x86 and CPU queue, 2016-10-24

x2APIC support to APIC code, cpu_exec_init() refactor on all
 architectures, and other x86 changes.
 -----BEGIN PGP SIGNATURE-----
 
 iQIcBAABCAAGBQJYDmYyAAoJECgHk2+YTcWmoSUP/2ga+b9YmPuyL7XC+12pff0I
 Z8gdjUzbMUNcCI0JMZCTGUJbs3BapLcnsA7ypmt88s9kG02WeDMhNx1BfYiAFgLU
 kPLQlXAM7awEdGagd3sTCiFojSUZ7GxYHjd5fuhPoOAXvXM8im6zJl18ZcsnStjO
 /J8JGoGDHq1XJlz+RIjnGamojJWCiO/+iiD+rFmVSic8zjHPDYq14sIk/QJX+DaF
 azLiOI6DAlX3kyrN5ZshhIRQ3COzzUMUSDF/ZaYHjudUco5MBnwj/oLQniTq+ZUd
 hCu7dr5TpLxI7q1yltyd0UIl/+aZGbE8tEvoXAtc735iK4m2CTckT7ql6x3xI+Ir
 PmpPgIswHqfCiCXm8imLj6ZI47kRA1x4x4AudLaNVKP7jO82485sS9HWpOadYsaU
 jvek2SqfqvH+vce4FzwlLEcXGDb73MT/XkIUvd7SfPIbs9umgdZc03U4SHfAWr0i
 lAIRs4Ym0AAS2WSE4E09wvdUUr9oxaQBMhw3JAiNmg7hLfyINTP+D/IhtlAVXXEA
 F9D7fky5lDwfKvIwPxPJbDD5bCBV9AmxhiahIhv3epu4Kg4orf1inkrx0IZWSbB0
 7+JZ7j8asuizfibkeZAN9rxVwmz32makJNsnjzZHlnaPxTvIDzvRkNceBnhC5vKq
 3yfxgl4agXmMjveraAtt
 =T2kg
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/ehabkost/tags/x86-pull-request' into staging

x86 and CPU queue, 2016-10-24

x2APIC support to APIC code, cpu_exec_init() refactor on all
architectures, and other x86 changes.

# gpg: Signature made Mon 24 Oct 2016 20:51:14 BST
# gpg:                using RSA key 0x2807936F984DC5A6
# gpg: Good signature from "Eduardo Habkost <ehabkost@redhat.com>"
# Primary key fingerprint: 5A32 2FD5 ABC4 D3DB ACCF  D1AA 2807 936F 984D C5A6

* remotes/ehabkost/tags/x86-pull-request:
  exec: call cpu_exec_exit() from a CPU unrealize common function
  exec: move cpu_exec_init() calls to realize functions
  exec: split cpu_exec_init()
  pc: q35: Bump max_cpus to 288
  pc: Require IRQ remapping and EIM if there could be x2APIC CPUs
  pc: Add 'etc/boot-cpus' fw_cfg file for machine with more than 255 CPUs
  Increase MAX_CPUMASK_BITS from 255 to 288
  pc: Clarify FW_CFG_MAX_CPUS usage comment
  pc: kvm_apic: Pass APIC ID depending on xAPIC/x2APIC mode
  pc: apic_common: Reset APIC ID to initial ID when switching into x2APIC mode
  pc: apic_common: Restore APIC ID to initial ID on reset
  pc: apic_common: Extend APIC ID property to 32bit
  pc: Leave max apic_id_limit only in legacy cpu hotplug code
  acpi: cphp: Force switch to modern cpu hotplug if APIC ID > 254
  pc: acpi: x2APIC support for SRAT table
  pc: acpi: x2APIC support for MADT table and _MAT method

Conflicts:
	target-arm/cpu.c

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

exec.c

@@ -630,7 +630,7 @@ AddressSpace *cpu_get_address_space(CPUState *cpu, int asidx)
 }
 #endif
 
-void cpu_exec_exit(CPUState *cpu)
+void cpu_exec_unrealizefn(CPUState *cpu)
 {
     CPUClass *cc = CPU_GET_CLASS(cpu);
 
@@ -644,11 +644,8 @@ void cpu_exec_exit(CPUState *cpu)
     }
 }
 
-void cpu_exec_init(CPUState *cpu, Error **errp)
+void cpu_exec_initfn(CPUState *cpu)
 {
-    CPUClass *cc ATTRIBUTE_UNUSED = CPU_GET_CLASS(cpu);
-    Error *local_err ATTRIBUTE_UNUSED = NULL;
-
     cpu->as = NULL;
     cpu->num_ases = 0;
 
@@ -669,6 +666,11 @@ void cpu_exec_init(CPUState *cpu, Error **errp)
     cpu->memory = system_memory;
     object_ref(OBJECT(cpu->memory));
 #endif
+}
+
+void cpu_exec_realizefn(CPUState *cpu, Error **errp)
+{
+    CPUClass *cc ATTRIBUTE_UNUSED = CPU_GET_CLASS(cpu);
 
     cpu_list_add(cpu);
 

hw/acpi/cpu.c

@@ -531,6 +531,11 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
                 apic->flags = cpu_to_le32(1);
                 break;
             }
+            case ACPI_APIC_LOCAL_X2APIC: {
+                AcpiMadtProcessorX2Apic *apic = (void *)madt_buf->data;
+                apic->flags = cpu_to_le32(1);
+                break;
+            }
             default:
                 assert(0);
             }

hw/acpi/cpu_hotplug.c

@@ -15,6 +15,7 @@
 #include "qapi/error.h"
 #include "qom/cpu.h"
 #include "hw/i386/pc.h"
+#include "qemu/error-report.h"
 
 #define CPU_EJECT_METHOD "CPEJ"
 #define CPU_MAT_METHOD "CPMA"
@@ -63,7 +64,8 @@ static void acpi_set_cpu_present_bit(AcpiCpuHotplug *g, CPUState *cpu,
 
     cpu_id = k->get_arch_id(cpu);
     if ((cpu_id / 8) >= ACPI_GPE_PROC_LEN) {
-        error_setg(errp, "acpi: invalid cpu id: %" PRIi64, cpu_id);
+        object_property_set_bool(g->device, false, "cpu-hotplug-legacy",
+                                 &error_abort);
         return;
     }
 
@@ -85,13 +87,14 @@ void legacy_acpi_cpu_hotplug_init(MemoryRegion *parent, Object *owner,
 {
     CPUState *cpu;
 
-    CPU_FOREACH(cpu) {
-        acpi_set_cpu_present_bit(gpe_cpu, cpu, &error_abort);
-    }
     memory_region_init_io(&gpe_cpu->io, owner, &AcpiCpuHotplug_ops,
                           gpe_cpu, "acpi-cpu-hotplug", ACPI_GPE_PROC_LEN);
     memory_region_add_subregion(parent, base, &gpe_cpu->io);
     gpe_cpu->device = owner;
+
+    CPU_FOREACH(cpu) {
+        acpi_set_cpu_present_bit(gpe_cpu, cpu, &error_abort);
+    }
 }
 
 void acpi_switch_to_modern_cphp(AcpiCpuHotplug *gpe_cpu,
@@ -234,7 +237,11 @@ void build_legacy_cpu_hotplug_aml(Aml *ctx, MachineState *machine,
     /* The current AML generator can cover the APIC ID range [0..255],
      * inclusive, for VCPU hotplug. */
     QEMU_BUILD_BUG_ON(ACPI_CPU_HOTPLUG_ID_LIMIT > 256);
-    g_assert(pcms->apic_id_limit <= ACPI_CPU_HOTPLUG_ID_LIMIT);
+    if (pcms->apic_id_limit > ACPI_CPU_HOTPLUG_ID_LIMIT) {
+        error_report("max_cpus is too large. APIC ID of last CPU is %u",
+                     pcms->apic_id_limit - 1);
+        exit(1);
+    }
 
     /* create PCI0.PRES device and its _CRS to reserve CPU hotplug MMIO */
     dev = aml_device("PCI0." stringify(CPU_HOTPLUG_RESOURCE_DEVICE));

hw/arm/virt.c

@@ -1494,7 +1494,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
      * it later in machvirt_init, where we have more information about the
      * configuration of the particular instance.
      */
-    mc->max_cpus = MAX_CPUMASK_BITS;
+    mc->max_cpus = 255;
     mc->has_dynamic_sysbus = true;
     mc->block_default_type = IF_VIRTIO;
     mc->no_cdrom = 1;

hw/i386/acpi-build.c

@@ -340,10 +340,17 @@ build_fadt(GArray *table_data, BIOSLinker *linker, AcpiPmInfo *pm,
 void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid,
                        CPUArchIdList *apic_ids, GArray *entry)
 {
-    int apic_id;
+    uint32_t apic_id = apic_ids->cpus[uid].arch_id;
+
+    /* ACPI spec says that LAPIC entry for non present
+     * CPU may be omitted from MADT or it must be marked
+     * as disabled. However omitting non present CPU from
+     * MADT breaks hotplug on linux. So possible CPUs
+     * should be put in MADT but kept disabled.
+     */
+    if (apic_id < 255) {
         AcpiMadtProcessorApic *apic = acpi_data_push(entry, sizeof *apic);
 
-    apic_id = apic_ids->cpus[uid].arch_id;
         apic->type = ACPI_APIC_PROCESSOR;
         apic->length = sizeof(*apic);
         apic->processor_id = uid;
@@ -351,14 +358,21 @@ void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid,
         if (apic_ids->cpus[uid].cpu != NULL) {
             apic->flags = cpu_to_le32(1);
         } else {
-        /* ACPI spec says that LAPIC entry for non present
-         * CPU may be omitted from MADT or it must be marked
-         * as disabled. However omitting non present CPU from
-         * MADT breaks hotplug on linux. So possible CPUs
-         * should be put in MADT but kept disabled.
-         */
             apic->flags = cpu_to_le32(0);
         }
+    } else {
+        AcpiMadtProcessorX2Apic *apic = acpi_data_push(entry, sizeof *apic);
+
+        apic->type = ACPI_APIC_LOCAL_X2APIC;
+        apic->length = sizeof(*apic);
+        apic->uid = cpu_to_le32(uid);
+        apic->x2apic_id = cpu_to_le32(apic_id);
+        if (apic_ids->cpus[uid].cpu != NULL) {
+            apic->flags = cpu_to_le32(1);
+        } else {
+            apic->flags = cpu_to_le32(0);
+        }
+    }
 }
 
 static void
@@ -369,11 +383,11 @@ build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms)
     int madt_start = table_data->len;
     AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(pcms->acpi_dev);
     AcpiDeviceIf *adev = ACPI_DEVICE_IF(pcms->acpi_dev);
+    bool x2apic_mode = false;
 
     AcpiMultipleApicTable *madt;
     AcpiMadtIoApic *io_apic;
     AcpiMadtIntsrcovr *intsrcovr;
-    AcpiMadtLocalNmi *local_nmi;
     int i;
 
     madt = acpi_data_push(table_data, sizeof *madt);
@@ -382,6 +396,9 @@ build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms)
 
     for (i = 0; i < apic_ids->len; i++) {
         adevc->madt_cpu(adev, i, apic_ids, table_data);
+        if (apic_ids->cpus[i].arch_id > 254) {
+            x2apic_mode = true;
+        }
     }
     g_free(apic_ids);
 
@@ -414,12 +431,25 @@ build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms)
         intsrcovr->flags  = cpu_to_le16(0xd); /* active high, level triggered */
     }
 
+    if (x2apic_mode) {
+        AcpiMadtLocalX2ApicNmi *local_nmi;
+
+        local_nmi = acpi_data_push(table_data, sizeof *local_nmi);
+        local_nmi->type   = ACPI_APIC_LOCAL_X2APIC_NMI;
+        local_nmi->length = sizeof(*local_nmi);
+        local_nmi->uid    = 0xFFFFFFFF; /* all processors */
+        local_nmi->flags  = cpu_to_le16(0);
+        local_nmi->lint   = 1; /* ACPI_LINT1 */
+    } else {
+        AcpiMadtLocalNmi *local_nmi;
+
         local_nmi = acpi_data_push(table_data, sizeof *local_nmi);
         local_nmi->type         = ACPI_APIC_LOCAL_NMI;
         local_nmi->length       = sizeof(*local_nmi);
         local_nmi->processor_id = 0xff; /* all processors */
         local_nmi->flags        = cpu_to_le16(0);
         local_nmi->lint         = 1; /* ACPI_LINT1 */
+    }
 
     build_header(linker, table_data,
                  (void *)(table_data->data + madt_start), "APIC",
@@ -2391,7 +2421,6 @@ static void
 build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
 {
     AcpiSystemResourceAffinityTable *srat;
-    AcpiSratProcessorAffinity *core;
     AcpiSratMemoryAffinity *numamem;
 
     int i;
@@ -2411,7 +2440,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
 
     for (i = 0; i < apic_ids->len; i++) {
         int j = numa_get_node_for_cpu(i);
-        int apic_id = apic_ids->cpus[i].arch_id;
+        uint32_t apic_id = apic_ids->cpus[i].arch_id;
+
+        if (apic_id < 255) {
+            AcpiSratProcessorAffinity *core;
 
             core = acpi_data_push(table_data, sizeof *core);
             core->type = ACPI_SRAT_PROCESSOR_APIC;
@@ -2423,6 +2455,18 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
             memset(core->proximity_hi, 0, 3);
             core->local_sapic_eid = 0;
             core->flags = cpu_to_le32(1);
+        } else {
+            AcpiSratProcessorX2ApicAffinity *core;
+
+            core = acpi_data_push(table_data, sizeof *core);
+            core->type = ACPI_SRAT_PROCESSOR_x2APIC;
+            core->length = sizeof(*core);
+            core->x2apic_id = cpu_to_le32(apic_id);
+            if (j < nb_numa_nodes) {
+                core->proximity_domain = cpu_to_le32(j);
+            }
+            core->flags = cpu_to_le32(1);
+        }
     }
 
 

hw/i386/kvm/apic.c

@@ -34,7 +34,11 @@ static void kvm_put_apic_state(APICCommonState *s, struct kvm_lapic_state *kapic
     int i;
 
     memset(kapic, 0, sizeof(*kapic));
+    if (kvm_has_x2apic_api() && s->apicbase & MSR_IA32_APICBASE_EXTD) {
+        kvm_apic_set_reg(kapic, 0x2, s->initial_apic_id);
+    } else {
         kvm_apic_set_reg(kapic, 0x2, s->id << 24);
+    }
     kvm_apic_set_reg(kapic, 0x8, s->tpr);
     kvm_apic_set_reg(kapic, 0xd, s->log_dest << 24);
     kvm_apic_set_reg(kapic, 0xe, s->dest_mode << 28 | 0x0fffffff);
@@ -59,7 +63,11 @@ void kvm_get_apic_state(DeviceState *dev, struct kvm_lapic_state *kapic)
     APICCommonState *s = APIC_COMMON(dev);
     int i, v;
 
+    if (kvm_has_x2apic_api() && s->apicbase & MSR_IA32_APICBASE_EXTD) {
+        assert(kvm_apic_get_reg(kapic, 0x2) == s->initial_apic_id);
+    } else {
         s->id = kvm_apic_get_reg(kapic, 0x2) >> 24;
+    }
     s->tpr = kvm_apic_get_reg(kapic, 0x8);
     s->arb_id = kvm_apic_get_reg(kapic, 0x9);
     s->log_dest = kvm_apic_get_reg(kapic, 0xd) >> 24;

hw/i386/pc.c

@@ -68,6 +68,7 @@
 #include "qapi-visit.h"
 #include "qom/cpu.h"
 #include "hw/nmi.h"
+#include "hw/i386/intel_iommu.h"
 
 /* debug PC/ISA interrupts */
 //#define DEBUG_IRQ
@@ -746,17 +747,15 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms)
 
     /* FW_CFG_MAX_CPUS is a bit confusing/problematic on x86:
      *
-     * SeaBIOS needs FW_CFG_MAX_CPUS for CPU hotplug, but the CPU hotplug
+     * For machine types prior to 1.8, SeaBIOS needs FW_CFG_MAX_CPUS for
-     * QEMU<->SeaBIOS interface is not based on the "CPU index", but on the APIC
+     * building MPTable, ACPI MADT, ACPI CPU hotplug and ACPI SRAT table,
-     * ID of hotplugged CPUs[1]. This means that FW_CFG_MAX_CPUS is not the
+     * that tables are based on xAPIC ID and QEMU<->SeaBIOS interface
-     * "maximum number of CPUs", but the "limit to the APIC ID values SeaBIOS
+     * for CPU hotplug also uses APIC ID and not "CPU index".
-     * may see".
+     * This means that FW_CFG_MAX_CPUS is not the "maximum number of CPUs",
+     * but the "limit to the APIC ID values SeaBIOS may see".
      *
-     * So, this means we must not use max_cpus, here, but the maximum possible
+     * So for compatibility reasons with old BIOSes we are stuck with
-     * APIC ID value, plus one.
+     * "etc/max-cpus" actually being apic_id_limit
-     *
-     * [1] The only kind of "CPU identifier" used between SeaBIOS and QEMU is
-     *     the APIC ID, not the "CPU index"
      */
     fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)pcms->apic_id_limit);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);
@@ -1087,17 +1086,6 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level)
     }
 }
 
-static int pc_present_cpus_count(PCMachineState *pcms)
-{
-    int i, boot_cpus = 0;
-    for (i = 0; i < pcms->possible_cpus->len; i++) {
-        if (pcms->possible_cpus->cpus[i].cpu) {
-            boot_cpus++;
-        }
-    }
-    return boot_cpus;
-}
-
 static X86CPU *pc_new_cpu(const char *typename, int64_t apic_id,
                           Error **errp)
 {
@@ -1190,12 +1178,6 @@ void pc_cpus_init(PCMachineState *pcms)
      * This is used for FW_CFG_MAX_CPUS. See comments on bochs_bios_init().
      */
     pcms->apic_id_limit = x86_cpu_apic_id_from_index(max_cpus - 1) + 1;
-    if (pcms->apic_id_limit > ACPI_CPU_HOTPLUG_ID_LIMIT) {
-        error_report("max_cpus is too large. APIC ID of last CPU is %u",
-                     pcms->apic_id_limit - 1);
-        exit(1);
-    }
-
     pcms->possible_cpus = g_malloc0(sizeof(CPUArchIdList) +
                                     sizeof(CPUArchId) * max_cpus);
     for (i = 0; i < max_cpus; i++) {
@@ -1240,6 +1222,19 @@ static void pc_build_feature_control_file(PCMachineState *pcms)
     fw_cfg_add_file(pcms->fw_cfg, "etc/msr_feature_control", val, sizeof(*val));
 }
 
+static void rtc_set_cpus_count(ISADevice *rtc, uint16_t cpus_count)
+{
+    if (cpus_count > 0xff) {
+        /* If the number of CPUs can't be represented in 8 bits, the
+         * BIOS must use "etc/boot-cpus". Set RTC field to 0 just
+         * to make old BIOSes fail more predictably.
+         */
+        rtc_set_memory(rtc, 0x5f, 0);
+    } else {
+        rtc_set_memory(rtc, 0x5f, cpus_count - 1);
+    }
+}
+
 static
 void pc_machine_done(Notifier *notifier, void *data)
 {
@@ -1248,7 +1243,7 @@ void pc_machine_done(Notifier *notifier, void *data)
     PCIBus *bus = pcms->bus;
 
     /* set the number of CPUs */
-    rtc_set_memory(pcms->rtc, 0x5f, pc_present_cpus_count(pcms) - 1);
+    rtc_set_cpus_count(pcms->rtc, le16_to_cpu(pcms->boot_cpus_le));
 
     if (bus) {
         int extra_hosts = 0;
@@ -1269,8 +1264,28 @@ void pc_machine_done(Notifier *notifier, void *data)
 
     acpi_setup();
     if (pcms->fw_cfg) {
+        MachineClass *mc = MACHINE_GET_CLASS(pcms);
+
         pc_build_smbios(pcms->fw_cfg);
         pc_build_feature_control_file(pcms);
+
+        if (mc->max_cpus > 255) {
+            fw_cfg_add_file(pcms->fw_cfg, "etc/boot-cpus", &pcms->boot_cpus_le,
+                            sizeof(pcms->boot_cpus_le));
+        }
+    }
+
+    if (pcms->apic_id_limit > 255) {
+        IntelIOMMUState *iommu = INTEL_IOMMU_DEVICE(x86_iommu_get_default());
+
+        if (!iommu || !iommu->x86_iommu.intr_supported ||
+            iommu->intr_eim != ON_OFF_AUTO_ON) {
+            error_report("current -smp configuration requires "
+                         "Extended Interrupt Mode enabled. "
+                         "You can add an IOMMU using: "
+                         "-device intel-iommu,intremap=on,eim=on");
+            exit(EXIT_FAILURE);
+        }
     }
 }
 
@@ -1794,9 +1809,11 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev,
         }
     }
 
-    if (dev->hotplugged) {
     /* increment the number of CPUs */
-        rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) + 1);
+    pcms->boot_cpus_le = cpu_to_le16(le16_to_cpu(pcms->boot_cpus_le) + 1);
+    if (dev->hotplugged) {
+        /* Update the number of CPUs in CMOS */
+        rtc_set_cpus_count(pcms->rtc, le16_to_cpu(pcms->boot_cpus_le));
     }
 
     found_cpu = pc_find_cpu_slot(pcms, CPU(dev), NULL);
@@ -1850,7 +1867,10 @@ static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev,
     found_cpu->cpu = NULL;
     object_unparent(OBJECT(dev));
 
-    rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) - 1);
+    /* decrement the number of CPUs */
+    pcms->boot_cpus_le = cpu_to_le16(le16_to_cpu(pcms->boot_cpus_le) - 1);
+    /* Update the number of CPUs in CMOS */
+    rtc_set_cpus_count(pcms->rtc, le16_to_cpu(pcms->boot_cpus_le));
  out:
     error_propagate(errp, local_err);
 }

hw/i386/pc_q35.c

@@ -291,6 +291,7 @@ static void pc_q35_machine_options(MachineClass *m)
     m->default_display = "std";
     m->no_floppy = 1;
     m->has_dynamic_sysbus = true;
+    m->max_cpus = 288;
 }
 
 static void pc_q35_2_8_machine_options(MachineClass *m)
@@ -306,6 +307,7 @@ static void pc_q35_2_7_machine_options(MachineClass *m)
 {
     pc_q35_2_8_machine_options(m);
     m->alias = NULL;
+    m->max_cpus = 255;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_7);
 }
 

hw/intc/apic_common.c

@@ -22,6 +22,7 @@
 #include "qapi/error.h"
 #include "qemu-common.h"
 #include "cpu.h"
+#include "qapi/visitor.h"
 #include "hw/i386/apic.h"
 #include "hw/i386/apic_internal.h"
 #include "trace.h"
@@ -39,6 +40,11 @@ void cpu_set_apic_base(DeviceState *dev, uint64_t val)
     if (dev) {
         APICCommonState *s = APIC_COMMON(dev);
         APICCommonClass *info = APIC_COMMON_GET_CLASS(s);
+        /* switching to x2APIC, reset possibly modified xAPIC ID */
+        if (!(s->apicbase & MSR_IA32_APICBASE_EXTD) &&
+            (val & MSR_IA32_APICBASE_EXTD)) {
+            s->id = s->initial_apic_id;
+        }
         info->set_base(s, val);
     }
 }
@@ -242,6 +248,7 @@ static void apic_reset_common(DeviceState *dev)
 
     bsp = s->apicbase & MSR_IA32_APICBASE_BSP;
     s->apicbase = APIC_DEFAULT_ADDRESS | bsp | MSR_IA32_APICBASE_ENABLE;
+    s->id = s->initial_apic_id;
 
     s->vapic_paddr = 0;
     info->vapic_base_update(s);
@@ -428,7 +435,6 @@ static const VMStateDescription vmstate_apic_common = {
 };
 
 static Property apic_properties_common[] = {
-    DEFINE_PROP_UINT8("id", APICCommonState, id, -1),
     DEFINE_PROP_UINT8("version", APICCommonState, version, 0x14),
     DEFINE_PROP_BIT("vapic", APICCommonState, vapic_control, VAPIC_ENABLE_BIT,
                     true),
@@ -437,6 +443,49 @@ static Property apic_properties_common[] = {
     DEFINE_PROP_END_OF_LIST(),
 };
 
+static void apic_common_get_id(Object *obj, Visitor *v, const char *name,
+                               void *opaque, Error **errp)
+{
+    APICCommonState *s = APIC_COMMON(obj);
+    int64_t value;
+
+    value = s->apicbase & MSR_IA32_APICBASE_EXTD ? s->initial_apic_id : s->id;
+    visit_type_int(v, name, &value, errp);
+}
+
+static void apic_common_set_id(Object *obj, Visitor *v, const char *name,
+                               void *opaque, Error **errp)
+{
+    APICCommonState *s = APIC_COMMON(obj);
+    DeviceState *dev = DEVICE(obj);
+    Error *local_err = NULL;
+    int64_t value;
+
+    if (dev->realized) {
+        qdev_prop_set_after_realize(dev, name, errp);
+        return;
+    }
+
+    visit_type_int(v, name, &value, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    s->initial_apic_id = value;
+    s->id = (uint8_t)value;
+}
+
+static void apic_common_initfn(Object *obj)
+{
+    APICCommonState *s = APIC_COMMON(obj);
+
+    s->id = s->initial_apic_id = -1;
+    object_property_add(obj, "id", "int",
+                        apic_common_get_id,
+                        apic_common_set_id, NULL, NULL, NULL);
+}
+
 static void apic_common_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -456,6 +505,7 @@ static const TypeInfo apic_common_type = {
     .name = TYPE_APIC_COMMON,
     .parent = TYPE_DEVICE,
     .instance_size = sizeof(APICCommonState),
+    .instance_init = apic_common_initfn,
     .class_size = sizeof(APICCommonClass),
     .class_init = apic_common_class_init,
     .abstract = true,

hw/ppc/spapr.c

@@ -2438,7 +2438,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
     mc->init = ppc_spapr_init;
     mc->reset = ppc_spapr_reset;
     mc->block_default_type = IF_SCSI;
-    mc->max_cpus = MAX_CPUMASK_BITS;
+    mc->max_cpus = 255;
     mc->no_parallel = 1;
     mc->default_boot_order = "";
     mc->default_ram_size = 512 * M_BYTE;

include/exec/exec-all.h

@@ -57,7 +57,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
                               uint32_t flags,
                               int cflags);
 
-void cpu_exec_init(CPUState *cpu, Error **errp);
 void QEMU_NORETURN cpu_loop_exit(CPUState *cpu);
 void QEMU_NORETURN cpu_loop_exit_restore(CPUState *cpu, uintptr_t pc);
 

include/hw/acpi/acpi-defs.h

@@ -343,6 +343,24 @@ struct AcpiMadtLocalNmi {
 } QEMU_PACKED;
 typedef struct AcpiMadtLocalNmi AcpiMadtLocalNmi;
 
+struct AcpiMadtProcessorX2Apic {
+    ACPI_SUB_HEADER_DEF
+    uint16_t reserved;
+    uint32_t x2apic_id;              /* Processor's local x2APIC ID */
+    uint32_t flags;
+    uint32_t uid;                    /* Processor object _UID */
+} QEMU_PACKED;
+typedef struct AcpiMadtProcessorX2Apic AcpiMadtProcessorX2Apic;
+
+struct AcpiMadtLocalX2ApicNmi {
+    ACPI_SUB_HEADER_DEF
+    uint16_t flags;                  /* MPS INTI flags */
+    uint32_t uid;                    /* Processor object _UID */
+    uint8_t  lint;                   /* Local APIC LINT# */
+    uint8_t  reserved[3];            /* Local APIC LINT# */
+} QEMU_PACKED;
+typedef struct AcpiMadtLocalX2ApicNmi AcpiMadtLocalX2ApicNmi;
+
 struct AcpiMadtGenericInterrupt {
     ACPI_SUB_HEADER_DEF
     uint16_t reserved;
@@ -485,6 +503,17 @@ struct AcpiSratProcessorAffinity
 } QEMU_PACKED;
 typedef struct AcpiSratProcessorAffinity AcpiSratProcessorAffinity;
 
+struct AcpiSratProcessorX2ApicAffinity {
+    ACPI_SUB_HEADER_DEF
+    uint16_t    reserved;
+    uint32_t    proximity_domain;
+    uint32_t    x2apic_id;
+    uint32_t    flags;
+    uint32_t    clk_domain;
+    uint32_t    reserved2;
+} QEMU_PACKED;
+typedef struct AcpiSratProcessorX2ApicAffinity AcpiSratProcessorX2ApicAffinity;
+
 struct AcpiSratMemoryAffinity
 {
     ACPI_SUB_HEADER_DEF

include/hw/i386/apic_internal.h

@@ -160,7 +160,8 @@ struct APICCommonState {
     MemoryRegion io_memory;
     X86CPU *cpu;
     uint32_t apicbase;
-    uint8_t id;
+    uint8_t id; /* legacy APIC ID */
+    uint32_t initial_apic_id;
     uint8_t version;
     uint8_t arb_id;
     uint8_t tpr;

include/hw/i386/pc.h

@@ -37,6 +37,7 @@
 /**
  * PCMachineState:
  * @acpi_dev: link to ACPI PM device that performs ACPI hotplug handling
+ * @boot_cpus_le: number of present VCPUs, referenced by 'etc/boot-cpus' fw_cfg
  */
 struct PCMachineState {
     /*< private >*/
@@ -69,6 +70,7 @@ struct PCMachineState {
     bool apic_xrupt_override;
     unsigned apic_id_limit;
     CPUArchIdList *possible_cpus;
+    uint16_t boot_cpus_le;
 
     /* NUMA information: */
     uint64_t numa_nodes;

include/qom/cpu.h

@@ -946,7 +946,9 @@ AddressSpace *cpu_get_address_space(CPUState *cpu, int asidx);
 
 void QEMU_NORETURN cpu_abort(CPUState *cpu, const char *fmt, ...)
     GCC_FMT_ATTR(2, 3);
-void cpu_exec_exit(CPUState *cpu);
+void cpu_exec_initfn(CPUState *cpu);
+void cpu_exec_realizefn(CPUState *cpu, Error **errp);
+void cpu_exec_unrealizefn(CPUState *cpu);
 
 #ifdef CONFIG_SOFTMMU
 extern const struct VMStateDescription vmstate_cpu_common;

include/sysemu/sysemu.h

@@ -173,7 +173,7 @@ extern int mem_prealloc;
  *
  * Note that cpu->get_arch_id() may be larger than MAX_CPUMASK_BITS.
  */
-#define MAX_CPUMASK_BITS 255
+#define MAX_CPUMASK_BITS 288
 
 #define MAX_OPTION_ROMS 16
 typedef struct QEMUOptionRom {

qom/cpu.c

@@ -345,6 +345,12 @@ static void cpu_common_realizefn(DeviceState *dev, Error **errp)
     trace_init_vcpu(cpu);
 }
 
+static void cpu_common_unrealizefn(DeviceState *dev, Error **errp)
+{
+    CPUState *cpu = CPU(dev);
+    cpu_exec_unrealizefn(cpu);
+}
+
 static void cpu_common_initfn(Object *obj)
 {
     CPUState *cpu = CPU(obj);
@@ -362,12 +368,13 @@ static void cpu_common_initfn(Object *obj)
     QTAILQ_INIT(&cpu->watchpoints);
 
     cpu->trace_dstate = bitmap_new(trace_get_vcpu_event_count());
+
+    cpu_exec_initfn(cpu);
 }
 
 static void cpu_common_finalize(Object *obj)
 {
     CPUState *cpu = CPU(obj);
-    cpu_exec_exit(cpu);
     g_free(cpu->trace_dstate);
 }
 
@@ -401,6 +408,7 @@ static void cpu_class_init(ObjectClass *klass, void *data)
     k->cpu_exec_exit = cpu_common_noop;
     k->cpu_exec_interrupt = cpu_common_exec_interrupt;
     dc->realize = cpu_common_realizefn;
+    dc->unrealize = cpu_common_unrealizefn;
     /*
      * Reason: CPUs still need special care by board code: wiring up
      * IRQs, adding reset handlers, halting non-first CPUs, ...

target-alpha/cpu.c

@@ -59,6 +59,13 @@ static void alpha_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     AlphaCPUClass *acc = ALPHA_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     qemu_init_vcpu(cs);
 
@@ -266,7 +273,6 @@ static void alpha_cpu_initfn(Object *obj)
     CPUAlphaState *env = &cpu->env;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
     tlb_flush(cs, 1);
 
     alpha_translate_init();
@@ -309,13 +315,6 @@ static void alpha_cpu_class_init(ObjectClass *oc, void *data)
     cc->disas_set_info = alpha_cpu_disas_set_info;
 
     cc->gdb_num_core_regs = 67;
-
-    /*
-     * Reason: alpha_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo alpha_cpu_type_info = {

target-arm/cpu-qom.h

@@ -80,9 +80,11 @@ void arm_gt_stimer_cb(void *opaque);
 #define ARM_AFF2_MASK  (0xFFULL << ARM_AFF2_SHIFT)
 #define ARM_AFF3_SHIFT 32
 #define ARM_AFF3_MASK  (0xFFULL << ARM_AFF3_SHIFT)
+#define ARM_DEFAULT_CPUS_PER_CLUSTER 8
 
 #define ARM32_AFFINITY_MASK (ARM_AFF0_MASK|ARM_AFF1_MASK|ARM_AFF2_MASK)
 #define ARM64_AFFINITY_MASK \
     (ARM_AFF0_MASK|ARM_AFF1_MASK|ARM_AFF2_MASK|ARM_AFF3_MASK)
+#define ARM64_AFFINITY_INVALID (~ARM64_AFFINITY_MASK)
 
 #endif

target-arm/cpu.c

@@ -434,29 +434,16 @@ static void arm_disas_set_info(CPUState *cpu, disassemble_info *info)
     }
 }
 
-#define ARM_CPUS_PER_CLUSTER 8
-
 static void arm_cpu_initfn(Object *obj)
 {
     CPUState *cs = CPU(obj);
     ARMCPU *cpu = ARM_CPU(obj);
     static bool inited;
-    uint32_t Aff1, Aff0;
 
     cs->env_ptr = &cpu->env;
-    cpu_exec_init(cs, &error_abort);
     cpu->cp_regs = g_hash_table_new_full(g_int_hash, g_int_equal,
                                          g_free, g_free);
 
-    /* This cpu-id-to-MPIDR affinity is used only for TCG; KVM will override it.
-     * We don't support setting cluster ID ([16..23]) (known as Aff2
-     * in later ARM ARM versions), or any of the higher affinity level fields,
-     * so these bits always RAZ.
-     */
-    Aff1 = cs->cpu_index / ARM_CPUS_PER_CLUSTER;
-    Aff0 = cs->cpu_index % ARM_CPUS_PER_CLUSTER;
-    cpu->mp_affinity = (Aff1 << ARM_AFF1_SHIFT) | Aff0;
-
 #ifndef CONFIG_USER_ONLY
     /* Our inbound IRQ and FIQ lines */
     if (kvm_enabled()) {
@@ -577,6 +564,13 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
     ARMCPUClass *acc = ARM_CPU_GET_CLASS(dev);
     CPUARMState *env = &cpu->env;
     int pagebits;
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     /* Some features automatically imply others: */
     if (arm_feature(env, ARM_FEATURE_V8)) {
@@ -655,6 +649,17 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
         return;
     }
 
+    /* This cpu-id-to-MPIDR affinity is used only for TCG; KVM will override it.
+     * We don't support setting cluster ID ([16..23]) (known as Aff2
+     * in later ARM ARM versions), or any of the higher affinity level fields,
+     * so these bits always RAZ.
+     */
+    if (cpu->mp_affinity == ARM64_AFFINITY_INVALID) {
+        uint32_t Aff1 = cs->cpu_index / ARM_DEFAULT_CPUS_PER_CLUSTER;
+        uint32_t Aff0 = cs->cpu_index % ARM_DEFAULT_CPUS_PER_CLUSTER;
+        cpu->mp_affinity = (Aff1 << ARM_AFF1_SHIFT) | Aff0;
+    }
+
     if (cpu->reset_hivecs) {
             cpu->reset_sctlr |= (1 << 13);
     }
@@ -1485,7 +1490,8 @@ static Property arm_cpu_properties[] = {
     DEFINE_PROP_BOOL("start-powered-off", ARMCPU, start_powered_off, false),
     DEFINE_PROP_UINT32("psci-conduit", ARMCPU, psci_conduit, 0),
     DEFINE_PROP_UINT32("midr", ARMCPU, midr, 0),
-    DEFINE_PROP_UINT64("mp-affinity", ARMCPU, mp_affinity, 0),
+    DEFINE_PROP_UINT64("mp-affinity", ARMCPU,
+                        mp_affinity, ARM64_AFFINITY_INVALID),
     DEFINE_PROP_END_OF_LIST()
 };
 
@@ -1557,17 +1563,6 @@ static void arm_cpu_class_init(ObjectClass *oc, void *data)
     cc->debug_check_watchpoint = arm_debug_check_watchpoint;
 
     cc->disas_set_info = arm_disas_set_info;
-
-    /*
-     * Reason: arm_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     *
-     * Once this is fixed, the devices that create ARM CPUs should be
-     * updated not to set cannot_destroy_with_object_finalize_yet,
-     * unless they still screw up something else.
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void cpu_register(const ARMCPUInfo *info)

target-cris/cpu.c

@@ -142,6 +142,13 @@ static void cris_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     CRISCPUClass *ccc = CRIS_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     cpu_reset(cs);
     qemu_init_vcpu(cs);
@@ -187,7 +194,6 @@ static void cris_cpu_initfn(Object *obj)
     static bool tcg_initialized;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     env->pregs[PR_VR] = ccc->vr;
 
@@ -326,13 +332,6 @@ static void cris_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_stop_before_watchpoint = true;
 
     cc->disas_set_info = cris_disas_set_info;
-
-    /*
-     * Reason: cris_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo cris_cpu_type_info = {

target-i386/cpu-qom.h

@@ -68,6 +68,7 @@ typedef struct X86CPUClass {
     const char *model_description;
 
     DeviceRealize parent_realize;
+    DeviceUnrealize parent_unrealize;
     void (*parent_reset)(CPUState *cpu);
 } X86CPUClass;
 

target-i386/cpu.c

@@ -2945,7 +2945,7 @@ static void x86_cpu_apic_create(X86CPU *cpu, Error **errp)
                               OBJECT(cpu->apic_state), &error_abort);
     object_unref(OBJECT(cpu->apic_state));
 
-    qdev_prop_set_uint8(cpu->apic_state, "id", cpu->apic_id);
+    qdev_prop_set_uint32(cpu->apic_state, "id", cpu->apic_id);
     /* TODO: convert to link<> */
     apic = APIC_COMMON(cpu->apic_state);
     apic->cpu = cpu;
@@ -3271,7 +3271,11 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
             cpu->phys_bits = 32;
         }
     }
-    cpu_exec_init(cs, &error_abort);
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     if (tcg_enabled()) {
         tcg_x86_init();
@@ -3352,6 +3356,8 @@ out:
 static void x86_cpu_unrealizefn(DeviceState *dev, Error **errp)
 {
     X86CPU *cpu = X86_CPU(dev);
+    X86CPUClass *xcc = X86_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
 
 #ifndef CONFIG_USER_ONLY
     cpu_remove_sync(CPU(dev));
@@ -3362,6 +3368,12 @@ static void x86_cpu_unrealizefn(DeviceState *dev, Error **errp)
         object_unparent(OBJECT(cpu->apic_state));
         cpu->apic_state = NULL;
     }
+
+    xcc->parent_unrealize(dev, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 }
 
 typedef struct BitProperty {
@@ -3636,6 +3648,7 @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     xcc->parent_realize = dc->realize;
+    xcc->parent_unrealize = dc->unrealize;
     dc->realize = x86_cpu_realizefn;
     dc->unrealize = x86_cpu_unrealizefn;
     dc->props = x86_cpu_properties;

target-i386/cpu.h

@@ -325,6 +325,7 @@
 #define MSR_IA32_APICBASE               0x1b
 #define MSR_IA32_APICBASE_BSP           (1<<8)
 #define MSR_IA32_APICBASE_ENABLE        (1<<11)
+#define MSR_IA32_APICBASE_EXTD          (1 << 10)
 #define MSR_IA32_APICBASE_BASE          (0xfffffU<<12)
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
 #define MSR_TSC_ADJUST                  0x0000003b

target-i386/kvm.c

@@ -129,9 +129,8 @@ static bool kvm_x2apic_api_set_flags(uint64_t flags)
     return !kvm_vm_enable_cap(s, KVM_CAP_X2APIC_API, 0, flags);
 }
 
-#define MEMORIZE(fn) \
+#define MEMORIZE(fn, _result) \
     ({ \
-        static typeof(fn) _result; \
         static bool _memorized; \
         \
         if (_memorized) { \
@@ -141,11 +140,19 @@ static bool kvm_x2apic_api_set_flags(uint64_t flags)
         _result = fn; \
     })
 
+static bool has_x2apic_api;
+
+bool kvm_has_x2apic_api(void)
+{
+    return has_x2apic_api;
+}
+
 bool kvm_enable_x2apic(void)
 {
     return MEMORIZE(
              kvm_x2apic_api_set_flags(KVM_X2APIC_API_USE_32BIT_IDS |
-                                      KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK));
+                                      KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK),
+             has_x2apic_api);
 }
 
 static int kvm_get_tsc(CPUState *cs)

target-i386/kvm_i386.h

@@ -44,4 +44,5 @@ int kvm_device_msix_deassign(KVMState *s, uint32_t dev_id);
 void kvm_put_apicbase(X86CPU *cpu, uint64_t value);
 
 bool kvm_enable_x2apic(void);
+bool kvm_has_x2apic_api(void);
 #endif

target-lm32/cpu.c

@@ -144,6 +144,13 @@ static void lm32_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     LM32CPUClass *lcc = LM32_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     cpu_reset(cs);
 
@@ -160,7 +167,6 @@ static void lm32_cpu_initfn(Object *obj)
     static bool tcg_initialized;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     env->flags = 0;
 
@@ -285,13 +291,6 @@ static void lm32_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_stop_before_watchpoint = true;
     cc->debug_excp_handler = lm32_debug_excp_handler;
     cc->disas_set_info = lm32_cpu_disas_set_info;
-
-    /*
-     * Reason: lm32_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void lm32_register_cpu_type(const LM32CPUInfo *info)

target-m68k/cpu.c

@@ -159,6 +159,13 @@ static void m68k_cpu_realizefn(DeviceState *dev, Error **errp)
     CPUState *cs = CPU(dev);
     M68kCPU *cpu = M68K_CPU(dev);
     M68kCPUClass *mcc = M68K_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     m68k_cpu_init_gdb(cpu);
 
@@ -176,7 +183,6 @@ static void m68k_cpu_initfn(Object *obj)
     static bool inited;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled() && !inited) {
         inited = true;
@@ -222,13 +228,6 @@ static void m68k_cpu_class_init(ObjectClass *c, void *data)
     cc->gdb_core_xml_file = "cf-core.xml";
 
     dc->vmsd = &vmstate_m68k_cpu;
-
-    /*
-     * Reason: m68k_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void register_cpu_type(const M68kCPUInfo *info)

target-microblaze/cpu.c

@@ -138,6 +138,13 @@ static void mb_cpu_realizefn(DeviceState *dev, Error **errp)
     CPUMBState *env = &cpu->env;
     uint8_t version_code = 0;
     int i = 0;
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     qemu_init_vcpu(cs);
 
@@ -199,7 +206,6 @@ static void mb_cpu_initfn(Object *obj)
     static bool tcg_initialized;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     set_float_rounding_mode(float_round_nearest_even, &env->fp_status);
 
@@ -267,12 +273,6 @@ static void mb_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_num_core_regs = 32 + 5;
 
     cc->disas_set_info = mb_disas_set_info;
-
-    /*
-     * Reason: mb_cpu_initfn() calls cpu_exec_init(), which saves the
-     * object in cpus -> dangling pointer after final object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo mb_cpu_type_info = {

target-mips/cpu.c

@@ -124,6 +124,13 @@ static void mips_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     MIPSCPUClass *mcc = MIPS_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     cpu_reset(cs);
     qemu_init_vcpu(cs);
@@ -138,7 +145,6 @@ static void mips_cpu_initfn(Object *obj)
     CPUMIPSState *env = &cpu->env;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled()) {
         mips_tcg_init();
@@ -177,13 +183,6 @@ static void mips_cpu_class_init(ObjectClass *c, void *data)
 
     cc->gdb_num_core_regs = 73;
     cc->gdb_stop_before_watchpoint = true;
-
-    /*
-     * Reason: mips_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo mips_cpu_type_info = {

target-moxie/cpu.c

@@ -61,6 +61,13 @@ static void moxie_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     MoxieCPUClass *mcc = MOXIE_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     qemu_init_vcpu(cs);
     cpu_reset(cs);
@@ -75,7 +82,6 @@ static void moxie_cpu_initfn(Object *obj)
     static int inited;
 
     cs->env_ptr = &cpu->env;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled() && !inited) {
         inited = 1;
@@ -124,13 +130,6 @@ static void moxie_cpu_class_init(ObjectClass *oc, void *data)
     cc->vmsd = &vmstate_moxie_cpu;
 #endif
     cc->disas_set_info = moxie_cpu_disas_set_info;
-
-    /*
-     * Reason: moxie_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void moxielite_initfn(Object *obj)

target-openrisc/cpu.c

@@ -81,6 +81,13 @@ static void openrisc_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     OpenRISCCPUClass *occ = OPENRISC_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     qemu_init_vcpu(cs);
     cpu_reset(cs);
@@ -95,7 +102,6 @@ static void openrisc_cpu_initfn(Object *obj)
     static int inited;
 
     cs->env_ptr = &cpu->env;
-    cpu_exec_init(cs, &error_abort);
 
 #ifndef CONFIG_USER_ONLY
     cpu_openrisc_mmu_init(cpu);
@@ -180,13 +186,6 @@ static void openrisc_cpu_class_init(ObjectClass *oc, void *data)
     dc->vmsd = &vmstate_openrisc_cpu;
 #endif
     cc->gdb_num_core_regs = 32 + 3;
-
-    /*
-     * Reason: openrisc_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void cpu_register(const OpenRISCCPUInfo *info)

target-ppc/cpu-qom.h

@@ -174,6 +174,7 @@ typedef struct PowerPCCPUClass {
     /*< public >*/
 
     DeviceRealize parent_realize;
+    DeviceUnrealize parent_unrealize;
     void (*parent_reset)(CPUState *cpu);
 
     uint32_t pvr;

target-ppc/translate_init.c

@@ -9678,7 +9678,7 @@ static void ppc_cpu_realizefn(DeviceState *dev, Error **errp)
     }
 #endif
 
-    cpu_exec_init(cs, &local_err);
+    cpu_exec_realizefn(cs, &local_err);
     if (local_err != NULL) {
         error_propagate(errp, local_err);
         return;
@@ -9906,11 +9906,17 @@ static void ppc_cpu_realizefn(DeviceState *dev, Error **errp)
 static void ppc_cpu_unrealizefn(DeviceState *dev, Error **errp)
 {
     PowerPCCPU *cpu = POWERPC_CPU(dev);
+    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
     CPUPPCState *env = &cpu->env;
+    Error *local_err = NULL;
     opc_handler_t **table, **table_2;
     int i, j, k;
 
-    cpu_exec_exit(CPU(dev));
+    pcc->parent_unrealize(dev, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     for (i = 0; i < PPC_CPU_OPCODES_LEN; i++) {
         if (env->opcodes[i] == &invalid_handler) {
@@ -10521,6 +10527,7 @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     pcc->parent_realize = dc->realize;
+    pcc->parent_unrealize = dc->unrealize;
     pcc->pvr_match = ppc_pvr_match_default;
     pcc->interrupts_big_endian = ppc_cpu_interrupts_big_endian_always;
     dc->realize = ppc_cpu_realizefn;

target-s390x/cpu.c

@@ -207,7 +207,7 @@ static void s390_cpu_realizefn(DeviceState *dev, Error **errp)
         goto out;
     }
 
-    cpu_exec_init(cs, &err);
+    cpu_exec_realizefn(cs, &err);
     if (err != NULL) {
         goto out;
     }
@@ -440,12 +440,6 @@ static void s390_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_core_xml_file = "s390x-core64.xml";
     cc->gdb_arch_name = s390_gdb_arch_name;
 
-    /*
-     * Reason: s390_cpu_realizefn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
     s390_cpu_model_class_register_props(oc);
 }
 

target-sh4/cpu.c

@@ -244,6 +244,13 @@ static void superh_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     SuperHCPUClass *scc = SUPERH_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     cpu_reset(cs);
     qemu_init_vcpu(cs);
@@ -258,7 +265,6 @@ static void superh_cpu_initfn(Object *obj)
     CPUSH4State *env = &cpu->env;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     env->movcal_backup_tail = &(env->movcal_backup);
 
@@ -303,13 +309,6 @@ static void superh_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_num_core_regs = 59;
 
     dc->vmsd = &vmstate_sh_cpu;
-
-    /*
-     * Reason: superh_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo superh_cpu_type_info = {

target-sparc/cpu.c

@@ -792,7 +792,9 @@ static bool sparc_cpu_has_work(CPUState *cs)
 
 static void sparc_cpu_realizefn(DeviceState *dev, Error **errp)
 {
+    CPUState *cs = CPU(dev);
     SPARCCPUClass *scc = SPARC_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
 #if defined(CONFIG_USER_ONLY)
     SPARCCPU *cpu = SPARC_CPU(dev);
     CPUSPARCState *env = &cpu->env;
@@ -802,7 +804,13 @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp)
     }
 #endif
 
-    qemu_init_vcpu(CPU(dev));
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    qemu_init_vcpu(cs);
 
     scc->parent_realize(dev, errp);
 }
@@ -814,7 +822,6 @@ static void sparc_cpu_initfn(Object *obj)
     CPUSPARCState *env = &cpu->env;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled()) {
         gen_intermediate_code_init(env);
@@ -867,13 +874,6 @@ static void sparc_cpu_class_init(ObjectClass *oc, void *data)
 #else
     cc->gdb_num_core_regs = 72;
 #endif
-
-    /*
-     * Reason: sparc_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo sparc_cpu_type_info = {

target-tilegx/cpu.c

@@ -92,6 +92,13 @@ static void tilegx_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     TileGXCPUClass *tcc = TILEGX_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     cpu_reset(cs);
     qemu_init_vcpu(cs);
@@ -107,7 +114,6 @@ static void tilegx_cpu_initfn(Object *obj)
     static bool tcg_initialized;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled() && !tcg_initialized) {
         tcg_initialized = true;
@@ -162,13 +168,6 @@ static void tilegx_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = tilegx_cpu_set_pc;
     cc->handle_mmu_fault = tilegx_cpu_handle_mmu_fault;
     cc->gdb_num_core_regs = 0;
-
-    /*
-     * Reason: tilegx_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo tilegx_cpu_type_info = {

target-tricore/cpu.c

@@ -69,6 +69,13 @@ static void tricore_cpu_realizefn(DeviceState *dev, Error **errp)
     TriCoreCPU *cpu = TRICORE_CPU(dev);
     TriCoreCPUClass *tcc = TRICORE_CPU_GET_CLASS(dev);
     CPUTriCoreState *env = &cpu->env;
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     /* Some features automatically imply others */
     if (tricore_feature(env, TRICORE_FEATURE_161)) {
@@ -95,7 +102,6 @@ static void tricore_cpu_initfn(Object *obj)
     CPUTriCoreState *env = &cpu->env;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled()) {
         tricore_tcg_init();
@@ -172,13 +178,6 @@ static void tricore_cpu_class_init(ObjectClass *c, void *data)
     cc->dump_state = tricore_cpu_dump_state;
     cc->set_pc = tricore_cpu_set_pc;
     cc->synchronize_from_tb = tricore_cpu_synchronize_from_tb;
-
-    /*
-     * Reason: tricore_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void cpu_register(const TriCoreCPUInfo *info)

target-unicore32/cpu.c

@@ -101,9 +101,17 @@ static const UniCore32CPUInfo uc32_cpus[] = {
 
 static void uc32_cpu_realizefn(DeviceState *dev, Error **errp)
 {
+    CPUState *cs = CPU(dev);
     UniCore32CPUClass *ucc = UNICORE32_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
 
-    qemu_init_vcpu(CPU(dev));
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    qemu_init_vcpu(cs);
 
     ucc->parent_realize(dev, errp);
 }
@@ -116,7 +124,6 @@ static void uc32_cpu_initfn(Object *obj)
     static bool inited;
 
     cs->env_ptr = env;
-    cpu_exec_init(cs, &error_abort);
 
 #ifdef CONFIG_USER_ONLY
     env->uncached_asr = ASR_MODE_USER;
@@ -160,13 +167,6 @@ static void uc32_cpu_class_init(ObjectClass *oc, void *data)
     cc->get_phys_page_debug = uc32_cpu_get_phys_page_debug;
 #endif
     dc->vmsd = &vmstate_uc32_cpu;
-
-    /*
-     * Reason: uc32_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static void uc32_register_cpu_type(const UniCore32CPUInfo *info)

target-xtensa/cpu.c

@@ -99,6 +99,13 @@ static void xtensa_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
     XtensaCPUClass *xcc = XTENSA_CPU_GET_CLASS(dev);
+    Error *local_err = NULL;
+
+    cpu_exec_realizefn(cs, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     cs->gdb_num_regs = xcc->config->gdb_regmap.num_regs;
 
@@ -117,7 +124,6 @@ static void xtensa_cpu_initfn(Object *obj)
 
     cs->env_ptr = env;
     env->config = xcc->config;
-    cpu_exec_init(cs, &error_abort);
 
     if (tcg_enabled() && !tcg_inited) {
         tcg_inited = true;
@@ -158,13 +164,6 @@ static void xtensa_cpu_class_init(ObjectClass *oc, void *data)
 #endif
     cc->debug_excp_handler = xtensa_breakpoint_handler;
     dc->vmsd = &vmstate_xtensa_cpu;
-
-    /*
-     * Reason: xtensa_cpu_initfn() calls cpu_exec_init(), which saves
-     * the object in cpus -> dangling pointer after final
-     * object_unref().
-     */
-    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo xtensa_cpu_type_info = {