main.tf

provider "aws" {
  region = local.region
}

locals {
  name            = replace(var.cluster_name, "_", "-")
  cluster_version = var.cluster_version
  region          = var.cluster_region

  tags = {
    Example    = local.name
    GithubRepo = "k8s-bootstrap-eks"
    GithubOrg  = "kzap"
  }
}

data "aws_caller_identity" "current" {}

################################################################################
# EKS Module
################################################################################

module "eks" {
  source  = "terraform-aws-modules/eks/aws"
  version = "18.6.0"

  cluster_name                    = local.name
  cluster_version                 = local.cluster_version
  cluster_endpoint_private_access = true
  cluster_endpoint_public_access  = true

  # IPV6
  cluster_ip_family          = "ipv6"
  create_cni_ipv6_iam_policy = true

  cluster_addons = {
    coredns = {
      resolve_conflicts = "OVERWRITE"
    }
    kube-proxy = {}
    vpc-cni = {
      resolve_conflicts = "OVERWRITE"
    }
  }

  cluster_encryption_config = [{
    provider_key_arn = aws_kms_key.eks.arn
    resources        = ["secrets"]
  }]

  vpc_id     = module.vpc.vpc_id
  subnet_ids = module.vpc.private_subnets

  # Extend cluster security group rules
  cluster_security_group_additional_rules = {
    egress_nodes_ephemeral_ports_tcp = {
      description                = "To node 1025-65535"
      protocol                   = "tcp"
      from_port                  = 1025
      to_port                    = 65535
      type                       = "egress"
      source_node_security_group = true
    }
  }

  # Extend node-to-node security group rules
  node_security_group_additional_rules = {
    ingress_self_all = {
      description = "Node to node all ports/protocols"
      protocol    = "-1"
      from_port   = 0
      to_port     = 0
      type        = "ingress"
      self        = true
    }
    egress_all = {
      description      = "Node all egress"
      protocol         = "-1"
      from_port        = 0
      to_port          = 0
      type             = "egress"
      cidr_blocks      = ["0.0.0.0/0"]
      ipv6_cidr_blocks = ["::/0"]
    }
  }

  eks_managed_node_group_defaults = {
    ami_type       = "AL2_x86_64"
    disk_size      = 50
    instance_types = ["m6i.large", "m5.large", "m5n.large", "m5zn.large"]
  }

  eks_managed_node_groups = {
    bottlerocket = {
      ami_type = "BOTTLEROCKET_x86_64"
      platform = "bottlerocket"

      # this will get added to what AWS provides
      bootstrap_extra_args = <<-EOT
      # extra args added
      [settings.kernel]
      lockdown = "integrity"
      EOT
    }

    # Complete
    complete = {
      name            = "complete-eks-mng"
      use_name_prefix = true

      subnet_ids = module.vpc.private_subnets

      min_size     = 1
      max_size     = 7
      desired_size = 1

      ami_id                     = data.aws_ami.eks_default.image_id
      enable_bootstrap_user_data = true
      bootstrap_extra_args       = "--container-runtime containerd --kubelet-extra-args '--max-pods=20'"

      pre_bootstrap_user_data = <<-EOT
      export CONTAINER_RUNTIME="containerd"
      export USE_MAX_PODS=false
      EOT

      post_bootstrap_user_data = <<-EOT
      echo "you are free little kubelet!"
      EOT

      capacity_type        = "SPOT"
      disk_size            = 256
      force_update_version = true
      instance_types       = ["m6i.large", "m5.large", "m5n.large", "m5zn.large"]
      labels = {
        GithubRepo = "terraform-aws-eks"
        GithubOrg  = "terraform-aws-modules"
      }

      taints = [
        {
          key    = "dedicated"
          value  = "gpuGroup"
          effect = "NO_SCHEDULE"
        }
      ]

      update_config = {
        max_unavailable_percentage = 50 # or set `max_unavailable`
      }

      description = "EKS managed node group example launch template"

      ebs_optimized           = true
      disable_api_termination = false
      enable_monitoring       = true

      block_device_mappings = {
        xvda = {
          device_name = "/dev/xvda"
          ebs = {
            volume_size           = 75
            volume_type           = "gp3"
            iops                  = 3000
            throughput            = 150
            encrypted             = true
            kms_key_id            = aws_kms_key.ebs.arn
            delete_on_termination = true
          }
        }
      }

      metadata_options = {
        http_endpoint               = "enabled"
        http_tokens                 = "required"
        http_put_response_hop_limit = 2
        instance_metadata_tags      = "disabled"
      }

      create_iam_role          = true
      iam_role_name            = "eks-managed-node-group-complete-example"
      iam_role_use_name_prefix = false
      iam_role_description     = "EKS managed node group complete example role"
      iam_role_tags = {
        Purpose = "Protector of the kubelet"
      }
      iam_role_additional_policies = [
        "arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly"
      ]

      create_security_group          = true
      security_group_name            = "eks-managed-node-group-complete-example"
      security_group_use_name_prefix = false
      security_group_description     = "EKS managed node group complete example security group"
      security_group_rules = {
        phoneOut = {
          description = "Hello CloudFlare"
          protocol    = "udp"
          from_port   = 53
          to_port     = 53
          type        = "egress"
          cidr_blocks = ["1.1.1.1/32"]
        }
        phoneHome = {
          description                   = "Hello cluster"
          protocol                      = "udp"
          from_port                     = 53
          to_port                       = 53
          type                          = "egress"
          source_cluster_security_group = true # bit of reflection lookup
        }
      }
      security_group_tags = {
        Purpose = "Protector of the kubelet"
      }

      tags = {
        ExtraTag = "EKS managed node group complete example"
      }
    }
  }

  tags = local.tags
}

# References to resources that do not exist yet when creating a cluster will cause a plan failure due to https://github.com/hashicorp/terraform/issues/4149
# There are two options users can take
# 1. Create the dependent resources before the cluster => `terraform apply -target <your policy or your security group> and then `terraform apply`
#   Note: this is the route users will have to take for adding additonal security groups to nodes since there isn't a separate "security group attachment" resource
# 2. For addtional IAM policies, users can attach the policies outside of the cluster definition as demonstrated below
resource "aws_iam_role_policy_attachment" "additional" {
  for_each = module.eks.eks_managed_node_groups

  policy_arn = aws_iam_policy.node_additional.arn
  role       = each.value.iam_role_name
}

################################################################################
# aws-auth configmap
# Only EKS managed node groups automatically add roles to aws-auth configmap
# so we need to ensure fargate profiles and self-managed node roles are added
################################################################################

data "aws_eks_cluster_auth" "this" {
  name = module.eks.cluster_id
}

locals {
  kubeconfig = yamlencode({
    apiVersion      = "v1"
    kind            = "Config"
    current-context = "terraform"
    clusters = [{
      name = module.eks.cluster_id
      cluster = {
        certificate-authority-data = module.eks.cluster_certificate_authority_data
        server                     = module.eks.cluster_endpoint
      }
    }]
    contexts = [{
      name = "terraform"
      context = {
        cluster = module.eks.cluster_id
        user    = "terraform"
      }
    }]
    users = [{
      name = "terraform"
      user = {
        token = data.aws_eks_cluster_auth.this.token
      }
    }]
  })
}

resource "null_resource" "patch" {
  triggers = {
    kubeconfig = base64encode(local.kubeconfig)
    cmd_patch  = "kubectl patch configmap/aws-auth --patch \"${module.eks.aws_auth_configmap_yaml}\" -n kube-system --kubeconfig <(echo $KUBECONFIG | base64 --decode)"
  }

  provisioner "local-exec" {
    interpreter = ["/bin/bash", "-c"]
    environment = {
      KUBECONFIG = self.triggers.kubeconfig
    }
    command = self.triggers.cmd_patch
  }
}

################################################################################
# Supporting Resources
################################################################################

module "vpc" {
  source  = "terraform-aws-modules/vpc/aws"
  version = "~> 3.0"

  name = local.name
  cidr = "10.0.0.0/16"

  azs             = ["${local.region}a", "${local.region}b", "${local.region}c"]
  private_subnets = ["10.0.1.0/24", "10.0.2.0/24", "10.0.3.0/24"]
  public_subnets  = ["10.0.4.0/24", "10.0.5.0/24", "10.0.6.0/24"]

  enable_ipv6                     = true
  assign_ipv6_address_on_creation = true
  create_egress_only_igw          = true

  public_subnet_ipv6_prefixes  = [0, 1, 2]
  private_subnet_ipv6_prefixes = [3, 4, 5]

  enable_nat_gateway   = true
  single_nat_gateway   = true
  enable_dns_hostnames = true

  enable_flow_log                      = true
  create_flow_log_cloudwatch_iam_role  = true
  create_flow_log_cloudwatch_log_group = true

  public_subnet_tags = {
    "kubernetes.io/cluster/${local.name}" = "shared"
    "kubernetes.io/role/elb"              = 1
  }

  private_subnet_tags = {
    "kubernetes.io/cluster/${local.name}" = "shared"
    "kubernetes.io/role/internal-elb"     = 1
  }

  tags = local.tags
}

resource "aws_kms_key" "eks" {
  description             = "EKS Secret Encryption Key"
  deletion_window_in_days = 7
  enable_key_rotation     = true

  tags = local.tags
}

resource "aws_kms_key" "ebs" {
  description             = "Customer managed key to encrypt EKS managed node group volumes"
  deletion_window_in_days = 7
  policy                  = data.aws_iam_policy_document.ebs.json
}

# This policy is required for the KMS key used for EKS root volumes, so the cluster is allowed to enc/dec/attach encrypted EBS volumes
data "aws_iam_policy_document" "ebs" {
  # Copy of default KMS policy that lets you manage it
  statement {
    sid       = "Enable IAM User Permissions"
    actions   = ["kms:*"]
    resources = ["*"]

    principals {
      type        = "AWS"
      identifiers = ["arn:aws:iam::${data.aws_caller_identity.current.account_id}:root"]
    }
  }

  # Required for EKS
  statement {
    sid = "Allow service-linked role use of the CMK"
    actions = [
      "kms:Encrypt",
      "kms:Decrypt",
      "kms:ReEncrypt*",
      "kms:GenerateDataKey*",
      "kms:DescribeKey"
    ]
    resources = ["*"]

    principals {
      type = "AWS"
      identifiers = [
        "arn:aws:iam::${data.aws_caller_identity.current.account_id}:role/aws-service-role/autoscaling.amazonaws.com/AWSServiceRoleForAutoScaling", # required for the ASG to manage encrypted volumes for nodes
        module.eks.cluster_iam_role_arn,                                                                                                            # required for the cluster / persistentvolume-controller to create encrypted PVCs
      ]
    }
  }

  statement {
    sid       = "Allow attachment of persistent resources"
    actions   = ["kms:CreateGrant"]
    resources = ["*"]

    principals {
      type = "AWS"
      identifiers = [
        "arn:aws:iam::${data.aws_caller_identity.current.account_id}:role/aws-service-role/autoscaling.amazonaws.com/AWSServiceRoleForAutoScaling", # required for the ASG to manage encrypted volumes for nodes
        module.eks.cluster_iam_role_arn,                                                                                                            # required for the cluster / persistentvolume-controller to create encrypted PVCs
      ]
    }

    condition {
      test     = "Bool"
      variable = "kms:GrantIsForAWSResource"
      values   = ["true"]
    }
  }
}

resource "aws_iam_policy" "node_additional" {
  name        = "${local.name}-additional"
  description = "Example usage of node additional policy"

  policy = jsonencode({
    Version = "2012-10-17"
    Statement = [
      {
        Action = [
          "ec2:Describe*",
        ]
        Effect   = "Allow"
        Resource = "*"
      },
    ]
  })

  tags = local.tags
}

data "aws_ami" "eks_default" {
  most_recent = true
  owners      = ["amazon"]

  filter {
    name   = "name"
    values = ["amazon-eks-node-${local.cluster_version}-v*"]
  }
}