Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.9-20170222' into staging

ppc patch queue for 2017-02-22

This pull request has:
   * Yet more POWER9 instruction implementations
   * Some extensions to the softfloat code which are necesssary for
     some of those instructions
   * Some preliminary patches in preparation for POWER9 softmmu
     implementation
   * Igor Mammedov's cleanups to unify hotplug cpu handling across
     architectures
   * Assorted bugfixes

The softfloat and cpu hotplug changes aren't entirely ppc specific (in
fact the hotplug stuff contains some pc specific patches).  However
they're included here because ppc is one of the main beneficiaries,
and the series depend on some ppc specific patches.

# gpg: Signature made Wed 22 Feb 2017 06:29:47 GMT
# gpg:                using RSA key 0x6C38CACA20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg:                 aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg:                 aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg:                 aka "David Gibson (kernel.org) <dwg@kernel.org>"
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E  87DC 6C38 CACA 20D9 B392

* remotes/dgibson/tags/ppc-for-2.9-20170222: (43 commits)
  hw/ppc/ppc405_uc.c: Avoid integer overflows
  hw/ppc/spapr: Check for valid page size when hot plugging memory
  target-ppc: fix Book-E TLB matching
  hw/net/spapr_llan: 6 byte mac address device tree entry
  machine: replace query_hotpluggable_cpus() callback with has_hotpluggable_cpus flag
  machine: unify [pc_|spapr_]query_hotpluggable_cpus() callbacks
  spapr: reuse machine->possible_cpus instead of cores[]
  change CPUArchId.cpu type to Object*
  pc: pass apic_id to pc_find_cpu_slot() directly so lookup could be done without CPU object
  pc: calculate topology only once when possible_cpus is initialised
  pc: move pcms->possible_cpus init out of pc_cpus_init()
  machine: move possible_cpus to MachineState
  hw/pci-host/prep: Do not use hw_error() in realize function
  target/ppc/POWER9: Direct all instr and data storage interrupts to the hypv
  target/ppc/POWER9: Adapt LPCR handling for POWER9
  target/ppc/POWER9: Add ISAv3.00 MMU definition
  target/ppc: Fix LPCR DPFD mask define
  target-ppc: Add xscvqpudz and xscvqpuwz instructions
  target-ppc: Implement round to odd variants of quad FP instructions
  softfloat: Add float128_to_uint32_round_to_zero()
  ...

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

35 files changed, 1093 insertions, 354 deletions

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index c295f3183f..485a006aa7 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -623,6 +623,9 @@ static float64 roundAndPackFloat64(flag zSign, int zExp, uint64_t zSig,
     case float_round_down:
         roundIncrement = zSign ? 0x3ff : 0;
         break;
+    case float_round_to_odd:
+        roundIncrement = (zSig & 0x400) ? 0 : 0x3ff;
+        break;
     default:
         abort();
     }
@@ -632,8 +635,10 @@ static float64 roundAndPackFloat64(flag zSign, int zExp, uint64_t zSig,
              || (    ( zExp == 0x7FD )
                   && ( (int64_t) ( zSig + roundIncrement ) < 0 ) )
            ) {
+            bool overflow_to_inf = roundingMode != float_round_to_odd &&
+                                   roundIncrement != 0;
             float_raise(float_flag_overflow | float_flag_inexact, status);
-            return packFloat64( zSign, 0x7FF, - ( roundIncrement == 0 ));
+            return packFloat64(zSign, 0x7FF, -(!overflow_to_inf));
         }
         if ( zExp < 0 ) {
             if (status->flush_to_zero) {
@@ -651,6 +656,13 @@ static float64 roundAndPackFloat64(flag zSign, int zExp, uint64_t zSig,
             if (isTiny && roundBits) {
                 float_raise(float_flag_underflow, status);
             }
+            if (roundingMode == float_round_to_odd) {
+                /*
+                 * For round-to-odd case, the roundIncrement depends on
+                 * zSig which just changed.
+                 */
+                roundIncrement = (zSig & 0x400) ? 0 : 0x3ff;
+            }
         }
     }
     if (roundBits) {
@@ -1149,6 +1161,9 @@ static float128 roundAndPackFloat128(flag zSign, int32_t zExp,
     case float_round_down:
         increment = zSign && zSig2;
         break;
+    case float_round_to_odd:
+        increment = !(zSig1 & 0x1) && zSig2;
+        break;
     default:
         abort();
     }
@@ -1168,6 +1183,7 @@ static float128 roundAndPackFloat128(flag zSign, int32_t zExp,
             if (    ( roundingMode == float_round_to_zero )
                  || ( zSign && ( roundingMode == float_round_up ) )
                  || ( ! zSign && ( roundingMode == float_round_down ) )
+                 || (roundingMode == float_round_to_odd)
                ) {
                 return
                     packFloat128(
@@ -1215,6 +1231,9 @@ static float128 roundAndPackFloat128(flag zSign, int32_t zExp,
             case float_round_down:
                 increment = zSign && zSig2;
                 break;
+            case float_round_to_odd:
+                increment = !(zSig1 & 0x1) && zSig2;
+                break;
             default:
                 abort();
             }
@@ -6109,6 +6128,93 @@ int64_t float128_to_int64_round_to_zero(float128 a, float_status *status)
 }
 
 /*----------------------------------------------------------------------------
+| Returns the result of converting the quadruple-precision floating-point value
+| `a' to the 64-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic---which means in particular that the conversion is rounded
+| according to the current rounding mode.  If `a' is a NaN, the largest
+| positive integer is returned.  If the conversion overflows, the
+| largest unsigned integer is returned.  If 'a' is negative, the value is
+| rounded and zero is returned; negative values that do not round to zero
+| will raise the inexact exception.
+*----------------------------------------------------------------------------*/
+
+uint64_t float128_to_uint64(float128 a, float_status *status)
+{
+    flag aSign;
+    int aExp;
+    int shiftCount;
+    uint64_t aSig0, aSig1;
+
+    aSig0 = extractFloat128Frac0(a);
+    aSig1 = extractFloat128Frac1(a);
+    aExp = extractFloat128Exp(a);
+    aSign = extractFloat128Sign(a);
+    if (aSign && (aExp > 0x3FFE)) {
+        float_raise(float_flag_invalid, status);
+        if (float128_is_any_nan(a)) {
+            return LIT64(0xFFFFFFFFFFFFFFFF);
+        } else {
+            return 0;
+        }
+    }
+    if (aExp) {
+        aSig0 |= LIT64(0x0001000000000000);
+    }
+    shiftCount = 0x402F - aExp;
+    if (shiftCount <= 0) {
+        if (0x403E < aExp) {
+            float_raise(float_flag_invalid, status);
+            return LIT64(0xFFFFFFFFFFFFFFFF);
+        }
+        shortShift128Left(aSig0, aSig1, -shiftCount, &aSig0, &aSig1);
+    } else {
+        shift64ExtraRightJamming(aSig0, aSig1, shiftCount, &aSig0, &aSig1);
+    }
+    return roundAndPackUint64(aSign, aSig0, aSig1, status);
+}
+
+uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *status)
+{
+    uint64_t v;
+    signed char current_rounding_mode = status->float_rounding_mode;
+
+    set_float_rounding_mode(float_round_to_zero, status);
+    v = float128_to_uint64(a, status);
+    set_float_rounding_mode(current_rounding_mode, status);
+
+    return v;
+}
+
+/*----------------------------------------------------------------------------
+| Returns the result of converting the quadruple-precision floating-point
+| value `a' to the 32-bit unsigned integer format.  The conversion
+| is performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic except that the conversion is always rounded toward zero.
+| If `a' is a NaN, the largest positive integer is returned.  Otherwise,
+| if the conversion overflows, the largest unsigned integer is returned.
+| If 'a' is negative, the value is rounded and zero is returned; negative
+| values that do not round to zero will raise the inexact exception.
+*----------------------------------------------------------------------------*/
+
+uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *status)
+{
+    uint64_t v;
+    uint32_t res;
+    int old_exc_flags = get_float_exception_flags(status);
+
+    v = float128_to_uint64_round_to_zero(a, status);
+    if (v > 0xffffffff) {
+        res = 0xffffffff;
+    } else {
+        return v;
+    }
+    set_float_exception_flags(old_exc_flags, status);
+    float_raise(float_flag_invalid, status);
+    return res;
+}
+
+/*----------------------------------------------------------------------------
 | Returns the result of converting the quadruple-precision floating-point
 | value `a' to the single-precision floating-point format.  The conversion
 | is performed according to the IEC/IEEE Standard for Binary Floating-Point
diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c
index 6017ca04bf..8c719d3f9d 100644
--- a/hw/acpi/cpu.c
+++ b/hw/acpi/cpu.c
@@ -198,7 +198,7 @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner,
     state->dev_count = id_list->len;
     state->devs = g_new0(typeof(*state->devs), state->dev_count);
     for (i = 0; i < id_list->len; i++) {
-        state->devs[i].cpu =  id_list->cpus[i].cpu;
+        state->devs[i].cpu =  CPU(id_list->cpus[i].cpu);
         state->devs[i].arch_id = id_list->cpus[i].arch_id;
     }
     memory_region_init_io(&state->ctrl_reg, owner, &cpu_hotplug_ops, state,
diff --git a/hw/core/machine.c b/hw/core/machine.c
index b0fd91f6cd..0699750336 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -357,6 +357,37 @@ static void machine_init_notify(Notifier *notifier, void *data)
     foreach_dynamic_sysbus_device(error_on_sysbus_device, NULL);
 }
 
+HotpluggableCPUList *machine_query_hotpluggable_cpus(MachineState *machine)
+{
+    int i;
+    Object *cpu;
+    HotpluggableCPUList *head = NULL;
+    const char *cpu_type;
+
+    cpu = machine->possible_cpus->cpus[0].cpu;
+    assert(cpu); /* Boot cpu is always present */
+    cpu_type = object_get_typename(cpu);
+    for (i = 0; i < machine->possible_cpus->len; i++) {
+        HotpluggableCPUList *list_item = g_new0(typeof(*list_item), 1);
+        HotpluggableCPU *cpu_item = g_new0(typeof(*cpu_item), 1);
+
+        cpu_item->type = g_strdup(cpu_type);
+        cpu_item->vcpus_count = machine->possible_cpus->cpus[i].vcpus_count;
+        cpu_item->props = g_memdup(&machine->possible_cpus->cpus[i].props,
+                                   sizeof(*cpu_item->props));
+
+        cpu = machine->possible_cpus->cpus[i].cpu;
+        if (cpu) {
+            cpu_item->has_qom_path = true;
+            cpu_item->qom_path = object_get_canonical_path(cpu);
+        }
+        list_item->value = cpu_item;
+        list_item->next = head;
+        head = list_item;
+    }
+    return head;
+}
+
 static void machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 60b0946be3..d24388e05f 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -707,7 +707,8 @@ static void pc_build_smbios(PCMachineState *pcms)
     size_t smbios_tables_len, smbios_anchor_len;
     struct smbios_phys_mem_area *mem_array;
     unsigned i, array_count;
-    X86CPU *cpu = X86_CPU(pcms->possible_cpus->cpus[0].cpu);
+    MachineState *ms = MACHINE(pcms);
+    X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
 
     /* tell smbios about cpuid version and features */
     smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
@@ -1111,7 +1112,7 @@ static void pc_new_cpu(const char *typename, int64_t apic_id, Error **errp)
 void pc_hot_add_cpu(const int64_t id, Error **errp)
 {
     ObjectClass *oc;
-    PCMachineState *pcms = PC_MACHINE(qdev_get_machine());
+    MachineState *ms = MACHINE(qdev_get_machine());
     int64_t apic_id = x86_cpu_apic_id_from_index(id);
     Error *local_err = NULL;
 
@@ -1127,8 +1128,8 @@ void pc_hot_add_cpu(const int64_t id, Error **errp)
         return;
     }
 
-    assert(pcms->possible_cpus->cpus[0].cpu); /* BSP is always present */
-    oc = OBJECT_CLASS(CPU_GET_CLASS(pcms->possible_cpus->cpus[0].cpu));
+    assert(ms->possible_cpus->cpus[0].cpu); /* BSP is always present */
+    oc = OBJECT_CLASS(CPU_GET_CLASS(ms->possible_cpus->cpus[0].cpu));
     pc_new_cpu(object_class_get_name(oc), apic_id, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -1143,7 +1144,9 @@ void pc_cpus_init(PCMachineState *pcms)
     ObjectClass *oc;
     const char *typename;
     gchar **model_pieces;
+    const CPUArchIdList *possible_cpus;
     MachineState *machine = MACHINE(pcms);
+    MachineClass *mc = MACHINE_GET_CLASS(pcms);
 
     /* init CPUs */
     if (machine->cpu_model == NULL) {
@@ -1178,20 +1181,16 @@ 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;
-    pcms->possible_cpus = g_malloc0(sizeof(CPUArchIdList) +
-                                    sizeof(CPUArchId) * max_cpus);
-    for (i = 0; i < max_cpus; i++) {
-        pcms->possible_cpus->cpus[i].arch_id = x86_cpu_apic_id_from_index(i);
-        pcms->possible_cpus->len++;
-        if (i < smp_cpus) {
-            pc_new_cpu(typename, x86_cpu_apic_id_from_index(i), &error_fatal);
-        }
+    possible_cpus = mc->possible_cpu_arch_ids(machine);
+    for (i = 0; i < smp_cpus; i++) {
+        pc_new_cpu(typename, possible_cpus->cpus[i].arch_id, &error_fatal);
     }
 }
 
 static void pc_build_feature_control_file(PCMachineState *pcms)
 {
-    X86CPU *cpu = X86_CPU(pcms->possible_cpus->cpus[0].cpu);
+    MachineState *ms = MACHINE(pcms);
+    X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
     CPUX86State *env = &cpu->env;
     uint32_t unused, ecx, edx;
     uint64_t feature_control_bits = 0;
@@ -1787,21 +1786,19 @@ static int pc_apic_cmp(const void *a, const void *b)
 }
 
 /* returns pointer to CPUArchId descriptor that matches CPU's apic_id
- * in pcms->possible_cpus->cpus, if pcms->possible_cpus->cpus has no
+ * in ms->possible_cpus->cpus, if ms->possible_cpus->cpus has no
  * entry corresponding to CPU's apic_id returns NULL.
  */
-static CPUArchId *pc_find_cpu_slot(PCMachineState *pcms, CPUState *cpu,
-                                   int *idx)
+static CPUArchId *pc_find_cpu_slot(MachineState *ms, uint32_t id, int *idx)
 {
-    CPUClass *cc = CPU_GET_CLASS(cpu);
     CPUArchId apic_id, *found_cpu;
 
-    apic_id.arch_id = cc->get_arch_id(CPU(cpu));
-    found_cpu = bsearch(&apic_id, pcms->possible_cpus->cpus,
-        pcms->possible_cpus->len, sizeof(*pcms->possible_cpus->cpus),
+    apic_id.arch_id = id;
+    found_cpu = bsearch(&apic_id, ms->possible_cpus->cpus,
+        ms->possible_cpus->len, sizeof(*ms->possible_cpus->cpus),
         pc_apic_cmp);
     if (found_cpu && idx) {
-        *idx = found_cpu - pcms->possible_cpus->cpus;
+        *idx = found_cpu - ms->possible_cpus->cpus;
     }
     return found_cpu;
 }
@@ -1812,6 +1809,7 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev,
     CPUArchId *found_cpu;
     HotplugHandlerClass *hhc;
     Error *local_err = NULL;
+    X86CPU *cpu = X86_CPU(dev);
     PCMachineState *pcms = PC_MACHINE(hotplug_dev);
 
     if (pcms->acpi_dev) {
@@ -1831,8 +1829,8 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev,
         fw_cfg_modify_i16(pcms->fw_cfg, FW_CFG_NB_CPUS, pcms->boot_cpus);
     }
 
-    found_cpu = pc_find_cpu_slot(pcms, CPU(dev), NULL);
-    found_cpu->cpu = CPU(dev);
+    found_cpu = pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, NULL);
+    found_cpu->cpu = OBJECT(dev);
 out:
     error_propagate(errp, local_err);
 }
@@ -1842,9 +1840,10 @@ static void pc_cpu_unplug_request_cb(HotplugHandler *hotplug_dev,
     int idx = -1;
     HotplugHandlerClass *hhc;
     Error *local_err = NULL;
+    X86CPU *cpu = X86_CPU(dev);
     PCMachineState *pcms = PC_MACHINE(hotplug_dev);
 
-    pc_find_cpu_slot(pcms, CPU(dev), &idx);
+    pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, &idx);
     assert(idx != -1);
     if (idx == 0) {
         error_setg(&local_err, "Boot CPU is unpluggable");
@@ -1869,6 +1868,7 @@ static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev,
     CPUArchId *found_cpu;
     HotplugHandlerClass *hhc;
     Error *local_err = NULL;
+    X86CPU *cpu = X86_CPU(dev);
     PCMachineState *pcms = PC_MACHINE(hotplug_dev);
 
     hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev);
@@ -1878,7 +1878,7 @@ static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev,
         goto out;
     }
 
-    found_cpu = pc_find_cpu_slot(pcms, CPU(dev), NULL);
+    found_cpu = pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, NULL);
     found_cpu->cpu = NULL;
     object_unparent(OBJECT(dev));
 
@@ -1936,13 +1936,15 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev,
         cpu->apic_id = apicid_from_topo_ids(smp_cores, smp_threads, &topo);
     }
 
-    cpu_slot = pc_find_cpu_slot(pcms, CPU(dev), &idx);
+    cpu_slot = pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, &idx);
     if (!cpu_slot) {
+        MachineState *ms = MACHINE(pcms);
+
         x86_topo_ids_from_apicid(cpu->apic_id, smp_cores, smp_threads, &topo);
         error_setg(errp, "Invalid CPU [socket: %u, core: %u, thread: %u] with"
                   " APIC ID %" PRIu32 ", valid index range 0:%d",
                    topo.pkg_id, topo.core_id, topo.smt_id, cpu->apic_id,
-                   pcms->possible_cpus->len - 1);
+                   ms->possible_cpus->len - 1);
         return;
     }
 
@@ -1953,7 +1955,7 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev,
     }
 
     /* if 'address' properties socket-id/core-id/thread-id are not set, set them
-     * so that query_hotpluggable_cpus would show correct values
+     * so that machine_query_hotpluggable_cpus would show correct values
      */
     /* TODO: move socket_id/core_id/thread_id checks into x86_cpu_realizefn()
      * once -smp refactoring is complete and there will be CPU private
@@ -2251,55 +2253,37 @@ static unsigned pc_cpu_index_to_socket_id(unsigned cpu_index)
     return topo.pkg_id;
 }
 
-static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *machine)
-{
-    PCMachineState *pcms = PC_MACHINE(machine);
-    assert(pcms->possible_cpus);
-    return pcms->possible_cpus;
-}
-
-static HotpluggableCPUList *pc_query_hotpluggable_cpus(MachineState *machine)
+static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *ms)
 {
     int i;
-    CPUState *cpu;
-    HotpluggableCPUList *head = NULL;
-    PCMachineState *pcms = PC_MACHINE(machine);
-    const char *cpu_type;
 
-    cpu = pcms->possible_cpus->cpus[0].cpu;
-    assert(cpu); /* BSP is always present */
-    cpu_type = object_class_get_name(OBJECT_CLASS(CPU_GET_CLASS(cpu)));
+    if (ms->possible_cpus) {
+        /*
+         * make sure that max_cpus hasn't changed since the first use, i.e.
+         * -smp hasn't been parsed after it
+        */
+        assert(ms->possible_cpus->len == max_cpus);
+        return ms->possible_cpus;
+    }
 
-    for (i = 0; i < pcms->possible_cpus->len; i++) {
+    ms->possible_cpus = g_malloc0(sizeof(CPUArchIdList) +
+                                  sizeof(CPUArchId) * max_cpus);
+    ms->possible_cpus->len = max_cpus;
+    for (i = 0; i < ms->possible_cpus->len; i++) {
         X86CPUTopoInfo topo;
-        HotpluggableCPUList *list_item = g_new0(typeof(*list_item), 1);
-        HotpluggableCPU *cpu_item = g_new0(typeof(*cpu_item), 1);
-        CpuInstanceProperties *cpu_props = g_new0(typeof(*cpu_props), 1);
-        const uint32_t apic_id = pcms->possible_cpus->cpus[i].arch_id;
-
-        x86_topo_ids_from_apicid(apic_id, smp_cores, smp_threads, &topo);
-
-        cpu_item->type = g_strdup(cpu_type);
-        cpu_item->vcpus_count = 1;
-        cpu_props->has_socket_id = true;
-        cpu_props->socket_id = topo.pkg_id;
-        cpu_props->has_core_id = true;
-        cpu_props->core_id = topo.core_id;
-        cpu_props->has_thread_id = true;
-        cpu_props->thread_id = topo.smt_id;
-        cpu_item->props = cpu_props;
-
-        cpu = pcms->possible_cpus->cpus[i].cpu;
-        if (cpu) {
-            cpu_item->has_qom_path = true;
-            cpu_item->qom_path = object_get_canonical_path(OBJECT(cpu));
-        }
 
-        list_item->value = cpu_item;
-        list_item->next = head;
-        head = list_item;
+        ms->possible_cpus->cpus[i].vcpus_count = 1;
+        ms->possible_cpus->cpus[i].arch_id = x86_cpu_apic_id_from_index(i);
+        x86_topo_ids_from_apicid(ms->possible_cpus->cpus[i].arch_id,
+                                 smp_cores, smp_threads, &topo);
+        ms->possible_cpus->cpus[i].props.has_socket_id = true;
+        ms->possible_cpus->cpus[i].props.socket_id = topo.pkg_id;
+        ms->possible_cpus->cpus[i].props.has_core_id = true;
+        ms->possible_cpus->cpus[i].props.core_id = topo.core_id;
+        ms->possible_cpus->cpus[i].props.has_thread_id = true;
+        ms->possible_cpus->cpus[i].props.thread_id = topo.smt_id;
     }
-    return head;
+    return ms->possible_cpus;
 }
 
 static void x86_nmi(NMIState *n, int cpu_index, Error **errp)
@@ -2342,7 +2326,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     mc->get_hotplug_handler = pc_get_hotpug_handler;
     mc->cpu_index_to_socket_id = pc_cpu_index_to_socket_id;
     mc->possible_cpu_arch_ids = pc_possible_cpu_arch_ids;
-    mc->query_hotpluggable_cpus = pc_query_hotpluggable_cpus;
+    mc->has_hotpluggable_cpus = true;
     mc->default_boot_order = "cad";
     mc->hot_add_cpu = pc_hot_add_cpu;
     mc->block_default_type = IF_IDE;
diff --git a/hw/net/spapr_llan.c b/hw/net/spapr_llan.c
index 058908d8d7..d239e4bd7d 100644
--- a/hw/net/spapr_llan.c
+++ b/hw/net/spapr_llan.c
@@ -385,18 +385,24 @@ static int spapr_vlan_devnode(VIOsPAPRDevice *dev, void *fdt, int node_off)
     int ret;
 
     /* Some old phyp versions give the mac address in an 8-byte
-     * property.  The kernel driver has an insane workaround for this;
+     * property.  The kernel driver (before 3.10) has an insane workaround;
      * rather than doing the obvious thing and checking the property
      * length, it checks whether the first byte has 0b10 in the low
      * bits.  If a correct 6-byte property has a different first byte
      * the kernel will get the wrong mac address, overrunning its
      * buffer in the process (read only, thank goodness).
      *
-     * Here we workaround the kernel workaround by always supplying an
-     * 8-byte property, with the mac address in the last six bytes */
-    memcpy(&padded_mac[2], &vdev->nicconf.macaddr, ETH_ALEN);
-    ret = fdt_setprop(fdt, node_off, "local-mac-address",
-                      padded_mac, sizeof(padded_mac));
+     * Here we return a 6-byte address unless that would break a pre-3.10
+     * driver.  In that case we return a padded 8-byte address to allow the old
+     * workaround to succeed. */
+    if ((vdev->nicconf.macaddr.a[0] & 0x3) == 0x2) {
+        ret = fdt_setprop(fdt, node_off, "local-mac-address",
+                          &vdev->nicconf.macaddr, ETH_ALEN);
+    } else {
+        memcpy(&padded_mac[2], &vdev->nicconf.macaddr, ETH_ALEN);
+        ret = fdt_setprop(fdt, node_off, "local-mac-address",
+                          padded_mac, sizeof(padded_mac));
+    }
     if (ret < 0) {
         return ret;
     }
diff --git a/hw/pci-host/prep.c b/hw/pci-host/prep.c
index 5580293f93..260a119a9e 100644
--- a/hw/pci-host/prep.c
+++ b/hw/pci-host/prep.c
@@ -309,7 +309,6 @@ static void raven_realize(PCIDevice *d, Error **errp)
     memory_region_set_readonly(&s->bios, true);
     memory_region_add_subregion(get_system_memory(), (uint32_t)(-BIOS_SIZE),
                                 &s->bios);
-    vmstate_register_ram_global(&s->bios);
     if (s->bios_name) {
         filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, s->bios_name);
         if (filename) {
@@ -328,12 +327,15 @@ static void raven_realize(PCIDevice *d, Error **errp)
                 }
             }
         }
+        g_free(filename);
         if (bios_size < 0 || bios_size > BIOS_SIZE) {
-            /* FIXME should error_setg() */
-            hw_error("qemu: could not load bios image '%s'\n", s->bios_name);
+            memory_region_del_subregion(get_system_memory(), &s->bios);
+            error_setg(errp, "Could not load bios image '%s'", s->bios_name);
+            return;
         }
-        g_free(filename);
     }
+
+    vmstate_register_ram_global(&s->bios);
 }
 
 static const VMStateDescription vmstate_raven = {
@@ -361,7 +363,6 @@ static void raven_class_init(ObjectClass *klass, void *data)
     /*
      * Reason: PCI-facing part of the host bridge, not usable without
      * the host-facing part, which can't be device_add'ed, yet.
-     * Reason: realize() method uses hw_error().
      */
     dc->cannot_instantiate_with_device_add_yet = true;
 }
diff --git a/hw/ppc/mac_newworld.c b/hw/ppc/mac_newworld.c
index 716aea6852..68aaedc06d 100644
--- a/hw/ppc/mac_newworld.c
+++ b/hw/ppc/mac_newworld.c
@@ -72,6 +72,7 @@
 #include "exec/address-spaces.h"
 #include "hw/sysbus.h"
 #include "qemu/cutils.h"
+#include "trace.h"
 
 #define MAX_IDE_BUS 2
 #define CFG_ADDR 0xf0000510
@@ -79,21 +80,11 @@
 #define CLOCKFREQ (266UL * 1000UL * 1000UL)
 #define BUSFREQ (100UL * 1000UL * 1000UL)
 
-/* debug UniNorth */
-//#define DEBUG_UNIN
-
-#ifdef DEBUG_UNIN
-#define UNIN_DPRINTF(fmt, ...)                                  \
-    do { printf("UNIN: " fmt , ## __VA_ARGS__); } while (0)
-#else
-#define UNIN_DPRINTF(fmt, ...)
-#endif
-
 /* UniN device */
 static void unin_write(void *opaque, hwaddr addr, uint64_t value,
                        unsigned size)
 {
-    UNIN_DPRINTF("write addr " TARGET_FMT_plx " val %"PRIx64"\n", addr, value);
+    trace_mac99_uninorth_write(addr, value);
     if (addr == 0x0) {
         *(int*)opaque = value;
     }
@@ -109,7 +100,7 @@ static uint64_t unin_read(void *opaque, hwaddr addr, unsigned size)
         value = *(int*)opaque;
     }
 
-    UNIN_DPRINTF("readl addr " TARGET_FMT_plx " val %x\n", addr, value);
+    trace_mac99_uninorth_read(addr, value);
 
     return value;
 }
diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index 4fab5c0ae7..09f0d22def 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -381,7 +381,7 @@ static void ppc_powernv_init(MachineState *machine)
 
     fw_size = load_image_targphys(fw_filename, FW_LOAD_ADDR, FW_MAX_SIZE);
     if (fw_size < 0) {
-        error_report("qemu: could not load OPAL '%s'", fw_filename);
+        error_report("Could not load OPAL '%s'", fw_filename);
         exit(1);
     }
     g_free(fw_filename);
@@ -393,7 +393,7 @@ static void ppc_powernv_init(MachineState *machine)
         kernel_size = load_image_targphys(machine->kernel_filename,
                                           KERNEL_LOAD_ADDR, 0x2000000);
         if (kernel_size < 0) {
-            error_report("qemu: could not load kernel'%s'",
+            error_report("Could not load kernel '%s'",
                          machine->kernel_filename);
             exit(1);
         }
@@ -405,7 +405,7 @@ static void ppc_powernv_init(MachineState *machine)
         pnv->initrd_size = load_image_targphys(machine->initrd_filename,
                                   pnv->initrd_base, 0x10000000); /* 128MB max */
         if (pnv->initrd_size < 0) {
-            error_report("qemu: could not load initial ram disk '%s'",
+            error_report("Could not load initial ram disk '%s'",
                          machine->initrd_filename);
             exit(1);
         }
diff --git a/hw/ppc/ppc405_uc.c b/hw/ppc/ppc405_uc.c
index d6d3fc2c4a..d5df94aa6e 100644
--- a/hw/ppc/ppc405_uc.c
+++ b/hw/ppc/ppc405_uc.c
@@ -1881,7 +1881,7 @@ static void ppc405cr_clk_setup (ppc405cr_cpc_t *cpc)
         D1 = (((cpc->pllmr >> 20) - 1) & 0xF) + 1; /* FBDV */
         D2 = 8 - ((cpc->pllmr >> 16) & 0x7); /* FWDVA */
         M = D0 * D1 * D2;
-        VCO_out = cpc->sysclk * M;
+        VCO_out = (uint64_t)cpc->sysclk * M;
         if (VCO_out < 400000000 || VCO_out > 800000000) {
             /* PLL cannot lock */
             cpc->pllmr &= ~0x80000000;
@@ -1892,7 +1892,7 @@ static void ppc405cr_clk_setup (ppc405cr_cpc_t *cpc)
         /* Bypass PLL */
     bypass_pll:
         M = D0;
-        PLL_out = cpc->sysclk * M;
+        PLL_out = (uint64_t)cpc->sysclk * M;
     }
     CPU_clk = PLL_out;
     if (cpc->cr1 & 0x00800000)
@@ -2242,7 +2242,7 @@ static void ppc405ep_compute_clocks (ppc405ep_cpc_t *cpc)
 #ifdef DEBUG_CLOCKS_LL
         printf("FWDA %01" PRIx32 " %d\n", (cpc->pllmr[1] >> 16) & 0x7, D);
 #endif
-        VCO_out = cpc->sysclk * M * D;
+        VCO_out = (uint64_t)cpc->sysclk * M * D;
         if (VCO_out < 500000000UL || VCO_out > 1000000000UL) {
             /* Error - unlock the PLL */
             printf("VCO out of range %" PRIu64 "\n", VCO_out);
diff --git a/hw/ppc/ppc4xx_pci.c b/hw/ppc/ppc4xx_pci.c
index 683218e5c5..dc19682970 100644
--- a/hw/ppc/ppc4xx_pci.c
+++ b/hw/ppc/ppc4xx_pci.c
@@ -26,13 +26,7 @@
 #include "hw/pci/pci.h"
 #include "hw/pci/pci_host.h"
 #include "exec/address-spaces.h"
-
-#undef DEBUG
-#ifdef DEBUG
-#define DPRINTF(fmt, ...) do { printf(fmt, ## __VA_ARGS__); } while (0)
-#else
-#define DPRINTF(fmt, ...)
-#endif /* DEBUG */
+#include "trace.h"
 
 struct PCIMasterMap {
     uint32_t la;
@@ -249,8 +243,7 @@ static int ppc4xx_pci_map_irq(PCIDevice *pci_dev, int irq_num)
 {
     int slot = pci_dev->devfn >> 3;
 
-    DPRINTF("%s: devfn %x irq %d -> %d\n", __func__,
-            pci_dev->devfn, irq_num, slot);
+    trace_ppc4xx_pci_map_irq(pci_dev->devfn, irq_num, slot);
 
     return slot - 1;
 }
@@ -259,7 +252,7 @@ static void ppc4xx_pci_set_irq(void *opaque, int irq_num, int level)
 {
     qemu_irq *pci_irqs = opaque;
 
-    DPRINTF("%s: PCI irq %d\n", __func__, irq_num);
+    trace_ppc4xx_pci_set_irq(irq_num);
     if (irq_num < 0) {
         fprintf(stderr, "%s: PCI irq %d\n", __func__, irq_num);
         return;
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index e465d7ac98..5904e6498f 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -958,7 +958,7 @@ static void *spapr_build_fdt(sPAPRMachineState *spapr,
         _FDT(spapr_drc_populate_dt(fdt, 0, NULL, SPAPR_DR_CONNECTOR_TYPE_LMB));
     }
 
-    if (mc->query_hotpluggable_cpus) {
+    if (mc->has_hotpluggable_cpus) {
         int offset = fdt_path_offset(fdt, "/cpus");
         ret = spapr_drc_populate_dt(fdt, offset, NULL,
                                     SPAPR_DR_CONNECTOR_TYPE_CPU);
@@ -1751,13 +1751,28 @@ static void spapr_validate_node_memory(MachineState *machine, Error **errp)
     }
 }
 
+/* find cpu slot in machine->possible_cpus by core_id */
+static CPUArchId *spapr_find_cpu_slot(MachineState *ms, uint32_t id, int *idx)
+{
+    int index = id / smp_threads;
+
+    if (index >= ms->possible_cpus->len) {
+        return NULL;
+    }
+    if (idx) {
+        *idx = index;
+    }
+    return &ms->possible_cpus->cpus[index];
+}
+
 static void spapr_init_cpus(sPAPRMachineState *spapr)
 {
     MachineState *machine = MACHINE(spapr);
     MachineClass *mc = MACHINE_GET_CLASS(machine);
     char *type = spapr_get_cpu_core_type(machine->cpu_model);
     int smt = kvmppc_smt_threads();
-    int spapr_max_cores, spapr_cores;
+    const CPUArchIdList *possible_cpus;
+    int boot_cores_nr = smp_cpus / smp_threads;
     int i;
 
     if (!type) {
@@ -1765,7 +1780,8 @@ static void spapr_init_cpus(sPAPRMachineState *spapr)
         exit(1);
     }
 
-    if (mc->query_hotpluggable_cpus) {
+    possible_cpus = mc->possible_cpu_arch_ids(machine);
+    if (mc->has_hotpluggable_cpus) {
         if (smp_cpus % smp_threads) {
             error_report("smp_cpus (%u) must be multiple of threads (%u)",
                          smp_cpus, smp_threads);
@@ -1776,24 +1792,18 @@ static void spapr_init_cpus(sPAPRMachineState *spapr)
                          max_cpus, smp_threads);
             exit(1);
         }
-
-        spapr_max_cores = max_cpus / smp_threads;
-        spapr_cores = smp_cpus / smp_threads;
     } else {
         if (max_cpus != smp_cpus) {
             error_report("This machine version does not support CPU hotplug");
             exit(1);
         }
-
-        spapr_max_cores = QEMU_ALIGN_UP(smp_cpus, smp_threads) / smp_threads;
-        spapr_cores = spapr_max_cores;
+        boot_cores_nr = possible_cpus->len;
     }
 
-    spapr->cores = g_new0(Object *, spapr_max_cores);
-    for (i = 0; i < spapr_max_cores; i++) {
+    for (i = 0; i < possible_cpus->len; i++) {
         int core_id = i * smp_threads;
 
-        if (mc->query_hotpluggable_cpus) {
+        if (mc->has_hotpluggable_cpus) {
             sPAPRDRConnector *drc =
                 spapr_dr_connector_new(OBJECT(spapr),
                                        SPAPR_DR_CONNECTOR_TYPE_CPU,
@@ -1802,7 +1812,7 @@ static void spapr_init_cpus(sPAPRMachineState *spapr)
             qemu_register_reset(spapr_drc_reset, drc);
         }
 
-        if (i < spapr_cores) {
+        if (i < boot_cores_nr) {
             Object *core  = object_new(type);
             int nr_threads = smp_threads;
 
@@ -2357,6 +2367,7 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     uint64_t align = memory_region_get_alignment(mr);
     uint64_t size = memory_region_size(mr);
     uint64_t addr;
+    char *mem_dev;
 
     if (size % SPAPR_MEMORY_BLOCK_SIZE) {
         error_setg(&local_err, "Hotplugged memory size must be a multiple of "
@@ -2364,6 +2375,13 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
         goto out;
     }
 
+    mem_dev = object_property_get_str(OBJECT(dimm), PC_DIMM_MEMDEV_PROP, NULL);
+    if (mem_dev && !kvmppc_is_mem_backend_page_size_ok(mem_dev)) {
+        error_setg(&local_err, "Memory backend has bad page size. "
+                   "Use 'memory-backend-file' with correct mem-path.");
+        goto out;
+    }
+
     pc_dimm_memory_plug(dev, &ms->hotplug_memory, mr, align, &local_err);
     if (local_err) {
         goto out;
@@ -2488,6 +2506,165 @@ void *spapr_populate_hotplug_cpu_dt(CPUState *cs, int *fdt_offset,
     return fdt;
 }
 
+static void spapr_core_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
+                              Error **errp)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    CPUCore *cc = CPU_CORE(dev);
+    CPUArchId *core_slot = spapr_find_cpu_slot(ms, cc->core_id, NULL);
+
+    core_slot->cpu = NULL;
+    object_unparent(OBJECT(dev));
+}
+
+static void spapr_core_release(DeviceState *dev, void *opaque)
+{
+    HotplugHandler *hotplug_ctrl;
+
+    hotplug_ctrl = qdev_get_hotplug_handler(dev);
+    hotplug_handler_unplug(hotplug_ctrl, dev, &error_abort);
+}
+
+static
+void spapr_core_unplug_request(HotplugHandler *hotplug_dev, DeviceState *dev,
+                               Error **errp)
+{
+    int index;
+    sPAPRDRConnector *drc;
+    sPAPRDRConnectorClass *drck;
+    Error *local_err = NULL;
+    CPUCore *cc = CPU_CORE(dev);
+    int smt = kvmppc_smt_threads();
+
+    if (!spapr_find_cpu_slot(MACHINE(hotplug_dev), cc->core_id, &index)) {
+        error_setg(errp, "Unable to find CPU core with core-id: %d",
+                   cc->core_id);
+        return;
+    }
+    if (index == 0) {
+        error_setg(errp, "Boot CPU core may not be unplugged");
+        return;
+    }
+
+    drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt);
+    g_assert(drc);
+
+    drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+    drck->detach(drc, dev, spapr_core_release, NULL, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    spapr_hotplug_req_remove_by_index(drc);
+}
+
+static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
+                            Error **errp)
+{
+    sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
+    MachineClass *mc = MACHINE_GET_CLASS(spapr);
+    sPAPRCPUCore *core = SPAPR_CPU_CORE(OBJECT(dev));
+    CPUCore *cc = CPU_CORE(dev);
+    CPUState *cs = CPU(core->threads);
+    sPAPRDRConnector *drc;
+    Error *local_err = NULL;
+    void *fdt = NULL;
+    int fdt_offset = 0;
+    int smt = kvmppc_smt_threads();
+    CPUArchId *core_slot;
+    int index;
+
+    core_slot = spapr_find_cpu_slot(MACHINE(hotplug_dev), cc->core_id, &index);
+    if (!core_slot) {
+        error_setg(errp, "Unable to find CPU core with core-id: %d",
+                   cc->core_id);
+        return;
+    }
+    drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt);
+
+    g_assert(drc || !mc->has_hotpluggable_cpus);
+
+    /*
+     * Setup CPU DT entries only for hotplugged CPUs. For boot time or
+     * coldplugged CPUs DT entries are setup in spapr_build_fdt().
+     */
+    if (dev->hotplugged) {
+        fdt = spapr_populate_hotplug_cpu_dt(cs, &fdt_offset, spapr);
+    }
+
+    if (drc) {
+        sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+        drck->attach(drc, dev, fdt, fdt_offset, !dev->hotplugged, &local_err);
+        if (local_err) {
+            g_free(fdt);
+            error_propagate(errp, local_err);
+            return;
+        }
+    }
+
+    if (dev->hotplugged) {
+        /*
+         * Send hotplug notification interrupt to the guest only in case
+         * of hotplugged CPUs.
+         */
+        spapr_hotplug_req_add_by_index(drc);
+    } else {
+        /*
+         * Set the right DRC states for cold plugged CPU.
+         */
+        if (drc) {
+            sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+            drck->set_allocation_state(drc, SPAPR_DR_ALLOCATION_STATE_USABLE);
+            drck->set_isolation_state(drc, SPAPR_DR_ISOLATION_STATE_UNISOLATED);
+        }
+    }
+    core_slot->cpu = OBJECT(dev);
+}
+
+static void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
+                                Error **errp)
+{
+    MachineState *machine = MACHINE(OBJECT(hotplug_dev));
+    MachineClass *mc = MACHINE_GET_CLASS(hotplug_dev);
+    Error *local_err = NULL;
+    CPUCore *cc = CPU_CORE(dev);
+    char *base_core_type = spapr_get_cpu_core_type(machine->cpu_model);
+    const char *type = object_get_typename(OBJECT(dev));
+    CPUArchId *core_slot;
+    int index;
+
+    if (dev->hotplugged && !mc->has_hotpluggable_cpus) {
+        error_setg(&local_err, "CPU hotplug not supported for this machine");
+        goto out;
+    }
+
+    if (strcmp(base_core_type, type)) {
+        error_setg(&local_err, "CPU core type should be %s", base_core_type);
+        goto out;
+    }
+
+    if (cc->core_id % smp_threads) {
+        error_setg(&local_err, "invalid core id %d", cc->core_id);
+        goto out;
+    }
+
+    core_slot = spapr_find_cpu_slot(MACHINE(hotplug_dev), cc->core_id, &index);
+    if (!core_slot) {
+        error_setg(&local_err, "core id %d out of range", cc->core_id);
+        goto out;
+    }
+
+    if (core_slot->cpu) {
+        error_setg(&local_err, "core %d already populated", cc->core_id);
+        goto out;
+    }
+
+out:
+    g_free(base_core_type);
+    error_propagate(errp, local_err);
+}
+
 static void spapr_machine_device_plug(HotplugHandler *hotplug_dev,
                                       DeviceState *dev, Error **errp)
 {
@@ -2550,7 +2727,7 @@ static void spapr_machine_device_unplug(HotplugHandler *hotplug_dev,
             error_setg(errp, "Memory hot unplug not supported for this guest");
         }
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
-        if (!mc->query_hotpluggable_cpus) {
+        if (!mc->has_hotpluggable_cpus) {
             error_setg(errp, "CPU hot unplug not supported on this machine");
             return;
         }
@@ -2577,11 +2754,11 @@ static void spapr_machine_device_unplug_request(HotplugHandler *hotplug_dev,
             error_setg(errp, "Memory hot unplug not supported for this guest");
         }
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) {
-        if (!mc->query_hotpluggable_cpus) {
+        if (!mc->has_hotpluggable_cpus) {
             error_setg(errp, "CPU hot unplug not supported on this machine");
             return;
         }
-        spapr_core_unplug(hotplug_dev, dev, errp);
+        spapr_core_unplug_request(hotplug_dev, dev, errp);
     }
 }
 
@@ -2610,35 +2787,34 @@ static unsigned spapr_cpu_index_to_socket_id(unsigned cpu_index)
     return cpu_index / smp_threads / smp_cores;
 }
 
-static HotpluggableCPUList *spapr_query_hotpluggable_cpus(MachineState *machine)
+static const CPUArchIdList *spapr_possible_cpu_arch_ids(MachineState *machine)
 {
     int i;
-    HotpluggableCPUList *head = NULL;
-    sPAPRMachineState *spapr = SPAPR_MACHINE(machine);
     int spapr_max_cores = max_cpus / smp_threads;
+    MachineClass *mc = MACHINE_GET_CLASS(machine);
 
-    for (i = 0; i < spapr_max_cores; i++) {
-        HotpluggableCPUList *list_item = g_new0(typeof(*list_item), 1);
-        HotpluggableCPU *cpu_item = g_new0(typeof(*cpu_item), 1);
-        CpuInstanceProperties *cpu_props = g_new0(typeof(*cpu_props), 1);
+    if (!mc->has_hotpluggable_cpus) {
+        spapr_max_cores = QEMU_ALIGN_UP(smp_cpus, smp_threads) / smp_threads;
+    }
+    if (machine->possible_cpus) {
+        assert(machine->possible_cpus->len == spapr_max_cores);
+        return machine->possible_cpus;
+    }
+
+    machine->possible_cpus = g_malloc0(sizeof(CPUArchIdList) +
+                             sizeof(CPUArchId) * spapr_max_cores);
+    machine->possible_cpus->len = spapr_max_cores;
+    for (i = 0; i < machine->possible_cpus->len; i++) {
+        int core_id = i * smp_threads;
 
-        cpu_item->type = spapr_get_cpu_core_type(machine->cpu_model);
-        cpu_item->vcpus_count = smp_threads;
-        cpu_props->has_core_id = true;
-        cpu_props->core_id = i * smp_threads;
+        machine->possible_cpus->cpus[i].vcpus_count = smp_threads;
+        machine->possible_cpus->cpus[i].arch_id = core_id;
+        machine->possible_cpus->cpus[i].props.has_core_id = true;
+        machine->possible_cpus->cpus[i].props.core_id = core_id;
         /* TODO: add 'has_node/node' here to describe
            to which node core belongs */
-
-        cpu_item->props = cpu_props;
-        if (spapr->cores[i]) {
-            cpu_item->has_qom_path = true;
-            cpu_item->qom_path = object_get_canonical_path(spapr->cores[i]);
-        }
-        list_item->value = cpu_item;
-        list_item->next = head;
-        head = list_item;
     }
-    return head;
+    return machine->possible_cpus;
 }
 
 static void spapr_phb_placement(sPAPRMachineState *spapr, uint32_t index,
@@ -2724,11 +2900,12 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
     hc->plug = spapr_machine_device_plug;
     hc->unplug = spapr_machine_device_unplug;
     mc->cpu_index_to_socket_id = spapr_cpu_index_to_socket_id;
+    mc->possible_cpu_arch_ids = spapr_possible_cpu_arch_ids;
     hc->unplug_request = spapr_machine_device_unplug_request;
 
     smc->dr_lmb_enabled = true;
     smc->tcg_default_cpu = "POWER8";
-    mc->query_hotpluggable_cpus = spapr_query_hotpluggable_cpus;
+    mc->has_hotpluggable_cpus = true;
     fwc->get_dev_path = spapr_get_fw_dev_path;
     nc->nmi_monitor_handler = spapr_nmi;
     smc->phb_placement = spapr_phb_placement;
@@ -2928,7 +3105,7 @@ static void spapr_machine_2_6_instance_options(MachineState *machine)
 static void spapr_machine_2_6_class_options(MachineClass *mc)
 {
     spapr_machine_2_7_class_options(mc);
-    mc->query_hotpluggable_cpus = NULL;
+    mc->has_hotpluggable_cpus = false;
     SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_2_6);
 }
 
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index 9dddaeb3fa..55cd0456eb 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -109,13 +109,12 @@ char *spapr_get_cpu_core_type(const char *model)
     return core_type;
 }
 
-static void spapr_core_release(DeviceState *dev, void *opaque)
+static void spapr_cpu_core_unrealizefn(DeviceState *dev, Error **errp)
 {
     sPAPRCPUCore *sc = SPAPR_CPU_CORE(OBJECT(dev));
     sPAPRCPUCoreClass *scc = SPAPR_CPU_CORE_GET_CLASS(OBJECT(dev));
     const char *typename = object_class_get_name(scc->cpu_class);
     size_t size = object_type_get_instance_size(typename);
-    sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
     CPUCore *cc = CPU_CORE(dev);
     int i;
 
@@ -129,140 +128,7 @@ static void spapr_core_release(DeviceState *dev, void *opaque)
         cpu_remove_sync(cs);
         object_unparent(obj);
     }
-
-    spapr->cores[cc->core_id / smp_threads] = NULL;
-
     g_free(sc->threads);
-    object_unparent(OBJECT(dev));
-}
-
-void spapr_core_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                       Error **errp)
-{
-    CPUCore *cc = CPU_CORE(dev);
-    int smt = kvmppc_smt_threads();
-    int index = cc->core_id / smp_threads;
-    sPAPRDRConnector *drc =
-        spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt);
-    sPAPRDRConnectorClass *drck;
-    Error *local_err = NULL;
-
-    if (index == 0) {
-        error_setg(errp, "Boot CPU core may not be unplugged");
-        return;
-    }
-
-    g_assert(drc);
-
-    drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
-    drck->detach(drc, dev, spapr_core_release, NULL, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    spapr_hotplug_req_remove_by_index(drc);
-}
-
-void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                     Error **errp)
-{
-    sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
-    MachineClass *mc = MACHINE_GET_CLASS(spapr);
-    sPAPRCPUCore *core = SPAPR_CPU_CORE(OBJECT(dev));
-    CPUCore *cc = CPU_CORE(dev);
-    CPUState *cs = CPU(core->threads);
-    sPAPRDRConnector *drc;
-    Error *local_err = NULL;
-    void *fdt = NULL;
-    int fdt_offset = 0;
-    int index = cc->core_id / smp_threads;
-    int smt = kvmppc_smt_threads();
-
-    drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt);
-    spapr->cores[index] = OBJECT(dev);
-
-    g_assert(drc || !mc->query_hotpluggable_cpus);
-
-    /*
-     * Setup CPU DT entries only for hotplugged CPUs. For boot time or
-     * coldplugged CPUs DT entries are setup in spapr_build_fdt().
-     */
-    if (dev->hotplugged) {
-        fdt = spapr_populate_hotplug_cpu_dt(cs, &fdt_offset, spapr);
-    }
-
-    if (drc) {
-        sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
-        drck->attach(drc, dev, fdt, fdt_offset, !dev->hotplugged, &local_err);
-        if (local_err) {
-            g_free(fdt);
-            spapr->cores[index] = NULL;
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-    if (dev->hotplugged) {
-        /*
-         * Send hotplug notification interrupt to the guest only in case
-         * of hotplugged CPUs.
-         */
-        spapr_hotplug_req_add_by_index(drc);
-    } else {
-        /*
-         * Set the right DRC states for cold plugged CPU.
-         */
-        if (drc) {
-            sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
-            drck->set_allocation_state(drc, SPAPR_DR_ALLOCATION_STATE_USABLE);
-            drck->set_isolation_state(drc, SPAPR_DR_ISOLATION_STATE_UNISOLATED);
-        }
-    }
-}
-
-void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                         Error **errp)
-{
-    MachineState *machine = MACHINE(OBJECT(hotplug_dev));
-    MachineClass *mc = MACHINE_GET_CLASS(hotplug_dev);
-    sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev));
-    int spapr_max_cores = max_cpus / smp_threads;
-    int index;
-    Error *local_err = NULL;
-    CPUCore *cc = CPU_CORE(dev);
-    char *base_core_type = spapr_get_cpu_core_type(machine->cpu_model);
-    const char *type = object_get_typename(OBJECT(dev));
-
-    if (dev->hotplugged && !mc->query_hotpluggable_cpus) {
-        error_setg(&local_err, "CPU hotplug not supported for this machine");
-        goto out;
-    }
-
-    if (strcmp(base_core_type, type)) {
-        error_setg(&local_err, "CPU core type should be %s", base_core_type);
-        goto out;
-    }
-
-    if (cc->core_id % smp_threads) {
-        error_setg(&local_err, "invalid core id %d", cc->core_id);
-        goto out;
-    }
-
-    index = cc->core_id / smp_threads;
-    if (index < 0 || index >= spapr_max_cores) {
-        error_setg(&local_err, "core id %d out of range", cc->core_id);
-        goto out;
-    }
-
-    if (spapr->cores[index]) {
-        error_setg(&local_err, "core %d already populated", cc->core_id);
-        goto out;
-    }
-
-out:
-    g_free(base_core_type);
-    error_propagate(errp, local_err);
 }
 
 static void spapr_cpu_core_realize_child(Object *child, Error **errp)
@@ -368,6 +234,7 @@ void spapr_cpu_core_class_init(ObjectClass *oc, void *data)
     sPAPRCPUCoreClass *scc = SPAPR_CPU_CORE_CLASS(oc);
 
     dc->realize = spapr_cpu_core_realize;
+    dc->unrealize = spapr_cpu_core_unrealizefn;
     scc->cpu_class = cpu_class_by_name(TYPE_POWERPC_CPU, data);
     g_assert(scc->cpu_class);
 }
diff --git a/hw/ppc/spapr_ovec.c b/hw/ppc/spapr_ovec.c
index 3eb1d5976f..41df4c35ba 100644
--- a/hw/ppc/spapr_ovec.c
+++ b/hw/ppc/spapr_ovec.c
@@ -16,18 +16,9 @@
 #include "qemu/bitmap.h"
 #include "exec/address-spaces.h"
 #include "qemu/error-report.h"
+#include "trace.h"
 #include <libfdt.h>
 
-/* #define DEBUG_SPAPR_OVEC */
-
-#ifdef DEBUG_SPAPR_OVEC
-#define DPRINTFN(fmt, ...) \
-    do { fprintf(stderr, fmt "\n", ## __VA_ARGS__); } while (0)
-#else
-#define DPRINTFN(fmt, ...) \
-    do { } while (0)
-#endif
-
 #define OV_MAXBYTES 256 /* not including length byte */
 #define OV_MAXBITS (OV_MAXBYTES * BITS_PER_BYTE)
 
@@ -210,8 +201,7 @@ sPAPROptionVector *spapr_ovec_parse_vector(target_ulong table_addr, int vector)
     for (i = 0; i < vector_len; i++) {
         uint8_t entry = ldub_phys(&address_space_memory, addr + i);
         if (entry) {
-            DPRINTFN("read guest vector %2d, byte %3d / %3d: 0x%.2x",
-                     vector, i + 1, vector_len, entry);
+            trace_spapr_ovec_parse_vector(vector, i + 1, vector_len, entry);
             guest_byte_to_bitmap(entry, ov->bitmap, i * BITS_PER_BYTE);
         }
     }
@@ -245,10 +235,9 @@ int spapr_ovec_populate_dt(void *fdt, int fdt_offset,
     for (i = 1; i < vec_len + 1; i++) {
         vec[i] = guest_byte_from_bitmap(ov->bitmap, (i - 1) * BITS_PER_BYTE);
         if (vec[i]) {
-            DPRINTFN("encoding guest vector byte %3d / %3d: 0x%.2x",
-                     i, vec_len, vec[i]);
+            trace_spapr_ovec_populate_dt(i, vec_len, vec[i]);
         }
     }
 
-    return fdt_setprop(fdt, fdt_offset, name, vec, vec_len);
+    return fdt_setprop(fdt, fdt_offset, name, vec, vec_len + 1);
 }
diff --git a/hw/ppc/trace-events b/hw/ppc/trace-events
index f46995cdb2..43d265f351 100644
--- a/hw/ppc/trace-events
+++ b/hw/ppc/trace-events
@@ -56,6 +56,10 @@ spapr_drc_realize_child(uint32_t index, char *childname) "drc: 0x%"PRIx32", chil
 spapr_drc_realize_complete(uint32_t index) "drc: 0x%"PRIx32
 spapr_drc_unrealize(uint32_t index) "drc: 0x%"PRIx32
 
+# hw/ppc/spapr_ovec.c
+spapr_ovec_parse_vector(int vector, int byte, uint16_t vec_len, uint8_t entry) "read guest vector %2d, byte %3d / %3d: 0x%.2x"
+spapr_ovec_populate_dt(int byte, uint16_t vec_len, uint8_t entry) "encoding guest vector byte %3d / %3d: 0x%.2x"
+
 # hw/ppc/spapr_rtas.c
 spapr_rtas_set_indicator_invalid(uint32_t index) "sensor index: 0x%"PRIx32
 spapr_rtas_set_indicator_not_supported(uint32_t index, uint32_t type) "sensor index: 0x%"PRIx32", type: %"PRIu32
@@ -85,3 +89,11 @@ rs6000mc_presence_read(uint32_t addr, uint32_t val) "read addr=%x val=%x"
 rs6000mc_size_read(uint32_t addr, uint32_t val) "read addr=%x val=%x"
 rs6000mc_size_write(uint32_t addr, uint32_t val) "write addr=%x val=%x"
 rs6000mc_parity_read(uint32_t addr, uint32_t val) "read addr=%x val=%x"
+
+# hw/ppc/mac_newworld.c
+mac99_uninorth_write(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64
+mac99_uninorth_read(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64
+
+# hw/ppc/ppc4xx_pci.c
+ppc4xx_pci_map_irq(int32_t devfn, int irq_num, int slot) "devfn %x irq %d -> %d"
+ppc4xx_pci_set_irq(int irq_num) "PCI irq %d"
diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h
index 842ec6b22a..f1288efa87 100644
--- a/include/fpu/softfloat.h
+++ b/include/fpu/softfloat.h
@@ -180,6 +180,8 @@ enum {
     float_round_up           = 2,
     float_round_to_zero      = 3,
     float_round_ties_away    = 4,
+    /* Not an IEEE rounding mode: round to the closest odd mantissa value */
+    float_round_to_odd       = 5,
 };
 
 /*----------------------------------------------------------------------------
@@ -712,6 +714,9 @@ int32_t float128_to_int32(float128, float_status *status);
 int32_t float128_to_int32_round_to_zero(float128, float_status *status);
 int64_t float128_to_int64(float128, float_status *status);
 int64_t float128_to_int64_round_to_zero(float128, float_status *status);
+uint64_t float128_to_uint64(float128, float_status *status);
+uint64_t float128_to_uint64_round_to_zero(float128, float_status *status);
+uint32_t float128_to_uint32_round_to_zero(float128, float_status *status);
 float32 float128_to_float32(float128, float_status *status);
 float64 float128_to_float64(float128, float_status *status);
 floatx80 float128_to_floatx80(float128, float_status *status);
diff --git a/include/hw/boards.h b/include/hw/boards.h
index ac891a828b..269d0ba399 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -41,15 +41,20 @@ int machine_phandle_start(MachineState *machine);
 bool machine_dump_guest_core(MachineState *machine);
 bool machine_mem_merge(MachineState *machine);
 void machine_register_compat_props(MachineState *machine);
+HotpluggableCPUList *machine_query_hotpluggable_cpus(MachineState *machine);
 
 /**
  * CPUArchId:
  * @arch_id - architecture-dependent CPU ID of present or possible CPU
  * @cpu - pointer to corresponding CPU object if it's present on NULL otherwise
+ * @props - CPU object properties, initialized by board
+ * #vcpus_count - number of threads provided by @cpu object
  */
 typedef struct {
     uint64_t arch_id;
-    struct CPUState *cpu;
+    int64_t vcpus_count;
+    CpuInstanceProperties props;
+    Object *cpu;
 } CPUArchId;
 
 /**
@@ -82,10 +87,8 @@ typedef struct {
  *    Returns an array of @CPUArchId architecture-dependent CPU IDs
  *    which includes CPU IDs for present and possible to hotplug CPUs.
  *    Caller is responsible for freeing returned list.
- * @query_hotpluggable_cpus:
- *    Returns a @HotpluggableCPUList, which describes CPUs objects which
- *    could be added with -device/device_add.
- *    Caller is responsible for freeing returned list.
+ * @has_hotpluggable_cpus:
+ *    If true, board supports CPUs creation with -device/device_add.
  * @minimum_page_bits:
  *    If non-zero, the board promises never to create a CPU with a page size
  *    smaller than this, so QEMU can use a more efficient larger page
@@ -131,12 +134,12 @@ struct MachineClass {
     bool option_rom_has_mr;
     bool rom_file_has_mr;
     int minimum_page_bits;
+    bool has_hotpluggable_cpus;
 
     HotplugHandler *(*get_hotplug_handler)(MachineState *machine,
                                            DeviceState *dev);
     unsigned (*cpu_index_to_socket_id)(unsigned cpu_index);
     const CPUArchIdList *(*possible_cpu_arch_ids)(MachineState *machine);
-    HotpluggableCPUList *(*query_hotpluggable_cpus)(MachineState *machine);
 };
 
 /**
@@ -178,6 +181,7 @@ struct MachineState {
     char *initrd_filename;
     const char *cpu_model;
     AccelState *accelerator;
+    CPUArchIdList *possible_cpus;
 };
 
 #define DEFINE_MACHINE(namestr, machine_initfn) \
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 079e8d9393..d1f45540a1 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -73,7 +73,6 @@ struct PCMachineState {
     /* CPU and apic information: */
     bool apic_xrupt_override;
     unsigned apic_id_limit;
-    CPUArchIdList *possible_cpus;
     uint16_t boot_cpus;
 
     /* NUMA information: */
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index a2d8964f7e..f9b17d860a 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -94,7 +94,6 @@ struct sPAPRMachineState {
     /*< public >*/
     char *kvm_type;
     MemoryHotplugState hotplug_memory;
-    Object **cores;
 };
 
 #define H_SUCCESS         0
diff --git a/include/hw/ppc/spapr_cpu_core.h b/include/hw/ppc/spapr_cpu_core.h
index 50292f48b1..3c35665221 100644
--- a/include/hw/ppc/spapr_cpu_core.h
+++ b/include/hw/ppc/spapr_cpu_core.h
@@ -34,12 +34,6 @@ typedef struct sPAPRCPUCoreClass {
     ObjectClass *cpu_class;
 } sPAPRCPUCoreClass;
 
-void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                         Error **errp);
 char *spapr_get_cpu_core_type(const char *model);
-void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                     Error **errp);
-void spapr_core_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                       Error **errp);
 void spapr_cpu_core_class_init(ObjectClass *oc, void *data);
 #endif
diff --git a/linux-user/main.c b/linux-user/main.c
index 4fd49ce6b6..9645122aa6 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -1712,10 +1712,12 @@ void cpu_loop(CPUPPCState *env)
              * in syscalls.
              */
             env->crf[0] &= ~0x1;
+            env->nip += 4;
             ret = do_syscall(env, env->gpr[0], env->gpr[3], env->gpr[4],
                              env->gpr[5], env->gpr[6], env->gpr[7],
                              env->gpr[8], 0, 0);
             if (ret == -TARGET_ERESTARTSYS) {
+                env->nip -= 4;
                 break;
             }
             if (ret == (target_ulong)(-TARGET_QEMU_ESIGRETURN)) {
@@ -1723,7 +1725,6 @@ void cpu_loop(CPUPPCState *env)
                    Avoid corrupting register state.  */
                 break;
             }
-            env->nip += 4;
             if (ret > (target_ulong)(-515)) {
                 env->crf[0] |= 0x1;
                 ret = -ret;
diff --git a/monitor.c b/monitor.c
index 5953fc984f..ead4c633fb 100644
--- a/monitor.c
+++ b/monitor.c
@@ -4181,10 +4181,10 @@ HotpluggableCPUList *qmp_query_hotpluggable_cpus(Error **errp)
     MachineState *ms = MACHINE(qdev_get_machine());
     MachineClass *mc = MACHINE_GET_CLASS(ms);
 
-    if (!mc->query_hotpluggable_cpus) {
+    if (!mc->has_hotpluggable_cpus) {
         error_setg(errp, QERR_FEATURE_DISABLED, "query-hotpluggable-cpus");
         return NULL;
     }
 
-    return mc->query_hotpluggable_cpus(ms);
+    return machine_query_hotpluggable_cpus(ms);
 }
diff --git a/target/ppc/cpu-qom.h b/target/ppc/cpu-qom.h
index b7977bad18..4e3132b56b 100644
--- a/target/ppc/cpu-qom.h
+++ b/target/ppc/cpu-qom.h
@@ -86,10 +86,13 @@ enum powerpc_mmu_t {
     POWERPC_MMU_2_07       = POWERPC_MMU_64 | POWERPC_MMU_1TSEG
                              | POWERPC_MMU_64K
                              | POWERPC_MMU_AMR | 0x00000004,
-    /* FIXME Add POWERPC_MMU_3_OO defines */
     /* Architecture 2.07 "degraded" (no 1T segments)           */
     POWERPC_MMU_2_07a      = POWERPC_MMU_64 | POWERPC_MMU_AMR
                              | 0x00000004,
+    /* Architecture 3.00 variant                               */
+    POWERPC_MMU_3_00       = POWERPC_MMU_64 | POWERPC_MMU_1TSEG
+                             | POWERPC_MMU_64K
+                             | POWERPC_MMU_AMR | 0x00000005,
 };
 
 /*****************************************************************************/
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index bc2a2ce431..425e79d52d 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -381,15 +381,22 @@ struct ppc_slb_t {
 #define LPCR_ISL          (1ull << (63 - 2))
 #define LPCR_KBV          (1ull << (63 - 3))
 #define LPCR_DPFD_SHIFT   (63 - 11)
-#define LPCR_DPFD         (0x3ull << LPCR_DPFD_SHIFT)
+#define LPCR_DPFD         (0x7ull << LPCR_DPFD_SHIFT)
 #define LPCR_VRMASD_SHIFT (63 - 16)
 #define LPCR_VRMASD       (0x1full << LPCR_VRMASD_SHIFT)
+/* P9: Power-saving mode Exit Cause Enable (Upper Section) Mask */
+#define LPCR_PECE_U_SHIFT (63 - 19)
+#define LPCR_PECE_U_MASK  (0x7ull << LPCR_PECE_U_SHIFT)
+#define LPCR_HVEE         (1ull << (63 - 17)) /* Hypervisor Virt Exit Enable */
 #define LPCR_RMLS_SHIFT   (63 - 37)
 #define LPCR_RMLS         (0xfull << LPCR_RMLS_SHIFT)
 #define LPCR_ILE          (1ull << (63 - 38))
 #define LPCR_AIL_SHIFT    (63 - 40)      /* Alternate interrupt location */
 #define LPCR_AIL          (3ull << LPCR_AIL_SHIFT)
+#define LPCR_UPRT         (1ull << (63 - 41)) /* Use Process Table */
+#define LPCR_EVIRT        (1ull << (63 - 42)) /* Enhanced Virtualisation */
 #define LPCR_ONL          (1ull << (63 - 45))
+#define LPCR_LD           (1ull << (63 - 46)) /* Large Decrementer */
 #define LPCR_P7_PECE0     (1ull << (63 - 49))
 #define LPCR_P7_PECE1     (1ull << (63 - 50))
 #define LPCR_P7_PECE2     (1ull << (63 - 51))
@@ -398,11 +405,22 @@ struct ppc_slb_t {
 #define LPCR_P8_PECE2     (1ull << (63 - 49))
 #define LPCR_P8_PECE3     (1ull << (63 - 50))
 #define LPCR_P8_PECE4     (1ull << (63 - 51))
+/* P9: Power-saving mode Exit Cause Enable (Lower Section) Mask */
+#define LPCR_PECE_L_SHIFT (63 - 51)
+#define LPCR_PECE_L_MASK  (0x1full << LPCR_PECE_L_SHIFT)
+#define LPCR_PDEE         (1ull << (63 - 47)) /* Privileged Doorbell Exit EN */
+#define LPCR_HDEE         (1ull << (63 - 48)) /* Hyperv Doorbell Exit Enable */
+#define LPCR_EEE          (1ull << (63 - 49)) /* External Exit Enable        */
+#define LPCR_DEE          (1ull << (63 - 50)) /* Decrementer Exit Enable     */
+#define LPCR_OEE          (1ull << (63 - 51)) /* Other Exit Enable           */
 #define LPCR_MER          (1ull << (63 - 52))
+#define LPCR_GTSE         (1ull << (63 - 53)) /* Guest Translation Shootdown */
 #define LPCR_TC           (1ull << (63 - 54))
+#define LPCR_HEIC         (1ull << (63 - 59)) /* HV Extern Interrupt Control */
 #define LPCR_LPES0        (1ull << (63 - 60))
 #define LPCR_LPES1        (1ull << (63 - 61))
 #define LPCR_RMI          (1ull << (63 - 62))
+#define LPCR_HVICE        (1ull << (63 - 62)) /* HV Virtualisation Int Enable */
 #define LPCR_HDICE        (1ull << (63 - 63))
 
 #define msr_sf   ((env->msr >> MSR_SF)   & 1)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 9f5cafd5ba..58aee640c3 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -1850,12 +1850,11 @@ void helper_xsaddqp(CPUPPCState *env, uint32_t opcode)
     getVSR(rD(opcode) + 32, &xt, env);
     helper_reset_fpstatus(env);
 
+    tstat = env->fp_status;
     if (unlikely(Rc(opcode) != 0)) {
-        /* TODO: Support xsadddpo after round-to-odd is implemented */
-        abort();
+        tstat.float_rounding_mode = float_round_to_odd;
     }
 
-    tstat = env->fp_status;
     set_float_exception_flags(0, &tstat);
     xt.f128 = float128_add(xa.f128, xb.f128, &tstat);
     env->fp_status.float_exception_flags |= tstat.float_exception_flags;
@@ -1930,19 +1929,18 @@ VSX_MUL(xvmulsp, 4, float32, VsrW(i), 0, 0)
 void helper_xsmulqp(CPUPPCState *env, uint32_t opcode)
 {
     ppc_vsr_t xt, xa, xb;
+    float_status tstat;
 
     getVSR(rA(opcode) + 32, &xa, env);
     getVSR(rB(opcode) + 32, &xb, env);
     getVSR(rD(opcode) + 32, &xt, env);
 
+    helper_reset_fpstatus(env);
+    tstat = env->fp_status;
     if (unlikely(Rc(opcode) != 0)) {
-        /* TODO: Support xsmulpo after round-to-odd is implemented */
-        abort();
+        tstat.float_rounding_mode = float_round_to_odd;
     }
 
-    helper_reset_fpstatus(env);
-
-    float_status tstat = env->fp_status;
     set_float_exception_flags(0, &tstat);
     xt.f128 = float128_mul(xa.f128, xb.f128, &tstat);
     env->fp_status.float_exception_flags |= tstat.float_exception_flags;
@@ -2019,18 +2017,18 @@ VSX_DIV(xvdivsp, 4, float32, VsrW(i), 0, 0)
 void helper_xsdivqp(CPUPPCState *env, uint32_t opcode)
 {
     ppc_vsr_t xt, xa, xb;
+    float_status tstat;
 
     getVSR(rA(opcode) + 32, &xa, env);
     getVSR(rB(opcode) + 32, &xb, env);
     getVSR(rD(opcode) + 32, &xt, env);
 
+    helper_reset_fpstatus(env);
+    tstat = env->fp_status;
     if (unlikely(Rc(opcode) != 0)) {
-        /* TODO: Support xsdivqpo after round-to-odd is implemented */
-        abort();
+        tstat.float_rounding_mode = float_round_to_odd;
     }
 
-    helper_reset_fpstatus(env);
-    float_status tstat = env->fp_status;
     set_float_exception_flags(0, &tstat);
     xt.f128 = float128_div(xa.f128, xb.f128, &tstat);
     env->fp_status.float_exception_flags |= tstat.float_exception_flags;
@@ -2679,6 +2677,99 @@ VSX_MAX_MIN(xsmindp, minnum, 1, float64, VsrD(0))
 VSX_MAX_MIN(xvmindp, minnum, 2, float64, VsrD(i))
 VSX_MAX_MIN(xvminsp, minnum, 4, float32, VsrW(i))
 
+#define VSX_MAX_MINC(name, max)                                               \
+void helper_##name(CPUPPCState *env, uint32_t opcode)                         \
+{                                                                             \
+    ppc_vsr_t xt, xa, xb;                                                     \
+    bool vxsnan_flag = false, vex_flag = false;                               \
+                                                                              \
+    getVSR(rA(opcode) + 32, &xa, env);                                        \
+    getVSR(rB(opcode) + 32, &xb, env);                                        \
+    getVSR(rD(opcode) + 32, &xt, env);                                        \
+                                                                              \
+    if (unlikely(float64_is_any_nan(xa.VsrD(0)) ||                            \
+                 float64_is_any_nan(xb.VsrD(0)))) {                           \
+        if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status) ||          \
+            float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) {          \
+            vxsnan_flag = true;                                               \
+        }                                                                     \
+        xt.VsrD(0) = xb.VsrD(0);                                              \
+    } else if ((max &&                                                        \
+               !float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) ||       \
+               (!max &&                                                       \
+               float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status))) {        \
+        xt.VsrD(0) = xa.VsrD(0);                                              \
+    } else {                                                                  \
+        xt.VsrD(0) = xb.VsrD(0);                                              \
+    }                                                                         \
+                                                                              \
+    vex_flag = fpscr_ve & vxsnan_flag;                                        \
+    if (vxsnan_flag) {                                                        \
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);            \
+    }                                                                         \
+    if (!vex_flag) {                                                          \
+        putVSR(rD(opcode) + 32, &xt, env);                                    \
+    }                                                                         \
+}                                                                             \
+
+VSX_MAX_MINC(xsmaxcdp, 1);
+VSX_MAX_MINC(xsmincdp, 0);
+
+#define VSX_MAX_MINJ(name, max)                                               \
+void helper_##name(CPUPPCState *env, uint32_t opcode)                         \
+{                                                                             \
+    ppc_vsr_t xt, xa, xb;                                                     \
+    bool vxsnan_flag = false, vex_flag = false;                               \
+                                                                              \
+    getVSR(rA(opcode) + 32, &xa, env);                                        \
+    getVSR(rB(opcode) + 32, &xb, env);                                        \
+    getVSR(rD(opcode) + 32, &xt, env);                                        \
+                                                                              \
+    if (unlikely(float64_is_any_nan(xa.VsrD(0)))) {                           \
+        if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status)) {          \
+            vxsnan_flag = true;                                               \
+        }                                                                     \
+        xt.VsrD(0) = xa.VsrD(0);                                              \
+    } else if (unlikely(float64_is_any_nan(xb.VsrD(0)))) {                    \
+        if (float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) {          \
+            vxsnan_flag = true;                                               \
+        }                                                                     \
+        xt.VsrD(0) = xb.VsrD(0);                                              \
+    } else if (float64_is_zero(xa.VsrD(0)) && float64_is_zero(xb.VsrD(0))) {  \
+        if (max) {                                                            \
+            if (!float64_is_neg(xa.VsrD(0)) || !float64_is_neg(xb.VsrD(0))) { \
+                xt.VsrD(0) = 0ULL;                                            \
+            } else {                                                          \
+                xt.VsrD(0) = 0x8000000000000000ULL;                           \
+            }                                                                 \
+        } else {                                                              \
+            if (float64_is_neg(xa.VsrD(0)) || float64_is_neg(xb.VsrD(0))) {   \
+                xt.VsrD(0) = 0x8000000000000000ULL;                           \
+            } else {                                                          \
+                xt.VsrD(0) = 0ULL;                                            \
+            }                                                                 \
+        }                                                                     \
+    } else if ((max &&                                                        \
+               !float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) ||       \
+               (!max &&                                                       \
+               float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status))) {        \
+        xt.VsrD(0) = xa.VsrD(0);                                              \
+    } else {                                                                  \
+        xt.VsrD(0) = xb.VsrD(0);                                              \
+    }                                                                         \
+                                                                              \
+    vex_flag = fpscr_ve & vxsnan_flag;                                        \
+    if (vxsnan_flag) {                                                        \
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);            \
+    }                                                                         \
+    if (!vex_flag) {                                                          \
+        putVSR(rD(opcode) + 32, &xt, env);                                    \
+    }                                                                         \
+}                                                                             \
+
+VSX_MAX_MINJ(xsmaxjdp, 1);
+VSX_MAX_MINJ(xsminjdp, 0);
+
 /* VSX_CMP - VSX floating point compare
  *   op    - instruction mnemonic
  *   nels  - number of elements (1, 2 or 4)
@@ -2861,18 +2952,20 @@ VSX_CVT_FP_TO_FP_HP(xvcvhpsp, 4, float16, float32, VsrH(2 * i + 1), VsrW(i), 0)
 void helper_xscvqpdp(CPUPPCState *env, uint32_t opcode)
 {
     ppc_vsr_t xt, xb;
+    float_status tstat;
 
     getVSR(rB(opcode) + 32, &xb, env);
     memset(&xt, 0, sizeof(xt));
 
+    tstat = env->fp_status;
     if (unlikely(Rc(opcode) != 0)) {
-        /* TODO: Support xscvqpdpo after round-to-odd is implemented */
-        abort();
+        tstat.float_rounding_mode = float_round_to_odd;
     }
 
-    xt.VsrD(0) = float128_to_float64(xb.f128, &env->fp_status);
+    xt.VsrD(0) = float128_to_float64(xb.f128, &tstat);
+    env->fp_status.float_exception_flags |= tstat.float_exception_flags;
     if (unlikely(float128_is_signaling_nan(xb.f128,
-                                           &env->fp_status))) {
+                                           &tstat))) {
         float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);
         xt.VsrD(0) = float64_snan_to_qnan(xt.VsrD(0));
     }
@@ -2993,6 +3086,8 @@ VSX_CVT_FP_TO_INT_VECTOR(xscvqpsdz, float128, int64, f128, VsrD(0),          \
 
 VSX_CVT_FP_TO_INT_VECTOR(xscvqpswz, float128, int32, f128, VsrD(0),          \
                   0xffffffff80000000ULL)
+VSX_CVT_FP_TO_INT_VECTOR(xscvqpudz, float128, uint64, f128, VsrD(0), 0x0ULL)
+VSX_CVT_FP_TO_INT_VECTOR(xscvqpuwz, float128, uint32, f128, VsrD(0), 0x0ULL)
 
 /* VSX_CVT_INT_TO_FP - VSX integer to floating point conversion
  *   op    - instruction mnemonic
@@ -3277,3 +3372,188 @@ void helper_xststdcsp(CPUPPCState *env, uint32_t opcode)
     env->fpscr |= cc << FPSCR_FPRF;
     env->crf[BF(opcode)] = cc;
 }
+
+void helper_xsrqpi(CPUPPCState *env, uint32_t opcode)
+{
+    ppc_vsr_t xb;
+    ppc_vsr_t xt;
+    uint8_t r = Rrm(opcode);
+    uint8_t ex = Rc(opcode);
+    uint8_t rmc = RMC(opcode);
+    uint8_t rmode = 0;
+    float_status tstat;
+
+    getVSR(rB(opcode) + 32, &xb, env);
+    memset(&xt, 0, sizeof(xt));
+    helper_reset_fpstatus(env);
+
+    if (r == 0 && rmc == 0) {
+        rmode = float_round_ties_away;
+    } else if (r == 0 && rmc == 0x3) {
+        rmode = fpscr_rn;
+    } else if (r == 1) {
+        switch (rmc) {
+        case 0:
+            rmode = float_round_nearest_even;
+            break;
+        case 1:
+            rmode = float_round_to_zero;
+            break;
+        case 2:
+            rmode = float_round_up;
+            break;
+        case 3:
+            rmode = float_round_down;
+            break;
+        default:
+            abort();
+        }
+    }
+
+    tstat = env->fp_status;
+    set_float_exception_flags(0, &tstat);
+    set_float_rounding_mode(rmode, &tstat);
+    xt.f128 = float128_round_to_int(xb.f128, &tstat);
+    env->fp_status.float_exception_flags |= tstat.float_exception_flags;
+
+    if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
+        if (float128_is_signaling_nan(xb.f128, &tstat)) {
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);
+            xt.f128 = float128_snan_to_qnan(xt.f128);
+        }
+    }
+
+    if (ex == 0 && (tstat.float_exception_flags & float_flag_inexact)) {
+        env->fp_status.float_exception_flags &= ~float_flag_inexact;
+    }
+
+    helper_compute_fprf_float128(env, xt.f128);
+    float_check_status(env);
+    putVSR(rD(opcode) + 32, &xt, env);
+}
+
+void helper_xsrqpxp(CPUPPCState *env, uint32_t opcode)
+{
+    ppc_vsr_t xb;
+    ppc_vsr_t xt;
+    uint8_t r = Rrm(opcode);
+    uint8_t rmc = RMC(opcode);
+    uint8_t rmode = 0;
+    floatx80 round_res;
+    float_status tstat;
+
+    getVSR(rB(opcode) + 32, &xb, env);
+    memset(&xt, 0, sizeof(xt));
+    helper_reset_fpstatus(env);
+
+    if (r == 0 && rmc == 0) {
+        rmode = float_round_ties_away;
+    } else if (r == 0 && rmc == 0x3) {
+        rmode = fpscr_rn;
+    } else if (r == 1) {
+        switch (rmc) {
+        case 0:
+            rmode = float_round_nearest_even;
+            break;
+        case 1:
+            rmode = float_round_to_zero;
+            break;
+        case 2:
+            rmode = float_round_up;
+            break;
+        case 3:
+            rmode = float_round_down;
+            break;
+        default:
+            abort();
+        }
+    }
+
+    tstat = env->fp_status;
+    set_float_exception_flags(0, &tstat);
+    set_float_rounding_mode(rmode, &tstat);
+    round_res = float128_to_floatx80(xb.f128, &tstat);
+    xt.f128 = floatx80_to_float128(round_res, &tstat);
+    env->fp_status.float_exception_flags |= tstat.float_exception_flags;
+
+    if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
+        if (float128_is_signaling_nan(xb.f128, &tstat)) {
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);
+            xt.f128 = float128_snan_to_qnan(xt.f128);
+        }
+    }
+
+    helper_compute_fprf_float128(env, xt.f128);
+    putVSR(rD(opcode) + 32, &xt, env);
+    float_check_status(env);
+}
+
+void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode)
+{
+    ppc_vsr_t xb;
+    ppc_vsr_t xt;
+    float_status tstat;
+
+    getVSR(rB(opcode) + 32, &xb, env);
+    memset(&xt, 0, sizeof(xt));
+    helper_reset_fpstatus(env);
+
+    tstat = env->fp_status;
+    if (unlikely(Rc(opcode) != 0)) {
+        tstat.float_rounding_mode = float_round_to_odd;
+    }
+
+    set_float_exception_flags(0, &tstat);
+    xt.f128 = float128_sqrt(xb.f128, &tstat);
+    env->fp_status.float_exception_flags |= tstat.float_exception_flags;
+
+    if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
+        if (float128_is_signaling_nan(xb.f128, &tstat)) {
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
+            xt.f128 = float128_snan_to_qnan(xb.f128);
+        } else if  (float128_is_quiet_nan(xb.f128, &tstat)) {
+            xt.f128 = xb.f128;
+        } else if (float128_is_neg(xb.f128) && !float128_is_zero(xb.f128)) {
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1);
+            set_snan_bit_is_one(0, &env->fp_status);
+            xt.f128 = float128_default_nan(&env->fp_status);
+        }
+    }
+
+    helper_compute_fprf_float128(env, xt.f128);
+    putVSR(rD(opcode) + 32, &xt, env);
+    float_check_status(env);
+}
+
+void helper_xssubqp(CPUPPCState *env, uint32_t opcode)
+{
+    ppc_vsr_t xt, xa, xb;
+    float_status tstat;
+
+    getVSR(rA(opcode) + 32, &xa, env);
+    getVSR(rB(opcode) + 32, &xb, env);
+    getVSR(rD(opcode) + 32, &xt, env);
+    helper_reset_fpstatus(env);
+
+    tstat = env->fp_status;
+    if (unlikely(Rc(opcode) != 0)) {
+        tstat.float_rounding_mode = float_round_to_odd;
+    }
+
+    set_float_exception_flags(0, &tstat);
+    xt.f128 = float128_sub(xa.f128, xb.f128, &tstat);
+    env->fp_status.float_exception_flags |= tstat.float_exception_flags;
+
+    if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
+        if (float128_is_infinity(xa.f128) && float128_is_infinity(xb.f128)) {
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1);
+        } else if (float128_is_signaling_nan(xa.f128, &tstat) ||
+                   float128_is_signaling_nan(xb.f128, &tstat)) {
+            float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1);
+        }
+    }
+
+    helper_compute_fprf_float128(env, xt.f128);
+    putVSR(rD(opcode) + 32, &xt, env);
+    float_check_status(env);
+}
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 85af9df36d..6d77661f7c 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -431,6 +431,10 @@ DEF_HELPER_2(xscmpoqp, void, env, i32)
 DEF_HELPER_2(xscmpuqp, void, env, i32)
 DEF_HELPER_2(xsmaxdp, void, env, i32)
 DEF_HELPER_2(xsmindp, void, env, i32)
+DEF_HELPER_2(xsmaxcdp, void, env, i32)
+DEF_HELPER_2(xsmincdp, void, env, i32)
+DEF_HELPER_2(xsmaxjdp, void, env, i32)
+DEF_HELPER_2(xsminjdp, void, env, i32)
 DEF_HELPER_2(xscvdphp, void, env, i32)
 DEF_HELPER_2(xscvdpqp, void, env, i32)
 DEF_HELPER_2(xscvdpsp, void, env, i32)
@@ -438,6 +442,8 @@ DEF_HELPER_2(xscvdpspn, i64, env, i64)
 DEF_HELPER_2(xscvqpdp, void, env, i32)
 DEF_HELPER_2(xscvqpsdz, void, env, i32)
 DEF_HELPER_2(xscvqpswz, void, env, i32)
+DEF_HELPER_2(xscvqpudz, void, env, i32)
+DEF_HELPER_2(xscvqpuwz, void, env, i32)
 DEF_HELPER_2(xscvhpdp, void, env, i32)
 DEF_HELPER_2(xscvsdqp, void, env, i32)
 DEF_HELPER_2(xscvspdp, void, env, i32)
@@ -459,6 +465,10 @@ DEF_HELPER_2(xsrdpic, void, env, i32)
 DEF_HELPER_2(xsrdpim, void, env, i32)
 DEF_HELPER_2(xsrdpip, void, env, i32)
 DEF_HELPER_2(xsrdpiz, void, env, i32)
+DEF_HELPER_2(xsrqpi, void, env, i32)
+DEF_HELPER_2(xsrqpxp, void, env, i32)
+DEF_HELPER_2(xssqrtqp, void, env, i32)
+DEF_HELPER_2(xssubqp, void, env, i32)
 
 DEF_HELPER_2(xsaddsp, void, env, i32)
 DEF_HELPER_2(xssubsp, void, env, i32)
@@ -661,6 +671,7 @@ DEF_HELPER_2(load_slb_vsid, tl, env, tl)
 DEF_HELPER_2(find_slb_vsid, tl, env, tl)
 DEF_HELPER_FLAGS_1(slbia, TCG_CALL_NO_RWG, void, env)
 DEF_HELPER_FLAGS_2(slbie, TCG_CALL_NO_RWG, void, env, tl)
+DEF_HELPER_FLAGS_2(slbieg, TCG_CALL_NO_RWG, void, env, tl)
 #endif
 DEF_HELPER_FLAGS_2(load_sr, TCG_CALL_NO_RWG, tl, env, tl)
 DEF_HELPER_FLAGS_3(store_sr, TCG_CALL_NO_RWG, void, env, tl, tl)
diff --git a/target/ppc/internal.h b/target/ppc/internal.h
index 5a2fd68427..1f441c6483 100644
--- a/target/ppc/internal.h
+++ b/target/ppc/internal.h
@@ -133,6 +133,8 @@ EXTRACT_HELPER(UIMM4, 16, 4);
 EXTRACT_HELPER(NB, 11, 5);
 /* Shift count */
 EXTRACT_HELPER(SH, 11, 5);
+/* lwat/stwat/ldat/lwat */
+EXTRACT_HELPER(FC, 11, 5);
 /* Vector shift count */
 EXTRACT_HELPER(VSH, 6, 4);
 /* Mask start */
@@ -186,6 +188,7 @@ EXTRACT_HELPER(DCM, 10, 6)
 
 /* DFP Z23-form */
 EXTRACT_HELPER(RMC, 9, 2)
+EXTRACT_HELPER(Rrm, 16, 1)
 
 EXTRACT_HELPER_SPLIT(DQxT, 3, 1, 21, 5);
 EXTRACT_HELPER_SPLIT(xT, 0, 1, 21, 5);
diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 663d2e79c9..52bbea514a 100644
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -438,12 +438,13 @@ static bool kvm_valid_page_size(uint32_t flags, long rampgsize, uint32_t shift)
     return (1ul << shift) <= rampgsize;
 }
 
+static long max_cpu_page_size;
+
 static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
 {
     static struct kvm_ppc_smmu_info smmu_info;
     static bool has_smmu_info;
     CPUPPCState *env = &cpu->env;
-    long rampagesize;
     int iq, ik, jq, jk;
     bool has_64k_pages = false;
 
@@ -458,7 +459,9 @@ static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
         has_smmu_info = true;
     }
 
-    rampagesize = getrampagesize();
+    if (!max_cpu_page_size) {
+        max_cpu_page_size = getrampagesize();
+    }
 
     /* Convert to QEMU form */
     memset(&env->sps, 0, sizeof(env->sps));
@@ -478,14 +481,14 @@ static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
         struct ppc_one_seg_page_size *qsps = &env->sps.sps[iq];
         struct kvm_ppc_one_seg_page_size *ksps = &smmu_info.sps[ik];
 
-        if (!kvm_valid_page_size(smmu_info.flags, rampagesize,
+        if (!kvm_valid_page_size(smmu_info.flags, max_cpu_page_size,
                                  ksps->page_shift)) {
             continue;
         }
         qsps->page_shift = ksps->page_shift;
         qsps->slb_enc = ksps->slb_enc;
         for (jk = jq = 0; jk < KVM_PPC_PAGE_SIZES_MAX_SZ; jk++) {
-            if (!kvm_valid_page_size(smmu_info.flags, rampagesize,
+            if (!kvm_valid_page_size(smmu_info.flags, max_cpu_page_size,
                                      ksps->enc[jk].page_shift)) {
                 continue;
             }
@@ -510,12 +513,33 @@ static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
         env->mmu_model &= ~POWERPC_MMU_64K;
     }
 }
+
+bool kvmppc_is_mem_backend_page_size_ok(char *obj_path)
+{
+    Object *mem_obj = object_resolve_path(obj_path, NULL);
+    char *mempath = object_property_get_str(mem_obj, "mem-path", NULL);
+    long pagesize;
+
+    if (mempath) {
+        pagesize = gethugepagesize(mempath);
+    } else {
+        pagesize = getpagesize();
+    }
+
+    return pagesize >= max_cpu_page_size;
+}
+
 #else /* defined (TARGET_PPC64) */
 
 static inline void kvm_fixup_page_sizes(PowerPCCPU *cpu)
 {
 }
 
+bool kvmppc_is_mem_backend_page_size_ok(char *obj_path)
+{
+    return true;
+}
+
 #endif /* !defined (TARGET_PPC64) */
 
 unsigned long kvm_arch_vcpu_id(CPUState *cpu)
diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index 151c00bac7..8da2ee418a 100644
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -60,6 +60,8 @@ int kvmppc_enable_hwrng(void);
 int kvmppc_put_books_sregs(PowerPCCPU *cpu);
 PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void);
 
+bool kvmppc_is_mem_backend_page_size_ok(char *obj_path);
+
 #else
 
 static inline uint32_t kvmppc_get_tbfreq(void)
@@ -192,6 +194,11 @@ static inline uint64_t kvmppc_rma_size(uint64_t current_size,
     return ram_size;
 }
 
+static inline bool kvmppc_is_mem_backend_page_size_ok(char *obj_path)
+{
+    return true;
+}
+
 #endif /* !CONFIG_USER_ONLY */
 
 static inline bool kvmppc_has_cap_epr(void)
diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c
index bb78fb5497..76669ed82c 100644
--- a/target/ppc/mmu-hash64.c
+++ b/target/ppc/mmu-hash64.c
@@ -115,7 +115,8 @@ void helper_slbia(CPUPPCState *env)
     }
 }
 
-void helper_slbie(CPUPPCState *env, target_ulong addr)
+static void __helper_slbie(CPUPPCState *env, target_ulong addr,
+                           target_ulong global)
 {
     PowerPCCPU *cpu = ppc_env_get_cpu(env);
     ppc_slb_t *slb;
@@ -132,10 +133,21 @@ void helper_slbie(CPUPPCState *env, target_ulong addr)
          *      and we still don't have a tlb_flush_mask(env, n, mask)
          *      in QEMU, we just invalidate all TLBs
          */
-        env->tlb_need_flush |= TLB_NEED_LOCAL_FLUSH;
+        env->tlb_need_flush |=
+            (global == false ? TLB_NEED_LOCAL_FLUSH : TLB_NEED_GLOBAL_FLUSH);
     }
 }
 
+void helper_slbie(CPUPPCState *env, target_ulong addr)
+{
+    __helper_slbie(env, addr, false);
+}
+
+void helper_slbieg(CPUPPCState *env, target_ulong addr)
+{
+    __helper_slbie(env, addr, true);
+}
+
 int ppc_store_slb(PowerPCCPU *cpu, target_ulong slot,
                   target_ulong esid, target_ulong vsid)
 {
@@ -640,7 +652,15 @@ static void ppc_hash64_set_isi(CPUState *cs, CPUPPCState *env,
     if (msr_ir) {
         vpm = !!(env->spr[SPR_LPCR] & LPCR_VPM1);
     } else {
-        vpm = !!(env->spr[SPR_LPCR] & LPCR_VPM0);
+        switch (env->mmu_model) {
+        case POWERPC_MMU_3_00:
+            /* Field deprecated in ISAv3.00 - interrupts always go to hyperv */
+            vpm = true;
+            break;
+        default:
+            vpm = !!(env->spr[SPR_LPCR] & LPCR_VPM0);
+            break;
+        }
     }
     if (vpm && !msr_hv) {
         cs->exception_index = POWERPC_EXCP_HISI;
@@ -658,7 +678,15 @@ static void ppc_hash64_set_dsi(CPUState *cs, CPUPPCState *env, uint64_t dar,
     if (msr_dr) {
         vpm = !!(env->spr[SPR_LPCR] & LPCR_VPM1);
     } else {
-        vpm = !!(env->spr[SPR_LPCR] & LPCR_VPM0);
+        switch (env->mmu_model) {
+        case POWERPC_MMU_3_00:
+            /* Field deprecated in ISAv3.00 - interrupts always go to hyperv */
+            vpm = true;
+            break;
+        default:
+            vpm = !!(env->spr[SPR_LPCR] & LPCR_VPM0);
+            break;
+        }
     }
     if (vpm && !msr_hv) {
         cs->exception_index = POWERPC_EXCP_HDSI;
@@ -1050,6 +1078,14 @@ void helper_store_lpcr(CPUPPCState *env, target_ulong val)
                       LPCR_P8_PECE2 | LPCR_P8_PECE3 | LPCR_P8_PECE4 |
                       LPCR_MER | LPCR_TC | LPCR_LPES0 | LPCR_HDICE);
         break;
+    case POWERPC_MMU_3_00: /* P9 */
+        lpcr = val & (LPCR_VPM1 | LPCR_ISL | LPCR_KBV | LPCR_DPFD |
+                      (LPCR_PECE_U_MASK & LPCR_HVEE) | LPCR_ILE | LPCR_AIL |
+                      LPCR_UPRT | LPCR_EVIRT | LPCR_ONL |
+                      (LPCR_PECE_L_MASK & (LPCR_PDEE | LPCR_HDEE | LPCR_EEE |
+                      LPCR_DEE | LPCR_OEE)) | LPCR_MER | LPCR_GTSE | LPCR_TC |
+                      LPCR_HEIC | LPCR_LPES0 | LPCR_HVICE | LPCR_HDICE);
+        break;
     default:
         ;
     }
diff --git a/target/ppc/mmu_helper.c b/target/ppc/mmu_helper.c
index f746f53615..eb2d482ef7 100644
--- a/target/ppc/mmu_helper.c
+++ b/target/ppc/mmu_helper.c
@@ -825,7 +825,7 @@ static int mmubooke_get_physical_address(CPUPPCState *env, mmu_ctx_t *ctx,
         tlb = &env->tlb.tlbe[i];
         ret = mmubooke_check_tlb(env, tlb, &raddr, &ctx->prot, address, rw,
                                  access_type, i);
-        if (!ret) {
+        if (ret != -1) {
             break;
         }
     }
@@ -1935,6 +1935,7 @@ void ppc_tlb_invalidate_all(CPUPPCState *env)
     case POWERPC_MMU_2_06a:
     case POWERPC_MMU_2_07:
     case POWERPC_MMU_2_07a:
+    case POWERPC_MMU_3_00:
 #endif /* defined(TARGET_PPC64) */
         env->tlb_need_flush = 0;
         tlb_flush(CPU(cpu));
@@ -1974,6 +1975,7 @@ void ppc_tlb_invalidate_one(CPUPPCState *env, target_ulong addr)
     case POWERPC_MMU_2_06a:
     case POWERPC_MMU_2_07:
     case POWERPC_MMU_2_07a:
+    case POWERPC_MMU_3_00:
         /* tlbie invalidate TLBs for all segments */
         /* XXX: given the fact that there are too many segments to invalidate,
          *      and we still don't have a tlb_flush_mask(env, n, mask) in QEMU,
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index b48abaedfb..3ba2616b8a 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -2976,6 +2976,113 @@ LARX(lbarx, DEF_MEMOP(MO_UB))
 LARX(lharx, DEF_MEMOP(MO_UW))
 LARX(lwarx, DEF_MEMOP(MO_UL))
 
+#define LD_ATOMIC(name, memop, tp, op, eop)                             \
+static void gen_##name(DisasContext *ctx)                               \
+{                                                                       \
+    int len = MEMOP_GET_SIZE(memop);                                    \
+    uint32_t gpr_FC = FC(ctx->opcode);                                  \
+    TCGv EA = tcg_temp_local_new();                                     \
+    TCGv_##tp t0, t1;                                                   \
+                                                                        \
+    gen_addr_register(ctx, EA);                                         \
+    if (len > 1) {                                                      \
+        gen_check_align(ctx, EA, len - 1);                              \
+    }                                                                   \
+    t0 = tcg_temp_new_##tp();                                           \
+    t1 = tcg_temp_new_##tp();                                           \
+    tcg_gen_##op(t0, cpu_gpr[rD(ctx->opcode) + 1]);                     \
+                                                                        \
+    switch (gpr_FC) {                                                   \
+    case 0: /* Fetch and add */                                         \
+        tcg_gen_atomic_fetch_add_##tp(t1, EA, t0, ctx->mem_idx, memop); \
+        break;                                                          \
+    case 1: /* Fetch and xor */                                         \
+        tcg_gen_atomic_fetch_xor_##tp(t1, EA, t0, ctx->mem_idx, memop); \
+        break;                                                          \
+    case 2: /* Fetch and or */                                          \
+        tcg_gen_atomic_fetch_or_##tp(t1, EA, t0, ctx->mem_idx, memop);  \
+        break;                                                          \
+    case 3: /* Fetch and 'and' */                                       \
+        tcg_gen_atomic_fetch_and_##tp(t1, EA, t0, ctx->mem_idx, memop); \
+        break;                                                          \
+    case 8: /* Swap */                                                  \
+        tcg_gen_atomic_xchg_##tp(t1, EA, t0, ctx->mem_idx, memop);      \
+        break;                                                          \
+    case 4:  /* Fetch and max unsigned */                               \
+    case 5:  /* Fetch and max signed */                                 \
+    case 6:  /* Fetch and min unsigned */                               \
+    case 7:  /* Fetch and min signed */                                 \
+    case 16: /* compare and swap not equal */                           \
+    case 24: /* Fetch and increment bounded */                          \
+    case 25: /* Fetch and increment equal */                            \
+    case 28: /* Fetch and decrement bounded */                          \
+        gen_invalid(ctx);                                               \
+        break;                                                          \
+    default:                                                            \
+        /* invoke data storage error handler */                         \
+        gen_exception_err(ctx, POWERPC_EXCP_DSI, POWERPC_EXCP_INVAL);   \
+    }                                                                   \
+    tcg_gen_##eop(cpu_gpr[rD(ctx->opcode)], t1);                        \
+    tcg_temp_free_##tp(t0);                                             \
+    tcg_temp_free_##tp(t1);                                             \
+    tcg_temp_free(EA);                                                  \
+}
+
+LD_ATOMIC(lwat, DEF_MEMOP(MO_UL), i32, trunc_tl_i32, extu_i32_tl)
+#if defined(TARGET_PPC64)
+LD_ATOMIC(ldat, DEF_MEMOP(MO_Q), i64, mov_i64, mov_i64)
+#endif
+
+#define ST_ATOMIC(name, memop, tp, op)                                  \
+static void gen_##name(DisasContext *ctx)                               \
+{                                                                       \
+    int len = MEMOP_GET_SIZE(memop);                                    \
+    uint32_t gpr_FC = FC(ctx->opcode);                                  \
+    TCGv EA = tcg_temp_local_new();                                     \
+    TCGv_##tp t0, t1;                                                   \
+                                                                        \
+    gen_addr_register(ctx, EA);                                         \
+    if (len > 1) {                                                      \
+        gen_check_align(ctx, EA, len - 1);                              \
+    }                                                                   \
+    t0 = tcg_temp_new_##tp();                                           \
+    t1 = tcg_temp_new_##tp();                                           \
+    tcg_gen_##op(t0, cpu_gpr[rD(ctx->opcode) + 1]);                     \
+                                                                        \
+    switch (gpr_FC) {                                                   \
+    case 0: /* add and Store */                                         \
+        tcg_gen_atomic_add_fetch_##tp(t1, EA, t0, ctx->mem_idx, memop); \
+        break;                                                          \
+    case 1: /* xor and Store */                                         \
+        tcg_gen_atomic_xor_fetch_##tp(t1, EA, t0, ctx->mem_idx, memop); \
+        break;                                                          \
+    case 2: /* Or and Store */                                          \
+        tcg_gen_atomic_or_fetch_##tp(t1, EA, t0, ctx->mem_idx, memop);  \
+        break;                                                          \
+    case 3: /* 'and' and Store */                                       \
+        tcg_gen_atomic_and_fetch_##tp(t1, EA, t0, ctx->mem_idx, memop); \
+        break;                                                          \
+    case 4:  /* Store max unsigned */                                   \
+    case 5:  /* Store max signed */                                     \
+    case 6:  /* Store min unsigned */                                   \
+    case 7:  /* Store min signed */                                     \
+    case 24: /* Store twin  */                                          \
+        gen_invalid(ctx);                                               \
+        break;                                                          \
+    default:                                                            \
+        /* invoke data storage error handler */                         \
+        gen_exception_err(ctx, POWERPC_EXCP_DSI, POWERPC_EXCP_INVAL);   \
+    }                                                                   \
+    tcg_temp_free_##tp(t0);                                             \
+    tcg_temp_free_##tp(t1);                                             \
+    tcg_temp_free(EA);                                                  \
+}
+
+ST_ATOMIC(stwat, DEF_MEMOP(MO_UL), i32, trunc_tl_i32)
+#if defined(TARGET_PPC64)
+ST_ATOMIC(stdat, DEF_MEMOP(MO_Q), i64, mov_i64)
+#endif
+
 #if defined(CONFIG_USER_ONLY)
 static void gen_conditional_store(DisasContext *ctx, TCGv EA,
                                   int reg, int memop)
@@ -4377,6 +4484,30 @@ static void gen_slbie(DisasContext *ctx)
     gen_helper_slbie(cpu_env, cpu_gpr[rB(ctx->opcode)]);
 #endif /* defined(CONFIG_USER_ONLY) */
 }
+
+/* slbieg */
+static void gen_slbieg(DisasContext *ctx)
+{
+#if defined(CONFIG_USER_ONLY)
+    GEN_PRIV;
+#else
+    CHK_SV;
+
+    gen_helper_slbieg(cpu_env, cpu_gpr[rB(ctx->opcode)]);
+#endif /* defined(CONFIG_USER_ONLY) */
+}
+
+/* slbsync */
+static void gen_slbsync(DisasContext *ctx)
+{
+#if defined(CONFIG_USER_ONLY)
+    GEN_PRIV;
+#else
+    CHK_SV;
+    gen_check_tlb_flush(ctx, true);
+#endif /* defined(CONFIG_USER_ONLY) */
+}
+
 #endif  /* defined(TARGET_PPC64) */
 
 /***                              External control                         ***/
@@ -6025,6 +6156,19 @@ static inline void gen_cp_abort(DisasContext *ctx)
     // Do Nothing
 }
 
+#define GEN_CP_PASTE_NOOP(name)                           \
+static inline void gen_##name(DisasContext *ctx)          \
+{                                                         \
+    /* Generate invalid exception until                   \
+     * we have an implementation of the copy              \
+     * paste facility                                     \
+     */                                                   \
+    gen_invalid(ctx);                                     \
+}
+
+GEN_CP_PASTE_NOOP(copy)
+GEN_CP_PASTE_NOOP(paste)
+
 static void gen_tcheck(DisasContext *ctx)
 {
     if (unlikely(!ctx->tm_enabled)) {
@@ -6174,7 +6318,9 @@ GEN_HANDLER2(andi_, "andi.", 0x1C, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
 GEN_HANDLER2(andis_, "andis.", 0x1D, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
 GEN_HANDLER(cntlzw, 0x1F, 0x1A, 0x00, 0x00000000, PPC_INTEGER),
 GEN_HANDLER_E(cnttzw, 0x1F, 0x1A, 0x10, 0x00000000, PPC_NONE, PPC2_ISA300),
+GEN_HANDLER_E(copy, 0x1F, 0x06, 0x18, 0x03C00001, PPC_NONE, PPC2_ISA300),
 GEN_HANDLER_E(cp_abort, 0x1F, 0x06, 0x1A, 0x03FFF801, PPC_NONE, PPC2_ISA300),
+GEN_HANDLER_E(paste, 0x1F, 0x06, 0x1C, 0x03C00000, PPC_NONE, PPC2_ISA300),
 GEN_HANDLER(or, 0x1F, 0x1C, 0x0D, 0x00000000, PPC_INTEGER),
 GEN_HANDLER(xor, 0x1F, 0x1C, 0x09, 0x00000000, PPC_INTEGER),
 GEN_HANDLER(ori, 0x18, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
@@ -6230,10 +6376,14 @@ GEN_HANDLER(isync, 0x13, 0x16, 0x04, 0x03FFF801, PPC_MEM),
 GEN_HANDLER_E(lbarx, 0x1F, 0x14, 0x01, 0, PPC_NONE, PPC2_ATOMIC_ISA206),
 GEN_HANDLER_E(lharx, 0x1F, 0x14, 0x03, 0, PPC_NONE, PPC2_ATOMIC_ISA206),
 GEN_HANDLER(lwarx, 0x1F, 0x14, 0x00, 0x00000000, PPC_RES),
+GEN_HANDLER_E(lwat, 0x1F, 0x06, 0x12, 0x00000001, PPC_NONE, PPC2_ISA300),
+GEN_HANDLER_E(stwat, 0x1F, 0x06, 0x16, 0x00000001, PPC_NONE, PPC2_ISA300),
 GEN_HANDLER_E(stbcx_, 0x1F, 0x16, 0x15, 0, PPC_NONE, PPC2_ATOMIC_ISA206),
 GEN_HANDLER_E(sthcx_, 0x1F, 0x16, 0x16, 0, PPC_NONE, PPC2_ATOMIC_ISA206),
 GEN_HANDLER2(stwcx_, "stwcx.", 0x1F, 0x16, 0x04, 0x00000000, PPC_RES),
 #if defined(TARGET_PPC64)
+GEN_HANDLER_E(ldat, 0x1F, 0x06, 0x13, 0x00000001, PPC_NONE, PPC2_ISA300),
+GEN_HANDLER_E(stdat, 0x1F, 0x06, 0x17, 0x00000001, PPC_NONE, PPC2_ISA300),
 GEN_HANDLER(ldarx, 0x1F, 0x14, 0x02, 0x00000000, PPC_64B),
 GEN_HANDLER_E(lqarx, 0x1F, 0x14, 0x08, 0, PPC_NONE, PPC2_LSQ_ISA207),
 GEN_HANDLER2(stdcx_, "stdcx.", 0x1F, 0x16, 0x06, 0x00000000, PPC_64B),
@@ -6241,6 +6391,7 @@ GEN_HANDLER_E(stqcx_, 0x1F, 0x16, 0x05, 0, PPC_NONE, PPC2_LSQ_ISA207),
 #endif
 GEN_HANDLER(sync, 0x1F, 0x16, 0x12, 0x039FF801, PPC_MEM_SYNC),
 GEN_HANDLER(wait, 0x1F, 0x1E, 0x01, 0x03FFF801, PPC_WAIT),
+GEN_HANDLER_E(wait, 0x1F, 0x1E, 0x00, 0x039FF801, PPC_NONE, PPC2_ISA300),
 GEN_HANDLER(b, 0x12, 0xFF, 0xFF, 0x00000000, PPC_FLOW),
 GEN_HANDLER(bc, 0x10, 0xFF, 0xFF, 0x00000000, PPC_FLOW),
 GEN_HANDLER(bcctr, 0x13, 0x10, 0x10, 0x00000000, PPC_FLOW),
@@ -6313,6 +6464,8 @@ GEN_HANDLER(tlbsync, 0x1F, 0x16, 0x11, 0x03FFF801, PPC_MEM_TLBSYNC),
 #if defined(TARGET_PPC64)
 GEN_HANDLER(slbia, 0x1F, 0x12, 0x0F, 0x031FFC01, PPC_SLBI),
 GEN_HANDLER(slbie, 0x1F, 0x12, 0x0D, 0x03FF0001, PPC_SLBI),
+GEN_HANDLER_E(slbieg, 0x1F, 0x12, 0x0E, 0x001F0001, PPC_NONE, PPC2_ISA300),
+GEN_HANDLER_E(slbsync, 0x1F, 0x12, 0x0A, 0x03FFF801, PPC_NONE, PPC2_ISA300),
 #endif
 GEN_HANDLER(eciwx, 0x1F, 0x16, 0x0D, 0x00000001, PPC_EXTERN),
 GEN_HANDLER(ecowx, 0x1F, 0x16, 0x09, 0x00000001, PPC_EXTERN),
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index a44c0034a8..7f12908029 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -808,6 +808,10 @@ GEN_VSX_HELPER_2(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsmaxcdp, 0x00, 0x10, 0, PPC2_ISA300)
+GEN_VSX_HELPER_2(xsmincdp, 0x00, 0x11, 0, PPC2_ISA300)
+GEN_VSX_HELPER_2(xsmaxjdp, 0x00, 0x12, 0, PPC2_ISA300)
+GEN_VSX_HELPER_2(xsminjdp, 0x00, 0x12, 0, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300)
@@ -815,6 +819,8 @@ GEN_VSX_HELPER_XT_XB_ENV(xscvdpspn, 0x16, 0x10, 0, PPC2_VSX207)
 GEN_VSX_HELPER_2(xscvqpdp, 0x04, 0x1A, 0x14, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvqpsdz, 0x04, 0x1A, 0x19, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvqpswz, 0x04, 0x1A, 0x09, PPC2_ISA300)
+GEN_VSX_HELPER_2(xscvqpudz, 0x04, 0x1A, 0x11, PPC2_ISA300)
+GEN_VSX_HELPER_2(xscvqpuwz, 0x04, 0x1A, 0x01, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvsdqp, 0x04, 0x1A, 0x0A, PPC2_ISA300)
 GEN_VSX_HELPER_2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
@@ -833,6 +839,11 @@ GEN_VSX_HELPER_2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_XT_XB_ENV(xsrsp, 0x12, 0x11, 0, PPC2_VSX207)
 
+GEN_VSX_HELPER_2(xsrqpi, 0x05, 0x00, 0, PPC2_ISA300)
+GEN_VSX_HELPER_2(xsrqpxp, 0x05, 0x01, 0, PPC2_ISA300)
+GEN_VSX_HELPER_2(xssqrtqp, 0x04, 0x19, 0x1B, PPC2_ISA300)
+GEN_VSX_HELPER_2(xssubqp, 0x04, 0x10, 0, PPC2_ISA300)
+
 GEN_VSX_HELPER_2(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
 GEN_VSX_HELPER_2(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
 GEN_VSX_HELPER_2(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
diff --git a/target/ppc/translate/vsx-ops.inc.c b/target/ppc/translate/vsx-ops.inc.c
index 7dc9f6f477..5030c4aceb 100644
--- a/target/ppc/translate/vsx-ops.inc.c
+++ b/target/ppc/translate/vsx-ops.inc.c
@@ -103,6 +103,21 @@ GEN_HANDLER_E(name, 0x3F, opc2, opc3, inval, PPC_NONE, PPC2_ISA300)
 #define GEN_VSX_XFORM_300_EO(name, opc2, opc3, opc4, inval)             \
 GEN_HANDLER_E_2(name, 0x3F, opc2, opc3, opc4, inval, PPC_NONE, PPC2_ISA300)
 
+#define GEN_VSX_Z23FORM_300(name, opc2, opc3, opc4, inval) \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x00, opc4 | 0x0, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x08, opc4 | 0x0, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x10, opc4 | 0x0, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x18, opc4 | 0x0, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x00, opc4 | 0x1, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x08, opc4 | 0x1, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x10, opc4 | 0x1, inval), \
+GEN_VSX_XFORM_300_EO(name, opc2, opc3 | 0x18, opc4 | 0x1, inval)
+
+GEN_VSX_Z23FORM_300(xsrqpi, 0x05, 0x0, 0x0, 0x0),
+GEN_VSX_Z23FORM_300(xsrqpxp, 0x05, 0x1, 0x0, 0x0),
+GEN_VSX_XFORM_300_EO(xssqrtqp, 0x04, 0x19, 0x1B, 0x0),
+GEN_VSX_XFORM_300(xssubqp, 0x04, 0x10, 0x0),
+
 GEN_XX2FORM(xsabsdp, 0x12, 0x15, PPC2_VSX),
 GEN_XX2FORM(xsnabsdp, 0x12, 0x16, PPC2_VSX),
 GEN_XX2FORM(xsnegdp, 0x12, 0x17, PPC2_VSX),
@@ -116,6 +131,8 @@ GEN_VSX_XFORM_300_EO(xscvdpqp, 0x04, 0x1A, 0x16, 0x00000001),
 GEN_VSX_XFORM_300_EO(xscvqpdp, 0x04, 0x1A, 0x14, 0x0),
 GEN_VSX_XFORM_300_EO(xscvqpsdz, 0x04, 0x1A, 0x19, 0x00000001),
 GEN_VSX_XFORM_300_EO(xscvqpswz, 0x04, 0x1A, 0x09, 0x00000001),
+GEN_VSX_XFORM_300_EO(xscvqpudz, 0x04, 0x1A, 0x11, 0x00000001),
+GEN_VSX_XFORM_300_EO(xscvqpuwz, 0x04, 0x1A, 0x01, 0x00000001),
 
 #ifdef TARGET_PPC64
 GEN_XX2FORM_EO(xsxexpdp, 0x16, 0x15, 0x00, PPC2_ISA300),
@@ -185,6 +202,10 @@ GEN_VSX_XFORM_300(xscmpoqp, 0x04, 0x04, 0x00600001),
 GEN_VSX_XFORM_300(xscmpuqp, 0x04, 0x14, 0x00600001),
 GEN_XX3FORM(xsmaxdp, 0x00, 0x14, PPC2_VSX),
 GEN_XX3FORM(xsmindp, 0x00, 0x15, PPC2_VSX),
+GEN_XX3FORM(xsmaxcdp, 0x00, 0x10, PPC2_ISA300),
+GEN_XX3FORM(xsmincdp, 0x00, 0x11, PPC2_ISA300),
+GEN_XX3FORM(xsmaxjdp, 0x00, 0x12, PPC2_ISA300),
+GEN_XX3FORM(xsminjdp, 0x00, 0x13, PPC2_ISA300),
 GEN_XX2FORM_EO(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300),
 GEN_XX2FORM(xscvdpsp, 0x12, 0x10, PPC2_VSX),
 GEN_XX2FORM(xscvdpspn, 0x16, 0x10, PPC2_VSX207),
diff --git a/target/ppc/translate_init.c b/target/ppc/translate_init.c
index 76f79fa77b..be35cbd3a2 100644
--- a/target/ppc/translate_init.c
+++ b/target/ppc/translate_init.c
@@ -8816,8 +8816,7 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data)
                     (1ull << MSR_PMM) |
                     (1ull << MSR_RI) |
                     (1ull << MSR_LE);
-    /* Using 2.07 defines until new radix model is added. */
-    pcc->mmu_model = POWERPC_MMU_2_07;
+    pcc->mmu_model = POWERPC_MMU_3_00;
 #if defined(CONFIG_SOFTMMU)
     pcc->handle_mmu_fault = ppc_hash64_handle_mmu_fault;
     /* segment page size remain the same */
@@ -8871,12 +8870,24 @@ void cpu_ppc_set_papr(PowerPCCPU *cpu)
     lpcr->default_value &= ~LPCR_RMLS;
     lpcr->default_value |= 1ull << LPCR_RMLS_SHIFT;
 
-    /* P7 and P8 has slightly different PECE bits, mostly because P8 adds
-     * bit 47 and 48 which are reserved on P7. Here we set them all, which
-     * will work as expected for both implementations
-     */
-    lpcr->default_value |= LPCR_P8_PECE0 | LPCR_P8_PECE1 | LPCR_P8_PECE2 |
-                           LPCR_P8_PECE3 | LPCR_P8_PECE4;
+    switch (env->mmu_model) {
+    case POWERPC_MMU_3_00:
+        /* By default we choose legacy mode and switch to new hash or radix
+         * when a register process table hcall is made. So disable process
+         * tables and guest translation shootdown by default
+         */
+        lpcr->default_value &= ~(LPCR_UPRT | LPCR_GTSE);
+        lpcr->default_value |= LPCR_PDEE | LPCR_HDEE | LPCR_EEE | LPCR_DEE |
+                               LPCR_OEE;
+        break;
+    default:
+        /* P7 and P8 has slightly different PECE bits, mostly because P8 adds
+         * bit 47 and 48 which are reserved on P7. Here we set them all, which
+         * will work as expected for both implementations
+         */
+        lpcr->default_value |= LPCR_P8_PECE0 | LPCR_P8_PECE1 | LPCR_P8_PECE2 |
+                               LPCR_P8_PECE3 | LPCR_P8_PECE4;
+    }
 
     /* We should be followed by a CPU reset but update the active value
      * just in case...
diff --git a/vl.c b/vl.c
index b5d0a19811..904e34b72c 100644
--- a/vl.c
+++ b/vl.c
@@ -1492,7 +1492,7 @@ MachineInfoList *qmp_query_machines(Error **errp)
 
         info->name = g_strdup(mc->name);
         info->cpu_max = !mc->max_cpus ? 1 : mc->max_cpus;
-        info->hotpluggable_cpus = !!mc->query_hotpluggable_cpus;
+        info->hotpluggable_cpus = mc->has_hotpluggable_cpus;
 
         entry = g_malloc0(sizeof(*entry));
         entry->value = info;