chore: release 1.3.3

packaging/vfio-native/.SRCINFO

@@ -1,6 +1,6 @@
 pkgbase = vfio-native
 	pkgdesc = Present a libvirt guest as a self-consistent physical machine, and tune it
-	pkgver = 1.1.1
+	pkgver = 1.3.3
 	pkgrel = 1
 	url = https://git.archworks.co/sandwich/vfio-native
 	install = vfio-native.install
@@ -17,7 +17,7 @@ pkgbase = vfio-native
 	optdepends = cpupower: set the host CPU governor
 	optdepends = vfio-native-kvm-dkms: patched KVM modules for the full level
 	optdepends = vfio-native-qemu: patched QEMU for the full level
-	source = git+https://git.archworks.co/sandwich/vfio-native.git#tag=v1.1.1
+	source = git+https://git.archworks.co/sandwich/vfio-native.git#tag=v1.3.3
 	sha256sums = SKIP
 
 pkgname = vfio-native

packaging/vfio-native/PKGBUILD

@@ -8,7 +8,7 @@
 #   vfio-native-qemu       QEMU 11.1.1 with the platform-identity patches, in /opt
 
 pkgname=vfio-native
-pkgver=1.3.0
+pkgver=1.3.3
 pkgrel=1
 pkgdesc="Present a libvirt guest as a self-consistent physical machine, and tune it"
 arch=('any')

scripts/cpuid-passthrough-watch

@@ -1,12 +1,18 @@
 #!/bin/bash
-# Waits for a just-started guest's network to actually come up, then turns
+# Keeps the kvm_amd cpuid_passthrough switch correct across a guest's whole life,
-# kvm_amd cpuid_passthrough on.
+# in-guest reboots included.
 #
-# The readiness signal is the guest's own tap RX counter: it is fresh every boot,
+# The switch must be OFF (N) while the guest enumerates CPUID at boot or Windows
-# it needs nothing enabled inside the guest (no SSH, no RDP, no agent), and it only
+# hangs, and ON (Y) once it is up, where it clears the timer detection. The libvirt
-# moves once the guest's NIC driver has really loaded - which is well past the CPU
+# hook only fires at VM start and stop, so a guest-initiated reboot would otherwise
-# enumeration that the switch must not change under. A DHCP lease left over from a
+# re-enumerate with the switch still Y and hang. This watcher drops it to N on every
-# previous boot cannot trip it early.
+# 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).
@@ -17,25 +23,49 @@ PARAM=/sys/module/kvm_amd/parameters
 V="virsh -c qemu:///system"
 
 running() { [ "$($V domstate "$DOMAIN" 2>/dev/null)" = running ]; }
+rx() { cat "$RX" 2>/dev/null || echo 0; }
 
-tap=""
+set_N() { echo N > "$PARAM/cpuid_passthrough"; }
-i=0
+set_Y() { printf '%s' "$BRAND" > "$PARAM/brand_string"; echo Y > "$PARAM/cpuid_passthrough"; }
-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
 
-running || exit 0                         # guest went away before it came up
+# Wait until the tap rx counter grows at least 4 past $1 (guest NIC driver up again).
-printf '%s' "$BRAND" > "$PARAM/brand_string"
+# The iteration floor keeps a stray pre-OS packet (a UEFI netboot attempt) from
-echo Y > "$PARAM/cpuid_passthrough"
+# 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
+}
+
+# The hook arms this watcher at prepare, before QEMU starts, so the domain is not
+# yet running and its tap does not exist. Wait for the domain, then read the tap;
+# otherwise the first running check in wait_net_up bails and the flip never happens.
+for _ in $(seq 1 120); do running && break; sleep 1; done
+running || exit 0
+tap=$($V domiflist "$DOMAIN" 2>/dev/null | awk '$1 ~ /^(vnet|tap|macvtap)/ {print $1; exit}')
+RX="/sys/class/net/$tap/statistics/rx_packets"
+
+# 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

scripts/gpu-passthrough.sh

@@ -57,6 +57,24 @@ group_members() {
     done
 }
 
+# The functions to hand to the guest with GPU $1: every device in its IOMMU group
+# (mandatory for vfio), plus any sibling function of the same PCI device that is
+# itself a display or HDMI/DP audio controller. An APU parks its PSP and USB
+# controllers on the same PCI device in separate IOMMU groups - those are the
+# host's, so siblings are filtered by class and never pulled in blindly.
+passthrough_devs() {
+    local d="$1" m cls
+    {
+        group_members "$d"
+        for m in "/sys/bus/pci/devices/${d%.*}".*; do
+            [ -e "$m" ] || continue
+            m=$(basename "$m")
+            cls=$(cat "/sys/bus/pci/devices/$m/class" 2>/dev/null)
+            case "$cls" in 0x03*|0x0403*) echo "$m";; esac
+        done
+    } | sort -u
+}
+
 driver_of() {
     local l
     l=$(readlink -f "/sys/bus/pci/devices/$1/driver" 2>/dev/null)
@@ -79,7 +97,7 @@ drives_display() {
 
 ids_of() {   # vendor:device for vfio-pci binding
     local d
-    for d in $(group_members "$1"); do
+    for d in $(passthrough_devs "$1"); do
         local cls; cls=$(cat "/sys/bus/pci/devices/$d/class" 2>/dev/null)
         # only real functions of the card: skip bridges (class 0x0604xx)
         case "$cls" in 0x0604*) continue;; esac
@@ -219,7 +237,7 @@ prepare)
 
     # 1. stop whatever is holding the DRM device
     dm=$(systemctl list-units --type=service --state=running --no-legend 2>/dev/null |
-         awk '{print $1}' | grep -xE '(gdm|sddm|lightdm|lxdm|greetd|display-manager)\.service' | head -1)
+         awk '{print $1}' | grep -xE '((gdm|sddm|lightdm|lxdm|greetd|ly|emptty|lemurs)(@[a-z0-9-]+)?|display-manager)\.service' | head -1)
     if [ -n "$dm" ]; then
         echo "$dm" > "$STATE/dm"
         log "stopping $dm"
@@ -303,7 +321,7 @@ apply() {
     "$v" -c qemu:///system dumpxml --inactive "$dom" > "$backup/$dom.gpu-current.xml"
     grep -q 'ua-vfionative-gpu' "$backup/$dom.gpu-current.xml" || cp "$backup/$dom.gpu-current.xml" "$backup/$dom.before-gpu.xml"
     local devs="" m
-    for m in $( { group_members "$d"; ls -d "/sys/bus/pci/devices/${d%.*}".* | xargs -n1 basename; } | sort -u); do
+    for m in $(passthrough_devs "$d"); do
         case "$(cat "/sys/bus/pci/devices/$m/class" 2>/dev/null)" in 0x0604*) continue;; esac
         IFS=':.' read -r dm bs sl fn <<< "$m"
         devs+="    <hostdev mode='subsystem' type='pci' managed='yes'>\n      <source>\n"
@@ -330,7 +348,7 @@ xml() {
     echo "Add this to the domain, inside <devices>. Every device in the GPU's"
     echo "IOMMU group has to go together:"
     echo
-    for m in $(group_members "$d"); do
+    for m in $(passthrough_devs "$d"); do
         local cls; cls=$(cat "/sys/bus/pci/devices/$m/class" 2>/dev/null)
         case "$cls" in 0x0604*) continue;; esac
         IFS=':. ' read -r dom bus slot fn <<< "$(echo "$m" | tr ':.' '  ')"