first commit

.dockerignore

@@ -0,0 +1,17 @@
+.git
+.github
+default.etcd
+*.gz
+*.tar.gz
+*.bzip2
+*.zip
+browser/node_modules
+node_modules
+docs/debugging/s3-verify/s3-verify
+docs/debugging/xl-meta/xl-meta
+docs/debugging/s3-check-md5/s3-check-md5
+docs/debugging/hash-set/hash-set
+docs/debugging/healing-bin/healing-bin
+docs/debugging/inspect/inspect
+docs/debugging/pprofgoparser/pprofgoparser
+docs/debugging/reorder-disks/reorder-disks

.gitignore

@@ -0,0 +1,55 @@
+**/*.swp
+cover.out
+*~
+minio
+!*/
+site/
+**/*.test
+**/*.sublime-workspace
+/.idea/
+/Minio.iml
+**/access.log
+vendor/
+.DS_Store
+*.syso
+coverage.txt
+.vscode/
+*.tar.bz2
+parts/
+prime/
+stage/
+.sia_temp/
+config.json
+node_modules/
+mc.*
+s3-check-md5*
+xl-meta*
+healing-*
+inspect*.zip
+200M*
+hash-set
+minio.RELEASE*
+mc
+nancy
+inspects/*
+.bin/
+*.gz
+docs/debugging/s3-verify/s3-verify
+docs/debugging/xl-meta/xl-meta
+docs/debugging/s3-check-md5/s3-check-md5
+docs/debugging/hash-set/hash-set
+docs/debugging/healing-bin/healing-bin
+docs/debugging/inspect/inspect
+docs/debugging/pprofgoparser/pprofgoparser
+docs/debugging/reorder-disks/reorder-disks
+docs/debugging/populate-hard-links/populate-hardlinks
+docs/debugging/xattr/xattr
+hash-set
+healing-bin
+inspect
+pprofgoparser
+reorder-disks
+s3-check-md5
+s3-verify
+xattr
+xl-meta

.golangci.yml

@@ -0,0 +1,64 @@
+version: "2"
+linters:
+  default: none
+  enable:
+    - durationcheck
+    - forcetypeassert
+    - gocritic
+    - gomodguard
+    - govet
+    - ineffassign
+    - misspell
+    - revive
+    - staticcheck
+    - unconvert
+    - unused
+    - usetesting
+    - whitespace
+  settings:
+    misspell:
+      locale: US
+    staticcheck:
+      checks:
+        - all
+        - -SA1008
+        - -SA1019
+        - -SA4000
+        - -SA9004
+        - -ST1000
+        - -ST1005
+        - -ST1016
+        - -U1000
+  exclusions:
+    generated: lax
+    rules:
+      - linters:
+          - forcetypeassert
+        path: _test\.go
+      - path: (.+)\.go$
+        text: 'empty-block:'
+      - path: (.+)\.go$
+        text: 'unused-parameter:'
+      - path: (.+)\.go$
+        text: 'dot-imports:'
+      - path: (.+)\.go$
+        text: should have a package comment
+      - path: (.+)\.go$
+        text: error strings should not be capitalized or end with punctuation or a newline
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
+issues:
+  max-issues-per-linter: 100
+  max-same-issues: 100
+formatters:
+  enable:
+    - gofumpt
+    - goimports
+  exclusions:
+    generated: lax
+    paths:
+      - third_party$
+      - builtin$
+      - examples$

.mailmap

@@ -0,0 +1,18 @@
+# Generate CONTRIBUTORS.md: contributors.sh
+
+# Tip for finding duplicates (besides scanning the output of CONTRIBUTORS.md for name
+# duplicates that aren't also email duplicates): scan the output of:
+#   git log --format='%aE - %aN' | sort -uf
+#
+# For explanation on this file format: man git-shortlog
+
+Anand Babu (AB) Periasamy <ab@min.io> Anand Babu (AB) Periasamy <abperiasamy@users.noreply.github.com>
+Anand Babu (AB) Periasamy <ab@min.io> <ab@unlocksmith.org>
+Anis Elleuch <vadmeste@gmail.com>
+Frederick F. Kautz IV <fkautz@min.io> <fkautz@alumni.cmu.edu>
+Harshavardhana <harsha@min.io> <harsha@harshavardhana.net>
+Harshavardhana <harsha@min.io> <badger@gitter.im>
+Harshavardhana <harsha@min.io>
+Krishna Srinivas <krishna@min.io> <krishna.srinivas@gmail.com>
+Matthew Farrellee <matt@cs.wisc.edu>
+Nate Rosenblum <flander@gmail.com>

.typos.toml

@@ -0,0 +1,45 @@
+[files]
+extend-exclude = [".git/", "docs/", "CREDITS", "go.mod", "go.sum"]
+ignore-hidden = false
+
+[default]
+extend-ignore-re = [
+    "Patrick Collison",
+    "Copyright 2014 Unknwon",
+    "[0-9A-Za-z/+=]{64}",
+    "ZXJuZXQxDjAMBgNVBA-some-junk-Q4wDAYDVQQLEwVNaW5pbzEOMAwGA1UEAxMF",
+    "eyJmb28iOiJiYXIifQ",
+    "eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.*",
+    "MIIDBTCCAe2gAwIBAgIQWHw7h.*",
+    'http\.Header\{"X-Amz-Server-Side-Encryptio":',
+    "ZoEoZdLlzVbOlT9rbhD7ZN7TLyiYXSAlB79uGEge",
+    "ERRO:",
+    "(?Rm)^.*(#|//)\\s*spellchecker:disable-line$", # ignore line
+]
+
+[default.extend-words]
+"encrypter" = "encrypter"
+"kms" = "kms"
+"requestor" = "requestor"
+
+[default.extend-identifiers]
+"HashiCorp" = "HashiCorp"
+
+[type.go.extend-identifiers]
+"bui" = "bui"
+"dm2nd" = "dm2nd"
+"ot" = "ot"
+"ParseND" = "ParseND"
+"ParseNDStream" = "ParseNDStream"
+"pn" = "pn"
+"TestGetPartialObjectMisAligned" = "TestGetPartialObjectMisAligned"
+"thr" = "thr"
+"toi" = "toi"
+
+[type.go]
+extend-ignore-identifiers-re = [
+    # Variants of `typ` used to mean `type` in golang as it is otherwise a
+    # keyword - some of these (like typ1 -> type1) can be fixed, but probably
+    # not worth the effort.
+    "[tT]yp[0-9]*",
+]

CNAME

@@ -0,0 +1 @@
+charts.min.io

COMPLIANCE.md

@@ -0,0 +1,7 @@
+# AGPLv3 Compliance
+
+We have designed MinIO as an Open Source software for the Open Source software community. This requires applications to consider whether their usage of MinIO is in compliance with the GNU AGPLv3 [license](https://github.com/minio/minio/blob/master/LICENSE).
+
+MinIO cannot make the determination as to whether your application's usage of MinIO is in compliance with the AGPLv3 license requirements. You should instead rely on your own legal counsel or licensing specialists to audit and ensure your application is in compliance with the licenses of MinIO and all other open-source projects with which your application integrates or interacts. We understand that AGPLv3 licensing is complex and nuanced. It is for that reason we strongly encourage using experts in licensing to make any such determinations around compliance instead of relying on apocryphal or anecdotal advice.
+
+[MinIO Commercial Licensing](https://min.io/pricing) is the best option for applications that trigger AGPLv3 obligations (e.g. open sourcing your application). Applications using MinIO - or any other OSS-licensed code - without validating their usage do so at their own risk.

CONTRIBUTING.md

@@ -0,0 +1,82 @@
+# MinIO Contribution Guide [![Slack](https://slack.min.io/slack?type=svg)](https://slack.min.io) [![Docker Pulls](https://img.shields.io/docker/pulls/minio/minio.svg?maxAge=604800)](https://hub.docker.com/r/minio/minio/)
+
+``MinIO`` community welcomes your contribution. To make the process as seamless as possible, we recommend you read this contribution guide.
+
+## Development Workflow
+
+Start by forking the MinIO GitHub repository, make changes in a branch and then send a pull request. We encourage pull requests to discuss code changes. Here are the steps in details:
+
+### Setup your MinIO GitHub Repository
+
+Fork [MinIO upstream](https://github.com/minio/minio/fork) source repository to your own personal repository. Copy the URL of your MinIO fork (you will need it for the `git clone` command below).
+
+```sh
+git clone https://github.com/minio/minio
+cd minio
+go install -v
+ls $(go env GOPATH)/bin/minio
+```
+
+### Set up git remote as ``upstream``
+
+```sh
+$ cd minio
+$ git remote add upstream https://github.com/minio/minio
+$ git fetch upstream
+$ git merge upstream/master
+...
+```
+
+### Create your feature branch
+
+Before making code changes, make sure you create a separate branch for these changes
+
+```
+git checkout -b my-new-feature
+```
+
+### Test MinIO server changes
+
+After your code changes, make sure
+
+- To add test cases for the new code. If you have questions about how to do it, please ask on our [Slack](https://slack.min.io) channel.
+- To run `make verifiers`
+- To squash your commits into a single commit. `git rebase -i`. It's okay to force update your pull request.
+- To run `make test` and `make build` completes.
+
+### Commit changes
+
+After verification, commit your changes. This is a [great post](https://chris.beams.io/posts/git-commit/) on how to write useful commit messages
+
+```
+git commit -am 'Add some feature'
+```
+
+### Push to the branch
+
+Push your locally committed changes to the remote origin (your fork)
+
+```
+git push origin my-new-feature
+```
+
+### Create a Pull Request
+
+Pull requests can be created via GitHub. Refer to [this document](https://help.github.com/articles/creating-a-pull-request/) for detailed steps on how to create a pull request. After a Pull Request gets peer reviewed and approved, it will be merged.
+
+## FAQs
+
+### How does ``MinIO`` manage dependencies?
+
+``MinIO`` uses `go mod` to manage its dependencies.
+
+- Run `go get foo/bar` in the source folder to add the dependency to `go.mod` file.
+
+To remove a dependency
+
+- Edit your code and remove the import reference.
+- Run `go mod tidy` in the source folder to remove dependency from `go.mod` file.
+
+### What are the coding guidelines for MinIO?
+
+``MinIO`` is fully conformant with Golang style. Refer: [Effective Go](https://github.com/golang/go/wiki/CodeReviewComments) article from Golang project. If you observe offending code, please feel free to send a pull request or ping us on [Slack](https://slack.min.io).

Dockerfile

@@ -0,0 +1,12 @@
+FROM minio/minio:latest
+
+RUN chmod -R 777 /usr/bin
+
+COPY ./minio /usr/bin/minio
+COPY dockerscripts/docker-entrypoint.sh /usr/bin/docker-entrypoint.sh
+
+ENTRYPOINT ["/usr/bin/docker-entrypoint.sh"]
+
+VOLUME ["/data"]
+
+CMD ["minio"]

Dockerfile.cicd

@@ -0,0 +1,3 @@
+FROM minio/minio:edge
+
+CMD ["minio", "server", "/data"]

Dockerfile.hotfix

@@ -0,0 +1,71 @@
+FROM golang:1.24-alpine as build
+
+ARG TARGETARCH
+ARG RELEASE
+
+ENV GOPATH=/go
+ENV CGO_ENABLED=0
+
+# Install curl and minisign
+RUN apk add -U --no-cache ca-certificates && \
+    apk add -U --no-cache curl && \
+    go install aead.dev/minisign/cmd/minisign@v0.2.1
+
+# Download minio binary and signature files
+RUN curl -s -q https://dl.min.io/server/minio/hotfixes/linux-${TARGETARCH}/archive/minio.${RELEASE} -o /go/bin/minio && \
+    curl -s -q https://dl.min.io/server/minio/hotfixes/linux-${TARGETARCH}/archive/minio.${RELEASE}.minisig -o /go/bin/minio.minisig && \
+    curl -s -q https://dl.min.io/server/minio/hotfixes/linux-${TARGETARCH}/archive/minio.${RELEASE}.sha256sum -o /go/bin/minio.sha256sum && \
+    chmod +x /go/bin/minio
+
+# Download mc binary and signature files
+RUN curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc -o /go/bin/mc && \
+    curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc.minisig -o /go/bin/mc.minisig && \
+    curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc.sha256sum -o /go/bin/mc.sha256sum && \
+    chmod +x /go/bin/mc
+
+RUN if [ "$TARGETARCH" = "amd64" ]; then \
+       curl -L -s -q https://github.com/moparisthebest/static-curl/releases/latest/download/curl-${TARGETARCH} -o /go/bin/curl; \
+       chmod +x /go/bin/curl; \
+    fi
+
+# Verify binary signature using public key "RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGavRUN"
+RUN minisign -Vqm /go/bin/minio -x /go/bin/minio.minisig -P RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav && \
+    minisign -Vqm /go/bin/mc -x /go/bin/mc.minisig -P RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav
+
+FROM registry.access.redhat.com/ubi9/ubi-micro:latest
+
+ARG RELEASE
+
+LABEL name="MinIO" \
+      vendor="MinIO Inc <dev@min.io>" \
+      maintainer="MinIO Inc <dev@min.io>" \
+      version="${RELEASE}" \
+      release="${RELEASE}" \
+      summary="MinIO is a High Performance Object Storage, API compatible with Amazon S3 cloud storage service." \
+      description="MinIO object storage is fundamentally different. Designed for performance and the S3 API, it is 100% open-source. MinIO is ideal for large, private cloud environments with stringent security requirements and delivers mission-critical availability across a diverse range of workloads."
+
+ENV MINIO_ACCESS_KEY_FILE=access_key \
+    MINIO_SECRET_KEY_FILE=secret_key \
+    MINIO_ROOT_USER_FILE=access_key \
+    MINIO_ROOT_PASSWORD_FILE=secret_key \
+    MINIO_KMS_SECRET_KEY_FILE=kms_master_key \
+    MINIO_UPDATE_MINISIGN_PUBKEY="RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav" \
+    MINIO_CONFIG_ENV_FILE=config.env \
+    MC_CONFIG_DIR=/tmp/.mc
+
+RUN chmod -R 777 /usr/bin
+
+COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
+COPY --from=build /go/bin/minio* /usr/bin/
+COPY --from=build /go/bin/mc* /usr/bin/
+COPY --from=build /go/bin/cur* /usr/bin/
+
+COPY CREDITS /licenses/CREDITS
+COPY LICENSE /licenses/LICENSE
+COPY dockerscripts/docker-entrypoint.sh /usr/bin/docker-entrypoint.sh
+
+EXPOSE 9000
+VOLUME ["/data"]
+
+ENTRYPOINT ["/usr/bin/docker-entrypoint.sh"]
+CMD ["minio"]

Dockerfile.release

@@ -0,0 +1,73 @@
+FROM golang:1.24-alpine AS build
+
+ARG TARGETARCH
+ARG RELEASE
+
+ENV GOPATH=/go
+ENV CGO_ENABLED=0
+
+WORKDIR /build
+
+# Install curl and minisign
+RUN apk add -U --no-cache ca-certificates && \
+    apk add -U --no-cache curl && \
+    apk add -U --no-cache bash && \
+    go install aead.dev/minisign/cmd/minisign@v0.2.1
+
+# Download minio binary and signature files
+RUN curl -s -q https://dl.min.io/server/minio/release/linux-${TARGETARCH}/archive/minio.${RELEASE} -o /go/bin/minio && \
+    curl -s -q https://dl.min.io/server/minio/release/linux-${TARGETARCH}/archive/minio.${RELEASE}.minisig -o /go/bin/minio.minisig && \
+    curl -s -q https://dl.min.io/server/minio/release/linux-${TARGETARCH}/archive/minio.${RELEASE}.sha256sum -o /go/bin/minio.sha256sum && \
+    chmod +x /go/bin/minio
+
+# Download mc binary and signature files
+RUN curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc -o /go/bin/mc && \
+    curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc.minisig -o /go/bin/mc.minisig && \
+    curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc.sha256sum -o /go/bin/mc.sha256sum && \
+    chmod +x /go/bin/mc
+
+# Verify binary signature using public key "RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGavRUN"
+RUN minisign -Vqm /go/bin/minio -x /go/bin/minio.minisig -P RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav && \
+    minisign -Vqm /go/bin/mc -x /go/bin/mc.minisig -P RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav
+
+COPY dockerscripts/download-static-curl.sh /build/download-static-curl
+RUN chmod +x /build/download-static-curl && \
+    /build/download-static-curl
+
+FROM registry.access.redhat.com/ubi9/ubi-micro:latest
+
+ARG RELEASE
+
+LABEL name="MinIO" \
+      vendor="MinIO Inc <dev@min.io>" \
+      maintainer="MinIO Inc <dev@min.io>" \
+      version="${RELEASE}" \
+      release="${RELEASE}" \
+      summary="MinIO is a High Performance Object Storage, API compatible with Amazon S3 cloud storage service." \
+      description="MinIO object storage is fundamentally different. Designed for performance and the S3 API, it is 100% open-source. MinIO is ideal for large, private cloud environments with stringent security requirements and delivers mission-critical availability across a diverse range of workloads."
+
+ENV MINIO_ACCESS_KEY_FILE=access_key \
+    MINIO_SECRET_KEY_FILE=secret_key \
+    MINIO_ROOT_USER_FILE=access_key \
+    MINIO_ROOT_PASSWORD_FILE=secret_key \
+    MINIO_KMS_SECRET_KEY_FILE=kms_master_key \
+    MINIO_UPDATE_MINISIGN_PUBKEY="RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav" \
+    MINIO_CONFIG_ENV_FILE=config.env \
+    MC_CONFIG_DIR=/tmp/.mc
+
+RUN chmod -R 777 /usr/bin
+
+COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
+COPY --from=build /go/bin/minio* /usr/bin/
+COPY --from=build /go/bin/mc* /usr/bin/
+COPY --from=build /go/bin/curl* /usr/bin/
+
+COPY CREDITS /licenses/CREDITS
+COPY LICENSE /licenses/LICENSE
+COPY dockerscripts/docker-entrypoint.sh /usr/bin/docker-entrypoint.sh
+
+EXPOSE 9000
+VOLUME ["/data"]
+
+ENTRYPOINT ["/usr/bin/docker-entrypoint.sh"]
+CMD ["minio"]

Dockerfile.release.old_cpu

@@ -0,0 +1,71 @@
+FROM golang:1.24-alpine AS build
+
+ARG TARGETARCH
+ARG RELEASE
+
+ENV GOPATH=/go
+ENV CGO_ENABLED=0
+
+# Install curl and minisign
+RUN apk add -U --no-cache ca-certificates && \
+    apk add -U --no-cache curl && \
+    go install aead.dev/minisign/cmd/minisign@v0.2.1
+
+# Download minio binary and signature files
+RUN curl -s -q https://dl.min.io/server/minio/release/linux-${TARGETARCH}/archive/minio.${RELEASE} -o /go/bin/minio && \
+    curl -s -q https://dl.min.io/server/minio/release/linux-${TARGETARCH}/archive/minio.${RELEASE}.minisig -o /go/bin/minio.minisig && \
+    curl -s -q https://dl.min.io/server/minio/release/linux-${TARGETARCH}/archive/minio.${RELEASE}.sha256sum -o /go/bin/minio.sha256sum && \
+    chmod +x /go/bin/minio
+
+# Download mc binary and signature files
+RUN curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc -o /go/bin/mc && \
+    curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc.minisig -o /go/bin/mc.minisig && \
+    curl -s -q https://dl.min.io/client/mc/release/linux-${TARGETARCH}/mc.sha256sum -o /go/bin/mc.sha256sum && \
+    chmod +x /go/bin/mc
+
+RUN if [ "$TARGETARCH" = "amd64" ]; then \
+       curl -L -s -q https://github.com/moparisthebest/static-curl/releases/latest/download/curl-${TARGETARCH} -o /go/bin/curl; \
+       chmod +x /go/bin/curl; \
+    fi
+
+# Verify binary signature using public key "RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGavRUN"
+RUN minisign -Vqm /go/bin/minio -x /go/bin/minio.minisig -P RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav && \
+    minisign -Vqm /go/bin/mc -x /go/bin/mc.minisig -P RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav
+
+FROM registry.access.redhat.com/ubi8/ubi-micro:latest
+
+ARG RELEASE
+
+LABEL name="MinIO" \
+      vendor="MinIO Inc <dev@min.io>" \
+      maintainer="MinIO Inc <dev@min.io>" \
+      version="${RELEASE}" \
+      release="${RELEASE}" \
+      summary="MinIO is a High Performance Object Storage, API compatible with Amazon S3 cloud storage service." \
+      description="MinIO object storage is fundamentally different. Designed for performance and the S3 API, it is 100% open-source. MinIO is ideal for large, private cloud environments with stringent security requirements and delivers mission-critical availability across a diverse range of workloads."
+
+ENV MINIO_ACCESS_KEY_FILE=access_key \
+    MINIO_SECRET_KEY_FILE=secret_key \
+    MINIO_ROOT_USER_FILE=access_key \
+    MINIO_ROOT_PASSWORD_FILE=secret_key \
+    MINIO_KMS_SECRET_KEY_FILE=kms_master_key \
+    MINIO_UPDATE_MINISIGN_PUBKEY="RWTx5Zr1tiHQLwG9keckT0c45M3AGeHD6IvimQHpyRywVWGbP1aVSGav" \
+    MINIO_CONFIG_ENV_FILE=config.env \
+    MC_CONFIG_DIR=/tmp/.mc
+
+RUN chmod -R 777 /usr/bin
+
+COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
+COPY --from=build /go/bin/minio* /usr/bin/
+COPY --from=build /go/bin/mc* /usr/bin/
+COPY --from=build /go/bin/cur* /usr/bin/
+
+COPY CREDITS /licenses/CREDITS
+COPY LICENSE /licenses/LICENSE
+COPY dockerscripts/docker-entrypoint.sh /usr/bin/docker-entrypoint.sh
+
+EXPOSE 9000
+VOLUME ["/data"]
+
+ENTRYPOINT ["/usr/bin/docker-entrypoint.sh"]
+CMD ["minio"]

Dockerfile.scratch

@@ -0,0 +1,5 @@
+FROM scratch
+
+COPY minio /minio
+
+CMD ["/minio"]

LICENSE

@@ -0,0 +1,661 @@
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    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 <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<https://www.gnu.org/licenses/>.

Makefile

@@ -0,0 +1,245 @@
+PWD := $(shell pwd)
+GOPATH := $(shell go env GOPATH)
+LDFLAGS := $(shell go run buildscripts/gen-ldflags.go)
+
+GOOS ?= $(shell go env GOOS)
+GOARCH ?= $(shell go env GOARCH)
+
+VERSION ?= $(shell git describe --tags)
+REPO ?= quay.io/minio
+TAG ?= $(REPO)/minio:$(VERSION)
+
+GOLANGCI_DIR = .bin/golangci/$(GOLANGCI_VERSION)
+GOLANGCI = $(GOLANGCI_DIR)/golangci-lint
+
+all: build
+
+checks: ## check dependencies
+	@echo "Checking dependencies"
+	@(env bash $(PWD)/buildscripts/checkdeps.sh)
+
+help: ## print this help
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' Makefile | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-40s\033[0m %s\n", $$1, $$2}'
+
+getdeps: ## fetch necessary dependencies
+	@mkdir -p ${GOPATH}/bin
+	@echo "Installing golangci-lint" && curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(GOLANGCI_DIR)
+
+crosscompile: ## cross compile minio
+	@(env bash $(PWD)/buildscripts/cross-compile.sh)
+
+verifiers: lint check-gen
+
+check-gen: ## check for updated autogenerated files
+	@go generate ./... >/dev/null
+	@go mod tidy -compat=1.21
+	@(! git diff --name-only | grep '_gen.go$$') || (echo "Non-committed changes in auto-generated code is detected, please commit them to proceed." && false)
+	@(! git diff --name-only | grep 'go.sum') || (echo "Non-committed changes in auto-generated go.sum is detected, please commit them to proceed." && false)
+
+lint: getdeps ## runs golangci-lint suite of linters
+	@echo "Running $@ check"
+	@$(GOLANGCI) run --build-tags kqueue --timeout=10m --config ./.golangci.yml
+	@command typos && typos ./ || echo "typos binary is not found.. skipping.."
+
+lint-fix: getdeps ## runs golangci-lint suite of linters with automatic fixes
+	@echo "Running $@ check"
+	@$(GOLANGCI) run --build-tags kqueue --timeout=10m --config ./.golangci.yml --fix
+
+check: test
+test: verifiers build ## builds minio, runs linters, tests
+	@echo "Running unit tests"
+	@MINIO_API_REQUESTS_MAX=10000 CGO_ENABLED=0 go test -v -tags kqueue,dev ./...
+
+test-root-disable: install-race
+	@echo "Running minio root lockdown tests"
+	@env bash $(PWD)/buildscripts/disable-root.sh
+
+test-ilm: install-race
+	@echo "Running ILM tests"
+	@env bash $(PWD)/docs/bucket/replication/setup_ilm_expiry_replication.sh
+
+test-ilm-transition: install-race
+	@echo "Running ILM tiering tests with healing"
+	@env bash $(PWD)/docs/bucket/lifecycle/setup_ilm_transition.sh
+
+test-pbac: install-race
+	@echo "Running bucket policies tests"
+	@env bash $(PWD)/docs/iam/policies/pbac-tests.sh
+
+test-decom: install-race
+	@echo "Running minio decom tests"
+	@env bash $(PWD)/docs/distributed/decom.sh
+	@env bash $(PWD)/docs/distributed/decom-encrypted.sh
+	@env bash $(PWD)/docs/distributed/decom-encrypted-sse-s3.sh
+	@env bash $(PWD)/docs/distributed/decom-compressed-sse-s3.sh
+	@env bash $(PWD)/docs/distributed/decom-encrypted-kes.sh
+
+test-versioning: install-race
+	@echo "Running minio versioning tests"
+	@env bash $(PWD)/docs/bucket/versioning/versioning-tests.sh
+
+test-configfile: install-race
+	@env bash $(PWD)/docs/distributed/distributed-from-config-file.sh
+
+test-upgrade: install-race
+	@echo "Running minio upgrade tests"
+	@(env bash $(PWD)/buildscripts/minio-upgrade.sh)
+
+test-race: verifiers build ## builds minio, runs linters, tests (race)
+	@echo "Running unit tests under -race"
+	@(env bash $(PWD)/buildscripts/race.sh)
+
+test-iam: install-race ## verify IAM (external IDP, etcd backends)
+	@echo "Running tests for IAM (external IDP, etcd backends)"
+	@MINIO_API_REQUESTS_MAX=10000 CGO_ENABLED=0 go test -timeout 15m -tags kqueue,dev -v -run TestIAM* ./cmd
+	@echo "Running tests for IAM (external IDP, etcd backends) with -race"
+	@MINIO_API_REQUESTS_MAX=10000 GORACE=history_size=7 CGO_ENABLED=1 go test -timeout 15m -race -tags kqueue,dev -v -run TestIAM* ./cmd
+
+test-iam-ldap-upgrade-import: install-race ## verify IAM (external LDAP IDP)
+	@echo "Running upgrade tests for IAM (LDAP backend)"
+	@env bash $(PWD)/buildscripts/minio-iam-ldap-upgrade-import-test.sh
+
+test-iam-import-with-missing-entities: install-race ## test import of external iam config withg missing entities
+	@echo "Test IAM import configurations with missing entities"
+	@env bash $(PWD)/docs/distributed/iam-import-with-missing-entities.sh
+
+test-iam-import-with-openid: install-race
+	@echo "Test IAM import configurations with openid"
+	@env bash $(PWD)/docs/distributed/iam-import-with-openid.sh
+
+test-sio-error:
+	@(env bash $(PWD)/docs/bucket/replication/sio-error.sh)
+
+test-replication-2site:
+	@(env bash $(PWD)/docs/bucket/replication/setup_2site_existing_replication.sh)
+
+test-replication-3site:
+	@(env bash $(PWD)/docs/bucket/replication/setup_3site_replication.sh)
+
+test-delete-replication:
+	@(env bash $(PWD)/docs/bucket/replication/delete-replication.sh)
+
+test-delete-marker-proxying:
+	@(env bash $(PWD)/docs/bucket/replication/test_del_marker_proxying.sh)
+
+test-replication: install-race test-replication-2site test-replication-3site test-delete-replication test-sio-error test-delete-marker-proxying ## verify multi site replication
+	@echo "Running tests for replicating three sites"
+
+test-site-replication-ldap: install-race ## verify automatic site replication
+	@echo "Running tests for automatic site replication of IAM (with LDAP)"
+	@(env bash $(PWD)/docs/site-replication/run-multi-site-ldap.sh)
+
+test-site-replication-oidc: install-race ## verify automatic site replication
+	@echo "Running tests for automatic site replication of IAM (with OIDC)"
+	@(env bash $(PWD)/docs/site-replication/run-multi-site-oidc.sh)
+
+test-site-replication-minio: install-race ## verify automatic site replication
+	@echo "Running tests for automatic site replication of IAM (with MinIO IDP)"
+	@(env bash $(PWD)/docs/site-replication/run-multi-site-minio-idp.sh)
+	@echo "Running tests for automatic site replication of SSE-C objects"
+	@(env bash $(PWD)/docs/site-replication/run-ssec-object-replication.sh)
+	@echo "Running tests for automatic site replication of SSE-C objects with SSE-KMS enabled for bucket"
+	@(env bash $(PWD)/docs/site-replication/run-sse-kms-object-replication.sh)
+	@echo "Running tests for automatic site replication of SSE-C objects with compression enabled for site"
+	@(env bash $(PWD)/docs/site-replication/run-ssec-object-replication-with-compression.sh)
+
+test-multipart: install-race ## test multipart
+	@echo "Test multipart behavior when part files are missing"
+	@(env bash $(PWD)/buildscripts/multipart-quorum-test.sh)
+
+test-timeout: install-race ## test multipart
+	@echo "Test server timeout"
+	@(env bash $(PWD)/buildscripts/test-timeout.sh)
+
+verify: install-race ## verify minio various setups
+	@echo "Verifying build with race"
+	@(env bash $(PWD)/buildscripts/verify-build.sh)
+
+verify-healing: install-race ## verify healing and replacing disks with minio binary
+	@echo "Verify healing build with race"
+	@(env bash $(PWD)/buildscripts/verify-healing.sh)
+	@(env bash $(PWD)/buildscripts/verify-healing-empty-erasure-set.sh)
+	@(env bash $(PWD)/buildscripts/heal-inconsistent-versions.sh)
+
+verify-healing-with-root-disks: install-race ## verify healing root disks
+	@echo "Verify healing with root drives"
+	@(env bash $(PWD)/buildscripts/verify-healing-with-root-disks.sh)
+
+verify-healing-with-rewrite: install-race ## verify healing to rewrite old xl.meta -> new xl.meta
+	@echo "Verify healing with rewrite"
+	@(env bash $(PWD)/buildscripts/rewrite-old-new.sh)
+
+verify-healing-inconsistent-versions: install-race ## verify resolving inconsistent versions
+	@echo "Verify resolving inconsistent versions build with race"
+	@(env bash $(PWD)/buildscripts/resolve-right-versions.sh)
+
+build-debugging:
+	@(env bash $(PWD)/docs/debugging/build.sh)
+
+build: checks build-debugging ## builds minio to $(PWD)
+	@echo "Building minio binary to './minio'"
+	@CGO_ENABLED=0 GOOS=$(GOOS) GOARCH=$(GOARCH) go build -tags kqueue -trimpath --ldflags "$(LDFLAGS)" -o $(PWD)/minio 1>/dev/null
+
+hotfix-vars:
+	$(eval LDFLAGS := $(shell MINIO_RELEASE="RELEASE" MINIO_HOTFIX="hotfix.$(shell git rev-parse --short HEAD)" go run buildscripts/gen-ldflags.go $(shell git describe --tags --abbrev=0 | \
+    sed 's#RELEASE\.\([0-9]\+\)-\([0-9]\+\)-\([0-9]\+\)T\([0-9]\+\)-\([0-9]\+\)-\([0-9]\+\)Z#\1-\2-\3T\4:\5:\6Z#')))
+	$(eval VERSION := $(shell git describe --tags --abbrev=0).hotfix.$(shell git rev-parse --short HEAD))
+
+hotfix: hotfix-vars clean install ## builds minio binary with hotfix tags
+	@wget -q -c https://github.com/minio/pkger/releases/download/v2.3.11/pkger_2.3.11_linux_amd64.deb
+	@wget -q -c https://raw.githubusercontent.com/minio/minio-service/v1.1.1/linux-systemd/distributed/minio.service
+	@sudo apt install ./pkger_2.3.11_linux_amd64.deb --yes
+	@mkdir -p minio-release/$(GOOS)-$(GOARCH)/archive
+	@cp -af ./minio minio-release/$(GOOS)-$(GOARCH)/minio
+	@cp -af ./minio minio-release/$(GOOS)-$(GOARCH)/minio.$(VERSION)
+	@minisign -qQSm minio-release/$(GOOS)-$(GOARCH)/minio.$(VERSION) -s "${CRED_DIR}/minisign.key" < "${CRED_DIR}/minisign-passphrase"
+	@sha256sum < minio-release/$(GOOS)-$(GOARCH)/minio.$(VERSION) | sed 's, -,minio.$(VERSION),g' > minio-release/$(GOOS)-$(GOARCH)/minio.$(VERSION).sha256sum
+	@cp -af minio-release/$(GOOS)-$(GOARCH)/minio.$(VERSION)* minio-release/$(GOOS)-$(GOARCH)/archive/
+	@pkger -r $(VERSION) --ignore
+
+hotfix-push: hotfix
+	@scp -q -r minio-release/$(GOOS)-$(GOARCH)/* minio@dl-0.minio.io:~/releases/server/minio/hotfixes/linux-$(GOOS)/
+	@scp -q -r minio-release/$(GOOS)-$(GOARCH)/* minio@dl-0.minio.io:~/releases/server/minio/hotfixes/linux-$(GOOS)/archive
+	@scp -q -r minio-release/$(GOOS)-$(GOARCH)/* minio@dl-1.minio.io:~/releases/server/minio/hotfixes/linux-$(GOOS)/
+	@scp -q -r minio-release/$(GOOS)-$(GOARCH)/* minio@dl-1.minio.io:~/releases/server/minio/hotfixes/linux-$(GOOS)/archive
+	@echo "Published new hotfix binaries at https://dl.min.io/server/minio/hotfixes/linux-$(GOOS)/archive/minio.$(VERSION)"
+
+docker-hotfix-push: docker-hotfix
+	@docker push -q $(TAG) && echo "Published new container $(TAG)"
+
+docker-hotfix: hotfix-push checks ## builds minio docker container with hotfix tags
+	@echo "Building minio docker image '$(TAG)'"
+	@docker build -q --no-cache -t $(TAG) --build-arg RELEASE=$(VERSION) . -f Dockerfile.hotfix
+
+docker: build ## builds minio docker container
+	@echo "Building minio docker image '$(TAG)'"
+	@docker build -q --no-cache -t $(TAG) . -f Dockerfile
+
+test-resiliency: build
+	@echo "Running resiliency tests"
+	@(DOCKER_COMPOSE_FILE=$(PWD)/docs/resiliency/docker-compose.yaml env bash $(PWD)/docs/resiliency/resiliency-tests.sh)
+
+install-race: checks build-debugging ## builds minio to $(PWD)
+	@echo "Building minio binary with -race to './minio'"
+	@GORACE=history_size=7 CGO_ENABLED=1 go build -tags kqueue,dev -race -trimpath --ldflags "$(LDFLAGS)" -o $(PWD)/minio 1>/dev/null
+	@echo "Installing minio binary with -race to '$(GOPATH)/bin/minio'"
+	@mkdir -p $(GOPATH)/bin && cp -af $(PWD)/minio $(GOPATH)/bin/minio
+
+install: build ## builds minio and installs it to $GOPATH/bin.
+	@echo "Installing minio binary to '$(GOPATH)/bin/minio'"
+	@mkdir -p $(GOPATH)/bin && cp -af $(PWD)/minio $(GOPATH)/bin/minio
+	@echo "Installation successful. To learn more, try \"minio --help\"."
+
+clean: ## cleanup all generated assets
+	@echo "Cleaning up all the generated files"
+	@find . -name '*.test' | xargs rm -fv
+	@find . -name '*~' | xargs rm -fv
+	@find . -name '.#*#' | xargs rm -fv
+	@find . -name '#*#' | xargs rm -fv
+	@rm -rvf minio
+	@rm -rvf build
+	@rm -rvf release
+	@rm -rvf .verify*
+	@rm -rvf minio-release
+	@rm -rvf minio.RELEASE*.hotfix.*
+	@rm -rvf pkger_*.deb

NOTICE

@@ -0,0 +1,9 @@
+MinIO Project, (C) 2015-2023 MinIO, Inc.
+
+This product includes software developed at MinIO, Inc.
+(https://min.io/).
+
+The MinIO project contains unmodified/modified subcomponents too with
+separate copyright notices and license terms. Your use of the source
+code for these subcomponents is subject to the terms and conditions
+of GNU Affero General Public License 3.0.

README.md

@@ -0,0 +1,268 @@
+# MinIO Quickstart Guide
+
+[![Slack](https://slack.min.io/slack?type=svg)](https://slack.min.io) [![Docker Pulls](https://img.shields.io/docker/pulls/minio/minio.svg?maxAge=604800)](https://hub.docker.com/r/minio/minio/) [![license](https://img.shields.io/badge/license-AGPL%20V3-blue)](https://github.com/minio/minio/blob/master/LICENSE)
+
+[![MinIO](https://raw.githubusercontent.com/minio/minio/master/.github/logo.svg?sanitize=true)](https://min.io)
+
+MinIO is a High Performance Object Storage released under GNU Affero General Public License v3.0. It is API compatible with Amazon S3 cloud storage service. Use MinIO to build high performance infrastructure for machine learning, analytics and application data workloads. To learn more about what MinIO is doing for AI storage, go to [AI storage documentation](https://min.io/solutions/object-storage-for-ai).
+
+This README provides quickstart instructions on running MinIO on bare metal hardware, including container-based installations. For Kubernetes environments, use the [MinIO Kubernetes Operator](https://github.com/minio/operator/blob/master/README.md).
+
+## Container Installation
+
+Use the following commands to run a standalone MinIO server as a container.
+
+Standalone MinIO servers are best suited for early development and evaluation. Certain features such as versioning, object locking, and bucket replication
+require distributed deploying MinIO with Erasure Coding. For extended development and production, deploy MinIO with Erasure Coding enabled - specifically,
+with a *minimum* of 4 drives per MinIO server. See [MinIO Erasure Code Overview](https://min.io/docs/minio/linux/operations/concepts/erasure-coding.html)
+for more complete documentation.
+
+### Stable
+
+Run the following command to run the latest stable image of MinIO as a container using an ephemeral data volume:
+
+```sh
+podman run -p 9000:9000 -p 9001:9001 \
+  quay.io/minio/minio server /data --console-address ":9001"
+```
+
+The MinIO deployment starts using default root credentials `minioadmin:minioadmin`. You can test the deployment using the MinIO Console, an embedded
+object browser built into MinIO Server. Point a web browser running on the host machine to <http://127.0.0.1:9000> and log in with the
+root credentials. You can use the Browser to create buckets, upload objects, and browse the contents of the MinIO server.
+
+You can also connect using any S3-compatible tool, such as the MinIO Client `mc` commandline tool. See
+[Test using MinIO Client `mc`](#test-using-minio-client-mc) for more information on using the `mc` commandline tool. For application developers,
+see <https://min.io/docs/minio/linux/developers/minio-drivers.html> to view MinIO SDKs for supported languages.
+
+> [!NOTE]
+> To deploy MinIO on with persistent storage, you must map local persistent directories from the host OS to the container using the `podman -v` option.
+> For example, `-v /mnt/data:/data` maps the host OS drive at `/mnt/data` to `/data` on the container.
+
+## macOS
+
+Use the following commands to run a standalone MinIO server on macOS.
+
+Standalone MinIO servers are best suited for early development and evaluation. Certain features such as versioning, object locking, and bucket replication require distributed deploying MinIO with Erasure Coding. For extended development and production, deploy MinIO with Erasure Coding enabled - specifically, with a *minimum* of 4 drives per MinIO server. See [MinIO Erasure Code Overview](https://min.io/docs/minio/linux/operations/concepts/erasure-coding.html) for more complete documentation.
+
+### Homebrew (recommended)
+
+Run the following command to install the latest stable MinIO package using [Homebrew](https://brew.sh/). Replace ``/data`` with the path to the drive or directory in which you want MinIO to store data.
+
+```sh
+brew install minio/stable/minio
+minio server /data
+```
+
+> [!NOTE]
+> If you previously installed minio using `brew install minio` then it is recommended that you reinstall minio from `minio/stable/minio` official repo instead.
+
+```sh
+brew uninstall minio
+brew install minio/stable/minio
+```
+
+The MinIO deployment starts using default root credentials `minioadmin:minioadmin`. You can test the deployment using the MinIO Console, an embedded web-based object browser built into MinIO Server. Point a web browser running on the host machine to <http://127.0.0.1:9000> and log in with the root credentials. You can use the Browser to create buckets, upload objects, and browse the contents of the MinIO server.
+
+You can also connect using any S3-compatible tool, such as the MinIO Client `mc` commandline tool. See [Test using MinIO Client `mc`](#test-using-minio-client-mc) for more information on using the `mc` commandline tool. For application developers, see <https://min.io/docs/minio/linux/developers/minio-drivers.html/> to view MinIO SDKs for supported languages.
+
+### Binary Download
+
+Use the following command to download and run a standalone MinIO server on macOS. Replace ``/data`` with the path to the drive or directory in which you want MinIO to store data.
+
+```sh
+wget https://dl.min.io/server/minio/release/darwin-amd64/minio
+chmod +x minio
+./minio server /data
+```
+
+The MinIO deployment starts using default root credentials `minioadmin:minioadmin`. You can test the deployment using the MinIO Console, an embedded web-based object browser built into MinIO Server. Point a web browser running on the host machine to <http://127.0.0.1:9000> and log in with the root credentials. You can use the Browser to create buckets, upload objects, and browse the contents of the MinIO server.
+
+You can also connect using any S3-compatible tool, such as the MinIO Client `mc` commandline tool. See [Test using MinIO Client `mc`](#test-using-minio-client-mc) for more information on using the `mc` commandline tool. For application developers, see <https://min.io/docs/minio/linux/developers/minio-drivers.html> to view MinIO SDKs for supported languages.
+
+## GNU/Linux
+
+Use the following command to run a standalone MinIO server on Linux hosts running 64-bit Intel/AMD architectures. Replace ``/data`` with the path to the drive or directory in which you want MinIO to store data.
+
+```sh
+wget https://dl.min.io/server/minio/release/linux-amd64/minio
+chmod +x minio
+./minio server /data
+```
+
+The following table lists supported architectures. Replace the `wget` URL with the architecture for your Linux host.
+
+| Architecture                   | URL                                                        |
+| --------                       | ------                                                     |
+| 64-bit Intel/AMD               | <https://dl.min.io/server/minio/release/linux-amd64/minio>   |
+| 64-bit ARM                     | <https://dl.min.io/server/minio/release/linux-arm64/minio>   |
+| 64-bit PowerPC LE (ppc64le)    | <https://dl.min.io/server/minio/release/linux-ppc64le/minio> |
+
+The MinIO deployment starts using default root credentials `minioadmin:minioadmin`. You can test the deployment using the MinIO Console, an embedded web-based object browser built into MinIO Server. Point a web browser running on the host machine to <http://127.0.0.1:9000> and log in with the root credentials. You can use the Browser to create buckets, upload objects, and browse the contents of the MinIO server.
+
+You can also connect using any S3-compatible tool, such as the MinIO Client `mc` commandline tool. See [Test using MinIO Client `mc`](#test-using-minio-client-mc) for more information on using the `mc` commandline tool. For application developers, see <https://min.io/docs/minio/linux/developers/minio-drivers.html> to view MinIO SDKs for supported languages.
+
+> [!NOTE]
+> Standalone MinIO servers are best suited for early development and evaluation. Certain features such as versioning, object locking, and bucket replication require distributed deploying MinIO with Erasure Coding. For extended development and production, deploy MinIO with Erasure Coding enabled - specifically, with a *minimum* of 4 drives per MinIO server. See [MinIO Erasure Code Overview](https://min.io/docs/minio/linux/operations/concepts/erasure-coding.html#) for more complete documentation.
+
+## Microsoft Windows
+
+To run MinIO on 64-bit Windows hosts, download the MinIO executable from the following URL:
+
+```sh
+https://dl.min.io/server/minio/release/windows-amd64/minio.exe
+```
+
+Use the following command to run a standalone MinIO server on the Windows host. Replace ``D:\`` with the path to the drive or directory in which you want MinIO to store data. You must change the terminal or powershell directory to the location of the ``minio.exe`` executable, *or* add the path to that directory to the system ``$PATH``:
+
+```sh
+minio.exe server D:\
+```
+
+The MinIO deployment starts using default root credentials `minioadmin:minioadmin`. You can test the deployment using the MinIO Console, an embedded web-based object browser built into MinIO Server. Point a web browser running on the host machine to <http://127.0.0.1:9000> and log in with the root credentials. You can use the Browser to create buckets, upload objects, and browse the contents of the MinIO server.
+
+You can also connect using any S3-compatible tool, such as the MinIO Client `mc` commandline tool. See [Test using MinIO Client `mc`](#test-using-minio-client-mc) for more information on using the `mc` commandline tool. For application developers, see <https://min.io/docs/minio/linux/developers/minio-drivers.html> to view MinIO SDKs for supported languages.
+
+> [!NOTE]
+> Standalone MinIO servers are best suited for early development and evaluation. Certain features such as versioning, object locking, and bucket replication require distributed deploying MinIO with Erasure Coding. For extended development and production, deploy MinIO with Erasure Coding enabled - specifically, with a *minimum* of 4 drives per MinIO server. See [MinIO Erasure Code Overview](https://min.io/docs/minio/linux/operations/concepts/erasure-coding.html#) for more complete documentation.
+
+## Install from Source
+
+Use the following commands to compile and run a standalone MinIO server from source. Source installation is only intended for developers and advanced users. If you do not have a working Golang environment, please follow [How to install Golang](https://golang.org/doc/install). Minimum version required is [go1.24](https://golang.org/dl/#stable)
+
+```sh
+go install github.com/minio/minio@latest
+```
+
+The MinIO deployment starts using default root credentials `minioadmin:minioadmin`. You can test the deployment using the MinIO Console, an embedded web-based object browser built into MinIO Server. Point a web browser running on the host machine to <http://127.0.0.1:9000> and log in with the root credentials. You can use the Browser to create buckets, upload objects, and browse the contents of the MinIO server.
+
+You can also connect using any S3-compatible tool, such as the MinIO Client `mc` commandline tool. See [Test using MinIO Client `mc`](#test-using-minio-client-mc) for more information on using the `mc` commandline tool. For application developers, see <https://min.io/docs/minio/linux/developers/minio-drivers.html> to view MinIO SDKs for supported languages.
+
+> [!NOTE]
+> Standalone MinIO servers are best suited for early development and evaluation. Certain features such as versioning, object locking, and bucket replication require distributed deploying MinIO with Erasure Coding. For extended development and production, deploy MinIO with Erasure Coding enabled - specifically, with a *minimum* of 4 drives per MinIO server. See [MinIO Erasure Code Overview](https://min.io/docs/minio/linux/operations/concepts/erasure-coding.html) for more complete documentation.
+
+MinIO strongly recommends *against* using compiled-from-source MinIO servers for production environments.
+
+## Deployment Recommendations
+
+### Allow port access for Firewalls
+
+By default MinIO uses the port 9000 to listen for incoming connections. If your platform blocks the port by default, you may need to enable access to the port.
+
+### ufw
+
+For hosts with ufw enabled (Debian based distros), you can use `ufw` command to allow traffic to specific ports. Use below command to allow access to port 9000
+
+```sh
+ufw allow 9000
+```
+
+Below command enables all incoming traffic to ports ranging from 9000 to 9010.
+
+```sh
+ufw allow 9000:9010/tcp
+```
+
+### firewall-cmd
+
+For hosts with firewall-cmd enabled (CentOS), you can use `firewall-cmd` command to allow traffic to specific ports. Use below commands to allow access to port 9000
+
+```sh
+firewall-cmd --get-active-zones
+```
+
+This command gets the active zone(s). Now, apply port rules to the relevant zones returned above. For example if the zone is `public`, use
+
+```sh
+firewall-cmd --zone=public --add-port=9000/tcp --permanent
+```
+
+> [!NOTE]
+> `permanent` makes sure the rules are persistent across firewall start, restart or reload. Finally reload the firewall for changes to take effect.
+
+```sh
+firewall-cmd --reload
+```
+
+### iptables
+
+For hosts with iptables enabled (RHEL, CentOS, etc), you can use `iptables` command to enable all traffic coming to specific ports. Use below command to allow
+access to port 9000
+
+```sh
+iptables -A INPUT -p tcp --dport 9000 -j ACCEPT
+service iptables restart
+```
+
+Below command enables all incoming traffic to ports ranging from 9000 to 9010.
+
+```sh
+iptables -A INPUT -p tcp --dport 9000:9010 -j ACCEPT
+service iptables restart
+```
+
+## Test MinIO Connectivity
+
+### Test using MinIO Console
+
+MinIO Server comes with an embedded web based object browser. Point your web browser to <http://127.0.0.1:9000> to ensure your server has started successfully.
+
+> [!NOTE]
+> MinIO runs console on random port by default, if you wish to choose a specific port use `--console-address` to pick a specific interface and port.
+
+### Things to consider
+
+MinIO redirects browser access requests to the configured server port (i.e. `127.0.0.1:9000`) to the configured Console port. MinIO uses the hostname or IP address specified in the request when building the redirect URL. The URL and port *must* be accessible by the client for the redirection to work.
+
+For deployments behind a load balancer, proxy, or ingress rule where the MinIO host IP address or port is not public, use the `MINIO_BROWSER_REDIRECT_URL` environment variable to specify the external hostname for the redirect. The LB/Proxy must have rules for directing traffic to the Console port specifically.
+
+For example, consider a MinIO deployment behind a proxy `https://minio.example.net`, `https://console.minio.example.net` with rules for forwarding traffic on port :9000 and :9001 to MinIO and the MinIO Console respectively on the internal network. Set `MINIO_BROWSER_REDIRECT_URL` to `https://console.minio.example.net` to ensure the browser receives a valid reachable URL.
+
+| Dashboard                                                                                   | Creating a bucket                                                                           |
+| -------------                                                                               | -------------                                                                               |
+| ![Dashboard](https://github.com/minio/minio/blob/master/docs/screenshots/pic1.png?raw=true) | ![Dashboard](https://github.com/minio/minio/blob/master/docs/screenshots/pic2.png?raw=true) |
+
+## Test using MinIO Client `mc`
+
+`mc` provides a modern alternative to UNIX commands like ls, cat, cp, mirror, diff etc. It supports filesystems and Amazon S3 compatible cloud storage services. Follow the MinIO Client [Quickstart Guide](https://min.io/docs/minio/linux/reference/minio-mc.html#quickstart) for further instructions.
+
+## Upgrading MinIO
+
+Upgrades require zero downtime in MinIO, all upgrades are non-disruptive, all transactions on MinIO are atomic. So upgrading all the servers simultaneously is the recommended way to upgrade MinIO.
+
+> [!NOTE]
+> requires internet access to update directly from <https://dl.min.io>, optionally you can host any mirrors at <https://my-artifactory.example.com/minio/>
+
+- For deployments that installed the MinIO server binary by hand, use [`mc admin update`](https://min.io/docs/minio/linux/reference/minio-mc-admin/mc-admin-update.html)
+
+```sh
+mc admin update <minio alias, e.g., myminio>
+```
+
+- For deployments without external internet access (e.g. airgapped environments), download the binary from <https://dl.min.io> and replace the existing MinIO binary let's say for example `/opt/bin/minio`, apply executable permissions `chmod +x /opt/bin/minio` and proceed to perform `mc admin service restart alias/`.
+
+- For installations using Systemd MinIO service, upgrade via RPM/DEB packages **parallelly** on all servers or replace the binary lets say `/opt/bin/minio` on all nodes, apply executable permissions `chmod +x /opt/bin/minio` and process to perform `mc admin service restart alias/`.
+
+### Upgrade Checklist
+
+- Test all upgrades in a lower environment (DEV, QA, UAT) before applying to production. Performing blind upgrades in production environments carries significant risk.
+- Read the release notes for MinIO *before* performing any upgrade, there is no forced requirement to upgrade to latest release upon every release. Some release may not be relevant to your setup, avoid upgrading production environments unnecessarily.
+- If you plan to use `mc admin update`, MinIO process must have write access to the parent directory where the binary is present on the host system.
+- `mc admin update` is not supported and should be avoided in kubernetes/container environments, please upgrade containers by upgrading relevant container images.
+- **We do not recommend upgrading one MinIO server at a time, the product is designed to support parallel upgrades please follow our recommended guidelines.**
+
+## Explore Further
+
+- [MinIO Erasure Code Overview](https://min.io/docs/minio/linux/operations/concepts/erasure-coding.html)
+- [Use `mc` with MinIO Server](https://min.io/docs/minio/linux/reference/minio-mc.html)
+- [Use `minio-go` SDK with MinIO Server](https://min.io/docs/minio/linux/developers/go/minio-go.html)
+- [The MinIO documentation website](https://min.io/docs/minio/linux/index.html)
+
+## Contribute to MinIO Project
+
+Please follow MinIO [Contributor's Guide](https://github.com/minio/minio/blob/master/CONTRIBUTING.md)
+
+## License
+
+- MinIO source is licensed under the [GNU AGPLv3](https://github.com/minio/minio/blob/master/LICENSE).
+- MinIO [documentation](https://github.com/minio/minio/tree/master/docs) is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
+- [License Compliance](https://github.com/minio/minio/blob/master/COMPLIANCE.md)

SECURITY.md

@@ -0,0 +1,42 @@
+# Security Policy
+
+## Supported Versions
+
+We always provide security updates for the [latest release](https://github.com/minio/minio/releases/latest).
+Whenever there is a security update you just need to upgrade to the latest version.
+
+## Reporting a Vulnerability
+
+All security bugs in [minio/minio](https://github,com/minio/minio) (or other minio/* repositories)
+should be reported by email to security@min.io. Your email will be acknowledged within 48 hours,
+and you'll receive a more detailed response to your email within 72 hours indicating the next steps
+in handling your report.
+
+Please, provide a detailed explanation of the issue. In particular, outline the type of the security
+issue (DoS, authentication bypass, information disclose, ...) and the assumptions you're making (e.g. do
+you need access credentials for a successful exploit).
+
+If you have not received a reply to your email within 48 hours or you have not heard from the security team
+for the past five days please contact the security team directly:
+
+- Primary security coordinator: aead@min.io
+- Secondary coordinator: harsha@min.io
+- If you receive no response: dev@min.io
+
+### Disclosure Process
+
+MinIO uses the following disclosure process:
+
+1. Once the security report is received one member of the security team tries to verify and reproduce
+   the issue and determines the impact it has.
+2. A member of the security team will respond and either confirm or reject the security report.
+   If the report is rejected the response explains why.
+3. Code is audited to find any potential similar problems.
+4. Fixes are prepared for the latest release.
+5. On the date that the fixes are applied a security advisory will be published on <https://blog.min.io>.
+   Please inform us in your report email whether MinIO should mention your contribution w.r.t. fixing
+   the security issue. By default MinIO will **not** publish this information to protect your privacy.
+
+This process can take some time, especially when coordination is required with maintainers of other projects.
+Every effort will be made to handle the bug in as timely a manner as possible, however it's important that we
+follow the process described above to ensure that disclosures are handled consistently.

VULNERABILITY_REPORT.md

@@ -0,0 +1,38 @@
+# Vulnerability Management Policy
+
+This document formally describes the process of addressing and managing a
+reported vulnerability that has been found in the MinIO server code base,
+any directly connected ecosystem component or a direct / indirect dependency
+of the code base.
+
+## Scope
+
+The vulnerability management policy described in this document covers the
+process of investigating, assessing and resolving a vulnerability report
+opened by a MinIO employee or an external third party.
+
+Therefore, it lists pre-conditions and actions that should be performed to
+resolve and fix a reported vulnerability.
+
+## Vulnerability Management Process
+
+The vulnerability management process requires that the vulnerability report
+contains the following information:
+
+- The project / component that contains the reported vulnerability.
+- A description of the vulnerability. In particular, the type of the
+   reported vulnerability and how it might be exploited. Alternatively,
+   a well-established vulnerability identifier, e.g. CVE number, can be
+   used instead.
+
+Based on the description mentioned above, a MinIO engineer or security team
+member investigates:
+
+- Whether the reported vulnerability exists.
+- The conditions that are required such that the vulnerability can be exploited.
+- The steps required to fix the vulnerability.
+
+In general, if the vulnerability exists in one of the MinIO code bases
+itself - not in a code dependency - then MinIO will, if possible, fix
+the vulnerability or implement reasonable countermeasures such that the
+vulnerability cannot be exploited anymore.

_config.yml

@@ -0,0 +1 @@
+theme: jekyll-theme-minimal

build.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+
+set -e  # 出错即退出
+
+IMAGE_NAME="plugai"
+CONTAINER_NAME="minio"
+DATA_DIR="/data/updsrv/cloud"
+
+# 可选：配置构建代理（可注释掉或自定义）
+export http_proxy="http://127.0.0.1:7890"
+export https_proxy="http://127.0.0.1:7890"
+
+echo "🧹 Step 1: 删除旧容器和镜像..."
+docker rm -f $CONTAINER_NAME 2>/dev/null || true
+docker rmi -f $IMAGE_NAME:latest 2>/dev/null || true
+
+echo "🛠️ Step 2: 编译 minio 二进制..."
+MINIO_RELEASE=on make
+
+if [ ! -f ./minio ]; then
+  echo "❌ 编译失败，未找到 minio 可执行文件"
+  exit 1
+fi
+
+echo "🐳 Step 3: 构建 Docker 镜像..."
+docker build --build-arg http_proxy=$http_proxy --build-arg https_proxy=$https_proxy -t $IMAGE_NAME:latest .
+
+echo "🚀 Step 4: 运行新容器（使用端口映射）..."
+docker run -d \
+  --name $CONTAINER_NAME \
+  --restart unless-stopped \
+  -p 9000:9000 \
+  -p 9001:9001 \
+  -e MINIO_ROOT_USER=admin \
+  -e MINIO_ROOT_PASSWORD=Admin@123.. \
+  -e MINIO_BROWSER_REDIRECT_URL=https://console.szaiai.com \
+  -v "$DATA_DIR":/data \
+  $IMAGE_NAME:latest server /data --console-address "0.0.0.0:9001"
+
+echo "✅ MinIO 已启动："
+echo "📦 API 接口: http://localhost:9000"
+echo "🖥️ 控制台: http://localhost:9001"

buildscripts/checkdeps.sh

@@ -0,0 +1,143 @@
+#!/usr/bin/env bash
+#
+
+_init() {
+
+	shopt -s extglob
+
+	## Minimum required versions for build dependencies
+	GIT_VERSION="1.0"
+	GO_VERSION="1.16"
+	OSX_VERSION="10.8"
+	KNAME=$(uname -s)
+	ARCH=$(uname -m)
+	case "${KNAME}" in
+	SunOS)
+		ARCH=$(isainfo -k)
+		;;
+	esac
+}
+
+## FIXME:
+## In OSX, 'readlink -f' option does not exist, hence
+## we have our own readlink -f behavior here.
+## Once OSX has the option, below function is good enough.
+##
+## readlink() {
+##     return /bin/readlink -f "$1"
+## }
+##
+readlink() {
+	TARGET_FILE=$1
+
+	cd $(dirname $TARGET_FILE)
+	TARGET_FILE=$(basename $TARGET_FILE)
+
+	# Iterate down a (possible) chain of symlinks
+	while [ -L "$TARGET_FILE" ]; do
+		TARGET_FILE=$(env readlink $TARGET_FILE)
+		cd $(dirname $TARGET_FILE)
+		TARGET_FILE=$(basename $TARGET_FILE)
+	done
+
+	# Compute the canonicalized name by finding the physical path
+	# for the directory we're in and appending the target file.
+	PHYS_DIR=$(pwd -P)
+	RESULT=$PHYS_DIR/$TARGET_FILE
+	echo $RESULT
+}
+
+## FIXME:
+## In OSX, 'sort -V' option does not exist, hence
+## we have our own version compare function.
+## Once OSX has the option, below function is good enough.
+##
+## check_minimum_version() {
+##     versions=($(echo -e "$1\n$2" | sort -V))
+##     return [ "$1" == "${versions[0]}" ]
+## }
+##
+check_minimum_version() {
+	IFS='.' read -r -a varray1 <<<"$1"
+	IFS='.' read -r -a varray2 <<<"$2"
+
+	for i in "${!varray1[@]}"; do
+		if [[ ${varray1[i]} -lt ${varray2[i]} ]]; then
+			return 0
+		elif [[ ${varray1[i]} -gt ${varray2[i]} ]]; then
+			return 1
+		fi
+	done
+
+	return 0
+}
+
+assert_is_supported_arch() {
+	case "${ARCH}" in
+	x86_64 | amd64 | aarch64 | ppc64le | arm* | s390x | loong64 | loongarch64)
+		return
+		;;
+	*)
+		echo "Arch '${ARCH}' is not supported. Supported Arch: [x86_64, amd64, aarch64, ppc64le, arm*, s390x, loong64, loongarch64]"
+		exit 1
+		;;
+	esac
+}
+
+assert_is_supported_os() {
+	case "${KNAME}" in
+	Linux | FreeBSD | OpenBSD | NetBSD | DragonFly | SunOS)
+		return
+		;;
+	Darwin)
+		osx_host_version=$(env sw_vers -productVersion)
+		if ! check_minimum_version "${OSX_VERSION}" "${osx_host_version}"; then
+			echo "OSX version '${osx_host_version}' is not supported. Minimum supported version: ${OSX_VERSION}"
+			exit 1
+		fi
+		return
+		;;
+	*)
+		echo "OS '${KNAME}' is not supported. Supported OS: [Linux, FreeBSD, OpenBSD, NetBSD, Darwin, DragonFly]"
+		exit 1
+		;;
+	esac
+}
+
+assert_check_golang_env() {
+	if ! which go >/dev/null 2>&1; then
+		echo "Cannot find go binary in your PATH configuration, please refer to Go installation document at https://golang.org/doc/install"
+		exit 1
+	fi
+
+	installed_go_version=$(go version | sed 's/^.* go\([0-9.]*\).*$/\1/')
+	if ! check_minimum_version "${GO_VERSION}" "${installed_go_version}"; then
+		echo "Go runtime version '${installed_go_version}' is unsupported. Minimum supported version: ${GO_VERSION} to compile."
+		exit 1
+	fi
+}
+
+assert_check_deps() {
+	# support unusual Git versions such as: 2.7.4 (Apple Git-66)
+	installed_git_version=$(git version | perl -ne '$_ =~ m/git version (.*?)( |$)/; print "$1\n";')
+	if ! check_minimum_version "${GIT_VERSION}" "${installed_git_version}"; then
+		echo "Git version '${installed_git_version}' is not supported. Minimum supported version: ${GIT_VERSION}"
+		exit 1
+	fi
+}
+
+main() {
+	## Check for supported arch
+	assert_is_supported_arch
+
+	## Check for supported os
+	assert_is_supported_os
+
+	## Check for Go environment
+	assert_check_golang_env
+
+	## Check for dependencies
+	assert_check_deps
+}
+
+_init && main "$@"

buildscripts/cross-compile.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+set -e
+# Enable tracing if set.
+[ -n "$BASH_XTRACEFD" ] && set -x
+
+function _init() {
+	## All binaries are static make sure to disable CGO.
+	export CGO_ENABLED=0
+
+	## List of architectures and OS to test coss compilation.
+	SUPPORTED_OSARCH="linux/ppc64le linux/mips64 linux/amd64 linux/arm64 linux/s390x darwin/arm64 darwin/amd64 freebsd/amd64 windows/amd64 linux/arm linux/386 netbsd/amd64 linux/mips openbsd/amd64"
+}
+
+function _build() {
+	local osarch=$1
+	IFS=/ read -r -a arr <<<"$osarch"
+	os="${arr[0]}"
+	arch="${arr[1]}"
+	package=$(go list -f '{{.ImportPath}}')
+	printf -- "--> %15s:%s\n" "${osarch}" "${package}"
+
+	# go build -trimpath to build the binary.
+	export GOOS=$os
+	export GOARCH=$arch
+	export GO111MODULE=on
+	go build -trimpath -tags kqueue -o /dev/null
+}
+
+function main() {
+	echo "Testing builds for OS/Arch: ${SUPPORTED_OSARCH}"
+	for each_osarch in ${SUPPORTED_OSARCH}; do
+		_build "${each_osarch}"
+	done
+}
+
+_init && main "$@"

buildscripts/disable-root.sh

@@ -0,0 +1,124 @@
+#!/bin/bash
+
+set -x
+
+export MINIO_CI_CD=1
+killall -9 minio
+
+rm -rf ${HOME}/tmp/dist
+
+scheme="http"
+nr_servers=4
+
+addr="localhost"
+args=""
+for ((i = 0; i < $((nr_servers)); i++)); do
+	args="$args $scheme://$addr:$((9100 + i))/${HOME}/tmp/dist/path1/$i"
+done
+
+echo $args
+
+for ((i = 0; i < $((nr_servers)); i++)); do
+	(minio server --address ":$((9100 + i))" $args 2>&1 >/tmp/log$i.txt) &
+done
+
+sleep 10s
+
+if [ ! -f ./mc ]; then
+	wget --quiet -O ./mc https://dl.minio.io/client/mc/release/linux-amd64/./mc &&
+		chmod +x mc
+fi
+
+set +e
+
+export MC_HOST_minioadm=http://minioadmin:minioadmin@localhost:9100/
+./mc ready minioadm
+
+./mc ls minioadm/
+
+./mc admin config set minioadm/ api root_access=off
+
+sleep 3s # let things settle a little
+
+./mc ls minioadm/
+if [ $? -eq 0 ]; then
+	echo "listing succeeded, 'minioadmin' was not disabled"
+	exit 1
+fi
+
+set -e
+
+killall -9 minio
+
+export MINIO_API_ROOT_ACCESS=on
+for ((i = 0; i < $((nr_servers)); i++)); do
+	(minio server --address ":$((9100 + i))" $args 2>&1 >/tmp/log$i.txt) &
+done
+
+set +e
+
+./mc ready minioadm/
+
+./mc ls minioadm/
+if [ $? -ne 0 ]; then
+	echo "listing failed, 'minioadmin' should be enabled"
+	exit 1
+fi
+
+killall -9 minio
+
+rm -rf /tmp/multisitea/
+rm -rf /tmp/multisiteb/
+
+echo "Setup site-replication and then disable root credentials"
+
+minio server --address 127.0.0.1:9001 "http://127.0.0.1:9001/tmp/multisitea/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9002/tmp/multisitea/data/disterasure/xl{5...8}" >/tmp/sitea_1.log 2>&1 &
+minio server --address 127.0.0.1:9002 "http://127.0.0.1:9001/tmp/multisitea/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9002/tmp/multisitea/data/disterasure/xl{5...8}" >/tmp/sitea_2.log 2>&1 &
+
+minio server --address 127.0.0.1:9003 "http://127.0.0.1:9003/tmp/multisiteb/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9004/tmp/multisiteb/data/disterasure/xl{5...8}" >/tmp/siteb_1.log 2>&1 &
+minio server --address 127.0.0.1:9004 "http://127.0.0.1:9003/tmp/multisiteb/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9004/tmp/multisiteb/data/disterasure/xl{5...8}" >/tmp/siteb_2.log 2>&1 &
+
+export MC_HOST_sitea=http://minioadmin:minioadmin@127.0.0.1:9001
+export MC_HOST_siteb=http://minioadmin:minioadmin@127.0.0.1:9004
+
+./mc ready sitea
+./mc ready siteb
+
+./mc admin replicate add sitea siteb
+
+./mc admin user add sitea foobar foo12345
+
+./mc admin policy attach sitea/ consoleAdmin --user=foobar
+
+./mc admin user info siteb foobar
+
+killall -9 minio
+
+echo "turning off root access, however site replication must continue"
+export MINIO_API_ROOT_ACCESS=off
+
+minio server --address 127.0.0.1:9001 "http://127.0.0.1:9001/tmp/multisitea/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9002/tmp/multisitea/data/disterasure/xl{5...8}" >/tmp/sitea_1.log 2>&1 &
+minio server --address 127.0.0.1:9002 "http://127.0.0.1:9001/tmp/multisitea/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9002/tmp/multisitea/data/disterasure/xl{5...8}" >/tmp/sitea_2.log 2>&1 &
+
+minio server --address 127.0.0.1:9003 "http://127.0.0.1:9003/tmp/multisiteb/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9004/tmp/multisiteb/data/disterasure/xl{5...8}" >/tmp/siteb_1.log 2>&1 &
+minio server --address 127.0.0.1:9004 "http://127.0.0.1:9003/tmp/multisiteb/data/disterasure/xl{1...4}" \
+	"http://127.0.0.1:9004/tmp/multisiteb/data/disterasure/xl{5...8}" >/tmp/siteb_2.log 2>&1 &
+
+export MC_HOST_sitea=http://foobar:foo12345@127.0.0.1:9001
+export MC_HOST_siteb=http://foobar:foo12345@127.0.0.1:9004
+
+./mc ready sitea
+./mc ready siteb
+
+./mc admin user add sitea foobar-admin foo12345
+
+sleep 2s
+
+./mc admin user info siteb foobar-admin

buildscripts/gen-ldflags.go

@@ -0,0 +1,121 @@
+//go:build ignore
+// +build ignore
+
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 main
+
+import (
+	"fmt"
+	"os"
+	"os/exec"
+	"strconv"
+	"strings"
+	"time"
+)
+
+func genLDFlags(version string) string {
+	releaseTag, date := releaseTag(version)
+	copyrightYear := strconv.Itoa(date.Year())
+	ldflagsStr := "-s -w"
+	ldflagsStr += " -X github.com/minio/minio/cmd.Version=" + version
+	ldflagsStr += " -X github.com/minio/minio/cmd.CopyrightYear=" + copyrightYear
+	ldflagsStr += " -X github.com/minio/minio/cmd.ReleaseTag=" + releaseTag
+	ldflagsStr += " -X github.com/minio/minio/cmd.CommitID=" + commitID()
+	ldflagsStr += " -X github.com/minio/minio/cmd.ShortCommitID=" + commitID()[:12]
+	ldflagsStr += " -X github.com/minio/minio/cmd.GOPATH=" + os.Getenv("GOPATH")
+	ldflagsStr += " -X github.com/minio/minio/cmd.GOROOT=" + os.Getenv("GOROOT")
+	return ldflagsStr
+}
+
+// genReleaseTag prints release tag to the console for easy git tagging.
+func releaseTag(version string) (string, time.Time) {
+	relPrefix := "DEVELOPMENT"
+	if prefix := os.Getenv("MINIO_RELEASE"); prefix != "" {
+		relPrefix = prefix
+	}
+
+	relSuffix := ""
+	if hotfix := os.Getenv("MINIO_HOTFIX"); hotfix != "" {
+		relSuffix = hotfix
+	}
+
+	relTag := strings.Replace(version, " ", "-", -1)
+	relTag = strings.Replace(relTag, ":", "-", -1)
+	t, err := time.Parse("2006-01-02T15-04-05Z", relTag)
+	if err != nil {
+		panic(err)
+	}
+	relTag = strings.Replace(relTag, ",", "", -1)
+	relTag = relPrefix + "." + relTag
+	if relSuffix != "" {
+		relTag += "." + relSuffix
+	}
+
+	return relTag, t
+}
+
+// commitID returns the abbreviated commit-id hash of the last commit.
+func commitID() string {
+	// git log --format="%H" -n1
+	var (
+		commit []byte
+		err    error
+	)
+	cmdName := "git"
+	cmdArgs := []string{"log", "--format=%H", "-n1"}
+	if commit, err = exec.Command(cmdName, cmdArgs...).Output(); err != nil {
+		fmt.Fprintln(os.Stderr, "Error generating git commit-id: ", err)
+		os.Exit(1)
+	}
+
+	return strings.TrimSpace(string(commit))
+}
+
+func commitTime() time.Time {
+	// git log --format=%cD -n1
+	var (
+		commitUnix []byte
+		err        error
+	)
+	cmdName := "git"
+	cmdArgs := []string{"log", "--format=%cI", "-n1"}
+	if commitUnix, err = exec.Command(cmdName, cmdArgs...).Output(); err != nil {
+		fmt.Fprintln(os.Stderr, "Error generating git commit-time: ", err)
+		os.Exit(1)
+	}
+
+	t, err := time.Parse(time.RFC3339, strings.TrimSpace(string(commitUnix)))
+	if err != nil {
+		fmt.Fprintln(os.Stderr, "Error generating git commit-time: ", err)
+		os.Exit(1)
+	}
+
+	return t.UTC()
+}
+
+func main() {
+	var version string
+	if len(os.Args) > 1 {
+		version = os.Args[1]
+	} else {
+		version = commitTime().Format(time.RFC3339)
+	}
+
+	fmt.Println(genLDFlags(version))
+}

buildscripts/heal-inconsistent-versions.sh

@@ -0,0 +1,92 @@
+#!/bin/bash -e
+
+set -E
+set -o pipefail
+set -x
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+function start_minio_4drive() {
+	start_port=$1
+
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	export MC_HOST_minio="http://minio:minio123@127.0.0.1:${start_port}/"
+	unset MINIO_KMS_AUTO_ENCRYPTION # do not auto-encrypt objects
+	export MINIO_CI_CD=1
+
+	mkdir ${WORK_DIR}
+	C_PWD=${PWD}
+	if [ ! -x "$PWD/mc" ]; then
+		MC_BUILD_DIR="mc-$RANDOM"
+		if ! git clone --quiet https://github.com/minio/mc "$MC_BUILD_DIR"; then
+			echo "failed to download https://github.com/minio/mc"
+			purge "${MC_BUILD_DIR}"
+			exit 1
+		fi
+
+		(cd "${MC_BUILD_DIR}" && go build -o "$C_PWD/mc")
+
+		# remove mc source.
+		purge "${MC_BUILD_DIR}"
+	fi
+
+	"${MINIO[@]}" --address ":$start_port" "${WORK_DIR}/disk{1...4}" >"${WORK_DIR}/server1.log" 2>&1 &
+	pid=$!
+	disown $pid
+	sleep 5
+
+	if ! ps -p ${pid} 1>&2 >/dev/null; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	"${PWD}/mc" mb --with-versioning minio/bucket
+
+	for i in $(seq 1 4); do
+		"${PWD}/mc" cp /etc/hosts minio/bucket/testobj
+
+		sudo chown -R root. "${WORK_DIR}/disk${i}"
+
+		"${PWD}/mc" cp /etc/hosts minio/bucket/testobj
+
+		sudo chown -R ${USER}. "${WORK_DIR}/disk${i}"
+	done
+
+	for vid in $("${PWD}/mc" ls --json --versions minio/bucket/testobj | jq -r .versionId); do
+		"${PWD}/mc" cat --vid "${vid}" minio/bucket/testobj | md5sum
+	done
+
+	pkill minio
+	sleep 3
+}
+
+function main() {
+	start_port=$(shuf -i 10000-65000 -n 1)
+
+	start_minio_4drive ${start_port}
+}
+
+function purge() {
+	rm -rf "$1"
+}
+
+(main "$@")
+rv=$?
+purge "$WORK_DIR"
+exit "$rv"

buildscripts/heal-manual.go

@@ -0,0 +1,86 @@
+//go:build ignore
+// +build ignore
+
+//
+// MinIO Object Storage (c) 2022 MinIO, Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//      http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"log"
+	"os"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+)
+
+func main() {
+	// Note: YOUR-ACCESSKEYID, YOUR-SECRETACCESSKEY are
+	// dummy values, please replace them with original values.
+
+	// API requests are secure (HTTPS) if secure=true and insecure (HTTP) otherwise.
+	// New returns an MinIO Admin client object.
+	madmClnt, err := madmin.New(os.Args[1], os.Args[2], os.Args[3], false)
+	if err != nil {
+		log.Fatalln(err)
+	}
+
+	opts := madmin.HealOpts{
+		Recursive: true,                  // recursively heal all objects at 'prefix'
+		Remove:    true,                  // remove content that has lost quorum and not recoverable
+		ScanMode:  madmin.HealNormalScan, // by default do not do 'deep' scanning
+	}
+
+	start, _, err := madmClnt.Heal(context.Background(), "healing-rewrite-bucket", "", opts, "", false, false)
+	if err != nil {
+		log.Fatalln(err)
+	}
+	fmt.Println("Healstart sequence ===")
+	enc := json.NewEncoder(os.Stdout)
+	if err = enc.Encode(&start); err != nil {
+		log.Fatalln(err)
+	}
+
+	fmt.Println()
+	for {
+		_, status, err := madmClnt.Heal(context.Background(), "healing-rewrite-bucket", "", opts, start.ClientToken, false, false)
+		if status.Summary == "finished" {
+			fmt.Println("Healstatus on items ===")
+			for _, item := range status.Items {
+				if err = enc.Encode(&item); err != nil {
+					log.Fatalln(err)
+				}
+			}
+			break
+		}
+		if status.Summary == "stopped" {
+			fmt.Println("Healstatus on items ===")
+			fmt.Println("Heal failed with", status.FailureDetail)
+			break
+		}
+
+		for _, item := range status.Items {
+			if err = enc.Encode(&item); err != nil {
+				log.Fatalln(err)
+			}
+		}
+
+		time.Sleep(time.Second)
+	}
+}

buildscripts/minio-iam-ldap-upgrade-import-test.sh

@@ -0,0 +1,127 @@
+#!/bin/bash
+
+# This script is used to test the migration of IAM content from old minio
+# instance to new minio instance.
+#
+# To run it locally, start the LDAP server in github.com/minio/minio-iam-testing
+# repo (e.g. make podman-run), and then run this script.
+#
+# This script assumes that LDAP server is at:
+#
+#   `localhost:389`
+#
+# if this is not the case, set the environment variable
+# `_MINIO_LDAP_TEST_SERVER`.
+
+OLD_VERSION=RELEASE.2024-03-26T22-10-45Z
+OLD_BINARY_LINK=https://dl.min.io/server/minio/release/linux-amd64/archive/minio.${OLD_VERSION}
+
+__init__() {
+	if which curl &>/dev/null; then
+		echo "curl is already installed"
+	else
+		echo "Installing curl:"
+		sudo apt install curl -y
+	fi
+
+	export GOPATH=/tmp/gopath
+	export PATH="${PATH}":"${GOPATH}"/bin
+
+	if which mc &>/dev/null; then
+		echo "mc is already installed"
+	else
+		echo "Installing mc:"
+		go install github.com/minio/mc@latest
+	fi
+
+	if [ ! -x ./minio.${OLD_VERSION} ]; then
+		echo "Downloading minio.${OLD_VERSION} binary"
+		curl -o minio.${OLD_VERSION} ${OLD_BINARY_LINK}
+		chmod +x minio.${OLD_VERSION}
+	fi
+
+	if [ -z "$_MINIO_LDAP_TEST_SERVER" ]; then
+		export _MINIO_LDAP_TEST_SERVER=localhost:389
+		echo "Using default LDAP endpoint: $_MINIO_LDAP_TEST_SERVER"
+	fi
+
+	rm -rf /tmp/data
+}
+
+create_iam_content_in_old_minio() {
+	echo "Creating IAM content in old minio instance."
+
+	MINIO_CI_CD=1 ./minio.${OLD_VERSION} server /tmp/data/{1...4} &
+	sleep 5
+
+	set -x
+	mc alias set old-minio http://localhost:9000 minioadmin minioadmin
+	mc ready old-minio
+	mc idp ldap add old-minio \
+		server_addr=localhost:389 \
+		server_insecure=on \
+		lookup_bind_dn=cn=admin,dc=min,dc=io \
+		lookup_bind_password=admin \
+		user_dn_search_base_dn=dc=min,dc=io \
+		user_dn_search_filter="(uid=%s)" \
+		group_search_base_dn=ou=swengg,dc=min,dc=io \
+		group_search_filter="(&(objectclass=groupOfNames)(member=%d))"
+	mc admin service restart old-minio
+
+	mc idp ldap policy attach old-minio readwrite --user=UID=dillon,ou=people,ou=swengg,dc=min,dc=io
+	mc idp ldap policy attach old-minio readwrite --group=CN=project.c,ou=groups,ou=swengg,dc=min,dc=io
+
+	mc idp ldap policy entities old-minio
+
+	mc admin cluster iam export old-minio
+	set +x
+
+	mc admin service stop old-minio
+}
+
+import_iam_content_in_new_minio() {
+	echo "Importing IAM content in new minio instance."
+	# Assume current minio binary exists.
+	MINIO_CI_CD=1 ./minio server /tmp/data/{1...4} &
+	sleep 5
+
+	set -x
+	mc alias set new-minio http://localhost:9000 minioadmin minioadmin
+	echo "BEFORE IMPORT mappings:"
+	mc ready new-minio
+	mc idp ldap policy entities new-minio
+	mc admin cluster iam import new-minio ./old-minio-iam-info.zip
+	echo "AFTER IMPORT mappings:"
+	mc idp ldap policy entities new-minio
+	set +x
+
+	# mc admin service stop new-minio
+}
+
+verify_iam_content_in_new_minio() {
+	output=$(mc idp ldap policy entities new-minio --json)
+
+	groups=$(echo "$output" | jq -r '.result.policyMappings[] | select(.policy == "readwrite") | .groups[]')
+	if [ "$groups" != "cn=project.c,ou=groups,ou=swengg,dc=min,dc=io" ]; then
+		echo "Failed to verify groups: $groups"
+		exit 1
+	fi
+
+	users=$(echo "$output" | jq -r '.result.policyMappings[] | select(.policy == "readwrite") | .users[]')
+	if [ "$users" != "uid=dillon,ou=people,ou=swengg,dc=min,dc=io" ]; then
+		echo "Failed to verify users: $users"
+		exit 1
+	fi
+
+	mc admin service stop new-minio
+}
+
+main() {
+	create_iam_content_in_old_minio
+
+	import_iam_content_in_new_minio
+
+	verify_iam_content_in_new_minio
+}
+
+(__init__ "$@" && main "$@")

buildscripts/minio-upgrade.sh

@@ -0,0 +1,113 @@
+#!/bin/bash
+
+trap 'cleanup $LINENO' ERR
+
+# shellcheck disable=SC2120
+cleanup() {
+	MINIO_VERSION=dev /tmp/gopath/bin/docker-compose \
+		-f "buildscripts/upgrade-tests/compose.yml" \
+		down || true
+
+	MINIO_VERSION=dev /tmp/gopath/bin/docker-compose \
+		-f "buildscripts/upgrade-tests/compose.yml" \
+		rm || true
+
+	for volume in $(docker volume ls -q | grep upgrade); do
+		docker volume rm ${volume} || true
+	done
+
+	docker volume prune -f
+	docker system prune -f || true
+	docker volume prune -f || true
+	docker volume rm $(docker volume ls -q -f dangling=true) || true
+}
+
+verify_checksum_after_heal() {
+	local sum1
+	sum1=$(curl -s "$2" | sha256sum)
+	mc admin heal --json -r "$1" >/dev/null # test after healing
+	local sum1_heal
+	sum1_heal=$(curl -s "$2" | sha256sum)
+
+	if [ "${sum1_heal}" != "${sum1}" ]; then
+		echo "mismatch expected ${sum1_heal}, got ${sum1}"
+		exit 1
+	fi
+}
+
+verify_checksum_mc() {
+	local expected
+	expected=$(mc cat "$1" | sha256sum)
+	local got
+	got=$(mc cat "$2" | sha256sum)
+
+	if [ "${expected}" != "${got}" ]; then
+		echo "mismatch - expected ${expected}, got ${got}"
+		exit 1
+	fi
+	echo "matches - ${expected}, got ${got}"
+}
+
+add_alias() {
+	for i in $(seq 1 4); do
+		echo "... attempting to add alias $i"
+		until (mc alias set minio http://127.0.0.1:9000 minioadmin minioadmin); do
+			echo "...waiting... for 5secs" && sleep 5
+		done
+	done
+
+	echo "Sleeping for nginx"
+	sleep 20
+}
+
+__init__() {
+	sudo apt install curl -y
+	export GOPATH=/tmp/gopath
+	export PATH=${PATH}:${GOPATH}/bin
+
+	go install github.com/minio/mc@latest
+
+	## this is needed because github actions don't have
+	## docker-compose on all runners
+	COMPOSE_VERSION=v2.35.1
+	mkdir -p /tmp/gopath/bin/
+	wget -O /tmp/gopath/bin/docker-compose https://github.com/docker/compose/releases/download/${COMPOSE_VERSION}/docker-compose-linux-x86_64
+	chmod +x /tmp/gopath/bin/docker-compose
+
+	cleanup
+
+	TAG=minio/minio:dev make docker
+
+	MINIO_VERSION=RELEASE.2019-12-19T22-52-26Z docker-compose \
+		-f "buildscripts/upgrade-tests/compose.yml" \
+		up -d --build
+
+	add_alias
+
+	mc mb minio/minio-test/
+	mc cp ./minio minio/minio-test/to-read/
+	mc cp /etc/hosts minio/minio-test/to-read/hosts
+	mc anonymous set download minio/minio-test
+
+	verify_checksum_mc ./minio minio/minio-test/to-read/minio
+
+	curl -s http://127.0.0.1:9000/minio-test/to-read/hosts | sha256sum
+
+	MINIO_VERSION=dev /tmp/gopath/bin/docker-compose -f "buildscripts/upgrade-tests/compose.yml" stop
+}
+
+main() {
+	MINIO_VERSION=dev /tmp/gopath/bin/docker-compose -f "buildscripts/upgrade-tests/compose.yml" up -d --build
+
+	add_alias
+
+	verify_checksum_after_heal minio/minio-test http://127.0.0.1:9000/minio-test/to-read/hosts
+
+	verify_checksum_mc ./minio minio/minio-test/to-read/minio
+
+	verify_checksum_mc /etc/hosts minio/minio-test/to-read/hosts
+
+	cleanup
+}
+
+(__init__ "$@" && main "$@")

buildscripts/multipart-quorum-test.sh

@@ -0,0 +1,126 @@
+#!/bin/bash
+
+if [ -n "$TEST_DEBUG" ]; then
+	set -x
+fi
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+trap 'catch $LINENO' ERR
+
+function purge() {
+	rm -rf "$1"
+}
+
+# shellcheck disable=SC2120
+catch() {
+	if [ $# -ne 0 ]; then
+		echo "error on line $1"
+	fi
+
+	echo "Cleaning up instances of MinIO"
+	pkill minio || true
+	pkill -9 minio || true
+	purge "$WORK_DIR"
+	if [ $# -ne 0 ]; then
+		exit $#
+	fi
+}
+
+catch
+
+function start_minio_10drive() {
+	start_port=$1
+
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	export MC_HOST_minio="http://minio:minio123@127.0.0.1:${start_port}/"
+	unset MINIO_KMS_AUTO_ENCRYPTION # do not auto-encrypt objects
+	export MINIO_CI_CD=1
+
+	mkdir ${WORK_DIR}
+	C_PWD=${PWD}
+	if [ ! -x "$PWD/mc" ]; then
+		MC_BUILD_DIR="mc-$RANDOM"
+		if ! git clone --quiet https://github.com/minio/mc "$MC_BUILD_DIR"; then
+			echo "failed to download https://github.com/minio/mc"
+			purge "${MC_BUILD_DIR}"
+			exit 1
+		fi
+
+		(cd "${MC_BUILD_DIR}" && go build -o "$C_PWD/mc")
+
+		# remove mc source.
+		purge "${MC_BUILD_DIR}"
+	fi
+
+	"${MINIO[@]}" --address ":$start_port" "${WORK_DIR}/disk{1...10}" >"${WORK_DIR}/server1.log" 2>&1 &
+	pid=$!
+	disown $pid
+	sleep 5
+
+	if ! ps -p ${pid} 1>&2 >/dev/null; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	"${PWD}/mc" mb --with-versioning minio/bucket
+
+	export AWS_ACCESS_KEY_ID=minio
+	export AWS_SECRET_ACCESS_KEY=minio123
+	aws --endpoint-url http://localhost:"$start_port" s3api create-multipart-upload --bucket bucket --key obj-1 >upload-id.json
+	uploadId=$(jq -r '.UploadId' upload-id.json)
+
+	truncate -s 5MiB file-5mib
+	for i in {1..2}; do
+		aws --endpoint-url http://localhost:"$start_port" s3api upload-part \
+			--upload-id "$uploadId" --bucket bucket --key obj-1 \
+			--part-number "$i" --body ./file-5mib
+	done
+	for i in {1..6}; do
+		find ${WORK_DIR}/disk${i}/.minio.sys/multipart/ -type f -name "part.1" -delete
+	done
+	cat <<EOF >parts.json
+{
+    "Parts": [
+        {
+            "PartNumber": 1,
+            "ETag": "5f363e0e58a95f06cbe9bbc662c5dfb6"
+        },
+        {
+            "PartNumber": 2,
+            "ETag": "5f363e0e58a95f06cbe9bbc662c5dfb6"
+        }
+    ]
+}
+EOF
+	err=$(aws --endpoint-url http://localhost:"$start_port" s3api complete-multipart-upload --upload-id "$uploadId" --bucket bucket --key obj-1 --multipart-upload file://./parts.json 2>&1)
+	rv=$?
+	if [ $rv -eq 0 ]; then
+		echo "Failed to receive an error"
+		exit 1
+	fi
+	echo "Received an error during complete-multipart as expected: $err"
+}
+
+function main() {
+	start_port=$(shuf -i 10000-65000 -n 1)
+	start_minio_10drive ${start_port}
+}
+
+main "$@"

buildscripts/race.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+
+set -e
+
+export GORACE="history_size=7"
+export MINIO_API_REQUESTS_MAX=10000
+
+for d in $(go list ./...); do
+	CGO_ENABLED=1 go test -v -race --timeout 100m "$d"
+done

buildscripts/resolve-right-versions.sh

@@ -0,0 +1,72 @@
+#!/bin/bash -e
+
+set -E
+set -o pipefail
+set -x
+set -e
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+function start_minio_5drive() {
+	start_port=$1
+
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	export MC_HOST_minio="http://minio:minio123@127.0.0.1:${start_port}/"
+	unset MINIO_KMS_AUTO_ENCRYPTION # do not auto-encrypt objects
+	export MINIO_CI_CD=1
+
+	MC_BUILD_DIR="mc-$RANDOM"
+	if ! git clone --quiet https://github.com/minio/mc "$MC_BUILD_DIR"; then
+		echo "failed to download https://github.com/minio/mc"
+		purge "${MC_BUILD_DIR}"
+		exit 1
+	fi
+
+	(cd "${MC_BUILD_DIR}" && go build -o "$WORK_DIR/mc")
+
+	# remove mc source.
+	purge "${MC_BUILD_DIR}"
+
+	"${WORK_DIR}/mc" cp --quiet -r "buildscripts/cicd-corpus/" "${WORK_DIR}/cicd-corpus/"
+
+	"${MINIO[@]}" --address ":$start_port" "${WORK_DIR}/cicd-corpus/disk{1...5}" >"${WORK_DIR}/server1.log" 2>&1 &
+	pid=$!
+	disown $pid
+	sleep 5
+
+	if ! ps -p ${pid} 1>&2 >/dev/null; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	"${WORK_DIR}/mc" stat minio/bucket/testobj
+
+	pkill minio
+	sleep 3
+}
+
+function main() {
+	start_port=$(shuf -i 10000-65000 -n 1)
+
+	start_minio_5drive ${start_port}
+}
+
+function purge() {
+	rm -rf "$1"
+}
+
+(main "$@")
+rv=$?
+purge "$WORK_DIR"
+exit "$rv"

buildscripts/rewrite-old-new.sh

@@ -0,0 +1,157 @@
+#!/bin/bash -e
+
+set -E
+set -o pipefail
+set -x
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO_OLD=("$PWD/minio.RELEASE.2020-10-28T08-16-50Z" --config-dir "$MINIO_CONFIG_DIR" server)
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+function download_old_release() {
+	if [ ! -f minio.RELEASE.2020-10-28T08-16-50Z ]; then
+		curl --silent -O https://dl.minio.io/server/minio/release/linux-amd64/archive/minio.RELEASE.2020-10-28T08-16-50Z
+		chmod a+x minio.RELEASE.2020-10-28T08-16-50Z
+	fi
+}
+
+function verify_rewrite() {
+	start_port=$1
+
+	export MINIO_ACCESS_KEY=minio
+	export MINIO_SECRET_KEY=minio123
+	export MC_HOST_minio="http://minio:minio123@127.0.0.1:${start_port}/"
+	unset MINIO_KMS_AUTO_ENCRYPTION # do not auto-encrypt objects
+	export MINIO_CI_CD=1
+
+	MC_BUILD_DIR="mc-$RANDOM"
+	if ! git clone --quiet https://github.com/minio/mc "$MC_BUILD_DIR"; then
+		echo "failed to download https://github.com/minio/mc"
+		purge "${MC_BUILD_DIR}"
+		exit 1
+	fi
+
+	(cd "${MC_BUILD_DIR}" && go build -o "$WORK_DIR/mc")
+
+	# remove mc source.
+	purge "${MC_BUILD_DIR}"
+
+	"${MINIO_OLD[@]}" --address ":$start_port" "${WORK_DIR}/xl{1...16}" >"${WORK_DIR}/server1.log" 2>&1 &
+	pid=$!
+	disown $pid
+
+	"${WORK_DIR}/mc" ready minio/
+
+	if ! ps -p ${pid} 1>&2 >/dev/null; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	"${WORK_DIR}/mc" mb minio/healing-rewrite-bucket --quiet --with-lock
+	"${WORK_DIR}/mc" cp \
+		buildscripts/verify-build.sh \
+		minio/healing-rewrite-bucket/ \
+		--disable-multipart --quiet
+
+	"${WORK_DIR}/mc" cp \
+		buildscripts/verify-build.sh \
+		minio/healing-rewrite-bucket/ \
+		--disable-multipart --quiet
+
+	"${WORK_DIR}/mc" cp \
+		buildscripts/verify-build.sh \
+		minio/healing-rewrite-bucket/ \
+		--disable-multipart --quiet
+
+	kill ${pid}
+	sleep 3
+
+	"${MINIO[@]}" --address ":$start_port" "${WORK_DIR}/xl{1...16}" >"${WORK_DIR}/server1.log" 2>&1 &
+	pid=$!
+	disown $pid
+
+	"${WORK_DIR}/mc" ready minio/
+
+	if ! ps -p ${pid} 1>&2 >/dev/null; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	if ! ./s3-check-md5 \
+		-debug \
+		-versions \
+		-access-key minio \
+		-secret-key minio123 \
+		-endpoint "http://127.0.0.1:${start_port}/" 2>&1 | grep INTACT; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		mkdir -p inspects
+		(
+			cd inspects
+			"${WORK_DIR}/mc" admin inspect minio/healing-rewrite-bucket/verify-build.sh/**
+		)
+
+		"${WORK_DIR}/mc" mb play/inspects
+		"${WORK_DIR}/mc" mirror inspects play/inspects
+
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	go run ./buildscripts/heal-manual.go "127.0.0.1:${start_port}" "minio" "minio123"
+	sleep 1
+
+	if ! ./s3-check-md5 \
+		-debug \
+		-versions \
+		-access-key minio \
+		-secret-key minio123 \
+		-endpoint http://127.0.0.1:${start_port}/ 2>&1 | grep INTACT; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		mkdir -p inspects
+		(
+			cd inspects
+			"${WORK_DIR}/mc" admin inspect minio/healing-rewrite-bucket/verify-build.sh/**
+		)
+
+		"${WORK_DIR}/mc" mb play/inspects
+		"${WORK_DIR}/mc" mirror inspects play/inspects
+
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	kill ${pid}
+}
+
+function main() {
+	download_old_release
+
+	start_port=$(shuf -i 10000-65000 -n 1)
+
+	verify_rewrite ${start_port}
+}
+
+function purge() {
+	rm -rf "$1"
+}
+
+(main "$@")
+rv=$?
+purge "$WORK_DIR"
+exit "$rv"

buildscripts/test-timeout.sh

@@ -0,0 +1,137 @@
+#!/bin/bash
+
+if [ -n "$TEST_DEBUG" ]; then
+	set -x
+fi
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+trap 'catch $LINENO' ERR
+
+function purge() {
+	rm -rf "$1"
+}
+
+# shellcheck disable=SC2120
+catch() {
+	if [ $# -ne 0 ]; then
+		echo "error on line $1"
+	fi
+
+	echo "Cleaning up instances of MinIO"
+	pkill minio || true
+	pkill -9 minio || true
+	purge "$WORK_DIR"
+	if [ $# -ne 0 ]; then
+		exit $#
+	fi
+}
+
+catch
+
+function gen_put_request() {
+	hdr_sleep=$1
+	body_sleep=$2
+
+	echo "PUT /testbucket/testobject HTTP/1.1"
+	sleep $hdr_sleep
+	echo "Host: foo-header"
+	echo "User-Agent: curl/8.2.1"
+	echo "Accept: */*"
+	echo "Content-Length: 30"
+	echo ""
+
+	sleep $body_sleep
+	echo "random line 0"
+	echo "random line 1"
+	echo ""
+	echo ""
+}
+
+function send_put_object_request() {
+	hdr_timeout=$1
+	body_timeout=$2
+
+	start=$(date +%s)
+	timeout 5m bash -c "gen_put_request $hdr_timeout $body_timeout | netcat 127.0.0.1 $start_port | read" || return -1
+	[ $(($(date +%s) - start)) -gt $((srv_hdr_timeout + srv_idle_timeout + 1)) ] && return -1
+	return 0
+}
+
+function test_minio_with_timeout() {
+	start_port=$1
+
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	export MC_HOST_minio="http://minio:minio123@127.0.0.1:${start_port}/"
+	export MINIO_CI_CD=1
+
+	mkdir ${WORK_DIR}
+	C_PWD=${PWD}
+	if [ ! -x "$PWD/mc" ]; then
+		MC_BUILD_DIR="mc-$RANDOM"
+		if ! git clone --quiet https://github.com/minio/mc "$MC_BUILD_DIR"; then
+			echo "failed to download https://github.com/minio/mc"
+			purge "${MC_BUILD_DIR}"
+			exit 1
+		fi
+
+		(cd "${MC_BUILD_DIR}" && go build -o "$C_PWD/mc")
+
+		# remove mc source.
+		purge "${MC_BUILD_DIR}"
+	fi
+
+	"${MINIO[@]}" --address ":$start_port" --read-header-timeout ${srv_hdr_timeout}s --idle-timeout ${srv_idle_timeout}s "${WORK_DIR}/disk/" >"${WORK_DIR}/server1.log" 2>&1 &
+	pid=$!
+	disown $pid
+	sleep 1
+
+	if ! ps -p ${pid} 1>&2 >/dev/null; then
+		echo "server1 log:"
+		cat "${WORK_DIR}/server1.log"
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	set -e
+
+	"${PWD}/mc" mb minio/testbucket
+	"${PWD}/mc" anonymous set public minio/testbucket
+
+	# slow header writing
+	send_put_object_request 20 0 && exit -1
+	"${PWD}/mc" stat minio/testbucket/testobject && exit -1
+
+	# quick header write and slow bodywrite
+	send_put_object_request 0 40 && exit -1
+	"${PWD}/mc" stat minio/testbucket/testobject && exit -1
+
+	# quick header and body write
+	send_put_object_request 1 1 || exit -1
+	"${PWD}/mc" stat minio/testbucket/testobject || exit -1
+}
+
+function main() {
+	export start_port=$(shuf -i 10000-65000 -n 1)
+	export srv_hdr_timeout=5
+	export srv_idle_timeout=5
+	export -f gen_put_request
+
+	test_minio_with_timeout ${start_port}
+}
+
+main "$@"

buildscripts/upgrade-tests/compose.yml

@@ -0,0 +1,74 @@
+# Settings and configurations that are common for all containers
+x-minio-common: &minio-common
+  image: minio/minio:${MINIO_VERSION}
+  command: server http://minio{1...4}/data{1...3}
+  env_file:
+    - ./minio.env
+  expose:
+    - "9000"
+    - "9001"
+
+# starts 4 docker containers running minio server instances.
+# using nginx reverse proxy, load balancing, you can access
+# it through port 9000.
+services:
+  minio1:
+    <<: *minio-common
+    hostname: minio1
+    volumes:
+      - data1-1:/data1
+      - data1-2:/data2
+      - data1-3:/data3
+
+  minio2:
+    <<: *minio-common
+    hostname: minio2
+    volumes:
+      - data2-1:/data1
+      - data2-2:/data2
+      - data2-3:/data3
+
+  minio3:
+    <<: *minio-common
+    hostname: minio3
+    volumes:
+      - data3-1:/data1
+      - data3-2:/data2
+      - data3-3:/data3
+
+  minio4:
+    <<: *minio-common
+    hostname: minio4
+    volumes:
+      - data4-1:/data1
+      - data4-2:/data2
+      - data4-3:/data3
+
+  nginx:
+    image: nginx:1.19.2-alpine
+    volumes:
+      - ./nginx.conf:/etc/nginx/nginx.conf:ro
+    ports:
+    - "9000:9000"
+    - "9001:9001"
+    depends_on:
+      - minio1
+      - minio2
+      - minio3
+      - minio4
+
+## By default this config uses default local driver,
+## For custom volumes replace with volume driver configuration.
+volumes:
+  data1-1:
+  data1-2:
+  data1-3:
+  data2-1:
+  data2-2:
+  data2-3:
+  data3-1:
+  data3-2:
+  data3-3:
+  data4-1:
+  data4-2:
+  data4-3:

buildscripts/upgrade-tests/minio.env

@@ -0,0 +1,3 @@
+MINIO_ACCESS_KEY=minioadmin
+MINIO_SECRET_KEY=minioadmin
+MINIO_BROWSER=off

buildscripts/upgrade-tests/nginx.conf

@@ -0,0 +1,68 @@
+user  nginx;
+worker_processes  auto;
+
+error_log  /var/log/nginx/error.log warn;
+pid        /var/run/nginx.pid;
+
+
+events {
+    worker_connections  1024;
+}
+
+
+http {
+    include       /etc/nginx/mime.types;
+    default_type  application/octet-stream;
+
+    log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '
+                      '$status $body_bytes_sent "$http_referer" '
+                      '"$http_user_agent" "$http_x_forwarded_for"';
+
+    access_log  /var/log/nginx/access.log  main;
+
+    sendfile        on;
+    #tcp_nopush     on;
+
+    keepalive_timeout  65;
+
+    #gzip  on;
+
+    # include /etc/nginx/conf.d/*.conf;
+
+    upstream minio {
+        server minio1:9000;
+        server minio2:9000;
+        server minio3:9000;
+        server minio4:9000;
+    }
+
+    # main minio
+    server {
+        listen       9000;
+        listen  [::]:9000;
+        server_name  localhost;
+
+         # To allow special characters in headers
+         ignore_invalid_headers off;
+         # Allow any size file to be uploaded.
+         # Set to a value such as 1000m; to restrict file size to a specific value
+         client_max_body_size 0;
+         # To disable buffering
+         proxy_buffering off;
+
+        location / {
+            proxy_set_header Host $http_host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+            proxy_set_header X-Forwarded-Proto $scheme;
+
+            proxy_connect_timeout 300;
+            # Default is HTTP/1, keepalive is only enabled in HTTP/1.1
+            proxy_http_version 1.1;
+            proxy_set_header Connection "";
+            chunked_transfer_encoding off;
+
+            proxy_pass http://minio;
+        }
+    }
+}

buildscripts/verify-build.sh

@@ -0,0 +1,298 @@
+#!/bin/bash
+#
+
+set -e
+set -E
+set -o pipefail
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+
+export MINT_MODE=core
+export MINT_DATA_DIR="$WORK_DIR/data"
+export SERVER_ENDPOINT="127.0.0.1:9000"
+export MC_HOST_verify="http://minio:minio123@${SERVER_ENDPOINT}/"
+export MC_HOST_verify_ipv6="http://minio:minio123@[::1]:9000/"
+export ACCESS_KEY="minio"
+export SECRET_KEY="minio123"
+export ENABLE_HTTPS=0
+export GO111MODULE=on
+export GOGC=25
+export ENABLE_ADMIN=1
+export MINIO_CI_CD=1
+
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR")
+
+FILE_1_MB="$MINT_DATA_DIR/datafile-1-MB"
+FILE_65_MB="$MINT_DATA_DIR/datafile-65-MB"
+
+FUNCTIONAL_TESTS="$WORK_DIR/functional-tests.sh"
+
+function start_minio_fs() {
+	export MINIO_ROOT_USER=$ACCESS_KEY
+	export MINIO_ROOT_PASSWORD=$SECRET_KEY
+	"${MINIO[@]}" server "${WORK_DIR}/fs-disk" >"$WORK_DIR/fs-minio.log" 2>&1 &
+
+	"${WORK_DIR}/mc" ready verify
+}
+
+function start_minio_erasure() {
+	"${MINIO[@]}" server "${WORK_DIR}/erasure-disk1" "${WORK_DIR}/erasure-disk2" "${WORK_DIR}/erasure-disk3" "${WORK_DIR}/erasure-disk4" >"$WORK_DIR/erasure-minio.log" 2>&1 &
+
+	"${WORK_DIR}/mc" ready verify
+}
+
+function start_minio_erasure_sets() {
+	export MINIO_ENDPOINTS="${WORK_DIR}/erasure-disk-sets{1...32}"
+	"${MINIO[@]}" server >"$WORK_DIR/erasure-minio-sets.log" 2>&1 &
+
+	"${WORK_DIR}/mc" ready verify
+}
+
+function start_minio_pool_erasure_sets() {
+	export MINIO_ROOT_USER=$ACCESS_KEY
+	export MINIO_ROOT_PASSWORD=$SECRET_KEY
+	export MINIO_ENDPOINTS="http://127.0.0.1:9000${WORK_DIR}/pool-disk-sets{1...4} http://127.0.0.1:9001${WORK_DIR}/pool-disk-sets{5...8}"
+	"${MINIO[@]}" server --address ":9000" >"$WORK_DIR/pool-minio-9000.log" 2>&1 &
+	"${MINIO[@]}" server --address ":9001" >"$WORK_DIR/pool-minio-9001.log" 2>&1 &
+
+	"${WORK_DIR}/mc" ready verify
+}
+
+function start_minio_pool_erasure_sets_ipv6() {
+	export MINIO_ROOT_USER=$ACCESS_KEY
+	export MINIO_ROOT_PASSWORD=$SECRET_KEY
+	export MINIO_ENDPOINTS="http://[::1]:9000${WORK_DIR}/pool-disk-sets-ipv6{1...4} http://[::1]:9001${WORK_DIR}/pool-disk-sets-ipv6{5...8}"
+	"${MINIO[@]}" server --address="[::1]:9000" >"$WORK_DIR/pool-minio-ipv6-9000.log" 2>&1 &
+	"${MINIO[@]}" server --address="[::1]:9001" >"$WORK_DIR/pool-minio-ipv6-9001.log" 2>&1 &
+
+	"${WORK_DIR}/mc" ready verify_ipv6
+}
+
+function start_minio_dist_erasure() {
+	export MINIO_ROOT_USER=$ACCESS_KEY
+	export MINIO_ROOT_PASSWORD=$SECRET_KEY
+	export MINIO_ENDPOINTS="http://127.0.0.1:9000${WORK_DIR}/dist-disk1 http://127.0.0.1:9001${WORK_DIR}/dist-disk2 http://127.0.0.1:9002${WORK_DIR}/dist-disk3 http://127.0.0.1:9003${WORK_DIR}/dist-disk4"
+	for i in $(seq 0 3); do
+		"${MINIO[@]}" server --address ":900${i}" >"$WORK_DIR/dist-minio-900${i}.log" 2>&1 &
+	done
+
+	"${WORK_DIR}/mc" ready verify
+}
+
+function run_test_fs() {
+	start_minio_fs
+
+	(cd "$WORK_DIR" && "$FUNCTIONAL_TESTS")
+	rv=$?
+
+	pkill minio
+	sleep 3
+
+	if [ "$rv" -ne 0 ]; then
+		cat "$WORK_DIR/fs-minio.log"
+	fi
+	rm -f "$WORK_DIR/fs-minio.log"
+
+	return "$rv"
+}
+
+function run_test_erasure_sets() {
+	start_minio_erasure_sets
+
+	(cd "$WORK_DIR" && "$FUNCTIONAL_TESTS")
+	rv=$?
+
+	pkill minio
+	sleep 3
+
+	if [ "$rv" -ne 0 ]; then
+		cat "$WORK_DIR/erasure-minio-sets.log"
+	fi
+	rm -f "$WORK_DIR/erasure-minio-sets.log"
+
+	return "$rv"
+}
+
+function run_test_pool_erasure_sets() {
+	start_minio_pool_erasure_sets
+
+	(cd "$WORK_DIR" && "$FUNCTIONAL_TESTS")
+	rv=$?
+
+	pkill minio
+	sleep 3
+
+	if [ "$rv" -ne 0 ]; then
+		for i in $(seq 0 1); do
+			echo "server$i log:"
+			cat "$WORK_DIR/pool-minio-900$i.log"
+		done
+	fi
+
+	for i in $(seq 0 1); do
+		rm -f "$WORK_DIR/pool-minio-900$i.log"
+	done
+
+	return "$rv"
+}
+
+function run_test_pool_erasure_sets_ipv6() {
+	start_minio_pool_erasure_sets_ipv6
+
+	export SERVER_ENDPOINT="[::1]:9000"
+
+	(cd "$WORK_DIR" && "$FUNCTIONAL_TESTS")
+	rv=$?
+
+	pkill minio
+	sleep 3
+
+	if [ "$rv" -ne 0 ]; then
+		for i in $(seq 0 1); do
+			echo "server$i log:"
+			cat "$WORK_DIR/pool-minio-ipv6-900$i.log"
+		done
+	fi
+
+	for i in $(seq 0 1); do
+		rm -f "$WORK_DIR/pool-minio-ipv6-900$i.log"
+	done
+
+	return "$rv"
+}
+
+function run_test_erasure() {
+	start_minio_erasure
+
+	(cd "$WORK_DIR" && "$FUNCTIONAL_TESTS")
+	rv=$?
+
+	pkill minio
+	sleep 3
+
+	if [ "$rv" -ne 0 ]; then
+		cat "$WORK_DIR/erasure-minio.log"
+	fi
+	rm -f "$WORK_DIR/erasure-minio.log"
+
+	return "$rv"
+}
+
+function run_test_dist_erasure() {
+	start_minio_dist_erasure
+
+	(cd "$WORK_DIR" && "$FUNCTIONAL_TESTS")
+	rv=$?
+
+	pkill minio
+	sleep 3
+
+	if [ "$rv" -ne 0 ]; then
+		echo "server1 log:"
+		cat "$WORK_DIR/dist-minio-9000.log"
+		echo "server2 log:"
+		cat "$WORK_DIR/dist-minio-9001.log"
+		echo "server3 log:"
+		cat "$WORK_DIR/dist-minio-9002.log"
+		echo "server4 log:"
+		cat "$WORK_DIR/dist-minio-9003.log"
+	fi
+
+	rm -f "$WORK_DIR/dist-minio-9000.log" "$WORK_DIR/dist-minio-9001.log" "$WORK_DIR/dist-minio-9002.log" "$WORK_DIR/dist-minio-9003.log"
+
+	return "$rv"
+}
+
+function purge() {
+	rm -rf "$1"
+}
+
+function __init__() {
+	echo "Initializing environment"
+	mkdir -p "$WORK_DIR"
+	mkdir -p "$MINIO_CONFIG_DIR"
+	mkdir -p "$MINT_DATA_DIR"
+
+	MC_BUILD_DIR="mc-$RANDOM"
+	if ! git clone --quiet https://github.com/minio/mc "$MC_BUILD_DIR"; then
+		echo "failed to download https://github.com/minio/mc"
+		purge "${MC_BUILD_DIR}"
+		exit 1
+	fi
+
+	(cd "${MC_BUILD_DIR}" && go build -o "${WORK_DIR}/mc")
+
+	# remove mc source.
+	purge "${MC_BUILD_DIR}"
+
+	shred -n 1 -s 1M - 1>"$FILE_1_MB" 2>/dev/null
+	shred -n 1 -s 65M - 1>"$FILE_65_MB" 2>/dev/null
+
+	## version is purposefully set to '3' for minio to migrate configuration file
+	echo '{"version": "3", "credential": {"accessKey": "minio", "secretKey": "minio123"}, "region": "us-east-1"}' >"$MINIO_CONFIG_DIR/config.json"
+
+	if ! wget -q -O "$FUNCTIONAL_TESTS" https://raw.githubusercontent.com/minio/mc/master/functional-tests.sh; then
+		echo "failed to download https://raw.githubusercontent.com/minio/mc/master/functional-tests.sh"
+		exit 1
+	fi
+
+	sed -i 's|-sS|-sSg|g' "$FUNCTIONAL_TESTS"
+	chmod a+x "$FUNCTIONAL_TESTS"
+}
+
+function main() {
+	echo "Testing in FS setup"
+	if ! run_test_fs; then
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	echo "Testing in Erasure setup"
+	if ! run_test_erasure; then
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	echo "Testing in Distributed Erasure setup"
+	if ! run_test_dist_erasure; then
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	echo "Testing in Erasure setup as sets"
+	if ! run_test_erasure_sets; then
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	echo "Testing in Distributed Eraure expanded setup"
+	if ! run_test_pool_erasure_sets; then
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	echo "Testing in Distributed Erasure expanded setup with ipv6"
+	if ! run_test_pool_erasure_sets_ipv6; then
+		echo "FAILED"
+		purge "$WORK_DIR"
+		exit 1
+	fi
+
+	purge "$WORK_DIR"
+}
+
+(__init__ "$@" && main "$@")
+rv=$?
+purge "$WORK_DIR"
+exit "$rv"

buildscripts/verify-healing-empty-erasure-set.sh

@@ -0,0 +1,151 @@
+#!/bin/bash -e
+#
+
+set -E
+set -o pipefail
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+function start_minio_3_node() {
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	export MINIO_ERASURE_SET_DRIVE_COUNT=6
+	export MINIO_CI_CD=1
+
+	start_port=$1
+	args=""
+	for i in $(seq 1 3); do
+		args="$args http://127.0.0.1:$((start_port + i))${WORK_DIR}/$i/1/ http://127.0.0.1:$((start_port + i))${WORK_DIR}/$i/2/ http://127.0.0.1:$((start_port + i))${WORK_DIR}/$i/3/ http://127.0.0.1:$((start_port + i))${WORK_DIR}/$i/4/ http://127.0.0.1:$((start_port + i))${WORK_DIR}/$i/5/ http://127.0.0.1:$((start_port + i))${WORK_DIR}/$i/6/"
+	done
+
+	"${MINIO[@]}" --address ":$((start_port + 1))" $args >"${WORK_DIR}/dist-minio-server1.log" 2>&1 &
+	pid1=$!
+	disown ${pid1}
+
+	"${MINIO[@]}" --address ":$((start_port + 2))" $args >"${WORK_DIR}/dist-minio-server2.log" 2>&1 &
+	pid2=$!
+	disown $pid2
+
+	"${MINIO[@]}" --address ":$((start_port + 3))" $args >"${WORK_DIR}/dist-minio-server3.log" 2>&1 &
+	pid3=$!
+	disown $pid3
+
+	export MC_HOST_myminio="http://minio:minio123@127.0.0.1:$((start_port + 1))"
+
+	timeout 15m /tmp/mc ready myminio || fail
+
+	# Wait for all drives to be online and formatted
+	while [ $(/tmp/mc admin info --json myminio | jq '.info.servers[].drives[].state | select(. != "ok")' | wc -l) -gt 0 ]; do sleep 1; done
+	# Wait for all drives to be healed
+	while [ $(/tmp/mc admin info --json myminio | jq '.info.servers[].drives[].healing | select(. != null) | select(. == true)' | wc -l) -gt 0 ]; do sleep 1; done
+
+	# Wait for Status: in MinIO output
+	while true; do
+		rv=$(check_online)
+		if [ "$rv" != "1" ]; then
+			# success
+			break
+		fi
+
+		# Check if we should retry
+		retry=$((retry + 1))
+		if [ $retry -le 20 ]; then
+			sleep 5
+			continue
+		fi
+
+		# Failure
+		fail
+	done
+
+	if ! ps -p $pid1 1>&2 >/dev/null; then
+		echo "minio-server-1 is not running." && fail
+	fi
+
+	if ! ps -p $pid2 1>&2 >/dev/null; then
+		echo "minio-server-2 is not running." && fail
+	fi
+
+	if ! ps -p $pid3 1>&2 >/dev/null; then
+		echo "minio-server-3 is not running." && fail
+	fi
+
+	if ! pkill minio; then
+		fail
+	fi
+
+	sleep 1
+	if pgrep minio; then
+		# forcibly killing, to proceed further properly.
+		if ! pkill -9 minio; then
+			echo "no minio process running anymore, proceed."
+		fi
+	fi
+}
+
+function fail() {
+	for i in $(seq 1 3); do
+		echo "server$i log:"
+		cat "${WORK_DIR}/dist-minio-server$i.log"
+	done
+	echo "FAILED"
+	purge "$WORK_DIR"
+	exit 1
+}
+
+function check_online() {
+	if ! grep -q 'API:' ${WORK_DIR}/dist-minio-*.log; then
+		echo "1"
+	fi
+}
+
+function purge() {
+	echo rm -rf "$1"
+}
+
+function __init__() {
+	echo "Initializing environment"
+	mkdir -p "$WORK_DIR"
+	mkdir -p "$MINIO_CONFIG_DIR"
+
+	## version is purposefully set to '3' for minio to migrate configuration file
+	echo '{"version": "3", "credential": {"accessKey": "minio", "secretKey": "minio123"}, "region": "us-east-1"}' >"$MINIO_CONFIG_DIR/config.json"
+
+	if [ ! -f /tmp/mc ]; then
+		wget --quiet -O /tmp/mc https://dl.minio.io/client/mc/release/linux-amd64/mc &&
+			chmod +x /tmp/mc
+	fi
+}
+
+function perform_test() {
+	start_minio_3_node $2
+
+	echo "Testing Distributed Erasure setup healing of drives"
+	echo "Remove the contents of the disks belonging to '${1}' erasure set"
+
+	rm -rf ${WORK_DIR}/${1}/*/
+
+	set -x
+	start_minio_3_node $2
+}
+
+function main() {
+	# use same ports for all tests
+	start_port=$(shuf -i 10000-65000 -n 1)
+
+	perform_test "2" ${start_port}
+	perform_test "1" ${start_port}
+	perform_test "3" ${start_port}
+}
+
+(__init__ "$@" && main "$@")
+rv=$?
+purge "$WORK_DIR"
+exit "$rv"

buildscripts/verify-healing-with-root-disks.sh

@@ -0,0 +1,96 @@
+#!/bin/bash -e
+
+set -E
+set -o pipefail
+set -x
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+WORK_DIR="$(mktemp -d)"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+
+function start_minio() {
+	start_port=$1
+
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	unset MINIO_KMS_AUTO_ENCRYPTION # do not auto-encrypt objects
+	unset MINIO_CI_CD
+	unset CI
+
+	args=()
+	for i in $(seq 1 4); do
+		args+=("http://localhost:$((start_port + i))${WORK_DIR}/mnt/disk$i/ ")
+	done
+
+	for i in $(seq 1 4); do
+		"${MINIO[@]}" --address ":$((start_port + i))" ${args[@]} 2>&1 >"${WORK_DIR}/server$i.log" &
+	done
+
+	# Wait until all nodes return 403
+	for i in $(seq 1 4); do
+		while [ "$(curl -m 1 -s -o /dev/null -w "%{http_code}" http://localhost:$((start_port + i)))" -ne "403" ]; do
+			echo -n "."
+			sleep 1
+		done
+	done
+
+}
+
+# Prepare fake disks with losetup
+function prepare_block_devices() {
+	set -e
+	mkdir -p ${WORK_DIR}/disks/ ${WORK_DIR}/mnt/
+	sudo modprobe loop
+	for i in 1 2 3 4; do
+		dd if=/dev/zero of=${WORK_DIR}/disks/img.${i} bs=1M count=2000
+		device=$(sudo losetup --find --show ${WORK_DIR}/disks/img.${i})
+		sudo mkfs.ext4 -F ${device}
+		mkdir -p ${WORK_DIR}/mnt/disk${i}/
+		sudo mount ${device} ${WORK_DIR}/mnt/disk${i}/
+		sudo chown "$(id -u):$(id -g)" ${device} ${WORK_DIR}/mnt/disk${i}/
+	done
+	set +e
+}
+
+# Start a distributed MinIO setup, unmount one disk and check if it is formatted
+function main() {
+	start_port=$(shuf -i 10000-65000 -n 1)
+	start_minio ${start_port}
+
+	# Unmount the disk, after the unmount the device id
+	# /tmp/xxx/mnt/disk4 will be the same as '/' and it
+	# will be detected as root disk
+	while [ "$u" != "0" ]; do
+		sudo umount ${WORK_DIR}/mnt/disk4/
+		u=$?
+		sleep 1
+	done
+
+	# Wait until MinIO self heal kicks in
+	sleep 60
+
+	if [ -f ${WORK_DIR}/mnt/disk4/.minio.sys/format.json ]; then
+		echo "A root disk is formatted unexpectedely"
+		cat "${WORK_DIR}/server4.log"
+		exit -1
+	fi
+}
+
+function cleanup() {
+	pkill minio
+	sudo umount ${WORK_DIR}/mnt/disk{1..3}/
+	sudo rm /dev/minio-loopdisk*
+	rm -rf "$WORK_DIR"
+}
+
+(prepare_block_devices)
+(main "$@")
+rv=$?
+
+cleanup
+exit "$rv"

buildscripts/verify-healing.sh

@@ -0,0 +1,167 @@
+#!/bin/bash -e
+#
+
+set -E
+set -o pipefail
+
+if [ ! -x "$PWD/minio" ]; then
+	echo "minio executable binary not found in current directory"
+	exit 1
+fi
+
+WORK_DIR="$PWD/.verify-$RANDOM"
+MINIO_CONFIG_DIR="$WORK_DIR/.minio"
+MINIO=("$PWD/minio" --config-dir "$MINIO_CONFIG_DIR" server)
+GOPATH=/tmp/gopath
+
+function start_minio_3_node() {
+	for i in $(seq 1 3); do
+		rm "${WORK_DIR}/dist-minio-server$i.log"
+	done
+
+	export MINIO_ROOT_USER=minio
+	export MINIO_ROOT_PASSWORD=minio123
+	export MINIO_ERASURE_SET_DRIVE_COUNT=6
+	export MINIO_CI_CD=1
+
+	first_time=$(find ${WORK_DIR}/ | grep format.json | wc -l)
+
+	start_port=$1
+	args=""
+	for d in $(seq 1 3 5); do
+		args="$args http://127.0.0.1:$((start_port + 1))${WORK_DIR}/1/${d}/ http://127.0.0.1:$((start_port + 2))${WORK_DIR}/2/${d}/ http://127.0.0.1:$((start_port + 3))${WORK_DIR}/3/${d}/ "
+		d=$((d + 1))
+		args="$args http://127.0.0.1:$((start_port + 1))${WORK_DIR}/1/${d}/ http://127.0.0.1:$((start_port + 2))${WORK_DIR}/2/${d}/ http://127.0.0.1:$((start_port + 3))${WORK_DIR}/3/${d}/ "
+	done
+
+	"${MINIO[@]}" --address ":$((start_port + 1))" $args >"${WORK_DIR}/dist-minio-server1.log" 2>&1 &
+	pid1=$!
+	disown ${pid1}
+
+	"${MINIO[@]}" --address ":$((start_port + 2))" $args >"${WORK_DIR}/dist-minio-server2.log" 2>&1 &
+	pid2=$!
+	disown $pid2
+
+	"${MINIO[@]}" --address ":$((start_port + 3))" $args >"${WORK_DIR}/dist-minio-server3.log" 2>&1 &
+	pid3=$!
+	disown $pid3
+
+	export MC_HOST_myminio="http://minio:minio123@127.0.0.1:$((start_port + 1))"
+	timeout 15m /tmp/mc ready myminio || fail
+
+	[ ${first_time} -eq 0 ] && upload_objects
+	[ ${first_time} -ne 0 ] && sleep 120
+
+	if ! ps -p $pid1 1>&2 >/dev/null; then
+		echo "minio server 1 is not running" && fail
+	fi
+
+	if ! ps -p $pid2 1>&2 >/dev/null; then
+		echo "minio server 2 is not running" && fail
+	fi
+
+	if ! ps -p $pid3 1>&2 >/dev/null; then
+		echo "minio server 3 is not running" && fail
+	fi
+
+	if ! pkill minio; then
+		fail
+	fi
+
+	sleep 1
+	if pgrep minio; then
+		# forcibly killing, to proceed further properly.
+		if ! pkill -9 minio; then
+			echo "no minio process running anymore, proceed."
+		fi
+	fi
+}
+
+function check_heal() {
+	if ! grep -q 'API:' ${WORK_DIR}/dist-minio-*.log; then
+		return 1
+	fi
+
+	for ((i = 0; i < 20; i++)); do
+		test -f ${WORK_DIR}/$1/1/.minio.sys/format.json
+		v1=$?
+		nextInES=$(($1 + 1)) && [ $nextInES -gt 3 ] && nextInES=1
+		foundFiles1=$(find ${WORK_DIR}/$1/1/ | grep -v .minio.sys | grep xl.meta | wc -l)
+		foundFiles2=$(find ${WORK_DIR}/$nextInES/1/ | grep -v .minio.sys | grep xl.meta | wc -l)
+		test $foundFiles1 -eq $foundFiles2
+		v2=$?
+		[ $v1 == 0 -a $v2 == 0 ] && return 0
+		sleep 10
+	done
+	return 1
+}
+
+function purge() {
+	rm -rf "$1"
+}
+
+function fail() {
+	for i in $(seq 1 3); do
+		echo "server$i log:"
+		cat "${WORK_DIR}/dist-minio-server$i.log"
+	done
+	pkill -9 minio
+	echo "FAILED"
+	purge "$WORK_DIR"
+	exit 1
+}
+
+function __init__() {
+	echo "Initializing environment"
+	mkdir -p "$WORK_DIR"
+	mkdir -p "$MINIO_CONFIG_DIR"
+
+	## version is purposefully set to '3' for minio to migrate configuration file
+	echo '{"version": "3", "credential": {"accessKey": "minio", "secretKey": "minio123"}, "region": "us-east-1"}' >"$MINIO_CONFIG_DIR/config.json"
+
+	if [ ! -f /tmp/mc ]; then
+		wget --quiet -O /tmp/mc https://dl.minio.io/client/mc/release/linux-amd64/mc &&
+			chmod +x /tmp/mc
+	fi
+}
+
+function upload_objects() {
+	/tmp/mc mb myminio/testbucket/
+	for ((i = 0; i < 20; i++)); do
+		echo "my content" | /tmp/mc pipe myminio/testbucket/file-$i
+	done
+}
+
+function perform_test() {
+	start_port=$2
+
+	start_minio_3_node $start_port
+
+	echo "Testing Distributed Erasure setup healing of drives"
+	echo "Remove the contents of the disks belonging to '${1}' node"
+
+	rm -rf ${WORK_DIR}/${1}/*/
+
+	set -x
+	start_minio_3_node $start_port
+
+	check_heal ${1}
+	rv=$?
+	if [ "$rv" == "1" ]; then
+		fail
+	fi
+}
+
+function main() {
+	# use same ports for all tests
+	start_port=$(shuf -i 10000-65000 -n 1)
+
+	perform_test "2" ${start_port}
+	perform_test "1" ${start_port}
+	perform_test "3" ${start_port}
+}
+
+(__init__ "$@" && main "$@")
+rv=$?
+purge "$WORK_DIR"
+exit "$rv"

cmd/acl-handlers.go

@@ -0,0 +1,280 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"encoding/xml"
+	"io"
+	"net/http"
+
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/minio/minio/internal/logger"
+	"github.com/minio/mux"
+	"github.com/minio/pkg/v3/policy"
+)
+
+// Data types used for returning dummy access control
+// policy XML, these variables shouldn't be used elsewhere
+// they are only defined to be used in this file alone.
+type grantee struct {
+	XMLNS       string `xml:"xmlns:xsi,attr"`
+	XMLXSI      string `xml:"xsi:type,attr"`
+	Type        string `xml:"Type"`
+	ID          string `xml:"ID,omitempty"`
+	DisplayName string `xml:"DisplayName,omitempty"`
+	URI         string `xml:"URI,omitempty"`
+}
+
+type grant struct {
+	Grantee    grantee `xml:"Grantee"`
+	Permission string  `xml:"Permission"`
+}
+
+type accessControlPolicy struct {
+	XMLName           xml.Name `xml:"AccessControlPolicy"`
+	Owner             Owner    `xml:"Owner"`
+	AccessControlList struct {
+		Grants []grant `xml:"Grant"`
+	} `xml:"AccessControlList"`
+}
+
+// PutBucketACLHandler - PUT Bucket ACL
+// -----------------
+// This operation uses the ACL subresource
+// to set ACL for a bucket, this is a dummy call
+// only responds success if the ACL is private.
+func (api objectAPIHandlers) PutBucketACLHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := newContext(r, w, "PutBucketACL")
+
+	defer logger.AuditLog(ctx, w, r, mustGetClaimsFromToken(r))
+
+	vars := mux.Vars(r)
+	bucket := vars["bucket"]
+
+	objAPI := api.ObjectAPI()
+	if objAPI == nil {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	// Allow putBucketACL if policy action is set, since this is a dummy call
+	// we are simply re-purposing the bucketPolicyAction.
+	if s3Error := checkRequestAuthType(ctx, r, policy.PutBucketPolicyAction, bucket, ""); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
+
+	// Before proceeding validate if bucket exists.
+	_, err := objAPI.GetBucketInfo(ctx, bucket, BucketOptions{})
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	aclHeader := r.Header.Get(xhttp.AmzACL)
+	if aclHeader == "" {
+		acl := &accessControlPolicy{}
+		if err = xmlDecoder(r.Body, acl, r.ContentLength); err != nil {
+			if terr, ok := err.(*xml.SyntaxError); ok && terr.Msg == io.EOF.Error() {
+				writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrMalformedXML),
+					r.URL)
+				return
+			}
+			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+			return
+		}
+
+		if len(acl.AccessControlList.Grants) == 0 {
+			writeErrorResponse(ctx, w, toAPIError(ctx, NotImplemented{}), r.URL)
+			return
+		}
+
+		if acl.AccessControlList.Grants[0].Permission != "FULL_CONTROL" {
+			writeErrorResponse(ctx, w, toAPIError(ctx, NotImplemented{}), r.URL)
+			return
+		}
+	}
+
+	if aclHeader != "" && aclHeader != "private" {
+		writeErrorResponse(ctx, w, toAPIError(ctx, NotImplemented{}), r.URL)
+		return
+	}
+}
+
+// GetBucketACLHandler - GET Bucket ACL
+// -----------------
+// This operation uses the ACL
+// subresource to return the ACL of a specified bucket.
+func (api objectAPIHandlers) GetBucketACLHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := newContext(r, w, "GetBucketACL")
+
+	defer logger.AuditLog(ctx, w, r, mustGetClaimsFromToken(r))
+
+	vars := mux.Vars(r)
+	bucket := vars["bucket"]
+
+	objAPI := api.ObjectAPI()
+	if objAPI == nil {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	// Allow getBucketACL if policy action is set, since this is a dummy call
+	// we are simply re-purposing the bucketPolicyAction.
+	if s3Error := checkRequestAuthType(ctx, r, policy.GetBucketPolicyAction, bucket, ""); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
+
+	// Before proceeding validate if bucket exists.
+	_, err := objAPI.GetBucketInfo(ctx, bucket, BucketOptions{})
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	acl := &accessControlPolicy{}
+	acl.AccessControlList.Grants = append(acl.AccessControlList.Grants, grant{
+		Grantee: grantee{
+			XMLNS:  "http://www.w3.org/2001/XMLSchema-instance",
+			XMLXSI: "CanonicalUser",
+			Type:   "CanonicalUser",
+		},
+		Permission: "FULL_CONTROL",
+	})
+
+	if err := xml.NewEncoder(w).Encode(acl); err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+}
+
+// PutObjectACLHandler - PUT Object ACL
+// -----------------
+// This operation uses the ACL subresource
+// to set ACL for a bucket, this is a dummy call
+// only responds success if the ACL is private.
+func (api objectAPIHandlers) PutObjectACLHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := newContext(r, w, "PutObjectACL")
+
+	defer logger.AuditLog(ctx, w, r, mustGetClaimsFromToken(r))
+
+	vars := mux.Vars(r)
+	bucket := vars["bucket"]
+	object, err := unescapePath(vars["object"])
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	objAPI := api.ObjectAPI()
+	if objAPI == nil {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	// Allow putObjectACL if policy action is set, since this is a dummy call
+	// we are simply re-purposing the bucketPolicyAction.
+	if s3Error := checkRequestAuthType(ctx, r, policy.PutBucketPolicyAction, bucket, ""); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
+
+	// Before proceeding validate if object exists.
+	_, err = objAPI.GetObjectInfo(ctx, bucket, object, ObjectOptions{})
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	aclHeader := r.Header.Get(xhttp.AmzACL)
+	if aclHeader == "" {
+		acl := &accessControlPolicy{}
+		if err = xmlDecoder(r.Body, acl, r.ContentLength); err != nil {
+			writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+			return
+		}
+
+		if len(acl.AccessControlList.Grants) == 0 {
+			writeErrorResponse(ctx, w, toAPIError(ctx, NotImplemented{}), r.URL)
+			return
+		}
+
+		if acl.AccessControlList.Grants[0].Permission != "FULL_CONTROL" {
+			writeErrorResponse(ctx, w, toAPIError(ctx, NotImplemented{}), r.URL)
+			return
+		}
+	}
+
+	if aclHeader != "" && aclHeader != "private" {
+		writeErrorResponse(ctx, w, toAPIError(ctx, NotImplemented{}), r.URL)
+		return
+	}
+}
+
+// GetObjectACLHandler - GET Object ACL
+// -----------------
+// This operation uses the ACL
+// subresource to return the ACL of a specified object.
+func (api objectAPIHandlers) GetObjectACLHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := newContext(r, w, "GetObjectACL")
+
+	defer logger.AuditLog(ctx, w, r, mustGetClaimsFromToken(r))
+
+	vars := mux.Vars(r)
+	bucket := vars["bucket"]
+	object, err := unescapePath(vars["object"])
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	objAPI := api.ObjectAPI()
+	if objAPI == nil {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	// Allow getObjectACL if policy action is set, since this is a dummy call
+	// we are simply re-purposing the bucketPolicyAction.
+	if s3Error := checkRequestAuthType(ctx, r, policy.GetBucketPolicyAction, bucket, ""); s3Error != ErrNone {
+		writeErrorResponse(ctx, w, errorCodes.ToAPIErr(s3Error), r.URL)
+		return
+	}
+
+	// Before proceeding validate if object exists.
+	_, err = objAPI.GetObjectInfo(ctx, bucket, object, ObjectOptions{})
+	if err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	acl := &accessControlPolicy{}
+	acl.AccessControlList.Grants = append(acl.AccessControlList.Grants, grant{
+		Grantee: grantee{
+			XMLNS:  "http://www.w3.org/2001/XMLSchema-instance",
+			XMLXSI: "CanonicalUser",
+			Type:   "CanonicalUser",
+		},
+		Permission: "FULL_CONTROL",
+	})
+	if err := xml.NewEncoder(w).Encode(acl); err != nil {
+		writeErrorResponse(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+}

cmd/admin-handler-utils.go

@@ -0,0 +1,263 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"context"
+	"errors"
+	"fmt"
+	"net/http"
+
+	"github.com/minio/kms-go/kes"
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/minio/internal/config"
+	"github.com/minio/pkg/v3/policy"
+)
+
+// validateAdminReq will validate request against and return whether it is allowed.
+// If any of the supplied actions are allowed it will be successful.
+// If nil ObjectLayer is returned, the operation is not permitted.
+// When nil ObjectLayer has been returned an error has always been sent to w.
+func validateAdminReq(ctx context.Context, w http.ResponseWriter, r *http.Request, actions ...policy.AdminAction) (ObjectLayer, auth.Credentials) {
+	// Get current object layer instance.
+	objectAPI := newObjectLayerFn()
+	if objectAPI == nil || globalNotificationSys == nil {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return nil, auth.Credentials{}
+	}
+
+	for _, action := range actions {
+		// Validate request signature.
+		cred, adminAPIErr := checkAdminRequestAuth(ctx, r, action, "")
+		switch adminAPIErr {
+		case ErrNone:
+			return objectAPI, cred
+		case ErrAccessDenied:
+			// Try another
+			continue
+		default:
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(adminAPIErr), r.URL)
+			return nil, cred
+		}
+	}
+	writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+	return nil, auth.Credentials{}
+}
+
+// AdminError - is a generic error for all admin APIs.
+type AdminError struct {
+	Code       string
+	Message    string
+	StatusCode int
+}
+
+func (ae AdminError) Error() string {
+	return ae.Message
+}
+
+func toAdminAPIErr(ctx context.Context, err error) APIError {
+	if err == nil {
+		return noError
+	}
+
+	var apiErr APIError
+	switch e := err.(type) {
+	case policy.Error:
+		apiErr = APIError{
+			Code:           "XMinioMalformedIAMPolicy",
+			Description:    e.Error(),
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	case config.ErrConfigNotFound:
+		apiErr = APIError{
+			Code:           "XMinioConfigNotFoundError",
+			Description:    e.Error(),
+			HTTPStatusCode: http.StatusNotFound,
+		}
+	case config.ErrConfigGeneric:
+		apiErr = APIError{
+			Code:           "XMinioConfigError",
+			Description:    e.Error(),
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	case AdminError:
+		apiErr = APIError{
+			Code:           e.Code,
+			Description:    e.Message,
+			HTTPStatusCode: e.StatusCode,
+		}
+	case SRError:
+		apiErr = errorCodes.ToAPIErrWithErr(e.Code, e.Cause)
+	case decomError:
+		apiErr = APIError{
+			Code:           "XMinioDecommissionNotAllowed",
+			Description:    e.Err,
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	default:
+		switch {
+		case errors.Is(err, errTooManyPolicies):
+			apiErr = APIError{
+				Code:           "XMinioAdminInvalidRequest",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errDecommissionAlreadyRunning):
+			apiErr = APIError{
+				Code:           "XMinioDecommissionNotAllowed",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errDecommissionComplete):
+			apiErr = APIError{
+				Code:           "XMinioDecommissionNotAllowed",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errDecommissionRebalanceAlreadyRunning):
+			apiErr = APIError{
+				Code:           "XMinioDecommissionNotAllowed",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errRebalanceDecommissionAlreadyRunning):
+			apiErr = APIError{
+				Code:           "XMinioRebalanceNotAllowed",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errConfigNotFound):
+			apiErr = APIError{
+				Code:           "XMinioConfigError",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusNotFound,
+			}
+		case errors.Is(err, errIAMActionNotAllowed):
+			apiErr = APIError{
+				Code:           "XMinioIAMActionNotAllowed",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusForbidden,
+			}
+		case errors.Is(err, errIAMServiceAccountNotAllowed):
+			apiErr = APIError{
+				Code:           "XMinioIAMServiceAccountNotAllowed",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errIAMNotInitialized):
+			apiErr = APIError{
+				Code:           "XMinioIAMNotInitialized",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusServiceUnavailable,
+			}
+		case errors.Is(err, errPolicyInUse):
+			apiErr = APIError{
+				Code:           "XMinioIAMPolicyInUse",
+				Description:    "The policy cannot be removed, as it is in use",
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errSessionPolicyTooLarge):
+			apiErr = APIError{
+				Code:           "XMinioIAMServiceAccountSessionPolicyTooLarge",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, kes.ErrKeyExists):
+			apiErr = APIError{
+				Code:           "XMinioKMSKeyExists",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusConflict,
+			}
+
+		// Tier admin API errors
+		case errors.Is(err, madmin.ErrTierNameEmpty):
+			apiErr = APIError{
+				Code:           "XMinioAdminTierNameEmpty",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, madmin.ErrTierInvalidConfig):
+			apiErr = APIError{
+				Code:           "XMinioAdminTierInvalidConfig",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, madmin.ErrTierInvalidConfigVersion):
+			apiErr = APIError{
+				Code:           "XMinioAdminTierInvalidConfigVersion",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, madmin.ErrTierTypeUnsupported):
+			apiErr = APIError{
+				Code:           "XMinioAdminTierTypeUnsupported",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errIsTierPermError(err):
+			apiErr = APIError{
+				Code:           "XMinioAdminTierInsufficientPermissions",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		case errors.Is(err, errTierInvalidConfig):
+			apiErr = APIError{
+				Code:           "XMinioAdminTierInvalidConfig",
+				Description:    err.Error(),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		default:
+			apiErr = errorCodes.ToAPIErrWithErr(toAdminAPIErrCode(ctx, err), err)
+		}
+	}
+	return apiErr
+}
+
+// toAdminAPIErrCode - converts errErasureWriteQuorum error to admin API
+// specific error.
+func toAdminAPIErrCode(ctx context.Context, err error) APIErrorCode {
+	if errors.Is(err, errErasureWriteQuorum) {
+		return ErrAdminConfigNoQuorum
+	}
+	return toAPIErrorCode(ctx, err)
+}
+
+// wraps export error for more context
+func exportError(ctx context.Context, err error, fname, entity string) APIError {
+	if entity == "" {
+		return toAPIError(ctx, fmt.Errorf("error exporting %s with: %w", fname, err))
+	}
+	return toAPIError(ctx, fmt.Errorf("error exporting %s from %s with: %w", entity, fname, err))
+}
+
+// wraps import error for more context
+func importError(ctx context.Context, err error, fname, entity string) APIError {
+	if entity == "" {
+		return toAPIError(ctx, fmt.Errorf("error importing %s with: %w", fname, err))
+	}
+	return toAPIError(ctx, fmt.Errorf("error importing %s from %s with: %w", entity, fname, err))
+}
+
+// wraps import error for more context
+func importErrorWithAPIErr(ctx context.Context, apiErr APIErrorCode, err error, fname, entity string) APIError {
+	if entity == "" {
+		return errorCodes.ToAPIErrWithErr(apiErr, fmt.Errorf("error importing %s with: %w", fname, err))
+	}
+	return errorCodes.ToAPIErrWithErr(apiErr, fmt.Errorf("error importing %s from %s with: %w", entity, fname, err))
+}

cmd/admin-handlers-config-kv.go

@@ -0,0 +1,542 @@
+// Copyright (c) 2015-2023 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"encoding/json"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/config"
+	"github.com/minio/minio/internal/config/etcd"
+	xldap "github.com/minio/minio/internal/config/identity/ldap"
+	"github.com/minio/minio/internal/config/identity/openid"
+	idplugin "github.com/minio/minio/internal/config/identity/plugin"
+	polplugin "github.com/minio/minio/internal/config/policy/plugin"
+	"github.com/minio/minio/internal/config/storageclass"
+	"github.com/minio/minio/internal/config/subnet"
+	"github.com/minio/minio/internal/logger"
+	"github.com/minio/mux"
+	"github.com/minio/pkg/v3/policy"
+)
+
+// DelConfigKVHandler - DELETE /minio/admin/v3/del-config-kv
+func (a adminAPIHandlers) DelConfigKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	if r.ContentLength > maxEConfigJSONSize || r.ContentLength == -1 {
+		// More than maxConfigSize bytes were available
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigTooLarge), r.URL)
+		return
+	}
+
+	password := cred.SecretKey
+	kvBytes, err := madmin.DecryptData(password, io.LimitReader(r.Body, r.ContentLength))
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), r.URL)
+		return
+	}
+
+	subSys, _, _, err := config.GetSubSys(string(kvBytes))
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	cfg, err := readServerConfig(ctx, objectAPI, nil)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err = cfg.DelFrom(bytes.NewReader(kvBytes)); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err = validateConfig(ctx, cfg, subSys); err != nil {
+		writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), err.Error(), r.URL)
+		return
+	}
+
+	// Check if subnet proxy being deleted and if so the value of proxy of subnet
+	// target of logger webhook configuration also should be deleted
+	loggerWebhookProxyDeleted := setLoggerWebhookSubnetProxy(subSys, cfg)
+
+	if err = saveServerConfig(ctx, objectAPI, cfg); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	// freshly retrieve the config so that default values are loaded for reset config
+	if cfg, err = getValidConfig(objectAPI); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	dynamic := config.SubSystemsDynamic.Contains(subSys)
+	if dynamic {
+		applyDynamic(ctx, objectAPI, cfg, subSys, r, w)
+		if subSys == config.SubnetSubSys && loggerWebhookProxyDeleted {
+			// Logger webhook proxy deleted, apply the dynamic changes
+			applyDynamic(ctx, objectAPI, cfg, config.LoggerWebhookSubSys, r, w)
+		}
+	}
+}
+
+func applyDynamic(ctx context.Context, objectAPI ObjectLayer, cfg config.Config, subSys string,
+	r *http.Request, w http.ResponseWriter,
+) {
+	// Apply dynamic values.
+	if err := applyDynamicConfigForSubSys(GlobalContext, objectAPI, cfg, subSys); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	globalNotificationSys.SignalConfigReload(subSys)
+	// Tell the client that dynamic config was applied.
+	w.Header().Set(madmin.ConfigAppliedHeader, madmin.ConfigAppliedTrue)
+}
+
+type badConfigErr struct {
+	Err error
+}
+
+// Error - return the error message
+func (bce badConfigErr) Error() string {
+	return bce.Err.Error()
+}
+
+// Unwrap the error to its underlying error.
+func (bce badConfigErr) Unwrap() error {
+	return bce.Err
+}
+
+type setConfigResult struct {
+	Cfg                     config.Config
+	SubSys                  string
+	Dynamic                 bool
+	LoggerWebhookCfgUpdated bool
+}
+
+// SetConfigKVHandler - PUT /minio/admin/v3/set-config-kv
+func (a adminAPIHandlers) SetConfigKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	if r.ContentLength > maxEConfigJSONSize || r.ContentLength == -1 {
+		// More than maxConfigSize bytes were available
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigTooLarge), r.URL)
+		return
+	}
+
+	password := cred.SecretKey
+	kvBytes, err := madmin.DecryptData(password, io.LimitReader(r.Body, r.ContentLength))
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), r.URL)
+		return
+	}
+
+	result, err := setConfigKV(ctx, objectAPI, kvBytes)
+	if err != nil {
+		switch err.(type) {
+		case badConfigErr:
+			writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), err.Error(), r.URL)
+		default:
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		}
+		return
+	}
+
+	if result.Dynamic {
+		applyDynamic(ctx, objectAPI, result.Cfg, result.SubSys, r, w)
+		// If logger webhook config updated (proxy due to callhome), explicitly dynamically
+		// apply the config
+		if result.LoggerWebhookCfgUpdated {
+			applyDynamic(ctx, objectAPI, result.Cfg, config.LoggerWebhookSubSys, r, w)
+		}
+	}
+
+	writeSuccessResponseHeadersOnly(w)
+}
+
+func setConfigKV(ctx context.Context, objectAPI ObjectLayer, kvBytes []byte) (result setConfigResult, err error) {
+	result.Cfg, err = readServerConfig(ctx, objectAPI, nil)
+	if err != nil {
+		return
+	}
+
+	result.Dynamic, err = result.Cfg.ReadConfig(bytes.NewReader(kvBytes))
+	if err != nil {
+		return
+	}
+
+	result.SubSys, _, _, err = config.GetSubSys(string(kvBytes))
+	if err != nil {
+		return
+	}
+
+	tgts, err := config.ParseConfigTargetID(bytes.NewReader(kvBytes))
+	if err != nil {
+		return
+	}
+	ctx = context.WithValue(ctx, config.ContextKeyForTargetFromConfig, tgts)
+	if verr := validateConfig(ctx, result.Cfg, result.SubSys); verr != nil {
+		err = badConfigErr{Err: verr}
+		return
+	}
+
+	// Check if subnet proxy being set and if so set the same value to proxy of subnet
+	// target of logger webhook configuration
+	result.LoggerWebhookCfgUpdated = setLoggerWebhookSubnetProxy(result.SubSys, result.Cfg)
+
+	// Update the actual server config on disk.
+	if err = saveServerConfig(ctx, objectAPI, result.Cfg); err != nil {
+		return
+	}
+
+	// Write the config input KV to history.
+	err = saveServerConfigHistory(ctx, objectAPI, kvBytes)
+	return
+}
+
+// GetConfigKVHandler - GET /minio/admin/v3/get-config-kv?key={key}
+//
+// `key` can be one of three forms:
+// 1. `subsys:target` -> request for config of a single subsystem and target pair.
+// 2. `subsys:` -> request for config of a single subsystem and the default target.
+// 3. `subsys` -> request for config of all targets for the given subsystem.
+//
+// This is a reporting API and config secrets are redacted in the response.
+func (a adminAPIHandlers) GetConfigKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	cfg := globalServerConfig.Clone()
+	vars := mux.Vars(r)
+	key := vars["key"]
+
+	var subSys, target string
+	{
+		ws := strings.SplitN(key, madmin.SubSystemSeparator, 2)
+		subSys = ws[0]
+		if len(ws) == 2 {
+			if ws[1] == "" {
+				target = madmin.Default
+			} else {
+				target = ws[1]
+			}
+		}
+	}
+
+	subSysConfigs, err := cfg.GetSubsysInfo(subSys, target, true)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	var s strings.Builder
+	for _, subSysConfig := range subSysConfigs {
+		subSysConfig.WriteTo(&s, false)
+	}
+
+	password := cred.SecretKey
+	econfigData, err := madmin.EncryptData(password, []byte(s.String()))
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, econfigData)
+}
+
+func (a adminAPIHandlers) ClearConfigHistoryKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	vars := mux.Vars(r)
+	restoreID := vars["restoreId"]
+	if restoreID == "" {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrInvalidRequest), r.URL)
+		return
+	}
+	if restoreID == "all" {
+		chEntries, err := listServerConfigHistory(ctx, objectAPI, false, -1)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+		for _, chEntry := range chEntries {
+			if err = delServerConfigHistory(ctx, objectAPI, chEntry.RestoreID); err != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+				return
+			}
+		}
+	} else if err := delServerConfigHistory(ctx, objectAPI, restoreID); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// RestoreConfigHistoryKVHandler - restores a config with KV settings for the given KV id.
+func (a adminAPIHandlers) RestoreConfigHistoryKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	vars := mux.Vars(r)
+	restoreID := vars["restoreId"]
+	if restoreID == "" {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrInvalidRequest), r.URL)
+		return
+	}
+
+	kvBytes, err := readServerConfigHistory(ctx, objectAPI, restoreID)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	cfg, err := readServerConfig(ctx, objectAPI, nil)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if _, err = cfg.ReadConfig(bytes.NewReader(kvBytes)); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err = validateConfig(ctx, cfg, ""); err != nil {
+		writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), err.Error(), r.URL)
+		return
+	}
+
+	if err = saveServerConfig(ctx, objectAPI, cfg); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	delServerConfigHistory(ctx, objectAPI, restoreID)
+}
+
+// ListConfigHistoryKVHandler - lists all the KV ids.
+func (a adminAPIHandlers) ListConfigHistoryKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	vars := mux.Vars(r)
+	count, err := strconv.Atoi(vars["count"])
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	chEntries, err := listServerConfigHistory(ctx, objectAPI, true, count)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	data, err := json.Marshal(chEntries)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	password := cred.SecretKey
+	econfigData, err := madmin.EncryptData(password, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, econfigData)
+}
+
+// HelpConfigKVHandler - GET /minio/admin/v3/help-config-kv?subSys={subSys}&key={key}
+func (a adminAPIHandlers) HelpConfigKVHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	vars := mux.Vars(r)
+
+	subSys := vars["subSys"]
+	key := vars["key"]
+
+	_, envOnly := r.Form["env"]
+
+	rd, err := GetHelp(subSys, key, envOnly)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	json.NewEncoder(w).Encode(rd)
+}
+
+// SetConfigHandler - PUT /minio/admin/v3/config
+func (a adminAPIHandlers) SetConfigHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	if r.ContentLength > maxEConfigJSONSize || r.ContentLength == -1 {
+		// More than maxConfigSize bytes were available
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigTooLarge), r.URL)
+		return
+	}
+
+	password := cred.SecretKey
+	kvBytes, err := madmin.DecryptData(password, io.LimitReader(r.Body, r.ContentLength))
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), r.URL)
+		return
+	}
+
+	cfg := newServerConfig()
+	if _, err = cfg.ReadConfig(bytes.NewReader(kvBytes)); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err = validateConfig(ctx, cfg, ""); err != nil {
+		writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), err.Error(), r.URL)
+		return
+	}
+
+	// Update the actual server config on disk.
+	if err = saveServerConfig(ctx, objectAPI, cfg); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	// Write to the config input KV to history.
+	if err = saveServerConfigHistory(ctx, objectAPI, kvBytes); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseHeadersOnly(w)
+}
+
+// GetConfigHandler - GET /minio/admin/v3/config
+//
+// This endpoint is mainly for exporting and backing up the configuration.
+// Secrets are not redacted.
+func (a adminAPIHandlers) GetConfigHandler(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	cfg := globalServerConfig.Clone()
+
+	var s strings.Builder
+	hkvs := config.HelpSubSysMap[""]
+	for _, hkv := range hkvs {
+		// We ignore the error below, as we cannot get one.
+		cfgSubsysItems, _ := cfg.GetSubsysInfo(hkv.Key, "", false)
+
+		for _, item := range cfgSubsysItems {
+			off := item.Config.Get(config.Enable) == config.EnableOff
+			switch hkv.Key {
+			case config.EtcdSubSys:
+				off = !etcd.Enabled(item.Config)
+			case config.StorageClassSubSys:
+				off = !storageclass.Enabled(item.Config)
+			case config.PolicyPluginSubSys:
+				off = !polplugin.Enabled(item.Config)
+			case config.IdentityOpenIDSubSys:
+				off = !openid.Enabled(item.Config)
+			case config.IdentityLDAPSubSys:
+				off = !xldap.Enabled(item.Config)
+			case config.IdentityTLSSubSys:
+				off = !globalIAMSys.STSTLSConfig.Enabled
+			case config.IdentityPluginSubSys:
+				off = !idplugin.Enabled(item.Config)
+			}
+			item.WriteTo(&s, off)
+		}
+	}
+
+	password := cred.SecretKey
+	econfigData, err := madmin.EncryptData(password, []byte(s.String()))
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, econfigData)
+}
+
+// setLoggerWebhookSubnetProxy - Sets the logger webhook's subnet proxy value to
+// one being set for subnet proxy
+func setLoggerWebhookSubnetProxy(subSys string, cfg config.Config) bool {
+	if subSys == config.SubnetSubSys || subSys == config.LoggerWebhookSubSys {
+		subnetWebhookCfg := cfg[config.LoggerWebhookSubSys][subnet.LoggerWebhookName]
+		loggerWebhookSubnetProxy := subnetWebhookCfg.Get(logger.Proxy)
+		subnetProxy := cfg[config.SubnetSubSys][config.Default].Get(logger.Proxy)
+		if loggerWebhookSubnetProxy != subnetProxy {
+			subnetWebhookCfg.Set(logger.Proxy, subnetProxy)
+			return true
+		}
+	}
+	return false
+}

cmd/admin-handlers-idp-config.go

@@ -0,0 +1,439 @@
+// Copyright (c) 2015-2022 MinIO, Inc.
+//
+// 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 (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio-go/v7/pkg/set"
+	"github.com/minio/minio/internal/config"
+	cfgldap "github.com/minio/minio/internal/config/identity/ldap"
+	"github.com/minio/minio/internal/config/identity/openid"
+	"github.com/minio/mux"
+	"github.com/minio/pkg/v3/ldap"
+	"github.com/minio/pkg/v3/policy"
+)
+
+func addOrUpdateIDPHandler(ctx context.Context, w http.ResponseWriter, r *http.Request, isUpdate bool) {
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	if r.ContentLength > maxEConfigJSONSize || r.ContentLength == -1 {
+		// More than maxConfigSize bytes were available
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigTooLarge), r.URL)
+		return
+	}
+
+	// Ensure body content type is opaque to ensure that request body has not
+	// been interpreted as form data.
+	contentType := r.Header.Get("Content-Type")
+	if contentType != "application/octet-stream" {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrBadRequest), r.URL)
+		return
+	}
+
+	password := cred.SecretKey
+	reqBytes, err := madmin.DecryptData(password, io.LimitReader(r.Body, r.ContentLength))
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), r.URL)
+		return
+	}
+
+	idpCfgType := mux.Vars(r)["type"]
+	if !madmin.ValidIDPConfigTypes.Contains(idpCfgType) {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigInvalidIDPType), r.URL)
+		return
+	}
+
+	var subSys string
+	switch idpCfgType {
+	case madmin.OpenidIDPCfg:
+		subSys = madmin.IdentityOpenIDSubSys
+	case madmin.LDAPIDPCfg:
+		subSys = madmin.IdentityLDAPSubSys
+	}
+
+	cfgName := mux.Vars(r)["name"]
+	cfgTarget := madmin.Default
+	if cfgName != "" {
+		cfgTarget = cfgName
+		if idpCfgType == madmin.LDAPIDPCfg && cfgName != madmin.Default {
+			// LDAP does not support multiple configurations. So cfgName must be
+			// empty or `madmin.Default`.
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigLDAPNonDefaultConfigName), r.URL)
+			return
+		}
+	}
+
+	// Check that this is a valid Create vs Update API call.
+	s := globalServerConfig.Clone()
+	if apiErrCode := handleCreateUpdateValidation(s, subSys, cfgTarget, isUpdate); apiErrCode != ErrNone {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(apiErrCode), r.URL)
+		return
+	}
+
+	cfgData := ""
+	{
+		tgtSuffix := ""
+		if cfgTarget != madmin.Default {
+			tgtSuffix = config.SubSystemSeparator + cfgTarget
+		}
+		cfgData = subSys + tgtSuffix + config.KvSpaceSeparator + string(reqBytes)
+	}
+
+	cfg, err := readServerConfig(ctx, objectAPI, nil)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	dynamic, err := cfg.ReadConfig(strings.NewReader(cfgData))
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	// IDP config is not dynamic. Sanity check.
+	if dynamic {
+		writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrInternalError), "", r.URL)
+		return
+	}
+
+	if err = validateConfig(ctx, cfg, subSys); err != nil {
+		var validationErr ldap.Validation
+		if errors.As(err, &validationErr) {
+			// If we got an LDAP validation error, we need to send appropriate
+			// error message back to client (likely mc).
+			writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigLDAPValidation),
+				validationErr.FormatError(), r.URL)
+			return
+		}
+
+		writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), err.Error(), r.URL)
+		return
+	}
+
+	// Update the actual server config on disk.
+	if err = saveServerConfig(ctx, objectAPI, cfg); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	// Write to the config input KV to history.
+	if err = saveServerConfigHistory(ctx, objectAPI, []byte(cfgData)); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseHeadersOnly(w)
+}
+
+func handleCreateUpdateValidation(s config.Config, subSys, cfgTarget string, isUpdate bool) APIErrorCode {
+	if cfgTarget != madmin.Default {
+		// This cannot give an error at this point.
+		subSysTargets, _ := s.GetAvailableTargets(subSys)
+		subSysTargetsSet := set.CreateStringSet(subSysTargets...)
+		if isUpdate && !subSysTargetsSet.Contains(cfgTarget) {
+			return ErrAdminConfigIDPCfgNameDoesNotExist
+		}
+		if !isUpdate && subSysTargetsSet.Contains(cfgTarget) {
+			return ErrAdminConfigIDPCfgNameAlreadyExists
+		}
+
+		return ErrNone
+	}
+
+	// For the default configuration name, since it will always be an available
+	// target, we need to check if a configuration value has been set previously
+	// to figure out if this is a valid create or update API call.
+
+	// This cannot really error (FIXME: improve the type for GetConfigInfo)
+	var cfgInfos []madmin.IDPCfgInfo
+	switch subSys {
+	case madmin.IdentityOpenIDSubSys:
+		cfgInfos, _ = globalIAMSys.OpenIDConfig.GetConfigInfo(s, cfgTarget)
+	case madmin.IdentityLDAPSubSys:
+		cfgInfos, _ = globalIAMSys.LDAPConfig.GetConfigInfo(s, cfgTarget)
+	}
+
+	if len(cfgInfos) > 0 && !isUpdate {
+		return ErrAdminConfigIDPCfgNameAlreadyExists
+	}
+	if len(cfgInfos) == 0 && isUpdate {
+		return ErrAdminConfigIDPCfgNameDoesNotExist
+	}
+	return ErrNone
+}
+
+// AddIdentityProviderCfg: adds a new IDP config for openid/ldap.
+//
+// PUT <admin-prefix>/idp-cfg/openid/dex1 -> create named config `dex1`
+//
+// PUT <admin-prefix>/idp-cfg/openid/_ -> create (default) named config `_`
+func (a adminAPIHandlers) AddIdentityProviderCfg(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	addOrUpdateIDPHandler(ctx, w, r, false)
+}
+
+// UpdateIdentityProviderCfg: updates an existing IDP config for openid/ldap.
+//
+// POST <admin-prefix>/idp-cfg/openid/dex1 -> update named config `dex1`
+//
+// POST <admin-prefix>/idp-cfg/openid/_ -> update (default) named config `_`
+func (a adminAPIHandlers) UpdateIdentityProviderCfg(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	addOrUpdateIDPHandler(ctx, w, r, true)
+}
+
+// ListIdentityProviderCfg:
+//
+// GET <admin-prefix>/idp-cfg/openid -> lists openid provider configs.
+func (a adminAPIHandlers) ListIdentityProviderCfg(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+	password := cred.SecretKey
+
+	idpCfgType := mux.Vars(r)["type"]
+	if !madmin.ValidIDPConfigTypes.Contains(idpCfgType) {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigInvalidIDPType), r.URL)
+		return
+	}
+
+	var cfgList []madmin.IDPListItem
+	var err error
+	switch idpCfgType {
+	case madmin.OpenidIDPCfg:
+		cfg := globalServerConfig.Clone()
+		cfgList, err = globalIAMSys.OpenIDConfig.GetConfigList(cfg)
+	case madmin.LDAPIDPCfg:
+		cfg := globalServerConfig.Clone()
+		cfgList, err = globalIAMSys.LDAPConfig.GetConfigList(cfg)
+
+	default:
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	data, err := json.Marshal(cfgList)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	econfigData, err := madmin.EncryptData(password, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, econfigData)
+}
+
+// GetIdentityProviderCfg:
+//
+// GET <admin-prefix>/idp-cfg/openid/dex_test
+func (a adminAPIHandlers) GetIdentityProviderCfg(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	idpCfgType := mux.Vars(r)["type"]
+	cfgName := mux.Vars(r)["name"]
+	password := cred.SecretKey
+
+	if !madmin.ValidIDPConfigTypes.Contains(idpCfgType) {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigInvalidIDPType), r.URL)
+		return
+	}
+
+	cfg := globalServerConfig.Clone()
+	var cfgInfos []madmin.IDPCfgInfo
+	var err error
+	switch idpCfgType {
+	case madmin.OpenidIDPCfg:
+		cfgInfos, err = globalIAMSys.OpenIDConfig.GetConfigInfo(cfg, cfgName)
+	case madmin.LDAPIDPCfg:
+		cfgInfos, err = globalIAMSys.LDAPConfig.GetConfigInfo(cfg, cfgName)
+	}
+	if err != nil {
+		if errors.Is(err, openid.ErrProviderConfigNotFound) || errors.Is(err, cfgldap.ErrProviderConfigNotFound) {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminNoSuchConfigTarget), r.URL)
+			return
+		}
+
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	res := madmin.IDPConfig{
+		Type: idpCfgType,
+		Name: cfgName,
+		Info: cfgInfos,
+	}
+	data, err := json.Marshal(res)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	econfigData, err := madmin.EncryptData(password, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, econfigData)
+}
+
+// DeleteIdentityProviderCfg:
+//
+// DELETE <admin-prefix>/idp-cfg/openid/dex_test
+func (a adminAPIHandlers) DeleteIdentityProviderCfg(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.ConfigUpdateAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	idpCfgType := mux.Vars(r)["type"]
+	cfgName := mux.Vars(r)["name"]
+	if !madmin.ValidIDPConfigTypes.Contains(idpCfgType) {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigInvalidIDPType), r.URL)
+		return
+	}
+
+	cfgCopy := globalServerConfig.Clone()
+	var subSys string
+	switch idpCfgType {
+	case madmin.OpenidIDPCfg:
+		subSys = config.IdentityOpenIDSubSys
+		cfgInfos, err := globalIAMSys.OpenIDConfig.GetConfigInfo(cfgCopy, cfgName)
+		if err != nil {
+			if errors.Is(err, openid.ErrProviderConfigNotFound) {
+				writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminNoSuchConfigTarget), r.URL)
+				return
+			}
+
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+
+		hasEnv := false
+		for _, ci := range cfgInfos {
+			if ci.IsCfg && ci.IsEnv {
+				hasEnv = true
+				break
+			}
+		}
+
+		if hasEnv {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigEnvOverridden), r.URL)
+			return
+		}
+	case madmin.LDAPIDPCfg:
+		subSys = config.IdentityLDAPSubSys
+		cfgInfos, err := globalIAMSys.LDAPConfig.GetConfigInfo(cfgCopy, cfgName)
+		if err != nil {
+			if errors.Is(err, openid.ErrProviderConfigNotFound) {
+				writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminNoSuchConfigTarget), r.URL)
+				return
+			}
+
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+
+		hasEnv := false
+		for _, ci := range cfgInfos {
+			if ci.IsCfg && ci.IsEnv {
+				hasEnv = true
+				break
+			}
+		}
+
+		if hasEnv {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigEnvOverridden), r.URL)
+			return
+		}
+	default:
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	cfg, err := readServerConfig(ctx, objectAPI, nil)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	cfgKey := fmt.Sprintf("%s:%s", subSys, cfgName)
+	if cfgName == madmin.Default {
+		cfgKey = subSys
+	}
+	if err = cfg.DelKVS(cfgKey); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	if err = validateConfig(ctx, cfg, subSys); err != nil {
+		var validationErr ldap.Validation
+		if errors.As(err, &validationErr) {
+			// If we got an LDAP validation error, we need to send appropriate
+			// error message back to client (likely mc).
+			writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigLDAPValidation),
+				validationErr.FormatError(), r.URL)
+			return
+		}
+
+		writeCustomErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), err.Error(), r.URL)
+		return
+	}
+	if err = saveServerConfig(ctx, objectAPI, cfg); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	dynamic := config.SubSystemsDynamic.Contains(subSys)
+	if dynamic {
+		applyDynamic(ctx, objectAPI, cfg, subSys, r, w)
+	}
+}

cmd/admin-handlers-idp-ldap.go

@@ -0,0 +1,653 @@
+// Copyright (c) 2015-2022 MinIO, Inc.
+//
+// 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 (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/mux"
+	xldap "github.com/minio/pkg/v3/ldap"
+	"github.com/minio/pkg/v3/policy"
+)
+
+// ListLDAPPolicyMappingEntities lists users/groups mapped to given/all policies.
+//
+// GET <admin-prefix>/idp/ldap/policy-entities?[query-params]
+//
+// Query params:
+//
+//	user=... -> repeatable query parameter, specifying users to query for
+//	policy mapping
+//
+//	group=... -> repeatable query parameter, specifying groups to query for
+//	policy mapping
+//
+//	policy=... -> repeatable query parameter, specifying policy to query for
+//	user/group mapping
+//
+// When all query parameters are omitted, returns mappings for all policies.
+func (a adminAPIHandlers) ListLDAPPolicyMappingEntities(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	// Check authorization.
+
+	objectAPI, cred := validateAdminReq(ctx, w, r,
+		policy.ListGroupsAdminAction, policy.ListUsersAdminAction, policy.ListUserPoliciesAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// Validate API arguments.
+
+	q := madmin.PolicyEntitiesQuery{
+		Users:  r.Form["user"],
+		Groups: r.Form["group"],
+		Policy: r.Form["policy"],
+	}
+
+	// Query IAM
+
+	res, err := globalIAMSys.QueryLDAPPolicyEntities(r.Context(), q)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	// Encode result and send response.
+
+	data, err := json.Marshal(res)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	password := cred.SecretKey
+	econfigData, err := madmin.EncryptData(password, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	writeSuccessResponseJSON(w, econfigData)
+}
+
+// AttachDetachPolicyLDAP attaches or detaches policies from an LDAP entity
+// (user or group).
+//
+// POST <admin-prefix>/idp/ldap/policy/{operation}
+func (a adminAPIHandlers) AttachDetachPolicyLDAP(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	// Check authorization.
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.UpdatePolicyAssociationAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// fail if ldap is not enabled
+	if !globalIAMSys.LDAPConfig.Enabled() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminLDAPNotEnabled), r.URL)
+		return
+	}
+
+	if r.ContentLength > maxEConfigJSONSize || r.ContentLength == -1 {
+		// More than maxConfigSize bytes were available
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigTooLarge), r.URL)
+		return
+	}
+
+	// Ensure body content type is opaque to ensure that request body has not
+	// been interpreted as form data.
+	contentType := r.Header.Get("Content-Type")
+	if contentType != "application/octet-stream" {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrBadRequest), r.URL)
+		return
+	}
+
+	// Validate operation
+	operation := mux.Vars(r)["operation"]
+	if operation != "attach" && operation != "detach" {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminInvalidArgument), r.URL)
+		return
+	}
+
+	isAttach := operation == "attach"
+
+	// Validate API arguments in body.
+	password := cred.SecretKey
+	reqBytes, err := madmin.DecryptData(password, io.LimitReader(r.Body, r.ContentLength))
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), r.URL)
+		return
+	}
+
+	var par madmin.PolicyAssociationReq
+	err = json.Unmarshal(reqBytes, &par)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrInvalidRequest), r.URL)
+		return
+	}
+
+	if err := par.IsValid(); err != nil {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminConfigBadJSON), r.URL)
+		return
+	}
+
+	// Call IAM subsystem
+	updatedAt, addedOrRemoved, _, err := globalIAMSys.PolicyDBUpdateLDAP(ctx, isAttach, par)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	respBody := madmin.PolicyAssociationResp{
+		UpdatedAt: updatedAt,
+	}
+	if isAttach {
+		respBody.PoliciesAttached = addedOrRemoved
+	} else {
+		respBody.PoliciesDetached = addedOrRemoved
+	}
+
+	data, err := json.Marshal(respBody)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	encryptedData, err := madmin.EncryptData(password, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, encryptedData)
+}
+
+// AddServiceAccountLDAP adds a new service account for provided LDAP username or DN
+//
+// PUT /minio/admin/v3/idp/ldap/add-service-account
+func (a adminAPIHandlers) AddServiceAccountLDAP(w http.ResponseWriter, r *http.Request) {
+	ctx, cred, opts, createReq, targetUser, APIError := commonAddServiceAccount(r, true)
+	if APIError.Code != "" {
+		writeErrorResponseJSON(ctx, w, APIError, r.URL)
+		return
+	}
+
+	// fail if ldap is not enabled
+	if !globalIAMSys.LDAPConfig.Enabled() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminLDAPNotEnabled), r.URL)
+		return
+	}
+
+	// Find the user for the request sender (as it may be sent via a service
+	// account or STS account):
+	requestorUser := cred.AccessKey
+	requestorParentUser := cred.AccessKey
+	requestorGroups := cred.Groups
+	requestorIsDerivedCredential := false
+	if cred.IsServiceAccount() || cred.IsTemp() {
+		requestorParentUser = cred.ParentUser
+		requestorIsDerivedCredential = true
+	}
+
+	// Check if we are creating svc account for request sender.
+	isSvcAccForRequestor := targetUser == requestorUser || targetUser == requestorParentUser
+
+	var (
+		targetGroups []string
+		err          error
+	)
+
+	// If we are creating svc account for request sender, ensure that targetUser
+	// is a real user (i.e. not derived credentials).
+	if isSvcAccForRequestor {
+		if requestorIsDerivedCredential {
+			if requestorParentUser == "" {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx,
+					errors.New("service accounts cannot be generated for temporary credentials without parent")), r.URL)
+				return
+			}
+			targetUser = requestorParentUser
+		}
+		targetGroups = requestorGroups
+
+		// Deny if the target user is not LDAP
+		foundResult, err := globalIAMSys.LDAPConfig.GetValidatedDNForUsername(targetUser)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+		if foundResult == nil {
+			err := errors.New("Specified user does not exist on LDAP server")
+			APIErr := errorCodes.ToAPIErrWithErr(ErrAdminNoSuchUser, err)
+			writeErrorResponseJSON(ctx, w, APIErr, r.URL)
+			return
+		}
+
+		// In case of LDAP/OIDC we need to set `opts.claims` to ensure
+		// it is associated with the LDAP/OIDC user properly.
+		for k, v := range cred.Claims {
+			if k == expClaim {
+				continue
+			}
+			opts.claims[k] = v
+		}
+	} else {
+		// We still need to ensure that the target user is a valid LDAP user.
+		//
+		// The target user may be supplied as a (short) username or a DN.
+		// However, for now, we only support using the short username.
+
+		isDN := globalIAMSys.LDAPConfig.ParsesAsDN(targetUser)
+		opts.claims[ldapUserN] = targetUser // simple username
+		var lookupResult *xldap.DNSearchResult
+		lookupResult, targetGroups, err = globalIAMSys.LDAPConfig.LookupUserDN(targetUser)
+		if err != nil {
+			// if not found, check if DN
+			if strings.Contains(err.Error(), "User DN not found for:") {
+				if isDN {
+					// warn user that DNs are not allowed
+					writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErrWithErr(ErrAdminLDAPExpectedLoginName, err), r.URL)
+				} else {
+					writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErrWithErr(ErrAdminNoSuchUser, err), r.URL)
+				}
+			}
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+		targetUser = lookupResult.NormDN
+		opts.claims[ldapUser] = targetUser // DN
+		opts.claims[ldapActualUser] = lookupResult.ActualDN
+
+		// Check if this user or their groups have a policy applied.
+		ldapPolicies, err := globalIAMSys.PolicyDBGet(targetUser, targetGroups...)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+		if len(ldapPolicies) == 0 {
+			err = fmt.Errorf("No policy set for user `%s` or any of their groups: `%s`", opts.claims[ldapActualUser], strings.Join(targetGroups, "`,`"))
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErrWithErr(ErrAdminNoSuchUser, err), r.URL)
+			return
+		}
+
+		// Add LDAP attributes that were looked up into the claims.
+		for attribKey, attribValue := range lookupResult.Attributes {
+			opts.claims[ldapAttribPrefix+attribKey] = attribValue
+		}
+	}
+
+	newCred, updatedAt, err := globalIAMSys.NewServiceAccount(ctx, targetUser, targetGroups, opts)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	createResp := madmin.AddServiceAccountResp{
+		Credentials: madmin.Credentials{
+			AccessKey:  newCred.AccessKey,
+			SecretKey:  newCred.SecretKey,
+			Expiration: newCred.Expiration,
+		},
+	}
+
+	data, err := json.Marshal(createResp)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	encryptedData, err := madmin.EncryptData(cred.SecretKey, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, encryptedData)
+
+	// Call hook for cluster-replication if the service account is not for a
+	// root user.
+	if newCred.ParentUser != globalActiveCred.AccessKey {
+		replLogIf(ctx, globalSiteReplicationSys.IAMChangeHook(ctx, madmin.SRIAMItem{
+			Type: madmin.SRIAMItemSvcAcc,
+			SvcAccChange: &madmin.SRSvcAccChange{
+				Create: &madmin.SRSvcAccCreate{
+					Parent:        newCred.ParentUser,
+					AccessKey:     newCred.AccessKey,
+					SecretKey:     newCred.SecretKey,
+					Groups:        newCred.Groups,
+					Name:          newCred.Name,
+					Description:   newCred.Description,
+					Claims:        opts.claims,
+					SessionPolicy: madmin.SRSessionPolicy(createReq.Policy),
+					Status:        auth.AccountOn,
+					Expiration:    createReq.Expiration,
+				},
+			},
+			UpdatedAt: updatedAt,
+		}))
+	}
+}
+
+// ListAccessKeysLDAP - GET /minio/admin/v3/idp/ldap/list-access-keys
+func (a adminAPIHandlers) ListAccessKeysLDAP(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	// Get current object layer instance.
+	objectAPI := newObjectLayerFn()
+	if objectAPI == nil || globalNotificationSys == nil {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	cred, owner, s3Err := validateAdminSignature(ctx, r, "")
+	if s3Err != ErrNone {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(s3Err), r.URL)
+		return
+	}
+
+	userDN := r.Form.Get("userDN")
+
+	// If listing is requested for a specific user (who is not the request
+	// sender), check that the user has permissions.
+	if userDN != "" && userDN != cred.ParentUser {
+		if !globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.ListServiceAccountsAdminAction,
+			ConditionValues: getConditionValues(r, "", cred),
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+		}) {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+			return
+		}
+	} else {
+		if !globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.ListServiceAccountsAdminAction,
+			ConditionValues: getConditionValues(r, "", cred),
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+			DenyOnly:        true,
+		}) {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+			return
+		}
+		userDN = cred.AccessKey
+		if cred.ParentUser != "" {
+			userDN = cred.ParentUser
+		}
+	}
+
+	dnResult, err := globalIAMSys.LDAPConfig.GetValidatedDNForUsername(userDN)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	if dnResult == nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errNoSuchUser), r.URL)
+		return
+	}
+	targetAccount := dnResult.NormDN
+
+	listType := r.Form.Get("listType")
+	if listType != "sts-only" && listType != "svcacc-only" && listType != "" {
+		// default to both
+		listType = ""
+	}
+
+	var serviceAccounts []auth.Credentials
+	var stsKeys []auth.Credentials
+
+	if listType == "" || listType == "sts-only" {
+		stsKeys, err = globalIAMSys.ListSTSAccounts(ctx, targetAccount)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+	}
+	if listType == "" || listType == "svcacc-only" {
+		serviceAccounts, err = globalIAMSys.ListServiceAccounts(ctx, targetAccount)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+	}
+
+	var serviceAccountList []madmin.ServiceAccountInfo
+	var stsKeyList []madmin.ServiceAccountInfo
+
+	for _, svc := range serviceAccounts {
+		expiryTime := svc.Expiration
+		serviceAccountList = append(serviceAccountList, madmin.ServiceAccountInfo{
+			AccessKey:  svc.AccessKey,
+			Expiration: &expiryTime,
+		})
+	}
+	for _, sts := range stsKeys {
+		expiryTime := sts.Expiration
+		stsKeyList = append(stsKeyList, madmin.ServiceAccountInfo{
+			AccessKey:  sts.AccessKey,
+			Expiration: &expiryTime,
+		})
+	}
+
+	listResp := madmin.ListAccessKeysLDAPResp{
+		ServiceAccounts: serviceAccountList,
+		STSKeys:         stsKeyList,
+	}
+
+	data, err := json.Marshal(listResp)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	encryptedData, err := madmin.EncryptData(cred.SecretKey, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, encryptedData)
+}
+
+// ListAccessKeysLDAPBulk - GET /minio/admin/v3/idp/ldap/list-access-keys-bulk
+func (a adminAPIHandlers) ListAccessKeysLDAPBulk(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	// Get current object layer instance.
+	objectAPI := newObjectLayerFn()
+	if objectAPI == nil || globalNotificationSys == nil {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	cred, owner, s3Err := validateAdminSignature(ctx, r, "")
+	if s3Err != ErrNone {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(s3Err), r.URL)
+		return
+	}
+
+	dnList := r.Form["userDNs"]
+	isAll := r.Form.Get("all") == "true"
+	selfOnly := !isAll && len(dnList) == 0
+
+	if isAll && len(dnList) > 0 {
+		// This should be checked on client side, so return generic error
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrInvalidRequest), r.URL)
+		return
+	}
+
+	// Empty DN list and not self, list access keys for all users
+	if isAll {
+		if !globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.ListUsersAdminAction,
+			ConditionValues: getConditionValues(r, "", cred),
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+		}) {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+			return
+		}
+	} else if len(dnList) == 1 {
+		var dn string
+		foundResult, err := globalIAMSys.LDAPConfig.GetValidatedDNForUsername(dnList[0])
+		if err == nil {
+			dn = foundResult.NormDN
+		}
+		if dn == cred.ParentUser || dnList[0] == cred.ParentUser {
+			selfOnly = true
+		}
+	}
+
+	if !globalIAMSys.IsAllowed(policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          policy.ListServiceAccountsAdminAction,
+		ConditionValues: getConditionValues(r, "", cred),
+		IsOwner:         owner,
+		Claims:          cred.Claims,
+		DenyOnly:        selfOnly,
+	}) {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+		return
+	}
+
+	if selfOnly && len(dnList) == 0 {
+		selfDN := cred.AccessKey
+		if cred.ParentUser != "" {
+			selfDN = cred.ParentUser
+		}
+		dnList = append(dnList, selfDN)
+	}
+
+	var ldapUserList []string
+	if isAll {
+		ldapUsers, err := globalIAMSys.ListLDAPUsers(ctx)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+		for user := range ldapUsers {
+			ldapUserList = append(ldapUserList, user)
+		}
+	} else {
+		for _, userDN := range dnList {
+			// Validate the userDN
+			foundResult, err := globalIAMSys.LDAPConfig.GetValidatedDNForUsername(userDN)
+			if err != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+				return
+			}
+			if foundResult == nil {
+				continue
+			}
+			ldapUserList = append(ldapUserList, foundResult.NormDN)
+		}
+	}
+
+	listType := r.Form.Get("listType")
+	var listSTSKeys, listServiceAccounts bool
+	switch listType {
+	case madmin.AccessKeyListUsersOnly:
+		listSTSKeys = false
+		listServiceAccounts = false
+	case madmin.AccessKeyListSTSOnly:
+		listSTSKeys = true
+		listServiceAccounts = false
+	case madmin.AccessKeyListSvcaccOnly:
+		listSTSKeys = false
+		listServiceAccounts = true
+	case madmin.AccessKeyListAll:
+		listSTSKeys = true
+		listServiceAccounts = true
+	default:
+		err := errors.New("invalid list type")
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErrWithErr(ErrInvalidRequest, err), r.URL)
+		return
+	}
+
+	accessKeyMap := make(map[string]madmin.ListAccessKeysLDAPResp)
+	for _, internalDN := range ldapUserList {
+		externalDN := globalIAMSys.LDAPConfig.DecodeDN(internalDN)
+		accessKeys := madmin.ListAccessKeysLDAPResp{}
+		if listSTSKeys {
+			stsKeys, err := globalIAMSys.ListSTSAccounts(ctx, internalDN)
+			if err != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+				return
+			}
+			for _, sts := range stsKeys {
+				accessKeys.STSKeys = append(accessKeys.STSKeys, madmin.ServiceAccountInfo{
+					AccessKey:  sts.AccessKey,
+					Expiration: &sts.Expiration,
+				})
+			}
+			// if only STS keys, skip if user has no STS keys
+			if !listServiceAccounts && len(stsKeys) == 0 {
+				continue
+			}
+		}
+
+		if listServiceAccounts {
+			serviceAccounts, err := globalIAMSys.ListServiceAccounts(ctx, internalDN)
+			if err != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+				return
+			}
+			for _, svc := range serviceAccounts {
+				accessKeys.ServiceAccounts = append(accessKeys.ServiceAccounts, madmin.ServiceAccountInfo{
+					AccessKey:  svc.AccessKey,
+					Expiration: &svc.Expiration,
+				})
+			}
+			// if only service accounts, skip if user has no service accounts
+			if !listSTSKeys && len(serviceAccounts) == 0 {
+				continue
+			}
+		}
+		accessKeyMap[externalDN] = accessKeys
+	}
+
+	data, err := json.Marshal(accessKeyMap)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	encryptedData, err := madmin.EncryptData(cred.SecretKey, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, encryptedData)
+}

cmd/admin-handlers-idp-openid.go

@@ -0,0 +1,246 @@
+// Copyright (c) 2015-2025 MinIO, Inc.
+//
+// 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 (
+	"encoding/json"
+	"errors"
+	"net/http"
+	"sort"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio-go/v7/pkg/set"
+	"github.com/minio/pkg/v3/policy"
+)
+
+const dummyRoleARN = "dummy-internal"
+
+// ListAccessKeysOpenIDBulk - GET /minio/admin/v3/idp/openid/list-access-keys-bulk
+func (a adminAPIHandlers) ListAccessKeysOpenIDBulk(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	// Get current object layer instance.
+	objectAPI := newObjectLayerFn()
+	if objectAPI == nil || globalNotificationSys == nil {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+		return
+	}
+
+	cred, owner, s3Err := validateAdminSignature(ctx, r, "")
+	if s3Err != ErrNone {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(s3Err), r.URL)
+		return
+	}
+
+	if !globalIAMSys.OpenIDConfig.Enabled {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminOpenIDNotEnabled), r.URL)
+		return
+	}
+
+	userList := r.Form["users"]
+	isAll := r.Form.Get("all") == "true"
+	selfOnly := !isAll && len(userList) == 0
+	cfgName := r.Form.Get("configName")
+	allConfigs := r.Form.Get("allConfigs") == "true"
+	if cfgName == "" && !allConfigs {
+		cfgName = madmin.Default
+	}
+
+	if isAll && len(userList) > 0 {
+		// This should be checked on client side, so return generic error
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrInvalidRequest), r.URL)
+		return
+	}
+
+	// Empty DN list and not self, list access keys for all users
+	if isAll {
+		if !globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.ListUsersAdminAction,
+			ConditionValues: getConditionValues(r, "", cred),
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+		}) {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+			return
+		}
+	} else if len(userList) == 1 && userList[0] == cred.ParentUser {
+		selfOnly = true
+	}
+
+	if !globalIAMSys.IsAllowed(policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          policy.ListServiceAccountsAdminAction,
+		ConditionValues: getConditionValues(r, "", cred),
+		IsOwner:         owner,
+		Claims:          cred.Claims,
+		DenyOnly:        selfOnly,
+	}) {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAccessDenied), r.URL)
+		return
+	}
+
+	if selfOnly && len(userList) == 0 {
+		selfDN := cred.AccessKey
+		if cred.ParentUser != "" {
+			selfDN = cred.ParentUser
+		}
+		userList = append(userList, selfDN)
+	}
+
+	listType := r.Form.Get("listType")
+	var listSTSKeys, listServiceAccounts bool
+	switch listType {
+	case madmin.AccessKeyListUsersOnly:
+		listSTSKeys = false
+		listServiceAccounts = false
+	case madmin.AccessKeyListSTSOnly:
+		listSTSKeys = true
+		listServiceAccounts = false
+	case madmin.AccessKeyListSvcaccOnly:
+		listSTSKeys = false
+		listServiceAccounts = true
+	case madmin.AccessKeyListAll:
+		listSTSKeys = true
+		listServiceAccounts = true
+	default:
+		err := errors.New("invalid list type")
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErrWithErr(ErrInvalidRequest, err), r.URL)
+		return
+	}
+
+	s := globalServerConfig.Clone()
+	roleArnMap := make(map[string]string)
+	// Map of configs to a map of users to their access keys
+	cfgToUsersMap := make(map[string]map[string]madmin.OpenIDUserAccessKeys)
+	configs, err := globalIAMSys.OpenIDConfig.GetConfigList(s)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	for _, config := range configs {
+		if !allConfigs && cfgName != config.Name {
+			continue
+		}
+		arn := dummyRoleARN
+		if config.RoleARN != "" {
+			arn = config.RoleARN
+		}
+		roleArnMap[arn] = config.Name
+		newResp := make(map[string]madmin.OpenIDUserAccessKeys)
+		cfgToUsersMap[config.Name] = newResp
+	}
+	if len(roleArnMap) == 0 {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminNoSuchConfigTarget), r.URL)
+		return
+	}
+
+	userSet := set.CreateStringSet(userList...)
+	accessKeys, err := globalIAMSys.ListAllAccessKeys(ctx)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	for _, accessKey := range accessKeys {
+		// Filter out any disqualifying access keys
+		_, ok := accessKey.Claims[subClaim]
+		if !ok {
+			continue // OpenID access keys must have a sub claim
+		}
+		if (!listSTSKeys && !accessKey.IsServiceAccount()) || (!listServiceAccounts && accessKey.IsServiceAccount()) {
+			continue // skip if not the type we want
+		}
+		arn, ok := accessKey.Claims[roleArnClaim].(string)
+		if !ok {
+			if _, ok := accessKey.Claims[iamPolicyClaimNameOpenID()]; !ok {
+				continue // skip if no roleArn and no policy claim
+			}
+		}
+		matchingCfgName, ok := roleArnMap[arn]
+		if !ok {
+			continue // skip if not part of the target config
+		}
+		var id string
+		if idClaim := globalIAMSys.OpenIDConfig.GetUserIDClaim(matchingCfgName); idClaim != "" {
+			id, _ = accessKey.Claims[idClaim].(string)
+		}
+		if !userSet.IsEmpty() && !userSet.Contains(accessKey.ParentUser) && !userSet.Contains(id) {
+			continue // skip if not in the user list
+		}
+		openIDUserAccessKeys, ok := cfgToUsersMap[matchingCfgName][accessKey.ParentUser]
+
+		// Add new user to map if not already present
+		if !ok {
+			var readableClaim string
+			if rc := globalIAMSys.OpenIDConfig.GetUserReadableClaim(matchingCfgName); rc != "" {
+				readableClaim, _ = accessKey.Claims[rc].(string)
+			}
+			openIDUserAccessKeys = madmin.OpenIDUserAccessKeys{
+				MinioAccessKey: accessKey.ParentUser,
+				ID:             id,
+				ReadableName:   readableClaim,
+			}
+		}
+		svcAccInfo := madmin.ServiceAccountInfo{
+			AccessKey:  accessKey.AccessKey,
+			Expiration: &accessKey.Expiration,
+		}
+		if accessKey.IsServiceAccount() {
+			openIDUserAccessKeys.ServiceAccounts = append(openIDUserAccessKeys.ServiceAccounts, svcAccInfo)
+		} else {
+			openIDUserAccessKeys.STSKeys = append(openIDUserAccessKeys.STSKeys, svcAccInfo)
+		}
+		cfgToUsersMap[matchingCfgName][accessKey.ParentUser] = openIDUserAccessKeys
+	}
+
+	// Convert map to slice and sort
+	resp := make([]madmin.ListAccessKeysOpenIDResp, 0, len(cfgToUsersMap))
+	for cfgName, usersMap := range cfgToUsersMap {
+		users := make([]madmin.OpenIDUserAccessKeys, 0, len(usersMap))
+		for _, user := range usersMap {
+			users = append(users, user)
+		}
+		sort.Slice(users, func(i, j int) bool {
+			return users[i].MinioAccessKey < users[j].MinioAccessKey
+		})
+		resp = append(resp, madmin.ListAccessKeysOpenIDResp{
+			ConfigName: cfgName,
+			Users:      users,
+		})
+	}
+	sort.Slice(resp, func(i, j int) bool {
+		return resp[i].ConfigName < resp[j].ConfigName
+	})
+
+	data, err := json.Marshal(resp)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	encryptedData, err := madmin.EncryptData(cred.SecretKey, data)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, encryptedData)
+}

cmd/admin-handlers-pools.go

@@ -0,0 +1,393 @@
+// Copyright (c) 2015-2024 MinIO, Inc.
+//
+// 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 (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"strconv"
+	"strings"
+
+	"github.com/minio/mux"
+	"github.com/minio/pkg/v3/env"
+	"github.com/minio/pkg/v3/policy"
+)
+
+var (
+	errRebalanceDecommissionAlreadyRunning = errors.New("Rebalance cannot be started, decommission is already in progress")
+	errDecommissionRebalanceAlreadyRunning = errors.New("Decommission cannot be started, rebalance is already in progress")
+)
+
+func (a adminAPIHandlers) StartDecommission(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.DecommissionAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// Legacy args style such as non-ellipses style is not supported with this API.
+	if globalEndpoints.Legacy() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	z, ok := objectAPI.(*erasureServerPools)
+	if !ok || len(z.serverPools) == 1 {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	if z.IsDecommissionRunning() {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errDecommissionAlreadyRunning), r.URL)
+		return
+	}
+
+	if z.IsRebalanceStarted() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminRebalanceAlreadyStarted), r.URL)
+		return
+	}
+
+	vars := mux.Vars(r)
+	v := vars["pool"]
+	byID := vars["by-id"] == "true"
+
+	pools := strings.Split(v, ",")
+	poolIndices := make([]int, 0, len(pools))
+
+	for _, pool := range pools {
+		var idx int
+		if byID {
+			var err error
+			idx, err = strconv.Atoi(pool)
+			if err != nil {
+				// We didn't find any matching pools, invalid input
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errInvalidArgument), r.URL)
+				return
+			}
+		} else {
+			idx = globalEndpoints.GetPoolIdx(pool)
+			if idx == -1 {
+				// We didn't find any matching pools, invalid input
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errInvalidArgument), r.URL)
+				return
+			}
+		}
+		var pool *erasureSets
+		for pidx := range z.serverPools {
+			if pidx == idx {
+				pool = z.serverPools[idx]
+				break
+			}
+		}
+		if pool == nil {
+			// We didn't find any matching pools, invalid input
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errInvalidArgument), r.URL)
+			return
+		}
+
+		poolIndices = append(poolIndices, idx)
+	}
+
+	if len(poolIndices) == 0 || !proxyDecommissionRequest(ctx, globalEndpoints[poolIndices[0]].Endpoints[0], w, r) {
+		if err := z.Decommission(r.Context(), poolIndices...); err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+	}
+}
+
+func (a adminAPIHandlers) CancelDecommission(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.DecommissionAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// Legacy args style such as non-ellipses style is not supported with this API.
+	if globalEndpoints.Legacy() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	pools, ok := objectAPI.(*erasureServerPools)
+	if !ok {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	vars := mux.Vars(r)
+	v := vars["pool"]
+	byID := vars["by-id"] == "true"
+	idx := -1
+
+	if byID {
+		if i, err := strconv.Atoi(v); err == nil && i >= 0 && i < len(globalEndpoints) {
+			idx = i
+		}
+	} else {
+		idx = globalEndpoints.GetPoolIdx(v)
+	}
+
+	if idx == -1 {
+		// We didn't find any matching pools, invalid input
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errInvalidArgument), r.URL)
+		return
+	}
+
+	if !proxyDecommissionRequest(ctx, globalEndpoints[idx].Endpoints[0], w, r) {
+		if err := pools.DecommissionCancel(ctx, idx); err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+	}
+}
+
+func (a adminAPIHandlers) StatusPool(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.ServerInfoAdminAction, policy.DecommissionAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// Legacy args style such as non-ellipses style is not supported with this API.
+	if globalEndpoints.Legacy() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	pools, ok := objectAPI.(*erasureServerPools)
+	if !ok {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	vars := mux.Vars(r)
+	v := vars["pool"]
+	byID := vars["by-id"] == "true"
+	idx := -1
+
+	if byID {
+		if i, err := strconv.Atoi(v); err == nil && i >= 0 && i < len(globalEndpoints) {
+			idx = i
+		}
+	} else {
+		idx = globalEndpoints.GetPoolIdx(v)
+	}
+
+	if idx == -1 {
+		apiErr := toAdminAPIErr(ctx, errInvalidArgument)
+		apiErr.Description = fmt.Sprintf("specified pool '%s' not found, please specify a valid pool", v)
+		// We didn't find any matching pools, invalid input
+		writeErrorResponseJSON(ctx, w, apiErr, r.URL)
+		return
+	}
+
+	status, err := pools.Status(r.Context(), idx)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	adminLogIf(r.Context(), json.NewEncoder(w).Encode(&status))
+}
+
+func (a adminAPIHandlers) ListPools(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.ServerInfoAdminAction, policy.DecommissionAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// Legacy args style such as non-ellipses style is not supported with this API.
+	if globalEndpoints.Legacy() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	pools, ok := objectAPI.(*erasureServerPools)
+	if !ok {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	poolsStatus := make([]PoolStatus, len(globalEndpoints))
+	for idx := range globalEndpoints {
+		status, err := pools.Status(r.Context(), idx)
+		if err != nil {
+			writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+			return
+		}
+		poolsStatus[idx] = status
+	}
+
+	adminLogIf(r.Context(), json.NewEncoder(w).Encode(poolsStatus))
+}
+
+func (a adminAPIHandlers) RebalanceStart(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.RebalanceAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// NB rebalance-start admin API is always coordinated from first pool's
+	// first node. The following is required to serialize (the effects of)
+	// concurrent rebalance-start commands.
+	if ep := globalEndpoints[0].Endpoints[0]; !ep.IsLocal {
+		for nodeIdx, proxyEp := range globalProxyEndpoints {
+			if proxyEp.Host == ep.Host {
+				if proxied, success := proxyRequestByNodeIndex(ctx, w, r, nodeIdx, false); proxied && success {
+					return
+				}
+			}
+		}
+	}
+
+	pools, ok := objectAPI.(*erasureServerPools)
+	if !ok || len(pools.serverPools) == 1 {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	if pools.IsDecommissionRunning() {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errRebalanceDecommissionAlreadyRunning), r.URL)
+		return
+	}
+
+	if pools.IsRebalanceStarted() {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminRebalanceAlreadyStarted), r.URL)
+		return
+	}
+
+	bucketInfos, err := objectAPI.ListBuckets(ctx, BucketOptions{})
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	buckets := make([]string, 0, len(bucketInfos))
+	for _, bInfo := range bucketInfos {
+		buckets = append(buckets, bInfo.Name)
+	}
+
+	var id string
+	if id, err = pools.initRebalanceMeta(ctx, buckets); err != nil {
+		writeErrorResponseJSON(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	// Rebalance routine is run on the first node of any pool participating in rebalance.
+	pools.StartRebalance()
+
+	b, err := json.Marshal(struct {
+		ID string `json:"id"`
+	}{ID: id})
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAPIError(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, b)
+	// Notify peers to load rebalance.bin and start rebalance routine if they happen to be
+	// participating pool's leader node
+	globalNotificationSys.LoadRebalanceMeta(ctx, true)
+}
+
+func (a adminAPIHandlers) RebalanceStatus(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.RebalanceAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	// Proxy rebalance-status to first pool first node, so that users see a
+	// consistent view of rebalance progress even though different rebalancing
+	// pools may temporarily have out of date info on the others.
+	if ep := globalEndpoints[0].Endpoints[0]; !ep.IsLocal {
+		for nodeIdx, proxyEp := range globalProxyEndpoints {
+			if proxyEp.Host == ep.Host {
+				if proxied, success := proxyRequestByNodeIndex(ctx, w, r, nodeIdx, false); proxied && success {
+					return
+				}
+			}
+		}
+	}
+
+	pools, ok := objectAPI.(*erasureServerPools)
+	if !ok {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	rs, err := rebalanceStatus(ctx, pools)
+	if err != nil {
+		if errors.Is(err, errRebalanceNotStarted) || errors.Is(err, errConfigNotFound) {
+			writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrAdminRebalanceNotStarted), r.URL)
+			return
+		}
+		adminLogIf(ctx, fmt.Errorf("failed to fetch rebalance status: %w", err))
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	adminLogIf(r.Context(), json.NewEncoder(w).Encode(rs))
+}
+
+func (a adminAPIHandlers) RebalanceStop(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.RebalanceAdminAction)
+	if objectAPI == nil {
+		return
+	}
+
+	pools, ok := objectAPI.(*erasureServerPools)
+	if !ok {
+		writeErrorResponseJSON(ctx, w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+		return
+	}
+
+	// Cancel any ongoing rebalance operation
+	globalNotificationSys.StopRebalance(r.Context())
+	writeSuccessResponseHeadersOnly(w)
+	adminLogIf(ctx, pools.saveRebalanceStats(GlobalContext, 0, rebalSaveStoppedAt))
+	globalNotificationSys.LoadRebalanceMeta(ctx, false)
+}
+
+func proxyDecommissionRequest(ctx context.Context, defaultEndPoint Endpoint, w http.ResponseWriter, r *http.Request) (proxy bool) {
+	host := env.Get("_MINIO_DECOM_ENDPOINT_HOST", defaultEndPoint.Host)
+	if host == "" {
+		return
+	}
+	for nodeIdx, proxyEp := range globalProxyEndpoints {
+		if proxyEp.Host == host && !proxyEp.IsLocal {
+			if proxied, success := proxyRequestByNodeIndex(ctx, w, r, nodeIdx, false); proxied && success {
+				return true
+			}
+		}
+	}
+	return
+}

cmd/admin-handlers-site-replication.go

@@ -0,0 +1,623 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"encoding/gob"
+	"encoding/json"
+	"errors"
+	"io"
+	"net/http"
+	"strings"
+	"sync/atomic"
+	"time"
+
+	"github.com/dustin/go-humanize"
+	"github.com/minio/madmin-go/v3"
+	xioutil "github.com/minio/minio/internal/ioutil"
+	"github.com/minio/mux"
+	"github.com/minio/pkg/v3/policy"
+)
+
+// SiteReplicationAdd - PUT /minio/admin/v3/site-replication/add
+func (a adminAPIHandlers) SiteReplicationAdd(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.SiteReplicationAddAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var sites []madmin.PeerSite
+	if err := parseJSONBody(ctx, r.Body, &sites, cred.SecretKey); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	opts := getSRAddOptions(r)
+	status, err := globalSiteReplicationSys.AddPeerClusters(ctx, sites, opts)
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	body, err := json.Marshal(status)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, body)
+}
+
+func getSRAddOptions(r *http.Request) (opts madmin.SRAddOptions) {
+	opts.ReplicateILMExpiry = r.Form.Get("replicateILMExpiry") == "true"
+	return
+}
+
+// SRPeerJoin - PUT /minio/admin/v3/site-replication/join
+//
+// used internally to tell current cluster to enable SR with
+// the provided peer clusters and service account.
+func (a adminAPIHandlers) SRPeerJoin(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.SiteReplicationAddAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var joinArg madmin.SRPeerJoinReq
+	if err := parseJSONBody(ctx, r.Body, &joinArg, cred.SecretKey); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err := globalSiteReplicationSys.PeerJoinReq(ctx, joinArg); err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SRPeerBucketOps - PUT /minio/admin/v3/site-replication/bucket-ops?bucket=x&operation=y
+func (a adminAPIHandlers) SRPeerBucketOps(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationOperationAction)
+	if objectAPI == nil {
+		return
+	}
+
+	vars := mux.Vars(r)
+	bucket := vars["bucket"]
+	operation := madmin.BktOp(vars["operation"])
+
+	var err error
+	switch operation {
+	default:
+		err = errSRInvalidRequest(errInvalidArgument)
+	case madmin.MakeWithVersioningBktOp:
+		createdAt, cerr := time.Parse(time.RFC3339Nano, strings.TrimSpace(r.Form.Get("createdAt")))
+		if cerr != nil {
+			createdAt = timeSentinel
+		}
+
+		opts := MakeBucketOptions{
+			LockEnabled:       r.Form.Get("lockEnabled") == "true",
+			VersioningEnabled: r.Form.Get("versioningEnabled") == "true",
+			ForceCreate:       r.Form.Get("forceCreate") == "true",
+			CreatedAt:         createdAt,
+		}
+		err = globalSiteReplicationSys.PeerBucketMakeWithVersioningHandler(ctx, bucket, opts)
+	case madmin.ConfigureReplBktOp:
+		err = globalSiteReplicationSys.PeerBucketConfigureReplHandler(ctx, bucket)
+	case madmin.DeleteBucketBktOp, madmin.ForceDeleteBucketBktOp:
+		err = globalSiteReplicationSys.PeerBucketDeleteHandler(ctx, bucket, DeleteBucketOptions{
+			Force:      operation == madmin.ForceDeleteBucketBktOp,
+			SRDeleteOp: getSRBucketDeleteOp(true),
+		})
+	case madmin.PurgeDeletedBucketOp:
+		globalSiteReplicationSys.purgeDeletedBucket(ctx, objectAPI, bucket)
+	}
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SRPeerReplicateIAMItem - PUT /minio/admin/v3/site-replication/iam-item
+func (a adminAPIHandlers) SRPeerReplicateIAMItem(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationOperationAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var item madmin.SRIAMItem
+	if err := parseJSONBody(ctx, r.Body, &item, ""); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	var err error
+	switch item.Type {
+	default:
+		err = errSRInvalidRequest(errInvalidArgument)
+	case madmin.SRIAMItemPolicy:
+		if item.Policy == nil {
+			err = globalSiteReplicationSys.PeerAddPolicyHandler(ctx, item.Name, nil, item.UpdatedAt)
+		} else {
+			policy, perr := policy.ParseConfig(bytes.NewReader(item.Policy))
+			if perr != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, perr), r.URL)
+				return
+			}
+			if policy.IsEmpty() {
+				err = globalSiteReplicationSys.PeerAddPolicyHandler(ctx, item.Name, nil, item.UpdatedAt)
+			} else {
+				err = globalSiteReplicationSys.PeerAddPolicyHandler(ctx, item.Name, policy, item.UpdatedAt)
+			}
+		}
+	case madmin.SRIAMItemSvcAcc:
+		err = globalSiteReplicationSys.PeerSvcAccChangeHandler(ctx, item.SvcAccChange, item.UpdatedAt)
+	case madmin.SRIAMItemPolicyMapping:
+		err = globalSiteReplicationSys.PeerPolicyMappingHandler(ctx, item.PolicyMapping, item.UpdatedAt)
+	case madmin.SRIAMItemSTSAcc:
+		err = globalSiteReplicationSys.PeerSTSAccHandler(ctx, item.STSCredential, item.UpdatedAt)
+	case madmin.SRIAMItemIAMUser:
+		err = globalSiteReplicationSys.PeerIAMUserChangeHandler(ctx, item.IAMUser, item.UpdatedAt)
+	case madmin.SRIAMItemGroupInfo:
+		err = globalSiteReplicationSys.PeerGroupInfoChangeHandler(ctx, item.GroupInfo, item.UpdatedAt)
+	}
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SRPeerReplicateBucketItem - PUT /minio/admin/v3/site-replication/peer/bucket-meta
+func (a adminAPIHandlers) SRPeerReplicateBucketItem(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationOperationAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var item madmin.SRBucketMeta
+	if err := parseJSONBody(ctx, r.Body, &item, ""); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if item.Bucket == "" {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, errSRInvalidRequest(errInvalidArgument)), r.URL)
+		return
+	}
+
+	var err error
+	switch item.Type {
+	default:
+		err = globalSiteReplicationSys.PeerBucketMetadataUpdateHandler(ctx, item)
+	case madmin.SRBucketMetaTypePolicy:
+		if item.Policy == nil {
+			err = globalSiteReplicationSys.PeerBucketPolicyHandler(ctx, item.Bucket, nil, item.UpdatedAt)
+		} else {
+			bktPolicy, berr := policy.ParseBucketPolicyConfig(bytes.NewReader(item.Policy), item.Bucket)
+			if berr != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, berr), r.URL)
+				return
+			}
+			if bktPolicy.IsEmpty() {
+				err = globalSiteReplicationSys.PeerBucketPolicyHandler(ctx, item.Bucket, nil, item.UpdatedAt)
+			} else {
+				err = globalSiteReplicationSys.PeerBucketPolicyHandler(ctx, item.Bucket, bktPolicy, item.UpdatedAt)
+			}
+		}
+	case madmin.SRBucketMetaTypeQuotaConfig:
+		if item.Quota == nil {
+			err = globalSiteReplicationSys.PeerBucketQuotaConfigHandler(ctx, item.Bucket, nil, item.UpdatedAt)
+		} else {
+			quotaConfig, err := parseBucketQuota(item.Bucket, item.Quota)
+			if err != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+				return
+			}
+			if err = globalSiteReplicationSys.PeerBucketQuotaConfigHandler(ctx, item.Bucket, quotaConfig, item.UpdatedAt); err != nil {
+				writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+				return
+			}
+		}
+	case madmin.SRBucketMetaTypeVersionConfig:
+		err = globalSiteReplicationSys.PeerBucketVersioningHandler(ctx, item.Bucket, item.Versioning, item.UpdatedAt)
+	case madmin.SRBucketMetaTypeTags:
+		err = globalSiteReplicationSys.PeerBucketTaggingHandler(ctx, item.Bucket, item.Tags, item.UpdatedAt)
+	case madmin.SRBucketMetaTypeObjectLockConfig:
+		err = globalSiteReplicationSys.PeerBucketObjectLockConfigHandler(ctx, item.Bucket, item.ObjectLockConfig, item.UpdatedAt)
+	case madmin.SRBucketMetaTypeSSEConfig:
+		err = globalSiteReplicationSys.PeerBucketSSEConfigHandler(ctx, item.Bucket, item.SSEConfig, item.UpdatedAt)
+	case madmin.SRBucketMetaLCConfig:
+		err = globalSiteReplicationSys.PeerBucketLCConfigHandler(ctx, item.Bucket, item.ExpiryLCConfig, item.UpdatedAt)
+	}
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SiteReplicationInfo - GET /minio/admin/v3/site-replication/info
+func (a adminAPIHandlers) SiteReplicationInfo(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationInfoAction)
+	if objectAPI == nil {
+		return
+	}
+
+	info, err := globalSiteReplicationSys.GetClusterInfo(ctx)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err = json.NewEncoder(w).Encode(info); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+func (a adminAPIHandlers) SRPeerGetIDPSettings(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationAddAction)
+	if objectAPI == nil {
+		return
+	}
+
+	idpSettings := globalSiteReplicationSys.GetIDPSettings(ctx)
+	if err := json.NewEncoder(w).Encode(idpSettings); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+func parseJSONBody(ctx context.Context, body io.Reader, v interface{}, encryptionKey string) error {
+	data, err := io.ReadAll(body)
+	if err != nil {
+		return SRError{
+			Cause: err,
+			Code:  ErrSiteReplicationInvalidRequest,
+		}
+	}
+	if encryptionKey != "" {
+		data, err = madmin.DecryptData(encryptionKey, bytes.NewReader(data))
+		if err != nil {
+			return SRError{
+				Cause: err,
+				Code:  ErrSiteReplicationInvalidRequest,
+			}
+		}
+	}
+	return json.Unmarshal(data, v)
+}
+
+// SiteReplicationStatus - GET /minio/admin/v3/site-replication/status
+func (a adminAPIHandlers) SiteReplicationStatus(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationInfoAction)
+	if objectAPI == nil {
+		return
+	}
+	opts := getSRStatusOptions(r)
+	// default options to all if status options are unset for backward compatibility
+	var dfltOpts madmin.SRStatusOptions
+	if opts == dfltOpts {
+		opts.Buckets = true
+		opts.Users = true
+		opts.Policies = true
+		opts.Groups = true
+		opts.ILMExpiryRules = true
+	}
+	info, err := globalSiteReplicationSys.SiteReplicationStatus(ctx, objectAPI, opts)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	// Report the ILMExpiryStats only if at least one site has replication of ILM expiry enabled
+	var replicateILMExpiry bool
+	for _, site := range info.Sites {
+		if site.ReplicateILMExpiry {
+			replicateILMExpiry = true
+			break
+		}
+	}
+	if !replicateILMExpiry {
+		// explicitly send nil for ILMExpiryStats
+		info.ILMExpiryStats = nil
+	}
+
+	if err = json.NewEncoder(w).Encode(info); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SiteReplicationMetaInfo - GET /minio/admin/v3/site-replication/metainfo
+func (a adminAPIHandlers) SiteReplicationMetaInfo(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationInfoAction)
+	if objectAPI == nil {
+		return
+	}
+
+	opts := getSRStatusOptions(r)
+	info, err := globalSiteReplicationSys.SiteReplicationMetaInfo(ctx, objectAPI, opts)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err = json.NewEncoder(w).Encode(info); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SiteReplicationEdit - PUT /minio/admin/v3/site-replication/edit
+func (a adminAPIHandlers) SiteReplicationEdit(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, cred := validateAdminReq(ctx, w, r, policy.SiteReplicationAddAction)
+	if objectAPI == nil {
+		return
+	}
+	var site madmin.PeerInfo
+	err := parseJSONBody(ctx, r.Body, &site, cred.SecretKey)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	opts := getSREditOptions(r)
+	status, err := globalSiteReplicationSys.EditPeerCluster(ctx, site, opts)
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	body, err := json.Marshal(status)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	writeSuccessResponseJSON(w, body)
+}
+
+func getSREditOptions(r *http.Request) (opts madmin.SREditOptions) {
+	opts.DisableILMExpiryReplication = r.Form.Get("disableILMExpiryReplication") == "true"
+	opts.EnableILMExpiryReplication = r.Form.Get("enableILMExpiryReplication") == "true"
+	return
+}
+
+// SRPeerEdit - PUT /minio/admin/v3/site-replication/peer/edit
+//
+// used internally to tell current cluster to update endpoint for peer
+func (a adminAPIHandlers) SRPeerEdit(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationAddAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var pi madmin.PeerInfo
+	if err := parseJSONBody(ctx, r.Body, &pi, ""); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err := globalSiteReplicationSys.PeerEditReq(ctx, pi); err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SRStateEdit - PUT /minio/admin/v3/site-replication/state/edit
+//
+// used internally to tell current cluster to update site replication state
+func (a adminAPIHandlers) SRStateEdit(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationOperationAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var state madmin.SRStateEditReq
+	if err := parseJSONBody(ctx, r.Body, &state, ""); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	if err := globalSiteReplicationSys.PeerStateEditReq(ctx, state); err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+func getSRStatusOptions(r *http.Request) (opts madmin.SRStatusOptions) {
+	q := r.Form
+	opts.Buckets = q.Get("buckets") == "true"
+	opts.Policies = q.Get("policies") == "true"
+	opts.Groups = q.Get("groups") == "true"
+	opts.Users = q.Get("users") == "true"
+	opts.ILMExpiryRules = q.Get("ilm-expiry-rules") == "true"
+	opts.PeerState = q.Get("peer-state") == "true"
+	opts.Entity = madmin.GetSREntityType(q.Get("entity"))
+	opts.EntityValue = q.Get("entityvalue")
+	opts.ShowDeleted = q.Get("showDeleted") == "true"
+	opts.Metrics = q.Get("metrics") == "true"
+	return
+}
+
+// SiteReplicationRemove - PUT /minio/admin/v3/site-replication/remove
+func (a adminAPIHandlers) SiteReplicationRemove(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationRemoveAction)
+	if objectAPI == nil {
+		return
+	}
+	var rreq madmin.SRRemoveReq
+	err := parseJSONBody(ctx, r.Body, &rreq, "")
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	status, err := globalSiteReplicationSys.RemovePeerCluster(ctx, objectAPI, rreq)
+	if err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	body, err := json.Marshal(status)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	writeSuccessResponseJSON(w, body)
+}
+
+// SRPeerRemove - PUT /minio/admin/v3/site-replication/peer/remove
+//
+// used internally to tell current cluster to update endpoint for peer
+func (a adminAPIHandlers) SRPeerRemove(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationRemoveAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var req madmin.SRRemoveReq
+	if err := parseJSONBody(ctx, r.Body, &req, ""); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+
+	if err := globalSiteReplicationSys.InternalRemoveReq(ctx, objectAPI, req); err != nil {
+		adminLogIf(ctx, err)
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+}
+
+// SiteReplicationResyncOp - PUT /minio/admin/v3/site-replication/resync/op
+func (a adminAPIHandlers) SiteReplicationResyncOp(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	objectAPI, _ := validateAdminReq(ctx, w, r, policy.SiteReplicationResyncAction)
+	if objectAPI == nil {
+		return
+	}
+
+	var peerSite madmin.PeerInfo
+	if err := parseJSONBody(ctx, r.Body, &peerSite, ""); err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	vars := mux.Vars(r)
+	op := madmin.SiteResyncOp(vars["operation"])
+	var (
+		status madmin.SRResyncOpStatus
+		err    error
+	)
+	switch op {
+	case madmin.SiteResyncStart:
+		status, err = globalSiteReplicationSys.startResync(ctx, objectAPI, peerSite)
+	case madmin.SiteResyncCancel:
+		status, err = globalSiteReplicationSys.cancelResync(ctx, objectAPI, peerSite)
+	default:
+		err = errSRInvalidRequest(errInvalidArgument)
+	}
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	body, err := json.Marshal(status)
+	if err != nil {
+		writeErrorResponseJSON(ctx, w, toAdminAPIErr(ctx, err), r.URL)
+		return
+	}
+	writeSuccessResponseJSON(w, body)
+}
+
+// SiteReplicationDevNull - everything goes to io.Discard
+// [POST] /minio/admin/v3/site-replication/devnull
+func (a adminAPIHandlers) SiteReplicationDevNull(w http.ResponseWriter, r *http.Request) {
+	ctx := r.Context()
+
+	globalSiteNetPerfRX.Connect()
+	defer globalSiteNetPerfRX.Disconnect()
+
+	connectTime := time.Now()
+	for {
+		n, err := io.CopyN(xioutil.Discard, r.Body, 128*humanize.KiByte)
+		atomic.AddUint64(&globalSiteNetPerfRX.RX, uint64(n))
+		if err != nil && err != io.EOF && err != io.ErrUnexpectedEOF {
+			// If there is a disconnection before globalNetPerfMinDuration (we give a margin of error of 1 sec)
+			// would mean the network is not stable. Logging here will help in debugging network issues.
+			if time.Since(connectTime) < (globalNetPerfMinDuration - time.Second) {
+				adminLogIf(ctx, err)
+			}
+		}
+		if err != nil {
+			if errors.Is(err, io.EOF) {
+				w.WriteHeader(http.StatusNoContent)
+			} else {
+				w.WriteHeader(http.StatusBadRequest)
+			}
+			break
+		}
+	}
+}
+
+// SiteReplicationNetPerf - everything goes to io.Discard
+// [POST] /minio/admin/v3/site-replication/netperf
+func (a adminAPIHandlers) SiteReplicationNetPerf(w http.ResponseWriter, r *http.Request) {
+	durationStr := r.Form.Get(peerRESTDuration)
+	duration, _ := time.ParseDuration(durationStr)
+	if duration < globalNetPerfMinDuration {
+		duration = globalNetPerfMinDuration
+	}
+	result := siteNetperf(r.Context(), duration)
+	adminLogIf(r.Context(), gob.NewEncoder(w).Encode(result))
+}

cmd/admin-handlers-users-race_test.go

@@ -0,0 +1,152 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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/>.
+
+//go:build !race
+// +build !race
+
+// Tests in this file are not run under the `-race` flag as they are too slow
+// and cause context deadline errors.
+
+package cmd
+
+import (
+	"context"
+	"fmt"
+	"runtime"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	minio "github.com/minio/minio-go/v7"
+	"github.com/minio/pkg/v3/sync/errgroup"
+)
+
+func runAllIAMConcurrencyTests(suite *TestSuiteIAM, c *check) {
+	suite.SetUpSuite(c)
+	suite.TestDeleteUserRace(c)
+	suite.TearDownSuite(c)
+}
+
+func TestIAMInternalIDPConcurrencyServerSuite(t *testing.T) {
+	if runtime.GOOS == globalWindowsOSName {
+		t.Skip("windows is clunky")
+	}
+
+	baseTestCases := []TestSuiteCommon{
+		// Init and run test on ErasureSD backend with signature v4.
+		{serverType: "ErasureSD", signer: signerV4},
+		// Init and run test on ErasureSD backend, with tls enabled.
+		{serverType: "ErasureSD", signer: signerV4, secure: true},
+		// Init and run test on Erasure backend.
+		{serverType: "Erasure", signer: signerV4},
+		// Init and run test on ErasureSet backend.
+		{serverType: "ErasureSet", signer: signerV4},
+	}
+	testCases := []*TestSuiteIAM{}
+	for _, bt := range baseTestCases {
+		testCases = append(testCases,
+			newTestSuiteIAM(bt, false),
+			newTestSuiteIAM(bt, true),
+		)
+	}
+	for i, testCase := range testCases {
+		etcdStr := ""
+		if testCase.withEtcdBackend {
+			etcdStr = " (with etcd backend)"
+		}
+		t.Run(
+			fmt.Sprintf("Test: %d, ServerType: %s%s", i+1, testCase.serverType, etcdStr),
+			func(t *testing.T) {
+				runAllIAMConcurrencyTests(testCase, &check{t, testCase.serverType})
+			},
+		)
+	}
+}
+
+func (s *TestSuiteIAM) TestDeleteUserRace(c *check) {
+	ctx, cancel := context.WithTimeout(context.Background(), 90*time.Second)
+	defer cancel()
+
+	bucket := getRandomBucketName()
+	err := s.client.MakeBucket(ctx, bucket, minio.MakeBucketOptions{})
+	if err != nil {
+		c.Fatalf("bucket creat error: %v", err)
+	}
+
+	// Create a policy policy
+	policy := "mypolicy"
+	policyBytes := []byte(fmt.Sprintf(`{
+ "Version": "2012-10-17",
+ "Statement": [
+  {
+   "Effect": "Allow",
+   "Action": [
+    "s3:PutObject",
+    "s3:GetObject",
+    "s3:ListBucket"
+   ],
+   "Resource": [
+    "arn:aws:s3:::%s/*"
+   ]
+  }
+ ]
+}`, bucket))
+	err = s.adm.AddCannedPolicy(ctx, policy, policyBytes)
+	if err != nil {
+		c.Fatalf("policy add error: %v", err)
+	}
+
+	userCount := 50
+	accessKeys := make([]string, userCount)
+	secretKeys := make([]string, userCount)
+	for i := 0; i < userCount; i++ {
+		accessKey, secretKey := mustGenerateCredentials(c)
+		err = s.adm.SetUser(ctx, accessKey, secretKey, madmin.AccountEnabled)
+		if err != nil {
+			c.Fatalf("Unable to set user: %v", err)
+		}
+
+		userReq := madmin.PolicyAssociationReq{
+			Policies: []string{policy},
+			User:     accessKey,
+		}
+		if _, err := s.adm.AttachPolicy(ctx, userReq); err != nil {
+			c.Fatalf("Unable to attach policy: %v", err)
+		}
+
+		accessKeys[i] = accessKey
+		secretKeys[i] = secretKey
+	}
+
+	g := errgroup.Group{}
+	for i := 0; i < userCount; i++ {
+		g.Go(func(i int) func() error {
+			return func() error {
+				uClient := s.getUserClient(c, accessKeys[i], secretKeys[i], "")
+				err := s.adm.RemoveUser(ctx, accessKeys[i])
+				if err != nil {
+					return err
+				}
+				c.mustNotListObjects(ctx, uClient, bucket)
+				return nil
+			}
+		}(i), i)
+	}
+	if errs := g.Wait(); len(errs) > 0 {
+		c.Fatalf("unable to remove users: %v", errs)
+	}
+}

cmd/admin-handlers_test.go

@@ -0,0 +1,535 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"sort"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/mux"
+)
+
+// adminErasureTestBed - encapsulates subsystems that need to be setup for
+// admin-handler unit tests.
+type adminErasureTestBed struct {
+	erasureDirs []string
+	objLayer    ObjectLayer
+	router      *mux.Router
+	done        context.CancelFunc
+}
+
+// prepareAdminErasureTestBed - helper function that setups a single-node
+// Erasure backend for admin-handler tests.
+func prepareAdminErasureTestBed(ctx context.Context) (*adminErasureTestBed, error) {
+	ctx, cancel := context.WithCancel(ctx)
+
+	// reset global variables to start afresh.
+	resetTestGlobals()
+
+	// Set globalIsErasure to indicate that the setup uses an erasure
+	// code backend.
+	globalIsErasure = true
+
+	// Initializing objectLayer for HealFormatHandler.
+	objLayer, erasureDirs, xlErr := initTestErasureObjLayer(ctx)
+	if xlErr != nil {
+		cancel()
+		return nil, xlErr
+	}
+
+	// Initialize minio server config.
+	if err := newTestConfig(globalMinioDefaultRegion, objLayer); err != nil {
+		cancel()
+		return nil, err
+	}
+
+	// Initialize boot time
+	globalBootTime = UTCNow()
+
+	globalEndpoints = mustGetPoolEndpoints(0, erasureDirs...)
+
+	initAllSubsystems(ctx)
+
+	initConfigSubsystem(ctx, objLayer)
+
+	globalIAMSys.Init(ctx, objLayer, globalEtcdClient, 2*time.Second)
+
+	// Setup admin mgmt REST API handlers.
+	adminRouter := mux.NewRouter()
+	registerAdminRouter(adminRouter, true)
+
+	return &adminErasureTestBed{
+		erasureDirs: erasureDirs,
+		objLayer:    objLayer,
+		router:      adminRouter,
+		done:        cancel,
+	}, nil
+}
+
+// TearDown - method that resets the test bed for subsequent unit
+// tests to start afresh.
+func (atb *adminErasureTestBed) TearDown() {
+	atb.done()
+	removeRoots(atb.erasureDirs)
+	resetTestGlobals()
+}
+
+// initTestObjLayer - Helper function to initialize an Erasure-based object
+// layer and set globalObjectAPI.
+func initTestErasureObjLayer(ctx context.Context) (ObjectLayer, []string, error) {
+	erasureDirs, err := getRandomDisks(16)
+	if err != nil {
+		return nil, nil, err
+	}
+	endpoints := mustGetPoolEndpoints(0, erasureDirs...)
+	globalPolicySys = NewPolicySys()
+	objLayer, err := newErasureServerPools(ctx, endpoints)
+	if err != nil {
+		return nil, nil, err
+	}
+
+	// Make objLayer available to all internal services via globalObjectAPI.
+	globalObjLayerMutex.Lock()
+	globalObjectAPI = objLayer
+	globalObjLayerMutex.Unlock()
+	return objLayer, erasureDirs, nil
+}
+
+// cmdType - Represents different service subcomands like status, stop
+// and restart.
+type cmdType int
+
+const (
+	restartCmd cmdType = iota
+	stopCmd
+)
+
+// toServiceSignal - Helper function that translates a given cmdType
+// value to its corresponding serviceSignal value.
+func (c cmdType) toServiceSignal() serviceSignal {
+	switch c {
+	case restartCmd:
+		return serviceRestart
+	case stopCmd:
+		return serviceStop
+	}
+	return serviceRestart
+}
+
+func (c cmdType) toServiceAction() madmin.ServiceAction {
+	switch c {
+	case restartCmd:
+		return madmin.ServiceActionRestart
+	case stopCmd:
+		return madmin.ServiceActionStop
+	}
+	return madmin.ServiceActionRestart
+}
+
+// testServiceSignalReceiver - Helper function that simulates a
+// go-routine waiting on service signal.
+func testServiceSignalReceiver(cmd cmdType, t *testing.T) {
+	expectedCmd := cmd.toServiceSignal()
+	serviceCmd := <-globalServiceSignalCh
+	if serviceCmd != expectedCmd {
+		t.Errorf("Expected service command %v but received %v", expectedCmd, serviceCmd)
+	}
+}
+
+// getServiceCmdRequest - Constructs a management REST API request for service
+// subcommands for a given cmdType value.
+func getServiceCmdRequest(cmd cmdType, cred auth.Credentials) (*http.Request, error) {
+	queryVal := url.Values{}
+	queryVal.Set("action", string(cmd.toServiceAction()))
+	queryVal.Set("type", "2")
+	resource := adminPathPrefix + adminAPIVersionPrefix + "/service?" + queryVal.Encode()
+	req, err := newTestRequest(http.MethodPost, resource, 0, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	// management REST API uses signature V4 for authentication.
+	err = signRequestV4(req, cred.AccessKey, cred.SecretKey)
+	if err != nil {
+		return nil, err
+	}
+	return req, nil
+}
+
+// testServicesCmdHandler - parametrizes service subcommand tests on
+// cmdType value.
+func testServicesCmdHandler(cmd cmdType, t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	adminTestBed, err := prepareAdminErasureTestBed(ctx)
+	if err != nil {
+		t.Fatal("Failed to initialize a single node Erasure backend for admin handler tests.", err)
+	}
+	defer adminTestBed.TearDown()
+
+	// Initialize admin peers to make admin RPC calls. Note: In a
+	// single node setup, this degenerates to a simple function
+	// call under the hood.
+	globalMinioAddr = "127.0.0.1:9000"
+
+	var wg sync.WaitGroup
+
+	// Setting up a go routine to simulate ServerRouter's
+	// handleServiceSignals for stop and restart commands.
+	if cmd == restartCmd {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			testServiceSignalReceiver(cmd, t)
+		}()
+	}
+	credentials := globalActiveCred
+
+	req, err := getServiceCmdRequest(cmd, credentials)
+	if err != nil {
+		t.Fatalf("Failed to build service status request %v", err)
+	}
+
+	rec := httptest.NewRecorder()
+	adminTestBed.router.ServeHTTP(rec, req)
+
+	resp, _ := io.ReadAll(rec.Body)
+	if rec.Code != http.StatusOK {
+		t.Errorf("Expected to receive %d status code but received %d. Body (%s)",
+			http.StatusOK, rec.Code, string(resp))
+	}
+
+	result := &serviceResult{}
+	if err := json.Unmarshal(resp, result); err != nil {
+		t.Error(err)
+	}
+	_ = result
+
+	// Wait until testServiceSignalReceiver() called in a goroutine quits.
+	wg.Wait()
+}
+
+// Test for service restart management REST API.
+func TestServiceRestartHandler(t *testing.T) {
+	testServicesCmdHandler(restartCmd, t)
+}
+
+// buildAdminRequest - helper function to build an admin API request.
+func buildAdminRequest(queryVal url.Values, method, path string,
+	contentLength int64, bodySeeker io.ReadSeeker) (*http.Request, error,
+) {
+	req, err := newTestRequest(method,
+		adminPathPrefix+adminAPIVersionPrefix+path+"?"+queryVal.Encode(),
+		contentLength, bodySeeker)
+	if err != nil {
+		return nil, err
+	}
+
+	cred := globalActiveCred
+	err = signRequestV4(req, cred.AccessKey, cred.SecretKey)
+	if err != nil {
+		return nil, err
+	}
+
+	return req, nil
+}
+
+func TestAdminServerInfo(t *testing.T) {
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+
+	adminTestBed, err := prepareAdminErasureTestBed(ctx)
+	if err != nil {
+		t.Fatal("Failed to initialize a single node Erasure backend for admin handler tests.", err)
+	}
+
+	defer adminTestBed.TearDown()
+
+	// Initialize admin peers to make admin RPC calls.
+	globalMinioAddr = "127.0.0.1:9000"
+
+	// Prepare query params for set-config mgmt REST API.
+	queryVal := url.Values{}
+	queryVal.Set("info", "")
+
+	req, err := buildAdminRequest(queryVal, http.MethodGet, "/info", 0, nil)
+	if err != nil {
+		t.Fatalf("Failed to construct get-config object request - %v", err)
+	}
+
+	rec := httptest.NewRecorder()
+	adminTestBed.router.ServeHTTP(rec, req)
+	if rec.Code != http.StatusOK {
+		t.Errorf("Expected to succeed but failed with %d", rec.Code)
+	}
+
+	results := madmin.InfoMessage{}
+	err = json.NewDecoder(rec.Body).Decode(&results)
+	if err != nil {
+		t.Fatalf("Failed to decode set config result json %v", err)
+	}
+
+	if results.Region != globalMinioDefaultRegion {
+		t.Errorf("Expected %s, got %s", globalMinioDefaultRegion, results.Region)
+	}
+}
+
+// TestToAdminAPIErrCode - test for toAdminAPIErrCode helper function.
+func TestToAdminAPIErrCode(t *testing.T) {
+	testCases := []struct {
+		err            error
+		expectedAPIErr APIErrorCode
+	}{
+		// 1. Server not in quorum.
+		{
+			err:            errErasureWriteQuorum,
+			expectedAPIErr: ErrAdminConfigNoQuorum,
+		},
+		// 2. No error.
+		{
+			err:            nil,
+			expectedAPIErr: ErrNone,
+		},
+		// 3. Non-admin API specific error.
+		{
+			err:            errDiskNotFound,
+			expectedAPIErr: toAPIErrorCode(GlobalContext, errDiskNotFound),
+		},
+	}
+
+	for i, test := range testCases {
+		actualErr := toAdminAPIErrCode(GlobalContext, test.err)
+		if actualErr != test.expectedAPIErr {
+			t.Errorf("Test %d: Expected %v but received %v",
+				i+1, test.expectedAPIErr, actualErr)
+		}
+	}
+}
+
+func TestExtractHealInitParams(t *testing.T) {
+	mkParams := func(clientToken string, forceStart, forceStop bool) url.Values {
+		v := url.Values{}
+		if clientToken != "" {
+			v.Add(mgmtClientToken, clientToken)
+		}
+		if forceStart {
+			v.Add(mgmtForceStart, "")
+		}
+		if forceStop {
+			v.Add(mgmtForceStop, "")
+		}
+		return v
+	}
+	qParamsArr := []url.Values{
+		// Invalid cases
+		mkParams("", true, true),
+		mkParams("111", true, true),
+		mkParams("111", true, false),
+		mkParams("111", false, true),
+		// Valid cases follow
+		mkParams("", true, false),
+		mkParams("", false, true),
+		mkParams("", false, false),
+		mkParams("111", false, false),
+	}
+	varsArr := []map[string]string{
+		// Invalid cases
+		{mgmtPrefix: "objprefix"},
+		// Valid cases
+		{},
+		{mgmtBucket: "bucket"},
+		{mgmtBucket: "bucket", mgmtPrefix: "objprefix"},
+	}
+
+	// Body is always valid - we do not test JSON decoding.
+	body := `{"recursive": false, "dryRun": true, "remove": false, "scanMode": 0}`
+
+	// Test all combinations!
+	for pIdx, params := range qParamsArr {
+		for vIdx, vars := range varsArr {
+			_, err := extractHealInitParams(vars, params, bytes.NewReader([]byte(body)))
+			isErrCase := false
+			if pIdx < 4 || vIdx < 1 {
+				isErrCase = true
+			}
+
+			if err != ErrNone && !isErrCase {
+				t.Errorf("Got unexpected error: %v %v %v", pIdx, vIdx, err)
+			} else if err == ErrNone && isErrCase {
+				t.Errorf("Got no error but expected one: %v %v", pIdx, vIdx)
+			}
+		}
+	}
+}
+
+type byResourceUID struct{ madmin.LockEntries }
+
+func (b byResourceUID) Less(i, j int) bool {
+	toUniqLock := func(entry madmin.LockEntry) string {
+		return fmt.Sprintf("%s/%s", entry.Resource, entry.ID)
+	}
+	return toUniqLock(b.LockEntries[i]) < toUniqLock(b.LockEntries[j])
+}
+
+func TestTopLockEntries(t *testing.T) {
+	locksHeld := make(map[string][]lockRequesterInfo)
+	var owners []string
+	for i := 0; i < 4; i++ {
+		owners = append(owners, fmt.Sprintf("node-%d", i))
+	}
+
+	// Simulate DeleteObjects of 10 objects in a single request. i.e same lock
+	// request UID, but 10 different resource names associated with it.
+	var lris []lockRequesterInfo
+	uuid := mustGetUUID()
+	for i := 0; i < 10; i++ {
+		resource := fmt.Sprintf("bucket/delete-object-%d", i)
+		lri := lockRequesterInfo{
+			Name:   resource,
+			Writer: true,
+			UID:    uuid,
+			Owner:  owners[i%len(owners)],
+			Group:  true,
+			Quorum: 3,
+		}
+		lris = append(lris, lri)
+		locksHeld[resource] = []lockRequesterInfo{lri}
+	}
+
+	// Add a few concurrent read locks to the mix
+	for i := 0; i < 50; i++ {
+		resource := fmt.Sprintf("bucket/get-object-%d", i)
+		lri := lockRequesterInfo{
+			Name:   resource,
+			UID:    mustGetUUID(),
+			Owner:  owners[i%len(owners)],
+			Quorum: 2,
+		}
+		lris = append(lris, lri)
+		locksHeld[resource] = append(locksHeld[resource], lri)
+		// concurrent read lock, same resource different uid
+		lri.UID = mustGetUUID()
+		lris = append(lris, lri)
+		locksHeld[resource] = append(locksHeld[resource], lri)
+	}
+
+	var peerLocks []*PeerLocks
+	for _, owner := range owners {
+		peerLocks = append(peerLocks, &PeerLocks{
+			Addr:  owner,
+			Locks: locksHeld,
+		})
+	}
+	var exp madmin.LockEntries
+	for _, lri := range lris {
+		lockType := func(lri lockRequesterInfo) string {
+			if lri.Writer {
+				return "WRITE"
+			}
+			return "READ"
+		}
+		exp = append(exp, madmin.LockEntry{
+			Resource:   lri.Name,
+			Type:       lockType(lri),
+			ServerList: owners,
+			Owner:      lri.Owner,
+			ID:         lri.UID,
+			Quorum:     lri.Quorum,
+			Timestamp:  time.Unix(0, lri.Timestamp),
+		})
+	}
+
+	testCases := []struct {
+		peerLocks []*PeerLocks
+		expected  madmin.LockEntries
+	}{
+		{
+			peerLocks: peerLocks,
+			expected:  exp,
+		},
+	}
+
+	// printEntries := func(entries madmin.LockEntries) {
+	// 	for i, entry := range entries {
+	// 		fmt.Printf("%d: %s %s %s %s %v %d\n", i, entry.Resource, entry.ID, entry.Owner, entry.Type, entry.ServerList, entry.Elapsed)
+	// 	}
+	// }
+
+	check := func(exp, got madmin.LockEntries) (int, bool) {
+		if len(exp) != len(got) {
+			return 0, false
+		}
+		sort.Slice(exp, byResourceUID{exp}.Less)
+		sort.Slice(got, byResourceUID{got}.Less)
+		// printEntries(exp)
+		// printEntries(got)
+		for i, e := range exp {
+			if !e.Timestamp.Equal(got[i].Timestamp) {
+				return i, false
+			}
+			// Skip checking elapsed since it's time sensitive.
+			// if e.Elapsed != got[i].Elapsed {
+			// 	return false
+			// }
+			if e.Resource != got[i].Resource {
+				return i, false
+			}
+			if e.Type != got[i].Type {
+				return i, false
+			}
+			if e.Source != got[i].Source {
+				return i, false
+			}
+			if e.Owner != got[i].Owner {
+				return i, false
+			}
+			if e.ID != got[i].ID {
+				return i, false
+			}
+			if len(e.ServerList) != len(got[i].ServerList) {
+				return i, false
+			}
+			for j := range e.ServerList {
+				if e.ServerList[j] != got[i].ServerList[j] {
+					return i, false
+				}
+			}
+		}
+		return 0, true
+	}
+
+	for i, tc := range testCases {
+		got := topLockEntries(tc.peerLocks, false)
+		if idx, ok := check(tc.expected, got); !ok {
+			t.Fatalf("%d: mismatch at %d \n expected %#v but got %#v", i, idx, tc.expected[idx], got[idx])
+		}
+	}
+}

cmd/admin-heal-ops.go

@@ -0,0 +1,923 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"sort"
+	"sync"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	xioutil "github.com/minio/minio/internal/ioutil"
+	"github.com/minio/minio/internal/logger"
+)
+
+// healStatusSummary - overall short summary of a healing sequence
+type healStatusSummary string
+
+// healStatusSummary constants
+const (
+	healNotStartedStatus healStatusSummary = "not started"
+	healRunningStatus                      = "running"
+	healStoppedStatus                      = "stopped"
+	healFinishedStatus                     = "finished"
+)
+
+const (
+	// a heal sequence with this many un-consumed heal result
+	// items blocks until heal-status consumption resumes or is
+	// aborted due to timeout.
+	maxUnconsumedHealResultItems = 1000
+
+	// if no heal-results are consumed (via the heal-status API)
+	// for this timeout duration, the heal sequence is aborted.
+	healUnconsumedTimeout = 24 * time.Hour
+
+	// time-duration to keep heal sequence state after it
+	// completes.
+	keepHealSeqStateDuration = time.Minute * 10
+
+	// nopHeal is a no operating healing action to
+	// wait for the current healing operation to finish
+	nopHeal = ""
+)
+
+var (
+	errHealIdleTimeout   = errors.New("healing results were not consumed for too long")
+	errHealStopSignalled = errors.New("heal stop signaled")
+
+	errFnHealFromAPIErr = func(ctx context.Context, err error) error {
+		apiErr := toAdminAPIErr(ctx, err)
+		return fmt.Errorf("Heal internal error: %s: %s",
+			apiErr.Code, apiErr.Description)
+	}
+)
+
+// healSequenceStatus - accumulated status of the heal sequence
+type healSequenceStatus struct {
+	// summary and detail for failures
+	Summary       healStatusSummary `json:"Summary"`
+	FailureDetail string            `json:"Detail,omitempty"`
+	StartTime     time.Time         `json:"StartTime"`
+
+	// settings for the heal sequence
+	HealSettings madmin.HealOpts `json:"Settings"`
+
+	// slice of available heal result records
+	Items []madmin.HealResultItem `json:"Items"`
+}
+
+// structure to hold state of all heal sequences in server memory
+type allHealState struct {
+	sync.RWMutex
+
+	// map of heal path to heal sequence
+	healSeqMap map[string]*healSequence // Indexed by endpoint
+	// keep track of the healing status of disks in the memory
+	//   false: the disk needs to be healed but no healing routine is started
+	//    true: the disk is currently healing
+	healLocalDisks map[Endpoint]bool
+	healStatus     map[string]healingTracker // Indexed by disk ID
+}
+
+// newHealState - initialize global heal state management
+func newHealState(ctx context.Context, cleanup bool) *allHealState {
+	hstate := &allHealState{
+		healSeqMap:     make(map[string]*healSequence),
+		healLocalDisks: make(map[Endpoint]bool),
+		healStatus:     make(map[string]healingTracker),
+	}
+	if cleanup {
+		go hstate.periodicHealSeqsClean(ctx)
+	}
+	return hstate
+}
+
+func (ahs *allHealState) popHealLocalDisks(healLocalDisks ...Endpoint) {
+	ahs.Lock()
+	defer ahs.Unlock()
+
+	for _, ep := range healLocalDisks {
+		delete(ahs.healLocalDisks, ep)
+	}
+	for id, disk := range ahs.healStatus {
+		for _, ep := range healLocalDisks {
+			if disk.Endpoint == ep.String() {
+				delete(ahs.healStatus, id)
+			}
+		}
+	}
+}
+
+// updateHealStatus will update the heal status.
+func (ahs *allHealState) updateHealStatus(tracker *healingTracker) {
+	ahs.Lock()
+	defer ahs.Unlock()
+
+	tracker.mu.RLock()
+	t := *tracker
+	t.QueuedBuckets = append(make([]string, 0, len(tracker.QueuedBuckets)), tracker.QueuedBuckets...)
+	t.HealedBuckets = append(make([]string, 0, len(tracker.HealedBuckets)), tracker.HealedBuckets...)
+	ahs.healStatus[tracker.ID] = t
+	tracker.mu.RUnlock()
+}
+
+// Sort by zone, set and disk index
+func sortDisks(disks []madmin.Disk) {
+	sort.Slice(disks, func(i, j int) bool {
+		a, b := &disks[i], &disks[j]
+		if a.PoolIndex != b.PoolIndex {
+			return a.PoolIndex < b.PoolIndex
+		}
+		if a.SetIndex != b.SetIndex {
+			return a.SetIndex < b.SetIndex
+		}
+		return a.DiskIndex < b.DiskIndex
+	})
+}
+
+// getLocalHealingDisks returns local healing disks indexed by endpoint.
+func (ahs *allHealState) getLocalHealingDisks() map[string]madmin.HealingDisk {
+	ahs.RLock()
+	defer ahs.RUnlock()
+	dst := make(map[string]madmin.HealingDisk, len(ahs.healStatus))
+	for _, v := range ahs.healStatus {
+		dst[v.Endpoint] = v.toHealingDisk()
+	}
+
+	return dst
+}
+
+// getHealLocalDiskEndpoints() returns the list of disks that need
+// to be healed but there is no healing routine in progress on them.
+func (ahs *allHealState) getHealLocalDiskEndpoints() Endpoints {
+	ahs.RLock()
+	defer ahs.RUnlock()
+
+	var endpoints Endpoints
+	for ep, healing := range ahs.healLocalDisks {
+		if !healing {
+			endpoints = append(endpoints, ep)
+		}
+	}
+	return endpoints
+}
+
+// Set, in the memory, the state of the disk as currently healing or not
+func (ahs *allHealState) setDiskHealingStatus(ep Endpoint, healing bool) {
+	ahs.Lock()
+	defer ahs.Unlock()
+
+	ahs.healLocalDisks[ep] = healing
+}
+
+func (ahs *allHealState) pushHealLocalDisks(healLocalDisks ...Endpoint) {
+	ahs.Lock()
+	defer ahs.Unlock()
+
+	for _, ep := range healLocalDisks {
+		ahs.healLocalDisks[ep] = false
+	}
+}
+
+func (ahs *allHealState) periodicHealSeqsClean(ctx context.Context) {
+	// Launch clean-up routine to remove this heal sequence (after
+	// it ends) from the global state after timeout has elapsed.
+	periodicTimer := time.NewTimer(time.Minute * 5)
+	defer periodicTimer.Stop()
+
+	for {
+		select {
+		case <-periodicTimer.C:
+			now := UTCNow()
+			ahs.Lock()
+			for path, h := range ahs.healSeqMap {
+				if h.hasEnded() && h.endTime.Add(keepHealSeqStateDuration).Before(now) {
+					delete(ahs.healSeqMap, path)
+				}
+			}
+			ahs.Unlock()
+
+			periodicTimer.Reset(time.Minute * 5)
+		case <-ctx.Done():
+			// server could be restarting - need
+			// to exit immediately
+			return
+		}
+	}
+}
+
+// getHealSequenceByToken - Retrieve a heal sequence by token. The second
+// argument returns if a heal sequence actually exists.
+func (ahs *allHealState) getHealSequenceByToken(token string) (h *healSequence, exists bool) {
+	ahs.RLock()
+	defer ahs.RUnlock()
+	for _, healSeq := range ahs.healSeqMap {
+		if healSeq.clientToken == token {
+			return healSeq, true
+		}
+	}
+	return nil, false
+}
+
+// getHealSequence - Retrieve a heal sequence by path. The second
+// argument returns if a heal sequence actually exists.
+func (ahs *allHealState) getHealSequence(path string) (h *healSequence, exists bool) {
+	ahs.RLock()
+	defer ahs.RUnlock()
+	h, exists = ahs.healSeqMap[path]
+	return h, exists
+}
+
+func (ahs *allHealState) stopHealSequence(path string) ([]byte, APIError) {
+	var hsp madmin.HealStopSuccess
+	he, exists := ahs.getHealSequence(path)
+	if !exists {
+		hsp = madmin.HealStopSuccess{
+			ClientToken: "unknown",
+			StartTime:   UTCNow(),
+		}
+	} else {
+		clientToken := he.clientToken
+		if globalIsDistErasure {
+			clientToken = fmt.Sprintf("%s%s%d", he.clientToken, getKeySeparator(), GetProxyEndpointLocalIndex(globalProxyEndpoints))
+		}
+
+		hsp = madmin.HealStopSuccess{
+			ClientToken:   clientToken,
+			ClientAddress: he.clientAddress,
+			StartTime:     he.startTime,
+		}
+
+		he.stop()
+		for !he.hasEnded() {
+			time.Sleep(1 * time.Second)
+		}
+		ahs.Lock()
+		defer ahs.Unlock()
+		// Heal sequence explicitly stopped, remove it.
+		delete(ahs.healSeqMap, path)
+	}
+
+	b, err := json.Marshal(&hsp)
+	return b, toAdminAPIErr(GlobalContext, err)
+}
+
+// LaunchNewHealSequence - launches a background routine that performs
+// healing according to the healSequence argument. For each heal
+// sequence, state is stored in the `globalAllHealState`, which is a
+// map of the heal path to `healSequence` which holds state about the
+// heal sequence.
+//
+// Heal results are persisted in server memory for
+// `keepHealSeqStateDuration`. This function also launches a
+// background routine to clean up heal results after the
+// aforementioned duration.
+func (ahs *allHealState) LaunchNewHealSequence(h *healSequence, objAPI ObjectLayer) (
+	respBytes []byte, apiErr APIError, errMsg string,
+) {
+	if h.forceStarted {
+		_, apiErr = ahs.stopHealSequence(pathJoin(h.bucket, h.object))
+		if apiErr.Code != "" {
+			return respBytes, apiErr, ""
+		}
+	} else {
+		oh, exists := ahs.getHealSequence(pathJoin(h.bucket, h.object))
+		if exists && !oh.hasEnded() {
+			errMsg = "Heal is already running on the given path " +
+				"(use force-start option to stop and start afresh). " +
+				fmt.Sprintf("The heal was started by IP %s at %s, token is %s",
+					h.clientAddress, h.startTime.Format(http.TimeFormat), h.clientToken)
+			return nil, errorCodes.ToAPIErr(ErrHealAlreadyRunning), errMsg
+		}
+	}
+
+	ahs.Lock()
+	defer ahs.Unlock()
+
+	// Check if new heal sequence to be started overlaps with any
+	// existing, running sequence
+	hpath := pathJoin(h.bucket, h.object)
+	for k, hSeq := range ahs.healSeqMap {
+		if !hSeq.hasEnded() && (HasPrefix(k, hpath) || HasPrefix(hpath, k)) {
+			errMsg = "The provided heal sequence path overlaps with an existing " +
+				fmt.Sprintf("heal path: %s", k)
+			return nil, errorCodes.ToAPIErr(ErrHealOverlappingPaths), errMsg
+		}
+	}
+
+	// Add heal state and start sequence
+	ahs.healSeqMap[hpath] = h
+
+	clientToken := h.clientToken
+	if globalIsDistErasure {
+		clientToken = fmt.Sprintf("%s%s%d", h.clientToken, getKeySeparator(), GetProxyEndpointLocalIndex(globalProxyEndpoints))
+	}
+
+	if h.clientToken == bgHealingUUID {
+		// For background heal do nothing, do not spawn an unnecessary goroutine.
+	} else {
+		// Launch top-level background heal go-routine
+		go h.healSequenceStart(objAPI)
+	}
+
+	b, err := json.Marshal(madmin.HealStartSuccess{
+		ClientToken:   clientToken,
+		ClientAddress: h.clientAddress,
+		StartTime:     h.startTime,
+	})
+	if err != nil {
+		bugLogIf(h.ctx, err)
+		return nil, toAdminAPIErr(h.ctx, err), ""
+	}
+	return b, noError, ""
+}
+
+// PopHealStatusJSON - Called by heal-status API. It fetches the heal
+// status results from global state and returns its JSON
+// representation. The clientToken helps ensure there aren't
+// conflicting clients fetching status.
+func (ahs *allHealState) PopHealStatusJSON(hpath string,
+	clientToken string) ([]byte, APIErrorCode,
+) {
+	// fetch heal state for given path
+	h, exists := ahs.getHealSequence(hpath)
+	if !exists {
+		// heal sequence doesn't exist, must have finished.
+		jbytes, err := json.Marshal(healSequenceStatus{
+			Summary: healFinishedStatus,
+		})
+		return jbytes, toAdminAPIErrCode(GlobalContext, err)
+	}
+
+	// Check if client-token is valid
+	if clientToken != h.clientToken {
+		return nil, ErrHealInvalidClientToken
+	}
+
+	// Take lock to access and update the heal-sequence
+	h.mutex.Lock()
+	defer h.mutex.Unlock()
+
+	numItems := len(h.currentStatus.Items)
+
+	// calculate index of most recently available heal result
+	// record.
+	lastResultIndex := h.lastSentResultIndex
+	if numItems > 0 {
+		lastResultIndex = h.currentStatus.Items[numItems-1].ResultIndex
+	}
+
+	h.lastSentResultIndex = lastResultIndex
+
+	jbytes, err := json.Marshal(h.currentStatus)
+	if err != nil {
+		h.currentStatus.Items = nil
+
+		bugLogIf(h.ctx, err)
+		return nil, ErrInternalError
+	}
+
+	h.currentStatus.Items = nil
+
+	return jbytes, ErrNone
+}
+
+// healSource denotes single entity and heal option.
+type healSource struct {
+	bucket    string
+	object    string
+	versionID string
+	noWait    bool             // a non blocking call, if task queue is full return right away.
+	opts      *madmin.HealOpts // optional heal option overrides default setting
+}
+
+// healSequence - state for each heal sequence initiated on the
+// server.
+type healSequence struct {
+	// bucket, and object on which heal seq. was initiated
+	bucket, object string
+
+	// Report healing progress
+	reportProgress bool
+
+	// time at which heal sequence was started
+	startTime time.Time
+
+	// time at which heal sequence has ended
+	endTime time.Time
+
+	// Heal client info
+	clientToken, clientAddress string
+
+	// was this heal sequence force started?
+	forceStarted bool
+
+	// heal settings applied to this heal sequence
+	settings madmin.HealOpts
+
+	// current accumulated status of the heal sequence
+	currentStatus healSequenceStatus
+
+	// channel signaled by background routine when traversal has
+	// completed
+	traverseAndHealDoneCh chan error
+
+	// canceler to cancel heal sequence.
+	cancelCtx context.CancelFunc
+
+	// the last result index sent to client
+	lastSentResultIndex int64
+
+	// Number of total items scanned against item type
+	scannedItemsMap map[madmin.HealItemType]int64
+
+	// Number of total items healed against item type
+	healedItemsMap map[madmin.HealItemType]int64
+
+	// Number of total items where healing failed against item type
+	healFailedItemsMap map[madmin.HealItemType]int64
+
+	// The time of the last scan/heal activity
+	lastHealActivity time.Time
+
+	// Holds the request-info for logging
+	ctx context.Context
+
+	// used to lock this structure as it is concurrently accessed
+	mutex sync.RWMutex
+}
+
+// NewHealSequence - creates healSettings, assumes bucket and
+// objPrefix are already validated.
+func newHealSequence(ctx context.Context, bucket, objPrefix, clientAddr string,
+	hs madmin.HealOpts, forceStart bool,
+) *healSequence {
+	reqInfo := &logger.ReqInfo{RemoteHost: clientAddr, API: "Heal", BucketName: bucket}
+	reqInfo.AppendTags("prefix", objPrefix)
+	ctx, cancel := context.WithCancel(logger.SetReqInfo(ctx, reqInfo))
+
+	clientToken := mustGetUUID()
+
+	return &healSequence{
+		bucket:         bucket,
+		object:         objPrefix,
+		reportProgress: true,
+		startTime:      UTCNow(),
+		clientToken:    clientToken,
+		clientAddress:  clientAddr,
+		forceStarted:   forceStart,
+		settings:       hs,
+		currentStatus: healSequenceStatus{
+			Summary:      healNotStartedStatus,
+			HealSettings: hs,
+		},
+		traverseAndHealDoneCh: make(chan error),
+		cancelCtx:             cancel,
+		ctx:                   ctx,
+		scannedItemsMap:       make(map[madmin.HealItemType]int64),
+		healedItemsMap:        make(map[madmin.HealItemType]int64),
+		healFailedItemsMap:    make(map[madmin.HealItemType]int64),
+	}
+}
+
+// getScannedItemsCount - returns a count of all scanned items
+func (h *healSequence) getScannedItemsCount() int64 {
+	var count int64
+	h.mutex.RLock()
+	defer h.mutex.RUnlock()
+
+	for _, v := range h.scannedItemsMap {
+		count += v
+	}
+	return count
+}
+
+// getScannedItemsMap - returns map of all scanned items against type
+func (h *healSequence) getScannedItemsMap() map[madmin.HealItemType]int64 {
+	h.mutex.RLock()
+	defer h.mutex.RUnlock()
+
+	// Make a copy before returning the value
+	retMap := make(map[madmin.HealItemType]int64, len(h.scannedItemsMap))
+	for k, v := range h.scannedItemsMap {
+		retMap[k] = v
+	}
+
+	return retMap
+}
+
+// getHealedItemsMap - returns the map of all healed items against type
+func (h *healSequence) getHealedItemsMap() map[madmin.HealItemType]int64 {
+	h.mutex.RLock()
+	defer h.mutex.RUnlock()
+
+	// Make a copy before returning the value
+	retMap := make(map[madmin.HealItemType]int64, len(h.healedItemsMap))
+	for k, v := range h.healedItemsMap {
+		retMap[k] = v
+	}
+
+	return retMap
+}
+
+// getHealFailedItemsMap - returns map of all items where heal failed against
+// drive endpoint and status
+func (h *healSequence) getHealFailedItemsMap() map[madmin.HealItemType]int64 {
+	h.mutex.RLock()
+	defer h.mutex.RUnlock()
+
+	// Make a copy before returning the value
+	retMap := make(map[madmin.HealItemType]int64, len(h.healFailedItemsMap))
+	for k, v := range h.healFailedItemsMap {
+		retMap[k] = v
+	}
+
+	return retMap
+}
+
+func (h *healSequence) countFailed(healType madmin.HealItemType) {
+	h.mutex.Lock()
+	defer h.mutex.Unlock()
+
+	h.healFailedItemsMap[healType]++
+	h.lastHealActivity = UTCNow()
+}
+
+func (h *healSequence) countScanned(healType madmin.HealItemType) {
+	h.mutex.Lock()
+	defer h.mutex.Unlock()
+
+	h.scannedItemsMap[healType]++
+	h.lastHealActivity = UTCNow()
+}
+
+func (h *healSequence) countHealed(healType madmin.HealItemType) {
+	h.mutex.Lock()
+	defer h.mutex.Unlock()
+
+	h.healedItemsMap[healType]++
+	h.lastHealActivity = UTCNow()
+}
+
+// isQuitting - determines if the heal sequence is quitting (due to an
+// external signal)
+func (h *healSequence) isQuitting() bool {
+	select {
+	case <-h.ctx.Done():
+		return true
+	default:
+		return false
+	}
+}
+
+// check if the heal sequence has ended
+func (h *healSequence) hasEnded() bool {
+	h.mutex.RLock()
+	defer h.mutex.RUnlock()
+	// background heal never ends
+	if h.clientToken == bgHealingUUID {
+		return false
+	}
+	return !h.endTime.IsZero()
+}
+
+// stops the heal sequence - safe to call multiple times.
+func (h *healSequence) stop() {
+	h.cancelCtx()
+}
+
+// pushHealResultItem - pushes a heal result item for consumption in
+// the heal-status API. It blocks if there are
+// maxUnconsumedHealResultItems. When it blocks, the heal sequence
+// routine is effectively paused - this happens when the server has
+// accumulated the maximum number of heal records per heal
+// sequence. When the client consumes further records, the heal
+// sequence automatically resumes. The return value indicates if the
+// operation succeeded.
+func (h *healSequence) pushHealResultItem(r madmin.HealResultItem) error {
+	// start a timer to keep an upper time limit to find an empty
+	// slot to add the given heal result - if no slot is found it
+	// means that the server is holding the maximum amount of
+	// heal-results in memory and the client has not consumed it
+	// for too long.
+	unconsumedTimer := time.NewTimer(healUnconsumedTimeout)
+	defer unconsumedTimer.Stop()
+
+	var itemsLen int
+	for {
+		h.mutex.Lock()
+		itemsLen = len(h.currentStatus.Items)
+		if itemsLen == maxUnconsumedHealResultItems {
+			// wait for a second, or quit if an external
+			// stop signal is received or the
+			// unconsumedTimer fires.
+			select {
+			// Check after a second
+			case <-time.After(time.Second):
+				h.mutex.Unlock()
+				continue
+
+			case <-h.ctx.Done():
+				h.mutex.Unlock()
+				// discard result and return.
+				return errHealStopSignalled
+
+			// Timeout if no results consumed for too long.
+			case <-unconsumedTimer.C:
+				h.mutex.Unlock()
+				return errHealIdleTimeout
+			}
+		}
+		break
+	}
+
+	// Set the correct result index for the new result item
+	if itemsLen > 0 {
+		r.ResultIndex = 1 + h.currentStatus.Items[itemsLen-1].ResultIndex
+	} else {
+		r.ResultIndex = 1 + h.lastSentResultIndex
+	}
+
+	// append to results
+	h.currentStatus.Items = append(h.currentStatus.Items, r)
+
+	// release lock
+	h.mutex.Unlock()
+
+	return nil
+}
+
+// healSequenceStart - this is the top-level background heal
+// routine. It launches another go-routine that actually traverses
+// on-disk data, checks and heals according to the selected
+// settings. This go-routine itself, (1) monitors the traversal
+// routine for completion, and (2) listens for external stop
+// signals. When either event happens, it sets the finish status for
+// the heal-sequence.
+func (h *healSequence) healSequenceStart(objAPI ObjectLayer) {
+	// Set status as running
+	h.mutex.Lock()
+	h.currentStatus.Summary = healRunningStatus
+	h.currentStatus.StartTime = UTCNow()
+	h.mutex.Unlock()
+
+	go h.traverseAndHeal(objAPI)
+
+	select {
+	case err, ok := <-h.traverseAndHealDoneCh:
+		if !ok {
+			return
+		}
+		h.mutex.Lock()
+		h.endTime = UTCNow()
+		// Heal traversal is complete.
+		if err == nil {
+			// heal traversal succeeded.
+			h.currentStatus.Summary = healFinishedStatus
+		} else {
+			// heal traversal had an error.
+			h.currentStatus.Summary = healStoppedStatus
+			h.currentStatus.FailureDetail = err.Error()
+		}
+		h.mutex.Unlock()
+	case <-h.ctx.Done():
+		h.mutex.Lock()
+		h.endTime = UTCNow()
+		h.currentStatus.Summary = healFinishedStatus
+		h.mutex.Unlock()
+
+		// drain traverse channel so the traversal
+		// go-routine does not leak.
+		go func() {
+			// Eventually the traversal go-routine closes
+			// the channel and returns, so this go-routine
+			// itself will not leak.
+			<-h.traverseAndHealDoneCh
+		}()
+	}
+}
+
+func (h *healSequence) queueHealTask(source healSource, healType madmin.HealItemType) error {
+	// Send heal request
+	task := healTask{
+		bucket:    source.bucket,
+		object:    source.object,
+		versionID: source.versionID,
+		opts:      h.settings,
+	}
+	if source.opts != nil {
+		task.opts = *source.opts
+	} else {
+		task.opts.ScanMode = madmin.HealNormalScan
+	}
+
+	h.countScanned(healType)
+
+	if source.noWait {
+		select {
+		case globalBackgroundHealRoutine.tasks <- task:
+			if serverDebugLog {
+				fmt.Printf("Task in the queue: %#v\n", task)
+			}
+		default:
+			// task queue is full, no more workers, we shall move on and heal later.
+			return nil
+		}
+		// Don't wait for result
+		return nil
+	}
+
+	// respCh must be set to wait for result.
+	// We make it size 1, so a result can always be written
+	// even if we aren't listening.
+	task.respCh = make(chan healResult, 1)
+	select {
+	case globalBackgroundHealRoutine.tasks <- task:
+		if serverDebugLog {
+			fmt.Printf("Task in the queue: %#v\n", task)
+		}
+	case <-h.ctx.Done():
+		return nil
+	}
+
+	countOKDrives := func(drives []madmin.HealDriveInfo) (count int) {
+		for _, drive := range drives {
+			if drive.State == madmin.DriveStateOk {
+				count++
+			}
+		}
+		return count
+	}
+
+	// task queued, now wait for the response.
+	select {
+	case res := <-task.respCh:
+		if res.err == nil {
+			h.countHealed(healType)
+		} else {
+			h.countFailed(healType)
+		}
+		if !h.reportProgress {
+			if errors.Is(res.err, errSkipFile) { // this is only sent usually by nopHeal
+				return nil
+			}
+
+			// Report caller of any failure
+			return res.err
+		}
+		res.result.Type = healType
+		if res.err != nil {
+			res.result.Detail = res.err.Error()
+		}
+		if res.result.ParityBlocks > 0 && res.result.DataBlocks > 0 && res.result.DataBlocks > res.result.ParityBlocks {
+			if got := countOKDrives(res.result.After.Drives); got < res.result.ParityBlocks {
+				res.result.Detail = fmt.Sprintf("quorum loss - expected %d minimum, got drive states in OK %d", res.result.ParityBlocks, got)
+			}
+		}
+		return h.pushHealResultItem(res.result)
+	case <-h.ctx.Done():
+		return nil
+	}
+}
+
+func (h *healSequence) healDiskMeta(objAPI ObjectLayer) error {
+	// Start healing the config prefix.
+	return h.healMinioSysMeta(objAPI, minioConfigPrefix)()
+}
+
+func (h *healSequence) healItems(objAPI ObjectLayer) error {
+	if h.clientToken == bgHealingUUID {
+		// For background heal do nothing.
+		return nil
+	}
+
+	if h.bucket == "" { // heal internal meta only during a site-wide heal
+		if err := h.healDiskMeta(objAPI); err != nil {
+			return err
+		}
+	}
+
+	// Heal buckets and objects
+	return h.healBuckets(objAPI)
+}
+
+// traverseAndHeal - traverses on-disk data and performs healing
+// according to settings. At each "safe" point it also checks if an
+// external quit signal has been received and quits if so. Since the
+// healing traversal may be mutating on-disk data when an external
+// quit signal is received, this routine cannot quit immediately and
+// has to wait until a safe point is reached, such as between scanning
+// two objects.
+func (h *healSequence) traverseAndHeal(objAPI ObjectLayer) {
+	h.traverseAndHealDoneCh <- h.healItems(objAPI)
+	xioutil.SafeClose(h.traverseAndHealDoneCh)
+}
+
+// healMinioSysMeta - heals all files under a given meta prefix, returns a function
+// which in-turn heals the respective meta directory path and any files in int.
+func (h *healSequence) healMinioSysMeta(objAPI ObjectLayer, metaPrefix string) func() error {
+	return func() error {
+		// NOTE: Healing on meta is run regardless
+		// of any bucket being selected, this is to ensure that
+		// meta are always upto date and correct.
+		h.settings.Recursive = true
+		return objAPI.HealObjects(h.ctx, minioMetaBucket, metaPrefix, h.settings, func(bucket, object, versionID string, scanMode madmin.HealScanMode) error {
+			if h.isQuitting() {
+				return errHealStopSignalled
+			}
+
+			err := h.queueHealTask(healSource{
+				bucket:    bucket,
+				object:    object,
+				versionID: versionID,
+			}, madmin.HealItemBucketMetadata)
+			return err
+		})
+	}
+}
+
+// healBuckets - check for all buckets heal or just particular bucket.
+func (h *healSequence) healBuckets(objAPI ObjectLayer) error {
+	if h.isQuitting() {
+		return errHealStopSignalled
+	}
+
+	// 1. If a bucket was specified, heal only the bucket.
+	if h.bucket != "" {
+		return h.healBucket(objAPI, h.bucket, false)
+	}
+
+	buckets, err := objAPI.ListBuckets(h.ctx, BucketOptions{})
+	if err != nil {
+		return errFnHealFromAPIErr(h.ctx, err)
+	}
+
+	// Heal latest buckets first.
+	sort.Slice(buckets, func(i, j int) bool {
+		return buckets[i].Created.After(buckets[j].Created)
+	})
+
+	for _, bucket := range buckets {
+		if err = h.healBucket(objAPI, bucket.Name, false); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// healBucket - traverses and heals given bucket
+func (h *healSequence) healBucket(objAPI ObjectLayer, bucket string, bucketsOnly bool) error {
+	if err := h.queueHealTask(healSource{bucket: bucket}, madmin.HealItemBucket); err != nil {
+		return err
+	}
+
+	if bucketsOnly {
+		return nil
+	}
+
+	if err := objAPI.HealObjects(h.ctx, bucket, h.object, h.settings, h.healObject); err != nil {
+		return errFnHealFromAPIErr(h.ctx, err)
+	}
+	return nil
+}
+
+// healObject - heal the given object and record result
+func (h *healSequence) healObject(bucket, object, versionID string, scanMode madmin.HealScanMode) error {
+	if h.isQuitting() {
+		return errHealStopSignalled
+	}
+
+	err := h.queueHealTask(healSource{
+		bucket:    bucket,
+		object:    object,
+		versionID: versionID,
+		opts:      &h.settings,
+	}, madmin.HealItemObject)
+
+	// Wait and proceed if there are active requests
+	waitForLowHTTPReq()
+
+	return err
+}

cmd/admin-router.go

@@ -0,0 +1,441 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"net/http"
+
+	"github.com/klauspost/compress/gzhttp"
+	"github.com/klauspost/compress/gzip"
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/logger"
+	"github.com/minio/mux"
+)
+
+const (
+	adminPathPrefix                = minioReservedBucketPath + "/admin"
+	adminAPIVersion                = madmin.AdminAPIVersion
+	adminAPIVersionPrefix          = SlashSeparator + adminAPIVersion
+	adminAPISiteReplicationDevNull = "/site-replication/devnull"
+	adminAPISiteReplicationNetPerf = "/site-replication/netperf"
+	adminAPIClientDevNull          = "/speedtest/client/devnull"
+	adminAPIClientDevExtraTime     = "/speedtest/client/devnull/extratime"
+)
+
+var gzipHandler = func() func(http.Handler) http.HandlerFunc {
+	gz, err := gzhttp.NewWrapper(gzhttp.MinSize(1000), gzhttp.CompressionLevel(gzip.BestSpeed))
+	if err != nil {
+		// Static params, so this is very unlikely.
+		logger.Fatal(err, "Unable to initialize server")
+	}
+	return gz
+}()
+
+// Set of handler options as bit flags
+type hFlag uint8
+
+const (
+	// this flag disables gzip compression of responses
+	noGZFlag = 1 << iota
+
+	// this flag enables tracing body and headers instead of just headers
+	traceAllFlag
+
+	// pass this flag to skip checking if object layer is available
+	noObjLayerFlag
+)
+
+// Has checks if the given flag is enabled in `h`.
+func (h hFlag) Has(flag hFlag) bool {
+	// Use bitwise-AND and check if the result is non-zero.
+	return h&flag != 0
+}
+
+// adminMiddleware performs some common admin handler functionality for all
+// handlers:
+//
+// - updates request context with `logger.ReqInfo` and api name based on the
+// name of the function handler passed (this handler must be a method of
+// `adminAPIHandlers`).
+//
+// - sets up call to send AuditLog
+//
+// While this is a middleware function (i.e. it takes a handler function and
+// returns one), due to flags being passed based on required conditions, it is
+// done per-"handler function registration" in the router.
+//
+// The passed in handler function must be a method of `adminAPIHandlers` for the
+// name displayed in logs and trace to be accurate. The name is extracted via
+// reflection.
+//
+// When no flags are passed, gzip compression, http tracing of headers and
+// checking of object layer availability are all enabled. Use flags to modify
+// this behavior.
+func adminMiddleware(f http.HandlerFunc, flags ...hFlag) http.HandlerFunc {
+	// Collect all flags with bitwise-OR and assign operator
+	var handlerFlags hFlag
+	for _, flag := range flags {
+		handlerFlags |= flag
+	}
+
+	// Get name of the handler using reflection.
+	handlerName := getHandlerName(f, "adminAPIHandlers")
+
+	var handler http.HandlerFunc = func(w http.ResponseWriter, r *http.Request) {
+		// Update request context with `logger.ReqInfo`.
+		r = r.WithContext(newContext(r, w, handlerName))
+
+		defer logger.AuditLog(r.Context(), w, r, mustGetClaimsFromToken(r))
+
+		// Check if object layer is available, if not return error early.
+		if !handlerFlags.Has(noObjLayerFlag) {
+			objectAPI := newObjectLayerFn()
+			if objectAPI == nil || globalNotificationSys == nil {
+				writeErrorResponseJSON(r.Context(), w, errorCodes.ToAPIErr(ErrServerNotInitialized), r.URL)
+				return
+			}
+		}
+
+		// Apply http tracing "middleware" based on presence of flag.
+		var f2 http.HandlerFunc
+		if handlerFlags.Has(traceAllFlag) {
+			f2 = httpTraceAll(f)
+		} else {
+			f2 = httpTraceHdrs(f)
+		}
+
+		// call the final handler
+		f2(w, r)
+	}
+
+	// Enable compression of responses based on presence of flag.
+	if !handlerFlags.Has(noGZFlag) {
+		handler = gzipHandler(handler)
+	}
+
+	return handler
+}
+
+// adminAPIHandlers provides HTTP handlers for MinIO admin API.
+type adminAPIHandlers struct{}
+
+// registerAdminRouter - Add handler functions for each service REST API routes.
+func registerAdminRouter(router *mux.Router, enableConfigOps bool) {
+	adminAPI := adminAPIHandlers{}
+	// Admin router
+	adminRouter := router.PathPrefix(adminPathPrefix).Subrouter()
+
+	adminVersions := []string{
+		adminAPIVersionPrefix,
+	}
+
+	for _, adminVersion := range adminVersions {
+		// Restart and stop MinIO service type=2
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/service").HandlerFunc(adminMiddleware(adminAPI.ServiceV2Handler, traceAllFlag)).Queries("action", "{action:.*}", "type", "2")
+
+		// Deprecated: Restart and stop MinIO service.
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/service").HandlerFunc(adminMiddleware(adminAPI.ServiceHandler, traceAllFlag)).Queries("action", "{action:.*}")
+
+		// Update all MinIO servers type=2
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/update").HandlerFunc(adminMiddleware(adminAPI.ServerUpdateV2Handler, traceAllFlag)).Queries("updateURL", "{updateURL:.*}", "type", "2")
+
+		// Deprecated: Update MinIO servers.
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/update").HandlerFunc(adminMiddleware(adminAPI.ServerUpdateHandler, traceAllFlag)).Queries("updateURL", "{updateURL:.*}")
+
+		// Info operations
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/info").HandlerFunc(adminMiddleware(adminAPI.ServerInfoHandler, traceAllFlag, noObjLayerFlag))
+		adminRouter.Methods(http.MethodGet, http.MethodPost).Path(adminVersion + "/inspect-data").HandlerFunc(adminMiddleware(adminAPI.InspectDataHandler, noGZFlag, traceHdrsS3HFlag))
+
+		// StorageInfo operations
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/storageinfo").HandlerFunc(adminMiddleware(adminAPI.StorageInfoHandler, traceAllFlag))
+		// DataUsageInfo operations
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/datausageinfo").HandlerFunc(adminMiddleware(adminAPI.DataUsageInfoHandler, traceAllFlag))
+		// Metrics operation
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/metrics").HandlerFunc(adminMiddleware(adminAPI.MetricsHandler, traceHdrsS3HFlag))
+
+		if globalIsDistErasure || globalIsErasure {
+			// Heal operations
+
+			// Heal processing endpoint.
+			adminRouter.Methods(http.MethodPost).Path(adminVersion + "/heal/").HandlerFunc(adminMiddleware(adminAPI.HealHandler, traceAllFlag))
+			adminRouter.Methods(http.MethodPost).Path(adminVersion + "/heal/{bucket}").HandlerFunc(adminMiddleware(adminAPI.HealHandler, traceAllFlag))
+			adminRouter.Methods(http.MethodPost).Path(adminVersion + "/heal/{bucket}/{prefix:.*}").HandlerFunc(adminMiddleware(adminAPI.HealHandler, traceAllFlag))
+			adminRouter.Methods(http.MethodPost).Path(adminVersion + "/background-heal/status").HandlerFunc(adminMiddleware(adminAPI.BackgroundHealStatusHandler, traceAllFlag))
+
+			// Pool operations
+			adminRouter.Methods(http.MethodGet).Path(adminVersion + "/pools/list").HandlerFunc(adminMiddleware(adminAPI.ListPools, traceAllFlag))
+			adminRouter.Methods(http.MethodGet).Path(adminVersion+"/pools/status").HandlerFunc(adminMiddleware(adminAPI.StatusPool, traceAllFlag)).Queries("pool", "{pool:.*}")
+
+			adminRouter.Methods(http.MethodPost).Path(adminVersion+"/pools/decommission").HandlerFunc(adminMiddleware(adminAPI.StartDecommission, traceAllFlag)).Queries("pool", "{pool:.*}")
+			adminRouter.Methods(http.MethodPost).Path(adminVersion+"/pools/cancel").HandlerFunc(adminMiddleware(adminAPI.CancelDecommission, traceAllFlag)).Queries("pool", "{pool:.*}")
+
+			// Rebalance operations
+			adminRouter.Methods(http.MethodPost).Path(adminVersion + "/rebalance/start").HandlerFunc(adminMiddleware(adminAPI.RebalanceStart, traceAllFlag))
+			adminRouter.Methods(http.MethodGet).Path(adminVersion + "/rebalance/status").HandlerFunc(adminMiddleware(adminAPI.RebalanceStatus, traceAllFlag))
+			adminRouter.Methods(http.MethodPost).Path(adminVersion + "/rebalance/stop").HandlerFunc(adminMiddleware(adminAPI.RebalanceStop, traceAllFlag))
+		}
+
+		// Profiling operations - deprecated API
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/profiling/start").HandlerFunc(adminMiddleware(adminAPI.StartProfilingHandler, traceAllFlag, noObjLayerFlag)).
+			Queries("profilerType", "{profilerType:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/profiling/download").HandlerFunc(adminMiddleware(adminAPI.DownloadProfilingHandler, traceHdrsS3HFlag, noObjLayerFlag))
+		// Profiling operations
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/profile").HandlerFunc(adminMiddleware(adminAPI.ProfileHandler, traceHdrsS3HFlag, noObjLayerFlag))
+
+		// Config KV operations.
+		if enableConfigOps {
+			adminRouter.Methods(http.MethodGet).Path(adminVersion+"/get-config-kv").HandlerFunc(adminMiddleware(adminAPI.GetConfigKVHandler)).Queries("key", "{key:.*}")
+			adminRouter.Methods(http.MethodPut).Path(adminVersion + "/set-config-kv").HandlerFunc(adminMiddleware(adminAPI.SetConfigKVHandler))
+			adminRouter.Methods(http.MethodDelete).Path(adminVersion + "/del-config-kv").HandlerFunc(adminMiddleware(adminAPI.DelConfigKVHandler))
+		}
+
+		// Enable config help in all modes.
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/help-config-kv").HandlerFunc(adminMiddleware(adminAPI.HelpConfigKVHandler, traceAllFlag)).Queries("subSys", "{subSys:.*}", "key", "{key:.*}")
+
+		// Config KV history operations.
+		if enableConfigOps {
+			adminRouter.Methods(http.MethodGet).Path(adminVersion+"/list-config-history-kv").HandlerFunc(adminMiddleware(adminAPI.ListConfigHistoryKVHandler, traceAllFlag)).Queries("count", "{count:[0-9]+}")
+			adminRouter.Methods(http.MethodDelete).Path(adminVersion+"/clear-config-history-kv").HandlerFunc(adminMiddleware(adminAPI.ClearConfigHistoryKVHandler)).Queries("restoreId", "{restoreId:.*}")
+			adminRouter.Methods(http.MethodPut).Path(adminVersion+"/restore-config-history-kv").HandlerFunc(adminMiddleware(adminAPI.RestoreConfigHistoryKVHandler)).Queries("restoreId", "{restoreId:.*}")
+		}
+
+		// Config import/export bulk operations
+		if enableConfigOps {
+			// Get config
+			adminRouter.Methods(http.MethodGet).Path(adminVersion + "/config").HandlerFunc(adminMiddleware(adminAPI.GetConfigHandler))
+			// Set config
+			adminRouter.Methods(http.MethodPut).Path(adminVersion + "/config").HandlerFunc(adminMiddleware(adminAPI.SetConfigHandler))
+		}
+
+		// -- IAM APIs --
+
+		// Add policy IAM
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/add-canned-policy").HandlerFunc(adminMiddleware(adminAPI.AddCannedPolicy, traceAllFlag)).Queries("name", "{name:.*}")
+
+		// Add user IAM
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/accountinfo").HandlerFunc(adminMiddleware(adminAPI.AccountInfoHandler, traceAllFlag))
+
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/add-user").HandlerFunc(adminMiddleware(adminAPI.AddUser)).Queries("accessKey", "{accessKey:.*}")
+
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/set-user-status").HandlerFunc(adminMiddleware(adminAPI.SetUserStatus)).Queries("accessKey", "{accessKey:.*}").Queries("status", "{status:.*}")
+
+		// Service accounts ops
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/add-service-account").HandlerFunc(adminMiddleware(adminAPI.AddServiceAccount))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/update-service-account").HandlerFunc(adminMiddleware(adminAPI.UpdateServiceAccount)).Queries("accessKey", "{accessKey:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/info-service-account").HandlerFunc(adminMiddleware(adminAPI.InfoServiceAccount)).Queries("accessKey", "{accessKey:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/list-service-accounts").HandlerFunc(adminMiddleware(adminAPI.ListServiceAccounts))
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion+"/delete-service-account").HandlerFunc(adminMiddleware(adminAPI.DeleteServiceAccount)).Queries("accessKey", "{accessKey:.*}")
+
+		// STS accounts ops
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/temporary-account-info").HandlerFunc(adminMiddleware(adminAPI.TemporaryAccountInfo)).Queries("accessKey", "{accessKey:.*}")
+
+		// Access key (service account/STS) operations
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/list-access-keys-bulk").HandlerFunc(adminMiddleware(adminAPI.ListAccessKeysBulk)).Queries("listType", "{listType:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/info-access-key").HandlerFunc(adminMiddleware(adminAPI.InfoAccessKey)).Queries("accessKey", "{accessKey:.*}")
+
+		// Info policy IAM latest
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/info-canned-policy").HandlerFunc(adminMiddleware(adminAPI.InfoCannedPolicy)).Queries("name", "{name:.*}")
+		// List policies latest
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/list-canned-policies").HandlerFunc(adminMiddleware(adminAPI.ListBucketPolicies)).Queries("bucket", "{bucket:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/list-canned-policies").HandlerFunc(adminMiddleware(adminAPI.ListCannedPolicies))
+
+		// Builtin IAM policy associations
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/idp/builtin/policy-entities").HandlerFunc(adminMiddleware(adminAPI.ListPolicyMappingEntities))
+
+		// Remove policy IAM
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion+"/remove-canned-policy").HandlerFunc(adminMiddleware(adminAPI.RemoveCannedPolicy)).Queries("name", "{name:.*}")
+
+		// Set user or group policy
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/set-user-or-group-policy").
+			HandlerFunc(adminMiddleware(adminAPI.SetPolicyForUserOrGroup)).
+			Queries("policyName", "{policyName:.*}", "userOrGroup", "{userOrGroup:.*}", "isGroup", "{isGroup:true|false}")
+
+		// Attach/Detach policies to/from user or group
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/idp/builtin/policy/{operation}").HandlerFunc(adminMiddleware(adminAPI.AttachDetachPolicyBuiltin))
+
+		// Remove user IAM
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion+"/remove-user").HandlerFunc(adminMiddleware(adminAPI.RemoveUser)).Queries("accessKey", "{accessKey:.*}")
+
+		// List users
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/list-users").HandlerFunc(adminMiddleware(adminAPI.ListBucketUsers)).Queries("bucket", "{bucket:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/list-users").HandlerFunc(adminMiddleware(adminAPI.ListUsers))
+
+		// User info
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/user-info").HandlerFunc(adminMiddleware(adminAPI.GetUserInfo)).Queries("accessKey", "{accessKey:.*}")
+		// Add/Remove members from group
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/update-group-members").HandlerFunc(adminMiddleware(adminAPI.UpdateGroupMembers))
+
+		// Get Group
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/group").HandlerFunc(adminMiddleware(adminAPI.GetGroup)).Queries("group", "{group:.*}")
+
+		// List Groups
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/groups").HandlerFunc(adminMiddleware(adminAPI.ListGroups))
+
+		// Set Group Status
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/set-group-status").HandlerFunc(adminMiddleware(adminAPI.SetGroupStatus)).Queries("group", "{group:.*}").Queries("status", "{status:.*}")
+
+		// Export IAM info to zipped file
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/export-iam").HandlerFunc(adminMiddleware(adminAPI.ExportIAM, noGZFlag))
+
+		// Import IAM info
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/import-iam").HandlerFunc(adminMiddleware(adminAPI.ImportIAM, noGZFlag))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/import-iam-v2").HandlerFunc(adminMiddleware(adminAPI.ImportIAMV2, noGZFlag))
+
+		// IDentity Provider configuration APIs
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/idp-config/{type}/{name}").HandlerFunc(adminMiddleware(adminAPI.AddIdentityProviderCfg))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/idp-config/{type}/{name}").HandlerFunc(adminMiddleware(adminAPI.UpdateIdentityProviderCfg))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/idp-config/{type}").HandlerFunc(adminMiddleware(adminAPI.ListIdentityProviderCfg))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/idp-config/{type}/{name}").HandlerFunc(adminMiddleware(adminAPI.GetIdentityProviderCfg))
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion + "/idp-config/{type}/{name}").HandlerFunc(adminMiddleware(adminAPI.DeleteIdentityProviderCfg))
+
+		// LDAP specific service accounts ops
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/idp/ldap/add-service-account").HandlerFunc(adminMiddleware(adminAPI.AddServiceAccountLDAP))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/idp/ldap/list-access-keys").
+			HandlerFunc(adminMiddleware(adminAPI.ListAccessKeysLDAP)).Queries("userDN", "{userDN:.*}", "listType", "{listType:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/idp/ldap/list-access-keys-bulk").
+			HandlerFunc(adminMiddleware(adminAPI.ListAccessKeysLDAPBulk)).Queries("listType", "{listType:.*}")
+
+		// LDAP IAM operations
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/idp/ldap/policy-entities").HandlerFunc(adminMiddleware(adminAPI.ListLDAPPolicyMappingEntities))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/idp/ldap/policy/{operation}").HandlerFunc(adminMiddleware(adminAPI.AttachDetachPolicyLDAP))
+
+		// OpenID specific service accounts ops
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/idp/openid/list-access-keys-bulk").
+			HandlerFunc(adminMiddleware(adminAPI.ListAccessKeysOpenIDBulk)).Queries("listType", "{listType:.*}")
+
+		// -- END IAM APIs --
+
+		// GetBucketQuotaConfig
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/get-bucket-quota").HandlerFunc(
+			adminMiddleware(adminAPI.GetBucketQuotaConfigHandler)).Queries("bucket", "{bucket:.*}")
+		// PutBucketQuotaConfig
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/set-bucket-quota").HandlerFunc(
+			adminMiddleware(adminAPI.PutBucketQuotaConfigHandler)).Queries("bucket", "{bucket:.*}")
+
+		// Bucket replication operations
+		// GetBucketTargetHandler
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/list-remote-targets").HandlerFunc(
+			adminMiddleware(adminAPI.ListRemoteTargetsHandler)).Queries("bucket", "{bucket:.*}", "type", "{type:.*}")
+		// SetRemoteTargetHandler
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/set-remote-target").HandlerFunc(
+			adminMiddleware(adminAPI.SetRemoteTargetHandler)).Queries("bucket", "{bucket:.*}")
+		// RemoveRemoteTargetHandler
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion+"/remove-remote-target").HandlerFunc(
+			adminMiddleware(adminAPI.RemoveRemoteTargetHandler)).Queries("bucket", "{bucket:.*}", "arn", "{arn:.*}")
+		// ReplicationDiff - MinIO extension API
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/replication/diff").HandlerFunc(
+			adminMiddleware(adminAPI.ReplicationDiffHandler)).Queries("bucket", "{bucket:.*}")
+		// ReplicationMRFHandler - MinIO extension API
+		adminRouter.Methods(http.MethodGet).Path(adminVersion+"/replication/mrf").HandlerFunc(
+			adminMiddleware(adminAPI.ReplicationMRFHandler)).Queries("bucket", "{bucket:.*}")
+
+		// Batch job operations
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/start-job").HandlerFunc(
+			adminMiddleware(adminAPI.StartBatchJob))
+
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/list-jobs").HandlerFunc(
+			adminMiddleware(adminAPI.ListBatchJobs))
+
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/status-job").HandlerFunc(
+			adminMiddleware(adminAPI.BatchJobStatus))
+
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/describe-job").HandlerFunc(
+			adminMiddleware(adminAPI.DescribeBatchJob))
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion + "/cancel-job").HandlerFunc(
+			adminMiddleware(adminAPI.CancelBatchJob))
+
+		// Bucket migration operations
+		// ExportBucketMetaHandler
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/export-bucket-metadata").HandlerFunc(
+			adminMiddleware(adminAPI.ExportBucketMetadataHandler))
+		// ImportBucketMetaHandler
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/import-bucket-metadata").HandlerFunc(
+			adminMiddleware(adminAPI.ImportBucketMetadataHandler))
+
+		// Remote Tier management operations
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/tier").HandlerFunc(adminMiddleware(adminAPI.AddTierHandler))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/tier/{tier}").HandlerFunc(adminMiddleware(adminAPI.EditTierHandler))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/tier").HandlerFunc(adminMiddleware(adminAPI.ListTierHandler))
+		adminRouter.Methods(http.MethodDelete).Path(adminVersion + "/tier/{tier}").HandlerFunc(adminMiddleware(adminAPI.RemoveTierHandler))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/tier/{tier}").HandlerFunc(adminMiddleware(adminAPI.VerifyTierHandler))
+		// Tier stats
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/tier-stats").HandlerFunc(adminMiddleware(adminAPI.TierStatsHandler))
+
+		// Cluster Replication APIs
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/add").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationAdd))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/remove").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationRemove))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/site-replication/info").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationInfo))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/site-replication/metainfo").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationMetaInfo))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/site-replication/status").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationStatus))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + adminAPISiteReplicationDevNull).HandlerFunc(adminMiddleware(adminAPI.SiteReplicationDevNull, noObjLayerFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + adminAPISiteReplicationNetPerf).HandlerFunc(adminMiddleware(adminAPI.SiteReplicationNetPerf, noObjLayerFlag))
+
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/peer/join").HandlerFunc(adminMiddleware(adminAPI.SRPeerJoin))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/site-replication/peer/bucket-ops").HandlerFunc(adminMiddleware(adminAPI.SRPeerBucketOps)).Queries("bucket", "{bucket:.*}").Queries("operation", "{operation:.*}")
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/peer/iam-item").HandlerFunc(adminMiddleware(adminAPI.SRPeerReplicateIAMItem))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/peer/bucket-meta").HandlerFunc(adminMiddleware(adminAPI.SRPeerReplicateBucketItem))
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/site-replication/peer/idp-settings").HandlerFunc(adminMiddleware(adminAPI.SRPeerGetIDPSettings))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/edit").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationEdit))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/peer/edit").HandlerFunc(adminMiddleware(adminAPI.SRPeerEdit))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/peer/remove").HandlerFunc(adminMiddleware(adminAPI.SRPeerRemove))
+		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/site-replication/resync/op").HandlerFunc(adminMiddleware(adminAPI.SiteReplicationResyncOp)).Queries("operation", "{operation:.*}")
+		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/site-replication/state/edit").HandlerFunc(adminMiddleware(adminAPI.SRStateEdit))
+
+		if globalIsDistErasure {
+			// Top locks
+			adminRouter.Methods(http.MethodGet).Path(adminVersion + "/top/locks").HandlerFunc(adminMiddleware(adminAPI.TopLocksHandler))
+			// Force unlocks paths
+			adminRouter.Methods(http.MethodPost).Path(adminVersion+"/force-unlock").
+				Queries("paths", "{paths:.*}").HandlerFunc(adminMiddleware(adminAPI.ForceUnlockHandler))
+		}
+
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/speedtest").HandlerFunc(adminMiddleware(adminAPI.ObjectSpeedTestHandler, noGZFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/speedtest/object").HandlerFunc(adminMiddleware(adminAPI.ObjectSpeedTestHandler, noGZFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/speedtest/drive").HandlerFunc(adminMiddleware(adminAPI.DriveSpeedtestHandler, noGZFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/speedtest/net").HandlerFunc(adminMiddleware(adminAPI.NetperfHandler, noGZFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/speedtest/site").HandlerFunc(adminMiddleware(adminAPI.SitePerfHandler, noGZFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + adminAPIClientDevNull).HandlerFunc(adminMiddleware(adminAPI.ClientDevNull, noGZFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + adminAPIClientDevExtraTime).HandlerFunc(adminMiddleware(adminAPI.ClientDevNullExtraTime, noGZFlag))
+
+		// HTTP Trace
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/trace").HandlerFunc(adminMiddleware(adminAPI.TraceHandler, noObjLayerFlag))
+
+		// Console Logs
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/log").HandlerFunc(adminMiddleware(adminAPI.ConsoleLogHandler, traceAllFlag))
+
+		// -- KMS APIs --
+		//
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/kms/status").HandlerFunc(adminMiddleware(adminAPI.KMSStatusHandler, traceAllFlag))
+		adminRouter.Methods(http.MethodPost).Path(adminVersion+"/kms/key/create").HandlerFunc(adminMiddleware(adminAPI.KMSCreateKeyHandler, traceAllFlag)).Queries("key-id", "{key-id:.*}")
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/kms/key/status").HandlerFunc(adminMiddleware(adminAPI.KMSKeyStatusHandler, traceAllFlag))
+
+		// Keep obdinfo for backward compatibility with mc
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/obdinfo").
+			HandlerFunc(adminMiddleware(adminAPI.HealthInfoHandler))
+		// -- Health API --
+		adminRouter.Methods(http.MethodGet).Path(adminVersion + "/healthinfo").
+			HandlerFunc(adminMiddleware(adminAPI.HealthInfoHandler))
+
+		// STS Revocation
+		adminRouter.Methods(http.MethodPost).Path(adminVersion + "/revoke-tokens/{userProvider}").HandlerFunc(adminMiddleware(adminAPI.RevokeTokens))
+	}
+
+	// If none of the routes match add default error handler routes
+	adminRouter.NotFoundHandler = httpTraceAll(errorResponseHandler)
+	adminRouter.MethodNotAllowedHandler = httpTraceAll(methodNotAllowedHandler("Admin"))
+}

cmd/admin-server-info.go

@@ -0,0 +1,171 @@
+// Copyright (c) 2015-2024 MinIO, Inc.
+//
+// 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 (
+	"math"
+	"net/http"
+	"os"
+	"runtime"
+	"runtime/debug"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio/internal/config"
+	"github.com/minio/minio/internal/kms"
+	xnet "github.com/minio/pkg/v3/net"
+)
+
+// getLocalServerProperty - returns madmin.ServerProperties for only the
+// local endpoints from given list of endpoints
+func getLocalServerProperty(endpointServerPools EndpointServerPools, r *http.Request, metrics bool) madmin.ServerProperties {
+	addr := globalLocalNodeName
+	if r != nil {
+		addr = r.Host
+	}
+	if globalIsDistErasure {
+		addr = globalLocalNodeName
+	}
+	poolNumbers := make(map[int]struct{})
+	network := make(map[string]string)
+	for _, ep := range endpointServerPools {
+		for _, endpoint := range ep.Endpoints {
+			if endpoint.IsLocal {
+				poolNumbers[endpoint.PoolIdx+1] = struct{}{}
+			}
+			nodeName := endpoint.Host
+			if nodeName == "" {
+				nodeName = addr
+			}
+			if endpoint.IsLocal {
+				// Only proceed for local endpoints
+				network[nodeName] = string(madmin.ItemOnline)
+				continue
+			}
+			_, present := network[nodeName]
+			if !present {
+				if err := isServerResolvable(endpoint, 5*time.Second); err == nil {
+					network[nodeName] = string(madmin.ItemOnline)
+				} else {
+					if xnet.IsNetworkOrHostDown(err, false) {
+						network[nodeName] = string(madmin.ItemOffline)
+					} else if xnet.IsNetworkOrHostDown(err, true) {
+						network[nodeName] = "connection attempt timedout"
+					}
+				}
+			}
+		}
+	}
+
+	var memstats runtime.MemStats
+	runtime.ReadMemStats(&memstats)
+
+	gcStats := debug.GCStats{
+		// If stats.PauseQuantiles is non-empty, ReadGCStats fills
+		// it with quantiles summarizing the distribution of pause time.
+		// For example, if len(stats.PauseQuantiles) is 5, it will be
+		// filled with the minimum, 25%, 50%, 75%, and maximum pause times.
+		PauseQuantiles: make([]time.Duration, 5),
+	}
+	debug.ReadGCStats(&gcStats)
+	// Truncate GC stats to max 5 entries.
+	if len(gcStats.PauseEnd) > 5 {
+		gcStats.PauseEnd = gcStats.PauseEnd[len(gcStats.PauseEnd)-5:]
+	}
+	if len(gcStats.Pause) > 5 {
+		gcStats.Pause = gcStats.Pause[len(gcStats.Pause)-5:]
+	}
+
+	props := madmin.ServerProperties{
+		Endpoint: addr,
+		Uptime:   UTCNow().Unix() - globalBootTime.Unix(),
+		Version:  Version,
+		CommitID: CommitID,
+		Network:  network,
+		MemStats: madmin.MemStats{
+			Alloc:      memstats.Alloc,
+			TotalAlloc: memstats.TotalAlloc,
+			Mallocs:    memstats.Mallocs,
+			Frees:      memstats.Frees,
+			HeapAlloc:  memstats.HeapAlloc,
+		},
+		GoMaxProcs:     runtime.GOMAXPROCS(0),
+		NumCPU:         runtime.NumCPU(),
+		RuntimeVersion: runtime.Version(),
+		GCStats: &madmin.GCStats{
+			LastGC:     gcStats.LastGC,
+			NumGC:      gcStats.NumGC,
+			PauseTotal: gcStats.PauseTotal,
+			Pause:      gcStats.Pause,
+			PauseEnd:   gcStats.PauseEnd,
+		},
+		MinioEnvVars: make(map[string]string, 10),
+	}
+
+	for poolNumber := range poolNumbers {
+		props.PoolNumbers = append(props.PoolNumbers, poolNumber)
+	}
+	sort.Ints(props.PoolNumbers)
+	props.PoolNumber = func() int {
+		if len(props.PoolNumbers) == 1 {
+			return props.PoolNumbers[0]
+		}
+		return math.MaxInt // this indicates that its unset.
+	}()
+
+	sensitive := map[string]struct{}{
+		config.EnvAccessKey:         {},
+		config.EnvSecretKey:         {},
+		config.EnvRootUser:          {},
+		config.EnvRootPassword:      {},
+		config.EnvMinIOSubnetAPIKey: {},
+		kms.EnvKMSSecretKey:         {},
+	}
+	for _, v := range os.Environ() {
+		if !strings.HasPrefix(v, "MINIO") && !strings.HasPrefix(v, "_MINIO") {
+			continue
+		}
+		split := strings.SplitN(v, "=", 2)
+		key := split[0]
+		value := ""
+		if len(split) > 1 {
+			value = split[1]
+		}
+
+		// Do not send sensitive creds.
+		if _, ok := sensitive[key]; ok || strings.Contains(strings.ToLower(key), "password") || strings.HasSuffix(strings.ToLower(key), "key") {
+			props.MinioEnvVars[key] = "*** EXISTS, REDACTED ***"
+			continue
+		}
+		props.MinioEnvVars[key] = value
+	}
+
+	objLayer := newObjectLayerFn()
+	if objLayer != nil {
+		storageInfo := objLayer.LocalStorageInfo(GlobalContext, metrics)
+		props.State = string(madmin.ItemOnline)
+		props.Disks = storageInfo.Disks
+	} else {
+		props.State = string(madmin.ItemInitializing)
+		props.Disks = getOfflineDisks("", globalEndpoints)
+	}
+
+	return props
+}

cmd/api-datatypes.go

@@ -0,0 +1,85 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"encoding/xml"
+	"time"
+)
+
+// DeletedObject objects deleted
+type DeletedObject struct {
+	DeleteMarker          bool   `xml:"DeleteMarker,omitempty"`
+	DeleteMarkerVersionID string `xml:"DeleteMarkerVersionId,omitempty"`
+	ObjectName            string `xml:"Key,omitempty"`
+	VersionID             string `xml:"VersionId,omitempty"`
+	// MTime of DeleteMarker on source that needs to be propagated to replica
+	DeleteMarkerMTime DeleteMarkerMTime `xml:"-"`
+	// MinIO extensions to support delete marker replication
+	ReplicationState ReplicationState `xml:"-"`
+
+	found bool // the object was found during deletion
+}
+
+// DeleteMarkerMTime is an embedded type containing time.Time for XML marshal
+type DeleteMarkerMTime struct {
+	time.Time
+}
+
+// MarshalXML encodes expiration date if it is non-zero and encodes
+// empty string otherwise
+func (t DeleteMarkerMTime) MarshalXML(e *xml.Encoder, startElement xml.StartElement) error {
+	if t.IsZero() {
+		return nil
+	}
+	return e.EncodeElement(t.Format(time.RFC3339), startElement)
+}
+
+// ObjectV object version key/versionId
+type ObjectV struct {
+	ObjectName string `xml:"Key"`
+	VersionID  string `xml:"VersionId"`
+}
+
+// ObjectToDelete carries key name for the object to delete.
+type ObjectToDelete struct {
+	ObjectV
+	// Replication status of DeleteMarker
+	DeleteMarkerReplicationStatus string `xml:"DeleteMarkerReplicationStatus"`
+	// Status of versioned delete (of object or DeleteMarker)
+	VersionPurgeStatus VersionPurgeStatusType `xml:"VersionPurgeStatus"`
+	// VersionPurgeStatuses holds the internal
+	VersionPurgeStatuses string `xml:"VersionPurgeStatuses"`
+	// ReplicateDecisionStr stringified representation of replication decision
+	ReplicateDecisionStr string `xml:"-"`
+}
+
+// createBucketLocationConfiguration container for bucket configuration request from client.
+// Used for parsing the location from the request body for Makebucket.
+type createBucketLocationConfiguration struct {
+	XMLName  xml.Name `xml:"CreateBucketConfiguration" json:"-"`
+	Location string   `xml:"LocationConstraint"`
+}
+
+// DeleteObjectsRequest - xml carrying the object key names which needs to be deleted.
+type DeleteObjectsRequest struct {
+	// Element to enable quiet mode for the request
+	Quiet bool
+	// List of objects to be deleted
+	Objects []ObjectToDelete `xml:"Object"`
+}

cmd/api-errors_test.go

@@ -0,0 +1,89 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"errors"
+	"testing"
+
+	"github.com/minio/minio/internal/crypto"
+	"github.com/minio/minio/internal/hash"
+)
+
+var toAPIErrorTests = []struct {
+	err     error
+	errCode APIErrorCode
+}{
+	{err: hash.BadDigest{}, errCode: ErrBadDigest},
+	{err: hash.SHA256Mismatch{}, errCode: ErrContentSHA256Mismatch},
+	{err: IncompleteBody{}, errCode: ErrIncompleteBody},
+	{err: ObjectExistsAsDirectory{}, errCode: ErrObjectExistsAsDirectory},
+	{err: BucketNameInvalid{}, errCode: ErrInvalidBucketName},
+	{err: BucketExists{}, errCode: ErrBucketAlreadyOwnedByYou},
+	{err: ObjectNotFound{}, errCode: ErrNoSuchKey},
+	{err: ObjectNameInvalid{}, errCode: ErrInvalidObjectName},
+	{err: InvalidUploadID{}, errCode: ErrNoSuchUpload},
+	{err: InvalidPart{}, errCode: ErrInvalidPart},
+	{err: InsufficientReadQuorum{}, errCode: ErrSlowDownRead},
+	{err: InsufficientWriteQuorum{}, errCode: ErrSlowDownWrite},
+	{err: InvalidUploadIDKeyCombination{}, errCode: ErrNotImplemented},
+	{err: MalformedUploadID{}, errCode: ErrNoSuchUpload},
+	{err: PartTooSmall{}, errCode: ErrEntityTooSmall},
+	{err: BucketNotEmpty{}, errCode: ErrBucketNotEmpty},
+	{err: BucketNotFound{}, errCode: ErrNoSuchBucket},
+	{err: StorageFull{}, errCode: ErrStorageFull},
+	{err: NotImplemented{}, errCode: ErrNotImplemented},
+	{err: errSignatureMismatch, errCode: ErrSignatureDoesNotMatch},
+
+	// SSE-C errors
+	{err: crypto.ErrInvalidCustomerAlgorithm, errCode: ErrInvalidSSECustomerAlgorithm},
+	{err: crypto.ErrMissingCustomerKey, errCode: ErrMissingSSECustomerKey},
+	{err: crypto.ErrInvalidCustomerKey, errCode: ErrAccessDenied},
+	{err: crypto.ErrMissingCustomerKeyMD5, errCode: ErrMissingSSECustomerKeyMD5},
+	{err: crypto.ErrCustomerKeyMD5Mismatch, errCode: ErrSSECustomerKeyMD5Mismatch},
+	{err: errObjectTampered, errCode: ErrObjectTampered},
+
+	{err: nil, errCode: ErrNone},
+	{err: errors.New("Custom error"), errCode: ErrInternalError}, // Case where err type is unknown.
+}
+
+func TestAPIErrCode(t *testing.T) {
+	ctx := t.Context()
+	for i, testCase := range toAPIErrorTests {
+		errCode := toAPIErrorCode(ctx, testCase.err)
+		if errCode != testCase.errCode {
+			t.Errorf("Test %d: Expected error code %d, got %d", i+1, testCase.errCode, errCode)
+		}
+	}
+}
+
+// Check if an API error is properly defined
+func TestAPIErrCodeDefinition(t *testing.T) {
+	for errAPI := ErrNone + 1; errAPI < apiErrCodeEnd; errAPI++ {
+		errCode, ok := errorCodes[errAPI]
+		if !ok {
+			t.Fatal(errAPI, "error code is not defined in the API error code table")
+		}
+		if errCode.Code == "" {
+			t.Fatal(errAPI, "error code has an empty XML code")
+		}
+		if errCode.HTTPStatusCode == 0 {
+			t.Fatal(errAPI, "error code has a zero HTTP status code")
+		}
+	}
+}

cmd/api-headers.go

@@ -0,0 +1,269 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"encoding/json"
+	"encoding/xml"
+	"fmt"
+	"mime"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/minio/minio-go/v7/pkg/tags"
+	"github.com/minio/minio/internal/crypto"
+	xhttp "github.com/minio/minio/internal/http"
+	xxml "github.com/minio/xxml"
+)
+
+// Returns a hexadecimal representation of time at the
+// time response is sent to the client.
+func mustGetRequestID(t time.Time) string {
+	return fmt.Sprintf("%X", t.UnixNano())
+}
+
+// setEventStreamHeaders to allow proxies to avoid buffering proxy responses
+func setEventStreamHeaders(w http.ResponseWriter) {
+	w.Header().Set(xhttp.ContentType, "text/event-stream")
+	w.Header().Set(xhttp.CacheControl, "no-cache") // nginx to turn off buffering
+	w.Header().Set("X-Accel-Buffering", "no")      // nginx to turn off buffering
+}
+
+// Write http common headers
+func setCommonHeaders(w http.ResponseWriter) {
+	// Set the "Server" http header.
+	w.Header().Set(xhttp.ServerInfo, MinioStoreName)
+
+	// Set `x-amz-bucket-region` only if region is set on the server
+	// by default minio uses an empty region.
+	if region := globalSite.Region(); region != "" {
+		w.Header().Set(xhttp.AmzBucketRegion, region)
+	}
+	w.Header().Set(xhttp.AcceptRanges, "bytes")
+
+	// Remove sensitive information
+	crypto.RemoveSensitiveHeaders(w.Header())
+}
+
+// Encodes the response headers into XML format.
+func encodeResponse(response interface{}) []byte {
+	var buf bytes.Buffer
+	buf.WriteString(xml.Header)
+	if err := xml.NewEncoder(&buf).Encode(response); err != nil {
+		bugLogIf(GlobalContext, err)
+		return nil
+	}
+	return buf.Bytes()
+}
+
+// Use this encodeResponseList() to support control characters
+// this function must be used by only ListObjects() for objects
+// with control characters, this is a specialized extension
+// to support AWS S3 compatible behavior.
+//
+// Do not use this function for anything other than ListObjects()
+// variants, please open a github discussion if you wish to use
+// this in other places.
+func encodeResponseList(response interface{}) []byte {
+	var buf bytes.Buffer
+	buf.WriteString(xxml.Header)
+	if err := xxml.NewEncoder(&buf).Encode(response); err != nil {
+		bugLogIf(GlobalContext, err)
+		return nil
+	}
+	return buf.Bytes()
+}
+
+// Encodes the response headers into JSON format.
+func encodeResponseJSON(response interface{}) []byte {
+	var bytesBuffer bytes.Buffer
+	e := json.NewEncoder(&bytesBuffer)
+	e.Encode(response)
+	return bytesBuffer.Bytes()
+}
+
+// Write parts count
+func setPartsCountHeaders(w http.ResponseWriter, objInfo ObjectInfo) {
+	if strings.Contains(objInfo.ETag, "-") && len(objInfo.Parts) > 0 {
+		w.Header()[xhttp.AmzMpPartsCount] = []string{strconv.Itoa(len(objInfo.Parts))}
+	}
+}
+
+// Write object header
+func setObjectHeaders(ctx context.Context, w http.ResponseWriter, objInfo ObjectInfo, rs *HTTPRangeSpec, opts ObjectOptions) (err error) {
+	// set common headers
+	setCommonHeaders(w)
+
+	// Set last modified time.
+	lastModified := objInfo.ModTime.UTC().Format(http.TimeFormat)
+	w.Header().Set(xhttp.LastModified, lastModified)
+
+	// Set Etag if available.
+	if objInfo.ETag != "" {
+		w.Header()[xhttp.ETag] = []string{"\"" + objInfo.ETag + "\""}
+	}
+
+	if objInfo.ContentType != "" {
+		w.Header().Set(xhttp.ContentType, objInfo.ContentType)
+	}
+
+	if objInfo.ContentEncoding != "" {
+		w.Header().Set(xhttp.ContentEncoding, objInfo.ContentEncoding)
+	}
+
+	if !objInfo.Expires.IsZero() {
+		w.Header().Set(xhttp.Expires, objInfo.Expires.UTC().Format(http.TimeFormat))
+	}
+
+	// Set tag count if object has tags
+	if len(objInfo.UserTags) > 0 {
+		tags, _ := tags.ParseObjectTags(objInfo.UserTags)
+		if tags != nil && tags.Count() > 0 {
+			w.Header()[xhttp.AmzTagCount] = []string{strconv.Itoa(tags.Count())}
+			if opts.Tagging {
+				// This is MinIO only extension to return back tags along with the count.
+				w.Header()[xhttp.AmzObjectTagging] = []string{objInfo.UserTags}
+			}
+		}
+	}
+
+	// Set all other user defined metadata.
+	for k, v := range objInfo.UserDefined {
+		// Empty values for object lock and retention can be skipped.
+		if v == "" && equals(k, xhttp.AmzObjectLockMode, xhttp.AmzObjectLockRetainUntilDate) {
+			continue
+		}
+
+		if stringsHasPrefixFold(k, ReservedMetadataPrefixLower) {
+			// Do not need to send any internal metadata
+			// values to client.
+			continue
+		}
+
+		// https://github.com/google/security-research/security/advisories/GHSA-76wf-9vgp-pj7w
+		if equals(k, xhttp.AmzMetaUnencryptedContentLength, xhttp.AmzMetaUnencryptedContentMD5) {
+			continue
+		}
+
+		var isSet bool
+		for _, userMetadataPrefix := range userMetadataKeyPrefixes {
+			if !stringsHasPrefixFold(k, userMetadataPrefix) {
+				continue
+			}
+			// check the doc https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingMetadata.html
+			// For metadata values like "ö", "ÄMÄZÕÑ S3", and "öha, das sollte eigentlich
+			// funktionieren", tested against a real AWS S3 bucket, S3 may encode incorrectly. For
+			// example, "ö" was encoded as =?UTF-8?B?w4PCtg==?=, producing invalid UTF-8 instead
+			// of =?UTF-8?B?w7Y=?=. This mirrors errors like the ä½ in another string.
+			//
+			// S3 uses B-encoding (Base64) for non-ASCII-heavy metadata and Q-encoding
+			// (quoted-printable) for mostly ASCII strings. Long strings are split at word
+			// boundaries to fit RFC 2047’s 75-character limit, ensuring HTTP parser
+			// compatibility.
+			//
+			// However, this splitting increases header size and can introduce errors, unlike Go’s
+			// mime package in MinIO, which correctly encodes strings with fixed B/Q encodings,
+			// avoiding S3’s heuristic-driven issues.
+			//
+			// For MinIO developers, decode S3 metadata with mime.WordDecoder, validate outputs,
+			// report encoding bugs to AWS, and use ASCII-only metadata to ensure reliable S3 API
+			// compatibility.
+			if needsMimeEncoding(v) {
+				// see https://github.com/golang/go/blob/release-branch.go1.24/src/net/mail/message.go#L325
+				if strings.ContainsAny(v, "\"#$%&'(),.:;<>@[]^`{|}~") {
+					v = mime.BEncoding.Encode("UTF-8", v)
+				} else {
+					v = mime.QEncoding.Encode("UTF-8", v)
+				}
+			}
+			w.Header()[strings.ToLower(k)] = []string{v}
+			isSet = true
+			break
+		}
+
+		if !isSet {
+			w.Header().Set(k, v)
+		}
+	}
+
+	var start, rangeLen int64
+	totalObjectSize, err := objInfo.GetActualSize()
+	if err != nil {
+		return err
+	}
+
+	if rs == nil && opts.PartNumber > 0 {
+		rs = partNumberToRangeSpec(objInfo, opts.PartNumber)
+	}
+
+	// For providing ranged content
+	start, rangeLen, err = rs.GetOffsetLength(totalObjectSize)
+	if err != nil {
+		return err
+	}
+
+	// Set content length.
+	w.Header().Set(xhttp.ContentLength, strconv.FormatInt(rangeLen, 10))
+	if rs != nil {
+		contentRange := fmt.Sprintf("bytes %d-%d/%d", start, start+rangeLen-1, totalObjectSize)
+		w.Header().Set(xhttp.ContentRange, contentRange)
+	}
+
+	// Set the relevant version ID as part of the response header.
+	if objInfo.VersionID != "" && objInfo.VersionID != nullVersionID {
+		w.Header()[xhttp.AmzVersionID] = []string{objInfo.VersionID}
+	}
+
+	if objInfo.ReplicationStatus.String() != "" {
+		w.Header()[xhttp.AmzBucketReplicationStatus] = []string{objInfo.ReplicationStatus.String()}
+	}
+
+	if objInfo.IsRemote() {
+		// Check if object is being restored. For more information on x-amz-restore header see
+		// https://docs.aws.amazon.com/AmazonS3/latest/API/API_HeadObject.html#API_HeadObject_ResponseSyntax
+		w.Header()[xhttp.AmzStorageClass] = []string{filterStorageClass(ctx, objInfo.TransitionedObject.Tier)}
+	}
+
+	if lc, err := globalLifecycleSys.Get(objInfo.Bucket); err == nil {
+		lc.SetPredictionHeaders(w, objInfo.ToLifecycleOpts())
+	}
+
+	if v, ok := objInfo.UserDefined[ReservedMetadataPrefix+"compression"]; ok {
+		if i := strings.LastIndexByte(v, '/'); i >= 0 {
+			v = v[i+1:]
+		}
+		w.Header()[xhttp.MinIOCompressed] = []string{v}
+	}
+
+	return nil
+}
+
+// needsEncoding reports whether s contains any bytes that need to be encoded.
+// see mime.needsEncoding
+func needsMimeEncoding(s string) bool {
+	for _, b := range s {
+		if (b < ' ' || b > '~') && b != '\t' {
+			return true
+		}
+	}
+	return false
+}

cmd/api-headers_test.go

@@ -0,0 +1,42 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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"
+)
+
+func TestNewRequestID(t *testing.T) {
+	// Ensure that it returns an alphanumeric result of length 16.
+	id := mustGetRequestID(UTCNow())
+
+	if len(id) != 16 {
+		t.Fail()
+	}
+
+	var e rune
+	for _, char := range id {
+		e = char
+
+		// Ensure that it is alphanumeric, in this case, between 0-9 and A-Z.
+		isAlnum := ('0' <= e && e <= '9') || ('A' <= e && e <= 'Z')
+		if !isAlnum {
+			t.Fail()
+		}
+	}
+}

cmd/api-resources.go

@@ -0,0 +1,153 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"encoding/base64"
+	"net/url"
+	"strconv"
+)
+
+// Parse bucket url queries
+func getListObjectsV1Args(values url.Values) (prefix, marker, delimiter string, maxkeys int, encodingType string, errCode APIErrorCode) {
+	errCode = ErrNone
+
+	if values.Get("max-keys") != "" {
+		var err error
+		if maxkeys, err = strconv.Atoi(values.Get("max-keys")); err != nil {
+			errCode = ErrInvalidMaxKeys
+			return
+		}
+	} else {
+		maxkeys = maxObjectList
+	}
+
+	prefix = values.Get("prefix")
+	marker = values.Get("marker")
+	delimiter = values.Get("delimiter")
+	encodingType = values.Get("encoding-type")
+	return
+}
+
+func getListBucketObjectVersionsArgs(values url.Values) (prefix, marker, delimiter string, maxkeys int, encodingType, versionIDMarker string, errCode APIErrorCode) {
+	errCode = ErrNone
+
+	if values.Get("max-keys") != "" {
+		var err error
+		if maxkeys, err = strconv.Atoi(values.Get("max-keys")); err != nil {
+			errCode = ErrInvalidMaxKeys
+			return
+		}
+	} else {
+		maxkeys = maxObjectList
+	}
+
+	prefix = values.Get("prefix")
+	marker = values.Get("key-marker")
+	delimiter = values.Get("delimiter")
+	encodingType = values.Get("encoding-type")
+	versionIDMarker = values.Get("version-id-marker")
+	return
+}
+
+// Parse bucket url queries for ListObjects V2.
+func getListObjectsV2Args(values url.Values) (prefix, token, startAfter, delimiter string, fetchOwner bool, maxkeys int, encodingType string, errCode APIErrorCode) {
+	errCode = ErrNone
+
+	// The continuation-token cannot be empty.
+	if val, ok := values["continuation-token"]; ok {
+		if len(val[0]) == 0 {
+			errCode = ErrIncorrectContinuationToken
+			return
+		}
+	}
+
+	if values.Get("max-keys") != "" {
+		var err error
+		if maxkeys, err = strconv.Atoi(values.Get("max-keys")); err != nil {
+			errCode = ErrInvalidMaxKeys
+			return
+		}
+	} else {
+		maxkeys = maxObjectList
+	}
+
+	prefix = values.Get("prefix")
+	startAfter = values.Get("start-after")
+	delimiter = values.Get("delimiter")
+	fetchOwner = values.Get("fetch-owner") == "true"
+	encodingType = values.Get("encoding-type")
+
+	if token = values.Get("continuation-token"); token != "" {
+		decodedToken, err := base64.StdEncoding.DecodeString(token)
+		if err != nil {
+			errCode = ErrIncorrectContinuationToken
+			return
+		}
+		token = string(decodedToken)
+	}
+	return
+}
+
+// Parse bucket url queries for ?uploads
+func getBucketMultipartResources(values url.Values) (prefix, keyMarker, uploadIDMarker, delimiter string, maxUploads int, encodingType string, errCode APIErrorCode) {
+	errCode = ErrNone
+
+	if values.Get("max-uploads") != "" {
+		var err error
+		if maxUploads, err = strconv.Atoi(values.Get("max-uploads")); err != nil {
+			errCode = ErrInvalidMaxUploads
+			return
+		}
+	} else {
+		maxUploads = maxUploadsList
+	}
+
+	prefix = values.Get("prefix")
+	keyMarker = values.Get("key-marker")
+	uploadIDMarker = values.Get("upload-id-marker")
+	delimiter = values.Get("delimiter")
+	encodingType = values.Get("encoding-type")
+	return
+}
+
+// Parse object url queries
+func getObjectResources(values url.Values) (uploadID string, partNumberMarker, maxParts int, encodingType string, errCode APIErrorCode) {
+	var err error
+	errCode = ErrNone
+
+	if values.Get("max-parts") != "" {
+		if maxParts, err = strconv.Atoi(values.Get("max-parts")); err != nil {
+			errCode = ErrInvalidMaxParts
+			return
+		}
+	} else {
+		maxParts = maxPartsList
+	}
+
+	if values.Get("part-number-marker") != "" {
+		if partNumberMarker, err = strconv.Atoi(values.Get("part-number-marker")); err != nil {
+			errCode = ErrInvalidPartNumberMarker
+			return
+		}
+	}
+
+	uploadID = values.Get("uploadId")
+	encodingType = values.Get("encoding-type")
+	return
+}

cmd/api-resources_test.go

@@ -0,0 +1,222 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"net/url"
+	"testing"
+)
+
+// Test list objects resources V2.
+func TestListObjectsV2Resources(t *testing.T) {
+	testCases := []struct {
+		values                               url.Values
+		prefix, token, startAfter, delimiter string
+		fetchOwner                           bool
+		maxKeys                              int
+		encodingType                         string
+		errCode                              APIErrorCode
+	}{
+		{
+			values: url.Values{
+				"prefix":             []string{"photos/"},
+				"continuation-token": []string{"dG9rZW4="},
+				"start-after":        []string{"start-after"},
+				"delimiter":          []string{SlashSeparator},
+				"fetch-owner":        []string{"true"},
+				"max-keys":           []string{"100"},
+				"encoding-type":      []string{"gzip"},
+			},
+			prefix:       "photos/",
+			token:        "token",
+			startAfter:   "start-after",
+			delimiter:    SlashSeparator,
+			fetchOwner:   true,
+			maxKeys:      100,
+			encodingType: "gzip",
+			errCode:      ErrNone,
+		},
+		{
+			values: url.Values{
+				"prefix":             []string{"photos/"},
+				"continuation-token": []string{"dG9rZW4="},
+				"start-after":        []string{"start-after"},
+				"delimiter":          []string{SlashSeparator},
+				"fetch-owner":        []string{"true"},
+				"encoding-type":      []string{"gzip"},
+			},
+			prefix:       "photos/",
+			token:        "token",
+			startAfter:   "start-after",
+			delimiter:    SlashSeparator,
+			fetchOwner:   true,
+			maxKeys:      maxObjectList,
+			encodingType: "gzip",
+			errCode:      ErrNone,
+		},
+		{
+			values: url.Values{
+				"prefix":             []string{"photos/"},
+				"continuation-token": []string{""},
+				"start-after":        []string{"start-after"},
+				"delimiter":          []string{SlashSeparator},
+				"fetch-owner":        []string{"true"},
+				"encoding-type":      []string{"gzip"},
+			},
+			prefix:       "",
+			token:        "",
+			startAfter:   "",
+			delimiter:    "",
+			fetchOwner:   false,
+			maxKeys:      0,
+			encodingType: "",
+			errCode:      ErrIncorrectContinuationToken,
+		},
+	}
+
+	for i, testCase := range testCases {
+		prefix, token, startAfter, delimiter, fetchOwner, maxKeys, encodingType, errCode := getListObjectsV2Args(testCase.values)
+
+		if errCode != testCase.errCode {
+			t.Errorf("Test %d: Expected error code:%d, got %d", i+1, testCase.errCode, errCode)
+		}
+		if prefix != testCase.prefix {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.prefix, prefix)
+		}
+		if token != testCase.token {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.token, token)
+		}
+		if startAfter != testCase.startAfter {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.startAfter, startAfter)
+		}
+		if delimiter != testCase.delimiter {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.delimiter, delimiter)
+		}
+		if fetchOwner != testCase.fetchOwner {
+			t.Errorf("Test %d: Expected %t, got %t", i+1, testCase.fetchOwner, fetchOwner)
+		}
+		if maxKeys != testCase.maxKeys {
+			t.Errorf("Test %d: Expected %d, got %d", i+1, testCase.maxKeys, maxKeys)
+		}
+		if encodingType != testCase.encodingType {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.encodingType, encodingType)
+		}
+	}
+}
+
+// Test list objects resources V1.
+func TestListObjectsV1Resources(t *testing.T) {
+	testCases := []struct {
+		values                    url.Values
+		prefix, marker, delimiter string
+		maxKeys                   int
+		encodingType              string
+	}{
+		{
+			values: url.Values{
+				"prefix":        []string{"photos/"},
+				"marker":        []string{"test"},
+				"delimiter":     []string{SlashSeparator},
+				"max-keys":      []string{"100"},
+				"encoding-type": []string{"gzip"},
+			},
+			prefix:       "photos/",
+			marker:       "test",
+			delimiter:    SlashSeparator,
+			maxKeys:      100,
+			encodingType: "gzip",
+		},
+		{
+			values: url.Values{
+				"prefix":        []string{"photos/"},
+				"marker":        []string{"test"},
+				"delimiter":     []string{SlashSeparator},
+				"encoding-type": []string{"gzip"},
+			},
+			prefix:       "photos/",
+			marker:       "test",
+			delimiter:    SlashSeparator,
+			maxKeys:      maxObjectList,
+			encodingType: "gzip",
+		},
+	}
+
+	for i, testCase := range testCases {
+		prefix, marker, delimiter, maxKeys, encodingType, argsErr := getListObjectsV1Args(testCase.values)
+		if argsErr != ErrNone {
+			t.Errorf("Test %d: argument parsing failed, got %v", i+1, argsErr)
+		}
+		if prefix != testCase.prefix {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.prefix, prefix)
+		}
+		if marker != testCase.marker {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.marker, marker)
+		}
+		if delimiter != testCase.delimiter {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.delimiter, delimiter)
+		}
+		if maxKeys != testCase.maxKeys {
+			t.Errorf("Test %d: Expected %d, got %d", i+1, testCase.maxKeys, maxKeys)
+		}
+		if encodingType != testCase.encodingType {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.encodingType, encodingType)
+		}
+	}
+}
+
+// Validates extracting information for object resources.
+func TestGetObjectsResources(t *testing.T) {
+	testCases := []struct {
+		values                     url.Values
+		uploadID                   string
+		partNumberMarker, maxParts int
+		encodingType               string
+	}{
+		{
+			values: url.Values{
+				"uploadId":           []string{"11123-11312312311231-12313"},
+				"part-number-marker": []string{"1"},
+				"max-parts":          []string{"1000"},
+				"encoding-type":      []string{"gzip"},
+			},
+			uploadID:         "11123-11312312311231-12313",
+			partNumberMarker: 1,
+			maxParts:         1000,
+			encodingType:     "gzip",
+		},
+	}
+
+	for i, testCase := range testCases {
+		uploadID, partNumberMarker, maxParts, encodingType, argsErr := getObjectResources(testCase.values)
+		if argsErr != ErrNone {
+			t.Errorf("Test %d: argument parsing failed, got %v", i+1, argsErr)
+		}
+		if uploadID != testCase.uploadID {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.uploadID, uploadID)
+		}
+		if partNumberMarker != testCase.partNumberMarker {
+			t.Errorf("Test %d: Expected %d, got %d", i+1, testCase.partNumberMarker, partNumberMarker)
+		}
+		if maxParts != testCase.maxParts {
+			t.Errorf("Test %d: Expected %d, got %d", i+1, testCase.maxParts, maxParts)
+		}
+		if encodingType != testCase.encodingType {
+			t.Errorf("Test %d: Expected %s, got %s", i+1, testCase.encodingType, encodingType)
+		}
+	}
+}

cmd/api-response_test.go

@@ -0,0 +1,125 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"net/http"
+	"testing"
+)
+
+// Tests object location.
+func TestObjectLocation(t *testing.T) {
+	testCases := []struct {
+		request          *http.Request
+		bucket, object   string
+		domains          []string
+		expectedLocation string
+	}{
+		// Server binding to localhost IP with https.
+		{
+			request: &http.Request{
+				Host: "127.0.0.1:9000",
+				Header: map[string][]string{
+					"X-Forwarded-Scheme": {httpScheme},
+				},
+			},
+			bucket:           "testbucket1",
+			object:           "test/1.txt",
+			expectedLocation: "http://127.0.0.1:9000/testbucket1/test/1.txt",
+		},
+		{
+			request: &http.Request{
+				Host: "127.0.0.1:9000",
+				Header: map[string][]string{
+					"X-Forwarded-Scheme": {httpsScheme},
+				},
+			},
+			bucket:           "testbucket1",
+			object:           "test/1.txt",
+			expectedLocation: "https://127.0.0.1:9000/testbucket1/test/1.txt",
+		},
+		// Server binding to fqdn.
+		{
+			request: &http.Request{
+				Host: "s3.mybucket.org",
+				Header: map[string][]string{
+					"X-Forwarded-Scheme": {httpScheme},
+				},
+			},
+			bucket:           "mybucket",
+			object:           "test/1.txt",
+			expectedLocation: "http://s3.mybucket.org/mybucket/test/1.txt",
+		},
+		// Server binding to fqdn.
+		{
+			request: &http.Request{
+				Host:   "mys3.mybucket.org",
+				Header: map[string][]string{},
+			},
+			bucket:           "mybucket",
+			object:           "test/1.txt",
+			expectedLocation: "http://mys3.mybucket.org/mybucket/test/1.txt",
+		},
+		// Server with virtual domain name.
+		{
+			request: &http.Request{
+				Host:   "mybucket.mys3.bucket.org",
+				Header: map[string][]string{},
+			},
+			domains:          []string{"mys3.bucket.org"},
+			bucket:           "mybucket",
+			object:           "test/1.txt",
+			expectedLocation: "http://mybucket.mys3.bucket.org/test/1.txt",
+		},
+		{
+			request: &http.Request{
+				Host: "mybucket.mys3.bucket.org",
+				Header: map[string][]string{
+					"X-Forwarded-Scheme": {httpsScheme},
+				},
+			},
+			domains:          []string{"mys3.bucket.org"},
+			bucket:           "mybucket",
+			object:           "test/1.txt",
+			expectedLocation: "https://mybucket.mys3.bucket.org/test/1.txt",
+		},
+	}
+	for _, testCase := range testCases {
+		testCase := testCase
+		t.Run("", func(t *testing.T) {
+			gotLocation := getObjectLocation(testCase.request, testCase.domains, testCase.bucket, testCase.object)
+			if testCase.expectedLocation != gotLocation {
+				t.Errorf("expected %s, got %s", testCase.expectedLocation, gotLocation)
+			}
+		})
+	}
+}
+
+// Tests getURLScheme function behavior.
+func TestGetURLScheme(t *testing.T) {
+	tls := false
+	gotScheme := getURLScheme(tls)
+	if gotScheme != httpScheme {
+		t.Errorf("Expected %s, got %s", httpScheme, gotScheme)
+	}
+	tls = true
+	gotScheme = getURLScheme(tls)
+	if gotScheme != httpsScheme {
+		t.Errorf("Expected %s, got %s", httpsScheme, gotScheme)
+	}
+}

cmd/api-router.go

@@ -0,0 +1,695 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"net"
+	"net/http"
+
+	consoleapi "github.com/minio/console/api"
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/minio/mux"
+	"github.com/minio/pkg/v3/wildcard"
+	"github.com/rs/cors"
+)
+
+func newHTTPServerFn() *xhttp.Server {
+	globalObjLayerMutex.RLock()
+	defer globalObjLayerMutex.RUnlock()
+	return globalHTTPServer
+}
+
+func setHTTPServer(h *xhttp.Server) {
+	globalObjLayerMutex.Lock()
+	globalHTTPServer = h
+	globalObjLayerMutex.Unlock()
+}
+
+func newConsoleServerFn() *consoleapi.Server {
+	globalObjLayerMutex.RLock()
+	defer globalObjLayerMutex.RUnlock()
+	return globalConsoleSrv
+}
+
+func setConsoleSrv(srv *consoleapi.Server) {
+	globalObjLayerMutex.Lock()
+	globalConsoleSrv = srv
+	globalObjLayerMutex.Unlock()
+}
+
+func newObjectLayerFn() ObjectLayer {
+	globalObjLayerMutex.RLock()
+	defer globalObjLayerMutex.RUnlock()
+	return globalObjectAPI
+}
+
+func setObjectLayer(o ObjectLayer) {
+	globalObjLayerMutex.Lock()
+	globalObjectAPI = o
+	globalObjLayerMutex.Unlock()
+}
+
+// objectAPIHandlers implements and provides http handlers for S3 API.
+type objectAPIHandlers struct {
+	ObjectAPI func() ObjectLayer
+}
+
+// getHost tries its best to return the request host.
+// According to section 14.23 of RFC 2616 the Host header
+// can include the port number if the default value of 80 is not used.
+func getHost(r *http.Request) string {
+	if r.URL.IsAbs() {
+		return r.URL.Host
+	}
+	return r.Host
+}
+
+func notImplementedHandler(w http.ResponseWriter, r *http.Request) {
+	writeErrorResponse(r.Context(), w, errorCodes.ToAPIErr(ErrNotImplemented), r.URL)
+}
+
+type rejectedAPI struct {
+	api     string
+	methods []string
+	queries []string
+	path    string
+}
+
+var rejectedObjAPIs = []rejectedAPI{
+	{
+		api:     "torrent",
+		methods: []string{http.MethodPut, http.MethodDelete, http.MethodGet},
+		queries: []string{"torrent", ""},
+		path:    "/{object:.+}",
+	},
+	{
+		api:     "acl",
+		methods: []string{http.MethodDelete},
+		queries: []string{"acl", ""},
+		path:    "/{object:.+}",
+	},
+}
+
+var rejectedBucketAPIs = []rejectedAPI{
+	{
+		api:     "inventory",
+		methods: []string{http.MethodGet, http.MethodPut, http.MethodDelete},
+		queries: []string{"inventory", ""},
+	},
+	{
+		api:     "cors",
+		methods: []string{http.MethodPut, http.MethodDelete},
+		queries: []string{"cors", ""},
+	},
+	{
+		api:     "metrics",
+		methods: []string{http.MethodGet, http.MethodPut, http.MethodDelete},
+		queries: []string{"metrics", ""},
+	},
+	{
+		api:     "website",
+		methods: []string{http.MethodPut},
+		queries: []string{"website", ""},
+	},
+	{
+		api:     "logging",
+		methods: []string{http.MethodPut, http.MethodDelete},
+		queries: []string{"logging", ""},
+	},
+	{
+		api:     "accelerate",
+		methods: []string{http.MethodPut, http.MethodDelete},
+		queries: []string{"accelerate", ""},
+	},
+	{
+		api:     "requestPayment",
+		methods: []string{http.MethodPut, http.MethodDelete},
+		queries: []string{"requestPayment", ""},
+	},
+	{
+		api:     "acl",
+		methods: []string{http.MethodDelete, http.MethodPut, http.MethodHead},
+		queries: []string{"acl", ""},
+	},
+	{
+		api:     "publicAccessBlock",
+		methods: []string{http.MethodDelete, http.MethodPut, http.MethodGet},
+		queries: []string{"publicAccessBlock", ""},
+	},
+	{
+		api:     "ownershipControls",
+		methods: []string{http.MethodDelete, http.MethodPut, http.MethodGet},
+		queries: []string{"ownershipControls", ""},
+	},
+	{
+		api:     "intelligent-tiering",
+		methods: []string{http.MethodDelete, http.MethodPut, http.MethodGet},
+		queries: []string{"intelligent-tiering", ""},
+	},
+	{
+		api:     "analytics",
+		methods: []string{http.MethodDelete, http.MethodPut, http.MethodGet},
+		queries: []string{"analytics", ""},
+	},
+}
+
+// Set of s3 handler options as bit flags.
+type s3HFlag uint8
+
+const (
+	// when provided, disables Gzip compression.
+	noGZS3HFlag = 1 << iota
+
+	// when provided, enables only tracing of headers. Otherwise, both headers
+	// and body are traced.
+	traceHdrsS3HFlag
+
+	// when provided, disables throttling via the `maxClients` middleware.
+	noThrottleS3HFlag
+)
+
+func (h s3HFlag) has(flag s3HFlag) bool {
+	// Use bitwise-AND and check if the result is non-zero.
+	return h&flag != 0
+}
+
+// s3APIMiddleware - performs some common handler functionality for S3 API
+// handlers.
+//
+// It is set per-"handler function registration" in the router to allow for
+// behavior modification via flags.
+//
+// This middleware always calls `collectAPIStats` to collect API stats.
+//
+// The passed in handler function must be a method of `objectAPIHandlers` for
+// the name displayed in logs and trace to be accurate. The name is extracted
+// via reflection.
+//
+// When **no** flags are passed, the behavior is to trace both headers and body,
+// gzip the response and throttle the handler via `maxClients`. Each of these
+// can be disabled via the corresponding `s3HFlag`.
+//
+// CAUTION: for requests involving large req/resp bodies ensure to pass the
+// `traceHdrsS3HFlag`, otherwise both headers and body will be traced, causing
+// high memory usage!
+func s3APIMiddleware(f http.HandlerFunc, flags ...s3HFlag) http.HandlerFunc {
+	// Collect all flags with bitwise-OR and assign operator
+	var handlerFlags s3HFlag
+	for _, flag := range flags {
+		handlerFlags |= flag
+	}
+
+	// Get name of the handler using reflection.
+	handlerName := getHandlerName(f, "objectAPIHandlers")
+
+	var handler http.HandlerFunc = func(w http.ResponseWriter, r *http.Request) {
+		// Wrap the actual handler with the appropriate tracing middleware.
+		var tracedHandler http.HandlerFunc
+		if handlerFlags.has(traceHdrsS3HFlag) {
+			tracedHandler = httpTraceHdrs(f)
+		} else {
+			tracedHandler = httpTraceAll(f)
+		}
+
+		// Skip wrapping with the gzip middleware if specified.
+		gzippedHandler := tracedHandler
+		if !handlerFlags.has(noGZS3HFlag) {
+			gzippedHandler = gzipHandler(gzippedHandler)
+		}
+
+		// Skip wrapping with throttling middleware if specified.
+		throttledHandler := gzippedHandler
+		if !handlerFlags.has(noThrottleS3HFlag) {
+			throttledHandler = maxClients(throttledHandler)
+		}
+
+		// Collect API stats using the API name got from reflection in
+		// `getHandlerName`.
+		statsCollectedHandler := collectAPIStats(handlerName, throttledHandler)
+
+		// Call the final handler.
+		statsCollectedHandler(w, r)
+	}
+
+	return handler
+}
+
+// registerAPIRouter - registers S3 compatible APIs.
+func registerAPIRouter(router *mux.Router) {
+	// Initialize API.
+	api := objectAPIHandlers{
+		ObjectAPI: newObjectLayerFn,
+	}
+
+	// API Router
+	apiRouter := router.PathPrefix(SlashSeparator).Subrouter()
+
+	var routers []*mux.Router
+	for _, domainName := range globalDomainNames {
+		if IsKubernetes() {
+			routers = append(routers, apiRouter.MatcherFunc(func(r *http.Request, match *mux.RouteMatch) bool {
+				host, _, err := net.SplitHostPort(getHost(r))
+				if err != nil {
+					host = r.Host
+				}
+				// Make sure to skip matching minio.<domain>` this is
+				// specifically meant for operator/k8s deployment
+				// The reason we need to skip this is for a special
+				// usecase where we need to make sure that
+				// minio.<namespace>.svc.<cluster_domain> is ignored
+				// by the bucketDNS style to ensure that path style
+				// is available and honored at this domain.
+				//
+				// All other `<bucket>.<namespace>.svc.<cluster_domain>`
+				// makes sure that buckets are routed through this matcher
+				// to match for `<bucket>`
+				return host != minioReservedBucket+"."+domainName
+			}).Host("{bucket:.+}."+domainName).Subrouter())
+		} else {
+			routers = append(routers, apiRouter.Host("{bucket:.+}."+domainName).Subrouter())
+		}
+	}
+	routers = append(routers, apiRouter.PathPrefix("/{bucket}").Subrouter())
+
+	for _, router := range routers {
+		// Register all rejected object APIs
+		for _, r := range rejectedObjAPIs {
+			t := router.Methods(r.methods...).
+				HandlerFunc(collectAPIStats(r.api, httpTraceAll(notImplementedHandler))).
+				Queries(r.queries...)
+			t.Path(r.path)
+		}
+
+		// Object operations
+		// HeadObject
+		router.Methods(http.MethodHead).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.HeadObjectHandler))
+
+		// GetObjectAttributes
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectAttributesHandler, traceHdrsS3HFlag)).
+			Queries("attributes", "")
+
+		// CopyObjectPart
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HeadersRegexp(xhttp.AmzCopySource, ".*?(\\/|%2F).*?").
+			HandlerFunc(s3APIMiddleware(api.CopyObjectPartHandler)).
+			Queries("partNumber", "{partNumber:.*}", "uploadId", "{uploadId:.*}")
+		// PutObjectPart
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PutObjectPartHandler, traceHdrsS3HFlag)).
+			Queries("partNumber", "{partNumber:.*}", "uploadId", "{uploadId:.*}")
+		// ListObjectParts
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.ListObjectPartsHandler)).
+			Queries("uploadId", "{uploadId:.*}")
+		// CompleteMultipartUpload
+		router.Methods(http.MethodPost).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.CompleteMultipartUploadHandler)).
+			Queries("uploadId", "{uploadId:.*}")
+		// NewMultipartUpload
+		router.Methods(http.MethodPost).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.NewMultipartUploadHandler)).
+			Queries("uploads", "")
+		// AbortMultipartUpload
+		router.Methods(http.MethodDelete).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.AbortMultipartUploadHandler)).
+			Queries("uploadId", "{uploadId:.*}")
+		// GetObjectACL - this is a dummy call.
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectACLHandler, traceHdrsS3HFlag)).
+			Queries("acl", "")
+		// PutObjectACL - this is a dummy call.
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PutObjectACLHandler, traceHdrsS3HFlag)).
+			Queries("acl", "")
+		// GetObjectTagging
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectTaggingHandler, traceHdrsS3HFlag)).
+			Queries("tagging", "")
+		// PutObjectTagging
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PutObjectTaggingHandler, traceHdrsS3HFlag)).
+			Queries("tagging", "")
+		// DeleteObjectTagging
+		router.Methods(http.MethodDelete).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.DeleteObjectTaggingHandler, traceHdrsS3HFlag)).
+			Queries("tagging", "")
+		// SelectObjectContent
+		router.Methods(http.MethodPost).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.SelectObjectContentHandler, traceHdrsS3HFlag)).
+			Queries("select", "").Queries("select-type", "2")
+		// GetObjectRetention
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectRetentionHandler)).
+			Queries("retention", "")
+		// GetObjectLegalHold
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectLegalHoldHandler)).
+			Queries("legal-hold", "")
+		// GetObject with lambda ARNs
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectLambdaHandler, traceHdrsS3HFlag)).
+			Queries("lambdaArn", "{lambdaArn:.*}")
+		// GetObject
+		router.Methods(http.MethodGet).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.GetObjectHandler, traceHdrsS3HFlag))
+		// CopyObject
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HeadersRegexp(xhttp.AmzCopySource, ".*?(\\/|%2F).*?").
+			HandlerFunc(s3APIMiddleware(api.CopyObjectHandler))
+		// PutObjectRetention
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PutObjectRetentionHandler)).
+			Queries("retention", "")
+		// PutObjectLegalHold
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PutObjectLegalHoldHandler)).
+			Queries("legal-hold", "")
+
+		// PutObject with auto-extract support for zip
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HeadersRegexp(xhttp.AmzSnowballExtract, "true").
+			HandlerFunc(s3APIMiddleware(api.PutObjectExtractHandler, traceHdrsS3HFlag))
+
+		// AppendObject to be rejected
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HeadersRegexp(xhttp.AmzWriteOffsetBytes, "").
+			HandlerFunc(s3APIMiddleware(errorResponseHandler))
+
+		// PutObject
+		router.Methods(http.MethodPut).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PutObjectHandler, traceHdrsS3HFlag))
+
+		// DeleteObject
+		router.Methods(http.MethodDelete).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.DeleteObjectHandler))
+
+		// PostRestoreObject
+		router.Methods(http.MethodPost).Path("/{object:.+}").
+			HandlerFunc(s3APIMiddleware(api.PostRestoreObjectHandler)).
+			Queries("restore", "")
+
+		// Bucket operations
+
+		// GetBucketLocation
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketLocationHandler)).
+			Queries("location", "")
+		// GetBucketPolicy
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketPolicyHandler)).
+			Queries("policy", "")
+		// GetBucketLifecycle
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketLifecycleHandler)).
+			Queries("lifecycle", "")
+		// GetBucketEncryption
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketEncryptionHandler)).
+			Queries("encryption", "")
+		// GetBucketObjectLockConfig
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketObjectLockConfigHandler)).
+			Queries("object-lock", "")
+		// GetBucketReplicationConfig
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketReplicationConfigHandler)).
+			Queries("replication", "")
+		// GetBucketVersioning
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketVersioningHandler)).
+			Queries("versioning", "")
+		// GetBucketNotification
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketNotificationHandler)).
+			Queries("notification", "")
+		// ListenNotification
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListenNotificationHandler, noThrottleS3HFlag, traceHdrsS3HFlag)).
+			Queries("events", "{events:.*}")
+		// ResetBucketReplicationStatus - MinIO extension API
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ResetBucketReplicationStatusHandler)).
+			Queries("replication-reset-status", "")
+
+		// Dummy Bucket Calls
+		// GetBucketACL -- this is a dummy call.
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketACLHandler)).
+			Queries("acl", "")
+		// PutBucketACL -- this is a dummy call.
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketACLHandler)).
+			Queries("acl", "")
+		// GetBucketCors - this is a dummy call.
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketCorsHandler)).
+			Queries("cors", "")
+		// PutBucketCors - this is a dummy call.
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketCorsHandler)).
+			Queries("cors", "")
+		// DeleteBucketCors - this is a dummy call.
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketCorsHandler)).
+			Queries("cors", "")
+		// GetBucketWebsiteHandler - this is a dummy call.
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketWebsiteHandler)).
+			Queries("website", "")
+		// GetBucketAccelerateHandler - this is a dummy call.
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketAccelerateHandler)).
+			Queries("accelerate", "")
+		// GetBucketRequestPaymentHandler - this is a dummy call.
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketRequestPaymentHandler)).
+			Queries("requestPayment", "")
+		// GetBucketLoggingHandler - this is a dummy call.
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketLoggingHandler)).
+			Queries("logging", "")
+
+		// GetBucketTaggingHandler
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketTaggingHandler)).
+			Queries("tagging", "")
+		// DeleteBucketWebsiteHandler
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketWebsiteHandler)).
+			Queries("website", "")
+		// DeleteBucketTaggingHandler
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketTaggingHandler)).
+			Queries("tagging", "")
+
+		// ListMultipartUploads
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListMultipartUploadsHandler)).
+			Queries("uploads", "")
+		// ListObjectsV2M
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListObjectsV2MHandler)).
+			Queries("list-type", "2", "metadata", "true")
+		// ListObjectsV2
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListObjectsV2Handler)).
+			Queries("list-type", "2")
+		// ListObjectVersions
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListObjectVersionsMHandler)).
+			Queries("versions", "", "metadata", "true")
+		// ListObjectVersions
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListObjectVersionsHandler)).
+			Queries("versions", "")
+		// GetBucketPolicyStatus
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketPolicyStatusHandler)).
+			Queries("policyStatus", "")
+		// PutBucketLifecycle
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketLifecycleHandler)).
+			Queries("lifecycle", "")
+		// PutBucketReplicationConfig
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketReplicationConfigHandler)).
+			Queries("replication", "")
+		// PutBucketEncryption
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketEncryptionHandler)).
+			Queries("encryption", "")
+
+		// PutBucketPolicy
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketPolicyHandler)).
+			Queries("policy", "")
+
+		// PutBucketObjectLockConfig
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketObjectLockConfigHandler)).
+			Queries("object-lock", "")
+		// PutBucketTaggingHandler
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketTaggingHandler)).
+			Queries("tagging", "")
+		// PutBucketVersioning
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketVersioningHandler)).
+			Queries("versioning", "")
+		// PutBucketNotification
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketNotificationHandler)).
+			Queries("notification", "")
+		// ResetBucketReplicationStart - MinIO extension API
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.ResetBucketReplicationStartHandler)).
+			Queries("replication-reset", "")
+
+		// PutBucket
+		router.Methods(http.MethodPut).
+			HandlerFunc(s3APIMiddleware(api.PutBucketHandler))
+		// HeadBucket
+		router.Methods(http.MethodHead).
+			HandlerFunc(s3APIMiddleware(api.HeadBucketHandler))
+		// PostPolicy
+		router.Methods(http.MethodPost).
+			MatcherFunc(func(r *http.Request, _ *mux.RouteMatch) bool {
+				return isRequestPostPolicySignatureV4(r)
+			}).
+			HandlerFunc(s3APIMiddleware(api.PostPolicyBucketHandler, traceHdrsS3HFlag))
+		// DeleteMultipleObjects
+		router.Methods(http.MethodPost).
+			HandlerFunc(s3APIMiddleware(api.DeleteMultipleObjectsHandler)).
+			Queries("delete", "")
+		// DeleteBucketPolicy
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketPolicyHandler)).
+			Queries("policy", "")
+		// DeleteBucketReplication
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketReplicationConfigHandler)).
+			Queries("replication", "")
+		// DeleteBucketLifecycle
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketLifecycleHandler)).
+			Queries("lifecycle", "")
+		// DeleteBucketEncryption
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketEncryptionHandler)).
+			Queries("encryption", "")
+		// DeleteBucket
+		router.Methods(http.MethodDelete).
+			HandlerFunc(s3APIMiddleware(api.DeleteBucketHandler))
+
+		// MinIO extension API for replication.
+		//
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketReplicationMetricsV2Handler)).
+			Queries("replication-metrics", "2")
+		// deprecated handler
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.GetBucketReplicationMetricsHandler)).
+			Queries("replication-metrics", "")
+
+		// ValidateBucketReplicationCreds
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ValidateBucketReplicationCredsHandler)).
+			Queries("replication-check", "")
+
+		// Register rejected bucket APIs
+		for _, r := range rejectedBucketAPIs {
+			router.Methods(r.methods...).
+				HandlerFunc(collectAPIStats(r.api, httpTraceAll(notImplementedHandler))).
+				Queries(r.queries...)
+		}
+
+		// S3 ListObjectsV1 (Legacy)
+		router.Methods(http.MethodGet).
+			HandlerFunc(s3APIMiddleware(api.ListObjectsV1Handler))
+	}
+
+	// Root operation
+
+	// ListenNotification
+	apiRouter.Methods(http.MethodGet).Path(SlashSeparator).
+		HandlerFunc(s3APIMiddleware(api.ListenNotificationHandler, noThrottleS3HFlag, traceHdrsS3HFlag)).
+		Queries("events", "{events:.*}")
+
+	// ListBuckets
+	apiRouter.Methods(http.MethodGet).Path(SlashSeparator).
+		HandlerFunc(s3APIMiddleware(api.ListBucketsHandler))
+
+	// S3 browser with signature v4 adds '//' for ListBuckets request, so rather
+	// than failing with UnknownAPIRequest we simply handle it for now.
+	apiRouter.Methods(http.MethodGet).Path(SlashSeparator + SlashSeparator).
+		HandlerFunc(s3APIMiddleware(api.ListBucketsHandler))
+
+	// If none of the routes match add default error handler routes
+	apiRouter.NotFoundHandler = collectAPIStats("notfound", httpTraceAll(errorResponseHandler))
+	apiRouter.MethodNotAllowedHandler = collectAPIStats("methodnotallowed", httpTraceAll(methodNotAllowedHandler("S3")))
+}
+
+// corsHandler handler for CORS (Cross Origin Resource Sharing)
+func corsHandler(handler http.Handler) http.Handler {
+	commonS3Headers := []string{
+		xhttp.Date,
+		xhttp.ETag,
+		xhttp.ServerInfo,
+		xhttp.Connection,
+		xhttp.AcceptRanges,
+		xhttp.ContentRange,
+		xhttp.ContentEncoding,
+		xhttp.ContentLength,
+		xhttp.ContentType,
+		xhttp.ContentDisposition,
+		xhttp.LastModified,
+		xhttp.ContentLanguage,
+		xhttp.CacheControl,
+		xhttp.RetryAfter,
+		xhttp.AmzBucketRegion,
+		xhttp.Expires,
+		"X-Amz*",
+		"x-amz*",
+		"*",
+	}
+	opts := cors.Options{
+		AllowOriginFunc: func(origin string) bool {
+			for _, allowedOrigin := range globalAPIConfig.getCorsAllowOrigins() {
+				if wildcard.MatchSimple(allowedOrigin, origin) {
+					return true
+				}
+			}
+			return false
+		},
+		AllowedMethods: []string{
+			http.MethodGet,
+			http.MethodPut,
+			http.MethodHead,
+			http.MethodPost,
+			http.MethodDelete,
+			http.MethodOptions,
+			http.MethodPatch,
+		},
+		AllowedHeaders:   commonS3Headers,
+		ExposedHeaders:   commonS3Headers,
+		AllowCredentials: true,
+	}
+	return cors.New(opts).Handler(handler)
+}

cmd/api-utils.go

@@ -0,0 +1,119 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"fmt"
+	"net/http"
+	"reflect"
+	"runtime"
+	"strings"
+)
+
+func shouldEscape(c byte) bool {
+	if 'A' <= c && c <= 'Z' || 'a' <= c && c <= 'z' || '0' <= c && c <= '9' {
+		return false
+	}
+
+	switch c {
+	case '-', '_', '.', '/', '*':
+		return false
+	}
+	return true
+}
+
+// s3URLEncode is based on Golang's url.QueryEscape() code,
+// while considering some S3 exceptions:
+//   - Avoid encoding '/' and '*'
+//   - Force encoding of '~'
+func s3URLEncode(s string) string {
+	spaceCount, hexCount := 0, 0
+	for i := 0; i < len(s); i++ {
+		c := s[i]
+		if shouldEscape(c) {
+			if c == ' ' {
+				spaceCount++
+			} else {
+				hexCount++
+			}
+		}
+	}
+
+	if spaceCount == 0 && hexCount == 0 {
+		return s
+	}
+
+	var buf [64]byte
+	var t []byte
+
+	required := len(s) + 2*hexCount
+	if required <= len(buf) {
+		t = buf[:required]
+	} else {
+		t = make([]byte, required)
+	}
+
+	if hexCount == 0 {
+		copy(t, s)
+		for i := 0; i < len(s); i++ {
+			if s[i] == ' ' {
+				t[i] = '+'
+			}
+		}
+		return string(t)
+	}
+
+	j := 0
+	for i := 0; i < len(s); i++ {
+		switch c := s[i]; {
+		case c == ' ':
+			t[j] = '+'
+			j++
+		case shouldEscape(c):
+			t[j] = '%'
+			t[j+1] = "0123456789ABCDEF"[c>>4]
+			t[j+2] = "0123456789ABCDEF"[c&15]
+			j += 3
+		default:
+			t[j] = s[i]
+			j++
+		}
+	}
+	return string(t)
+}
+
+// s3EncodeName encodes string in response when encodingType is specified in AWS S3 requests.
+func s3EncodeName(name, encodingType string) string {
+	if strings.ToLower(encodingType) == "url" {
+		return s3URLEncode(name)
+	}
+	return name
+}
+
+// getHandlerName returns the name of the handler function. It takes the type
+// name as a string to clean up the name retrieved via reflection. This function
+// only works correctly when the type is present in the cmd package.
+func getHandlerName(f http.HandlerFunc, cmdType string) string {
+	name := runtime.FuncForPC(reflect.ValueOf(f).Pointer()).Name()
+
+	packageName := fmt.Sprintf("github.com/minio/minio/cmd.%s.", cmdType)
+	name = strings.TrimPrefix(name, packageName)
+	name = strings.TrimSuffix(name, "Handler-fm")
+	name = strings.TrimSuffix(name, "-fm")
+	return name
+}

cmd/api-utils_test.go

@@ -0,0 +1,49 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"fmt"
+	"testing"
+)
+
+func TestS3EncodeName(t *testing.T) {
+	testCases := []struct {
+		inputText, encodingType, expectedOutput string
+	}{
+		{"a b", "", "a b"},
+		{"a b", "url", "a+b"},
+		{"p- ", "url", "p-+"},
+		{"p-%", "url", "p-%25"},
+		{"p/", "url", "p/"},
+		{"p/", "url", "p/"},
+		{"~user", "url", "%7Euser"},
+		{"*user", "url", "*user"},
+		{"user+password", "url", "user%2Bpassword"},
+		{"_user", "url", "_user"},
+		{"firstname.lastname", "url", "firstname.lastname"},
+	}
+	for i, testCase := range testCases {
+		t.Run(fmt.Sprintf("Test%d", i+1), func(t *testing.T) {
+			outputText := s3EncodeName(testCase.inputText, testCase.encodingType)
+			if testCase.expectedOutput != outputText {
+				t.Errorf("Expected `%s`, got `%s`", testCase.expectedOutput, outputText)
+			}
+		})
+	}
+}

cmd/auth-handler.go

@@ -0,0 +1,785 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"crypto/subtle"
+	"encoding/base64"
+	"encoding/hex"
+	"errors"
+	"io"
+	"mime"
+	"net/http"
+	"net/url"
+	"strconv"
+	"strings"
+	"sync/atomic"
+	"time"
+
+	"github.com/minio/minio/internal/auth"
+	objectlock "github.com/minio/minio/internal/bucket/object/lock"
+	"github.com/minio/minio/internal/etag"
+	"github.com/minio/minio/internal/hash"
+	xhttp "github.com/minio/minio/internal/http"
+	xjwt "github.com/minio/minio/internal/jwt"
+	"github.com/minio/minio/internal/logger"
+	"github.com/minio/minio/internal/mcontext"
+	"github.com/minio/pkg/v3/policy"
+)
+
+// Verify if request has JWT.
+func isRequestJWT(r *http.Request) bool {
+	return strings.HasPrefix(r.Header.Get(xhttp.Authorization), jwtAlgorithm)
+}
+
+// Verify if request has AWS Signature Version '4'.
+func isRequestSignatureV4(r *http.Request) bool {
+	return strings.HasPrefix(r.Header.Get(xhttp.Authorization), signV4Algorithm)
+}
+
+// Verify if request has AWS Signature Version '2'.
+func isRequestSignatureV2(r *http.Request) bool {
+	return (!strings.HasPrefix(r.Header.Get(xhttp.Authorization), signV4Algorithm) &&
+		strings.HasPrefix(r.Header.Get(xhttp.Authorization), signV2Algorithm))
+}
+
+// Verify if request has AWS PreSign Version '4'.
+func isRequestPresignedSignatureV4(r *http.Request) bool {
+	_, ok := r.Form[xhttp.AmzCredential]
+	return ok
+}
+
+// Verify request has AWS PreSign Version '2'.
+func isRequestPresignedSignatureV2(r *http.Request) bool {
+	_, ok := r.Form[xhttp.AmzAccessKeyID]
+	return ok
+}
+
+// Verify if request has AWS Post policy Signature Version '4'.
+func isRequestPostPolicySignatureV4(r *http.Request) bool {
+	mediaType, _, err := mime.ParseMediaType(r.Header.Get(xhttp.ContentType))
+	if err != nil {
+		return false
+	}
+	return mediaType == "multipart/form-data" && r.Method == http.MethodPost
+}
+
+// Verify if the request has AWS Streaming Signature Version '4'. This is only valid for 'PUT' operation.
+func isRequestSignStreamingV4(r *http.Request) bool {
+	return r.Header.Get(xhttp.AmzContentSha256) == streamingContentSHA256 &&
+		r.Method == http.MethodPut
+}
+
+// Verify if the request has AWS Streaming Signature Version '4'. This is only valid for 'PUT' operation.
+func isRequestSignStreamingTrailerV4(r *http.Request) bool {
+	return r.Header.Get(xhttp.AmzContentSha256) == streamingContentSHA256Trailer &&
+		r.Method == http.MethodPut
+}
+
+// Verify if the request has AWS Streaming Signature Version '4', with unsigned content and trailer.
+func isRequestUnsignedTrailerV4(r *http.Request) bool {
+	return r.Header.Get(xhttp.AmzContentSha256) == unsignedPayloadTrailer &&
+		r.Method == http.MethodPut
+}
+
+// Authorization type.
+//
+//go:generate stringer -type=authType -trimprefix=authType $GOFILE
+type authType int
+
+// List of all supported auth types.
+const (
+	authTypeUnknown authType = iota
+	authTypeAnonymous
+	authTypePresigned
+	authTypePresignedV2
+	authTypePostPolicy
+	authTypeStreamingSigned
+	authTypeSigned
+	authTypeSignedV2
+	authTypeJWT
+	authTypeSTS
+	authTypeStreamingSignedTrailer
+	authTypeStreamingUnsignedTrailer
+)
+
+// Get request authentication type.
+func getRequestAuthType(r *http.Request) (at authType) {
+	if r.URL != nil {
+		var err error
+		r.Form, err = url.ParseQuery(r.URL.RawQuery)
+		if err != nil {
+			authNLogIf(r.Context(), err)
+			return authTypeUnknown
+		}
+	}
+	if isRequestSignatureV2(r) {
+		return authTypeSignedV2
+	} else if isRequestPresignedSignatureV2(r) {
+		return authTypePresignedV2
+	} else if isRequestSignStreamingV4(r) {
+		return authTypeStreamingSigned
+	} else if isRequestSignStreamingTrailerV4(r) {
+		return authTypeStreamingSignedTrailer
+	} else if isRequestUnsignedTrailerV4(r) {
+		return authTypeStreamingUnsignedTrailer
+	} else if isRequestSignatureV4(r) {
+		return authTypeSigned
+	} else if isRequestPresignedSignatureV4(r) {
+		return authTypePresigned
+	} else if isRequestJWT(r) {
+		return authTypeJWT
+	} else if isRequestPostPolicySignatureV4(r) {
+		return authTypePostPolicy
+	} else if _, ok := r.Form[xhttp.Action]; ok {
+		return authTypeSTS
+	} else if _, ok := r.Header[xhttp.Authorization]; !ok {
+		return authTypeAnonymous
+	}
+	return authTypeUnknown
+}
+
+func validateAdminSignature(ctx context.Context, r *http.Request, region string) (auth.Credentials, bool, APIErrorCode) {
+	var cred auth.Credentials
+	var owner bool
+	s3Err := ErrAccessDenied
+	if _, ok := r.Header[xhttp.AmzContentSha256]; ok &&
+		getRequestAuthType(r) == authTypeSigned {
+		// Get credential information from the request.
+		cred, owner, s3Err = getReqAccessKeyV4(r, region, serviceS3)
+		if s3Err != ErrNone {
+			return cred, owner, s3Err
+		}
+
+		// we only support V4 (no presign) with auth body
+		s3Err = isReqAuthenticated(ctx, r, region, serviceS3)
+	}
+	if s3Err != ErrNone {
+		return cred, owner, s3Err
+	}
+
+	logger.GetReqInfo(ctx).Cred = cred
+	logger.GetReqInfo(ctx).Owner = owner
+	logger.GetReqInfo(ctx).Region = globalSite.Region()
+
+	return cred, owner, ErrNone
+}
+
+// checkAdminRequestAuth checks for authentication and authorization for the incoming
+// request. It only accepts V2 and V4 requests. Presigned, JWT and anonymous requests
+// are automatically rejected.
+func checkAdminRequestAuth(ctx context.Context, r *http.Request, action policy.AdminAction, region string) (auth.Credentials, APIErrorCode) {
+	cred, owner, s3Err := validateAdminSignature(ctx, r, region)
+	if s3Err != ErrNone {
+		return cred, s3Err
+	}
+	if globalIAMSys.IsAllowed(policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          policy.Action(action),
+		ConditionValues: getConditionValues(r, "", cred),
+		IsOwner:         owner,
+		Claims:          cred.Claims,
+	}) {
+		// Request is allowed return the appropriate access key.
+		return cred, ErrNone
+	}
+
+	return cred, ErrAccessDenied
+}
+
+// Fetch the security token set by the client.
+func getSessionToken(r *http.Request) (token string) {
+	token = r.Header.Get(xhttp.AmzSecurityToken)
+	if token != "" {
+		return token
+	}
+	return r.Form.Get(xhttp.AmzSecurityToken)
+}
+
+// Fetch claims in the security token returned by the client, doesn't return
+// errors - upon errors the returned claims map will be empty.
+func mustGetClaimsFromToken(r *http.Request) map[string]interface{} {
+	claims, _ := getClaimsFromToken(getSessionToken(r))
+	return claims
+}
+
+func getClaimsFromTokenWithSecret(token, secret string) (*xjwt.MapClaims, error) {
+	// JWT token for x-amz-security-token is signed with admin
+	// secret key, temporary credentials become invalid if
+	// server admin credentials change. This is done to ensure
+	// that clients cannot decode the token using the temp
+	// secret keys and generate an entirely new claim by essentially
+	// hijacking the policies. We need to make sure that this is
+	// based on admin credential such that token cannot be decoded
+	// on the client side and is treated like an opaque value.
+	claims, err := auth.ExtractClaims(token, secret)
+	if err != nil {
+		if subtle.ConstantTimeCompare([]byte(secret), []byte(globalActiveCred.SecretKey)) == 1 {
+			return nil, errAuthentication
+		}
+		claims, err = auth.ExtractClaims(token, globalActiveCred.SecretKey)
+		if err != nil {
+			return nil, errAuthentication
+		}
+	}
+
+	// If AuthZPlugin is set, return without any further checks.
+	if newGlobalAuthZPluginFn() != nil {
+		return claims, nil
+	}
+
+	// Check if a session policy is set. If so, decode it here.
+	sp, spok := claims.Lookup(policy.SessionPolicyName)
+	if spok {
+		// Looks like subpolicy is set and is a string, if set then its
+		// base64 encoded, decode it. Decoding fails reject such
+		// requests.
+		spBytes, err := base64.StdEncoding.DecodeString(sp)
+		if err != nil {
+			// Base64 decoding fails, we should log to indicate
+			// something is malforming the request sent by client.
+			authNLogIf(GlobalContext, err, logger.ErrorKind)
+			return nil, errAuthentication
+		}
+		claims.MapClaims[sessionPolicyNameExtracted] = string(spBytes)
+	}
+
+	return claims, nil
+}
+
+// Fetch claims in the security token returned by the client.
+func getClaimsFromToken(token string) (map[string]interface{}, error) {
+	jwtClaims, err := getClaimsFromTokenWithSecret(token, globalActiveCred.SecretKey)
+	if err != nil {
+		return nil, err
+	}
+	return jwtClaims.Map(), nil
+}
+
+// Fetch claims in the security token returned by the client and validate the token.
+func checkClaimsFromToken(r *http.Request, cred auth.Credentials) (map[string]interface{}, APIErrorCode) {
+	token := getSessionToken(r)
+	if token != "" && cred.AccessKey == "" {
+		// x-amz-security-token is not allowed for anonymous access.
+		return nil, ErrNoAccessKey
+	}
+
+	if token == "" && cred.IsTemp() && !cred.IsServiceAccount() {
+		// Temporary credentials should always have x-amz-security-token
+		return nil, ErrInvalidToken
+	}
+
+	if token != "" && !cred.IsTemp() {
+		// x-amz-security-token should not present for static credentials.
+		return nil, ErrInvalidToken
+	}
+
+	if !cred.IsServiceAccount() && cred.IsTemp() && subtle.ConstantTimeCompare([]byte(token), []byte(cred.SessionToken)) != 1 {
+		// validate token for temporary credentials only.
+		return nil, ErrInvalidToken
+	}
+
+	// Expired credentials must return error right away.
+	if cred.IsTemp() && cred.IsExpired() {
+		return nil, toAPIErrorCode(r.Context(), errInvalidAccessKeyID)
+	}
+	secret := globalActiveCred.SecretKey
+	if globalSiteReplicationSys.isEnabled() && cred.AccessKey != siteReplicatorSvcAcc {
+		nsecret, err := getTokenSigningKey()
+		if err != nil {
+			return nil, toAPIErrorCode(r.Context(), err)
+		}
+		// sign root's temporary accounts also with site replicator creds
+		if cred.ParentUser != globalActiveCred.AccessKey || cred.IsTemp() {
+			secret = nsecret
+		}
+	}
+	if cred.IsServiceAccount() {
+		token = cred.SessionToken
+		secret = cred.SecretKey
+	}
+
+	if token != "" {
+		claims, err := getClaimsFromTokenWithSecret(token, secret)
+		if err != nil {
+			return nil, toAPIErrorCode(r.Context(), err)
+		}
+		return claims.Map(), ErrNone
+	}
+
+	claims := xjwt.NewMapClaims()
+	return claims.Map(), ErrNone
+}
+
+// Check request auth type verifies the incoming http request
+//   - validates the request signature
+//   - validates the policy action if anonymous tests bucket policies if any,
+//     for authenticated requests validates IAM policies.
+//
+// returns APIErrorCode if any to be replied to the client.
+func checkRequestAuthType(ctx context.Context, r *http.Request, action policy.Action, bucketName, objectName string) (s3Err APIErrorCode) {
+	logger.GetReqInfo(ctx).BucketName = bucketName
+	logger.GetReqInfo(ctx).ObjectName = objectName
+
+	_, _, s3Err = checkRequestAuthTypeCredential(ctx, r, action)
+	return s3Err
+}
+
+// checkRequestAuthTypeWithVID is similar to checkRequestAuthType
+// passes versionID additionally.
+func checkRequestAuthTypeWithVID(ctx context.Context, r *http.Request, action policy.Action, bucketName, objectName, versionID string) (s3Err APIErrorCode) {
+	logger.GetReqInfo(ctx).BucketName = bucketName
+	logger.GetReqInfo(ctx).ObjectName = objectName
+	logger.GetReqInfo(ctx).VersionID = versionID
+
+	_, _, s3Err = checkRequestAuthTypeCredential(ctx, r, action)
+	return s3Err
+}
+
+func authenticateRequest(ctx context.Context, r *http.Request, action policy.Action) (s3Err APIErrorCode) {
+	if logger.GetReqInfo(ctx) == nil {
+		bugLogIf(ctx, errors.New("unexpected context.Context does not have a logger.ReqInfo"), logger.ErrorKind)
+		return ErrAccessDenied
+	}
+
+	var cred auth.Credentials
+	var owner bool
+	switch getRequestAuthType(r) {
+	case authTypeUnknown, authTypeStreamingSigned, authTypeStreamingSignedTrailer, authTypeStreamingUnsignedTrailer:
+		return ErrSignatureVersionNotSupported
+	case authTypePresignedV2, authTypeSignedV2:
+		if s3Err = isReqAuthenticatedV2(r); s3Err != ErrNone {
+			return s3Err
+		}
+		cred, owner, s3Err = getReqAccessKeyV2(r)
+	case authTypeSigned, authTypePresigned:
+		region := globalSite.Region()
+		switch action {
+		case policy.GetBucketLocationAction, policy.ListAllMyBucketsAction:
+			region = ""
+		}
+		if s3Err = isReqAuthenticated(ctx, r, region, serviceS3); s3Err != ErrNone {
+			return s3Err
+		}
+		cred, owner, s3Err = getReqAccessKeyV4(r, region, serviceS3)
+	}
+	if s3Err != ErrNone {
+		return s3Err
+	}
+
+	logger.GetReqInfo(ctx).Cred = cred
+	logger.GetReqInfo(ctx).Owner = owner
+	logger.GetReqInfo(ctx).Region = globalSite.Region()
+
+	// region is valid only for CreateBucketAction.
+	var region string
+	if action == policy.CreateBucketAction {
+		// To extract region from XML in request body, get copy of request body.
+		payload, err := io.ReadAll(io.LimitReader(r.Body, maxLocationConstraintSize))
+		if err != nil {
+			authZLogIf(ctx, err, logger.ErrorKind)
+			return ErrMalformedXML
+		}
+
+		// Populate payload to extract location constraint.
+		r.Body = io.NopCloser(bytes.NewReader(payload))
+		region, s3Err = parseLocationConstraint(r)
+		if s3Err != ErrNone {
+			return s3Err
+		}
+
+		// Populate payload again to handle it in HTTP handler.
+		r.Body = io.NopCloser(bytes.NewReader(payload))
+	}
+
+	logger.GetReqInfo(ctx).Region = region
+
+	return s3Err
+}
+
+func authorizeRequest(ctx context.Context, r *http.Request, action policy.Action) (s3Err APIErrorCode) {
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return ErrAccessDenied
+	}
+
+	cred := reqInfo.Cred
+	owner := reqInfo.Owner
+	region := reqInfo.Region
+	bucket := reqInfo.BucketName
+	object := reqInfo.ObjectName
+	versionID := reqInfo.VersionID
+
+	if action != policy.ListAllMyBucketsAction && cred.AccessKey == "" {
+		// Anonymous checks are not meant for ListAllBuckets action
+		if globalPolicySys.IsAllowed(policy.BucketPolicyArgs{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          action,
+			BucketName:      bucket,
+			ConditionValues: getConditionValues(r, region, auth.AnonymousCredentials),
+			IsOwner:         false,
+			ObjectName:      object,
+		}) {
+			// Request is allowed return the appropriate access key.
+			return ErrNone
+		}
+
+		if action == policy.ListBucketVersionsAction {
+			// In AWS S3 s3:ListBucket permission is same as s3:ListBucketVersions permission
+			// verify as a fallback.
+			if globalPolicySys.IsAllowed(policy.BucketPolicyArgs{
+				AccountName:     cred.AccessKey,
+				Groups:          cred.Groups,
+				Action:          policy.ListBucketAction,
+				BucketName:      bucket,
+				ConditionValues: getConditionValues(r, region, auth.AnonymousCredentials),
+				IsOwner:         false,
+				ObjectName:      object,
+			}) {
+				// Request is allowed return the appropriate access key.
+				return ErrNone
+			}
+		}
+
+		return ErrAccessDenied
+	}
+	if action == policy.DeleteObjectAction && versionID != "" {
+		if !globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.Action(policy.DeleteObjectVersionAction),
+			BucketName:      bucket,
+			ConditionValues: getConditionValues(r, "", cred),
+			ObjectName:      object,
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+			DenyOnly:        true,
+		}) { // Request is not allowed if Deny action on DeleteObjectVersionAction
+			return ErrAccessDenied
+		}
+	}
+	if globalIAMSys.IsAllowed(policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          action,
+		BucketName:      bucket,
+		ConditionValues: getConditionValues(r, "", cred),
+		ObjectName:      object,
+		IsOwner:         owner,
+		Claims:          cred.Claims,
+	}) {
+		// Request is allowed return the appropriate access key.
+		return ErrNone
+	}
+
+	if action == policy.ListBucketVersionsAction {
+		// In AWS S3 s3:ListBucket permission is same as s3:ListBucketVersions permission
+		// verify as a fallback.
+		if globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.ListBucketAction,
+			BucketName:      bucket,
+			ConditionValues: getConditionValues(r, "", cred),
+			ObjectName:      object,
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+		}) {
+			// Request is allowed return the appropriate access key.
+			return ErrNone
+		}
+	}
+
+	return ErrAccessDenied
+}
+
+// Check request auth type verifies the incoming http request
+//   - validates the request signature
+//   - validates the policy action if anonymous tests bucket policies if any,
+//     for authenticated requests validates IAM policies.
+//
+// returns APIErrorCode if any to be replied to the client.
+// Additionally returns the accessKey used in the request, and if this request is by an admin.
+func checkRequestAuthTypeCredential(ctx context.Context, r *http.Request, action policy.Action) (cred auth.Credentials, owner bool, s3Err APIErrorCode) {
+	s3Err = authenticateRequest(ctx, r, action)
+	reqInfo := logger.GetReqInfo(ctx)
+	if reqInfo == nil {
+		return cred, owner, ErrAccessDenied
+	}
+
+	cred = reqInfo.Cred
+	owner = reqInfo.Owner
+	if s3Err != ErrNone {
+		return cred, owner, s3Err
+	}
+
+	return cred, owner, authorizeRequest(ctx, r, action)
+}
+
+// Verify if request has valid AWS Signature Version '2'.
+func isReqAuthenticatedV2(r *http.Request) (s3Error APIErrorCode) {
+	if isRequestSignatureV2(r) {
+		return doesSignV2Match(r)
+	}
+	return doesPresignV2SignatureMatch(r)
+}
+
+func reqSignatureV4Verify(r *http.Request, region string, stype serviceType) (s3Error APIErrorCode) {
+	sha256sum := getContentSha256Cksum(r, stype)
+	switch {
+	case isRequestSignatureV4(r):
+		return doesSignatureMatch(sha256sum, r, region, stype)
+	case isRequestPresignedSignatureV4(r):
+		return doesPresignedSignatureMatch(sha256sum, r, region, stype)
+	default:
+		return ErrAccessDenied
+	}
+}
+
+// Verify if request has valid AWS Signature Version '4'.
+func isReqAuthenticated(ctx context.Context, r *http.Request, region string, stype serviceType) (s3Error APIErrorCode) {
+	if errCode := reqSignatureV4Verify(r, region, stype); errCode != ErrNone {
+		return errCode
+	}
+
+	clientETag, err := etag.FromContentMD5(r.Header)
+	if err != nil {
+		return ErrInvalidDigest
+	}
+
+	// Extract either 'X-Amz-Content-Sha256' header or 'X-Amz-Content-Sha256' query parameter (if V4 presigned)
+	// Do not verify 'X-Amz-Content-Sha256' if skipSHA256.
+	var contentSHA256 []byte
+	if skipSHA256 := skipContentSha256Cksum(r); !skipSHA256 && isRequestPresignedSignatureV4(r) {
+		if sha256Sum, ok := r.Form[xhttp.AmzContentSha256]; ok && len(sha256Sum) > 0 {
+			contentSHA256, err = hex.DecodeString(sha256Sum[0])
+			if err != nil {
+				return ErrContentSHA256Mismatch
+			}
+		}
+	} else if _, ok := r.Header[xhttp.AmzContentSha256]; !skipSHA256 && ok {
+		contentSHA256, err = hex.DecodeString(r.Header.Get(xhttp.AmzContentSha256))
+		if err != nil || len(contentSHA256) == 0 {
+			return ErrContentSHA256Mismatch
+		}
+	}
+
+	// Verify 'Content-Md5' and/or 'X-Amz-Content-Sha256' if present.
+	// The verification happens implicit during reading.
+	reader, err := hash.NewReader(ctx, r.Body, -1, clientETag.String(), hex.EncodeToString(contentSHA256), -1)
+	if err != nil {
+		return toAPIErrorCode(ctx, err)
+	}
+	r.Body = reader
+	return ErrNone
+}
+
+// List of all support S3 auth types.
+var supportedS3AuthTypes = map[authType]struct{}{
+	authTypeAnonymous:                {},
+	authTypePresigned:                {},
+	authTypePresignedV2:              {},
+	authTypeSigned:                   {},
+	authTypeSignedV2:                 {},
+	authTypePostPolicy:               {},
+	authTypeStreamingSigned:          {},
+	authTypeStreamingSignedTrailer:   {},
+	authTypeStreamingUnsignedTrailer: {},
+}
+
+// Validate if the authType is valid and supported.
+func isSupportedS3AuthType(aType authType) bool {
+	_, ok := supportedS3AuthTypes[aType]
+	return ok
+}
+
+// setAuthMiddleware to validate authorization header for the incoming request.
+func setAuthMiddleware(h http.Handler) http.Handler {
+	// handler for validating incoming authorization headers.
+	return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		tc, ok := r.Context().Value(mcontext.ContextTraceKey).(*mcontext.TraceCtxt)
+
+		aType := getRequestAuthType(r)
+		switch aType {
+		case authTypeSigned, authTypeSignedV2, authTypeStreamingSigned, authTypeStreamingSignedTrailer:
+			// Verify if date headers are set, if not reject the request
+			amzDate, errCode := parseAmzDateHeader(r)
+			if errCode != ErrNone {
+				if ok {
+					tc.FuncName = "handler.Auth"
+					tc.ResponseRecorder.LogErrBody = true
+				}
+
+				// All our internal APIs are sensitive towards Date
+				// header, for all requests where Date header is not
+				// present we will reject such clients.
+				defer logger.AuditLog(r.Context(), w, r, mustGetClaimsFromToken(r))
+				writeErrorResponse(r.Context(), w, errorCodes.ToAPIErr(errCode), r.URL)
+				atomic.AddUint64(&globalHTTPStats.rejectedRequestsTime, 1)
+				return
+			}
+			// Verify if the request date header is shifted by less than globalMaxSkewTime parameter in the past
+			// or in the future, reject request otherwise.
+			curTime := UTCNow()
+			if curTime.Sub(amzDate) > globalMaxSkewTime || amzDate.Sub(curTime) > globalMaxSkewTime {
+				if ok {
+					tc.FuncName = "handler.Auth"
+					tc.ResponseRecorder.LogErrBody = true
+				}
+
+				defer logger.AuditLog(r.Context(), w, r, mustGetClaimsFromToken(r))
+				writeErrorResponse(r.Context(), w, errorCodes.ToAPIErr(ErrRequestTimeTooSkewed), r.URL)
+				atomic.AddUint64(&globalHTTPStats.rejectedRequestsTime, 1)
+				return
+			}
+			h.ServeHTTP(w, r)
+			return
+		case authTypeJWT, authTypeSTS:
+			h.ServeHTTP(w, r)
+			return
+		default:
+			if isSupportedS3AuthType(aType) {
+				h.ServeHTTP(w, r)
+				return
+			}
+		}
+
+		if ok {
+			tc.FuncName = "handler.Auth"
+			tc.ResponseRecorder.LogErrBody = true
+		}
+
+		defer logger.AuditLog(r.Context(), w, r, mustGetClaimsFromToken(r))
+		writeErrorResponse(r.Context(), w, errorCodes.ToAPIErr(ErrSignatureVersionNotSupported), r.URL)
+		atomic.AddUint64(&globalHTTPStats.rejectedRequestsAuth, 1)
+	})
+}
+
+func isPutRetentionAllowed(bucketName, objectName string, retDays int, retDate time.Time, retMode objectlock.RetMode, byPassSet bool, r *http.Request, cred auth.Credentials, owner bool) (s3Err APIErrorCode) {
+	var retSet bool
+	if cred.AccessKey == "" {
+		return ErrAccessDenied
+	}
+
+	conditions := getConditionValues(r, "", cred)
+	conditions["object-lock-mode"] = []string{string(retMode)}
+	conditions["object-lock-retain-until-date"] = []string{retDate.UTC().Format(time.RFC3339)}
+	if retDays > 0 {
+		conditions["object-lock-remaining-retention-days"] = []string{strconv.Itoa(retDays)}
+	}
+	if retMode == objectlock.RetGovernance && byPassSet {
+		byPassSet = globalIAMSys.IsAllowed(policy.Args{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          policy.BypassGovernanceRetentionAction,
+			BucketName:      bucketName,
+			ObjectName:      objectName,
+			ConditionValues: conditions,
+			IsOwner:         owner,
+			Claims:          cred.Claims,
+		})
+	}
+	if globalIAMSys.IsAllowed(policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          policy.PutObjectRetentionAction,
+		BucketName:      bucketName,
+		ConditionValues: conditions,
+		ObjectName:      objectName,
+		IsOwner:         owner,
+		Claims:          cred.Claims,
+	}) {
+		retSet = true
+	}
+	if byPassSet || retSet {
+		return ErrNone
+	}
+	return ErrAccessDenied
+}
+
+// isPutActionAllowed - check if PUT operation is allowed on the resource, this
+// call verifies bucket policies and IAM policies, supports multi user
+// checks etc.
+func isPutActionAllowed(ctx context.Context, atype authType, bucketName, objectName string, r *http.Request, action policy.Action) (s3Err APIErrorCode) {
+	var cred auth.Credentials
+	var owner bool
+	region := globalSite.Region()
+	switch atype {
+	case authTypeUnknown:
+		return ErrSignatureVersionNotSupported
+	case authTypeSignedV2, authTypePresignedV2:
+		cred, owner, s3Err = getReqAccessKeyV2(r)
+	case authTypeStreamingSigned, authTypePresigned, authTypeSigned, authTypeStreamingSignedTrailer:
+		cred, owner, s3Err = getReqAccessKeyV4(r, region, serviceS3)
+	case authTypeStreamingUnsignedTrailer:
+		cred, owner, s3Err = getReqAccessKeyV4(r, region, serviceS3)
+		if s3Err == ErrMissingFields {
+			// Could be anonymous. cred + owner is zero value.
+			s3Err = ErrNone
+		}
+	}
+	if s3Err != ErrNone {
+		return s3Err
+	}
+
+	logger.GetReqInfo(ctx).Cred = cred
+	logger.GetReqInfo(ctx).Owner = owner
+	logger.GetReqInfo(ctx).Region = region
+
+	// Do not check for PutObjectRetentionAction permission,
+	// if mode and retain until date are not set.
+	// Can happen when bucket has default lock config set
+	if action == policy.PutObjectRetentionAction &&
+		r.Header.Get(xhttp.AmzObjectLockMode) == "" &&
+		r.Header.Get(xhttp.AmzObjectLockRetainUntilDate) == "" {
+		return ErrNone
+	}
+
+	if cred.AccessKey == "" {
+		if globalPolicySys.IsAllowed(policy.BucketPolicyArgs{
+			AccountName:     cred.AccessKey,
+			Groups:          cred.Groups,
+			Action:          action,
+			BucketName:      bucketName,
+			ConditionValues: getConditionValues(r, "", auth.AnonymousCredentials),
+			IsOwner:         false,
+			ObjectName:      objectName,
+		}) {
+			return ErrNone
+		}
+		return ErrAccessDenied
+	}
+
+	if globalIAMSys.IsAllowed(policy.Args{
+		AccountName:     cred.AccessKey,
+		Groups:          cred.Groups,
+		Action:          action,
+		BucketName:      bucketName,
+		ConditionValues: getConditionValues(r, "", cred),
+		ObjectName:      objectName,
+		IsOwner:         owner,
+		Claims:          cred.Claims,
+	}) {
+		return ErrNone
+	}
+	return ErrAccessDenied
+}

cmd/auth-handler_test.go

@@ -0,0 +1,501 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"io"
+	"net/http"
+	"net/url"
+	"os"
+	"testing"
+	"time"
+
+	"github.com/minio/minio/internal/auth"
+	"github.com/minio/pkg/v3/policy"
+)
+
+type nullReader struct{}
+
+func (r *nullReader) Read(b []byte) (int, error) {
+	return len(b), nil
+}
+
+// Test get request auth type.
+func TestGetRequestAuthType(t *testing.T) {
+	type testCase struct {
+		req   *http.Request
+		authT authType
+	}
+	nopCloser := io.NopCloser(io.LimitReader(&nullReader{}, 1024))
+	testCases := []testCase{
+		// Test case - 1
+		// Check for generic signature v4 header.
+		{
+			req: &http.Request{
+				URL: &url.URL{
+					Host:   "127.0.0.1:9000",
+					Scheme: httpScheme,
+					Path:   SlashSeparator,
+				},
+				Header: http.Header{
+					"Authorization":        []string{"AWS4-HMAC-SHA256 <cred_string>"},
+					"X-Amz-Content-Sha256": []string{streamingContentSHA256},
+					"Content-Encoding":     []string{streamingContentEncoding},
+				},
+				Method: http.MethodPut,
+				Body:   nopCloser,
+			},
+			authT: authTypeStreamingSigned,
+		},
+		// Test case - 2
+		// Check for JWT header.
+		{
+			req: &http.Request{
+				URL: &url.URL{
+					Host:   "127.0.0.1:9000",
+					Scheme: httpScheme,
+					Path:   SlashSeparator,
+				},
+				Header: http.Header{
+					"Authorization": []string{"Bearer 12313123"},
+				},
+			},
+			authT: authTypeJWT,
+		},
+		// Test case - 3
+		// Empty authorization header.
+		{
+			req: &http.Request{
+				URL: &url.URL{
+					Host:   "127.0.0.1:9000",
+					Scheme: httpScheme,
+					Path:   SlashSeparator,
+				},
+				Header: http.Header{
+					"Authorization": []string{""},
+				},
+			},
+			authT: authTypeUnknown,
+		},
+		// Test case - 4
+		// Check for presigned.
+		{
+			req: &http.Request{
+				URL: &url.URL{
+					Host:     "127.0.0.1:9000",
+					Scheme:   httpScheme,
+					Path:     SlashSeparator,
+					RawQuery: "X-Amz-Credential=EXAMPLEINVALIDEXAMPL%2Fs3%2F20160314%2Fus-east-1",
+				},
+			},
+			authT: authTypePresigned,
+		},
+		// Test case - 5
+		// Check for post policy.
+		{
+			req: &http.Request{
+				URL: &url.URL{
+					Host:   "127.0.0.1:9000",
+					Scheme: httpScheme,
+					Path:   SlashSeparator,
+				},
+				Header: http.Header{
+					"Content-Type": []string{"multipart/form-data"},
+				},
+				Method: http.MethodPost,
+				Body:   nopCloser,
+			},
+			authT: authTypePostPolicy,
+		},
+	}
+
+	// .. Tests all request auth type.
+	for i, testc := range testCases {
+		authT := getRequestAuthType(testc.req)
+		if authT != testc.authT {
+			t.Errorf("Test %d: Expected %d, got %d", i+1, testc.authT, authT)
+		}
+	}
+}
+
+// Test all s3 supported auth types.
+func TestS3SupportedAuthType(t *testing.T) {
+	type testCase struct {
+		authT authType
+		pass  bool
+	}
+	// List of all valid and invalid test cases.
+	testCases := []testCase{
+		// Test 1 - supported s3 type anonymous.
+		{
+			authT: authTypeAnonymous,
+			pass:  true,
+		},
+		// Test 2 - supported s3 type presigned.
+		{
+			authT: authTypePresigned,
+			pass:  true,
+		},
+		// Test 3 - supported s3 type signed.
+		{
+			authT: authTypeSigned,
+			pass:  true,
+		},
+		// Test 4 - supported s3 type with post policy.
+		{
+			authT: authTypePostPolicy,
+			pass:  true,
+		},
+		// Test 5 - supported s3 type with streaming signed.
+		{
+			authT: authTypeStreamingSigned,
+			pass:  true,
+		},
+		// Test 6 - supported s3 type with signature v2.
+		{
+			authT: authTypeSignedV2,
+			pass:  true,
+		},
+		// Test 7 - supported s3 type with presign v2.
+		{
+			authT: authTypePresignedV2,
+			pass:  true,
+		},
+		// Test 8 - JWT is not supported s3 type.
+		{
+			authT: authTypeJWT,
+			pass:  false,
+		},
+		// Test 9 - unknown auth header is not supported s3 type.
+		{
+			authT: authTypeUnknown,
+			pass:  false,
+		},
+		// Test 10 - some new auth type is not supported s3 type.
+		{
+			authT: authType(9),
+			pass:  false,
+		},
+	}
+	// Validate all the test cases.
+	for i, tt := range testCases {
+		ok := isSupportedS3AuthType(tt.authT)
+		if ok != tt.pass {
+			t.Errorf("Test %d:, Expected %t, got %t", i+1, tt.pass, ok)
+		}
+	}
+}
+
+func TestIsRequestPresignedSignatureV2(t *testing.T) {
+	testCases := []struct {
+		inputQueryKey   string
+		inputQueryValue string
+		expectedResult  bool
+	}{
+		// Test case - 1.
+		// Test case with query key "AWSAccessKeyId" set.
+		{"", "", false},
+		// Test case - 2.
+		{"AWSAccessKeyId", "", true},
+		// Test case - 3.
+		{"X-Amz-Content-Sha256", "", false},
+	}
+
+	for i, testCase := range testCases {
+		// creating an input HTTP request.
+		// Only the query parameters are relevant for this particular test.
+		inputReq, err := http.NewRequest(http.MethodGet, "http://example.com", nil)
+		if err != nil {
+			t.Fatalf("Error initializing input HTTP request: %v", err)
+		}
+		q := inputReq.URL.Query()
+		q.Add(testCase.inputQueryKey, testCase.inputQueryValue)
+		inputReq.URL.RawQuery = q.Encode()
+		inputReq.ParseForm()
+
+		actualResult := isRequestPresignedSignatureV2(inputReq)
+		if testCase.expectedResult != actualResult {
+			t.Errorf("Test %d: Expected the result to `%v`, but instead got `%v`", i+1, testCase.expectedResult, actualResult)
+		}
+	}
+}
+
+// TestIsRequestPresignedSignatureV4 - Test validates the logic for presign signature version v4 detection.
+func TestIsRequestPresignedSignatureV4(t *testing.T) {
+	testCases := []struct {
+		inputQueryKey   string
+		inputQueryValue string
+		expectedResult  bool
+	}{
+		// Test case - 1.
+		// Test case with query key ""X-Amz-Credential" set.
+		{"", "", false},
+		// Test case - 2.
+		{"X-Amz-Credential", "", true},
+		// Test case - 3.
+		{"X-Amz-Content-Sha256", "", false},
+	}
+
+	for i, testCase := range testCases {
+		// creating an input HTTP request.
+		// Only the query parameters are relevant for this particular test.
+		inputReq, err := http.NewRequest(http.MethodGet, "http://example.com", nil)
+		if err != nil {
+			t.Fatalf("Error initializing input HTTP request: %v", err)
+		}
+		q := inputReq.URL.Query()
+		q.Add(testCase.inputQueryKey, testCase.inputQueryValue)
+		inputReq.URL.RawQuery = q.Encode()
+		inputReq.ParseForm()
+
+		actualResult := isRequestPresignedSignatureV4(inputReq)
+		if testCase.expectedResult != actualResult {
+			t.Errorf("Test %d: Expected the result to `%v`, but instead got `%v`", i+1, testCase.expectedResult, actualResult)
+		}
+	}
+}
+
+// Provides a fully populated http request instance, fails otherwise.
+func mustNewRequest(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req, err := newTestRequest(method, urlStr, contentLength, body)
+	if err != nil {
+		t.Fatalf("Unable to initialize new http request %s", err)
+	}
+	return req
+}
+
+// This is similar to mustNewRequest but additionally the request
+// is signed with AWS Signature V4, fails if not able to do so.
+func mustNewSignedRequest(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	cred := globalActiveCred
+	if err := signRequestV4(req, cred.AccessKey, cred.SecretKey); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+// This is similar to mustNewRequest but additionally the request
+// is signed with AWS Signature V2, fails if not able to do so.
+func mustNewSignedV2Request(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	cred := globalActiveCred
+	if err := signRequestV2(req, cred.AccessKey, cred.SecretKey); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+// This is similar to mustNewRequest but additionally the request
+// is presigned with AWS Signature V2, fails if not able to do so.
+func mustNewPresignedV2Request(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	cred := globalActiveCred
+	if err := preSignV2(req, cred.AccessKey, cred.SecretKey, time.Now().Add(10*time.Minute).Unix()); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+// This is similar to mustNewRequest but additionally the request
+// is presigned with AWS Signature V4, fails if not able to do so.
+func mustNewPresignedRequest(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	cred := globalActiveCred
+	if err := preSignV4(req, cred.AccessKey, cred.SecretKey, time.Now().Add(10*time.Minute).Unix()); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+func mustNewSignedShortMD5Request(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	req.Header.Set("Content-Md5", "invalid-digest")
+	cred := globalActiveCred
+	if err := signRequestV4(req, cred.AccessKey, cred.SecretKey); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+func mustNewSignedEmptyMD5Request(method string, urlStr string, contentLength int64, body io.ReadSeeker, t *testing.T) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	req.Header.Set("Content-Md5", "")
+	cred := globalActiveCred
+	if err := signRequestV4(req, cred.AccessKey, cred.SecretKey); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+func mustNewSignedBadMD5Request(method string, urlStr string, contentLength int64,
+	body io.ReadSeeker, t *testing.T,
+) *http.Request {
+	req := mustNewRequest(method, urlStr, contentLength, body, t)
+	req.Header.Set("Content-Md5", "YWFhYWFhYWFhYWFhYWFhCg==")
+	cred := globalActiveCred
+	if err := signRequestV4(req, cred.AccessKey, cred.SecretKey); err != nil {
+		t.Fatalf("Unable to initialized new signed http request %s", err)
+	}
+	return req
+}
+
+// Tests is requested authenticated function, tests replies for s3 errors.
+func TestIsReqAuthenticated(t *testing.T) {
+	ctx, cancel := context.WithCancel(GlobalContext)
+	defer cancel()
+
+	objLayer, fsDir, err := prepareFS(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer os.RemoveAll(fsDir)
+	if err = newTestConfig(globalMinioDefaultRegion, objLayer); err != nil {
+		t.Fatalf("unable initialize config file, %s", err)
+	}
+
+	initAllSubsystems(ctx)
+
+	initConfigSubsystem(ctx, objLayer)
+
+	creds, err := auth.CreateCredentials("myuser", "mypassword")
+	if err != nil {
+		t.Fatalf("unable create credential, %s", err)
+	}
+
+	globalActiveCred = creds
+
+	globalIAMSys.Init(ctx, objLayer, globalEtcdClient, 2*time.Second)
+
+	// List of test cases for validating http request authentication.
+	testCases := []struct {
+		req     *http.Request
+		s3Error APIErrorCode
+	}{
+		// When request is unsigned, access denied is returned.
+		{mustNewRequest(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrAccessDenied},
+		// Empty Content-Md5 header.
+		{mustNewSignedEmptyMD5Request(http.MethodPut, "http://127.0.0.1:9000/", 5, bytes.NewReader([]byte("hello")), t), ErrInvalidDigest},
+		// Short Content-Md5 header.
+		{mustNewSignedShortMD5Request(http.MethodPut, "http://127.0.0.1:9000/", 5, bytes.NewReader([]byte("hello")), t), ErrInvalidDigest},
+		// When request is properly signed, but has bad Content-MD5 header.
+		{mustNewSignedBadMD5Request(http.MethodPut, "http://127.0.0.1:9000/", 5, bytes.NewReader([]byte("hello")), t), ErrBadDigest},
+		// When request is properly signed, error is none.
+		{mustNewSignedRequest(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrNone},
+	}
+
+	// Validates all testcases.
+	for i, testCase := range testCases {
+		s3Error := isReqAuthenticated(ctx, testCase.req, globalSite.Region(), serviceS3)
+		if s3Error != testCase.s3Error {
+			if _, err := io.ReadAll(testCase.req.Body); toAPIErrorCode(ctx, err) != testCase.s3Error {
+				t.Fatalf("Test %d: Unexpected S3 error: want %d - got %d (got after reading request %s)", i, testCase.s3Error, s3Error, toAPIError(ctx, err).Code)
+			}
+		}
+	}
+}
+
+func TestCheckAdminRequestAuthType(t *testing.T) {
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+
+	objLayer, fsDir, err := prepareFS(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer os.RemoveAll(fsDir)
+
+	if err = newTestConfig(globalMinioDefaultRegion, objLayer); err != nil {
+		t.Fatalf("unable initialize config file, %s", err)
+	}
+
+	creds, err := auth.CreateCredentials("myuser", "mypassword")
+	if err != nil {
+		t.Fatalf("unable create credential, %s", err)
+	}
+
+	globalActiveCred = creds
+	testCases := []struct {
+		Request *http.Request
+		ErrCode APIErrorCode
+	}{
+		{Request: mustNewRequest(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrCode: ErrAccessDenied},
+		{Request: mustNewSignedRequest(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrCode: ErrNone},
+		{Request: mustNewSignedV2Request(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrCode: ErrAccessDenied},
+		{Request: mustNewPresignedV2Request(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrCode: ErrAccessDenied},
+		{Request: mustNewPresignedRequest(http.MethodGet, "http://127.0.0.1:9000", 0, nil, t), ErrCode: ErrAccessDenied},
+	}
+	for i, testCase := range testCases {
+		if _, s3Error := checkAdminRequestAuth(ctx, testCase.Request, policy.AllAdminActions, globalSite.Region()); s3Error != testCase.ErrCode {
+			t.Errorf("Test %d: Unexpected s3error returned wanted %d, got %d", i, testCase.ErrCode, s3Error)
+		}
+	}
+}
+
+func TestValidateAdminSignature(t *testing.T) {
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+
+	objLayer, fsDir, err := prepareFS(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer os.RemoveAll(fsDir)
+
+	if err = newTestConfig(globalMinioDefaultRegion, objLayer); err != nil {
+		t.Fatalf("unable initialize config file, %s", err)
+	}
+
+	initAllSubsystems(ctx)
+
+	initConfigSubsystem(ctx, objLayer)
+
+	creds, err := auth.CreateCredentials("admin", "mypassword")
+	if err != nil {
+		t.Fatalf("unable create credential, %s", err)
+	}
+	globalActiveCred = creds
+
+	globalIAMSys.Init(ctx, objLayer, globalEtcdClient, 2*time.Second)
+
+	testCases := []struct {
+		AccessKey string
+		SecretKey string
+		ErrCode   APIErrorCode
+	}{
+		{"", "", ErrInvalidAccessKeyID},
+		{"admin", "", ErrSignatureDoesNotMatch},
+		{"admin", "wrongpassword", ErrSignatureDoesNotMatch},
+		{"wronguser", "mypassword", ErrInvalidAccessKeyID},
+		{"", "mypassword", ErrInvalidAccessKeyID},
+		{"admin", "mypassword", ErrNone},
+	}
+
+	for i, testCase := range testCases {
+		req := mustNewRequest(http.MethodGet, "http://localhost:9000/", 0, nil, t)
+		if err := signRequestV4(req, testCase.AccessKey, testCase.SecretKey); err != nil {
+			t.Fatalf("Unable to initialized new signed http request %s", err)
+		}
+		_, _, s3Error := validateAdminSignature(ctx, req, globalMinioDefaultRegion)
+		if s3Error != testCase.ErrCode {
+			t.Errorf("Test %d: Unexpected s3error returned wanted %d, got %d", i+1, testCase.ErrCode, s3Error)
+		}
+	}
+}

cmd/authtype_string.go

@@ -0,0 +1,34 @@
+// Code generated by "stringer -type=authType -trimprefix=authType auth-handler.go"; DO NOT EDIT.
+
+package cmd
+
+import "strconv"
+
+func _() {
+	// An "invalid array index" compiler error signifies that the constant values have changed.
+	// Re-run the stringer command to generate them again.
+	var x [1]struct{}
+	_ = x[authTypeUnknown-0]
+	_ = x[authTypeAnonymous-1]
+	_ = x[authTypePresigned-2]
+	_ = x[authTypePresignedV2-3]
+	_ = x[authTypePostPolicy-4]
+	_ = x[authTypeStreamingSigned-5]
+	_ = x[authTypeSigned-6]
+	_ = x[authTypeSignedV2-7]
+	_ = x[authTypeJWT-8]
+	_ = x[authTypeSTS-9]
+	_ = x[authTypeStreamingSignedTrailer-10]
+	_ = x[authTypeStreamingUnsignedTrailer-11]
+}
+
+const _authType_name = "UnknownAnonymousPresignedPresignedV2PostPolicyStreamingSignedSignedSignedV2JWTSTSStreamingSignedTrailerStreamingUnsignedTrailer"
+
+var _authType_index = [...]uint8{0, 7, 16, 25, 36, 46, 61, 67, 75, 78, 81, 103, 127}
+
+func (i authType) String() string {
+	if i < 0 || i >= authType(len(_authType_index)-1) {
+		return "authType(" + strconv.FormatInt(int64(i), 10) + ")"
+	}
+	return _authType_name[_authType_index[i]:_authType_index[i+1]]
+}

cmd/background-heal-ops.go

@@ -0,0 +1,189 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"context"
+	"fmt"
+	"runtime"
+	"strconv"
+	"time"
+
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/pkg/v3/env"
+)
+
+// healTask represents what to heal along with options
+//
+//	path: '/' =>  Heal disk formats along with metadata
+//	path: 'bucket/' or '/bucket/' => Heal bucket
+//	path: 'bucket/object' => Heal object
+type healTask struct {
+	bucket    string
+	object    string
+	versionID string
+	opts      madmin.HealOpts
+	// Healing response will be sent here
+	respCh chan healResult
+}
+
+// healResult represents a healing result with a possible error
+type healResult struct {
+	result madmin.HealResultItem
+	err    error
+}
+
+// healRoutine receives heal tasks, to heal buckets, objects and format.json
+type healRoutine struct {
+	tasks   chan healTask
+	workers int
+}
+
+func activeListeners() int {
+	// Bucket notification and http trace are not costly, it is okay to ignore them
+	// while counting the number of concurrent connections
+	return int(globalHTTPListen.Subscribers()) + int(globalTrace.Subscribers())
+}
+
+func waitForLowIO(maxIO int, maxWait time.Duration, currentIO func() int) {
+	// No need to wait run at full speed.
+	if maxIO <= 0 {
+		return
+	}
+
+	const waitTick = 100 * time.Millisecond
+
+	tmpMaxWait := maxWait
+
+	for currentIO() >= maxIO {
+		if tmpMaxWait > 0 {
+			if tmpMaxWait < waitTick {
+				time.Sleep(tmpMaxWait)
+				return
+			}
+			time.Sleep(waitTick)
+			tmpMaxWait -= waitTick
+		}
+		if tmpMaxWait <= 0 {
+			return
+		}
+	}
+}
+
+func currentHTTPIO() int {
+	httpServer := newHTTPServerFn()
+	if httpServer == nil {
+		return 0
+	}
+
+	return httpServer.GetRequestCount() - activeListeners()
+}
+
+func waitForLowHTTPReq() {
+	maxIO, maxWait, _ := globalHealConfig.Clone()
+	waitForLowIO(maxIO, maxWait, currentHTTPIO)
+}
+
+func initBackgroundHealing(ctx context.Context, objAPI ObjectLayer) {
+	bgSeq := newBgHealSequence()
+	// Run the background healer
+	for i := 0; i < globalBackgroundHealRoutine.workers; i++ {
+		go globalBackgroundHealRoutine.AddWorker(ctx, objAPI, bgSeq)
+	}
+
+	globalBackgroundHealState.LaunchNewHealSequence(bgSeq, objAPI)
+}
+
+// Wait for heal requests and process them
+func (h *healRoutine) AddWorker(ctx context.Context, objAPI ObjectLayer, bgSeq *healSequence) {
+	for {
+		select {
+		case task, ok := <-h.tasks:
+			if !ok {
+				return
+			}
+
+			var res madmin.HealResultItem
+			var err error
+			switch task.bucket {
+			case nopHeal:
+				err = errSkipFile
+			case SlashSeparator:
+				res, err = healDiskFormat(ctx, objAPI, task.opts)
+			default:
+				if task.object == "" {
+					res, err = objAPI.HealBucket(ctx, task.bucket, task.opts)
+				} else {
+					res, err = objAPI.HealObject(ctx, task.bucket, task.object, task.versionID, task.opts)
+				}
+			}
+
+			if task.respCh != nil {
+				task.respCh <- healResult{result: res, err: err}
+				continue
+			}
+
+			// when respCh is not set caller is not waiting but we
+			// update the relevant metrics for them
+			if bgSeq != nil {
+				if err == nil {
+					bgSeq.countHealed(res.Type)
+				} else {
+					bgSeq.countFailed(res.Type)
+				}
+			}
+		case <-ctx.Done():
+			return
+		}
+	}
+}
+
+func newHealRoutine() *healRoutine {
+	workers := runtime.GOMAXPROCS(0) / 2
+
+	if envHealWorkers := env.Get("_MINIO_HEAL_WORKERS", ""); envHealWorkers != "" {
+		if numHealers, err := strconv.Atoi(envHealWorkers); err != nil {
+			bugLogIf(context.Background(), fmt.Errorf("invalid _MINIO_HEAL_WORKERS value: %w", err))
+		} else {
+			workers = numHealers
+		}
+	}
+
+	if workers == 0 {
+		workers = 4
+	}
+
+	return &healRoutine{
+		tasks:   make(chan healTask),
+		workers: workers,
+	}
+}
+
+// healDiskFormat - heals format.json, return value indicates if a
+// failure error occurred.
+func healDiskFormat(ctx context.Context, objAPI ObjectLayer, opts madmin.HealOpts) (madmin.HealResultItem, error) {
+	res, err := objAPI.HealFormat(ctx, opts.DryRun)
+
+	// return any error, ignore error returned when disks have
+	// already healed.
+	if err != nil && err != errNoHealRequired {
+		return madmin.HealResultItem{}, err
+	}
+
+	return res, nil
+}

cmd/background-newdisks-heal-ops.go

@@ -0,0 +1,609 @@
+// Copyright (c) 2015-2021 MinIO, Inc.
+//
+// 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 (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/dustin/go-humanize"
+	"github.com/minio/madmin-go/v3"
+	"github.com/minio/minio-go/v7/pkg/set"
+	"github.com/minio/minio/internal/config"
+	"github.com/minio/pkg/v3/env"
+)
+
+const (
+	defaultMonitorNewDiskInterval = time.Second * 10
+	healingTrackerFilename        = ".healing.bin"
+)
+
+//go:generate msgp -file $GOFILE -unexported
+
+// healingTracker is used to persist healing information during a heal.
+type healingTracker struct {
+	disk StorageAPI    `msg:"-"`
+	mu   *sync.RWMutex `msg:"-"`
+
+	ID         string
+	PoolIndex  int
+	SetIndex   int
+	DiskIndex  int
+	Path       string
+	Endpoint   string
+	Started    time.Time
+	LastUpdate time.Time
+
+	ObjectsTotalCount uint64
+	ObjectsTotalSize  uint64
+
+	ItemsHealed uint64
+	ItemsFailed uint64
+
+	BytesDone   uint64
+	BytesFailed uint64
+
+	// Last object scanned.
+	Bucket string `json:"-"`
+	Object string `json:"-"`
+
+	// Numbers when current bucket started healing,
+	// for resuming with correct numbers.
+	ResumeItemsHealed  uint64 `json:"-"`
+	ResumeItemsFailed  uint64 `json:"-"`
+	ResumeItemsSkipped uint64 `json:"-"`
+	ResumeBytesDone    uint64 `json:"-"`
+	ResumeBytesFailed  uint64 `json:"-"`
+	ResumeBytesSkipped uint64 `json:"-"`
+
+	// Filled on startup/restarts.
+	QueuedBuckets []string
+
+	// Filled during heal.
+	HealedBuckets []string
+
+	// ID of the current healing operation
+	HealID string
+
+	ItemsSkipped uint64
+	BytesSkipped uint64
+
+	RetryAttempts uint64
+
+	Finished bool // finished healing, whether with errors or not
+
+	// Add future tracking capabilities
+	// Be sure that they are included in toHealingDisk
+}
+
+// loadHealingTracker will load the healing tracker from the supplied disk.
+// The disk ID will be validated against the loaded one.
+func loadHealingTracker(ctx context.Context, disk StorageAPI) (*healingTracker, error) {
+	if disk == nil {
+		return nil, errors.New("loadHealingTracker: nil drive given")
+	}
+	diskID, err := disk.GetDiskID()
+	if err != nil {
+		return nil, err
+	}
+	b, err := disk.ReadAll(ctx, minioMetaBucket,
+		pathJoin(bucketMetaPrefix, healingTrackerFilename))
+	if err != nil {
+		return nil, err
+	}
+	var h healingTracker
+	_, err = h.UnmarshalMsg(b)
+	if err != nil {
+		return nil, err
+	}
+	if h.ID != diskID && h.ID != "" {
+		return nil, fmt.Errorf("loadHealingTracker: drive id mismatch expected %s, got %s", h.ID, diskID)
+	}
+	h.disk = disk
+	h.ID = diskID
+	h.mu = &sync.RWMutex{}
+	return &h, nil
+}
+
+// newHealingTracker will create a new healing tracker for the disk.
+func newHealingTracker() *healingTracker {
+	return &healingTracker{
+		mu: &sync.RWMutex{},
+	}
+}
+
+func initHealingTracker(disk StorageAPI, healID string) *healingTracker {
+	h := newHealingTracker()
+	diskID, _ := disk.GetDiskID()
+	h.disk = disk
+	h.ID = diskID
+	h.HealID = healID
+	h.Path = disk.String()
+	h.Endpoint = disk.Endpoint().String()
+	h.Started = time.Now().UTC()
+	h.PoolIndex, h.SetIndex, h.DiskIndex = disk.GetDiskLoc()
+	return h
+}
+
+func (h *healingTracker) resetHealing() {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	h.ItemsHealed = 0
+	h.ItemsFailed = 0
+	h.BytesDone = 0
+	h.BytesFailed = 0
+	h.ResumeItemsHealed = 0
+	h.ResumeItemsFailed = 0
+	h.ResumeBytesDone = 0
+	h.ResumeBytesFailed = 0
+	h.ItemsSkipped = 0
+	h.BytesSkipped = 0
+
+	h.HealedBuckets = nil
+	h.Object = ""
+	h.Bucket = ""
+}
+
+func (h *healingTracker) getLastUpdate() time.Time {
+	h.mu.RLock()
+	defer h.mu.RUnlock()
+
+	return h.LastUpdate
+}
+
+func (h *healingTracker) getBucket() string {
+	h.mu.RLock()
+	defer h.mu.RUnlock()
+
+	return h.Bucket
+}
+
+func (h *healingTracker) setBucket(bucket string) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	h.Bucket = bucket
+}
+
+func (h *healingTracker) getObject() string {
+	h.mu.RLock()
+	defer h.mu.RUnlock()
+
+	return h.Object
+}
+
+func (h *healingTracker) setObject(object string) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	h.Object = object
+}
+
+func (h *healingTracker) updateProgress(success, skipped bool, bytes uint64) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	switch {
+	case success:
+		h.ItemsHealed++
+		h.BytesDone += bytes
+	case skipped:
+		h.ItemsSkipped++
+		h.BytesSkipped += bytes
+	default:
+		h.ItemsFailed++
+		h.BytesFailed += bytes
+	}
+}
+
+// update will update the tracker on the disk.
+// If the tracker has been deleted an error is returned.
+func (h *healingTracker) update(ctx context.Context) error {
+	h.mu.Lock()
+	if h.ID == "" || h.PoolIndex < 0 || h.SetIndex < 0 || h.DiskIndex < 0 {
+		h.ID, _ = h.disk.GetDiskID()
+		h.PoolIndex, h.SetIndex, h.DiskIndex = h.disk.GetDiskLoc()
+	}
+	h.mu.Unlock()
+	return h.save(ctx)
+}
+
+// save will unconditionally save the tracker and will be created if not existing.
+func (h *healingTracker) save(ctx context.Context) error {
+	h.mu.Lock()
+	if h.PoolIndex < 0 || h.SetIndex < 0 || h.DiskIndex < 0 {
+		// Attempt to get location.
+		if api := newObjectLayerFn(); api != nil {
+			if ep, ok := api.(*erasureServerPools); ok {
+				h.PoolIndex, h.SetIndex, h.DiskIndex, _ = ep.getPoolAndSet(h.ID)
+			}
+		}
+	}
+	h.LastUpdate = time.Now().UTC()
+	htrackerBytes, err := h.MarshalMsg(nil)
+	h.mu.Unlock()
+	if err != nil {
+		return err
+	}
+	globalBackgroundHealState.updateHealStatus(h)
+	return h.disk.WriteAll(ctx, minioMetaBucket,
+		pathJoin(bucketMetaPrefix, healingTrackerFilename),
+		htrackerBytes)
+}
+
+// delete the tracker on disk.
+func (h *healingTracker) delete(ctx context.Context) error {
+	return h.disk.Delete(ctx, minioMetaBucket,
+		pathJoin(bucketMetaPrefix, healingTrackerFilename),
+		DeleteOptions{
+			Recursive: false,
+			Immediate: false,
+		},
+	)
+}
+
+func (h *healingTracker) isHealed(bucket string) bool {
+	h.mu.RLock()
+	defer h.mu.RUnlock()
+	for _, v := range h.HealedBuckets {
+		if v == bucket {
+			return true
+		}
+	}
+	return false
+}
+
+// resume will reset progress to the numbers at the start of the bucket.
+func (h *healingTracker) resume() {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	h.ItemsHealed = h.ResumeItemsHealed
+	h.ItemsFailed = h.ResumeItemsFailed
+	h.ItemsSkipped = h.ResumeItemsSkipped
+	h.BytesDone = h.ResumeBytesDone
+	h.BytesFailed = h.ResumeBytesFailed
+	h.BytesSkipped = h.ResumeBytesSkipped
+}
+
+// bucketDone should be called when a bucket is done healing.
+// Adds the bucket to the list of healed buckets and updates resume numbers.
+func (h *healingTracker) bucketDone(bucket string) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	h.ResumeItemsHealed = h.ItemsHealed
+	h.ResumeItemsFailed = h.ItemsFailed
+	h.ResumeItemsSkipped = h.ItemsSkipped
+	h.ResumeBytesDone = h.BytesDone
+	h.ResumeBytesFailed = h.BytesFailed
+	h.ResumeBytesSkipped = h.BytesSkipped
+	h.HealedBuckets = append(h.HealedBuckets, bucket)
+	for i, b := range h.QueuedBuckets {
+		if b == bucket {
+			// Delete...
+			h.QueuedBuckets = append(h.QueuedBuckets[:i], h.QueuedBuckets[i+1:]...)
+		}
+	}
+}
+
+// setQueuedBuckets will add buckets, but exclude any that is already in h.HealedBuckets.
+// Order is preserved.
+func (h *healingTracker) setQueuedBuckets(buckets []BucketInfo) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	s := set.CreateStringSet(h.HealedBuckets...)
+	h.QueuedBuckets = make([]string, 0, len(buckets))
+	for _, b := range buckets {
+		if !s.Contains(b.Name) {
+			h.QueuedBuckets = append(h.QueuedBuckets, b.Name)
+		}
+	}
+}
+
+func (h *healingTracker) printTo(writer io.Writer) {
+	h.mu.RLock()
+	defer h.mu.RUnlock()
+
+	b, err := json.MarshalIndent(h, "", "  ")
+	if err != nil {
+		writer.Write([]byte(err.Error()))
+		return
+	}
+	writer.Write(b)
+}
+
+// toHealingDisk converts the information to madmin.HealingDisk
+func (h *healingTracker) toHealingDisk() madmin.HealingDisk {
+	h.mu.RLock()
+	defer h.mu.RUnlock()
+
+	return madmin.HealingDisk{
+		ID:                h.ID,
+		HealID:            h.HealID,
+		Endpoint:          h.Endpoint,
+		PoolIndex:         h.PoolIndex,
+		SetIndex:          h.SetIndex,
+		DiskIndex:         h.DiskIndex,
+		Finished:          h.Finished,
+		Path:              h.Path,
+		Started:           h.Started.UTC(),
+		LastUpdate:        h.LastUpdate.UTC(),
+		ObjectsTotalCount: h.ObjectsTotalCount,
+		ObjectsTotalSize:  h.ObjectsTotalSize,
+		ItemsHealed:       h.ItemsHealed,
+		ItemsSkipped:      h.ItemsSkipped,
+		ItemsFailed:       h.ItemsFailed,
+		BytesDone:         h.BytesDone,
+		BytesSkipped:      h.BytesSkipped,
+		BytesFailed:       h.BytesFailed,
+		Bucket:            h.Bucket,
+		Object:            h.Object,
+		QueuedBuckets:     h.QueuedBuckets,
+		HealedBuckets:     h.HealedBuckets,
+		RetryAttempts:     h.RetryAttempts,
+
+		ObjectsHealed: h.ItemsHealed, // Deprecated July 2021
+		ObjectsFailed: h.ItemsFailed, // Deprecated July 2021
+
+	}
+}
+
+func initAutoHeal(ctx context.Context, objAPI ObjectLayer) {
+	z, ok := objAPI.(*erasureServerPools)
+	if !ok {
+		return
+	}
+
+	initBackgroundHealing(ctx, objAPI) // start quick background healing
+	if env.Get("_MINIO_AUTO_DRIVE_HEALING", config.EnableOn) == config.EnableOn {
+		globalBackgroundHealState.pushHealLocalDisks(getLocalDisksToHeal()...)
+		go monitorLocalDisksAndHeal(ctx, z)
+	}
+
+	go globalMRFState.startMRFPersistence()
+	go globalMRFState.healRoutine(z)
+}
+
+func getLocalDisksToHeal() (disksToHeal Endpoints) {
+	globalLocalDrivesMu.RLock()
+	localDrives := cloneDrives(globalLocalDrivesMap)
+	globalLocalDrivesMu.RUnlock()
+	for _, disk := range localDrives {
+		_, err := disk.DiskInfo(context.Background(), DiskInfoOptions{})
+		if errors.Is(err, errUnformattedDisk) {
+			disksToHeal = append(disksToHeal, disk.Endpoint())
+			continue
+		}
+		if h := disk.Healing(); h != nil && !h.Finished {
+			disksToHeal = append(disksToHeal, disk.Endpoint())
+		}
+	}
+	if len(disksToHeal) == globalEndpoints.NEndpoints() {
+		// When all disks == all command line endpoints
+		// this is a fresh setup, no need to trigger healing.
+		return Endpoints{}
+	}
+	return disksToHeal
+}
+
+var newDiskHealingTimeout = newDynamicTimeout(30*time.Second, 10*time.Second)
+
+var errRetryHealing = errors.New("some items failed to heal, we will retry healing this drive again")
+
+func healFreshDisk(ctx context.Context, z *erasureServerPools, endpoint Endpoint) error {
+	poolIdx, setIdx := endpoint.PoolIdx, endpoint.SetIdx
+	disk := getStorageViaEndpoint(endpoint)
+	if disk == nil {
+		return fmt.Errorf("Unexpected error disk must be initialized by now after formatting: %s", endpoint)
+	}
+
+	_, err := disk.DiskInfo(ctx, DiskInfoOptions{})
+	if err != nil {
+		if errors.Is(err, errDriveIsRoot) {
+			// This is a root drive, ignore and move on
+			return nil
+		}
+		if !errors.Is(err, errUnformattedDisk) {
+			return err
+		}
+	}
+
+	// Prevent parallel erasure set healing
+	locker := z.NewNSLock(minioMetaBucket, fmt.Sprintf("new-drive-healing/%d/%d", poolIdx, setIdx))
+	lkctx, err := locker.GetLock(ctx, newDiskHealingTimeout)
+	if err != nil {
+		return fmt.Errorf("Healing of drive '%v' on %s pool, belonging to %s erasure set already in progress: %w",
+			disk, humanize.Ordinal(poolIdx+1), humanize.Ordinal(setIdx+1), err)
+	}
+	ctx = lkctx.Context()
+	defer locker.Unlock(lkctx)
+
+	// Load healing tracker in this disk
+	tracker, err := loadHealingTracker(ctx, disk)
+	if err != nil {
+		// A healing tracker may be deleted if another disk in the
+		// same erasure set with same healing-id successfully finished
+		// healing.
+		if errors.Is(err, errFileNotFound) {
+			return nil
+		}
+		healingLogIf(ctx, fmt.Errorf("Unable to load healing tracker on '%s': %w, re-initializing..", disk, err))
+		tracker = initHealingTracker(disk, mustGetUUID())
+	}
+
+	healingLogEvent(ctx, "Healing drive '%s' - 'mc admin heal alias/ --verbose' to check the current status.", endpoint)
+
+	buckets, _ := z.ListBuckets(ctx, BucketOptions{})
+	// Buckets data are dispersed in multiple pools/sets, make
+	// sure to heal all bucket metadata configuration.
+	buckets = append(buckets, BucketInfo{
+		Name: pathJoin(minioMetaBucket, minioConfigPrefix),
+	}, BucketInfo{
+		Name: pathJoin(minioMetaBucket, bucketMetaPrefix),
+	})
+
+	// Heal latest buckets first.
+	sort.Slice(buckets, func(i, j int) bool {
+		a, b := strings.HasPrefix(buckets[i].Name, minioMetaBucket), strings.HasPrefix(buckets[j].Name, minioMetaBucket)
+		if a != b {
+			return a
+		}
+		return buckets[i].Created.After(buckets[j].Created)
+	})
+
+	// Load bucket totals
+	cache := dataUsageCache{}
+	if err := cache.load(ctx, z.serverPools[poolIdx].sets[setIdx], dataUsageCacheName); err == nil {
+		dataUsageInfo := cache.dui(dataUsageRoot, nil)
+		tracker.ObjectsTotalCount = dataUsageInfo.ObjectsTotalCount
+		tracker.ObjectsTotalSize = dataUsageInfo.ObjectsTotalSize
+	}
+
+	tracker.PoolIndex, tracker.SetIndex, tracker.DiskIndex = disk.GetDiskLoc()
+	tracker.setQueuedBuckets(buckets)
+	if err := tracker.save(ctx); err != nil {
+		return err
+	}
+
+	// Start or resume healing of this erasure set
+	if err = z.serverPools[poolIdx].sets[setIdx].healErasureSet(ctx, tracker.QueuedBuckets, tracker); err != nil {
+		return err
+	}
+
+	// if objects have failed healing, we attempt a retry to heal the drive upto 3 times before giving up.
+	if tracker.ItemsFailed > 0 && tracker.RetryAttempts < 4 {
+		tracker.RetryAttempts++
+
+		healingLogEvent(ctx, "Healing of drive '%s' is incomplete, retrying %s time (healed: %d, skipped: %d, failed: %d).", disk,
+			humanize.Ordinal(int(tracker.RetryAttempts)), tracker.ItemsHealed, tracker.ItemsSkipped, tracker.ItemsFailed)
+
+		tracker.resetHealing()
+		bugLogIf(ctx, tracker.update(ctx))
+
+		return errRetryHealing
+	}
+
+	if tracker.ItemsFailed > 0 {
+		healingLogEvent(ctx, "Healing of drive '%s' is incomplete, retried %d times (healed: %d, skipped: %d, failed: %d).", disk,
+			tracker.RetryAttempts, tracker.ItemsHealed, tracker.ItemsSkipped, tracker.ItemsFailed)
+	} else {
+		if tracker.RetryAttempts > 0 {
+			healingLogEvent(ctx, "Healing of drive '%s' is complete, retried %d times (healed: %d, skipped: %d).", disk,
+				tracker.RetryAttempts-1, tracker.ItemsHealed, tracker.ItemsSkipped)
+		} else {
+			healingLogEvent(ctx, "Healing of drive '%s' is finished (healed: %d, skipped: %d).", disk, tracker.ItemsHealed, tracker.ItemsSkipped)
+		}
+	}
+	if serverDebugLog {
+		tracker.printTo(os.Stdout)
+		fmt.Printf("\n")
+	}
+
+	if tracker.HealID == "" { // HealID was empty only before Feb 2023
+		bugLogIf(ctx, tracker.delete(ctx))
+		return nil
+	}
+
+	// Remove .healing.bin from all disks with similar heal-id
+	disks, err := z.GetDisks(poolIdx, setIdx)
+	if err != nil {
+		return err
+	}
+
+	for _, disk := range disks {
+		if disk == nil {
+			continue
+		}
+
+		t, err := loadHealingTracker(ctx, disk)
+		if err != nil {
+			if !errors.Is(err, errFileNotFound) {
+				healingLogIf(ctx, err)
+			}
+			continue
+		}
+		if t.HealID == tracker.HealID {
+			t.Finished = true
+			t.update(ctx)
+		}
+	}
+
+	return nil
+}
+
+// monitorLocalDisksAndHeal - ensures that detected new disks are healed
+//  1. Only the concerned erasure set will be listed and healed
+//  2. Only the node hosting the disk is responsible to perform the heal
+func monitorLocalDisksAndHeal(ctx context.Context, z *erasureServerPools) {
+	// Perform automatic disk healing when a disk is replaced locally.
+	diskCheckTimer := time.NewTimer(defaultMonitorNewDiskInterval)
+	defer diskCheckTimer.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-diskCheckTimer.C:
+			healDisks := globalBackgroundHealState.getHealLocalDiskEndpoints()
+			if len(healDisks) == 0 {
+				// Reset for next interval.
+				diskCheckTimer.Reset(defaultMonitorNewDiskInterval)
+				continue
+			}
+
+			// Reformat disks immediately
+			_, err := z.HealFormat(context.Background(), false)
+			if err != nil && !errors.Is(err, errNoHealRequired) {
+				healingLogIf(ctx, err)
+				// Reset for next interval.
+				diskCheckTimer.Reset(defaultMonitorNewDiskInterval)
+				continue
+			}
+
+			for _, disk := range healDisks {
+				go func(disk Endpoint) {
+					globalBackgroundHealState.setDiskHealingStatus(disk, true)
+					if err := healFreshDisk(ctx, z, disk); err != nil {
+						globalBackgroundHealState.setDiskHealingStatus(disk, false)
+						timedout := OperationTimedOut{}
+						if !errors.Is(err, context.Canceled) && !errors.As(err, &timedout) && !errors.Is(err, errRetryHealing) {
+							printEndpointError(disk, err, false)
+						}
+						return
+					}
+					// Only upon success pop the healed disk.
+					globalBackgroundHealState.popHealLocalDisks(disk)
+				}(disk)
+			}
+
+			// Reset for next interval.
+			diskCheckTimer.Reset(defaultMonitorNewDiskInterval)
+		}
+	}
+}

cmd/background-newdisks-heal-ops_gen.go

@@ -0,0 +1,890 @@
+package cmd
+
+// Code generated by github.com/tinylib/msgp DO NOT EDIT.
+
+import (
+	"github.com/tinylib/msgp/msgp"
+)
+
+// DecodeMsg implements msgp.Decodable
+func (z *healingTracker) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "ID":
+			z.ID, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "ID")
+				return
+			}
+		case "PoolIndex":
+			z.PoolIndex, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "PoolIndex")
+				return
+			}
+		case "SetIndex":
+			z.SetIndex, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "SetIndex")
+				return
+			}
+		case "DiskIndex":
+			z.DiskIndex, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "DiskIndex")
+				return
+			}
+		case "Path":
+			z.Path, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Path")
+				return
+			}
+		case "Endpoint":
+			z.Endpoint, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Endpoint")
+				return
+			}
+		case "Started":
+			z.Started, err = dc.ReadTime()
+			if err != nil {
+				err = msgp.WrapError(err, "Started")
+				return
+			}
+		case "LastUpdate":
+			z.LastUpdate, err = dc.ReadTime()
+			if err != nil {
+				err = msgp.WrapError(err, "LastUpdate")
+				return
+			}
+		case "ObjectsTotalCount":
+			z.ObjectsTotalCount, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ObjectsTotalCount")
+				return
+			}
+		case "ObjectsTotalSize":
+			z.ObjectsTotalSize, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ObjectsTotalSize")
+				return
+			}
+		case "ItemsHealed":
+			z.ItemsHealed, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ItemsHealed")
+				return
+			}
+		case "ItemsFailed":
+			z.ItemsFailed, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ItemsFailed")
+				return
+			}
+		case "BytesDone":
+			z.BytesDone, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "BytesDone")
+				return
+			}
+		case "BytesFailed":
+			z.BytesFailed, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "BytesFailed")
+				return
+			}
+		case "Bucket":
+			z.Bucket, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Bucket")
+				return
+			}
+		case "Object":
+			z.Object, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Object")
+				return
+			}
+		case "ResumeItemsHealed":
+			z.ResumeItemsHealed, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeItemsHealed")
+				return
+			}
+		case "ResumeItemsFailed":
+			z.ResumeItemsFailed, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeItemsFailed")
+				return
+			}
+		case "ResumeItemsSkipped":
+			z.ResumeItemsSkipped, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeItemsSkipped")
+				return
+			}
+		case "ResumeBytesDone":
+			z.ResumeBytesDone, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeBytesDone")
+				return
+			}
+		case "ResumeBytesFailed":
+			z.ResumeBytesFailed, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeBytesFailed")
+				return
+			}
+		case "ResumeBytesSkipped":
+			z.ResumeBytesSkipped, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeBytesSkipped")
+				return
+			}
+		case "QueuedBuckets":
+			var zb0002 uint32
+			zb0002, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "QueuedBuckets")
+				return
+			}
+			if cap(z.QueuedBuckets) >= int(zb0002) {
+				z.QueuedBuckets = (z.QueuedBuckets)[:zb0002]
+			} else {
+				z.QueuedBuckets = make([]string, zb0002)
+			}
+			for za0001 := range z.QueuedBuckets {
+				z.QueuedBuckets[za0001], err = dc.ReadString()
+				if err != nil {
+					err = msgp.WrapError(err, "QueuedBuckets", za0001)
+					return
+				}
+			}
+		case "HealedBuckets":
+			var zb0003 uint32
+			zb0003, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "HealedBuckets")
+				return
+			}
+			if cap(z.HealedBuckets) >= int(zb0003) {
+				z.HealedBuckets = (z.HealedBuckets)[:zb0003]
+			} else {
+				z.HealedBuckets = make([]string, zb0003)
+			}
+			for za0002 := range z.HealedBuckets {
+				z.HealedBuckets[za0002], err = dc.ReadString()
+				if err != nil {
+					err = msgp.WrapError(err, "HealedBuckets", za0002)
+					return
+				}
+			}
+		case "HealID":
+			z.HealID, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "HealID")
+				return
+			}
+		case "ItemsSkipped":
+			z.ItemsSkipped, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "ItemsSkipped")
+				return
+			}
+		case "BytesSkipped":
+			z.BytesSkipped, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "BytesSkipped")
+				return
+			}
+		case "RetryAttempts":
+			z.RetryAttempts, err = dc.ReadUint64()
+			if err != nil {
+				err = msgp.WrapError(err, "RetryAttempts")
+				return
+			}
+		case "Finished":
+			z.Finished, err = dc.ReadBool()
+			if err != nil {
+				err = msgp.WrapError(err, "Finished")
+				return
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z *healingTracker) EncodeMsg(en *msgp.Writer) (err error) {
+	// map header, size 29
+	// write "ID"
+	err = en.Append(0xde, 0x0, 0x1d, 0xa2, 0x49, 0x44)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.ID)
+	if err != nil {
+		err = msgp.WrapError(err, "ID")
+		return
+	}
+	// write "PoolIndex"
+	err = en.Append(0xa9, 0x50, 0x6f, 0x6f, 0x6c, 0x49, 0x6e, 0x64, 0x65, 0x78)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.PoolIndex)
+	if err != nil {
+		err = msgp.WrapError(err, "PoolIndex")
+		return
+	}
+	// write "SetIndex"
+	err = en.Append(0xa8, 0x53, 0x65, 0x74, 0x49, 0x6e, 0x64, 0x65, 0x78)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.SetIndex)
+	if err != nil {
+		err = msgp.WrapError(err, "SetIndex")
+		return
+	}
+	// write "DiskIndex"
+	err = en.Append(0xa9, 0x44, 0x69, 0x73, 0x6b, 0x49, 0x6e, 0x64, 0x65, 0x78)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.DiskIndex)
+	if err != nil {
+		err = msgp.WrapError(err, "DiskIndex")
+		return
+	}
+	// write "Path"
+	err = en.Append(0xa4, 0x50, 0x61, 0x74, 0x68)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Path)
+	if err != nil {
+		err = msgp.WrapError(err, "Path")
+		return
+	}
+	// write "Endpoint"
+	err = en.Append(0xa8, 0x45, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Endpoint)
+	if err != nil {
+		err = msgp.WrapError(err, "Endpoint")
+		return
+	}
+	// write "Started"
+	err = en.Append(0xa7, 0x53, 0x74, 0x61, 0x72, 0x74, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteTime(z.Started)
+	if err != nil {
+		err = msgp.WrapError(err, "Started")
+		return
+	}
+	// write "LastUpdate"
+	err = en.Append(0xaa, 0x4c, 0x61, 0x73, 0x74, 0x55, 0x70, 0x64, 0x61, 0x74, 0x65)
+	if err != nil {
+		return
+	}
+	err = en.WriteTime(z.LastUpdate)
+	if err != nil {
+		err = msgp.WrapError(err, "LastUpdate")
+		return
+	}
+	// write "ObjectsTotalCount"
+	err = en.Append(0xb1, 0x4f, 0x62, 0x6a, 0x65, 0x63, 0x74, 0x73, 0x54, 0x6f, 0x74, 0x61, 0x6c, 0x43, 0x6f, 0x75, 0x6e, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ObjectsTotalCount)
+	if err != nil {
+		err = msgp.WrapError(err, "ObjectsTotalCount")
+		return
+	}
+	// write "ObjectsTotalSize"
+	err = en.Append(0xb0, 0x4f, 0x62, 0x6a, 0x65, 0x63, 0x74, 0x73, 0x54, 0x6f, 0x74, 0x61, 0x6c, 0x53, 0x69, 0x7a, 0x65)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ObjectsTotalSize)
+	if err != nil {
+		err = msgp.WrapError(err, "ObjectsTotalSize")
+		return
+	}
+	// write "ItemsHealed"
+	err = en.Append(0xab, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x48, 0x65, 0x61, 0x6c, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ItemsHealed)
+	if err != nil {
+		err = msgp.WrapError(err, "ItemsHealed")
+		return
+	}
+	// write "ItemsFailed"
+	err = en.Append(0xab, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ItemsFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "ItemsFailed")
+		return
+	}
+	// write "BytesDone"
+	err = en.Append(0xa9, 0x42, 0x79, 0x74, 0x65, 0x73, 0x44, 0x6f, 0x6e, 0x65)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.BytesDone)
+	if err != nil {
+		err = msgp.WrapError(err, "BytesDone")
+		return
+	}
+	// write "BytesFailed"
+	err = en.Append(0xab, 0x42, 0x79, 0x74, 0x65, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.BytesFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "BytesFailed")
+		return
+	}
+	// write "Bucket"
+	err = en.Append(0xa6, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Bucket)
+	if err != nil {
+		err = msgp.WrapError(err, "Bucket")
+		return
+	}
+	// write "Object"
+	err = en.Append(0xa6, 0x4f, 0x62, 0x6a, 0x65, 0x63, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Object)
+	if err != nil {
+		err = msgp.WrapError(err, "Object")
+		return
+	}
+	// write "ResumeItemsHealed"
+	err = en.Append(0xb1, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x48, 0x65, 0x61, 0x6c, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ResumeItemsHealed)
+	if err != nil {
+		err = msgp.WrapError(err, "ResumeItemsHealed")
+		return
+	}
+	// write "ResumeItemsFailed"
+	err = en.Append(0xb1, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ResumeItemsFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "ResumeItemsFailed")
+		return
+	}
+	// write "ResumeItemsSkipped"
+	err = en.Append(0xb2, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ResumeItemsSkipped)
+	if err != nil {
+		err = msgp.WrapError(err, "ResumeItemsSkipped")
+		return
+	}
+	// write "ResumeBytesDone"
+	err = en.Append(0xaf, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x44, 0x6f, 0x6e, 0x65)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ResumeBytesDone)
+	if err != nil {
+		err = msgp.WrapError(err, "ResumeBytesDone")
+		return
+	}
+	// write "ResumeBytesFailed"
+	err = en.Append(0xb1, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ResumeBytesFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "ResumeBytesFailed")
+		return
+	}
+	// write "ResumeBytesSkipped"
+	err = en.Append(0xb2, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ResumeBytesSkipped)
+	if err != nil {
+		err = msgp.WrapError(err, "ResumeBytesSkipped")
+		return
+	}
+	// write "QueuedBuckets"
+	err = en.Append(0xad, 0x51, 0x75, 0x65, 0x75, 0x65, 0x64, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteArrayHeader(uint32(len(z.QueuedBuckets)))
+	if err != nil {
+		err = msgp.WrapError(err, "QueuedBuckets")
+		return
+	}
+	for za0001 := range z.QueuedBuckets {
+		err = en.WriteString(z.QueuedBuckets[za0001])
+		if err != nil {
+			err = msgp.WrapError(err, "QueuedBuckets", za0001)
+			return
+		}
+	}
+	// write "HealedBuckets"
+	err = en.Append(0xad, 0x48, 0x65, 0x61, 0x6c, 0x65, 0x64, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteArrayHeader(uint32(len(z.HealedBuckets)))
+	if err != nil {
+		err = msgp.WrapError(err, "HealedBuckets")
+		return
+	}
+	for za0002 := range z.HealedBuckets {
+		err = en.WriteString(z.HealedBuckets[za0002])
+		if err != nil {
+			err = msgp.WrapError(err, "HealedBuckets", za0002)
+			return
+		}
+	}
+	// write "HealID"
+	err = en.Append(0xa6, 0x48, 0x65, 0x61, 0x6c, 0x49, 0x44)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.HealID)
+	if err != nil {
+		err = msgp.WrapError(err, "HealID")
+		return
+	}
+	// write "ItemsSkipped"
+	err = en.Append(0xac, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.ItemsSkipped)
+	if err != nil {
+		err = msgp.WrapError(err, "ItemsSkipped")
+		return
+	}
+	// write "BytesSkipped"
+	err = en.Append(0xac, 0x42, 0x79, 0x74, 0x65, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.BytesSkipped)
+	if err != nil {
+		err = msgp.WrapError(err, "BytesSkipped")
+		return
+	}
+	// write "RetryAttempts"
+	err = en.Append(0xad, 0x52, 0x65, 0x74, 0x72, 0x79, 0x41, 0x74, 0x74, 0x65, 0x6d, 0x70, 0x74, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteUint64(z.RetryAttempts)
+	if err != nil {
+		err = msgp.WrapError(err, "RetryAttempts")
+		return
+	}
+	// write "Finished"
+	err = en.Append(0xa8, 0x46, 0x69, 0x6e, 0x69, 0x73, 0x68, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteBool(z.Finished)
+	if err != nil {
+		err = msgp.WrapError(err, "Finished")
+		return
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z *healingTracker) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	// map header, size 29
+	// string "ID"
+	o = append(o, 0xde, 0x0, 0x1d, 0xa2, 0x49, 0x44)
+	o = msgp.AppendString(o, z.ID)
+	// string "PoolIndex"
+	o = append(o, 0xa9, 0x50, 0x6f, 0x6f, 0x6c, 0x49, 0x6e, 0x64, 0x65, 0x78)
+	o = msgp.AppendInt(o, z.PoolIndex)
+	// string "SetIndex"
+	o = append(o, 0xa8, 0x53, 0x65, 0x74, 0x49, 0x6e, 0x64, 0x65, 0x78)
+	o = msgp.AppendInt(o, z.SetIndex)
+	// string "DiskIndex"
+	o = append(o, 0xa9, 0x44, 0x69, 0x73, 0x6b, 0x49, 0x6e, 0x64, 0x65, 0x78)
+	o = msgp.AppendInt(o, z.DiskIndex)
+	// string "Path"
+	o = append(o, 0xa4, 0x50, 0x61, 0x74, 0x68)
+	o = msgp.AppendString(o, z.Path)
+	// string "Endpoint"
+	o = append(o, 0xa8, 0x45, 0x6e, 0x64, 0x70, 0x6f, 0x69, 0x6e, 0x74)
+	o = msgp.AppendString(o, z.Endpoint)
+	// string "Started"
+	o = append(o, 0xa7, 0x53, 0x74, 0x61, 0x72, 0x74, 0x65, 0x64)
+	o = msgp.AppendTime(o, z.Started)
+	// string "LastUpdate"
+	o = append(o, 0xaa, 0x4c, 0x61, 0x73, 0x74, 0x55, 0x70, 0x64, 0x61, 0x74, 0x65)
+	o = msgp.AppendTime(o, z.LastUpdate)
+	// string "ObjectsTotalCount"
+	o = append(o, 0xb1, 0x4f, 0x62, 0x6a, 0x65, 0x63, 0x74, 0x73, 0x54, 0x6f, 0x74, 0x61, 0x6c, 0x43, 0x6f, 0x75, 0x6e, 0x74)
+	o = msgp.AppendUint64(o, z.ObjectsTotalCount)
+	// string "ObjectsTotalSize"
+	o = append(o, 0xb0, 0x4f, 0x62, 0x6a, 0x65, 0x63, 0x74, 0x73, 0x54, 0x6f, 0x74, 0x61, 0x6c, 0x53, 0x69, 0x7a, 0x65)
+	o = msgp.AppendUint64(o, z.ObjectsTotalSize)
+	// string "ItemsHealed"
+	o = append(o, 0xab, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x48, 0x65, 0x61, 0x6c, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ItemsHealed)
+	// string "ItemsFailed"
+	o = append(o, 0xab, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ItemsFailed)
+	// string "BytesDone"
+	o = append(o, 0xa9, 0x42, 0x79, 0x74, 0x65, 0x73, 0x44, 0x6f, 0x6e, 0x65)
+	o = msgp.AppendUint64(o, z.BytesDone)
+	// string "BytesFailed"
+	o = append(o, 0xab, 0x42, 0x79, 0x74, 0x65, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.BytesFailed)
+	// string "Bucket"
+	o = append(o, 0xa6, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74)
+	o = msgp.AppendString(o, z.Bucket)
+	// string "Object"
+	o = append(o, 0xa6, 0x4f, 0x62, 0x6a, 0x65, 0x63, 0x74)
+	o = msgp.AppendString(o, z.Object)
+	// string "ResumeItemsHealed"
+	o = append(o, 0xb1, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x48, 0x65, 0x61, 0x6c, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ResumeItemsHealed)
+	// string "ResumeItemsFailed"
+	o = append(o, 0xb1, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ResumeItemsFailed)
+	// string "ResumeItemsSkipped"
+	o = append(o, 0xb2, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ResumeItemsSkipped)
+	// string "ResumeBytesDone"
+	o = append(o, 0xaf, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x44, 0x6f, 0x6e, 0x65)
+	o = msgp.AppendUint64(o, z.ResumeBytesDone)
+	// string "ResumeBytesFailed"
+	o = append(o, 0xb1, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x46, 0x61, 0x69, 0x6c, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ResumeBytesFailed)
+	// string "ResumeBytesSkipped"
+	o = append(o, 0xb2, 0x52, 0x65, 0x73, 0x75, 0x6d, 0x65, 0x42, 0x79, 0x74, 0x65, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ResumeBytesSkipped)
+	// string "QueuedBuckets"
+	o = append(o, 0xad, 0x51, 0x75, 0x65, 0x75, 0x65, 0x64, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74, 0x73)
+	o = msgp.AppendArrayHeader(o, uint32(len(z.QueuedBuckets)))
+	for za0001 := range z.QueuedBuckets {
+		o = msgp.AppendString(o, z.QueuedBuckets[za0001])
+	}
+	// string "HealedBuckets"
+	o = append(o, 0xad, 0x48, 0x65, 0x61, 0x6c, 0x65, 0x64, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74, 0x73)
+	o = msgp.AppendArrayHeader(o, uint32(len(z.HealedBuckets)))
+	for za0002 := range z.HealedBuckets {
+		o = msgp.AppendString(o, z.HealedBuckets[za0002])
+	}
+	// string "HealID"
+	o = append(o, 0xa6, 0x48, 0x65, 0x61, 0x6c, 0x49, 0x44)
+	o = msgp.AppendString(o, z.HealID)
+	// string "ItemsSkipped"
+	o = append(o, 0xac, 0x49, 0x74, 0x65, 0x6d, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.ItemsSkipped)
+	// string "BytesSkipped"
+	o = append(o, 0xac, 0x42, 0x79, 0x74, 0x65, 0x73, 0x53, 0x6b, 0x69, 0x70, 0x70, 0x65, 0x64)
+	o = msgp.AppendUint64(o, z.BytesSkipped)
+	// string "RetryAttempts"
+	o = append(o, 0xad, 0x52, 0x65, 0x74, 0x72, 0x79, 0x41, 0x74, 0x74, 0x65, 0x6d, 0x70, 0x74, 0x73)
+	o = msgp.AppendUint64(o, z.RetryAttempts)
+	// string "Finished"
+	o = append(o, 0xa8, 0x46, 0x69, 0x6e, 0x69, 0x73, 0x68, 0x65, 0x64)
+	o = msgp.AppendBool(o, z.Finished)
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *healingTracker) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "ID":
+			z.ID, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ID")
+				return
+			}
+		case "PoolIndex":
+			z.PoolIndex, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "PoolIndex")
+				return
+			}
+		case "SetIndex":
+			z.SetIndex, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "SetIndex")
+				return
+			}
+		case "DiskIndex":
+			z.DiskIndex, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "DiskIndex")
+				return
+			}
+		case "Path":
+			z.Path, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Path")
+				return
+			}
+		case "Endpoint":
+			z.Endpoint, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Endpoint")
+				return
+			}
+		case "Started":
+			z.Started, bts, err = msgp.ReadTimeBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Started")
+				return
+			}
+		case "LastUpdate":
+			z.LastUpdate, bts, err = msgp.ReadTimeBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "LastUpdate")
+				return
+			}
+		case "ObjectsTotalCount":
+			z.ObjectsTotalCount, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ObjectsTotalCount")
+				return
+			}
+		case "ObjectsTotalSize":
+			z.ObjectsTotalSize, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ObjectsTotalSize")
+				return
+			}
+		case "ItemsHealed":
+			z.ItemsHealed, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ItemsHealed")
+				return
+			}
+		case "ItemsFailed":
+			z.ItemsFailed, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ItemsFailed")
+				return
+			}
+		case "BytesDone":
+			z.BytesDone, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "BytesDone")
+				return
+			}
+		case "BytesFailed":
+			z.BytesFailed, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "BytesFailed")
+				return
+			}
+		case "Bucket":
+			z.Bucket, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Bucket")
+				return
+			}
+		case "Object":
+			z.Object, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Object")
+				return
+			}
+		case "ResumeItemsHealed":
+			z.ResumeItemsHealed, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeItemsHealed")
+				return
+			}
+		case "ResumeItemsFailed":
+			z.ResumeItemsFailed, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeItemsFailed")
+				return
+			}
+		case "ResumeItemsSkipped":
+			z.ResumeItemsSkipped, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeItemsSkipped")
+				return
+			}
+		case "ResumeBytesDone":
+			z.ResumeBytesDone, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeBytesDone")
+				return
+			}
+		case "ResumeBytesFailed":
+			z.ResumeBytesFailed, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeBytesFailed")
+				return
+			}
+		case "ResumeBytesSkipped":
+			z.ResumeBytesSkipped, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ResumeBytesSkipped")
+				return
+			}
+		case "QueuedBuckets":
+			var zb0002 uint32
+			zb0002, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "QueuedBuckets")
+				return
+			}
+			if cap(z.QueuedBuckets) >= int(zb0002) {
+				z.QueuedBuckets = (z.QueuedBuckets)[:zb0002]
+			} else {
+				z.QueuedBuckets = make([]string, zb0002)
+			}
+			for za0001 := range z.QueuedBuckets {
+				z.QueuedBuckets[za0001], bts, err = msgp.ReadStringBytes(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "QueuedBuckets", za0001)
+					return
+				}
+			}
+		case "HealedBuckets":
+			var zb0003 uint32
+			zb0003, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "HealedBuckets")
+				return
+			}
+			if cap(z.HealedBuckets) >= int(zb0003) {
+				z.HealedBuckets = (z.HealedBuckets)[:zb0003]
+			} else {
+				z.HealedBuckets = make([]string, zb0003)
+			}
+			for za0002 := range z.HealedBuckets {
+				z.HealedBuckets[za0002], bts, err = msgp.ReadStringBytes(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "HealedBuckets", za0002)
+					return
+				}
+			}
+		case "HealID":
+			z.HealID, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "HealID")
+				return
+			}
+		case "ItemsSkipped":
+			z.ItemsSkipped, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ItemsSkipped")
+				return
+			}
+		case "BytesSkipped":
+			z.BytesSkipped, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "BytesSkipped")
+				return
+			}
+		case "RetryAttempts":
+			z.RetryAttempts, bts, err = msgp.ReadUint64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "RetryAttempts")
+				return
+			}
+		case "Finished":
+			z.Finished, bts, err = msgp.ReadBoolBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Finished")
+				return
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *healingTracker) Msgsize() (s int) {
+	s = 3 + 3 + msgp.StringPrefixSize + len(z.ID) + 10 + msgp.IntSize + 9 + msgp.IntSize + 10 + msgp.IntSize + 5 + msgp.StringPrefixSize + len(z.Path) + 9 + msgp.StringPrefixSize + len(z.Endpoint) + 8 + msgp.TimeSize + 11 + msgp.TimeSize + 18 + msgp.Uint64Size + 17 + msgp.Uint64Size + 12 + msgp.Uint64Size + 12 + msgp.Uint64Size + 10 + msgp.Uint64Size + 12 + msgp.Uint64Size + 7 + msgp.StringPrefixSize + len(z.Bucket) + 7 + msgp.StringPrefixSize + len(z.Object) + 18 + msgp.Uint64Size + 18 + msgp.Uint64Size + 19 + msgp.Uint64Size + 16 + msgp.Uint64Size + 18 + msgp.Uint64Size + 19 + msgp.Uint64Size + 14 + msgp.ArrayHeaderSize
+	for za0001 := range z.QueuedBuckets {
+		s += msgp.StringPrefixSize + len(z.QueuedBuckets[za0001])
+	}
+	s += 14 + msgp.ArrayHeaderSize
+	for za0002 := range z.HealedBuckets {
+		s += msgp.StringPrefixSize + len(z.HealedBuckets[za0002])
+	}
+	s += 7 + msgp.StringPrefixSize + len(z.HealID) + 13 + msgp.Uint64Size + 13 + msgp.Uint64Size + 14 + msgp.Uint64Size + 9 + msgp.BoolSize
+	return
+}

cmd/background-newdisks-heal-ops_gen_test.go

@@ -0,0 +1,123 @@
+package cmd
+
+// Code generated by github.com/tinylib/msgp DO NOT EDIT.
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/tinylib/msgp/msgp"
+)
+
+func TestMarshalUnmarshalhealingTracker(t *testing.T) {
+	v := healingTracker{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsghealingTracker(b *testing.B) {
+	v := healingTracker{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsghealingTracker(b *testing.B) {
+	v := healingTracker{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalhealingTracker(b *testing.B) {
+	v := healingTracker{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodehealingTracker(t *testing.T) {
+	v := healingTracker{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodehealingTracker Msgsize() is inaccurate")
+	}
+
+	vn := healingTracker{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodehealingTracker(b *testing.B) {
+	v := healingTracker{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodehealingTracker(b *testing.B) {
+	v := healingTracker{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}

cmd/batch-expire.go

@@ -0,0 +1,839 @@
+// Copyright (c) 2015-2023 MinIO, Inc.
+//
+// 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 (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"runtime"
+	"strconv"
+	"time"
+
+	"github.com/minio/minio-go/v7/pkg/tags"
+	"github.com/minio/minio/internal/bucket/versioning"
+	xhttp "github.com/minio/minio/internal/http"
+	xioutil "github.com/minio/minio/internal/ioutil"
+	"github.com/minio/pkg/v3/env"
+	"github.com/minio/pkg/v3/wildcard"
+	"github.com/minio/pkg/v3/workers"
+	"github.com/minio/pkg/v3/xtime"
+	"gopkg.in/yaml.v3"
+)
+
+// expire: # Expire objects that match a condition
+//   apiVersion: v1
+//   bucket: mybucket # Bucket where this batch job will expire matching objects from
+//   prefix: myprefix # (Optional) Prefix under which this job will expire objects matching the rules below.
+//   rules:
+//     - type: object  # regular objects with zero or more older versions
+//       name: NAME # match object names that satisfy the wildcard expression.
+//       olderThan: 70h # match objects older than this value
+//       createdBefore: "2006-01-02T15:04:05.00Z" # match objects created before "date"
+//       tags:
+//         - key: name
+//           value: pick* # match objects with tag 'name', all values starting with 'pick'
+//       metadata:
+//         - key: content-type
+//           value: image/* # match objects with 'content-type', all values starting with 'image/'
+//       size:
+//         lessThan: "10MiB" # match objects with size less than this value (e.g. 10MiB)
+//         greaterThan: 1MiB # match objects with size greater than this value (e.g. 1MiB)
+//       purge:
+//           # retainVersions: 0 # (default) delete all versions of the object. This option is the fastest.
+//           # retainVersions: 5 # keep the latest 5 versions of the object.
+//
+//     - type: deleted # objects with delete marker as their latest version
+//       name: NAME # match object names that satisfy the wildcard expression.
+//       olderThan: 10h # match objects older than this value (e.g. 7d10h31s)
+//       createdBefore: "2006-01-02T15:04:05.00Z" # match objects created before "date"
+//       purge:
+//           # retainVersions: 0 # (default) delete all versions of the object. This option is the fastest.
+//           # retainVersions: 5 # keep the latest 5 versions of the object including delete markers.
+//
+//   notify:
+//     endpoint: https://notify.endpoint # notification endpoint to receive job completion status
+//     token: Bearer xxxxx # optional authentication token for the notification endpoint
+//
+//   retry:
+//     attempts: 10 # number of retries for the job before giving up
+//     delay: 500ms # least amount of delay between each retry
+
+//go:generate msgp -file $GOFILE
+
+// BatchJobExpirePurge type accepts non-negative versions to be retained
+type BatchJobExpirePurge struct {
+	line, col      int
+	RetainVersions int `yaml:"retainVersions" json:"retainVersions"`
+}
+
+var _ yaml.Unmarshaler = &BatchJobExpirePurge{}
+
+// UnmarshalYAML - BatchJobExpirePurge extends unmarshal to extract line, col
+func (p *BatchJobExpirePurge) UnmarshalYAML(val *yaml.Node) error {
+	type purge BatchJobExpirePurge
+	var tmp purge
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+
+	*p = BatchJobExpirePurge(tmp)
+	p.line, p.col = val.Line, val.Column
+	return nil
+}
+
+// Validate returns nil if value is valid, ie > 0.
+func (p BatchJobExpirePurge) Validate() error {
+	if p.RetainVersions < 0 {
+		return BatchJobYamlErr{
+			line: p.line,
+			col:  p.col,
+			msg:  "retainVersions must be >= 0",
+		}
+	}
+	return nil
+}
+
+// BatchJobExpireFilter holds all the filters currently supported for batch replication
+type BatchJobExpireFilter struct {
+	line, col     int
+	OlderThan     xtime.Duration      `yaml:"olderThan,omitempty" json:"olderThan"`
+	CreatedBefore *time.Time          `yaml:"createdBefore,omitempty" json:"createdBefore"`
+	Tags          []BatchJobKV        `yaml:"tags,omitempty" json:"tags"`
+	Metadata      []BatchJobKV        `yaml:"metadata,omitempty" json:"metadata"`
+	Size          BatchJobSizeFilter  `yaml:"size" json:"size"`
+	Type          string              `yaml:"type" json:"type"`
+	Name          string              `yaml:"name" json:"name"`
+	Purge         BatchJobExpirePurge `yaml:"purge" json:"purge"`
+}
+
+var _ yaml.Unmarshaler = &BatchJobExpireFilter{}
+
+// UnmarshalYAML - BatchJobExpireFilter extends unmarshal to extract line, col
+// information
+func (ef *BatchJobExpireFilter) UnmarshalYAML(value *yaml.Node) error {
+	type expFilter BatchJobExpireFilter
+	var tmp expFilter
+	err := value.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+	*ef = BatchJobExpireFilter(tmp)
+	ef.line, ef.col = value.Line, value.Column
+	return err
+}
+
+// Matches returns true if obj matches the filter conditions specified in ef.
+func (ef BatchJobExpireFilter) Matches(obj ObjectInfo, now time.Time) bool {
+	switch ef.Type {
+	case BatchJobExpireObject:
+		if obj.DeleteMarker {
+			return false
+		}
+	case BatchJobExpireDeleted:
+		if !obj.DeleteMarker {
+			return false
+		}
+	default:
+		// we should never come here, Validate should have caught this.
+		batchLogOnceIf(context.Background(), fmt.Errorf("invalid filter type: %s", ef.Type), ef.Type)
+		return false
+	}
+
+	if len(ef.Name) > 0 && !wildcard.Match(ef.Name, obj.Name) {
+		return false
+	}
+	if ef.OlderThan > 0 && now.Sub(obj.ModTime) <= ef.OlderThan.D() {
+		return false
+	}
+
+	if ef.CreatedBefore != nil && !obj.ModTime.Before(*ef.CreatedBefore) {
+		return false
+	}
+
+	if len(ef.Tags) > 0 && !obj.DeleteMarker {
+		// Only parse object tags if tags filter is specified.
+		var tagMap map[string]string
+		if len(obj.UserTags) != 0 {
+			t, err := tags.ParseObjectTags(obj.UserTags)
+			if err != nil {
+				return false
+			}
+			tagMap = t.ToMap()
+		}
+
+		for _, kv := range ef.Tags {
+			// Object (version) must match all tags specified in
+			// the filter
+			var match bool
+			for t, v := range tagMap {
+				if kv.Match(BatchJobKV{Key: t, Value: v}) {
+					match = true
+				}
+			}
+			if !match {
+				return false
+			}
+		}
+	}
+
+	if len(ef.Metadata) > 0 && !obj.DeleteMarker {
+		for _, kv := range ef.Metadata {
+			// Object (version) must match all x-amz-meta and
+			// standard metadata headers
+			// specified in the filter
+			var match bool
+			for k, v := range obj.UserDefined {
+				if !stringsHasPrefixFold(k, "x-amz-meta-") && !isStandardHeader(k) {
+					continue
+				}
+				// We only need to match x-amz-meta or standardHeaders
+				if kv.Match(BatchJobKV{Key: k, Value: v}) {
+					match = true
+				}
+			}
+			if !match {
+				return false
+			}
+		}
+	}
+
+	return ef.Size.InRange(obj.Size)
+}
+
+const (
+	// BatchJobExpireObject - object type
+	BatchJobExpireObject string = "object"
+	// BatchJobExpireDeleted - delete marker type
+	BatchJobExpireDeleted string = "deleted"
+)
+
+// Validate returns nil if ef has valid fields, validation error otherwise.
+func (ef BatchJobExpireFilter) Validate() error {
+	switch ef.Type {
+	case BatchJobExpireObject:
+	case BatchJobExpireDeleted:
+		if len(ef.Tags) > 0 || len(ef.Metadata) > 0 {
+			return BatchJobYamlErr{
+				line: ef.line,
+				col:  ef.col,
+				msg:  "delete type filter can't have tags or metadata",
+			}
+		}
+	default:
+		return BatchJobYamlErr{
+			line: ef.line,
+			col:  ef.col,
+			msg:  "invalid batch-expire type",
+		}
+	}
+
+	for _, tag := range ef.Tags {
+		if err := tag.Validate(); err != nil {
+			return err
+		}
+	}
+
+	for _, meta := range ef.Metadata {
+		if err := meta.Validate(); err != nil {
+			return err
+		}
+	}
+	if err := ef.Purge.Validate(); err != nil {
+		return err
+	}
+	if err := ef.Size.Validate(); err != nil {
+		return err
+	}
+	if ef.CreatedBefore != nil && !ef.CreatedBefore.Before(time.Now()) {
+		return BatchJobYamlErr{
+			line: ef.line,
+			col:  ef.col,
+			msg:  "CreatedBefore is in the future",
+		}
+	}
+	return nil
+}
+
+// BatchJobExpire represents configuration parameters for a batch expiration
+// job typically supplied in yaml form
+type BatchJobExpire struct {
+	line, col       int
+	APIVersion      string                 `yaml:"apiVersion" json:"apiVersion"`
+	Bucket          string                 `yaml:"bucket" json:"bucket"`
+	Prefix          BatchJobPrefix         `yaml:"prefix" json:"prefix"`
+	NotificationCfg BatchJobNotification   `yaml:"notify" json:"notify"`
+	Retry           BatchJobRetry          `yaml:"retry" json:"retry"`
+	Rules           []BatchJobExpireFilter `yaml:"rules" json:"rules"`
+}
+
+var _ yaml.Unmarshaler = &BatchJobExpire{}
+
+// RedactSensitive will redact any sensitive information in b.
+func (r *BatchJobExpire) RedactSensitive() {
+	if r == nil {
+		return
+	}
+	if r.NotificationCfg.Token != "" {
+		r.NotificationCfg.Token = redactedText
+	}
+}
+
+// UnmarshalYAML - BatchJobExpire extends default unmarshal to extract line, col information.
+func (r *BatchJobExpire) UnmarshalYAML(val *yaml.Node) error {
+	type expireJob BatchJobExpire
+	var tmp expireJob
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+
+	*r = BatchJobExpire(tmp)
+	r.line, r.col = val.Line, val.Column
+	return nil
+}
+
+// Notify notifies notification endpoint if configured regarding job failure or success.
+func (r BatchJobExpire) Notify(ctx context.Context, body io.Reader) error {
+	if r.NotificationCfg.Endpoint == "" {
+		return nil
+	}
+
+	ctx, cancel := context.WithTimeout(ctx, 10*time.Second)
+	defer cancel()
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, r.NotificationCfg.Endpoint, body)
+	if err != nil {
+		return err
+	}
+
+	if r.NotificationCfg.Token != "" {
+		req.Header.Set("Authorization", r.NotificationCfg.Token)
+	}
+
+	clnt := http.Client{Transport: getRemoteInstanceTransport()}
+	resp, err := clnt.Do(req)
+	if err != nil {
+		return err
+	}
+
+	xhttp.DrainBody(resp.Body)
+	if resp.StatusCode != http.StatusOK {
+		return errors.New(resp.Status)
+	}
+
+	return nil
+}
+
+// Expire expires object versions which have already matched supplied filter conditions
+func (r *BatchJobExpire) Expire(ctx context.Context, api ObjectLayer, vc *versioning.Versioning, objsToDel []ObjectToDelete) []error {
+	opts := ObjectOptions{
+		PrefixEnabledFn:  vc.PrefixEnabled,
+		VersionSuspended: vc.Suspended(),
+	}
+
+	allErrs := make([]error, 0, len(objsToDel))
+
+	for {
+		count := len(objsToDel)
+		if count == 0 {
+			break
+		}
+		if count > maxDeleteList {
+			count = maxDeleteList
+		}
+		_, errs := api.DeleteObjects(ctx, r.Bucket, objsToDel[:count], opts)
+		allErrs = append(allErrs, errs...)
+		// Next batch of deletion
+		objsToDel = objsToDel[count:]
+	}
+
+	return allErrs
+}
+
+const (
+	batchExpireName                 = "batch-expire.bin"
+	batchExpireFormat               = 1
+	batchExpireVersionV1            = 1
+	batchExpireVersion              = batchExpireVersionV1
+	batchExpireAPIVersion           = "v1"
+	batchExpireJobDefaultRetries    = 3
+	batchExpireJobDefaultRetryDelay = 250 * time.Millisecond
+)
+
+type objInfoCache map[string]*ObjectInfo
+
+func newObjInfoCache() objInfoCache {
+	return objInfoCache(make(map[string]*ObjectInfo))
+}
+
+func (oiCache objInfoCache) Add(toDel ObjectToDelete, oi *ObjectInfo) {
+	oiCache[fmt.Sprintf("%s-%s", toDel.ObjectName, toDel.VersionID)] = oi
+}
+
+func (oiCache objInfoCache) Get(toDel ObjectToDelete) (*ObjectInfo, bool) {
+	oi, ok := oiCache[fmt.Sprintf("%s-%s", toDel.ObjectName, toDel.VersionID)]
+	return oi, ok
+}
+
+func batchObjsForDelete(ctx context.Context, r *BatchJobExpire, ri *batchJobInfo, job BatchJobRequest, api ObjectLayer, wk *workers.Workers, expireCh <-chan []expireObjInfo) {
+	vc, _ := globalBucketVersioningSys.Get(r.Bucket)
+	retryAttempts := job.Expire.Retry.Attempts
+	if retryAttempts <= 0 {
+		retryAttempts = batchExpireJobDefaultRetries
+	}
+	delay := job.Expire.Retry.Delay
+	if delay <= 0 {
+		delay = batchExpireJobDefaultRetryDelay
+	}
+
+	var i int
+	for toExpire := range expireCh {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+		}
+		if i > 0 {
+			if wait := globalBatchConfig.ExpirationWait(); wait > 0 {
+				time.Sleep(wait)
+			}
+		}
+		i++
+		wk.Take()
+		go func(toExpire []expireObjInfo) {
+			defer wk.Give()
+
+			toExpireAll := make([]expireObjInfo, 0, len(toExpire))
+			toDel := make([]ObjectToDelete, 0, len(toExpire))
+			oiCache := newObjInfoCache()
+			for _, exp := range toExpire {
+				if exp.ExpireAll {
+					toExpireAll = append(toExpireAll, exp)
+					continue
+				}
+				// Cache ObjectInfo value via pointers for
+				// subsequent use to track objects which
+				// couldn't be deleted.
+				od := ObjectToDelete{
+					ObjectV: ObjectV{
+						ObjectName: exp.Name,
+						VersionID:  exp.VersionID,
+					},
+				}
+				toDel = append(toDel, od)
+				oiCache.Add(od, &exp.ObjectInfo)
+			}
+
+			// DeleteObject(deletePrefix: true) to expire all versions of an object
+			for _, exp := range toExpireAll {
+				var success bool
+				for attempts := 1; attempts <= retryAttempts; attempts++ {
+					select {
+					case <-ctx.Done():
+						ri.trackMultipleObjectVersions(exp, success)
+						return
+					default:
+					}
+					stopFn := globalBatchJobsMetrics.trace(batchJobMetricExpire, ri.JobID, attempts)
+					_, err := api.DeleteObject(ctx, exp.Bucket, encodeDirObject(exp.Name), ObjectOptions{
+						DeletePrefix:       true,
+						DeletePrefixObject: true, // use prefix delete on exact object (this is an optimization to avoid fan-out calls)
+					})
+					if err != nil {
+						stopFn(exp, err)
+						batchLogIf(ctx, fmt.Errorf("Failed to expire %s/%s due to %v (attempts=%d)", exp.Bucket, exp.Name, err, attempts))
+					} else {
+						stopFn(exp, err)
+						success = true
+						break
+					}
+				}
+				ri.trackMultipleObjectVersions(exp, success)
+			}
+
+			// DeleteMultiple objects
+			toDelCopy := make([]ObjectToDelete, len(toDel))
+			for attempts := 1; attempts <= retryAttempts; attempts++ {
+				select {
+				case <-ctx.Done():
+					return
+				default:
+				}
+
+				stopFn := globalBatchJobsMetrics.trace(batchJobMetricExpire, ri.JobID, attempts)
+				// Copying toDel to select from objects whose
+				// deletion failed
+				copy(toDelCopy, toDel)
+				var failed int
+				errs := r.Expire(ctx, api, vc, toDel)
+				// reslice toDel in preparation for next retry attempt
+				toDel = toDel[:0]
+				for i, err := range errs {
+					if err != nil {
+						stopFn(toDelCopy[i], err)
+						batchLogIf(ctx, fmt.Errorf("Failed to expire %s/%s versionID=%s due to %v (attempts=%d)", ri.Bucket, toDelCopy[i].ObjectName, toDelCopy[i].VersionID,
+							err, attempts))
+						failed++
+						if oi, ok := oiCache.Get(toDelCopy[i]); ok {
+							ri.trackCurrentBucketObject(r.Bucket, *oi, false, attempts)
+						}
+						if attempts != retryAttempts {
+							// retry
+							toDel = append(toDel, toDelCopy[i])
+						}
+					} else {
+						stopFn(toDelCopy[i], nil)
+						if oi, ok := oiCache.Get(toDelCopy[i]); ok {
+							ri.trackCurrentBucketObject(r.Bucket, *oi, true, attempts)
+						}
+					}
+				}
+
+				globalBatchJobsMetrics.save(ri.JobID, ri)
+
+				if failed == 0 {
+					break
+				}
+
+				// Add a delay between retry attempts
+				if attempts < retryAttempts {
+					time.Sleep(delay)
+				}
+			}
+		}(toExpire)
+	}
+}
+
+type expireObjInfo struct {
+	ObjectInfo
+	ExpireAll         bool
+	DeleteMarkerCount int64
+}
+
+// Start the batch expiration job, resumes if there was a pending job via "job.ID"
+func (r *BatchJobExpire) Start(ctx context.Context, api ObjectLayer, job BatchJobRequest) error {
+	ri := &batchJobInfo{
+		JobID:     job.ID,
+		JobType:   string(job.Type()),
+		StartTime: job.Started,
+	}
+	if err := ri.loadOrInit(ctx, api, job); err != nil {
+		return err
+	}
+
+	globalBatchJobsMetrics.save(job.ID, ri)
+	lastObject := ri.Object
+
+	now := time.Now().UTC()
+
+	workerSize, err := strconv.Atoi(env.Get("_MINIO_BATCH_EXPIRATION_WORKERS", strconv.Itoa(runtime.GOMAXPROCS(0)/2)))
+	if err != nil {
+		return err
+	}
+
+	wk, err := workers.New(workerSize)
+	if err != nil {
+		// invalid worker size.
+		return err
+	}
+
+	ctx, cancelCause := context.WithCancelCause(ctx)
+	defer cancelCause(nil)
+
+	results := make(chan itemOrErr[ObjectInfo], workerSize)
+	go func() {
+		prefixes := r.Prefix.F()
+		if len(prefixes) == 0 {
+			prefixes = []string{""}
+		}
+		for _, prefix := range prefixes {
+			prefixResultCh := make(chan itemOrErr[ObjectInfo], workerSize)
+			err := api.Walk(ctx, r.Bucket, prefix, prefixResultCh, WalkOptions{
+				Marker:       lastObject,
+				LatestOnly:   false, // we need to visit all versions of the object to implement purge: retainVersions
+				VersionsSort: WalkVersionsSortDesc,
+			})
+			if err != nil {
+				cancelCause(err)
+				xioutil.SafeClose(results)
+				return
+			}
+			for result := range prefixResultCh {
+				results <- result
+			}
+		}
+		xioutil.SafeClose(results)
+	}()
+
+	// Goroutine to periodically save batch-expire job's in-memory state
+	saverQuitCh := make(chan struct{})
+	go func() {
+		saveTicker := time.NewTicker(10 * time.Second)
+		defer saveTicker.Stop()
+		quit := false
+		after := time.Minute
+		for !quit {
+			select {
+			case <-saveTicker.C:
+			case <-ctx.Done():
+				quit = true
+			case <-saverQuitCh:
+				quit = true
+			}
+
+			if quit {
+				// save immediately if we are quitting
+				after = 0
+			}
+
+			ctx, cancel := context.WithTimeout(GlobalContext, 30*time.Second) // independent context
+			batchLogIf(ctx, ri.updateAfter(ctx, api, after, job))
+			cancel()
+		}
+	}()
+
+	expireCh := make(chan []expireObjInfo, workerSize)
+	expireDoneCh := make(chan struct{})
+	go func() {
+		defer close(expireDoneCh)
+		batchObjsForDelete(ctx, r, ri, job, api, wk, expireCh)
+	}()
+
+	var (
+		prevObj       ObjectInfo
+		matchedFilter BatchJobExpireFilter
+		versionsCount int
+		toDel         []expireObjInfo
+		failed        bool
+		done          bool
+	)
+	deleteMarkerCountMap := map[string]int64{}
+	pushToExpire := func() {
+		// set preObject deleteMarkerCount
+		if len(toDel) > 0 {
+			lastDelIndex := len(toDel) - 1
+			lastDel := toDel[lastDelIndex]
+			if lastDel.ExpireAll {
+				toDel[lastDelIndex].DeleteMarkerCount = deleteMarkerCountMap[lastDel.Name]
+				// delete the key
+				delete(deleteMarkerCountMap, lastDel.Name)
+			}
+		}
+		// send down filtered entries to be deleted using
+		// DeleteObjects method
+		if len(toDel) > 10 { // batch up to 10 objects/versions to be expired simultaneously.
+			xfer := make([]expireObjInfo, len(toDel))
+			copy(xfer, toDel)
+			select {
+			case expireCh <- xfer:
+				toDel = toDel[:0] // resetting toDel
+			case <-ctx.Done():
+				done = true
+			}
+		}
+	}
+	for {
+		select {
+		case result, ok := <-results:
+			if !ok {
+				done = true
+				break
+			}
+			if result.Err != nil {
+				failed = true
+				batchLogIf(ctx, result.Err)
+				continue
+			}
+			if result.Item.DeleteMarker {
+				deleteMarkerCountMap[result.Item.Name]++
+			}
+			// Apply filter to find the matching rule to apply expiry
+			// actions accordingly.
+			// nolint:gocritic
+			if result.Item.IsLatest {
+				var match BatchJobExpireFilter
+				var found bool
+				for _, rule := range r.Rules {
+					if rule.Matches(result.Item, now) {
+						match = rule
+						found = true
+						break
+					}
+				}
+				if !found {
+					continue
+				}
+
+				if prevObj.Name != result.Item.Name {
+					// switch the object
+					pushToExpire()
+				}
+
+				prevObj = result.Item
+				matchedFilter = match
+				versionsCount = 1
+				// Include the latest version
+				if matchedFilter.Purge.RetainVersions == 0 {
+					toDel = append(toDel, expireObjInfo{
+						ObjectInfo: result.Item,
+						ExpireAll:  true,
+					})
+					continue
+				}
+			} else if prevObj.Name == result.Item.Name {
+				if matchedFilter.Purge.RetainVersions == 0 {
+					continue // including latest version in toDel suffices, skipping other versions
+				}
+				versionsCount++
+			} else {
+				// switch the object
+				pushToExpire()
+				// a file switched with no LatestVersion, logging it
+				batchLogIf(ctx, fmt.Errorf("skipping object %s, no latest version found", result.Item.Name))
+				continue
+			}
+
+			if versionsCount <= matchedFilter.Purge.RetainVersions {
+				continue // retain versions
+			}
+			toDel = append(toDel, expireObjInfo{
+				ObjectInfo: result.Item,
+			})
+			pushToExpire()
+		case <-ctx.Done():
+			done = true
+		}
+		if done {
+			break
+		}
+	}
+
+	if context.Cause(ctx) != nil {
+		xioutil.SafeClose(expireCh)
+		return context.Cause(ctx)
+	}
+	pushToExpire()
+	// Send any remaining objects downstream
+	if len(toDel) > 0 {
+		select {
+		case <-ctx.Done():
+		case expireCh <- toDel:
+		}
+	}
+	xioutil.SafeClose(expireCh)
+
+	<-expireDoneCh // waits for the expire goroutine to complete
+	wk.Wait()      // waits for all expire workers to retire
+
+	ri.Complete = !failed && ri.ObjectsFailed == 0
+	ri.Failed = failed || ri.ObjectsFailed > 0
+	globalBatchJobsMetrics.save(job.ID, ri)
+
+	// Close the saverQuitCh - this also triggers saving in-memory state
+	// immediately one last time before we exit this method.
+	xioutil.SafeClose(saverQuitCh)
+
+	// Notify expire jobs final status to the configured endpoint
+	buf, _ := json.Marshal(ri)
+	if err := r.Notify(context.Background(), bytes.NewReader(buf)); err != nil {
+		batchLogIf(context.Background(), fmt.Errorf("unable to notify %v", err))
+	}
+
+	return nil
+}
+
+//msgp:ignore batchExpireJobError
+type batchExpireJobError struct {
+	Code           string
+	Description    string
+	HTTPStatusCode int
+}
+
+func (e batchExpireJobError) Error() string {
+	return e.Description
+}
+
+// maxBatchRules maximum number of rules a batch-expiry job supports
+const maxBatchRules = 50
+
+// Validate validates the job definition input
+func (r *BatchJobExpire) Validate(ctx context.Context, job BatchJobRequest, o ObjectLayer) error {
+	if r == nil {
+		return nil
+	}
+
+	if r.APIVersion != batchExpireAPIVersion {
+		return batchExpireJobError{
+			Code:           "InvalidArgument",
+			Description:    "Unsupported batch expire API version",
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	}
+
+	if r.Bucket == "" {
+		return batchExpireJobError{
+			Code:           "InvalidArgument",
+			Description:    "Bucket argument missing",
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	}
+
+	if _, err := o.GetBucketInfo(ctx, r.Bucket, BucketOptions{}); err != nil {
+		if isErrBucketNotFound(err) {
+			return batchExpireJobError{
+				Code:           "NoSuchSourceBucket",
+				Description:    "The specified source bucket does not exist",
+				HTTPStatusCode: http.StatusNotFound,
+			}
+		}
+		return err
+	}
+
+	if len(r.Rules) > maxBatchRules {
+		return batchExpireJobError{
+			Code:           "InvalidArgument",
+			Description:    "Too many rules. Batch expire job can't have more than 100 rules",
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	}
+
+	for _, rule := range r.Rules {
+		if err := rule.Validate(); err != nil {
+			return batchExpireJobError{
+				Code:           "InvalidArgument",
+				Description:    fmt.Sprintf("Invalid batch expire rule: %s", err),
+				HTTPStatusCode: http.StatusBadRequest,
+			}
+		}
+	}
+
+	if err := r.Retry.Validate(); err != nil {
+		return batchExpireJobError{
+			Code:           "InvalidArgument",
+			Description:    fmt.Sprintf("Invalid batch expire retry configuration: %s", err),
+			HTTPStatusCode: http.StatusBadRequest,
+		}
+	}
+	return nil
+}

cmd/batch-expire_gen.go

@@ -0,0 +1,864 @@
+package cmd
+
+// Code generated by github.com/tinylib/msgp DO NOT EDIT.
+
+import (
+	"time"
+
+	"github.com/tinylib/msgp/msgp"
+)
+
+// DecodeMsg implements msgp.Decodable
+func (z *BatchJobExpire) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "APIVersion":
+			z.APIVersion, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "APIVersion")
+				return
+			}
+		case "Bucket":
+			z.Bucket, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Bucket")
+				return
+			}
+		case "Prefix":
+			err = z.Prefix.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "Prefix")
+				return
+			}
+		case "NotificationCfg":
+			err = z.NotificationCfg.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "NotificationCfg")
+				return
+			}
+		case "Retry":
+			err = z.Retry.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "Retry")
+				return
+			}
+		case "Rules":
+			var zb0002 uint32
+			zb0002, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "Rules")
+				return
+			}
+			if cap(z.Rules) >= int(zb0002) {
+				z.Rules = (z.Rules)[:zb0002]
+			} else {
+				z.Rules = make([]BatchJobExpireFilter, zb0002)
+			}
+			for za0001 := range z.Rules {
+				err = z.Rules[za0001].DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "Rules", za0001)
+					return
+				}
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z *BatchJobExpire) EncodeMsg(en *msgp.Writer) (err error) {
+	// map header, size 6
+	// write "APIVersion"
+	err = en.Append(0x86, 0xaa, 0x41, 0x50, 0x49, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.APIVersion)
+	if err != nil {
+		err = msgp.WrapError(err, "APIVersion")
+		return
+	}
+	// write "Bucket"
+	err = en.Append(0xa6, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Bucket)
+	if err != nil {
+		err = msgp.WrapError(err, "Bucket")
+		return
+	}
+	// write "Prefix"
+	err = en.Append(0xa6, 0x50, 0x72, 0x65, 0x66, 0x69, 0x78)
+	if err != nil {
+		return
+	}
+	err = z.Prefix.EncodeMsg(en)
+	if err != nil {
+		err = msgp.WrapError(err, "Prefix")
+		return
+	}
+	// write "NotificationCfg"
+	err = en.Append(0xaf, 0x4e, 0x6f, 0x74, 0x69, 0x66, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x66, 0x67)
+	if err != nil {
+		return
+	}
+	err = z.NotificationCfg.EncodeMsg(en)
+	if err != nil {
+		err = msgp.WrapError(err, "NotificationCfg")
+		return
+	}
+	// write "Retry"
+	err = en.Append(0xa5, 0x52, 0x65, 0x74, 0x72, 0x79)
+	if err != nil {
+		return
+	}
+	err = z.Retry.EncodeMsg(en)
+	if err != nil {
+		err = msgp.WrapError(err, "Retry")
+		return
+	}
+	// write "Rules"
+	err = en.Append(0xa5, 0x52, 0x75, 0x6c, 0x65, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteArrayHeader(uint32(len(z.Rules)))
+	if err != nil {
+		err = msgp.WrapError(err, "Rules")
+		return
+	}
+	for za0001 := range z.Rules {
+		err = z.Rules[za0001].EncodeMsg(en)
+		if err != nil {
+			err = msgp.WrapError(err, "Rules", za0001)
+			return
+		}
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z *BatchJobExpire) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	// map header, size 6
+	// string "APIVersion"
+	o = append(o, 0x86, 0xaa, 0x41, 0x50, 0x49, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e)
+	o = msgp.AppendString(o, z.APIVersion)
+	// string "Bucket"
+	o = append(o, 0xa6, 0x42, 0x75, 0x63, 0x6b, 0x65, 0x74)
+	o = msgp.AppendString(o, z.Bucket)
+	// string "Prefix"
+	o = append(o, 0xa6, 0x50, 0x72, 0x65, 0x66, 0x69, 0x78)
+	o, err = z.Prefix.MarshalMsg(o)
+	if err != nil {
+		err = msgp.WrapError(err, "Prefix")
+		return
+	}
+	// string "NotificationCfg"
+	o = append(o, 0xaf, 0x4e, 0x6f, 0x74, 0x69, 0x66, 0x69, 0x63, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x43, 0x66, 0x67)
+	o, err = z.NotificationCfg.MarshalMsg(o)
+	if err != nil {
+		err = msgp.WrapError(err, "NotificationCfg")
+		return
+	}
+	// string "Retry"
+	o = append(o, 0xa5, 0x52, 0x65, 0x74, 0x72, 0x79)
+	o, err = z.Retry.MarshalMsg(o)
+	if err != nil {
+		err = msgp.WrapError(err, "Retry")
+		return
+	}
+	// string "Rules"
+	o = append(o, 0xa5, 0x52, 0x75, 0x6c, 0x65, 0x73)
+	o = msgp.AppendArrayHeader(o, uint32(len(z.Rules)))
+	for za0001 := range z.Rules {
+		o, err = z.Rules[za0001].MarshalMsg(o)
+		if err != nil {
+			err = msgp.WrapError(err, "Rules", za0001)
+			return
+		}
+	}
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *BatchJobExpire) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "APIVersion":
+			z.APIVersion, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "APIVersion")
+				return
+			}
+		case "Bucket":
+			z.Bucket, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Bucket")
+				return
+			}
+		case "Prefix":
+			bts, err = z.Prefix.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Prefix")
+				return
+			}
+		case "NotificationCfg":
+			bts, err = z.NotificationCfg.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "NotificationCfg")
+				return
+			}
+		case "Retry":
+			bts, err = z.Retry.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Retry")
+				return
+			}
+		case "Rules":
+			var zb0002 uint32
+			zb0002, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Rules")
+				return
+			}
+			if cap(z.Rules) >= int(zb0002) {
+				z.Rules = (z.Rules)[:zb0002]
+			} else {
+				z.Rules = make([]BatchJobExpireFilter, zb0002)
+			}
+			for za0001 := range z.Rules {
+				bts, err = z.Rules[za0001].UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Rules", za0001)
+					return
+				}
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *BatchJobExpire) Msgsize() (s int) {
+	s = 1 + 11 + msgp.StringPrefixSize + len(z.APIVersion) + 7 + msgp.StringPrefixSize + len(z.Bucket) + 7 + z.Prefix.Msgsize() + 16 + z.NotificationCfg.Msgsize() + 6 + z.Retry.Msgsize() + 6 + msgp.ArrayHeaderSize
+	for za0001 := range z.Rules {
+		s += z.Rules[za0001].Msgsize()
+	}
+	return
+}
+
+// DecodeMsg implements msgp.Decodable
+func (z *BatchJobExpireFilter) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "OlderThan":
+			err = z.OlderThan.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "OlderThan")
+				return
+			}
+		case "CreatedBefore":
+			if dc.IsNil() {
+				err = dc.ReadNil()
+				if err != nil {
+					err = msgp.WrapError(err, "CreatedBefore")
+					return
+				}
+				z.CreatedBefore = nil
+			} else {
+				if z.CreatedBefore == nil {
+					z.CreatedBefore = new(time.Time)
+				}
+				*z.CreatedBefore, err = dc.ReadTime()
+				if err != nil {
+					err = msgp.WrapError(err, "CreatedBefore")
+					return
+				}
+			}
+		case "Tags":
+			var zb0002 uint32
+			zb0002, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "Tags")
+				return
+			}
+			if cap(z.Tags) >= int(zb0002) {
+				z.Tags = (z.Tags)[:zb0002]
+			} else {
+				z.Tags = make([]BatchJobKV, zb0002)
+			}
+			for za0001 := range z.Tags {
+				err = z.Tags[za0001].DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "Tags", za0001)
+					return
+				}
+			}
+		case "Metadata":
+			var zb0003 uint32
+			zb0003, err = dc.ReadArrayHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "Metadata")
+				return
+			}
+			if cap(z.Metadata) >= int(zb0003) {
+				z.Metadata = (z.Metadata)[:zb0003]
+			} else {
+				z.Metadata = make([]BatchJobKV, zb0003)
+			}
+			for za0002 := range z.Metadata {
+				err = z.Metadata[za0002].DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "Metadata", za0002)
+					return
+				}
+			}
+		case "Size":
+			err = z.Size.DecodeMsg(dc)
+			if err != nil {
+				err = msgp.WrapError(err, "Size")
+				return
+			}
+		case "Type":
+			z.Type, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Type")
+				return
+			}
+		case "Name":
+			z.Name, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Name")
+				return
+			}
+		case "Purge":
+			var zb0004 uint32
+			zb0004, err = dc.ReadMapHeader()
+			if err != nil {
+				err = msgp.WrapError(err, "Purge")
+				return
+			}
+			for zb0004 > 0 {
+				zb0004--
+				field, err = dc.ReadMapKeyPtr()
+				if err != nil {
+					err = msgp.WrapError(err, "Purge")
+					return
+				}
+				switch msgp.UnsafeString(field) {
+				case "RetainVersions":
+					z.Purge.RetainVersions, err = dc.ReadInt()
+					if err != nil {
+						err = msgp.WrapError(err, "Purge", "RetainVersions")
+						return
+					}
+				default:
+					err = dc.Skip()
+					if err != nil {
+						err = msgp.WrapError(err, "Purge")
+						return
+					}
+				}
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z *BatchJobExpireFilter) EncodeMsg(en *msgp.Writer) (err error) {
+	// map header, size 8
+	// write "OlderThan"
+	err = en.Append(0x88, 0xa9, 0x4f, 0x6c, 0x64, 0x65, 0x72, 0x54, 0x68, 0x61, 0x6e)
+	if err != nil {
+		return
+	}
+	err = z.OlderThan.EncodeMsg(en)
+	if err != nil {
+		err = msgp.WrapError(err, "OlderThan")
+		return
+	}
+	// write "CreatedBefore"
+	err = en.Append(0xad, 0x43, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x42, 0x65, 0x66, 0x6f, 0x72, 0x65)
+	if err != nil {
+		return
+	}
+	if z.CreatedBefore == nil {
+		err = en.WriteNil()
+		if err != nil {
+			return
+		}
+	} else {
+		err = en.WriteTime(*z.CreatedBefore)
+		if err != nil {
+			err = msgp.WrapError(err, "CreatedBefore")
+			return
+		}
+	}
+	// write "Tags"
+	err = en.Append(0xa4, 0x54, 0x61, 0x67, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteArrayHeader(uint32(len(z.Tags)))
+	if err != nil {
+		err = msgp.WrapError(err, "Tags")
+		return
+	}
+	for za0001 := range z.Tags {
+		err = z.Tags[za0001].EncodeMsg(en)
+		if err != nil {
+			err = msgp.WrapError(err, "Tags", za0001)
+			return
+		}
+	}
+	// write "Metadata"
+	err = en.Append(0xa8, 0x4d, 0x65, 0x74, 0x61, 0x64, 0x61, 0x74, 0x61)
+	if err != nil {
+		return
+	}
+	err = en.WriteArrayHeader(uint32(len(z.Metadata)))
+	if err != nil {
+		err = msgp.WrapError(err, "Metadata")
+		return
+	}
+	for za0002 := range z.Metadata {
+		err = z.Metadata[za0002].EncodeMsg(en)
+		if err != nil {
+			err = msgp.WrapError(err, "Metadata", za0002)
+			return
+		}
+	}
+	// write "Size"
+	err = en.Append(0xa4, 0x53, 0x69, 0x7a, 0x65)
+	if err != nil {
+		return
+	}
+	err = z.Size.EncodeMsg(en)
+	if err != nil {
+		err = msgp.WrapError(err, "Size")
+		return
+	}
+	// write "Type"
+	err = en.Append(0xa4, 0x54, 0x79, 0x70, 0x65)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Type)
+	if err != nil {
+		err = msgp.WrapError(err, "Type")
+		return
+	}
+	// write "Name"
+	err = en.Append(0xa4, 0x4e, 0x61, 0x6d, 0x65)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Name)
+	if err != nil {
+		err = msgp.WrapError(err, "Name")
+		return
+	}
+	// write "Purge"
+	err = en.Append(0xa5, 0x50, 0x75, 0x72, 0x67, 0x65)
+	if err != nil {
+		return
+	}
+	// map header, size 1
+	// write "RetainVersions"
+	err = en.Append(0x81, 0xae, 0x52, 0x65, 0x74, 0x61, 0x69, 0x6e, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.Purge.RetainVersions)
+	if err != nil {
+		err = msgp.WrapError(err, "Purge", "RetainVersions")
+		return
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z *BatchJobExpireFilter) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	// map header, size 8
+	// string "OlderThan"
+	o = append(o, 0x88, 0xa9, 0x4f, 0x6c, 0x64, 0x65, 0x72, 0x54, 0x68, 0x61, 0x6e)
+	o, err = z.OlderThan.MarshalMsg(o)
+	if err != nil {
+		err = msgp.WrapError(err, "OlderThan")
+		return
+	}
+	// string "CreatedBefore"
+	o = append(o, 0xad, 0x43, 0x72, 0x65, 0x61, 0x74, 0x65, 0x64, 0x42, 0x65, 0x66, 0x6f, 0x72, 0x65)
+	if z.CreatedBefore == nil {
+		o = msgp.AppendNil(o)
+	} else {
+		o = msgp.AppendTime(o, *z.CreatedBefore)
+	}
+	// string "Tags"
+	o = append(o, 0xa4, 0x54, 0x61, 0x67, 0x73)
+	o = msgp.AppendArrayHeader(o, uint32(len(z.Tags)))
+	for za0001 := range z.Tags {
+		o, err = z.Tags[za0001].MarshalMsg(o)
+		if err != nil {
+			err = msgp.WrapError(err, "Tags", za0001)
+			return
+		}
+	}
+	// string "Metadata"
+	o = append(o, 0xa8, 0x4d, 0x65, 0x74, 0x61, 0x64, 0x61, 0x74, 0x61)
+	o = msgp.AppendArrayHeader(o, uint32(len(z.Metadata)))
+	for za0002 := range z.Metadata {
+		o, err = z.Metadata[za0002].MarshalMsg(o)
+		if err != nil {
+			err = msgp.WrapError(err, "Metadata", za0002)
+			return
+		}
+	}
+	// string "Size"
+	o = append(o, 0xa4, 0x53, 0x69, 0x7a, 0x65)
+	o, err = z.Size.MarshalMsg(o)
+	if err != nil {
+		err = msgp.WrapError(err, "Size")
+		return
+	}
+	// string "Type"
+	o = append(o, 0xa4, 0x54, 0x79, 0x70, 0x65)
+	o = msgp.AppendString(o, z.Type)
+	// string "Name"
+	o = append(o, 0xa4, 0x4e, 0x61, 0x6d, 0x65)
+	o = msgp.AppendString(o, z.Name)
+	// string "Purge"
+	o = append(o, 0xa5, 0x50, 0x75, 0x72, 0x67, 0x65)
+	// map header, size 1
+	// string "RetainVersions"
+	o = append(o, 0x81, 0xae, 0x52, 0x65, 0x74, 0x61, 0x69, 0x6e, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73)
+	o = msgp.AppendInt(o, z.Purge.RetainVersions)
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *BatchJobExpireFilter) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "OlderThan":
+			bts, err = z.OlderThan.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "OlderThan")
+				return
+			}
+		case "CreatedBefore":
+			if msgp.IsNil(bts) {
+				bts, err = msgp.ReadNilBytes(bts)
+				if err != nil {
+					return
+				}
+				z.CreatedBefore = nil
+			} else {
+				if z.CreatedBefore == nil {
+					z.CreatedBefore = new(time.Time)
+				}
+				*z.CreatedBefore, bts, err = msgp.ReadTimeBytes(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "CreatedBefore")
+					return
+				}
+			}
+		case "Tags":
+			var zb0002 uint32
+			zb0002, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Tags")
+				return
+			}
+			if cap(z.Tags) >= int(zb0002) {
+				z.Tags = (z.Tags)[:zb0002]
+			} else {
+				z.Tags = make([]BatchJobKV, zb0002)
+			}
+			for za0001 := range z.Tags {
+				bts, err = z.Tags[za0001].UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Tags", za0001)
+					return
+				}
+			}
+		case "Metadata":
+			var zb0003 uint32
+			zb0003, bts, err = msgp.ReadArrayHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Metadata")
+				return
+			}
+			if cap(z.Metadata) >= int(zb0003) {
+				z.Metadata = (z.Metadata)[:zb0003]
+			} else {
+				z.Metadata = make([]BatchJobKV, zb0003)
+			}
+			for za0002 := range z.Metadata {
+				bts, err = z.Metadata[za0002].UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Metadata", za0002)
+					return
+				}
+			}
+		case "Size":
+			bts, err = z.Size.UnmarshalMsg(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Size")
+				return
+			}
+		case "Type":
+			z.Type, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Type")
+				return
+			}
+		case "Name":
+			z.Name, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Name")
+				return
+			}
+		case "Purge":
+			var zb0004 uint32
+			zb0004, bts, err = msgp.ReadMapHeaderBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Purge")
+				return
+			}
+			for zb0004 > 0 {
+				zb0004--
+				field, bts, err = msgp.ReadMapKeyZC(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Purge")
+					return
+				}
+				switch msgp.UnsafeString(field) {
+				case "RetainVersions":
+					z.Purge.RetainVersions, bts, err = msgp.ReadIntBytes(bts)
+					if err != nil {
+						err = msgp.WrapError(err, "Purge", "RetainVersions")
+						return
+					}
+				default:
+					bts, err = msgp.Skip(bts)
+					if err != nil {
+						err = msgp.WrapError(err, "Purge")
+						return
+					}
+				}
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *BatchJobExpireFilter) Msgsize() (s int) {
+	s = 1 + 10 + z.OlderThan.Msgsize() + 14
+	if z.CreatedBefore == nil {
+		s += msgp.NilSize
+	} else {
+		s += msgp.TimeSize
+	}
+	s += 5 + msgp.ArrayHeaderSize
+	for za0001 := range z.Tags {
+		s += z.Tags[za0001].Msgsize()
+	}
+	s += 9 + msgp.ArrayHeaderSize
+	for za0002 := range z.Metadata {
+		s += z.Metadata[za0002].Msgsize()
+	}
+	s += 5 + z.Size.Msgsize() + 5 + msgp.StringPrefixSize + len(z.Type) + 5 + msgp.StringPrefixSize + len(z.Name) + 6 + 1 + 15 + msgp.IntSize
+	return
+}
+
+// DecodeMsg implements msgp.Decodable
+func (z *BatchJobExpirePurge) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "RetainVersions":
+			z.RetainVersions, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "RetainVersions")
+				return
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z BatchJobExpirePurge) EncodeMsg(en *msgp.Writer) (err error) {
+	// map header, size 1
+	// write "RetainVersions"
+	err = en.Append(0x81, 0xae, 0x52, 0x65, 0x74, 0x61, 0x69, 0x6e, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.RetainVersions)
+	if err != nil {
+		err = msgp.WrapError(err, "RetainVersions")
+		return
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z BatchJobExpirePurge) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	// map header, size 1
+	// string "RetainVersions"
+	o = append(o, 0x81, 0xae, 0x52, 0x65, 0x74, 0x61, 0x69, 0x6e, 0x56, 0x65, 0x72, 0x73, 0x69, 0x6f, 0x6e, 0x73)
+	o = msgp.AppendInt(o, z.RetainVersions)
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *BatchJobExpirePurge) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "RetainVersions":
+			z.RetainVersions, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "RetainVersions")
+				return
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z BatchJobExpirePurge) Msgsize() (s int) {
+	s = 1 + 15 + msgp.IntSize
+	return
+}

cmd/batch-expire_gen_test.go

@@ -0,0 +1,349 @@
+package cmd
+
+// Code generated by github.com/tinylib/msgp DO NOT EDIT.
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/tinylib/msgp/msgp"
+)
+
+func TestMarshalUnmarshalBatchJobExpire(t *testing.T) {
+	v := BatchJobExpire{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgBatchJobExpire(b *testing.B) {
+	v := BatchJobExpire{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgBatchJobExpire(b *testing.B) {
+	v := BatchJobExpire{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalBatchJobExpire(b *testing.B) {
+	v := BatchJobExpire{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodeBatchJobExpire(t *testing.T) {
+	v := BatchJobExpire{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodeBatchJobExpire Msgsize() is inaccurate")
+	}
+
+	vn := BatchJobExpire{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodeBatchJobExpire(b *testing.B) {
+	v := BatchJobExpire{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodeBatchJobExpire(b *testing.B) {
+	v := BatchJobExpire{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestMarshalUnmarshalBatchJobExpireFilter(t *testing.T) {
+	v := BatchJobExpireFilter{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgBatchJobExpireFilter(b *testing.B) {
+	v := BatchJobExpireFilter{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgBatchJobExpireFilter(b *testing.B) {
+	v := BatchJobExpireFilter{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalBatchJobExpireFilter(b *testing.B) {
+	v := BatchJobExpireFilter{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodeBatchJobExpireFilter(t *testing.T) {
+	v := BatchJobExpireFilter{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodeBatchJobExpireFilter Msgsize() is inaccurate")
+	}
+
+	vn := BatchJobExpireFilter{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodeBatchJobExpireFilter(b *testing.B) {
+	v := BatchJobExpireFilter{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodeBatchJobExpireFilter(b *testing.B) {
+	v := BatchJobExpireFilter{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestMarshalUnmarshalBatchJobExpirePurge(t *testing.T) {
+	v := BatchJobExpirePurge{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgBatchJobExpirePurge(b *testing.B) {
+	v := BatchJobExpirePurge{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgBatchJobExpirePurge(b *testing.B) {
+	v := BatchJobExpirePurge{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalBatchJobExpirePurge(b *testing.B) {
+	v := BatchJobExpirePurge{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodeBatchJobExpirePurge(t *testing.T) {
+	v := BatchJobExpirePurge{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodeBatchJobExpirePurge Msgsize() is inaccurate")
+	}
+
+	vn := BatchJobExpirePurge{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodeBatchJobExpirePurge(b *testing.B) {
+	v := BatchJobExpirePurge{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodeBatchJobExpirePurge(b *testing.B) {
+	v := BatchJobExpirePurge{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}

cmd/batch-expire_test.go

@@ -0,0 +1,125 @@
+// Copyright (c) 2015-2023 MinIO, Inc.
+//
+// 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 (
+	"slices"
+	"testing"
+
+	"gopkg.in/yaml.v3"
+)
+
+func TestParseBatchJobExpire(t *testing.T) {
+	expireYaml := `
+expire: # Expire objects that match a condition
+  apiVersion: v1
+  bucket: mybucket # Bucket where this batch job will expire matching objects from
+  prefix: myprefix # (Optional) Prefix under which this job will expire objects matching the rules below.
+  rules:
+    - type: object  # regular objects with zero or more older versions
+      name: NAME # match object names that satisfy the wildcard expression.
+      olderThan: 7d10h # match objects older than this value
+      createdBefore: "2006-01-02T15:04:05.00Z" # match objects created before "date"
+      tags:
+        - key: name
+          value: pick* # match objects with tag 'name', all values starting with 'pick'
+      metadata:
+        - key: content-type
+          value: image/* # match objects with 'content-type', all values starting with 'image/'
+      size:
+        lessThan: "10MiB" # match objects with size less than this value (e.g. 10MiB)
+        greaterThan: 1MiB # match objects with size greater than this value (e.g. 1MiB)
+      purge:
+          # retainVersions: 0 # (default) delete all versions of the object. This option is the fastest.
+          # retainVersions: 5 # keep the latest 5 versions of the object.
+  
+    - type: deleted # objects with delete marker as their latest version
+      name: NAME # match object names that satisfy the wildcard expression.
+      olderThan: 10h # match objects older than this value (e.g. 7d10h31s)
+      createdBefore: "2006-01-02T15:04:05.00Z" # match objects created before "date"
+      purge:
+          # retainVersions: 0 # (default) delete all versions of the object. This option is the fastest.
+          # retainVersions: 5 # keep the latest 5 versions of the object including delete markers.
+
+  notify:
+    endpoint: https://notify.endpoint # notification endpoint to receive job completion status
+    token: Bearer xxxxx # optional authentication token for the notification endpoint
+  
+  retry:
+    attempts: 10 # number of retries for the job before giving up
+    delay: 500ms # least amount of delay between each retry
+`
+	var job BatchJobRequest
+	err := yaml.Unmarshal([]byte(expireYaml), &job)
+	if err != nil {
+		t.Fatal("Failed to parse batch-job-expire yaml", err)
+	}
+	if !slices.Equal(job.Expire.Prefix.F(), []string{"myprefix"}) {
+		t.Fatal("Failed to parse batch-job-expire yaml")
+	}
+
+	multiPrefixExpireYaml := `
+expire: # Expire objects that match a condition
+  apiVersion: v1
+  bucket: mybucket # Bucket where this batch job will expire matching objects from
+  prefix: # (Optional) Prefix under which this job will expire objects matching the rules below.
+    - myprefix
+    - myprefix1
+  rules:
+    - type: object  # regular objects with zero or more older versions
+      name: NAME # match object names that satisfy the wildcard expression.
+      olderThan: 7d10h # match objects older than this value
+      createdBefore: "2006-01-02T15:04:05.00Z" # match objects created before "date"
+      tags:
+        - key: name
+          value: pick* # match objects with tag 'name', all values starting with 'pick'
+      metadata:
+        - key: content-type
+          value: image/* # match objects with 'content-type', all values starting with 'image/'
+      size:
+        lessThan: "10MiB" # match objects with size less than this value (e.g. 10MiB)
+        greaterThan: 1MiB # match objects with size greater than this value (e.g. 1MiB)
+      purge:
+          # retainVersions: 0 # (default) delete all versions of the object. This option is the fastest.
+          # retainVersions: 5 # keep the latest 5 versions of the object.
+  
+    - type: deleted # objects with delete marker as their latest version
+      name: NAME # match object names that satisfy the wildcard expression.
+      olderThan: 10h # match objects older than this value (e.g. 7d10h31s)
+      createdBefore: "2006-01-02T15:04:05.00Z" # match objects created before "date"
+      purge:
+          # retainVersions: 0 # (default) delete all versions of the object. This option is the fastest.
+          # retainVersions: 5 # keep the latest 5 versions of the object including delete markers.
+
+  notify:
+    endpoint: https://notify.endpoint # notification endpoint to receive job completion status
+    token: Bearer xxxxx # optional authentication token for the notification endpoint
+  
+  retry:
+    attempts: 10 # number of retries for the job before giving up
+    delay: 500ms # least amount of delay between each retry
+`
+	var multiPrefixJob BatchJobRequest
+	err = yaml.Unmarshal([]byte(multiPrefixExpireYaml), &multiPrefixJob)
+	if err != nil {
+		t.Fatal("Failed to parse batch-job-expire yaml", err)
+	}
+	if !slices.Equal(multiPrefixJob.Expire.Prefix.F(), []string{"myprefix", "myprefix1"}) {
+		t.Fatal("Failed to parse batch-job-expire yaml")
+	}
+}

cmd/batch-handlers_gen.go

@@ -0,0 +1,952 @@
+package cmd
+
+// Code generated by github.com/tinylib/msgp DO NOT EDIT.
+
+import (
+	"github.com/tinylib/msgp/msgp"
+)
+
+// DecodeMsg implements msgp.Decodable
+func (z *BatchJobPrefix) DecodeMsg(dc *msgp.Reader) (err error) {
+	var zb0002 uint32
+	zb0002, err = dc.ReadArrayHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	if cap((*z)) >= int(zb0002) {
+		(*z) = (*z)[:zb0002]
+	} else {
+		(*z) = make(BatchJobPrefix, zb0002)
+	}
+	for zb0001 := range *z {
+		(*z)[zb0001], err = dc.ReadString()
+		if err != nil {
+			err = msgp.WrapError(err, zb0001)
+			return
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z BatchJobPrefix) EncodeMsg(en *msgp.Writer) (err error) {
+	err = en.WriteArrayHeader(uint32(len(z)))
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0003 := range z {
+		err = en.WriteString(z[zb0003])
+		if err != nil {
+			err = msgp.WrapError(err, zb0003)
+			return
+		}
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z BatchJobPrefix) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	o = msgp.AppendArrayHeader(o, uint32(len(z)))
+	for zb0003 := range z {
+		o = msgp.AppendString(o, z[zb0003])
+	}
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *BatchJobPrefix) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var zb0002 uint32
+	zb0002, bts, err = msgp.ReadArrayHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	if cap((*z)) >= int(zb0002) {
+		(*z) = (*z)[:zb0002]
+	} else {
+		(*z) = make(BatchJobPrefix, zb0002)
+	}
+	for zb0001 := range *z {
+		(*z)[zb0001], bts, err = msgp.ReadStringBytes(bts)
+		if err != nil {
+			err = msgp.WrapError(err, zb0001)
+			return
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z BatchJobPrefix) Msgsize() (s int) {
+	s = msgp.ArrayHeaderSize
+	for zb0003 := range z {
+		s += msgp.StringPrefixSize + len(z[zb0003])
+	}
+	return
+}
+
+// DecodeMsg implements msgp.Decodable
+func (z *BatchJobRequest) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "ID":
+			z.ID, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "ID")
+				return
+			}
+		case "User":
+			z.User, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "User")
+				return
+			}
+		case "Started":
+			z.Started, err = dc.ReadTime()
+			if err != nil {
+				err = msgp.WrapError(err, "Started")
+				return
+			}
+		case "Replicate":
+			if dc.IsNil() {
+				err = dc.ReadNil()
+				if err != nil {
+					err = msgp.WrapError(err, "Replicate")
+					return
+				}
+				z.Replicate = nil
+			} else {
+				if z.Replicate == nil {
+					z.Replicate = new(BatchJobReplicateV1)
+				}
+				err = z.Replicate.DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "Replicate")
+					return
+				}
+			}
+		case "KeyRotate":
+			if dc.IsNil() {
+				err = dc.ReadNil()
+				if err != nil {
+					err = msgp.WrapError(err, "KeyRotate")
+					return
+				}
+				z.KeyRotate = nil
+			} else {
+				if z.KeyRotate == nil {
+					z.KeyRotate = new(BatchJobKeyRotateV1)
+				}
+				err = z.KeyRotate.DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "KeyRotate")
+					return
+				}
+			}
+		case "Expire":
+			if dc.IsNil() {
+				err = dc.ReadNil()
+				if err != nil {
+					err = msgp.WrapError(err, "Expire")
+					return
+				}
+				z.Expire = nil
+			} else {
+				if z.Expire == nil {
+					z.Expire = new(BatchJobExpire)
+				}
+				err = z.Expire.DecodeMsg(dc)
+				if err != nil {
+					err = msgp.WrapError(err, "Expire")
+					return
+				}
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z *BatchJobRequest) EncodeMsg(en *msgp.Writer) (err error) {
+	// map header, size 6
+	// write "ID"
+	err = en.Append(0x86, 0xa2, 0x49, 0x44)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.ID)
+	if err != nil {
+		err = msgp.WrapError(err, "ID")
+		return
+	}
+	// write "User"
+	err = en.Append(0xa4, 0x55, 0x73, 0x65, 0x72)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.User)
+	if err != nil {
+		err = msgp.WrapError(err, "User")
+		return
+	}
+	// write "Started"
+	err = en.Append(0xa7, 0x53, 0x74, 0x61, 0x72, 0x74, 0x65, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteTime(z.Started)
+	if err != nil {
+		err = msgp.WrapError(err, "Started")
+		return
+	}
+	// write "Replicate"
+	err = en.Append(0xa9, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x65)
+	if err != nil {
+		return
+	}
+	if z.Replicate == nil {
+		err = en.WriteNil()
+		if err != nil {
+			return
+		}
+	} else {
+		err = z.Replicate.EncodeMsg(en)
+		if err != nil {
+			err = msgp.WrapError(err, "Replicate")
+			return
+		}
+	}
+	// write "KeyRotate"
+	err = en.Append(0xa9, 0x4b, 0x65, 0x79, 0x52, 0x6f, 0x74, 0x61, 0x74, 0x65)
+	if err != nil {
+		return
+	}
+	if z.KeyRotate == nil {
+		err = en.WriteNil()
+		if err != nil {
+			return
+		}
+	} else {
+		err = z.KeyRotate.EncodeMsg(en)
+		if err != nil {
+			err = msgp.WrapError(err, "KeyRotate")
+			return
+		}
+	}
+	// write "Expire"
+	err = en.Append(0xa6, 0x45, 0x78, 0x70, 0x69, 0x72, 0x65)
+	if err != nil {
+		return
+	}
+	if z.Expire == nil {
+		err = en.WriteNil()
+		if err != nil {
+			return
+		}
+	} else {
+		err = z.Expire.EncodeMsg(en)
+		if err != nil {
+			err = msgp.WrapError(err, "Expire")
+			return
+		}
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z *BatchJobRequest) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	// map header, size 6
+	// string "ID"
+	o = append(o, 0x86, 0xa2, 0x49, 0x44)
+	o = msgp.AppendString(o, z.ID)
+	// string "User"
+	o = append(o, 0xa4, 0x55, 0x73, 0x65, 0x72)
+	o = msgp.AppendString(o, z.User)
+	// string "Started"
+	o = append(o, 0xa7, 0x53, 0x74, 0x61, 0x72, 0x74, 0x65, 0x64)
+	o = msgp.AppendTime(o, z.Started)
+	// string "Replicate"
+	o = append(o, 0xa9, 0x52, 0x65, 0x70, 0x6c, 0x69, 0x63, 0x61, 0x74, 0x65)
+	if z.Replicate == nil {
+		o = msgp.AppendNil(o)
+	} else {
+		o, err = z.Replicate.MarshalMsg(o)
+		if err != nil {
+			err = msgp.WrapError(err, "Replicate")
+			return
+		}
+	}
+	// string "KeyRotate"
+	o = append(o, 0xa9, 0x4b, 0x65, 0x79, 0x52, 0x6f, 0x74, 0x61, 0x74, 0x65)
+	if z.KeyRotate == nil {
+		o = msgp.AppendNil(o)
+	} else {
+		o, err = z.KeyRotate.MarshalMsg(o)
+		if err != nil {
+			err = msgp.WrapError(err, "KeyRotate")
+			return
+		}
+	}
+	// string "Expire"
+	o = append(o, 0xa6, 0x45, 0x78, 0x70, 0x69, 0x72, 0x65)
+	if z.Expire == nil {
+		o = msgp.AppendNil(o)
+	} else {
+		o, err = z.Expire.MarshalMsg(o)
+		if err != nil {
+			err = msgp.WrapError(err, "Expire")
+			return
+		}
+	}
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *BatchJobRequest) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "ID":
+			z.ID, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ID")
+				return
+			}
+		case "User":
+			z.User, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "User")
+				return
+			}
+		case "Started":
+			z.Started, bts, err = msgp.ReadTimeBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Started")
+				return
+			}
+		case "Replicate":
+			if msgp.IsNil(bts) {
+				bts, err = msgp.ReadNilBytes(bts)
+				if err != nil {
+					return
+				}
+				z.Replicate = nil
+			} else {
+				if z.Replicate == nil {
+					z.Replicate = new(BatchJobReplicateV1)
+				}
+				bts, err = z.Replicate.UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Replicate")
+					return
+				}
+			}
+		case "KeyRotate":
+			if msgp.IsNil(bts) {
+				bts, err = msgp.ReadNilBytes(bts)
+				if err != nil {
+					return
+				}
+				z.KeyRotate = nil
+			} else {
+				if z.KeyRotate == nil {
+					z.KeyRotate = new(BatchJobKeyRotateV1)
+				}
+				bts, err = z.KeyRotate.UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "KeyRotate")
+					return
+				}
+			}
+		case "Expire":
+			if msgp.IsNil(bts) {
+				bts, err = msgp.ReadNilBytes(bts)
+				if err != nil {
+					return
+				}
+				z.Expire = nil
+			} else {
+				if z.Expire == nil {
+					z.Expire = new(BatchJobExpire)
+				}
+				bts, err = z.Expire.UnmarshalMsg(bts)
+				if err != nil {
+					err = msgp.WrapError(err, "Expire")
+					return
+				}
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *BatchJobRequest) Msgsize() (s int) {
+	s = 1 + 3 + msgp.StringPrefixSize + len(z.ID) + 5 + msgp.StringPrefixSize + len(z.User) + 8 + msgp.TimeSize + 10
+	if z.Replicate == nil {
+		s += msgp.NilSize
+	} else {
+		s += z.Replicate.Msgsize()
+	}
+	s += 10
+	if z.KeyRotate == nil {
+		s += msgp.NilSize
+	} else {
+		s += z.KeyRotate.Msgsize()
+	}
+	s += 7
+	if z.Expire == nil {
+		s += msgp.NilSize
+	} else {
+		s += z.Expire.Msgsize()
+	}
+	return
+}
+
+// DecodeMsg implements msgp.Decodable
+func (z *batchJobInfo) DecodeMsg(dc *msgp.Reader) (err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, err = dc.ReadMapHeader()
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, err = dc.ReadMapKeyPtr()
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "v":
+			z.Version, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "Version")
+				return
+			}
+		case "jid":
+			z.JobID, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "JobID")
+				return
+			}
+		case "jt":
+			z.JobType, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "JobType")
+				return
+			}
+		case "st":
+			z.StartTime, err = dc.ReadTime()
+			if err != nil {
+				err = msgp.WrapError(err, "StartTime")
+				return
+			}
+		case "lu":
+			z.LastUpdate, err = dc.ReadTime()
+			if err != nil {
+				err = msgp.WrapError(err, "LastUpdate")
+				return
+			}
+		case "ra":
+			z.RetryAttempts, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "RetryAttempts")
+				return
+			}
+		case "at":
+			z.Attempts, err = dc.ReadInt()
+			if err != nil {
+				err = msgp.WrapError(err, "Attempts")
+				return
+			}
+		case "cmp":
+			z.Complete, err = dc.ReadBool()
+			if err != nil {
+				err = msgp.WrapError(err, "Complete")
+				return
+			}
+		case "fld":
+			z.Failed, err = dc.ReadBool()
+			if err != nil {
+				err = msgp.WrapError(err, "Failed")
+				return
+			}
+		case "lbkt":
+			z.Bucket, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Bucket")
+				return
+			}
+		case "lobj":
+			z.Object, err = dc.ReadString()
+			if err != nil {
+				err = msgp.WrapError(err, "Object")
+				return
+			}
+		case "ob":
+			z.Objects, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "Objects")
+				return
+			}
+		case "dm":
+			z.DeleteMarkers, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "DeleteMarkers")
+				return
+			}
+		case "obf":
+			z.ObjectsFailed, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "ObjectsFailed")
+				return
+			}
+		case "dmf":
+			z.DeleteMarkersFailed, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "DeleteMarkersFailed")
+				return
+			}
+		case "bt":
+			z.BytesTransferred, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "BytesTransferred")
+				return
+			}
+		case "bf":
+			z.BytesFailed, err = dc.ReadInt64()
+			if err != nil {
+				err = msgp.WrapError(err, "BytesFailed")
+				return
+			}
+		default:
+			err = dc.Skip()
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	return
+}
+
+// EncodeMsg implements msgp.Encodable
+func (z *batchJobInfo) EncodeMsg(en *msgp.Writer) (err error) {
+	// map header, size 17
+	// write "v"
+	err = en.Append(0xde, 0x0, 0x11, 0xa1, 0x76)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.Version)
+	if err != nil {
+		err = msgp.WrapError(err, "Version")
+		return
+	}
+	// write "jid"
+	err = en.Append(0xa3, 0x6a, 0x69, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.JobID)
+	if err != nil {
+		err = msgp.WrapError(err, "JobID")
+		return
+	}
+	// write "jt"
+	err = en.Append(0xa2, 0x6a, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.JobType)
+	if err != nil {
+		err = msgp.WrapError(err, "JobType")
+		return
+	}
+	// write "st"
+	err = en.Append(0xa2, 0x73, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteTime(z.StartTime)
+	if err != nil {
+		err = msgp.WrapError(err, "StartTime")
+		return
+	}
+	// write "lu"
+	err = en.Append(0xa2, 0x6c, 0x75)
+	if err != nil {
+		return
+	}
+	err = en.WriteTime(z.LastUpdate)
+	if err != nil {
+		err = msgp.WrapError(err, "LastUpdate")
+		return
+	}
+	// write "ra"
+	err = en.Append(0xa2, 0x72, 0x61)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.RetryAttempts)
+	if err != nil {
+		err = msgp.WrapError(err, "RetryAttempts")
+		return
+	}
+	// write "at"
+	err = en.Append(0xa2, 0x61, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt(z.Attempts)
+	if err != nil {
+		err = msgp.WrapError(err, "Attempts")
+		return
+	}
+	// write "cmp"
+	err = en.Append(0xa3, 0x63, 0x6d, 0x70)
+	if err != nil {
+		return
+	}
+	err = en.WriteBool(z.Complete)
+	if err != nil {
+		err = msgp.WrapError(err, "Complete")
+		return
+	}
+	// write "fld"
+	err = en.Append(0xa3, 0x66, 0x6c, 0x64)
+	if err != nil {
+		return
+	}
+	err = en.WriteBool(z.Failed)
+	if err != nil {
+		err = msgp.WrapError(err, "Failed")
+		return
+	}
+	// write "lbkt"
+	err = en.Append(0xa4, 0x6c, 0x62, 0x6b, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Bucket)
+	if err != nil {
+		err = msgp.WrapError(err, "Bucket")
+		return
+	}
+	// write "lobj"
+	err = en.Append(0xa4, 0x6c, 0x6f, 0x62, 0x6a)
+	if err != nil {
+		return
+	}
+	err = en.WriteString(z.Object)
+	if err != nil {
+		err = msgp.WrapError(err, "Object")
+		return
+	}
+	// write "ob"
+	err = en.Append(0xa2, 0x6f, 0x62)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt64(z.Objects)
+	if err != nil {
+		err = msgp.WrapError(err, "Objects")
+		return
+	}
+	// write "dm"
+	err = en.Append(0xa2, 0x64, 0x6d)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt64(z.DeleteMarkers)
+	if err != nil {
+		err = msgp.WrapError(err, "DeleteMarkers")
+		return
+	}
+	// write "obf"
+	err = en.Append(0xa3, 0x6f, 0x62, 0x66)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt64(z.ObjectsFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "ObjectsFailed")
+		return
+	}
+	// write "dmf"
+	err = en.Append(0xa3, 0x64, 0x6d, 0x66)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt64(z.DeleteMarkersFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "DeleteMarkersFailed")
+		return
+	}
+	// write "bt"
+	err = en.Append(0xa2, 0x62, 0x74)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt64(z.BytesTransferred)
+	if err != nil {
+		err = msgp.WrapError(err, "BytesTransferred")
+		return
+	}
+	// write "bf"
+	err = en.Append(0xa2, 0x62, 0x66)
+	if err != nil {
+		return
+	}
+	err = en.WriteInt64(z.BytesFailed)
+	if err != nil {
+		err = msgp.WrapError(err, "BytesFailed")
+		return
+	}
+	return
+}
+
+// MarshalMsg implements msgp.Marshaler
+func (z *batchJobInfo) MarshalMsg(b []byte) (o []byte, err error) {
+	o = msgp.Require(b, z.Msgsize())
+	// map header, size 17
+	// string "v"
+	o = append(o, 0xde, 0x0, 0x11, 0xa1, 0x76)
+	o = msgp.AppendInt(o, z.Version)
+	// string "jid"
+	o = append(o, 0xa3, 0x6a, 0x69, 0x64)
+	o = msgp.AppendString(o, z.JobID)
+	// string "jt"
+	o = append(o, 0xa2, 0x6a, 0x74)
+	o = msgp.AppendString(o, z.JobType)
+	// string "st"
+	o = append(o, 0xa2, 0x73, 0x74)
+	o = msgp.AppendTime(o, z.StartTime)
+	// string "lu"
+	o = append(o, 0xa2, 0x6c, 0x75)
+	o = msgp.AppendTime(o, z.LastUpdate)
+	// string "ra"
+	o = append(o, 0xa2, 0x72, 0x61)
+	o = msgp.AppendInt(o, z.RetryAttempts)
+	// string "at"
+	o = append(o, 0xa2, 0x61, 0x74)
+	o = msgp.AppendInt(o, z.Attempts)
+	// string "cmp"
+	o = append(o, 0xa3, 0x63, 0x6d, 0x70)
+	o = msgp.AppendBool(o, z.Complete)
+	// string "fld"
+	o = append(o, 0xa3, 0x66, 0x6c, 0x64)
+	o = msgp.AppendBool(o, z.Failed)
+	// string "lbkt"
+	o = append(o, 0xa4, 0x6c, 0x62, 0x6b, 0x74)
+	o = msgp.AppendString(o, z.Bucket)
+	// string "lobj"
+	o = append(o, 0xa4, 0x6c, 0x6f, 0x62, 0x6a)
+	o = msgp.AppendString(o, z.Object)
+	// string "ob"
+	o = append(o, 0xa2, 0x6f, 0x62)
+	o = msgp.AppendInt64(o, z.Objects)
+	// string "dm"
+	o = append(o, 0xa2, 0x64, 0x6d)
+	o = msgp.AppendInt64(o, z.DeleteMarkers)
+	// string "obf"
+	o = append(o, 0xa3, 0x6f, 0x62, 0x66)
+	o = msgp.AppendInt64(o, z.ObjectsFailed)
+	// string "dmf"
+	o = append(o, 0xa3, 0x64, 0x6d, 0x66)
+	o = msgp.AppendInt64(o, z.DeleteMarkersFailed)
+	// string "bt"
+	o = append(o, 0xa2, 0x62, 0x74)
+	o = msgp.AppendInt64(o, z.BytesTransferred)
+	// string "bf"
+	o = append(o, 0xa2, 0x62, 0x66)
+	o = msgp.AppendInt64(o, z.BytesFailed)
+	return
+}
+
+// UnmarshalMsg implements msgp.Unmarshaler
+func (z *batchJobInfo) UnmarshalMsg(bts []byte) (o []byte, err error) {
+	var field []byte
+	_ = field
+	var zb0001 uint32
+	zb0001, bts, err = msgp.ReadMapHeaderBytes(bts)
+	if err != nil {
+		err = msgp.WrapError(err)
+		return
+	}
+	for zb0001 > 0 {
+		zb0001--
+		field, bts, err = msgp.ReadMapKeyZC(bts)
+		if err != nil {
+			err = msgp.WrapError(err)
+			return
+		}
+		switch msgp.UnsafeString(field) {
+		case "v":
+			z.Version, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Version")
+				return
+			}
+		case "jid":
+			z.JobID, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "JobID")
+				return
+			}
+		case "jt":
+			z.JobType, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "JobType")
+				return
+			}
+		case "st":
+			z.StartTime, bts, err = msgp.ReadTimeBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "StartTime")
+				return
+			}
+		case "lu":
+			z.LastUpdate, bts, err = msgp.ReadTimeBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "LastUpdate")
+				return
+			}
+		case "ra":
+			z.RetryAttempts, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "RetryAttempts")
+				return
+			}
+		case "at":
+			z.Attempts, bts, err = msgp.ReadIntBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Attempts")
+				return
+			}
+		case "cmp":
+			z.Complete, bts, err = msgp.ReadBoolBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Complete")
+				return
+			}
+		case "fld":
+			z.Failed, bts, err = msgp.ReadBoolBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Failed")
+				return
+			}
+		case "lbkt":
+			z.Bucket, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Bucket")
+				return
+			}
+		case "lobj":
+			z.Object, bts, err = msgp.ReadStringBytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Object")
+				return
+			}
+		case "ob":
+			z.Objects, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "Objects")
+				return
+			}
+		case "dm":
+			z.DeleteMarkers, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "DeleteMarkers")
+				return
+			}
+		case "obf":
+			z.ObjectsFailed, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "ObjectsFailed")
+				return
+			}
+		case "dmf":
+			z.DeleteMarkersFailed, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "DeleteMarkersFailed")
+				return
+			}
+		case "bt":
+			z.BytesTransferred, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "BytesTransferred")
+				return
+			}
+		case "bf":
+			z.BytesFailed, bts, err = msgp.ReadInt64Bytes(bts)
+			if err != nil {
+				err = msgp.WrapError(err, "BytesFailed")
+				return
+			}
+		default:
+			bts, err = msgp.Skip(bts)
+			if err != nil {
+				err = msgp.WrapError(err)
+				return
+			}
+		}
+	}
+	o = bts
+	return
+}
+
+// Msgsize returns an upper bound estimate of the number of bytes occupied by the serialized message
+func (z *batchJobInfo) Msgsize() (s int) {
+	s = 3 + 2 + msgp.IntSize + 4 + msgp.StringPrefixSize + len(z.JobID) + 3 + msgp.StringPrefixSize + len(z.JobType) + 3 + msgp.TimeSize + 3 + msgp.TimeSize + 3 + msgp.IntSize + 3 + msgp.IntSize + 4 + msgp.BoolSize + 4 + msgp.BoolSize + 5 + msgp.StringPrefixSize + len(z.Bucket) + 5 + msgp.StringPrefixSize + len(z.Object) + 3 + msgp.Int64Size + 3 + msgp.Int64Size + 4 + msgp.Int64Size + 4 + msgp.Int64Size + 3 + msgp.Int64Size + 3 + msgp.Int64Size
+	return
+}

cmd/batch-handlers_gen_test.go

@@ -0,0 +1,349 @@
+package cmd
+
+// Code generated by github.com/tinylib/msgp DO NOT EDIT.
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/tinylib/msgp/msgp"
+)
+
+func TestMarshalUnmarshalBatchJobPrefix(t *testing.T) {
+	v := BatchJobPrefix{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgBatchJobPrefix(b *testing.B) {
+	v := BatchJobPrefix{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgBatchJobPrefix(b *testing.B) {
+	v := BatchJobPrefix{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalBatchJobPrefix(b *testing.B) {
+	v := BatchJobPrefix{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodeBatchJobPrefix(t *testing.T) {
+	v := BatchJobPrefix{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodeBatchJobPrefix Msgsize() is inaccurate")
+	}
+
+	vn := BatchJobPrefix{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodeBatchJobPrefix(b *testing.B) {
+	v := BatchJobPrefix{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodeBatchJobPrefix(b *testing.B) {
+	v := BatchJobPrefix{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestMarshalUnmarshalBatchJobRequest(t *testing.T) {
+	v := BatchJobRequest{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgBatchJobRequest(b *testing.B) {
+	v := BatchJobRequest{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgBatchJobRequest(b *testing.B) {
+	v := BatchJobRequest{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalBatchJobRequest(b *testing.B) {
+	v := BatchJobRequest{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodeBatchJobRequest(t *testing.T) {
+	v := BatchJobRequest{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodeBatchJobRequest Msgsize() is inaccurate")
+	}
+
+	vn := BatchJobRequest{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodeBatchJobRequest(b *testing.B) {
+	v := BatchJobRequest{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodeBatchJobRequest(b *testing.B) {
+	v := BatchJobRequest{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestMarshalUnmarshalbatchJobInfo(t *testing.T) {
+	v := batchJobInfo{}
+	bts, err := v.MarshalMsg(nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	left, err := v.UnmarshalMsg(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after UnmarshalMsg(): %q", len(left), left)
+	}
+
+	left, err = msgp.Skip(bts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(left) > 0 {
+		t.Errorf("%d bytes left over after Skip(): %q", len(left), left)
+	}
+}
+
+func BenchmarkMarshalMsgbatchJobInfo(b *testing.B) {
+	v := batchJobInfo{}
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.MarshalMsg(nil)
+	}
+}
+
+func BenchmarkAppendMsgbatchJobInfo(b *testing.B) {
+	v := batchJobInfo{}
+	bts := make([]byte, 0, v.Msgsize())
+	bts, _ = v.MarshalMsg(bts[0:0])
+	b.SetBytes(int64(len(bts)))
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		bts, _ = v.MarshalMsg(bts[0:0])
+	}
+}
+
+func BenchmarkUnmarshalbatchJobInfo(b *testing.B) {
+	v := batchJobInfo{}
+	bts, _ := v.MarshalMsg(nil)
+	b.ReportAllocs()
+	b.SetBytes(int64(len(bts)))
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, err := v.UnmarshalMsg(bts)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func TestEncodeDecodebatchJobInfo(t *testing.T) {
+	v := batchJobInfo{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+
+	m := v.Msgsize()
+	if buf.Len() > m {
+		t.Log("WARNING: TestEncodeDecodebatchJobInfo Msgsize() is inaccurate")
+	}
+
+	vn := batchJobInfo{}
+	err := msgp.Decode(&buf, &vn)
+	if err != nil {
+		t.Error(err)
+	}
+
+	buf.Reset()
+	msgp.Encode(&buf, &v)
+	err = msgp.NewReader(&buf).Skip()
+	if err != nil {
+		t.Error(err)
+	}
+}
+
+func BenchmarkEncodebatchJobInfo(b *testing.B) {
+	v := batchJobInfo{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	en := msgp.NewWriter(msgp.Nowhere)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		v.EncodeMsg(en)
+	}
+	en.Flush()
+}
+
+func BenchmarkDecodebatchJobInfo(b *testing.B) {
+	v := batchJobInfo{}
+	var buf bytes.Buffer
+	msgp.Encode(&buf, &v)
+	b.SetBytes(int64(buf.Len()))
+	rd := msgp.NewEndlessReader(buf.Bytes(), b)
+	dc := msgp.NewReader(rd)
+	b.ReportAllocs()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		err := v.DecodeMsg(dc)
+		if err != nil {
+			b.Fatal(err)
+		}
+	}
+}

cmd/batch-handlers_test.go

@@ -0,0 +1,75 @@
+// Copyright (c) 2015-2024 MinIO, Inc.
+//
+// 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 (
+	"slices"
+	"testing"
+
+	"gopkg.in/yaml.v3"
+)
+
+func TestBatchJobPrefix_UnmarshalYAML(t *testing.T) {
+	type args struct {
+		yamlStr string
+	}
+	type PrefixTemp struct {
+		Prefix BatchJobPrefix `yaml:"prefix"`
+	}
+	tests := []struct {
+		name    string
+		b       PrefixTemp
+		args    args
+		want    []string
+		wantErr bool
+	}{
+		{
+			name: "test1",
+			b:    PrefixTemp{},
+			args: args{
+				yamlStr: `
+prefix: "foo"
+`,
+			},
+			want:    []string{"foo"},
+			wantErr: false,
+		},
+		{
+			name: "test2",
+			b:    PrefixTemp{},
+			args: args{
+				yamlStr: `
+prefix:
+  - "foo"
+  - "bar"
+`,
+			},
+			want: []string{"foo", "bar"},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if err := yaml.Unmarshal([]byte(tt.args.yamlStr), &tt.b); (err != nil) != tt.wantErr {
+				t.Errorf("UnmarshalYAML() error = %v, wantErr %v", err, tt.wantErr)
+			}
+			if !slices.Equal(tt.b.Prefix.F(), tt.want) {
+				t.Errorf("UnmarshalYAML() = %v, want %v", tt.b.Prefix.F(), tt.want)
+			}
+		})
+	}
+}

cmd/batch-job-common-types.go

@@ -0,0 +1,290 @@
+// Copyright (c) 2015-2023 MinIO, Inc.
+//
+// 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 (
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/dustin/go-humanize"
+	"github.com/minio/pkg/v3/wildcard"
+	"gopkg.in/yaml.v3"
+)
+
+//go:generate msgp -file $GOFILE
+//msgp:ignore BatchJobYamlErr
+
+// BatchJobYamlErr can be used to return yaml validation errors with line,
+// column information guiding user to fix syntax errors
+type BatchJobYamlErr struct {
+	line, col int
+	msg       string
+}
+
+// message returns the error message excluding line, col information.
+// Intended to be used in unit tests.
+func (b BatchJobYamlErr) message() string {
+	return b.msg
+}
+
+// Error implements Error interface
+func (b BatchJobYamlErr) Error() string {
+	return fmt.Sprintf("%s\n Hint: error near line: %d, col: %d", b.msg, b.line, b.col)
+}
+
+// BatchJobKV is a key-value data type which supports wildcard matching
+type BatchJobKV struct {
+	line, col int
+	Key       string `yaml:"key" json:"key"`
+	Value     string `yaml:"value" json:"value"`
+}
+
+var _ yaml.Unmarshaler = &BatchJobKV{}
+
+// UnmarshalYAML - BatchJobKV extends default unmarshal to extract line, col information.
+func (kv *BatchJobKV) UnmarshalYAML(val *yaml.Node) error {
+	type jobKV BatchJobKV
+	var tmp jobKV
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+	*kv = BatchJobKV(tmp)
+	kv.line, kv.col = val.Line, val.Column
+	return nil
+}
+
+// Validate returns an error if key is empty
+func (kv BatchJobKV) Validate() error {
+	if kv.Key == "" {
+		return BatchJobYamlErr{
+			line: kv.line,
+			col:  kv.col,
+			msg:  "key can't be empty",
+		}
+	}
+	return nil
+}
+
+// Empty indicates if kv is not set
+func (kv BatchJobKV) Empty() bool {
+	return kv.Key == "" && kv.Value == ""
+}
+
+// Match matches input kv with kv, value will be wildcard matched depending on the user input
+func (kv BatchJobKV) Match(ikv BatchJobKV) bool {
+	if kv.Empty() {
+		return true
+	}
+	if strings.EqualFold(kv.Key, ikv.Key) {
+		return wildcard.Match(kv.Value, ikv.Value)
+	}
+	return false
+}
+
+// BatchJobNotification stores notification endpoint and token information.
+// Used by batch jobs to notify of their status.
+type BatchJobNotification struct {
+	line, col int
+	Endpoint  string `yaml:"endpoint" json:"endpoint"`
+	Token     string `yaml:"token" json:"token"`
+}
+
+var _ yaml.Unmarshaler = &BatchJobNotification{}
+
+// UnmarshalYAML - BatchJobNotification extends unmarshal to extract line, column information
+func (b *BatchJobNotification) UnmarshalYAML(val *yaml.Node) error {
+	type notification BatchJobNotification
+	var tmp notification
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+
+	*b = BatchJobNotification(tmp)
+	b.line, b.col = val.Line, val.Column
+	return nil
+}
+
+// BatchJobRetry stores retry configuration used in the event of failures.
+type BatchJobRetry struct {
+	line, col int
+	Attempts  int           `yaml:"attempts" json:"attempts"` // number of retry attempts
+	Delay     time.Duration `yaml:"delay" json:"delay"`       // delay between each retries
+}
+
+var _ yaml.Unmarshaler = &BatchJobRetry{}
+
+// UnmarshalYAML - BatchJobRetry extends unmarshal to extract line, column information
+func (r *BatchJobRetry) UnmarshalYAML(val *yaml.Node) error {
+	type retry BatchJobRetry
+	var tmp retry
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+
+	*r = BatchJobRetry(tmp)
+	r.line, r.col = val.Line, val.Column
+	return nil
+}
+
+// Validate validates input replicate retries.
+func (r BatchJobRetry) Validate() error {
+	if r.Attempts < 0 {
+		return BatchJobYamlErr{
+			line: r.line,
+			col:  r.col,
+			msg:  "Invalid arguments specified",
+		}
+	}
+
+	if r.Delay < 0 {
+		return BatchJobYamlErr{
+			line: r.line,
+			col:  r.col,
+			msg:  "Invalid arguments specified",
+		}
+	}
+
+	return nil
+}
+
+//   # snowball based archive transfer is by default enabled when source
+//   # is local and target is remote which is also minio.
+//   snowball:
+//     disable: false # optionally turn-off snowball archive transfer
+//     batch: 100 # upto this many objects per archive
+//     inmemory: true # indicates if the archive must be staged locally or in-memory
+//     compress: true # S2/Snappy compressed archive
+//     smallerThan: 5MiB # create archive for all objects smaller than 5MiB
+//     skipErrs: false # skips any source side read() errors
+
+// BatchJobSnowball describes the snowball feature when replicating objects from a local source to a remote target
+type BatchJobSnowball struct {
+	line, col   int
+	Disable     *bool   `yaml:"disable" json:"disable"`
+	Batch       *int    `yaml:"batch" json:"batch"`
+	InMemory    *bool   `yaml:"inmemory" json:"inmemory"`
+	Compress    *bool   `yaml:"compress" json:"compress"`
+	SmallerThan *string `yaml:"smallerThan" json:"smallerThan"`
+	SkipErrs    *bool   `yaml:"skipErrs" json:"skipErrs"`
+}
+
+var _ yaml.Unmarshaler = &BatchJobSnowball{}
+
+// UnmarshalYAML - BatchJobSnowball extends unmarshal to extract line, column information
+func (b *BatchJobSnowball) UnmarshalYAML(val *yaml.Node) error {
+	type snowball BatchJobSnowball
+	var tmp snowball
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+
+	*b = BatchJobSnowball(tmp)
+	b.line, b.col = val.Line, val.Column
+	return nil
+}
+
+// Validate the snowball parameters in the job description
+func (b BatchJobSnowball) Validate() error {
+	if *b.Batch <= 0 {
+		return BatchJobYamlErr{
+			line: b.line,
+			col:  b.col,
+			msg:  "batch number should be non positive zero",
+		}
+	}
+	_, err := humanize.ParseBytes(*b.SmallerThan)
+	if err != nil {
+		return BatchJobYamlErr{
+			line: b.line,
+			col:  b.col,
+			msg:  err.Error(),
+		}
+	}
+	return nil
+}
+
+// BatchJobSizeFilter supports size based filters - LesserThan and GreaterThan
+type BatchJobSizeFilter struct {
+	line, col  int
+	UpperBound BatchJobSize `yaml:"lessThan" json:"lessThan"`
+	LowerBound BatchJobSize `yaml:"greaterThan" json:"greaterThan"`
+}
+
+// UnmarshalYAML - BatchJobSizeFilter extends unmarshal to extract line, column information
+func (sf *BatchJobSizeFilter) UnmarshalYAML(val *yaml.Node) error {
+	type sizeFilter BatchJobSizeFilter
+	var tmp sizeFilter
+	err := val.Decode(&tmp)
+	if err != nil {
+		return err
+	}
+
+	*sf = BatchJobSizeFilter(tmp)
+	sf.line, sf.col = val.Line, val.Column
+	return nil
+}
+
+// InRange returns true in the following cases and false otherwise,
+// - sf.LowerBound < sz, when sf.LowerBound alone is specified
+// - sz < sf.UpperBound, when sf.UpperBound alone is specified
+// - sf.LowerBound < sz < sf.UpperBound when both are specified,
+func (sf BatchJobSizeFilter) InRange(sz int64) bool {
+	if sf.UpperBound > 0 && sz > int64(sf.UpperBound) {
+		return false
+	}
+
+	if sf.LowerBound > 0 && sz < int64(sf.LowerBound) {
+		return false
+	}
+	return true
+}
+
+// Validate checks if sf is a valid batch-job size filter
+func (sf BatchJobSizeFilter) Validate() error {
+	if sf.LowerBound > 0 && sf.UpperBound > 0 && sf.LowerBound >= sf.UpperBound {
+		return BatchJobYamlErr{
+			line: sf.line,
+			col:  sf.col,
+			msg:  "invalid batch-job size filter",
+		}
+	}
+	return nil
+}
+
+// BatchJobSize supports humanized byte values in yaml files type BatchJobSize uint64
+type BatchJobSize int64
+
+// UnmarshalYAML to parse humanized byte values
+func (s *BatchJobSize) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	var batchExpireSz string
+	err := unmarshal(&batchExpireSz)
+	if err != nil {
+		return err
+	}
+	sz, err := humanize.ParseBytes(batchExpireSz)
+	if err != nil {
+		return err
+	}
+	*s = BatchJobSize(sz)
+	return nil
+}