Skip to content

Commit

Permalink
v4.0.0
Browse files Browse the repository at this point in the history
This is a security-focused release of the AWS Deployment Framework (ADF) that
aims to restrict the default access required and provided by ADF via the
least-privilege principle.

__Key security enhancements include:__

- Applying IAM best practices by restricting excessive permissions granted to
  IAM roles and policies used by ADF.
- Leveraging new IAM features to further limit access privileges granted by
  default, reducing the potential attack surface.
- Where privileged access is required for specific ADF use cases, the scope and
  duration of elevated privileges have been minimized to limit the associated
  risks.

By implementing these security improvements, ADF now follows the principle of
least privilege, reducing the risk of unauthorized access or
privilege-escalation attacks.

Please make sure to go through the list of changes breaking changes carefully.

As with every release, it is strongly recommended to thoroughly review and test
this version of ADF in a non-production environment first.

### Breaking changes

#### Security: Confused Deputy Problem

Addressed the [Confused Deputy
problem](https://docs.aws.amazon.com/IAM/latest/UserGuide/confused-deputy.html)
in IAM roles created by ADF to use by the AWS Services. Where supported, the
roles are restricted to specific resources via an `aws:SourceArn` condition.
If you were using the ADF roles for other resources or use cases not covered
by ADF, you might need to patch the Assume Role policies accordingly.

#### Security: Cross-Account Access Role and the new Jump Role

ADF relies on the privileged Cross-Account Access Role to bootstrap accounts.
In the past, ADF used this role for every update and deployment of the
bootstrap stacks, as well as account management features.

With the release of v4.0, a jump role is introduced to lock-down the usage of
the privileged cross-account access role. Part of the bootstrap stack, the
`adf-bootstrap-update-deployment-role` is created. This role grants access to
perform restricted updates that are frequently performed via the
`aws-deployment-framework-bootstrap` pipeline. By default, the jump role is
granted access to assume into this update deployment role.

A dedicated jump role manager is responsible to grant the jump role access to
the cross-account access role for AWS accounts where ADF requires access and
the `adf-bootstrap-update-deployment-role` is not available yet.
For example, accounts that are newly created only have the cross-account access
role to assume into. Same holds for ADF managed accounts that are not updated
to the new v4.0 bootstrap stack yet.

During the installation/update of ADF, a new parameter enables you to grant
the jump role temporary access to the cross-account access role as an
privileged escalation path.
This parameter is called `GrantOrgWidePrivilegedBootstrapAccessUntil`.
By setting this to a date/time in the future you will grant access to the
cross-account access role until that date/time. This would be required if you
modify ADF itself or the bootstrap stack templates. Changing permissions like
the `adf-cloudformation-deployment-role` is possible without relying on the
cross-account access role. For most changes deployed via the bootstrap pipeline
it does not require elevated privileged access to update.

With the above changes, the `aws-deployment-framework-bootstrap` CodeBuild
project no longer has unrestricted access to the privileged cross-account role.
Starting from version 4.0, access to assume the privileged cross-account access
role is restricted and must be obtained through the Jump Role as described
above.

#### Security: Restricted account management access

Account Management is able to access non-protected organization units.
Prior to ADF v4.0, the account management process used the privileged
cross-account assess role to operate. Hence it could move an account or update
the properties of an account that is located in a protected organization unit
too. With the release of v4.0, it is only able to move or manage accounts if
they are accessible via the Jump Role. The Jump Role is restricted to
non-protected organization units only.

This enhances the security of ADF, as defining a organization unit as protected
will block access to that via the Jump Role accordingly.

#### Security: Restricted bootstrapping of management account

The `adf-global-base-adf-build` stack in the management account was initially
deployed to facilitate bootstrap access to the management account.
It accomplished this by creating a cross-account access role with limited
permissions in the management account ahead of the bootstrapping process.

ADF created this role as it is not provisioned by AWS Organizations or
AWS Control Tower in the management account itself. However, ADF required some
level of access to deploy the necessary bootstrap stacks when needed.

It is important to note that deploying this role and bootstrapping the
management account introduces a potential risk. A pipeline created via a
deployment map could target the management account and create resources within
it, which may have unintended consequences.

To mitigate the potential risk, it is recommended to implement strict
least-privilege policies and apply permission boundaries to protect
the management account.
Additionally, thoroughly reviewing all deployment map changes is crucial to
ensure no unintended access is granted to the management account.

With the release of ADF v4.0, the `adf-global-base-adf-build` stack is removed
and its resources are moved to the main ADF CloudFormation template.
These resources will only get deployed if the new
`AllowBootstrappingOfManagementAccount` parameter is set to `Yes`. By default
it will not allow bootstrapping of the management account.

#### Security: Restricted bootstrapping of deployment account

Considering the sensitive workloads that run in the deployment account, it is
important to limit the permissions granted for pipelines to deploy to the
deployment account itself. You should consider the deployment account a
production account.

It is recommended to apply the least-privilege principle and only allow
pipelines to deploy resources that are required in the deployment account.

Follow these steps after the changes introduced by the ADF v4.0 release are
applied in the main branch of the `aws-deployment-framework-bootstrap`
repository.

Please take this moment to review the following:

* Navigate to the `adf-boostrap/deployment` folder in that repository.
* Check if it contains a `global-iam.yml` file:

    * If it does __not__ contain a `global-iam.yml` file yet, please ensure you
      copy the `example-global-iam.yml` file in that directory.
    * If it does, please compare it against the `example-global-iam.yml` file
      in that directory.

* Apply the least-privilege principle on the permissions you grant in the
  deployment account.

#### Security: Shared Modules Bucket

ADF uses the Shared Modules Bucket as hosted in the management account in the
main deployment region to share artifacts from the
`aws-deployment-framework-bootstrap` repository.

The breaking change enforces all objects to be owned by the bucket owner from
v4.0 onward.

#### Security: ADF Role policy restrictions

With the v4.0 release, all ADF roles and policies were reviewed, applying
the latest best-practices and granting access to ADF resources only where
required. This review also includes the roles that were used by the pipelines
generated by ADF.

Please be aware of the changes made to the following roles:

##### adf-codecommit-role

The `adf-codecommit-role` no longer grants read/write access to all buckets.
It only grants access to the buckets created and managed by ADF where it
needed to. Please grant access accordingly if you use custom S3 buckets or need
to copy from an S3 bucket in an ADF-generated pipeline.

##### adf-codebuild-role

The `adf-codebuild-role` can only be used by CodeBuild projects in the main
deployment region. ADF did not allow running CodeBuild projects in other
regions before. But in case you manually configured the role in a project
in a different region it will fail to launch.

The `adf-codebuild-role` is no longer allowed to assume any IAM Role in the
target accounts if those roles would grant access in the Assume Role
Policy Document.

The `adf-codebuild-role` is restricted to assume only the
`adf-readonly-automation-role` roles in the target accounts.
And, in the case that the Terraform ADF Extension is enabled, it is allowed to
assume the `adf-terraform-role` too.

It is therefore not allowed to assume the `adf-cloudformation-deployment-role`
any longer. If you were deploying with `cdk deploy` into target accounts from an
ADF pipeline you will need to specifically grant the `adf-codebuild-role`
access to assume the `adf-cloudformation-deployment-role`. However, we strongly
recommend you synthesize the templates instead and let AWS CloudFormation do
the deployment for you.

For Terraform support, CodeBuild was granted access to the `adf-tflocktable`
table in release v3.2.0. This access is restricted to only grant read/write
access to that table if the Terraform extension is enabled.
Please bear in mind that if you enable Terraform access the first time, you
will need to use the `GrantOrgWidePrivilegedBootstrapAccessUntil` parameter
if ADF v4.0 bootstrapped to accounts before. As this operation requires
privileged access.

The `adf-codebuild-role` is allowed to assume into the
`adf-terraform-role` if the Terraform extension is enabled.
As written in the docs, the `adf-terraform-role` is configured
in the `global-iam.yml` file. This role is commented out by default.
When you define this role, it is important to make sure to grant it
[least-privilege access](https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html#grant-least-privilege)
only.

##### adf-cloudformation-role

The `adf-cloudformation-role` is no longer assumable by CloudFormation.
This role is used by CodePipeline to orchestrate various deployment actions
across accounts. For example, CodeDeploy, S3, and obviously the CloudFormation
actions.

For CloudFormation, it would instruct the service to use the CloudFormation
Deployment role for the actual deployment.
The CloudFormation deployment role is the role that is assumed by the
CloudFormation service. This change should not impact you, unless you
use this role in relation with CloudFormation that is not managed by ADF.

With v4.0, the `adf-cloudformation-role` is only allowed to pass the
CloudFormation Deployment role to CloudFormation and no other roles to other
services.

If you were/want to make use of a custom CloudFormation deployment role for
specific pipelines, you need to make sure that the `adf-cloudformation-role` is
allowed to perform an `iam:PassRole` action with the given role.
It is recommended to limit this to be passed to the CloudFormation service
only. You can find an example of this in the
`adf-bootstrap/deployment/global.yml` file where it allows the
CloudFormation role to perform `iam:PassRole` with the
`adf-cloudformation-deployment-role`. When required, please grant this access
in the `adf-bootstrap/deployment/global-iam.yml` file in the
`aws-deployment-framework-bootstrap` repository.

Additionally, the `adf-cloudformation-role` is not allowed to access S3 buckets
except the ADF buckets it needs to transfer pipeline assets to CloudFormation.

##### adf-codepipeline-role

The `adf-codepipeline-role` is no longer assumable by CloudFormation,
CodeDeploy, and S3. The role itself was not passed to any of these services by
ADF.

If you relied on the permissions that were removed, feel free to extend the
role permissions via the `global-iam.yml` stack.

#### Security: Restricted access to ADF-managed S3 buckets only

With v4.0, access is restricted to ADF-managed S3 buckets only.
If a pipeline used the S3 source or deployment provider, it will require
the required access to those buckets. Please add the required access to the
`global-iam.yml` bootstrap stack in the OU where it is hosted.

Grant read access to the `adf-codecommit-role` for S3 source buckets.
Grant write access to the `adf-cloudformation-role` for S3 buckets an ADF
pipeline deploys to.

#### Security: Bootstrap stack no longer named after organization unit

The global and regional bootstrap stacks are renamed to
`adf-global-base-bootstrap` and `adf-regional-base-bootstrap` respectively.

In prior releases of ADF, the name ended with the organization unit name.
As a result, an account could not move from one organization unit to
another without first removing the bootstrap stacks. Additionally, it made
writing IAM policies and SCPs harder in a least-privilege way.

When ADF v4.0 is installed, the legacy stacks will get removed by the
`aws-deployment-framework-bootstrap` pipeline automatically. Shortly after
removal, it will deploy the new bootstrap stacks.

With v4.0, accounts can move from one organization unit to another,
without requiring the removal of the ADF bootstrap stacks.

#### Security: KMS Encryption required on Deployment Account Pipeline Buckets

The deployment account pipeline buckets only accepts KMS Encrypted objects from
v4.0 onward. Ensuring that all objects are encrypted with the same KMS Key.

Before, some objects used KMS encryption while others did not. The bucket
policy now requires all objects to be encrypted via the KMS key. All ADF
components have been adjusted to upload with this key. If, however, you copy
files from systems that are not managed by ADF, you will need to adjust these
to encrypt the objects with the KMS key as well.

#### Security: TLS Encryption required on all ADF-managed buckets

S3 Buckets created by ADF will require TLS 1.2 or later. All actions that occur
on these buckets with older TLS versions will be denied via the bucket policies
that these buckets received.

#### New installer

The dependencies that are bundled by the move to the AWS Cloud Development Kit
(CDK) v2 increased the deployment size of ADF.
Unfortunately it increased the deployment size beyond the limit that is
supported by the Serverless Application Repository (SAR).

Hence a new installation mechanism is required.

Please read the [installation
instructions](https://github.com/awslabs/aws-deployment-framework/blob/master/docs/installation-guide.md)
carefully.

In case you are upgrading an existing installation of ADF, please consider
following the [upgrade steps as defined in the admin
guide](https://github.com/awslabs/aws-deployment-framework/blob/master/docs/admin-guide.md#updating-between-versions).

#### CDK v2

ADF v4.0 is built on the AWS Cloud Development Kit (CDK) v2. Which is an
upgrade to CDK v1 that ADF relied on before.

For most end-users, this change would not have an immediate impact.
If, however, you made customizations to ADF it might require you to upgrade
these customizations to CDK v2 as well.

#### CodeBuild default image

As written in the [CodeBuild provider
docs](./docs/providers-guide.md#properties-3), it is a best-practice to define
the exact CodeBuild container image you would like to use for each pipeline.

However, in case you rely on the default, in prior ADF releases it would
default to `UBUNTU_14_04_PYTHON_3_7_1`. This container image is no longer
supported. With ADF v4.0, the new default is `STANDARD_7_0`.
Also referred to as: `aws/codebuild/standard:7.0`.

#### ADF Renaming of Roles

ADF v4.0 changes most of the roles that it relies on. The reason for this
change is to make it easier to secure ADF with Service Control Policies and
IAM permission boundaries. Where applicable, the roles received a new prefix.
This makes it easier to identify what part of ADF relies on those roles and
whom should have access to assume the role or modify it.

| Previous prefix  | Previous name                                                       | New prefix                 | New name                                                      |
|------------------|---------------------------------------------------------------------|----------------------------|---------------------------------------------------------------|
| /                | ${CrossAccountAccessRoleName}-readonly                              | /adf/organizations/        | adf-organizations-readonly                                    |
| /                | adf-update-cross-account-access-role                                | /adf/bootstrap/            | adf-update-cross-account-access                               |
| /adf-automation/ | adf-create-repository-role                                          | /adf/pipeline-management/  | adf-pipeline-management-create-repository                     |
| /adf-automation/ | adf-pipeline-provisioner-generate-inputs                            | /adf/pipeline-management/  | adf-pipeline-management-generate-inputs                       |
| /adf-automation/ | adf-pipeline-create-update-rule                                     | /adf/pipeline-management/  | adf-pipeline-management-create-update-rule                    |
| /                | adf-event-rule-${AWS::AccountId}-${DeploymentAccountId}-EventRole-* | /adf/cross-account-events/ | adf-cc-event-from-${AWS::AccountId}-to-${DeploymentAccountId} |
|------------------|---------------------------------------------------------------------|----------------------------|---------------------------------------------------------------|

#### ADF Renaming of Resources

| Type         | Previous name                                 | New name                                               |
|--------------|-----------------------------------------------|--------------------------------------------------------|
| StateMachine | EnableCrossAccountAccess                      | adf-bootstrap-enable-cross-account                     |
| StateMachine | ADFPipelineManagementStateMachine             | adf-pipeline-management                                |
| StateMachine | PipelineDeletionStateMachine-*                | adf-pipeline-management-delete-outdated                |
| Lambda       | DeploymentMapProcessorFunction                | adf-pipeline-management-deployment-map-processor       |
| Lambda       | ADFPipelineCreateOrUpdateRuleFunction         | adf-pipeline-management-create-update-rule             |
| Lambda       | ADFPipelineCreateRepositoryFunction           | adf-pipeline-management-create-repository              |
| Lambda       | ADFPipelineGenerateInputsFunction             | adf-pipeline-management-generate-pipeline-inputs       |
| Lambda       | ADFPipelineStoreDefinitionFunction            | adf-pipeline-management-store-pipeline-definition      |
| Lambda       | ADFPipelineIdentifyOutOfDatePipelinesFunction | adf-pipeline-management-identify-out-of-date-pipelines |
|--------------|-----------------------------------------------|--------------------------------------------------------|

#### ADF Parameters in AWS Systems Manager Parameter Store

Some of the parameters stored by ADF in AWS Systems Manager Parameter Store
were located at the root of the Parameter Store. This made it hard to maintain
and restrict access to the limited set of ADF specific parameters.

With ADF v4.0, the parameters used by ADF are located under the `/adf/` prefix.
For example, `/adf/deployment_account_id`.

The `global-iam.yml` bootstrap stack templates get copied from their
`example-global-iam.yml` counterparts. When this was copied in v3.2.0, the
default path for the `deployment_account_id` parameter should be updated to
`/adf/deployment_account_id`. Please apply this new default value to the
CloudFormation templates accordingly. If you forget to do this, the stack
deployment of the `adf-global-base-iam` stack might fail with a failure stating
that it does not have permission to fetch the `deployment_account_id`
parameter.

The error you run into if the parameter path is not updated:

> An error occurred (ValidationError) when calling the CreateChangeSet
> operation: User:
> arn:aws:sts::111111111111:assumed-role/${CrossAccountAccessRoleName}/base_update
> is not authorized to perform: ssm:GetParameters on resource:
> arn:aws:ssm:${deployment_region}:111111111111:parameter/deployment_account_id
> because no identity-based policy allows the ssm:GetParameters action
> (Service: AWSSimpleSystemsManagement; Status Code: 400;
> Error Code: AccessDeniedException; Request ID: xxx).

If an application or customization to ADF relies on one of these parameters
they will need to be updated to include this prefix. Unless the application
code relies on ADF's ParameterStore class, in that case it will automatically
prefix the `/adf/` to all parameters read or written.

With the changes in the IAM policies, ADF's access is restricted to the `/adf/`
prefix. This, unfortunately implies that old parameters are not deleted when
you update your installation of ADF. There is no cost associated to these
parameters, so you can leave them as is.
Feel free to delete the old parameters.

The parameters that are managed by ADF that got their path changed are:

For the __management account__, in the __AWS Organizations region__
(`us-east-1`, or `us-gov-west-1`):

| Old Parameter Path           | New Parameter Path               |
|------------------------------|----------------------------------|
| `/adf_log_level`             | `/adf/adf_log_level`             |
| `/adf_version`               | `/adf/adf_version`               |
| `/bucket_name`               | `/adf/bucket_name`               |
| `/confit`                    | `/adf/config`                    |
| `/cross_account_access_role` | `/adf/cross_account_access_role` |
| `/deployment_account_id`     | `/adf/deployment_account_id`     |
| `/deployment_account_region` | `/adf/deployment_account_region` |
| `/kms_arn`                   | `/adf/kms_arn`                   |
| `/notification_channel`      | `/adf/notification_channel`      |
| `/organization_id`           | `/adf/organization_id`           |
| `/protected`                 | `/adf/protected`                 |
| `/scp`                       | `/adf/scp`                       |
| `/shared_modules_bucket`     | `/adf/shared_modules_bucket`     |
| `/tagging-policy`            | `/adf/tagging_policy`            |
| `/target_regions`            | `/adf/target_regions`            |

For the __management account__, in __other ADF regions__:

| Old Parameter Path           | New Parameter Path               |
|------------------------------|----------------------------------|
| `/adf_version`               | `/adf/adf_version`               |
| `/bucket_name`               | `/adf/bucket_name`               |
| `/cross_account_access_role` | `/adf/cross_account_access_role` |
| `/deployment_account_id`     | `/adf/deployment_account_id`     |
| `/kms_arn`                   | `/adf/kms_arn`                   |

For the __deployment account__, in __the deployment region__:

| Old Parameter Path           | New Parameter Path                  |
|------------------------------|-------------------------------------|
| `/adf_log_level`             | `/adf/adf_log_level`                |
| `/adf_version`               | `/adf/adf_version`                  |
| `/auto_create_repositories`  | `/adf/scm/auto_create_repositories` |
| `/cross_account_access_role` | `/adf/cross_account_access_role`    |
| `/default_scm_branch`        | `/adf/scm//default_scm_branch`      |
| `/deployment_account_bucket` | `/adf/shared_modules_bucket`        |
| `/master_account_id`         | `/adf/management_account_id`        |
| `/notification_endpoint`     | `/adf/notification_endpoint`        |
| `/notification_type`         | `/adf/notification_type`            |
| `/organization_id`           | `/adf/organization_id`              |

For the __deployment account__, in __other ADF regions__:

| Old Parameter Path           | New Parameter Path               |
|------------------------------|----------------------------------|
| `/adf_log_level`             | `/adf/adf_log_level`             |
| `/adf_version`               | `/adf/adf_version`               |
| `/cross_account_access_role` | `/adf/cross_account_access_role` |
| `/deployment_account_bucket` | `/adf/shared_modules_bucket`     |
| `/master_account_id`         | `/adf/management_account_id`     |
| `/notification_endpoint`     | `/adf/notification_endpoint`     |
| `/notification_type`         | `/adf/notification_type`         |
| `/organization_id`           | `/adf/organization_id`           |

For a __target account__, in __each ADF region__:

| Old Parameter Path       | New Parameter Path           |
|--------------------------|------------------------------|
| `/bucket_name`           | `/adf/bucket_name`           |
| `/deployment_account_id` | `/adf/deployment_account_id` |
| `/kms_arn`               | `/adf/kms_arn`               |

#### AWS CodeStar Connections OAuth Token support dropped

ADF v4.0 discontinued the support for the OAuth Token stored in
SSM Parameter Store. As this method is not advised to be used by CodePipeline,
and might leave the OAuth Token accessible to other users of the deployment
account. As this is not a security best practice, ADF v4.0 no longer supports
it.

To upgrade, please read the [Administrator Guide on Using AWS CodeConnections
for Bitbucket, GitHub, or
GitLab](./docs/admin-guide.md#using-aws-codeconnections-for-bitbucket-github-github-enterprise-or-gitlab).

#### AWS CodeStar Connections changed to AWS CodeConnections

The AWS CodeStar Connection service [changed its name to AWS
CodeConnections](https://docs.aws.amazon.com/dtconsole/latest/userguide/rename.html).

If you configured a CodeStar Connection before, you can continue to use that.
You do not need to update the CodeStar policy as defined in the
`aws-deployment-framework-bootstrap/adf-bootstrap/deployment/global-iam.yml`
stack.

However, please update the pipeline definitions in your deployment map files.
The changes you need to make are renaming the source
provider from `codestar` to `codeconnections`.
Also update the `codestar_connection_path` source property to
`codeconnections_param_path`.

Both of these changes can be seen in the following example:

```yaml
pipelines:
  - name: sample-vpc
    default_providers:
      source:
        # provider: codestar
        provider: codeconnections
        properties:
          # codestar_connection_path: /adf/my_connection_arn_param
          codeconnections_param_path: /adf/my_connection_arn_param
```

If you are upgrading from the GitHub OAuth token or otherwise require a new
source code connection, please proceed with the AWS CodeConnections
configuration as defined in the
[Admin Guide - Using AWS CodeConnections for Bitbucket, GitHub, or
GitLab](./docs/admin-guide.md#using-aws-codeconnections-for-bitbucket-github-or-gitlab).

### Features

- Update CDK from v1 to v2 (awslabs#619), by @pergardebrink, resolves awslabs#503, awslabs#614, and
  awslabs#617.
- Account Management State Machine will now opt-in to target regions when
  creating an account (awslabs#604) by @StewartW.
- Add support for nested organization unit targets (awslabs#538) by @StewartW,
  resolves awslabs#20.
- Enable single ADF bootstrap and pipeline repositories to multi-AWS
  Organization setup, resolves awslabs#410:
    - Introduce the org-stage (awslabs#636) by @AndyEfaa.
    - Add support to allow empty targets in deployment maps (awslabs#634) by
      @AndyEfaa.
    - Add support to define the "default-scm-codecommit-account-id" in
      adfconfig.yml, no value in either falls back to deployment account id
      (awslabs#633) by @AndyEfaa.
    - Add multi AWS Organization support to adfconfig.yml (awslabs#668) by
      @alexevansigg.
    - Add multi AWS Organization support to generate_params.py (awslabs#672) by
      @AndyEfaa.
- Terraform: add support for distinct variable files per region per account in
  Terraform pipelines (awslabs#662) by @igordust, resolves awslabs#661.
- CodeBuild environment agnostic custom images references, allowing to specify
  the repository name or ARN of the ECR repository to use (awslabs#623) by @abhi1094.
- Add kms_encryption_key_arn and cache_control parameters to S3 deploy
  provider (awslabs#669) by @alFReD-NSH.
- Allow inter-ou move of accounts (awslabs#712) by @sbkok.

### Fixes

- Fix Terraform terrascan failure due to incorrect curl call (awslabs#607), by
  @lasv-az.
- Fix custom pipeline type configuration not loaded (awslabs#612), by @lydialim.
- Fix Terraform module execution error (awslabs#600), by @stemons, resolves awslabs#599 and
  awslabs#602.
- Fix resource untagging permissions (awslabs#635) by @sbkok.
- Fix GitHub Pipeline secret token usage (awslabs#645) by @sbkok.
- Fix Terraform error masking by tee (awslabs#643) by @igordust, resolves awslabs#642.
- Fix create repository bug when in rollback complete state (awslabs#648) by
  @alexevansigg.
- Fix cleanup of parameters upon pipeline retirement (awslabs#652) by @sbkok.
- Fix wave calculation for non-default CloudFormation actions and multi-region
  deployments (awslabs#624 and awslabs#651), by @alexevansigg.
- Fix ChatBot channel ref + add notification management permissions (awslabs#650) by
  @sbkok.
- Improve docs and add CodeStar Connection policy (awslabs#649) by @sbkok.
- Fix Terraform account variables were not copied correctly (awslabs#665) by
  @donnyDonowitz, resolves awslabs#664.
- Fix pipeline management state machine error handling (awslabs#683) by @sbkok.
- Fix target schema for tags (awslabs#667) by @AndyEfaa.
- Fix avoid overwriting truncated pipeline definitions with pipelines that
  share the same start (awslabs#653) by @AndyEfaa.
- Fix updating old global-iam stacks in the deployment account (awslabs#711) by
  @sbkok.
- Remove default org-stage reference to dev (awslabs#717) by @alexevansigg.
- Fix racing condition on first-usage of ADF pipelines leading to an auth
  error (awslabs#732) by @sbkok.
- Fix support for custom S3 deployment roles (awslabs#732) by @sbkok, resolves awslabs#355.
- Fix pipeline completion trigger description (awslabs#734) by @sbkok, resolves awslabs#654.

### Improvements

- Sanitizing account names before using them in SFn Invocation (awslabs#598) by
  @StewartW, resolves awslabs#597.
- Improve Terraform documentation sample (awslabs#605), by @lasv-az.
- Fix CodeDeploy sample to work in gov-cloud (awslabs#609), by @sbkok.
- Fix documentation error on CodeBuild custom image (awslabs#622), by @abhi1094.
- Speedup bootstrap pipeline by removing unused SAM Build (awslabs#613), by
  @AlexMackechnie.
- Upgrade CDK (v2.88), SAM (v1.93), and others to latest compatible version
  (awslabs#647) by @sbkok, resolves awslabs#644.
- Update pip before installing dependencies (awslabs#606) by @lasv-az.
- Fix: Adding hash to pipelines processing step function execution names to
  prevent collisions (awslabs#641) by @avolip, resolves awslabs#640.
- Modify trust relations for roles to ease redeployment of roles (awslabs#526) by
  @AndreasAugustin, resolves awslabs#472.
- Limit adf-state-machine-role to what is needed (awslabs#657) by @alFReD-NSH.
- Upload SCP policies with spaces removed (awslabs#656) by @alFReD-NSH.
- Move from ACL enforced bucket ownership to Ownership Controls + MegaLinter
  prettier fix (awslabs#666) by @sbkok.
- Upgrade CDK (v2.119), SAM (v1.107), Jinja2 (v3.1.3), and others to latest
  compatible version (awslabs#676) by @sbkok.
- Fix initial value type of allow-empty-targets (awslabs#678) by @sbkok.
- Fix Shared ADF Lambda Layer builds and add move to ARM-64 Lambdas (awslabs#680) by
  @sbkok.
- Add /adf params prefix and other SSM Parameter improvements (awslabs#695) by @sbkok,
  resolves awslabs#594 and awslabs#659.
- Fix pipeline support for CodeBuild containers with Python < v3.10 (awslabs#705) by
  @sbkok.
- Update CDK v2.136, SAM CLI 1.114, and others (awslabs#715) by @sbkok.
- AWS CodeStar Connections name change to CodeConnections (awslabs#714) by @sbkok,
  resolves awslabs#616.
- Adding retry logic for awslabs#655 and add tests for delete_default_vpc.py (awslabs#708) by
  @javydekoning, resolves awslabs#655.
- Fix allow-empty-targets to match config boolean style (awslabs#725) by @sbkok.
- Require previously optional CodeBuild image property in build/deploy from v4
  onward (awslabs#731) by @sbkok, resolves awslabs#626 and awslabs#601.
- YAML files are interpreted via `YAML.safe_load` instead of `YAML.load` (awslabs#732)
  by @sbkok.
- Hardened all urlopen calls by checking the protocol (awslabs#732) by @sbkok.
- Added check to ensure the CloudFormation deployment account id matches with
  the `/adf/deployment_account_id` if that exists (awslabs#732) by @sbkok.
- Add automatic creation of the `/adf/deployment_account_id` and
  `/adf/management_account_id` if that does not exist (awslabs#732) by @sbkok.
- Separate delete outdated state machine from pipeline creation state machines
  (awslabs#732) by @sbkok.
- Review and restrict access provided by ADF managed IAM roles and permissions
  (awslabs#732) by @sbkok, resolves awslabs#608 and awslabs#390.
- Add automatic clean-up of legacy bootstrap stacks, auto recreate if required
  (awslabs#732) by @sbkok.

#### Installation improvements

With the addition of CDK v2 support. The dependencies that go with it,
unfortunately increased the deployment size beyond the limit that is supported
by the Serverless Application Repository. Hence the SAR installer is replaced
by a new installation process.
Please read the [Installation Guide](https://github.com/awslabs/aws-deployment-framework/blob/make/latest/docs/installation-guide.md) how to install ADF.
In case you are upgrading, please follow [the admin guide on updating ADF](https://github.com/awslabs/aws-deployment-framework/blob/make/latest/docs/admin-guide.md#updating-between-versions) instead.

- New installation process (awslabs#677) by @sbkok.
- Auto generate unique branch names on new version deployments (awslabs#682) by
  @sbkok.
- Ensure tox fails at first pytest failure (awslabs#686) by @sbkok.
- Install: Add checks to ensure installer dependencies are available (awslabs#702) by @sbkok.
- Install: Add version checks and pre-deploy warnings (awslabs#726) by @sbkok.
- Install: Add uncommitted changes check (awslabs#733) by @sbkok.

#### Documentation, ADF GitHub, and code only improvements

- Fixing broken Travis link and build badge (awslabs#625), by @javydekoning.
- Temporarily disabled cfn-lint after for awslabs#619 (awslabs#630), by @javydekoning.
- Upgrade MegaLinter to v7 and enable cfn-lint (awslabs#632), by @javydekoning.
- Fix linter failures (awslabs#637) by @javydekoning.
- Linter fixes (awslabs#646) by @javydekoning.
- Add docs enhancement regarding ADF and AWS Control Tower (awslabs#638) by @AndyEfaa.
- Fix include all tests in pytest.ini for bootstrap CodeBuild project (awslabs#621) by
  @AndyEfaa.
- Remove CodeCommitRole from initial base stack (awslabs#663) by @alFReD-NSH.
- Fix bootstrap pipeline tests (awslabs#679) by @sbkok.
- Add AccessControl property on S3 Buckets (awslabs#681) by @sbkok.
- Version bump GitHub actions (awslabs#704) by @javydekoning, resolves awslabs#698.
- Bump express from 4.17.3 to 4.19.2 in /samples/sample-fargate-node-app (awslabs#697)
  by @dependabot.
- Update copyright statements and license info (awslabs#713) by @sbkok.
- Fix dead-link in docs (awslabs#707) by @javydekoning.
- Add BASH_SHFMT linter + linter fixes (awslabs#709) by @javydekoning.
- Fix sample expunge VPC, if-len, and process deployment maps (awslabs#716) by @sbkok.
- Moving CDK example app to latest CDK version (awslabs#706) by @javydekoning,
  resolves awslabs#618.
- Fix Markdown Anchor Link Check (awslabs#722) by @sbkok.
- Improve samples (awslabs#718) by @sbkok.
- Explain special purpose of adf-bootstrap/global.yml in docs (awslabs#730) by @sbkok,
  resolves awslabs#615.
- Rename `deployment_account_bucket` to `shared_modules_bucket` (awslabs#732) by @sbkok.
- Moved CodeCommit and EventBridge templates from lambda to the bootstrap
  repository to ease maintenance (awslabs#732) by @sbkok.
  • Loading branch information
sbkok committed Jun 11, 2024
1 parent b2da600 commit b463851
Show file tree
Hide file tree
Showing 105 changed files with 6,327 additions and 1,490 deletions.
1 change: 1 addition & 0 deletions .cspell.json
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
],
"ignorePaths": [
".pylintrc",
"CHANGELOG.md",
"requirements.txt",
"requirements-dev.txt",
"maven-wrapper.jar",
Expand Down
572 changes: 569 additions & 3 deletions CHANGELOG.md

Large diffs are not rendered by default.

67 changes: 30 additions & 37 deletions docs/admin-guide.md
Original file line number Diff line number Diff line change
Expand Up @@ -1091,7 +1091,7 @@ This process is managed in an AWS Step Function state machine.

1. Navigate to the AWS Step Functions service in the deployment account
in _your main region_.
2. Check the `ADFPipelineManagementStateMachine` state machine, all recent
2. Check the `adf-pipeline-management` state machine, all recent
invocations since we performed the update should succeed.

We need to confirm that the pipelines generated by ADF are fully functional
Expand Down Expand Up @@ -1138,45 +1138,38 @@ Alternatively, you can also perform the update using the AWS CLI.

If you wish to remove ADF you can delete the CloudFormation stack named
`serverlessrepo-aws-deployment-framework` in the management account in
the `us-east-1` region. This will move into a `DELETE_FAILED` at some stage because
there is an S3 Bucket that is created via a custom resource _(cross region)_.
After it moves into `DELETE_FAILED`, you can right-click on the stack and hit
delete again while selecting to skip the Bucket the stack will successfully
delete, you can then manually delete the bucket and its contents.

After the main stack has been removed you can remove the base stack in the
deployment account `adf-global-base-deployment` and any associated regional
the `us-east-1` region. This will remove most resources created by ADF
in the management account. With the exception of S3 buckets and SSM parameters.
If you bootstrapped ADF into the management account you need to manually remove
the bootstrap stacks as well.

Feel free to delete the S3 buckets, SSM parameters that start with the `/adf`
prefix, as well as other CloudFormation stacks such as:

- adf-global-base-bootstrap (in the main deployment region)
- adf-global-base-iam (in the main deployment region)
- adf-regional-base-bootstrap (in every other region configured for ADF)

When these stacks are removed, you can switch into the deployment
account. We need to remove the base stack in the deployment account
`adf-global-base-deployment` and any associated regional
deployment account base stacks. After you have deleted these stacks, you can
manually remove any base stacks from accounts that were bootstrapped.

Alternatively prior to removing the initial
`serverlessrepo-aws-deployment-framework` stack, you can set the _moves_ section
of the `adfconfig.yml` file to _remove-base_ which would automatically clean up
the base stack when the account is moved to the Root of the AWS Organization.

One thing to keep in mind if you are planning to re-install ADF is that you
will want to clean up the parameter from SSM Parameter Store named
_deployment_account_id_ in `us-east-1` on the management account. AWS Step
Functions uses this parameter to determine if ADF has already got a deployment
account setup. If you re-install ADF with this parameter set to a value,
ADF will attempt an assume role to the account to do some work, which will fail
since that role will not be on the account at that point.

There is also a CloudFormation stack named `adf-global-base-adf-build` which
lives on the management account in your main deployment region. This stack
creates two roles on the management account after the deployment account has
been setup. These roles allow the deployment accounts CodeBuild role to assume a
role back to the management account in order to query Organizations for AWS
Accounts. This stack must be deleted manually also. If you do not remove this
stack and then perform a fresh install of ADF, AWS CodeBuild on the deployment
account will not be able to assume a role to the management account to query
AWS Organizations. This is because this specific stack creates IAM roles with a
strict trust relationship to the CodeBuild role on the deployment account, if
that role gets deleted _(Which is will when you delete
`adf-global-base-deployment`)_ then this stack references invalid IAM roles that
no longer exist. If you forget to remove this stack and notice the trust
relationship of the IAM roles referenced in the stack are no longer valid,
you can delete the stack and re-run the main bootstrap pipeline which will
recreate it with valid roles and links to the correct roles.
will want to clean up the parameter from SSM Parameter Store. You can safely
remove all `/adf` prefixed SSM parameters. But most importantly, you need to
remove the `/adf/deployment_account_id` in `us-east-1` on the
management account.
As AWS Step Functions uses this parameter to determine if ADF has already got a
deployment account setup. If you re-install ADF with this parameter set to a
value, ADF will attempt an assume role to the account to configure it, which
will fail since that role will not be on the account at that point.

## Troubleshooting

Expand Down Expand Up @@ -1234,15 +1227,15 @@ The main components to look at are:
deployment region.
8. Navigate to the [AWS Step Functions service](https://eu-west-1.console.aws.amazon.com/states/home?region=eu-west-1#/statemachines)
in the deployment account in your main region. Please note, the link points
to the `eu-west-` region. Please update that to your own deployment region.
Check the state machines named `ADFPipelineManagementStateMachine`,
`EnableCrossAccountAccess`, and `PipelineDeletionStateMachine...`.
Look at recent executions only.
to the `eu-west-1` region. Please update that to your own deployment region.
Check the state machines named `adf-pipeline-management`,
`adf-bootstrap-enable-cross-account`, and
`adf-pipeline-management-delete-outdated`. Look at recent executions only.
- When you find one that has a failed execution, check the components that
are marked orange/red in the diagram.
- If one failed and you want to trigger it again, you can execute it with
the `New Execution` button in AWS Step Functions. Or even better in case
of the `ADFPipelineManagementStateMachine`, trigger all executions again,
of the `adf-pipeline-management`, trigger all executions again,
Release a Change in the
[ADF Pipeline generation CodePipeline - aws-deployment-framework-pipelines](https://console.aws.amazon.com/codesuite/codepipeline/pipelines/aws-deployment-framework-pipelines/view?region=eu-west-1).

Expand Down
29 changes: 28 additions & 1 deletion docs/installation-guide.md
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,9 @@ AWS Control Tower prior to installing ADF.**

---------------------------------

## 1. Enable CloudTrail
## 1. Enable Services

### 1.1. Enable CloudTrail

Ensure you have setup [AWS CloudTrail](https://aws.amazon.com/cloudtrail/)
*(Not the default trail)* in your Management Account that spans **all
Expand All @@ -49,6 +51,28 @@ instructions](https://docs.aws.amazon.com/awscloudtrail/latest/userguide/cloudtr
to configure the CloudTrail in the `us-east-1` region within the AWS
Organizations Management AWS Account.

### 1.2. Enable AWS Organizations API Access

ADF will setup and configure [AWS
Organizations](https://us-east-1.console.aws.amazon.com/organizations/v2/home?region=us-east-1)
automatically.

However, ADF requires, but does not configure AWS Account Management
automatically.

Without configuring AWS Account Management, the `adf-account-management` Step
Functions state machine will fail to configure the AWS accounts such as the
deployment account for you. The error message that it would return would state:

> An error occurred (AccessDeniedException) when calling the ListRegions operation:
> User: arn:[...assumed-sts-role-arn...]/adf-account-management-config-region
> is not authorized to perform: account:ListRegions
> (Your organization must first enable trusted access with AWS Account Management.)
To enable this, go to AWS Organizations service console after it is configured
and [enable AWS Account Management via this
link](https://us-east-1.console.aws.amazon.com/organizations/v2/home/services/AWS%20Account%20Management).

## 2. Setup Your Build Environment

### 2.1. Local Instructions
Expand Down Expand Up @@ -624,6 +648,9 @@ automatically in the background, to follow its progress:
open AWS CodePipeline from within the management account in `us-east-1` and
see that there is an initial pipeline execution that started.

Upon first installation, this pipeline might fail to fetch the source
code from the repository. Click the retry failed action button to try again.

When ADF is deployed for the first-time, it will make the initial commit
with the skeleton structure of the `aws-deployment-framework-bootstrap`
CodeCommit repository.
Expand Down
66 changes: 50 additions & 16 deletions docs/providers-guide.md
Original file line number Diff line number Diff line change
Expand Up @@ -87,10 +87,12 @@ Provider type: `codecommit`.
information on the use of the owner attribute can be found in the
[CodePipeline
documentation](https://docs.aws.amazon.com/codepipeline/latest/APIReference/API_ActionTypeId.html).
- *role* - *(String)* default ADF managed role.
- The role to use to fetch the contents of the CodeCommit repository. Only
specify when you need a specific role to access it. By default ADF will use
its own role to access it instead.
- *role* - *(String)* default: `adf-codecommit-role`.
- The role name of the role to use to fetch the contents of the CodeCommit
repository. Only specify when you need a specific role to access it.
By default ADF will use its own role to access it instead.
- Please read the [user guide](./user-guide.md#custom-roles-for-pipelines) to
learn more about creating custom roles.
- *trigger_on_changes* - *(Boolean)* default: `True`.
- Whether CodePipeline should release a change and trigger the pipeline.
- **When set to False**, you either need to trigger the pipeline manually,
Expand All @@ -114,9 +116,15 @@ S3 can be used as the source for a pipeline too. **Please note:** you can use
S3 as a source and deployment provider. The properties that are available are
slightly different.

The role used to fetch the object from the S3 bucket is:
The default role used to fetch the object from the S3 bucket is:
`arn:${partition}:iam::${source_account_id}:role/adf-codecommit-role`.

Please add the required S3 read permissions to the `adf-codecomit-role` via the
`adf-bootstrap/deployment/global-iam.yml` file in the
`aws-deployment-framework-bootstrap` repository. Or, allow
the `adf-codecommit-role` S3 read permissions in the bucket policy of the
source bucket.

Provider type: `s3`.

#### Properties
Expand Down Expand Up @@ -277,6 +285,8 @@ Provider type: `codebuild`.
**Please note:** Since the CodeBuild environment runs in the deployment
account, the role you specify will be assumed in and should be available
in the deployment account too.
- Please read the [user guide](./user-guide.md#custom-roles-for-pipelines) to
learn more about creating custom roles.
- *timeout* *(Number)* in minutes, default: `20`.
- If you wish to define a custom timeout for the Build stage.
- *privileged* *(Boolean)* default: `False`.
Expand Down Expand Up @@ -452,12 +462,15 @@ Provider type: `codedeploy`.
- The name of the CodeDeploy Application you want to use for this deployment.
- *deployment_group_name* *(String)* **(required)**
- The name of the Deployment Group you want to use for this deployment.
- *role* - *(String)* default
`arn:${partition}:iam::${target_account_id}:role/adf-cloudformation-role`.
- *role* - *(String)* default `adf-cloudformation-role`
- Automatically assumes into the given role in the target account, i.e.
`arn:${partition}:iam::${target_account_id}:role/adf-cloudformation-role`.
- The role you would like to use on the target AWS account to execute the
CodeDeploy action. The role should allow the CodeDeploy service to assume
it. As is [documented in the CodeDeploy service role
documentation](https://docs.aws.amazon.com/codedeploy/latest/userguide/getting-started-create-service-role.html).
- Please read the [user guide](./user-guide.md#custom-roles-for-pipelines) to
learn more about creating custom roles.

### CloudFormation

Expand Down Expand Up @@ -513,11 +526,23 @@ Provider type: `cloudformation`.
to `infra`.
- **Defaults to empty string**, the root of the source repository or input
artifact.
- *role* - *(String)* default
`arn:${partition}:iam::${target_account_id}:role/adf-cloudformation-deployment-role`.
- *role* - *(String)* default `adf-cloudformation-deployment-role`
- Automatically assumes into the given role in the target account, i.e.
`arn:${partition}:iam::${target_account_id}:role/adf-cloudformation-deployment-role`.
- The role you would like to use on the target AWS account to execute the
CloudFormation action. Ensure that the CloudFormation service should be
allowed to assume that role.
CloudFormation action.
- Ensure that the CloudFormation service should be allowed to assume that
role.
- Additionally, make sure that the `adf-cloudformation-role` is allowed to
perform an `iam:PassRole` action with the given role. Restrict this action
for the CloudFormation service only.
You can find an example of this in the `adf-bootstrap/deployment/global.yml`
file where it allows the CloudFormation Role to perform `iam:PassRole` with
the `adf-cloudformation-deployment-role`.
Please grant this access in the `adf-bootstrap/deployment/global-iam.yml`
file in the `aws-deployment-framework-bootstrap` repository.
- Please read the [user guide](./user-guide.md#custom-roles-for-pipelines) to
learn more about creating custom roles.
- *action* -
(`CHANGE_SET_EXECUTE|CHANGE_SET_REPLACE|CREATE_UPDATE|DELETE_ONLY|REPLACE_ON_FAILURE`)
default: `CHANGE_SET_EXECUTE`.
Expand Down Expand Up @@ -586,7 +611,7 @@ Provider type: `service_catalog`.

### S3

S3 can use used to deploy with too.
S3 is available as a source and deployment provider.

S3 cannot be used to target multiple accounts or regions in one stage.
As the `bucket_name` property needs to be defined and these are globally
Expand All @@ -597,9 +622,17 @@ instead. Where each will target the specific bucket in the target account.
Please note: you can use S3 as a source and deployment provider. The properties
that are available are slightly different.

The role used to upload the object(s) to the S3 bucket is:
When S3 is used as the deployment provider, the default role used to upload
the object(s) to the S3 bucket is the:
`arn:${partition}:iam::${target_account_id}:role/adf-cloudformation-role`.

The `adf-cloudformation-role` is not granted access to read S3 buckets yet.
Please add the required S3 write permissions to the `adf-cloudformation-role`
via the `adf-bootstrap/global-iam.yml` file in the
`aws-deployment-framework-bootstrap` repository. Or, alternatively, allow
the `adf-cloudformation-role` S3 write permissions in the bucket policy of the
target bucket.

Provider type: `s3`.

#### Properties
Expand All @@ -611,9 +644,10 @@ Provider type: `s3`.
- *extract* - *(Boolean)* default: `False`.
- Whether CodePipeline should extract the contents of the object when it
deploys it.
- *role* - *(String)* default:
`arn:${partition}:iam::${target_account_id}:role/adf-cloudformation-role`.
- The role you would like to use for this action.
- *role* - *(String)* default: `adf-cloudformation-role`.
- The role name of the role you would like to use for this action.
- Please read the [user guide](./user-guide.md#custom-roles-for-pipelines) to
learn more about creating custom roles.
- *kms_encryption_key_arn* - *(String)*
- The ARN of the AWS KMS encryption key for the host bucket. The
`kms_encryption_key_arn` parameter encrypts uploaded artifacts with the
Expand Down
Loading

0 comments on commit b463851

Please sign in to comment.