[pve-devel] [PATCH qemu-server v2 2/2] fix #3258: block vm start when pci device is already in use

[Dominik Csapak <d.csapak@proxmox.com>]

on vm start, we reserve all pciids that we use, and
remove the reservation again in vm_stop_cleanup

first with only a time-based reservation but after the vm is started,
we reserve again but with the pid.

for this, we have to move the start_timeout calculation above the
hostpci handling.

this way, when a vm starts with a pci device that is already configured
for a different running vm, will not be started and the user gets
the error that the device is already in use

Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
---
 PVE/QemuServer.pm | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm
index e5175b3..f05d858 100644
--- a/PVE/QemuServer.pm
+++ b/PVE/QemuServer.pm
@@ -5381,11 +5381,23 @@ sub vm_start_nolock {
 	push @$cmd, '-S';
     }
 
+    my $start_timeout = $params->{timeout} // config_aware_timeout($conf, $resume);
+    my $pciids_to_reserve = [];
+
     # host pci devices
     for (my $i = 0; $i < $PVE::QemuServer::PCI::MAX_HOSTPCI_DEVICES; $i++)  {
       my $d = parse_hostpci($conf->{"hostpci$i"});
       next if !$d;
       my $pcidevices = $d->{pciid};
+
+      # reserve all pciids before actually doing anything with them
+      foreach my $pcidevice (@$pcidevices) {
+	  my $pciid = $pcidevice->{id};
+	  PVE::QemuServer::PCI::reserve_pci_usage($pciid, $vmid, $start_timeout);
+	  # we need to update the reservation later
+	  push @$pciids_to_reserve, $pciid;
+      }
+
       foreach my $pcidevice (@$pcidevices) {
 	    my $pciid = $pcidevice->{id};
 
@@ -5417,7 +5429,6 @@ sub vm_start_nolock {
 
     my $cpuunits = get_cpuunits($conf);
 
-    my $start_timeout = $params->{timeout} // config_aware_timeout($conf, $resume);
     my %run_params = (
 	timeout => $statefile ? undef : $start_timeout,
 	umask => 0077,
@@ -5497,9 +5508,22 @@ sub vm_start_nolock {
     if (my $err = $@) {
 	# deactivate volumes if start fails
 	eval { PVE::Storage::deactivate_volumes($storecfg, $vollist); };
+	foreach my $id (@$pciids_to_reserve) {
+	    eval { PVE::QemuServer::PCI::remove_pci_reservation($id) };
+	    warn $@ if $@;
+	}
+
 	die "start failed: $err";
     }
 
+    # reserve all pciids again with the pid
+    # the vm is already started, we can only warn on error here
+    my $pid = PVE::QemuServer::Helpers::vm_running_locally($vmid);
+    foreach my $id (@$pciids_to_reserve) {
+	eval { PVE::QemuServer::PCI::reserve_pci_usage($id, $vmid, undef, $pid) };
+	warn $@ if $@;
+    }
+
     print "migration listens on $migrate_uri\n" if $migrate_uri;
     $res->{migrate_uri} = $migrate_uri;
 
@@ -5697,6 +5721,7 @@ sub vm_stop_cleanup {
 	    foreach my $pci (@{$d->{pciid}}) {
 		my $pciid = $pci->{id};
 		PVE::SysFSTools::pci_cleanup_mdev_device($pciid, $uuid);
+		PVE::QemuServer::PCI::remove_pci_reservation($pciid);
 	    }
 	}
 
-- 
2.30.2