Add hpz440 host configuration and SSH setup for Windows; update Prometheus targets and variables

ansible/host_vars/game-01.lab.alexpires.me.yml

@@ -10,6 +10,16 @@ game_password: "{{ lookup('env', 'WIN_GAME_PASSWORD') }}"
 game_default_groups:
   - Administradores # This is mandatory to install games
 
+ssh_users:
+  - name: "{{ ansible_user }}"
+    admin: true
+    keys:
+      - "{{ lookup('file', 'keys/ansible_user.pub') }}"
+  - name: calex
+    admin: true
+    keys:
+      - "{{ lookup('file', 'keys/operator.pub') }}"
+
 grafana_prometheus_sources:
   - 10.19.4.136
 windows_exporter_collectors:

ansible/host_vars/hpz440.lab.alexpires.me.yml

@@ -0,0 +1,35 @@
+hostname: hpz440.lab.alexpires.me
+ansible_user: "{{ lookup('env', 'ANSIBLE_USER') }}"
+ansible_password: "{{ lookup('env', 'WIN_HPZ440_PASSWORD') }}"
+ansible_connection: winrm
+ansible_winrm_transport: basic
+ansible_winrm_server_cert_validation: ignore
+
+ssh_users:
+  - name: "{{ ansible_user }}"
+    admin: true
+    keys:
+      - "{{ lookup('file', 'keys/ansible_user.pub') }}"
+  - name: HP
+    admin: true
+    keys:
+      - "{{ lookup('file', 'keys/operator.pub') }}"
+
+grafana_prometheus_sources:
+  - 10.19.4.136
+
+windows_exporter_collectors:
+  - cache
+  - cpu
+  - cpu_info
+  - gpu
+  - diskdrive
+  - logical_disk
+  - memory
+  - net
+  - os
+  - process
+  - service
+  - tcp
+  - time
+  - update

ansible/host_vars/prod-01.alexpires.me.yml

@@ -89,7 +89,7 @@ fail2ban_jails:
     logpath: "/var/log/auth.log"
     maxretry: 5
     findtime: 600
-    bantime: 3600
+    bantime: -1
   postfix:
     enabled: true
     port: "smtp,ssmtp"

ansible/playbook_windows_ssh.yml

@@ -0,0 +1,7 @@
+- name: Setup ssh on Windows
+  hosts: windows
+
+  tasks:
+    - name: Setup ssh
+      ansible.builtin.include_tasks:
+        file: tasks/windows_ssh.yml

ansible/sectool.env

@@ -15,3 +15,4 @@ CLOUDNS_AUTH_ID=$CLOUDNS_AUTH_ID
 CLOUDNS_PASSWORD=$CLOUDNS_PASSWORD
 WIN_PROVISION_PASSWORD=$WIN_PROVISION_PASSWORD
 WIN_GAME_PASSWORD=$WIN_GAME_PASSWORD
+WIN_HPZ440_PASSWORD=$WIN_HPZ440_PASSWORD

ansible/tasks/windows_ssh.yml

@@ -0,0 +1,213 @@
+# Expects variable `ssh_users` as list of objects:
+# ssh_users:
+#   - name: alice
+#     keys:
+#       - "ssh-ed25519 AAAA..."
+#       - "ssh-rsa AAAA..."
+#   - name: bob
+#     keys:
+#       - "ssh-rsa AAAA..."
+- name: Ensure OpenSSH Server capability is installed (if available)
+  ansible.windows.win_shell: |
+    $cap = Get-WindowsCapability -Online | Where-Object { $_.Name -like 'OpenSSH.Server*' }
+    if ($cap -and $cap.State -ne 'Installed') {
+      Add-WindowsCapability -Online -Name $cap.Name
+      Write-Output 'installed'
+    } else {
+      Write-Output 'present'
+    }
+  args:
+    executable: powershell.exe
+  register: openssh_install
+  changed_when: "'installed' in openssh_install.stdout"
+
+- name: Ensure host keys exist (ssh-keygen -A)
+  ansible.windows.win_shell: |
+    $exe = 'C:\Windows\System32\OpenSSH\ssh-keygen.exe'
+    if (Test-Path $exe) {
+      & $exe -A 2>&1
+      Write-Output 'hostkeys-generated'
+    } else {
+      Write-Output 'ssh-keygen-not-found'
+      exit 2
+    }
+  register: ssh_keygen
+  changed_when: "'hostkeys-generated' in ssh_keygen.stdout"
+
+- name: Restrict private host key file permissions (icacls) and remove provision user access
+  ansible.windows.win_shell: |
+    $current = [System.Security.Principal.WindowsIdentity]::GetCurrent().Name
+    $keys = Get-ChildItem -Path 'C:\ProgramData\ssh' -Filter 'ssh_host_*_key' -File -ErrorAction SilentlyContinue
+    if ($keys -and $keys.Count -gt 0) {
+      foreach ($k in $keys) {
+        icacls.exe $k.FullName /inheritance:r
+        icacls.exe $k.FullName /grant:r "S-1-5-18:(F)"
+        icacls.exe $k.FullName /remove $current 2>$null
+      }
+      Write-Output "restricted: removed access for $current"
+    } else {
+      Write-Output 'no-keys'
+    }
+  args:
+    executable: powershell.exe
+  register: restrict_hostkey_perms
+  changed_when: "'restricted' in restrict_hostkey_perms.stdout"
+
+- name: Ensure sshd service is enabled and running
+  ansible.windows.win_service:
+    name: sshd
+    start_mode: auto
+    state: started
+
+- name: Ensure firewall allows SSH (TCP/22)
+  community.windows.win_firewall_rule:
+    name: "OpenSSH Server (sshd)"
+    enable: true
+    direction: in
+    action: allow
+    localport: 22
+    protocol: TCP
+    profile: "Domain,Private"
+
+- name: Ensure PubkeyAuthentication is enabled in sshd_config
+  community.windows.win_lineinfile:
+    path: 'C:\ProgramData\ssh\sshd_config'
+    regexp: "^#?PubkeyAuthentication"
+    line: "PubkeyAuthentication yes"
+    create: true
+    backup: true
+  register: sshd_pubkey_changed
+
+- name: Ensure AuthorizedKeysFile is set to .ssh/authorized_keys
+  community.windows.win_lineinfile:
+    path: 'C:\ProgramData\ssh\sshd_config'
+    regexp: "^#?AuthorizedKeysFile"
+    line: "AuthorizedKeysFile .ssh/authorized_keys"
+    create: true
+    backup: true
+  register: sshd_authkeys_changed
+
+- name: Detect available PowerShell for ssh subsystem
+  ansible.windows.win_shell: |
+    if (Test-Path 'C:\Program Files\PowerShell\7\pwsh.exe') { Write-Output 'C:\Program Files\PowerShell\7\pwsh.exe' }
+    elseif (Test-Path 'C:\Program Files\PowerShell\6\pwsh.exe') { Write-Output 'C:\Program Files\PowerShell\6\pwsh.exe' }
+    elseif (Test-Path 'C:\Windows\System32\WindowsPowerShell\v1.0\powershell.exe') { Write-Output 'C:\Windows\System32\WindowsPowerShell\v1.0\powershell.exe' }
+    else { Write-Output '' }
+  register: ssh_subsystem_path
+  changed_when: false
+
+- name: Configure sshd Subsystem to allow PowerShell sessions
+  community.windows.win_lineinfile:
+    path: 'C:\ProgramData\ssh\sshd_config'
+    regexp: '^Subsystem\s+powershell'
+    line: 'Subsystem powershell "{{ ssh_subsystem_path.stdout | trim }}" -sshs -NoLogo -NoProfile'
+    create: true
+    backup: true
+  register: sshd_subsystem_changed
+  when: ssh_subsystem_path.stdout != ''
+
+- name: Restart sshd if config changed
+  ansible.windows.win_service:
+    name: sshd
+    state: restarted
+  when: sshd_pubkey_changed.changed or sshd_authkeys_changed.changed or sshd_subsystem_changed.changed
+
+- name: Ensure users for SSH keys exist (no-op if already present)
+  ansible.windows.win_user:
+    name: "{{ item.name }}"
+    state: present
+  loop: "{{ ssh_users | default([]) }}"
+  loop_control:
+    label: "{{ item.name }}"
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Ensure user .ssh directory exists
+  ansible.windows.win_file:
+    path: "C:\\Users\\{{ item.name }}\\.ssh"
+    state: directory
+  loop: "{{ ssh_users | default([]) }}"
+  loop_control:
+    label: "{{ item.name }}"
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Deploy authorized_keys for each user
+  ansible.windows.win_copy:
+    dest: "C:\\Users\\{{ item.name }}\\.ssh\\authorized_keys"
+    content: "{{ (item['keys'] | default([])) | join('\r\n') }}\r\n"
+    force: true
+  loop: "{{ ssh_users | default([]) }}"
+  loop_control:
+    label: "{{ item.name }}"
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Set ACL on .ssh directory to allow only the user and Administradores (directory)
+  ansible.windows.win_acl:
+    path: "C:\\Users\\{{ item.name }}\\.ssh"
+    user: "{{ item.name }}"
+    rights: FullControl
+    type: allow
+    inheritance: false
+    propagate: false
+    state: present
+  loop: "{{ ssh_users | default([]) }}"
+  loop_control:
+    label: "{{ item.name }}"
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Set ACL on authorized_keys file to allow only the user and Administradores (file)
+  ansible.windows.win_acl:
+    path: "C:\\Users\\{{ item.name }}\\.ssh\\authorized_keys"
+    user: "{{ item.name }}"
+    rights: FullControl
+    type: allow
+    inheritance: false
+    propagate: false
+    state: present
+  loop: "{{ ssh_users | default([]) }}"
+  loop_control:
+    label: "{{ item.name }}"
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Create administrators_authorized_keys from admin users' keys (if any)
+  ansible.windows.win_copy:
+    dest: 'C:\ProgramData\ssh\administrators_authorized_keys'
+    content: "{{ (ssh_users | default([]) | selectattr('admin','equalto',true) | map(attribute='keys') | list | flatten | default([])) | join('\r\n') }}\r\n"
+    force: true
+  when: (ssh_users | default([]) | selectattr('admin','equalto',true) | list) | length > 0
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Tighten ACLs for administrators_authorized_keys (icacls)
+  ansible.windows.win_shell: |
+    $f = 'C:\ProgramData\ssh\administrators_authorized_keys'
+    $current = [System.Security.Principal.WindowsIdentity]::GetCurrent().Name
+    if (Test-Path $f) {
+      icacls.exe $f /inheritance:r
+      icacls.exe $f /grant:r "S-1-5-18:(F)" "S-1-5-32-544:(F)"
+      icacls.exe $f /remove $current 2>$null
+      Write-Output 'restricted'
+    } else {
+      Write-Output 'no-file'
+    }
+  args:
+    executable: powershell.exe
+  register: restrict_admin_auth_perms
+  changed_when: "'restricted' in restrict_admin_auth_perms.stdout"
+  become: true
+  become_method: runas
+  become_user: "NT AUTHORITY\\SYSTEM"
+
+- name: Debug administrators_authorized_keys ACL change
+  ansible.builtin.debug:
+    var: restrict_admin_auth_perms.stdout

inventory/hosts

@@ -98,13 +98,15 @@ gpu-01.lab.alexpires.me
 
 [windows]
 game-01.lab.alexpires.me
+hpz440.lab.alexpires.me
 
 [windows_game]
 game-01.lab.alexpires.me
 
-[prometheus]
+[prometheus_linux]
 prod-01.alexpires.me
 dev-01.lab.alexpires.me
 
 [windows_prometheus]
-game-01.lab.alexpires.me
+game-01.lab.alexpires.me
+hpz440.lab.alexpires.me

scripts/ConfigureRemotingForAnsible.ps1

@@ -165,11 +165,20 @@ Function New-LegacySelfSignedCert {
     $certdata = $enrollment.CreateRequest(0)
     $enrollment.InstallResponse(2, $certdata, 0, "")
 
-    # extract/return the thumbprint from the generated cert
+    try {
-    $parsed_cert = New-Object System.Security.Cryptography.X509Certificates.X509Certificate2
+        # Try to decode as base64 (most likely) then construct the cert from raw bytes.
-    $parsed_cert.Import([System.Text.Encoding]::UTF8.GetBytes($certdata))
+        $raw = $null
-
+        try {
-    return $parsed_cert.Thumbprint
+            $raw = [Convert]::FromBase64String($certdata)
+        } catch {
+            # Fallback to UTF8 bytes if it's not base64
+            $raw = [System.Text.Encoding]::UTF8.GetBytes($certdata)
+        }
+        $parsed_cert = New-Object System.Security.Cryptography.X509Certificates.X509Certificate2 -ArgumentList (, $raw)
+        return $parsed_cert.Thumbprint
+    } catch {
+        Throw "Failed to construct X509Certificate2 from generated data: $($_.Exception.Message)"
+    }
 }
 
 Function Enable-GlobalHttpFirewallAccess {
@@ -327,7 +336,9 @@ If (!($listeners | Where-Object { $_.Keys -like "TRANSPORT=HTTPS" })) {
     }
 
     Write-Verbose "Enabling SSL listener."
-    New-WSManInstance -ResourceURI 'winrm/config/Listener' -SelectorSet $selectorset -ValueSet $valueset
+    # Fallback to winrm.exe create which is more compatible across WinRM versions
+    $body = "@{Hostname=`"$SubjectName`";CertificateThumbprint=`"$thumbprint`"}"
+    & winrm create 'winrm/config/Listener?Address=*+Transport=HTTPS' $body
     Write-ProgressLog "Enabled SSL listener."
 }
 Else {
@@ -353,7 +364,8 @@ Else {
         Remove-WSManInstance -ResourceURI 'winrm/config/Listener' -SelectorSet $selectorset
 
         # Add new Listener with new SSL cert
-        New-WSManInstance -ResourceURI 'winrm/config/Listener' -SelectorSet $selectorset -ValueSet $valueset
+        $body = "@{Hostname=`"$SubjectName`";CertificateThumbprint=`"$thumbprint`"}"
+        & winrm create 'winrm/config/Listener?Address=*+Transport=HTTPS' $body
     }
 }
 

terraform/apps/dev-01/config.tf

@@ -92,6 +92,11 @@ locals {
           type    = "A"
           content = "10.5.5.2"
         },
+        {
+          name    = "hpz440"
+          type    = "A"
+          content = "10.19.4.121"
+        },
       ]
     }
   ]

terraform/apps/dev-01/resources/prometheus.yml

@@ -3,10 +3,10 @@ scrape_configs:
     scrape_interval: 10s
     static_configs:
       - targets:
-          - "node-exporter.kube-system.svc.cluster.local:9100"
+          - "node-exporter.prometheus.svc.cluster.local:9100"
           - "10.19.4.1:9100"
   - job_name: auth-exporter
     scrape_interval: 10s
     static_configs:
       - targets:
-          - "auth-exporter.kube-system.svc.cluster.local:9100"
+          - "auth-exporter.prometheus.svc.cluster.local:9100"

terraform/apps/prod-01/resources/prometheus.yml

@@ -2,13 +2,15 @@ scrape_configs:
   - job_name: node-exporter
     scrape_interval: 10s
     static_configs:
-      - targets: ["node-exporter.kube-system.svc.cluster.local:9100"]
+      - targets:
+          - "node-exporter.prometheus.svc.cluster.local:9100"
   - job_name: fail2ban
     scrape_interval: 60s
     static_configs:
-      - targets: ["fail2ban-exporter.kube-system.svc.cluster.local:9100"]
+      - targets:
+          - "fail2ban-exporter.prometheus.svc.cluster.local:9100"
   - job_name: auth-exporter
     scrape_interval: 10s
     static_configs:
       - targets:
-          - "auth-exporter.kube-system.svc.cluster.local:9100"
+          - "auth-exporter.prometheus.svc.cluster.local:9100"

terraform/modules/apps/grafana/resources/prometheus.bak.yml

@@ -1,126 +0,0 @@
-global:
-  scrape_interval: 5s
-  evaluation_interval: 5s
-rule_files:
-  - /etc/prometheus/prometheus.rules
-alerting:
-  alertmanagers:
-    - scheme: http
-      static_configs:
-        - targets:
-            - "alertmanager.monitoring.svc:9093"
-scrape_configs:
-  - job_name: "node-exporter"
-    kubernetes_sd_configs:
-      - role: endpoints
-    relabel_configs:
-      - source_labels: [__meta_kubernetes_endpoints_name]
-        regex: "node-exporter"
-        action: keep
-  - job_name: "kubernetes-apiservers"
-    kubernetes_sd_configs:
-      - role: endpoints
-    scheme: https
-    tls_config:
-      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
-    relabel_configs:
-      - source_labels:
-          [
-            __meta_kubernetes_namespace,
-            __meta_kubernetes_service_name,
-            __meta_kubernetes_endpoint_port_name,
-          ]
-        action: keep
-        regex: default;kubernetes;https
-  - job_name: "kubernetes-nodes"
-    scheme: https
-    tls_config:
-      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
-    kubernetes_sd_configs:
-      - role: node
-    relabel_configs:
-      - action: labelmap
-        regex: __meta_kubernetes_node_label_(.+)
-      - target_label: __address__
-        replacement: kubernetes.default.svc:443
-      - source_labels: [__meta_kubernetes_node_name]
-        regex: (.+)
-        target_label: __metrics_path__
-        replacement: /api/v1/nodes/$${1}/proxy/metrics
-  - job_name: "kubernetes-pods"
-    kubernetes_sd_configs:
-      - role: pod
-    relabel_configs:
-      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
-        action: keep
-        regex: true
-      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
-        action: replace
-        target_label: __metrics_path__
-        regex: (.+)
-      - source_labels:
-          [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
-        action: replace
-        regex: ([^:]+)(?::\d+)?;(\d+)
-        replacement: $1:$2
-        target_label: __address__
-      - action: labelmap
-        regex: __meta_kubernetes_pod_label_(.+)
-      - source_labels: [__meta_kubernetes_namespace]
-        action: replace
-        target_label: kubernetes_namespace
-      - source_labels: [__meta_kubernetes_pod_name]
-        action: replace
-        target_label: kubernetes_pod_name
-  - job_name: "kube-state-metrics"
-    static_configs:
-      - targets: ["kube-state-metrics.kube-system.svc.cluster.local:8080"]
-  - job_name: "kubernetes-cadvisor"
-    scheme: https
-    tls_config:
-      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
-    kubernetes_sd_configs:
-      - role: node
-    relabel_configs:
-      - action: labelmap
-        regex: __meta_kubernetes_node_label_(.+)
-      - target_label: __address__
-        replacement: kubernetes.default.svc:443
-      - source_labels: [__meta_kubernetes_node_name]
-        regex: (.+)
-        target_label: __metrics_path__
-        replacement: /api/v1/nodes/$${1}/proxy/metrics/cadvisor
-  - job_name: "kubernetes-service-endpoints"
-    kubernetes_sd_configs:
-      - role: endpoints
-    relabel_configs:
-      - source_labels:
-          [__meta_kubernetes_service_annotation_prometheus_io_scrape]
-        action: keep
-        regex: true
-      - source_labels:
-          [__meta_kubernetes_service_annotation_prometheus_io_scheme]
-        action: replace
-        target_label: __scheme__
-        regex: (https?)
-      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
-        action: replace
-        target_label: __metrics_path__
-        regex: (.+)
-      - source_labels:
-          [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
-        action: replace
-        target_label: __address__
-        regex: ([^:]+)(?::\d+)?;(\d+)
-        replacement: $1:$2
-      - action: labelmap
-        regex: __meta_kubernetes_service_label_(.+)
-      - source_labels: [__meta_kubernetes_namespace]
-        action: replace
-        target_label: kubernetes_namespace
-      - source_labels: [__meta_kubernetes_service_name]
-        action: replace
-        target_label: kubernetes_name

terraform/modules/utils/auth-exporter/variables.tf

@@ -7,7 +7,7 @@ variable "tag" {
 variable "namespace" {
   description = "Kubernetes namespace to deploy the prometheus exporter"
   type        = string
-  default     = "kube-system"
+  default     = "prometheus"
 }
 
 variable "persistent_folder" {

terraform/modules/utils/fail2ban-exporter/variables.tf

@@ -7,5 +7,5 @@ variable "tag" {
 variable "namespace" {
   description = "Kubernetes namespace to deploy the Fail2Ban exporter"
   type        = string
-  default     = "kube-system"
+  default     = "prometheus"
 }

terraform/modules/utils/node-exporter/variables.tf

@@ -7,5 +7,5 @@ variable "tag" {
 variable "namespace" {
   description = "Kubernetes namespace to deploy the Fail2Ban exporter"
   type        = string
-  default     = "kube-system"
+  default     = "prometheus"
 }