-09T00-00-00Z)（包版本 `20261109000000.0.0`，源码 `d998292387cc`）修复了多池生命周期、原生恢复、Object Lock、批处理授权与 IAM 等缺陷，内嵌 Console `v2.7.0` 并配套 `mcli 20261109`、`silo-pkg v3.16.0` 与 Go `1.27.3`。升级前请阅读[发布说明与升级要求](https://silo.pgsty.com/zh/blog/release/silo-20261109/)。
 
 > [!NOTE]
 > 2026-08-06，`pgsty/minio` 更名为 `pgsty/silo`，默认分支由 `master` 改为 `main`。最后一个 MinIO 品牌发布是 [`minio`](https://github.com/pgsty/silo/tree/minio) 分支上的 [`20260804`](https://github.com/pgsty/silo/releases/tag/RELEASE.2026-08-04T00-00-00Z)。
@@ -98,9 +98,9 @@ Silo 保留 S3 与存储格式兼容性，包括既有 `MINIO_*` 环境变量、
 
 ### TLS 与 Go 升级
 
-Server 20260916 已恢复 Go 默认密钥交换策略，20261018 在 Go 1.27.2 下保留该行为。
-`GODEBUG=tlsmlkem=0`、`tlssecpmlkem=0` 的适用范围、macOS 根证书来源变化，
-以及 OIDC discovery 的诊断方法见 [Go 1.27 TLS 与 OIDC 指南](https://silo.pgsty.com/zh/blog/design/go127-tls-oidc-discovery/)。
+Server 20260916 恢复了 Go 默认密钥交换策略，Server 20261109 在 Go 1.27.3 下保留该行为。S3 监听端口、节点间连接、站点与桶复制、身份提供方、etcd 及外部 HTTP 服务均使用 Go 默认 TLS 密钥交换。若对端无法接受 ML-KEM，设置 `GODEBUG=tlsmlkem=0` 可在当前进程禁用默认混合密钥交换（证书校验保持开启）；该选项不会禁用 ML-DSA 签名，也不能解决所有 TLS 连接重置问题，建议在升级不兼容对端后移除该临时配置。若仅新增的 SecP 混合组引发问题，可设置 `GODEBUG=tlssecpmlkem=0` 仅禁用这些组并保留 `X25519MLKEM768`。
+
+在 Go 1.27 构建中，macOS 上设置 `SSL_CERT_FILE` 或 `SSL_CERT_DIR` 会以磁盘根证书和 Go 验证器替代系统钥匙串信任；陈旧或不完整的 CA 路径可能导致原先受信任的连接失败，清除继承的环境变量即可恢复钥匙串信任。配置的 `CAs` 目录中的显式证书仍会叠加加入所选根证书池。Go 1.27 二进制要求 macOS 13 或更高版本。详见 [Go 1.27 发行说明](https://go.dev/doc/go1.27)与 [Go 1.27 TLS 与 OIDC 发现指南](https://silo.pgsty.com/zh/blog/design/go127-tls-oidc-discovery/)。
 
 ## 文档归属
 

SECURITY.md

@@ -38,7 +38,7 @@ For vulnerabilities in this fork:
 
 1. Follow the fork-specific expectations in [VULNERABILITY_REPORT.md](VULNERABILITY_REPORT.md).
 2. Prefer this repository's [private GitHub security advisory](https://github.com/pgsty/silo/security/advisories/new) workflow.
-3. If you cannot use GitHub private reporting, email [ron@pgsty.com](mailto:ron@pgsty.com) or rh@vonng.com
+3. If you cannot use GitHub private reporting, email [ron@pgsty.com](mailto:ron@pgsty.com) or [rh@vonng.com](mailto:rh@vonng.com)
    directly. Do not publish vulnerability details or exploit code in public
    issues or pull requests.
 4. If you confirm the issue also affects upstream `minio/minio`, report it upstream separately.

buildscripts/check-release-commit.sh

@@ -0,0 +1,116 @@
+#!/usr/bin/env bash
+
+# Fail closed before a release job builds a commit that main never accepted or
+# that CI never validated.
+#
+# check-release-state.sh answers "is this tag safe to write to". This answers
+# the other half: "is this commit safe to ship". The release workflow already
+# proves the tag resolves to the checkout, but a tag can be pushed to any
+# commit at any time, including one that never landed on main and one whose
+# tests have not finished.
+
+set -euo pipefail
+
+release_commit="${1:-}"
+fixture="${2:-}"
+repository="${GITHUB_REPOSITORY:-pgsty/silo}"
+release_branch="${RELEASE_BRANCH:-origin/main}"
+
+# Workflows that must have a successful run for this exact commit, keyed by the
+# workflow file path rather than the display name: a name is free text, so a
+# second workflow could otherwise be added that calls itself "Go CI", succeeds
+# trivially, and satisfies this check while the real one fails.
+required_workflow_paths=(
+	".github/workflows/go.yml"
+	".github/workflows/vulncheck.yml"
+)
+
+if ! command -v jq >/dev/null 2>&1; then
+	echo "jq is required to inspect workflow runs" >&2
+	exit 1
+fi
+
+if [[ ! "${release_commit}" =~ ^[0-9a-f]{40}$ ]]; then
+	echo "Invalid release commit: ${release_commit:-<empty>}" >&2
+	exit 1
+fi
+
+if [ -z "${fixture}" ]; then
+	if ! git rev-parse --verify --quiet "${release_branch}" >/dev/null; then
+		echo "Cannot resolve ${release_branch}; fetch it before releasing" >&2
+		exit 1
+	fi
+	# The exact tip, not merely an ancestor: an older commit on main has no
+	# push run of its own when it arrived as part of a multi-commit push, and a
+	# release must not trail behind what main already contains.
+	tip="$(git rev-parse "${release_branch}^{commit}")"
+	if [ "${tip}" != "${release_commit}" ]; then
+		echo "Refusing to release ${release_commit}: ${release_branch} is at ${tip}" >&2
+		exit 1
+	fi
+	echo "Release commit ${release_commit} is the tip of ${release_branch}."
+
+	error_file="$(mktemp)"
+	trap 'rm -f "${error_file}"' EXIT
+	# A pull_request run checks out GitHub's synthetic merge ref, so a green
+	# run proves the merge result was good, not that this commit was ever built
+	# on its own. exclude_pull_requests only trims the pull_requests field of
+	# each run; the event/head_branch filter below is what drops those runs.
+	if ! runs_json="$(
+		gh api --paginate \
+			"repos/${repository}/actions/runs?head_sha=${release_commit}&exclude_pull_requests=true&per_page=100" \
+			--jq '.workflow_runs[] | {path, event, head_branch, head_sha, status, conclusion, run_number, run_attempt}' \
+			2>"${error_file}" | jq -s '.'
+	)"; then
+		cat "${error_file}" >&2
+		exit 1
+	fi
+else
+	runs_json="$(<"${fixture}")"
+fi
+
+if ! jq -e 'type == "array" and all(.[]; type == "object" and (.path | type == "string"))' \
+	<<<"${runs_json}" >/dev/null 2>&1; then
+	echo "Invalid workflow run response for ${release_commit}" >&2
+	exit 1
+fi
+
+fail=0
+for workflow in "${required_workflow_paths[@]}"; do
+	# Only runs that actually built this commit count: the right workflow file,
+	# triggered by the push that put this SHA on main. A manual dispatch is not
+	# substitute evidence - it can be run from any ref. Take the newest such
+	# run; an older success must not paper over a later failure.
+	latest="$(jq -c --arg path "${workflow}" --arg sha "${release_commit}" '
+		[ .[]
+		  | select(.path == $path)
+		  | select(.head_sha == $sha)
+		  | select(.event == "push" and .head_branch == "main")
+		]
+		| sort_by([.run_number // 0, .run_attempt // 0])
+		| last // null' <<<"${runs_json}")"
+
+	if [ "${latest}" = "null" ]; then
+		echo "Required workflow ${workflow} has no qualifying run for ${release_commit} (no run)" >&2
+		fail=1
+		continue
+	fi
+
+	status="$(jq -r '.status // "unknown"' <<<"${latest}")"
+	conclusion="$(jq -r '.conclusion // "none"' <<<"${latest}")"
+	if [ "${status}" != "completed" ] || [ "${conclusion}" != "success" ]; then
+		observed="${conclusion}"
+		if [ "${status}" != "completed" ]; then
+			observed="${status}"
+		fi
+		echo "Required workflow ${workflow} did not succeed for ${release_commit} (${observed})" >&2
+		fail=1
+	fi
+done
+
+if [ "${fail}" -ne 0 ]; then
+	echo "Refusing to release ${release_commit}: required checks are not green" >&2
+	exit 1
+fi
+
+echo "Required workflows are green for ${release_commit}."

buildscripts/check-release-commit_test.sh

@@ -0,0 +1,132 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+checker="${script_dir}/check-release-commit.sh"
+commit="0123456789abcdef0123456789abcdef01234567"
+other_commit="89abcdef0123456789abcdef0123456789abcdef"
+fixture="$(mktemp)"
+stdout_file="$(mktemp)"
+stderr_file="$(mktemp)"
+trap 'rm -f "${fixture}" "${stdout_file}" "${stderr_file}"' EXIT
+
+expect_success() {
+	if ! "${checker}" "$@" >"${stdout_file}" 2>"${stderr_file}"; then
+		cat "${stderr_file}" >&2
+		return 1
+	fi
+}
+
+expect_failure() {
+	if "${checker}" "$@" >"${stdout_file}" 2>"${stderr_file}"; then
+		echo "Expected release-commit check to fail: $*" >&2
+		cat "${stdout_file}" >&2
+		return 1
+	fi
+}
+
+# run <path> <conclusion> [event] [branch] [sha] [run_number] [status]
+run() {
+	local path="$1" conclusion="$2"
+	local event="${3:-push}" branch="${4:-main}" sha="${5:-${commit}}"
+	local number="${6:-1}" status="${7:-completed}"
+	local conclusion_json="\"${conclusion}\""
+	[ "${conclusion}" = "null" ] && conclusion_json=null
+	printf '{"path":"%s","event":"%s","head_branch":"%s","head_sha":"%s","status":"%s","conclusion":%s,"run_number":%s,"run_attempt":1}' \
+		"${path}" "${event}" "${branch}" "${sha}" "${status}" "${conclusion_json}" "${number}"
+}
+
+go_ok="$(run .github/workflows/go.yml success)"
+vuln_ok="$(run .github/workflows/vulncheck.yml success)"
+
+all_green() {
+	printf '[%s,%s]\n' "${go_ok}" "${vuln_ok}" >"${fixture}"
+}
+
+# Baseline: both required workflows green on a push to main.
+all_green
+expect_success "${commit}" "${fixture}"
+grep -qF "Required workflows are green for ${commit}." "${stdout_file}"
+
+# A manual dispatch is not evidence: it can be run from any ref.
+printf '[%s,%s]\n' \
+	"$(run .github/workflows/go.yml success workflow_dispatch main)" \
+	"${vuln_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "no qualifying run" "${stderr_file}"
+
+# A re-run that finally succeeded is enough; the earlier failure is history.
+printf '[%s,%s,%s]\n' \
+	"$(run .github/workflows/go.yml failure push main "${commit}" 1)" \
+	"$(run .github/workflows/go.yml success push main "${commit}" 2)" \
+	"${vuln_ok}" >"${fixture}"
+expect_success "${commit}" "${fixture}"
+
+# ...but a LATER failure must not be papered over by an earlier success.
+printf '[%s,%s,%s]\n' \
+	"$(run .github/workflows/go.yml success push main "${commit}" 1)" \
+	"$(run .github/workflows/go.yml failure push main "${commit}" 2)" \
+	"${vuln_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "Required workflow .github/workflows/go.yml did not succeed" "${stderr_file}"
+grep -qF "(failure)" "${stderr_file}"
+
+# A decoy workflow that merely calls itself "Go CI" must not satisfy the gate.
+printf '[%s,%s]\n' \
+	"$(run .github/workflows/decoy.yml success)" "${vuln_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "Required workflow .github/workflows/go.yml has no qualifying run" "${stderr_file}"
+
+# A pull_request run tests GitHub's merge ref, not this commit on its own.
+printf '[%s,%s]\n' \
+	"$(run .github/workflows/go.yml success pull_request feature)" "${vuln_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "no qualifying run" "${stderr_file}"
+
+# A push run on some other branch is not evidence that main accepted it.
+printf '[%s,%s]\n' \
+	"$(run .github/workflows/go.yml success push feature)" "${vuln_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "no qualifying run" "${stderr_file}"
+
+# A run reporting a different head_sha must be ignored.
+printf '[%s,%s]\n' \
+	"$(run .github/workflows/go.yml success push main "${other_commit}")" "${vuln_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "no qualifying run" "${stderr_file}"
+
+# Missing workflow entirely.
+printf '[%s]\n' "${go_ok}" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "Required workflow .github/workflows/vulncheck.yml has no qualifying run" "${stderr_file}"
+
+# Still running.
+printf '[%s,%s]\n' "${go_ok}" \
+	"$(run .github/workflows/vulncheck.yml null push main "${commit}" 1 in_progress)" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "(in_progress)" "${stderr_file}"
+
+# Cancelled counts as not green.
+printf '[%s,%s]\n' "${go_ok}" \
+	"$(run .github/workflows/vulncheck.yml cancelled)" >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "(cancelled)" "${stderr_file}"
+
+# Malformed API response.
+printf '{not-json}\n' >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "Invalid workflow run response for ${commit}" "${stderr_file}"
+
+# An empty array is a valid response that satisfies nothing.
+printf '[]\n' >"${fixture}"
+expect_failure "${commit}" "${fixture}"
+grep -qF "Required workflow .github/workflows/go.yml has no qualifying run" "${stderr_file}"
+
+expect_failure "not-a-commit" "${fixture}"
+grep -qF "Invalid release commit" "${stderr_file}"
+
+expect_failure "" "${fixture}"
+grep -qF "Invalid release commit: <empty>" "${stderr_file}"
+
+echo "release-commit decision tests passed"

buildscripts/checkdeps.sh

@@ -7,7 +7,7 @@ _init() {
 
 	## Minimum required versions for build dependencies
 	GIT_VERSION="1.0"
-	GO_VERSION="1.27.3"
+	GO_VERSION="1.27.4"
 	OSX_VERSION="10.8"
 	KNAME=$(uname -s)
 	ARCH=$(uname -m)

buildscripts/install-mcli.sh

@@ -40,7 +40,7 @@ if [ -n "${MCLI_BIN:-}" ]; then
 	exit 0
 fi
 
-release=${MCLI_RELEASE:-RELEASE.2026-11-09T00-00-00Z}
+release=${MCLI_RELEASE:-RELEASE.2026-11-12T00-00-00Z}
 version_hyphen=${release#RELEASE.}
 package_version=$(printf '%s\n' "${version_hyphen}" | sed -E 's/^([0-9]{4})-([0-9]{2})-([0-9]{2})T([0-9]{2})-([0-9]{2})-([0-9]{2})Z$/\1\2\3\4\5\6.0.0/')
 if [ "${package_version}" = "${version_hyphen}" ]; then

buildscripts/release-dependency-guard/main.go

@@ -0,0 +1,156 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+// release-dependency-guard checks the modules and bundled client actually used
+// by a release. A local workspace must not substitute unreleased source trees.
+package main
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"regexp"
+	"strings"
+
+	"golang.org/x/mod/semver"
+)
+
+type module struct {
+	Path, Version, Dir string
+	Main               bool
+	Replace            *module
+}
+
+func selected(m module, path string) (module, error) {
+	if m.Replace != nil {
+		m = *m.Replace
+	}
+	if m.Main || m.Path != path || m.Version == "" {
+		return module{}, fmt.Errorf("%s must select an immutable maintained module, got %s@%s", path, m.Path, m.Version)
+	}
+	return m, nil
+}
+
+func atLeast(version, minimum string) bool {
+	return semver.IsValid(version) && semver.Prerelease(version) == "" && semver.Compare(version, minimum) >= 0
+}
+
+func validate(modules map[string]module, consoleVersion, mcTag, mcCommit string) error {
+	pkg, err := selected(modules["github.com/pgsty/silo-pkg/v3"], "github.com/pgsty/silo-pkg/v3")
+	if err != nil {
+		return err
+	}
+	if !atLeast(pkg.Version, "v3.16.1") {
+		return fmt.Errorf("silo-pkg %s lacks the strict policy release; need v3.16.1 or newer", pkg.Version)
+	}
+	if _, err := selected(modules["github.com/minio/console"], "github.com/pgsty/silo-console"); err != nil {
+		return err
+	}
+	if !atLeast("v"+consoleVersion, "v2.7.2") {
+		return fmt.Errorf("embedded Console %s lacks the v2.7.2 release; need 2.7.2 or newer", consoleVersion)
+	}
+	mc, err := selected(modules["github.com/minio/mc"], "github.com/pgsty/mc")
+	if err != nil {
+		return err
+	}
+	if !regexp.MustCompile(`^RELEASE\.\d{4}-\d{2}-\d{2}T\d{2}-\d{2}-\d{2}Z$`).MatchString(mcTag) || mcTag <= "RELEASE.2026-11-09T00-00-00Z" {
+		return fmt.Errorf("bundled mcli %s must be a release after 20261109", mcTag)
+	}
+	if len(mcCommit) != 40 || !strings.HasSuffix(mc.Version, "-"+mcCommit[:12]) {
+		return fmt.Errorf("mc module %s does not match Dockerfile.goreleaser tag %s (%s)", mc.Version, mcTag, mcCommit)
+	}
+	return nil
+}
+
+func command(name string, args ...string) ([]byte, error) {
+	cmd := exec.Command(name, args...)
+	cmd.Stderr = os.Stderr
+	return cmd.Output()
+}
+
+func check() error {
+	if err := os.Setenv("GOWORK", "off"); err != nil {
+		return err
+	}
+	data, err := command("go", "list", "-mod=readonly", "-m", "-json", "github.com/pgsty/silo-pkg/v3", "github.com/minio/console", "github.com/minio/mc")
+	if err != nil {
+		return err
+	}
+	modules := make(map[string]module)
+	dec := json.NewDecoder(bytes.NewReader(data))
+	for {
+		var m module
+		if err := dec.Decode(&m); err != nil {
+			if err == io.EOF {
+				break
+			}
+			return err
+		}
+		modules[m.Path] = m
+	}
+	pkg, err := selected(modules["github.com/pgsty/silo-pkg/v3"], "github.com/pgsty/silo-pkg/v3")
+	if err != nil {
+		return err
+	}
+	if !atLeast(pkg.Version, "v3.16.1") {
+		return fmt.Errorf("release blocked: select silo-pkg v3.16.1 or newer (currently %s)", pkg.Version)
+	}
+	console, err := selected(modules["github.com/minio/console"], "github.com/pgsty/silo-console")
+	if err != nil {
+		return err
+	}
+	if console.Dir == "" {
+		data, err = command("go", "mod", "download", "-json", console.Path+"@"+console.Version)
+		if err != nil {
+			return err
+		}
+		if err := json.Unmarshal(data, &console); err != nil {
+			return err
+		}
+	}
+	data, err = os.ReadFile(filepath.Join(console.Dir, "web-app", "package.json"))
+	if err != nil {
+		return err
+	}
+	var metadata struct{ Version string }
+	if err := json.Unmarshal(data, &metadata); err != nil {
+		return err
+	}
+	data, err = os.ReadFile("Dockerfile.goreleaser")
+	if err != nil {
+		return err
+	}
+	match := regexp.MustCompile(`(?m)^ARG MC_VERSION=(\S+)\s*$`).FindSubmatch(data)
+	if len(match) != 2 {
+		return fmt.Errorf("Dockerfile.goreleaser must pin MC_VERSION")
+	}
+	tag := string(match[1])
+	data, err = command("gh", "api", "repos/pgsty/mc/commits/"+tag, "--jq", ".sha")
+	if err != nil {
+		return err
+	}
+	commit := strings.TrimSpace(string(data))
+	if err := validate(modules, metadata.Version, tag, commit); err != nil {
+		return err
+	}
+	data, err = command("gh", "api", "repos/pgsty/mc/compare/d7262c2a5fbdf2b9503cc0283f1d37ae8da41baf..."+commit, "--jq", ".status")
+	if err != nil {
+		return err
+	}
+	if status := strings.TrimSpace(string(data)); status != "ahead" && status != "identical" {
+		return fmt.Errorf("mcli %s does not include the access-key policy repair", tag)
+	}
+	fmt.Printf("Release dependencies verified: silo-pkg %s, Console %s, mcli %s (%s)\n", pkg.Version, metadata.Version, tag, commit)
+	return nil
+}
+
+func main() {
+	if err := check(); err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+}

buildscripts/release-dependency-guard/main_test.go

@@ -0,0 +1,44 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package main
+
+import "testing"
+
+func TestReleaseDependencySelection(t *testing.T) {
+	const commit = "0123456789abcdef0123456789abcdef01234567"
+	for _, tc := range []struct {
+		name, pkg, console, tag, mcSHA string
+		local, upstream, wantError     bool
+	}{
+		{name: "coordinated", pkg: "v3.16.1", console: "2.7.2", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: commit},
+		{name: "old-package", pkg: "v3.16.0", console: "2.7.2", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: commit, wantError: true},
+		{name: "prerelease-package", pkg: "v3.16.1-rc.1", console: "2.7.2", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: commit, wantError: true},
+		{name: "old-embedded-console", pkg: "v3.16.1", console: "2.7.1", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: commit, wantError: true},
+		{name: "old-container-client", pkg: "v3.16.1", console: "2.7.2", tag: "RELEASE.2026-11-09T00-00-00Z", mcSHA: commit, wantError: true},
+		{name: "source-binary-mismatch", pkg: "v3.16.1", console: "2.7.2", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: "ffffffffffffffffffffffffffffffffffffffff", wantError: true},
+		{name: "workspace-console", pkg: "v3.16.1", console: "2.7.2", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: commit, local: true, wantError: true},
+		{name: "upstream-console", pkg: "v3.16.1", console: "2.7.2", tag: "RELEASE.2026-11-12T00-00-00Z", mcSHA: commit, upstream: true, wantError: true},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			modules := map[string]module{
+				"github.com/pgsty/silo-pkg/v3": {Path: "github.com/pgsty/silo-pkg/v3", Version: tc.pkg},
+				"github.com/minio/console": {Path: "github.com/minio/console", Replace: &module{
+					Path: "github.com/pgsty/silo-console", Version: "v0.0.0-20261112000000-0123456789ab",
+				}},
+				"github.com/minio/mc": {Path: "github.com/minio/mc", Replace: &module{
+					Path: "github.com/pgsty/mc", Version: "v0.0.0-20261112000000-0123456789ab",
+				}},
+			}
+			if tc.local {
+				modules["github.com/minio/console"].Replace.Version = ""
+			}
+			if tc.upstream {
+				modules["github.com/minio/console"].Replace.Path = "github.com/minio/console"
+			}
+			if err := validate(modules, tc.console, tc.tag, tc.mcSHA); (err != nil) != tc.wantError {
+				t.Fatalf("got %v, wantError=%t", err, tc.wantError)
+			}
+		})
+	}
+}

buildscripts/verify-helm-migration.sh

@@ -120,6 +120,10 @@ if [ -z "${app_version}" ] || [ "${image_tag}" != "${app_version}" ]; then
 	echo "helm/silo: image.tag '${image_tag}' must equal appVersion '${app_version}'" >&2
 	exit 1
 fi
+if [ -n "${RELEASE_TAG:-}" ] && [ "${image_tag}" != "${RELEASE_TAG}" ]; then
+	echo "helm/silo: image.tag '${image_tag}' must equal RELEASE_TAG '${RELEASE_TAG}'" >&2
+	exit 1
+fi
 
 helm_run package "${new_chart}" --destination "${output_dir}" >/dev/null
 test -s "${work_dir}/silo-${chart_version}.tgz"

cmd/admin-bucket-handlers.go

@@ -817,17 +817,17 @@ func (a adminAPIHandlers) ImportBucketMetadataHandler(w http.ResponseWriter, r *
 				bucketMap[bucket] = &v
 			}
 
-			if globalSiteReplicationSys.isEnabled() && v.Suspended() {
-				rpt.SetStatus(bucket, fileName, fmt.Errorf("Cluster replication is enabled for this site, so the versioning state cannot be suspended."))
+			if globalSiteReplicationSys.isEnabled() && (v.Suspended() || v.PrefixesExcluded()) {
+				rpt.SetStatus(bucket, fileName, fmt.Errorf("Cluster replication is enabled for this site, so the versioning state cannot be suspended or exclude prefixes."))
 				continue
 			}
 
-			if rcfg, _ := globalBucketObjectLockSys.Get(bucket); rcfg.LockEnabled && v.Suspended() {
-				rpt.SetStatus(bucket, fileName, fmt.Errorf("An Object Lock configuration is present on this bucket, so the versioning state cannot be suspended."))
+			if rcfg, _ := globalBucketObjectLockSys.Get(bucket); rcfg.LockEnabled && (v.Suspended() || v.PrefixesExcluded()) {
+				rpt.SetStatus(bucket, fileName, fmt.Errorf("An Object Lock configuration is present on this bucket, so the versioning state cannot be suspended or exclude prefixes."))
 				continue
 			}
-			if rcfg, _ := getReplicationConfig(ctx, bucket); rcfg != nil && v.Suspended() {
-				rpt.SetStatus(bucket, fileName, fmt.Errorf("A replication configuration is present on this bucket, so the versioning state cannot be suspended."))
+			if rcfg, _ := getReplicationConfig(ctx, bucket); rcfg != nil && (v.Suspended() || v.PrefixesExcluded()) {
+				rpt.SetStatus(bucket, fileName, fmt.Errorf("A replication configuration is present on this bucket, so the versioning state cannot be suspended or exclude prefixes."))
 				continue
 			}
 
@@ -907,7 +907,7 @@ func (a adminAPIHandlers) ImportBucketMetadataHandler(w http.ResponseWriter, r *
 				continue
 			}
 
-			bucketPolicy, err := policy.ParseBucketPolicyConfig(bytes.NewReader(bucketPolicyBytes), bucket)
+			bucketPolicy, err := parseBucketPolicyStrictBytes(bucketPolicyBytes, bucket)
 			if err != nil {
 				rpt.SetStatus(bucket, fileName, err)
 				continue

cmd/admin-handlers-site-replication.go

@@ -165,10 +165,10 @@ func (a adminAPIHandlers) SRPeerReplicateIAMItem(w http.ResponseWriter, r *http.
 	default:
 		err = errSRInvalidRequest(errInvalidArgument)
 	case madmin.SRIAMItemPolicy:
-		if item.Policy == nil {
+		if item.Policy == nil || bytes.Equal(bytes.TrimSpace(item.Policy), []byte("null")) {
 			err = globalSiteReplicationSys.PeerAddPolicyHandler(ctx, item.Name, nil, item.UpdatedAt)
 		} else {
-			policy, perr := policy.ParseConfig(bytes.NewReader(item.Policy))
+			policy, perr := parsePolicySnapshotBytes(item.Policy)
 			if perr != nil {
 				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, perr), r.URL)
 				return
@@ -222,10 +222,10 @@ func (a adminAPIHandlers) SRPeerReplicateBucketItem(w http.ResponseWriter, r *ht
 	default:
 		err = globalSiteReplicationSys.PeerBucketMetadataUpdateHandler(ctx, item)
 	case madmin.SRBucketMetaTypePolicy:
-		if item.Policy == nil {
+		if item.Policy == nil || bytes.Equal(bytes.TrimSpace(item.Policy), []byte("null")) {
 			err = globalSiteReplicationSys.PeerBucketPolicyHandler(ctx, item.Bucket, nil, item.UpdatedAt)
 		} else {
-			bktPolicy, berr := policy.ParseBucketPolicyConfig(bytes.NewReader(item.Policy), item.Bucket)
+			bktPolicy, berr := parseBucketPolicyStrictBytes(item.Policy, item.Bucket)
 			if berr != nil {
 				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, berr), r.URL)
 				return

cmd/admin-handlers-users-authz_test.go

@@ -169,8 +169,9 @@ func TestIAMAdminEmptyPolicyDelegation(t *testing.T) {
 					{"{}", http.StatusOK, true},
 					{`{"Statement":null}`, http.StatusOK, true},
 					{limitedPolicy, http.StatusOK, false},
-					{`{"Version":"2012-10-17"}`, http.StatusForbidden, false},
-					{`{"Statement":[]}`, http.StatusForbidden, false},
+					{`{"Version":"2012-10-17"}`, http.StatusOK, true},
+					{`{"Statement":[]}`, http.StatusOK, true},
+					{`{"Version":"2012-10-17","Statement":[]}`, http.StatusOK, true},
 				} {
 					expires := UTCNow().Add(time.Hour)
 					req := madmin.AddServiceAccountReq{Expiration: &expires}

cmd/admin-handlers-users.go

@@ -885,16 +885,17 @@ func (a adminAPIHandlers) UpdateServiceAccount(w http.ResponseWriter, r *http.Re
 		return
 	}
 
+	// A request without a policy, or with a JSON null for one, keeps the
+	// policy the account has. An empty policy document is passed on as
+	// such: it is the request to remove the embedded policy.
 	var sp *policy.Policy
-	if len(updateReq.NewPolicy) > 0 {
-		sp, err = policy.ParseConfigStrict(bytes.NewReader(updateReq.NewPolicy))
+	trimmedPolicy := bytes.TrimSpace(updateReq.NewPolicy)
+	if len(trimmedPolicy) > 0 && !bytes.Equal(trimmedPolicy, []byte("null")) {
+		sp, err = parseSessionPolicyStrictBytes(trimmedPolicy)
 		if err != nil {
 			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
 			return
 		}
-		if sp.Version == "" && len(sp.Statements) == 0 {
-			sp = nil
-		}
 	}
 	opts := updateServiceAccountOpts{
 		secretKey:     updateReq.NewSecretKey,
@@ -914,21 +915,13 @@ func (a adminAPIHandlers) UpdateServiceAccount(w http.ResponseWriter, r *http.Re
 	}
 
 	// Call site replication hook - non-root user accounts are replicated.
+	// The hook sends the account as it is stored after this edit, not the
+	// fields the request changed (see replicationItem).
 	if svcAccount.ParentUser != globalActiveCred.AccessKey {
 		replLogIf(ctx, globalSiteReplicationSys.IAMChangeHook(ctx, madmin.SRIAMItem{
-			Type: madmin.SRIAMItemSvcAcc,
-			SvcAccChange: &madmin.SRSvcAccChange{
-				Update: &madmin.SRSvcAccUpdate{
-					AccessKey:     accessKey,
-					SecretKey:     opts.secretKey,
-					Status:        opts.status,
-					Name:          opts.name,
-					Description:   opts.description,
-					SessionPolicy: madmin.SRSessionPolicy(updateReq.NewPolicy),
-					Expiration:    updateReq.NewExpiration,
-				},
-			},
-			UpdatedAt: updatedAt,
+			Type:         madmin.SRIAMItemSvcAcc,
+			SvcAccChange: &madmin.SRSvcAccChange{Update: &madmin.SRSvcAccUpdate{AccessKey: accessKey}},
+			UpdatedAt:    updatedAt,
 		}))
 	}
 
@@ -1774,7 +1767,7 @@ func (a adminAPIHandlers) AddCannedPolicy(w http.ResponseWriter, r *http.Request
 		return
 	}
 
-	iamPolicy, err := policy.ParseConfigStrict(bytes.NewReader(iamPolicyBytes))
+	iamPolicy, err := parsePolicyStrictBytes(iamPolicyBytes)
 	if err != nil {
 		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
 		return
@@ -2399,37 +2392,13 @@ func (a adminAPIHandlers) ExportIAM(w http.ResponseWriter, r *http.Request) {
 					// skip site-replication service account.
 					continue
 				}
-				claims, err := globalIAMSys.GetClaimsForSvcAcc(ctx, acc.Credentials.AccessKey)
+				// The stored record only: this server's cache may not have
+				// heard of an edit made through another server.
+				svcAccts[user], err = serviceAccountSnapshot(acc)
 				if err != nil {
 					writeErrorResponse(ctx, w, exportError(ctx, err, iamFile, ""), r.URL)
 					return
 				}
-				sa, policy, err := globalIAMSys.GetServiceAccount(ctx, acc.Credentials.AccessKey)
-				if err != nil {
-					writeErrorResponse(ctx, w, exportError(ctx, err, iamFile, ""), r.URL)
-					return
-				}
-
-				var policyJSON []byte
-				if policy != nil {
-					policyJSON, err = json.Marshal(policy)
-					if err != nil {
-						writeErrorResponse(ctx, w, exportError(ctx, err, iamFile, ""), r.URL)
-						return
-					}
-				}
-				svcAccts[user] = madmin.SRSvcAccCreate{
-					Parent:        acc.Credentials.ParentUser,
-					AccessKey:     user,
-					SecretKey:     acc.Credentials.SecretKey,
-					Groups:        acc.Credentials.Groups,
-					Claims:        claims,
-					SessionPolicy: policyJSON,
-					Status:        acc.Credentials.Status,
-					Name:          sa.Name,
-					Description:   sa.Description,
-					Expiration:    &sa.Expiration,
-				}
 			}
 
 			svcAccData, err := json.Marshal(svcAccts)
@@ -2542,23 +2511,34 @@ func (a adminAPIHandlers) importIAM(w http.ResponseWriter, r *http.Request, apiV
 			return
 		default:
 			defer f.Close()
-			var allPolicies map[string]policy.Policy
+			var policyDocuments map[string]json.RawMessage
 			data, err = io.ReadAll(f)
 			if err != nil {
 				writeErrorResponseJSON(ctx, w, importErrorWithAPIErr(ctx, ErrInvalidRequest, err, allPoliciesFile, ""), r.URL)
 				return
 			}
-			err = json.Unmarshal(data, &allPolicies)
+			err = json.Unmarshal(data, &policyDocuments)
 			if err != nil {
 				writeErrorResponseJSON(ctx, w, importErrorWithAPIErr(ctx, ErrAdminConfigBadJSON, err, allPoliciesFile, ""), r.URL)
 				return
 			}
+			// Validate the entire policy file before applying any entries. Keep
+			// legacy semantic validation, but never discard unknown wire fields.
+			allPolicies := make(map[string]*policy.Policy, len(policyDocuments))
+			for policyName, document := range policyDocuments {
+				parsed, parseErr := parsePolicySnapshotBytes(document)
+				if parseErr != nil {
+					writeErrorResponseJSON(ctx, w, importErrorWithAPIErr(ctx, ErrAdminConfigBadJSON, parseErr, allPoliciesFile, policyName), r.URL)
+					return
+				}
+				allPolicies[policyName] = parsed
+			}
 			for policyName, policy := range allPolicies {
 				if policy.IsEmpty() {
 					err = globalIAMSys.DeletePolicy(ctx, policyName, true)
 					removed.Policies = append(removed.Policies, policyName)
 				} else {
-					_, err = globalIAMSys.SetPolicy(ctx, policyName, policy)
+					_, err = globalIAMSys.SetPolicy(ctx, policyName, *policy)
 					added.Policies = append(added.Policies, policyName)
 				}
 				if err != nil {
@@ -2650,8 +2630,17 @@ func (a adminAPIHandlers) importIAM(w http.ResponseWriter, r *http.Request, apiV
 						return
 					}
 				}
-				if _, gerr := globalIAMSys.AddUsersToGroup(ctx, group, grpInfo.Members); gerr != nil {
-					failed.Groups = append(failed.Groups, madmin.IAMErrEntity{Name: group, Error: err})
+				_, gerr := globalIAMSys.AddUsersToGroup(ctx, group, grpInfo.Members)
+				if gerr == nil {
+					switch grpInfo.Status {
+					case statusDisabled:
+						_, gerr = globalIAMSys.SetGroupStatus(ctx, group, false)
+					case statusEnabled:
+						_, gerr = globalIAMSys.SetGroupStatus(ctx, group, true)
+					}
+				}
+				if gerr != nil {
+					failed.Groups = append(failed.Groups, madmin.IAMErrEntity{Name: group, Error: gerr})
 				} else {
 					added.Groups = append(added.Groups, group)
 				}
@@ -2697,10 +2686,13 @@ func (a adminAPIHandlers) importIAM(w http.ResponseWriter, r *http.Request, apiV
 				var sp *policy.Policy
 				var err error
 				if len(svcAcctReq.SessionPolicy) > 0 {
-					sp, err = policy.ParseConfig(bytes.NewReader(svcAcctReq.SessionPolicy))
-					if err != nil {
-						writeErrorResponseJSON(ctx, w, importError(ctx, err, allSvcAcctsFile, user), r.URL)
-						return
+					trimmedSP := bytes.TrimSpace(svcAcctReq.SessionPolicy)
+					if len(trimmedSP) > 0 && !bytes.Equal(trimmedSP, []byte("null")) {
+						sp, err = parsePolicySnapshotBytes(trimmedSP)
+						if err != nil {
+							writeErrorResponseJSON(ctx, w, importError(ctx, err, allSvcAcctsFile, user), r.URL)
+							return
+						}
 					}
 				}
 				// service account access key cannot have space characters
@@ -2729,14 +2721,16 @@ func (a adminAPIHandlers) importIAM(w http.ResponseWriter, r *http.Request, apiV
 					}
 				}
 				opts := newServiceAccountOpts{
-					accessKey:                  user,
-					secretKey:                  svcAcctReq.SecretKey,
-					sessionPolicy:              sp,
-					claims:                     svcAcctReq.Claims,
-					name:                       svcAcctReq.Name,
-					description:                svcAcctReq.Description,
-					expiration:                 svcAcctReq.Expiration,
-					allowSiteReplicatorAccount: false,
+					accessKey:                   user,
+					secretKey:                   svcAcctReq.SecretKey,
+					status:                      svcAcctReq.Status,
+					sessionPolicy:               sp,
+					claims:                      svcAcctReq.Claims,
+					name:                        svcAcctReq.Name,
+					description:                 svcAcctReq.Description,
+					expiration:                  svcAcctReq.Expiration,
+					allowSiteReplicatorAccount:  false,
+					preserveEmptyEmbeddedPolicy: svcAcctClaimsHaveEmbeddedPolicy(svcAcctReq.Claims),
 				}
 
 				if _, _, err = globalIAMSys.NewServiceAccount(ctx, svcAcctReq.Parent, svcAcctReq.Groups, opts); err != nil {
@@ -3080,14 +3074,17 @@ func commonAddServiceAccount(r *http.Request, ldap bool) (context.Context, auth.
 	}
 
 	var sp *policy.Policy
-	if len(createReq.Policy) > 0 {
-		sp, err = policy.ParseConfigStrict(bytes.NewReader(createReq.Policy))
+	trimmedCreatePolicy := bytes.TrimSpace(createReq.Policy)
+	if bytes.Equal(trimmedCreatePolicy, []byte("null")) {
+		createReq.Policy = nil
+	} else if len(trimmedCreatePolicy) > 0 {
+		sp, err = parseSessionPolicyStrictBytes(trimmedCreatePolicy)
 		if err != nil {
 			return ctx, auth.Credentials{}, newServiceAccountOpts{}, madmin.AddServiceAccountReq{}, "", toAdminAPIErr(ctx, err)
 		}
 		// Empty service policies mean inheritance, including for expiring keys.
 		// Normalize the replication request as well as the local credential.
-		if sp.Version == "" && sp.Statements == nil && sp.ID == "" {
+		if sp.IsEmpty() {
 			sp = nil
 			createReq.Policy = nil
 		}

cmd/api-headers.go

@@ -134,8 +134,8 @@ func setObjectHeaders(ctx context.Context, w http.ResponseWriter, objInfo Object
 		w.Header().Set(xhttp.Expires, objInfo.Expires.UTC().Format(http.TimeFormat))
 	}
 
-	// Set tag count if object has tags
-	if len(objInfo.UserTags) > 0 {
+	// Both the count and the optional values require permission to read tags.
+	if opts.TaggingCount && len(objInfo.UserTags) > 0 {
 		tags, _ := tags.ParseObjectTags(objInfo.UserTags)
 		if tags != nil && tags.Count() > 0 {
 			w.Header()[xhttp.AmzTagCount] = []string{strconv.Itoa(tags.Count())}
@@ -159,6 +159,11 @@ func setObjectHeaders(ctx context.Context, w http.ResponseWriter, objInfo Object
 			continue
 		}
 
+		// Tag count and tag values are gated above by opts.TaggingCount / opts.Tagging.
+		if equals(k, xhttp.AmzTagCount, xhttp.AmzObjectTagging) {
+			continue
+		}
+
 		// https://github.com/google/security-research/security/advisories/GHSA-76wf-9vgp-pj7w
 		if equals(k, xhttp.AmzMetaUnencryptedContentLength, xhttp.AmzMetaUnencryptedContentMD5) {
 			continue

cmd/api-response.go

@@ -568,18 +568,15 @@ func generateListVersionsResponse(ctx context.Context, bucket, prefix, marker, v
 		DisplayName: "minio",
 	}
 	data := ListVersionsResponse{}
-	var lastObjMetaName string
 	var tagErr, metaErr APIErrorCode = -1, -1
 
 	for _, object := range resp.Objects {
 		if object.Name == "" {
 			continue
 		}
-		// Cache checks for the same object
-		if metadata != nil && lastObjMetaName != object.Name {
-			tagErr = metadata(object.Name, policy.GetObjectTaggingAction)
-			metaErr = metadata(object.Name, policy.GetObjectAction)
-			lastObjMetaName = object.Name
+		if metadata != nil {
+			tagErr = metadata(object, policy.GetObjectTaggingAction)
+			metaErr = metadata(object, policy.GetObjectAction)
 		}
 		content := ObjectVersion{}
 		content.Key = s3EncodeName(object.Name, encodingType)
@@ -727,10 +724,10 @@ func generateListObjectsV2Response(ctx context.Context, bucket, prefix, token, n
 		}
 		content.Owner = owner
 		if metadata != nil {
-			if metadata(object.Name, policy.GetObjectTaggingAction) == ErrNone {
+			if metadata(object, policy.GetObjectTaggingAction) == ErrNone {
 				content.UserTags = object.UserTags
 			}
-			if metadata(object.Name, policy.GetObjectAction) == ErrNone {
+			if metadata(object, policy.GetObjectAction) == ErrNone {
 				content.UserMetadata = &Metadata{}
 				switch kind, _ := crypto.IsEncrypted(object.UserDefined); kind {
 				case crypto.S3:
@@ -774,7 +771,7 @@ func generateListObjectsV2Response(ctx context.Context, bucket, prefix, token, n
 	return data
 }
 
-type metaCheckFn = func(name string, action policy.Action) (s3Err APIErrorCode)
+type metaCheckFn = func(object ObjectInfo, action policy.Action) (s3Err APIErrorCode)
 
 // generates CopyObjectResponse from the committed object information.
 func generateCopyObjectResponse(oi ObjectInfo, cs map[string]string) CopyObjectResponse {

cmd/auth-handler-unread-tags.go

@@ -0,0 +1,716 @@
+// Copyright (c) 2026 Denis Babchuk
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"context"
+	"encoding/json"
+	"maps"
+	"net/http"
+	"slices"
+	"strings"
+
+	"github.com/minio/minio-go/v7/pkg/set"
+	"github.com/minio/minio-go/v7/pkg/tags"
+	"github.com/minio/minio/internal/arn"
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/minio/internal/logger"
+	"github.com/pgsty/silo-pkg/v3/policy"
+	"github.com/pgsty/silo-pkg/v3/policy/condition"
+	"github.com/puzpuzpuz/xsync/v3"
+)
+
+func withScopedReqObject(ctx context.Context, bucket, object, versionID string, fn func() APIErrorCode) APIErrorCode {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return ErrAccessDenied
+	}
+	prevBucket, prevObject, prevVID := reqInfo.BucketName, reqInfo.ObjectName, reqInfo.VersionID
+	reqInfo.BucketName = bucket
+	reqInfo.ObjectName = object
+	reqInfo.VersionID = versionID
+	defer func() {
+		reqInfo.BucketName = prevBucket
+		reqInfo.ObjectName = prevObject
+		reqInfo.VersionID = prevVID
+	}()
+	return fn()
+}
+
+func objectVersionAction(base policy.Action, versionID string) (policy.Action, bool) {
+	if versionID == "" {
+		return base, false
+	}
+	switch base {
+	case policy.GetObjectAction:
+		return policy.GetObjectVersionAction, true
+	case policy.GetObjectTaggingAction:
+		return policy.GetObjectVersionTaggingAction, true
+	case policy.PutObjectTaggingAction:
+		return policy.PutObjectVersionTaggingAction, true
+	case policy.DeleteObjectTaggingAction:
+		return policy.DeleteObjectVersionTaggingAction, true
+	default:
+		return base, false
+	}
+}
+
+func (sys *IAMSys) policySetsForExplicitDeny(cred auth.Credentials) [][]policy.Policy {
+	derived := cred.IsTemp() || cred.IsServiceAccount()
+	name := cred.AccessKey
+	if derived {
+		name = cred.ParentUser
+	}
+	cache := sys.store.rlock()
+	var names []string
+	roleARN := (policy.Args{Claims: cred.Claims}).GetRoleArn()
+	switch {
+	case name == globalActiveCred.AccessKey:
+	case derived && roleARN != "":
+		parsed, err := arn.Parse(roleARN)
+		if err != nil {
+			sys.store.runlock()
+			return nil
+		}
+		names = newMappedPolicy(sys.rolesMap[parsed]).toSlice()
+	default:
+		var err error
+		names, _, err = cache.policyDBGet(sys.store, name, false, false)
+		if err != nil && err != errNoSuchPolicy {
+			sys.store.runlock()
+			return nil
+		}
+		groups, gerr := cache.policyDBGetGroups(sys.store, len(names) > 0, cred.Groups...)
+		if gerr != nil && gerr != errNoSuchPolicy {
+			sys.store.runlock()
+			return nil
+		}
+		names = append(names, groups...)
+		if derived && len(names) == 0 {
+			claims, _ := policy.GetPoliciesFromClaims(cred.Claims, iamPolicyClaimNameOpenID())
+			names = claims.ToSlice()
+		}
+	}
+	sys.store.runlock()
+
+	sets := [][]policy.Policy{nil}
+	slices.Sort(names)
+	compactNames := slices.Compact(names)
+	if len(compactNames) > 0 {
+		if avail, merged, err := sys.store.MergePolicies(strings.Join(compactNames, ",")); err == nil && avail != "" {
+			sets[0] = append(sets[0], merged)
+		}
+	}
+	if derived && (cred.IsTemp() || cred.Claims[iamPolicyClaimNameSA()] != inheritedPolicyType) {
+		if sp, ok := cred.Claims[sessionPolicyNameExtracted].(string); ok {
+			if p, err := policy.ParseConfig(strings.NewReader(sp)); err == nil {
+				sets = append(sets, []policy.Policy{*p})
+			}
+		}
+	}
+	return sets
+}
+
+func isActionExplicitlyDenied(ctx context.Context, r *http.Request, action policy.Action, existingTags string, requestTags *string) bool {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return true
+	}
+	if reqInfo.Owner {
+		return false
+	}
+	cred := reqInfo.Cred
+	bucket := reqInfo.BucketName
+	object := reqInfo.ObjectName
+	versionID := reqInfo.VersionID
+	buildValues := func(loc string, c auth.Credentials) map[string][]string {
+		values := getConditionValuesWithTags(r, loc, c, existingTags, requestTags)
+		if actionUsesObjectVersion(action) {
+			if versionID == "" {
+				delete(values, "versionid")
+			} else {
+				values["versionid"] = []string{versionID}
+			}
+		}
+		return values
+	}
+
+	if cred.AccessKey == "" {
+		p, err := globalPolicySys.Get(bucket)
+		if err != nil {
+			return false
+		}
+		bArgs := policy.BucketPolicyArgs{
+			Action:          action,
+			BucketName:      bucket,
+			ObjectName:      object,
+			ConditionValues: buildValues(reqInfo.Region, auth.AnonymousCredentials),
+			IsOwner:         false,
+		}
+		for _, st := range p.Statements {
+			if st.Effect != policy.Deny {
+				continue
+			}
+			probe := st
+			probe.Effect = policy.Allow
+			if probe.IsAllowed(bArgs) {
+				return true
+			}
+		}
+		return false
+	}
+
+	values := buildValues("", cred)
+	if newGlobalAuthZPluginFn() != nil {
+		return !globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          action,
+			BucketName:      bucket,
+			ObjectName:      object,
+			ConditionValues: values,
+			IsOwner:         false,
+			Claims:          cred.Claims,
+			DenyOnly:        true,
+		})
+	}
+	if !globalIAMSys.Initialized() {
+		return false
+	}
+	args := policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          action,
+		BucketName:      bucket,
+		ObjectName:      object,
+		ConditionValues: values,
+		IsOwner:         false,
+		Claims:          cred.Claims,
+		DenyOnly:        true,
+	}
+	for _, policies := range globalIAMSys.policySetsForExplicitDeny(cred) {
+		if len(policies) == 0 {
+			continue
+		}
+		merged := policy.MergePolicies(policies...)
+		if !merged.IsAllowed(args) {
+			return true
+		}
+	}
+	return false
+}
+
+func authorizeVersionedRequestWithTags(ctx context.Context, r *http.Request, baseAction policy.Action, versionID, existingTags string, requestTags *string) APIErrorCode {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return ErrAccessDenied
+	}
+	prevVID := reqInfo.VersionID
+	reqInfo.VersionID = versionID
+	defer func() { reqInfo.VersionID = prevVID }()
+
+	if verAction, ok := objectVersionAction(baseAction, versionID); ok {
+		if authorizeRequestWithTags(ctx, r, verAction, existingTags, requestTags) == ErrNone {
+			return ErrNone
+		}
+		if isActionExplicitlyDenied(ctx, r, verAction, existingTags, requestTags) {
+			return ErrAccessDenied
+		}
+	}
+	return authorizeRequestWithTags(ctx, r, baseAction, existingTags, requestTags)
+}
+
+func authorizeVersionedRequestWithExistingTags(ctx context.Context, r *http.Request, baseAction policy.Action, versionID, existingTags string) APIErrorCode {
+	return authorizeVersionedRequestWithTags(ctx, r, baseAction, versionID, existingTags, nil)
+}
+
+func authorizeVersionedRequestWithUnreadTags(ctx context.Context, r *http.Request, baseAction policy.Action, versionID string, readErr error) APIErrorCode {
+	s3Err := authorizeVersionedRequestWithExistingTags(ctx, r, baseAction, versionID, "")
+	if s3Err == ErrNone || toAPIError(ctx, readErr).HTTPStatusCode < http.StatusInternalServerError {
+		return s3Err
+	}
+	return authorizeVersionedRequestWithTagCandidates(ctx, r, baseAction, versionID, s3Err)
+}
+
+func authorizeVersionedRequestWithPotentialTags(ctx context.Context, r *http.Request, baseAction policy.Action, versionID string) APIErrorCode {
+	s3Err := authorizeVersionedRequestWithExistingTags(ctx, r, baseAction, versionID, "")
+	if s3Err == ErrNone {
+		return ErrNone
+	}
+	return authorizeVersionedRequestWithTagCandidates(ctx, r, baseAction, versionID, s3Err)
+}
+
+func authorizeVersionedRequestWithTagCandidates(ctx context.Context, r *http.Request, baseAction policy.Action, versionID string, s3Err APIErrorCode) APIErrorCode {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return ErrAccessDenied
+	}
+	prevVID := reqInfo.VersionID
+	reqInfo.VersionID = versionID
+	defer func() { reqInfo.VersionID = prevVID }()
+
+	candidates := policyExistingObjectTags(ctx, r, baseAction)
+	if verAction, ok := objectVersionAction(baseAction, versionID); ok {
+		candidates = append(candidates, policyExistingObjectTags(ctx, r, verAction)...)
+	}
+	for _, existingTags := range slices.Compact(candidates) {
+		if authorizeVersionedRequestWithExistingTags(ctx, r, baseAction, versionID, existingTags) == ErrNone {
+			return ErrNone
+		}
+	}
+	return s3Err
+}
+
+// canPotentiallyAllowAction reports whether the authenticated caller has any
+// grant capable of allowing action on bucket/object once condition values
+// (such as copied source tags on CopyObject) are resolved.
+func canPotentiallyAllowAction(ctx context.Context, r *http.Request, action policy.Action, bucket, object string) bool {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return false
+	}
+	emptyTags := ""
+	if withScopedReqObject(ctx, bucket, object, "", func() APIErrorCode {
+		return authorizeRequestWithTags(ctx, r, action, "", &emptyTags)
+	}) == ErrNone {
+		return true
+	}
+	if reqInfo.Owner {
+		return true
+	}
+	cred := reqInfo.Cred
+	if cred.AccessKey == "" {
+		p, err := globalPolicySys.Get(bucket)
+		if err != nil {
+			return false
+		}
+		values := getConditionValues(r, reqInfo.Region, auth.AnonymousCredentials)
+		for _, st := range p.Statements {
+			if st.Effect != policy.Allow {
+				continue
+			}
+			probe := st
+			probe.Conditions = nil
+			if probe.IsAllowed(policy.BucketPolicyArgs{Action: action, BucketName: bucket, ObjectName: object, ConditionValues: values}) {
+				return true
+			}
+		}
+		return false
+	}
+	if newGlobalAuthZPluginFn() != nil || !globalIAMSys.Initialized() {
+		return true
+	}
+	values := getConditionValues(r, "", cred)
+	for _, policies := range globalIAMSys.policySetsForExplicitDeny(cred) {
+		setAllows := false
+		for _, p := range policies {
+			for _, st := range p.Statements {
+				if st.Effect != policy.Allow {
+					continue
+				}
+				probe := st
+				probe.Conditions = nil
+				if probe.IsAllowed(policy.Args{
+					AccountName:     cred.AccessKey,
+					Groups:          cred.Groups,
+					Action:          action,
+					BucketName:      bucket,
+					ObjectName:      object,
+					ConditionValues: values,
+					Claims:          cred.Claims,
+				}) {
+					setAllows = true
+					break
+				}
+			}
+			if setAllows {
+				break
+			}
+		}
+		if len(policies) > 0 && !setAllows {
+			return false
+		}
+		if len(policies) == 0 && cred.ParentUser != globalActiveCred.AccessKey && cred.AccessKey != globalActiveCred.AccessKey {
+			return false
+		}
+	}
+	return true
+}
+
+func canReturnObjectTagsHeader(ctx context.Context, r *http.Request, versionID, existingTags string) bool {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return false
+	}
+	prevVID := reqInfo.VersionID
+	reqInfo.VersionID = versionID
+	defer func() { reqInfo.VersionID = prevVID }()
+
+	if isActionExplicitlyDenied(ctx, r, policy.GetObjectTaggingAction, existingTags, nil) {
+		return false
+	}
+	if verAction, ok := objectVersionAction(policy.GetObjectTaggingAction, versionID); ok {
+		if isActionExplicitlyDenied(ctx, r, verAction, existingTags, nil) {
+			return false
+		}
+	}
+	if authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectTaggingAction, versionID, existingTags) == ErrNone {
+		return true
+	}
+	return reqInfo.Cred.AccessKey != "" &&
+		isRequestSignatureV4(r) &&
+		!isRequestPresignedSignatureV4(r) &&
+		authorizeRequestWithExistingTags(ctx, r, policy.ReplicateTagsAction, existingTags) == ErrNone
+}
+
+// authorizeRequestWithUnreadTags decides whether to disclose readErr for an
+// object whose stored tags could not be read. It must not grant object access.
+//
+// Without the tags, an Allow statement that tests s3:ExistingObjectTag cannot
+// match, so a caller allowed only by such a statement would get AccessDenied,
+// which clients do not retry, for a transient server error such as lost read
+// quorum. For a server error, try a bounded set of tags from the caller's
+// policies and return the storage error if normal authorization accepts one.
+// If no candidate passes, keep AccessDenied. This is not an exhaustive policy
+// solver. For any other error, NoSuchKey among them, the tags stay empty.
+func authorizeRequestWithUnreadTags(ctx context.Context, r *http.Request, action policy.Action, readErr error) APIErrorCode {
+	s3Err := authorizeRequest(ctx, r, action)
+	if s3Err == ErrNone || toAPIError(ctx, readErr).HTTPStatusCode < http.StatusInternalServerError {
+		return s3Err
+	}
+	return authorizeRequestWithTagCandidates(ctx, r, action, s3Err)
+}
+
+func authorizeRequestWithTagCandidates(ctx context.Context, r *http.Request, action policy.Action, s3Err APIErrorCode) APIErrorCode {
+	for _, existingTags := range policyExistingObjectTags(ctx, r, action) {
+		if authorizeRequestWithExistingTags(ctx, r, action, existingTags) == ErrNone {
+			return ErrNone
+		}
+	}
+	return s3Err
+}
+
+// maxExistingTagCandidates bounds the tag sets tried for one request; each
+// one costs an authorization.
+const maxExistingTagCandidates = 64
+
+// policyExistingObjectTags returns tag sets under which the policies that
+// authorize the request may let action through on its object: the bucket
+// policy for an anonymous request, else the cached IAM policies and, as a
+// second policy set, the session policy of the credential. A tag set passes
+// the s3:ExistingObjectTag tests of one Allow statement of each policy set and,
+// as far as the same tags allow, keeps the Deny statements that test tags from
+// matching. The tag sets are only candidates; the regular authorization
+// decides what they allow.
+func policyExistingObjectTags(ctx context.Context, r *http.Request, action policy.Action) []string {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return nil
+	}
+	bucket, object := reqInfo.BucketName, reqInfo.ObjectName
+	var (
+		allows [][]map[string]string // per policy set, the tags its Allow statements ask for
+		denies [][]map[string]string // per Deny statement, alternative tags that keep it from matching
+	)
+	// add collects the tags of a statement that applies to action on the
+	// object, whatever its conditions.
+	add := func(effect policy.Effect, conditions condition.Functions, values map[string][]string, fromSet *[]map[string]string) {
+		candidates := existingObjectTagsCandidatesFor(effect, conditions, values)
+		if effect == policy.Allow {
+			*fromSet = append(*fromSet, candidates...)
+		} else if len(candidates) > 0 {
+			denies = append(denies, candidates)
+		}
+	}
+	switch {
+	case reqInfo.Cred.AccessKey == "":
+		p, err := globalPolicySys.Get(bucket)
+		if err != nil {
+			return nil
+		}
+		values := getConditionValues(r, reqInfo.Region, auth.AnonymousCredentials)
+		var fromSet []map[string]string
+		for _, st := range p.Statements {
+			match := st
+			match.Effect, match.Conditions = policy.Allow, nil
+			if match.IsAllowed(policy.BucketPolicyArgs{Action: action, BucketName: bucket, ObjectName: object, ConditionValues: values}) {
+				add(st.Effect, st.Conditions, values, &fromSet)
+			}
+		}
+		allows = append(allows, fromSet)
+	case newGlobalAuthZPluginFn() == nil && globalIAMSys.Initialized():
+		values := getConditionValues(r, "", reqInfo.Cred)
+		policySets := globalIAMSys.unreadTagPolicySets(reqInfo.Cred)
+		for _, policies := range policySets {
+			var fromSet []map[string]string
+			for _, p := range policies {
+				for _, st := range p.Statements {
+					match := st
+					match.Effect, match.Conditions = policy.Allow, nil
+					if match.IsAllowed(policy.Args{Action: action, BucketName: bucket, ObjectName: object, ConditionValues: values}) {
+						add(st.Effect, st.Conditions, values, &fromSet)
+					}
+				}
+			}
+			allows = append(allows, fromSet)
+		}
+	}
+	return combineExistingObjectTags(append(allows, denies...))
+}
+
+// unreadTagMappings reuses the normal user/group mapping lookup without lazy
+// storage reads. Missing cache entries contribute no candidates; the regular
+// authorization still decides whether any candidate is allowed.
+type unreadTagMappings struct {
+	*IAMStoreSys
+}
+
+func (unreadTagMappings) loadMappedPolicy(context.Context, string, IAMUserType, bool, *xsync.MapOf[string, MappedPolicy]) error {
+	return errNoSuchPolicy
+}
+
+func (unreadTagMappings) loadGroup(context.Context, string, map[string]GroupInfo) error {
+	return errNoSuchGroup
+}
+
+// unreadTagPolicySets selects only this credential's cached policies. Base
+// and session policies remain separate because both must allow the request.
+// This only supplies candidates, so identity, claims and policy validity are
+// left to the normal authorization on each candidate.
+func (sys *IAMSys) unreadTagPolicySets(cred auth.Credentials) [][]policy.Policy {
+	derived := cred.IsTemp() || cred.IsServiceAccount()
+	name := cred.AccessKey
+	if derived {
+		name = cred.ParentUser
+	}
+	cache := sys.store.rlock()
+	defer sys.store.runlock()
+	var names []string
+	roleARN := (policy.Args{Claims: cred.Claims}).GetRoleArn()
+	switch {
+	case name == globalActiveCred.AccessKey:
+	case derived && roleARN != "":
+		parsed, err := arn.Parse(roleARN)
+		if err != nil {
+			return nil
+		}
+		names = newMappedPolicy(sys.rolesMap[parsed]).toSlice()
+	default:
+		loader := unreadTagMappings{sys.store}
+		var err error
+		names, _, err = cache.policyDBGet(loader, name, false, false)
+		if err != nil {
+			return nil
+		}
+		groups, err := cache.policyDBGetGroups(loader, len(names) > 0, cred.Groups...)
+		if err != nil {
+			return nil
+		}
+		names = append(names, groups...)
+		if derived && len(names) == 0 {
+			claims, _ := policy.GetPoliciesFromClaims(cred.Claims, iamPolicyClaimNameOpenID())
+			names = claims.ToSlice()
+		}
+	}
+
+	sets := [][]policy.Policy{nil}
+	slices.Sort(names)
+	for _, name := range slices.Compact(names) {
+		if doc, ok := cache.iamPolicyDocsMap[name]; ok {
+			sets[0] = append(sets[0], doc.Policy)
+		}
+	}
+	if derived && (cred.IsTemp() || cred.Claims[iamPolicyClaimNameSA()] != inheritedPolicyType) {
+		if sp, ok := cred.Claims[sessionPolicyNameExtracted].(string); ok {
+			if p, err := policy.ParseConfig(strings.NewReader(sp)); err == nil {
+				sets = append(sets, []policy.Policy{*p})
+			}
+		}
+	}
+	return sets
+}
+
+// combineExistingObjectTags combines alternatives from each base/session
+// Allow set and each tag-dependent Deny. A set may also contribute no tags:
+// another statement or another set may already supply what it needs. First
+// values win conflicts; the normal authorization decides whether they work.
+func combineExistingObjectTags(sets [][]map[string]string) []string {
+	combos := []map[string]string{{}}
+	for _, fromSet := range sets {
+		fromSet = append(uniqueExistingObjectTagMaps(fromSet), nil)
+		var next []map[string]string
+		seen := set.NewStringSet()
+	combinations:
+		for _, combo := range combos {
+			for _, addition := range fromSet {
+				merged := maps.Clone(combo)
+				for k, v := range addition {
+					if _, ok := merged[k]; !ok {
+						merged[k] = v
+					}
+				}
+				t, err := tags.MapToObjectTags(merged)
+				if err != nil || seen.Contains(t.String()) {
+					continue
+				}
+				seen.Add(t.String())
+				next = append(next, merged)
+				if len(next) == maxExistingTagCandidates {
+					break combinations
+				}
+			}
+		}
+		combos = next
+	}
+	var candidates []string
+	for _, combo := range combos {
+		if len(combo) != 0 { // empty tags were already authorized
+			t, _ := tags.MapToObjectTags(combo)
+			candidates = append(candidates, t.String())
+		}
+	}
+	return candidates
+}
+
+// existingObjectTagsCandidatesFor returns tag sets under which the
+// s3:ExistingObjectTag tests of conditions all pass, for an Allow statement,
+// or one of them fails, for a Deny statement; a tag left out is absent. For an
+// Allow, values for different tag keys are combined, while a Deny needs only
+// one failing key. It tries the values named in the conditions, with policy
+// variables resolved, wildcard fillers, and absence, then lets the policy
+// engine decide whether each candidate really satisfies the conditions.
+func existingObjectTagsCandidatesFor(effect policy.Effect, conditions condition.Functions, values map[string][]string) []map[string]string {
+	// Each function tests one key, so the tests of one tag pass or fail
+	// whatever the other tags are.
+	byKey := make(map[string]condition.Functions)
+	for _, f := range conditions {
+		for key := range condition.NewFunctions(f).Keys() {
+			if key.Is(condition.ExistingObjectTag) {
+				byKey[key.Name()] = append(byKey[key.Name()], f)
+			}
+		}
+	}
+	if len(byKey) == 0 {
+		return nil
+	}
+
+	keys := slices.Sorted(maps.Keys(byKey))
+	if effect == policy.Deny {
+		var candidates []map[string]string
+		for _, key := range keys {
+			candidates = append(candidates, existingObjectTagValues(key, strings.TrimPrefix(key, condition.ExistingObjectTag.Name()+"/"), byKey[key], values, false)...)
+		}
+		return uniqueExistingObjectTagMaps(candidates)
+	}
+
+	candidates := []map[string]string{{}}
+	for _, key := range keys {
+		keyCandidates := existingObjectTagValues(key, strings.TrimPrefix(key, condition.ExistingObjectTag.Name()+"/"), byKey[key], values, true)
+		if len(keyCandidates) == 0 {
+			return nil
+		}
+		next := make([]map[string]string, 0, min(maxExistingTagCandidates, len(candidates)*len(keyCandidates)))
+		for _, base := range candidates {
+			for _, keyCandidate := range keyCandidates {
+				merged := maps.Clone(base)
+				maps.Copy(merged, keyCandidate)
+				next = append(next, merged)
+				if len(next) == maxExistingTagCandidates {
+					break
+				}
+			}
+			if len(next) == maxExistingTagCandidates {
+				break
+			}
+		}
+		candidates = next
+	}
+	return uniqueExistingObjectTagMaps(candidates)
+}
+
+func uniqueExistingObjectTagMaps(candidates []map[string]string) []map[string]string {
+	seen := set.NewStringSet()
+	unique := make([]map[string]string, 0, len(candidates))
+	for _, candidate := range candidates {
+		t, err := tags.MapToObjectTags(candidate)
+		if err != nil || seen.Contains(t.String()) {
+			continue
+		}
+		seen.Add(t.String())
+		unique = append(unique, candidate)
+	}
+	return unique
+}
+
+// existingObjectTagValues looks for values of tag tagKey, or its absence,
+// under which the functions that test the condition key key evaluate to want.
+func existingObjectTagValues(key, tagKey string, tests condition.Functions, values map[string][]string, want bool) []map[string]string {
+	defer delete(values, key)
+	delete(values, key)
+	var candidates []map[string]string
+	if tests.Evaluate(values) == want {
+		candidates = append(candidates, map[string]string{})
+	}
+	// The functions keep their values unexported; JSON exposes them.
+	buf, err := json.Marshal(tests)
+	if err != nil {
+		return candidates
+	}
+	var byName map[string]map[string]condition.ValueSet
+	if err = json.Unmarshal(buf, &byName); err != nil {
+		return candidates
+	}
+	var tried []string
+	for name, byKey := range byName {
+		if name == "Null" {
+			continue // its operand says whether the tag is there, not a value
+		}
+		for _, valueSet := range byKey {
+			for _, v := range valueSet.ToSlice() {
+				s := substituteConditionVariables(v.String(), values)
+				tried = append(tried, s, strings.NewReplacer("*", "", "?", "_").Replace(s))
+			}
+		}
+	}
+	slices.Sort(tried)
+	for _, v := range append(slices.Compact(tried), "", "_") {
+		if _, err := tags.MapToObjectTags(map[string]string{tagKey: v}); err != nil {
+			continue
+		}
+		values[key] = []string{v}
+		if tests.Evaluate(values) == want {
+			candidates = append(candidates, map[string]string{tagKey: v})
+			if len(candidates) == maxExistingTagCandidates {
+				break
+			}
+		}
+	}
+	return uniqueExistingObjectTagMaps(candidates)
+}
+
+// substituteConditionVariables resolves the policy variables in v from the
+// condition values as the policy engine does for the values of a condition;
+// silo-pkg keeps its own function for this unexported.
+func substituteConditionVariables(v string, values map[string][]string) string {
+	for _, key := range condition.CommonKeys {
+		if rvalues, ok := values[key.Name()]; ok && len(rvalues) > 0 && rvalues[0] != "" {
+			v = strings.ReplaceAll(v, key.VarName(), rvalues[0])
+		}
+	}
+	return v
+}

cmd/auth-handler-unread-tags_test.go

@@ -0,0 +1,443 @@
+// Copyright (c) 2026 Denis Babchuk
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"encoding/xml"
+	"fmt"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/minio-go/v7/pkg/tags"
+	"github.com/minio/minio/internal/arn"
+	"github.com/minio/minio/internal/auth"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/pgsty/silo-pkg/v3/policy"
+	"github.com/pgsty/silo-pkg/v3/policy/condition"
+)
+
+// objectReadFault takes the first n drives of the set that holds object
+// offline for the metadata reads of that object only, so that IAM and bucket
+// metadata stay readable. It returns a function that restores the drives.
+func objectReadFault(z *erasureServerPools, bucket, object string, n int) func() {
+	pool := z.serverPools[0]
+	setIndex := pool.getHashedSetIndex(object)
+	pool.erasureDisksMu.Lock()
+	defer pool.erasureDisksMu.Unlock()
+	previous := pool.erasureDisks[setIndex]
+	disks := append([]StorageAPI(nil), previous...)
+	for i := range n {
+		disks[i] = consistencyReadFaultDisk{StorageAPI: disks[i], bucket: bucket, object: object}
+	}
+	pool.erasureDisks[setIndex] = disks
+	return func() {
+		pool.erasureDisksMu.Lock()
+		pool.erasureDisks[setIndex] = previous
+		pool.erasureDisksMu.Unlock()
+	}
+}
+
+// A caller allowed to read an object only through s3:ExistingObjectTag must
+// get the storage error, which clients retry, and not AccessDenied, when the
+// object's tags cannot be read because read quorum is lost. A caller that no
+// tags would let through must still get AccessDenied, and nothing changes
+// while the tags can be read.
+func TestExistingObjectTagAuthReadQuorumLost(t *testing.T) {
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+	obj, dirs, err := prepareErasure16(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	z := obj.(*erasureServerPools)
+	previous := newObjectLayerFn()
+	setObjectLayer(z)
+	defer func() {
+		z.Shutdown(context.Background())
+		removeRoots(dirs)
+		setObjectLayer(previous)
+	}()
+	bucket, router, err := initAPIHandlerTest(ctx, z, nil, MakeBucketOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	statement := func(effect, resource, conditions string) string {
+		st := fmt.Sprintf(`{"Effect": %q, "Action": ["s3:GetObject", "s3:GetObjectTagging", "s3:PutObjectTagging", "s3:DeleteObjectTagging"], "Resource": ["arn:aws:s3:::%s/%s"]`,
+			effect, bucket, resource)
+		if conditions != "" {
+			st += `, "Condition": ` + conditions
+		}
+		return st + "}"
+	}
+	tagStatement := func(effect, resource, value string) string {
+		return statement(effect, resource, fmt.Sprintf(`{"StringEquals": {"s3:ExistingObjectTag/k": %q}}`, value))
+	}
+	newUser := func(statements ...string) auth.Credentials {
+		return newDeleteAuthzPolicyUser(t, "", bucket, "["+strings.Join(statements, ",")+"]")
+	}
+	newServiceAccount := func(parent auth.Credentials, statements string) auth.Credentials {
+		sessionPolicy, err := policy.ParseConfig(strings.NewReader(`{"Version": "2012-10-17", "Statement": [` + statements + `]}`))
+		if err != nil {
+			t.Fatal(err)
+		}
+		cred, _, err := globalIAMSys.NewServiceAccount(ctx, parent.AccessKey, nil, newServiceAccountOpts{sessionPolicy: sessionPolicy})
+		if err != nil {
+			t.Fatal(err)
+		}
+		return cred
+	}
+	newTempUser := func(parent auth.Credentials, statements string) auth.Credentials {
+		session := `{"Version": "2012-10-17", "Statement": [` + statements + `]}`
+		secret, err := getTokenSigningKey()
+		if err != nil {
+			t.Fatal(err)
+		}
+		cred, err := auth.GetNewCredentialsWithMetadata(map[string]any{
+			parentClaim: parent.AccessKey, "exp": UTCNow().Add(time.Hour).Unix(),
+			policy.SessionPolicyName: base64.StdEncoding.EncodeToString([]byte(session)),
+		}, secret)
+		if err != nil {
+			t.Fatal(err)
+		}
+		cred.ParentUser = parent.AccessKey
+		if _, err := globalIAMSys.SetTempUser(ctx, cred.AccessKey, cred, ""); err != nil {
+			t.Fatal(err)
+		}
+		return cred
+	}
+	// An unrelated cached policy must not consume the candidate limit. The
+	// target user's policy is created below and sorts after this policy.
+	fillerStatements := make([]string, 0, maxExistingTagCandidates)
+	for i := range maxExistingTagCandidates {
+		fillerStatements = append(fillerStatements, statement("Allow", "*",
+			fmt.Sprintf(`{"StringEquals": {"s3:ExistingObjectTag/fill%02d": "v"}}`, i)))
+	}
+	fillerPolicy, err := policy.ParseConfig(strings.NewReader(`{"Version": "2012-10-17", "Statement": [` + strings.Join(fillerStatements, ",") + `]}`))
+	if err != nil {
+		t.Fatal(err)
+	}
+	fillerPolicyName := "000-unread-tags-filler-" + mustGetUUID()
+	if _, err = globalIAMSys.SetPolicy(ctx, fillerPolicyName, *fillerPolicy); err != nil {
+		t.Fatal(err)
+	}
+	defer func() {
+		if err := globalIAMSys.DeletePolicy(ctx, fillerPolicyName, false); err != nil {
+			t.Logf("delete filler policy: %v", err)
+		}
+	}()
+
+	type user struct {
+		name  string
+		creds auth.Credentials
+		// The status with the object's tags readable and with read quorum
+		// lost: 200 and 503 for a caller that some tags let through, 403
+		// and 403 for a caller that none do.
+		healthy, quorumLost int
+	}
+	allowedByTags := func(name string, creds auth.Credentials) user {
+		return user{name, creds, http.StatusOK, http.StatusServiceUnavailable}
+	}
+	deniedByAnyTags := func(name string, creds auth.Credentials) user {
+		return user{name, creds, http.StatusForbidden, http.StatusForbidden}
+	}
+	// Each case below that tests a tag key of its own uses a key no other
+	// policy asks for.
+	ownerCondition := `{"StringEquals": {"s3:ExistingObjectTag/owner": "${aws:username}"}}`
+	owner := newUser(statement("Allow", "*", ownerCondition))
+	users := []user{
+		// Allowed only while the object carries k=v.
+		allowedByTags("tagged", newUser(tagStatement("Allow", "*", "v"))),
+		// Allowed while the object carries a tag np, whatever its value.
+		allowedByTags("nullFalse", newUser(statement("Allow", "*", `{"Null": {"s3:ExistingObjectTag/np": "false"}}`))),
+		// Allowed while a tag ne is there and is not w.
+		allowedByTags("notEquals", newUser(statement("Allow", "*",
+			`{"Null": {"s3:ExistingObjectTag/ne": "false"}, "StringNotEquals": {"s3:ExistingObjectTag/ne": "w"}}`))),
+		// Allowed while every value of tag fa differs from w; that needs a tag fa.
+		allowedByTags("forAllNotEquals", newUser(statement("Allow", "*", `{"ForAllValues:StringNotEquals": {"s3:ExistingObjectTag/fa": "w"}}`))),
+		// Allowed while the object is tagged with the caller's name.
+		allowedByTags("owner", owner),
+		// Allowed, but denied unless the object carries du=1.
+		allowedByTags("denyUnlessTagged", newUser(statement("Allow", "*", ""),
+			statement("Deny", "*", `{"StringNotEquals": {"s3:ExistingObjectTag/du": "1"}}`))),
+		// A service account whose parent asks for k=v and whose own policy
+		// asks for j=w: only an object carrying both lets it through.
+		allowedByTags("serviceAccount", newServiceAccount(newUser(tagStatement("Allow", "*", "v")),
+			statement("Allow", "*", `{"StringEquals": {"s3:ExistingObjectTag/j": "w"}}`))),
+		allowedByTags("temporary", newTempUser(newUser(tagStatement("Allow", "*", "v")),
+			statement("Allow", "*", `{"StringEquals": {"s3:ExistingObjectTag/j": "w"}}`))),
+		allowedByTags("rootTemporary", newTempUser(globalActiveCred, tagStatement("Allow", "*", "v"))),
+		allowedByTags("rootServiceAccount", newServiceAccount(globalActiveCred, tagStatement("Allow", "*", "v"))),
+		// The effective policy must be selected before applying the candidate
+		// limit; the unrelated cached policy above has 64 other tag statements.
+		allowedByTags("unrelatedPolicies", newUser(statement("Allow", "*",
+			`{"StringEquals": {"s3:ExistingObjectTag/target": "ok"}}`))),
+		// An alternative allowed value must survive a Deny that excludes the
+		// first value. With unread tags, k=v is the only valid candidate.
+		allowedByTags("alternativeAllowedValue", newUser(
+			statement("Allow", "*", `{"StringEquals": {"s3:ExistingObjectTag/k": ["a", "v"]}}`),
+			tagStatement("Deny", "*", "a"))),
+		allowedByTags("alternativeValuesAcrossKeys", newUser(
+			statement("Allow", "*", `{"StringEquals": {"s3:ExistingObjectTag/k": ["a", "v"], "s3:ExistingObjectTag/j": ["b", "w"]}}`),
+			tagStatement("Deny", "*", "a"),
+			statement("Deny", "*", `{"StringEquals": {"s3:ExistingObjectTag/j": "b"}}`))),
+		// Both Deny statements must be avoided. The first candidate (k="")
+		// avoids the Null Deny but still matches the second Deny.
+		allowedByTags("multipleDenies", newUser(statement("Allow", "*", ""),
+			statement("Deny", "*", `{"Null": {"s3:ExistingObjectTag/k": "true"}}`),
+			tagStatement("Deny", "*", ""))),
+		// The Deny can be avoided by k=v OR j=w. Only j=w is compatible
+		// with this Allow, so stopping at the first Deny key loses it.
+		{
+			"alternativeDenyKey", newUser(tagStatement("Allow", "*", "a"),
+				statement("Deny", "*", `{"StringNotEquals": {"s3:ExistingObjectTag/k": "v", "s3:ExistingObjectTag/j": "w"}}`)),
+			http.StatusForbidden, http.StatusServiceUnavailable,
+		},
+
+		// Allowed only for k=w: the decision still depends on the tags.
+		{"otherValue", newUser(tagStatement("Allow", "*", "w")), http.StatusForbidden, http.StatusServiceUnavailable},
+
+		// Allowed for k=v under another prefix only.
+		deniedByAnyTags("otherPrefix", newUser(tagStatement("Allow", "other/*", "v"))),
+		// Allowed and denied for k=v alike.
+		deniedByAnyTags("allowDeny", newUser(tagStatement("Allow", "*", "v"), tagStatement("Deny", "*", "v"))),
+		// Allowed only without a tag nc that is 1.
+		deniedByAnyTags("nullConflict", newUser(statement("Allow", "*",
+			`{"Null": {"s3:ExistingObjectTag/nc": "true"}, "StringEquals": {"s3:ExistingObjectTag/nc": "1"}}`))),
+		// Tagged with the caller's name, under another prefix only.
+		deniedByAnyTags("ownerPrefix", newUser(statement("Allow", "other/*", ownerCondition))),
+		// Denied unless the object carries db=1, and denied if it does.
+		deniedByAnyTags("denyBoth", newUser(statement("Allow", "*", ""),
+			statement("Deny", "*", `{"StringNotEquals": {"s3:ExistingObjectTag/db": "1"}}`),
+			statement("Deny", "*", `{"StringEquals": {"s3:ExistingObjectTag/db": "1"}}`))),
+		// The parent asks for k=v and the service account for k=x.
+		deniedByAnyTags("serviceAccountConflict", newServiceAccount(newUser(tagStatement("Allow", "*", "v")),
+			tagStatement("Allow", "*", "x"))),
+	}
+
+	const object, missing = "tagged", "missing"
+	if _, err := z.PutObject(ctx, bucket, object, mustGetPutObjReader(t, bytes.NewReader([]byte("data")), 4, "", ""),
+		ObjectOptions{UserDefined: map[string]string{xhttp.AmzObjectTagging: "k=v&j=w&np=1&ne=1&fa=1&du=1&target=ok&owner=" + owner.AccessKey}}); err != nil {
+		t.Fatal(err)
+	}
+	// Anonymous reads are allowed by the bucket policy while the object carries k=v.
+	if _, err := globalBucketMetadataSys.Update(ctx, bucket, bucketPolicyConfig, []byte(`{"Version": "2012-10-17", "Statement": [
+  {"Effect": "Allow", "Principal": {"AWS": ["*"]}, "Action": ["s3:GetObject"], "Resource": ["arn:aws:s3:::`+bucket+`/*"],
+   "Condition": {"StringEquals": {"s3:ExistingObjectTag/k": "v"}}}]}`)); err != nil {
+		t.Fatal(err)
+	}
+
+	type request struct {
+		name           string
+		method, target string
+		header         map[string]string
+		body           []byte
+	}
+	objectURL := getGetObjectURL("", bucket, object)
+	get := request{"GET", http.MethodGet, objectURL, nil, nil}
+	head := request{"HEAD", http.MethodHead, objectURL, nil, nil}
+	taggingURL := makeTestTargetURL("", bucket, object, url.Values{"tagging": []string{""}})
+	taggingBody := []byte(`<Tagging><TagSet><Tag><Key>k</Key><Value>v</Value></Tag></TagSet></Tagging>`)
+	putTagging := request{"PutObjectTagging", http.MethodPut, taggingURL, nil, taggingBody}
+	getTagging := request{"GetObjectTagging", http.MethodGet, taggingURL, nil, nil}
+	deleteTagging := request{"DeleteObjectTagging", http.MethodDelete, taggingURL, nil, nil}
+	check := func(stage string, creds auth.Credentials, name string, req request, want int) {
+		t.Helper()
+		var rec *httptest.ResponseRecorder
+		if creds.AccessKey == "" {
+			anonymous, err := newTestRequest(req.method, req.target, 0, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, anonymous)
+		} else {
+			var body io.ReadSeeker
+			if req.body != nil {
+				body = bytes.NewReader(req.body)
+			}
+			header := make(map[string]string)
+			for k, v := range req.header {
+				header[k] = v
+			}
+			if creds.IsTemp() {
+				header[xhttp.AmzSecurityToken] = creds.SessionToken
+			}
+			signed, err := newTestSignedRequestV4(req.method, req.target, int64(len(req.body)), body, creds.AccessKey, creds.SecretKey, header)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, signed)
+		}
+		if rec.Code != want {
+			var apiErr APIErrorResponse
+			_ = xml.Unmarshal(rec.Body.Bytes(), &apiErr)
+			t.Errorf("%s: %s by %s: status %d %s, want %d", stage, req.name, name, rec.Code, apiErr.Code, want)
+		}
+	}
+
+	var anonymous auth.Credentials
+	for _, u := range users {
+		check("healthy", u.creds, u.name, get, u.healthy)
+		check("healthy", u.creds, u.name, getTagging, u.healthy)
+	}
+	check("healthy", anonymous, "anonymous", get, http.StatusOK)
+	// The tags were read and allow the request: the range error is the answer.
+	check("healthy", users[0].creds, users[0].name,
+		request{"GET bytes=100-200", http.MethodGet, objectURL, map[string]string{xhttp.Range: "bytes=100-200"}, nil},
+		http.StatusRequestedRangeNotSatisfiable)
+	// Without an object there are no tags: AccessDenied, as before.
+	missingURL := getGetObjectURL("", bucket, missing)
+	check("missing key", users[0].creds, users[0].name, request{"GET", http.MethodGet, missingURL, nil, nil}, http.StatusForbidden)
+	check("missing key", users[0].creds, users[0].name, request{"HEAD", http.MethodHead, missingURL, nil, nil}, http.StatusForbidden)
+	check("missing key", users[0].creds, users[0].name, request{"GetObjectTagging", http.MethodGet, missingURL + "?tagging", nil, nil}, http.StatusForbidden)
+
+	defer objectReadFault(z, bucket, object, 10)()
+	if _, err := z.GetObjectInfo(ctx, bucket, object, ObjectOptions{}); !isErrReadQuorum(err) {
+		t.Fatalf("GetObjectInfo with 10 of 16 drives failing: %v, want InsufficientReadQuorum", err)
+	}
+	for _, req := range []request{get, head, getTagging, putTagging, deleteTagging} {
+		for _, u := range users {
+			check("read quorum lost", u.creds, u.name, req, u.quorumLost)
+		}
+	}
+	check("read quorum lost", anonymous, "anonymous", get, http.StatusServiceUnavailable)
+	check("read quorum lost", anonymous, "anonymous", head, http.StatusServiceUnavailable)
+}
+
+func TestExistingObjectTagsFor(t *testing.T) {
+	values := map[string][]string{"username": {"alice"}, "sub": {"u1"}}
+	for _, tc := range []struct {
+		effect     policy.Effect
+		conditions string
+		want       string // the tags to set, encoded as in x-amz-tagging
+		ok         bool   // false: no tags for this statement
+	}{
+		{policy.Allow, `{"StringEquals": {"s3:ExistingObjectTag/k": "v"}}`, "k=v", true},
+		{policy.Allow, `{"StringEqualsIgnoreCase": {"s3:ExistingObjectTag/k": "V"}, "IpAddress": {"aws:SourceIp": "10.0.0.0/8"}}`, "k=V", true},
+		{policy.Allow, `{"ForAnyValue:StringEquals": {"s3:ExistingObjectTag/k": ["b", "a"]}}`, "k=a", true},
+		{policy.Allow, `{"StringLike": {"s3:ExistingObjectTag/k": "a?c*"}}`, "k=a_c", true},
+		{policy.Allow, `{"StringEquals": {"s3:ExistingObjectTag/b": "2", "s3:ExistingObjectTag/a": "1"}}`, "a=1&b=2", true},
+		// Passed without the tag.
+		{policy.Allow, `{"StringNotEquals": {"s3:ExistingObjectTag/k": "v"}}`, "", true},
+		{policy.Allow, `{"Null": {"s3:ExistingObjectTag/k": "true"}}`, "", true},
+		// Null "false" asks for the tag, with any value.
+		{policy.Allow, `{"Null": {"s3:ExistingObjectTag/k": "false"}}`, "k=", true},
+		{policy.Allow, `{"Null": {"s3:ExistingObjectTag/k": "false"}, "StringNotEquals": {"s3:ExistingObjectTag/k": ["", "w"]}}`, "k=_", true},
+		{policy.Allow, `{"Null": {"s3:ExistingObjectTag/k": "false"}, "StringNotLike": {"s3:ExistingObjectTag/k": "*w"}}`, "k=", true},
+		{policy.Allow, `{"ForAllValues:StringNotEquals": {"s3:ExistingObjectTag/k": "w"}}`, "k=", true},
+		{policy.Allow, `{"Null": {"s3:ExistingObjectTag/k": "true"}, "StringEquals": {"s3:ExistingObjectTag/k": "v"}}`, "", false},
+		// Policy variables take the values of the request.
+		{policy.Allow, `{"StringEquals": {"s3:ExistingObjectTag/owner": "${aws:username}"}}`, "owner=alice", true},
+		{policy.Allow, `{"StringLike": {"s3:ExistingObjectTag/owner": "${jwt:sub}-*"}}`, "owner=u1-", true},
+		{policy.Allow, `{"StringEquals": {"s3:ExistingObjectTag/owner": "${ldap:user}"}}`, "", false},
+		// A Deny is kept from matching.
+		{policy.Deny, `{"StringNotEquals": {"s3:ExistingObjectTag/k": "v"}}`, "k=v", true},
+		{policy.Deny, `{"Null": {"s3:ExistingObjectTag/k": "true"}}`, "k=", true},
+		{policy.Deny, `{"StringEquals": {"s3:ExistingObjectTag/k": "v"}}`, "", true},
+		{policy.Deny, `{"StringEquals": {"s3:prefix": "v"}}`, "", false},
+		// No tag tests.
+		{policy.Allow, `{"StringEquals": {"s3:prefix": "v"}}`, "", false},
+		{policy.Allow, "", "", false},
+	} {
+		var conditions condition.Functions // nil: a statement without a Condition
+		if tc.conditions != "" {
+			if err := json.Unmarshal([]byte(tc.conditions), &conditions); err != nil {
+				t.Fatalf("%s: %v", tc.conditions, err)
+			}
+		}
+		candidates := existingObjectTagsCandidatesFor(tc.effect, conditions, values)
+		ok := len(candidates) > 0
+		got := ""
+		if ok {
+			encoded, err := tags.MapToObjectTags(candidates[0])
+			if err != nil {
+				t.Fatalf("%s: %v", tc.conditions, err)
+			}
+			got = encoded.String()
+		}
+		if got != tc.want || ok != tc.ok {
+			t.Errorf("%s %s: got %q %v, want %q %v", tc.effect, tc.conditions, got, ok, tc.want, tc.ok)
+		}
+	}
+}
+
+// Group-only and external identities need mapping lookups that normally
+// fall back to storage. Candidate collection must stay within the cache even
+// for those identities, while still finding their group/claim/role policy.
+func TestUnreadTagPolicySetsCacheOnly(t *testing.T) {
+	ctx, sys, _ := prepareIAMRevisionFixture(t)
+	const policyName = "unread-tag-policy"
+	batchAuthzPolicy(ctx, t, sys, policyName, `{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::bucket/*"],"Condition":{"StringEquals":{"s3:ExistingObjectTag/k":"v"}}}`)
+	member := iamAdminUser(ctx, t, sys, "unread-group-member", "")
+	_, err := sys.AddUsersToGroup(ctx, "unread-group", []string{member.AccessKey})
+	mustIAM(t, err)
+	_, err = sys.PolicyDBSet(ctx, "unread-group", policyName, regUser, true)
+	mustIAM(t, err)
+	role, err := arn.NewIAMRoleARN("unread-role", "")
+	mustIAM(t, err)
+	sys.rolesMap = map[arn.ARN]string{role: policyName}
+	claimUser := auth.Credentials{
+		AccessKey: "unread-sts", ParentUser: "external-parent", SessionToken: "token",
+		Expiration: UTCNow().Add(time.Hour), Claims: map[string]any{iamPolicyClaimNameOpenID(): policyName},
+	}
+	roleUser := claimUser
+	roleUser.Claims = map[string]any{roleArnClaim: role.String()}
+	original := sys.store.IAMStorageAPI
+	defer func() { sys.store.IAMStorageAPI = original }()
+	for _, tc := range []struct {
+		name string
+		cred auth.Credentials
+	}{
+		{"group", member},
+		{"claims", claimUser},
+		{"role", roleUser},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			name := tc.cred.AccessKey
+			if tc.cred.ParentUser != "" {
+				name = tc.cred.ParentUser
+			}
+			probe := &batchBlockedIAMStore{
+				IAMStorageAPI: original, mapping: name, doc: policyName,
+				started: make(chan struct{}), release: make(chan struct{}),
+			}
+			close(probe.release) // report an accidental read without blocking the test
+			sys.store.IAMStorageAPI = probe
+			sets := sys.unreadTagPolicySets(tc.cred)
+			select {
+			case <-probe.started:
+				t.Error("candidate collection attempted a storage read")
+			default:
+			}
+			if len(sets) != 1 || len(sets[0]) != 1 {
+				t.Fatalf("expected the cached policy through %s, got %v", tc.name, sets)
+			}
+		})
+	}
+}

cmd/auth-handler.go

@@ -340,16 +340,6 @@ func checkRequestAuthType(ctx context.Context, r *http.Request, action policy.Ac
 	return s3Err
 }
 
-func checkRequestAuthTypeWithExistingTags(ctx context.Context, r *http.Request, action policy.Action, bucketName, objectName, existingTags string) (s3Err APIErrorCode) {
-	logger.GetReqInfo(ctx).BucketName = bucketName
-	logger.GetReqInfo(ctx).ObjectName = objectName
-
-	if s3Err = authenticateRequest(ctx, r, action); s3Err != ErrNone {
-		return s3Err
-	}
-	return authorizeRequestWithExistingTags(ctx, r, action, existingTags)
-}
-
 func checkRequestAuthTypeWithRequestTags(ctx context.Context, r *http.Request, action policy.Action, bucketName, objectName string, requestTags *string) (s3Err APIErrorCode) {
 	logger.GetReqInfo(ctx).BucketName = bucketName
 	logger.GetReqInfo(ctx).ObjectName = objectName
@@ -425,6 +415,19 @@ func authorizeRequest(ctx context.Context, r *http.Request, action policy.Action
 	return authorizeRequestWithExistingTags(ctx, r, action, "")
 }
 
+// authorizeBucketRequest authorizes a bucket action, such as s3:ListBucket,
+// on the bucket of a request made for one of its objects.
+func authorizeBucketRequest(ctx context.Context, r *http.Request, action policy.Action) APIErrorCode {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return ErrAccessDenied
+	}
+	objectName := reqInfo.ObjectName
+	reqInfo.ObjectName = ""
+	defer func() { reqInfo.ObjectName = objectName }()
+	return authorizeRequest(ctx, r, action)
+}
+
 func deleteObjectAction(versionID string) policy.Action {
 	if versionID != "" {
 		return policy.DeleteObjectVersionAction
@@ -435,7 +438,12 @@ func deleteObjectAction(versionID string) policy.Action {
 func actionUsesObjectVersion(action policy.Action) bool {
 	switch action {
 	case policy.DeleteObjectAction, policy.DeleteObjectVersionAction,
-		policy.ReplicateDeleteAction, policy.BypassGovernanceRetentionAction:
+		policy.ReplicateDeleteAction, policy.BypassGovernanceRetentionAction,
+		policy.GetObjectAction, policy.GetObjectVersionAction,
+		policy.GetObjectAttributesAction, policy.GetObjectVersionAttributesAction,
+		policy.GetObjectTaggingAction, policy.GetObjectVersionTaggingAction,
+		policy.PutObjectTaggingAction, policy.PutObjectVersionTaggingAction,
+		policy.DeleteObjectTaggingAction, policy.DeleteObjectVersionTaggingAction:
 		return true
 	default:
 		return false
@@ -676,7 +684,15 @@ func setAuthMiddleware(h http.Handler) http.Handler {
 
 		aType := getRequestAuthType(r)
 		switch aType {
-		case authTypeSigned, authTypeSignedV2, authTypeStreamingSigned, authTypeStreamingSignedTrailer:
+		case authTypeSigned, authTypeSignedV2, authTypeStreamingSigned, authTypeStreamingSignedTrailer, authTypeStreamingUnsignedTrailer:
+			// STREAMING-UNSIGNED-PAYLOAD-TRAILER is valid for a genuinely
+			// anonymous request. Once Authorization is present, it is a
+			// signed REST-HEADER request and must obey the same date/skew
+			// bound as the other SigV4 streaming forms.
+			if aType == authTypeStreamingUnsignedTrailer && r.Header.Get(xhttp.Authorization) == "" {
+				h.ServeHTTP(w, r)
+				return
+			}
 			// Verify if date headers are set, if not reject the request
 			amzDate, errCode := parseAmzDateHeader(r)
 			if errCode != ErrNone {
@@ -774,11 +790,12 @@ func isPutActionAllowedWithRequestTags(ctx context.Context, atype authType, buck
 
 func isPutActionAllowedWithCred(bucketName, objectName string, r *http.Request, action policy.Action, requestTags *string, cred auth.Credentials, owner bool) APIErrorCode {
 	// Do not check for PutObjectRetentionAction permission,
-	// if mode and retain until date are not set.
+	// if neither retention values nor a replica retention revision are set.
 	// Can happen when bucket has default lock config set
 	if action == policy.PutObjectRetentionAction &&
 		r.Header.Get(xhttp.AmzObjectLockMode) == "" &&
-		r.Header.Get(xhttp.AmzObjectLockRetainUntilDate) == "" {
+		r.Header.Get(xhttp.AmzObjectLockRetainUntilDate) == "" &&
+		r.Header.Get(xhttp.MinIOSourceObjectRetentionTimestamp) == "" {
 		return ErrNone
 	}
 

cmd/batch-authz-review6_test.go

@@ -330,7 +330,7 @@ func TestBatchReviewRotationKeepsMigrationCleanup(t *testing.T) {
 				t.Errorf("rotation changed a draining source after its version was copied (rotation error: %v)", rotationErr)
 			}
 			snapshot := []FileInfo{{VersionID: before.VersionID, ModTime: beforeInfo.ModTime}}
-			if err := z.removeMovedVersions(t.Context(), bucket, object, 0, snapshot, nil); err != nil {
+			if _, err := z.removeMovedVersions(t.Context(), bucket, object, 0, snapshot, nil); err != nil {
 				t.Fatalf("rotation prevented migration cleanup: %v", err)
 			}
 			if _, err := z.serverPools[0].GetObjectInfo(t.Context(), bucket, object, ObjectOptions{VersionID: before.VersionID}); !isErrObjectNotFound(err) && !isErrVersionNotFound(err) {

cmd/batch-authz-variables_test.go

@@ -0,0 +1,152 @@
+// Copyright (c) 2026 Feng Ruohang
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"encoding/base64"
+	"fmt"
+	"maps"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+// Use explicit condition values to exercise the evaluator, including literal
+// spellings that S3 tag validation does not permit in stored tags.
+func TestBatchPolicyConditionVariableParity(t *testing.T) {
+	f := newBatchAuthzFixture(t)
+	cases := []struct {
+		value, actual string
+		matches       bool
+		requestOnly   bool
+	}{
+		{"${$}100", "${$}100", true, false},
+		{"${$}100", "$100", false, false},
+		{"${*}", "${*}", true, false},
+		{"${?}", "${?}", true, false},
+		{"${custom:unknown}", "${custom:unknown}", true, false},
+		{"${aws:Unknown}", "${aws:Unknown}", true, false},
+		{"${aws:UserAgent", "${aws:UserAgent", true, false},
+		{"${aws:username}", "", true, false},
+		{"${aws:UserAgent}", "test-agent", true, true},
+		{"${prefix${aws:UserAgent}}", "${prefixtest-agent}", true, true},
+	}
+	for i, tc := range cases {
+		for opIndex, op := range []string{
+			"StringEquals", "StringNotEquals", "StringEqualsIgnoreCase", "StringNotEqualsIgnoreCase",
+			"StringLike", "StringNotLike", "ForAnyValue:StringEquals", "ForAllValues:StringEquals", "BinaryEquals",
+		} {
+			for _, effect := range []string{"Allow", "Deny"} {
+				t.Run(fmt.Sprintf("%d/%s/%s", i, op, effect), func(t *testing.T) {
+					name := fmt.Sprintf("var-%d-%d-%s", i, opIndex, effect)
+					conditionValue := tc.value
+					if op == "BinaryEquals" {
+						conditionValue = base64.StdEncoding.EncodeToString([]byte(conditionValue))
+					}
+					statement := fmt.Sprintf(`{"Effect":%q,"Action":["s3:GetObject"],"Resource":["arn:aws:s3:::batch-authz/data/*"],"Condition":{%q:{"s3:ExistingObjectTag/label":%q}}}`, effect, op, conditionValue)
+					if effect == "Deny" {
+						statement += `,{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::batch-authz/data/*"]}`
+					}
+					cred, sub := batchContextUser(t, f, name, statement)
+					actual := tc.actual
+					if tc.value == "${aws:username}" {
+						actual = cred.AccessKey
+					}
+					values := map[string][]string{"ExistingObjectTag/label": {actual}}
+					ordinaryValues := maps.Clone(values)
+					ordinaryValues["username"] = []string{cred.AccessKey}
+					ordinaryValues["UserAgent"] = []string{"test-agent"}
+					ordinaryAllowed := f.sys.isAllowedLocally(policy.Args{
+						AccountName:     cred.AccessKey,
+						Action:          policy.GetObjectAction,
+						BucketName:      f.bucket,
+						ObjectName:      "data/" + name,
+						ConditionValues: ordinaryValues,
+					})
+					matches := tc.matches
+					if strings.Contains(op, "Not") {
+						matches = !matches
+					}
+					if want := matches == (effect == "Allow"); ordinaryAllowed != want {
+						t.Fatalf("ordinary evaluator allowed=%v want %v", ordinaryAllowed, want)
+					}
+					batchErr := sub.authorize(f.ctx, batchAuthzRequest{
+						action: policy.GetObjectAction, bucket: f.bucket, object: "data/" + name, values: values,
+					})
+					if tc.requestOnly {
+						if !isBatchJobAuthzError(batchErr) {
+							t.Fatalf("missing request context must deny: %v", batchErr)
+						}
+						if (effect == "Deny") != isBatchContextRefusal(batchErr) {
+							t.Fatalf("only a Deny must refuse missing context: %v", batchErr)
+						}
+						return
+					}
+					if (batchErr == nil) != ordinaryAllowed {
+						t.Fatalf("ordinary allowed=%v; batch=%v", ordinaryAllowed, batchErr)
+					}
+				})
+			}
+		}
+	}
+
+	// Condition keys themselves are never expanded.
+	const statement = `{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::batch-authz/*"],"Condition":{"StringEquals":{"s3:ExistingObjectTag/${aws:UserAgent}":"literal"}}}`
+	cred, sub := batchContextUser(t, f, "literal-condition-key", statement)
+	values := map[string][]string{"ExistingObjectTag/${aws:UserAgent}": {"literal"}}
+	if !f.sys.isAllowedLocally(policy.Args{AccountName: cred.AccessKey, Action: policy.GetObjectAction, BucketName: f.bucket, ObjectName: "data/key", ConditionValues: values}) {
+		t.Fatal("ordinary evaluator did not match the literal condition key")
+	}
+	if err := sub.authorize(f.ctx, batchAuthzRequest{action: policy.GetObjectAction, bucket: f.bucket, object: "data/key", values: values}); err != nil {
+		t.Fatalf("batch treated a condition key as a variable: %v", err)
+	}
+}
+
+// Object names permit these spellings, so also compare real S3 GETs with batch.
+func TestBatchPolicyResourceVariableParity(t *testing.T) {
+	f := newBatchAuthzFixture(t)
+	router := initTestAPIEndPoints(f.obj, []string{"GetObject"})
+	for i, raw := range []string{"${$}100", "${*}", "${?}", "${custom:unknown}", "${prefix${aws:UserAgent}}", "${aws:username}", "${aws:UserAgent}"} {
+		for _, effect := range []string{"Allow", "Deny"} {
+			t.Run(fmt.Sprintf("%d/%s", i, effect), func(t *testing.T) {
+				name := fmt.Sprintf("res-%d-%s", i, effect)
+				statement := fmt.Sprintf(`{"Effect":%q,"Action":["s3:GetObject"],"Resource":[%q]}`, effect, "arn:aws:s3:::batch-authz/"+raw)
+				if effect == "Deny" {
+					statement += `,{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::batch-authz/*"]}`
+				}
+				cred, sub := batchContextUser(t, f, name, statement)
+				object := strings.ReplaceAll(raw, "${aws:username}", cred.AccessKey)
+				if raw == "${aws:UserAgent}" {
+					object = "test-agent"
+				}
+				_, err := f.obj.PutObject(f.ctx, f.bucket, object, mustGetPutObjReader(t, strings.NewReader("data"), 4, "", ""), ObjectOptions{})
+				mustIAM(t, err)
+				req, err := newTestSignedRequestV4(http.MethodGet, getGetObjectURL("", f.bucket, object), 0, nil, cred.AccessKey, cred.SecretKey, map[string]string{"User-Agent": "test-agent"})
+				mustIAM(t, err)
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				wantStatus := http.StatusOK
+				if effect == "Deny" {
+					wantStatus = http.StatusForbidden
+				}
+				if rec.Code != wantStatus {
+					t.Fatalf("S3 read: %d want %d: %s", rec.Code, wantStatus, rec.Body.String())
+				}
+				err = sub.authorize(f.ctx, batchAuthzRequest{action: policy.GetObjectAction, bucket: f.bucket, object: object})
+				if raw == "${aws:UserAgent}" {
+					if !isBatchJobAuthzError(err) || (effect == "Deny") != isBatchContextRefusal(err) {
+						t.Fatalf("batch did not reject missing request context: %v", err)
+					}
+					return
+				}
+				if (err == nil) != (rec.Code == http.StatusOK) {
+					t.Fatalf("resource %q %s: S3=%d batch=%v", raw, effect, rec.Code, err)
+				}
+			})
+		}
+	}
+}

cmd/batch-authz.go

@@ -829,15 +829,15 @@ func batchStatementNeedsRequest(st policy.Statement, args policy.Args, supplied
 	// Policy variables in condition values.
 	if len(st.Conditions) > 0 {
 		data, err := json.Marshal(st.Conditions)
-		if err != nil || batchUnsuppliedVariable(string(data), supplied) {
+		if err != nil || batchConditionsNeedVariables(data, supplied) {
 			return true
 		}
 	}
 	return false
 }
 
-// batchUnsuppliedVariable reports whether s holds a policy variable, ${key},
-// whose value the job does not supply.
+// batchUnsuppliedVariable follows Resource.Match: only CommonKeys are expanded,
+// and an unsupported ${...} sequence (including its nested text) stays literal.
 func batchUnsuppliedVariable(s string, supplied map[string]bool) bool {
 	for {
 		i := strings.Index(s, "${")
@@ -849,13 +849,53 @@ func batchUnsuppliedVariable(s string, supplied map[string]bool) bool {
 		if j < 0 {
 			return false
 		}
-		if !batchKeySupplied(supplied, s[:j]) {
+		if condition.CommonKeysMap[condition.KeyName(s[:j])] && !batchKeySupplied(supplied, s[:j]) {
 			return true
 		}
 		s = s[j+1:]
 	}
 }
 
+// Conditions replace each recognized variable wherever it occurs in a string
+// value, unlike the resource parser. Inspect values only, not condition keys,
+// and decode BinaryEquals as the policy evaluator does before substitution.
+func batchConditionsNeedVariables(data []byte, supplied map[string]bool) bool {
+	var conditions map[string]map[string]condition.ValueSet
+	if err := json.Unmarshal(data, &conditions); err != nil {
+		return true
+	}
+	for name, keys := range conditions {
+		name = strings.TrimPrefix(strings.TrimPrefix(name, "ForAnyValue:"), "ForAllValues:")
+		name = strings.TrimSuffix(name, "IfExists")
+		switch name {
+		case "StringEquals", "StringNotEquals", "StringEqualsIgnoreCase", "StringNotEqualsIgnoreCase", "StringLike", "StringNotLike", "BinaryEquals":
+		default:
+			continue
+		}
+		for _, values := range keys {
+			for value := range values {
+				s, err := value.GetString()
+				if err != nil {
+					return true
+				}
+				if name == "BinaryEquals" {
+					decoded, err := base64.StdEncoding.DecodeString(s)
+					if err != nil {
+						return true
+					}
+					s = string(decoded)
+				}
+				for _, key := range condition.CommonKeys {
+					if strings.Contains(s, key.VarName()) && !batchKeySupplied(supplied, string(key)) {
+						return true
+					}
+				}
+			}
+		}
+	}
+	return false
+}
+
 // batchStatementMayApply matches the resources of a statement, in both forms
 // a bucket request can take. A statement whose resources the evaluator
 // translates (S3 Tables and vectors actions cover S3 data actions) is taken

cmd/batch-rotate-context_test.go

@@ -0,0 +1,177 @@
+// Copyright (c) 2026 Feng Ruohang
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"bytes"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"io"
+	"maps"
+	"net/http"
+	"strings"
+	"testing"
+
+	"github.com/minio/minio/internal/crypto"
+	"github.com/minio/minio/internal/kms"
+)
+
+func TestBatchRotationContextValidation(t *testing.T) {
+	previous := GlobalKMS
+	GlobalKMS = nil
+	t.Cleanup(func() { GlobalKMS = previous })
+	for _, encoded := range []string{"not-base64!", base64.StdEncoding.EncodeToString([]byte(`{`)), base64.StdEncoding.EncodeToString([]byte(`{"tenant":1}`)), base64.StdEncoding.EncodeToString([]byte(`[]`))} {
+		enc := BatchJobKeyRotateEncryption{Type: ssekms, Key: "key", Context: encoded}
+		if err := enc.Validate(); err == nil {
+			t.Fatalf("accepted invalid context %q", encoded)
+		}
+	}
+	for _, raw := range []string{"", `{}`, `null`, `{"tenant":"acme"}`} {
+		encoded := base64.StdEncoding.EncodeToString([]byte(raw))
+		if raw == "" {
+			encoded = ""
+		}
+		if err := (BatchJobKeyRotateEncryption{Type: ssekms, Key: "key", Context: encoded}).Validate(); err != nil {
+			t.Fatalf("context %q: %v", raw, err)
+		}
+	}
+}
+
+func TestBatchRotationContextInitialRetryAndReload(t *testing.T) {
+	for _, mode := range []string{"initial", "retry", "reload"} {
+		t.Run(mode, func(t *testing.T) {
+			f := newBatchAuthzFixture(t)
+			previous := GlobalKMS
+			t.Cleanup(func() { GlobalKMS = previous })
+			configured, err := kms.NewBuiltin("context-key", bytes.Repeat([]byte{0x42}, 32))
+			mustIAM(t, err)
+			GlobalKMS = configured
+			const object = "rotation/context"
+			const payload = "a context-bound encryption key keeps this readable"
+			metadata := map[string]string{}
+			key, err := newEncryptMetadata(f.ctx, crypto.S3KMS, "context-key", nil, f.bucket, object, metadata, kms.Context{"tenant": "old"})
+			mustIAM(t, err)
+			ciphertext, err := io.ReadAll(crypto.EncryptSinglePart(strings.NewReader(payload), key))
+			mustIAM(t, err)
+			original, err := f.obj.PutObject(f.ctx, f.bucket, object, mustGetPutObjReader(t, bytes.NewReader(ciphertext), int64(len(ciphertext)), "", ""), ObjectOptions{Versioned: true, UserDefined: metadata})
+			mustIAM(t, err)
+			contextJSON := `{"tenant":"acme","purpose":"batch-rotation","区域":"杭州","�":"replacement","emoji":"🔑"}`
+			encoded := base64.StdEncoding.EncodeToString([]byte(contextJSON))
+			rec, job := f.submit(t, globalActiveCred, fmt.Sprintf("keyrotate:\n  apiVersion: v1\n  bucket: %s\n  prefix: rotation/\n  encryption:\n    type: sse-kms\n    key: context-key\n    context: %s\n", f.bucket, encoded))
+			if job == nil {
+				t.Fatalf("submit: %d %s", rec.Code, rec.Body.String())
+			}
+			if mode == "retry" {
+				GlobalKMS = nil
+				err := job.KeyRotate.KeyRotate(f.ctx, f.obj, original, job.Submitter)
+				GlobalKMS = configured
+				if err == nil {
+					t.Fatal("rotation succeeded while KMS was unavailable")
+				}
+				before, err := f.obj.GetObjectInfo(f.ctx, f.bucket, object, ObjectOptions{VersionID: original.VersionID})
+				mustIAM(t, err)
+				if before.UserDefined[crypto.MetaContext] != metadata[crypto.MetaContext] {
+					t.Fatal("failed attempt changed context")
+				}
+			}
+			if mode == "reload" {
+				loaded := &BatchJobRequest{}
+				mustIAM(t, loaded.load(f.ctx, f.obj, getJobPath(*job)))
+				job = loaded
+			}
+			mustIAM(t, job.KeyRotate.Start(f.ctx, f.obj, *job))
+			progress := f.jobInfo(t, job)
+			if !progress.Complete || progress.Failed || progress.Objects != 1 {
+				t.Fatalf("rotation incomplete: %+v", progress)
+			}
+			after, err := f.obj.GetObjectInfo(f.ctx, f.bucket, object, ObjectOptions{VersionID: original.VersionID})
+			mustIAM(t, err)
+			raw, err := base64.StdEncoding.DecodeString(after.UserDefined[crypto.MetaContext])
+			mustIAM(t, err)
+			var got kms.Context
+			mustIAM(t, json.Unmarshal(raw, &got))
+			if !maps.Equal(got, kms.Context{"tenant": "acme", "purpose": "batch-rotation", "区域": "杭州", "�": "replacement", "emoji": "🔑"}) {
+				t.Fatalf("stored context %v", got)
+			}
+			actual, err := crypto.S3KMS.UnsealObjectKey(configured, after.UserDefined, f.bucket, object)
+			mustIAM(t, err)
+			if actual != key {
+				t.Fatal("rotation changed the plaintext data key")
+			}
+			if got := readCopyChecksumObject(t, f.obj, f.bucket, object, ObjectOptions{VersionID: original.VersionID}); string(got) != payload {
+				t.Fatal("rotated object is unreadable")
+			}
+		})
+	}
+}
+
+func TestBatchRotationInvalidUTF8LeavesObjectReadable(t *testing.T) {
+	for _, tc := range []struct{ name, raw string }{
+		{"colliding-keys", "{\"\xff\":\"a\",\"\xfe\":\"b\"}"},
+		{"replacement-key", "{\"\xff\":\"a\",\"�\":\"b\"}"},
+		{"invalid-value", "{\"tenant\":\"\xff\"}"},
+	} {
+		for _, phase := range []string{"submit", "reload"} {
+			t.Run(tc.name+"/"+phase, func(t *testing.T) {
+				f := newBatchAuthzFixture(t)
+				previous := GlobalKMS
+				t.Cleanup(func() { GlobalKMS = previous })
+				configured, err := kms.NewBuiltin("context-key", bytes.Repeat([]byte{0x42}, 32))
+				mustIAM(t, err)
+				GlobalKMS = configured
+				const object, payload = "rotation/context", "the original encrypted payload must remain readable"
+				metadata := map[string]string{}
+				key, err := newEncryptMetadata(f.ctx, crypto.S3KMS, "context-key", nil, f.bucket, object, metadata, kms.Context{"tenant": "old"})
+				mustIAM(t, err)
+				ciphertext, err := io.ReadAll(crypto.EncryptSinglePart(strings.NewReader(payload), key))
+				mustIAM(t, err)
+				original, err := f.obj.PutObject(f.ctx, f.bucket, object, mustGetPutObjReader(t, bytes.NewReader(ciphertext), int64(len(ciphertext)), "", ""), ObjectOptions{Versioned: true, UserDefined: metadata})
+				mustIAM(t, err)
+				encoded := base64.StdEncoding.EncodeToString([]byte(tc.raw))
+				submitContext := encoded
+				if phase == "reload" {
+					submitContext = base64.StdEncoding.EncodeToString([]byte(`{"tenant":"safe"}`))
+				}
+				rec, job := f.submit(t, globalActiveCred, fmt.Sprintf("keyrotate:\n  apiVersion: v1\n  bucket: %s\n  prefix: rotation/\n  encryption:\n    type: sse-kms\n    key: context-key\n    context: %s\n", f.bucket, submitContext))
+				if phase == "submit" {
+					if job != nil || rec.Code != http.StatusBadRequest {
+						t.Fatalf("invalid UTF-8 context accepted: %d %s", rec.Code, rec.Body.String())
+					}
+				} else {
+					if job == nil {
+						t.Fatalf("valid submit: %d %s", rec.Code, rec.Body.String())
+					}
+					// Simulate a manifest saved by a version which accepted these
+					// bytes. Execution must validate again before changing the key.
+					job.KeyRotate.Encryption.Context = encoded
+					job.KeyRotate.Flags.Retry.Attempts = 1
+					manifest, err := job.MarshalMsg([]byte(batchJobEnvelope))
+					mustIAM(t, err)
+					mustIAM(t, saveConfig(f.ctx, f.obj, getJobPath(*job), manifest))
+					loaded := &BatchJobRequest{}
+					mustIAM(t, loaded.load(f.ctx, f.obj, getJobPath(*job)))
+					mustIAM(t, loaded.KeyRotate.Start(f.ctx, f.obj, *loaded))
+					progress := f.jobInfo(t, loaded)
+					if progress.Complete || !progress.Failed || progress.Objects != 0 || progress.ObjectsFailed != 1 {
+						t.Fatalf("invalid context reported as success: %+v", progress)
+					}
+				}
+				after, err := f.obj.GetObjectInfo(f.ctx, f.bucket, object, ObjectOptions{VersionID: original.VersionID})
+				mustIAM(t, err)
+				if after.UserDefined[crypto.MetaContext] != metadata[crypto.MetaContext] {
+					t.Fatal("rejected rotation changed stored context")
+				}
+				actual, err := crypto.S3KMS.UnsealObjectKey(configured, after.UserDefined, f.bucket, object)
+				mustIAM(t, err)
+				if actual != key {
+					t.Fatal("rejected rotation changed data key")
+				}
+				if got := readCopyChecksumObject(t, f.obj, f.bucket, object, ObjectOptions{VersionID: original.VersionID}); string(got) != payload {
+					t.Fatal("rejected rotation damaged stored content")
+				}
+			})
+		}
+	}
+}

cmd/batch-rotate.go

@@ -29,10 +29,13 @@ import (
 	"strconv"
 	"strings"
 	"time"
+	"unicode/utf8"
 
 	jsoniter "github.com/json-iterator/go"
 	"github.com/minio/minio-go/v7/pkg/tags"
 	"github.com/minio/minio/internal/crypto"
+	"github.com/minio/minio/internal/etag"
+	"github.com/minio/minio/internal/hash"
 	xhttp "github.com/minio/minio/internal/http"
 	"github.com/minio/minio/internal/kms"
 	"github.com/pgsty/silo-pkg/v3/env"
@@ -83,43 +86,67 @@ const (
 
 // BatchJobKeyRotateEncryption defines key rotation encryption options passed
 type BatchJobKeyRotateEncryption struct {
-	Type       BatchKeyRotationType `yaml:"type" json:"type"`
-	Key        string               `yaml:"key" json:"key"`
-	Context    string               `yaml:"context" json:"context"`
-	kmsContext kms.Context          `msg:"-"`
+	Type    BatchKeyRotationType `yaml:"type" json:"type"`
+	Key     string               `yaml:"key" json:"key"`
+	Context string               `yaml:"context" json:"context"`
+}
+
+// batchKeyRotateContext decodes the persisted configuration on every run. It
+// must not depend on unpersisted derived state or mutate shared job options.
+func batchKeyRotateContext(encoded string) (kms.Context, error) {
+	ctx := kms.Context{}
+	if encoded == "" {
+		return ctx, nil
+	}
+	b, err := base64.StdEncoding.DecodeString(encoded)
+	if err != nil {
+		return nil, err
+	}
+	// Saving the context replaces invalid UTF-8 and can collapse distinct
+	// keys, changing the associated data required to decrypt the object.
+	if !utf8.Valid(b) {
+		return nil, fmt.Errorf("KMS context must be valid UTF-8: %w", errInvalidArgument)
+	}
+	if err = jsoniter.ConfigCompatibleWithStandardLibrary.Unmarshal(b, &ctx); err != nil {
+		return nil, err
+	}
+	if ctx == nil {
+		ctx = kms.Context{}
+	}
+	return ctx, nil
 }
 
 // Validate validates input key rotation encryption options.
 func (e BatchJobKeyRotateEncryption) Validate() error {
+	_, err := e.validate()
+	return err
+}
+
+// validate also returns a fresh context for the actual rotation. Validation's
+// probe entry is added to a separate map, never to the object's context.
+func (e BatchJobKeyRotateEncryption) validate() (kms.Context, error) {
 	if e.Type != sses3 && e.Type != ssekms {
-		return errInvalidArgument
+		return nil, errInvalidArgument
 	}
 	spaces := strings.HasPrefix(e.Key, " ") || strings.HasSuffix(e.Key, " ")
 	if e.Type == ssekms && spaces {
-		return crypto.ErrInvalidEncryptionKeyID
+		return nil, crypto.ErrInvalidEncryptionKeyID
 	}
-
-	if e.Type == ssekms && GlobalKMS != nil {
-		ctx := kms.Context{}
-		if e.Context != "" {
-			b, err := base64.StdEncoding.DecodeString(e.Context)
-			if err != nil {
-				return err
-			}
-
-			json := jsoniter.ConfigCompatibleWithStandardLibrary
-			if err := json.Unmarshal(b, &ctx); err != nil {
-				return err
-			}
-		}
-		e.kmsContext = kms.Context{}
-		maps.Copy(e.kmsContext, ctx)
-		ctx["MinIO batch API"] = "batchrotate" // Context for a test key operation
-		if _, err := GlobalKMS.GenerateKey(GlobalContext, &kms.GenerateKeyRequest{Name: e.Key, AssociatedData: ctx}); err != nil {
-			return err
+	if e.Type != ssekms {
+		return nil, nil
+	}
+	ctx, err := batchKeyRotateContext(e.Context)
+	if err != nil {
+		return nil, err
+	}
+	if GlobalKMS != nil {
+		probe := maps.Clone(ctx)
+		probe["MinIO batch API"] = "batchrotate" // Context for a test key operation
+		if _, err := GlobalKMS.GenerateKey(GlobalContext, &kms.GenerateKeyRequest{Name: e.Key, AssociatedData: probe}); err != nil {
+			return nil, err
 		}
 	}
-	return nil
+	return ctx, nil
 }
 
 // BatchKeyRotateFilter holds all the filters currently supported for batch replication
@@ -203,11 +230,11 @@ func (r *BatchJobKeyRotateV1) rotateAuthzRequests(oi ObjectInfo) []batchAuthzReq
 	if versionID == "" {
 		versionID = nullVersionID
 	}
-	// The encryption the rewrite leaves: rotation keeps the kind of the
-	// version (rotateKey), and SSE-KMS takes the requested key.
+	// The encryption the rewrite leaves: SSE-KMS takes the requested key,
+	// including when migrating an SSE-S3 version to SSE-KMS.
 	values := map[string][]string{}
 	switch {
-	case crypto.S3KMS.IsEncrypted(oi.UserDefined):
+	case crypto.S3KMS.IsEncrypted(oi.UserDefined) || r.Encryption.Type == ssekms:
 		values[strings.ToLower(xhttp.AmzServerSideEncryption)] = []string{xhttp.AmzEncryptionKMS}
 		if r.Encryption.Type == ssekms && r.Encryption.Key != "" {
 			values[strings.ToLower(xhttp.AmzServerSideEncryptionKmsID)] = []string{r.Encryption.Key}
@@ -285,31 +312,113 @@ func (r *BatchJobKeyRotateV1) KeyRotate(ctx context.Context, api ObjectLayer, ob
 	}
 	oi := obj.Clone()
 	var (
-		newKeyID      string
-		newKeyContext kms.Context
+		newKeyID       string
+		newKeyContext  kms.Context
+		replaceContext bool
+		targetKind     crypto.Type = crypto.S3
 	)
-	encMetadata := make(map[string]string)
-	for k, v := range oi.UserDefined {
-		if stringsHasPrefixFold(k, ReservedMetadataPrefixLower) {
-			encMetadata[k] = v
-		}
+	if sseKMS || r.Encryption.Type == ssekms {
+		targetKind = crypto.S3KMS
 	}
-
 	if (sseKMS || sseS3) && r.Encryption.Type == ssekms {
-		if err = r.Encryption.Validate(); err != nil {
+		newKeyContext, err = r.Encryption.validate()
+		if err != nil {
 			return err
 		}
 		newKeyID = strings.TrimPrefix(r.Encryption.Key, crypto.ARNPrefix)
-		newKeyContext = r.Encryption.kmsContext
-	}
-	if err = rotateKey(ctx, []byte{}, newKeyID, []byte{}, r.Bucket, oi.Name, encMetadata, newKeyContext); err != nil {
-		return err
+		replaceContext = r.Encryption.Context != ""
 	}
 
-	// Since we are rotating the keys, make sure to update the metadata.
-	oi.metadataOnly = true
-	oi.keyRotation = true
-	maps.Copy(oi.UserDefined, encMetadata)
+	srcOpts := ObjectOptions{VersionID: oi.VersionID}
+	dstOpts := ObjectOptions{
+		VersionID:        oi.VersionID,
+		Versioned:        versioned,
+		VersionSuspended: versionSuspended,
+		NoLock:           true,
+	}
+
+	if oi.Legacy {
+		if targetKind == crypto.S3KMS && !replaceContext && len(newKeyContext) == 0 && sseKMS {
+			_, _, _, newKeyContext, err = crypto.S3KMS.ParseMetadata(oi.UserDefined)
+			if err != nil {
+				return err
+			}
+		}
+		readOpts := ObjectOptions{
+			VersionID:        oi.VersionID,
+			Versioned:        versioned,
+			VersionSuspended: versionSuspended,
+			NoLock:           true,
+			NoAuditLog:       true,
+		}
+		var gr *GetObjectReader
+		if z, ok := api.(*erasureServerPools); ok && pool >= 0 {
+			gr, err = z.serverPools[pool].GetObjectNInfo(ctx, r.Bucket, encodeDirObject(oi.Name), nil, http.Header{}, readOpts)
+		} else {
+			gr, err = api.GetObjectNInfo(ctx, r.Bucket, oi.Name, nil, http.Header{}, readOpts)
+		}
+		if err != nil {
+			return err
+		}
+		defer gr.Close()
+
+		actualSize, err := gr.ObjInfo.GetActualSize()
+		if err != nil {
+			return err
+		}
+		rawReader, err := hash.NewReader(ctx, gr, actualSize, "", "", actualSize)
+		if err != nil {
+			return err
+		}
+		pReader := NewPutObjReader(rawReader)
+		encMetadata := make(map[string]string)
+		encReader, objEncKey, err := newEncryptReader(ctx, rawReader, targetKind, newKeyID, nil, r.Bucket, oi.Name, encMetadata, newKeyContext)
+		if err != nil {
+			return err
+		}
+		crypto.RemoveInternalEntries(oi.UserDefined)
+		delete(oi.UserDefined, crypto.MetaContext)
+		delete(oi.UserDefined, ReservedMetadataPrefix+"compression")
+		delete(oi.UserDefined, ReservedMetadataPrefix+"actual-size")
+		maps.Copy(oi.UserDefined, encMetadata)
+
+		targetSize := (&ObjectInfo{Size: actualSize}).EncryptedSize()
+		wrapped := etag.Wrap(encReader, rawReader)
+		hReader, err := hash.NewReader(ctx, wrapped, targetSize, "", "", actualSize)
+		if err != nil {
+			return err
+		}
+		pReader, err = pReader.WithEncryption(hReader, &objEncKey)
+		if err != nil {
+			return err
+		}
+		oi.PutObjReader = pReader
+		oi.metadataOnly = false
+		oi.keyRotation = true
+		dstOpts.EncryptFn = metadataEncrypter(objEncKey)
+		if dstOpts.VersionID == "" && (versioned || versionSuspended) {
+			dstOpts.VersionID = nullVersionID
+		}
+	} else {
+		encMetadata := make(map[string]string)
+		for k, v := range oi.UserDefined {
+			if stringsHasPrefixFold(k, ReservedMetadataPrefixLower) {
+				encMetadata[k] = v
+			}
+		}
+		if err = rotateKeyWithTarget(ctx, []byte{}, targetKind, newKeyID, []byte{}, r.Bucket, oi.Name, encMetadata, newKeyContext, replaceContext); err != nil {
+			return err
+		}
+		// Since we are rotating the keys, make sure to update the metadata.
+		oi.metadataOnly = true
+		oi.keyRotation = true
+		delete(oi.UserDefined, crypto.MetaSealedKeyS3)
+		delete(oi.UserDefined, crypto.MetaSealedKeyKMS)
+		delete(oi.UserDefined, crypto.MetaKeyID)
+		delete(oi.UserDefined, crypto.MetaDataEncryptionKey)
+		delete(oi.UserDefined, crypto.MetaContext)
+		maps.Copy(oi.UserDefined, encMetadata)
+	}
 	// The rewrite replaces the stored metadata with UserDefined, which a
 	// read returns without the tags and the expiry: keep them.
 	if oi.UserTags != "" {
@@ -318,8 +427,6 @@ func (r *BatchJobKeyRotateV1) KeyRotate(ctx context.Context, api ObjectLayer, ob
 	if !oi.Expires.IsZero() {
 		oi.UserDefined["expires"] = oi.ExpiresStr()
 	}
-	srcOpts := ObjectOptions{VersionID: oi.VersionID}
-	dstOpts := ObjectOptions{VersionID: oi.VersionID, NoLock: true}
 	if z, ok := api.(*erasureServerPools); ok && pool >= 0 {
 		// Rewrite the copy that was read and authorized. The pools layer
 		// would route the rewrite by the latest version of the key, which

cmd/batch-submitter-authz_test.go

@@ -33,6 +33,9 @@ func newBatchAuthzFixture(t *testing.T) *batchAuthzFixture {
 	t.Helper()
 	ctx, sys := iamAdminFixture(t)
 	obj := newObjectLayerFn()
+	// Match storage-class parity to this fixture's single drive, even after
+	// an API test has loaded the configuration of a larger erasure set.
+	mustIAM(t, newTestConfig(globalMinioDefaultRegion, obj))
 	batchTestJobPool(ctx, t, obj)
 	f := &batchAuthzFixture{ctx: ctx, sys: sys, obj: obj, bucket: "batch-authz"}
 	mustIAM(t, obj.MakeBucket(ctx, f.bucket, MakeBucketOptions{VersioningEnabled: true}))

cmd/bucket-handlers.go

@@ -478,15 +478,11 @@ func (api objectAPIHandlers) DeleteMultipleObjectsHandler(w http.ResponseWriter,
 	getObjectInfoFn := objectAPI.GetObjectInfo
 
 	var (
-		hasLockEnabled bool
-		dsc            ReplicateDecision
-		goi            ObjectInfo
-		gerr           error
+		dsc  ReplicateDecision
+		goi  ObjectInfo
+		gerr error
 	)
 	replicateDeletes := hasReplicationRules(ctx, bucket, deleteObjectsReq.Objects)
-	if rcfg, _ := globalBucketObjectLockSys.Get(bucket); rcfg.LockEnabled {
-		hasLockEnabled = true
-	}
 
 	type deleteResult struct {
 		delInfo DeletedObject
@@ -496,7 +492,14 @@ func (api objectAPIHandlers) DeleteMultipleObjectsHandler(w http.ResponseWriter,
 	deleteResults := make([]deleteResult, len(deleteObjectsReq.Objects))
 	duplicateOf := make(map[int]int)
 
-	vc, _ := globalBucketVersioningSys.Get(bucket)
+	vc, rcfg, metaErr := checkBucketDeleteMetadata(bucket)
+	if metaErr != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, metaErr), r.URL)
+		return
+	}
+	lockedNullDelete := func(obj ObjectToDelete) bool {
+		return obj.VersionID == "" && rcfg.LockEnabled && !vc.PrefixEnabled(obj.ObjectName)
+	}
 	oss := make([]*objSweeper, len(deleteObjectsReq.Objects))
 	for index, object := range deleteObjectsReq.Objects {
 		reqInfo.ObjectName = object.ObjectName
@@ -537,10 +540,10 @@ func (api objectAPIHandlers) DeleteMultipleObjectsHandler(w http.ResponseWriter,
 			VersionSuspended: vc.Suspended(),
 		}
 
-		// Physical version deletes in a locked bucket are checked by the
-		// single-object path below, while its mutation lock is held. A lookup
-		// here could miss a later protection update or a protected pool copy.
-		if hasLockEnabled && object.VersionID != "" {
+		// Every physical version delete checks the version's own protection
+		// under its mutation lock. Bucket metadata may be stale or unavailable
+		// and cannot establish that a stored version is unprotected.
+		if object.VersionID != "" || lockedNullDelete(object) {
 			if first, ok := objectsToDelete[object]; ok {
 				duplicateOf[index] = first
 			} else {
@@ -605,23 +608,32 @@ func (api objectAPIHandlers) DeleteMultipleObjectsHandler(w http.ResponseWriter,
 	bulk := make([]ObjectToDelete, 0, len(deleteList))
 	bulkIndex := make([]int, 0, len(deleteList))
 	for i, object := range deleteList {
-		if !hasLockEnabled || object.VersionID == "" {
+		if object.VersionID == "" && !lockedNullDelete(object) {
 			bulk = append(bulk, object)
 			bulkIndex = append(bulkIndex, i)
 			continue
 		}
 		reqInfo.ObjectName, reqInfo.VersionID = object.ObjectName, object.VersionID
 		opts := ObjectOptions{
-			VersionID:        object.VersionID,
-			Versioned:        vc.PrefixEnabled(object.ObjectName),
-			VersionSuspended: vc.Suspended(),
+			VersionID:             object.VersionID,
+			Versioned:             vc.PrefixEnabled(object.ObjectName),
+			VersionSuspended:      vc.Suspended(),
+			RefuseLockedOverwrite: lockedNullDelete(object),
 		}
 		index := objectsToDelete[object]
 		if !globalTierConfigMgr.Empty() {
-			oss[index] = newObjSweeper(bucket, object.ObjectName).WithVersion(object.VersionID).WithVersioning(opts.Versioned, opts.VersionSuspended)
+			sweepVID := object.VersionID
+			if sweepVID == "" && opts.VersionSuspended {
+				sweepVID = nullVersionID
+			}
+			oss[index] = newObjSweeper(bucket, object.ObjectName).WithVersion(sweepVID).WithVersioning(opts.Versioned, opts.VersionSuspended)
 		}
 		opts.SetEvalRetentionBypassFn(func(oi ObjectInfo, err error) error {
-			return enforceRetentionBypassForDelete(ctx, r, bucket, object, oi, err)
+			checkObj := object
+			if checkObj.VersionID == "" {
+				checkObj.VersionID = nullVersionID
+			}
+			return enforceRetentionBypassForDelete(ctx, r, bucket, checkObj, oi, err)
 		})
 		opts.SetEvalMetadataFn(func(oi *ObjectInfo, err error) (ReplicateDecision, error) {
 			if err == nil && oss[index] != nil {
@@ -635,11 +647,17 @@ func (api objectAPIHandlers) DeleteMultipleObjectsHandler(w http.ResponseWriter,
 		// DeleteObject merges protection across pools before evaluating these
 		// callbacks and holds the same lock as retention and legal-hold writes.
 		oi, err := objectAPI.DeleteObject(ctx, bucket, object.ObjectName, opts)
-		dObjects[i] = DeletedObject{
+		delObj := DeletedObject{
 			ObjectName:       object.ObjectName,
 			VersionID:        object.VersionID,
 			ReplicationState: oi.ReplicationState(),
 		}
+		if object.VersionID == "" && oi.DeleteMarker {
+			delObj.DeleteMarker = true
+			delObj.DeleteMarkerVersionID = oi.VersionID
+			delObj.DeleteMarkerMTime = DeleteMarkerMTime{oi.ModTime}
+		}
+		dObjects[i] = delObj
 		errs[i] = err
 	}
 	if len(bulk) > 0 {
@@ -663,7 +681,7 @@ func (api objectAPIHandlers) DeleteMultipleObjectsHandler(w http.ResponseWriter,
 		// under the mutation lock, and a missing version has no stored identity.
 		dindex := objectsToDelete[deleteList[i]]
 		if errs[i] == nil || isErrObjectNotFound(errs[i]) || isErrVersionNotFound(errs[i]) {
-			if replicateDeletes && (!hasLockEnabled || deleteList[i].VersionID == "") {
+			if replicateDeletes && deleteList[i].VersionID == "" && !lockedNullDelete(deleteList[i]) {
 				dObjects[i].ReplicationState = deleteList[i].ReplicationState()
 			}
 			deleteResults[dindex].delInfo = dObjects[i]

cmd/bucket-listobjects-handlers.go

@@ -90,8 +90,14 @@ func (api objectAPIHandlers) listObjectVersionsHandler(w http.ResponseWriter, r
 	}
 	var checkObjMeta metaCheckFn
 	if metadata {
-		checkObjMeta = func(name string, action policy.Action) (s3Err APIErrorCode) {
-			return checkRequestAuthType(ctx, r, action, bucket, name)
+		checkObjMeta = func(obj ObjectInfo, action policy.Action) (s3Err APIErrorCode) {
+			vid := obj.VersionID
+			if vid == "" {
+				vid = nullVersionID
+			}
+			return withScopedReqObject(ctx, bucket, obj.Name, vid, func() APIErrorCode {
+				return authorizeVersionedRequestWithExistingTags(ctx, r, action, vid, obj.UserTags)
+			})
 		}
 	}
 	urlValues := r.Form
@@ -176,8 +182,10 @@ func (api objectAPIHandlers) listObjectsV2Handler(ctx context.Context, w http.Re
 
 	var checkObjMeta metaCheckFn
 	if metadata {
-		checkObjMeta = func(name string, action policy.Action) (s3Err APIErrorCode) {
-			return checkRequestAuthType(ctx, r, action, bucket, name)
+		checkObjMeta = func(obj ObjectInfo, action policy.Action) (s3Err APIErrorCode) {
+			return withScopedReqObject(ctx, bucket, obj.Name, "", func() APIErrorCode {
+				return authorizeVersionedRequestWithExistingTags(ctx, r, action, "", obj.UserTags)
+			})
 		}
 	}
 	urlValues := r.Form
@@ -202,7 +210,7 @@ func (api objectAPIHandlers) listObjectsV2Handler(ctx context.Context, w http.Re
 
 	if r.Header.Get(xMinIOExtract) == "true" && strings.Contains(prefix, archivePattern) {
 		// Initiate a list objects operation inside a zip file based in the input params
-		listObjectsV2Info, err = listObjectsV2InArchive(ctx, objectAPI, bucket, prefix, token, delimiter, maxKeys, startAfter, r.Header)
+		listObjectsV2Info, err = listObjectsV2InArchive(ctx, objectAPI, bucket, prefix, token, delimiter, maxKeys, startAfter, r)
 	} else {
 		// Initiate a list objects operation based on the input params.
 		// On success would return back ListObjectsInfo object to be

cmd/bucket-metadata-cache-security_test.go

@@ -0,0 +1,125 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"context"
+	"encoding/xml"
+	"net/http"
+	"net/http/httptest"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/auth"
+)
+
+type metadataCacheLoadBarrier struct {
+	ObjectLayer
+	key          string
+	read, resume chan struct{}
+	once         sync.Once
+}
+
+func (b *metadataCacheLoadBarrier) GetObjectNInfo(ctx context.Context, bucket, key string, rs *HTTPRangeSpec, h http.Header, opts ObjectOptions) (*GetObjectReader, error) {
+	r, err := b.ObjectLayer.GetObjectNInfo(ctx, bucket, key, rs, h, opts)
+	if bucket == minioMetaBucket && key == b.key {
+		b.once.Do(func() { close(b.read); <-b.resume })
+	}
+	return r, err
+}
+
+func TestBucketMetadataLoadPreservesConcurrentPublication(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t,
+		objAPITest: func(obj ObjectLayer, backend, bucket string, _ http.Handler, _ auth.Credentials, t *testing.T) {
+			// Disk has the old unlocked config; a concurrent publication enables
+			// lock and versioning after the cache miss has started loading it.
+			enableBucketObjectLock(t, bucket)
+			newer, err := globalBucketMetadataSys.Get(bucket)
+			if err != nil {
+				t.Fatal(err)
+			}
+			globalBucketMetadataSys.Remove(bucket)
+			barrier := &metadataCacheLoadBarrier{ObjectLayer: obj, key: pathJoin(bucketMetaPrefix, bucket, bucketMetadataFile), read: make(chan struct{}), resume: make(chan struct{})}
+			previous := newObjectLayerFn()
+			setObjectLayer(barrier)
+			defer setObjectLayer(previous)
+			release := sync.OnceFunc(func() { close(barrier.resume) })
+			defer release()
+			type result struct {
+				meta     BucketMetadata
+				reloaded bool
+				err      error
+			}
+			done := make(chan result, 1)
+			go func() {
+				meta, reloaded, err := globalBucketMetadataSys.GetConfig(t.Context(), bucket)
+				done <- result{meta, reloaded, err}
+			}()
+			select {
+			case <-barrier.read:
+			case <-time.After(10 * time.Second):
+				t.Fatal("metadata load did not reach disk")
+			}
+			globalBucketMetadataSys.Set(bucket, newer)
+			release()
+			select {
+			case got := <-done:
+				if got.err != nil || got.reloaded || got.meta.objectLockConfig == nil || got.meta.objectLockConfig.ObjectLockEnabled != "Enabled" {
+					t.Fatalf("%s: stale load replaced the publication: %+v", backend, got)
+				}
+			case <-time.After(10 * time.Second):
+				t.Fatal("metadata load did not finish")
+			}
+			cached, err := globalBucketMetadataSys.Get(bucket)
+			if err != nil || cached.objectLockConfig == nil || cached.objectLockConfig.ObjectLockEnabled != "Enabled" {
+				t.Fatalf("cached lock lost: %+v %v", cached, err)
+			}
+		},
+	})
+}
+
+func TestBulkDeleteVersionLockWithStaleBucketCache(t *testing.T) {
+	for _, pools := range []int{1, 2} {
+		z, _ := bulkDeletePools(t, pools)
+		bucket, router, err := initAPIHandlerTest(t.Context(), z, nil, MakeBucketOptions{LockEnabled: true})
+		if err != nil {
+			t.Fatal(err)
+		}
+		for _, protection := range batchLockKinds {
+			oi := batchPutVersion(t, z, bucket, protection, batchLockMeta(protection))
+			saved, err := globalBucketMetadataSys.Get(bucket)
+			if err != nil {
+				t.Fatal(err)
+			}
+			globalBucketMetadataSys.Set(bucket, newBucketMetadata(bucket))
+			rec := httptest.NewRecorder()
+			router.ServeHTTP(rec, bulkDeleteLockRequest(t, bucket, protection, oi.VersionID))
+			globalBucketMetadataSys.Set(bucket, saved)
+			var response DeleteObjectsResponse
+			if err := xml.Unmarshal(rec.Body.Bytes(), &response); err != nil {
+				t.Fatal(err)
+			}
+			if rec.Code != http.StatusOK || len(response.Errors) != 1 || len(response.DeletedObjects) != 0 || !batchVersionExists(t, z, bucket, protection, oi.VersionID) {
+				t.Fatalf("pools=%d %s: stale bucket cache bypassed version lock: %s", pools, protection, rec.Body.String())
+			}
+		}
+	}
+}

cmd/bucket-metadata-replication.go

@@ -182,8 +182,13 @@ func bucketConfigPayload(bucket, file string, data []byte, lockEnabled bool) ([]
 	key := data
 	switch file {
 	case bucketPolicyConfig:
+		// Replication uses explicit null as a tombstone; ordinary policy PUTs
+		// validate their JSON before entering this metadata path.
+		if bytes.Equal(bytes.TrimSpace(data), []byte("null")) {
+			return nil, nil, nil
+		}
 		var cfg *policy.BucketPolicy
-		cfg, err = policy.ParseBucketPolicyConfig(bytes.NewReader(data), bucket)
+		cfg, err = parseBucketPolicyStrictBytes(data, bucket)
 		if err == nil {
 			if cfg.IsEmpty() {
 				return nil, nil, nil

cmd/bucket-metadata-sys.go

@@ -697,7 +697,7 @@ func (sys *BucketMetadataSys) GetConfig(ctx context.Context, bucket string) (met
 	}
 
 	val, err, _ := sys.group.Do(bucket, func() (val any, err error) {
-		meta, err = loadBucketMetadata(ctx, objAPI, bucket)
+		meta, err := loadBucketMetadata(ctx, objAPI, bucket)
 		if err != nil {
 			if !sys.Initialized() {
 				// bucket metadata not yet initialized
@@ -707,13 +707,18 @@ func (sys *BucketMetadataSys) GetConfig(ctx context.Context, bucket string) (met
 		return meta, err
 	})
 	meta, _ = val.(BucketMetadata)
+	sys.Lock()
+	defer sys.Unlock()
+	// A writer may have published a newer configuration while the disk read
+	// was in flight. Never replace that publication with the older load.
+	if current, ok := sys.metadataMap[bucket]; ok {
+		return current, false, nil
+	}
 	if err != nil {
 		return meta, false, err
 	}
-	sys.Lock()
 	sys.metadataMap[bucket] = meta
 	sys.clearLoadFailure(bucket)
-	sys.Unlock()
 
 	return meta, true, nil
 }

cmd/bucket-object-lock.go

@@ -28,11 +28,27 @@ import (
 	"github.com/minio/minio/internal/amztime"
 	"github.com/minio/minio/internal/auth"
 	objectlock "github.com/minio/minio/internal/bucket/object/lock"
+	"github.com/minio/minio/internal/bucket/versioning"
 	xhttp "github.com/minio/minio/internal/http"
 	"github.com/minio/minio/internal/logger"
 	"github.com/pgsty/silo-pkg/v3/policy"
 )
 
+// checkBucketDeleteMetadata loads bucket versioning and Object Lock configs
+// fail-closed so delete handlers never fall back to unversioned/unlocked
+// defaults when bucket metadata cannot be read.
+func checkBucketDeleteMetadata(bucketName string) (*versioning.Versioning, objectlock.Retention, error) {
+	vc, err := globalBucketVersioningSys.Get(bucketName)
+	if err != nil {
+		return nil, objectlock.Retention{}, err
+	}
+	rcfg, err := globalBucketObjectLockSys.Get(bucketName)
+	if err != nil {
+		return nil, objectlock.Retention{}, err
+	}
+	return vc, rcfg, nil
+}
+
 // BucketObjectLockSys - map of bucket and retention configuration.
 type BucketObjectLockSys struct{}
 
@@ -354,6 +370,8 @@ func checkPutObjectLockAllowed(ctx context.Context, rq *http.Request, bucket, ob
 	var legalHold objectlock.ObjectLegalHold
 
 	retentionRequested := objectlock.IsObjectLockRetentionRequested(rq.Header)
+	// A timestamp without a value is a replicated retention removal.
+	retentionRequested = retentionRequested || replicaTrusted && rq.Header.Get(xhttp.MinIOSourceObjectRetentionTimestamp) != ""
 	legalHoldRequested := objectlock.IsObjectLockLegalHoldRequested(rq.Header)
 
 	retentionCfg, err := globalBucketObjectLockSys.Get(bucket)
@@ -472,6 +490,103 @@ func storedObjectLockState(metadata map[string]string) objectLockState {
 	}
 }
 
+// reducePoolLockState selects each field independently using a total order,
+// so neither pool enumeration nor the starting copy can change the result.
+// Active COMPLIANCE takes precedence over revisions; among those copies the
+// longest retention wins. Only expired COMPLIANCE may lose to a removal.
+func reducePoolLockState(copies []PoolObjInfo, readState func(map[string]string) objectLockState) objectLockState {
+	var now time.Time
+	clockRead := false
+	state := readState(copies[0].ObjInfo.UserDefined)
+	for _, copy := range copies[1:] {
+		next := readState(copy.ObjInfo.UserDefined)
+		if !clockRead && (state.mode == string(objectlock.RetCompliance) || next.mode == string(objectlock.RetCompliance)) {
+			var err error
+			now, err = objectlock.UTCNowNTP()
+			if err != nil {
+				now = time.Time{} // An unavailable clock cannot prove retention expired.
+			}
+			clockRead = true
+		}
+		if comparePoolRetention(next, state, now) > 0 {
+			state.mode, state.retainUntil, state.retentionTimestamp = next.mode, next.retainUntil, next.retentionTimestamp
+		}
+		order := compareLockRevision(next.legalHoldTimestamp, state.legalHoldTimestamp)
+		// Equal or unordered conflicting holds resolve to ON, then OFF, then
+		// absence. A strictly newer valid OFF still releases a prior hold.
+		if order == 0 {
+			order = strings.Compare(next.legalHold, state.legalHold)
+		}
+		if order == 0 {
+			order = strings.Compare(next.legalHoldTimestamp, state.legalHoldTimestamp)
+		}
+		if order > 0 {
+			state.legalHold, state.legalHoldTimestamp = next.legalHold, next.legalHoldTimestamp
+		}
+	}
+	return state
+}
+
+func compareLockRevision(a, b string) int {
+	ta, aok := lockRevisionTime(a)
+	tb, bok := lockRevisionTime(b)
+	if aok != bok {
+		if aok {
+			return 1
+		}
+		return -1
+	}
+	if !aok {
+		return 0
+	}
+	return ta.Compare(tb)
+}
+
+func comparePoolRetention(a, b objectLockState, now time.Time) int {
+	au, ae := time.Parse(time.RFC3339Nano, a.retainUntil)
+	bu, be := time.Parse(time.RFC3339Nano, b.retainUntil)
+	ap := a.mode == string(objectlock.RetCompliance) && (ae != nil || now.IsZero() || au.After(now))
+	bp := b.mode == string(objectlock.RetCompliance) && (be != nil || now.IsZero() || bu.After(now))
+	if ap != bp {
+		if ap {
+			return 1
+		}
+		return -1
+	}
+	if ap { // An unreadable COMPLIANCE deadline cannot be shortened either.
+		if (ae != nil) != (be != nil) {
+			if ae != nil {
+				return 1
+			}
+			return -1
+		}
+		if ae == nil && au.Compare(bu) != 0 {
+			return au.Compare(bu)
+		}
+	}
+	if order := compareLockRevision(a.retentionTimestamp, b.retentionTimestamp); order != 0 {
+		return order
+	}
+	// Ties and legacy unordered metadata must also have a stable winner.
+	// A retained value takes precedence over an unordered absence.
+	if order := strings.Compare(a.mode, b.mode); order != 0 {
+		return order
+	}
+	if (ae != nil) != (be != nil) {
+		if ae != nil {
+			return 1
+		}
+		return -1
+	}
+	if ae == nil && be == nil && au.Compare(bu) != 0 {
+		return au.Compare(bu)
+	}
+	if order := strings.Compare(a.retainUntil, b.retainUntil); order != 0 {
+		return order
+	}
+	return strings.Compare(a.retentionTimestamp, b.retentionTimestamp)
+}
+
 // olderThan reports whether a stored replication timestamp is missing,
 // unreadable, or earlier than the source timestamp, in which case the
 // replica update wins. A zero source timestamp never wins.
@@ -491,6 +606,25 @@ func (s objectLockState) legalHoldIsOlderThan(src time.Time) bool {
 	return olderThan(s.legalHoldTimestamp, src)
 }
 
+// A peer's ordering timestamp cannot override an unexpired COMPLIANCE lock.
+// Otherwise it could first remove retention with a same-content retransmit,
+// then replace the now-unprotected version in a second request.
+func (s objectLockState) complianceWouldWeaken(incoming objectLockState) bool {
+	if s.mode != string(objectlock.RetCompliance) {
+		return false
+	}
+	until, err := time.Parse(time.RFC3339Nano, s.retainUntil)
+	if err != nil {
+		return true
+	}
+	now, err := objectlock.UTCNowNTP()
+	if err == nil && !until.After(now) {
+		return false
+	}
+	nextUntil, nextErr := time.Parse(time.RFC3339Nano, incoming.retainUntil)
+	return incoming.mode != string(objectlock.RetCompliance) || nextErr != nil || nextUntil.Before(until)
+}
+
 // restoreRetention and restoreLegalHold put the stored state back into
 // metadata that was rebuilt from a request whose update was not applied.
 func (s objectLockState) restoreRetention(metadata map[string]string) {
@@ -524,14 +658,20 @@ func (s objectLockState) restoreLegalHold(metadata map[string]string) {
 // (an older incoming value must not win over a newer stored one just because the
 // read timed out).
 func replicaStoredLock(ctx context.Context, getObjectInfo GetObjectInfoFn, bucket, object, versionID string) (objectLockState, error) {
-	oi, err := getObjectInfo(ctx, bucket, object, ObjectOptions{VersionID: versionID})
+	oi, err := replicaStoredObjectInfo(ctx, getObjectInfo, bucket, object, versionID)
+	return storedObjectLockState(oi.UserDefined), err
+}
+
+// The same destination lookup supplies both Object Lock and tag revisions.
+func replicaStoredObjectInfo(ctx context.Context, getObjectInfo GetObjectInfoFn, bucket, object, versionID string) (ObjectInfo, error) {
+	oi, err := getObjectInfo(ctx, bucket, object, ObjectOptions{VersionID: versionID, ReplicationRequest: true})
 	switch {
 	case err == nil:
-		return storedObjectLockState(oi.UserDefined), nil
+		return oi, nil
 	case isErrObjectNotFound(err) || isErrVersionNotFound(err):
-		return objectLockState{}, nil
+		return ObjectInfo{}, nil
 	default:
-		return objectLockState{}, err
+		return ObjectInfo{}, err
 	}
 }
 
@@ -610,7 +750,7 @@ func reconcileStoredObjectLock(metadata map[string]string, stored objectLockStat
 	incoming := storedObjectLockState(metadata)
 
 	incomingRetentionTS, _ := time.Parse(time.RFC3339Nano, incoming.retentionTimestamp)
-	if !stored.retentionIsOlderThan(incomingRetentionTS) {
+	if !stored.retentionIsOlderThan(incomingRetentionTS) || stored.complianceWouldWeaken(incoming) {
 		// The stored retention is at least as new as the incoming one (or the
 		// incoming update is unordered): drop the incoming value and put the stored
 		// state back, which may itself be a removal (value keys absent, timestamp

cmd/bucket-policy-handlers.go

@@ -18,7 +18,6 @@
 package cmd
 
 import (
-	"bytes"
 	"io"
 	"net/http"
 
@@ -83,7 +82,7 @@ func (api objectAPIHandlers) PutBucketPolicyHandler(w http.ResponseWriter, r *ht
 		return
 	}
 
-	bucketPolicy, err := policy.ParseBucketPolicyConfig(bytes.NewReader(bucketPolicyBytes), bucket)
+	bucketPolicy, err := parseBucketPolicyStrictBytes(bucketPolicyBytes, bucket)
 	if err != nil {
 		writeErrorResponse(ctx, w, APIError{
 			Code:           "MalformedPolicy",

cmd/bucket-policy.go

@@ -213,16 +213,27 @@ func getConditionValuesWithTags(r *http.Request, lc string, cred auth.Credential
 	switch authType {
 	case authTypeSignedV2, authTypePresignedV2:
 		signatureVersion = signV2Algorithm
-	case authTypeSigned, authTypePresigned, authTypeStreamingSigned, authTypePostPolicy:
+	case authTypeSigned, authTypePresigned, authTypeStreamingSigned,
+		authTypeStreamingSignedTrailer, authTypePostPolicy:
 		signatureVersion = signV4Algorithm
+	case authTypeStreamingUnsignedTrailer:
+		// This form is also valid for a genuinely anonymous request. Only
+		// expose SigV4 condition values when header authentication is present.
+		if r.Header.Get(xhttp.Authorization) != "" {
+			signatureVersion = signV4Algorithm
+		}
 	}
 
 	var authtype string
 	switch authType {
 	case authTypePresignedV2, authTypePresigned:
 		authtype = "REST-QUERY-STRING"
-	case authTypeSignedV2, authTypeSigned, authTypeStreamingSigned:
+	case authTypeSignedV2, authTypeSigned, authTypeStreamingSigned, authTypeStreamingSignedTrailer:
 		authtype = "REST-HEADER"
+	case authTypeStreamingUnsignedTrailer:
+		if r.Header.Get(xhttp.Authorization) != "" {
+			authtype = "REST-HEADER"
+		}
 	case authTypePostPolicy:
 		authtype = "POST"
 	}

cmd/bucket-replication.go

@@ -2673,6 +2673,7 @@ func proxyHeadToRepTarget(ctx context.Context, bucket, object string, rs *HTTPRa
 			},
 			PartNumber: opts.PartNumber,
 		}
+		gopts.Set(xhttp.AmzTagDirective, accessDirective)
 		if rs != nil {
 			h, err := rs.ToHeader()
 			if err != nil {
@@ -2710,6 +2711,9 @@ func proxyHeadToRepTarget(ctx context.Context, bucket, object string, rs *HTTPRa
 		}
 		oi.UserDefined = make(map[string]string, len(objInfo.Metadata))
 		for k, v := range objInfo.Metadata {
+			if equals(k, xhttp.AmzTagCount, xhttp.AmzObjectTagging) {
+				continue
+			}
 			oi.UserDefined[k] = v[0]
 		}
 		ce, ok := oi.UserDefined[xhttp.ContentEncoding]
@@ -2773,127 +2777,135 @@ func scheduleReplication(ctx context.Context, oi ObjectInfo, o ObjectLayer, dsc
 	}
 }
 
-// proxyTaggingToRepTarget proxies tagging requests to remote targets for
-// active-active replicated setups
-func proxyTaggingToRepTarget(ctx context.Context, bucket, object string, tags *tags.Tags, opts ObjectOptions, proxyTargets *madmin.BucketTargets) (proxy proxyResult) {
-	// this option is set when active-active replication is in place between site A -> B,
-	// and request hits site B that does not have the object yet.
-	if opts.ProxyRequest || (opts.ProxyHeaderSet && !opts.ProxyRequest) { // true only when site B sets MinIOSourceProxyRequest header
-		return proxy
+// taggingProxyTarget keeps the exact client and tags that were authorized.
+// A second discovery must not introduce an unauthorized destination.
+type taggingProxyTarget struct {
+	client *TargetClient
+	tags   *tags.Tags
+}
+
+// readTaggingProxyTargets authorizes all present replicas before returning any
+// tags or allowing any mutation. Missing replicas may simply lag replication;
+// unreadable replicas must still fail closed.
+func readTaggingProxyTargets(ctx context.Context, bucket, object string, opts ObjectOptions, proxyTargets *madmin.BucketTargets, authorize func(string, error) APIErrorCode) ([]taggingProxyTarget, proxyResult, APIErrorCode) {
+	var targets []taggingProxyTarget
+	for _, target := range proxyTargets.Targets {
+		tgt := globalBucketTargetSys.GetRemoteTargetClient(bucket, target.Arn)
+		if tgt == nil || globalBucketTargetSys.isOffline(tgt.EndpointURL()) || tgt.disableProxy {
+			continue
+		}
+		targets = append(targets, taggingProxyTarget{client: tgt})
 	}
+	if len(targets) == 0 {
+		err := RemoteTargetConnectionErr{Bucket: bucket, Err: errors.New("no available remote replication target")}
+		return nil, proxyResult{Err: err}, authorize("", err)
+	}
+
 	var wg sync.WaitGroup
-	errs := make([]error, len(proxyTargets.Targets))
-	for idx, t := range proxyTargets.Targets {
-		tgt := globalBucketTargetSys.GetRemoteTargetClient(bucket, t.Arn)
-		if tgt == nil || globalBucketTargetSys.isOffline(tgt.EndpointURL()) {
-			continue
-		}
-		// if proxying explicitly disabled on remote target
-		if tgt.disableProxy {
-			continue
-		}
-		idx := idx
-		wg.Add(1)
-		go func(idx int, tgt *TargetClient) {
-			defer wg.Done()
-			var err error
-			if tags != nil {
-				popts := minio.PutObjectTaggingOptions{
-					VersionID: opts.VersionID,
-					Internal: minio.AdvancedObjectTaggingOptions{
-						ReplicationProxyRequest: "true",
-					},
-				}
-				err = tgt.PutObjectTagging(ctx, tgt.Bucket, object, tags, popts)
-			} else {
-				dopts := minio.RemoveObjectTaggingOptions{
-					VersionID: opts.VersionID,
-					Internal: minio.AdvancedObjectTaggingOptions{
-						ReplicationProxyRequest: "true",
-					},
-				}
-				err = tgt.RemoveObjectTagging(ctx, tgt.Bucket, object, dopts)
-			}
-			if err != nil {
-				errs[idx] = err
-			}
-		}(idx, tgt)
+	errs := make([]error, len(targets))
+	for i := range targets {
+		wg.Go(func() {
+			tgt := &targets[i]
+			tgt.tags, errs[i] = tgt.client.GetObjectTagging(ctx, tgt.client.Bucket, object, minio.GetObjectTaggingOptions{
+				VersionID: opts.VersionID,
+				Internal:  minio.AdvancedObjectTaggingOptions{ReplicationProxyRequest: "true"},
+			})
+		})
 	}
 	wg.Wait()
 
-	var (
-		terr        error
-		taggedCount int
-	)
+	var firstNotFound, readErr error
 	for _, err := range errs {
-		if err == nil {
-			taggedCount++
+		switch {
+		case err == nil:
+		case isRemoteTaggingNotFound(err):
+			if firstNotFound == nil {
+				firstNotFound = err
+			}
+		default:
+			if code := authorize("", err); code != ErrNone {
+				return nil, proxyResult{}, code
+			}
+			if readErr == nil {
+				readErr = err
+			}
+		}
+	}
+	present := make([]taggingProxyTarget, 0, len(targets))
+	for i, tgt := range targets {
+		if errs[i] != nil {
 			continue
 		}
-		if err != nil {
-			terr = err
+		if tgt.tags == nil {
+			tgt.tags, _ = tags.MapToObjectTags(nil)
 		}
+		if code := authorize(tgt.tags.String(), nil); code != ErrNone {
+			return nil, proxyResult{}, code
+		}
+		present = append(present, tgt)
 	}
-	// don't return error if at least one target was tagged successfully
-	if taggedCount == 0 && terr != nil {
-		proxy.Err = terr
+	if readErr != nil {
+		return nil, proxyResult{Err: readErr}, ErrNone
 	}
-	return proxy
+	if len(present) == 0 {
+		// With no object anywhere, authorize the empty tag set once before
+		// disclosing its absence. No write RPC can help a missing replica.
+		return nil, proxyResult{Err: firstNotFound}, authorize("", firstNotFound)
+	}
+	return present, proxyResult{}, ErrNone
+}
+
+// proxyTaggingToRepTarget proxies tagging requests to remote targets for
+// active-active replicated setups.
+func proxyTaggingToRepTarget(ctx context.Context, bucket, object string, tags *tags.Tags, opts ObjectOptions, proxyTargets *madmin.BucketTargets, authorize func(string, error) APIErrorCode) (proxy proxyResult, authErr APIErrorCode) {
+	if opts.ProxyRequest || (opts.ProxyHeaderSet && !opts.ProxyRequest) {
+		return proxy, ErrNone
+	}
+	targets, proxy, authErr := readTaggingProxyTargets(ctx, bucket, object, opts, proxyTargets, authorize)
+	if authErr != ErrNone || proxy.Err != nil {
+		return proxy, authErr
+	}
+
+	var wg sync.WaitGroup
+	writeErrs := make([]error, len(targets))
+	for i, target := range targets {
+		wg.Go(func() {
+			tgt := target.client
+			if tags != nil {
+				writeErrs[i] = tgt.PutObjectTagging(ctx, tgt.Bucket, object, tags, minio.PutObjectTaggingOptions{
+					VersionID: opts.VersionID,
+					Internal:  minio.AdvancedObjectTaggingOptions{ReplicationProxyRequest: "true"},
+				})
+			} else {
+				writeErrs[i] = tgt.RemoveObjectTagging(ctx, tgt.Bucket, object, minio.RemoveObjectTaggingOptions{
+					VersionID: opts.VersionID,
+					Internal:  minio.AdvancedObjectTaggingOptions{ReplicationProxyRequest: "true"},
+				})
+			}
+		})
+	}
+	wg.Wait()
+	var lastErr error
+	for _, err := range writeErrs {
+		if err == nil {
+			return proxy, ErrNone
+		}
+		lastErr = err
+	}
+	return proxyResult{Err: lastErr}, ErrNone
 }
 
 // proxyGetTaggingToRepTarget proxies get tagging requests to remote targets for
-// active-active replicated setups
-func proxyGetTaggingToRepTarget(ctx context.Context, bucket, object string, opts ObjectOptions, proxyTargets *madmin.BucketTargets) (tgs *tags.Tags, proxy proxyResult) {
-	// this option is set when active-active replication is in place between site A -> B,
-	// and request hits site B that does not have the object yet.
-	if opts.ProxyRequest || (opts.ProxyHeaderSet && !opts.ProxyRequest) { // true only when site B sets MinIOSourceProxyRequest header
-		return nil, proxy
+// active-active replicated setups.
+func proxyGetTaggingToRepTarget(ctx context.Context, bucket, object string, opts ObjectOptions, proxyTargets *madmin.BucketTargets, authorize func(string, error) APIErrorCode) (tgs *tags.Tags, proxy proxyResult, authErr APIErrorCode) {
+	if opts.ProxyRequest || (opts.ProxyHeaderSet && !opts.ProxyRequest) {
+		return nil, proxy, ErrNone
 	}
-	var wg sync.WaitGroup
-	errs := make([]error, len(proxyTargets.Targets))
-	tagSlc := make([]map[string]string, len(proxyTargets.Targets))
-	for idx, t := range proxyTargets.Targets {
-		tgt := globalBucketTargetSys.GetRemoteTargetClient(bucket, t.Arn)
-		if tgt == nil || globalBucketTargetSys.isOffline(tgt.EndpointURL()) {
-			continue
-		}
-		// if proxying explicitly disabled on remote target
-		if tgt.disableProxy {
-			continue
-		}
-		idx := idx
-		wg.Add(1)
-		go func(idx int, tgt *TargetClient) {
-			defer wg.Done()
-			var err error
-			gopts := minio.GetObjectTaggingOptions{
-				VersionID: opts.VersionID,
-				Internal: minio.AdvancedObjectTaggingOptions{
-					ReplicationProxyRequest: "true",
-				},
-			}
-			tgs, err = tgt.GetObjectTagging(ctx, tgt.Bucket, object, gopts)
-			if err != nil {
-				errs[idx] = err
-			} else {
-				tagSlc[idx] = tgs.ToMap()
-			}
-		}(idx, tgt)
+	targets, proxy, authErr := readTaggingProxyTargets(ctx, bucket, object, opts, proxyTargets, authorize)
+	if authErr != ErrNone || proxy.Err != nil {
+		return nil, proxy, authErr
 	}
-	wg.Wait()
-	for idx, err := range errs {
-		errCode := minio.ToErrorResponse(err).Code
-		if err != nil && errCode != "NoSuchKey" && errCode != "NoSuchVersion" {
-			return nil, proxyResult{Err: err}
-		}
-		if err == nil {
-			tgs, _ = tags.MapToObjectTags(tagSlc[idx])
-		}
-	}
-	if len(errs) == 1 {
-		proxy.Err = errs[0]
-	}
-	return tgs, proxy
+	return targets[0].tags, proxy, ErrNone
 }
 
 func scheduleReplicationDelete(ctx context.Context, dv DeletedObjectReplicationInfo, o ObjectLayer) {

cmd/bulk-delete-invalid-name_test.go

@@ -0,0 +1,156 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"bytes"
+	"encoding/xml"
+	"net/http"
+	"net/http/httptest"
+	"slices"
+	"testing"
+
+	"github.com/minio/minio/internal/auth"
+)
+
+// A bulk delete joins each name to the request bucket on the drives, so a name
+// with a ".." segment names a path in another bucket or in the meta bucket.
+// Such a name is the error of its own entry and reaches no drive, and the
+// other entries of the request are deleted as usual. This holds for the one
+// bulk lock of a single node, for a pool that locks per set, and for more than
+// one pool.
+func TestPoolsBulkDeleteInvalidNames(t *testing.T) {
+	for _, topology := range []struct {
+		name string
+		new  func(t *testing.T) (*erasureServerPools, string)
+	}{
+		{"single node", func(t *testing.T) (*erasureServerPools, string) { return bulkDeletePools(t, 1) }},
+		{"set locks", func(t *testing.T) (*erasureServerPools, string) { return ldPool(t, ldLocal) }},
+		{"two pools", func(t *testing.T) (*erasureServerPools, string) { return bulkDeletePools(t, 2) }},
+	} {
+		t.Run(topology.name, func(t *testing.T) {
+			z, bucket := topology.new(t)
+			ctx := t.Context()
+			other := "bulk-delete-other"
+			if err := z.MakeBucket(ctx, other, MakeBucketOptions{VersioningEnabled: true}); err != nil {
+				t.Fatal(err)
+			}
+			old := batchPutVersion(t, z, other, "kept", nil)
+			latest := batchPutVersion(t, z, other, "kept", nil)
+			batchPutVersion(t, z, other, "visible", nil)
+			metaKey := pathJoin(bucketMetaPrefix, other, bucketMetadataFile)
+			if !batchVersionExists(t, z, minioMetaBucket, metaKey, "") {
+				t.Fatal("the bucket metadata is not an object of the meta bucket")
+			}
+			for _, key := range []string{"own", "dir/"} {
+				if _, err := z.PutObject(ctx, bucket, key, mustGetPutObjReader(t, bytes.NewReader(nil), 0, "", ""), ObjectOptions{}); err != nil {
+					t.Fatal(err)
+				}
+			}
+
+			names := []ObjectToDelete{
+				{ObjectV: ObjectV{ObjectName: "../" + other + "/kept", VersionID: old.VersionID}}, // purge in another bucket
+				{ObjectV: ObjectV{ObjectName: "own"}},
+				{ObjectV: ObjectV{ObjectName: "a/../../" + other + "/visible"}},         // marker in another bucket
+				{ObjectV: ObjectV{ObjectName: "../" + minioMetaBucket + "/" + metaKey}}, // marker on bucket metadata
+				{ObjectV: ObjectV{ObjectName: "dir/"}},
+				{ObjectV: ObjectV{ObjectName: ""}},
+			}
+			invalid := map[int]bool{0: true, 2: true, 3: true, 5: true}
+			// Without a version ID these options ask for a delete marker, the
+			// one write a bulk delete makes.
+			deleted, errs := z.DeleteObjects(ctx, bucket, slices.Clone(names), ObjectOptions{Versioned: true})
+			for i, name := range names {
+				_, rejected := errs[i].(ObjectNameInvalid)
+				if rejected != invalid[i] || !invalid[i] && errs[i] != nil {
+					t.Errorf("%d %q: error = %v, rejected as invalid = %v, want %v", i, name.ObjectName, errs[i], rejected, invalid[i])
+				}
+				if deleted[i].ObjectName != name.ObjectName || deleted[i].found == invalid[i] {
+					t.Errorf("%d %q: result = %+v", i, name.ObjectName, deleted[i])
+				}
+			}
+
+			for _, version := range []string{old.VersionID, latest.VersionID} {
+				if !batchVersionExists(t, z, other, "kept", version) {
+					t.Errorf("version %q of the object in the other bucket was removed", version)
+				}
+			}
+			if !batchVersionExists(t, z, other, "visible", "") {
+				t.Error("the object of the other bucket is hidden by a marker")
+			}
+			if !batchVersionExists(t, z, minioMetaBucket, metaKey, "") {
+				t.Error("the metadata of the other bucket is hidden by a marker")
+			}
+			for _, key := range []string{"own", "dir/"} {
+				if batchVersionExists(t, z, bucket, key, "") {
+					t.Errorf("%q of the request bucket was not deleted", key)
+				}
+			}
+		})
+	}
+}
+
+// The names of an S3 DeleteObjects request come from its body, which the path
+// checks of the request URL do not see. A user allowed to delete in one bucket
+// reaches nothing outside it through such a name: a version under COMPLIANCE
+// retention in another bucket stays, and no delete marker lands on that object
+// or on the stored metadata of its bucket.
+func TestBulkDeleteObjectLockNameOutsideBucket(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, endpoints: []string{"DeleteMultipleObjects"},
+		makeBucketOptions: MakeBucketOptions{VersioningEnabled: true},
+		objAPITest: func(obj ObjectLayer, instance, bucket string, router http.Handler, _ auth.Credentials, t *testing.T) {
+			ctx := t.Context()
+			user := newObjectAttributesAuthzUser(t, instance, bucket, `"s3:DeleteObject","s3:DeleteObjectVersion"`)
+			locked := getRandomBucketName()
+			if err := obj.MakeBucket(ctx, locked, MakeBucketOptions{VersioningEnabled: true, LockEnabled: true}); err != nil {
+				t.Fatal(err)
+			}
+			enableBucketObjectLock(t, locked)
+			worm := batchPutVersion(t, obj, locked, "secret", batchLockMeta("COMPLIANCE"))
+			batchPutVersion(t, obj, bucket, "own", nil)
+			metaKey := pathJoin(bucketMetaPrefix, locked, bucketMetadataFile)
+
+			outside := []ObjectToDelete{
+				{ObjectV: ObjectV{ObjectName: "../" + locked + "/secret", VersionID: worm.VersionID}},
+				{ObjectV: ObjectV{ObjectName: "../" + locked + "/secret"}},
+				{ObjectV: ObjectV{ObjectName: "../" + minioMetaBucket + "/" + metaKey}},
+			}
+			body := encodeResponse(DeleteObjectsRequest{Objects: append(slices.Clone(outside), ObjectToDelete{ObjectV: ObjectV{ObjectName: "own"}})})
+			req, err := newTestSignedRequestV4(http.MethodPost, getDeleteMultipleObjectsURL("", bucket), int64(len(body)), bytes.NewReader(body),
+				user.AccessKey, user.SecretKey, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec := httptest.NewRecorder()
+			router.ServeHTTP(rec, req)
+			var resp DeleteObjectsResponse
+			if rec.Code != http.StatusOK || xml.Unmarshal(rec.Body.Bytes(), &resp) != nil {
+				t.Fatalf("%s: status %d: %s", instance, rec.Code, rec.Body.String())
+			}
+
+			if len(resp.DeletedObjects) != 1 || resp.DeletedObjects[0].ObjectName != "own" || len(resp.Errors) != len(outside) {
+				t.Errorf("%s: want the three names outside the bucket refused and \"own\" deleted: %s", instance, rec.Body.String())
+			}
+			for _, e := range resp.Errors {
+				if e.Code != errorCodes[ErrInvalidObjectName].Code {
+					t.Errorf("%s: %q: code %s, want %s", instance, e.Key, e.Code, errorCodes[ErrInvalidObjectName].Code)
+				}
+			}
+			if !batchVersionExists(t, obj, locked, "secret", worm.VersionID) {
+				t.Errorf("%s: the version under COMPLIANCE retention in the other bucket was removed", instance)
+			}
+			if !batchVersionExists(t, obj, locked, "secret", "") {
+				t.Errorf("%s: a delete marker hides the object of the other bucket", instance)
+			}
+			if !batchVersionExists(t, obj, minioMetaBucket, metaKey, "") {
+				t.Errorf("%s: a delete marker hides the stored metadata of the other bucket", instance)
+			}
+			if batchVersionExists(t, obj, bucket, "own", "") {
+				t.Errorf("%s: the object of the request bucket was not deleted", instance)
+			}
+		},
+	})
+}

cmd/encryption-v1.go

@@ -260,6 +260,15 @@ func ParseSSECustomerHeader(header http.Header) (key []byte, err error) {
 // This function rotates old to new key.
 func rotateKey(ctx context.Context, oldKey []byte, newKeyID string, newKey []byte, bucket, object string, metadata map[string]string, cryptoCtx kms.Context) error {
 	kind, _ := crypto.IsEncrypted(metadata)
+	return rotateKeyWithTarget(ctx, oldKey, kind, newKeyID, newKey, bucket, object, metadata, cryptoCtx, len(cryptoCtx) > 0)
+}
+
+func rotateKeyWithTarget(ctx context.Context, oldKey []byte, targetKind crypto.Type, newKeyID string, newKey []byte, bucket, object string, metadata map[string]string, cryptoCtx kms.Context, replaceContext bool) error {
+	kind, _ := crypto.IsEncrypted(metadata)
+	if targetKind == nil {
+		targetKind = kind
+	}
+	var objectKey crypto.ObjectKey
 	switch kind {
 	case crypto.S3:
 		if GlobalKMS == nil {
@@ -269,7 +278,7 @@ func rotateKey(ctx context.Context, oldKey []byte, newKeyID string, newKey []byt
 		if err != nil {
 			return err
 		}
-		oldKey, err := GlobalKMS.Decrypt(ctx, &kms.DecryptRequest{
+		unsealKey, err := GlobalKMS.Decrypt(ctx, &kms.DecryptRequest{
 			Name:           keyID,
 			Ciphertext:     kmsKey,
 			AssociatedData: kms.Context{bucket: path.Join(bucket, object)},
@@ -277,66 +286,30 @@ func rotateKey(ctx context.Context, oldKey []byte, newKeyID string, newKey []byt
 		if err != nil {
 			return err
 		}
-		var objectKey crypto.ObjectKey
-		if err = objectKey.Unseal(oldKey, sealedKey, crypto.S3.String(), bucket, object); err != nil {
+		if err = objectKey.Unseal(unsealKey, sealedKey, crypto.S3.String(), bucket, object); err != nil {
 			return err
 		}
-
-		newKey, err := GlobalKMS.GenerateKey(ctx, &kms.GenerateKeyRequest{
-			Name:           GlobalKMS.DefaultKey,
-			AssociatedData: kms.Context{bucket: path.Join(bucket, object)},
-		})
-		if err != nil {
-			return err
-		}
-		sealedKey = objectKey.Seal(newKey.Plaintext, crypto.GenerateIV(rand.Reader), crypto.S3.String(), bucket, object)
-		crypto.S3.CreateMetadata(metadata, newKey.KeyID, newKey.Ciphertext, sealedKey)
-		return nil
 	case crypto.S3KMS:
 		if GlobalKMS == nil {
 			return errKMSNotConfigured
 		}
-		objectKey, err := crypto.S3KMS.UnsealObjectKey(GlobalKMS, metadata, bucket, object)
+		var err error
+		objectKey, err = crypto.S3KMS.UnsealObjectKey(GlobalKMS, metadata, bucket, object)
 		if err != nil {
 			return err
 		}
-
-		if len(cryptoCtx) == 0 {
+		if targetKind == crypto.S3KMS && !replaceContext && len(cryptoCtx) == 0 {
 			_, _, _, cryptoCtx, err = crypto.S3KMS.ParseMetadata(metadata)
 			if err != nil {
 				return err
 			}
 		}
-
-		// If the context does not contain the bucket key
-		// we must add it for key generation. However,
-		// the context must be stored exactly like the
-		// client provided it. Therefore, we create a copy
-		// of the client provided context and add the bucket
-		// key, if not present.
-		kmsCtx := kms.Context{}
-		maps.Copy(kmsCtx, cryptoCtx)
-		if _, ok := kmsCtx[bucket]; !ok {
-			kmsCtx[bucket] = path.Join(bucket, object)
-		}
-		newKey, err := GlobalKMS.GenerateKey(ctx, &kms.GenerateKeyRequest{
-			Name:           newKeyID,
-			AssociatedData: kmsCtx,
-		})
-		if err != nil {
-			return err
-		}
-
-		sealedKey := objectKey.Seal(newKey.Plaintext, crypto.GenerateIV(rand.Reader), crypto.S3KMS.String(), bucket, object)
-		crypto.S3KMS.CreateMetadata(metadata, newKey.KeyID, newKey.Ciphertext, sealedKey, cryptoCtx)
-		return nil
 	case crypto.SSEC:
 		sealedKey, err := crypto.SSEC.ParseMetadata(metadata)
 		if err != nil {
 			return err
 		}
 
-		var objectKey crypto.ObjectKey
 		if err = objectKey.Unseal(oldKey, sealedKey, crypto.SSEC.String(), bucket, object); err != nil {
 			if subtle.ConstantTimeCompare(oldKey, newKey) == 1 {
 				return errInvalidSSEParameters // AWS returns special error for equal but invalid keys.
@@ -353,6 +326,55 @@ func rotateKey(ctx context.Context, oldKey []byte, newKeyID string, newKey []byt
 	default:
 		return errObjectTampered
 	}
+
+	switch targetKind {
+	case crypto.S3:
+		genKey, err := GlobalKMS.GenerateKey(ctx, &kms.GenerateKeyRequest{
+			Name:           GlobalKMS.DefaultKey,
+			AssociatedData: kms.Context{bucket: path.Join(bucket, object)},
+		})
+		if err != nil {
+			return err
+		}
+		delete(metadata, crypto.MetaSealedKeyKMS)
+		delete(metadata, crypto.MetaKeyID)
+		delete(metadata, crypto.MetaDataEncryptionKey)
+		delete(metadata, crypto.MetaContext)
+		sealedKey := objectKey.Seal(genKey.Plaintext, crypto.GenerateIV(rand.Reader), crypto.S3.String(), bucket, object)
+		crypto.S3.CreateMetadata(metadata, genKey.KeyID, genKey.Ciphertext, sealedKey)
+		return nil
+	case crypto.S3KMS:
+		// If the context does not contain the bucket key
+		// we must add it for key generation. However,
+		// the context must be stored exactly like the
+		// client provided it. Therefore, we create a copy
+		// of the client provided context and add the bucket
+		// key, if not present.
+		kmsCtx := kms.Context{}
+		maps.Copy(kmsCtx, cryptoCtx)
+		if _, ok := kmsCtx[bucket]; !ok {
+			kmsCtx[bucket] = path.Join(bucket, object)
+		}
+		genKey, err := GlobalKMS.GenerateKey(ctx, &kms.GenerateKeyRequest{
+			Name:           newKeyID,
+			AssociatedData: kmsCtx,
+		})
+		if err != nil {
+			if errors.Is(err, kes.ErrKeyNotFound) {
+				return errKMSKeyNotFound
+			}
+			return err
+		}
+		delete(metadata, crypto.MetaSealedKeyS3)
+		delete(metadata, crypto.MetaKeyID)
+		delete(metadata, crypto.MetaDataEncryptionKey)
+		delete(metadata, crypto.MetaContext)
+		sealedKey := objectKey.Seal(genKey.Plaintext, crypto.GenerateIV(rand.Reader), crypto.S3KMS.String(), bucket, object)
+		crypto.S3KMS.CreateMetadata(metadata, genKey.KeyID, genKey.Ciphertext, sealedKey, cryptoCtx)
+		return nil
+	default:
+		return errInvalidEncryptionParameters
+	}
 }
 
 func newEncryptMetadata(ctx context.Context, kind crypto.Type, keyID string, key []byte, bucket, object string, metadata map[string]string, cryptoCtx kms.Context) (crypto.ObjectKey, error) {

cmd/erasure-multipart.go

@@ -1722,6 +1722,9 @@ func (er erasureObjects) CompleteMultipartUpload(ctx context.Context, bucket str
 		}
 	}
 
+	if err := er.checkReplicaContent(ctx, bucket, object, minioMetaMultipartBucket, uploadIDPath, partsMetadata, onlineDisks, opts); err != nil {
+		return oi, toObjectErr(err, bucket, object)
+	}
 	er.cleanupMultipartPath(ctx, paths...) // cleanup all part.N.meta, and skipped part.N's before final rename().
 
 	defer func() {

cmd/erasure-object.go

@@ -133,8 +133,25 @@ func (er erasureObjects) CopyObject(ctx context.Context, srcBucket, srcObject, d
 	}
 
 	if dstOpts.ReplicaLockReconcile {
-		reconcileStoredObjectLock(srcInfo.UserDefined, storedObjectLockState(fi.Metadata))
-		reconcileStoredObjectTags(srcInfo.UserDefined, fi.Metadata[xhttp.AmzObjectTagging], fi.Metadata[ReservedMetadataPrefixLower+TaggingTimestamp])
+		stored := fi.ToObjectInfo(dstBucket, dstObject, dstOpts.Versioned || dstOpts.VersionSuspended)
+		if srcInfo.versionOnly || dstOpts.replicaObjectInfo != nil {
+			// fi describes the source of the new reference, not the version
+			// being replaced. A pooled lookup also preserves protection merged
+			// from another copy, even when this set holds a newer weak revision.
+			getInfo := er.getObjectInfo
+			if dstOpts.replicaObjectInfo != nil {
+				getInfo = dstOpts.replicaObjectInfo
+			}
+			stored, err = replicaStoredObjectInfo(ctx, func(ctx context.Context, bucket, object string, opts ObjectOptions) (ObjectInfo, error) {
+				opts.NoLock = true
+				return getInfo(ctx, bucket, object, opts)
+			}, dstBucket, dstObject, dstOpts.VersionID)
+			if err != nil {
+				return oi, err
+			}
+		}
+		reconcileStoredObjectLock(srcInfo.UserDefined, storedObjectLockState(stored.UserDefined))
+		reconcileStoredObjectTags(srcInfo.UserDefined, stored.UserTags, stored.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp])
 	}
 
 	filterOnlineDisksInplace(fi, metaArr, onlineDisks)
@@ -148,6 +165,17 @@ func (er erasureObjects) CopyObject(ctx context.Context, srcBucket, srcObject, d
 			fi.IsLatest = true // we are creating a new version so this is latest.
 		}
 	}
+	if srcInfo.versionOnly && (dstOpts.ReplicaLockReconcile || dstOpts.ReplicationRequest) && !dstOpts.DataMovement {
+		candidate := slices.Clone(metaArr)
+		for i := range candidate {
+			candidate[i].VersionID = versionID
+			candidate[i].Metadata = srcInfo.UserDefined
+		}
+		readDisks, readMeta := shuffleDisksAndPartsMetadataByIndex(onlineDisks, candidate, fi)
+		if err := er.checkReplicaContent(ctx, dstBucket, dstObject, srcBucket, srcObject, readMeta, readDisks, dstOpts); err != nil {
+			return oi, err
+		}
+	}
 
 	if !dstOpts.ReplicationRequest && !dstOpts.ReplicaLockReconcile && !dstOpts.DataMovement &&
 		(versionID == "" || versionID == nullVersionID) {
@@ -935,11 +963,14 @@ func (er erasureObjects) getObjectFileInfo(ctx context.Context, bucket, object s
 	// to the disks; this value is not accurate because we do
 	// not know the storage class of the object yet
 	minDisks := 0
-	if p := globalStorageClass.GetParityForSC(""); p > -1 {
+	if p := globalStorageClass.GetParityForSC(""); p > -1 && p < er.setDriveCount {
 		minDisks = er.setDriveCount - p
 	} else {
 		minDisks = er.setDriveCount - er.defaultParityCount
 	}
+	if minDisks < 1 {
+		minDisks = 1
+	}
 
 	if minDisks == er.setDriveCount/2 {
 		// when data and parity are same we must atleast
@@ -1722,6 +1753,9 @@ func (er erasureObjects) putObject(ctx context.Context, bucket string, object st
 	}
 
 	// Rename the successfully written temporary object to final location.
+	if err := er.checkReplicaContent(ctx, bucket, object, minioMetaTmpBucket, tempObj, partsMetadata, onlineDisks, opts); err != nil {
+		return ObjectInfo{}, toObjectErr(err, bucket, object)
+	}
 	onlineDisks, versions, oldDataDir, err := renameData(ctx, onlineDisks, minioMetaTmpBucket, tempObj, partsMetadata, bucket, object, writeQuorum)
 	if err != nil {
 		if errors.Is(err, errFileNotFound) {
@@ -2186,7 +2220,7 @@ func (er erasureObjects) DeleteObject(ctx context.Context, bucket, object string
 			// A restored-copy expiry needs fresh metadata to confirm its target
 			// and deadline, a checked expiry to guard its protection; ordinary
 			// unversioned DELETE may still try a blind delete.
-			if opts.Transition.ExpireRestored || checkedExpiry || opts.Versioned || opts.VersionSuspended || countOnlineDisks(storageDisks) < len(storageDisks)/2+1 {
+			if opts.Transition.ExpireRestored || checkedExpiry || opts.Versioned || opts.VersionSuspended || opts.RefuseLockedOverwrite || countOnlineDisks(storageDisks) < len(storageDisks)/2+1 {
 				// Add an MRF heal for next time.
 				er.addPartial(bucket, object, opts.VersionID)
 				return objInfo, InsufficientWriteQuorum{}
@@ -2237,8 +2271,28 @@ func (er erasureObjects) DeleteObject(ctx context.Context, bucket, object string
 		}
 	}
 
+	// When versioning is disabled or suspended for this key, an unaddressed
+	// delete overwrites or removes the null version even if a newer non-null
+	// version is returned as latest by getObjectInfoAndQuorum above.
+	retOI, retErr := goi, gerr
+	if !opts.Versioned && !opts.DeleteMarker && opts.VersionID == "" && (opts.EvalRetentionBypassFn != nil || opts.RefuseLockedOverwrite) {
+		if gerr == nil && goi.VersionID != "" && goi.VersionID != nullVersionID {
+			nullOpts := opts
+			nullOpts.VersionID = nullVersionID
+			retOI, _, retErr = er.getObjectInfoAndQuorum(ctx, bucket, object, nullOpts)
+			if _, ok := retErr.(InsufficientReadQuorum); ok && opts.RefuseLockedOverwrite {
+				er.addPartial(bucket, object, nullVersionID)
+				return objInfo, InsufficientWriteQuorum{}
+			}
+		}
+	}
+
 	if opts.EvalRetentionBypassFn != nil {
-		if err := opts.EvalRetentionBypassFn(goi, gerr); err != nil {
+		if err := opts.EvalRetentionBypassFn(retOI, retErr); err != nil {
+			return ObjectInfo{}, err
+		}
+	} else if opts.RefuseLockedOverwrite && !opts.Versioned && !opts.DeleteMarker && opts.VersionID == "" {
+		if err := refuseLockedMarkerOverwrite(ctx, bucket, object, nullVersionID, retOI, retErr); err != nil {
 			return ObjectInfo{}, err
 		}
 	}
@@ -2560,7 +2614,7 @@ func (er erasureObjects) PutObjectTags(ctx context.Context, bucket, object strin
 
 	fi.Metadata[xhttp.AmzObjectTagging] = tags
 	fi.ReplicationState = opts.PutReplicationState()
-	stamp := monotonicTaggingTimestamp(opts.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp], fi.Metadata[ReservedMetadataPrefixLower+TaggingTimestamp])
+	stamp := monotonicMetadataTimestamp(opts.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp], fi.Metadata[ReservedMetadataPrefixLower+TaggingTimestamp])
 	maps.Copy(fi.Metadata, opts.UserDefined)
 	if stamp != "" {
 		fi.Metadata[ReservedMetadataPrefixLower+TaggingTimestamp] = stamp

cmd/erasure-server-pool-consistency.go

@@ -271,11 +271,33 @@ func (z *erasureServerPools) applyMigrationExpiry(ctx context.Context, bucket, o
 // in the source until the ordinary expiry path has deleted them: that path
 // owns replication state and tier cleanup, and it re-evaluates the current
 // lifecycle rule. A migration cleanup must never turn an asynchronous ILM
-// decision into an unconditional physical purge.
-func (z *erasureServerPools) removeMovedVersions(ctx context.Context, bucket, object string, source int, versions []FileInfo, expired []migrationExpiredVersion) error {
+// decision into an unconditional physical purge. It returns how many source
+// versions were removed, including versions deleted by ILM before cleanup.
+func (z *erasureServerPools) removeMovedVersions(ctx context.Context, bucket, object string, source int, versions []FileInfo, expired []migrationExpiredVersion) (int, error) {
+	err := z.retireMovedVersions(ctx, bucket, object, source, versions, expired)
+	removed, countErr := z.countAbsentMigrationVersions(ctx, bucket, object, source, versions)
+	if ctx.Err() != nil {
+		return 0, ctx.Err()
+	}
+	if err != nil {
+		return removed, err
+	}
+	return removed, countErr
+}
+
+// retireMovedVersions does not infer physical progress from a pool-level read
+// or delete result. Decommission verifies the entire walk snapshot once after
+// this cleanup and tier GC, including versions concurrently deleted by clients.
+func (z *erasureServerPools) retireMovedVersions(ctx context.Context, bucket, object string, source int, versions []FileInfo, expired []migrationExpiredVersion) error {
+	if err := ctx.Err(); err != nil {
+		return err
+	}
 	if err := z.applyMigrationExpiry(ctx, bucket, object, source, expired); err != nil {
 		return err
 	}
+	if len(versions) == 0 {
+		return nil
+	}
 	object = encodeDirObject(object)
 	lk := z.NewNSLock(bucket, object)
 	lkctx, err := lk.GetLock(ctx, globalOperationTimeout)
@@ -289,6 +311,7 @@ func (z *erasureServerPools) removeMovedVersions(ctx context.Context, bucket, ob
 		if vid == "" {
 			vid = nullVersionID
 		}
+		expiredVersion := isExpiredVersion(expired, version)
 		copies, err := z.objectPoolInfos(ctx, bucket, object, ObjectOptions{VersionID: vid, NoAuditLog: true})
 		if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
 			continue
@@ -311,7 +334,7 @@ func (z *erasureServerPools) removeMovedVersions(ctx context.Context, bucket, ob
 		if !src.ModTime.Equal(version.ModTime) || src.DeleteMarker != version.Deleted {
 			return PreConditionFailed{}
 		}
-		if isExpiredVersion(expired, version) {
+		if expiredVersion {
 			// The logical expiry path owns this version. Keeping the source is
 			// also the retry point if that path failed or the pool check races it.
 			continue
@@ -370,19 +393,7 @@ func (z *erasureServerPools) healObjectInPool(ctx context.Context, er *erasureOb
 // mergePoolLockState resolves each independently ordered field. An ordered
 // removal is a value in its own right; an absent unordered field is not one.
 func mergePoolLockState(copies []PoolObjInfo) objectLockState {
-	state := storedObjectLockState(copies[0].ObjInfo.UserDefined)
-	for _, copy := range copies[1:] {
-		next := storedObjectLockState(copy.ObjInfo.UserDefined)
-		retentionTime, _ := time.Parse(time.RFC3339Nano, next.retentionTimestamp)
-		if state.retentionIsOlderThan(retentionTime) || (state.retentionTimestamp == "" && state.mode == "" && next.mode != "") {
-			state.mode, state.retainUntil, state.retentionTimestamp = next.mode, next.retainUntil, next.retentionTimestamp
-		}
-		holdTime, _ := time.Parse(time.RFC3339Nano, next.legalHoldTimestamp)
-		if state.legalHoldIsOlderThan(holdTime) || (state.legalHoldTimestamp == "" && state.legalHold == "" && next.legalHold != "") {
-			state.legalHold, state.legalHoldTimestamp = next.legalHold, next.legalHoldTimestamp
-		}
-	}
-	return state
+	return reducePoolLockState(copies, storedObjectLockState)
 }
 
 func replaceObjectLockMetadata(metadata map[string]string, state objectLockState) {
@@ -534,10 +545,10 @@ func reconcileStoredObjectTags(metadata map[string]string, storedTags, storedTim
 	}
 }
 
-// Local tagging mutations must advance the revision they overwrite, even when
+// Local metadata mutations must advance the revision they overwrite, even when
 // a request's clock or lock acquisition order is behind the stored revision.
 // Replica writes use reconcileStoredObjectTags instead of minting a revision.
-func monotonicTaggingTimestamp(incoming, stored string) string {
+func monotonicMetadataTimestamp(incoming, stored string) string {
 	requested, err := time.Parse(time.RFC3339Nano, incoming)
 	if err != nil {
 		return incoming
@@ -635,6 +646,26 @@ func (z *erasureServerPools) deleteObjectReconciled(ctx context.Context, bucket,
 		case opts.VersionID != "":
 			// An addressed version already resolved every copy above.
 			logical = mergedPoolObjectInfo(copies)
+		case !opts.Versioned && !opts.DeleteMarker:
+			// An unqualified delete when versioning is not active for this key
+			// removes or replaces the null version in every pool that holds one,
+			// even if a newer non-null version is current for reads.
+			nullOpts := opts
+			nullOpts.VersionID = nullVersionID
+			nullCopies, err := z.objectPoolInfos(ctx, bucket, object, nullOpts)
+			switch {
+			case err == nil:
+				if nullCopies[0].ObjInfo.DeleteMarker {
+					gerr = toObjectErr(errFileNotFound, bucket, object)
+					logical = nullCopies[0].ObjInfo
+				} else {
+					logical = mergedPoolObjectInfo(nullCopies)
+				}
+			case isErrObjectNotFound(err) || isErrVersionNotFound(err):
+				gerr = toObjectErr(errFileNotFound, bucket, object)
+			default:
+				return ObjectInfo{}, err
+			}
 		default:
 			versions, err := z.metadataPoolInfos(ctx, bucket, object, opts)
 			if err != nil {
@@ -650,6 +681,14 @@ func (z *erasureServerPools) deleteObjectReconciled(ctx context.Context, bucket,
 				return ObjectInfo{}, err
 			}
 			opts.EvalRetentionBypassFn = nil
+			if !opts.Versioned && !opts.DeleteMarker && opts.VersionID == "" {
+				opts.RefuseLockedOverwrite = false
+			}
+		} else if opts.RefuseLockedOverwrite && !opts.Versioned && !opts.DeleteMarker && opts.VersionID == "" {
+			if err := refuseLockedMarkerOverwrite(ctx, bucket, object, nullVersionID, logical, gerr); err != nil {
+				return ObjectInfo{}, err
+			}
+			opts.RefuseLockedOverwrite = false
 		}
 		if opts.EvalMetadataFn != nil {
 			decision, err := opts.EvalMetadataFn(&logical, gerr)

cmd/erasure-server-pool-decom-keys-below_test.go

@@ -0,0 +1,102 @@
+// Copyright (c) 2026 Denis Babchuk
+//
+// This file is part of MinIO Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"testing"
+	"time"
+)
+
+// A key below another key ("k/b" under "k") is a directory inside the
+// directory of that key. The listing treats the directory of an object as a
+// leaf, so a decommission walk does not see "k/b" while "k" is still in the
+// pool. The walk has to be repeated once the keys above are gone, or the
+// check after the bucket finds them and the decommission fails.
+
+func keysBelowDecommission(t *testing.T, z *erasureServerPools) PoolDecommissionInfo {
+	t.Helper()
+	if err := z.StartDecommission(t.Context(), 0); err != nil {
+		t.Fatal(err)
+	}
+	z.doDecommissionInRoutine(t.Context(), 0)
+	z.poolMetaMutex.RLock()
+	defer z.poolMetaMutex.RUnlock()
+	return *z.poolMeta.Pools[0].Decommission
+}
+
+func keysBelowPools(t *testing.T) (*erasureServerPools, string, []string) {
+	t.Helper()
+	z, _ := migrationTestPools(t)
+	const bucket = "keys-below"
+	if err := z.MakeBucket(t.Context(), bucket, MakeBucketOptions{VersioningEnabled: true}); err != nil {
+		t.Fatal(err)
+	}
+	keys := []string{"k", "k/b", "k/b/c"}
+	for _, key := range keys {
+		putConsistencyObject(t, z, bucket, key, 0, key, ObjectOptions{Versioned: true})
+	}
+	return z, bucket, keys
+}
+
+func TestDecommissionMovesKeysBelowAKey(t *testing.T) {
+	z, bucket, keys := keysBelowPools(t)
+	if info := keysBelowDecommission(t, z); !info.Complete || info.Failed {
+		t.Errorf("decommission: complete %v, failed %v; want complete", info.Complete, info.Failed)
+	}
+	for _, key := range keys {
+		if _, err := z.serverPools[0].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{}); !isErrObjectNotFound(err) {
+			t.Errorf("%s still in pool 0: %v", key, err)
+		}
+		if body := migrationTestBody(t, z.GetObjectNInfo, bucket, key, ""); body != key {
+			t.Errorf("%s reads %q", key, body)
+		}
+	}
+}
+
+// An ILM expiry can remove the parent key during a decommission walk. That
+// removal must count as progress, or the next key below the parent remains
+// hidden from the listing and the source pool is left non-empty.
+func TestDecommissionContinuesAfterLifecycleRemovesParent(t *testing.T) {
+	z, _ := migrationTestPools(t)
+	const bucket = "decommission-ilm-keys-below"
+	if err := z.MakeBucket(t.Context(), bucket, MakeBucketOptions{}); err != nil {
+		t.Fatal(err)
+	}
+	meta, err := globalBucketMetadataSys.Get(bucket)
+	if err != nil {
+		t.Fatal(err)
+	}
+	meta.LifecycleConfigXML = []byte(`<LifecycleConfiguration><Rule><ID>expire-old</ID><Status>Enabled</Status><Filter><Prefix></Prefix></Filter><Expiration><Days>1</Days></Expiration></Rule></LifecycleConfiguration>`)
+	if err := meta.Save(t.Context(), z); err != nil {
+		t.Fatal(err)
+	}
+	globalBucketMetadataSys.Set(bucket, meta)
+
+	putConsistencyObject(t, z, bucket, "k", 0, "parent", ObjectOptions{MTime: UTCNow().Add(-72 * time.Hour)})
+	putConsistencyObject(t, z, bucket, "k/b", 0, "child", ObjectOptions{MTime: UTCNow()})
+
+	if info := keysBelowDecommission(t, z); !info.Complete || info.Failed {
+		t.Fatalf("decommission: complete %v, failed %v; want complete", info.Complete, info.Failed)
+	}
+	if _, err := z.serverPools[0].GetObjectInfo(t.Context(), bucket, "k/b", ObjectOptions{}); !isErrObjectNotFound(err) {
+		t.Fatalf("child still in source pool: %v", err)
+	}
+	if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k/b", ""); body != "child" {
+		t.Fatalf("child reads %q", body)
+	}
+}

cmd/erasure-server-pool-decom.go

@@ -28,6 +28,8 @@ import (
 	"slices"
 	"sort"
 	"strings"
+	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/dustin/go-humanize"
@@ -752,7 +754,34 @@ func (set *erasureObjects) listObjectsToDecommission(ctx context.Context, bi dec
 	return err
 }
 
+// decommissionPool moves bucket bi out of pool idx. A key below another key
+// ("k/b" under "k") is a directory inside the directory of that key, and the
+// listing does not descend into the directory of an object: a walk sees "k/b"
+// only once "k" has left the pool. The walk is repeated while it removes
+// source versions, so each pass moves the keys that the previous one
+// uncovered. Each repeat needs a version removed from the pool, which takes
+// no new writes, so the repeats end.
 func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool *erasureSets, bi decomBucketInfo) error {
+	for {
+		if err := ctx.Err(); err != nil {
+			return err
+		}
+		removed, err := z.decommissionPoolWalk(ctx, idx, pool, bi)
+		if ctx.Err() != nil {
+			return ctx.Err()
+		}
+		if err != nil || removed == 0 {
+			return err
+		}
+	}
+}
+
+// decommissionPoolWalk walks bucket bi of pool idx once and returns the number
+// of snapshot versions verified absent from every online source drive afterwards.
+func (z *erasureServerPools) decommissionPoolWalk(ctx context.Context, idx int, pool *erasureSets, bi decomBucketInfo) (int64, error) {
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
 	ctx = logger.SetReqInfo(ctx, &logger.ReqInfo{})
 
 	const envDecomWorkers = "_MINIO_DECOMMISSION_WORKERS"
@@ -766,9 +795,13 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 	// add that many extra workers.
 	workerSize += len(pool.sets)
 
+	var removed atomic.Int64
+	var verifyErr error
+	var verifyOnce sync.Once
+
 	wk, err := workers.New(workerSize)
 	if err != nil {
-		return err
+		return 0, err
 	}
 
 	var vc *versioning.Versioning
@@ -779,24 +812,24 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 	if bi.Name != minioMetaBucket {
 		vc, err = globalBucketVersioningSys.Get(bi.Name)
 		if err != nil {
-			return err
+			return 0, err
 		}
 
 		// Check if the current bucket has a configured lifecycle policy
 		lc, lifecycleUpdatedAt, err = globalBucketMetadataSys.GetLifecycleConfig(bi.Name)
 		if err != nil && !errors.Is(err, BucketLifecycleNotFound{Bucket: bi.Name}) {
-			return err
+			return 0, err
 		}
 
 		// Check if bucket is object locked.
 		lr, err = globalBucketObjectLockSys.Get(bi.Name)
 		if err != nil {
-			return err
+			return 0, err
 		}
 
 		rcfg, err = getReplicationConfig(ctx, bi.Name)
 		if err != nil {
-			return err
+			return 0, err
 		}
 	}
 
@@ -855,7 +888,7 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 			// to create the appropriate stack.
 			versionsSorter(fivs.Versions).reverse()
 
-			var decommissioned int
+			var candidates []FileInfo
 			var expired []migrationExpiredVersion
 			// The key's history in all pools, read once for its versions.
 			var history migrationHistory
@@ -863,8 +896,8 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 				stopFn := globalDecommissionMetrics.log(decomMetricDecommissionObject, idx, bi.Name, version.Name, version.VersionID)
 				// Apply lifecycle rules on the objects that are expired.
 				if action := filterLifecycle(bi.Name, version.Name, version, &history); action.Delete() {
-					decommissioned++
 					if ilmDeletesVersionOnly(action) || (action.DeleteAll() && !version.IsRemote()) {
+						candidates = append(candidates, version)
 						// Run the logical expiry before retiring the source.
 						// A full-object expiry is safe here only for hot-tier
 						// metadata; transitioned objects retain their tier cleanup
@@ -912,7 +945,6 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 						// This can happen when rebalance stop races with ongoing rebalance workers.
 						// These rebalance failures can be ignored.
 						if isErrObjectNotFound(err) || isErrVersionNotFound(err) || isDataMovementOverWriteErr(err) {
-							ignore = true
 							stopFn(0, nil)
 							continue
 						}
@@ -926,8 +958,7 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 					z.poolMeta.CountItem(idx, 0, failure)
 					z.poolMetaMutex.Unlock()
 					if !failure {
-						// Success keep a count.
-						decommissioned++
+						candidates = append(candidates, version)
 					}
 					auditLogDecom(ctx, "DecomCopyDeleteMarker", bi.Name, version.Name, versionID, err)
 					continue
@@ -1013,16 +1044,32 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 				if failure {
 					break // break out on first error
 				}
-				decommissioned++
+				candidates = append(candidates, version)
 			}
 
-			// if all versions were decommissioned, then we can delete the object versions.
-			if decommissioned == len(fivs.Versions) {
+			// Retire only successful moves and eligible expiries. A concurrently
+			// deleted or failed sibling must not strand the successful copies.
+			// Skipped versions are checked for absence, never purged here.
+			{
 				stopFn := globalDecommissionMetrics.log(decomMetricDecommissionRemoveObject, idx, bi.Name, entry.name)
-				err := z.removeMovedVersions(ctx, bi.Name, entry.name, idx, fivs.Versions, expired)
+				err := z.retireMovedVersions(ctx, bi.Name, entry.name, idx, candidates, expired)
 				if err == nil {
 					err = z.removeFreeVersions(ctx, bi.Name, entry.name, idx, fivs.FreeVersions)
 				}
+				// One metadata-only read of each source drive per entry, regardless
+				// of its version count. No read error can become progress or trigger
+				// another walk; leave the bucket queued for an explicit retry.
+				snapshot := slices.Concat(fivs.Versions, fivs.FreeVersions)
+				n, countErr := z.countAbsentMigrationVersions(ctx, bi.Name, entry.name, idx, snapshot)
+				removed.Add(int64(n))
+				// The disposable usage cache is also excluded by the final
+				// verification. Its unreadability still never counts as progress.
+				if countErr != nil && (bi.Name != minioMetaBucket || !strings.Contains(entry.name, dataUsageCacheName)) {
+					verifyOnce.Do(func() { verifyErr = countErr })
+					if err == nil {
+						err = countErr
+					}
+				}
 				stopFn(0, err)
 				auditLogDecom(ctx, "DecomDeleteObject", bi.Name, entry.name, "", err)
 				if err != nil {
@@ -1057,12 +1104,19 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
 				setN := humanize.Ordinal(setIdx + 1)
 				retryDur := time.Duration(rand.Float64() * float64(5*time.Second))
 				decomLogOnceIf(ctx, fmt.Errorf("listing objects from %s set failed with %v, retrying in %v", setN, err, retryDur), "decom-listing-failed"+setN)
-				time.Sleep(retryDur)
+				select {
+				case <-ctx.Done():
+					return
+				case <-time.After(retryDur):
+				}
 			}
 		}(setIdx)
 	}
 	wk.Wait()
-	return nil
+	if err := ctx.Err(); err != nil {
+		return removed.Load(), err
+	}
+	return removed.Load(), verifyErr
 }
 
 //msgp:ignore decomMetrics
@@ -1113,6 +1167,9 @@ func (m *decomMetrics) log(d decomMetric, poolIdx int, paths ...string) func(z i
 // decommission fails and a retry resumes with what is left. A canceled
 // context returns at once.
 func (z *erasureServerPools) decommissionInBackground(ctx context.Context, idx int) error {
+	if err := ctx.Err(); err != nil {
+		return err
+	}
 	pool := z.serverPools[idx]
 	z.poolMetaMutex.RLock()
 	pending := z.poolMeta.PendingBuckets(idx)
@@ -1151,7 +1208,7 @@ func (z *erasureServerPools) decommissionInBackground(ctx context.Context, idx i
 		if err := z.decommissionPool(ctx, idx, pool, bucket); err != nil {
 			stopFn(0, err)
 			if contextCanceled(ctx) {
-				return err
+				return ctx.Err()
 			}
 			failed(bucket, err)
 			continue
@@ -1164,7 +1221,7 @@ func (z *erasureServerPools) decommissionInBackground(ctx context.Context, idx i
 		if err := z.checkAfterDecomBucket(ctx, idx, bucket); err != nil {
 			stopFn(0, err)
 			if contextCanceled(ctx) {
-				return err
+				return ctx.Err()
 			}
 			failed(bucket, err)
 			continue
@@ -1177,6 +1234,9 @@ func (z *erasureServerPools) decommissionInBackground(ctx context.Context, idx i
 		}
 		z.poolMetaMutex.Unlock()
 	}
+	if err := ctx.Err(); err != nil {
+		return err
+	}
 	return firstErr
 }
 
@@ -1211,34 +1271,74 @@ func (z *erasureServerPools) removeFreeVersions(ctx context.Context, bucket, obj
 	return nil
 }
 
-// checkAfterDecomBucket verifies that a source bucket is physically empty
+// checkAfterDecomBucket verifies that a source bucket's online drives are empty
 // before it is removed from the resumable decommission queue. ILM decisions
 // are deliberately not treated as an exemption: an expired version remains
 // until the expiry path has performed its logical delete, replication, and
 // tier cleanup.
 func (z *erasureServerPools) checkAfterDecomBucket(ctx context.Context, idx int, bi decomBucketInfo) error {
-	versionsFound := 0
+	if err := ctx.Err(); err != nil {
+		return err
+	}
 	for _, set := range z.serverPools[idx].sets {
-		if err := set.listObjectsToDecommission(ctx, bi, func(entry metaCacheEntry) {
-			if !entry.isObject() {
-				return
+		disks := set.getDisks()
+		if len(disks) == 0 {
+			return toObjectErr(errErasureReadQuorum, bi.Name)
+		}
+		readQuorum := set.migrationReadQuorum(len(disks))
+		onlineCount := 0
+		for _, disk := range disks {
+			if disk == nil {
+				continue
 			}
-			if bi.Name == minioMetaBucket && strings.Contains(entry.name, dataUsageCacheName) {
-				return
+			// Quorum listings omit minority versions, and WalkDir can skip
+			// unreadable metadata. Inspect physical directory entries instead:
+			// even a corrupt or truncated xl.meta must keep this pool queued.
+			pending := []string{bi.Prefix}
+			diskOffline := false
+			for len(pending) > 0 {
+				if err := ctx.Err(); err != nil {
+					return err
+				}
+				dir := pending[len(pending)-1]
+				pending = pending[:len(pending)-1]
+				entries, err := disk.ListDir(ctx, "", bi.Name, dir, -1)
+				if ctx.Err() != nil {
+					return ctx.Err()
+				}
+				if errors.Is(err, errFileNotFound) || errors.Is(err, errVolumeNotFound) {
+					continue // A concurrent deletion can remove the directory.
+				}
+				if errors.Is(err, errDiskNotFound) {
+					diskOffline = true
+					break
+				}
+				if err != nil {
+					return err
+				}
+				for _, entry := range entries {
+					name := pathJoin(dir, entry)
+					if bi.Name == minioMetaBucket && strings.Contains(name, dataUsageCacheName) {
+						continue
+					}
+					if entry == xlStorageFormatFile || entry == xlStorageFormatFileV1 {
+						return fmt.Errorf("object metadata %s remains in bucket %s after decommissioning", name, bi.Name)
+					}
+					if strings.HasSuffix(entry, SlashSeparator) {
+						pending = append(pending, name)
+					}
+				}
 			}
-			fivs, err := entry.fileInfoVersions(bi.Name)
-			if err != nil {
-				return
+			if diskOffline {
+				continue
 			}
-			versionsFound += len(fivs.Versions) + len(fivs.FreeVersions)
-		}); err != nil {
-			return err
+			onlineCount++
+		}
+		if onlineCount < readQuorum {
+			return toObjectErr(errErasureReadQuorum, bi.Name)
 		}
 	}
-	if versionsFound > 0 {
-		return fmt.Errorf("at least %d object(s)/version(s) were found in bucket `%s` after decommissioning", versionsFound, bi.Name)
-	}
-	return nil
+	return ctx.Err()
 }
 
 func (z *erasureServerPools) checkAfterDecom(ctx context.Context, idx int) error {

cmd/erasure-server-pool-lifecycle-authority_test.go

@@ -20,6 +20,7 @@ package cmd
 import (
 	"context"
 	"crypto/sha256"
+	"encoding/binary"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -29,6 +30,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/cespare/xxhash/v2"
 	"github.com/google/uuid"
 	"github.com/minio/madmin-go/v3"
 	"github.com/minio/minio/internal/bucket/lifecycle"
@@ -632,6 +634,180 @@ func TestPoolsLifecycleLegacyHistory(t *testing.T) {
 	}
 }
 
+// authoritySignature2021 is the header signature of o, a version whose part
+// ETags are all empty, as the releases from RELEASE.2021-11-24 until
+// RELEASE.2022-01-25 computed it: with these ETags.
+func authoritySignature2021(o xlMetaV2Object) (sig [4]byte) {
+	o.ErasureIndex = 0
+	crc := hashDeterministicString(o.MetaUser) ^ hashDeterministicBytes(o.MetaSys)
+	o.MetaUser, o.MetaSys = nil, nil
+	bts, _ := o.MarshalMsg(nil)
+	crc ^= xxhash.Sum64(bts)
+	binary.LittleEndian.PutUint32(sig[:], uint32(crc^(crc>>32)))
+	return sig
+}
+
+// A drive holds the header that the release which wrote a version there
+// stored. Before RELEASE.2024-04-28 it has no erasure coding, and until
+// RELEASE.2022-01-25 its signature counted the empty part ETags of versions
+// written before RELEASE.2021-11-24. A heal writes the header of its own
+// release and leaves the other drives alone, so the drives of an old version
+// differ there for good once some were replaced. That is one revision, as
+// reads and heal take it, on however many of the drives.
+func TestPoolsLifecycleHeaderEras(t *testing.T) {
+	id := [16]byte{1}
+	current := func(drive int) xlMetaV2ShallowVersion { return authorityRevision(t, id, 1, drive+1, "") }
+	// stored returns the version as drive holds it after change, under the
+	// header that header derives from the one a current release writes.
+	stored := func(drive int, change func(*xlMetaV2Object), header func(xlMetaV2VersionHeader, xlMetaV2Object) xlMetaV2VersionHeader) xlMetaV2ShallowVersion {
+		ver := current(drive)
+		var v xlMetaV2Version
+		if _, err := v.UnmarshalMsg(ver.meta); err != nil {
+			t.Fatal(err)
+		}
+		change(v.ObjectV2)
+		meta, err := v.MarshalMsg(nil)
+		if err != nil {
+			t.Fatal(err)
+		}
+		return xlMetaV2ShallowVersion{header: header(ver.header, *v.ObjectV2), meta: meta}
+	}
+	eras := map[string]func(drive int) xlMetaV2ShallowVersion{
+		"no-erasure-coding": func(drive int) xlMetaV2ShallowVersion {
+			return stored(drive, func(*xlMetaV2Object) {}, func(h xlMetaV2VersionHeader, _ xlMetaV2Object) xlMetaV2VersionHeader {
+				h.EcN, h.EcM = 0, 0
+				return h
+			})
+		},
+		"empty-part-etags-signed": func(drive int) xlMetaV2ShallowVersion {
+			return stored(drive, func(o *xlMetaV2Object) { o.PartETags = []string{""} }, func(h xlMetaV2VersionHeader, o xlMetaV2Object) xlMetaV2VersionHeader {
+				h.EcN, h.EcM, h.Signature = 0, 0, authoritySignature2021(o)
+				return h
+			})
+		},
+	}
+	metaVs := slices.Repeat([]uint8{xlMetaVersion}, 16)
+	readQuorum := func(xlMetaV2ShallowVersion, uint8) int { return 12 }
+	for name, old := range eras {
+		t.Run(name, func(t *testing.T) {
+			if old(0).header == current(0).header {
+				t.Fatal("fixture: the old header is the current one")
+			}
+			if versionRevision(old(0), xlMetaVersion) != versionRevision(current(7), xlMetaVersion) {
+				t.Error("one version under the headers of two releases has two keys")
+			}
+			// The normalized current header orders the merge.
+			wantHeader := current(0).header
+			wantHeader.Flags &^= xlFlagUsesDataDir
+			if versionRevision(old(0), xlMetaVersion).header != wantHeader {
+				t.Error("the key does not carry the header of the current release")
+			}
+			for healed := range 17 {
+				metas := make([][]xlMetaV2ShallowVersion, 16)
+				for i := range metas {
+					if i < healed {
+						metas[i] = []xlMetaV2ShallowVersion{current(i)}
+					} else {
+						metas[i] = []xlMetaV2ShallowVersion{old(i)}
+					}
+				}
+				merged, err := authoritativeHistory(t.Context(), metas, metaVs, xlMetaVersion, 9, readQuorum)
+				if err != nil || len(merged) != 1 {
+					t.Errorf("%d healed drives: %d versions, err=%v", healed, len(merged), err)
+				}
+			}
+		})
+	}
+	// Control: the erasure coding still tells revisions apart, by the
+	// metadata. Another one under the same header is another revision.
+	other := stored(0, func(o *xlMetaV2Object) { o.ErasureM, o.ErasureN = 8, 8 }, func(h xlMetaV2VersionHeader, _ xlMetaV2Object) xlMetaV2VersionHeader { return h })
+	if versionRevision(other, xlMetaVersion) == versionRevision(current(0), xlMetaVersion) {
+		t.Error("another erasure coding under one header keeps the revision")
+	}
+}
+
+// The same on drives, through a heal: two versions with headers from before
+// RELEASE.2024-04-28 on a set where half of the drives were replaced. GET
+// reads them and heal has nothing left to do. Their expiry has to run as
+// well: of a noncurrent version with several pools, and of all versions of a
+// key with one pool too, which reads the history like the pools do. A
+// restore takes the drives for one generation, not for a failed status write.
+func TestPoolsLifecycleHealedOldHeaders(t *testing.T) {
+	for _, single := range []bool{false, true} {
+		name, key := "noncurrent-version", "ncv-old-headers"
+		if single {
+			name, key = "all-versions-one-pool", "eav-old-headers"
+		}
+		t.Run(name, func(t *testing.T) {
+			s := newSplitILM(t, versioning.Enabled, splitILMRules)
+			ctx := t.Context()
+			s.write(key, splitAt("old", 5, 0))
+			s.write(key, splitAt("new", 3, 0))
+			ids := []string{s.ids[key+" old"], s.ids[key+" new"]}
+			if single {
+				prior := s.z.serverPools
+				t.Cleanup(func() { s.z.serverPools = prior })
+				s.z.serverPools = s.z.serverPools[:1]
+			}
+			set := s.z.serverPools[0].getHashedSet(key)
+			disks := set.getDisks()
+			for _, disk := range disks {
+				rewriteTierTestMeta(t, disk, s.bucket, key, func(xl *xlMetaV2) {
+					for i := range xl.versions {
+						// Control: the key of a version this release wrote
+						// carries its header with only the time-derived flag removed.
+						wantHeader := xl.versions[i].header
+						wantHeader.Flags &^= xlFlagUsesDataDir
+						if versionRevision(xl.versions[i], xl.metaV).header != wantHeader {
+							t.Fatal("the key of a current version carries another header")
+						}
+						xl.versions[i].header.EcN, xl.versions[i].header.EcM = 0, 0
+					}
+				})
+			}
+			replaced := len(disks) / 2
+			for _, disk := range disks[:replaced] {
+				if err := disk.Delete(ctx, s.bucket, key, DeleteOptions{Recursive: true, Immediate: true}); err != nil {
+					t.Fatal(err)
+				}
+				for _, id := range ids {
+					if _, err := s.z.HealObject(ctx, s.bucket, key, id, madmin.HealOpts{ScanMode: madmin.HealNormalScan}); err != nil {
+						t.Fatalf("heal %s: %v", id, err)
+					}
+				}
+			}
+			for i, disk := range disks {
+				if authorityHeader(t, disk, s.bucket, key, ids[0]).hasEC() != (i < replaced) {
+					t.Fatalf("fixture: drive %d of %d, %d replaced, holds the other header", i, len(disks), replaced)
+				}
+			}
+			authorityPresent(t, s, 0, key, ids[0])
+			res, err := s.z.HealObject(ctx, s.bucket, key, ids[0], madmin.HealOpts{DryRun: true, ScanMode: madmin.HealNormalScan})
+			if err != nil || slices.ContainsFunc(res.Before.Drives, func(d madmin.HealDriveInfo) bool { return d.State != madmin.DriveStateOk }) {
+				t.Fatalf("fixture: heal has work left: %v", err)
+			}
+
+			if gen, err := set.readRestoreGeneration(ctx, s.bucket, key, ids[0]); err != nil || gen.split {
+				t.Errorf("restore generation: split=%v, err=%v", gen.split, err)
+			}
+			if single {
+				_, err = s.z.DeleteObject(ctx, s.bucket, key, authorityDeleteAll)
+			} else {
+				err = authorityExpireVersion(t, s, key, ids[0])
+			}
+			if err != nil {
+				t.Fatalf("expiry: %v", err)
+			}
+			if _, err := s.z.GetObjectInfo(ctx, s.bucket, key, ObjectOptions{VersionID: ids[0]}); !isErrVersionNotFound(err) && !isErrObjectNotFound(err) {
+				t.Errorf("the expired version: %v", err)
+			}
+			if !single {
+				authorityPresent(t, s, 0, key, ids[1])
+			}
+		})
+	}
+}
+
 // authorityDeleteAll is the expiry of all versions of a key as the expiry
 // worker sends it: a purge of all versions, approved by the lifecycle.
 var authorityDeleteAll = ObjectOptions{DeleteAllVersions: true, Expiration: ExpirationOptions{Expire: true}}
@@ -1088,6 +1264,7 @@ func TestPoolsLifecycleCheckedExpirySafeguard(t *testing.T) {
 		{"hold-equal-stamps", poolLockMetadata("", "ON", old, recent), objectLockState{legalHold: "OFF", legalHoldTimestamp: recent}, false},
 		{"hold-missing-approved-stamp", poolLockMetadata("", "ON", old, old), objectLockState{legalHold: "OFF"}, false},
 		{"retention-newer-locally", poolLockMetadata("GOVERNANCE", "OFF", recent, old), objectLockState{retentionTimestamp: old, legalHold: "OFF", legalHoldTimestamp: old}, false},
+		{"compliance-cannot-release", poolLockMetadata("COMPLIANCE", "OFF", old, old), objectLockState{retentionTimestamp: recent, legalHold: "OFF", legalHoldTimestamp: old}, false},
 		// Controls: the approval strictly supersedes the local protection.
 		{"hold-released", poolLockMetadata("", "ON", old, old), objectLockState{legalHold: "OFF", legalHoldTimestamp: recent}, true},
 		{"retention-released", poolLockMetadata("GOVERNANCE", "OFF", old, old), objectLockState{retentionTimestamp: recent, legalHold: "OFF", legalHoldTimestamp: old}, true},
@@ -1494,7 +1671,7 @@ func TestPoolsMigrationLifecycleRefusedExpiryKeepsSource(t *testing.T) {
 		t.Fatal(err)
 	}
 	version := FileInfo{Name: key, VersionID: id, ModTime: source.ModTime}
-	err = s.z.removeMovedVersions(ctx, s.bucket, key, 0, []FileInfo{version}, []migrationExpiredVersion{{
+	_, err = s.z.removeMovedVersions(ctx, s.bucket, key, 0, []FileInfo{version}, []migrationExpiredVersion{{
 		version:            version,
 		event:              lifecycle.Event{Action: lifecycle.DeleteAction},
 		lifecycleUpdatedAt: updatedAt,

cmd/erasure-server-pool-lifecycle-safety_test.go

@@ -70,6 +70,8 @@ func TestPoolsLifecycleDuplicateLockMetadata(t *testing.T) {
 		{name: "independent-fields", copies: [2]map[string]string{poolLockMetadata("GOVERNANCE", "OFF", recent, old), poolLockMetadata("", "ON", old, recent)}, mode: "GOVERNANCE", hold: "ON"},
 		{name: "hold-released", copies: [2]map[string]string{poolLockMetadata("", "ON", old, old), poolLockMetadata("", "OFF", old, recent)}, hold: "OFF", delete: true},
 		{name: "retention-released", copies: [2]map[string]string{poolLockMetadata("GOVERNANCE", "OFF", old, old), poolLockMetadata("", "OFF", recent, old)}, hold: "OFF", delete: true},
+		{name: "compliance-before-removal", copies: [2]map[string]string{poolLockMetadata("COMPLIANCE", "OFF", old, old), poolLockMetadata("", "OFF", recent, old)}, mode: "COMPLIANCE", hold: "OFF"},
+		{name: "compliance-after-removal", copies: [2]map[string]string{poolLockMetadata("", "OFF", recent, old), poolLockMetadata("COMPLIANCE", "OFF", old, old)}, mode: "COMPLIANCE", hold: "OFF"},
 	} {
 		for _, batch := range []bool{false, true} {
 			path := "single"

cmd/erasure-server-pool-lifecycle.go

@@ -187,9 +187,18 @@ type revisionKey struct {
 // input is canonical: each map, including the part checksums of a legacy
 // version, is its own section with its entry count and sorted,
 // length-prefixed entries, since msgp encodes maps in iteration order and an
-// entry must not move between maps unnoticed. The header of a
-// legacy version carries a signature over its per-shard checksums, so the
-// key replaces it with one from the digest.
+// entry must not move between maps unnoticed.
+//
+// A drive holds the header that the release which wrote the version there
+// stored, and a heal writes the one of its own release: headers from before
+// RELEASE.2024-04-28 carry no erasure coding, and the signature counted
+// empty part ETags until RELEASE.2022-01-25. Reads and heal take such drives
+// for one version (matchesNotStrict), and nothing rewrites them. The key has
+// both as the current release computes them from the metadata, so that the
+// header of a version it wrote stays as stored, except UsesDataDir, which can
+// change solely because a restored copy expired before healing. The signature
+// also orders versions of one time in the merge. The signature of a legacy version is
+// over its per-shard checksums; the key has one from the digest.
 func versionRevision(ver xlMetaV2ShallowVersion, metaV uint8) revisionKey {
 	h := sha256.New()
 	writeUint := func(n int) {
@@ -267,8 +276,13 @@ func versionRevision(ver xlMetaV2ShallowVersion, metaV uint8) revisionKey {
 			section("fields", 1)
 			writeField(bts)
 			h.Sum(key.digest[:0])
-			if v.Type == LegacyType {
+			switch v.Type {
+			case LegacyType:
 				copy(key.header.Signature[:], key.digest[:])
+			case ObjectType:
+				key.header.Signature = v.ObjectV2.Signature()
+				key.header.EcN, key.header.EcM = uint8(v.ObjectV2.ErasureN), uint8(v.ObjectV2.ErasureM)
+				key.header.Flags &^= xlFlagUsesDataDir
 			}
 			return key
 		}
@@ -350,7 +364,7 @@ func authoritativeHistory(ctx context.Context, metas [][]xlMetaV2ShallowVersion,
 	// its count, and one that shares the header could stand in for the
 	// accepted one, so the merge only sees the accepted revision of each
 	// version and free versions as they are. It sees the headers of the
-	// keys, which do not differ between the drives of a legacy version.
+	// keys, which do not differ between the drives of a revision.
 	filtered := make([][]xlMetaV2ShallowVersion, len(metas))
 	for i, versions := range metas {
 		for j, ver := range versions {
@@ -575,20 +589,10 @@ func setLifecycleLockState(metadata map[string]string, state objectLockState) {
 	set(ReservedMetadataPrefix+ObjectLockLegalHoldTimestamp, state.legalHoldTimestamp)
 }
 
-// newestLockState returns the newest hold and the newest retention of the
-// copies of a version, which lockRevisionsOrdered found equal or ordered.
+// newestLockState orders independently revised fields without weakening a
+// COMPLIANCE retention that any copy still protects.
 func newestLockState(copies []PoolObjInfo) objectLockState {
-	state := lifecycleLockState(copies[0].ObjInfo.UserDefined)
-	for _, copy := range copies[1:] {
-		next := lifecycleLockState(copy.ObjInfo.UserDefined)
-		if lockRevisionNewer(next.legalHoldTimestamp, state.legalHoldTimestamp) {
-			state.legalHold, state.legalHoldTimestamp = next.legalHold, next.legalHoldTimestamp
-		}
-		if lockRevisionNewer(next.retentionTimestamp, state.retentionTimestamp) {
-			state.mode, state.retainUntil, state.retentionTimestamp = next.mode, next.retainUntil, next.retentionTimestamp
-		}
-	}
-	return state
+	return reducePoolLockState(copies, lifecycleLockState)
 }
 
 // checkedExpiryRefused reports whether a set must keep a version whose ILM
@@ -611,7 +615,7 @@ func checkedExpiryRefused(lc lifecycle.Lifecycle, lr objectlock.Retention, rcfg
 	if lockRevisionNewer(approved.legalHoldTimestamp, local.legalHoldTimestamp) {
 		obj.UserDefined[strings.ToLower(xhttp.AmzObjectLockLegalHold)] = approved.legalHold
 	}
-	if lockRevisionNewer(approved.retentionTimestamp, local.retentionTimestamp) {
+	if lockRevisionNewer(approved.retentionTimestamp, local.retentionTimestamp) && !local.complianceWouldWeaken(approved) {
 		obj.UserDefined[strings.ToLower(xhttp.AmzObjectLockMode)] = approved.mode
 		obj.UserDefined[strings.ToLower(xhttp.AmzObjectLockRetainUntilDate)] = approved.retainUntil
 	}

cmd/erasure-server-pool-migration-delete_test.go

@@ -132,7 +132,7 @@ func TestPoolsMigrationCleanupRechecksSource(t *testing.T) {
 				_, err := z.serverPools[1].DeleteObject(t.Context(), bucket, oi.Name, ObjectOptions{VersionID: nullVersionID})
 				mustIAM(t, err)
 			}
-			err := z.removeMovedVersions(t.Context(), bucket, oi.Name, 0, snapshot, nil)
+			_, err := z.removeMovedVersions(t.Context(), bucket, oi.Name, 0, snapshot, nil)
 			if change != "delete-uuid" && err == nil {
 				t.Fatal("cleanup accepted changed or uncertain state")
 			}

cmd/erasure-server-pool-migration-ilm_test.go

@@ -414,6 +414,46 @@ func testMigrationLifecycleExpiry(t *testing.T, kind string) {
 	})
 }
 
+// Physical expiry advances the walk; creating a delete marker does not remove
+// the addressed version and must not make a walk repeat without progress.
+func TestPoolsMigrationLifecycleRemovalProgress(t *testing.T) {
+	for _, versioned := range []bool{false, true} {
+		status := versioning.State("")
+		name, wantRemoved := "physical-delete", 1
+		if versioned {
+			status = versioning.Enabled
+			name, wantRemoved = "delete-marker-only", 0
+		}
+		t.Run(name, func(t *testing.T) {
+			m := newMigrationILM(t, status, false, migrationILMExpireCurrent())
+			oi := m.put("obj-01", "v1", ObjectOptions{Versioned: versioned, MTime: UTCNow().Add(-72 * time.Hour)})
+			_, updatedAt, err := globalBucketMetadataSys.GetLifecycleConfig(m.bucket)
+			if err != nil {
+				t.Fatal(err)
+			}
+			version := FileInfo{Name: oi.Name, VersionID: oi.VersionID, ModTime: oi.ModTime}
+			removed, err := m.z.removeMovedVersions(t.Context(), m.bucket, oi.Name, 0, []FileInfo{version}, []migrationExpiredVersion{{
+				version:            version,
+				event:              lifecycle.Event{Action: lifecycle.DeleteAction},
+				lifecycleUpdatedAt: updatedAt,
+				source:             lcEventSrc_Decom,
+			}})
+			if err != nil || removed != wantRemoved {
+				t.Fatalf("removed %d versions, err %v; want %d, nil", removed, err, wantRemoved)
+			}
+			if versioned {
+				if body := migrationTestBody(t, m.z.GetObjectNInfo, m.bucket, oi.Name, oi.VersionID); body != "obj-01 v1" {
+					t.Fatalf("noncurrent version reads %q", body)
+				}
+			}
+			current, err := m.z.GetObjectInfo(t.Context(), m.bucket, oi.Name, ObjectOptions{})
+			if !isErrObjectNotFound(err) || current.DeleteMarker != versioned {
+				t.Fatalf("after expiry: delete marker %t, err %v", current.DeleteMarker, err)
+			}
+		})
+	}
+}
+
 // A lifecycle action found during the migration walk must not be applied
 // after the bucket's lifecycle configuration changes. The source copy stays
 // available for a fresh scan under the new policy.

cmd/erasure-server-pool-migration-progress_test.go

@@ -0,0 +1,601 @@
+// Copyright (c) 2026 Feng Ruohang
+// SPDX-License-Identifier: AGPL-3.0-or-later
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"io"
+	"slices"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/bucket/lifecycle"
+)
+
+// The walk has already captured the version when its data read reaches this
+// hook. Metadata-only checks made by a concurrent DELETE do not reenter it.
+type migrationProgressReadDisk struct {
+	StorageAPI
+	bucket, object, version string
+	before                  func() error
+}
+
+func (d migrationProgressReadDisk) ReadVersion(ctx context.Context, orig, bucket, object, version string, opts ReadOptions) (FileInfo, error) {
+	if opts.ReadData && bucket == d.bucket && object == d.object && version == d.version {
+		if err := d.before(); err != nil {
+			return FileInfo{}, err
+		}
+	}
+	return d.StorageAPI.ReadVersion(ctx, orig, bucket, object, version, opts)
+}
+
+// Buffer every drive's first walk before publishing any entry. Thus deleting
+// the parent cannot accidentally let this same walk discover the child.
+type migrationSnapshotWalk struct {
+	bucket string
+	drives int32
+	calls  atomic.Int32
+	ready  chan struct{}
+}
+
+type migrationSnapshotWalkDisk struct {
+	StorageAPI
+	snapshot *migrationSnapshotWalk
+}
+
+func (d migrationSnapshotWalkDisk) WalkDir(ctx context.Context, opts WalkDirOptions, out io.Writer) error {
+	if opts.Bucket != d.snapshot.bucket {
+		return d.StorageAPI.WalkDir(ctx, opts, out)
+	}
+	var buf bytes.Buffer
+	if err := d.StorageAPI.WalkDir(ctx, opts, &buf); err != nil {
+		return err
+	}
+	if d.snapshot.calls.Add(1) == d.snapshot.drives {
+		close(d.snapshot.ready)
+	}
+	select {
+	case <-d.snapshot.ready:
+	case <-ctx.Done():
+		return ctx.Err()
+	}
+	_, err := io.Copy(out, &buf)
+	return err
+}
+
+func migrationProgressSnapshot(t *testing.T, z *erasureServerPools, bucket, key string) *migrationSnapshotWalk {
+	t.Helper()
+	s := &migrationSnapshotWalk{bucket: bucket, drives: int32(len(z.serverPools[0].getHashedSet(key).getDisks())), ready: make(chan struct{})}
+	t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], key, func(d StorageAPI) StorageAPI {
+		return migrationSnapshotWalkDisk{StorageAPI: d, snapshot: s}
+	}))
+	return s
+}
+
+func migrationProgressPrepare(t *testing.T, z *erasureServerPools, kind string) {
+	t.Helper()
+	migrationTestMover(t, z, 0, kind)
+	z.poolMetaMutex.Lock()
+	z.poolMeta.Pools[0].LastUpdate = UTCNow()
+	z.poolMetaMutex.Unlock()
+}
+
+func TestDecommissionSplitMetadataDoesNotAdvance(t *testing.T) {
+	m := newMigrationILM(t, "", false, migrationILMExpireCurrent())
+	const key = "obj-01"
+	m.put(key, "old", ObjectOptions{MTime: UTCNow().Add(-96 * time.Hour)})
+	disks := m.z.serverPools[0].getHashedSet(key).getDisks()
+	old := make([][]byte, len(disks)/2)
+	for i := range old {
+		var err error
+		old[i], err = disks[i].ReadAll(t.Context(), m.bucket, pathJoin(key, xlStorageFormatFile))
+		mustIAM(t, err)
+	}
+	m.put(key, "new-and-longer", ObjectOptions{MTime: UTCNow().Add(-72 * time.Hour)})
+	for i := range old {
+		mustIAM(t, disks[i].WriteAll(t.Context(), m.bucket, pathJoin(key, xlStorageFormatFile), old[i]))
+	}
+	if _, err := m.z.serverPools[0].GetObjectInfo(t.Context(), m.bucket, key, ObjectOptions{VersionID: nullVersionID}); !isErrVersionNotFound(err) {
+		t.Fatalf("fixture must expose the ambiguous logical NotFound, got %v", err)
+	}
+	migrationProgressPrepare(t, m.z, "decommission")
+	walk := migrationProgressSnapshot(t, m.z, m.bucket, key)
+	bi := decomBucketInfo{Name: m.bucket}
+	// Check a single pass first, so the unfixed implementation fails rather
+	// than looping until the test timeout.
+	removed, err := m.z.decommissionPoolWalk(t.Context(), 0, m.z.serverPools[0], bi)
+	if err != nil || removed != 0 {
+		t.Fatalf("split metadata reported progress: removed=%d err=%v", removed, err)
+	}
+	mustIAM(t, m.z.decommissionPool(t.Context(), 0, m.z.serverPools[0], bi))
+	if got := walk.calls.Load(); got != 2*walk.drives {
+		t.Fatalf("unchanged metadata repeated the walk: calls=%d", got)
+	}
+	if err := m.z.checkAfterDecomBucket(t.Context(), 0, bi); err == nil {
+		t.Fatal("final verification accepted split metadata still on disk")
+	}
+	for _, disk := range disks {
+		if _, err := disk.ReadVersion(t.Context(), "", m.bucket, key, nullVersionID, ReadOptions{}); err != nil {
+			t.Fatalf("migration removed an ambiguous source revision: %v", err)
+		}
+	}
+}
+
+func TestPoolsMigrationConcurrentDeleteCleanup(t *testing.T) {
+	for _, kind := range []string{"decommission", "rebalance"} {
+		t.Run(kind, func(t *testing.T) {
+			z, bucket := migrationTestPools(t)
+			v1 := putConsistencyObject(t, z, bucket, "k", 0, "older", ObjectOptions{Versioned: true, MTime: UTCNow().Add(-time.Hour)})
+			v2 := putConsistencyObject(t, z, bucket, "k", 0, "newer", ObjectOptions{Versioned: true})
+			var once sync.Once
+			var deleteErr error
+			before := func() error {
+				once.Do(func() {
+					_, deleteErr = z.DeleteObject(t.Context(), bucket, "k", ObjectOptions{Versioned: true, VersionID: v2.VersionID})
+				})
+				return deleteErr
+			}
+			restore := conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+				return migrationProgressReadDisk{StorageAPI: d, bucket: bucket, object: "k", version: v2.VersionID, before: before}
+			})
+			defer restore()
+			if failed := migrationTestWalk(t, z, bucket, 0, kind); failed != 0 {
+				t.Fatalf("failed moves: %d", failed)
+			}
+			restore()
+			for _, v := range []ObjectInfo{v1, v2} {
+				for _, disk := range z.serverPools[0].getHashedSet("k").getDisks() {
+					_, err := disk.ReadVersion(t.Context(), "", bucket, "k", v.VersionID, ReadOptions{})
+					if !errors.Is(err, errFileVersionNotFound) && !errors.Is(err, errFileNotFound) {
+						t.Fatalf("source version %s remained: %v", v.VersionID, err)
+					}
+				}
+			}
+			if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k", v1.VersionID); body != "older" {
+				t.Fatalf("moved version reads %q", body)
+			}
+			if _, err := z.GetObjectInfo(t.Context(), bucket, "k", ObjectOptions{VersionID: v2.VersionID}); !isErrVersionNotFound(err) {
+				t.Fatalf("concurrently deleted version resurrected: %v", err)
+			}
+		})
+	}
+}
+
+func TestPoolsMigrationSiblingFailureCleanup(t *testing.T) {
+	for _, kind := range []string{"decommission", "rebalance"} {
+		for _, loseDestination := range []bool{false, true} {
+			name := kind + "/destination-retained"
+			if loseDestination {
+				name = kind + "/destination-removed"
+			}
+			t.Run(name, func(t *testing.T) {
+				z, bucket := migrationTestPools(t)
+				v1 := putConsistencyObject(t, z, bucket, "k", 0, "older", ObjectOptions{Versioned: true, MTime: UTCNow().Add(-time.Hour)})
+				v2 := putConsistencyObject(t, z, bucket, "k", 0, "newer", ObjectOptions{Versioned: true})
+				var once sync.Once
+				var deleteErr error
+				before := func() error {
+					once.Do(func() {
+						if loseDestination {
+							_, deleteErr = z.serverPools[1].DeleteObject(t.Context(), bucket, "k", ObjectOptions{VersionID: v1.VersionID})
+						}
+					})
+					return errDiskNotFound // only the sibling's data read fails
+				}
+				restore := conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+					return migrationProgressReadDisk{StorageAPI: d, bucket: bucket, object: "k", version: v2.VersionID, before: before}
+				})
+				defer restore()
+				migrationProgressPrepare(t, z, kind)
+				if kind == "rebalance" {
+					mustIAM(t, z.rebalanceBucket(t.Context(), bucket, 0))
+				} else {
+					_, err := z.decommissionPoolWalk(t.Context(), 0, z.serverPools[0], decomBucketInfo{Name: bucket})
+					mustIAM(t, err)
+					if err := z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: bucket}); err == nil {
+						t.Fatal("failed sibling must block final decommission verification")
+					}
+				}
+				restore()
+				mustIAM(t, deleteErr)
+				if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k", v2.VersionID); body != "newer" {
+					t.Fatalf("failed sibling reads %q", body)
+				}
+				if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k", v1.VersionID); body != "older" {
+					t.Fatalf("successful candidate lost: %q", body)
+				}
+				_, err := z.serverPools[0].GetObjectInfo(t.Context(), bucket, "k", ObjectOptions{VersionID: v1.VersionID})
+				if loseDestination && err != nil || !loseDestination && !isErrVersionNotFound(err) {
+					t.Fatalf("source cleanup ignored destination state: %v", err)
+				}
+			})
+		}
+	}
+}
+
+func TestDecommissionConcurrentParentDeleteRescansChildren(t *testing.T) {
+	z, bucket := migrationTestPools(t)
+	putConsistencyObject(t, z, bucket, "k", 0, "parent", ObjectOptions{})
+	putConsistencyObject(t, z, bucket, "k/b", 0, "child", ObjectOptions{})
+	migrationProgressSnapshot(t, z, bucket, "k")
+	var once sync.Once
+	var deleteErr error
+	t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+		return migrationProgressReadDisk{StorageAPI: d, bucket: bucket, object: "k", version: nullVersionID, before: func() error {
+			once.Do(func() {
+				_, deleteErr = z.DeleteObject(t.Context(), bucket, "k", ObjectOptions{VersionID: nullVersionID})
+			})
+			return deleteErr
+		}}
+	}))
+	if failed := migrationTestWalk(t, z, bucket, 0, "decommission"); failed != 0 {
+		t.Fatalf("failed moves: %d", failed)
+	}
+	mustIAM(t, z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: bucket}))
+	if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k/b", ""); body != "child" {
+		t.Fatalf("child reads %q", body)
+	}
+}
+
+func TestDecommissionDegradedPoolRescansChildren(t *testing.T) {
+	z, bucket := migrationTestPools(t)
+	putConsistencyObject(t, z, bucket, "k", 0, "parent", ObjectOptions{})
+	putConsistencyObject(t, z, bucket, "k/b", 0, "child", ObjectOptions{})
+	var wrapped int
+	t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+		wrapped++
+		if wrapped == 1 {
+			return nil
+		}
+		return d
+	}))
+	if failed := migrationTestWalk(t, z, bucket, 0, "decommission"); failed != 0 {
+		t.Fatalf("failed moves: %d", failed)
+	}
+	mustIAM(t, z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: bucket}))
+	if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k/b", ""); body != "child" {
+		t.Fatalf("child reads %q", body)
+	}
+}
+
+func TestFreeVersionDecommissionRescansChildren(t *testing.T) {
+	f := newFreeVersionTest(t, "")
+	f.bucket = "free-parent"
+	mustIAM(t, f.z.MakeBucket(t.Context(), f.bucket, MakeBucketOptions{VersioningEnabled: true}))
+	f.deleteVersion(f.tiered("k", "parent", UTCNow().Add(-time.Hour)))
+	f.put("k/b", "child", UTCNow())
+	migrationProgressSnapshot(t, f.z, f.bucket, "k")
+	migrationProgressPrepare(t, f.z, "decommission")
+	bi := decomBucketInfo{Name: f.bucket}
+	removed, err := f.z.decommissionPoolWalk(t.Context(), 0, f.z.serverPools[0], bi)
+	if err != nil || removed != 1 {
+		t.Fatalf("free-only parent removal: removed=%d err=%v", removed, err)
+	}
+	if err := f.z.checkAfterDecomBucket(t.Context(), 0, bi); err == nil {
+		t.Fatal("the newly exposed child must still block completion")
+	}
+	mustIAM(t, f.z.decommissionPool(t.Context(), 0, f.z.serverPools[0], bi))
+	mustIAM(t, f.z.checkAfterDecomBucket(t.Context(), 0, bi))
+	if body := migrationTestBody(t, f.z.GetObjectNInfo, f.bucket, "k/b", ""); body != "k/b child" {
+		t.Fatalf("child reads %q", body)
+	}
+	if !slices.Contains(f.tier.removed, f.remote("k", "parent")) {
+		t.Fatal("free version cleanup did not delete its remote object")
+	}
+}
+
+func TestPoolsMigrationCancellation(t *testing.T) {
+	for _, kind := range []string{"decommission", "rebalance"} {
+		for _, phase := range []string{"before-walk", "during-read", "deadline"} {
+			name := kind + "/" + phase
+			t.Run(name, func(t *testing.T) {
+				z, bucket := migrationTestPools(t)
+				oi := putConsistencyObject(t, z, bucket, "k", 0, "source", ObjectOptions{Versioned: true})
+				migrationProgressPrepare(t, z, kind)
+				ctx, cancel := context.WithCancel(t.Context())
+				wantErr := context.Canceled
+				if phase == "deadline" {
+					cancel()
+					ctx, cancel = context.WithDeadline(t.Context(), time.Time{})
+					wantErr = context.DeadlineExceeded
+				}
+				defer cancel()
+				if phase == "during-read" {
+					t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+						return migrationProgressReadDisk{StorageAPI: d, bucket: bucket, object: "k", version: oi.VersionID, before: func() error { cancel(); return ctx.Err() }}
+					}))
+				} else {
+					cancel()
+				}
+				var err error
+				if kind == "decommission" {
+					err = z.decommissionPool(ctx, 0, z.serverPools[0], decomBucketInfo{Name: bucket})
+				} else {
+					err = z.rebalanceBucket(ctx, bucket, 0)
+				}
+				if !errors.Is(err, wantErr) {
+					t.Fatalf("cancellation returned %v", err)
+				}
+				if err := z.decommissionInBackground(ctx, 0); !errors.Is(err, wantErr) {
+					t.Fatalf("canceled background migration returned %v", err)
+				}
+				if err := z.rebalanceBuckets(ctx, 0); !errors.Is(err, wantErr) {
+					t.Fatalf("canceled background rebalance returned %v", err)
+				}
+				if n, err := z.countAbsentMigrationVersions(ctx, bucket, "k", 0, []FileInfo{{VersionID: oi.VersionID}}); n != 0 || !errors.Is(err, wantErr) {
+					t.Fatalf("canceled progress verification: removed=%d err=%v", n, err)
+				}
+				if _, err := z.serverPools[0].GetObjectInfo(t.Context(), bucket, "k", ObjectOptions{VersionID: oi.VersionID}); err != nil {
+					t.Fatalf("canceled migration lost source: %v", err)
+				}
+				if err := z.checkAfterDecomBucket(ctx, 0, decomBucketInfo{Name: bucket}); !errors.Is(err, wantErr) {
+					t.Fatalf("canceled verification returned %v", err)
+				}
+			})
+		}
+	}
+}
+
+type migrationProgressRawDisk struct {
+	StorageAPI
+	buf   []byte
+	err   error
+	reads *atomic.Int32
+}
+
+func (d migrationProgressRawDisk) ReadXL(ctx context.Context, bucket, object string, data bool) (RawFileInfo, error) {
+	d.reads.Add(1)
+	if data {
+		return RawFileInfo{}, errors.New("progress check requested object data")
+	}
+	return RawFileInfo{Buf: d.buf}, d.err
+}
+
+func (d migrationProgressRawDisk) ListDir(context.Context, string, string, string, int) ([]string, error) {
+	return nil, errFileNotFound
+}
+
+func TestPoolsMigrationPhysicalProgress(t *testing.T) {
+	f := newFreeVersionTest(t, "")
+	buf := f.xlMeta(0, "obj-01")
+	versions, err := getFileInfoVersions(buf, f.bucket, "obj-01", true)
+	mustIAM(t, err)
+	if len(versions.Versions) != 3 || !versions.Versions[0].TierFreeVersion() {
+		t.Fatal("fixture must contain two live versions and one free version")
+	}
+	missing := FileInfo{VersionID: mustGetUUID()}
+	snapshot := append(slices.Clone(versions.Versions), missing)
+	for _, tc := range []struct {
+		name    string
+		buf     []byte
+		err     error
+		want    int
+		wantErr bool
+	}{
+		{name: "all-absent", err: errFileNotFound, want: 4},
+		{name: "missing-volume", err: errVolumeNotFound, want: 4},
+		{name: "minority-live-and-free", buf: buf, want: 1},
+		{name: "unavailable", err: errDiskNotFound, wantErr: true},
+		{name: "read-quorum", err: errErasureReadQuorum, wantErr: true},
+		{name: "corrupt-read", err: errFileCorrupt, wantErr: true},
+		{name: "corrupt-metadata", buf: []byte("broken xl.meta"), wantErr: true},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			var reads atomic.Int32
+			disks := make([]StorageAPI, 4)
+			for i := range disks {
+				disks[i] = migrationProgressRawDisk{err: errFileNotFound, reads: &reads}
+			}
+			disks[3] = migrationProgressRawDisk{buf: tc.buf, err: tc.err, reads: &reads}
+			er := erasureObjects{getDisks: func() []StorageAPI { return disks }}
+			n, err := er.countAbsentMigrationVersions(t.Context(), f.bucket, "obj-01", snapshot)
+			if n != tc.want || (err != nil) != tc.wantErr {
+				t.Fatalf("removed=%d err=%v, want %d / error=%t", n, err, tc.want, tc.wantErr)
+			}
+			if reads.Load() != int32(len(disks)) {
+				t.Fatalf("read count %d must not depend on version count", reads.Load())
+			}
+		})
+	}
+	putConsistencyObject(t, f.z, f.bucket, "null", 0, "null-data", ObjectOptions{})
+	nullBuf := f.xlMeta(0, "null")
+	var reads atomic.Int32
+	er := erasureObjects{getDisks: func() []StorageAPI {
+		return []StorageAPI{migrationProgressRawDisk{buf: nullBuf, reads: &reads}}
+	}}
+	if n, err := er.countAbsentMigrationVersions(t.Context(), f.bucket, "null", []FileInfo{{VersionID: nullVersionID}, {VersionID: ""}}); n != 0 || err != nil {
+		t.Fatalf("null version normalization: removed=%d err=%v", n, err)
+	}
+}
+
+func TestCountAbsentMigrationVersionsToleratesConfiguredOfflineDrives(t *testing.T) {
+	makeDisks := func(offlineCount int, asError bool) []StorageAPI {
+		disks := make([]StorageAPI, 4)
+		for i := range disks {
+			disks[i] = migrationProgressRawDisk{err: errFileNotFound, reads: &atomic.Int32{}}
+		}
+		for i := range offlineCount {
+			if asError {
+				disks[i] = migrationProgressRawDisk{err: errDiskNotFound, reads: &atomic.Int32{}}
+			} else {
+				disks[i] = nil
+			}
+		}
+		return disks
+	}
+	snapshot := []FileInfo{{VersionID: mustGetUUID()}}
+	for _, tc := range []struct {
+		name      string
+		offline   int
+		parity    int
+		asError   bool
+		wantCount int
+		wantErr   bool
+	}{
+		{name: "nil-drive-within-parity", offline: 1, parity: 1, wantCount: 1},
+		{name: "read-error-within-parity", offline: 1, parity: 1, asError: true, wantCount: 1},
+		{name: "half-offline-within-parity", offline: 2, parity: 2, wantCount: 1},
+		{name: "offline-beyond-parity", offline: 2, parity: 1, wantErr: true},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			disks := makeDisks(tc.offline, tc.asError)
+			er := erasureObjects{
+				setDriveCount:      len(disks),
+				defaultParityCount: tc.parity,
+				getDisks:           func() []StorageAPI { return disks },
+			}
+			got, err := er.countAbsentMigrationVersions(t.Context(), "bucket", "object", snapshot)
+			if got != tc.wantCount || (err != nil) != tc.wantErr {
+				t.Fatalf("removed=%d err=%v, want %d / error=%t", got, err, tc.wantCount, tc.wantErr)
+			}
+		})
+	}
+}
+
+// A successful quorum deletion can leave one source drive behind. It must not
+// count as physical removal or pass the final check, nor cause a retry loop.
+func TestDecommissionQuorumDeletionIsNotPhysicalProgress(t *testing.T) {
+	z, bucket := migrationTestPools(t)
+	oi := putConsistencyObject(t, z, bucket, "k", 0, "payload", ObjectOptions{Versioned: true})
+	move := migrationTestMover(t, z, 0, "decommission")
+	mustIAM(t, move(t.Context(), 0, bucket, migrationTestReader(t, z, 0, oi)))
+	first := true
+	restore := conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+		if first {
+			first = false
+			return consistencyDeleteFaultDisk{StorageAPI: d, bucket: bucket, object: "k", version: oi.VersionID}
+		}
+		return d
+	})
+	defer restore()
+	snapshot := []FileInfo{{VersionID: oi.VersionID, ModTime: oi.ModTime}}
+	for range 2 {
+		n, err := z.removeMovedVersions(t.Context(), bucket, "k", 0, snapshot, nil)
+		if err != nil || n != 0 {
+			t.Fatalf("partial deletion reported progress: removed=%d err=%v", n, err)
+		}
+	}
+	if err := z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: bucket}); err == nil {
+		t.Fatal("final verification accepted a minority-drive source copy")
+	}
+	if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k", oi.VersionID); body != "payload" {
+		t.Fatalf("destination copy lost: %q", body)
+	}
+}
+
+func TestDecommissionProgressReadFailureStopsWalk(t *testing.T) {
+	z, bucket := migrationTestPools(t)
+	putConsistencyObject(t, z, bucket, "k", 0, "payload", ObjectOptions{Versioned: true})
+	migrationProgressPrepare(t, z, "decommission")
+	walk := migrationProgressSnapshot(t, z, bucket, "k")
+	restore := conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+		return tierReadFaultDisk{StorageAPI: d, bucket: bucket, object: "k", err: errDiskNotFound}
+	})
+	defer restore()
+	if err := z.decommissionPool(t.Context(), 0, z.serverPools[0], decomBucketInfo{Name: bucket}); err == nil {
+		t.Fatal("unreadable source progress check reported success")
+	}
+	if got := walk.calls.Load(); got != walk.drives {
+		t.Fatalf("verification failure repeated the walk: calls=%d", got)
+	}
+	restore()
+	if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k", ""); body != "payload" {
+		t.Fatalf("quorum move lost destination: %q", body)
+	}
+}
+
+type migrationProgressListFaultDisk struct {
+	StorageAPI
+}
+
+func (d migrationProgressListFaultDisk) ListDir(context.Context, string, string, string, int) ([]string, error) {
+	return nil, errDiskAccessDenied
+}
+
+func TestDecommissionFinalVerificationFailsClosed(t *testing.T) {
+	for _, state := range []string{"offline-drive", "directory-error", "corrupt-metadata", "truncated-metadata", "legacy-metadata"} {
+		t.Run(state, func(t *testing.T) {
+			z, bucket := migrationTestPools(t)
+			switch state {
+			case "offline-drive":
+				set := z.serverPools[0].getHashedSet("k")
+				maxOffline := set.defaultParityCount + 1
+				wrapped := 0
+				t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+					wrapped++
+					if wrapped <= maxOffline {
+						return nil
+					}
+					return d
+				}))
+			case "directory-error":
+				t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+					return migrationProgressListFaultDisk{StorageAPI: d}
+				}))
+			default:
+				// Real metadata on only one drive, without a readable quorum.
+				// This also covers errors that WalkDir deliberately skips.
+				disk := z.serverPools[0].getHashedSet("k").getDisks()[0]
+				file, data := xlStorageFormatFile, []byte("broken xl.meta")
+				if state == "truncated-metadata" {
+					data = nil
+				}
+				if state == "legacy-metadata" {
+					file = xlStorageFormatFileV1
+				}
+				mustIAM(t, disk.WriteAll(t.Context(), bucket, pathJoin("k", file), data))
+			}
+			if err := z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: bucket}); err == nil {
+				t.Fatal("unreadable storage was accepted as physically empty")
+			}
+			if n, err := z.countAbsentMigrationVersions(t.Context(), bucket, "k", 0, []FileInfo{{VersionID: mustGetUUID()}}); n != 0 || err == nil {
+				t.Fatalf("unreadable storage was counted as progress: removed=%d err=%v", n, err)
+			}
+		})
+	}
+}
+
+func TestFreeVersionDecommissionPreservesLiveRemoteOwner(t *testing.T) {
+	f := newFreeVersionTest(t, "")
+	const key = "obj-02"
+	fv, tuple := f.freeRecord(0, key)
+	owner := putConsistencyObject(t, f.z, f.bucket, key, 1, "live-owner", ObjectOptions{Versioned: true})
+	infos, errs := readAllFileInfo(t.Context(), f.z.serverPools[1].getHashedSet(key).getDisks(), "", f.bucket, key, owner.VersionID, false, false)
+	mustIAM(t, errs[0])
+	fi := infos[0]
+	fi.TransitionStatus, fi.TransitionTier = lifecycle.TransitionComplete, tuple.Tier
+	fi.TransitionedObjName, fi.TransitionVersionID = tuple.Object, tuple.VersionID
+	mustIAM(t, f.z.serverPools[1].DecomTieredObject(t.Context(), f.bucket, key, fi, ObjectOptions{}))
+	if err := f.z.removeFreeVersions(t.Context(), f.bucket, key, 0, []FileInfo{fv}); !errors.Is(err, errTierStillReferenced) {
+		t.Fatalf("cleanup with a live remote owner: %v", err)
+	}
+	if n, err := f.z.countAbsentMigrationVersions(t.Context(), f.bucket, key, 0, []FileInfo{fv}); err != nil || n != 0 {
+		t.Fatalf("retained free record reported progress: removed=%d err=%v", n, err)
+	}
+	if slices.Contains(f.tier.removed, tuple.Object) {
+		t.Fatal("cleanup deleted a live remote object")
+	}
+	if err := f.z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: f.bucket}); err == nil {
+		t.Fatal("retained free record must block final decommission verification")
+	}
+}

cmd/erasure-server-pool-migration.go

@@ -17,7 +17,147 @@
 
 package cmd
 
-import xhttp "github.com/minio/minio/internal/http"
+import (
+	"context"
+	"errors"
+
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/pgsty/silo-pkg/v3/sync/errgroup"
+)
+
+func migrationVersionKey(versionID string) string {
+	if versionID == "" || versionID == nullVersionID {
+		return nullVersionID
+	}
+	return versionID
+}
+
+// migrationReadQuorum requires enough online drives to intersect every
+// committed write quorum. All of those drives must be checked: a minority
+// remnant still prevents progress. Unknown set geometry tolerates no outages.
+func (er erasureObjects) migrationReadQuorum(diskCount int) int {
+	if er.setDriveCount <= 0 || er.setDriveCount != diskCount || er.defaultParityCount < 0 || er.defaultParityCount > er.setDriveCount/2 {
+		return diskCount
+	}
+	return er.defaultRQuorum()
+}
+
+// countAbsentMigrationVersions counts snapshot versions that no online source drive
+// holds anymore, including free versions. A pool-level NotFound is insufficient:
+// the ordinary read path can return it for inconsistent metadata. Only readable
+// per-drive metadata (or physical absence) proves progress for another walk.
+// The caller holds the object's writer lock while checking the source.
+func (er erasureObjects) countAbsentMigrationVersions(ctx context.Context, bucket, object string, versions []FileInfo) (int, error) {
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	if len(versions) == 0 {
+		return 0, nil
+	}
+	absent := make(map[string]struct{}, len(versions))
+	for _, version := range versions {
+		absent[migrationVersionKey(version.VersionID)] = struct{}{}
+	}
+	disks := er.getDisks()
+	if len(disks) == 0 {
+		return 0, toObjectErr(errErasureReadQuorum, bucket, object)
+	}
+	readQuorum := er.migrationReadQuorum(len(disks))
+	offline := make([]bool, len(disks))
+	stored := make([][]FileInfo, len(disks))
+	g := errgroup.WithNErrs(len(disks))
+	for i := range disks {
+		g.Go(func() error {
+			if disks[i] == nil {
+				offline[i] = true
+				return nil
+			}
+			raw, err := disks[i].ReadXL(ctx, bucket, object, false)
+			if errors.Is(err, errDiskNotFound) {
+				offline[i] = true
+				return nil
+			}
+			if errors.Is(err, errFileNotFound) {
+				// ReadXL also returns NotFound for an empty xl.meta, and may
+				// ignore legacy metadata. Confirm physical absence before using
+				// that result as progress. This does not descend into child keys.
+				// Both reads run in parallel across drives, once per object.
+				entries, err := disks[i].ListDir(ctx, "", bucket, object, -1)
+				if errors.Is(err, errDiskNotFound) {
+					offline[i] = true
+					return nil
+				}
+				if err != nil && !errors.Is(err, errFileNotFound) && !errors.Is(err, errVolumeNotFound) {
+					return err
+				}
+				for _, entry := range entries {
+					if entry == xlStorageFormatFile || entry == xlStorageFormatFileV1 {
+						return errFileCorrupt
+					}
+				}
+				return nil
+			}
+			if errors.Is(err, errVolumeNotFound) {
+				return nil
+			}
+			if err != nil {
+				return err
+			}
+			// allParts=false omits part details, not free versions. Decode every
+			// version before concluding absence, so corrupt metadata fails closed.
+			fivs, err := getAllFileInfoVersions(raw.Buf, bucket, object, false)
+			stored[i] = fivs.Versions
+			return err
+		}, i)
+	}
+	errs := g.Wait()
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	for i, err := range errs {
+		if err != nil {
+			return 0, toObjectErr(err, bucket, object)
+		}
+		for _, version := range stored[i] {
+			delete(absent, migrationVersionKey(version.VersionID))
+		}
+	}
+	offlineCount := 0
+	for _, unavailable := range offline {
+		if unavailable {
+			offlineCount++
+		}
+	}
+	if len(disks)-offlineCount < readQuorum {
+		return 0, toObjectErr(errErasureReadQuorum, bucket, object)
+	}
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	return len(absent), nil
+}
+
+// countAbsentMigrationVersions checks ignored walk entries without authorizing
+// their deletion. A concurrent client delete may have uncovered child keys.
+func (z *erasureServerPools) countAbsentMigrationVersions(ctx context.Context, bucket, object string, source int, versions []FileInfo) (int, error) {
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	if len(versions) == 0 {
+		return 0, nil
+	}
+	object = encodeDirObject(object)
+	lk := z.NewNSLock(bucket, object)
+	lkctx, err := lk.GetLock(ctx, globalOperationTimeout)
+	if err != nil {
+		if ctx.Err() != nil {
+			return 0, ctx.Err()
+		}
+		return 0, err
+	}
+	defer lk.Unlock(lkctx)
+	return z.serverPools[source].getHashedSet(object).countAbsentMigrationVersions(lkctx.Context(), bucket, object, versions)
+}
 
 // migrationObjectMetadata restores tags removed from the read representation.
 // Keep the original revision, including ordered empty states, for the existing

cmd/erasure-server-pool-multipart-lock-order_test.go

@@ -0,0 +1,205 @@
+// Copyright (c) 2026 PGSTY
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"sync"
+	"testing"
+	"time"
+
+	xhttp "github.com/minio/minio/internal/http"
+)
+
+type copyPartSourceContextKey struct{}
+
+// Pause the HTTP copy after the real reader has acquired its source lock.
+// IAM and other background readers do not carry the request's context key.
+type copyPartSourceGate struct {
+	ObjectLayer
+	opened, release chan struct{}
+}
+
+func (a *copyPartSourceGate) GetObjectNInfo(ctx context.Context, bucket, object string, rs *HTTPRangeSpec, h http.Header, opts ObjectOptions) (*GetObjectReader, error) {
+	gr, err := a.ObjectLayer.GetObjectNInfo(ctx, bucket, object, rs, h, opts)
+	if err != nil || ctx.Value(copyPartSourceContextKey{}) != true {
+		return gr, err
+	}
+	close(a.opened)
+	select {
+	case <-a.release:
+		return gr, nil
+	case <-ctx.Done():
+		gr.Close()
+		return nil, ctx.Err()
+	}
+}
+
+func copyPartLockRefs(l *localLockInstance) int32 {
+	l.ns.lockMapMutex.Lock()
+	defer l.ns.lockMapMutex.Unlock()
+	if lock := l.ns.lockMap[pathJoin(l.volume, l.paths[0])]; lock != nil {
+		return lock.ref
+	}
+	return 0
+}
+
+// A copy from the upload's own key holds object RLock before asking for the
+// upload RLock. Complete must wait for that reader without holding upload
+// Lock, on both single- and multi-pool backends. Cancellation of either
+// request must release its locks and let the other request finish.
+func TestUploadPartCopyConcurrentComplete(t *testing.T) {
+	for _, pools := range []int{1, 2} {
+		for _, action := range []string{"complete", "cancel-copy", "cancel-complete"} {
+			t.Run(fmt.Sprintf("pools=%d/%s", pools, action), func(t *testing.T) {
+				z, _ := bulkDeletePools(t, pools)
+				ctx, cancel := context.WithTimeout(t.Context(), 15*time.Second)
+				var workers sync.WaitGroup
+				defer func() { cancel(); workers.Wait() }()
+				api := &copyPartSourceGate{ObjectLayer: z, opened: make(chan struct{}), release: make(chan struct{})}
+				bucket, router, err := initAPIHandlerTest(ctx, api, nil, MakeBucketOptions{})
+				if err != nil {
+					t.Fatal(err)
+				}
+				setObjectLayer(api)
+				const key = "copy-part-self"
+				data := bytes.Repeat([]byte("existing source bytes"), 32768)
+				oi, err := z.PutObject(ctx, bucket, key, mustGetPutObjReader(t, bytes.NewReader(data), int64(len(data)), "", ""), ObjectOptions{})
+				if err != nil {
+					t.Fatal(err)
+				}
+				if oi.Inlined {
+					t.Fatal("the source must retain its read lock until its reader closes")
+				}
+				upload, err := z.NewMultipartUpload(ctx, bucket, key, ObjectOptions{})
+				if err != nil {
+					t.Fatal(err)
+				}
+				first := []byte("the completed part")
+				part, err := z.PutObjectPart(ctx, bucket, key, upload.UploadID, 1, mustGetPutObjReader(t, bytes.NewReader(first), int64(len(first)), "", ""), ObjectOptions{})
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				objectLock := z.NewObjectNSLock(bucket, key).(*localLockInstance)
+				uploadLock := z.uploadIDNSLock(bucket, key, upload.UploadID).(*localLockInstance)
+				copyCtx, cancelCopy := context.WithCancel(context.WithValue(ctx, copyPartSourceContextKey{}, true))
+				defer cancelCopy()
+				req, err := newTestSignedRequestV4(http.MethodPut, getPutObjectPartURL("", bucket, key, upload.UploadID, "2"), 0, nil, globalActiveCred.AccessKey, globalActiveCred.SecretKey, map[string]string{xhttp.AmzCopySource: "/" + bucket + "/" + key})
+				if err != nil {
+					t.Fatal(err)
+				}
+				copyDone := make(chan *httptest.ResponseRecorder, 1)
+				workers.Go(func() {
+					rec := httptest.NewRecorder()
+					router.ServeHTTP(rec, req.WithContext(copyCtx))
+					copyDone <- rec
+				})
+				select {
+				case <-api.opened:
+				case <-ctx.Done():
+					t.Fatal("COPY did not open its source")
+				}
+				if refs := copyPartLockRefs(objectLock); refs != 1 {
+					t.Fatalf("COPY object lock references = %d, want 1", refs)
+				}
+
+				completeCtx, cancelComplete := context.WithCancel(ctx)
+				defer cancelComplete()
+				completeDone := make(chan error, 1)
+				workers.Go(func() {
+					_, err := z.CompleteMultipartUpload(completeCtx, bucket, key, upload.UploadID, []CompletePart{{PartNumber: 1, ETag: part.ETag}}, ObjectOptions{})
+					completeDone <- err
+				})
+				// One reference belongs to COPY, the second to Complete waiting
+				// for it. Check the actual lock resources, not elapsed time.
+				ticker := time.NewTicker(time.Millisecond)
+				defer ticker.Stop()
+				for copyPartLockRefs(objectLock) != 2 {
+					select {
+					case err := <-completeDone:
+						t.Fatalf("Complete exited before waiting for COPY: %v", err)
+					case <-ctx.Done():
+						t.Fatal("Complete did not wait for the source object lock")
+					case <-ticker.C:
+					}
+				}
+				if refs := copyPartLockRefs(uploadLock); refs != 0 {
+					t.Fatalf("Complete holds the upload lock while waiting for COPY's object lock: refs=%d", refs)
+				}
+
+				if action == "cancel-complete" {
+					cancelComplete()
+					select {
+					case err := <-completeDone:
+						if !errors.Is(err, context.Canceled) {
+							t.Fatalf("canceled Complete: %v", err)
+						}
+					case <-ctx.Done():
+						t.Fatal("Complete did not cancel while COPY held the source")
+					}
+				}
+				if action == "cancel-copy" {
+					cancelCopy()
+				} else {
+					close(api.release)
+				}
+				select {
+				case rec := <-copyDone:
+					want := http.StatusOK
+					if action == "cancel-copy" {
+						want = 499
+					}
+					if rec.Code != want {
+						t.Fatalf("COPY: %d, want %d: %s", rec.Code, want, rec.Body.String())
+					}
+				case <-ctx.Done():
+					t.Fatal("COPY did not finish")
+				}
+				if action != "cancel-complete" {
+					select {
+					case err := <-completeDone:
+						if err != nil {
+							t.Fatalf("Complete after source release: %v", err)
+						}
+					case <-ctx.Done():
+						t.Fatal("Complete did not finish after source release")
+					}
+				}
+				if copyPartLockRefs(objectLock) != 0 || copyPartLockRefs(uploadLock) != 0 {
+					t.Fatal("request left an object or upload lock behind")
+				}
+				wantBody := string(first)
+				if action == "cancel-complete" {
+					wantBody = string(data)
+					if _, err := z.GetMultipartInfo(ctx, bucket, key, upload.UploadID, ObjectOptions{}); err != nil {
+						t.Fatalf("canceled completion lost the upload: %v", err)
+					}
+				}
+				if body := bulkDeleteBody(t, z, bucket, key, ""); body != wantBody {
+					t.Fatalf("object body length = %d, want %d", len(body), len(wantBody))
+				}
+			})
+		}
+	}
+}

cmd/erasure-server-pool-put-conditional_test.go

@@ -590,9 +590,9 @@ func TestSinglePoolConditionalPutHTTP(t *testing.T) {
 	}
 }
 
-// An internal replica callback without an addressed version is not a public
-// condition. Preserve its availability when another pool is unreadable. An
-// addressed replica already requires all pools for lock/tag reconciliation.
+// Replica overwrites must establish protection across every pool, including
+// the null version of an unversioned request. An unreadable pool may hold a
+// protected copy, so neither addressed nor unaddressed writes may replace it.
 func TestPoolsConditionalPutReplicaAvailability(t *testing.T) {
 	for _, addressed := range []bool{false, true} {
 		t.Run(fmt.Sprintf("addressed=%t", addressed), func(t *testing.T) {
@@ -615,10 +615,9 @@ func TestPoolsConditionalPutReplicaAvailability(t *testing.T) {
 				xhttp.MinIOSourceETag:               fmt.Sprintf("%x", md5.Sum([]byte("replacement"))),
 			}
 			url := getPutObjectURL("", bucket, object)
-			wantStatus, wantBody := http.StatusOK, "replacement"
+			wantStatus, wantBody := http.StatusServiceUnavailable, "old"
 			if addressed {
 				url += "?versionId=" + oi.VersionID
-				wantStatus, wantBody = http.StatusServiceUnavailable, "old"
 			}
 			put := multipartConditionRequest(t, router, http.MethodPut, url, "replacement", headers)
 			if put.Code != wantStatus {

cmd/erasure-server-pool-rebalance.go

@@ -376,6 +376,9 @@ func (z *erasureServerPools) IsPoolRebalancing(poolIndex int) bool {
 }
 
 func (z *erasureServerPools) rebalanceBuckets(ctx context.Context, poolIdx int) (err error) {
+	if err := ctx.Err(); err != nil {
+		return err
+	}
 	doneCh := make(chan error, 1)
 	defer xioutil.SafeClose(doneCh)
 
@@ -450,7 +453,7 @@ func (z *erasureServerPools) rebalanceBuckets(ctx context.Context, poolIdx int)
 		select {
 		case <-ctx.Done():
 			doneCh <- ctx.Err()
-			return err
+			return ctx.Err()
 		default:
 		}
 
@@ -474,6 +477,10 @@ func (z *erasureServerPools) rebalanceBuckets(ctx context.Context, poolIdx int)
 		z.bucketRebalanceDone(bucket, poolIdx)
 	}
 
+	if err := ctx.Err(); err != nil {
+		doneCh <- err
+		return err
+	}
 	rebalanceLogEvent(GlobalContext, "Pool %d rebalancing is done", poolIdx+1)
 
 	return err
@@ -538,6 +545,9 @@ func (set *erasureObjects) listObjectsToRebalance(ctx context.Context, bucketNam
 
 // rebalanceBucket rebalances objects under bucket in poolIdx pool
 func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string, poolIdx int) (err error) {
+	if err := ctx.Err(); err != nil {
+		return err
+	}
 	ctx = logger.SetReqInfo(ctx, &logger.ReqInfo{})
 
 	var vc *versioning.Versioning
@@ -643,7 +653,7 @@ func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string,
 			// to create the appropriate stack.
 			versionsSorter(fivs.Versions).reverse()
 
-			var rebalanced int
+			var candidates []FileInfo
 			var expired []migrationExpiredVersion
 			// The key's history in all pools, read once for its versions.
 			var history migrationHistory
@@ -658,12 +668,8 @@ func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string,
 
 				// Apply lifecycle rules on the objects that are expired.
 				if action := filterLifecycle(bucket, version.Name, version, &history); action.Delete() {
-					// Count the version, or the source copies of the moved
-					// ones stay behind as duplicates. Its own source copy
-					// goes with them when ILM deletes it alone; any other
-					// version stays until the expiry has run.
-					rebalanced++
 					if ilmDeletesVersionOnly(action) || action.DeleteAll() {
+						candidates = append(candidates, version)
 						expired = append(expired, migrationExpiredVersion{
 							version:            version,
 							event:              lifecycle.Event{Action: action},
@@ -706,7 +712,6 @@ func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string,
 						// This can happen when rebalance stop races with ongoing rebalance workers.
 						// These rebalance failures can be ignored.
 						if isErrObjectNotFound(err) || isErrVersionNotFound(err) || isDataMovementOverWriteErr(err) {
-							ignore = true
 							stopFn(0, nil)
 							continue
 						}
@@ -716,7 +721,7 @@ func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string,
 					failure = err != nil
 					if !failure {
 						z.updatePoolStats(poolIdx, bucket, version)
-						rebalanced++
+						candidates = append(candidates, version)
 					}
 					auditLogRebalance(ctx, "Rebalance:DeleteMarker", bucket, version.Name, versionID, err)
 					continue
@@ -773,13 +778,14 @@ func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string,
 					break // break out on first error
 				}
 				z.updatePoolStats(poolIdx, bucket, version)
-				rebalanced++
+				candidates = append(candidates, version)
 			}
 
-			// if all versions were rebalanced, we can delete the object versions.
-			if rebalanced == len(fivs.Versions) {
+			// A skipped or failed sibling does not prevent retiring successful
+			// moves. Cleanup still rechecks each candidate and its destination.
+			if len(candidates) > 0 {
 				stopFn := globalRebalanceMetrics.log(rebalanceMetricRebalanceRemoveObject, poolIdx, bucket, entry.name)
-				err := z.removeMovedVersions(ctx, bucket, entry.name, poolIdx, fivs.Versions, expired)
+				_, err := z.removeMovedVersions(ctx, bucket, entry.name, poolIdx, candidates, expired)
 				stopFn(0, err)
 				auditLogRebalance(ctx, "Rebalance:DeleteObject", bucket, entry.name, "", err)
 				if err != nil {
@@ -806,7 +812,7 @@ func (z *erasureServerPools) rebalanceBucket(ctx context.Context, bucket string,
 	}
 
 	wk.Wait()
-	return nil
+	return ctx.Err()
 }
 
 type rebalSaveOpts uint8

cmd/erasure-server-pool.go

@@ -26,6 +26,7 @@ import (
 	"math/rand"
 	"net/http"
 	"path"
+	"slices"
 	"sort"
 	"strconv"
 	"strings"
@@ -1194,6 +1195,7 @@ func (z *erasureServerPools) PutObject(ctx context.Context, bucket string, objec
 	if opts.replicaObjectInfo == nil && (opts.ReplicaLockReconcile || !opts.ReplicationRequest) {
 		opts.replicaObjectInfo = z.replicaObjectInfo
 	}
+	opts.replicaContentGuard = z.guardReplicaContent
 	oi, err := z.serverPools[idx].PutObject(ctx, bucket, object, data, opts)
 	if err == nil && opts.ReplicaLockReconcile && !opts.DataMovement {
 		err = z.retireReplicaCopies(ctx, bucket, object, idx, oi)
@@ -1318,7 +1320,9 @@ func (z *erasureServerPools) DeleteObject(ctx context.Context, bucket string, ob
 	approvedExpiry := opts.Expiration.Expire && opts.Expiration.CheckedAllPools && !opts.Transition.ExpireRestored
 	reconcileVersion := opts.VersionID != "" && !opts.DataMovement &&
 		(!opts.ReplicationRequest || opts.isVersionPurge()) && (!opts.Expiration.Expire || approvedExpiry) && !opts.InclFreeVersions
-	if !z.SinglePool() && (opts.CheckPrecondFn != nil || reconcileVersion) {
+	reconcileUnaddressedLock := opts.VersionID == "" && !opts.Versioned && !opts.DeleteMarker &&
+		opts.RefuseLockedOverwrite && !opts.DataMovement && !opts.ReplicationRequest && !opts.Expiration.Expire && !opts.InclFreeVersions
+	if !z.SinglePool() && (opts.CheckPrecondFn != nil || reconcileVersion || reconcileUnaddressedLock) {
 		return z.deleteObjectReconciled(ctx, bucket, object, opts)
 	}
 
@@ -1543,6 +1547,27 @@ func (z *erasureServerPools) DeleteObjects(ctx context.Context, bucket string, o
 		objSets.Add(objects[i].ObjectName)
 	}
 
+	// A name that fails the check keeps its error and goes no further. Joined
+	// to the bucket it can name a path in another bucket or in the meta
+	// bucket, so it is not locked, looked up or sent to a drive. The other
+	// names are deleted as a request of their own: everything below sees only
+	// names that passed.
+	if slices.ContainsFunc(derrs, func(err error) bool { return err != nil }) {
+		valid, at := make([]ObjectToDelete, 0, len(objects)), make([]int, 0, len(objects))
+		for i, obj := range objects {
+			if derrs[i] == nil {
+				valid, at = append(valid, obj), append(at, i)
+			}
+		}
+		if len(valid) > 0 {
+			deleted, errs := z.DeleteObjects(ctx, bucket, valid, opts)
+			for j, i := range at {
+				dobjects[i], derrs[i] = deleted[j], errs[j]
+			}
+		}
+		return dobjects, derrs
+	}
+
 	// A single pool locks each name in the set its writers lock it in, one
 	// set at a time. A single node keeps one lock table for all sets, so it
 	// keeps the one bulk lock below: its local lock takes the names one by
@@ -1666,6 +1691,51 @@ func (z *erasureServerPools) DeleteObjects(ctx context.Context, bucket string, o
 	return dobjects, derrs
 }
 
+// copyObjectPlan fixes placement before a caller prepares encrypted or compressed
+// bytes. A reference can only be made in the pool holding the source version.
+type copyObjectPlan struct {
+	poolIdx int
+	rewrite bool
+}
+
+// prepareCopyObject requires the same source/destination locks as CopyObject.
+// In-place changes address the exact version; new versions retain the normal
+// write placement and rewrite the data when it lives in a different pool.
+func (z *erasureServerPools) prepareCopyObject(ctx context.Context, srcBucket, srcObject, dstBucket, dstObject string, srcInfo ObjectInfo, srcOpts, dstOpts ObjectOptions) (copyObjectPlan, error) {
+	if err := checkCopyObjArgs(ctx, dstBucket, dstObject); err != nil {
+		return copyObjectPlan{}, err
+	}
+	srcObject, dstObject = encodeDirObject(srcObject), encodeDirObject(dstObject)
+	sameObject := isStringEqual(pathJoin(srcBucket, srcObject), pathJoin(dstBucket, dstObject))
+	reference := sameObject && !copyRewritesObjectData(srcInfo.metadataOnly && !srcInfo.Legacy, srcOpts, dstOpts)
+	inPlace := reference && (dstOpts.VersionID != "" && srcOpts.VersionID == dstOpts.VersionID || !dstOpts.Versioned && srcOpts.VersionID == "")
+	if inPlace {
+		// Metadata must stay with the authoritative source bytes, including
+		// when that pool is draining. Write allocation could select a stale
+		// duplicate and later retire the only current copy.
+		sourceOpts := srcOpts
+		sourceOpts.NoLock = true
+		sourceOpts.Transition = dstOpts.Transition
+		_, idx, err := z.getLatestObjectInfoWithIdx(ctx, srcBucket, srcObject, sourceOpts)
+		return copyObjectPlan{poolIdx: idx}, err
+	}
+	idx, err := z.getPoolIdxNoLock(ctx, dstBucket, dstObject, srcInfo.Size)
+	if err != nil {
+		return copyObjectPlan{}, err
+	}
+	plan := copyObjectPlan{poolIdx: idx}
+	if reference && !z.SinglePool() {
+		sourceOpts := srcOpts
+		sourceOpts.NoLock = true
+		_, sourcePool, err := z.getLatestObjectInfoWithIdx(ctx, srcBucket, srcObject, sourceOpts)
+		if err != nil {
+			return copyObjectPlan{}, err
+		}
+		plan.rewrite = sourcePool != idx
+	}
+	return plan, nil
+}
+
 func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObject, dstBucket, dstObject string, srcInfo ObjectInfo, srcOpts, dstOpts ObjectOptions) (objInfo ObjectInfo, err error) {
 	if err := checkCopyObjArgs(ctx, srcBucket, srcObject); err != nil {
 		return ObjectInfo{}, err
@@ -1692,6 +1762,15 @@ func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObjec
 		dstOpts.NoLock = true
 	}
 
+	if dstOpts.copyPlan == nil {
+		plan, err := z.prepareCopyObject(ctx, srcBucket, srcObject, dstBucket, dstObject, srcInfo, srcOpts, dstOpts)
+		if err != nil {
+			return ObjectInfo{}, err
+		}
+		dstOpts.copyPlan = &plan
+	}
+	poolIdx := dstOpts.copyPlan.poolIdx
+
 	if !z.SinglePool() && cpSrcDstSame && srcInfo.metadataOnly && dstOpts.ReplicaLockReconcile && srcOpts.VersionID == dstOpts.VersionID {
 		copies, err := z.metadataPoolInfos(ctx, dstBucket, dstObject, dstOpts)
 		if err != nil {
@@ -1700,7 +1779,8 @@ func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObjec
 		stored := mergedPoolObjectInfo(copies)
 		reconcileStoredObjectLock(srcInfo.UserDefined, storedObjectLockState(stored.UserDefined))
 		reconcileStoredObjectTags(srcInfo.UserDefined, stored.UserTags, stored.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp])
-		idx := copies[0].Index
+		dstOpts.replicaObjectInfo = z.replicaObjectInfo
+		idx := poolIdx
 		oi, err := z.serverPools[idx].CopyObject(ctx, srcBucket, srcObject, dstBucket, dstObject, srcInfo, srcOpts, dstOpts)
 		if err == nil {
 			err = z.retireReplicaCopies(ctx, dstBucket, dstObject, idx, oi)
@@ -1708,25 +1788,9 @@ func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObjec
 		return oi, err
 	}
 
-	var poolIdx int
-	if dstOpts.MetadataChg && cpSrcDstSame && srcInfo.metadataOnly && srcOpts.VersionID == dstOpts.VersionID {
-		// Restore status updates address an existing version. Keep ordinary
-		// copy/write allocation unchanged, including its latest-version lookup.
-		poolIdx, err = z.getPoolIdxExistingWithOpts(ctx, dstBucket, dstObject, ObjectOptions{
-			VersionID:          dstOpts.VersionID,
-			MetadataChg:        true,
-			NoLock:             true,
-			Transition:         dstOpts.Transition,
-			SkipDecommissioned: true,
-			SkipRebalancing:    true,
-		})
-	} else {
-		poolIdx, err = z.getPoolIdxNoLock(ctx, dstBucket, dstObject, srcInfo.Size)
+	if !z.SinglePool() {
+		dstOpts.replicaContentGuard = z.guardReplicaContent
 	}
-	if err != nil {
-		return objInfo, err
-	}
-
 	if !z.SinglePool() && (dstOpts.ReplicaLockReconcile || !dstOpts.ReplicationRequest) {
 		dstOpts.replicaObjectInfo = z.replicaObjectInfo
 		if dstOpts.ReplicaLockReconcile && !dstOpts.DataMovement {
@@ -1738,9 +1802,7 @@ func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObjec
 		}
 	}
 
-	// CopyObjectHandler predicts the outcome of this decision in
-	// copyRewritesObjectData(); keep the two in sync.
-	if cpSrcDstSame && srcInfo.metadataOnly {
+	if cpSrcDstSame && !copyRewritesObjectData(srcInfo.metadataOnly && !srcInfo.Legacy, srcOpts, dstOpts) {
 		// Version ID is set for the destination and source == destination version ID.
 		if dstOpts.VersionID != "" && srcOpts.VersionID == dstOpts.VersionID {
 			return z.serverPools[poolIdx].CopyObject(ctx, srcBucket, srcObject, dstBucket, dstObject, srcInfo, srcOpts, dstOpts)
@@ -1762,6 +1824,10 @@ func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObjec
 		}
 	}
 
+	if srcInfo.PutObjReader == nil {
+		return ObjectInfo{}, errInvalidArgument
+	}
+
 	putOpts := ObjectOptions{
 		ServerSideEncryption:       dstOpts.ServerSideEncryption,
 		UserDefined:                srcInfo.UserDefined,
@@ -1771,12 +1837,15 @@ func (z *erasureServerPools) CopyObject(ctx context.Context, srcBucket, srcObjec
 		MTime:                      dstOpts.MTime,
 		NoLock:                     true,
 		EncryptFn:                  dstOpts.EncryptFn,
+		IndexCB:                    dstOpts.IndexCB,
 		WantChecksum:               dstOpts.WantChecksum,
 		WantServerSideChecksumType: dstOpts.WantServerSideChecksumType,
+		PreserveETag:               dstOpts.PreserveETag,
 		ReplicationRequest:         dstOpts.ReplicationRequest,
 		ReplicaLockReconcile:       dstOpts.ReplicaLockReconcile,
 		DataMovement:               dstOpts.DataMovement,
 		replicaObjectInfo:          dstOpts.replicaObjectInfo,
+		replicaContentGuard:        dstOpts.replicaContentGuard,
 	}
 
 	return z.serverPools[poolIdx].PutObject(ctx, dstBucket, dstObject, srcInfo.PutObjReader, putOpts)
@@ -2437,21 +2506,21 @@ func (z *erasureServerPools) CompleteMultipartUpload(ctx context.Context, bucket
 		}
 	}()
 
-	// Several pools take the object lock first, then the upload lock below.
-	// A single pool takes the upload lock here and the set takes the object
-	// lock, in the object's own erasure set, only right before it commits.
-	if !z.SinglePool() {
-		if !opts.NoLock {
-			lk := z.NewObjectNSLock(bucket, encodeDirObject(object))
-			lkctx, err := lk.GetLock(ctx, globalOperationTimeout)
-			if err != nil {
-				return objInfo, err
-			}
-			ctx = lkctx.Context()
-			defer lk.Unlock(lkctx)
+	// Take the object lock before the upload lock for every pool count.
+	// UploadPartCopy holds its source read lock while it reads upload
+	// metadata, including when the source and destination are the same key.
+	if !opts.NoLock {
+		lk := z.NewObjectNSLock(bucket, encodeDirObject(object))
+		lkctx, err := lk.GetLock(ctx, globalOperationTimeout)
+		if err != nil {
+			return objInfo, err
 		}
-		opts.NoLock = true
+		ctx = lkctx.Context()
+		defer lk.Unlock(lkctx)
+	}
+	opts.NoLock = true
 
+	if !z.SinglePool() {
 		// A conditional completion must be evaluated against the logical
 		// latest object across pools, under the object write lock held for
 		// this operation. The pool hosting the upload may only hold a stale
@@ -2502,6 +2571,7 @@ func (z *erasureServerPools) CompleteMultipartUpload(ctx context.Context, bucket
 		opts.replicaObjectInfo = z.replicaObjectInfo
 	}
 
+	opts.replicaContentGuard = z.guardReplicaContent
 	for idx, pool := range z.serverPools {
 		if z.IsSuspended(idx) {
 			continue
@@ -3345,7 +3415,7 @@ func (z *erasureServerPools) PutObjectTags(ctx context.Context, bucket, object s
 	// revision beyond all copies, so the returned value and every pool agree.
 	if stamp := opts.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp]; stamp != "" {
 		for _, copy := range copies {
-			stamp = monotonicTaggingTimestamp(stamp, copy.ObjInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp])
+			stamp = monotonicMetadataTimestamp(stamp, copy.ObjInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp])
 		}
 		opts.UserDefined = cloneMSS(opts.UserDefined)
 		opts.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp] = stamp

cmd/erasure-sets.go

@@ -844,7 +844,7 @@ func (s *erasureSets) CopyObject(ctx context.Context, srcBucket, srcObject, dstB
 	// Check if this request is only metadata update.
 	// CopyObjectHandler predicts the outcome of this decision in
 	// copyRewritesObjectData(); keep the two in sync.
-	if cpSrcDstSame && srcInfo.metadataOnly {
+	if cpSrcDstSame && srcInfo.metadataOnly && !srcInfo.Legacy {
 		// Version ID is set for the destination and source == destination version ID.
 		// perform an in-place update.
 		if dstOpts.VersionID != "" && srcOpts.VersionID == dstOpts.VersionID {
@@ -868,6 +868,10 @@ func (s *erasureSets) CopyObject(ctx context.Context, srcBucket, srcObject, dstB
 		}
 	}
 
+	if srcInfo.PutObjReader == nil {
+		return ObjectInfo{}, errInvalidArgument
+	}
+
 	putOpts := ObjectOptions{
 		ServerSideEncryption:       dstOpts.ServerSideEncryption,
 		UserDefined:                srcInfo.UserDefined,
@@ -879,10 +883,12 @@ func (s *erasureSets) CopyObject(ctx context.Context, srcBucket, srcObject, dstB
 		EncryptFn:                  dstOpts.EncryptFn,
 		WantChecksum:               dstOpts.WantChecksum,
 		WantServerSideChecksumType: dstOpts.WantServerSideChecksumType,
+		PreserveETag:               dstOpts.PreserveETag,
 		ReplicationRequest:         dstOpts.ReplicationRequest,
 		ReplicaLockReconcile:       dstOpts.ReplicaLockReconcile,
 		DataMovement:               dstOpts.DataMovement,
 		replicaObjectInfo:          dstOpts.replicaObjectInfo,
+		replicaContentGuard:        dstOpts.replicaContentGuard,
 	}
 
 	return dstSet.putObject(ctx, dstBucket, dstObject, srcInfo.PutObjReader, putOpts)

cmd/iam-import-state_test.go

@@ -0,0 +1,196 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"archive/zip"
+	"bytes"
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/auth"
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+func iamImportArchive(t *testing.T, assets map[string]any) []byte {
+	t.Helper()
+	var buf bytes.Buffer
+	zw := zip.NewWriter(&buf)
+	for name, value := range assets {
+		w, err := zw.Create(pathJoin(iamAssetsDir, name))
+		mustIAM(t, err)
+		mustIAM(t, json.NewEncoder(w).Encode(value))
+	}
+	mustIAM(t, zw.Close())
+	return buf.Bytes()
+}
+
+func iamImportCall(t *testing.T, data []byte) *httptest.ResponseRecorder {
+	t.Helper()
+	req, err := newTestSignedRequestV4(http.MethodPut, "http://localhost/minio/admin/v3/import-iam-v2", int64(len(data)), bytes.NewReader(data), globalActiveCred.AccessKey, globalActiveCred.SecretKey, nil)
+	mustIAM(t, err)
+	mustIAM(t, req.ParseForm())
+	rec := httptest.NewRecorder()
+	adminAPIHandlers{}.ImportIAMV2(rec, req.WithContext(newContext(req, rec, "ImportIAM")))
+	if rec.Code != http.StatusOK {
+		t.Fatalf("import-iam-v2: %d %s", rec.Code, rec.Body.String())
+	}
+	return rec
+}
+
+func TestIAMImportExportState(t *testing.T) {
+	for _, target := range []string{"fresh", "existing"} {
+		t.Run(target, func(t *testing.T) {
+			ctx, sys := iamAdminFixture(t)
+			parent := iamAdminUser(ctx, t, sys, "import-parent", "")
+			for _, status := range []string{statusDisabled, statusEnabled} {
+				group := "import-" + status
+				_, err := sys.AddUsersToGroup(ctx, group, []string{parent.AccessKey})
+				mustIAM(t, err)
+				_, err = sys.SetGroupStatus(ctx, group, status == statusEnabled)
+				mustIAM(t, err)
+			}
+			_, err := sys.PolicyDBSet(ctx, "import-disabled", "readwrite", regUser, true)
+			mustIAM(t, err)
+			sp, err := policy.ParseConfig(strings.NewReader(svcAccEditPolicy))
+			mustIAM(t, err)
+			expires := UTCNow().Add(time.Hour).Truncate(time.Second)
+			_, _, err = sys.NewServiceAccount(ctx, parent.AccessKey, nil, newServiceAccountOpts{
+				accessKey: "import-service", secretKey: "import-service-secret", status: auth.AccountOff,
+				sessionPolicy: sp, expiration: &expires, name: "disabled service", claims: map[string]any{"identity-attribute": "preserved"},
+			})
+			mustIAM(t, err)
+			exported := iamAdminCall(t, globalActiveCred, http.MethodGet, "/minio/admin/v3/export-iam", nil, nil, adminAPIHandlers{}.ExportIAM)
+			if exported.Code != http.StatusOK {
+				t.Fatalf("export-iam: %d %s", exported.Code, exported.Body.String())
+			}
+			if target == "fresh" {
+				ctx, sys = iamAdminFixture(t)
+			} else {
+				// Import must also replace an existing enabled account/group and
+				// restore an enabled group that is disabled on the target.
+				_, err = sys.UpdateServiceAccount(ctx, "import-service", updateServiceAccountOpts{status: auth.AccountOn})
+				mustIAM(t, err)
+				_, err = sys.SetGroupStatus(ctx, "import-disabled", true)
+				mustIAM(t, err)
+				_, err = sys.SetGroupStatus(ctx, "import-enabled", false)
+				mustIAM(t, err)
+			}
+			rec := iamImportCall(t, exported.Body.Bytes())
+			var result madmin.ImportIAMResult
+			mustIAM(t, json.Unmarshal(rec.Body.Bytes(), &result))
+			if len(result.Failed.Groups) != 0 || len(result.Failed.ServiceAccounts) != 0 || len(result.Added.ServiceAccounts) != 1 {
+				t.Fatalf("import did not restore the exported entities: %s", rec.Body.String())
+			}
+			mustIAM(t, sys.store.LoadIAMCache(ctx, false))
+			for _, status := range []string{statusDisabled, statusEnabled} {
+				group, err := sys.GetGroupDescription("import-" + status)
+				mustIAM(t, err)
+				if group.Status != status || len(group.Members) != 1 || group.Members[0] != parent.AccessKey {
+					t.Fatalf("group status or members changed: %+v", group)
+				}
+			}
+			if sys.IsAllowed(policy.Args{AccountName: parent.AccessKey, Action: policy.GetObjectAction, BucketName: "edit", ObjectName: "object"}) {
+				t.Error("the disabled imported group grants access")
+			}
+			cr, gotPolicy, err := sys.GetServiceAccount(ctx, "import-service")
+			mustIAM(t, err)
+			if cr.Status != auth.AccountOff || !cr.Expiration.Equal(expires) || cr.Name != "disabled service" || gotPolicy == nil || !gotPolicy.Equals(*sp) {
+				t.Fatal("import changed the service account status, expiration, name or inline policy")
+			}
+			if _, valid, err := sys.CheckKey(ctx, "import-service"); err != nil || valid {
+				t.Fatalf("imported disabled credential is usable: valid=%v err=%v", valid, err)
+			}
+			var stored UserIdentity
+			mustIAM(t, sys.store.loadIAMConfig(ctx, &stored, getUserIdentityPath("import-service", svcUser)))
+			raw, err := auth.ExtractClaims(stored.Credentials.SessionToken, stored.Credentials.SecretKey)
+			mustIAM(t, err)
+			if _, ok := raw.Map()[sessionPolicyNameExtracted]; ok || raw.Map()["identity-attribute"] != "preserved" {
+				t.Fatal("import polluted the raw JWT or lost identity claims")
+			}
+			// Old exports may contain a derived claim and omit the policy version.
+			snapshot, err := serviceAccountSnapshot(stored)
+			mustIAM(t, err)
+			snapshot.Claims[sessionPolicyNameExtracted] = "stale decoded policy"
+			snapshot.SessionPolicy = []byte(strings.ReplaceAll(svcAccEditPolicy, `"Version":"2012-10-17",`, ""))
+			rec = iamImportCall(t, iamImportArchive(t, map[string]any{allSvcAcctsFile: map[string]madmin.SRSvcAccCreate{"import-service": snapshot}}))
+			mustIAM(t, json.Unmarshal(rec.Body.Bytes(), &result))
+			if len(result.Failed.ServiceAccounts) != 0 {
+				t.Fatalf("legacy snapshot import failed: %s", rec.Body.String())
+			}
+			_, gotPolicy, err = sys.GetServiceAccount(ctx, "import-service")
+			mustIAM(t, err)
+			if gotPolicy == nil || !gotPolicy.Equals(*sp) {
+				t.Fatal("import did not normalize the inline policy")
+			}
+			mustIAM(t, sys.store.loadIAMConfig(ctx, &stored, getUserIdentityPath("import-service", svcUser)))
+			raw, err = auth.ExtractClaims(stored.Credentials.SessionToken, stored.Credentials.SecretKey)
+			mustIAM(t, err)
+			if _, ok := raw.Map()[sessionPolicyNameExtracted]; ok {
+				t.Fatal("legacy import signed a derived claim into the JWT")
+			}
+		})
+	}
+}
+
+type iamImportGroupFailureStore struct {
+	IAMStorageAPI
+	statusOnly bool
+	err        error
+}
+
+func (s *iamImportGroupFailureStore) saveIAMConfig(ctx context.Context, item any, path string, opts ...options) error {
+	mutation, _ := ctx.Value(iamGroupMutationKey{}).(iamGroupMutation)
+	if path == getGroupInfoPath("import-failure") && mutation.StatusOnly == s.statusOnly {
+		return s.err
+	}
+	return s.IAMStorageAPI.saveIAMConfig(ctx, item, path, opts...)
+}
+
+func TestIAMImportGroupFailure(t *testing.T) {
+	for _, operation := range []string{"members", "status"} {
+		t.Run(operation, func(t *testing.T) {
+			_, sys := iamAdminFixture(t)
+			injected := madmin.ErrorResponse{Code: "InjectedGroupWrite", Message: operation + " write failed"}
+			sys.store.IAMStorageAPI = &iamImportGroupFailureStore{IAMStorageAPI: sys.store.IAMStorageAPI, statusOnly: operation == "status", err: injected}
+			rec := iamImportCall(t, iamImportArchive(t, map[string]any{allGroupsFile: map[string]GroupInfo{
+				"import-failure": {Status: statusDisabled},
+			}}))
+			var result struct {
+				Added  madmin.IAMEntities `json:"added"`
+				Failed struct {
+					Groups []struct {
+						Name  string          `json:"name"`
+						Error json.RawMessage `json:"error"`
+					} `json:"groups"`
+				} `json:"failed"`
+			}
+			mustIAM(t, json.Unmarshal(rec.Body.Bytes(), &result))
+			wantError, err := json.Marshal(injected)
+			mustIAM(t, err)
+			if len(result.Added.Groups) != 0 || len(result.Failed.Groups) != 1 || result.Failed.Groups[0].Name != "import-failure" || !bytes.Equal(result.Failed.Groups[0].Error, wantError) {
+				t.Fatalf("import did not report the actual %s error: %s", operation, rec.Body.String())
+			}
+		})
+	}
+}

cmd/iam-replication-protocol.go

@@ -4,7 +4,6 @@
 package cmd
 
 import (
-	"bytes"
 	"context"
 	"crypto/sha256"
 	"encoding/hex"
@@ -172,14 +171,41 @@ func (c *SiteReplicationSys) replicationItem(ctx context.Context, item madmin.SR
 			key = item.SvcAccChange.Update.AccessKey
 		}
 		if key != "" {
-			r, err := loadIAMRevision(ctx, globalIAMSys.store, getUserIdentityPath(key, svcUser))
+			// A create or an edit goes out as the account stored now: the
+			// whole record, under its revision, whatever the caller's item
+			// says. A peer orders items by revision and drops an older one,
+			// so an edit sent as the fields it changed would lose every
+			// earlier edit that did not reach the peer, or reaches it late.
+			// A later write that won before sending goes out in place of
+			// this one.
+			stored := make(map[string]UserIdentity, 1)
+			err := globalIAMSys.store.loadUser(ctx, key, svcUser, stored)
+			if err != nil && !errors.Is(err, errNoSuchUser) {
+				return out, err
+			}
+			u, ok := stored[key]
+			if !ok {
+				// Nothing is sent for an account that is deleted, expired or
+				// of a revoked parent meanwhile; a deletion replicates itself.
+				// A stored token that cannot be read is an error, and the
+				// account is not taken for sent.
+				var raw UserIdentity
+				err := globalIAMSys.store.loadIAMConfig(ctx, &raw, getUserIdentityPath(key, svcUser))
+				if err == nil && !raw.Deleted && !raw.Credentials.IsExpired() {
+					_, err = extractJWTClaims(raw)
+				}
+				if err != nil && !errors.Is(err, errConfigNotFound) {
+					return out, err
+				}
+				return out, errIAMStaleUpdate
+			}
+			snapshot, err := serviceAccountSnapshot(u)
 			if err != nil {
 				return out, err
 			}
-			if r.Deleted || r.timestamp().After(item.UpdatedAt) {
-				return out, errIAMStaleUpdate
-			}
-			out.RevokedBefore = r.RevokedBefore
+			out.SvcAccChange = &madmin.SRSvcAccChange{Create: &snapshot}
+			out.UpdatedAt = u.UpdatedAt
+			out.RevokedBefore = u.RevokedBefore
 		}
 	}
 	if item.Type == madmin.SRIAMItemGroupInfo && item.GroupInfo != nil && !item.GroupInfo.UpdateReq.IsRemove {
@@ -275,7 +301,7 @@ func applyIAMReplicationItem(ctx context.Context, item iamReplicationItem) error
 		if len(item.Policy) == 0 {
 			return globalSiteReplicationSys.PeerAddPolicyHandler(ctx, item.Name, nil, item.UpdatedAt)
 		}
-		p, err := policy.ParseConfig(bytes.NewReader(item.Policy))
+		p, err := parsePolicySnapshotBytes(item.Policy)
 		if err != nil {
 			return err
 		}

cmd/iam-revision.go

@@ -676,9 +676,8 @@ func (c *SiteReplicationSys) healIAMDeletions(ctx context.Context) (err error) {
 	}()
 	c.iamHealMu.Lock()
 	defer c.iamHealMu.Unlock()
-	c.RLock()
-	defer c.RUnlock()
-	if !c.enabled {
+	state, ok := c.stateSnapshot()
+	if !ok {
 		return nil
 	}
 	snapshot := globalIAMSys.store.revisionIndex().snapshot()
@@ -719,17 +718,17 @@ func (c *SiteReplicationSys) healIAMDeletions(ctx context.Context) (err error) {
 		c.iamRevisionProgress = make(map[string]iamRevisionProgress)
 	}
 	for id := range c.iamRevisionProgress {
-		if _, present := c.state.Peers[id]; !present {
+		if _, present := state.Peers[id]; !present {
 			delete(c.iamRevisionProgress, id)
 		}
 	}
 	var progressMu sync.Mutex
-	cerr := c.concDo(nil, func(id string, p madmin.PeerInfo) error {
+	cerr := state.concDo(nil, func(id string, p madmin.PeerInfo) error {
 		// Bound each pass, but retain acknowledgements independently of the
 		// pass deadline or unrelated changes at either site.
 		peerCtx, cancel := context.WithTimeout(ctx, defaultContextTimeout)
 		defer cancel()
-		client, err := c.getAdminClient(peerCtx, id)
+		client, err := state.getAdminClient(id)
 		if err != nil {
 			return err
 		}

cmd/iam-store.go

@@ -20,7 +20,6 @@ package cmd
 import (
 	"context"
 	"encoding/base64"
-	"encoding/json"
 	"errors"
 	"fmt"
 	"maps"
@@ -2930,30 +2929,19 @@ func updatedServiceAccountCredentials(ctx context.Context, accessKey string, cr
 	// at this point.
 	m.Delete(sessionPolicyNameExtracted)
 
-	nosp := opts.sessionPolicy == nil || opts.sessionPolicy.Version == "" && len(opts.sessionPolicy.Statements) == 0
-
-	// sessionPolicy is nil and there is embedded policy attached we remove
-	// embedded policy at that point.
-	if _, ok := m.Lookup(policy.SessionPolicyName); ok && nosp {
-		m.Delete(policy.SessionPolicyName)
-		m.Set(iamPolicyClaimNameSA(), inheritedPolicyType)
-	}
-
-	if opts.sessionPolicy != nil { // session policies is being updated
-		if err := opts.sessionPolicy.Validate(); err != nil {
+	// A nil sessionPolicy is an edit that does not concern the policy, and
+	// the embedded one stays. Only a policy that was given, and is empty,
+	// removes it: the account then has all its parent is allowed, which is
+	// usually more.
+	if opts.sessionPolicy != nil {
+		policyBuf, err := marshalServiceAccountPolicy(opts.sessionPolicy)
+		if err != nil {
 			return cr, err
 		}
-
-		if opts.sessionPolicy.Version != "" && len(opts.sessionPolicy.Statements) > 0 {
-			policyBuf, err := json.Marshal(opts.sessionPolicy)
-			if err != nil {
-				return cr, err
-			}
-
-			if len(policyBuf) > maxSVCSessionPolicySize {
-				return cr, errSessionPolicyTooLarge
-			}
-
+		if len(policyBuf) == 0 {
+			m.Delete(policy.SessionPolicyName)
+			m.Set(iamPolicyClaimNameSA(), inheritedPolicyType)
+		} else {
 			// Overwrite session policy claims.
 			m.Set(policy.SessionPolicyName, base64.StdEncoding.EncodeToString(policyBuf))
 			m.Set(iamPolicyClaimNameSA(), embeddedPolicyType)

cmd/iam-svcacct-policy-edit_test.go

@@ -0,0 +1,358 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"reflect"
+	"runtime"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	minio "github.com/minio/minio-go/v7"
+	"github.com/minio/minio/internal/auth"
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+// An edit of a service account that names no policy keeps the embedded
+// policy: the account must not come out of a status change, a key rotation
+// or a rename with all its parent is allowed. Only a policy that is given
+// and empty removes the embedded one.
+
+const svcAccEditPolicy = `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::edit/*"]}]}`
+
+func TestIAMServiceAccountPolicySemantics(t *testing.T) {
+	for _, expiring := range []bool{false, true} {
+		t.Run(fmt.Sprintf("expiring=%v", expiring), func(t *testing.T) {
+			f := newGroupRefreshFixture(t)
+			readPolicy, err := policy.ParseConfig(strings.NewReader(svcAccEditPolicy))
+			mustIAM(t, err)
+			writePolicy, err := policy.ParseConfig(strings.NewReader(strings.ReplaceAll(svcAccEditPolicy, "s3:GetObject", "s3:PutObject")))
+			mustIAM(t, err)
+			_, err = f.sys.PolicyDBSet(f.ctx, f.parent.AccessKey, "readwrite", regUser, false)
+			mustIAM(t, err)
+			for _, action := range []policy.Action{policy.GetObjectAction, policy.PutObjectAction} {
+				if !f.sys.IsAllowed(policy.Args{AccountName: f.parent.AccessKey, Action: action, BucketName: "edit", ObjectName: "object"}) {
+					t.Fatal("control: the parent must allow reads and writes to the test object")
+				}
+			}
+			noVersion, invalidVersion, oversized := *writePolicy, *writePolicy, *writePolicy
+			noVersion.Version = ""
+			invalidVersion.Version = "2008-10-17"
+			oversized.ID = policy.ID(strings.Repeat("x", maxSVCSessionPolicySize))
+			var expiration *time.Time
+			if expiring {
+				later := UTCNow().Add(time.Hour)
+				expiration = &later
+			}
+			for i, tc := range []struct {
+				name    string
+				input   *policy.Policy
+				invalid bool
+			}{
+				{"nil", nil, false},
+				{"empty", &policy.Policy{}, false},
+				{"empty-statements", &policy.Policy{Statements: []policy.Statement{}}, false},
+				{"empty-with-version", &policy.Policy{Version: policy.DefaultVersion, Statements: []policy.Statement{}}, false},
+				{"missing-version", &noVersion, false},
+				{"version", writePolicy, false},
+				{"invalid-version", &invalidVersion, true},
+				{"empty-invalid-version", &policy.Policy{Version: "2008-10-17"}, true},
+				{"invalid-statement", &policy.Policy{Statements: []policy.Statement{{}}}, true},
+				{"oversized", &oversized, true},
+			} {
+				for _, edit := range []bool{false, true} {
+					t.Run(fmt.Sprintf("%s/edit=%v", tc.name, edit), func(t *testing.T) {
+						key := fmt.Sprintf("policy-%d-%v", i, edit)
+						inputBefore, err := json.Marshal(tc.input)
+						mustIAM(t, err)
+						var before UserIdentity
+						if edit {
+							_, _, err = f.sys.NewServiceAccount(f.ctx, f.parent.AccessKey, nil, newServiceAccountOpts{
+								accessKey: key, secretKey: "policy-valid-secret", sessionPolicy: readPolicy, expiration: expiration,
+							})
+							mustIAM(t, err)
+							mustIAM(t, f.sys.store.loadIAMConfig(f.ctx, &before, getUserIdentityPath(key, svcUser)))
+							_, err = f.sys.UpdateServiceAccount(f.ctx, key, updateServiceAccountOpts{sessionPolicy: tc.input, description: "edited"})
+						} else {
+							// Snapshots can carry a stale copy of the policy in claims.
+							var claims map[string]any
+							if tc.input != nil {
+								claims = map[string]any{policy.SessionPolicyName: base64.StdEncoding.EncodeToString([]byte(svcAccEditPolicy))}
+							}
+							_, _, err = f.sys.NewServiceAccount(f.ctx, f.parent.AccessKey, nil, newServiceAccountOpts{
+								accessKey: key, secretKey: "policy-valid-secret", sessionPolicy: tc.input, expiration: expiration,
+								claims: claims,
+							})
+						}
+						if (err != nil) != tc.invalid {
+							t.Fatalf("operation error = %v, want rejected=%v", err, tc.invalid)
+						}
+						inputAfter, err := json.Marshal(tc.input)
+						mustIAM(t, err)
+						if !bytes.Equal(inputBefore, inputAfter) {
+							t.Fatal("operation changed the caller's policy")
+						}
+						var stored UserIdentity
+						loadErr := f.sys.store.loadIAMConfig(f.ctx, &stored, getUserIdentityPath(key, svcUser))
+						if tc.invalid {
+							if edit {
+								mustIAM(t, loadErr)
+								if !reflect.DeepEqual(stored, before) {
+									t.Fatal("rejected edit changed the stored account")
+								}
+							} else if loadErr != errConfigNotFound {
+								t.Fatalf("rejected create left an account: %v", loadErr)
+							}
+							return
+						}
+						mustIAM(t, loadErr)
+						claims, err := auth.ExtractClaims(stored.Credentials.SessionToken, stored.Credentials.SecretKey)
+						mustIAM(t, err)
+						if _, ok := claims.Map()[sessionPolicyNameExtracted]; ok {
+							t.Fatal("raw JWT contains the derived policy claim")
+						}
+						var want *policy.Policy
+						if tc.input != nil && !tc.input.IsEmpty() {
+							want = writePolicy
+						} else if tc.input == nil && edit {
+							want = readPolicy
+						}
+						got, err := embeddedServiceAccountPolicy(claims)
+						mustIAM(t, err)
+						if (got == nil) != (want == nil) || (got != nil && !got.Equals(*want)) {
+							t.Fatalf("stored policy = %+v, want %+v", got, want)
+						}
+						if want == nil {
+							if _, ok := claims.Lookup(policy.SessionPolicyName); ok || claims.Map()[iamPolicyClaimNameSA()] != inheritedPolicyType {
+								t.Fatal("inheritance must remove the embedded policy claim")
+							}
+						}
+						mustIAM(t, f.sys.store.LoadIAMCache(f.ctx, false))
+						u, valid, err := f.sys.CheckKey(f.ctx, key)
+						mustIAM(t, err)
+						if !valid || u.Credentials.IsTemp() != expiring {
+							t.Fatal("credential validity or expiration changed")
+						}
+						for _, action := range []policy.Action{policy.GetObjectAction, policy.PutObjectAction} {
+							allowed := f.sys.IsAllowed(policy.Args{AccountName: key, Claims: u.Credentials.Claims, Action: action, BucketName: "edit", ObjectName: "object"})
+							wantAllowed := want == nil || (want == readPolicy && action == policy.GetObjectAction) || (want == writePolicy && action == policy.PutObjectAction)
+							if allowed != wantAllowed {
+								t.Errorf("%s allowed=%v, want %v", action, allowed, wantAllowed)
+							}
+						}
+					})
+				}
+			}
+		})
+	}
+}
+
+func TestIAMServiceAccountEditKeepsPolicy(t *testing.T) {
+	f := newGroupRefreshFixture(t)
+	want, err := policy.ParseConfig(strings.NewReader(svcAccEditPolicy))
+	mustIAM(t, err)
+
+	// restricted creates a service account with the embedded policy.
+	restricted := func(t *testing.T, key, status string) {
+		t.Helper()
+		_, _, err := f.sys.NewServiceAccount(f.ctx, f.parent.AccessKey, nil, newServiceAccountOpts{accessKey: key, secretKey: "edit-original-secret", status: status, sessionPolicy: want})
+		mustIAM(t, err)
+	}
+	// embedded reports whether this server and storage have the policy, and
+	// returns the stored credential.
+	embedded := func(t *testing.T, key string) (cached, stored bool, cr auth.Credentials) {
+		t.Helper()
+		_, got, err := f.sys.GetServiceAccount(f.ctx, key)
+		mustIAM(t, err)
+		if got != nil && !got.Equals(*want) {
+			t.Fatalf("the embedded policy changed: %+v", got)
+		}
+		u, ok := f.stored(t, key)
+		if !ok {
+			t.Fatal("service account missing in storage")
+		}
+		claims, err := getClaimsFromTokenWithSecret(u.Credentials.SessionToken, u.Credentials.SecretKey)
+		mustIAM(t, err)
+		_, hasPolicy := claims.Lookup(policy.SessionPolicyName)
+		return got != nil, hasPolicy && claims.MapClaims[iamPolicyClaimNameSA()] == embeddedPolicyType, u.Credentials
+	}
+	// check wants the edit applied, and the policy kept or removed.
+	check := func(t *testing.T, key string, keep bool, took func(auth.Credentials) bool) {
+		t.Helper()
+		cached, stored, cr := embedded(t, key)
+		if cached != keep || stored != keep {
+			t.Errorf("embedded policy: cached=%v stored=%v, want %v", cached, stored, keep)
+		}
+		if took != nil && !took(cr) {
+			t.Errorf("the edit did not apply: status=%q name=%q description=%q expiration=%v", cr.Status, cr.Name, cr.Description, cr.Expiration)
+		}
+	}
+
+	later := UTCNow().Add(time.Hour)
+	for _, edit := range []struct {
+		name, start string
+		opts        updateServiceAccountOpts
+		took        func(auth.Credentials) bool
+	}{
+		{"disable", auth.AccountOn, updateServiceAccountOpts{status: string(madmin.AccountDisabled)}, func(c auth.Credentials) bool { return c.Status == auth.AccountOff }},
+		{"enable", auth.AccountOff, updateServiceAccountOpts{status: string(madmin.AccountEnabled)}, func(c auth.Credentials) bool { return c.Status == auth.AccountOn }},
+		{"status-off", auth.AccountOn, updateServiceAccountOpts{status: auth.AccountOff}, func(c auth.Credentials) bool { return c.Status == auth.AccountOff }},
+		{"status-on", auth.AccountOff, updateServiceAccountOpts{status: auth.AccountOn}, func(c auth.Credentials) bool { return c.Status == auth.AccountOn }},
+		{"secret-key", auth.AccountOn, updateServiceAccountOpts{secretKey: "edit-rotated-secret"}, func(c auth.Credentials) bool { return c.SecretKey == "edit-rotated-secret" }},
+		{"name", auth.AccountOn, updateServiceAccountOpts{name: "renamed"}, func(c auth.Credentials) bool { return c.Name == "renamed" }},
+		{"description", auth.AccountOn, updateServiceAccountOpts{description: "described"}, func(c auth.Credentials) bool { return c.Description == "described" }},
+		{"expiration", auth.AccountOn, updateServiceAccountOpts{expiration: &later}, func(c auth.Credentials) bool { return c.Expiration.Equal(later) }},
+	} {
+		t.Run(edit.name, func(t *testing.T) {
+			key := "edit-" + edit.name
+			restricted(t, key, edit.start)
+			_, err := f.sys.UpdateServiceAccount(f.ctx, key, edit.opts)
+			mustIAM(t, err)
+			check(t, key, true, edit.took)
+		})
+	}
+
+	t.Run("empty-policy", func(t *testing.T) {
+		const key = "edit-empty-policy"
+		restricted(t, key, auth.AccountOn)
+		_, err := f.sys.UpdateServiceAccount(f.ctx, key, updateServiceAccountOpts{sessionPolicy: &policy.Policy{}})
+		mustIAM(t, err)
+		check(t, key, false, nil)
+	})
+
+	// A peer applies the edit as the site that took it did. The edit goes
+	// through the encoding of the wire, which is where no policy and a null
+	// one become the same.
+	for _, edit := range []struct {
+		name   string
+		update madmin.SRSvcAccUpdate
+		keep   bool
+		took   func(auth.Credentials) bool
+	}{
+		{"peer-status", madmin.SRSvcAccUpdate{Status: auth.AccountOff}, true, func(c auth.Credentials) bool { return c.Status == auth.AccountOff }},
+		{"peer-null", madmin.SRSvcAccUpdate{Description: "described", SessionPolicy: madmin.SRSessionPolicy("null")}, true, func(c auth.Credentials) bool { return c.Description == "described" }},
+		{"peer-empty", madmin.SRSvcAccUpdate{SessionPolicy: madmin.SRSessionPolicy(`{"Statement":[]}`)}, false, nil},
+		{"peer-empty-v", madmin.SRSvcAccUpdate{SessionPolicy: madmin.SRSessionPolicy(`{"Version":"2012-10-17","Statement":[]}`)}, false, nil},
+	} {
+		t.Run(edit.name, func(t *testing.T) {
+			key := "edit-" + edit.name
+			restricted(t, key, auth.AccountOn)
+			edit.update.AccessKey = key
+			sent, err := json.Marshal(iamReplicationItem{SRIAMItem: madmin.SRIAMItem{
+				Type:         madmin.SRIAMItemSvcAcc,
+				SvcAccChange: &madmin.SRSvcAccChange{Update: &edit.update},
+				UpdatedAt:    UTCNow(),
+			}})
+			mustIAM(t, err)
+			var got iamReplicationItem
+			mustIAM(t, json.Unmarshal(sent, &got))
+			mustIAM(t, applyIAMReplicationItem(f.ctx, got))
+			check(t, key, edit.keep, edit.took)
+		})
+	}
+}
+
+// The same over the admin API, with what a client can send for no policy.
+func TestServiceAccountUpdateKeepsPolicy(t *testing.T) {
+	if runtime.GOOS == globalWindowsOSName {
+		t.Skip("IAM integration harness is disabled on Windows")
+	}
+	s := newTestSuiteIAM(TestSuiteCommon{serverType: "ErasureSD", signer: signerV4}, false)
+	c := &check{t, s.serverType}
+	s.SetUpSuite(c)
+	defer s.TearDownSuite(c)
+
+	ctx, cancel := context.WithTimeout(context.Background(), testDefaultTimeout)
+	defer cancel()
+
+	bucket := getRandomBucketName()
+	if err := s.client.MakeBucket(ctx, bucket, minio.MakeBucketOptions{}); err != nil {
+		c.Fatalf("bucket create error: %v", err)
+	}
+	if err := s.adm.AddCannedPolicy(ctx, "keeps-policy-parent", fmt.Appendf(nil, `{"Version":"2012-10-17","Statement":[
+{"Effect":"Allow","Action":["s3:ListBucket"],"Resource":["arn:aws:s3:::%s"]},
+{"Effect":"Allow","Action":["s3:PutObject","s3:GetObject"],"Resource":["arn:aws:s3:::%s/*"]}]}`, bucket, bucket)); err != nil {
+		c.Fatalf("policy add error: %v", err)
+	}
+	parentAK, parentSK := mustGenerateCredentials(c)
+	if err := s.adm.SetUser(ctx, parentAK, parentSK, madmin.AccountEnabled); err != nil {
+		c.Fatalf("unable to set user: %v", err)
+	}
+	if _, err := s.adm.AttachPolicy(ctx, madmin.PolicyAssociationReq{Policies: []string{"keeps-policy-parent"}, User: parentAK}); err != nil {
+		c.Fatalf("unable to attach policy: %v", err)
+	}
+
+	// The account may read objects; listing is its parent's to do.
+	svcAK, svcSK := mustGenerateCredentials(c)
+	cr, err := s.adm.AddServiceAccount(ctx, madmin.AddServiceAccountReq{
+		Policy:     fmt.Appendf(nil, `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::%s/*"]}]}`, bucket),
+		TargetUser: parentAK,
+		AccessKey:  svcAK,
+		SecretKey:  svcSK,
+	})
+	if err != nil {
+		c.Fatalf("unable to create svc acc: %v", err)
+	}
+	c.mustUpload(ctx, s.client, bucket)
+	svcClient := s.getUserClient(c, cr.AccessKey, cr.SecretKey, "")
+	c.mustDownload(ctx, svcClient, bucket)
+	c.mustNotListObjects(ctx, svcClient, bucket)
+
+	info := func() madmin.InfoServiceAccountResp {
+		info, err := s.adm.InfoServiceAccount(ctx, svcAK)
+		if err != nil {
+			c.Fatalf("unable to get svc acc info: %v", err)
+		}
+		return info
+	}
+
+	_, rotatedSK := mustGenerateCredentials(c)
+	later := UTCNow().Add(time.Hour).Truncate(time.Second)
+	for _, edit := range []struct {
+		name string
+		req  madmin.UpdateServiceAccountReq
+		took func(madmin.InfoServiceAccountResp) bool
+	}{
+		{"disable", madmin.UpdateServiceAccountReq{NewStatus: "off"}, func(i madmin.InfoServiceAccountResp) bool { return i.AccountStatus == auth.AccountOff }},
+		{"enable", madmin.UpdateServiceAccountReq{NewStatus: "on"}, func(i madmin.InfoServiceAccountResp) bool { return i.AccountStatus == auth.AccountOn }},
+		{"description", madmin.UpdateServiceAccountReq{NewDescription: "described"}, func(i madmin.InfoServiceAccountResp) bool { return i.Description == "described" }},
+		{"name", madmin.UpdateServiceAccountReq{NewName: "renamed"}, func(i madmin.InfoServiceAccountResp) bool { return i.Name == "renamed" }},
+		{"expiry", madmin.UpdateServiceAccountReq{NewExpiration: &later}, func(i madmin.InfoServiceAccountResp) bool { return i.Expiration != nil && i.Expiration.Equal(later) }},
+		{"secret-key", madmin.UpdateServiceAccountReq{NewSecretKey: rotatedSK}, func(madmin.InfoServiceAccountResp) bool {
+			// The new key signs a request the embedded policy allows.
+			svcClient = s.getUserClient(c, svcAK, rotatedSK, "")
+			_, err := svcClient.StatObject(ctx, bucket, "some-object", minio.StatObjectOptions{})
+			return err == nil
+		}},
+		{"null-policy", madmin.UpdateServiceAccountReq{NewPolicy: json.RawMessage("null"), NewDescription: "null"}, func(i madmin.InfoServiceAccountResp) bool { return i.Description == "null" }},
+	} {
+		if err := s.adm.UpdateServiceAccount(ctx, svcAK, edit.req); err != nil {
+			c.Fatalf("%s: unable to update svc acc: %v", edit.name, err)
+		}
+		got := info()
+		if got.ImpliedPolicy {
+			c.Fatalf("%s: the account lost its embedded policy", edit.name)
+		}
+		if !edit.took(got) {
+			c.Fatalf("%s: the edit did not apply: %+v", edit.name, got)
+		}
+	}
+	c.mustNotListObjects(ctx, svcClient, bucket)
+
+	// An empty policy document asks for the parent's policies.
+	if err := s.adm.UpdateServiceAccount(ctx, svcAK, madmin.UpdateServiceAccountReq{NewPolicy: []byte(`{"Statement":[]}`)}); err != nil {
+		c.Fatalf("unable to remove the policy of svc acc: %v", err)
+	}
+	if !info().ImpliedPolicy {
+		c.Fatalf("an empty policy document must remove the embedded policy")
+	}
+	c.mustListObjects(ctx, svcClient, bucket)
+}

cmd/iam-svcacct-replication-snapshot_test.go

@@ -0,0 +1,578 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"archive/zip"
+	"bytes"
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"errors"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"path"
+	"reflect"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/auth"
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+// Site replication sends a service account as the record its site has
+// stored, whole. A peer that applies the last item it was sent then has
+// the account of the sending site, whatever it received or lost before,
+// and whatever the sending server holds in its cache.
+
+const svcAccSnapshotPolicy = `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::snapshot/*"]}]}`
+
+// svcAccRecord is what a site has of a service account.
+type svcAccRecord struct {
+	Parent, Secret, Status, Name, Description, Policy string
+	Expiration, UpdatedAt                             time.Time
+}
+
+// svcAccPolicyText is a policy document in the one form it is compared in;
+// an account without an embedded policy has "".
+func svcAccPolicyText(t *testing.T, document []byte) string {
+	t.Helper()
+	if len(document) == 0 {
+		return ""
+	}
+	p, err := policy.ParseConfig(bytes.NewReader(document))
+	mustIAM(t, err)
+	text, err := json.Marshal(p)
+	mustIAM(t, err)
+	return string(text)
+}
+
+// svcAccStored is the account as a server that starts now loads it.
+func svcAccStored(t *testing.T, f *groupRefreshFixture, key string) svcAccRecord {
+	t.Helper()
+	u, ok := f.stored(t, key)
+	if !ok {
+		t.Fatalf("service account %s is not stored", key)
+	}
+	cr := u.Credentials
+	rawClaims, err := auth.ExtractClaims(cr.SessionToken, cr.SecretKey)
+	mustIAM(t, err)
+	if _, ok := rawClaims.Map()[sessionPolicyNameExtracted]; ok {
+		t.Fatal("stored JWT contains the derived policy claim")
+	}
+	claims, err := getClaimsFromTokenWithSecret(cr.SessionToken, cr.SecretKey)
+	mustIAM(t, err)
+	rec := svcAccRecord{Parent: cr.ParentUser, Secret: cr.SecretKey, Status: cr.Status, Name: cr.Name, Description: cr.Description, Expiration: cr.Expiration, UpdatedAt: u.UpdatedAt}
+	if sp, ok := claims.Lookup(policy.SessionPolicyName); ok && claims.MapClaims[iamPolicyClaimNameSA()] == embeddedPolicyType {
+		document, err := base64.StdEncoding.DecodeString(sp)
+		mustIAM(t, err)
+		rec.Policy = svcAccPolicyText(t, document)
+	}
+	return rec
+}
+
+// svcAccSite is a site that replicates to one peer, which records the IAM
+// items it is sent.
+type svcAccSite struct {
+	*groupRefreshFixture
+	mu   sync.Mutex
+	sent []iamReplicationItem
+}
+
+func newSvcAccSite(t *testing.T) *svcAccSite {
+	t.Helper()
+	s := &svcAccSite{groupRefreshFixture: newGroupRefreshFixture(t)}
+	globalObjLayerMutex.Lock()
+	globalObjectAPI = s.obj
+	globalObjLayerMutex.Unlock()
+
+	peer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.Method == http.MethodPut && strings.HasSuffix(r.URL.Path, iamRevisionPeerPath) {
+			var batch iamRevisionBatch
+			if err := json.NewDecoder(r.Body).Decode(&batch); err != nil {
+				t.Error(err)
+			}
+			s.mu.Lock()
+			s.sent = append(s.sent, batch.Items...)
+			s.mu.Unlock()
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_ = json.NewEncoder(w).Encode(iamRevisionResponse{iamRevisionStatus: iamRevisionStatus{Version: iamRevisionProtocol, Node: "node", Instance: "boot", Digest: "fixture"}})
+	}))
+	globalSiteReplicatorCred.Set("snapshot-site-signing-key")
+	globalSiteReplicationSys.Lock()
+	globalSiteReplicationSys.enabled = true
+	globalSiteReplicationSys.state = srState{ServiceAccountAccessKey: s.parent.AccessKey, Peers: s.peers(peer.URL)}
+	globalSiteReplicationSys.Unlock()
+	t.Cleanup(func() {
+		s.leave()
+		peer.Close()
+	})
+	return s
+}
+
+func (s *svcAccSite) peers(endpoint string) map[string]madmin.PeerInfo {
+	return map[string]madmin.PeerInfo{
+		globalDeploymentID(): {Name: "local", DeploymentID: globalDeploymentID()},
+		"remote":             {Name: "remote", DeploymentID: "remote", Endpoint: endpoint},
+	}
+}
+
+// leave ends the replication of this process, for the site that comes next.
+func (s *svcAccSite) leave() {
+	globalSiteReplicationSys.Lock()
+	globalSiteReplicationSys.enabled = false
+	globalSiteReplicationSys.state = srState{}
+	globalSiteReplicationSys.Unlock()
+	globalSiteReplicatorCred.Set("")
+}
+
+// items are the creates and edits of account key the peer was sent, in the
+// order of sending.
+func (s *svcAccSite) items(key string) []iamReplicationItem {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	var items []iamReplicationItem
+	for _, item := range s.sent {
+		c := item.SvcAccChange
+		if c != nil && ((c.Create != nil && c.Create.AccessKey == key) || (c.Update != nil && c.Update.AccessKey == key)) {
+			items = append(items, item)
+		}
+	}
+	return items
+}
+
+// create and edit are an administrator's requests to this site.
+func (s *svcAccSite) create(t *testing.T, key string) {
+	t.Helper()
+	rec := iamAdminCall(t, globalActiveCred, http.MethodPut, "/minio/admin/v3/add-service-account",
+		madmin.AddServiceAccountReq{TargetUser: s.parent.AccessKey, AccessKey: key, SecretKey: "snapshot-original-secret"}, nil, adminAPIHandlers{}.AddServiceAccount)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("add-service-account: %d %s", rec.Code, rec.Body.String())
+	}
+}
+
+func (s *svcAccSite) edit(t *testing.T, key string, req madmin.UpdateServiceAccountReq) {
+	t.Helper()
+	rec := iamAdminCall(t, globalActiveCred, http.MethodPost, "/minio/admin/v3/update-service-account?accessKey="+key,
+		req, map[string]string{"accessKey": key}, adminAPIHandlers{}.UpdateServiceAccount)
+	if rec.Code != http.StatusNoContent {
+		t.Fatalf("update-service-account: %d %s", rec.Code, rec.Body.String())
+	}
+}
+
+// svcAccPeer is the site that applies items, in the order given, and what
+// it then has of account key. It has the parent user, as a peer does.
+func svcAccPeer(t *testing.T, from *svcAccSite, key string, items ...iamReplicationItem) svcAccRecord {
+	t.Helper()
+	from.leave()
+	peer := newGroupRefreshFixture(t)
+	for i, item := range items {
+		// As the peer reads it off the wire.
+		raw, err := json.Marshal(item)
+		mustIAM(t, err)
+		var received iamReplicationItem
+		mustIAM(t, json.Unmarshal(raw, &received))
+		if create := received.SvcAccChange.Create; create != nil {
+			if _, ok := create.Claims[sessionPolicyNameExtracted]; ok {
+				t.Fatal("replication snapshot contains the derived policy claim")
+			}
+		}
+		if err := applyIAMReplicationItem(peer.ctx, received); err != nil {
+			t.Fatalf("the peer refused item %d: %v", i, err)
+		}
+	}
+	return svcAccStored(t, peer, key)
+}
+
+func wantSvcAccRecord(t *testing.T, where string, got, want svcAccRecord) {
+	t.Helper()
+	if got != want {
+		t.Errorf("%s:\n got %+v\nwant %+v", where, got, want)
+	}
+}
+
+// An edit of a service account reaches a peer whatever became of the edits
+// before it: one that arrives late, or never, is not lost.
+func TestSiteReplicationServiceAccountEdits(t *testing.T) {
+	const key = "snapshot-edits"
+	for _, tc := range []struct {
+		name  string
+		edits []madmin.UpdateServiceAccountReq
+		took  func(svcAccRecord) bool // control: what the site has after them
+	}{
+		{"policy-secret-description", []madmin.UpdateServiceAccountReq{
+			{NewPolicy: json.RawMessage(svcAccSnapshotPolicy)},
+			{NewSecretKey: "snapshot-rotated-secret"},
+			{NewDescription: "described"},
+		}, func(r svcAccRecord) bool {
+			return r.Policy != "" && r.Secret == "snapshot-rotated-secret" && r.Description == "described"
+		}},
+		{"secret-disable", []madmin.UpdateServiceAccountReq{
+			{NewPolicy: json.RawMessage(svcAccSnapshotPolicy), NewSecretKey: "snapshot-rotated-secret"},
+			{NewStatus: string(madmin.AccountDisabled)},
+		}, func(r svcAccRecord) bool {
+			return r.Policy != "" && r.Secret == "snapshot-rotated-secret" && r.Status == auth.AccountOff
+		}},
+		// The last edit removes the embedded policy: the peer gets an
+		// account without one, and the description set before.
+		{"policy-removed", []madmin.UpdateServiceAccountReq{
+			{NewPolicy: json.RawMessage(svcAccSnapshotPolicy)},
+			{NewDescription: "described"},
+			{NewPolicy: json.RawMessage(`{"Statement":[]}`)},
+		}, func(r svcAccRecord) bool { return r.Policy == "" && r.Description == "described" }},
+		{"policy-removed-with-version", []madmin.UpdateServiceAccountReq{
+			{NewPolicy: json.RawMessage(svcAccSnapshotPolicy)},
+			{NewPolicy: json.RawMessage(`{"Version":"2012-10-17","Statement":[]}`), NewName: "named"},
+			{NewDescription: "described"},
+		}, func(r svcAccRecord) bool {
+			return r.Policy == "" && r.Name == "named" && r.Description == "described"
+		}},
+		{"policy-missing-version", []madmin.UpdateServiceAccountReq{
+			{NewPolicy: json.RawMessage(svcAccSnapshotPolicy)},
+			{NewPolicy: json.RawMessage(strings.ReplaceAll(strings.ReplaceAll(svcAccSnapshotPolicy, `"Version":"2012-10-17",`, ""), "s3:GetObject", "s3:PutObject"))},
+			{NewDescription: "described"},
+		}, func(r svcAccRecord) bool {
+			return r.Policy == svcAccPolicyText(t, []byte(strings.ReplaceAll(svcAccSnapshotPolicy, "s3:GetObject", "s3:PutObject"))) && r.Description == "described"
+		}},
+	} {
+		for _, delivery := range []string{"late", "lost"} {
+			t.Run(tc.name+"/"+delivery, func(t *testing.T) {
+				site := newSvcAccSite(t)
+				site.create(t, key)
+				for _, edit := range tc.edits {
+					site.edit(t, key, edit)
+				}
+				sent := site.items(key)
+				if len(sent) != 1+len(tc.edits) {
+					t.Fatalf("the site sent %d items for the account, want one for the create and each edit", len(sent))
+				}
+				want := svcAccStored(t, site.groupRefreshFixture, key)
+				if !tc.took(want) {
+					t.Fatalf("control: the site did not apply the edits: %+v", want)
+				}
+				// The peer has the account and gets the last edit. The edits
+				// before it were lost, or reach it after the last.
+				last := len(sent) - 1
+				deliver := []iamReplicationItem{sent[0], sent[last]}
+				if delivery == "late" {
+					deliver = append(deliver, sent[1:last]...)
+				}
+				wantSvcAccRecord(t, "peer", svcAccPeer(t, site, key, deliver...), want)
+			})
+		}
+	}
+
+	// Two requests edit the account through this site at once, and the
+	// first comes to replicate when the second is stored.
+	t.Run("concurrent", func(t *testing.T) {
+		site := newSvcAccSite(t)
+		site.create(t, key)
+		sp, err := policy.ParseConfig(strings.NewReader(svcAccSnapshotPolicy))
+		mustIAM(t, err)
+		first, err := site.sys.UpdateServiceAccount(site.ctx, key, updateServiceAccountOpts{sessionPolicy: sp})
+		mustIAM(t, err)
+		second, err := site.sys.UpdateServiceAccount(site.ctx, key, updateServiceAccountOpts{description: "described"})
+		mustIAM(t, err)
+		for _, at := range []time.Time{first, second} {
+			mustIAM(t, globalSiteReplicationSys.IAMChangeHook(site.ctx, madmin.SRIAMItem{
+				Type:         madmin.SRIAMItemSvcAcc,
+				SvcAccChange: &madmin.SRSvcAccChange{Update: &madmin.SRSvcAccUpdate{AccessKey: key}},
+				UpdatedAt:    at,
+			}))
+		}
+		want := svcAccStored(t, site.groupRefreshFixture, key)
+		if want.Policy == "" || want.Description != "described" {
+			t.Fatalf("control: the site did not apply the edits: %+v", want)
+		}
+		wantSvcAccRecord(t, "peer", svcAccPeer(t, site, key, site.items(key)...), want)
+	})
+}
+
+// Another server of the site restricted, rotated and disabled the account,
+// and this server's cache has not heard of it. What this server sends, and
+// exports, is the account that is stored.
+func TestSiteReplicationServiceAccountStaleCache(t *testing.T) {
+	const key = "snapshot-stale"
+	// prepare returns the site, the stored account and what it sent for the
+	// create.
+	prepare := func(t *testing.T) (*svcAccSite, svcAccRecord, iamReplicationItem) {
+		t.Helper()
+		site := newSvcAccSite(t)
+		site.create(t, key)
+		created := site.items(key)
+		if len(created) != 1 {
+			t.Fatalf("the site sent %d items for the create", len(created))
+		}
+		sp, err := policy.ParseConfig(strings.NewReader(svcAccSnapshotPolicy))
+		mustIAM(t, err)
+		_, err = site.sibling(t).UpdateServiceAccount(site.ctx, key, updateServiceAccountOpts{
+			sessionPolicy: sp, secretKey: "snapshot-rotated-secret", status: auth.AccountOff, description: "restricted",
+		})
+		mustIAM(t, err)
+		if cached, _ := site.sys.store.GetUser(key); cached.Credentials.SecretKey != "snapshot-original-secret" || cached.Credentials.Status != auth.AccountOn {
+			t.Fatal("control: this server's cache must not have heard of the edit")
+		}
+		want := svcAccStored(t, site.groupRefreshFixture, key)
+		if want.Policy == "" || want.Secret != "snapshot-rotated-secret" || want.Status != auth.AccountOff {
+			t.Fatalf("control: the edit is not stored: %+v", want)
+		}
+		return site, want, created[0]
+	}
+
+	t.Run("heal", func(t *testing.T) {
+		site, want, created := prepare(t)
+		local := madmin.UserInfo{Status: madmin.AccountStatus(want.Status), UpdatedAt: want.UpdatedAt}
+		remote := madmin.UserInfo{Status: madmin.AccountStatus(auth.AccountOn), UpdatedAt: created.UpdatedAt}
+		info := srStatusInfo{Sites: globalSiteReplicationSys.state.Peers, UserStats: map[string]map[string]srUserStatsSummary{key: {
+			globalDeploymentID(): {userInfo: srUserInfo{UserInfo: local}},
+			"remote":             {SRUserStatsSummary: madmin.SRUserStatsSummary{UserInfoMismatch: true}, userInfo: srUserInfo{UserInfo: remote}},
+		}}}
+		mustIAM(t, globalSiteReplicationSys.healUsers(site.ctx, site.obj, key, info))
+		sent := site.items(key)
+		if len(sent) != 2 {
+			t.Fatalf("heal sent %d items for the account, want 1", len(sent)-1)
+		}
+		wantSvcAccRecord(t, "healed peer", svcAccPeer(t, site, key, sent...), want)
+	})
+
+	t.Run("sync", func(t *testing.T) {
+		site, want, _ := prepare(t)
+		mustIAM(t, globalSiteReplicationSys.syncToAllPeers(site.ctx, madmin.SRAddOptions{}))
+		sent := site.items(key)
+		if len(sent) != 2 {
+			t.Fatalf("sync sent %d items for the account, want 1", len(sent)-1)
+		}
+		wantSvcAccRecord(t, "new peer", svcAccPeer(t, site, key, sent[1]), want)
+	})
+
+	t.Run("export", func(t *testing.T) {
+		_, want, _ := prepare(t)
+		rec := iamAdminCall(t, globalActiveCred, http.MethodGet, "/minio/admin/v3/export-iam", nil, nil, adminAPIHandlers{}.ExportIAM)
+		if rec.Code != http.StatusOK {
+			t.Fatalf("export-iam: %d %s", rec.Code, rec.Body.String())
+		}
+		archive, err := zip.NewReader(bytes.NewReader(rec.Body.Bytes()), int64(rec.Body.Len()))
+		mustIAM(t, err)
+		file, err := archive.Open(path.Join(iamAssetsDir, allSvcAcctsFile))
+		mustIAM(t, err)
+		raw, err := io.ReadAll(file)
+		mustIAM(t, err)
+		var accounts map[string]madmin.SRSvcAccCreate
+		mustIAM(t, json.Unmarshal(raw, &accounts))
+		a, ok := accounts[key]
+		if !ok || a.Expiration == nil {
+			t.Fatalf("the export has no account %s with an expiration (present=%v)", key, ok)
+		}
+		got := svcAccRecord{Parent: a.Parent, Secret: a.SecretKey, Status: a.Status, Name: a.Name, Description: a.Description, Policy: svcAccPolicyText(t, a.SessionPolicy), Expiration: *a.Expiration}
+		want.UpdatedAt = time.Time{} // an export has no revisions
+		wantSvcAccRecord(t, "export", got, want)
+		if a.Claims[iamPolicyClaimNameSA()] != embeddedPolicyType {
+			t.Errorf("exported claims say %v, want %s", a.Claims[iamPolicyClaimNameSA()], embeddedPolicyType)
+		}
+		if _, ok := a.Claims[sessionPolicyNameExtracted]; ok {
+			t.Error("exported claims contain the derived policy claim")
+		}
+	})
+}
+
+func TestIAMServiceAccountSnapshotClaims(t *testing.T) {
+	f := newGroupRefreshFixture(t)
+	sp, err := policy.ParseConfig(strings.NewReader(svcAccSnapshotPolicy))
+	mustIAM(t, err)
+	_, _, err = f.sys.NewServiceAccount(f.ctx, f.parent.AccessKey, nil, newServiceAccountOpts{
+		accessKey: "snapshot-claims", secretKey: "snapshot-valid-secret", sessionPolicy: sp,
+		claims: map[string]any{"identity-attribute": "preserved"},
+	})
+	mustIAM(t, err)
+	u, ok := f.stored(t, "snapshot-claims")
+	if !ok {
+		t.Fatal("service account missing")
+	}
+	cr := u.Credentials
+	rawClaims, err := auth.ExtractClaims(cr.SessionToken, cr.SecretKey)
+	mustIAM(t, err)
+	derived, ok := cr.Claims[sessionPolicyNameExtracted]
+	if !ok {
+		t.Fatal("control: loaded claims must contain the derived policy")
+	}
+	snapshot, err := serviceAccountSnapshot(u)
+	mustIAM(t, err)
+	if !reflect.DeepEqual(snapshot.Claims, rawClaims.Map()) {
+		t.Fatal("snapshot claims differ from the raw JWT")
+	}
+	if u.Credentials.SessionToken != cr.SessionToken || u.Credentials.Claims[sessionPolicyNameExtracted] != derived {
+		t.Fatal("snapshot changed the source token or its cached claims")
+	}
+}
+
+// The parent was deleted and created again on both sites. The token of a
+// service account created afterwards names that revocation, and a peer
+// refuses a credential of the parent that does not: the create must carry
+// the claims of the token.
+func TestSiteReplicationServiceAccountOfRecreatedParent(t *testing.T) {
+	const key = "snapshot-reparent"
+	site := newSvcAccSite(t)
+	mustIAM(t, site.sys.DeleteUser(site.ctx, site.parent.AccessKey, false))
+	iamAdminUser(site.ctx, t, site.sys, site.parent.AccessKey, "refresh-parent")
+	revoked, err := loadIAMRevision(site.ctx, site.sys.store, getUserIdentityPath(site.parent.AccessKey, regUser))
+	mustIAM(t, err)
+	if revoked.RevokedBefore.IsZero() {
+		t.Fatal("control: the parent must have a revocation boundary")
+	}
+	site.create(t, key)
+	sent := site.items(key)
+	if len(sent) != 1 {
+		t.Fatalf("the site sent %d items for the create", len(sent))
+	}
+	want := svcAccStored(t, site.groupRefreshFixture, key)
+
+	// The peer's parent is newer than the deletion, which leaves it live
+	// with the boundary: a parent that was deleted and created again.
+	site.leave()
+	peer := newGroupRefreshFixture(t)
+	mustIAM(t, peer.sys.DeleteUser(withIAMReplicationTime(peer.ctx, revoked.RevokedBefore), peer.parent.AccessKey, false))
+	if r, err := loadIAMRevision(peer.ctx, peer.sys.store, getUserIdentityPath(peer.parent.AccessKey, regUser)); err != nil || r.Deleted || !r.RevokedBefore.Equal(revoked.RevokedBefore) {
+		t.Fatalf("control: the peer's parent must be live with the boundary (err=%v deleted=%v)", err, r.Deleted)
+	}
+	mustIAM(t, applyIAMReplicationItem(peer.ctx, sent[0]))
+	if _, ok := peer.stored(t, key); !ok {
+		t.Fatal("the peer dropped the new service account")
+	}
+	wantSvcAccRecord(t, "peer", svcAccStored(t, peer, key), want)
+}
+
+// An account that is deleted is not sent, and that is not an error. An
+// account whose stored token cannot be read is not taken for deleted: the
+// site signing key is not available here, and no token is read without it.
+func TestSiteReplicationServiceAccountUnreadable(t *testing.T) {
+	const key = "snapshot-unreadable"
+	site := newSvcAccSite(t)
+	site.create(t, key)
+	item := madmin.SRIAMItem{Type: madmin.SRIAMItemSvcAcc, SvcAccChange: &madmin.SRSvcAccChange{Update: &madmin.SRSvcAccUpdate{AccessKey: key}}}
+
+	globalSiteReplicatorCred.Set("")
+	if _, err := globalSiteReplicationSys.replicationItem(site.ctx, item); err == nil || errors.Is(err, errIAMStaleUpdate) {
+		t.Errorf("an account whose token cannot be read must be an error, got %v", err)
+	}
+	if err := globalSiteReplicationSys.IAMChangeHook(site.ctx, item); err == nil {
+		t.Error("the hook reported an account as sent that it could not read")
+	}
+	globalSiteReplicatorCred.Set("snapshot-site-signing-key")
+
+	mustIAM(t, site.sys.DeleteServiceAccount(site.ctx, key, false))
+	if _, err := globalSiteReplicationSys.replicationItem(site.ctx, item); !errors.Is(err, errIAMStaleUpdate) {
+		t.Errorf("a deleted account must not be sent, got %v", err)
+	}
+	if sent := site.items(key); len(sent) != 1 {
+		t.Errorf("the site sent %d items for the account, want only the create", len(sent))
+	}
+}
+
+// svcAccPausedStore holds every load of a user until proceed is closed.
+type svcAccPausedStore struct {
+	IAMStorageAPI
+	once             sync.Once
+	loading, proceed chan struct{}
+}
+
+func (s *svcAccPausedStore) loadUser(ctx context.Context, user string, userType IAMUserType, m map[string]UserIdentity) error {
+	s.once.Do(func() { close(s.loading) })
+	<-s.proceed
+	return s.IAMStorageAPI.loadUser(ctx, user, userType, m)
+}
+
+// The hook reads the account from storage without the lock of the
+// replication configuration. Loading an identity takes that lock for
+// reading; if the hook held it too, a change of the configuration that
+// arrives in between would wait for the hook, and the hook for it.
+func TestSiteReplicationHookReadsStorageUnlocked(t *testing.T) {
+	const key = "snapshot-unlocked"
+	site := newSvcAccSite(t)
+	site.create(t, key)
+	paused := &svcAccPausedStore{IAMStorageAPI: site.sys.store.IAMStorageAPI, loading: make(chan struct{}), proceed: make(chan struct{})}
+	site.sys.store.IAMStorageAPI = paused
+
+	sent := make(chan error, 1)
+	go func() {
+		sent <- globalSiteReplicationSys.IAMChangeHook(site.ctx, madmin.SRIAMItem{
+			Type:         madmin.SRIAMItemSvcAcc,
+			SvcAccChange: &madmin.SRSvcAccChange{Update: &madmin.SRSvcAccUpdate{AccessKey: key}},
+		})
+	}()
+	select {
+	case <-paused.loading:
+	case err := <-sent:
+		t.Fatalf("the hook did not read the account from storage (err=%v)", err)
+	}
+	// A writer that had to wait here would never get the lock, nor the
+	// hook its next read lock behind that writer: try, do not wait.
+	if globalSiteReplicationSys.TryLock() {
+		globalSiteReplicationSys.Unlock() //nolint:staticcheck // only the lock is of interest
+	} else {
+		t.Error("the hook holds the lock of the replication configuration while it reads storage")
+	}
+	close(paused.proceed)
+	select {
+	case err := <-sent:
+		mustIAM(t, err)
+	case <-time.After(10 * time.Second):
+		t.Fatal("the hook did not return")
+	}
+	if got := site.items(key); len(got) != 2 {
+		t.Errorf("the site sent %d items for the account, want the create and the edit", len(got))
+	}
+}
+
+// Healing must release its own configuration lock before calling the hook.
+// Otherwise a waiting configuration writer blocks the hook's next read lock.
+func TestSiteReplicationHealReadsStorageUnlocked(t *testing.T) {
+	const key = "heal-unlocked"
+	site := newSvcAccSite(t)
+	site.create(t, key)
+	stored := svcAccStored(t, site.groupRefreshFixture, key)
+	local := madmin.UserInfo{Status: madmin.AccountEnabled, UpdatedAt: stored.UpdatedAt}
+	remote := madmin.UserInfo{Status: madmin.AccountDisabled, UpdatedAt: stored.UpdatedAt.Add(-time.Minute)}
+	info := srStatusInfo{Sites: globalSiteReplicationSys.state.Peers, UserStats: map[string]map[string]srUserStatsSummary{key: {
+		globalDeploymentID(): {userInfo: srUserInfo{UserInfo: local}},
+		"remote":             {SRUserStatsSummary: madmin.SRUserStatsSummary{UserInfoMismatch: true}, userInfo: srUserInfo{UserInfo: remote}},
+	}}}
+	paused := &svcAccPausedStore{IAMStorageAPI: site.sys.store.IAMStorageAPI, loading: make(chan struct{}), proceed: make(chan struct{})}
+	site.sys.store.IAMStorageAPI = paused
+	release := sync.OnceFunc(func() { close(paused.proceed) })
+	defer release()
+
+	done := make(chan error, 1)
+	go func() {
+		done <- globalSiteReplicationSys.healUsers(site.ctx, site.obj, key, info)
+	}()
+	select {
+	case <-paused.loading:
+	case err := <-done:
+		t.Fatalf("heal did not read the account from storage (err=%v)", err)
+	case <-time.After(10 * time.Second):
+		t.Fatal("heal did not reach the storage read")
+	}
+	// Testing the writer lock without waiting keeps a regression from leaving
+	// deadlocked goroutines behind in the test process.
+	if globalSiteReplicationSys.TryLock() {
+		globalSiteReplicationSys.Unlock() //nolint:staticcheck // only the lock is of interest
+	} else {
+		t.Error("heal holds the replication configuration lock during a storage read")
+	}
+	release()
+	select {
+	case err := <-done:
+		mustIAM(t, err)
+	case <-time.After(10 * time.Second):
+		t.Fatal("heal did not return")
+	}
+	if got := site.items(key); len(got) != 2 {
+		t.Errorf("the site sent %d items, want the create and the healed snapshot", len(got))
+	}
+}

cmd/iam.go

@@ -1087,17 +1087,52 @@ func (sys *IAMSys) notifyForServiceAccount(ctx context.Context, accessKey string
 }
 
 type newServiceAccountOpts struct {
-	sessionPolicy              *policy.Policy
-	accessKey                  string
-	secretKey                  string
-	status                     string // Used by replication snapshots; local creates default to enabled.
-	name, description          string
-	expiration                 *time.Time
-	allowSiteReplicatorAccount bool // allow creating internal service account for site-replication.
+	sessionPolicy               *policy.Policy
+	accessKey                   string
+	secretKey                   string
+	status                      string // Used by replication snapshots; local creates default to enabled.
+	name, description           string
+	expiration                  *time.Time
+	allowSiteReplicatorAccount  bool // allow creating internal service account for site-replication.
+	preserveEmptyEmbeddedPolicy bool // preserve historical deny-all empty embedded policies on snapshot import/replication.
 
 	claims map[string]any
 }
 
+func svcAcctClaimsHaveEmbeddedPolicy(claims map[string]any) bool {
+	if claims == nil {
+		return false
+	}
+	pt, _ := claims[iamPolicyClaimNameSA()].(string)
+	return pt == embeddedPolicyType
+}
+
+// marshalServiceAccountPolicy validates a supplied policy and normalizes its
+// version without changing the caller's policy. An empty policy means inheritance.
+func marshalServiceAccountPolicy(sp *policy.Policy) ([]byte, error) {
+	if sp == nil {
+		return nil, nil
+	}
+	p := *sp
+	if p.Version == "" {
+		p.Version = policy.DefaultVersion
+	}
+	if err := p.Validate(); err != nil {
+		return nil, err
+	}
+	if p.IsEmpty() {
+		return nil, nil
+	}
+	buf, err := json.Marshal(p)
+	if err != nil {
+		return nil, err
+	}
+	if len(buf) > maxSVCSessionPolicySize {
+		return nil, errSessionPolicyTooLarge
+	}
+	return buf, nil
+}
+
 // NewServiceAccount - create a new service account
 func (sys *IAMSys) NewServiceAccount(ctx context.Context, parentUser string, groups []string, opts newServiceAccountOpts) (auth.Credentials, time.Time, error) {
 	if !sys.Initialized() {
@@ -1115,19 +1150,9 @@ func (sys *IAMSys) NewServiceAccount(ctx context.Context, parentUser string, gro
 		return auth.Credentials{}, time.Time{}, auth.ErrNoAccessKeyWithSecretKey
 	}
 
-	var policyBuf []byte
-	if opts.sessionPolicy != nil {
-		err := opts.sessionPolicy.Validate()
-		if err != nil {
-			return auth.Credentials{}, time.Time{}, err
-		}
-		policyBuf, err = json.Marshal(opts.sessionPolicy)
-		if err != nil {
-			return auth.Credentials{}, time.Time{}, err
-		}
-		if len(policyBuf) > maxSVCSessionPolicySize {
-			return auth.Credentials{}, time.Time{}, errSessionPolicyTooLarge
-		}
+	policyBuf, err := marshalServiceAccountPolicy(opts.sessionPolicy)
+	if err != nil {
+		return auth.Credentials{}, time.Time{}, err
 	}
 
 	// found newly requested service account, to be same as
@@ -1141,15 +1166,45 @@ func (sys *IAMSys) NewServiceAccount(ctx context.Context, parentUser string, gro
 	m := make(map[string]any)
 	m[parentClaim] = parentUser
 
-	if len(policyBuf) > 0 {
+	switch {
+	case len(policyBuf) > 0:
 		m[policy.SessionPolicyName] = base64.StdEncoding.EncodeToString(policyBuf)
 		m[iamPolicyClaimNameSA()] = embeddedPolicyType
-	} else {
+	case opts.preserveEmptyEmbeddedPolicy:
+		switch {
+		case opts.sessionPolicy != nil:
+			p := *opts.sessionPolicy
+			if p.Version == "" {
+				p.Version = policy.DefaultVersion
+			}
+			buf, merr := json.Marshal(p)
+			if merr != nil {
+				return auth.Credentials{}, time.Time{}, merr
+			}
+			m[policy.SessionPolicyName] = base64.StdEncoding.EncodeToString(buf)
+			m[iamPolicyClaimNameSA()] = embeddedPolicyType
+		default:
+			if raw, ok := opts.claims[policy.SessionPolicyName].(string); ok && raw != "" {
+				m[policy.SessionPolicyName] = raw
+				m[iamPolicyClaimNameSA()] = embeddedPolicyType
+			} else {
+				m[iamPolicyClaimNameSA()] = inheritedPolicyType
+			}
+		}
+	default:
 		m[iamPolicyClaimNameSA()] = inheritedPolicyType
 	}
 
 	// Add all the necessary claims for the service account.
 	for k, v := range opts.claims {
+		// Older snapshots may carry this cache-only, decoded policy claim.
+		if k == sessionPolicyNameExtracted {
+			continue
+		}
+		// An explicit policy, including an empty one, owns this claim.
+		if k == policy.SessionPolicyName && opts.sessionPolicy != nil {
+			continue
+		}
 		_, ok := m[k]
 		if !ok {
 			m[k] = v
@@ -1162,7 +1217,6 @@ func (sys *IAMSys) NewServiceAccount(ctx context.Context, parentUser string, gro
 	}
 
 	var accessKey, secretKey string
-	var err error
 	if len(opts.accessKey) > 0 || len(opts.secretKey) > 0 {
 		accessKey, secretKey = opts.accessKey, opts.secretKey
 	} else {
@@ -1311,22 +1365,65 @@ func (sys *IAMSys) getServiceAccount(ctx context.Context, accessKey string) (Use
 		return UserIdentity{}, nil, errNoSuchServiceAccount
 	}
 
-	var embeddedPolicy *policy.Policy
+	embeddedPolicy, err := embeddedServiceAccountPolicy(jwtClaims)
+	if err != nil {
+		return UserIdentity{}, nil, err
+	}
+	return sa, embeddedPolicy, nil
+}
 
+// embeddedServiceAccountPolicy returns the policy embedded in the token of a
+// service account, or nil when the account has the policies of its parent.
+func embeddedServiceAccountPolicy(jwtClaims *jwt.MapClaims) (*policy.Policy, error) {
 	pt, ptok := jwtClaims.Lookup(iamPolicyClaimNameSA())
 	sp, spok := jwtClaims.Lookup(policy.SessionPolicyName)
-	if ptok && spok && pt == embeddedPolicyType {
-		policyBytes, err := base64.StdEncoding.DecodeString(sp)
-		if err != nil {
-			return UserIdentity{}, nil, err
-		}
-		embeddedPolicy, err = policy.ParseConfig(bytes.NewReader(policyBytes))
-		if err != nil {
-			return UserIdentity{}, nil, err
+	if !ptok || !spok || pt != embeddedPolicyType {
+		return nil, nil
+	}
+	policyBytes, err := base64.StdEncoding.DecodeString(sp)
+	if err != nil {
+		return nil, err
+	}
+	return policy.ParseConfig(bytes.NewReader(policyBytes))
+}
+
+// serviceAccountSnapshot returns service account u, a record loaded from
+// storage, as the create that replication, the first sync, heal and export
+// carry. Its claims and its embedded policy are read from the token of that
+// record, so that every part of the snapshot is of one revision: a server's
+// cache may hold the account as it was before an edit made through another
+// server.
+func serviceAccountSnapshot(u UserIdentity) (madmin.SRSvcAccCreate, error) {
+	jwtClaims, err := extractJWTClaims(u)
+	if err != nil {
+		return madmin.SRSvcAccCreate{}, err
+	}
+	// Extraction adds a decoded policy for local authorization. Transport only
+	// the token's claims, so peers and imports do not sign this derived value.
+	jwtClaims.Delete(sessionPolicyNameExtracted)
+	embeddedPolicy, err := embeddedServiceAccountPolicy(jwtClaims)
+	if err != nil {
+		return madmin.SRSvcAccCreate{}, err
+	}
+	var policyJSON []byte
+	if embeddedPolicy != nil {
+		if policyJSON, err = json.Marshal(embeddedPolicy); err != nil {
+			return madmin.SRSvcAccCreate{}, err
 		}
 	}
-
-	return sa, embeddedPolicy, nil
+	cr := u.Credentials
+	return madmin.SRSvcAccCreate{
+		Parent:        cr.ParentUser,
+		AccessKey:     cr.AccessKey,
+		SecretKey:     cr.SecretKey,
+		Groups:        cr.Groups,
+		Claims:        jwtClaims.Map(),
+		SessionPolicy: policyJSON,
+		Status:        cr.Status,
+		Name:          cr.Name,
+		Description:   cr.Description,
+		Expiration:    &cr.Expiration,
+	}, nil
 }
 
 // GetTemporaryAccount - wrapper method to get information about a temporary account
@@ -1398,25 +1495,6 @@ func (sys *IAMSys) getAccountWithClaims(ctx context.Context, accessKey string) (
 	return acc, jwtClaims, nil
 }
 
-// GetClaimsForSvcAcc - gets the claims associated with the service account.
-func (sys *IAMSys) GetClaimsForSvcAcc(ctx context.Context, accessKey string) (map[string]any, error) {
-	if !sys.Initialized() {
-		return nil, errServerNotInitialized
-	}
-
-	sa, ok := sys.store.GetUser(accessKey)
-	if !ok || !sa.Credentials.IsServiceAccount() {
-		return nil, errNoSuchServiceAccount
-	}
-
-	jwtClaims, err := extractJWTClaims(sa)
-	if err != nil {
-		return nil, err
-	}
-
-	return jwtClaims.Map(), nil
-}
-
 // DeleteServiceAccount - delete a service account
 func (sys *IAMSys) DeleteServiceAccount(ctx context.Context, accessKey string, notifyPeers bool) error {
 	if !sys.Initialized() {

cmd/object-api-interface.go

@@ -71,6 +71,7 @@ type ObjectOptions struct {
 	DeleteMarker            bool // Is only set in DELETE operations for delete marker replication
 	CheckDMReplicationReady bool // Is delete marker ready to be replicated - set only during HEAD
 	Tagging                 bool // Is only in GET/HEAD operations to return tagging metadata along with regular metadata and body.
+	TaggingCount            bool // GET/HEAD caller is authorized to receive object tag metadata.
 
 	UserDefined         map[string]string   // only set in case of POST/PUT operations
 	ObjectAttributes    map[string]struct{} // Attribute tags defined by the users for the GetObjectAttributes request
@@ -122,6 +123,10 @@ type ObjectOptions struct {
 
 	// Pools-layer version resolver; the caller holds the shared object lock.
 	replicaObjectInfo GetObjectInfoFn
+	// Verifies protected content in every pool before a replica commits.
+	replicaContentGuard replicaContentGuardFn
+	// Selected under the object locks, before copy encryption/compression.
+	copyPlan *copyObjectPlan
 
 	// RefuseLockedOverwrite refuses, under the destination's write lock, a
 	// write that would replace a stored version Object Lock protects: the
@@ -297,6 +302,7 @@ type ObjectLayer interface {
 	NewObjectNSLock(bucket, object string) RWLocker
 	// lockObjects locks several objects together, see erasureServerPools.
 	lockObjects(ctx context.Context, reqs ...objectLockRequest) (LockContext, func(), error)
+	prepareCopyObject(ctx context.Context, srcBucket, srcObject, dstBucket, dstObject string, srcInfo ObjectInfo, srcOpts, dstOpts ObjectOptions) (copyObjectPlan, error)
 
 	// Storage operations.
 	Shutdown(context.Context) error

cmd/object-api-options.go

@@ -303,13 +303,18 @@ func delOpts(ctx context.Context, r *http.Request, bucket, object string) (opts
 		}
 	}
 
+	vc, _, err := checkBucketDeleteMetadata(bucket)
+	if err != nil {
+		return opts, err
+	}
+
 	opts.DeletePrefix = deletePrefix
-	opts.Versioned = globalBucketVersioningSys.PrefixEnabled(bucket, object)
+	opts.Versioned = vc.PrefixEnabled(object)
 	// Objects matching prefixes should not leave delete markers,
 	// dramatically reduces namespace pollution while keeping the
 	// benefits of replication, make sure to apply version suspension
 	// only at bucket level instead.
-	opts.VersionSuspended = globalBucketVersioningSys.Suspended(bucket)
+	opts.VersionSuspended = vc.Suspended()
 	// For directory objects, delete `null` version permanently.
 	if isDirObject(object) && opts.VersionID == "" {
 		opts.VersionID = nullVersionID

cmd/object-api-utils.go

@@ -916,7 +916,7 @@ func NewGetObjectReader(rs *HTTPRangeSpec, oi ObjectInfo, opts ObjectOptions, h
 			}
 			// Decompression reader.
 			var dopts []s2.ReaderOption
-			if off > 0 || decOff > 0 {
+			if off > 0 || decOff > 0 || decryptSkip > 0 {
 				// We are not starting at the beginning, so ignore stream identifiers.
 				dopts = append(dopts, s2.ReaderIgnoreStreamIdentifier())
 			}

cmd/object-attributes-archive-tags_test.go

@@ -0,0 +1,170 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"archive/zip"
+	"bytes"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"testing"
+
+	"github.com/minio/minio/internal/auth"
+	xhttp "github.com/minio/minio/internal/http"
+)
+
+func TestAPIAttributesAndArchiveStoredTags(t *testing.T) {
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{VersioningEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, root auth.Credentials, t *testing.T) {
+			_, err := globalBucketMetadataSys.Update(t.Context(), bucket, bucketVersioningConfig, enabledBucketVersioningConfig)
+			if err != nil {
+				t.Fatal(err)
+			}
+			var archive bytes.Buffer
+			zw := zip.NewWriter(&archive)
+			entry, err := zw.Create("entry.txt")
+			if err != nil {
+				t.Fatal(err)
+			}
+			if _, err = entry.Write([]byte("private entry")); err != nil {
+				t.Fatal(err)
+			}
+			if err = zw.Close(); err != nil {
+				t.Fatal(err)
+			}
+			for _, indexed := range []bool{false, true} {
+				key := fmt.Sprintf("tagged-%v.zip", indexed)
+				put := func(tag string) ObjectInfo {
+					oi, err := obj.PutObject(t.Context(), bucket, key, mustGetPutObjReader(t, bytes.NewReader(archive.Bytes()), int64(archive.Len()), "", ""), ObjectOptions{Versioned: true, UserDefined: map[string]string{xhttp.AmzObjectTagging: "tier=" + tag}})
+					if err != nil {
+						t.Fatal(err)
+					}
+					return oi
+				}
+				old := put("public")
+				latest := put("restricted")
+				if indexed {
+					if _, err := updateObjectMetadataWithZipInfo(t.Context(), obj, bucket, key, ObjectOptions{VersionID: latest.VersionID}); err != nil {
+						t.Fatal(err)
+					}
+				}
+				for _, anonymous := range []bool{false, true} {
+					for _, effect := range []string{"Allow", "Deny"} {
+						actions := `"s3:GetObject","s3:GetObjectAttributes","s3:GetObjectVersion","s3:GetObjectVersionAttributes"`
+						condition := `"Condition":{"StringEquals":{"s3:ExistingObjectTag/tier":"restricted"}}`
+						statement := fmt.Sprintf(`{"Effect":"%s","Action":[%s],"Resource":["arn:aws:s3:::%s/*"],%s}`, effect, actions, bucket, condition)
+						if effect == "Deny" {
+							statement += fmt.Sprintf(`,{"Effect":"Allow","Action":[%s],"Resource":["arn:aws:s3:::%s/*"]}`, actions, bucket)
+						}
+						statement += fmt.Sprintf(`,{"Effect":"Allow","Action":["s3:ListBucket"],"Resource":["arn:aws:s3:::%s"]}`, bucket)
+						creds := newDeleteAuthzPolicyUser(t, backend, bucket, "["+statement+"]")
+						if anonymous {
+							document := `{"Version":"2012-10-17","Statement":[` + strings.ReplaceAll(statement, `"Effect":`, `"Principal":"*","Effect":`) + `]}`
+							if _, err := globalBucketMetadataSys.Update(t.Context(), bucket, bucketPolicyConfig, []byte(document)); err != nil {
+								t.Fatal(err)
+							}
+						}
+						for _, operation := range []string{"attributes", "version-attributes", http.MethodGet, http.MethodHead, "LIST"} {
+							t.Run(fmt.Sprintf("%s/indexed=%v/anonymous=%v/%s/%s", backend, indexed, anonymous, effect, operation), func(t *testing.T) {
+								verb := http.MethodGet
+								target := getGetObjectURL("", bucket, key+"/entry.txt")
+								headers := map[string]string{xMinIOExtract: "true", xhttp.AmzObjectTagging: "tier=public"}
+								want := http.StatusOK
+								if effect == "Deny" {
+									want = http.StatusForbidden
+								}
+								switch operation {
+								case "attributes", "version-attributes":
+									q := url.Values{"attributes": {""}}
+									if operation == "version-attributes" {
+										q.Set("versionId", old.VersionID)
+										if effect == "Allow" {
+											want = http.StatusForbidden
+										} else {
+											want = http.StatusOK
+										}
+									}
+									target = makeTestTargetURL("", bucket, key, q)
+									headers[xhttp.AmzObjectAttributes] = "ETag,ObjectSize"
+								case http.MethodHead:
+									verb = http.MethodHead
+								case "LIST":
+									target = "/" + bucket + "?list-type=2&prefix=" + key + "/"
+								}
+								req, err := newTestSignedRequestV4(verb, target, 0, nil, creds.AccessKey, creds.SecretKey, headers)
+								if err != nil {
+									t.Fatal(err)
+								}
+								if anonymous {
+									req.Header.Del("Authorization")
+								}
+								rec := httptest.NewRecorder()
+								router.ServeHTTP(rec, req)
+								if rec.Code != want {
+									t.Fatalf("status %d, want %d: %s", rec.Code, want, rec.Body.String())
+								}
+								if rec.Code == http.StatusOK && operation == http.MethodGet && rec.Body.String() != "private entry" {
+									t.Fatalf("wrong extracted content: %s", rec.Body.String())
+								}
+								if rec.Code == http.StatusForbidden && strings.Contains(rec.Body.String(), "private entry") {
+									t.Fatal("denied response disclosed content")
+								}
+							})
+						}
+					}
+				}
+			}
+			// Each Attributes action is necessary; a conditional Deny on either
+			// action must win even when the other action is unconditionally allowed.
+			for _, versioned := range []bool{false, true} {
+				for _, deniedAction := range []string{"GetObject", "GetObjectAttributes"} {
+					actions := `"s3:GetObject","s3:GetObjectAttributes"`
+					if versioned {
+						actions = `"s3:GetObjectVersion","s3:GetObjectVersionAttributes"`
+						deniedAction = strings.Replace(deniedAction, "GetObject", "GetObjectVersion", 1)
+					}
+					statements := fmt.Sprintf(`[{"Effect":"Allow","Action":[%s],"Resource":["arn:aws:s3:::%s/*"]},{"Effect":"Deny","Action":["s3:%s"],"Resource":["arn:aws:s3:::%s/*"],"Condition":{"StringEquals":{"s3:ExistingObjectTag/tier":"restricted"}}}]`, actions, bucket, deniedAction, bucket)
+					creds := newDeleteAuthzPolicyUser(t, backend, bucket, statements)
+					q := url.Values{"attributes": {""}}
+					if versioned {
+						oi, err := obj.GetObjectInfo(t.Context(), bucket, "tagged-true.zip", ObjectOptions{})
+						if err != nil {
+							t.Fatal(err)
+						}
+						q.Set("versionId", oi.VersionID)
+					}
+					req, err := newTestSignedRequestV4(http.MethodGet, makeTestTargetURL("", bucket, "tagged-true.zip", q), 0, nil, creds.AccessKey, creds.SecretKey, map[string]string{xhttp.AmzObjectAttributes: "ETag"})
+					if err != nil {
+						t.Fatal(err)
+					}
+					rec := httptest.NewRecorder()
+					router.ServeHTTP(rec, req)
+					if rec.Code != http.StatusForbidden {
+						t.Fatalf("%s Deny: %d %s", deniedAction, rec.Code, rec.Body.String())
+					}
+				}
+			}
+			listOnly := newDeleteAuthzPolicyUser(t, backend, bucket, fmt.Sprintf(`[{"Effect":"Allow","Action":["s3:ListBucket"],"Resource":["arn:aws:s3:::%s"]}]`, bucket))
+			for _, extract := range []bool{false, true} {
+				req, err := newTestSignedRequestV4(http.MethodGet, "/"+bucket+"?list-type=2&prefix=tagged-true.zip/", 0, nil, listOnly.AccessKey, listOnly.SecretKey, map[string]string{xMinIOExtract: fmt.Sprint(extract)})
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				want := http.StatusOK
+				if extract {
+					want = http.StatusForbidden
+				}
+				if rec.Code != want {
+					t.Fatalf("list-only extract=%v: %d %s", extract, rec.Code, rec.Body.String())
+				}
+			}
+		},
+	})
+}

cmd/object-attributes-read-error_test.go

@@ -0,0 +1,99 @@
+// Copyright (c) 2026 Denis Babchuk
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"encoding/xml"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"testing"
+
+	"github.com/minio/minio/internal/auth"
+	xhttp "github.com/minio/minio/internal/http"
+)
+
+// GetObjectAttributes answers NoSuchKey with AccessDenied to a caller without
+// s3:ListBucket on the bucket, as S3 does, so that a missing object cannot be
+// told apart from a forbidden one. A server error, such as lost read quorum,
+// must reach a caller allowed to read the object as the error it is.
+func TestGetObjectAttributesReadQuorumLost(t *testing.T) {
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+	obj, dirs, err := prepareErasure16(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	z := obj.(*erasureServerPools)
+	previous := newObjectLayerFn()
+	setObjectLayer(z)
+	defer func() {
+		z.Shutdown(context.Background())
+		removeRoots(dirs)
+		setObjectLayer(previous)
+	}()
+	bucket, router, err := initAPIHandlerTest(ctx, z, nil, MakeBucketOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	const object, missing = "object", "missing"
+	if _, err := z.PutObject(ctx, bucket, object, mustGetPutObjReader(t, bytes.NewReader([]byte("data")), 4, "", ""), ObjectOptions{UserDefined: map[string]string{xhttp.AmzObjectTagging: "tier=restricted"}}); err != nil {
+		t.Fatal(err)
+	}
+
+	read := `{"Effect": "Allow", "Action": ["s3:GetObject", "s3:GetObjectAttributes"], "Resource": ["arn:aws:s3:::` + bucket + `/*"]}`
+	withoutList := newDeleteAuthzPolicyUser(t, "", bucket, "["+read+"]")
+	withList := newDeleteAuthzPolicyUser(t, "", bucket, "["+read+
+		`, {"Effect": "Allow", "Action": ["s3:ListBucket"], "Resource": ["arn:aws:s3:::`+bucket+`"]}]`)
+
+	tagged := newDeleteAuthzPolicyUser(t, "", bucket, `[{"Effect":"Allow","Action":["s3:GetObject","s3:GetObjectAttributes"],"Resource":["arn:aws:s3:::`+bucket+`/*"],"Condition":{"StringEquals":{"s3:ExistingObjectTag/tier":"restricted"}}}]`)
+	unauthorized := newDeleteAuthzPolicyUser(t, "", bucket, `[{"Effect":"Allow","Action":["s3:GetObjectAttributes"],"Resource":["arn:aws:s3:::`+bucket+`/*"]}]`)
+
+	check := func(stage, user string, creds auth.Credentials, key string, want int) {
+		t.Helper()
+		target := makeTestTargetURL("", bucket, key, url.Values{"attributes": []string{""}})
+		req, err := newTestSignedRequestV4(http.MethodGet, target, 0, nil, creds.AccessKey, creds.SecretKey,
+			map[string]string{xhttp.AmzObjectAttributes: "ETag"})
+		if err != nil {
+			t.Fatal(err)
+		}
+		rec := httptest.NewRecorder()
+		router.ServeHTTP(rec, req)
+		if rec.Code != want {
+			var apiErr APIErrorResponse
+			_ = xml.Unmarshal(rec.Body.Bytes(), &apiErr)
+			t.Errorf("%s: GetObjectAttributes %s by %s: status %d %s, want %d", stage, key, user, rec.Code, apiErr.Code, want)
+		}
+	}
+
+	check("healthy", "withoutList", withoutList, object, http.StatusOK)
+	check("healthy", "withList", withList, object, http.StatusOK)
+	check("healthy", "withoutList", withoutList, missing, http.StatusForbidden)
+	check("healthy", "withList", withList, missing, http.StatusNotFound)
+
+	check("healthy", "tagged", tagged, object, http.StatusOK)
+	check("healthy", "unauthorized", unauthorized, object, http.StatusForbidden)
+
+	defer objectReadFault(z, bucket, object, 10)()
+	check("read quorum lost", "withoutList", withoutList, object, http.StatusServiceUnavailable)
+	check("read quorum lost", "withList", withList, object, http.StatusServiceUnavailable)
+	check("read quorum lost", "tagged", tagged, object, http.StatusServiceUnavailable)
+	check("read quorum lost", "unauthorized", unauthorized, object, http.StatusForbidden)
+}

cmd/object-compressed-range_test.go

@@ -0,0 +1,183 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"fmt"
+	"net/http"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/minio/internal/crypto"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/minio/minio/internal/kms"
+)
+
+// Indexed reads may skip into the first decrypted block while both the disk
+// offset and the remaining decompressed skip are zero. The reader must still
+// accept a compression block without the original stream identifier.
+func TestAPICompressedEncryptedRange(t *testing.T) {
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t,
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			previousKMS, previousTLS := GlobalKMS, globalIsTLS
+			var err error
+			GlobalKMS, err = kms.NewBuiltin("range-key", bytes.Repeat([]byte{0x42}, 32))
+			if err != nil {
+				t.Fatal(err)
+			}
+			globalIsTLS = true
+			defer func() { GlobalKMS, globalIsTLS = previousKMS, previousTLS }()
+			restore := setCopyChecksumCompression(true)
+			defer restore()
+			part := bytes.Repeat([]byte("compressible-A"), 1<<20)
+			for _, mode := range []string{"compressed", "sse-s3", "sse-kms"} {
+				for _, multipart := range []bool{false, true} {
+					t.Run(fmt.Sprintf("%s/%s/multipart=%t", backend, mode, multipart), func(t *testing.T) {
+						key := fmt.Sprintf("range-%s-%t.txt", mode, multipart)
+						headers := map[string]string{}
+						switch mode {
+						case "sse-s3":
+							headers[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionAES
+						case "sse-kms":
+							headers[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionKMS
+							headers[xhttp.AmzServerSideEncryptionKmsID] = "range-key"
+						}
+						data := part
+						if multipart {
+							data = attributesPartsUpload(t, router, cred, bucket, key, headers,
+								[][]byte{part, bytes.Repeat([]byte("compressible-B"), 1<<20)}, []int{1, 2})
+						} else {
+							putCopyChecksumSource(t, router, cred, bucket, key, data, headers)
+						}
+						oi, err := obj.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{})
+						if err != nil {
+							t.Fatal(err)
+						}
+						_, encrypted := crypto.IsEncrypted(oi.UserDefined)
+						if !oi.IsCompressed() || encrypted != (mode != "compressed") || len(oi.Parts) == 0 || len(oi.Parts[0].Index) == 0 {
+							t.Fatal("fixture must have indexed compression and the requested encryption")
+						}
+						if encrypted {
+							off, decOff, _, skip, _ := getCompressedOffsets(oi, 1<<20, func(b []byte) ([]byte, error) { return oi.compressionIndexDecrypt(b, nil) })
+							if off != 0 || decOff != 0 || skip <= 0 {
+								t.Fatalf("fixture misses boundary: off=%d decOff=%d decryptSkip=%d", off, decOff, skip)
+							}
+						}
+						offsets := []int{0, 100, 1 << 20, 1<<20 + 1, len(data) - 1000}
+						if multipart {
+							offsets = append(offsets, len(part)-500, len(part), len(part)+1<<20)
+						}
+						for _, start := range offsets {
+							rec := attributesPartsSignedRequest(t, router, cred, http.MethodGet, getGetObjectURL("", bucket, key), nil,
+								map[string]string{"Range": fmt.Sprintf("bytes=%d-%d", start, start+999)})
+							if rec.Code != http.StatusPartialContent || !bytes.Equal(rec.Body.Bytes(), data[start:start+1000]) {
+								t.Errorf("range at %d: status=%d bytes=%d, want 206 and exact slice", start, rec.Code, rec.Body.Len())
+							}
+						}
+						rec := attributesPartsSignedRequest(t, router, cred, http.MethodGet, getGetObjectURL("", bucket, key), nil, nil)
+						if rec.Code != http.StatusOK || !bytes.Equal(rec.Body.Bytes(), data) {
+							t.Fatal("full read changed after ranged reads")
+						}
+					})
+				}
+			}
+		},
+	})
+}
+
+func TestAPICompressedEncryptedRangeCorruptBlockRejected(t *testing.T) {
+	resetTestGlobals()
+	ctx := GlobalContext
+	obj, fsDir, err := prepareFSWithDisks(ctx, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer removeAll(fsDir)
+	defer obj.Shutdown(ctx)
+
+	bucket, router, err := initAPIHandlerTest(ctx, obj, nil, MakeBucketOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := newTestConfig(globalMinioDefaultRegion, obj); err != nil {
+		t.Fatal(err)
+	}
+	previousKMS, previousTLS := GlobalKMS, globalIsTLS
+	GlobalKMS, err = kms.NewBuiltin("range-key", bytes.Repeat([]byte{0x42}, 32))
+	if err != nil {
+		t.Fatal(err)
+	}
+	globalIsTLS = true
+	defer func() { GlobalKMS, globalIsTLS = previousKMS, previousTLS }()
+	restore := setCopyChecksumCompression(true)
+	defer restore()
+
+	cred := globalActiveCred
+	payload := bytes.Repeat([]byte("compressible-A"), 1<<20)
+
+	for _, mode := range []string{"compressed", "sse-kms"} {
+		key := "corrupt-" + mode + ".txt"
+		headers := map[string]string{}
+		if mode == "sse-kms" {
+			headers[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionKMS
+			headers[xhttp.AmzServerSideEncryptionKmsID] = "range-key"
+		}
+		putCopyChecksumSource(t, router, cred, bucket, key, payload, headers)
+
+		rec := attributesPartsSignedRequest(t, router, cred, http.MethodGet, getGetObjectURL("", bucket, key), nil,
+			map[string]string{"Range": fmt.Sprintf("bytes=%d-%d", 1<<20, (1<<20)+999)})
+		if rec.Code != http.StatusPartialContent || !bytes.Equal(rec.Body.Bytes(), payload[1<<20:(1<<20)+1000]) {
+			t.Fatalf("%s pre-corrupt range failed: code=%d", mode, rec.Code)
+		}
+
+		corruptedAny := false
+		_ = filepath.Walk(fsDir, func(path string, info os.FileInfo, walkErr error) error {
+			if walkErr != nil || info.IsDir() || !strings.Contains(path, key) {
+				return nil
+			}
+			raw, rerr := os.ReadFile(path)
+			if rerr != nil {
+				return nil
+			}
+			if strings.HasSuffix(path, "part.1") {
+				raw[len(raw)/2] ^= 0xff
+				_ = os.WriteFile(path, raw, info.Mode())
+				corruptedAny = true
+			} else if strings.HasSuffix(path, xlStorageFormatFile) && len(raw) > 256 {
+				raw[len(raw)-64] ^= 0xff
+				_ = os.WriteFile(path, raw, info.Mode())
+				corruptedAny = true
+			}
+			return nil
+		})
+		if !corruptedAny {
+			t.Fatalf("%s: failed to locate backing storage file to corrupt", mode)
+		}
+
+		recAfter := attributesPartsSignedRequest(t, router, cred, http.MethodGet, getGetObjectURL("", bucket, key), nil,
+			map[string]string{"Range": fmt.Sprintf("bytes=%d-%d", 1<<20, (1<<20)+999)})
+		if recAfter.Code == http.StatusPartialContent && recAfter.Body.Len() == 1000 {
+			t.Fatalf("%s: corrupted range unexpectedly returned 206 with 1000 bytes", mode)
+		}
+	}
+}

cmd/object-copy-pools_test.go

@@ -0,0 +1,408 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"crypto/md5"
+	"encoding/base64"
+	"fmt"
+	"maps"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/hash"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/minio/minio/internal/kms"
+)
+
+// Place uploaded versions in specific pools, while retaining the real HTTP
+// encryption/compression pipeline and the normal pools-layer copy operation.
+type copyUploadPool struct {
+	*erasureServerPools
+	uploadPool int
+}
+
+func (z *copyUploadPool) PutObject(ctx context.Context, bucket, object string, r *PutObjReader, opts ObjectOptions) (ObjectInfo, error) {
+	return z.serverPools[z.uploadPool].PutObject(ctx, bucket, object, r, opts)
+}
+
+func TestAPICopyHistoricalVersionAcrossPools(t *testing.T) {
+	z, _ := consistencyPools(t)
+	placed := &copyUploadPool{erasureServerPools: z}
+	bucket, router, err := initAPIHandlerTest(t.Context(), placed, nil, MakeBucketOptions{VersioningEnabled: true})
+	if err != nil {
+		t.Fatal(err)
+	}
+	setObjectLayer(placed)
+	if _, err = globalBucketMetadataSys.Update(t.Context(), bucket, bucketVersioningConfig, enabledBucketVersioningConfig); err != nil {
+		t.Fatal(err)
+	}
+	previousKMS, previousTLS := GlobalKMS, globalIsTLS
+	GlobalKMS, err = kms.NewBuiltin("copy-key", bytes.Repeat([]byte{0x33}, 32))
+	if err != nil {
+		t.Fatal(err)
+	}
+	globalIsTLS = true
+	defer func() { GlobalKMS, globalIsTLS = previousKMS, previousTLS }()
+	customer := func(value byte) map[string]string {
+		key := bytes.Repeat([]byte{value}, 32)
+		sum := md5.Sum(key)
+		return map[string]string{xhttp.AmzServerSideEncryptionCustomerAlgorithm: xhttp.AmzEncryptionAES, xhttp.AmzServerSideEncryptionCustomerKey: base64.StdEncoding.EncodeToString(key), xhttp.AmzServerSideEncryptionCustomerKeyMD5: base64.StdEncoding.EncodeToString(sum[:])}
+	}
+	for _, tc := range []struct{ mode, movement string }{
+		{"plain", "active"},
+		{"compressed", "active"},
+		{"sse-s3", "active"},
+		{"sse-c", "active"},
+		{"sse-kms", "active"},
+		{"sse-c", "decommission"},
+		{"sse-kms", "rebalance"},
+	} {
+		mode := tc.mode
+		for _, sourcePool := range []int{0, 1} {
+			t.Run(fmt.Sprintf("%s/%s/source=%d", mode, tc.movement, sourcePool), func(t *testing.T) {
+				compressed := mode == "compressed"
+				restore := setCopyChecksumCompression(true)
+				globalCompressConfigMu.Lock()
+				globalCompressConfig.Enabled = compressed
+				globalCompressConfigMu.Unlock()
+				defer restore()
+				sourceHeaders := map[string]string{xhttp.AmzChecksumCRC32: ""}
+				if mode == "sse-s3" {
+					sourceHeaders[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionAES
+				}
+				if mode == "sse-kms" {
+					sourceHeaders[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionKMS
+					sourceHeaders[xhttp.AmzServerSideEncryptionKmsID] = "copy-key"
+					sourceHeaders[xhttp.AmzServerSideEncryptionKmsContext] = base64.StdEncoding.EncodeToString([]byte(`{"tenant":"source"}`))
+				}
+				if mode == "sse-c" {
+					maps.Copy(sourceHeaders, customer(0x11))
+				}
+				pattern := []byte("historical encrypted compressed content-")
+				repeats := 8192
+				if mode == "plain" {
+					repeats = compMinIndexSize/len(pattern) + 1
+				}
+				data := bytes.Repeat(pattern, repeats)
+				sourceHeaders[xhttp.AmzChecksumCRC32] = mustChecksum(t, hash.ChecksumCRC32, data)
+				key := fmt.Sprintf("copy-%s-%s-%d.txt", mode, tc.movement, sourcePool)
+				placed.uploadPool = sourcePool
+				putCopyChecksumSource(t, router, globalActiveCred, bucket, key, data, sourceHeaders)
+				original, err := z.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{})
+				if err != nil {
+					t.Fatal(err)
+				}
+				if original.VersionID == "" {
+					t.Fatal("fixture has no version ID")
+				}
+				if _, err := z.serverPools[sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: original.VersionID}); err != nil {
+					t.Fatal(err)
+				}
+				if original.IsCompressed() != compressed {
+					t.Fatalf("fixture compressed=%v", original.IsCompressed())
+				}
+				placed.uploadPool = 1 - sourcePool
+				putCopyChecksumSource(t, router, globalActiveCred, bucket, key, []byte("newer version"), nil)
+				newer, err := z.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{})
+				if err != nil {
+					t.Fatal(err)
+				}
+				setCopyMovingPool(t, z, sourcePool, tc.movement)
+				// Toggle compression so metadata has to describe the bytes written now.
+				restore()
+				restoreTarget := setCopyChecksumCompression(true)
+				globalCompressConfigMu.Lock()
+				globalCompressConfig.Enabled = !compressed
+				globalCompressConfigMu.Unlock()
+				defer restoreTarget()
+				headers := map[string]string{xhttp.AmzMetadataDirective: "REPLACE"}
+				getHeaders := map[string]string{}
+				if mode == "sse-s3" {
+					headers[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionAES
+				}
+				if mode == "sse-kms" {
+					headers[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionKMS
+					headers[xhttp.AmzServerSideEncryptionKmsID] = "copy-key"
+					headers[xhttp.AmzServerSideEncryptionKmsContext] = base64.StdEncoding.EncodeToString([]byte(`{"tenant":"destination"}`))
+				}
+				if mode == "sse-c" {
+					maps.Copy(headers, customer(0x22))
+					maps.Copy(getHeaders, customer(0x22))
+					old := customer(0x11)
+					headers[xhttp.AmzServerSideEncryptionCopyCustomerAlgorithm] = old[xhttp.AmzServerSideEncryptionCustomerAlgorithm]
+					headers[xhttp.AmzServerSideEncryptionCopyCustomerKey] = old[xhttp.AmzServerSideEncryptionCustomerKey]
+					headers[xhttp.AmzServerSideEncryptionCopyCustomerKeyMD5] = old[xhttp.AmzServerSideEncryptionCustomerKeyMD5]
+				}
+				rec := copyChecksumRequest(t, router, globalActiveCred, bucket, key+"?versionId="+original.VersionID, key, headers)
+				if rec.Code != http.StatusOK {
+					t.Fatalf("copy: %d %s", rec.Code, rec.Body.String())
+				}
+				copied, err := z.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{})
+				if err != nil || copied.VersionID == "" || copied.VersionID == original.VersionID || copied.VersionID == newer.VersionID {
+					t.Fatalf("copy did not create a version: %+v %v", copied, err)
+				}
+				if copied.IsCompressed() != (!compressed && mode != "sse-c") {
+					t.Fatalf("copy did not use destination compression setting: %v", copied.IsCompressed())
+				}
+				if copied.IsCompressed() && len(data) > compMinIndexSize {
+					if len(copied.Parts) == 0 || len(copied.Parts[0].Index) == 0 {
+						t.Fatalf("compressed multi-block copy lost seek index: %+v", copied.Parts)
+					}
+					rangeHeaders := maps.Clone(getHeaders)
+					rangeHeaders["Range"] = "bytes=6000000-6000127"
+					req, err := newTestSignedRequestV4(http.MethodGet, getGetObjectURL("", bucket, key)+"?versionId="+copied.VersionID, 0, nil, globalActiveCred.AccessKey, globalActiveCred.SecretKey, rangeHeaders)
+					if err != nil {
+						t.Fatal(err)
+					}
+					rrec := httptest.NewRecorder()
+					router.ServeHTTP(rrec, req)
+					if rrec.Code != http.StatusPartialContent || !bytes.Equal(rrec.Body.Bytes(), data[6000000:6000128]) {
+						t.Fatalf("ranged GET on compressed copy: %d len=%d", rrec.Code, rrec.Body.Len())
+					}
+				}
+				if mode == "sse-kms" {
+					assertFederationKMSContext(t, copied, headers[xhttp.AmzServerSideEncryptionKmsContext])
+					assertFederationKMSContext(t, original, sourceHeaders[xhttp.AmzServerSideEncryptionKmsContext])
+				}
+				if _, err = z.serverPools[1-sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: copied.VersionID}); err != nil {
+					t.Fatalf("copy was not placed with destination: %v", err)
+				}
+				read := func(version string, headers map[string]string, want []byte) {
+					t.Helper()
+					req, err := newTestSignedRequestV4(http.MethodGet, getGetObjectURL("", bucket, key)+"?versionId="+version, 0, nil, globalActiveCred.AccessKey, globalActiveCred.SecretKey, headers)
+					if err != nil {
+						t.Fatal(err)
+					}
+					rec := httptest.NewRecorder()
+					router.ServeHTTP(rec, req)
+					if rec.Code != http.StatusOK || !bytes.Equal(rec.Body.Bytes(), want) {
+						t.Fatalf("GET version %s: %d body length=%d, want %d", version, rec.Code, rec.Body.Len(), len(want))
+					}
+				}
+				read(copied.VersionID, getHeaders, data)
+				oldHeaders := map[string]string{}
+				if mode == "sse-c" {
+					oldHeaders = customer(0x11)
+				}
+				read(original.VersionID, oldHeaders, data)
+				read(newer.VersionID, nil, []byte("newer version"))
+			})
+		}
+	}
+}
+
+// Internal metadata updates do not all set MetadataChg. They must still
+// address the requested historical version, and must never create a new one.
+func TestPoolsCopyExactVersionMetadata(t *testing.T) {
+	z, bucket := consistencyPools(t)
+	for sourcePool := range 2 {
+		key := fmt.Sprintf("exact-%d", sourcePool)
+		older := putConsistencyObject(t, z, bucket, key, sourcePool, "old data", ObjectOptions{Versioned: true, MTime: UTCNow().Add(-time.Hour)})
+		newer := putConsistencyObject(t, z, bucket, key, 1-sourcePool, "new data", ObjectOptions{Versioned: true, MTime: UTCNow()})
+		gr, err := z.GetObjectNInfo(t.Context(), bucket, key, nil, nil, ObjectOptions{VersionID: older.VersionID, NoLock: true})
+		if err != nil {
+			t.Fatal(err)
+		}
+		info := gr.ObjInfo
+		info.Reader, err = hash.NewReader(t.Context(), gr, info.Size, "", "", info.Size)
+		if err != nil {
+			gr.Close()
+			t.Fatal(err)
+		}
+		info.PutObjReader = NewPutObjReader(info.Reader)
+		info.metadataOnly = true
+		info.UserDefined["updated"] = "yes"
+		_, err = z.CopyObject(t.Context(), bucket, key, bucket, key, info, ObjectOptions{VersionID: older.VersionID}, ObjectOptions{Versioned: true, VersionID: older.VersionID, MTime: older.ModTime})
+		gr.Close()
+		if err != nil {
+			t.Fatal(err)
+		}
+		got, err := z.serverPools[sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: older.VersionID})
+		if err != nil || got.UserDefined["updated"] != "yes" {
+			t.Fatalf("historical metadata not updated: %v %v", got.UserDefined, err)
+		}
+		got, err = z.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{})
+		if err != nil || got.VersionID != newer.VersionID || got.UserDefined["updated"] != "" {
+			t.Fatalf("latest changed: %+v %v", got, err)
+		}
+		if got := readCopyChecksumObject(t, z, bucket, key, ObjectOptions{VersionID: older.VersionID}); string(got) != "old data" {
+			t.Fatalf("historical body changed: %q", got)
+		}
+	}
+}
+
+func setCopyMovingPool(t *testing.T, z *erasureServerPools, pool int, movement string) {
+	t.Helper()
+	switch movement {
+	case "decommission":
+		z.poolMetaMutex.Lock()
+		z.poolMeta.Pools[pool].Decommission = &PoolDecommissionInfo{}
+		z.poolMetaMutex.Unlock()
+		t.Cleanup(func() {
+			z.poolMetaMutex.Lock()
+			z.poolMeta.Pools[pool].Decommission = nil
+			z.poolMetaMutex.Unlock()
+		})
+	case "rebalance":
+		z.rebalMu.Lock()
+		z.rebalMeta = &rebalanceMeta{PoolStats: []*rebalanceStats{{}, {}}}
+		z.rebalMeta.PoolStats[pool] = &rebalanceStats{Participating: true, Info: rebalanceInfo{Status: rebalStarted}}
+		z.rebalMu.Unlock()
+		t.Cleanup(func() { z.rebalMu.Lock(); z.rebalMeta = nil; z.rebalMu.Unlock() })
+	}
+}
+
+// The content that a metadata-only replica preserves must be the same content
+// that reads selected, even when write allocation would skip its pool.
+func TestCopyReplicaMetadataMovingPool(t *testing.T) {
+	z, _ := consistencyPools(t)
+	bucket, router, err := initAPIHandlerTest(t.Context(), z, nil, MakeBucketOptions{LockEnabled: true})
+	mustIAM(t, err)
+	setObjectLayer(z)
+	_, err = globalBucketMetadataSys.Update(t.Context(), bucket, bucketVersioningConfig, enabledBucketVersioningConfig)
+	mustIAM(t, err)
+	const body = "current-body"
+	for _, api := range []bool{false, true} {
+		for sourcePool := range 2 {
+			for _, movement := range []string{"decommission", "rebalance"} {
+				for _, kind := range []string{"uuid", "null"} {
+					for _, duplicate := range []string{"absent", "older", "tie"} {
+						// The lower pool index wins equal ModTimes, just as on reads.
+						if duplicate == "tie" && sourcePool != 0 {
+							continue
+						}
+						t.Run(fmt.Sprintf("api=%t/source=%d/%s/%s/%s", api, sourcePool, movement, kind, duplicate), func(t *testing.T) {
+							key := fmt.Sprintf("metadata-%t-%d-%s-%s-%s", api, sourcePool, movement, kind, duplicate)
+							oi := putConsistencyObject(t, z, bucket, key, sourcePool, body, ObjectOptions{
+								Versioned: kind == "uuid", MTime: UTCNow().Add(-time.Minute),
+								WantChecksum: hash.NewChecksumFromData(hash.ChecksumCRC32, []byte(body)),
+							})
+							version := oi.VersionID
+							if version == "" {
+								version = nullVersionID
+							}
+							if duplicate != "absent" {
+								stamp := oi.ModTime
+								if duplicate == "older" {
+									stamp = stamp.Add(-time.Hour)
+								}
+								putConsistencyObject(t, z, bucket, key, 1-sourcePool, "stale---body", ObjectOptions{
+									Versioned: kind == "uuid", VersionID: version, MTime: stamp,
+									UserDefined: poolLockMetadata("", "ON", "", objectLockTestStamp1000),
+								})
+							}
+							if got := readCopyChecksumObject(t, z, bucket, key, ObjectOptions{VersionID: version}); string(got) != body {
+								t.Fatalf("fixture: %q", got)
+							}
+							setCopyMovingPool(t, z, sourcePool, movement)
+							if api {
+								headers := map[string]string{
+									xhttp.AmzCopySource:        "/" + bucket + "/" + key + "?versionId=" + version,
+									xhttp.AmzMetadataDirective: "REPLACE", "X-Amz-Meta-Updated": "yes",
+									xhttp.MinIOSourceReplicationRequest: "true", xhttp.AmzBucketReplicationStatus: "REPLICA",
+								}
+								rec := r5Request(t, router, globalActiveCred, http.MethodPut, "/"+bucket+"/"+key+"?versionId="+version, "", headers)
+								if rec.Code != http.StatusOK {
+									t.Fatalf("metadata copy: %d %s", rec.Code, rec.Body.String())
+								}
+								assertCopyChecksumResponse(t, rec, hash.ChecksumCRC32, []byte(body))
+							} else {
+								oi.metadataOnly = true
+								oi.UserDefined["X-Amz-Meta-Updated"] = "yes"
+								_, err = z.CopyObject(t.Context(), bucket, key, bucket, key, oi,
+									ObjectOptions{VersionID: version}, ObjectOptions{Versioned: kind == "uuid", VersionID: version, MTime: oi.ModTime, ReplicaLockReconcile: true})
+								mustIAM(t, err)
+							}
+							if got := readCopyChecksumObject(t, z, bucket, key, ObjectOptions{VersionID: version}); string(got) != body {
+								t.Fatalf("metadata copy replaced content: %q", got)
+							}
+							stored, err := z.serverPools[sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: version})
+							mustIAM(t, err)
+							if stored.UserDefined["X-Amz-Meta-Updated"] != "yes" || !bytes.Equal(stored.Checksum, oi.Checksum) {
+								t.Fatalf("metadata/checksum: %v, %x; want checksum %x", stored.UserDefined, stored.Checksum, oi.Checksum)
+							}
+							if duplicate != "absent" && storedObjectLockState(stored.UserDefined).legalHold != "ON" {
+								t.Fatal("lost protection from the retired copy")
+							}
+							_, err = z.serverPools[1-sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: version})
+							if !isErrObjectNotFound(err) && !isErrVersionNotFound(err) {
+								t.Fatalf("stale copy not retired: %v", err)
+							}
+						})
+					}
+				}
+			}
+		}
+	}
+}
+
+func TestAPICopyRewriteMovingPool(t *testing.T) {
+	z, _ := consistencyPools(t)
+	placed := &copyUploadPool{erasureServerPools: z}
+	bucket, router, err := initAPIHandlerTest(t.Context(), placed, nil, MakeBucketOptions{})
+	mustIAM(t, err)
+	setObjectLayer(placed)
+	previousKMS := GlobalKMS
+	GlobalKMS, err = kms.NewBuiltin("copy-key", bytes.Repeat([]byte{0x33}, 32))
+	mustIAM(t, err)
+	defer func() { GlobalKMS = previousKMS }()
+	for sourcePool := range 2 {
+		for _, movement := range []string{"decommission", "rebalance"} {
+			for _, mode := range []string{"sse-s3", "checksum", "default-checksum", "invalid-self-copy"} {
+				t.Run(fmt.Sprintf("source=%d/%s/%s", sourcePool, movement, mode), func(t *testing.T) {
+					key := fmt.Sprintf("rewrite-%d-%s-%s", sourcePool, movement, mode)
+					data := []byte("rewriting a source on a draining pool")
+					sourceHeaders := map[string]string{}
+					if mode != "default-checksum" {
+						sourceHeaders[xhttp.AmzChecksumCRC32] = mustChecksum(t, hash.ChecksumCRC32, data)
+					}
+					placed.uploadPool = sourcePool
+					putCopyChecksumSource(t, router, globalActiveCred, bucket, key, data, sourceHeaders)
+					setCopyMovingPool(t, z, sourcePool, movement)
+					headers := map[string]string{xhttp.AmzMetadataDirective: "REPLACE"}
+					wantChecksum := hash.ChecksumCRC32
+					switch mode {
+					case "sse-s3":
+						headers[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionAES
+					case "checksum", "invalid-self-copy":
+						headers[xhttp.AmzChecksumAlgo] = "SHA256"
+						wantChecksum = hash.ChecksumSHA256
+						if mode == "invalid-self-copy" {
+							delete(headers, xhttp.AmzMetadataDirective)
+						}
+					case "default-checksum":
+						wantChecksum = hash.ChecksumCRC64NVME
+					}
+					rec := copyChecksumRequest(t, router, globalActiveCred, bucket, key, key, headers)
+					if mode == "invalid-self-copy" {
+						if rec.Code != http.StatusBadRequest {
+							t.Fatalf("invalid self-copy: %d %s", rec.Code, rec.Body.String())
+						}
+						_, err := z.serverPools[1-sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{})
+						if !isErrObjectNotFound(err) {
+							t.Fatalf("rejected copy wrote a destination: %v", err)
+						}
+						return
+					}
+					if rec.Code != http.StatusOK {
+						t.Fatalf("rewrite: %d %s", rec.Code, rec.Body.String())
+					}
+					assertCopyChecksumResponse(t, rec, wantChecksum, data)
+					if got := readCopyChecksumObject(t, z, bucket, key, ObjectOptions{}); !bytes.Equal(got, data) {
+						t.Fatalf("rewritten body: %q", got)
+					}
+					if _, err := z.serverPools[1-sourcePool].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{}); err != nil {
+						t.Fatalf("rewrite did not reach active pool: %v", err)
+					}
+					assertCopyChecksum(t, z, bucket, key, wantChecksum, data, false, nil)
+				})
+			}
+		}
+	}
+}

cmd/object-copy-replication-tagging_test.go

@@ -35,22 +35,15 @@ import (
 // the single-disk and 16-disk fixtures are single-pool backends.
 func TestAPICopyObjectReplicaTaggingTimestampUnderKMS(t *testing.T) {
 	defer DetectTestLeak(t)()
-	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{t: t, objAPITest: testAPICopyObjectReplicaTaggingTimestampUnderKMS})
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, objAPITest: testAPICopyObjectReplicaTaggingTimestampUnderKMS,
+		// Ignore host free-space percentage while retaining real disk I/O.
+		// Install once before IAM starts and keep the disks until shutdown.
+		wrapDisk: func(disk StorageAPI) StorageAPI { return tagTestCapacityDisk{StorageAPI: disk} },
+	})
 }
 
 func testAPICopyObjectReplicaTaggingTimestampUnderKMS(obj ObjectLayer, instance, bucket string, router http.Handler, creds auth.Credentials, t *testing.T) {
-	// Ignore the host free-space percentage while retaining real disk I/O.
-	for _, pool := range obj.(*erasureServerPools).serverPools {
-		for _, set := range pool.sets {
-			original := set.getDisks
-			disks := append([]StorageAPI(nil), original()...)
-			for i := range disks {
-				disks[i] = tagTestCapacityDisk{StorageAPI: disks[i]}
-			}
-			set.getDisks = func() []StorageAPI { return disks }
-			defer func() { set.getDisks = original }()
-		}
-	}
 	oldKMS, oldAuto := GlobalKMS, globalAutoEncryption
 	GlobalKMS = kms.NewStub("replica-tags-key")
 	globalAutoEncryption = false

cmd/object-handlers.go

@@ -139,7 +139,13 @@ func (api objectAPIHandlers) SelectObjectContentHandler(w http.ResponseWriter, r
 
 	// Check for auth type to return S3 compatible error.
 	// type to return the correct error (NoSuchKey vs AccessDenied)
-	if s3Error := checkRequestAuthType(ctx, r, policy.GetObjectAction, bucket, object); s3Error != ErrNone {
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
+	s3Error := authenticateRequest(ctx, r, policy.GetObjectAction)
+	if s3Error == ErrNone {
+		s3Error = authorizeVersionedRequestWithPotentialTags(ctx, r, policy.GetObjectAction, opts.VersionID)
+	}
+	if s3Error != ErrNone {
 		if getRequestAuthType(r) == authTypeAnonymous {
 			// As per "Permission" section in
 			// https://docs.aws.amazon.com/AmazonS3/latest/API/RESTObjectGET.html
@@ -199,6 +205,19 @@ func (api objectAPIHandlers) SelectObjectContentHandler(w http.ResponseWriter, r
 	gopts.NoLock = true // We already have a lock, we can live with it.
 	objInfo, err := getObjectInfo(ctx, bucket, object, gopts)
 	if err != nil {
+		if s3Error := authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, opts.VersionID, err); s3Error != ErrNone {
+			if getRequestAuthType(r) == authTypeAnonymous && toAPIError(ctx, err).Code == "NoSuchKey" &&
+				globalPolicySys.IsAllowed(policy.BucketPolicyArgs{
+					Action:          policy.ListBucketAction,
+					BucketName:      bucket,
+					ConditionValues: getConditionValues(r, "", auth.AnonymousCredentials),
+					IsOwner:         false,
+				}) {
+				s3Error = ErrNoSuchKey
+			}
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
 		// Versioning enabled quite possibly object is deleted might be delete-marker
 		// if present set the headers, no idea why AWS S3 sets these headers.
 		if objInfo.VersionID != "" && objInfo.DeleteMarker {
@@ -208,10 +227,14 @@ func (api objectAPIHandlers) SelectObjectContentHandler(w http.ResponseWriter, r
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
 	}
+	if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, objInfo.UserTags); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
 
 	// filter object lock metadata if permission does not permit
-	getRetPerms := checkRequestAuthType(ctx, r, policy.GetObjectRetentionAction, bucket, object)
-	legalHoldPerms := checkRequestAuthType(ctx, r, policy.GetObjectLegalHoldAction, bucket, object)
+	getRetPerms := authorizeRequest(ctx, r, policy.GetObjectRetentionAction)
+	legalHoldPerms := authorizeRequest(ctx, r, policy.GetObjectLegalHoldAction)
 
 	// filter object lock metadata if permission does not permit
 	objInfo.UserDefined = objectlock.FilterObjectLockMetadata(objInfo.UserDefined, getRetPerms != ErrNone, legalHoldPerms != ErrNone)
@@ -326,6 +349,8 @@ func (api objectAPIHandlers) getObjectHandler(ctx context.Context, objectAPI Obj
 
 	// Check for auth type to return S3 compatible error.
 	// type to return the correct error (NoSuchKey vs AccessDenied)
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
 	if s3Error := authenticateRequest(ctx, r, policy.GetObjectAction); s3Error != ErrNone {
 		if getRequestAuthType(r) == authTypeAnonymous {
 			// As per "Permission" section in
@@ -395,14 +420,16 @@ func (api objectAPIHandlers) getObjectHandler(ctx context.Context, objectAPI Obj
 	}
 
 	// Validate pre-conditions if any.
+	var storedTags *string // set once the object has been read far enough
 	opts.CheckPrecondFn = func(oi ObjectInfo) bool {
-		if _, err := DecryptObjectInfo(&oi, r); err != nil {
-			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		storedTags = &oi.UserTags
+		if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, oi.UserTags); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 			return true
 		}
 
-		if s3Error := authorizeRequestWithExistingTags(ctx, r, policy.GetObjectAction, oi.UserTags); s3Error != ErrNone {
-			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		if _, err := DecryptObjectInfo(&oi, r); err != nil {
+			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 			return true
 		}
 
@@ -421,7 +448,7 @@ func (api objectAPIHandlers) getObjectHandler(ctx context.Context, objectAPI Obj
 
 		if (isErrObjectNotFound(err) || isErrVersionNotFound(err) || isErrReadQuorum(err)) && (gr == nil || !gr.ObjInfo.DeleteMarker) {
 			proxytgts := getProxyTargets(ctx, bucket, object, opts)
-			if !proxytgts.Empty() {
+			if !proxytgts.Empty() && authorizeVersionedRequestWithPotentialTags(ctx, r, policy.GetObjectAction, opts.VersionID) == ErrNone {
 				globalReplicationStats.Load().incProxy(bucket, getObjectAPI, false)
 				// proxy to replication target if active-active replication is in place.
 				reader, proxy, perr = proxyGetToReplicationTarget(ctx, bucket, object, rs, r.Header, opts, proxytgts)
@@ -439,14 +466,29 @@ func (api objectAPIHandlers) getObjectHandler(ctx context.Context, objectAPI Obj
 			}
 		}
 		if reader == nil || !proxy.Proxy {
-			// The conditional callback has already written 304/412. Do not
+			// The conditional callback has already written 304/412 (or 403). Do not
 			// authorize again without the stored tags or write a second response.
-			if isErrPreconditionFailed(err) {
+			if isErrPreconditionFailed(err) || isErrPreconditionFailed(perr) {
 				return
 			}
 			// validate if the request indeed was authorized, if it wasn't we need to return "ErrAccessDenied"
-			// instead of any namespace related error.
-			if s3Error := authorizeRequest(ctx, r, policy.GetObjectAction); s3Error != ErrNone {
+			// instead of any namespace related error. Use the stored tags if the callback read them.
+			var s3Error APIErrorCode
+			if storedTags != nil {
+				s3Error = authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, *storedTags)
+			} else {
+				readErr := err
+				if proxy.Err != nil {
+					readErr = proxy.Err
+				}
+				if getRequestAuthType(r) == authTypeAnonymous && toAPIError(ctx, readErr).Code == "NoSuchKey" &&
+					authorizeBucketRequest(ctx, r, policy.ListBucketAction) == ErrNone {
+					s3Error = ErrNone
+				} else {
+					s3Error = authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, opts.VersionID, readErr)
+				}
+			}
+			if s3Error != ErrNone {
 				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 				return
 			}
@@ -478,6 +520,12 @@ func (api objectAPIHandlers) getObjectHandler(ctx context.Context, objectAPI Obj
 	defer gr.Close()
 
 	objInfo := gr.ObjInfo
+	if storedTags == nil {
+		if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, objInfo.UserTags); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
+	}
 
 	if !proxy.Proxy { // apply lifecycle rules only for local requests
 		// Automatically remove the object/version if an expiry lifecycle rule can be applied
@@ -539,6 +587,8 @@ func (api objectAPIHandlers) getObjectHandler(ctx context.Context, objectAPI Obj
 		hash.AddChecksumHeader(w, cs)
 	}
 
+	opts.TaggingCount = len(objInfo.UserTags) > 0 && canReturnObjectTagsHeader(ctx, r, opts.VersionID, objInfo.UserTags)
+
 	if err = setObjectHeaders(ctx, w, objInfo, rs, opts); err != nil {
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
@@ -597,20 +647,14 @@ func (api objectAPIHandlers) getObjectAttributesHandler(ctx context.Context, obj
 		return
 	}
 
-	var s3Error APIErrorCode
+	actions := [2]policy.Action{policy.GetObjectAttributesAction, policy.GetObjectAction}
 	if opts.VersionID != "" {
-		s3Error = checkRequestAuthType(ctx, r, policy.GetObjectVersionAttributesAction, bucket, object)
-		if s3Error == ErrNone {
-			s3Error = checkRequestAuthType(ctx, r, policy.GetObjectVersionAction, bucket, object)
-		}
-	} else {
-		s3Error = checkRequestAuthType(ctx, r, policy.GetObjectAttributesAction, bucket, object)
-		if s3Error == ErrNone {
-			s3Error = checkRequestAuthType(ctx, r, policy.GetObjectAction, bucket, object)
-		}
+		actions = [2]policy.Action{policy.GetObjectVersionAttributesAction, policy.GetObjectVersionAction}
 	}
-
-	if s3Error != ErrNone {
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
+	logger.GetReqInfo(ctx).VersionID = opts.VersionID
+	if s3Error := authenticateRequest(ctx, r, actions[0]); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
 	}
@@ -622,13 +666,30 @@ func (api objectAPIHandlers) getObjectAttributesHandler(ctx context.Context, obj
 	}
 
 	objInfo, err := objectAPI.GetObjectInfo(ctx, bucket, object, opts)
-	if err != nil {
-		s3Error = authorizeRequest(ctx, r, policy.ListBucketAction)
-		if s3Error == ErrNone {
-			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+	// Both actions must be authorized with the stored tags. Authorizing first
+	// with empty tags would reject conditional Allows and miss conditional Denies.
+	for _, action := range actions {
+		var s3Error APIErrorCode
+		if err != nil {
+			s3Error = authorizeRequestWithUnreadTags(ctx, r, action, err)
+		} else {
+			s3Error = authorizeRequestWithExistingTags(ctx, r, action, objInfo.UserTags)
+		}
+		if s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 			return
 		}
-		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+	}
+	if err != nil {
+		// As with S3, a caller without s3:ListBucket on the bucket gets
+		// AccessDenied in place of NoSuchKey. A server error, such as lost
+		// read quorum, tells nothing about the object and reaches the caller,
+		// who may read the object, as it is.
+		apiErr := toAPIError(ctx, err)
+		if apiErr.HTTPStatusCode < http.StatusInternalServerError && authorizeBucketRequest(ctx, r, policy.ListBucketAction) != ErrNone {
+			apiErr = errorCodes.ToAPIErr(ErrAccessDenied)
+		}
+		writeErrorResponse(ctx, w, apiErr, r.URL)
 		return
 	}
 
@@ -833,6 +894,8 @@ func (api objectAPIHandlers) headObjectHandler(ctx context.Context, objectAPI Ob
 
 	// Check for auth type to return S3 compatible error.
 	// type to return the correct error (NoSuchKey vs AccessDenied)
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
 	if s3Error := authenticateRequest(ctx, r, policy.GetObjectAction); s3Error != ErrNone {
 		if getRequestAuthType(r) == authTypeAnonymous {
 			// As per "Permission" section in
@@ -910,25 +973,43 @@ func (api objectAPIHandlers) headObjectHandler(ctx context.Context, objectAPI Ob
 	if err != nil && !objInfo.DeleteMarker && (isErrObjectNotFound(err) || isErrVersionNotFound(err) || isErrReadQuorum(err)) {
 		// proxy HEAD to replication target if active-active replication configured on bucket
 		proxytgts := getProxyTargets(ctx, bucket, object, opts)
-		if !proxytgts.Empty() {
+		if !proxytgts.Empty() && authorizeVersionedRequestWithPotentialTags(ctx, r, policy.GetObjectAction, opts.VersionID) == ErrNone {
 			globalReplicationStats.Load().incProxy(bucket, headObjectAPI, false)
 			var oi ObjectInfo
 			oi, proxy = proxyHeadToReplicationTarget(ctx, bucket, object, rs, opts, proxytgts)
-			if proxy.Proxy {
+			if proxy.Proxy && proxy.Err == nil {
 				objInfo = oi
 			}
 			if proxy.Err != nil {
 				globalReplicationStats.Load().incProxy(bucket, headObjectAPI, true)
-				writeErrorResponseHeadersOnly(w, toAPIError(ctx, proxy.Err))
-				return
 			}
 		}
 	}
 
-	if s3Error := authorizeRequestWithExistingTags(ctx, r, policy.GetObjectAction, objInfo.UserTags); s3Error != ErrNone {
+	// objInfo carries the stored tags unless reading the object failed.
+	var s3Error APIErrorCode
+	if (err != nil && !proxy.Proxy) || proxy.Err != nil {
+		readErr := err
+		if proxy.Err != nil {
+			readErr = proxy.Err
+		}
+		if getRequestAuthType(r) == authTypeAnonymous && toAPIError(ctx, readErr).Code == "NoSuchKey" &&
+			authorizeBucketRequest(ctx, r, policy.ListBucketAction) == ErrNone {
+			s3Error = ErrNone
+		} else {
+			s3Error = authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, opts.VersionID, readErr)
+		}
+	} else {
+		s3Error = authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, objInfo.UserTags)
+	}
+	if s3Error != ErrNone {
 		writeErrorResponseHeadersOnly(w, errorCodes.ToAPIErr(s3Error))
 		return
 	}
+	if proxy.Err != nil {
+		writeErrorResponseHeadersOnly(w, toAPIError(ctx, proxy.Err))
+		return
+	}
 
 	if err != nil && !proxy.Proxy {
 		switch {
@@ -1033,6 +1114,8 @@ func (api objectAPIHandlers) headObjectHandler(ctx context.Context, objectAPI Ob
 		hash.AddChecksumHeader(w, cs)
 	}
 
+	opts.TaggingCount = len(objInfo.UserTags) > 0 && canReturnObjectTagsHeader(ctx, r, opts.VersionID, objInfo.UserTags)
+
 	// Set standard object headers.
 	if err = setObjectHeaders(ctx, w, objInfo, rs, opts); err != nil {
 		writeErrorResponseHeadersOnly(w, toAPIError(ctx, err))
@@ -1292,13 +1375,11 @@ func isRemoteCallRequired(ctx context.Context, bucket string, objAPI ObjectLayer
 
 // copyRewritesObjectData reports whether the object layer stores new object data
 // for this copy instead of updating metadata in place or adding a
-// self-referential version. It mirrors the metadata-only decision taken by
-// erasureServerPools.CopyObject and erasureSets.CopyObject. CopyObjectHandler
-// has to predict that decision because the compression metadata it records must
-// describe whichever bytes are finally stored. metadataOnly already excludes
-// legacy sources, which the object layer always rewrites.
+// self-referential version. The selected pool must contain the source data to
+// add a reference. metadataOnly already excludes legacy sources, which the
+// object layer always rewrites.
 func copyRewritesObjectData(metadataOnly bool, srcOpts, dstOpts ObjectOptions) bool {
-	if !metadataOnly {
+	if !metadataOnly || dstOpts.copyPlan != nil && dstOpts.copyPlan.rewrite {
 		return true
 	}
 	switch {
@@ -1343,9 +1424,23 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 		return
 	}
 
-	if s3Error := checkRequestAuthType(ctx, r, policy.PutObjectAction, dstBucket, dstObject); s3Error != ErrNone {
-		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
-		return
+	if isDirectiveReplace(r.Header.Get(xhttp.AmzTagDirective)) {
+		if s3Error := checkRequestAuthType(ctx, r, policy.PutObjectAction, dstBucket, dstObject); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
+	} else {
+		logger.GetReqInfo(ctx).BucketName = dstBucket
+		logger.GetReqInfo(ctx).ObjectName = dstObject
+		logger.GetReqInfo(ctx).VersionID = ""
+		if s3Error := authenticateRequest(ctx, r, policy.PutObjectAction); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
+		if !canPotentiallyAllowAction(ctx, r, policy.PutObjectAction, dstBucket, dstObject) {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+			return
+		}
 	}
 
 	// Read escaped copy source path to check for parameters.
@@ -1379,7 +1474,9 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 		}
 	}
 
-	if s3Error := checkRequestAuthType(ctx, r, policy.GetObjectAction, srcBucket, srcObject); s3Error != ErrNone {
+	if s3Error := withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+		return authorizeVersionedRequestWithPotentialTags(ctx, r, policy.GetObjectAction, vid)
+	}); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
 	}
@@ -1463,7 +1560,15 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 
 	getObjectNInfo := objectAPI.GetObjectNInfo
 
+	var storedSrcTags *string
 	checkCopyPrecondFn := func(o ObjectInfo) bool {
+		storedSrcTags = &o.UserTags
+		if s3Error := withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+			return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, vid, o.UserTags)
+		}); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return true
+		}
 		if _, err := DecryptObjectInfo(&o, r); err != nil {
 			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 			return true
@@ -1515,6 +1620,20 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 		if isErrPreconditionFailed(err) {
 			return
 		}
+		var s3Error APIErrorCode
+		if storedSrcTags != nil {
+			s3Error = withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+				return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, vid, *storedSrcTags)
+			})
+		} else {
+			s3Error = withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+				return authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, vid, err)
+			})
+		}
+		if s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
 
 		// Versioning enabled quite possibly object is deleted might be delete-marker
 		// if present set the headers, no idea why AWS S3 sets these headers.
@@ -1532,6 +1651,23 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 	}
 	defer gr.Close()
 	srcInfo := gr.ObjInfo
+	if storedSrcTags == nil {
+		if s3Error := withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+			return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, vid, srcInfo.UserTags)
+		}); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
+	}
+	if !isDirectiveReplace(r.Header.Get(xhttp.AmzTagDirective)) {
+		copiedTags := srcInfo.UserTags
+		if s3Error := withScopedReqObject(ctx, dstBucket, dstObject, "", func() APIErrorCode {
+			return authorizeRequestWithTags(ctx, r, policy.PutObjectAction, "", &copiedTags)
+		}); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
+	}
 	// A trusted SSE-C replica reads raw ciphertext. Federation's ordinary PUT
 	// expects plaintext and does not forward the replica's sealed-key metadata.
 	if remoteCallRequired && replicaTrusted && crypto.SSEC.IsEncrypted(srcInfo.UserDefined) {
@@ -1673,16 +1809,23 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 	// Without a requested destination checksum algorithm, an in-place SSE-C
 	// rotation preserves the stored checksum state, including absence; it does
 	// not add the default CRC64NVME.
-	canRotateKeyInPlace := !srcInfo.Legacy &&
+	canRotateKeyInPlace := cpSrcDstSame && sseCopyC && sseC && !chStorageClass && !srcInfo.Legacy &&
 		!copyRewritesObjectData(srcInfo.metadataOnly, copySrcOpts, dstOpts) &&
 		(replicaTrusted || !hash.NewChecksumHeader(r.Header).IsSet())
 
-	// If src == dst and either
-	// - the object is encrypted using SSE-C and two different SSE-C keys are present
-	// - the object is encrypted using SSE-S3 and the SSE-S3 header is present
-	// - the object storage class is not changing
-	// then execute a key rotation.
-	if cpSrcDstSame && (sseCopyC && sseC) && !chStorageClass && canRotateKeyInPlace {
+	if canRotateKeyInPlace {
+		// A new version may need another pool. Resolve that before rewrapping
+		// the key, since a cross-pool copy must re-encrypt the source stream.
+		plan, err := objectAPI.prepareCopyObject(lockCtx, srcBucket, srcObject, dstBucket, dstObject, srcInfo, copySrcOpts, dstOpts)
+		if err != nil {
+			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+			return
+		}
+		dstOpts.copyPlan = &plan
+		canRotateKeyInPlace = !plan.rewrite
+	}
+
+	if canRotateKeyInPlace {
 		oldKey, err = ParseSSECopyCustomerRequest(r.Header, srcInfo.UserDefined)
 		if err != nil {
 			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
@@ -1773,6 +1916,20 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 			}
 		}
 
+		if !remoteCallRequired && dstOpts.copyPlan == nil {
+			// Encryption and checksum recomputation require new data. Plan
+			// with that final decision before starting either transform, but
+			// retain metadataOnly for the invalid self-copy check below.
+			planInfo := srcInfo
+			planInfo.metadataOnly = srcInfo.metadataOnly && !dstOpts.WantServerSideChecksumType.IsSet()
+			plan, err := objectAPI.prepareCopyObject(lockCtx, srcBucket, srcObject, dstBucket, dstObject, planInfo, copySrcOpts, dstOpts)
+			if err != nil {
+				writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+				return
+			}
+			dstOpts.copyPlan = &plan
+		}
+
 		if isDstCompressed {
 			checksumReader := srcInfo.Reader
 			wantEncryption := crypto.Requested(r.Header)
@@ -1829,12 +1986,27 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 
 	srcInfo.PutObjReader = pReader
 
-	// Object Lock state as stored on disk, captured before the metadata
-	// directive rebuilds the map. A replica update is applied only when its
-	// source timestamp is newer than the stored one, and a stale update must
-	// leave the stored state in place instead of erasing it.
-	storedLock := storedObjectLockState(srcInfo.UserDefined)
-	storedTagTimestamp := srcInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp]
+	// Reconcile against the addressed destination version under its write
+	// lock. The source can be a different object or version, including when
+	// the destination version has never been written.
+	getObjectInfo := func(_ context.Context, bucket, object string, opts ObjectOptions) (ObjectInfo, error) {
+		opts.NoLock = true
+		return objectAPI.GetObjectInfo(lockCtx, bucket, object, opts)
+	}
+	var storedInfo ObjectInfo
+	if replicaTrusted && !remoteCallRequired {
+		storedInfo, err = replicaStoredObjectInfo(lockCtx, getObjectInfo, dstBucket, dstObject, dstOpts.VersionID)
+		if err != nil {
+			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+			return
+		}
+	}
+	storedLock := storedObjectLockState(storedInfo.UserDefined)
+	storedTagTimestamp := storedInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp]
+	localTagTimestamp := ""
+	if cpSrcDstSame {
+		localTagTimestamp = srcInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp]
+	}
 
 	srcInfo.UserDefined, err = getCpObjMetadataFromHeader(ctx, r, srcInfo.UserDefined, allowReplicationMetadata)
 	if err != nil {
@@ -1859,9 +2031,9 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 			// the captured state even if metadata REPLACE rebuilt the map.
 			srcInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp] = srcTimestamp.UTC().Format(time.RFC3339Nano)
 			srcInfo.UserDefined[xhttp.AmzObjectTagging] = objTags
-			reconcileStoredObjectTags(srcInfo.UserDefined, srcInfo.UserTags, storedTagTimestamp)
+			reconcileStoredObjectTags(srcInfo.UserDefined, storedInfo.UserTags, storedTagTimestamp)
 		} else {
-			srcInfo.UserDefined[xhttp.AmzObjectTagging] = srcInfo.UserTags
+			srcInfo.UserDefined[xhttp.AmzObjectTagging] = storedInfo.UserTags
 			if storedTagTimestamp != "" {
 				srcInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp] = storedTagTimestamp
 			} else {
@@ -1870,7 +2042,18 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 		}
 	} else {
 		srcInfo.UserDefined[xhttp.AmzObjectTagging] = objTags
-		srcInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp] = UTCNow().Format(time.RFC3339Nano)
+		srcInfo.UserDefined[ReservedMetadataPrefixLower+TaggingTimestamp] = monotonicMetadataTimestamp(UTCNow().Format(time.RFC3339Nano), localTagTimestamp)
+	}
+	if !isDirectiveReplace(r.Header.Get(xhttp.AmzTagDirective)) {
+		finalDstTags := srcInfo.UserDefined[xhttp.AmzObjectTagging]
+		if finalDstTags != srcInfo.UserTags {
+			if s3Error := withScopedReqObject(ctx, dstBucket, dstObject, "", func() APIErrorCode {
+				return authorizeRequestWithTags(ctx, r, policy.PutObjectAction, "", &finalDstTags)
+			}); s3Error != ErrNone {
+				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+				return
+			}
+		}
 	}
 	// SSE-C rotation snapshots reserved metadata before the tag decision. Its
 	// later merge must not put the old timestamp back over the accepted state.
@@ -1878,14 +2061,12 @@ func (api objectAPIHandlers) CopyObjectHandler(w http.ResponseWriter, r *http.Re
 
 	srcInfo.UserDefined = filterReplicationStatusMetadata(srcInfo.UserDefined)
 	srcInfo.UserDefined = objectlock.FilterObjectLockMetadata(srcInfo.UserDefined, true, true)
+	// COPY may have preserved the source's reserved timestamps. Only the
+	// addressed destination and the incoming update may order a replica.
+	delete(srcInfo.UserDefined, ReservedMetadataPrefixLower+ObjectLockRetentionTimestamp)
+	delete(srcInfo.UserDefined, ReservedMetadataPrefixLower+ObjectLockLegalHoldTimestamp)
 	retPerms := isPutActionAllowed(ctx, getRequestAuthType(r), dstBucket, dstObject, r, policy.PutObjectRetentionAction)
 	holdPerms := isPutActionAllowed(ctx, getRequestAuthType(r), dstBucket, dstObject, r, policy.PutObjectLegalHoldAction)
-	// The destination is locked above: look it up without its lock, in the
-	// locks' context.
-	getObjectInfo := func(_ context.Context, bucket, object string, opts ObjectOptions) (ObjectInfo, error) {
-		opts.NoLock = true
-		return objectAPI.GetObjectInfo(lockCtx, bucket, object, opts)
-	}
 
 	// apply default bucket configuration/governance headers for dest side.
 	retentionMode, retentionDate, legalHold, s3Err := checkPutObjectLockAllowed(ctx, r, dstBucket, dstObject, getObjectInfo, retPerms, holdPerms, replicaTrusted)
@@ -2236,9 +2417,13 @@ func (api objectAPIHandlers) PutObjectHandler(w http.ResponseWriter, r *http.Req
 				writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 				return
 			}
+			if size < 0 {
+				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrInvalidArgument), r.URL)
+				return
+			}
 		}
 	}
-	if size == -1 {
+	if size < 0 {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrMissingContentLength), r.URL)
 		return
 	}
@@ -2701,10 +2886,14 @@ func (api objectAPIHandlers) PutObjectExtractHandler(w http.ResponseWriter, r *h
 				writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 				return
 			}
+			if size < 0 {
+				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrInvalidArgument), r.URL)
+				return
+			}
 		}
 	}
 
-	if size == -1 {
+	if size < 0 {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrMissingContentLength), r.URL)
 		return
 	}
@@ -3140,6 +3329,22 @@ func (api objectAPIHandlers) DeleteObjectHandler(w http.ResponseWriter, r *http.
 		}
 	}
 
+	// Check before delOpts reads bucket versioning: unavailable bucket metadata
+	// must fail the request before a force-delete can reach the object layer.
+	if forceDelete, _ := strconv.ParseBool(r.Header.Get(xhttp.MinIOForceDelete)); forceDelete {
+		rcfg, err := globalBucketObjectLockSys.Get(bucket)
+		if err != nil {
+			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+			return
+		}
+		if rcfg.LockEnabled {
+			apiErr := toAPIError(ctx, errInvalidArgument)
+			apiErr.Description = "force-delete is forbidden on Object Locking enabled buckets"
+			writeErrorResponse(ctx, w, apiErr, r.URL)
+			return
+		}
+	}
+
 	opts, err := delOpts(ctx, r, bucket, object)
 	if err != nil {
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
@@ -3160,14 +3365,6 @@ func (api objectAPIHandlers) DeleteObjectHandler(w http.ResponseWriter, r *http.
 		}
 	}
 
-	rcfg, _ := globalBucketObjectLockSys.Get(bucket)
-	if rcfg.LockEnabled && opts.DeletePrefix {
-		apiErr := toAPIError(ctx, errInvalidArgument)
-		apiErr.Description = "force-delete is forbidden on Object Locking enabled buckets"
-		writeErrorResponse(ctx, w, apiErr, r.URL)
-		return
-	}
-
 	os := newObjSweeper(bucket, object).WithVersion(opts.VersionID).WithVersioning(opts.Versioned, opts.VersionSuspended)
 
 	opts.SetEvalMetadataFn(func(oi *ObjectInfo, gerr error) (dsc ReplicateDecision, err error) {
@@ -3190,6 +3387,12 @@ func (api objectAPIHandlers) DeleteObjectHandler(w http.ResponseWriter, r *http.
 		return dsc, nil
 	})
 
+	_, rcfg, err := checkBucketDeleteMetadata(bucket)
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
 	vID := opts.VersionID
 	if replica {
 		opts.SetReplicaStatus(replication.Replica)
@@ -3201,20 +3404,27 @@ func (api objectAPIHandlers) DeleteObjectHandler(w http.ResponseWriter, r *http.
 			opts.RefuseLockedOverwrite = true
 		}
 	}
+	checkUnaddressedLock := vID == "" && !opts.Versioned && !opts.DeleteMarker && rcfg.LockEnabled
+	if checkUnaddressedLock {
+		opts.RefuseLockedOverwrite = true
+	}
 	opts.SetEvalRetentionBypassFn(func(goi ObjectInfo, gerr error) (err error) {
-		err = nil
-		if vID != "" {
+		if vID != "" || checkUnaddressedLock || (vID == "" && !opts.Versioned && !opts.DeleteMarker && gerr == nil) {
+			checkVID := vID
+			if checkVID == "" {
+				checkVID = nullVersionID
+			}
 			err := enforceRetentionBypassForDelete(ctx, r, bucket, ObjectToDelete{
 				ObjectV: ObjectV{
 					ObjectName: object,
-					VersionID:  vID,
+					VersionID:  checkVID,
 				},
 			}, goi, gerr)
 			if err != nil && !isErrObjectNotFound(err) {
 				return err
 			}
 		}
-		return err
+		return nil
 	})
 
 	deleteObject := objectAPI.DeleteObject
@@ -3366,7 +3576,7 @@ func (api objectAPIHandlers) PutObjectLegalHoldHandler(w http.ResponseWriter, r
 		VersionID: opts.VersionID,
 		EvalMetadataFn: func(oi *ObjectInfo, gerr error) (ReplicateDecision, error) {
 			oi.UserDefined[strings.ToLower(xhttp.AmzObjectLockLegalHold)] = strings.ToUpper(string(legalHold.Status))
-			oi.UserDefined[ReservedMetadataPrefixLower+ObjectLockLegalHoldTimestamp] = UTCNow().Format(time.RFC3339Nano)
+			oi.UserDefined[ReservedMetadataPrefixLower+ObjectLockLegalHoldTimestamp] = monotonicMetadataTimestamp(UTCNow().Format(time.RFC3339Nano), oi.UserDefined[ReservedMetadataPrefixLower+ObjectLockLegalHoldTimestamp])
 
 			dsc := mustReplicate(ctx, bucket, object, oi.getMustReplicateOptions(replication.MetadataReplicationType, opts))
 			if dsc.ReplicateAny() {
@@ -3543,7 +3753,7 @@ func (api objectAPIHandlers) PutObjectRetentionHandler(w http.ResponseWriter, r
 				oi.UserDefined[strings.ToLower(xhttp.AmzObjectLockMode)] = ""
 				oi.UserDefined[strings.ToLower(xhttp.AmzObjectLockRetainUntilDate)] = ""
 			}
-			oi.UserDefined[ReservedMetadataPrefixLower+ObjectLockRetentionTimestamp] = UTCNow().Format(time.RFC3339Nano)
+			oi.UserDefined[ReservedMetadataPrefixLower+ObjectLockRetentionTimestamp] = monotonicMetadataTimestamp(UTCNow().Format(time.RFC3339Nano), oi.UserDefined[ReservedMetadataPrefixLower+ObjectLockRetentionTimestamp])
 			dsc = mustReplicate(ctx, bucket, object, oi.getMustReplicateOptions(replication.MetadataReplicationType, opts))
 			if dsc.ReplicateAny() {
 				oi.UserDefined[ReservedMetadataPrefixLower+ReplicationTimestamp] = UTCNow().Format(time.RFC3339Nano)
@@ -3668,6 +3878,8 @@ func (api objectAPIHandlers) GetObjectTaggingHandler(w http.ResponseWriter, r *h
 		return
 	}
 
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
 	if s3Error := authenticateRequest(ctx, r, policy.GetObjectTaggingAction); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
@@ -3687,9 +3899,22 @@ func (api objectAPIHandlers) GetObjectTaggingHandler(w http.ResponseWriter, r *h
 		if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
 			proxytgts := getProxyTargets(ctx, bucket, object, opts)
 			if !proxytgts.Empty() {
+				if s3Error := authorizeVersionedRequestWithPotentialTags(ctx, r, policy.GetObjectTaggingAction, opts.VersionID); s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
 				globalReplicationStats.Load().incProxy(bucket, getObjectTaggingAPI, false)
 				// proxy to replication target if site replication is in place.
-				tags, gerr := proxyGetTaggingToRepTarget(ctx, bucket, object, opts, proxytgts)
+				tags, gerr, s3Error := proxyGetTaggingToRepTarget(ctx, bucket, object, opts, proxytgts, func(existingTags string, readErr error) APIErrorCode {
+					if readErr != nil && !isRemoteTaggingNotFound(readErr) {
+						return authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectTaggingAction, opts.VersionID, readErr)
+					}
+					return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectTaggingAction, opts.VersionID, existingTags)
+				})
+				if s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
 				if gerr.Err != nil || tags == nil {
 					globalReplicationStats.Load().incProxy(bucket, getObjectTaggingAPI, true)
 					writeErrorResponse(ctx, w, toAPIError(ctx, gerr.Err), r.URL)
@@ -3698,16 +3923,24 @@ func (api objectAPIHandlers) GetObjectTaggingHandler(w http.ResponseWriter, r *h
 				ot = tags
 				w.Header()[xhttp.MinIOTaggingProxied] = []string{"true"} // indicate that the request was proxied.
 			} else {
+				if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectTaggingAction, opts.VersionID, ""); s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
 				writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 				return
 			}
 		} else {
+			if s3Error := authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectTaggingAction, opts.VersionID, err); s3Error != ErrNone {
+				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+				return
+			}
 			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 			return
 		}
 	}
 
-	if s3Error := authorizeRequestWithExistingTags(ctx, r, policy.GetObjectTaggingAction, ot.String()); s3Error != ErrNone {
+	if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectTaggingAction, opts.VersionID, ot.String()); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
 	}
@@ -3736,6 +3969,18 @@ func (api objectAPIHandlers) GetObjectTaggingHandler(w http.ResponseWriter, r *h
 	writeSuccessResponseXML(w, encodeResponse(otags))
 }
 
+func isRemoteTaggingNotFound(err error) bool {
+	if err == nil {
+		return false
+	}
+	switch miniogo.ToErrorResponse(err).Code {
+	case "NoSuchKey", "NoSuchVersion":
+		return true
+	default:
+		return false
+	}
+}
+
 // PutObjectTaggingHandler - PUT object tagging
 func (api objectAPIHandlers) PutObjectTaggingHandler(w http.ResponseWriter, r *http.Request) {
 	ctx := newContext(r, w, "PutObjectTagging")
@@ -3755,6 +4000,13 @@ func (api objectAPIHandlers) PutObjectTaggingHandler(w http.ResponseWriter, r *h
 		return
 	}
 
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
+	if s3Error := authenticateRequest(ctx, r, policy.PutObjectTaggingAction); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
+
 	// Tags XML will not be bigger than 1MiB in size, fail if its bigger.
 	tags, err := tags.ParseObjectXML(io.LimitReader(r.Body, 1<<20))
 	if err != nil {
@@ -3763,13 +4015,6 @@ func (api objectAPIHandlers) PutObjectTaggingHandler(w http.ResponseWriter, r *h
 	}
 	tagsStr := tags.String()
 
-	logger.GetReqInfo(ctx).BucketName = bucket
-	logger.GetReqInfo(ctx).ObjectName = object
-	if s3Error := authenticateRequest(ctx, r, policy.PutObjectTaggingAction); s3Error != ErrNone {
-		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
-		return
-	}
-
 	// Set this such that authorization policies can be applied on the object
 	// tags. This is derived from the request body, so it must be injected only
 	// after signature verification: the SigV4 verifier now rejects unsigned
@@ -3783,14 +4028,6 @@ func (api objectAPIHandlers) PutObjectTaggingHandler(w http.ResponseWriter, r *h
 	}
 
 	objInfo, err := objAPI.GetObjectInfo(ctx, bucket, object, opts)
-	existingTags := ""
-	if err == nil {
-		existingTags = objInfo.UserTags
-	}
-	if s3Error := authorizeRequestWithExistingTags(ctx, r, policy.PutObjectTaggingAction, existingTags); s3Error != ErrNone {
-		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
-		return
-	}
 	if err != nil {
 		// if object is not found locally, but exists on peer site - proxy
 		// the tagging request to peer site. The response to client will
@@ -3798,9 +4035,21 @@ func (api objectAPIHandlers) PutObjectTaggingHandler(w http.ResponseWriter, r *h
 		if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
 			proxytgts := getProxyTargets(ctx, bucket, object, opts)
 			if !proxytgts.Empty() {
+				if s3Error := authorizeVersionedRequestWithPotentialTags(ctx, r, policy.PutObjectTaggingAction, opts.VersionID); s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
+				perr, s3Error := proxyTaggingToRepTarget(ctx, bucket, object, tags, opts, proxytgts, func(existingTags string, readErr error) APIErrorCode {
+					if readErr != nil && !isRemoteTaggingNotFound(readErr) {
+						return authorizeVersionedRequestWithUnreadTags(ctx, r, policy.PutObjectTaggingAction, opts.VersionID, readErr)
+					}
+					return authorizeVersionedRequestWithExistingTags(ctx, r, policy.PutObjectTaggingAction, opts.VersionID, existingTags)
+				})
+				if s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
 				globalReplicationStats.Load().incProxy(bucket, putObjectTaggingAPI, false)
-				// proxy to replication target if site replication is in place.
-				perr := proxyTaggingToRepTarget(ctx, bucket, object, tags, opts, proxytgts)
 				if perr.Err != nil {
 					globalReplicationStats.Load().incProxy(bucket, putObjectTaggingAPI, true)
 					writeErrorResponse(ctx, w, toAPIError(ctx, perr.Err), r.URL)
@@ -3821,9 +4070,26 @@ func (api objectAPIHandlers) PutObjectTaggingHandler(w http.ResponseWriter, r *h
 				return
 			}
 		}
+		// A local read failure must never be turned into a write grant. A
+		// server error may still be disclosed to an otherwise authorized
+		// caller for retry, while a missing object is evaluated as untagged.
+		var s3Error APIErrorCode
+		if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
+			s3Error = authorizeVersionedRequestWithExistingTags(ctx, r, policy.PutObjectTaggingAction, opts.VersionID, "")
+		} else {
+			s3Error = authorizeVersionedRequestWithUnreadTags(ctx, r, policy.PutObjectTaggingAction, opts.VersionID, err)
+		}
+		if s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
 	}
+	if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.PutObjectTaggingAction, opts.VersionID, objInfo.UserTags); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
 
 	dsc := mustReplicate(ctx, bucket, object, getMustReplicateOptions(objInfo.UserDefined, tagsStr, objInfo.ReplicationStatus, replication.MetadataReplicationType, opts))
 	stamp := UTCNow().Format(time.RFC3339Nano)
@@ -3880,6 +4146,13 @@ func (api objectAPIHandlers) DeleteObjectTaggingHandler(w http.ResponseWriter, r
 		return
 	}
 
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = object
+	if s3Error := authenticateRequest(ctx, r, policy.DeleteObjectTaggingAction); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
+
 	opts, err := getOpts(ctx, r, bucket, object)
 	if err != nil {
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
@@ -3894,9 +4167,21 @@ func (api objectAPIHandlers) DeleteObjectTaggingHandler(w http.ResponseWriter, r
 		if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
 			proxytgts := getProxyTargets(ctx, bucket, object, opts)
 			if !proxytgts.Empty() {
+				if s3Error := authorizeVersionedRequestWithPotentialTags(ctx, r, policy.DeleteObjectTaggingAction, opts.VersionID); s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
+				perr, s3Error := proxyTaggingToRepTarget(ctx, bucket, object, nil, opts, proxytgts, func(existingTags string, readErr error) APIErrorCode {
+					if readErr != nil && !isRemoteTaggingNotFound(readErr) {
+						return authorizeVersionedRequestWithUnreadTags(ctx, r, policy.DeleteObjectTaggingAction, opts.VersionID, readErr)
+					}
+					return authorizeVersionedRequestWithExistingTags(ctx, r, policy.DeleteObjectTaggingAction, opts.VersionID, existingTags)
+				})
+				if s3Error != ErrNone {
+					writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+					return
+				}
 				globalReplicationStats.Load().incProxy(bucket, removeObjectTaggingAPI, false)
-				// proxy to replication target if active-active replication is in place.
-				perr := proxyTaggingToRepTarget(ctx, bucket, object, nil, opts, proxytgts)
 				if perr.Err != nil {
 					globalReplicationStats.Load().incProxy(bucket, removeObjectTaggingAPI, true)
 					writeErrorResponse(ctx, w, toAPIError(ctx, perr.Err), r.URL)
@@ -3918,12 +4203,22 @@ func (api objectAPIHandlers) DeleteObjectTaggingHandler(w http.ResponseWriter, r
 				return
 			}
 		}
+		var s3Error APIErrorCode
+		if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
+			s3Error = authorizeVersionedRequestWithExistingTags(ctx, r, policy.DeleteObjectTaggingAction, opts.VersionID, "")
+		} else {
+			s3Error = authorizeVersionedRequestWithUnreadTags(ctx, r, policy.DeleteObjectTaggingAction, opts.VersionID, err)
+		}
+		if s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
 	}
 
 	// Allow deleteObjectTagging if policy action is set
-	if s3Error := checkRequestAuthTypeWithExistingTags(ctx, r, policy.DeleteObjectTaggingAction, bucket, object, oi.UserTags); s3Error != ErrNone {
+	if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.DeleteObjectTaggingAction, opts.VersionID, oi.UserTags); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
 	}

cmd/object-lock-reconciliation_test.go

@@ -0,0 +1,421 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"context"
+	"crypto/md5"
+	"encoding/base64"
+	"fmt"
+	"maps"
+	"net/http"
+	"net/url"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/auth"
+	xhttp "github.com/minio/minio/internal/http"
+)
+
+func TestPoolLockReductionOrderIndependent(t *testing.T) {
+	const old = objectLockTestStamp0900
+	const recent = objectLockTestStamp1000
+	const newest = objectLockTestStamp1100
+	compliance := objectLockState{mode: "COMPLIANCE", retainUntil: "2035-01-01T00:00:00Z", retentionTimestamp: old}
+	for _, tc := range []struct {
+		name   string
+		states [3]objectLockState
+		want   objectLockState
+	}{
+		{"compliance-before-newer-removal", [3]objectLockState{compliance, {retentionTimestamp: recent}, {mode: "GOVERNANCE", retainUntil: "2036-01-01T00:00:00Z", retentionTimestamp: newest}}, compliance},
+		{"longer-compliance-before-newer-shortening", [3]objectLockState{compliance, {mode: "COMPLIANCE", retainUntil: "2034-01-01T00:00:00Z", retentionTimestamp: newest}, {retentionTimestamp: recent}}, compliance},
+		{"unordered-compliance", [3]objectLockState{{mode: "COMPLIANCE", retainUntil: compliance.retainUntil, retentionTimestamp: "invalid"}, {retentionTimestamp: newest}, {}}, objectLockState{mode: "COMPLIANCE", retainUntil: compliance.retainUntil, retentionTimestamp: "invalid"}},
+		{"expired-compliance-can-release", [3]objectLockState{{mode: "COMPLIANCE", retainUntil: "2000-01-01T00:00:00Z", retentionTimestamp: old}, {retentionTimestamp: newest}, {retentionTimestamp: recent}}, objectLockState{retentionTimestamp: newest}},
+		{"governance-can-release", [3]objectLockState{{mode: "GOVERNANCE", retainUntil: compliance.retainUntil, retentionTimestamp: old}, {retentionTimestamp: newest}, {}}, objectLockState{retentionTimestamp: newest}},
+		{"unordered-hold-conflict", [3]objectLockState{{legalHold: "OFF"}, {legalHold: "ON"}, {}}, objectLockState{legalHold: "ON"}},
+		{"newer-hold-release", [3]objectLockState{{legalHold: "ON", legalHoldTimestamp: old}, {legalHold: "OFF", legalHoldTimestamp: newest}, {legalHold: "ON", legalHoldTimestamp: "invalid"}}, objectLockState{legalHold: "OFF", legalHoldTimestamp: newest}},
+		{"independent-fields", [3]objectLockState{compliance, {retentionTimestamp: newest, legalHold: "ON", legalHoldTimestamp: recent}, {legalHold: "OFF", legalHoldTimestamp: old}}, objectLockState{mode: compliance.mode, retainUntil: compliance.retainUntil, retentionTimestamp: old, legalHold: "ON", legalHoldTimestamp: recent}},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			for _, order := range [][3]int{{0, 1, 2}, {0, 2, 1}, {1, 0, 2}, {1, 2, 0}, {2, 0, 1}, {2, 1, 0}} {
+				var copies []PoolObjInfo
+				for _, i := range order {
+					meta := make(map[string]string)
+					tc.states[i].restoreRetention(meta)
+					tc.states[i].restoreLegalHold(meta)
+					copies = append(copies, PoolObjInfo{Index: i, ObjInfo: ObjectInfo{UserDefined: meta}})
+				}
+				for name, reduce := range map[string]func([]PoolObjInfo) objectLockState{"merge": mergePoolLockState, "lifecycle": newestLockState} {
+					if got := reduce(copies); got != tc.want {
+						t.Errorf("%s order=%v: got %+v want %+v", name, order, got, tc.want)
+					}
+				}
+			}
+		})
+	}
+}
+
+// All requests copy the same bytes. Revisions belong to the addressed
+// destination, even if the source is the latest version of the same key.
+func TestAPICopyReplicaDestinationState(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			for _, sameKey := range []bool{true, false} {
+				for _, missing := range []bool{false, true} {
+					for _, directive := range []string{copyDirective, replaceDirective} {
+						name := fmt.Sprintf("copy-destination/%t/%t/%s", sameKey, missing, directive)
+						source := name
+						if !sameKey {
+							source += "-source"
+						}
+						targetMeta := poolLockMetadata("GOVERNANCE", "ON", objectLockTestStamp1000, objectLockTestStamp1000)
+						targetMeta[xhttp.AmzObjectTagging] = "state=destination"
+						targetMeta[r5TagStamp] = objectLockTestStamp1000
+						targetID := mustGetUUID()
+						if !missing {
+							targetID = putObjectLockVersion(t, obj, bucket, name, targetMeta)
+						}
+						sourceMeta := poolLockMetadata("", "OFF", objectLockTestStamp1100, objectLockTestStamp1100)
+						sourceMeta[xhttp.AmzObjectTagging] = "state=source"
+						sourceMeta[r5TagStamp] = objectLockTestStamp1100
+						sourceID := putObjectLockVersion(t, obj, bucket, source, sourceMeta)
+						headers := map[string]string{
+							xhttp.AmzCopySource:        "/" + bucket + "/" + source + "?versionId=" + sourceID,
+							xhttp.AmzMetadataDirective: directive, xhttp.AmzTagDirective: replaceDirective,
+							xhttp.MinIOSourceReplicationRequest: "true", xhttp.AmzBucketReplicationStatus: "REPLICA",
+						}
+						// No source revision means no change, including no
+						// inheritance from a different source for a first write.
+						rec := r5Request(t, router, cred, http.MethodPut, "/"+bucket+"/"+name+"?versionId="+targetID, "", headers)
+						if rec.Code != http.StatusOK {
+							t.Fatalf("%s %s: %d %s", backend, name, rec.Code, rec.Body.String())
+						}
+						want := storedObjectLockState(targetMeta)
+						wantTags, wantStamp := "state=destination", objectLockTestStamp1000
+						if missing {
+							want = objectLockState{}
+							wantTags = ""
+							wantStamp = ""
+						}
+						got := r5Stored(t, obj, bucket, name, targetID, wantTags, wantStamp)
+						if state := storedObjectLockState(got.UserDefined); state != want {
+							t.Fatalf("%s absent revision: got %+v want %+v", name, state, want)
+						}
+						// The incoming update is older than the source but may
+						// still win at a new destination. A source lookup loses it.
+						headers[xhttp.MinIOSourceObjectRetentionTimestamp] = objectLockTestStamp0930
+						headers[xhttp.MinIOSourceObjectLegalHoldTimestamp] = objectLockTestStamp0930
+						headers[xhttp.AmzObjectLockMode] = "GOVERNANCE"
+						headers[xhttp.AmzObjectLockRetainUntilDate] = objectLockTestRetainUntil
+						headers[xhttp.AmzObjectLockLegalHold] = "ON"
+						headers[xhttp.MinIOSourceTaggingTimestamp] = objectLockTestStamp0930
+						headers[xhttp.AmzObjectTagging] = "state=incoming"
+						rec = r5Request(t, router, cred, http.MethodPut, "/"+bucket+"/"+name+"?versionId="+targetID, "", headers)
+						if rec.Code != http.StatusOK {
+							t.Fatalf("incoming %s: %d %s", name, rec.Code, rec.Body.String())
+						}
+						if missing {
+							want = objectLockState{mode: "GOVERNANCE", retainUntil: "2030-01-01T00:00:00.000Z", retentionTimestamp: objectLockTestStamp0930, legalHold: "ON", legalHoldTimestamp: objectLockTestStamp0930}
+							wantTags = "state=incoming"
+							wantStamp = objectLockTestStamp0930
+						}
+						got = r5Stored(t, obj, bucket, name, targetID, wantTags, wantStamp)
+						if state := storedObjectLockState(got.UserDefined); state != want {
+							t.Fatalf("%s stale revision: got %+v want %+v", name, state, want)
+						}
+						// Authorized same-content release needs no governance
+						// bypass header; it must not be rejected by the data guard.
+						delete(headers, xhttp.AmzObjectLockMode)
+						delete(headers, xhttp.AmzObjectLockRetainUntilDate)
+						headers[xhttp.MinIOSourceObjectRetentionTimestamp] = "2026-09-03T10:30:00Z"
+						headers[xhttp.MinIOSourceObjectLegalHoldTimestamp] = "2026-09-03T10:30:00Z"
+						headers[xhttp.AmzObjectLockLegalHold] = "OFF"
+						rec = r5Request(t, router, cred, http.MethodPut, "/"+bucket+"/"+name+"?versionId="+targetID, "", headers)
+						if rec.Code != http.StatusOK {
+							t.Fatalf("release %s: %d %s", name, rec.Code, rec.Body.String())
+						}
+						got = r5Stored(t, obj, bucket, name, targetID, wantTags, wantStamp)
+						want = objectLockState{retentionTimestamp: "2026-09-03T10:30:00Z", legalHold: "OFF", legalHoldTimestamp: "2026-09-03T10:30:00Z"}
+						if state := storedObjectLockState(got.UserDefined); state != want {
+							t.Fatalf("%s release: got %+v want %+v", name, state, want)
+						}
+					}
+				}
+			}
+		},
+	})
+}
+
+func TestReplicaReferenceCopyDestinationState(t *testing.T) {
+	z, bucket := consistencyPools(t)
+	for _, missing := range []bool{false, true} {
+		key := fmt.Sprintf("reference-copy-%t", missing)
+		id := mustGetUUID()
+		targetMeta := poolLockMetadata("GOVERNANCE", "ON", objectLockTestStamp1000, objectLockTestStamp1000)
+		targetMeta[xhttp.AmzObjectTagging] = "state=destination"
+		targetMeta[r5TagStamp] = objectLockTestStamp1000
+		if !missing {
+			putConsistencyObject(t, z, bucket, key, 0, "data", ObjectOptions{Versioned: true, VersionID: id, UserDefined: targetMeta})
+		}
+		sourceMeta := poolLockMetadata("", "OFF", objectLockTestStamp1100, objectLockTestStamp1100)
+		sourceMeta[xhttp.AmzObjectTagging] = "state=source"
+		sourceMeta[r5TagStamp] = objectLockTestStamp1100
+		src := putConsistencyObject(t, z, bucket, key, 0, "data", ObjectOptions{Versioned: true, UserDefined: sourceMeta})
+		src.metadataOnly = true
+		src.UserDefined = make(map[string]string)
+		_, err := z.CopyObject(t.Context(), bucket, key, bucket, key, src, ObjectOptions{VersionID: src.VersionID}, ObjectOptions{Versioned: true, VersionID: id, ReplicaLockReconcile: true, ReplicationRequest: true})
+		if err != nil {
+			t.Fatal(err)
+		}
+		want := storedObjectLockState(targetMeta)
+		wantTags, wantStamp := "state=destination", objectLockTestStamp1000
+		if missing {
+			want = objectLockState{}
+			wantTags = ""
+			wantStamp = ""
+		}
+		got := r5Stored(t, z, bucket, key, id, wantTags, wantStamp)
+		if state := storedObjectLockState(got.UserDefined); state != want {
+			t.Fatalf("missing=%t: got %+v want %+v", missing, state, want)
+		}
+	}
+}
+
+// The set must not undo the all-pools decision with a newer weak revision
+// from its own copy before the protected competing copy is retired.
+func TestPoolsReplicaComplianceMetadataCopyOrder(t *testing.T) {
+	z, bucket := consistencyPools(t)
+	for _, protectedPool := range []int{0, 1} {
+		key := fmt.Sprintf("compliance-copy-%d", protectedPool)
+		id := mustGetUUID()
+		stamp := UTCNow().Add(-time.Hour)
+		var source ObjectInfo
+		for pool := range 2 {
+			meta := poolLockMetadata("", "OFF", objectLockTestStamp1100, objectLockTestStamp1000)
+			if pool == protectedPool {
+				meta = poolLockMetadata("COMPLIANCE", "OFF", objectLockTestStamp0900, objectLockTestStamp1000)
+			}
+			oi := putConsistencyObject(t, z, bucket, key, pool, "data", ObjectOptions{Versioned: true, VersionID: id, MTime: stamp, UserDefined: meta})
+			if pool == 0 {
+				source = oi
+			}
+		}
+		source.metadataOnly = true
+		source.UserDefined = map[string]string{}
+		_, err := z.CopyObject(t.Context(), bucket, key, bucket, key, source, ObjectOptions{VersionID: id}, ObjectOptions{VersionID: id, Versioned: true, ReplicaLockReconcile: true, ReplicationRequest: true})
+		if err != nil {
+			t.Fatal(err)
+		}
+		got := readObjectLockFields(t, z, bucket, key, id)
+		if got.mode != "COMPLIANCE" || got.retainUntil != "2030-01-01T00:00:00Z" {
+			t.Fatalf("protected pool %d lost COMPLIANCE: %+v", protectedPool, got)
+		}
+	}
+}
+
+func TestAPIReplicaRetentionTimestampAuthorization(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, _ auth.Credentials, t *testing.T) {
+			basic := `"s3:GetObject","s3:PutObject","s3:ReplicateObject"`
+			noRetention := newObjectAttributesAuthzUser(t, backend, bucket, basic)
+			withRetention := newObjectAttributesAuthzUser(t, backend, bucket, basic+`,"s3:PutObjectRetention"`)
+			for _, operation := range []string{"put", "copy", "multipart"} {
+				for _, authorized := range []bool{false, true} {
+					for _, timestamp := range []bool{false, true} {
+						key := fmt.Sprintf("replica-permission/%s/%t/%t", operation, authorized, timestamp)
+						meta := poolLockMetadata("GOVERNANCE", "", objectLockTestStamp0900, "")
+						id := putObjectLockVersion(t, obj, bucket, key, meta)
+						headers := map[string]string{xhttp.MinIOSourceReplicationRequest: "true", xhttp.AmzBucketReplicationStatus: "REPLICA"}
+						if timestamp {
+							headers[xhttp.MinIOSourceObjectRetentionTimestamp] = objectLockTestStamp1000
+						}
+						method, path, body := http.MethodPut, "/"+bucket+"/"+key+"?versionId="+id, "data"
+						switch operation {
+						case "copy":
+							headers[xhttp.AmzCopySource] = "/" + bucket + "/" + key + "?versionId=" + id
+							headers[xhttp.AmzMetadataDirective] = replaceDirective
+							body = ""
+						case "multipart":
+							method = http.MethodPost
+							path += "&uploads"
+							body = ""
+						}
+						cred := noRetention
+						if authorized {
+							cred = withRetention
+						}
+						rec := r5Request(t, router, cred, method, path, body, headers)
+						want := http.StatusOK
+						if timestamp && !authorized {
+							want = http.StatusForbidden
+						}
+						if rec.Code != want {
+							t.Fatalf("%s: %d want %d: %s", key, rec.Code, want, rec.Body.String())
+						}
+						if want == http.StatusForbidden || !timestamp {
+							got := readObjectLockFields(t, obj, bucket, key, id)
+							if got.mode != "GOVERNANCE" || got.retentionStamp != objectLockTestStamp0900 {
+								t.Fatalf("unrequested/denied retention changed: %+v", got)
+							}
+						}
+					}
+				}
+			}
+		},
+	})
+}
+
+func TestAPILocalObjectLockTimestampsAdvance(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			future := UTCNow().Add(48 * time.Hour)
+			meta := poolLockMetadata("GOVERNANCE", "ON", future.Format(time.RFC3339Nano), future.Format(time.RFC3339Nano))
+			id := putObjectLockVersion(t, obj, bucket, "local-lock", meta)
+			for n := 1; n <= 2; n++ {
+				if status := putRetention(t, router, cred, bucket, "local-lock", id, "GOVERNANCE", time.Date(2035, 1, n, 0, 0, 0, 0, time.UTC), false); status != http.StatusOK {
+					t.Fatalf("%s retention: %d", backend, status)
+				}
+				body := []byte(`<LegalHold xmlns="http://s3.amazonaws.com/doc/2006-03-01/"><Status>OFF</Status></LegalHold>`)
+				sum := md5.Sum(body)
+				rec := retentionAuthzRequest(t, router, cred, http.MethodPut, makeTestTargetURL("", bucket, "local-lock", url.Values{"legal-hold": {""}, "versionId": {id}}), body, map[string]string{xhttp.ContentMD5: base64.StdEncoding.EncodeToString(sum[:])})
+				if rec.Code != http.StatusOK {
+					t.Fatalf("%s hold: %d %s", backend, rec.Code, rec.Body.String())
+				}
+				got := readObjectLockFields(t, obj, bucket, "local-lock", id)
+				want := future.Add(time.Duration(n) * time.Nanosecond).Format(time.RFC3339Nano)
+				if got.retentionStamp != want || got.legalHoldStamp != want {
+					t.Fatalf("local mutation %d regressed: %+v want %s", n, got, want)
+				}
+			}
+		},
+	})
+}
+
+type lockBoundaryReadFailure struct {
+	ObjectLayer
+	bucket, key, version string
+	metadataError        error
+	destinationError     error
+	deleteCalls          int
+}
+
+func (f *lockBoundaryReadFailure) GetObjectNInfo(ctx context.Context, bucket, key string, rs *HTTPRangeSpec, h http.Header, opts ObjectOptions) (*GetObjectReader, error) {
+	if f.metadataError != nil && bucket == minioMetaBucket && strings.HasPrefix(key, pathJoin(bucketMetaPrefix, f.bucket)+"/") {
+		return nil, f.metadataError
+	}
+	return f.ObjectLayer.GetObjectNInfo(ctx, bucket, key, rs, h, opts)
+}
+
+func (f *lockBoundaryReadFailure) GetObjectInfo(ctx context.Context, bucket, key string, opts ObjectOptions) (ObjectInfo, error) {
+	if f.destinationError != nil && bucket == f.bucket && key == f.key && opts.VersionID == f.version {
+		return ObjectInfo{}, f.destinationError
+	}
+	return f.ObjectLayer.GetObjectInfo(ctx, bucket, key, opts)
+}
+
+func (f *lockBoundaryReadFailure) DeleteObject(ctx context.Context, bucket, key string, opts ObjectOptions) (ObjectInfo, error) {
+	f.deleteCalls++
+	return f.ObjectLayer.DeleteObject(ctx, bucket, key, opts)
+}
+
+func TestAPICopyReplicaDestinationReadFailure(t *testing.T) {
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true}, objAPITest: func(obj ObjectLayer, backend, bucket string, _ http.Handler, cred auth.Credentials, t *testing.T) {
+		id := putObjectLockVersion(t, obj, bucket, "destination", poolLockMetadata("GOVERNANCE", "ON", objectLockTestStamp1000, objectLockTestStamp1000))
+		source := putObjectLockVersion(t, obj, bucket, "source", nil)
+		f := &lockBoundaryReadFailure{ObjectLayer: obj, bucket: bucket, key: "destination", version: id, destinationError: errErasureReadQuorum}
+		router := initTestAPIEndPoints(f, []string{"CopyObject"})
+		headers := map[string]string{xhttp.AmzCopySource: "/" + bucket + "/source?versionId=" + source, xhttp.MinIOSourceReplicationRequest: "true", xhttp.AmzBucketReplicationStatus: "REPLICA"}
+		rec := r5Request(t, router, cred, http.MethodPut, "/"+bucket+"/destination?versionId="+id, "", headers)
+		if rec.Code < 500 {
+			t.Fatalf("%s read failure allowed copy: %d %s", backend, rec.Code, rec.Body.String())
+		}
+		if got := readObjectLockFields(t, obj, bucket, "destination", id); got.legalHold != "ON" || got.mode != "GOVERNANCE" {
+			t.Fatalf("failed read changed state: %+v", got)
+		}
+	}})
+}
+
+func TestAPIForceDeleteLockConfigFailure(t *testing.T) {
+	for _, locked := range []bool{false, true} {
+		t.Run(fmt.Sprintf("locked=%t", locked), func(t *testing.T) {
+			ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: locked}, objAPITest: func(obj ObjectLayer, backend, bucket string, _ http.Handler, cred auth.Credentials, t *testing.T) {
+				saved, err := globalBucketMetadataSys.Get(bucket)
+				if err != nil {
+					t.Fatal(err)
+				}
+				restoreInit := markBucketMetadataInitialized(t)
+				defer restoreInit()
+				previous := newObjectLayerFn()
+				defer setObjectLayer(previous)
+				defer globalBucketMetadataSys.Set(bucket, saved)
+				for _, failure := range []string{"quorum", "unavailable", "cache-miss"} {
+					key := "force-" + failure + "/data"
+					putObjectLockVersion(t, obj, bucket, key, nil)
+					f := &lockBoundaryReadFailure{ObjectLayer: obj, bucket: bucket}
+					globalBucketMetadataSys.Remove(bucket)
+					switch failure {
+					case "quorum":
+						f.metadataError = errErasureReadQuorum
+					case "unavailable":
+						f.metadataError = errServerNotInitialized
+					}
+					router := initTestAPIEndPoints(f, []string{"DeleteObject"})
+					rec := r5Request(t, router, cred, http.MethodDelete, "/"+bucket+"/force-"+failure, "", map[string]string{xhttp.MinIOForceDelete: "true"})
+					setObjectLayer(previous)
+					globalBucketMetadataSys.Set(bucket, saved)
+					allowed := failure == "cache-miss" && !locked
+					if allowed {
+						if rec.Code != http.StatusNoContent || f.deleteCalls != 1 {
+							t.Fatalf("%s missing unlocked cache: %d calls=%d %s", backend, rec.Code, f.deleteCalls, rec.Body.String())
+						}
+					} else {
+						if rec.Code < 400 || f.deleteCalls != 0 {
+							t.Fatalf("%s %s: force-delete proceeded: %d calls=%d %s", backend, failure, rec.Code, f.deleteCalls, rec.Body.String())
+						}
+						if _, err := obj.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{}); err != nil {
+							t.Fatalf("rejected force-delete lost data: %v", err)
+						}
+					}
+				}
+			}})
+		})
+	}
+}
+
+func TestAPILocalCopyTagTimestampAdvances(t *testing.T) {
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{t: t, objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+		stamp := UTCNow().Add(48 * time.Hour)
+		meta := map[string]string{r5TagStamp: stamp.Format(time.RFC3339Nano), xhttp.AmzObjectTagging: "key=old"}
+		_, err := obj.PutObject(t.Context(), bucket, "local-copy", mustGetPutObjReader(t, strings.NewReader("data"), 4, "", ""), ObjectOptions{UserDefined: maps.Clone(meta)})
+		if err != nil {
+			t.Fatal(err)
+		}
+		rec := r5Request(t, router, cred, http.MethodPut, "/"+bucket+"/local-copy", "", map[string]string{xhttp.AmzCopySource: "/" + bucket + "/local-copy", xhttp.AmzMetadataDirective: replaceDirective, xhttp.AmzTagDirective: replaceDirective})
+		if rec.Code != http.StatusOK {
+			t.Fatalf("%s copy: %d %s", backend, rec.Code, rec.Body.String())
+		}
+		r5Stored(t, obj, bucket, "local-copy", "", "", stamp.Add(time.Nanosecond).Format(time.RFC3339Nano))
+	}})
+}

cmd/object-multipart-handlers.go

@@ -427,7 +427,9 @@ func (api objectAPIHandlers) CopyObjectPartHandler(w http.ResponseWriter, r *htt
 		}
 	}
 
-	if s3Error := checkRequestAuthType(ctx, r, policy.GetObjectAction, srcBucket, srcObject); s3Error != ErrNone {
+	if s3Error := withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+		return authorizeVersionedRequestWithPotentialTags(ctx, r, policy.GetObjectAction, vid)
+	}); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
 	}
@@ -491,7 +493,15 @@ func (api objectAPIHandlers) CopyObjectPartHandler(w http.ResponseWriter, r *htt
 		}
 	}
 
+	var storedSrcTags *string
 	checkCopyPartPrecondFn := func(o ObjectInfo) bool {
+		storedSrcTags = &o.UserTags
+		if s3Error := withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+			return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, vid, o.UserTags)
+		}); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return true
+		}
 		if _, err := DecryptObjectInfo(&o, r); err != nil {
 			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 			return true
@@ -513,6 +523,20 @@ func (api objectAPIHandlers) CopyObjectPartHandler(w http.ResponseWriter, r *htt
 		if isErrPreconditionFailed(err) {
 			return
 		}
+		var s3Error APIErrorCode
+		if storedSrcTags != nil {
+			s3Error = withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+				return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, vid, *storedSrcTags)
+			})
+		} else {
+			s3Error = withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+				return authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, vid, err)
+			})
+		}
+		if s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
 		if globalBucketVersioningSys.PrefixEnabled(srcBucket, srcObject) && gr != nil {
 			// Versioning enabled quite possibly object is deleted might be delete-marker
 			// if present set the headers, no idea why AWS S3 sets these headers.
@@ -521,11 +545,22 @@ func (api objectAPIHandlers) CopyObjectPartHandler(w http.ResponseWriter, r *htt
 				w.Header()[xhttp.AmzDeleteMarker] = []string{strconv.FormatBool(gr.ObjInfo.DeleteMarker)}
 			}
 		}
+		reqInfo := logger.GetReqInfo(ctx)
+		reqInfo.BucketName = srcBucket
+		reqInfo.ObjectName = srcObject
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
 	}
 	defer gr.Close()
 	srcInfo := gr.ObjInfo
+	if storedSrcTags == nil {
+		if s3Error := withScopedReqObject(ctx, srcBucket, srcObject, vid, func() APIErrorCode {
+			return authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, vid, srcInfo.UserTags)
+		}); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return
+		}
+	}
 
 	actualPartSize, err := srcInfo.GetActualSize()
 	if err != nil {
@@ -788,10 +823,14 @@ func (api objectAPIHandlers) PutObjectPartHandler(w http.ResponseWriter, r *http
 				writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 				return
 			}
+			if size < 0 {
+				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrInvalidArgument), r.URL)
+				return
+			}
 		}
 	}
 
-	if size == -1 {
+	if size < 0 {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrMissingContentLength), r.URL)
 		return
 	}

cmd/policy-import-validation_test.go

@@ -0,0 +1,47 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"bytes"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+)
+
+func TestIAMImportRejectsUnknownPolicyFields(t *testing.T) {
+	_, _ = iamAdminFixture(t)
+	for _, raw := range []string{
+		`{"Version":"2012-10-17","Statements":[]}`,
+		`{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::b/*"],"Conditions":{"StringEquals":{"s3:ExistingObjectTag/classification":"public"}}}]}`,
+	} {
+		data := iamImportArchive(t, map[string]any{allPoliciesFile: map[string]json.RawMessage{"import-policy": json.RawMessage(raw)}})
+		req, err := newTestSignedRequestV4(http.MethodPut, "http://localhost/minio/admin/v3/import-iam-v2", int64(len(data)), bytes.NewReader(data), globalActiveCred.AccessKey, globalActiveCred.SecretKey, nil)
+		mustIAM(t, err)
+		mustIAM(t, req.ParseForm())
+		rec := httptest.NewRecorder()
+		adminAPIHandlers{}.ImportIAMV2(rec, req.WithContext(newContext(req, rec, "ImportIAM")))
+		if rec.Code != http.StatusBadRequest {
+			t.Fatalf("import malformed policy: got %d %s, want 400", rec.Code, rec.Body.String())
+		}
+	}
+}
+
+func TestSessionPolicyWriteKeepsStrictSemanticValidation(t *testing.T) {
+	raw := []byte(`{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["admin:GetBucketQuota"],"Resource":["arn:aws:s3:::mybucket"],"NotResource":["arn:aws:s3:::otherbucket"]}]}`)
+	if _, err := parseSessionPolicyStrictBytes(raw); err == nil {
+		t.Fatal("new session policy accepted conflicting Resource and NotResource")
+	}
+	if _, err := parsePolicySnapshotBytes(raw); err != nil {
+		t.Fatalf("historical snapshot compatibility lost: %v", err)
+	}
+}
+
+func TestBucketPolicyRejectsUnsupportedNotPrincipal(t *testing.T) {
+	raw := []byte(`{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Principal":"*","NotPrincipal":{"AWS":"excluded-user"},"Action":"s3:GetObject","Resource":"arn:aws:s3:::b/*"}]}`)
+	if _, err := parseBucketPolicyStrictBytes(raw, "b"); err == nil {
+		t.Fatal("unsupported NotPrincipal was silently discarded")
+	}
+}

cmd/policy-strict.go

@@ -0,0 +1,159 @@
+// Copyright (c) 2026 PGSTY
+//
+// This file is part of MinIO Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+package cmd
+
+import (
+	"bytes"
+	"encoding/json"
+	"io"
+
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+type strictIAMStatementWire struct {
+	SID          policy.ID       `json:"Sid,omitempty"`
+	Effect       policy.Effect   `json:"Effect"`
+	Actions      json.RawMessage `json:"Action,omitempty"`
+	NotActions   json.RawMessage `json:"NotAction,omitempty"`
+	Resources    json.RawMessage `json:"Resource,omitempty"`
+	NotResources json.RawMessage `json:"NotResource,omitempty"`
+	Conditions   json.RawMessage `json:"Condition,omitempty"`
+}
+
+type strictIAMPolicyWire struct {
+	ID         policy.ID                `json:"ID,omitempty"`
+	Version    string                   `json:"Version"`
+	Statements []strictIAMStatementWire `json:"Statement"`
+}
+
+type strictPrincipalWire struct {
+	AWS json.RawMessage `json:"AWS"`
+}
+
+type strictBucketStatementWire struct {
+	SID          policy.ID       `json:"Sid,omitempty"`
+	Effect       policy.Effect   `json:"Effect"`
+	Principal    json.RawMessage `json:"Principal,omitempty"`
+	Actions      json.RawMessage `json:"Action,omitempty"`
+	NotActions   json.RawMessage `json:"NotAction,omitempty"`
+	Resources    json.RawMessage `json:"Resource,omitempty"`
+	NotResources json.RawMessage `json:"NotResource,omitempty"`
+	Conditions   json.RawMessage `json:"Condition,omitempty"`
+}
+
+type strictBucketPolicyWire struct {
+	ID         policy.ID                   `json:"ID,omitempty"`
+	Version    string                      `json:"Version"`
+	Statements []strictBucketStatementWire `json:"Statement"`
+}
+
+func validateStrictIAMPolicyWire(data []byte) ([]byte, error) {
+	trimmed := bytes.TrimSpace(data)
+	if len(trimmed) == 0 || trimmed[0] != '{' {
+		return nil, policy.Errorf("policy must be a JSON object")
+	}
+	var wire strictIAMPolicyWire
+	dec := json.NewDecoder(bytes.NewReader(trimmed))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&wire); err != nil {
+		return nil, policy.Errorf("%w", err)
+	}
+	var extra any
+	if err := dec.Decode(&extra); err != io.EOF {
+		if err == nil {
+			return nil, policy.Errorf("unexpected trailing JSON data in policy")
+		}
+		return nil, policy.Errorf("%w", err)
+	}
+	return trimmed, nil
+}
+
+func parsePolicyStrictBytes(data []byte) (*policy.Policy, error) {
+	trimmed, err := validateStrictIAMPolicyWire(data)
+	if err != nil {
+		return nil, err
+	}
+	p, err := policy.ParseConfigStrict(bytes.NewReader(trimmed))
+	if err != nil {
+		return nil, err
+	}
+	if p.IsEmpty() {
+		return nil, policy.Errorf("empty policies are not allowed")
+	}
+	return p, nil
+}
+
+func parseSessionPolicyStrictBytes(data []byte) (*policy.Policy, error) {
+	trimmed, err := validateStrictIAMPolicyWire(data)
+	if err != nil {
+		return nil, err
+	}
+	return policy.ParseConfigStrict(bytes.NewReader(trimmed))
+}
+
+// Snapshot imports retain supported historical policy semantics while rejecting
+// unknown JSON fields that could silently discard restrictions.
+func parsePolicySnapshotBytes(data []byte) (*policy.Policy, error) {
+	trimmed, err := validateStrictIAMPolicyWire(data)
+	if err != nil {
+		return nil, err
+	}
+	return policy.ParseConfig(bytes.NewReader(trimmed))
+}
+
+func validateStrictPrincipalWire(raw json.RawMessage) error {
+	trimmed := bytes.TrimSpace(raw)
+	if len(trimmed) == 0 || trimmed[0] != '{' {
+		return nil
+	}
+	var pw strictPrincipalWire
+	dec := json.NewDecoder(bytes.NewReader(trimmed))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&pw); err != nil {
+		return policy.Errorf("%w", err)
+	}
+	var extra any
+	if err := dec.Decode(&extra); err != io.EOF {
+		if err == nil {
+			return policy.Errorf("unexpected trailing JSON data in principal")
+		}
+		return policy.Errorf("%w", err)
+	}
+	if len(bytes.TrimSpace(pw.AWS)) == 0 {
+		return policy.Errorf("invalid principal '%s'", string(raw))
+	}
+	return nil
+}
+
+func parseBucketPolicyStrictBytes(data []byte, bucket string) (*policy.BucketPolicy, error) {
+	trimmed := bytes.TrimSpace(data)
+	if len(trimmed) == 0 || trimmed[0] != '{' {
+		return nil, policy.Errorf("bucket policy must be a JSON object")
+	}
+	var wire strictBucketPolicyWire
+	dec := json.NewDecoder(bytes.NewReader(trimmed))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&wire); err != nil {
+		return nil, policy.Errorf("%w", err)
+	}
+	var extra any
+	if err := dec.Decode(&extra); err != io.EOF {
+		if err == nil {
+			return nil, policy.Errorf("unexpected trailing JSON data in bucket policy")
+		}
+		return nil, policy.Errorf("%w", err)
+	}
+	for _, st := range wire.Statements {
+		if err := validateStrictPrincipalWire(st.Principal); err != nil {
+			return nil, err
+		}
+	}
+	return policy.ParseBucketPolicyConfig(bytes.NewReader(trimmed), bucket)
+}

cmd/release-review-boundaries_test.go

@@ -0,0 +1,162 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"bufio"
+	"encoding/base64"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/auth"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+type trailerFaultReader struct {
+	err   error
+	reads int
+}
+
+func (r *trailerFaultReader) Read([]byte) (int, error) {
+	r.reads++
+	if r.reads > 2 {
+		return 0, io.EOF // Bound a broken parser rather than exhausting test memory.
+	}
+	return 0, r.err
+}
+
+func TestTrailerReadPreservesConnectionErrors(t *testing.T) {
+	for _, signed := range []bool{false, true} {
+		for _, prefix := range []string{"", "checksum:value\r", "checksum:value\r\n", "checksum:value\r\nx-amz-trailer-signature:a\r"} {
+			if !signed && strings.Contains(prefix, "\r\n") {
+				continue
+			}
+			t.Run(fmt.Sprintf("signed=%t/prefix=%q", signed, prefix), func(t *testing.T) {
+				failure := errors.New("injected connection reset")
+				fault := &trailerFaultReader{err: failure}
+				reader := bufio.NewReader(io.MultiReader(strings.NewReader(prefix), fault))
+				var err error
+				if signed {
+					err = (&s3ChunkedReader{reader: reader}).readTrailers()
+				} else {
+					err = (&s3UnsignedChunkedReader{reader: reader}).readTrailers()
+				}
+				if !errors.Is(err, failure) || fault.reads != 1 {
+					t.Fatalf("got err=%v reads=%d, want original connection error after one read", err, fault.reads)
+				}
+			})
+		}
+	}
+}
+
+func TestLatestMetadataListingDoesNotRequireVersionGrants(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t,
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, _ auth.Credentials, t *testing.T) {
+			_, err := globalBucketMetadataSys.Update(t.Context(), bucket, bucketVersioningConfig, enabledBucketVersioningConfig)
+			mustIAM(t, err)
+			_, err = obj.PutObject(t.Context(), bucket, "latest", mustGetPutObjReader(t, strings.NewReader("data"), 4, "", ""), ObjectOptions{
+				Versioned: true, UserDefined: map[string]string{xhttp.AmzObjectTagging: "classification=public"},
+			})
+			mustIAM(t, err)
+			cred := createTestPolicyUser(t, fmt.Sprintf(`{"Version":"2012-10-17","Statement":[
+				{"Effect":"Allow","Action":["s3:ListBucket","s3:ListBucketVersions"],"Resource":["arn:aws:s3:::%s"]},
+				{"Effect":"Allow","Action":["s3:GetObject","s3:GetObjectTagging"],"Resource":["arn:aws:s3:::%s/*"]},
+				{"Effect":"Deny","Action":["s3:GetObjectVersion","s3:GetObjectVersionTagging"],"Resource":["arn:aws:s3:::%s/*"]}]}`, bucket, bucket, bucket))
+			for _, query := range []string{"list-type=2", "versions="} {
+				req, err := newTestSignedRequestV4(http.MethodGet, "/"+bucket+"?"+query+"&metadata=true&prefix=latest", 0, nil, cred.AccessKey, cred.SecretKey, nil)
+				mustIAM(t, err)
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				wantTags := query == "list-type=2"
+				if rec.Code != http.StatusOK || strings.Contains(rec.Body.String(), "classification=public") != wantTags {
+					t.Fatalf("%s %s: status=%d body=%s, want tags=%t", backend, query, rec.Code, rec.Body.String(), wantTags)
+				}
+			}
+		},
+	})
+}
+
+func TestVersionDeniesSurviveInheritedAndSessionPolicies(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{t: t, objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, _ auth.Credentials, t *testing.T) {
+		ctx := t.Context()
+		_, err := globalBucketMetadataSys.Update(ctx, bucket, bucketVersioningConfig, enabledBucketVersioningConfig)
+		mustIAM(t, err)
+		oi, err := obj.PutObject(ctx, bucket, "item", mustGetPutObjReader(t, strings.NewReader("data"), 4, "", ""), ObjectOptions{
+			Versioned: true, UserDefined: map[string]string{xhttp.AmzObjectTagging: "classification=public"},
+		})
+		mustIAM(t, err)
+		allow := fmt.Sprintf(`{"Effect":"Allow","Action":["s3:GetObject","s3:GetObjectTagging"],"Resource":["arn:aws:s3:::%s/*"]}`, bucket)
+		deny := fmt.Sprintf(`{"Effect":"Deny","Action":["s3:GetObjectVersion","s3:GetObjectVersionTagging"],"Resource":["arn:aws:s3:::%s/*"],"Condition":{"StringEquals":{"s3:versionid":%q}}}`, bucket, oi.VersionID)
+		document := func(statements string) string {
+			return `{"Version":"2012-10-17","Statement":[` + statements + `]}`
+		}
+		baseOnly := createTestPolicyUser(t, document(allow))
+		denied := createTestPolicyUser(t, document(allow+","+deny))
+		inherited, _, err := globalIAMSys.NewServiceAccount(ctx, denied.AccessKey, nil, newServiceAccountOpts{})
+		mustIAM(t, err)
+		session, err := policy.ParseConfig(strings.NewReader(document(allow + "," + deny)))
+		mustIAM(t, err)
+		inline, _, err := globalIAMSys.NewServiceAccount(ctx, globalActiveCred.AccessKey, nil, newServiceAccountOpts{sessionPolicy: session})
+		mustIAM(t, err)
+		secret, err := getTokenSigningKey()
+		mustIAM(t, err)
+		temporary, err := auth.GetNewCredentialsWithMetadata(map[string]any{
+			parentClaim: globalActiveCred.AccessKey, "exp": UTCNow().Add(time.Hour).Unix(),
+			policy.SessionPolicyName: base64.StdEncoding.EncodeToString([]byte(document(allow + "," + deny))),
+		}, secret)
+		mustIAM(t, err)
+		temporary.ParentUser = globalActiveCred.AccessKey
+		_, err = globalIAMSys.SetTempUser(ctx, temporary.AccessKey, temporary, "")
+		mustIAM(t, err)
+		groupUser := createTestPolicyUser(t, document(allow))
+		groupPolicy, err := policy.ParseConfig(strings.NewReader(document(deny)))
+		mustIAM(t, err)
+		_, err = globalIAMSys.SetPolicy(ctx, "version-deny", *groupPolicy)
+		mustIAM(t, err)
+		_, err = globalIAMSys.AddUsersToGroup(ctx, "version-deny-group", []string{groupUser.AccessKey})
+		mustIAM(t, err)
+		_, err = globalIAMSys.PolicyDBSet(ctx, "version-deny-group", "version-deny", regUser, true)
+		mustIAM(t, err)
+		for _, tc := range []struct {
+			name string
+			cred auth.Credentials
+			deny bool
+		}{
+			{"legacy-base-grant", baseOnly, false},
+			{"regular", denied, true},
+			{"inherited-service-account", inherited, true},
+			{"root-service-account-session", inline, true},
+			{"root-sts-session", temporary, true},
+			{"group", groupUser, true},
+		} {
+			for _, query := range []string{"", "?versionId=" + oi.VersionID, "?tagging=&versionId=" + oi.VersionID} {
+				headers := map[string]string{xhttp.AmzTagDirective: "ACCESS"}
+				if tc.cred.IsTemp() {
+					headers[xhttp.AmzSecurityToken] = tc.cred.SessionToken
+				}
+				req, err := newTestSignedRequestV4(http.MethodGet, "/"+bucket+"/item"+query, 0, nil, tc.cred.AccessKey, tc.cred.SecretKey, headers)
+				mustIAM(t, err)
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				want := http.StatusOK
+				if tc.deny && query != "" {
+					want = http.StatusForbidden
+				}
+				if rec.Code != want {
+					t.Errorf("%s %s %s: got %d %s, want %d", backend, tc.name, query, rec.Code, rec.Body.String(), want)
+				}
+			}
+		}
+	}})
+}

cmd/release_gate_audit_regressions_test.go

@@ -0,0 +1,941 @@
+// Copyright (c) 2026 PGSTY
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"archive/zip"
+	"bytes"
+	"crypto/hmac"
+	"crypto/md5"
+	"crypto/sha256"
+	"encoding/base64"
+	"encoding/hex"
+	"encoding/json"
+	"encoding/xml"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/minio/internal/bucket/versioning"
+	"github.com/minio/minio/internal/crypto"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/minio/minio/internal/kms"
+	"github.com/pgsty/silo-pkg/v3/policy"
+)
+
+func TestStrictPolicyParsingRejectsMalformedAndTypoJSON(t *testing.T) {
+	invalidDocs := []struct {
+		name string
+		raw  string
+	}{
+		{"null-literal", "null"},
+		{"array-literal", "[]"},
+		{"string-literal", `"policy"`},
+		{"trailing-object", `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::b/*"]}]} {"extra":1}`},
+		{"typo-statement-key", `{"Version":"2012-10-17","Statment":[{"Effect":"Allow","Action":["s3:GetObject"],"Resource":["arn:aws:s3:::b/*"]}]}`}, //nolint:misspell
+		{"unknown-stmt-field", `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Actions":["s3:GetObject"],"Resource":["arn:aws:s3:::b/*"]}]}`},
+	}
+
+	for _, tc := range invalidDocs {
+		t.Run(tc.name, func(t *testing.T) {
+			if _, err := parsePolicyStrictBytes([]byte(tc.raw)); err == nil {
+				t.Fatalf("parsePolicyStrictBytes(%s) unexpectedly succeeded", tc.name)
+			}
+			if _, err := parseSessionPolicyStrictBytes([]byte(tc.raw)); err == nil {
+				t.Fatalf("parseSessionPolicyStrictBytes(%s) unexpectedly succeeded", tc.name)
+			}
+			if _, err := parseBucketPolicyStrictBytes([]byte(tc.raw), "b"); err == nil {
+				t.Fatalf("parseBucketPolicyStrictBytes(%s) unexpectedly succeeded", tc.name)
+			}
+		})
+	}
+
+	// Bucket policy must reject unknown Principal keys such as Service instead of treating AWS as empty.
+	servicePrincipalPolicy := `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Principal":{"Service":["s3.amazonaws.com"]},"Action":["s3:GetObject"],"Resource":["arn:aws:s3:::b/*"]}]}`
+	if _, err := parseBucketPolicyStrictBytes([]byte(servicePrincipalPolicy), "b"); err == nil {
+		t.Fatal("parseBucketPolicyStrictBytes accepted Principal.Service without AWS key")
+	}
+
+	// Explicit session-policy reset documents remain accepted for service accounts,
+	// while named IAM policies reject empty statement lists.
+	for _, resetDoc := range []string{`{}`, `{"Statement":[]}`, `{"Version":"2012-10-17","Statement":[]}`} {
+		sp, err := parseSessionPolicyStrictBytes([]byte(resetDoc))
+		if err != nil {
+			t.Fatalf("parseSessionPolicyStrictBytes(%s) unexpected error: %v", resetDoc, err)
+		}
+		if !sp.IsEmpty() {
+			t.Fatalf("parseSessionPolicyStrictBytes(%s) expected empty policy", resetDoc)
+		}
+		if _, err := parsePolicyStrictBytes([]byte(resetDoc)); err == nil {
+			t.Fatalf("parsePolicyStrictBytes(%s) accepted empty named policy", resetDoc)
+		}
+	}
+
+	// Versioning ExcludedPrefixes must be recognized as PrefixesExcluded so Object Lock import rejects it.
+	var v versioning.Versioning
+	if err := xml.Unmarshal([]byte(`<VersioningConfiguration xmlns="http://s3.amazonaws.com/doc/2006-03-01/"><Status>Enabled</Status><ExcludedPrefixes><Prefix>tmp/</Prefix></ExcludedPrefixes></VersioningConfiguration>`), &v); err != nil {
+		t.Fatal(err)
+	}
+	if !v.PrefixesExcluded() {
+		t.Fatal("expected v.PrefixesExcluded() == true when ExcludedPrefixes is populated")
+	}
+}
+
+func TestLegacyEmptyEmbeddedPolicyServiceAccountStaysDenyAll(t *testing.T) {
+	f := newGroupRefreshFixture(t)
+	_, err := f.sys.PolicyDBSet(f.ctx, f.parent.AccessKey, "readwrite", regUser, false)
+	mustIAM(t, err)
+
+	// Sanity check: parent has full access.
+	if !f.sys.IsAllowed(policy.Args{AccountName: f.parent.AccessKey, Action: policy.GetObjectAction, BucketName: "b", ObjectName: "k"}) {
+		t.Fatal("expected parent user to allow GetObject")
+	}
+
+	const legacyKey = "legacy-deny-all-sa"
+	legacyClaims := map[string]any{
+		iamPolicyClaimNameSA():   embeddedPolicyType,
+		policy.SessionPolicyName: base64.StdEncoding.EncodeToString([]byte(`{"Version":"2012-10-17","Statement":[]}`)),
+	}
+	_, _, err = f.sys.NewServiceAccount(f.ctx, f.parent.AccessKey, nil, newServiceAccountOpts{
+		accessKey:                   legacyKey,
+		secretKey:                   "legacy-secret-key-12345",
+		claims:                      legacyClaims,
+		preserveEmptyEmbeddedPolicy: true,
+	})
+	mustIAM(t, err)
+	mustIAM(t, f.sys.store.LoadIAMCache(f.ctx, false))
+
+	u, valid, err := f.sys.CheckKey(f.ctx, legacyKey)
+	mustIAM(t, err)
+	if !valid {
+		t.Fatal("expected legacy service account to remain valid")
+	}
+	if f.sys.IsAllowed(policy.Args{AccountName: legacyKey, Claims: u.Credentials.Claims, Action: policy.GetObjectAction, BucketName: "b", ObjectName: "k"}) {
+		t.Fatal("legacy empty embedded-policy service account was promoted to parent permissions")
+	}
+
+	// Metadata-only edit (nil sessionPolicy) must preserve the deny-all embedded-policy state.
+	_, err = f.sys.UpdateServiceAccount(f.ctx, legacyKey, updateServiceAccountOpts{
+		description: "metadata-only-update",
+	})
+	mustIAM(t, err)
+	mustIAM(t, f.sys.store.LoadIAMCache(f.ctx, false))
+
+	u, _, err = f.sys.CheckKey(f.ctx, legacyKey)
+	mustIAM(t, err)
+	if u.Credentials.Description != "metadata-only-update" {
+		t.Fatalf("description = %q, want metadata-only-update", u.Credentials.Description)
+	}
+	if f.sys.IsAllowed(policy.Args{AccountName: legacyKey, Claims: u.Credentials.Claims, Action: policy.GetObjectAction, BucketName: "b", ObjectName: "k"}) {
+		t.Fatal("metadata-only edit promoted legacy deny-all service account to parent permissions")
+	}
+
+	// Explicit empty reset document clears the inline policy to parent inheritance.
+	_, err = f.sys.UpdateServiceAccount(f.ctx, legacyKey, updateServiceAccountOpts{
+		sessionPolicy: &policy.Policy{},
+	})
+	mustIAM(t, err)
+	mustIAM(t, f.sys.store.LoadIAMCache(f.ctx, false))
+
+	u, _, err = f.sys.CheckKey(f.ctx, legacyKey)
+	mustIAM(t, err)
+	if !f.sys.IsAllowed(policy.Args{AccountName: legacyKey, Claims: u.Credentials.Claims, Action: policy.GetObjectAction, BucketName: "b", ObjectName: "k"}) {
+		t.Fatal("explicit empty-policy reset did not restore parent inheritance")
+	}
+}
+
+func TestObjectLockSuspendedAndExcludedNullVersionProtection(t *testing.T) {
+	t.Run("multi-pool-null-version-lock", func(t *testing.T) {
+		z, bucket := consistencyPools(t)
+		const key = "null-locked-obj"
+		retainUntil := UTCNow().Add(24 * time.Hour).Format(time.RFC3339)
+
+		// Pool 0 holds a COMPLIANCE-locked null version; Pool 1 holds an unlocked competing copy.
+		metaLocked := poolLockMetadata("COMPLIANCE", "OFF", objectLockTestStamp0900, "")
+		metaLocked[strings.ToLower(xhttp.AmzObjectLockRetainUntilDate)] = retainUntil
+		metaUnlocked := poolLockMetadata("", "OFF", objectLockTestStamp1000, "")
+		stamp := UTCNow().Add(-time.Minute)
+		putConsistencyObject(t, z, bucket, key, 0, "locked-null", ObjectOptions{
+			VersionID: nullVersionID, VersionSuspended: true, MTime: stamp, UserDefined: metaLocked,
+		})
+		putConsistencyObject(t, z, bucket, key, 1, "locked-null", ObjectOptions{
+			VersionID: nullVersionID, VersionSuspended: true, MTime: stamp.Add(time.Second), UserDefined: metaUnlocked,
+		})
+
+		// Unaddressed DeleteObject (prefix-excluded or unversioned delete with RefuseLockedOverwrite) must fail closed,
+		// even if a newer unlocked UUID version also exists on top of the locked null version.
+		putConsistencyObject(t, z, bucket, key, 1, "newer-unlocked-v2", ObjectOptions{
+			VersionID: mustGetUUID(), Versioned: true, MTime: stamp.Add(2 * time.Second),
+		})
+		_, err := z.DeleteObject(t.Context(), bucket, key, ObjectOptions{RefuseLockedOverwrite: true})
+		var lockedErr ObjectLocked
+		if !errors.As(err, &lockedErr) {
+			t.Fatalf("DeleteObject error = %v, want ObjectLocked", err)
+		}
+
+		// Verify the COMPLIANCE-locked null version on pool 0 is untouched.
+		got, err := z.serverPools[0].GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: nullVersionID, VersionSuspended: true})
+		if err != nil {
+			t.Fatalf("locked null version lost from pool 0: %v", err)
+		}
+		if got.UserDefined[strings.ToLower(xhttp.AmzObjectLockMode)] != "COMPLIANCE" {
+			t.Fatalf("unexpected retention mode after blocked delete: %+v", got.UserDefined)
+		}
+	})
+
+	t.Run("api-excluded-prefix-unaddressed-delete-and-bulk-delete", func(t *testing.T) {
+		defer DetectTestLeak(t)()
+		ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+			t:                 t,
+			makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+			objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+				const key = "excl/worm-null"
+				retainUntil := UTCNow().Add(24 * time.Hour).Format(time.RFC3339)
+				meta := map[string]string{
+					strings.ToLower(xhttp.AmzObjectLockMode):            "COMPLIANCE",
+					strings.ToLower(xhttp.AmzObjectLockRetainUntilDate): retainUntil,
+				}
+				const payload = "immutable-null-version-data"
+				// Write a COMPLIANCE-locked null version AND a newer unlocked UUID version on top of it,
+				// then simulate a legacy Object Lock bucket with ExcludedPrefixes loaded in memory.
+				_, err := obj.PutObject(t.Context(), bucket, key, mustGetPutObjReader(t, strings.NewReader(payload), int64(len(payload)), "", ""), ObjectOptions{
+					Versioned:   false,
+					UserDefined: meta,
+				})
+				if err != nil {
+					t.Fatalf("%s: PutObject null: %v", backend, err)
+				}
+				_, err = obj.PutObject(t.Context(), bucket, key, mustGetPutObjReader(t, strings.NewReader("newer-v2"), int64(len("newer-v2")), "", ""), ObjectOptions{
+					Versioned: true,
+				})
+				if err != nil {
+					t.Fatalf("%s: PutObject v2: %v", backend, err)
+				}
+
+				bm, err := globalBucketMetadataSys.Get(bucket)
+				if err != nil {
+					t.Fatalf("%s: get bucket metadata: %v", backend, err)
+				}
+				bm.versioningConfig = &versioning.Versioning{
+					XMLNS:            "http://s3.amazonaws.com/doc/2006-03-01/",
+					Status:           versioning.Enabled,
+					ExcludedPrefixes: []versioning.ExcludedPrefix{{Prefix: "excl/"}},
+				}
+				globalBucketMetadataSys.Set(bucket, bm)
+
+				// 1. Unaddressed DELETE /bucket/excl/worm-null must fail closed with ErrObjectLocked (400 InvalidRequest).
+				delReq, err := newTestSignedRequestV4(http.MethodDelete, "/"+bucket+"/"+key, 0, nil, cred.AccessKey, cred.SecretKey, nil)
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, delReq)
+				if rec.Code != http.StatusBadRequest || !strings.Contains(rec.Body.String(), "WORM protected") {
+					t.Fatalf("%s: unaddressed DELETE status = %d, want 400 WORM protected; body=%s", backend, rec.Code, rec.Body.String())
+				}
+
+				// 2. Unaddressed Multi-Object Delete POST /bucket?delete must report WORM error per key.
+				delBody := `<Delete><Object><Key>` + key + `</Key></Object></Delete>`
+				sum := md5.Sum([]byte(delBody))
+				headers := map[string]string{
+					xhttp.ContentMD5: base64.StdEncoding.EncodeToString(sum[:]),
+				}
+				bulkReq, err := newTestSignedRequestV4(http.MethodPost, "/"+bucket+"?delete", int64(len(delBody)), strings.NewReader(delBody), cred.AccessKey, cred.SecretKey, headers)
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec = httptest.NewRecorder()
+				router.ServeHTTP(rec, bulkReq)
+				if rec.Code != http.StatusOK || !strings.Contains(rec.Body.String(), "WORM protected") {
+					t.Fatalf("%s: DeleteObjects status=%d body=%s, want WORM protected error entry", backend, rec.Code, rec.Body.String())
+				}
+
+				// Locked null-version object must remain intact and readable.
+				if _, err := obj.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: nullVersionID, VersionSuspended: true}); err != nil {
+					t.Fatalf("%s: locked null-version object disappeared: %v", backend, err)
+				}
+			},
+		})
+	})
+}
+
+func TestStreamingTrailerEOFAndNegativeDecodedLength(t *testing.T) {
+	t.Run("unsigned-trailer-truncated-and-oversized", func(t *testing.T) {
+		// Truncated mid-trailer (missing final \r\n\r\n) must return ErrUnexpectedEOF, never nil/EOF.
+		truncatedBody := "5\r\nhello\r\n0\r\nx-amz-checksum-crc32:AAAAAA=="
+		req := httptest.NewRequest(http.MethodPut, "http://minio.local/b/k", strings.NewReader(truncatedBody))
+		req.Header.Set(xhttp.AmzContentSha256, unsignedPayloadTrailer)
+		req.Header.Set(xhttp.AmzDecodedContentLength, "5")
+		req.Header.Set(awsTrailerHeader, "x-amz-checksum-crc32")
+
+		rd, code := newUnsignedV4ChunkedReader(req, true)
+		if code != ErrNone {
+			t.Fatalf("newUnsignedV4ChunkedReader code = %v", code)
+		}
+		_, err := io.ReadAll(rd)
+		rd.Close()
+		if !errors.Is(err, io.ErrUnexpectedEOF) {
+			t.Fatalf("truncated trailer ReadAll error = %v, want io.ErrUnexpectedEOF", err)
+		}
+
+		// Oversized trailer (> 64 KiB without \r\n\r\n) must reject cleanly without unbounded growth.
+		oversizedBody := "1\r\na\r\n0\r\nx-amz-checksum-crc32:" + strings.Repeat("A", 64*1024+1024)
+		req2 := httptest.NewRequest(http.MethodPut, "http://minio.local/b/k", strings.NewReader(oversizedBody))
+		req2.Header.Set(xhttp.AmzContentSha256, unsignedPayloadTrailer)
+		req2.Header.Set(xhttp.AmzDecodedContentLength, "1")
+		req2.Header.Set(awsTrailerHeader, "x-amz-checksum-crc32")
+
+		rd2, code := newUnsignedV4ChunkedReader(req2, true)
+		if code != ErrNone {
+			t.Fatalf("newUnsignedV4ChunkedReader oversized code = %v", code)
+		}
+		_, err = io.ReadAll(rd2)
+		rd2.Close()
+		if err == nil || errors.Is(err, io.EOF) {
+			t.Fatalf("oversized trailer ReadAll error = %v, want non-EOF error", err)
+		}
+	})
+
+	t.Run("negative-decoded-content-length-rejected", func(t *testing.T) {
+		defer DetectTestLeak(t)()
+		ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+			t:         t,
+			endpoints: []string{"PutObject"},
+			objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+				req, err := newStreamingUnsignedTrailerRequest(http.MethodPut, getPutObjectURL("", bucket, "neg-len"), []byte("abc"), UTCNow())
+				if err != nil {
+					t.Fatal(err)
+				}
+				req.Header.Set(xhttp.AmzDecodedContentLength, "-5")
+				if err := signRequestV4(req, cred.AccessKey, cred.SecretKey); err != nil {
+					t.Fatal(err)
+				}
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				if rec.Code != http.StatusBadRequest {
+					t.Fatalf("%s: negative X-Amz-Decoded-Content-Length status = %d, want 400; body=%s", backend, rec.Code, rec.Body.String())
+				}
+				if _, err := obj.GetObjectInfo(t.Context(), bucket, "neg-len", ObjectOptions{}); err == nil {
+					t.Fatalf("%s: object stored despite negative X-Amz-Decoded-Content-Length", backend)
+				}
+			},
+		})
+	})
+}
+
+func signV4WithScopeDate(req *http.Request, accessKey, secretKey, region string, reqTime, scopeTime time.Time, payloadHash string) {
+	req.Header.Set(xhttp.AmzDate, reqTime.Format(iso8601Format))
+	req.Header.Set(xhttp.AmzContentSha256, payloadHash)
+	if req.Header.Get("Host") == "" {
+		req.Header.Set("Host", req.Host)
+	}
+	signedHeaders := []string{"host", "x-amz-content-sha256", "x-amz-date"}
+	canonicalHeaders := fmt.Sprintf("host:%s\nx-amz-content-sha256:%s\nx-amz-date:%s\n",
+		req.Host, payloadHash, reqTime.Format(iso8601Format))
+	canonicalRequest := strings.Join([]string{
+		req.Method,
+		req.URL.EscapedPath(),
+		req.URL.RawQuery,
+		canonicalHeaders,
+		strings.Join(signedHeaders, ";"),
+		payloadHash,
+	}, "\n")
+	scope := fmt.Sprintf("%s/%s/s3/aws4_request", scopeTime.Format(yyyymmdd), region)
+	sum := sha256.Sum256([]byte(canonicalRequest))
+	stringToSign := strings.Join([]string{
+		signV4Algorithm,
+		reqTime.Format(iso8601Format),
+		scope,
+		hex.EncodeToString(sum[:]),
+	}, "\n")
+	signingKey := getSigningKey(secretKey, scopeTime, region, serviceS3)
+	sig := getSignature(signingKey, stringToSign)
+	req.Header.Set(xhttp.Authorization, fmt.Sprintf("%s Credential=%s/%s, SignedHeaders=%s, Signature=%s",
+		signV4Algorithm, accessKey, scope, strings.Join(signedHeaders, ";"), sig))
+}
+
+func TestSigV4ScopeDateMismatchRejected(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t:         t,
+		endpoints: []string{"GetObject", "PutObject"},
+		objAPITest: func(_ ObjectLayer, backend, bucket string, _ http.Handler, cred auth.Credentials, t *testing.T) {
+			now := UTCNow()
+			yesterday := now.Add(-24 * time.Hour)
+			const region = globalMinioDefaultRegion
+
+			// 1. Standard Header SigV4
+			req := httptest.NewRequest(http.MethodGet, "http://minio.local/"+bucket+"/obj", nil)
+			signV4WithScopeDate(req, cred.AccessKey, cred.SecretKey, region, now, yesterday, emptySHA256)
+			if code := doesSignatureMatch(emptySHA256, req, region, serviceS3); code == ErrNone {
+				t.Fatalf("%s: doesSignatureMatch accepted mismatched scope date", backend)
+			}
+
+			// 2. Streaming Seed SigV4
+			sreq := httptest.NewRequest(http.MethodPut, "http://minio.local/"+bucket+"/obj", strings.NewReader("0\r\n\r\n"))
+			sreq.Header.Set(xhttp.AmzDecodedContentLength, "0")
+			signV4WithScopeDate(sreq, cred.AccessKey, cred.SecretKey, region, now, yesterday, streamingContentSHA256)
+			if _, _, _, _, code := calculateSeedSignature(sreq, false); code == ErrNone {
+				t.Fatalf("%s: calculateSeedSignature accepted mismatched scope date", backend)
+			}
+
+			// 3. Presigned SigV4
+			q := url.Values{}
+			scope := fmt.Sprintf("%s/%s/s3/aws4_request", yesterday.Format(yyyymmdd), region)
+			q.Set(xhttp.AmzAlgorithm, signV4Algorithm)
+			q.Set(xhttp.AmzCredential, cred.AccessKey+"/"+scope)
+			q.Set(xhttp.AmzDate, now.Format(iso8601Format))
+			q.Set(xhttp.AmzExpires, "300")
+			q.Set(xhttp.AmzSignedHeaders, "host")
+			preq := httptest.NewRequest(http.MethodGet, "http://minio.local/"+bucket+"/obj?"+q.Encode(), nil)
+			canonicalPresigned := strings.Join([]string{
+				http.MethodGet,
+				preq.URL.EscapedPath(),
+				preq.URL.Query().Encode(),
+				"host:" + preq.Host + "\n",
+				"host",
+				unsignedPayload,
+			}, "\n")
+			psum := sha256.Sum256([]byte(canonicalPresigned))
+			pSTS := strings.Join([]string{
+				signV4Algorithm,
+				now.Format(iso8601Format),
+				scope,
+				hex.EncodeToString(psum[:]),
+			}, "\n")
+			pSig := getSignature(getSigningKey(cred.SecretKey, yesterday, region, serviceS3), pSTS)
+			q.Set(xhttp.AmzSignature, pSig)
+			preq.URL.RawQuery = q.Encode()
+			if code := doesPresignedSignatureMatch(unsignedPayload, preq, region, serviceS3); code == ErrNone {
+				t.Fatalf("%s: doesPresignedSignatureMatch accepted mismatched scope date", backend)
+			}
+
+			// 4. POST Policy SigV4
+			policyDoc := fmt.Sprintf(`{"expiration":%q,"conditions":[["eq","$bucket",%q],["eq","$x-amz-date",%q],["eq","$x-amz-credential",%q],["eq","$x-amz-algorithm","AWS4-HMAC-SHA256"]]}`,
+				now.Add(10*time.Minute).Format(iso8601Format), bucket, now.Format(iso8601Format), cred.AccessKey+"/"+scope)
+			policyB64 := base64.StdEncoding.EncodeToString([]byte(policyDoc))
+			mac := hmac.New(sha256.New, getSigningKey(cred.SecretKey, yesterday, region, serviceS3))
+			mac.Write([]byte(policyB64))
+			postSig := hex.EncodeToString(mac.Sum(nil))
+			formValues := http.Header{}
+			formValues.Set(xhttp.AmzAlgorithm, signV4Algorithm)
+			formValues.Set(xhttp.AmzCredential, cred.AccessKey+"/"+scope)
+			formValues.Set(xhttp.AmzDate, now.Format(iso8601Format))
+			formValues.Set(xhttp.AmzSignature, postSig)
+			formValues.Set("Policy", policyB64)
+			if _, code := doesPolicySignatureV4Match(formValues); code == ErrNone {
+				t.Fatalf("%s: doesPolicySignatureV4Match accepted mismatched scope date", backend)
+			}
+		},
+	})
+}
+
+func TestBatchKeyRotateLegacyXLV1AndSSES3ToKMS(t *testing.T) {
+	f := newBatchAuthzFixture(t)
+	previous := GlobalKMS
+	t.Cleanup(func() { GlobalKMS = previous })
+	configured, err := kms.NewBuiltin("rotate-key", bytes.Repeat([]byte{0x37}, 32))
+	mustIAM(t, err)
+	GlobalKMS = configured
+
+	t.Run("sse-s3-multipart-to-sse-kms-empty-context", func(t *testing.T) {
+		const object = "sses3-mp/item"
+		const payload = "multipart sse-s3 migrated to sse-kms without losing multipart flag"
+		metadata := map[string]string{
+			crypto.MetaMultipart: "1",
+		}
+		key, err := newEncryptMetadata(f.ctx, crypto.S3, "", nil, f.bucket, object, metadata, nil)
+		mustIAM(t, err)
+		ciphertext, err := io.ReadAll(crypto.EncryptSinglePart(strings.NewReader(payload), key))
+		mustIAM(t, err)
+		original, err := f.obj.PutObject(f.ctx, f.bucket, object, mustGetPutObjReader(t, bytes.NewReader(ciphertext), int64(len(ciphertext)), "", ""), ObjectOptions{
+			Versioned:   true,
+			UserDefined: metadata,
+		})
+		mustIAM(t, err)
+
+		rec, job := f.submit(t, globalActiveCred, fmt.Sprintf("keyrotate:\n  apiVersion: v1\n  bucket: %s\n  prefix: sses3-mp/\n  encryption:\n    type: sse-kms\n    key: rotate-key\n", f.bucket))
+		if job == nil {
+			t.Fatalf("submit: %d %s", rec.Code, rec.Body.String())
+		}
+		mustIAM(t, job.KeyRotate.Start(f.ctx, f.obj, *job))
+		progress := f.jobInfo(t, job)
+		if !progress.Complete || progress.Failed || progress.Objects != 1 {
+			t.Fatalf("SSE-S3 -> SSE-KMS rotation failed: %+v", progress)
+		}
+
+		after, err := f.obj.GetObjectInfo(f.ctx, f.bucket, object, ObjectOptions{VersionID: original.VersionID})
+		mustIAM(t, err)
+		if !crypto.S3KMS.IsEncrypted(after.UserDefined) || crypto.S3.IsEncrypted(after.UserDefined) {
+			t.Fatalf("unexpected encryption headers after SSE-S3 -> SSE-KMS: %+v", after.UserDefined)
+		}
+		if after.UserDefined[crypto.MetaMultipart] != "1" {
+			t.Fatalf("MetaMultipart stripped during SSE-S3 -> SSE-KMS rotation: %+v", after.UserDefined)
+		}
+		actual, err := crypto.S3KMS.UnsealObjectKey(configured, after.UserDefined, f.bucket, object)
+		mustIAM(t, err)
+		if actual != key {
+			t.Fatal("data encryption key changed during metadata rotation")
+		}
+	})
+
+	t.Run("legacy-xlv1-stream-rewrite-rotation", func(t *testing.T) {
+		const legacyBucket = "legacy-xlv1-bucket"
+		mustIAM(t, f.obj.MakeBucket(f.ctx, legacyBucket, MakeBucketOptions{}))
+
+		const object = "legacy/obj"
+		payload := strings.Repeat("legacy XLV1 object rotated cleanly to XLV2 without panic! ", 4096)
+		metadata := map[string]string{
+			xhttp.AmzObjectTagging: "tier=legacy",
+		}
+		key, err := newEncryptMetadata(f.ctx, crypto.S3KMS, "rotate-key", nil, legacyBucket, object, metadata, kms.Context{"stage": "v1"})
+		mustIAM(t, err)
+		ciphertext, err := io.ReadAll(crypto.EncryptSinglePart(strings.NewReader(payload), key))
+		mustIAM(t, err)
+		plainMD5 := md5.Sum([]byte(payload))
+		sealedETag := hex.EncodeToString(key.SealETag(plainMD5[:]))
+		metadata["etag"] = sealedETag
+
+		_, err = f.obj.PutObject(f.ctx, legacyBucket, object, mustGetPutObjReader(t, bytes.NewReader(ciphertext), int64(len(ciphertext)), "", ""), ObjectOptions{
+			UserDefined: metadata,
+		})
+		mustIAM(t, err)
+
+		// Convert stored XLV2 layout on the single test disk into a real XLV1 xl.json + part.1 layout.
+		disk := f.obj.(*erasureServerPools).serverPools[0].sets[0].getDisks()[0]
+		xlDisk := disk.(*xlStorageDiskIDCheck).storage
+		xlDisk.Lock()
+		xlDisk.formatLegacy = true
+		xlDisk.Unlock()
+		t.Cleanup(func() {
+			xlDisk.Lock()
+			xlDisk.formatLegacy = false
+			xlDisk.Unlock()
+		})
+
+		fi, err := disk.ReadVersion(f.ctx, "", legacyBucket, object, "", ReadOptions{})
+		mustIAM(t, err)
+
+		partPath := pathJoin(object, fi.DataDir, "part.1")
+		rawPartBytes, err := disk.ReadAll(f.ctx, legacyBucket, partPath)
+		mustIAM(t, err)
+
+		mustIAM(t, disk.Delete(f.ctx, legacyBucket, pathJoin(object, xlStorageFormatFile), DeleteOptions{}))
+		mustIAM(t, disk.Delete(f.ctx, legacyBucket, partPath, DeleteOptions{}))
+		mustIAM(t, disk.AppendFile(f.ctx, legacyBucket, pathJoin(object, "part.1"), rawPartBytes))
+
+		fi.Metadata["etag"] = sealedETag
+		v1Obj := xlMetaV1Object{
+			Version: xlMetaVersion101,
+			Format:  xlMetaFormat,
+			Stat: StatInfo{
+				Size:    fi.Size,
+				ModTime: fi.ModTime,
+			},
+			Erasure: fi.Erasure,
+			Meta:    fi.Metadata,
+			Parts:   fi.Parts,
+		}
+		v1Obj.Minio.Release = "RELEASE.2019-12-30T05-45-39Z"
+		v1Bytes, err := json.Marshal(v1Obj)
+		mustIAM(t, err)
+		mustIAM(t, disk.AppendFile(f.ctx, legacyBucket, pathJoin(object, xlStorageFormatFileV1), v1Bytes))
+
+		legacyOI, err := f.obj.GetObjectInfo(f.ctx, legacyBucket, object, ObjectOptions{})
+		mustIAM(t, err)
+		if !legacyOI.Legacy {
+			t.Fatal("expected test fixture object to report Legacy (XLV1) == true")
+		}
+
+		newCtxB64 := base64.StdEncoding.EncodeToString([]byte(`{"stage":"v2"}`))
+		rec, job := f.submit(t, globalActiveCred, fmt.Sprintf("keyrotate:\n  apiVersion: v1\n  bucket: %s\n  prefix: legacy/\n  encryption:\n    type: sse-kms\n    key: rotate-key\n    context: %s\n", legacyBucket, newCtxB64))
+		if job == nil {
+			t.Fatalf("submit legacy keyrotate: %d %s", rec.Code, rec.Body.String())
+		}
+		mustIAM(t, job.KeyRotate.Start(f.ctx, f.obj, *job))
+		progress := f.jobInfo(t, job)
+		if !progress.Complete || progress.Failed || progress.Objects != 1 {
+			t.Fatalf("legacy XLV1 rotation failed: %+v", progress)
+		}
+
+		after, err := f.obj.GetObjectInfo(f.ctx, legacyBucket, object, ObjectOptions{})
+		mustIAM(t, err)
+		if after.Legacy {
+			t.Fatal("expected rotated legacy object to be upgraded to XLV2 (Legacy == false)")
+		}
+		if after.UserTags != "tier=legacy" {
+			t.Fatalf("UserTags = %q, want tier=legacy", after.UserTags)
+		}
+		if got := readCopyChecksumObject(t, f.obj, legacyBucket, object, ObjectOptions{}); string(got) != payload {
+			t.Fatalf("decrypted content = %q, want %q", string(got), payload)
+		}
+		newObjKey, err := crypto.S3KMS.UnsealObjectKey(configured, after.UserDefined, legacyBucket, object)
+		mustIAM(t, err)
+		unsealedETag, err := DecryptETag(newObjKey, ObjectInfo{ETag: after.ETag})
+		mustIAM(t, err)
+		if wantETag := hex.EncodeToString(plainMD5[:]); unsealedETag != wantETag {
+			t.Fatalf("unsealed ETag = %q, want %q", unsealedETag, wantETag)
+		}
+	})
+}
+
+func createTestPolicyUser(t *testing.T, policyJSON string) auth.Credentials {
+	t.Helper()
+	ctx := t.Context()
+	ak, sk, err := auth.GenerateCredentials()
+	if err != nil {
+		t.Fatal(err)
+	}
+	creds := auth.Credentials{AccessKey: ak, SecretKey: sk}
+	if _, err = globalIAMSys.CreateUser(ctx, creds.AccessKey, madmin.AddOrUpdateUserReq{
+		SecretKey: creds.SecretKey,
+		Status:    madmin.AccountEnabled,
+	}); err != nil {
+		t.Fatal(err)
+	}
+	parsed, err := policy.ParseConfig(strings.NewReader(policyJSON))
+	if err != nil {
+		t.Fatalf("parse policy: %v\n%s", err, policyJSON)
+	}
+	pName := "audit-policy-" + mustGetUUID()
+	if _, err = globalIAMSys.SetPolicy(ctx, pName, *parsed); err != nil {
+		t.Fatal(err)
+	}
+	if _, err = globalIAMSys.PolicyDBSet(ctx, creds.AccessKey, pName, regUser, false); err != nil {
+		t.Fatal(err)
+	}
+	return creds
+}
+
+func TestObjectTagAndVersionAuthSymmetry(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t,
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, adminCred auth.Credentials, t *testing.T) {
+			if _, err := globalBucketMetadataSys.Update(t.Context(), bucket, bucketVersioningConfig, enabledBucketVersioningConfig); err != nil {
+				t.Fatalf("%s: enable versioning: %v", backend, err)
+			}
+
+			// Create v1 (env=prod) and v2 (env=dev) of src-obj.
+			v1, err := obj.PutObject(t.Context(), bucket, "src-obj", mustGetPutObjReader(t, strings.NewReader("prod-secret"), int64(len("prod-secret")), "", ""), ObjectOptions{
+				Versioned:   true,
+				UserDefined: map[string]string{xhttp.AmzObjectTagging: "env=prod"},
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			v2, err := obj.PutObject(t.Context(), bucket, "src-obj", mustGetPutObjReader(t, strings.NewReader("dev-public"), int64(len("dev-public")), "", ""), ObjectOptions{
+				Versioned:   true,
+				UserDefined: map[string]string{xhttp.AmzObjectTagging: "env=dev"},
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			// Also create a ZIP object with env=prod tag to verify ZIP sub-handlers enforce ExistingObjectTag.
+			var zipBuf bytes.Buffer
+			zw := zip.NewWriter(&zipBuf)
+			zf, err := zw.Create("inside.txt")
+			if err != nil {
+				t.Fatal(err)
+			}
+			_, _ = zf.Write([]byte("zip-inner"))
+			if err := zw.Close(); err != nil {
+				t.Fatal(err)
+			}
+			_, err = obj.PutObject(t.Context(), bucket, "archive.zip", mustGetPutObjReader(t, bytes.NewReader(zipBuf.Bytes()), int64(zipBuf.Len()), "", ""), ObjectOptions{
+				Versioned:   true,
+				UserDefined: map[string]string{xhttp.AmzObjectTagging: "env=prod"},
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			// User A:
+			// - Can read/tag ONLY objects/versions tagged env=dev.
+			// - Can write dst/* ONLY when RequestObjectTag/env == dev (plus unconditional PutObject on prod-readable copy test).
+			userAPolicy := fmt.Sprintf(`{
+				"Version": "2012-10-17",
+				"Statement": [
+					{
+						"Effect": "Allow",
+						"Action": [
+							"s3:GetObject",
+							"s3:GetObjectVersion",
+							"s3:GetObjectTagging",
+							"s3:GetObjectVersionTagging",
+							"s3:PutObjectTagging",
+							"s3:PutObjectVersionTagging",
+							"s3:DeleteObjectTagging",
+							"s3:DeleteObjectVersionTagging"
+						],
+						"Resource": ["arn:aws:s3:::%s/*"],
+						"Condition": {"StringEquals": {"s3:ExistingObjectTag/env": ["dev"]}}
+					},
+					{
+						"Effect": "Allow",
+						"Action": ["s3:ListBucket", "s3:ListBucketVersions", "s3:ListBucketMultipartUploads"],
+						"Resource": ["arn:aws:s3:::%s"]
+					},
+					{
+						"Effect": "Allow",
+						"Action": ["s3:PutObject"],
+						"Resource": ["arn:aws:s3:::%s/dst-*"],
+						"Condition": {"StringEquals": {"s3:RequestObjectTag/env": ["dev"]}}
+					},
+					{
+						"Effect": "Allow",
+						"Action": ["s3:PutObject", "s3:AbortMultipartUpload", "s3:ListMultipartUploadParts"],
+						"Resource": ["arn:aws:s3:::%s/mp-*"]
+					}
+				]
+			}`, bucket, bucket, bucket, bucket)
+			userA := createTestPolicyUser(t, userAPolicy)
+
+			// 1. CopyObject from v1 (env=prod) must fail 403 due to source ExistingObjectTag.
+			cpDenied, err := newTestSignedRequestV4(http.MethodPut, "/"+bucket+"/dst-denied", 0, nil, userA.AccessKey, userA.SecretKey, map[string]string{
+				xhttp.AmzCopySource:    "/" + bucket + "/src-obj?versionId=" + v1.VersionID,
+				xhttp.AmzTagDirective:  "REPLACE",
+				xhttp.AmzObjectTagging: "env=dev",
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec := httptest.NewRecorder()
+			router.ServeHTTP(rec, cpDenied)
+			if rec.Code != http.StatusForbidden {
+				t.Fatalf("%s: CopyObject from env=prod version status=%d, want 403", backend, rec.Code)
+			}
+
+			// 2. CopyObject from v2 (env=dev) with COPY directive succeeds (RequestObjectTag/env == dev from copied tags).
+			cpOK, err := newTestSignedRequestV4(http.MethodPut, "/"+bucket+"/dst-ok", 0, nil, userA.AccessKey, userA.SecretKey, map[string]string{
+				xhttp.AmzCopySource:   "/" + bucket + "/src-obj?versionId=" + v2.VersionID,
+				xhttp.AmzTagDirective: "COPY",
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, cpOK)
+			if rec.Code != http.StatusOK {
+				t.Fatalf("%s: CopyObject from env=dev with COPY directive status=%d body=%s, want 200", backend, rec.Code, rec.Body.String())
+			}
+
+			// 3. RequestObjectTag spoofing defense on COPY directive:
+			// User B can read all versions of src-obj, but can PutObject to dst-* ONLY when RequestObjectTag/env == dev.
+			// Copying v1 (env=prod) with Tagging-Directive: COPY and a spoofed X-Amz-Tagging: env=dev header MUST fail 403!
+			userBPolicy := fmt.Sprintf(`{
+				"Version": "2012-10-17",
+				"Statement": [
+					{
+						"Effect": "Allow",
+						"Action": ["s3:GetObject", "s3:GetObjectVersion", "s3:GetObjectTagging", "s3:GetObjectVersionTagging"],
+						"Resource": ["arn:aws:s3:::%s/src-obj"]
+					},
+					{
+						"Effect": "Allow",
+						"Action": ["s3:PutObject", "s3:PutObjectTagging"],
+						"Resource": ["arn:aws:s3:::%s/dst-*"],
+						"Condition": {"StringEquals": {"s3:RequestObjectTag/env": ["dev"]}}
+					},
+					{
+						"Effect": "Allow",
+						"Action": ["s3:GetObject"],
+						"Resource": ["arn:aws:s3:::%s/src-obj"]
+					}
+				]
+			}`, bucket, bucket, bucket)
+			userB := createTestPolicyUser(t, userBPolicy)
+
+			cpSpoof, err := newTestSignedRequestV4(http.MethodPut, "/"+bucket+"/dst-spoof", 0, nil, userB.AccessKey, userB.SecretKey, map[string]string{
+				xhttp.AmzCopySource:    "/" + bucket + "/src-obj?versionId=" + v1.VersionID,
+				xhttp.AmzTagDirective:  "COPY",
+				xhttp.AmzObjectTagging: "env=dev",
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, cpSpoof)
+			if rec.Code != http.StatusForbidden {
+				t.Fatalf("%s: CopyObject accepted spoofed X-Amz-Tagging under COPY directive: status=%d body=%s", backend, rec.Code, rec.Body.String())
+			}
+
+			// 4. UploadPartCopy enforces ExistingObjectTag on versioned source!
+			initMP, err := newTestSignedRequestV4(http.MethodPost, "/"+bucket+"/mp-target?uploads", 0, nil, userA.AccessKey, userA.SecretKey, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, initMP)
+			if rec.Code != http.StatusOK {
+				t.Fatalf("%s: CreateMultipartUpload status=%d body=%s", backend, rec.Code, rec.Body.String())
+			}
+			var initResp InitiateMultipartUploadResponse
+			if err := xml.Unmarshal(rec.Body.Bytes(), &initResp); err != nil {
+				t.Fatal(err)
+			}
+
+			upcDenied, err := newTestSignedRequestV4(http.MethodPut, fmt.Sprintf("/%s/mp-target?partNumber=1&uploadId=%s", bucket, url.QueryEscape(initResp.UploadID)), 0, nil, userA.AccessKey, userA.SecretKey, map[string]string{
+				xhttp.AmzCopySource: "/" + bucket + "/src-obj?versionId=" + v1.VersionID,
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, upcDenied)
+			if rec.Code != http.StatusForbidden {
+				t.Fatalf("%s: UploadPartCopy from env=prod status=%d, want 403", backend, rec.Code)
+			}
+
+			upcOK, err := newTestSignedRequestV4(http.MethodPut, fmt.Sprintf("/%s/mp-target?partNumber=1&uploadId=%s", bucket, url.QueryEscape(initResp.UploadID)), 0, nil, userA.AccessKey, userA.SecretKey, map[string]string{
+				xhttp.AmzCopySource: "/" + bucket + "/src-obj?versionId=" + v2.VersionID,
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, upcOK)
+			if rec.Code != http.StatusOK {
+				t.Fatalf("%s: UploadPartCopy from env=dev status=%d body=%s, want 200", backend, rec.Code, rec.Body.String())
+			}
+
+			// Tag counts require the same permission as values, even without ACCESS.
+			for _, tc := range []struct {
+				name, extra              string
+				currentTags, versionTags bool
+			}{
+				{"implicit-deny", "", false, false},
+				{"allow", `,{"Effect":"Allow","Action":["s3:GetObjectTagging","s3:GetObjectVersionTagging"],"Resource":"arn:aws:s3:::*"}`, true, true},
+				{"explicit-deny", `,{"Effect":"Allow","Action":"s3:*","Resource":"arn:aws:s3:::*"},{"Effect":"Deny","Action":["s3:GetObjectTagging","s3:GetObjectVersionTagging"],"Resource":"arn:aws:s3:::*"}`, false, false},
+				{"current-only", `,{"Effect":"Allow","Action":"s3:GetObjectTagging","Resource":"arn:aws:s3:::*"},{"Effect":"Deny","Action":"s3:GetObjectVersionTagging","Resource":"arn:aws:s3:::*"}`, true, false},
+				{"replicate-tags", `,{"Effect":"Allow","Action":"s3:ReplicateTags","Resource":"arn:aws:s3:::*"}`, true, true},
+			} {
+				creds := createTestPolicyUser(t, fmt.Sprintf(`{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":["s3:GetObject","s3:GetObjectVersion"],"Resource":"arn:aws:s3:::%s/*"}%s]}`, bucket, tc.extra))
+				for _, method := range []string{http.MethodGet, http.MethodHead} {
+					for _, access := range []bool{false, true} {
+						for _, version := range []string{"", v1.VersionID} {
+							t.Run(fmt.Sprintf("%s/headers/%s/%s/access=%t/version=%t", backend, tc.name, method, access, version != ""), func(t *testing.T) {
+								target := "/" + bucket + "/src-obj"
+								wantTags, allowed := "env=dev", tc.currentTags
+								if version != "" {
+									target += "?versionId=" + version
+									wantTags, allowed = "env=prod", tc.versionTags
+								}
+								headers := map[string]string{}
+								if access {
+									headers[xhttp.AmzTagDirective] = "ACCESS"
+								}
+								req, err := newTestSignedRequestV4(method, target, 0, nil, creds.AccessKey, creds.SecretKey, headers)
+								if err != nil {
+									t.Fatal(err)
+								}
+								rec := httptest.NewRecorder()
+								router.ServeHTTP(rec, req)
+								if rec.Code != http.StatusOK {
+									t.Fatalf("status=%d: %s", rec.Code, rec.Body.String())
+								}
+								// Normalize literal handler keys as net/http does on the wire.
+								responseHeaders := http.Header{}
+								for key, values := range rec.Header() {
+									for _, value := range values {
+										responseHeaders.Add(key, value)
+									}
+								}
+								wantCount := ""
+								if allowed {
+									wantCount = "1"
+								}
+								if !allowed || !access {
+									wantTags = ""
+								}
+								if got := responseHeaders.Get(xhttp.AmzTagCount); got != wantCount {
+									t.Errorf("tag count=%q, want %q", got, wantCount)
+								}
+								if got := responseHeaders.Get(xhttp.AmzObjectTagging); got != wantTags {
+									t.Errorf("tag values=%q, want %q", got, wantTags)
+								}
+							})
+						}
+					}
+				}
+			}
+
+			// 6. ListObjectVersions with metadata=true filters <UserTags> per version's ExistingObjectTag!
+			listVerReq, err := newTestSignedRequestV4(http.MethodGet, "/"+bucket+"?versions=&metadata=true&prefix=src-obj", 0, nil, userA.AccessKey, userA.SecretKey, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, listVerReq)
+			if rec.Code != http.StatusOK {
+				t.Fatalf("%s: ListObjectVersions status=%d body=%s", backend, rec.Code, rec.Body.String())
+			}
+			bodyStr := rec.Body.String()
+			if strings.Contains(bodyStr, "env=prod") {
+				t.Fatalf("%s: ListObjectVersions metadata=true leaked unauthorized version tags env=prod: %s", backend, bodyStr)
+			}
+			if !strings.Contains(bodyStr, "env=dev") {
+				t.Fatalf("%s: ListObjectVersions metadata=true omitted authorized version tags env=dev: %s", backend, bodyStr)
+			}
+
+			// 7. GetObjectTagging & DeleteObjectTagging with ?versionId= enforce ExistingObjectTag on that version!
+			for _, method := range []string{http.MethodGet, http.MethodDelete} {
+				tagDenied, err := newTestSignedRequestV4(method, "/"+bucket+"/src-obj?tagging=&versionId="+v1.VersionID, 0, nil, userA.AccessKey, userA.SecretKey, nil)
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec = httptest.NewRecorder()
+				router.ServeHTTP(rec, tagDenied)
+				if rec.Code != http.StatusForbidden {
+					t.Fatalf("%s: %s tagging on v1 (env=prod) status=%d, want 403", backend, method, rec.Code)
+				}
+			}
+			getTagOK, err := newTestSignedRequestV4(http.MethodGet, "/"+bucket+"/src-obj?tagging=&versionId="+v2.VersionID, 0, nil, userA.AccessKey, userA.SecretKey, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec = httptest.NewRecorder()
+			router.ServeHTTP(rec, getTagOK)
+			if rec.Code != http.StatusOK {
+				t.Fatalf("%s: GET tagging on v2 (env=dev) status=%d, want 200", backend, rec.Code)
+			}
+
+			// 8. Archive x-minio-extract sub-handlers (HEAD/GET/ListObjectsV2) reject access when archive ExistingObjectTag mismatches!
+			for _, tc := range []struct {
+				name, method, target string
+			}{
+				{"zip-get", http.MethodGet, "/" + bucket + "/archive.zip/inside.txt"},
+				{"zip-head", http.MethodHead, "/" + bucket + "/archive.zip/inside.txt"},
+				{"zip-list", http.MethodGet, "/" + bucket + "?list-type=2&prefix=archive.zip/"},
+			} {
+				zreq, err := newTestSignedRequestV4(tc.method, tc.target, 0, nil, userA.AccessKey, userA.SecretKey, map[string]string{
+					"x-minio-extract": "true",
+				})
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec = httptest.NewRecorder()
+				router.ServeHTTP(rec, zreq)
+				if rec.Code != http.StatusForbidden {
+					t.Fatalf("%s: %s on env=prod archive status=%d, want 403", backend, tc.name, rec.Code)
+				}
+			}
+
+			// Clean up multipart upload with admin credentials so DetectTestLeak sees no background state.
+			abortReq, err := newTestSignedRequestV4(http.MethodDelete, fmt.Sprintf("/%s/mp-target?uploadId=%s", bucket, url.QueryEscape(initResp.UploadID)), 0, nil, adminCred.AccessKey, adminCred.SecretKey, nil)
+			if err == nil {
+				router.ServeHTTP(httptest.NewRecorder(), abortReq)
+			}
+		},
+	})
+}

cmd/replica-content.go

@@ -0,0 +1,205 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"context"
+	"io"
+	"net/http"
+
+	"github.com/minio/minio/internal/crypto"
+	"github.com/minio/minio/internal/hash/sha256"
+	xioutil "github.com/minio/minio/internal/ioutil"
+)
+
+type replicaContentGuardFn func(context.Context, string, string, ObjectInfo, func() (*GetObjectReader, error)) error
+
+// verifyLockedReplica compares the actual data, never a sender's ETag or
+// checksum assertion. A peer may retransmit a protected version to update its
+// metadata, but may not replace its content. Call under the object write lock.
+func verifyLockedReplica(ctx context.Context, incoming, stored ObjectInfo, openIncoming, openStored func() (*GetObjectReader, error)) error {
+	if !enforceRetentionForDeletion(ctx, stored) {
+		return nil
+	}
+	locked := ObjectLocked{Bucket: stored.Bucket, Object: stored.Name, VersionID: stored.VersionID}
+	if storedObjectLockState(stored.UserDefined).complianceWouldWeaken(storedObjectLockState(incoming.UserDefined)) {
+		return locked
+	}
+	inSSEC, oldSSEC := crypto.SSEC.IsEncrypted(incoming.UserDefined), crypto.SSEC.IsEncrypted(stored.UserDefined)
+	if inSSEC != oldSSEC {
+		return locked
+	}
+	if inSSEC {
+		inSize, inErr := incoming.GetActualSize()
+		oldSize, oldErr := stored.GetActualSize()
+		if inErr != nil || oldErr != nil || inSize != oldSize {
+			return locked
+		}
+		// Without the customer key, compare ciphertext and its interpretation.
+		// Equal ciphertext with a changed seal or multipart framing is not the
+		// same object, even if the supplied ETag and size are unchanged.
+		for _, key := range []string{
+			crypto.MetaIV, crypto.MetaAlgorithm, crypto.MetaSealedKeySSEC,
+			ReservedMetadataPrefix + "compression",
+		} {
+			if incoming.UserDefined[key] != stored.UserDefined[key] {
+				return locked
+			}
+		}
+		if crypto.IsMultiPart(incoming.UserDefined) != crypto.IsMultiPart(stored.UserDefined) || incoming.isMultipart() != stored.isMultipart() {
+			return locked
+		}
+		if crypto.IsMultiPart(incoming.UserDefined) {
+			if len(incoming.Parts) != len(stored.Parts) {
+				return locked
+			}
+			for i, p := range incoming.Parts {
+				old := stored.Parts[i]
+				if p.Number != old.Number || p.Size != old.Size {
+					return locked
+				}
+			}
+		}
+	}
+	in, err := openIncoming()
+	if err != nil {
+		return err
+	}
+	defer in.Close()
+	old, err := openStored()
+	if err != nil {
+		return err
+	}
+	defer old.Close()
+	ih, oh := sha256.New(), sha256.New()
+	inSize, err := io.Copy(ih, in)
+	if err != nil {
+		return err
+	}
+	oldSize, err := io.Copy(oh, old)
+	if err != nil {
+		return err
+	}
+	if inSize != oldSize || !bytes.Equal(ih.Sum(nil), oh.Sum(nil)) {
+		return locked
+	}
+	return nil
+}
+
+func (er erasureObjects) guardReplicaContent(ctx context.Context, bucket, object string, incoming ObjectInfo, openIncoming func() (*GetObjectReader, error)) error {
+	opts := ObjectOptions{VersionID: incoming.VersionID, NoLock: true, NoAuditLog: true, ReplicationRequest: true}
+	if opts.VersionID == "" {
+		opts.VersionID = nullVersionID
+	}
+	stored, err := er.getObjectInfo(ctx, bucket, object, opts)
+	if isErrObjectNotFound(err) || isErrVersionNotFound(err) || isErrMethodNotAllowed(err) {
+		return nil
+	}
+	if err != nil {
+		return err
+	}
+	return verifyLockedReplica(ctx, incoming, stored, openIncoming, func() (*GetObjectReader, error) {
+		return er.GetObjectNInfo(ctx, bucket, object, nil, http.Header{}, opts)
+	})
+}
+
+func (z *erasureServerPools) guardReplicaContent(ctx context.Context, bucket, object string, incoming ObjectInfo, openIncoming func() (*GetObjectReader, error)) error {
+	opts := ObjectOptions{VersionID: incoming.VersionID, NoLock: true, NoAuditLog: true, ReplicationRequest: true}
+	if opts.VersionID == "" {
+		opts.VersionID = nullVersionID
+	}
+	copies, err := z.objectPoolInfos(ctx, bucket, object, opts)
+	if isErrObjectNotFound(err) || isErrVersionNotFound(err) {
+		return nil
+	}
+	if err != nil {
+		return err
+	}
+	for _, copy := range copies {
+		if err := verifyLockedReplica(ctx, incoming, copy.ObjInfo, openIncoming, func() (*GetObjectReader, error) {
+			return z.serverPools[copy.Index].GetObjectNInfo(ctx, bucket, object, nil, http.Header{}, opts)
+		}); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// checkReplicaContent reads the staged version before rename commits it. Its
+// data is decoded/decrypted just like a GET (raw ciphertext for SSE-C), so this
+// covers multipart, compression and destination SSE-S3/KMS re-encryption.
+// disks and metadata are in erasure shard order, as passed to renameData.
+func (er erasureObjects) checkReplicaContent(ctx context.Context, bucket, object, stageBucket, stageObject string, metadata []FileInfo, disks []StorageAPI, opts ObjectOptions) error {
+	if (!opts.ReplicaLockReconcile && !opts.ReplicationRequest) || opts.DataMovement {
+		return nil
+	}
+	var fi FileInfo
+	for i, disk := range disks {
+		if disk != nil {
+			fi = metadata[i]
+			break
+		}
+	}
+	incoming := fi.ToObjectInfo(bucket, object, opts.Versioned || opts.VersionSuspended)
+	guard := opts.replicaContentGuard
+	if guard == nil {
+		guard = er.guardReplicaContent
+	}
+	return guard(ctx, bucket, object, incoming, func() (*GetObjectReader, error) {
+		// A marker-only peer write does not reconcile the stored protection.
+		// It therefore cannot replace a protected version, even with equal data.
+		if !opts.ReplicaLockReconcile {
+			return nil, ObjectLocked{Bucket: bucket, Object: decodeDirObject(object), VersionID: incoming.VersionID}
+		}
+		if incoming.IsCompressed() {
+			// A replica may assert the source's logical size. A compressed GET
+			// limits its output to that size, so verify it against the lengths
+			// recorded while consuming the uploaded parts before comparing GETs.
+			// Otherwise a forged zero size could hide a non-empty replacement.
+			var actual int64
+			for _, part := range incoming.Parts {
+				actual += part.ActualSize
+			}
+			declared, err := incoming.GetActualSize()
+			if err != nil || declared != actual {
+				return nil, ObjectLocked{Bucket: bucket, Object: decodeDirObject(object), VersionID: incoming.VersionID}
+			}
+		}
+		readOpts := ObjectOptions{NoDecryption: crypto.SSEC.IsEncrypted(incoming.UserDefined)}
+		fn, off, length, err := NewGetObjectReader(nil, incoming, readOpts, http.Header{})
+		if err != nil {
+			return nil, err
+		}
+		// The ordinary reader expects original drive order, not shard order.
+		readDisks, readMeta := make([]StorageAPI, len(disks)), make([]FileInfo, len(metadata))
+		for i, shard := range fi.Erasure.Distribution {
+			readDisks[i], readMeta[i] = disks[shard-1], metadata[shard-1]
+			readMeta[i].Erasure.Index = shard
+		}
+		pr, pw := xioutil.WaitPipe()
+		go func() {
+			pw.CloseWithError(er.getObjectWithFileInfo(ctx, stageBucket, stageObject, off, length, pw, fi, readMeta, readDisks))
+		}()
+		reader, err := fn(pr, http.Header{}, func() { pr.CloseWithError(nil) })
+		if err != nil {
+			pr.CloseWithError(err)
+		}
+		return reader, err
+	})
+}

cmd/replica-content_test.go

@@ -0,0 +1,314 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"encoding/xml"
+	"fmt"
+	"io"
+	"maps"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strconv"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/minio/internal/crypto"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/minio/minio/internal/kms"
+)
+
+func TestAPIReplicaPreservesProtectedContent(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			oldTLS, oldKMS := globalIsTLS, GlobalKMS
+			globalIsTLS, GlobalKMS = true, kms.NewStub("replica-content")
+			defer func() { globalIsTLS, GlobalKMS = oldTLS, oldKMS }()
+			restoreCompression := disableCompression()
+			defer restoreCompression()
+			request := func(method, url string, data []byte, headers map[string]string) *httptest.ResponseRecorder {
+				t.Helper()
+				req, err := newTestSignedRequestV4(method, url, int64(len(data)), bytes.NewReader(data), cred.AccessKey, cred.SecretKey, headers)
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				return rec
+			}
+			for _, encryption := range []string{"plain", "sse-s3", "sse-kms", "sse-c", "plain-compressed", "sse-s3-compressed"} {
+				restore := func() {}
+				if strings.HasSuffix(encryption, "-compressed") {
+					restore = setCopyChecksumCompression(true)
+				}
+				for _, multipart := range []bool{false, true} {
+					for _, protection := range []string{"COMPLIANCE", "LEGALHOLD", "GOVERNANCE"} {
+						key := fmt.Sprintf("protected/%s/%v/%s.txt", encryption, multipart, protection)
+						enc := map[string]string{}
+						switch encryption {
+						case "sse-s3", "sse-s3-compressed":
+							enc[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionAES
+						case "sse-kms":
+							enc[xhttp.AmzServerSideEncryption] = xhttp.AmzEncryptionKMS
+							enc[xhttp.AmzServerSideEncryptionKmsID] = "replica-content"
+						case "sse-c":
+							enc = ssecKeyHeaders(bytes.Repeat([]byte{0x37}, 32), false)
+						}
+						headers := maps.Clone(enc)
+						maps.Copy(headers, batchLockMeta(protection))
+						// Both inline and disk-backed writes are exercised.
+						body := bytes.Repeat([]byte("immutable content "), 20000)
+						switch protection {
+						case "LEGALHOLD":
+							body = body[:64]
+						case "GOVERNANCE":
+							body = nil
+						}
+						if !multipart {
+							putCopyChecksumSource(t, router, cred, bucket, key, body, headers)
+						} else {
+							initRec := request(http.MethodPost, getNewMultipartURL("", bucket, key), nil, headers)
+							if initRec.Code != http.StatusOK {
+								t.Fatalf("source initiate: %d %s", initRec.Code, initRec.Body.String())
+							}
+							var init InitiateMultipartUploadResponse
+							if err := xml.Unmarshal(initRec.Body.Bytes(), &init); err != nil {
+								t.Fatal(err)
+							}
+							part := request(http.MethodPut, getPutObjectPartURL("", bucket, key, init.UploadID, "1"), body, enc)
+							if part.Code != http.StatusOK {
+								t.Fatalf("source part: %d %s", part.Code, part.Body.String())
+							}
+							complete, err := xml.Marshal(CompleteMultipartUpload{Parts: []CompletePart{{PartNumber: 1, ETag: canonicalizeETag(part.Header()[xhttp.ETag][0])}}})
+							if err != nil {
+								t.Fatal(err)
+							}
+							rec := request(http.MethodPost, getCompleteMultipartUploadURL("", bucket, key, init.UploadID), complete, enc)
+							if rec.Code != http.StatusOK {
+								t.Fatalf("source complete: %d %s", rec.Code, rec.Body.String())
+							}
+						}
+						gr, err := obj.GetObjectNInfo(t.Context(), bucket, key, nil, http.Header{}, ObjectOptions{ReplicationRequest: true})
+						if err != nil {
+							t.Fatal(err)
+						}
+						src := gr.ObjInfo
+						wire, err := io.ReadAll(gr)
+						gr.Close()
+						if err != nil {
+							t.Fatal(err)
+						}
+						for _, altered := range []bool{true, false} {
+							data := bytes.Clone(wire)
+							if altered {
+								if len(data) == 0 {
+									data = []byte("x")
+								} else {
+									data[len(data)-1] ^= 0x20
+								}
+							}
+							opts, _, err := putReplicationOpts(t.Context(), "", src)
+							if err != nil {
+								t.Fatal(err)
+							}
+							hdrs := map[string]string{}
+							for k, vs := range opts.Header() {
+								if len(vs) > 0 {
+									hdrs[k] = vs[0]
+								}
+							}
+							hdrs[xhttp.MinIOSourceReplicationRequest] = "true"
+							hdrs[xhttp.AmzBucketReplicationStatus] = "REPLICA"
+							// Forge the old ETag and size along with a newer tag revision:
+							// the body comparison must still reject different bytes.
+							hdrs[xhttp.MinIOSourceETag] = src.ETag
+							hdrs[xhttp.MinIOSourceTaggingTimestamp] = UTCNow().Add(time.Minute).Format(time.RFC3339Nano)
+							hdrs[xhttp.AmzObjectTagging] = "replica=updated"
+							var rec *httptest.ResponseRecorder
+							if !multipart {
+								rec = request(http.MethodPut, getPutObjectURL("", bucket, key)+"?versionId="+src.VersionID, data, hdrs)
+							} else {
+								initRec := request(http.MethodPost, getNewMultipartURL("", bucket, key)+"&versionId="+src.VersionID, nil, hdrs)
+								if initRec.Code != http.StatusOK {
+									t.Fatalf("%s %s initiate: %d %s", backend, key, initRec.Code, initRec.Body.String())
+								}
+								var init InitiateMultipartUploadResponse
+								if err := xml.Unmarshal(initRec.Body.Bytes(), &init); err != nil {
+									t.Fatal(err)
+								}
+								partHdrs := map[string]string{xhttp.MinIOSourceReplicationRequest: "true"}
+								partRec := request(http.MethodPut, getPutObjectPartURL("", bucket, key, init.UploadID, "1"), data, partHdrs)
+								if partRec.Code != http.StatusOK && (!altered || !strings.Contains(partRec.Body.String(), "XMinioObjectTampered")) {
+									t.Fatalf("%s %s part: %d %s", backend, key, partRec.Code, partRec.Body.String())
+								}
+								if partRec.Code != http.StatusOK {
+									rec = partRec
+								} else {
+									complete, err := xml.Marshal(CompleteMultipartUpload{Parts: []CompletePart{{PartNumber: 1, ETag: canonicalizeETag(partRec.Header()[xhttp.ETag][0])}}})
+									if err != nil {
+										t.Fatal(err)
+									}
+									actual, err := src.GetActualSize()
+									if err != nil {
+										t.Fatal(err)
+									}
+									partHdrs[xhttp.MinIOReplicationActualObjectSize] = strconv.FormatInt(actual, 10)
+									rec = request(http.MethodPost, getCompleteMultipartUploadURL("", bucket, key, init.UploadID), complete, partHdrs)
+								}
+							}
+							if altered {
+								if rec.Code < 400 || !strings.Contains(rec.Body.String(), "WORM") && !strings.Contains(rec.Body.String(), "XMinioObjectTampered") {
+									t.Fatalf("%s %s: different content not refused: %d %s", backend, key, rec.Code, rec.Body.String())
+								}
+							} else if rec.Code != http.StatusOK {
+								t.Fatalf("%s %s: same content refused: %d %s", backend, key, rec.Code, rec.Body.String())
+							}
+							getHdrs := map[string]string{}
+							if encryption == "sse-c" {
+								getHdrs = enc
+							}
+							got := request(http.MethodGet, getGetObjectURL("", bucket, key)+"?versionId="+src.VersionID, nil, getHdrs)
+							if got.Code != http.StatusOK || !bytes.Equal(got.Body.Bytes(), body) {
+								t.Fatalf("%s %s: protected content changed or became unreadable: %d", backend, key, got.Code)
+							}
+						}
+					}
+				}
+				restore()
+			}
+		},
+	})
+}
+
+func TestPoolsReplicaProtectedContentAcrossPools(t *testing.T) {
+	z, bucket := consistencyPools(t)
+	const key = "protected-across-pools"
+	id := mustGetUUID()
+	stamp := UTCNow().Add(-time.Hour)
+	putConsistencyObject(t, z, bucket, key, 0, "original", ObjectOptions{Versioned: true, VersionID: id, MTime: stamp})
+	putConsistencyObject(t, z, bucket, key, 1, "original", ObjectOptions{Versioned: true, VersionID: id, MTime: stamp, UserDefined: batchLockMeta("COMPLIANCE")})
+	_, err := z.PutObject(t.Context(), bucket, key, mustGetPutObjReader(t, strings.NewReader("tampered"), 8, "", ""), ObjectOptions{Versioned: true, VersionID: id, ReplicationRequest: true, ReplicaLockReconcile: true, UserDefined: map[string]string{}})
+	if _, ok := err.(ObjectLocked); !ok {
+		t.Fatalf("protected pool copy allowed overwrite: %v", err)
+	}
+	for i, pool := range z.serverPools {
+		gr, err := pool.GetObjectNInfo(t.Context(), bucket, key, nil, http.Header{}, ObjectOptions{VersionID: id})
+		if err != nil {
+			t.Fatal(err)
+		}
+		data, err := io.ReadAll(gr)
+		gr.Close()
+		if err != nil || string(data) != "original" {
+			t.Fatalf("pool %d: changed protected data: %q %v", i, data, err)
+		}
+	}
+}
+
+func TestLockedSSECReplicaRejectsChangedSeal(t *testing.T) {
+	stored := ObjectInfo{Bucket: "bucket", Name: "key", Size: 0, UserDefined: batchLockMeta("LEGALHOLD")}
+	stored.UserDefined[crypto.MetaSealedKeySSEC] = "stored-seal"
+	incoming := stored
+	incoming.UserDefined = maps.Clone(stored.UserDefined)
+	incoming.UserDefined[crypto.MetaSealedKeySSEC] = "changed-seal"
+	open := func() (*GetObjectReader, error) {
+		t.Fatal("changed seal must be rejected before reading")
+		return nil, nil
+	}
+	if err := verifyLockedReplica(t.Context(), incoming, stored, open, open); err == nil {
+		t.Fatal("changed SSE-C seal accepted")
+	}
+}
+
+func TestAPIReplicaCopyPreservesProtectedVersion(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			const key = "copy-protected-version"
+			original := batchPutVersion(t, obj, bucket, key, batchLockMeta("COMPLIANCE"))
+			data := []byte("different source version")
+			source, err := obj.PutObject(t.Context(), bucket, key, mustGetPutObjReader(t, bytes.NewReader(data), int64(len(data)), "", ""), ObjectOptions{Versioned: true})
+			if err != nil {
+				t.Fatal(err)
+			}
+			headers := map[string]string{
+				xhttp.AmzCopySource:                 url.QueryEscape("/"+bucket+"/"+key) + "?versionId=" + source.VersionID,
+				xhttp.MinIOSourceReplicationRequest: "true", xhttp.AmzBucketReplicationStatus: "REPLICA",
+				xhttp.AmzMetadataDirective: replaceDirective,
+			}
+			req, err := newTestSignedRequestV4(http.MethodPut, getCopyObjectURL("", bucket, key)+"?versionId="+original.VersionID, 0, nil, cred.AccessKey, cred.SecretKey, headers)
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec := httptest.NewRecorder()
+			router.ServeHTTP(rec, req)
+			if rec.Code < 400 || !strings.Contains(rec.Body.String(), "WORM") {
+				t.Fatalf("%s: copy replaced protected version: %d %s", backend, rec.Code, rec.Body.String())
+			}
+			gr, err := obj.GetObjectNInfo(t.Context(), bucket, key, nil, http.Header{}, ObjectOptions{VersionID: original.VersionID})
+			if err != nil {
+				t.Fatal(err)
+			}
+			got, err := io.ReadAll(gr)
+			gr.Close()
+			if err != nil || string(got) != "batch lock "+key {
+				t.Fatalf("%s: protected body changed: %q %v", backend, got, err)
+			}
+		},
+	})
+}
+
+func TestAPIReplicaCannotWeakenCompliance(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			const key = "compliance-removal"
+			oi := batchPutVersion(t, obj, bucket, key, batchLockMeta("COMPLIANCE"))
+			until := oi.UserDefined[strings.ToLower(xhttp.AmzObjectLockRetainUntilDate)]
+			for _, copyRequest := range []bool{false, true} {
+				headers := map[string]string{xhttp.MinIOSourceReplicationRequest: "true", xhttp.AmzBucketReplicationStatus: "REPLICA", xhttp.MinIOSourceObjectRetentionTimestamp: UTCNow().Add(time.Hour).Format(time.RFC3339Nano)}
+				body := []byte("batch lock " + key)
+				if copyRequest {
+					headers[xhttp.AmzCopySource] = url.QueryEscape("/"+bucket+"/"+key) + "?versionId=" + oi.VersionID
+					headers[xhttp.AmzMetadataDirective] = replaceDirective
+					body = nil
+				}
+				req, err := newTestSignedRequestV4(http.MethodPut, getPutObjectURL("", bucket, key)+"?versionId="+oi.VersionID, int64(len(body)), bytes.NewReader(body), cred.AccessKey, cred.SecretKey, headers)
+				if err != nil {
+					t.Fatal(err)
+				}
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				if rec.Code != http.StatusOK {
+					t.Fatalf("%s copy=%v: %d %s", backend, copyRequest, rec.Code, rec.Body.String())
+				}
+				stored, err := obj.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: oi.VersionID})
+				if err != nil || stored.UserDefined[strings.ToLower(xhttp.AmzObjectLockMode)] != "COMPLIANCE" || stored.UserDefined[strings.ToLower(xhttp.AmzObjectLockRetainUntilDate)] != until {
+					t.Fatalf("%s copy=%v: a replica cleared COMPLIANCE: %+v %v", backend, copyRequest, stored.UserDefined, err)
+				}
+			}
+		},
+	})
+}

cmd/replication-signed-headers_test.go

@@ -0,0 +1,94 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"bytes"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/minio/minio/internal/auth"
+	xhttp "github.com/minio/minio/internal/http"
+)
+
+func TestReplicationControlsRequireSignedHeaders(t *testing.T) {
+	for _, header := range replicationRequestHeaders {
+		t.Run(header, func(t *testing.T) {
+			req, err := newTestSignedRequestV4(http.MethodGet, "http://localhost/bucket/key", 0, nil, "access-key", "secret-key", nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			// Membership matters even for a present-empty internal header.
+			req.Header.Set(header, "")
+			if replicationHeadersSigned(req) {
+				t.Fatal("unsigned control granted replication trust")
+			}
+			if err := signRequestV4(req, "access-key", "secret-key"); err != nil {
+				t.Fatal(err)
+			}
+			if !replicationHeadersSigned(req) {
+				t.Fatal("signed control rejected")
+			}
+		})
+	}
+	for _, authorization := range []string{"", "AWS access-key:signature", "Credential=access-key"} {
+		req := httptest.NewRequest(http.MethodGet, "/bucket/key", nil)
+		req.Header.Set(xhttp.Authorization, authorization)
+		req.Header.Set(xhttp.MinIOSourceReplicationRequest, "true")
+		if replicationHeadersSigned(req) {
+			t.Fatalf("non-SigV4 authorization granted trust: %q", authorization)
+		}
+	}
+	req := httptest.NewRequest(http.MethodGet, "http://localhost/bucket/key", nil)
+	req.Header.Set(xhttp.MinIOSourceReplicationRequest, "true")
+	presignBoundaryRequest(t, req, UTCNow(), []string{"host", "x-minio-source-replication-request"}, auth.Credentials{AccessKey: "access-key", SecretKey: "secret-key"})
+	getRequestAuthType(req)
+	if replicationHeadersSigned(req) {
+		t.Fatal("presigned request granted peer trust")
+	}
+}
+
+func TestAPIUnsignedReplicationControlsAreIgnored(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, endpoints: []string{"PutObject"},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			for _, signedMarker := range []bool{false, true} {
+				headers := map[string]string{}
+				if signedMarker {
+					headers[xhttp.MinIOSourceReplicationRequest] = "true"
+				}
+				body := []byte("replication controls are authenticated")
+				req, err := newTestSignedRequestV4(http.MethodPut, getPutObjectURL("", bucket, "key"), int64(len(body)), bytes.NewReader(body), cred.AccessKey, cred.SecretKey, headers)
+				if err != nil {
+					t.Fatal(err)
+				}
+				req.Header.Set(xhttp.MinIOSourceReplicationRequest, "true")
+				req.Header.Set(xhttp.MinIOSourceMTime, "2100-01-01T00:00:00Z")
+				req.Header.Set(xhttp.MinIOSourceETag, "forged-source-etag")
+				rec := httptest.NewRecorder()
+				router.ServeHTTP(rec, req)
+				oi, err := obj.GetObjectInfo(t.Context(), bucket, "key", ObjectOptions{})
+				if rec.Code != http.StatusOK || err != nil || oi.ModTime.Year() == 2100 || oi.ETag == "forged-source-etag" {
+					t.Fatalf("%s signedMarker=%v: unsigned replication state was accepted: HTTP=%d info=%+v err=%v", backend, signedMarker, rec.Code, oi, err)
+				}
+			}
+		},
+	})
+}

cmd/replication-ssec-retransmit_test.go

@@ -1850,6 +1850,12 @@ func testReplicaLockReconcileNullVersion(obj ObjectLayer, instanceType, bucketNa
 	_ http.Handler, _ auth.Credentials, t *testing.T,
 ) {
 	ctx := t.Context()
+	// A protected retransmit must preserve both the source ciphertext and
+	// its seal. Generate it once for the stored null version and its retry.
+	var ciphertext bytes.Buffer
+	if _, err := sio.Encrypt(&ciphertext, bytes.NewReader([]byte("data")), sio.Config{Key: bytes.Repeat([]byte{1}, 32)}); err != nil {
+		t.Fatal(err)
+	}
 
 	// completeNullMPU runs an SSE-C replica multipart upload addressing the null
 	// version (VersionSuspended) carrying uploadLock, through the reconcile.
@@ -1861,13 +1867,6 @@ func testReplicaLockReconcileNullVersion(obj ObjectLayer, instanceType, bucketNa
 		if err != nil {
 			t.Fatal(err)
 		}
-		// PutObjectPart now validates the DARE stream length (#119). This
-		// object-layer fixture needs an encrypted body before it can exercise
-		// the completion-time null-version metadata reconciliation.
-		var ciphertext bytes.Buffer
-		if _, err := sio.Encrypt(&ciphertext, bytes.NewReader([]byte("data")), sio.Config{Key: bytes.Repeat([]byte{1}, 32)}); err != nil {
-			t.Fatal(err)
-		}
 		part, err := obj.PutObjectPart(ctx, bucketName, object, res.UploadID, 1,
 			mustGetPutObjReader(t, bytes.NewReader(ciphertext.Bytes()), int64(ciphertext.Len()), "", ""), ObjectOptions{})
 		if err != nil {
@@ -1884,8 +1883,9 @@ func testReplicaLockReconcileNullVersion(obj ObjectLayer, instanceType, bucketNa
 		object := "reconcile/null-vs-uuid"
 		// The null version holds a newer legal hold ON@10:00.
 		if _, err := obj.PutObject(ctx, bucketName, object,
-			mustGetPutObjReader(t, bytes.NewReader([]byte("data")), 4, "", ""),
+			mustGetPutObjReader(t, bytes.NewReader(ciphertext.Bytes()), int64(ciphertext.Len()), "", ""),
 			ObjectOptions{VersionSuspended: true, MTime: time.Date(2026, 9, 3, 10, 0, 0, 0, time.UTC), UserDefined: map[string]string{
+				crypto.MetaSealedKeySSEC:                                   "dummy-sealed-key",
 				strings.ToLower(xhttp.AmzObjectLockLegalHold):              "ON",
 				ReservedMetadataPrefixLower + ObjectLockLegalHoldTimestamp: objectLockTestStamp1000,
 			}}); err != nil {

cmd/replication-trust.go

@@ -13,6 +13,8 @@ package cmd
 import (
 	"context"
 	"net/http"
+	"slices"
+	"strings"
 
 	objectreplication "github.com/minio/minio/internal/bucket/replication"
 	xhttp "github.com/minio/minio/internal/http"
@@ -62,7 +64,7 @@ func isReplicaTrusted(ctx context.Context) bool {
 // grant must not turn client-controlled internal headers into trusted state.
 func replicationPermissionAllowed(ctx context.Context, r *http.Request, bucket, object string, action policy.Action) bool {
 	reqInfo := logger.GetReqInfo(ctx)
-	if reqInfo == nil || reqInfo.Cred.AccessKey == "" {
+	if reqInfo == nil || reqInfo.Cred.AccessKey == "" || !replicationHeadersSigned(r) {
 		return false
 	}
 	reqInfo.BucketName = bucket
@@ -70,6 +72,25 @@ func replicationPermissionAllowed(ctx context.Context, r *http.Request, bucket,
 	return authorizeRequest(ctx, r, action) == ErrNone
 }
 
+// replicationHeadersSigned binds every internal control to the authenticated
+// header signature. Query grants and SigV2 requests cannot confer peer trust.
+// Call only after the request's signature has been verified.
+func replicationHeadersSigned(r *http.Request) bool {
+	if !isRequestSignatureV4(r) || isRequestPresignedSignatureV4(r) {
+		return false
+	}
+	sig, errCode := parseSignV4(r.Header.Get(xhttp.Authorization), globalSite.Region(), serviceS3)
+	if errCode != ErrNone {
+		return false
+	}
+	for _, name := range replicationRequestHeaders {
+		if _, present := r.Header[http.CanonicalHeaderKey(name)]; present && !slices.Contains(sig.SignedHeaders, strings.ToLower(name)) {
+			return false
+		}
+	}
+	return true
+}
+
 // evaluateReplicationTrust decides whether a request may carry replication
 // semantics for the given action. A request that declares itself a replica
 // without holding the replication permission is rejected. trusted reports that

cmd/restore-revision-flags_test.go

@@ -0,0 +1,141 @@
+// Copyright (c) 2026 Feng Ruohang
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"errors"
+	"testing"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/bucket/lifecycle"
+	"github.com/minio/minio/internal/bucket/versioning"
+	xhttp "github.com/minio/minio/internal/http"
+)
+
+func TestVersionRevisionRestoreFlags(t *testing.T) {
+	base := authorityRevision(t, [16]byte{1}, 1, 1, "")
+	cleared := base
+	cleared.header.Flags &^= xlFlagUsesDataDir
+	set := base
+	set.header.Flags |= xlFlagUsesDataDir
+	if versionRevision(cleared, xlMetaVersion) != versionRevision(set, xlMetaVersion) {
+		t.Fatal("derived flag splits one revision")
+	}
+	for _, change := range []struct {
+		name  string
+		apply func(*xlMetaV2Object)
+	}{
+		{"data-dir", func(o *xlMetaV2Object) { o.DataDir[0]++ }},
+		{"restore", func(o *xlMetaV2Object) { o.MetaUser[xhttp.AmzRestore] = `ongoing-request="true"` }},
+		{"retention", func(o *xlMetaV2Object) { o.MetaUser["x-amz-object-lock-mode"] = "COMPLIANCE" }},
+		{"layout", func(o *xlMetaV2Object) { o.ErasureM, o.ErasureN = 8, 8 }},
+	} {
+		t.Run(change.name, func(t *testing.T) {
+			var v xlMetaV2Version
+			if _, err := v.unmarshalV(xlMetaVersion, base.meta); err != nil {
+				t.Fatal(err)
+			}
+			change.apply(v.ObjectV2)
+			meta, err := v.MarshalMsg(nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+			different := xlMetaV2ShallowVersion{header: cleared.header, meta: meta}
+			if versionRevision(different, xlMetaVersion) == versionRevision(set, xlMetaVersion) {
+				t.Fatal("real metadata change lost")
+			}
+		})
+	}
+	// Every other header flag remains part of identity, even if metadata is equal.
+	for flag := xlFlags(1); flag != 0; flag <<= 1 {
+		if flag == xlFlagUsesDataDir {
+			continue
+		}
+		other := base
+		other.header.Flags ^= flag
+		if versionRevision(other, xlMetaVersion) == versionRevision(base, xlMetaVersion) {
+			t.Fatalf("flag %d was normalized", flag)
+		}
+	}
+	malformed := base
+	malformed.meta = []byte{0xc1}
+	other := malformed
+	other.header.Flags ^= xlFlagUsesDataDir
+	if versionRevision(malformed, xlMetaVersion) == versionRevision(other, xlMetaVersion) {
+		t.Fatal("undecodable metadata was normalized")
+	}
+	marker := authorityMarker(t, [16]byte{2}, 2)
+	other = marker
+	other.header.Flags ^= xlFlagUsesDataDir
+	if versionRevision(marker, xlMetaVersion) == versionRevision(other, xlMetaVersion) {
+		t.Fatal("delete marker was normalized as an object")
+	}
+}
+
+// Two drives are replaced one at a time after the restore expires. The old
+// headers describe the pre-expiry state; heal writes the current derived flag.
+func TestRestoreExpiryAcrossSuccessiveHeals(t *testing.T) {
+	r := newRestoreSafetyTest(t, 2, versioning.Enabled)
+	ctx := t.Context()
+	oi := r.put("restored", false, true)
+	r.restore(oi)
+	before := r.fileInfo(oi.VersionID)
+	disks := r.z.serverPools[0].getHashedSet(r.object).getDisks()
+	// Model the headers written before wall-clock expiry without a timing race.
+	for _, disk := range disks {
+		rewriteTierTestMeta(t, disk, r.bucket, r.object, func(xl *xlMetaV2) { xl.versions[0].header.Flags |= xlFlagUsesDataDir })
+	}
+	for _, i := range []int{3, 2} {
+		if err := disks[i].Delete(ctx, r.bucket, r.object, DeleteOptions{Recursive: true, Immediate: true}); err != nil {
+			t.Fatal(err)
+		}
+		if _, err := r.z.HealObject(ctx, r.bucket, r.object, oi.VersionID, madmin.HealOpts{ScanMode: madmin.HealNormalScan}); err != nil {
+			t.Fatal(err)
+		}
+	}
+	for i, disk := range disks {
+		raw, err := disk.ReadXL(ctx, r.bucket, r.object, false)
+		if err != nil {
+			t.Fatal(err)
+		}
+		var xl xlMetaV2
+		if err = xl.Load(raw.Buf); err != nil {
+			t.Fatal(err)
+		}
+		if got := xl.versions[0].header.Flags&xlFlagUsesDataDir != 0; got != (i < 2) {
+			t.Fatalf("drive %d has unexpected derived flag %v", i, got)
+		}
+	}
+	if _, _, err := r.z.lifecycleEventsAllPools(ctx, r.bucket, r.object); err != nil {
+		t.Fatalf("history with split flags: %v", err)
+	}
+	current, err := r.z.GetObjectInfo(ctx, r.bucket, r.object, r.opts(oi.VersionID))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err = expireTransitionedObject(ctx, r.z, &current, lifecycle.Event{Action: lifecycle.DeleteRestoredAction}, lcEventSrc_Scanner); err != nil {
+		t.Fatalf("expire restored copy: %v", err)
+	}
+	if n := r.dataDirs(before.DataDir); n != 0 {
+		t.Fatalf("restore cleanup left %d data directories", n)
+	}
+	if got := readCopyChecksumObject(t, r.z, r.bucket, r.object, r.opts(oi.VersionID)); string(got) != string(r.bodies["restored"]) {
+		t.Fatal("tiered object is no longer readable")
+	}
+	r.put("newer", false, false)
+	if _, _, err = r.z.lifecycleEventsAllPools(ctx, r.bucket, r.object); err != nil {
+		t.Fatal(err)
+	}
+	if _, err = r.z.deleteAllHistory(ctx, r.bucket, r.object); err != nil {
+		t.Fatalf("purge history with split flags: %v", err)
+	}
+	// The rule permits tiering, not a purge. Normalizing the header must not
+	// turn a readable history into permission to remove the versions.
+	if _, err = r.z.DeleteObject(ctx, r.bucket, r.object, ObjectOptions{DeleteAllVersions: true, Expiration: ExpirationOptions{Expire: true}}); !errors.Is(err, errLifecycleNotApplicable) {
+		t.Fatalf("purge without an applicable rule: %v", err)
+	}
+	if _, err = r.z.GetObjectInfo(ctx, r.bucket, r.object, r.opts(oi.VersionID)); err != nil {
+		t.Fatalf("refused purge removed the tiered version: %v", err)
+	}
+}

cmd/restore-stage.go

@@ -320,11 +320,8 @@ func (er erasureObjects) stageRestore(ctx context.Context, bucket, object string
 
 // fileInfoRevisions are the revisions the entry that writing fi creates can
 // have, as readRestoreGeneration and the convergence identify the entries
-// they read. The header flag that tells whether a transitioned version uses
-// its data directory follows whether its restored copy has expired at the
-// moment a drive writes the entry, so a restore whose copy expires while it
-// publishes can find either value: both are this entry. Every other field of
-// the header and the full metadata digest still have to match.
+// they read. versionRevision normalizes the time-derived UsesDataDir flag;
+// the stored data directory and restore metadata still have to match.
 func fileInfoRevisions(fi FileInfo) ([]revisionKey, error) {
 	var x xlMetaV2
 	if err := x.AddVersion(fi); err != nil {
@@ -342,9 +339,7 @@ func fileInfoRevisions(fi FileInfo) ([]revisionKey, error) {
 		return nil, errFileCorrupt
 	}
 	ver := y.versions[0]
-	other := ver
-	other.header.Flags ^= xlFlagUsesDataDir
-	return []revisionKey{versionRevision(ver, y.metaV), versionRevision(other, y.metaV)}, nil
+	return []revisionKey{versionRevision(ver, y.metaV)}, nil
 }
 
 // restorePublication remembers, for a commit that published the staged copy

cmd/restore-two-phase_test.go

@@ -731,7 +731,7 @@ func TestRestorePublishedRevisionAcrossExpiry(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	stored := func() revisionKey {
+	stored := func() (xlMetaV2VersionHeader, revisionKey) {
 		var x xlMetaV2
 		if err := x.AddVersion(published); err != nil {
 			t.Fatal(err)
@@ -744,16 +744,19 @@ func TestRestorePublishedRevisionAcrossExpiry(t *testing.T) {
 		if err := y.Load(buf); err != nil {
 			t.Fatal(err)
 		}
-		return versionRevision(y.versions[0], y.metaV)
+		return y.versions[0].header, versionRevision(y.versions[0], y.metaV)
 	}
-	before := stored()
+	beforeHeader, before := stored()
 	time.Sleep(time.Until(expiry) + 100*time.Millisecond)
-	after := stored()
-	if before == after {
+	afterHeader, after := stored()
+	if beforeHeader.Flags == afterHeader.Flags {
 		t.Fatal("fixture: the stored flag did not change at the expiry")
 	}
+	if before != after {
+		t.Fatal("expiry changed the identity of the published revision")
+	}
 	for _, got := range []revisionKey{before, after} {
-		if got != keys[0] && got != keys[1] {
+		if got != keys[0] {
 			t.Errorf("a publication's own entry is not recognized: %v not in %v", got, keys)
 		}
 	}

cmd/s3-zip-handlers.go

@@ -28,10 +28,10 @@ import (
 	"sort"
 	"strings"
 
-	"github.com/minio/minio/internal/auth"
 	"github.com/minio/minio/internal/crypto"
 	xhttp "github.com/minio/minio/internal/http"
 	xioutil "github.com/minio/minio/internal/ioutil"
+	"github.com/minio/minio/internal/logger"
 	"github.com/minio/zipindex"
 	"github.com/pgsty/silo-pkg/v3/policy"
 )
@@ -82,35 +82,9 @@ func (api objectAPIHandlers) getObjectInArchiveFileHandler(ctx context.Context,
 
 	getObjectInfo := objectAPI.GetObjectInfo
 
-	// Check for auth type to return S3 compatible error.
-	// type to return the correct error (NoSuchKey vs AccessDenied)
-	if s3Error := checkRequestAuthType(ctx, r, policy.GetObjectAction, bucket, zipPath); s3Error != ErrNone {
-		if getRequestAuthType(r) == authTypeAnonymous {
-			// As per "Permission" section in
-			// https://docs.aws.amazon.com/AmazonS3/latest/API/RESTObjectGET.html
-			// If the object you request does not exist,
-			// the error Amazon S3 returns depends on
-			// whether you also have the s3:ListBucket
-			// permission.
-			// * If you have the s3:ListBucket permission
-			//   on the bucket, Amazon S3 will return an
-			//   HTTP status code 404 ("no such key")
-			//   error.
-			// * if you don’t have the s3:ListBucket
-			//   permission, Amazon S3 will return an HTTP
-			//   status code 403 ("access denied") error.`
-			if globalPolicySys.IsAllowed(policy.BucketPolicyArgs{
-				Action:          policy.ListBucketAction,
-				BucketName:      bucket,
-				ConditionValues: getConditionValues(r, "", auth.AnonymousCredentials),
-				IsOwner:         false,
-			}) {
-				_, err = getObjectInfo(ctx, bucket, zipPath, opts)
-				if toAPIError(ctx, err).Code == "NoSuchKey" {
-					s3Error = ErrNoSuchKey
-				}
-			}
-		}
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = zipPath
+	if s3Error := authenticateRequest(ctx, r, policy.GetObjectAction); s3Error != ErrNone {
 		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
 		return
 	}
@@ -128,6 +102,10 @@ func (api objectAPIHandlers) getObjectInArchiveFileHandler(ctx context.Context,
 
 	// Validate pre-conditions if any.
 	opts.CheckPrecondFn = func(oi ObjectInfo) bool {
+		if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, oi.UserTags); s3Error != ErrNone {
+			writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+			return true
+		}
 		if _, err := DecryptObjectInfo(&oi, r); err != nil {
 			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 			return true
@@ -138,19 +116,20 @@ func (api objectAPIHandlers) getObjectInArchiveFileHandler(ctx context.Context,
 
 	zipObjInfo, err := getObjectInfo(ctx, bucket, zipPath, opts)
 	if err != nil {
+		err = archiveReadError(ctx, r, bucket, zipPath, opts.VersionID, err)
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
 	}
+	if opts.CheckPrecondFn(zipObjInfo) {
+		return
+	}
 
 	zipInfo := zipObjInfo.ArchiveInfo(r.Header)
 	if len(zipInfo) == 0 {
-		opts.EncryptFn, err = zipObjInfo.metadataEncryptFn(r.Header)
-		if err != nil {
-			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
-			return
-		}
-
-		zipInfo, err = updateObjectMetadataWithZipInfo(ctx, objectAPI, bucket, zipPath, opts)
+		zipInfo, _, err = readObjectZIPInfo(ctx, objectAPI, bucket, zipPath, opts)
+	}
+	if isErrPreconditionFailed(err) {
+		return
 	}
 	if err != nil {
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
@@ -183,6 +162,9 @@ func (api objectAPIHandlers) getObjectInArchiveFileHandler(ctx context.Context,
 		end := min(file.Offset+int64(file.CompressedSize64)+64<<10, zipObjInfo.Size)
 		rs := &HTTPRangeSpec{Start: file.Offset, End: end}
 		gr, err := objectAPI.GetObjectNInfo(ctx, bucket, zipPath, rs, nil, opts)
+		if isErrPreconditionFailed(err) {
+			return
+		}
 		if err != nil {
 			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 			return
@@ -199,6 +181,7 @@ func (api objectAPIHandlers) getObjectInArchiveFileHandler(ctx context.Context,
 
 	defer rc.Close()
 
+	opts.Tagging = false
 	if err = setObjectHeaders(ctx, w, fileObjInfo, nil, opts); err != nil {
 		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
 		return
@@ -230,23 +213,40 @@ func (api objectAPIHandlers) getObjectInArchiveFileHandler(ctx context.Context,
 }
 
 // listObjectsV2InArchive generates S3 listing result ListObjectsV2Info from zip file, all parameters are already validated by the caller.
-func listObjectsV2InArchive(ctx context.Context, objectAPI ObjectLayer, bucket, prefix, token, delimiter string, maxKeys int, startAfter string, h http.Header) (ListObjectsV2Info, error) {
+func listObjectsV2InArchive(ctx context.Context, objectAPI ObjectLayer, bucket, prefix, token, delimiter string, maxKeys int, startAfter string, r *http.Request) (ListObjectsV2Info, error) {
 	zipPath, _, err := splitZipExtensionPath(prefix)
 	if err != nil {
 		// Return empty listing
 		return ListObjectsV2Info{}, nil
 	}
 
-	zipObjInfo, err := objectAPI.GetObjectInfo(ctx, bucket, zipPath, ObjectOptions{})
+	// The bucket listing permission does not grant access to ZIP contents.
+	logger.GetReqInfo(ctx).ObjectName = zipPath
+	opts := ObjectOptions{}
+	zipObjInfo, err := objectAPI.GetObjectInfo(ctx, bucket, zipPath, opts)
 	if err != nil {
-		// Return empty listing
-		return ListObjectsV2Info{}, nil
+		if s3Error := authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, "", err); s3Error != ErrNone {
+			return ListObjectsV2Info{}, PrefixAccessDenied{Bucket: bucket, Object: zipPath}
+		}
+		if isErrObjectNotFound(err) {
+			return ListObjectsV2Info{}, nil
+		}
+		return ListObjectsV2Info{}, err
 	}
-
-	zipInfo := zipObjInfo.ArchiveInfo(h)
+	if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, "", zipObjInfo.UserTags); s3Error != ErrNone {
+		return ListObjectsV2Info{}, PrefixAccessDenied{Bucket: bucket, Object: zipPath}
+	}
+	var denied bool
+	opts.CheckPrecondFn = func(oi ObjectInfo) bool {
+		denied = authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, "", oi.UserTags) != ErrNone
+		return denied
+	}
+	zipInfo := zipObjInfo.ArchiveInfo(r.Header)
 	if len(zipInfo) == 0 {
-		// Always update the latest version
-		zipInfo, err = updateObjectMetadataWithZipInfo(ctx, objectAPI, bucket, zipPath, ObjectOptions{})
+		zipInfo, _, err = readObjectZIPInfo(ctx, objectAPI, bucket, zipPath, opts)
+	}
+	if denied {
+		return ListObjectsV2Info{}, PrefixAccessDenied{Bucket: bucket, Object: zipPath}
 	}
 	if err != nil {
 		return ListObjectsV2Info{}, err
@@ -379,42 +379,19 @@ func (api objectAPIHandlers) headObjectInArchiveFileHandler(ctx context.Context,
 		return
 	}
 
-	if s3Error := checkRequestAuthType(ctx, r, policy.GetObjectAction, bucket, zipPath); s3Error != ErrNone {
-		if getRequestAuthType(r) == authTypeAnonymous {
-			// As per "Permission" section in
-			// https://docs.aws.amazon.com/AmazonS3/latest/API/RESTObjectHEAD.html
-			// If the object you request does not exist,
-			// the error Amazon S3 returns depends on
-			// whether you also have the s3:ListBucket
-			// permission.
-			// * If you have the s3:ListBucket permission
-			//   on the bucket, Amazon S3 will return an
-			//   HTTP status code 404 ("no such key")
-			//   error.
-			// * if you don’t have the s3:ListBucket
-			//   permission, Amazon S3 will return an HTTP
-			//   status code 403 ("access denied") error.`
-			if globalPolicySys.IsAllowed(policy.BucketPolicyArgs{
-				Action:          policy.ListBucketAction,
-				BucketName:      bucket,
-				ConditionValues: getConditionValues(r, "", auth.AnonymousCredentials),
-				IsOwner:         false,
-			}) {
-				_, err = getObjectInfo(ctx, bucket, zipPath, opts)
-				if toAPIError(ctx, err).Code == "NoSuchKey" {
-					s3Error = ErrNoSuchKey
-				}
-			}
-		}
-		errCode := errorCodes.ToAPIErr(s3Error)
-		w.Header().Set(xMinIOErrCodeHeader, errCode.Code)
-		w.Header().Set(xMinIOErrDescHeader, "\""+errCode.Description+"\"")
-		writeErrorResponseHeadersOnly(w, errCode)
+	logger.GetReqInfo(ctx).BucketName = bucket
+	logger.GetReqInfo(ctx).ObjectName = zipPath
+	if s3Error := authenticateRequest(ctx, r, policy.GetObjectAction); s3Error != ErrNone {
+		writeErrorResponseHeadersOnly(w, errorCodes.ToAPIErr(s3Error))
 		return
 	}
 
 	// Validate pre-conditions if any.
 	opts.CheckPrecondFn = func(oi ObjectInfo) bool {
+		if s3Error := authorizeVersionedRequestWithExistingTags(ctx, r, policy.GetObjectAction, opts.VersionID, oi.UserTags); s3Error != ErrNone {
+			writeErrorResponseHeadersOnly(w, errorCodes.ToAPIErr(s3Error))
+			return true
+		}
 		return checkPreconditions(ctx, w, r, oi, opts)
 	}
 
@@ -431,18 +408,20 @@ func (api objectAPIHandlers) headObjectInArchiveFileHandler(ctx context.Context,
 
 	zipObjInfo, err := getObjectInfo(ctx, bucket, zipPath, opts)
 	if err != nil {
+		err = archiveReadError(ctx, r, bucket, zipPath, opts.VersionID, err)
 		writeErrorResponseHeadersOnly(w, toAPIError(ctx, err))
 		return
 	}
+	if opts.CheckPrecondFn(zipObjInfo) {
+		return
+	}
 
 	zipInfo := zipObjInfo.ArchiveInfo(r.Header)
 	if len(zipInfo) == 0 {
-		opts.EncryptFn, err = zipObjInfo.metadataEncryptFn(r.Header)
-		if err != nil {
-			writeErrorResponseHeadersOnly(w, toAPIError(ctx, err))
-			return
-		}
-		zipInfo, err = updateObjectMetadataWithZipInfo(ctx, objectAPI, bucket, zipPath, opts)
+		zipInfo, _, err = readObjectZIPInfo(ctx, objectAPI, bucket, zipPath, opts)
+	}
+	if isErrPreconditionFailed(err) {
+		return
 	}
 	if err != nil {
 		writeErrorResponseHeadersOnly(w, toAPIError(ctx, err))
@@ -466,6 +445,7 @@ func (api objectAPIHandlers) headObjectInArchiveFileHandler(ctx context.Context,
 		ModTime: zipObjInfo.ModTime,
 	}
 
+	opts.Tagging = false
 	// Set standard object headers.
 	if err = setObjectHeaders(ctx, w, objInfo, nil, opts); err != nil {
 		writeErrorResponseHeadersOnly(w, toAPIError(ctx, err))
@@ -482,15 +462,35 @@ func (api objectAPIHandlers) headObjectInArchiveFileHandler(ctx context.Context,
 	w.WriteHeader(http.StatusOK)
 }
 
-// Update the passed zip object metadata with the zip contents info, file name, modtime, size, etc.
-// The returned zip index will de decrypted.
-func updateObjectMetadataWithZipInfo(ctx context.Context, objectAPI ObjectLayer, bucket, object string, opts ObjectOptions) ([]byte, error) {
+// archiveReadError preserves the anonymous ListBucket missing-object response.
+// All other failures are disclosed only to callers authorized to read the ZIP.
+func archiveReadError(ctx context.Context, r *http.Request, bucket, object, versionID string, err error) error {
+	if getRequestAuthType(r) == authTypeAnonymous && isErrObjectNotFound(err) &&
+		authorizeBucketRequest(ctx, r, policy.ListBucketAction) == ErrNone {
+		return err
+	}
+	if authorizeVersionedRequestWithUnreadTags(ctx, r, policy.GetObjectAction, versionID, err) != ErrNone {
+		return PrefixAccessDenied{Bucket: bucket, Object: object}
+	}
+	return err
+}
+
+// readObjectZIPInfo builds an index without modifying the object. A GET, HEAD
+// or archive listing must remain read-only even when no index was stored.
+func readObjectZIPInfo(ctx context.Context, objectAPI ObjectLayer, bucket, object string, opts ObjectOptions) ([]byte, ObjectInfo, error) {
 	files, srcInfo, err := getFilesListFromZIPObject(ctx, objectAPI, bucket, object, opts)
 	if err != nil {
-		return nil, err
+		return nil, srcInfo, err
 	}
 	files.OptimizeSize()
 	zipInfo, err := files.Serialize()
+	return zipInfo, srcInfo, err
+}
+
+// updateObjectMetadataWithZipInfo persists an index only for upload operations
+// that explicitly request extraction. The returned index is decrypted.
+func updateObjectMetadataWithZipInfo(ctx context.Context, objectAPI ObjectLayer, bucket, object string, opts ObjectOptions) ([]byte, error) {
+	zipInfo, srcInfo, err := readObjectZIPInfo(ctx, objectAPI, bucket, object, opts)
 	if err != nil {
 		return nil, err
 	}
@@ -500,7 +500,6 @@ func updateObjectMetadataWithZipInfo(ctx context.Context, objectAPI ObjectLayer,
 		at = archiveTypeEnc
 		zipInfoStr = string(opts.EncryptFn(archiveTypeEnc, zipInfo))
 	}
-	srcInfo.UserDefined[archiveTypeMetadataKey] = at
 	popts := ObjectOptions{
 		MTime:     srcInfo.ModTime,
 		VersionID: srcInfo.VersionID,

cmd/s3-zip-readonly_test.go

@@ -0,0 +1,109 @@
+// Copyright (c) 2026 Feng Ruohang
+//
+// This file is part of Silo Object Storage stack
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"archive/zip"
+	"bytes"
+	"fmt"
+	"maps"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/minio/minio/internal/auth"
+)
+
+func TestAPIArchiveReadsDoNotPersistMetadata(t *testing.T) {
+	defer DetectTestLeak(t)()
+	ExecObjectLayerAPITest(ExecObjectLayerAPITestArgs{
+		t: t, makeBucketOptions: MakeBucketOptions{LockEnabled: true},
+		objAPITest: func(obj ObjectLayer, backend, bucket string, router http.Handler, cred auth.Credentials, t *testing.T) {
+			var archive bytes.Buffer
+			zw := zip.NewWriter(&archive)
+			file, err := zw.Create("entry.txt")
+			if err != nil {
+				t.Fatal(err)
+			}
+			if _, err = file.Write([]byte("archive content")); err != nil {
+				t.Fatal(err)
+			}
+			if err = zw.Close(); err != nil {
+				t.Fatal(err)
+			}
+			reader := newObjectAttributesAuthzUser(t, backend, bucket, `"s3:GetObject","s3:ListBucket"`)
+			policy := fmt.Appendf(nil, `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Principal":"*","Action":["s3:GetObject","s3:ListBucket"],"Resource":["arn:aws:s3:::%s","arn:aws:s3:::%s/*"]}]}`, bucket, bucket)
+			if _, err = globalBucketMetadataSys.Update(t.Context(), bucket, bucketPolicyConfig, policy); err != nil {
+				t.Fatal(err)
+			}
+			for _, anonymous := range []bool{false, true} {
+				for _, method := range []string{http.MethodGet, http.MethodHead, "LIST"} {
+					key := fmt.Sprintf("archive-%v-%s.zip", anonymous, method)
+					before, err := obj.PutObject(t.Context(), bucket, key, mustGetPutObjReader(t, bytes.NewReader(archive.Bytes()), int64(archive.Len()), "", ""), ObjectOptions{Versioned: true, UserDefined: batchLockMeta("COMPLIANCE")})
+					if err != nil {
+						t.Fatal(err)
+					}
+					before, err = obj.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: before.VersionID})
+					if err != nil {
+						t.Fatal(err)
+					}
+					url := getGetObjectURL("", bucket, key+"/entry.txt")
+					verb := method
+					if method == "LIST" {
+						verb = http.MethodGet
+						url = "/" + bucket + "?list-type=2&prefix=" + key + "/"
+					}
+					req, err := newTestSignedRequestV4(verb, url, 0, nil, reader.AccessKey, reader.SecretKey, map[string]string{xMinIOExtract: "true"})
+					if err != nil {
+						t.Fatal(err)
+					}
+					if anonymous {
+						req.Header.Del("Authorization")
+					}
+					rec := httptest.NewRecorder()
+					router.ServeHTTP(rec, req)
+					if rec.Code != http.StatusOK {
+						t.Fatalf("%s anonymous=%v %s: %d %s", backend, anonymous, method, rec.Code, rec.Body.String())
+					}
+					if method == http.MethodGet && rec.Body.String() != "archive content" {
+						t.Fatalf("wrong archive entry: %s", rec.Body.String())
+					}
+					if method == "LIST" && !bytes.Contains(rec.Body.Bytes(), []byte("entry.txt")) {
+						t.Fatal("archive listing omitted entry")
+					}
+					after, err := obj.GetObjectInfo(t.Context(), bucket, key, ObjectOptions{VersionID: before.VersionID})
+					if err != nil || !maps.Equal(before.UserDefined, after.UserDefined) || !after.ModTime.Equal(before.ModTime) || after.ETag != before.ETag {
+						t.Fatalf("%s anonymous=%v %s changed stored metadata: before=%v after=%v err=%v", backend, anonymous, method, before.UserDefined, after.UserDefined, err)
+					}
+				}
+			}
+			// Explicit extraction during an authorized upload still builds and
+			// persists the index for subsequent reads.
+			req, err := newTestSignedRequestV4(http.MethodPut, getPutObjectURL("", bucket, "indexed.zip"), int64(archive.Len()), bytes.NewReader(archive.Bytes()), cred.AccessKey, cred.SecretKey, map[string]string{xMinIOExtract: "true"})
+			if err != nil {
+				t.Fatal(err)
+			}
+			rec := httptest.NewRecorder()
+			router.ServeHTTP(rec, req)
+			oi, err := obj.GetObjectInfo(t.Context(), bucket, "indexed.zip", ObjectOptions{})
+			if rec.Code != http.StatusOK || err != nil || len(oi.ArchiveInfo(nil)) == 0 {
+				t.Fatalf("explicit extraction lost index: %d %s %v", rec.Code, rec.Body.String(), err)
+			}
+		},
+	})
+}

cmd/signature-v4.go

@@ -189,6 +189,16 @@ func doesPolicySignatureV4Match(formValues http.Header) (auth.Credentials, APIEr
 		return cred, s3Err
 	}
 
+	if dateStr := formValues.Get(xhttp.AmzDate); dateStr != "" {
+		t, err := time.Parse(iso8601Format, dateStr)
+		if err != nil {
+			return cred, ErrMalformedDate
+		}
+		if credHeader.scope.date.Format(yyyymmdd) != t.UTC().Format(yyyymmdd) {
+			return cred, ErrSignatureDoesNotMatch
+		}
+	}
+
 	// Get signing key.
 	signingKey := getSigningKey(cred.SecretKey, credHeader.scope.date, credHeader.scope.region, serviceS3)
 
@@ -248,6 +258,9 @@ func doesPresignedSignatureMatch(hashedPayload string, r *http.Request, region s
 
 	// Save the date and expires.
 	t := pSignValues.Date
+	if pSignValues.Credential.scope.date.Format(yyyymmdd) != t.UTC().Format(yyyymmdd) {
+		return ErrSignatureDoesNotMatch
+	}
 	expireSeconds := int(pSignValues.Expires / time.Second)
 
 	// Construct new query.
@@ -388,6 +401,9 @@ func doesSignatureMatch(hashedPayload string, r *http.Request, region string, st
 	if e != nil {
 		return ErrMalformedDate
 	}
+	if signV4Values.Credential.scope.date.Format(yyyymmdd) != t.UTC().Format(yyyymmdd) {
+		return ErrSignatureDoesNotMatch
+	}
 
 	// Query string.
 	queryStr := req.Form.Encode()

cmd/site-replication-metadata.go

@@ -126,9 +126,8 @@ func latestBucketConfig(bucket, file string, info srStatusInfo) (bucketConfigSta
 }
 
 func (c *SiteReplicationSys) healBucketConfig(ctx context.Context, bucket, file string, info srStatusInfo) error {
-	c.RLock()
-	defer c.RUnlock()
-	if !c.enabled {
+	state, ok := c.stateSnapshot()
+	if !ok {
 		return nil
 	}
 	latest, found := latestBucketConfig(bucket, file, info)
@@ -177,7 +176,7 @@ func (c *SiteReplicationSys) healBucketConfig(ctx context.Context, bucket, file
 			_, err = globalBucketMetadataSys.updateAndParseMetadata(ctx, bucket, file, latest.data, false, false, &latest.at)
 		} else {
 			var client *madmin.AdminClient
-			client, err = c.getAdminClient(ctx, id)
+			client, err = state.getAdminClient(id)
 			if err == nil {
 				err = client.SRPeerReplicateBucketMeta(ctx, newBucketConfigReplicationEvent(bucket, file, incoming))
 			}

cmd/site-replication-metadata_test.go

@@ -622,6 +622,23 @@ func TestLocalBucketMetadataCommittedEvents(t *testing.T) {
 				t.Fatalf("zero quota event: %+v", last)
 			}
 
+			// Replicated buckets must reject prefix exclusions without changing
+			// the stored versioning document or announcing a successful update.
+			beforeRejected := len(events())
+			rec = corsAdminRequest(t, cred, http.MethodPut, "/import-bucket-metadata", corsZip(t, map[string][]byte{
+				bucket + "/" + bucketVersioningConfig: []byte(`<VersioningConfiguration><Status>Enabled</Status><ExcludeFolders>true</ExcludeFolders></VersioningConfiguration>`),
+			}))
+			if report := corsImportReport(t, rec).Buckets[bucket]; report.Versioning.Err == "" {
+				t.Fatal("replicated bucket accepted excluded prefixes")
+			}
+			afterRejected, err := loadBucketMetadata(ctx, obj, bucket)
+			if err != nil {
+				t.Fatal(err)
+			}
+			if !bytes.Equal(afterRejected.VersioningConfigXML, meta.VersioningConfigXML) || !afterRejected.VersioningConfigUpdatedAt.Equal(meta.VersioningConfigUpdatedAt) || len(events()) != beforeRejected {
+				t.Fatal("rejected versioning import changed metadata or emitted an event")
+			}
+
 			injectedAt := UTCNow().Add(2 * time.Hour)
 			interleaving := &importInterleavingObjectLayer{ObjectLayer: obj, write: func() {
 				data := []byte(`{"quota":2048,"quotatype":"hard"}`)
@@ -638,10 +655,10 @@ func TestLocalBucketMetadataCommittedEvents(t *testing.T) {
 				bucket + "/quota.json":                []byte(`{}`),
 				bucket + "/" + bucketTaggingConfig:    []byte(`<Tagging><TagSet><Tag><Key>imported</Key><Value>yes</Value></Tag></TagSet></Tagging>`),
 				bucket + "/" + objectLockConfig:       enabledBucketObjectLockConfig,
-				bucket + "/" + bucketVersioningConfig: []byte(`<VersioningConfiguration><Status>Enabled</Status><ExcludeFolders>true</ExcludeFolders></VersioningConfiguration>`),
+				bucket + "/" + bucketVersioningConfig: enabledBucketVersioningConfig,
 			}))
 			report := corsImportReport(t, rec).Buckets[bucket]
-			if report.Err != "" || report.Policy.Err != "" || report.Quota.Err != "" || report.Tagging.Err != "" {
+			if report.Err != "" || report.Policy.Err != "" || report.Quota.Err != "" || report.Tagging.Err != "" || report.Versioning.Err != "" {
 				t.Fatalf("import: %+v", report)
 			}
 			meta, err = loadBucketMetadata(ctx, obj, bucket)

cmd/site-replication-status_test.go

@@ -0,0 +1,519 @@
+// Copyright (c) 2026 Feng Ruohang
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+package cmd
+
+import (
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"maps"
+	"net/http"
+	"net/http/httptest"
+	"reflect"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+)
+
+// Pause before the real IAM loader, which can itself read replication state.
+// TryLock below proves that a configuration writer can proceed at this point
+// without leaving deadlocked goroutines behind when this test regresses.
+type siteStatusPausedStore struct {
+	IAMStorageAPI
+	once             sync.Once
+	loading, proceed chan struct{}
+}
+
+func (s *siteStatusPausedStore) loadUsers(ctx context.Context, typ IAMUserType, users map[string]UserIdentity) error {
+	s.once.Do(func() { close(s.loading); <-s.proceed })
+	return s.IAMStorageAPI.loadUsers(ctx, typ, users)
+}
+
+func TestSiteReplicationStatusReadsStorageUnlocked(t *testing.T) {
+	for _, entry := range []string{"metadata", "status", "heal"} {
+		for _, change := range []string{"disable", "topology", "cancel"} {
+			t.Run(entry+"/"+change, func(t *testing.T) {
+				site := newSvcAccSite(t)
+				c := &globalSiteReplicationSys
+				paused := &siteStatusPausedStore{IAMStorageAPI: site.sys.store.IAMStorageAPI, loading: make(chan struct{}), proceed: make(chan struct{})}
+				site.sys.store.IAMStorageAPI = paused
+				release := sync.OnceFunc(func() { close(paused.proceed) })
+				defer release()
+				c.iamMetaCache.Lock()
+				c.iamMetaCache.lastUpdate = time.Time{}
+				c.iamMetaCache.Unlock()
+				c.RLock()
+				peers := maps.Clone(c.state.Peers)
+				c.RUnlock()
+				ctx, cancel := context.WithCancel(site.ctx)
+				defer cancel()
+				var meta madmin.SRInfo
+				var status srStatusInfo
+				done := make(chan error, 1)
+				go func() {
+					var err error
+					opts := madmin.SRStatusOptions{Users: true, Groups: true, Policies: true, PeerState: true}
+					switch entry {
+					case "metadata":
+						meta, err = c.SiteReplicationMetaInfo(ctx, site.obj, opts)
+					case "status":
+						status, err = c.siteReplicationStatus(ctx, site.obj, opts)
+					case "heal":
+						err = c.healIAMSystem(ctx, site.obj)
+					}
+					done <- err
+				}()
+				select {
+				case <-paused.loading:
+				case err := <-done:
+					t.Fatalf("did not read IAM storage: %v", err)
+				case <-time.After(10 * time.Second):
+					t.Fatal("did not reach IAM loader")
+				}
+				if c.TryLock() {
+					switch change {
+					case "disable":
+						c.enabled = false
+						c.state = srState{}
+					case "topology":
+						delete(c.state.Peers, "remote")
+						c.state.UpdatedAt = UTCNow()
+					}
+					c.Unlock()
+				} else {
+					t.Error("replication configuration is locked during IAM storage read")
+				}
+				if change == "cancel" {
+					cancel()
+				}
+				release()
+				select {
+				case err := <-done:
+					if change != "cancel" {
+						mustIAM(t, err)
+					}
+				case <-time.After(10 * time.Second):
+					t.Fatal("operation did not finish")
+				}
+				if change != "cancel" {
+					if entry == "metadata" && !reflect.DeepEqual(meta.State.Peers, peers) || entry == "status" && !reflect.DeepEqual(status.Sites, peers) {
+						t.Fatal("result topology changed after its snapshot")
+					}
+				}
+			})
+		}
+	}
+}
+
+func TestSiteReplicationStatusRemoteUnlocked(t *testing.T) {
+	for _, fail := range []bool{false, true} {
+		t.Run(map[bool]string{false: "success", true: "peer-error"}[fail], func(t *testing.T) {
+			site := newSvcAccSite(t)
+			entered, proceed := make(chan struct{}), make(chan struct{})
+			var once sync.Once
+			peer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				once.Do(func() { close(entered) })
+				<-proceed
+				w.Header().Set("Content-Type", "application/json")
+				if fail {
+					w.WriteHeader(http.StatusForbidden)
+					_ = json.NewEncoder(w).Encode(madmin.ErrorResponse{Code: "AccessDenied", Message: "denied"})
+					return
+				}
+				_ = json.NewEncoder(w).Encode(madmin.SRInfo{DeploymentID: "remote"})
+			}))
+			defer peer.Close()
+			release := sync.OnceFunc(func() { close(proceed) })
+			defer release()
+			c := &globalSiteReplicationSys
+			c.Lock()
+			c.state.Peers = site.peers(peer.URL)
+			c.state.UpdatedAt = UTCNow()
+			updated := c.state.UpdatedAt
+			c.Unlock()
+			var status srStatusInfo
+			done := make(chan error, 1)
+			go func() {
+				var err error
+				status, err = c.siteReplicationStatus(site.ctx, site.obj, madmin.SRStatusOptions{})
+				done <- err
+			}()
+			select {
+			case <-entered:
+			case err := <-done:
+				t.Fatalf("did not request remote status: %v", err)
+			case <-time.After(10 * time.Second):
+				t.Fatal("did not reach peer")
+			}
+			if c.TryLock() {
+				delete(c.state.Peers, "remote")
+				c.state.UpdatedAt = updated.Add(time.Second)
+				c.Unlock()
+			} else {
+				t.Error("replication configuration is locked during remote request")
+			}
+			release()
+			select {
+			case err := <-done:
+				if fail {
+					if err == nil || !strings.Contains(err.Error(), "site remote (remote)") {
+						t.Fatalf("lost original peer name in error: %v", err)
+					}
+				} else {
+					mustIAM(t, err)
+					if len(status.Sites) != 2 || status.Sites["remote"].Endpoint != peer.URL || status.UpdatedAt != updated {
+						t.Fatal("status mixed different topology revisions")
+					}
+				}
+			case <-time.After(10 * time.Second):
+				t.Fatal("status did not finish")
+			}
+		})
+	}
+}
+
+func TestSiteReplicationMetaInfoCachedPeerState(t *testing.T) {
+	site := newSvcAccSite(t)
+	c := &globalSiteReplicationSys
+	c.srCacheIAMInfo(madmin.SRInfo{DeploymentID: globalDeploymentID(), State: madmin.SRStateInfo{Name: "obsolete"}})
+	opts := madmin.SRStatusOptions{Users: true, Groups: true, Policies: true, PeerState: true}
+	got, err := c.SiteReplicationMetaInfo(site.ctx, site.obj, opts)
+	mustIAM(t, err)
+	if !reflect.DeepEqual(got.State.Peers, c.state.Peers) || got.State.Name != c.state.Name {
+		t.Fatal("cached IAM response returned stale peer state")
+	}
+	delete(got.State.Peers, "remote")
+	if len(c.state.Peers) != 2 {
+		t.Fatal("returned peer map aliases the replication configuration")
+	}
+	opts.PeerState = false
+	got, err = c.SiteReplicationMetaInfo(site.ctx, site.obj, opts)
+	mustIAM(t, err)
+	if got.State.Name != "" || got.State.Peers != nil {
+		t.Fatal("returned cached peer state that was not requested")
+	}
+}
+
+type siteBucketDeletePausedLayer struct {
+	ObjectLayer
+	once             sync.Once
+	deleting, resume chan struct{}
+}
+
+func (l *siteBucketDeletePausedLayer) DeleteBucket(ctx context.Context, bucket string, opts DeleteBucketOptions) error {
+	l.once.Do(func() { close(l.deleting); <-l.resume })
+	return l.ObjectLayer.DeleteBucket(ctx, bucket, opts)
+}
+
+func TestSiteReplicationHealAndHooksReleaseLock(t *testing.T) {
+	cases := []string{
+		"make-bucket-hook",
+		"delete-bucket-hook",
+		"bucket-meta-hook",
+		"iam-change-hook",
+		"configure-repl",
+		"peer-bucket-delete",
+		"heal-bucket-make",
+		"heal-bucket-delete",
+		"heal-bucket-repl-config",
+		"heal-bucket-config",
+		"heal-cors",
+		"heal-ilm-expiry-config",
+		"heal-bucket-ilm-expiry",
+	}
+	for _, tc := range cases {
+		t.Run(tc, func(t *testing.T) {
+			site := newSvcAccSite(t)
+			c := &globalSiteReplicationSys
+			const bucket = "sr-lock-test-bucket"
+			mustIAM(t, site.obj.MakeBucket(site.ctx, bucket, MakeBucketOptions{VersioningEnabled: true}))
+			_, err := globalBucketMetadataSys.Update(site.ctx, bucket, bucketVersioningConfig, enabledBucketVersioningConfig)
+			mustIAM(t, err)
+
+			entered, proceed := make(chan struct{}), make(chan struct{})
+			var once sync.Once
+			pause := func() {
+				once.Do(func() { close(entered) })
+				<-proceed
+			}
+			release := sync.OnceFunc(func() { close(proceed) })
+			defer release()
+
+			peer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				pause()
+				if strings.HasSuffix(r.URL.Path, iamRevisionPeerPath) {
+					w.Header().Set("Content-Type", "application/json")
+					_ = json.NewEncoder(w).Encode(iamRevisionResponse{
+						iamRevisionStatus: iamRevisionStatus{Version: iamRevisionProtocol, Node: "node", Instance: "boot", Digest: "fixture"},
+					})
+					return
+				}
+				if r.Method == http.MethodGet {
+					if _, ok := r.URL.Query()["versioning"]; ok {
+						w.Header().Set("Content-Type", "application/xml")
+						_, _ = w.Write([]byte(`<VersioningConfiguration xmlns="http://s3.amazonaws.com/doc/2006-03-01/"><Status>Enabled</Status></VersioningConfiguration>`))
+						return
+					}
+					if _, ok := r.URL.Query()["location"]; ok {
+						w.Header().Set("Content-Type", "application/xml")
+						_, _ = w.Write([]byte(`<LocationConstraint xmlns="http://s3.amazonaws.com/doc/2006-03-01/"></LocationConstraint>`))
+						return
+					}
+				}
+				w.WriteHeader(http.StatusOK)
+			}))
+			defer peer.Close()
+
+			pausedObj := &siteBucketDeletePausedLayer{
+				ObjectLayer: site.obj,
+				deleting:    entered,
+				resume:      proceed,
+			}
+			if tc == "peer-bucket-delete" || tc == "heal-bucket-delete" {
+				setObjectLayer(pausedObj)
+				defer setObjectLayer(site.obj)
+			}
+
+			local := globalDeploymentID()
+			now := UTCNow().Truncate(time.Second)
+			peers := site.peers(peer.URL)
+			for id, p := range peers {
+				p.ReplicateILMExpiry = true
+				peers[id] = p
+			}
+			c.Lock()
+			c.enabled = true
+			c.state = srState{
+				Name:                    "local",
+				ServiceAccountAccessKey: site.parent.AccessKey,
+				Peers:                   peers,
+				UpdatedAt:               now,
+			}
+			c.Unlock()
+
+			done := make(chan error, 1)
+			go func() {
+				switch tc {
+				case "make-bucket-hook":
+					done <- c.MakeBucketHook(site.ctx, bucket, MakeBucketOptions{CreatedAt: now})
+				case "delete-bucket-hook":
+					done <- c.DeleteBucketHook(site.ctx, bucket, true)
+				case "bucket-meta-hook":
+					done <- c.BucketMetaHook(site.ctx, madmin.SRBucketMeta{
+						Type:      madmin.SRBucketMetaTypeTags,
+						Bucket:    bucket,
+						UpdatedAt: now,
+					})
+				case "iam-change-hook":
+					site.create(t, "sr-lock-hook-sa")
+					done <- c.IAMChangeHook(site.ctx, madmin.SRIAMItem{
+						Type:         madmin.SRIAMItemSvcAcc,
+						SvcAccChange: &madmin.SRSvcAccChange{Create: &madmin.SRSvcAccCreate{AccessKey: "sr-lock-hook-sa"}},
+						UpdatedAt:    now,
+					})
+				case "configure-repl":
+					done <- c.PeerBucketConfigureReplHandler(site.ctx, bucket)
+				case "peer-bucket-delete":
+					done <- c.PeerBucketDeleteHandler(site.ctx, bucket, DeleteBucketOptions{Force: true})
+				case "heal-bucket-make":
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						BucketStats: map[string]map[string]srBucketStatsSummary{
+							bucket: {
+								local:    {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now}}},
+								"remote": {HasBucket: false},
+							},
+						},
+					}
+					done <- c.healBucket(site.ctx, site.obj, bucket, info)
+				case "heal-bucket-delete":
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						BucketStats: map[string]map[string]srBucketStatsSummary{
+							bucket: {
+								local:    {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute), DeletedAt: now}}},
+								"remote": {HasBucket: false, BucketMarkedDeleted: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{DeletedAt: now.Add(-2 * time.Minute)}}},
+							},
+						},
+					}
+					done <- c.healBucket(site.ctx, pausedObj, bucket, info)
+				case "heal-bucket-repl-config":
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						BucketStats: map[string]map[string]srBucketStatsSummary{
+							bucket: {
+								local: {HasBucket: true, ReplicationCfgMismatch: true},
+							},
+						},
+					}
+					done <- c.healBucketReplicationConfig(site.ctx, site.obj, bucket, info, &validateReplicationDestinationOptions{CheckReady: true})
+				case "heal-bucket-config":
+					tagPayload := base64.StdEncoding.EncodeToString([]byte(`<Tagging><TagSet><Tag><Key>k</Key><Value>v</Value></Tag></TagSet></Tagging>`))
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						BucketStats: map[string]map[string]srBucketStatsSummary{
+							bucket: {
+								local:    {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute), Tags: &tagPayload, TagConfigUpdatedAt: now}}},
+								"remote": {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute)}}},
+							},
+						},
+					}
+					done <- c.healBucketConfig(site.ctx, bucket, bucketTaggingConfig, info)
+				case "heal-cors":
+					corsPayload := base64.StdEncoding.EncodeToString([]byte(`<CORSConfiguration><CORSRule><AllowedOrigin>*</AllowedOrigin><AllowedMethod>GET</AllowedMethod></CORSRule></CORSConfiguration>`))
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						BucketStats: map[string]map[string]srBucketStatsSummary{
+							bucket: {
+								local:    {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute), CorsConfig: &corsPayload, CorsConfigUpdatedAt: now}}},
+								"remote": {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute)}}},
+							},
+						},
+					}
+					done <- c.healCORSMetadata(site.ctx, site.obj, bucket, info)
+				case "heal-ilm-expiry-config":
+					stalePeers := site.peers(peer.URL)
+					for id, p := range stalePeers {
+						p.ReplicateILMExpiry = false
+						stalePeers[id] = p
+					}
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						PeerStates: map[string]madmin.SRStateInfo{
+							local:    {Name: "local", Peers: peers, UpdatedAt: now},
+							"remote": {Name: "remote", Peers: stalePeers, UpdatedAt: now.Add(-time.Minute)},
+						},
+					}
+					done <- c.healILMExpiryConfig(site.ctx, site.obj, info)
+				case "heal-bucket-ilm-expiry":
+					lcXML := `<LifecycleConfiguration><Rule><ID>exp</ID><Status>Enabled</Status><Expiration><Days>1</Days></Expiration></Rule></LifecycleConfiguration>`
+					lcPayload := base64.StdEncoding.EncodeToString([]byte(lcXML))
+					info := srStatusInfo{
+						Sites: site.peers(peer.URL),
+						BucketStats: map[string]map[string]srBucketStatsSummary{
+							bucket: {
+								local:    {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute), ExpiryLCConfig: &lcPayload, ExpiryLCConfigUpdatedAt: now}}},
+								"remote": {HasBucket: true, meta: srBucketMetaInfo{SRBucketInfo: madmin.SRBucketInfo{CreatedAt: now.Add(-time.Minute)}}},
+							},
+						},
+					}
+					done <- c.healBucketILMExpiry(site.ctx, site.obj, bucket, info)
+				}
+			}()
+
+			select {
+			case <-entered:
+			case err := <-done:
+				t.Fatalf("operation returned before reaching storage/peer pause point: %v", err)
+			case <-time.After(10 * time.Second):
+				t.Fatal("timed out waiting for storage/peer pause point")
+			}
+
+			if c.TryLock() {
+				c.state.Name = "mutated-while-in-flight"
+				delete(c.state.Peers, "remote")
+				c.state.UpdatedAt = now.Add(time.Second)
+				c.Unlock()
+			} else {
+				t.Error("SiteReplicationSys lock held across storage I/O or peer RPC")
+			}
+
+			release()
+			select {
+			case err := <-done:
+				if err != nil {
+					t.Fatalf("unexpected error: %v", err)
+				}
+			case <-time.After(10 * time.Second):
+				t.Fatal("operation deadlocked after writer mutation")
+			}
+		})
+	}
+}
+
+func TestSiteReplicationConcurrentStateUpdates(t *testing.T) {
+	site := newSvcAccSite(t)
+	c := &globalSiteReplicationSys
+	const bucket = "sr-concurrent-state-bucket"
+	mustIAM(t, site.obj.MakeBucket(site.ctx, bucket, MakeBucketOptions{VersioningEnabled: true}))
+	_, err := globalBucketMetadataSys.Update(site.ctx, bucket, bucketVersioningConfig, enabledBucketVersioningConfig)
+	mustIAM(t, err)
+
+	peer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if strings.Contains(r.URL.Path, "metainfo") {
+			w.Header().Set("Content-Type", "application/json")
+			_ = json.NewEncoder(w).Encode(madmin.SRInfo{DeploymentID: "remote"})
+			return
+		}
+		if r.Method == http.MethodGet {
+			if _, ok := r.URL.Query()["versioning"]; ok {
+				w.Header().Set("Content-Type", "application/xml")
+				_, _ = w.Write([]byte(`<VersioningConfiguration xmlns="http://s3.amazonaws.com/doc/2006-03-01/"><Status>Enabled</Status></VersioningConfiguration>`))
+				return
+			}
+			if _, ok := r.URL.Query()["location"]; ok {
+				w.Header().Set("Content-Type", "application/xml")
+				_, _ = w.Write([]byte(`<LocationConstraint xmlns="http://s3.amazonaws.com/doc/2006-03-01/"></LocationConstraint>`))
+				return
+			}
+		}
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer peer.Close()
+
+	basePeers := site.peers(peer.URL)
+	now := UTCNow().Truncate(time.Second)
+	c.Lock()
+	c.enabled = true
+	c.state = srState{
+		Name:                    "local",
+		ServiceAccountAccessKey: site.parent.AccessKey,
+		Peers:                   maps.Clone(basePeers),
+		UpdatedAt:               now,
+	}
+	c.Unlock()
+
+	var wg sync.WaitGroup
+	wg.Add(4)
+	go func() {
+		defer wg.Done()
+		for i := range 10 {
+			_ = c.PeerEditReq(site.ctx, madmin.PeerInfo{
+				DeploymentID:       "remote",
+				Name:               "remote",
+				Endpoint:           peer.URL,
+				ReplicateILMExpiry: i%2 == 0,
+			})
+		}
+	}()
+	go func() {
+		defer wg.Done()
+		for i := range 10 {
+			peers := site.peers(peer.URL)
+			p := peers["remote"]
+			p.ReplicateILMExpiry = i%2 == 1
+			peers["remote"] = p
+			_ = c.PeerStateEditReq(site.ctx, madmin.SRStateEditReq{
+				Peers:     peers,
+				UpdatedAt: now.Add(time.Duration(i+1) * time.Second),
+			})
+		}
+	}()
+	go func() {
+		defer wg.Done()
+		for range 10 {
+			_ = c.PeerBucketConfigureReplHandler(site.ctx, bucket)
+		}
+	}()
+	go func() {
+		defer wg.Done()
+		for range 5 {
+			_ = c.healBuckets(site.ctx, site.obj)
+		}
+	}()
+	wg.Wait()
+}