feat: add system-upgrade role for kernel/nvidia migration

Co-authored-by: Junie <junie@jetbrains.com>

ansible/roles/system-upgrade/defaults/main.yml

@@ -0,0 +1,6 @@
+---
+# Role-local defaults for system-upgrade.
+# Project-wide kernel/NVIDIA package lists live in ansible/vars/main.yml so
+# they can be reused by future roles (e.g. hyprland) without re-declaration.
+# Override here only if you need a different value when running this role
+# stand-alone (ansible-playbook ... -e @custom-vars.yml).

ansible/roles/system-upgrade/handlers/main.yml

@@ -0,0 +1,6 @@
+---
+# Handlers for system-upgrade role.
+# Currently the role uses explicit gated tasks (when: ... .changed) rather
+# than notify/handler chains, because every kernel/driver change must trigger
+# both mkinitcpio AND grub-mkconfig in a strict order. If you later split
+# tasks across files, prefer the standard notify pattern here.

ansible/roles/system-upgrade/tasks/main.yml

@@ -0,0 +1,289 @@
+---
+# system-upgrade role — full system upgrade + kernel/NVIDIA preparation
+# for the upcoming Hyprland/Wayland migration. Idempotent: a clean re-run
+# on an already-upgraded box performs no destructive action.
+#
+# Sections:
+#   1. Pre-flight checks  (OS guard, free space, summary)
+#   2. Full system upgrade   (pacman -Syu)            — added in Step 2
+#   3. NVIDIA branch migration + kernel install        — added in Step 3
+#   4. Initramfs + GRUB refresh + final reboot notice  — added in Step 4
+#
+# Run as:
+#   ansible-playbook ansible/workstation.yml --check --tags system-upgrade
+#   ansible-playbook ansible/workstation.yml          --tags system-upgrade
+
+# ---------------------------------------------------------------------------
+# 1. Pre-flight checks
+# ---------------------------------------------------------------------------
+
+- name: Pre-flight - announce role start
+  debug:
+    msg:
+      - "system-upgrade: preparing baseline for Hyprland/Wayland migration"
+      - "kernels to ensure installed: {{ kernel_packages | join(', ') }}"
+      - "nvidia modules to ensure installed: {{ nvidia_kernel_modules | join(', ') }}"
+      - "nvidia legacy packages to remove: {{ nvidia_packages_to_remove | join(', ') }}"
+  tags: [system-upgrade, preflight]
+
+- name: Pre-flight - capture free space on / (GiB)
+  shell: |
+    set -o pipefail
+    df --output=avail -BG / | tail -1 | tr -dc '0-9'
+  args:
+    executable: /bin/bash
+  register: root_free_gb
+  changed_when: false
+  check_mode: false
+  tags: [system-upgrade, preflight]
+
+- name: Pre-flight - fail if free space on / < {{ min_free_root_gb }} GiB
+  fail:
+    msg: >-
+      Only {{ root_free_gb.stdout }} GiB free on /, need at least
+      {{ min_free_root_gb }} GiB before running pacman -Syu and installing
+      a second kernel. Run `paccache -rk2` and clear ~/.cache before retrying.
+  when: (root_free_gb.stdout | int) < (min_free_root_gb | int)
+  tags: [system-upgrade, preflight]
+
+- name: Pre-flight - record currently running kernel
+  command: uname -r
+  register: running_kernel
+  changed_when: false
+  check_mode: false
+  tags: [system-upgrade, preflight]
+
+- name: Pre-flight - summary
+  debug:
+    msg:
+      - "running kernel:   {{ running_kernel.stdout }}"
+      - "free space on /:  {{ root_free_gb.stdout }} GiB (min required {{ min_free_root_gb }})"
+      - "OS guard:         os_type == '{{ os_type }}' (must be 'archlinux')"
+  tags: [system-upgrade, preflight]
+
+# ---------------------------------------------------------------------------
+# 2. Full system upgrade (pacman -Syu)
+# ---------------------------------------------------------------------------
+# Bring the box to current Manjaro Stable before touching kernels/drivers.
+# `community.general.pacman` runs the equivalent of `pacman -Syu`:
+#   - update_cache: yes  -> pacman -Sy
+#   - upgrade: yes       -> pacman -Su
+# It reports changed=True iff packages were actually upgraded, which we use
+# below to gate the kernel/driver migration so an already-current box is a
+# true no-op.
+
+- name: Upgrade - full system upgrade (pacman -Syu)
+  community.general.pacman:
+    update_cache: yes
+    upgrade: yes
+  register: pacman_syu
+  tags: [system-upgrade, upgrade, pacman]
+
+- name: Upgrade - summary
+  debug:
+    msg:
+      - "pacman -Syu changed: {{ pacman_syu.changed | default(false) }}"
+      - "packages touched:    {{ (pacman_syu.packages | default([])) | length }}"
+      - "first 10 packages:   {{ (pacman_syu.packages | default([]))[:10] | join(', ') }}"
+  tags: [system-upgrade, upgrade]
+
+# ---------------------------------------------------------------------------
+# 3. NVIDIA branch migration + kernel install
+# ---------------------------------------------------------------------------
+# Goal: end up with BOTH linux618 (LTS/Fallback) and linux70 (stable) installed, each
+# with matching *-nvidia kernel modules on the 580xx branch.
+# in the same transaction so the GPU never has a "no driver" window of more
+# than ~1 second on a local pacman cache.
+#
+# Safety guarantees:
+#   - linux618 (currently running kernel) is in `kernel_packages`, never in
+#     `nvidia_packages_to_remove` — asserted below.
+#   - The remove step uses the list of 575xx packages that are *actually*
+#     installed, so re-running the role after a successful migration is a
+#     true no-op (LEGACY is empty -> pacman -Rdd is skipped).
+#   - The install step uses --needed so already-current packages are not
+#     touched a second time.
+
+- name: Migration - safety assertion (Fallback kernel must NOT be removed)
+  assert:
+    that:
+      - "'linux618' in kernel_packages"
+      - "'linux618' not in nvidia_packages_to_remove"
+      - "kernel_packages | length > 0"
+      - "nvidia_kernel_modules | length > 0"
+    fail_msg: >-
+      Refusing to migrate: configuration would remove the running fallback kernel.
+      Check ansible/vars/main.yml: 'linux618' must stay in kernel_packages.
+  tags: [system-upgrade, migration]
+
+- name: Migration - detect which legacy 575xx packages are currently installed
+  shell: |
+    set -o pipefail
+    pacman -Qq {{ nvidia_packages_to_remove | join(' ') }} 2>/dev/null || true
+  args:
+    executable: /bin/bash
+  register: nvidia_legacy_installed
+  changed_when: false
+  check_mode: false
+  tags: [system-upgrade, migration]
+
+- name: Migration - check-mode dry-run (pacman -S --print)
+  shell: |
+    set -o pipefail
+    pacman -S --needed --print {{ (kernel_packages + nvidia_kernel_modules + nvidia_userspace_packages) | join(' ') }} 2>&1 | head -40 || true
+  args:
+    executable: /bin/bash
+  register: nvidia_dryrun
+  changed_when: false
+  check_mode: false
+  when: ansible_check_mode
+  tags: [system-upgrade, migration]
+
+- name: Migration - check-mode preview output
+  debug:
+    msg:
+      - "legacy 575xx packages currently installed:"
+      - "{{ nvidia_legacy_installed.stdout_lines | default([]) }}"
+      - "pacman would install (first 40 lines of --print):"
+      - "{{ nvidia_dryrun.stdout_lines | default([]) }}"
+  when: ansible_check_mode
+  tags: [system-upgrade, migration]
+
+- name: Migration - swap NVIDIA branch (575xx -> 580xx) and install kernels
+  shell: |
+    set -eo pipefail
+    LEGACY="{{ nvidia_legacy_installed.stdout_lines | default([]) | join(' ') }}"
+    if [ -n "$LEGACY" ]; then
+      echo ">>> dropping legacy 575xx packages: $LEGACY"
+      pacman -Rdd --noconfirm $LEGACY
+    else
+      echo ">>> no legacy 575xx packages present — skipping drop step"
+    fi
+    echo ">>> ensuring target packages are present (kernels + nvidia modules + userspace)"
+    pacman -S --needed --noconfirm {{ (kernel_packages + nvidia_kernel_modules + nvidia_userspace_packages) | join(' ') }}
+  args:
+    executable: /bin/bash
+  register: nvidia_migration
+  become: yes
+  when: not ansible_check_mode
+  # Detect REAL pacman activity (not our own echo lines): pacman prints
+  # progress lines like "(3/4) installing linux70" / "(1/4) upgrading foo" /
+  # "(2/4) removing nvidia-575xx-utils". Match exactly that format so re-runs
+  # on an already-current box report changed=false.
+  changed_when: >-
+    (nvidia_migration.stdout | default('')) is search('\([0-9]+/[0-9]+\)\s+(installing|upgrading|removing)\s')
+  tags: [system-upgrade, migration]
+
+- name: Migration - verify all target packages are present after install
+  command: pacman -Q {{ item }}
+  loop: "{{ kernel_packages + nvidia_kernel_modules + nvidia_userspace_packages }}"
+  register: pkg_verify
+  changed_when: false
+  check_mode: false
+  failed_when: (pkg_verify.rc | default(0)) != 0 and not ansible_check_mode
+  tags: [system-upgrade, migration]
+
+- name: Migration - recovery notice
+  debug:
+    msg:
+      - "Recovery if linux70 fails to boot:"
+      - "  1. Reboot, hold SHIFT (or ESC) at POST to open the GRUB menu."
+      - "  2. Pick 'Advanced options for Manjaro Linux' -> 'linux618-x86_64'."
+      - "  3. linux618 + linux618-nvidia (580xx) modules are kept intact"
+      - "     so the fallback path is always bootable."
+  tags: [system-upgrade, migration]
+
+# ---------------------------------------------------------------------------
+# 4. Initramfs refresh + GRUB regenerate + final reboot notice
+# ---------------------------------------------------------------------------
+# Manjaro's pacman post-install hooks normally invoke mkinitcpio and update-grub
+# automatically. We re-run them explicitly here as a belt-and-suspenders safety
+# net: if a hook was missed (e.g. interrupted transaction), the system still
+# ends up bootable. Both tasks are gated on "did pacman actually change
+# anything?" so an idempotent re-run is a true no-op.
+
+- name: Boot - rebuild initramfs for all installed kernels (mkinitcpio -P)
+  command: mkinitcpio -P
+  become: yes
+  register: mkinitcpio_result
+  when:
+    - not ansible_check_mode
+    - (pacman_syu.changed | default(false)) or (nvidia_migration.changed | default(false))
+  tags: [system-upgrade, boot, initramfs]
+
+- name: Boot - regenerate GRUB config (-> /boot/grub/grub.cfg)
+  command: grub-mkconfig -o /boot/grub/grub.cfg
+  become: yes
+  register: grub_mkconfig_result
+  when:
+    - not ansible_check_mode
+    - (pacman_syu.changed | default(false)) or (nvidia_migration.changed | default(false))
+  tags: [system-upgrade, boot, grub]
+
+- name: Boot - stat both initramfs images
+  stat:
+    path: "{{ item }}"
+  loop:
+    - /boot/initramfs-6.18-x86_64.img
+    - /boot/initramfs-7.0-x86_64.img
+  register: initramfs_stat
+  changed_when: false
+  check_mode: false
+  tags: [system-upgrade, boot, initramfs]
+
+- name: Boot - assert both initramfs images are present after install
+  assert:
+    that:
+      - item.stat.exists
+    fail_msg: >-
+      Missing initramfs image: {{ item.item }} — investigate the mkinitcpio
+      output above before rebooting. linux618 path may still be usable
+      if only the linux70 image is missing.
+  loop: "{{ initramfs_stat.results }}"
+  loop_control:
+    label: "{{ item.item }}"
+  when: not ansible_check_mode
+  tags: [system-upgrade, boot, initramfs]
+
+- name: Boot - assert GRUB menu lists both kernels (linux618 + linux70)
+  shell: |
+    # Manjaro grub.cfg uses 'Manjaro Linux (Kernel: X.Y.Z-MANJARO x64)' format,
+    # NOT 'linux618'/'linux70' package-name tokens. Count menuentries for each
+    # kernel family separately so we fail if one is missing (a simple total
+    # count would mask a missing kernel if the other family has 2+ entries).
+    K618=$(grep -cE "menuentry .*Kernel: 6\.18\." /boot/grub/grub.cfg)
+    K70=$(grep  -cE "menuentry .*Kernel: 7\.0\."  /boot/grub/grub.cfg)
+    echo "linux618 (Kernel: 6.18.x) menuentries: ${K618}"
+    echo "linux70  (Kernel: 7.0.x)  menuentries: ${K70}"
+    if [ "${K618}" -lt 1 ] || [ "${K70}" -lt 1 ]; then
+      echo "FAIL: missing menuentry for one or both kernels" >&2
+      exit 1
+    fi
+    echo "OK: both kernels are listed in /boot/grub/grub.cfg"
+  args:
+    executable: /bin/bash
+  register: grub_menu_check
+  changed_when: false
+  check_mode: false
+  failed_when:
+    - grub_menu_check.rc != 0
+    - not ansible_check_mode
+  tags: [system-upgrade, boot, grub]
+
+- name: Boot - final reboot notice
+  debug:
+    msg:
+      - "================================================================"
+      - "system-upgrade role finished successfully."
+      - ""
+      - "NEXT STEP: reboot and select 'linux70' from the GRUB menu."
+      - "  1. sudo reboot"
+      - "  2. At the GRUB menu, choose 'Advanced options for Manjaro Linux'"
+      - "     -> 'Manjaro Linux on /dev/... linux70-x86_64'."
+      - "  3. After login, verify with:"
+      - "       uname -r     # expect 7.0.x"
+      - "       nvidia-smi   # expect driver 580.159.03 on GTX 1050 Ti"
+      - ""
+      - "Only AFTER a successful linux70 boot, run the upcoming Hyprland role."
+      - "================================================================"
+  tags: [system-upgrade, notice]