## Resolves code-e2dp (Kyverno TF apply blocked)
Root cause: terraform-provider-kubernetes v3.1.0 panics on plan/refresh of
kubernetes_manifest resources holding Kyverno ClusterPolicy CRDs (large
CEL/foreach schemas). Workaround: swap to gavinbunney/kubectl_manifest which
treats manifests as opaque YAML strings.
## Migration mechanics
- Root terragrunt.hcl: added gavinbunney/kubectl provider declaration so all
stacks get it generated in providers.tf.
- stacks/kyverno/modules/kyverno/versions.tf (new): module-level provider source
declaration (required for kubectl_manifest in a child module).
- Converted 17 kubernetes_manifest resources across 7 files to kubectl_manifest
with yaml_body = yamlencode({...}). depends_on chains preserved.
- terraform state rm for all 17 old kubernetes_manifest entries.
- stacks/kyverno/imports.tf (new): TF 1.5+ import blocks mapping each
kubectl_manifest to its live cluster resource by apiVersion//Kind//name ID.
- One resource (policy_inject_keel_annotations) needed kubectl delete + recreate
because the kubectl provider couldn't patch it cleanly (resourceVersion=0
invalid for update — gotcha when adopting a resource previously
kubernetes_manifest-owned).
## W1.4 — security policies Audit → Enforce (LIVE)
Three policies flipped: deny-privileged-containers, deny-host-namespaces,
restrict-sys-admin. Verified live via kubectl. failurePolicy=Ignore preserved.
## Shared exclude list (35 namespaces)
local.security_policy_exclude_namespaces in security-policies.tf.
- 31 critical from memory id=1970 (Keel rollout list)
- + frigate (camera HW transcoding needs host access)
- + kured (privileged DaemonSet for node reboots)
- + default (etcd backup/defrag CronJobs use hostNetwork)
- + changedetection (uses SYS_ADMIN for chromium sandbox)
## W1.5 — require-trusted-registries stays Audit
Pattern */* allows anything-with-a-slash; Enforce would be a no-op for supply
chain. Tracked under beads code-8ywc as follow-up.
## TF import-blocks
The imports.tf file should be removed in a follow-up cleanup commit once
verified — TF doesn't auto-clean these.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Closes: code-e2dp
141 lines
3.6 KiB
HCL
141 lines
3.6 KiB
HCL
# Root Terragrunt configuration
|
|
# Provides DRY provider, backend, and variable loading for all stacks.
|
|
|
|
# Two-tier state backend:
|
|
# Tier 0 (bootstrap): local state, SOPS-encrypted in git — must exist before PG is reachable.
|
|
# Tier 1 (everything else): PG backend on CNPG cluster, native pg_advisory_lock.
|
|
locals {
|
|
tier0_stacks = ["infra", "platform", "cnpg", "vault", "dbaas", "external-secrets"]
|
|
stack_name = replace(path_relative_to_include(), "stacks/", "")
|
|
is_tier0 = contains(local.tier0_stacks, local.stack_name)
|
|
}
|
|
|
|
remote_state {
|
|
backend = local.is_tier0 ? "local" : "pg"
|
|
generate = {
|
|
path = "backend.tf"
|
|
if_exists = "overwrite_terragrunt"
|
|
}
|
|
config = local.is_tier0 ? {
|
|
path = "${get_repo_root()}/state/${path_relative_to_include()}/terraform.tfstate"
|
|
} : {
|
|
conn_str = get_env("PG_CONN_STR", "")
|
|
schema_name = local.stack_name
|
|
}
|
|
}
|
|
|
|
# Load config.tfvars (plaintext). Secrets come from Vault KV — authenticate via `vault login -method=oidc`.
|
|
terraform {
|
|
extra_arguments "common_vars" {
|
|
commands = get_terraform_commands_that_need_vars()
|
|
required_var_files = [
|
|
"${get_repo_root()}/config.tfvars"
|
|
]
|
|
}
|
|
|
|
extra_arguments "no_backup" {
|
|
commands = ["apply", "plan", "destroy", "import"]
|
|
arguments = ["-backup=-"]
|
|
}
|
|
|
|
extra_arguments "kube_config" {
|
|
commands = get_terraform_commands_that_need_vars()
|
|
arguments = [
|
|
"-var", "kube_config_path=${get_repo_root()}/config"
|
|
]
|
|
}
|
|
}
|
|
|
|
# Generate kubernetes + helm + cloudflare providers for all stacks.
|
|
# The infra stack overrides this to add the proxmox provider.
|
|
generate "k8s_providers" {
|
|
path = "providers.tf"
|
|
if_exists = "overwrite_terragrunt"
|
|
contents = <<EOF
|
|
terraform {
|
|
required_providers {
|
|
vault = {
|
|
source = "hashicorp/vault"
|
|
version = "~> 4.0"
|
|
}
|
|
cloudflare = {
|
|
source = "cloudflare/cloudflare"
|
|
version = "~> 4"
|
|
}
|
|
authentik = {
|
|
source = "goauthentik/authentik"
|
|
version = "~> 2024.10"
|
|
}
|
|
# kubectl (gavinbunney) — workaround for hashicorp/kubernetes
|
|
# `kubernetes_manifest` panics on Kyverno CRDs. See beads code-e2dp.
|
|
# Declared for all stacks but only used where opted-in.
|
|
kubectl = {
|
|
source = "gavinbunney/kubectl"
|
|
version = "~> 1.14"
|
|
}
|
|
}
|
|
}
|
|
|
|
variable "kube_config_path" {
|
|
type = string
|
|
default = "~/.kube/config"
|
|
}
|
|
|
|
provider "kubernetes" {
|
|
config_path = var.kube_config_path
|
|
}
|
|
|
|
provider "helm" {
|
|
kubernetes = {
|
|
config_path = var.kube_config_path
|
|
}
|
|
}
|
|
|
|
provider "vault" {
|
|
address = "https://vault.viktorbarzin.me"
|
|
skip_child_token = true
|
|
}
|
|
|
|
provider "kubectl" {
|
|
config_path = var.kube_config_path
|
|
load_config_file = true
|
|
}
|
|
EOF
|
|
}
|
|
|
|
# Generate Cloudflare provider config (separate file to avoid conflicts
|
|
# with stacks that override providers.tf, e.g. infra stack).
|
|
# DNS records are created per-service via ingress_factory's dns_type param.
|
|
generate "cloudflare_provider" {
|
|
path = "cloudflare_provider.tf"
|
|
if_exists = "overwrite_terragrunt"
|
|
contents = <<EOF
|
|
data "vault_kv_secret_v2" "cf_platform" {
|
|
mount = "secret"
|
|
name = "platform"
|
|
}
|
|
|
|
provider "cloudflare" {
|
|
api_key = data.vault_kv_secret_v2.cf_platform.data["cloudflare_api_key"]
|
|
email = "vbarzin@gmail.com"
|
|
}
|
|
EOF
|
|
}
|
|
|
|
# Generate shared tiers locals for all stacks.
|
|
# Previously duplicated in 67+ stacks; now defined once here.
|
|
generate "tiers" {
|
|
path = "tiers.tf"
|
|
if_exists = "overwrite_terragrunt"
|
|
contents = <<EOF
|
|
locals {
|
|
tiers = {
|
|
core = "0-core"
|
|
cluster = "1-cluster"
|
|
gpu = "2-gpu"
|
|
edge = "3-edge"
|
|
aux = "4-aux"
|
|
}
|
|
}
|
|
EOF
|
|
}
|