vIOMMU enables the option to passthrough pci devices to L2 VMs in L1 VMs via Nested Virtualisation.
QEMU-Parameters: https://www.qemu.org/docs/master/system/qemu-manpage.html https://wiki.qemu.org/Features/VT-d -machine ...,kernel-irqchip=split: "split" because of intremap see below. -device intel-iommu: * caching-mode=on: "It is required for -device vfio-pci to work with the VT-d device, because host assigned devices requires to setup the DMA mapping on the host before guest DMA starts." * intremap=on: "This enables interrupt remapping feature. It's required to enable complete x2apic. Currently it only supports kvm kernel-irqchip modes off or split, while full kernel-irqchip is not yet supported." Signed-off-by: Markus Frank <[email protected]> --- PVE/API2/Qemu.pm | 11 +++++-- PVE/QemuConfig.pm | 3 +- PVE/QemuServer.pm | 62 +++++++++++++++++++++++++++++++++++++-- PVE/QemuServer/Machine.pm | 6 ++-- 4 files changed, 74 insertions(+), 8 deletions(-) diff --git a/PVE/API2/Qemu.pm b/PVE/API2/Qemu.pm index 9606e72..a968f40 100644 --- a/PVE/API2/Qemu.pm +++ b/PVE/API2/Qemu.pm @@ -1043,13 +1043,16 @@ __PACKAGE__->register_method({ $conf->{vmgenid} = PVE::QemuServer::generate_uuid(); } - my $machine = $conf->{machine}; + my $machine_conf = PVE::QemuServer::parse_machine($conf->{machine}); + my $machine = $machine_conf->{type}; if (!$machine || $machine =~ m/^(?:pc|q35|virt)$/) { # always pin Windows' machine version on create, they get to easily confused if (PVE::QemuServer::Helpers::windows_version($conf->{ostype})) { - $conf->{machine} = PVE::QemuServer::windows_get_pinned_machine_version($machine); + $machine_conf->{type} = PVE::QemuServer::windows_get_pinned_machine_version($machine); + $conf->{machine} = PVE::QemuServer::print_machine($machine_conf); } } + PVE::QemuServer::check_machine_config($conf, $machine_conf); PVE::QemuConfig->write_config($vmid, $conf); @@ -1880,6 +1883,10 @@ my $update_vm_api = sub { ); } $conf->{pending}->{$opt} = $param->{$opt}; + } elsif ($opt eq 'machine') { + my $machine_conf = PVE::QemuServer::parse_machine($param->{$opt}); + PVE::QemuServer::check_machine_config($conf, $machine_conf); + $conf->{pending}->{$opt} = $param->{$opt}; } else { $conf->{pending}->{$opt} = $param->{$opt}; diff --git a/PVE/QemuConfig.pm b/PVE/QemuConfig.pm index 10e6929..c4834a7 100644 --- a/PVE/QemuConfig.pm +++ b/PVE/QemuConfig.pm @@ -433,7 +433,8 @@ sub __snapshot_rollback_hook { } else { # Note: old code did not store 'machine', so we try to be smart # and guess the snapshot was generated with kvm 1.4 (pc-i440fx-1.4). - $data->{forcemachine} = $conf->{machine} || 'pc-i440fx-1.4'; + my $machine_conf = PVE::QemuServer::parse_machine($conf->{machine}); + $data->{forcemachine} = $machine_conf->{type} || 'pc-i440fx-1.4'; # we remove the 'machine' configuration if not explicitly specified # in the original config. diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm index bf1de17..013792d 100644 --- a/PVE/QemuServer.pm +++ b/PVE/QemuServer.pm @@ -118,12 +118,32 @@ PVE::JSONSchema::register_standard_option('pve-qm-stateuri', { optional => 1, }); -PVE::JSONSchema::register_standard_option('pve-qemu-machine', { +my $machine_fmt = { + type => { + default_key => 1, description => "Specifies the QEMU machine type.", type => 'string', pattern => '(pc|pc(-i440fx)?-\d+(\.\d+)+(\+pve\d+)?(\.pxe)?|q35|pc-q35-\d+(\.\d+)+(\+pve\d+)?(\.pxe)?|virt(?:-\d+(\.\d+)+)?(\+pve\d+)?)', maxLength => 40, + format_description => 'machine type', optional => 1, + }, + viommu => { + type => 'boolean', + description => "Enable/disable guest vIOMMU" + ." (needs kvm to be enabled and q35 to be set as machine type).", + default => 0, + optional => 1, + }, +}; + +PVE::JSONSchema::register_format('pve-qemu-machine-fmt', $machine_fmt); + +PVE::JSONSchema::register_standard_option('pve-qemu-machine', { + description => "Specify the QEMU machine type & enable/disable vIOMMU.", + type => 'string', + optional => 1, + format => PVE::JSONSchema::get_format('pve-qemu-machine-fmt'), }); # FIXME: remove in favor of just using the INotify one, it's cached there exactly the same way @@ -2133,6 +2153,31 @@ sub parse_watchdog { return $res; } +sub parse_machine { + my ($value) = @_; + + return if !$value; + + my $res = parse_property_string($machine_fmt, $value); + return $res; +} + +sub check_machine_config { + my ($conf, $machine_conf) = @_; + my $q35 = $machine_conf->{type} && ($machine_conf->{type} =~ m/q35/) ? 1 : 0; + my $kvm = $conf->{kvm}; + my $arch = get_vm_arch($conf); + $kvm //= 1 if is_native($arch); + if ($machine_conf->{viommu} && (!$kvm || !$q35)) { + die "to use vIOMMU please enable kvm and set the machine type to q35\n"; + } +} + +sub print_machine { + my ($machine_conf) = @_; + return PVE::JSONSchema::print_property_string($machine_conf, $machine_fmt); +} + sub parse_guest_agent { my ($conf) = @_; @@ -2204,8 +2249,9 @@ sub qemu_created_version_fixups { # check if we need to apply some handling for VMs that always use the latest machine version but # had a machine version transition happen that affected HW such that, e.g., an OS config change # would be required (we do not want to pin machine version for non-windows OS type) + my $machine_conf = parse_machine($conf->{machine}); if ( - (!defined($conf->{machine}) || $conf->{machine} =~ m/^(?:pc|q35|virt)$/) # non-versioned machine + (!defined($machine_conf->{type}) || $machine_conf->{type} =~ m/^(?:pc|q35|virt)$/) # non-versioned machine && (!defined($meta->{'creation-qemu'}) || !min_version($meta->{'creation-qemu'}, 6, 1)) # created before 6.1 && (!$forced_vers || min_version($forced_vers, 6, 1)) # handle snapshot-rollback/migrations && min_version($kvmver, 6, 1) # only need to apply the change since 6.1 @@ -3364,7 +3410,8 @@ sub windows_get_pinned_machine_version { sub get_vm_machine { my ($conf, $forcemachine, $arch, $add_pve_version, $kvmversion) = @_; - my $machine = $forcemachine || $conf->{machine}; + my $machine_conf = parse_machine($conf->{machine}); + my $machine = $forcemachine || $machine_conf->{type}; if (!$machine || $machine =~ m/^(?:pc|q35|virt)$/) { $kvmversion //= kvm_user_version(); @@ -3609,6 +3656,8 @@ sub config_to_command { my $kvm = $conf->{kvm}; my $nodename = nodename(); + my $machine_conf = parse_machine($conf->{machine}); + my $arch = get_vm_arch($conf); my $kvm_binary = get_command_for_arch($arch); my $kvmver = kvm_user_version($kvm_binary); @@ -4174,6 +4223,13 @@ sub config_to_command { } push @$machineFlags, "type=${machine_type_min}"; + check_machine_config($conf, $machine_conf); + + if ($machine_conf->{viommu}) { + unshift @$devices, '-device', "intel-iommu,intremap=on,caching-mode=on"; + push @$machineFlags, 'kernel-irqchip=split'; + } + push @$cmd, @$devices; push @$cmd, '-rtc', join(',', @$rtcFlags) if scalar(@$rtcFlags); push @$cmd, '-machine', join(',', @$machineFlags) if scalar(@$machineFlags); diff --git a/PVE/QemuServer/Machine.pm b/PVE/QemuServer/Machine.pm index d9429ed..bfbde59 100644 --- a/PVE/QemuServer/Machine.pm +++ b/PVE/QemuServer/Machine.pm @@ -15,7 +15,8 @@ our $PVE_MACHINE_VERSION = { sub machine_type_is_q35 { my ($conf) = @_; - return $conf->{machine} && ($conf->{machine} =~ m/q35/) ? 1 : 0; + my $machine_conf = PVE::QemuServer::parse_machine($conf->{machine}); + return $machine_conf->{type} && ($machine_conf->{type} =~ m/q35/) ? 1 : 0; } sub current_from_query_machines { @@ -120,7 +121,8 @@ sub qemu_machine_pxe { my $machine = get_current_qemu_machine($vmid); - if ($conf->{machine} && $conf->{machine} =~ m/\.pxe$/) { + my $machine_conf = PVE::QemuServer::parse_machine($conf->{machine}); + if ($machine_conf->{type} && $machine_conf->{type} =~ m/\.pxe$/) { $machine .= '.pxe'; } -- 2.39.2 _______________________________________________ pve-devel mailing list [email protected] https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
