qemu: Turn EIM IOMMU on automagically

If a Q35 domain has huge number of vCPUS (over 255, currently), then
it needs IOMMU with Extended Interrupt Mode enabled (see check in
qemuValidateDomainVCpuTopology()).

Well, we already add some devices and to other tricks when
parsing new domain XML. Might as well turn the EIM on for IOMMU
device.

Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>

src/qemu/qemu_domain.c

@@ -6453,6 +6453,37 @@ qemuDomainPstoreDefPostParse(virDomainPstoreDef *pstore,
 }
 
 
+static int
+qemuDomainIOMMUDefPostParse(virDomainIOMMUDef *iommu,
+                            const virDomainDef *def,
+                            virQEMUCaps *qemuCaps,
+                            unsigned int parseFlags)
+{
+    /* In case domain has huge number of vCPUS and Extended Interrupt Mode
+     * (EIM) is not explicitly turned off, let's enable it. If we didn't then
+     * guest will have troubles with interrupts. */
+    if (parseFlags & VIR_DOMAIN_DEF_PARSE_ABI_UPDATE &&
+        ARCH_IS_X86(def->os.arch) &&
+        virDomainDefGetVcpusMax(def) > QEMU_MAX_VCPUS_WITHOUT_EIM &&
+        qemuDomainIsQ35(def) &&
+        iommu && iommu->model == VIR_DOMAIN_IOMMU_MODEL_INTEL) {
+
+        /* eim requires intremap. */
+        if (iommu->intremap == VIR_TRISTATE_SWITCH_ABSENT &&
+            virQEMUCapsGet(qemuCaps, QEMU_CAPS_INTEL_IOMMU_INTREMAP)) {
+            iommu->intremap = VIR_TRISTATE_SWITCH_ON;
+        }
+
+        if (iommu->eim == VIR_TRISTATE_SWITCH_ABSENT &&
+            virQEMUCapsGet(qemuCaps, QEMU_CAPS_INTEL_IOMMU_EIM)) {
+            iommu->eim = VIR_TRISTATE_SWITCH_ON;
+        }
+    }
+
+    return 0;
+}
+
+
 static int
 qemuDomainDeviceDefPostParse(virDomainDeviceDef *dev,
                              const virDomainDef *def,
@@ -6518,6 +6549,11 @@ qemuDomainDeviceDefPostParse(virDomainDeviceDef *dev,
         ret = qemuDomainPstoreDefPostParse(dev->data.pstore, def, driver);
         break;
 
+    case VIR_DOMAIN_DEVICE_IOMMU:
+        ret = qemuDomainIOMMUDefPostParse(dev->data.iommu, def,
+                                          qemuCaps, parseFlags);
+        break;
+
     case VIR_DOMAIN_DEVICE_LEASE:
     case VIR_DOMAIN_DEVICE_FS:
     case VIR_DOMAIN_DEVICE_INPUT:
@@ -6530,7 +6566,6 @@ qemuDomainDeviceDefPostParse(virDomainDeviceDef *dev,
     case VIR_DOMAIN_DEVICE_MEMBALLOON:
     case VIR_DOMAIN_DEVICE_NVRAM:
     case VIR_DOMAIN_DEVICE_RNG:
-    case VIR_DOMAIN_DEVICE_IOMMU:
     case VIR_DOMAIN_DEVICE_AUDIO:
     case VIR_DOMAIN_DEVICE_CRYPTO:
         ret = 0;

src/qemu/qemu_validate.c

@@ -31,7 +31,6 @@
 #include "virutil.h"
 
 #define VIR_FROM_THIS VIR_FROM_QEMU
-#define QEMU_MAX_VCPUS_WITHOUT_EIM 255
 
 VIR_LOG_INIT("qemu.qemu_validate");
 

src/qemu/qemu_validate.h

@@ -22,6 +22,8 @@
 
 #include "qemu_capabilities.h"
 
+#define QEMU_MAX_VCPUS_WITHOUT_EIM 255
+
 int
 qemuValidateDomainDef(const virDomainDef *def,
                       void *opaque,

tests/qemuxmlconfdata/intel-iommu-eim-autoadd.x86_64-latest.abi-update.args

@@ -0,0 +1,34 @@
+LC_ALL=C \
+PATH=/bin \
+HOME=/var/lib/libvirt/qemu/domain--1-QEMUGuest1 \
+USER=test \
+LOGNAME=test \
+XDG_DATA_HOME=/var/lib/libvirt/qemu/domain--1-QEMUGuest1/.local/share \
+XDG_CACHE_HOME=/var/lib/libvirt/qemu/domain--1-QEMUGuest1/.cache \
+XDG_CONFIG_HOME=/var/lib/libvirt/qemu/domain--1-QEMUGuest1/.config \
+/usr/bin/qemu-system-x86_64 \
+-name guest=QEMUGuest1,debug-threads=on \
+-S \
+-object '{"qom-type":"secret","id":"masterKey0","format":"raw","file":"/var/lib/libvirt/qemu/domain--1-QEMUGuest1/master-key.aes"}' \
+-machine q35,usb=off,kernel_irqchip=split,dump-guest-core=off,memory-backend=pc.ram,acpi=off \
+-accel kvm \
+-cpu qemu64 \
+-m size=219136k \
+-object '{"qom-type":"memory-backend-ram","id":"pc.ram","size":224395264}' \
+-overcommit mem-lock=off \
+-smp 288,sockets=288,cores=1,threads=1 \
+-uuid c7a5fdbd-edaf-9455-926a-d65c16db1809 \
+-display none \
+-no-user-config \
+-nodefaults \
+-chardev socket,id=charmonitor,fd=1729,server=on,wait=off \
+-mon chardev=charmonitor,id=monitor,mode=control \
+-rtc base=utc \
+-no-shutdown \
+-boot strict=on \
+-device '{"driver":"intel-iommu","id":"iommu0","intremap":"on","eim":"on"}' \
+-audiodev '{"id":"audio1","driver":"none"}' \
+-global ICH9-LPC.noreboot=off \
+-watchdog-action reset \
+-sandbox on,obsolete=deny,elevateprivileges=deny,spawn=deny,resourcecontrol=deny \
+-msg timestamp=on

tests/qemuxmlconfdata/intel-iommu-eim-autoadd.x86_64-latest.abi-update.xml

@@ -0,0 +1,37 @@
+<domain type='kvm'>
+  <name>QEMUGuest1</name>
+  <uuid>c7a5fdbd-edaf-9455-926a-d65c16db1809</uuid>
+  <memory unit='KiB'>219100</memory>
+  <currentMemory unit='KiB'>219100</currentMemory>
+  <vcpu placement='static'>288</vcpu>
+  <os>
+    <type arch='x86_64' machine='q35'>hvm</type>
+    <boot dev='hd'/>
+  </os>
+  <features>
+    <ioapic driver='qemu'/>
+  </features>
+  <cpu mode='custom' match='exact' check='none'>
+    <model fallback='forbid'>qemu64</model>
+  </cpu>
+  <clock offset='utc'/>
+  <on_poweroff>destroy</on_poweroff>
+  <on_reboot>restart</on_reboot>
+  <on_crash>destroy</on_crash>
+  <devices>
+    <emulator>/usr/bin/qemu-system-x86_64</emulator>
+    <controller type='pci' index='0' model='pcie-root'/>
+    <controller type='usb' index='0' model='none'/>
+    <controller type='sata' index='0'>
+      <address type='pci' domain='0x0000' bus='0x00' slot='0x1f' function='0x2'/>
+    </controller>
+    <input type='mouse' bus='ps2'/>
+    <input type='keyboard' bus='ps2'/>
+    <audio id='1' type='none'/>
+    <watchdog model='itco' action='reset'/>
+    <memballoon model='none'/>
+    <iommu model='intel'>
+      <driver intremap='on' eim='on'/>
+    </iommu>
+  </devices>
+</domain>

tests/qemuxmlconfdata/intel-iommu-eim-autoadd.xml

@@ -0,0 +1,35 @@
+<domain type='kvm'>
+  <name>QEMUGuest1</name>
+  <uuid>c7a5fdbd-edaf-9455-926a-d65c16db1809</uuid>
+  <memory unit='KiB'>219100</memory>
+  <currentMemory unit='KiB'>219100</currentMemory>
+  <vcpu placement='static'>288</vcpu>
+  <os>
+    <type arch='x86_64' machine='q35'>hvm</type>
+    <boot dev='hd'/>
+  </os>
+  <features>
+    <ioapic driver='qemu'/>
+  </features>
+  <cpu mode='custom' match='exact' check='none'>
+    <model fallback='forbid'>qemu64</model>
+  </cpu>
+  <clock offset='utc'/>
+  <on_poweroff>destroy</on_poweroff>
+  <on_reboot>restart</on_reboot>
+  <on_crash>destroy</on_crash>
+  <devices>
+    <emulator>/usr/bin/qemu-system-x86_64</emulator>
+    <controller type='pci' index='0' model='pcie-root'/>
+    <controller type='usb' index='0' model='none'/>
+    <controller type='sata' index='0'>
+      <address type='pci' domain='0x0000' bus='0x00' slot='0x1f' function='0x2'/>
+    </controller>
+    <input type='mouse' bus='ps2'/>
+    <input type='keyboard' bus='ps2'/>
+    <audio id='1' type='none'/>
+    <watchdog model='itco' action='reset'/>
+    <memballoon model='none'/>
+    <iommu model='intel'/>
+  </devices>
+</domain>

tests/qemuxmlconftest.c

@@ -2764,6 +2764,7 @@ mymain(void)
     DO_TEST_CAPS_LATEST("intel-iommu-aw-bits");
     DO_TEST_CAPS_LATEST("intel-iommu-dma-translation");
     DO_TEST_CAPS_LATEST_PARSE_ERROR("intel-iommu-wrong-machine");
+    DO_TEST_CAPS_LATEST_ABI_UPDATE("intel-iommu-eim-autoadd");
     DO_TEST_CAPS_ARCH_LATEST("iommu-smmuv3", "aarch64");
     DO_TEST_CAPS_LATEST("virtio-iommu-x86_64");
     DO_TEST_CAPS_VER_PARSE_ERROR("virtio-iommu-x86_64", "6.1.0");