Add NVIDIA self-heal tools and per-GPU SAT status

audit/internal/app/support_bundle.go

@@ -40,7 +40,36 @@ var supportBundleCommands = []struct {
 	{name: "system/mount.txt", cmd: []string{"mount"}},
 	{name: "system/df-h.txt", cmd: []string{"df", "-h"}},
 	{name: "system/dmesg.txt", cmd: []string{"dmesg"}},
+	{name: "system/kernel-aer-nvidia.txt", cmd: []string{"sh", "-c", `
+if command -v dmesg >/dev/null 2>&1; then
+  dmesg | grep -iE 'AER|NVRM|Xid|pcieport|nvidia' || echo "no AER/NVRM/Xid kernel messages found"
+else
+  echo "dmesg not found"
+fi
+`}},
 	{name: "system/nvidia-smi-q.txt", cmd: []string{"nvidia-smi", "-q"}},
+	{name: "system/lspci-nvidia-bridges-vv.txt", cmd: []string{"sh", "-c", `
+if ! command -v lspci >/dev/null 2>&1; then
+  echo "lspci not found"
+  exit 0
+fi
+found=0
+for gpu in $(lspci -Dn | awk '$3 ~ /^10de:/ {print $1}'); do
+  found=1
+  echo "=== GPU $gpu ==="
+  lspci -s "$gpu" -vv 2>&1 || true
+  bridge=$(basename "$(readlink -f "/sys/bus/pci/devices/$gpu/.." 2>/dev/null)" 2>/dev/null)
+  if [ -n "$bridge" ] && [ "$bridge" != "$gpu" ]; then
+    echo
+    echo "=== UPSTREAM $bridge for $gpu ==="
+    lspci -s "$bridge" -vv 2>&1 || true
+  fi
+  echo
+done
+if [ "$found" -eq 0 ]; then
+  echo "no NVIDIA PCI devices found"
+fi
+`}},
 	{name: "system/pcie-nvidia-link.txt", cmd: []string{"sh", "-c", `
 for d in /sys/bus/pci/devices/*/; do
   vendor=$(cat "$d/vendor" 2>/dev/null)
@@ -51,6 +80,30 @@ for d in /sys/bus/pci/devices/*/; do
     printf "  %-22s %s\n" "$f" "$(cat "$d/$f" 2>/dev/null)"
   done
 done
+`}},
+	{name: "system/pcie-aer-sysfs.txt", cmd: []string{"sh", "-c", `
+found=0
+for dev in /sys/bus/pci/devices/*; do
+  [ -e "$dev" ] || continue
+  bdf=$(basename "$dev")
+  block=""
+  for f in aer_dev_correctable aer_dev_fatal aer_dev_nonfatal aer_rootport_total_err_cor aer_rootport_total_err_fatal aer_rootport_total_err_nonfatal; do
+    if [ -r "$dev/$f" ]; then
+      if [ -z "$block" ]; then
+        block=1
+        found=1
+        echo "=== $bdf ==="
+      fi
+      printf "  %-30s %s\n" "$f" "$(cat "$dev/$f" 2>/dev/null)"
+    fi
+  done
+  if [ -n "$block" ]; then
+    echo
+  fi
+done
+if [ "$found" -eq 0 ]; then
+  echo "no PCIe AER sysfs counters found"
+fi
 `}},
 	{name: "system/ethtool-info.txt", cmd: []string{"sh", "-c", `
 if ! command -v ethtool >/dev/null 2>&1; then