Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20160714' into staging

target-arm queue:
 * add virtio-mmio transport base address to device path
   (avoid an assertion failure with multiple virtio-scsi-devices)
 * revert hw/ptimer commit 5a50307 which causes regressions on
   SPARC guests
 * use Neon to accelerate zero-page checking on AArch64 hosts
 * set the MPIDR for TCG to match how KVM does it (and fit with
   GICv2/GICv3 restrictions on SGI target lists)
 * add some missing AArch32 TLBI hypervisor TLB operations
 * m25p80: Fix QIOR/DIOR handling for Winbond
 * hw/misc: fix typo in Aspeed SCU hw-strap2 property name
 * ast2400: pretend DMAs are done for U-boot
 * ast2400: some minor code cleanups

# gpg: Signature made Thu 14 Jul 2016 17:21:30 BST
# gpg:                using RSA key 0x3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20160714:
  ast2400: externalize revision numbers
  ast2400: pretend DMAs are done for U-boot
  ast2400: replace aspeed_smc_is_implemented()
  hw/misc: fix typo in Aspeed SCU hw-strap2 property name
  m25p80: Fix QIOR/DIOR handling for Winbond
  target-arm: Add missed AArch32 TLBI sytem registers
  hw/arm/virt: tcg: adjust MPIDR like KVM
  gic: provide defines for v2/v3 targetlist sizes
  target-arm: Use Neon for zero checking
  Revert "hw/ptimer: Perform counter wrap around if timer already expired"
  virtio-mmio: format transport base address in BusClass.get_dev_path

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

13 files changed, 262 insertions, 37 deletions

diff --git a/hw/arm/ast2400.c b/hw/arm/ast2400.c
index 0555843620..326fdb36ee 100644
--- a/hw/arm/ast2400.c
+++ b/hw/arm/ast2400.c
@@ -34,8 +34,6 @@
 #define AST2400_FMC_FLASH_BASE   0x20000000
 #define AST2400_SPI_FLASH_BASE   0x30000000
 
-#define AST2400_A0_SILICON_REV   0x02000303
-
 static const int uart_irqs[] = { 9, 32, 33, 34, 10 };
 static const int timer_irqs[] = { 16, 17, 18, 35, 36, 37, 38, 39, };
 
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 4dafd42be8..a193b5a95b 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -52,7 +52,8 @@
 #include "hw/arm/sysbus-fdt.h"
 #include "hw/platform-bus.h"
 #include "hw/arm/fdt.h"
-#include "hw/intc/arm_gic_common.h"
+#include "hw/intc/arm_gic.h"
+#include "hw/intc/arm_gicv3_common.h"
 #include "kvm_arm.h"
 #include "hw/smbios/smbios.h"
 #include "qapi/visitor.h"
@@ -82,6 +83,7 @@ typedef struct VirtBoardInfo {
 typedef struct {
     MachineClass parent;
     VirtBoardInfo *daughterboard;
+    bool disallow_affinity_adjustment;
 } VirtMachineClass;
 
 typedef struct {
@@ -1165,6 +1167,7 @@ void virt_guest_info_machine_done(Notifier *notifier, void *data)
 static void machvirt_init(MachineState *machine)
 {
     VirtMachineState *vms = VIRT_MACHINE(machine);
+    VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(machine);
     qemu_irq pic[NUM_IRQS];
     MemoryRegion *sysmem = get_system_memory();
     MemoryRegion *secure_sysmem = NULL;
@@ -1181,6 +1184,7 @@ static void machvirt_init(MachineState *machine)
     CPUClass *cc;
     Error *err = NULL;
     bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
+    uint8_t clustersz;
 
     if (!cpu_model) {
         cpu_model = "cortex-a15";
@@ -1226,8 +1230,10 @@ static void machvirt_init(MachineState *machine)
      */
     if (gic_version == 3) {
         virt_max_cpus = vbi->memmap[VIRT_GIC_REDIST].size / 0x20000;
+        clustersz = GICV3_TARGETLIST_BITS;
     } else {
         virt_max_cpus = GIC_NCPU;
+        clustersz = GIC_TARGETLIST_BITS;
     }
 
     if (max_cpus > virt_max_cpus) {
@@ -1281,6 +1287,20 @@ static void machvirt_init(MachineState *machine)
 
     for (n = 0; n < smp_cpus; n++) {
         Object *cpuobj = object_new(typename);
+        if (!vmc->disallow_affinity_adjustment) {
+            /* Adjust MPIDR like 64-bit KVM hosts, which incorporate the
+             * GIC's target-list limitations. 32-bit KVM hosts currently
+             * always create clusters of 4 CPUs, but that is expected to
+             * change when they gain support for gicv3. When KVM is enabled
+             * it will override the changes we make here, therefore our
+             * purposes are to make TCG consistent (with 64-bit KVM hosts)
+             * and to improve SGI efficiency.
+             */
+            uint8_t aff1 = n / clustersz;
+            uint8_t aff0 = n % clustersz;
+            object_property_set_int(cpuobj, (aff1 << ARM_AFF1_SHIFT) | aff0,
+                                    "mp-affinity", NULL);
+        }
 
         if (!vms->secure) {
             object_property_set_bool(cpuobj, false, "has_el3", NULL);
@@ -1507,7 +1527,10 @@ static void virt_2_6_instance_init(Object *obj)
 
 static void virt_machine_2_6_options(MachineClass *mc)
 {
+    VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
     virt_machine_2_7_options(mc);
     SET_MACHINE_COMPAT(mc, VIRT_COMPAT_2_6);
+    vmc->disallow_affinity_adjustment = true;
 }
 DEFINE_VIRT_MACHINE(2, 6)
diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c
index ca8c12c0f8..9828ee61d5 100644
--- a/hw/block/m25p80.c
+++ b/hw/block/m25p80.c
@@ -149,6 +149,7 @@ typedef struct FlashPartInfo {
 */
 
 #define SPANSION_CONTINUOUS_READ_MODE_CMD_LEN 1
+#define WINBOND_CONTINUOUS_READ_MODE_CMD_LEN 1
 
 static const FlashPartInfo known_devices[] = {
     /* Atmel -- some are (confusingly) marketed as "DataFlash" */
@@ -777,7 +778,7 @@ static void decode_dio_read_cmd(Flash *s)
     /* Dummy cycles modeled with bytes writes instead of bits */
     switch (get_man(s)) {
     case MAN_WINBOND:
-        s->needed_bytes += 8;
+        s->needed_bytes += WINBOND_CONTINUOUS_READ_MODE_CMD_LEN;
         break;
     case MAN_SPANSION:
         s->needed_bytes += SPANSION_CONTINUOUS_READ_MODE_CMD_LEN;
@@ -816,7 +817,8 @@ static void decode_qio_read_cmd(Flash *s)
     /* Dummy cycles modeled with bytes writes instead of bits */
     switch (get_man(s)) {
     case MAN_WINBOND:
-        s->needed_bytes += 8;
+        s->needed_bytes += WINBOND_CONTINUOUS_READ_MODE_CMD_LEN;
+        s->needed_bytes += 4;
         break;
     case MAN_SPANSION:
         s->needed_bytes += SPANSION_CONTINUOUS_READ_MODE_CMD_LEN;
diff --git a/hw/core/ptimer.c b/hw/core/ptimer.c
index 05b0c276eb..30829ee97b 100644
--- a/hw/core/ptimer.c
+++ b/hw/core/ptimer.c
@@ -93,7 +93,7 @@ uint64_t ptimer_get_count(ptimer_state *s)
         bool oneshot = (s->enabled == 2);
 
         /* Figure out the current counter value.  */
-        if (s->period == 0 || (expired && (oneshot || use_icount))) {
+        if (expired) {
             /* Prevent timer underflowing if it should already have
                triggered.  */
             counter = 0;
@@ -120,7 +120,7 @@ uint64_t ptimer_get_count(ptimer_state *s)
                backwards.
             */
 
-            rem = expired ? now - next : next - now;
+            rem = next - now;
             div = period;
 
             clz1 = clz64(rem);
@@ -140,11 +140,6 @@ uint64_t ptimer_get_count(ptimer_state *s)
                     div += 1;
             }
             counter = rem / div;
-
-            if (expired && counter != 0) {
-                /* Wrap around periodic counter.  */
-                counter = s->limit - (counter - 1) % s->limit;
-            }
         }
     } else {
         counter = s->delta;
diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c
index 23f51752b0..c7e2c8263f 100644
--- a/hw/misc/aspeed_scu.c
+++ b/hw/misc/aspeed_scu.c
@@ -88,8 +88,6 @@
 #define PROT_KEY_UNLOCK 0x1688A8A8
 #define SCU_IO_REGION_SIZE 0x20000
 
-#define AST2400_A0_SILICON_REV     0x02000303U
-
 static const uint32_t ast2400_a0_resets[ASPEED_SCU_NR_REGS] = {
      [SYS_RST_CTRL]    = 0xFFCFFEDCU,
      [CLK_SEL]         = 0xF3F40000U,
@@ -212,7 +210,7 @@ static void aspeed_scu_reset(DeviceState *dev)
 
 static uint32_t aspeed_silicon_revs[] = { AST2400_A0_SILICON_REV, };
 
-static bool is_supported_silicon_rev(uint32_t silicon_rev)
+bool is_supported_silicon_rev(uint32_t silicon_rev)
 {
     int i;
 
@@ -255,7 +253,7 @@ static const VMStateDescription vmstate_aspeed_scu = {
 static Property aspeed_scu_properties[] = {
     DEFINE_PROP_UINT32("silicon-rev", AspeedSCUState, silicon_rev, 0),
     DEFINE_PROP_UINT32("hw-strap1", AspeedSCUState, hw_strap1, 0),
-    DEFINE_PROP_UINT32("hw-strap2", AspeedSCUState, hw_strap1, 0),
+    DEFINE_PROP_UINT32("hw-strap2", AspeedSCUState, hw_strap2, 0),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c
index a371e302d4..d319e04a27 100644
--- a/hw/ssi/aspeed_smc.c
+++ b/hw/ssi/aspeed_smc.c
@@ -273,6 +273,9 @@ static void aspeed_smc_reset(DeviceState *d)
 
     memset(s->regs, 0, sizeof s->regs);
 
+    /* Pretend DMA is done (u-boot initialization) */
+    s->regs[R_INTR_CTRL] = INTR_CTRL_DMA_STATUS;
+
     /* Unselect all slaves */
     for (i = 0; i < s->num_cs; ++i) {
         s->regs[s->r_ctrl0 + i] |= CTRL_CE_STOP_ACTIVE;
@@ -281,12 +284,6 @@ static void aspeed_smc_reset(DeviceState *d)
     aspeed_smc_update_cs(s);
 }
 
-static bool aspeed_smc_is_implemented(AspeedSMCState *s, hwaddr addr)
-{
-    return (addr == s->r_conf || addr == s->r_timings || addr == s->r_ce_ctrl ||
-            (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs));
-}
-
 static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size)
 {
     AspeedSMCState *s = ASPEED_SMC(opaque);
@@ -300,13 +297,17 @@ static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size)
         return 0;
     }
 
-    if (!aspeed_smc_is_implemented(s, addr)) {
+    if (addr == s->r_conf ||
+        addr == s->r_timings ||
+        addr == s->r_ce_ctrl ||
+        addr == R_INTR_CTRL ||
+        (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs)) {
+        return s->regs[addr];
+    } else {
         qemu_log_mask(LOG_UNIMP, "%s: not implemented: 0x%" HWADDR_PRIx "\n",
-                __func__, addr);
+                      __func__, addr);
         return 0;
     }
-
-    return s->regs[addr];
 }
 
 static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data,
@@ -324,20 +325,18 @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data,
         return;
     }
 
-    if (!aspeed_smc_is_implemented(s, addr)) {
+    if (addr == s->r_conf ||
+        addr == s->r_timings ||
+        addr == s->r_ce_ctrl) {
+        s->regs[addr] = value;
+    } else if (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs) {
+        s->regs[addr] = value;
+        aspeed_smc_update_cs(s);
+    } else {
         qemu_log_mask(LOG_UNIMP, "%s: not implemented: 0x%" HWADDR_PRIx "\n",
                       __func__, addr);
         return;
     }
-
-    /*
-     * Not much to do apart from storing the value and set the cs
-     * lines if the register is a controlling one.
-     */
-    s->regs[addr] = value;
-    if (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs) {
-        aspeed_smc_update_cs(s);
-    }
 }
 
 static const MemoryRegionOps aspeed_smc_ops = {
diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c
index eb84b74532..13798b3cb8 100644
--- a/hw/virtio/virtio-mmio.c
+++ b/hw/virtio/virtio-mmio.c
@@ -91,6 +91,7 @@ typedef struct {
     VirtioBusState bus;
     bool ioeventfd_disabled;
     bool ioeventfd_started;
+    bool format_transport_address;
 } VirtIOMMIOProxy;
 
 static bool virtio_mmio_ioeventfd_started(DeviceState *d)
@@ -469,6 +470,12 @@ assign_error:
 
 /* virtio-mmio device */
 
+static Property virtio_mmio_properties[] = {
+    DEFINE_PROP_BOOL("format_transport_address", VirtIOMMIOProxy,
+                     format_transport_address, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static void virtio_mmio_realizefn(DeviceState *d, Error **errp)
 {
     VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d);
@@ -489,6 +496,7 @@ static void virtio_mmio_class_init(ObjectClass *klass, void *data)
     dc->realize = virtio_mmio_realizefn;
     dc->reset = virtio_mmio_reset;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    dc->props = virtio_mmio_properties;
 }
 
 static const TypeInfo virtio_mmio_info = {
@@ -500,6 +508,46 @@ static const TypeInfo virtio_mmio_info = {
 
 /* virtio-mmio-bus. */
 
+static char *virtio_mmio_bus_get_dev_path(DeviceState *dev)
+{
+    BusState *virtio_mmio_bus;
+    VirtIOMMIOProxy *virtio_mmio_proxy;
+    char *proxy_path;
+    SysBusDevice *proxy_sbd;
+    char *path;
+
+    virtio_mmio_bus = qdev_get_parent_bus(dev);
+    virtio_mmio_proxy = VIRTIO_MMIO(virtio_mmio_bus->parent);
+    proxy_path = qdev_get_dev_path(DEVICE(virtio_mmio_proxy));
+
+    /*
+     * If @format_transport_address is false, then we just perform the same as
+     * virtio_bus_get_dev_path(): we delegate the address formatting for the
+     * device on the virtio-mmio bus to the bus that the virtio-mmio proxy
+     * (i.e., the device that implements the virtio-mmio bus) resides on. In
+     * this case the base address of the virtio-mmio transport will be
+     * invisible.
+     */
+    if (!virtio_mmio_proxy->format_transport_address) {
+        return proxy_path;
+    }
+
+    /* Otherwise, we append the base address of the transport. */
+    proxy_sbd = SYS_BUS_DEVICE(virtio_mmio_proxy);
+    assert(proxy_sbd->num_mmio == 1);
+    assert(proxy_sbd->mmio[0].memory == &virtio_mmio_proxy->iomem);
+
+    if (proxy_path) {
+        path = g_strdup_printf("%s/virtio-mmio@" TARGET_FMT_plx, proxy_path,
+                               proxy_sbd->mmio[0].addr);
+    } else {
+        path = g_strdup_printf("virtio-mmio@" TARGET_FMT_plx,
+                               proxy_sbd->mmio[0].addr);
+    }
+    g_free(proxy_path);
+    return path;
+}
+
 static void virtio_mmio_bus_class_init(ObjectClass *klass, void *data)
 {
     BusClass *bus_class = BUS_CLASS(klass);
@@ -516,6 +564,7 @@ static void virtio_mmio_bus_class_init(ObjectClass *klass, void *data)
     k->ioeventfd_assign = virtio_mmio_ioeventfd_assign;
     k->has_variable_vring_alignment = true;
     bus_class->max_dev = 1;
+    bus_class->get_dev_path = virtio_mmio_bus_get_dev_path;
 }
 
 static const TypeInfo virtio_mmio_bus_info = {
diff --git a/include/hw/compat.h b/include/hw/compat.h
index 636befedb4..9914e7a59e 100644
--- a/include/hw/compat.h
+++ b/include/hw/compat.h
@@ -2,7 +2,11 @@
 #define HW_COMPAT_H
 
 #define HW_COMPAT_2_6 \
-    /* empty */
+    {\
+        .driver   = "virtio-mmio",\
+        .property = "format_transport_address",\
+        .value    = "off",\
+    },
 
 #define HW_COMPAT_2_5 \
     {\
diff --git a/include/hw/intc/arm_gic.h b/include/hw/intc/arm_gic.h
index 0971e37710..42bb535fd4 100644
--- a/include/hw/intc/arm_gic.h
+++ b/include/hw/intc/arm_gic.h
@@ -23,6 +23,9 @@
 
 #include "arm_gic_common.h"
 
+/* Number of SGI target-list bits */
+#define GIC_TARGETLIST_BITS 8
+
 #define TYPE_ARM_GIC "arm_gic"
 #define ARM_GIC(obj) \
      OBJECT_CHECK(GICState, (obj), TYPE_ARM_GIC)
diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h
index f72e49922f..341a3118f0 100644
--- a/include/hw/intc/arm_gicv3_common.h
+++ b/include/hw/intc/arm_gicv3_common.h
@@ -35,6 +35,9 @@
 #define GICV3_MAXIRQ 1020
 #define GICV3_MAXSPI (GICV3_MAXIRQ - GIC_INTERNAL)
 
+/* Number of SGI target-list bits */
+#define GICV3_TARGETLIST_BITS 16
+
 /* Minimum BPR for Secure, or when security not enabled */
 #define GIC_MIN_BPR 0
 /* Minimum BPR for Nonsecure when security is enabled */
diff --git a/include/hw/misc/aspeed_scu.h b/include/hw/misc/aspeed_scu.h
index 6b8e46f85f..fdfd982288 100644
--- a/include/hw/misc/aspeed_scu.h
+++ b/include/hw/misc/aspeed_scu.h
@@ -31,4 +31,9 @@ typedef struct AspeedSCUState {
     uint32_t hw_strap2;
 } AspeedSCUState;
 
+#define AST2400_A0_SILICON_REV   0x02000303U
+#define AST2500_A0_SILICON_REV   0x04000303U
+
+extern bool is_supported_silicon_rev(uint32_t silicon_rev);
+
 #endif /* ASPEED_SCU_H */
diff --git a/target-arm/helper.c b/target-arm/helper.c
index 1f9cdacc59..bdb842cc45 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -572,6 +572,102 @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     }
 }
 
+static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                               uint64_t value)
+{
+    CPUState *cs = ENV_GET_CPU(env);
+
+    tlb_flush_by_mmuidx(cs, ARMMMUIdx_S12NSE1, ARMMMUIdx_S12NSE0,
+                        ARMMMUIdx_S2NS, -1);
+}
+
+static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                  uint64_t value)
+{
+    CPUState *other_cs;
+
+    CPU_FOREACH(other_cs) {
+        tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S12NSE1,
+                            ARMMMUIdx_S12NSE0, ARMMMUIdx_S2NS, -1);
+    }
+}
+
+static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                            uint64_t value)
+{
+    /* Invalidate by IPA. This has to invalidate any structures that
+     * contain only stage 2 translation information, but does not need
+     * to apply to structures that contain combined stage 1 and stage 2
+     * translation information.
+     * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero.
+     */
+    CPUState *cs = ENV_GET_CPU(env);
+    uint64_t pageaddr;
+
+    if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
+        return;
+    }
+
+    pageaddr = sextract64(value << 12, 0, 40);
+
+    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S2NS, -1);
+}
+
+static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                               uint64_t value)
+{
+    CPUState *other_cs;
+    uint64_t pageaddr;
+
+    if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
+        return;
+    }
+
+    pageaddr = sextract64(value << 12, 0, 40);
+
+    CPU_FOREACH(other_cs) {
+        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S2NS, -1);
+    }
+}
+
+static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    CPUState *cs = ENV_GET_CPU(env);
+
+    tlb_flush_by_mmuidx(cs, ARMMMUIdx_S1E2, -1);
+}
+
+static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                 uint64_t value)
+{
+    CPUState *other_cs;
+
+    CPU_FOREACH(other_cs) {
+        tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S1E2, -1);
+    }
+}
+
+static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    CPUState *cs = ENV_GET_CPU(env);
+    uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12);
+
+    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S1E2, -1);
+}
+
+static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                 uint64_t value)
+{
+    CPUState *other_cs;
+    uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12);
+
+    CPU_FOREACH(other_cs) {
+        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S1E2, -1);
+    }
+}
+
 static const ARMCPRegInfo cp_reginfo[] = {
     /* Define the secure and non-secure FCSE identifier CP registers
      * separately because there is no secure bank in V8 (no _EL3).  This allows
@@ -3273,6 +3369,29 @@ static const ARMCPRegInfo v8_cp_reginfo[] = {
       .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_write },
     { .name = "TLBIMVAAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7,
       .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimvaa_write },
+    { .name = "TLBIMVALH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbimva_hyp_write },
+    { .name = "TLBIMVALHIS",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbimva_hyp_is_write },
+    { .name = "TLBIIPAS2",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiipas2_write },
+    { .name = "TLBIIPAS2IS",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiipas2_is_write },
+    { .name = "TLBIIPAS2L",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiipas2_write },
+    { .name = "TLBIIPAS2LIS",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiipas2_is_write },
     /* 32 bit cache operations */
     { .name = "ICIALLUIS", .cp = 15, .opc1 = 0, .crn = 7, .crm = 1, .opc2 = 0,
       .type = ARM_CP_NOP, .access = PL1_W },
@@ -3605,6 +3724,26 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
     { .name = "HTTBR", .cp = 15, .opc1 = 4, .crm = 2,
       .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_ALIAS,
       .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el[2]) },
+    { .name = "TLBIALLNSNH",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiall_nsnh_write },
+    { .name = "TLBIALLNSNHIS",
+      .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiall_nsnh_is_write },
+    { .name = "TLBIALLH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiall_hyp_write },
+    { .name = "TLBIALLHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbiall_hyp_is_write },
+    { .name = "TLBIMVAH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbimva_hyp_write },
+    { .name = "TLBIMVAHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1,
+      .type = ARM_CP_NO_RAW, .access = PL2_W,
+      .writefn = tlbimva_hyp_is_write },
     { .name = "TLBI_ALLE2", .state = ARM_CP_STATE_AA64,
       .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0,
       .type = ARM_CP_NO_RAW, .access = PL2_W,
diff --git a/util/cutils.c b/util/cutils.c
index 5830a688dc..7505fdaa81 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -184,6 +184,13 @@ int qemu_fdatasync(int fd)
 #define SPLAT(p)       _mm_set1_epi8(*(p))
 #define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
 #define VEC_OR(v1, v2) (_mm_or_si128(v1, v2))
+#elif defined(__aarch64__)
+#include "arm_neon.h"
+#define VECTYPE        uint64x2_t
+#define ALL_EQ(v1, v2) \
+        ((vgetq_lane_u64(v1, 0) == vgetq_lane_u64(v2, 0)) && \
+         (vgetq_lane_u64(v1, 1) == vgetq_lane_u64(v2, 1)))
+#define VEC_OR(v1, v2) ((v1) | (v2))
 #else
 #define VECTYPE        unsigned long
 #define SPLAT(p)       (*(p) * (~0UL / 255))