From a956ececfd90049e6b6329d3d98d14c2458e1cab Mon Sep 17 00:00:00 2001
From: Sandwich <sandwich@archworks.co>
Date: Sun, 6 Sep 2026 10:07:57 +0200
Subject: [PATCH] fix: keep cpuid passthrough correct across in-guest reboots

---
 scripts/cpuid-passthrough-watch | 77 ++++++++++++++++++++++-----------
 1 file changed, 51 insertions(+), 26 deletions(-)

diff --git a/scripts/cpuid-passthrough-watch b/scripts/cpuid-passthrough-watch
index 7d9301a..ea60fa5 100755
--- a/scripts/cpuid-passthrough-watch
+++ b/scripts/cpuid-passthrough-watch
@@ -1,12 +1,18 @@
 #!/bin/bash
-# Waits for a just-started guest's network to actually come up, then turns
-# kvm_amd cpuid_passthrough on.
+# Keeps the kvm_amd cpuid_passthrough switch correct across a guest's whole life,
+# in-guest reboots included.
 #
-# The readiness signal is the guest's own tap RX counter: it is fresh every boot,
-# it needs nothing enabled inside the guest (no SSH, no RDP, no agent), and it only
-# moves once the guest's NIC driver has really loaded - which is well past the CPU
-# enumeration that the switch must not change under. A DHCP lease left over from a
-# previous boot cannot trip it early.
+# The switch must be OFF (N) while the guest enumerates CPUID at boot or Windows
+# hangs, and ON (Y) once it is up, where it clears the timer detection. The libvirt
+# hook only fires at VM start and stop, so a guest-initiated reboot would otherwise
+# re-enumerate with the switch still Y and hang. This watcher drops it to N on every
+# QEMU RESET and raises it again once the guest's NIC is back up.
+#
+# Readiness signal: the guest tap's rx_packets counter growing past a baseline. It
+# only moves once the guest NIC driver has loaded, well past CPU enumeration, and it
+# needs nothing enabled inside the guest. The counter is cumulative and does NOT
+# reset on an in-guest reboot, so readiness is growth past the value captured at the
+# reset, not an absolute threshold.
 #
 # Launched as a transient systemd unit by the cpuid-passthrough hook, so it is free
 # to call virsh (the hook itself must not - that deadlocks libvirtd).
@@ -18,24 +24,43 @@ V="virsh -c qemu:///system"
 
 running() { [ "$($V domstate "$DOMAIN" 2>/dev/null)" = running ]; }
 
-tap=""
-i=0
-for _ in $(seq 1 65); do                  # ~195 s cap, then flip anyway if still up
-    i=$((i + 1))
-    running || { sleep 3; continue; }     # not "running" yet at prepare time - wait
-    [ -z "$tap" ] && tap=$($V domiflist "$DOMAIN" 2>/dev/null |
-                           awk '$1 ~ /^(vnet|tap|macvtap)/ {print $1; exit}')
-    rx="/sys/class/net/$tap/statistics/rx_packets"
-    # the iteration floor keeps a stray pre-OS packet (a UEFI netboot attempt) from
-    # tripping the flip before the guest is even past its interrupt and timer setup
-    if [ "$i" -ge 4 ] && [ -n "$tap" ] && [ -r "$rx" ] &&
-       [ "$(cat "$rx" 2>/dev/null || echo 0)" -ge 4 ]; then
-        break
-    fi
-    sleep 3
-done
+tap=$($V domiflist "$DOMAIN" 2>/dev/null | awk '$1 ~ /^(vnet|tap|macvtap)/ {print $1; exit}')
+RX="/sys/class/net/$tap/statistics/rx_packets"
+rx() { cat "$RX" 2>/dev/null || echo 0; }
 
-running || exit 0                         # guest went away before it came up
-printf '%s' "$BRAND" > "$PARAM/brand_string"
-echo Y > "$PARAM/cpuid_passthrough"
+set_N() { echo N > "$PARAM/cpuid_passthrough"; }
+set_Y() { printf '%s' "$BRAND" > "$PARAM/brand_string"; echo Y > "$PARAM/cpuid_passthrough"; }
+
+# Wait until the tap rx counter grows at least 4 past $1 (guest NIC driver up again).
+# The iteration floor keeps a stray pre-OS packet (a UEFI netboot attempt) from
+# tripping the flip before the guest is even past its interrupt and timer setup.
+wait_net_up() {
+    local base=$1 i=0
+    for _ in $(seq 1 100); do            # ~300 s cap, then raise anyway if still up
+        i=$((i + 1))
+        running || return 1
+        [ "$i" -ge 4 ] && [ -n "$tap" ] && [ -r "$RX" ] &&
+            [ "$(rx)" -ge "$((base + 4))" ] && return 0
+        sleep 3
+    done
+    return 0
+}
+
+# initial cold boot: wait for the network, then harden
+wait_net_up 0
+running || exit 0
+set_Y
 logger -t vfio-cpuid "$DOMAIN network up: cpuid_passthrough=Y"
+
+# every in-guest reboot fires a QEMU RESET: drop to N for the re-enumeration, then
+# raise it again once the guest's NIC is back. --loop streams one line per reset.
+$V qemu-monitor-event --domain "$DOMAIN" --event RESET --loop 2>/dev/null | while read -r _; do
+    running || continue
+    base=$(rx)
+    set_N
+    logger -t vfio-cpuid "$DOMAIN reset: cpuid_passthrough=N for re-enumeration"
+    wait_net_up "$base" || continue
+    running || continue
+    set_Y
+    logger -t vfio-cpuid "$DOMAIN back up: cpuid_passthrough=Y"
+done