infrastructure/mw-pfeddersheim-workstation
2
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity
Files
5a714e6256464bd7122eac28f1624b7860be1eac
mw-pfeddersheim-workstation/scripts/nvidia-recovery.sh
T
jaandJunie de24990208 chore: add maintenance scripts and update editor preference 
- Add scripts/cleanup.sh for package cleanup (dry-run/apply modes)
- Add scripts/nvidia-recovery.sh for broken GUI recovery
- Update AGENTS.md with new script references
- Change default editor from vim to nvim in bashrc

Co-authored-by: Junie <junie@jetbrains.com>
2026-06-15 06:43:43 +02:00

231 lines
8.1 KiB
Bash
Executable File
Raw Blame History

#!/bin/bash
set -euo pipefail
# NVIDIA Kernel Module Recovery Script
# Purpose: Reinstall nvidia-580xx-dkms and rebuild kernel module after package cleanup removed it
# Target: mw-pfeddersheim-workstation (Manjaro, NVIDIA GPU)
MODE="apply"
if [[ "${1:-}" == "--check" ]]; then
MODE="check"
echo "=== Running in CHECK mode (diagnostic only, no changes) ==="
elif [[ "${1:-}" == "--help" ]]; then
echo "Usage: $0 [--check | --apply | --help]"
echo " --check Diagnose and show what would be done"
echo " --apply Reinstall nvidia-580xx-dkms and rebuild module (requires sudo)"
echo " --help Show this help"
exit 0
fi
mkdir -p "$HOME/logs" 2>/dev/null || true
LOCAL_LOG="$HOME/logs/nvidia-recovery-$(date +%Y%m%d-%H%M%S).log"
BOLD=$(tput bold 2>/dev/null || true)
RED=$(tput setaf 1 2>/dev/null || true)
GREEN=$(tput setaf 2 2>/dev/null || true)
YELLOW=$(tput setaf 3 2>/dev/null || true)
RESET=$(tput sgr0 2>/dev/null || true)
log() { echo -e "$*" | tee -a "$LOCAL_LOG"; }
section() { log ""; log "${BOLD}--- $1 ---${RESET}"; }
echo "" | tee -a "$LOCAL_LOG"
log "============================================="
log " NVIDIA Kernel Module Recovery"
log " Date: $(date)"
log " Log: $LOCAL_LOG"
log "============================================="
# ============================================================
# 1. DIAGNOSTICS
# ============================================================
section "Diagnostic"
# Get current kernel
RUNNING_KERNEL=$(uname -r)
log "Running kernel: $RED$RUNNING_KERNEL$RESET"
KERNEL_VERSION="${RUNNING_KERNEL%-MANJARO}" # 6.18.33-1
KERNEL_MAJOR="${KERNEL_VERSION%%.*}" # 6
KERNEL_MINOR="${KERNEL_VERSION#*.}" # 18.33-1
KERNEL_MINOR="${KERNEL_MINOR%%.*}" # 18
KERNEL_PKG="linux${KERNEL_MAJOR}${KERNEL_MINOR}" # linux618
log "Kernel package: $KERNEL_PKG"
# Check if nvidia module exists
MODULE_PATH="/usr/lib/modules/$RUNNING_KERNEL/extra/modules/nvidia.ko.zst"
MODULE_PATH2="/usr/lib/modules/$RUNNING_KERNEL/extra/nvidia.ko.zst"
MODULE_PATH3="/usr/lib/modules/$RUNNING_KERNEL/updates/dkms/nvidia.ko.zst"
MODULE_PATH4="/usr/lib/modules/$RUNNING_KERNEL/updates/nvidia.ko.zst"
MODULE_PATH5="/usr/lib/modules/$RUNNING_KERNEL/kernel/drivers/gpu/drm/nvidia/nvidia.ko.zst"
MODULE_FOUND=false
if [[ -f "$MODULE_PATH" ]] || [[ -f "$MODULE_PATH2" ]] || [[ -f "$MODULE_PATH3" ]] || [[ -f "$MODULE_PATH4" ]] || [[ -f "$MODULE_PATH5" ]]; then
MODULE_FOUND=true
log "${GREEN}NVIDIA module found at $MODULE_PATH3$RESET"
else
log "${RED}NVIDIA module MISSING for kernel $RUNNING_KERNEL$RESET"
fi
# Check nvidia-utils
if command -v nvidia-smi &>/dev/null; then
log "${GREEN}nvidia-smi: available$RESET"
else
log "${RED}nvidia-smi: not found$RESET"
fi
# Check DKMS
if command -v dkms &>/dev/null; then
log "${GREEN}dkms: available$RESET"
else
log "${RED}dkms: not found$RESET"
fi
# Check if nvidia-580xx-dkms is installed
if pacman -Q nvidia-580xx-dkms &>/dev/null; then
DKMS_INSTALLED=true
log "${GREEN}nvidia-580xx-dkms: installed$(pacman -Qi nvidia-580xx-dkms 2>/dev/null | grep Version)"
else
DKMS_INSTALLED=false
log "${RED}nvidia-580xx-dkms: NOT installed$RESET"
fi
# Check if nvidia-utils is installed
if pacman -Q nvidia-utils &>/dev/null; then
log "${GREEN}nvidia-utils: installed"
else
log "${RED}nvidia-utils: NOT installed$RESET"
fi
# Check modules-load config
if [[ -f /etc/modules-load.d/mhwd-gpu.conf ]]; then
log "modules-load config: /etc/modules-load.d/mhwd-gpu.conf exists"
log " Entries: $(grep -v '^#\|^$' /etc/modules-load.d/mhwd-gpu.conf | tr '\n' ' ')"
else
log "${RED}No mhwd-gpu.conf found$RESET"
fi
# ============================================================
# 2. CHECK DEPENDENCIES
# ============================================================
section "Dependency Check"
MISSING=()
if ! command -v dkms &>/dev/null; then
MISSING+=(dkms)
fi
if ! command -v mkinitcpio &>/dev/null; then
MISSING+=(mkinitcpio)
fi
if [[ ${#MISSING[@]} -gt 0 ]]; then
log "${RED}Missing base tools: ${MISSING[*]}$RESET"
log "These will be installed as part of the fix."
fi
# Check available disk space
DISK_AVAIL=$(df -h / | awk 'NR==2 {print $4}')
log "Disk available: $DISK_AVAIL"
# ============================================================
# 3. APPLY FIX
# ============================================================
section "Applying Fix"
if [[ "$MODE" == "check" ]]; then
log "${BOLD}DRY-RUN MODE${RESET}"
log "Would execute:"
log " sudo pacman -Rns --noconfirm nvidia-utils # remove conflicting non-580xx driver"
log " sudo pacman -S --needed nvidia-580xx-dkms nvidia-580xx-utils"
log " sudo pacman -S --needed linux618-headers # kernel headers for DKMS"
log " sudo dkms autoinstall"
log " sudo mkinitcpio -P"
log " sudo reboot"
exit 0
fi
# Confirm before destructive action
log "${BOLD}This will reinstall the NVIDIA kernel module driver.$RESET"
log "The system will reboot automatically."
read -rp "Continue? [y/N] " confirm
if [[ ! "$confirm" =~ ^[Yy]$ ]]; then
log "ABORTED by user."
exit 0
fi
# Step 1: Resolve driver conflict, install 580xx suite
log "[1/5] Resolving NVIDIA driver conflict and installing 580xx suite..."
# Check if newer nvidia-utils conflicts with 580xx-dkms
if pacman -Q nvidia-utils &>/dev/null && ! pacman -Q nvidia-580xx-utils &>/dev/null; then
log "Conflict: nvidia-utils (non-580xx) installed alongside nvidia-580xx-dkms."
log "Removing conflicting nvidia-utils, installing nvidia-580xx-utils..."
sudo pacman -Rns --noconfirm nvidia-utils 2>&1 | tee -a "$LOCAL_LOG"
sudo pacman -S --needed --noconfirm nvidia-580xx-dkms nvidia-580xx-utils 2>&1 | tee -a "$LOCAL_LOG"
else
sudo pacman -S --needed --noconfirm nvidia-580xx-dkms nvidia-580xx-utils 2>&1 | tee -a "$LOCAL_LOG"
fi
# Step 2: Ensure kernel headers are available for DKMS
log "[1b/4] Checking kernel headers for DKMS..."
KERNEL_HEADERS="${KERNEL_PKG}-headers"
if pacman -Q "$KERNEL_HEADERS" &>/dev/null; then
log "${GREEN}Kernel headers ($KERNEL_HEADERS) already installed.$RESET"
else
log "Installing $KERNEL_HEADERS for DKMS..."
sudo pacman -S --needed --noconfirm "$KERNEL_HEADERS" 2>&1 | tee -a "$LOCAL_LOG"
fi
# Step 3: Rebuild DKMS module for current kernel
log "[2/5] Rebuilding DKMS module for kernel $RUNNING_KERNEL..."
sudo dkms autoinstall 2>&1 | tee -a "$LOCAL_LOG"
# Step 3: Verify module was created
log "[3/5] Verifying module..."
if [[ -f "$MODULE_PATH" ]] || [[ -f "$MODULE_PATH2" ]] || [[ -f "$MODULE_PATH3" ]] || [[ -f "$MODULE_PATH4" ]] || [[ -f "$MODULE_PATH5" ]]; then
log "${GREEN}Module verified!$RESET"
# Show module details
modinfo_output=$(modinfo nvidia 2>/dev/null || echo "modinfo failed")
log " $modinfo_output"
else
log "${RED}WARNING: Module file not found after DKMS build.$RESET"
# Detect version for manual build
DKMS_VERSION=$(pacman -Qi nvidia-580xx-dkms 2>/dev/null | grep Version | awk '{print $2}' | cut -d- -f1)
[[ -z "$DKMS_VERSION" ]] && DKMS_VERSION="580.159.04"
log "Attempting manual build (version: $DKMS_VERSION)..."
sudo dkms build -m nvidia -v "$DKMS_VERSION" -k "$RUNNING_KERNEL" 2>&1 | tee -a "$LOCAL_LOG"
sudo dkms install -m nvidia -v "$DKMS_VERSION" -k "$RUNNING_KERNEL" 2>&1 | tee -a "$LOCAL_LOG"
fi
# Step 4: Rebuild initramfs
log "[4/5] Rebuilding initramfs..."
sudo mkinitcpio -P 2>&1 | tee -a "$LOCAL_LOG"
# ============================================================
# 4. VERIFICATION
# ============================================================
section "Post-Recovery Verification"
log "Checking module loading..."
if sudo modprobe nvidia 2>&1; then
log "${GREEN}nvidia module loaded successfully$RESET"
else
log "${YELLOW}modprobe nvidia failed - module will be loaded at next boot$RESET"
fi
# Detect 580xx version for manual DKMS fallback
DKMS_VERSION=$(pacman -Qi nvidia-580xx-dkms 2>/dev/null | grep Version | awk '{print $2}' | cut -d- -f1 || echo "580.159.04")
# Manual DKMS fallback uses DKMS_VERSION variable
log ""
log "${BOLD}Recovery complete!${RESET}"
log ""
log "Before rebooting, verify:"
log " 1. Module exists: ls /usr/lib/modules/$(uname -r)/extra/nvidia*"
log " 2. nvidia-smi works: sudo nvidia-smi"
log ""
log "Then reboot:"
log " sudo reboot"
log ""
log "Log saved to: $LOCAL_LOG"
log "============================================="
Reference in New Issue View Git Blame Copy Permalink