Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20150213' into staging

target-arm queue:
 * PCIe support in virt board
 * Support 32-bit guests on 64-bit KVM hosts in virt board
 * Fixes to avoid C undefined behaviour

# gpg: Signature made Fri 13 Feb 2015 05:53:07 GMT using RSA key ID 14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"

* remotes/pmaydell/tags/pull-target-arm-20150213:
  target-arm: A64: Avoid signed shifts in disas_ldst_pair()
  target-arm: A64: Avoid left shifting negative integers in disas_pc_rel_addr
  target-arm: A64: Fix handling of rotate in logic_imm_decode_wmask
  target-arm: A64: Fix shifts into sign bit
  target-arm: Add AArch32 guest support to KVM64
  target-arm: Add 32/64-bit register sync
  target-arm: Add feature parsing to virt
  target-arm: Add CPU property to disable AArch64
  pci: Move PCI VGA to pci.mak
  arm: Add PCIe host bridge in virt machine
  pci: Add generic PCIe host bridge
  pci: Allocate PCIe host bridge PCI ID

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

27 files changed, 678 insertions, 49 deletions

diff --git a/default-configs/alpha-softmmu.mak b/default-configs/alpha-softmmu.mak
index bc07600f96..7f6161eba9 100644
--- a/default-configs/alpha-softmmu.mak
+++ b/default-configs/alpha-softmmu.mak
@@ -5,8 +5,6 @@ include usb.mak
 CONFIG_SERIAL=y
 CONFIG_I8254=y
 CONFIG_PCKBD=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_VGA_CIRRUS=y
 CONFIG_IDE_CORE=y
 CONFIG_IDE_QDEV=y
diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak
index f3513fa124..7671ee278a 100644
--- a/default-configs/arm-softmmu.mak
+++ b/default-configs/arm-softmmu.mak
@@ -82,6 +82,8 @@ CONFIG_ZYNQ=y
 CONFIG_VERSATILE_PCI=y
 CONFIG_VERSATILE_I2C=y
 
+CONFIG_PCI_GENERIC=y
+
 CONFIG_SDHCI=y
 CONFIG_INTEGRATOR_DEBUG=y
 
diff --git a/default-configs/i386-softmmu.mak b/default-configs/i386-softmmu.mak
index 8e08841760..bd99af9942 100644
--- a/default-configs/i386-softmmu.mak
+++ b/default-configs/i386-softmmu.mak
@@ -3,9 +3,7 @@
 include pci.mak
 include sound.mak
 include usb.mak
-CONFIG_VGA=y
 CONFIG_QXL=$(CONFIG_SPICE)
-CONFIG_VGA_PCI=y
 CONFIG_VGA_ISA=y
 CONFIG_VGA_CIRRUS=y
 CONFIG_VMWARE_VGA=y
diff --git a/default-configs/mips-softmmu.mak b/default-configs/mips-softmmu.mak
index 2a80b04dc0..cce2c8116b 100644
--- a/default-configs/mips-softmmu.mak
+++ b/default-configs/mips-softmmu.mak
@@ -4,8 +4,6 @@ include pci.mak
 include sound.mak
 include usb.mak
 CONFIG_ESP=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_VGA_ISA=y
 CONFIG_VGA_ISA_MM=y
 CONFIG_VGA_CIRRUS=y
diff --git a/default-configs/mips64-softmmu.mak b/default-configs/mips64-softmmu.mak
index f1f933bc44..7a88a08adc 100644
--- a/default-configs/mips64-softmmu.mak
+++ b/default-configs/mips64-softmmu.mak
@@ -4,8 +4,6 @@ include pci.mak
 include sound.mak
 include usb.mak
 CONFIG_ESP=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_VGA_ISA=y
 CONFIG_VGA_ISA_MM=y
 CONFIG_VGA_CIRRUS=y
diff --git a/default-configs/mips64el-softmmu.mak b/default-configs/mips64el-softmmu.mak
index 317b151361..095de43186 100644
--- a/default-configs/mips64el-softmmu.mak
+++ b/default-configs/mips64el-softmmu.mak
@@ -4,8 +4,6 @@ include pci.mak
 include sound.mak
 include usb.mak
 CONFIG_ESP=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_VGA_ISA=y
 CONFIG_VGA_ISA_MM=y
 CONFIG_VGA_CIRRUS=y
diff --git a/default-configs/mipsel-softmmu.mak b/default-configs/mipsel-softmmu.mak
index 7708185f6b..0e25108b7f 100644
--- a/default-configs/mipsel-softmmu.mak
+++ b/default-configs/mipsel-softmmu.mak
@@ -4,8 +4,6 @@ include pci.mak
 include sound.mak
 include usb.mak
 CONFIG_ESP=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_VGA_ISA=y
 CONFIG_VGA_ISA_MM=y
 CONFIG_VGA_CIRRUS=y
diff --git a/default-configs/pci.mak b/default-configs/pci.mak
index 030cdc7d3d..bea6b01553 100644
--- a/default-configs/pci.mak
+++ b/default-configs/pci.mak
@@ -33,3 +33,5 @@ CONFIG_NVME_PCI=y
 CONFIG_SD=y
 CONFIG_SDHCI=y
 CONFIG_EDU=y
+CONFIG_VGA=y
+CONFIG_VGA_PCI=y
diff --git a/default-configs/ppc-softmmu.mak b/default-configs/ppc-softmmu.mak
index d725b23312..aebfab92eb 100644
--- a/default-configs/ppc-softmmu.mak
+++ b/default-configs/ppc-softmmu.mak
@@ -6,8 +6,6 @@ include usb.mak
 CONFIG_ISA_MMIO=y
 CONFIG_ESCC=y
 CONFIG_M48T59=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_SERIAL=y
 CONFIG_PARALLEL=y
 CONFIG_I8254=y
diff --git a/default-configs/ppc64-softmmu.mak b/default-configs/ppc64-softmmu.mak
index bd30d69347..f195a8721a 100644
--- a/default-configs/ppc64-softmmu.mak
+++ b/default-configs/ppc64-softmmu.mak
@@ -6,8 +6,6 @@ include usb.mak
 CONFIG_ISA_MMIO=y
 CONFIG_ESCC=y
 CONFIG_M48T59=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_SERIAL=y
 CONFIG_PARALLEL=y
 CONFIG_I8254=y
diff --git a/default-configs/ppcemb-softmmu.mak b/default-configs/ppcemb-softmmu.mak
index e032761457..a1b3d5f35d 100644
--- a/default-configs/ppcemb-softmmu.mak
+++ b/default-configs/ppcemb-softmmu.mak
@@ -4,8 +4,6 @@ include pci.mak
 include sound.mak
 include usb.mak
 CONFIG_M48T59=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_SERIAL=y
 CONFIG_I8257=y
 CONFIG_OPENPIC=y
diff --git a/default-configs/sparc64-softmmu.mak b/default-configs/sparc64-softmmu.mak
index 299c97b715..123bb993ef 100644
--- a/default-configs/sparc64-softmmu.mak
+++ b/default-configs/sparc64-softmmu.mak
@@ -5,8 +5,6 @@ include usb.mak
 CONFIG_ISA_MMIO=y
 CONFIG_M48T59=y
 CONFIG_PTIMER=y
-CONFIG_VGA=y
-CONFIG_VGA_PCI=y
 CONFIG_SERIAL=y
 CONFIG_PARALLEL=y
 CONFIG_PCKBD=y
diff --git a/default-configs/x86_64-softmmu.mak b/default-configs/x86_64-softmmu.mak
index 66557ac590..e7c273417b 100644
--- a/default-configs/x86_64-softmmu.mak
+++ b/default-configs/x86_64-softmmu.mak
@@ -3,9 +3,7 @@
 include pci.mak
 include sound.mak
 include usb.mak
-CONFIG_VGA=y
 CONFIG_QXL=$(CONFIG_SPICE)
-CONFIG_VGA_PCI=y
 CONFIG_VGA_ISA=y
 CONFIG_VGA_CIRRUS=y
 CONFIG_VMWARE_VGA=y
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 34d9379032..69f51ac0da 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -42,6 +42,7 @@
 #include "exec/address-spaces.h"
 #include "qemu/bitops.h"
 #include "qemu/error-report.h"
+#include "hw/pci-host/gpex.h"
 
 #define NUM_VIRTIO_TRANSPORTS 32
 
@@ -69,6 +70,7 @@ enum {
     VIRT_MMIO,
     VIRT_RTC,
     VIRT_FW_CFG,
+    VIRT_PCIE,
 };
 
 typedef struct MemMapEntry {
@@ -129,13 +131,21 @@ static const MemMapEntry a15memmap[] = {
     [VIRT_FW_CFG] =     { 0x09020000, 0x0000000a },
     [VIRT_MMIO] =       { 0x0a000000, 0x00000200 },
     /* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */
-    /* 0x10000000 .. 0x40000000 reserved for PCI */
+    /*
+     * PCIE verbose map:
+     *
+     * MMIO window      { 0x10000000, 0x2eff0000 },
+     * PIO window       { 0x3eff0000, 0x00010000 },
+     * ECAM             { 0x3f000000, 0x01000000 },
+     */
+    [VIRT_PCIE] =       { 0x10000000, 0x30000000 },
     [VIRT_MEM] =        { 0x40000000, 30ULL * 1024 * 1024 * 1024 },
 };
 
 static const int a15irqmap[] = {
     [VIRT_UART] = 1,
     [VIRT_RTC] = 2,
+    [VIRT_PCIE] = 3, /* ... to 6 */
     [VIRT_MMIO] = 16, /* ...to 16 + NUM_VIRTIO_TRANSPORTS - 1 */
 };
 
@@ -312,7 +322,7 @@ static void fdt_add_cpu_nodes(const VirtBoardInfo *vbi)
     }
 }
 
-static void fdt_add_gic_node(const VirtBoardInfo *vbi)
+static uint32_t fdt_add_gic_node(const VirtBoardInfo *vbi)
 {
     uint32_t gic_phandle;
 
@@ -331,9 +341,11 @@ static void fdt_add_gic_node(const VirtBoardInfo *vbi)
                                      2, vbi->memmap[VIRT_GIC_CPU].base,
                                      2, vbi->memmap[VIRT_GIC_CPU].size);
     qemu_fdt_setprop_cell(vbi->fdt, "/intc", "phandle", gic_phandle);
+
+    return gic_phandle;
 }
 
-static void create_gic(const VirtBoardInfo *vbi, qemu_irq *pic)
+static uint32_t create_gic(const VirtBoardInfo *vbi, qemu_irq *pic)
 {
     /* We create a standalone GIC v2 */
     DeviceState *gicdev;
@@ -380,7 +392,7 @@ static void create_gic(const VirtBoardInfo *vbi, qemu_irq *pic)
         pic[i] = qdev_get_gpio_in(gicdev, i);
     }
 
-    fdt_add_gic_node(vbi);
+    return fdt_add_gic_node(vbi);
 }
 
 static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic)
@@ -585,6 +597,119 @@ static void create_fw_cfg(const VirtBoardInfo *vbi)
     g_free(nodename);
 }
 
+static void create_pcie_irq_map(const VirtBoardInfo *vbi, uint32_t gic_phandle,
+                                int first_irq, const char *nodename)
+{
+    int devfn, pin;
+    uint32_t full_irq_map[4 * 4 * 8] = { 0 };
+    uint32_t *irq_map = full_irq_map;
+
+    for (devfn = 0; devfn <= 0x18; devfn += 0x8) {
+        for (pin = 0; pin < 4; pin++) {
+            int irq_type = GIC_FDT_IRQ_TYPE_SPI;
+            int irq_nr = first_irq + ((pin + PCI_SLOT(devfn)) % PCI_NUM_PINS);
+            int irq_level = GIC_FDT_IRQ_FLAGS_LEVEL_HI;
+            int i;
+
+            uint32_t map[] = {
+                devfn << 8, 0, 0,                           /* devfn */
+                pin + 1,                                    /* PCI pin */
+                gic_phandle, irq_type, irq_nr, irq_level }; /* GIC irq */
+
+            /* Convert map to big endian */
+            for (i = 0; i < 8; i++) {
+                irq_map[i] = cpu_to_be32(map[i]);
+            }
+            irq_map += 8;
+        }
+    }
+
+    qemu_fdt_setprop(vbi->fdt, nodename, "interrupt-map",
+                     full_irq_map, sizeof(full_irq_map));
+
+    qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupt-map-mask",
+                           0x1800, 0, 0, /* devfn (PCI_SLOT(3)) */
+                           0x7           /* PCI irq */);
+}
+
+static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic,
+                        uint32_t gic_phandle)
+{
+    hwaddr base = vbi->memmap[VIRT_PCIE].base;
+    hwaddr size = vbi->memmap[VIRT_PCIE].size;
+    hwaddr end = base + size;
+    hwaddr size_mmio;
+    hwaddr size_ioport = 64 * 1024;
+    int nr_pcie_buses = 16;
+    hwaddr size_ecam = PCIE_MMCFG_SIZE_MIN * nr_pcie_buses;
+    hwaddr base_mmio = base;
+    hwaddr base_ioport;
+    hwaddr base_ecam;
+    int irq = vbi->irqmap[VIRT_PCIE];
+    MemoryRegion *mmio_alias;
+    MemoryRegion *mmio_reg;
+    MemoryRegion *ecam_alias;
+    MemoryRegion *ecam_reg;
+    DeviceState *dev;
+    char *nodename;
+    int i;
+
+    base_ecam = QEMU_ALIGN_DOWN(end - size_ecam, size_ecam);
+    base_ioport = QEMU_ALIGN_DOWN(base_ecam - size_ioport, size_ioport);
+    size_mmio = base_ioport - base;
+
+    dev = qdev_create(NULL, TYPE_GPEX_HOST);
+    qdev_init_nofail(dev);
+
+    /* Map only the first size_ecam bytes of ECAM space */
+    ecam_alias = g_new0(MemoryRegion, 1);
+    ecam_reg = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
+    memory_region_init_alias(ecam_alias, OBJECT(dev), "pcie-ecam",
+                             ecam_reg, 0, size_ecam);
+    memory_region_add_subregion(get_system_memory(), base_ecam, ecam_alias);
+
+    /* Map the MMIO window into system address space so as to expose
+     * the section of PCI MMIO space which starts at the same base address
+     * (ie 1:1 mapping for that part of PCI MMIO space visible through
+     * the window).
+     */
+    mmio_alias = g_new0(MemoryRegion, 1);
+    mmio_reg = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 1);
+    memory_region_init_alias(mmio_alias, OBJECT(dev), "pcie-mmio",
+                             mmio_reg, base_mmio, size_mmio);
+    memory_region_add_subregion(get_system_memory(), base_mmio, mmio_alias);
+
+    /* Map IO port space */
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 2, base_ioport);
+
+    for (i = 0; i < GPEX_NUM_IRQS; i++) {
+        sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, pic[irq + i]);
+    }
+
+    nodename = g_strdup_printf("/pcie@%" PRIx64, base);
+    qemu_fdt_add_subnode(vbi->fdt, nodename);
+    qemu_fdt_setprop_string(vbi->fdt, nodename,
+                            "compatible", "pci-host-ecam-generic");
+    qemu_fdt_setprop_string(vbi->fdt, nodename, "device_type", "pci");
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "#address-cells", 3);
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "#size-cells", 2);
+    qemu_fdt_setprop_cells(vbi->fdt, nodename, "bus-range", 0,
+                           nr_pcie_buses - 1);
+
+    qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+                                 2, base_ecam, 2, size_ecam);
+    qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "ranges",
+                                 1, FDT_PCI_RANGE_IOPORT, 2, 0,
+                                 2, base_ioport, 2, size_ioport,
+                                 1, FDT_PCI_RANGE_MMIO, 2, base_mmio,
+                                 2, base_mmio, 2, size_mmio);
+
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "#interrupt-cells", 1);
+    create_pcie_irq_map(vbi, gic_phandle, irq, nodename);
+
+    g_free(nodename);
+}
+
 static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size)
 {
     const VirtBoardInfo *board = (const VirtBoardInfo *)binfo;
@@ -602,15 +727,20 @@ static void machvirt_init(MachineState *machine)
     MemoryRegion *ram = g_new(MemoryRegion, 1);
     const char *cpu_model = machine->cpu_model;
     VirtBoardInfo *vbi;
+    uint32_t gic_phandle;
+    char **cpustr;
 
     if (!cpu_model) {
         cpu_model = "cortex-a15";
     }
 
-    vbi = find_machine_info(cpu_model);
+    /* Separate the actual CPU model name from any appended features */
+    cpustr = g_strsplit(cpu_model, ",", 2);
+
+    vbi = find_machine_info(cpustr[0]);
 
     if (!vbi) {
-        error_report("mach-virt: CPU %s not supported", cpu_model);
+        error_report("mach-virt: CPU %s not supported", cpustr[0]);
         exit(1);
     }
 
@@ -624,8 +754,10 @@ static void machvirt_init(MachineState *machine)
     create_fdt(vbi);
 
     for (n = 0; n < smp_cpus; n++) {
-        ObjectClass *oc = cpu_class_by_name(TYPE_ARM_CPU, cpu_model);
+        ObjectClass *oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]);
+        CPUClass *cc = CPU_CLASS(oc);
         Object *cpuobj;
+        Error *err = NULL;
 
         if (!oc) {
             fprintf(stderr, "Unable to find CPU definition\n");
@@ -633,6 +765,13 @@ static void machvirt_init(MachineState *machine)
         }
         cpuobj = object_new(object_class_get_name(oc));
 
+        /* Handle any CPU options specified by the user */
+        cc->parse_features(CPU(cpuobj), cpustr[1], &err);
+        if (err) {
+            error_report("%s", error_get_pretty(err));
+            exit(1);
+        }
+
         if (!vms->secure) {
             object_property_set_bool(cpuobj, false, "has_el3", NULL);
         }
@@ -652,6 +791,7 @@ static void machvirt_init(MachineState *machine)
 
         object_property_set_bool(cpuobj, true, "realized", NULL);
     }
+    g_strfreev(cpustr);
     fdt_add_timer_nodes(vbi);
     fdt_add_cpu_nodes(vbi);
     fdt_add_psci_node(vbi);
@@ -663,12 +803,14 @@ static void machvirt_init(MachineState *machine)
 
     create_flash(vbi);
 
-    create_gic(vbi, pic);
+    gic_phandle = create_gic(vbi, pic);
 
     create_uart(vbi, pic);
 
     create_rtc(vbi, pic);
 
+    create_pcie(vbi, pic, gic_phandle);
+
     /* Create mmio transports, so the user can create virtio backends
      * (which will be automatically plugged in to the transports). If
      * no backend is created the transport will just sit harmlessly idle.
diff --git a/hw/pci-host/Makefile.objs b/hw/pci-host/Makefile.objs
index bb65f9c4d2..45f1f0ebab 100644
--- a/hw/pci-host/Makefile.objs
+++ b/hw/pci-host/Makefile.objs
@@ -15,3 +15,4 @@ common-obj-$(CONFIG_PCI_APB) += apb.o
 common-obj-$(CONFIG_FULONG) += bonito.o
 common-obj-$(CONFIG_PCI_PIIX) += piix.o
 common-obj-$(CONFIG_PCI_Q35) += q35.o
+common-obj-$(CONFIG_PCI_GENERIC) += gpex.o
diff --git a/hw/pci-host/gpex.c b/hw/pci-host/gpex.c
new file mode 100644
index 0000000000..9d8fb5a496
--- /dev/null
+++ b/hw/pci-host/gpex.c
@@ -0,0 +1,154 @@
+/*
+ * QEMU Generic PCI Express Bridge Emulation
+ *
+ * Copyright (C) 2015 Alexander Graf <agraf@suse.de>
+ *
+ * Code loosely based on q35.c.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ * Check out these documents for more information on the device:
+ *
+ * http://www.kernel.org/doc/Documentation/devicetree/bindings/pci/host-generic-pci.txt
+ * http://www.firmware.org/1275/practice/imap/imap0_9d.pdf
+ */
+#include "hw/hw.h"
+#include "hw/pci-host/gpex.h"
+
+/****************************************************************************
+ * GPEX host
+ */
+
+static void gpex_set_irq(void *opaque, int irq_num, int level)
+{
+    GPEXHost *s = opaque;
+
+    qemu_set_irq(s->irq[irq_num], level);
+}
+
+static void gpex_host_realize(DeviceState *dev, Error **errp)
+{
+    PCIHostState *pci = PCI_HOST_BRIDGE(dev);
+    GPEXHost *s = GPEX_HOST(dev);
+    SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
+    PCIExpressHost *pex = PCIE_HOST_BRIDGE(dev);
+    int i;
+
+    pcie_host_mmcfg_init(pex, PCIE_MMCFG_SIZE_MAX);
+    memory_region_init(&s->io_mmio, OBJECT(s), "gpex_mmio", UINT64_MAX);
+    memory_region_init(&s->io_ioport, OBJECT(s), "gpex_ioport", 64 * 1024);
+
+    sysbus_init_mmio(sbd, &pex->mmio);
+    sysbus_init_mmio(sbd, &s->io_mmio);
+    sysbus_init_mmio(sbd, &s->io_ioport);
+    for (i = 0; i < GPEX_NUM_IRQS; i++) {
+        sysbus_init_irq(sbd, &s->irq[i]);
+    }
+
+    pci->bus = pci_register_bus(dev, "pcie.0", gpex_set_irq,
+                                pci_swizzle_map_irq_fn, s, &s->io_mmio,
+                                &s->io_ioport, 0, 4, TYPE_PCIE_BUS);
+
+    qdev_set_parent_bus(DEVICE(&s->gpex_root), BUS(pci->bus));
+    qdev_init_nofail(DEVICE(&s->gpex_root));
+}
+
+static const char *gpex_host_root_bus_path(PCIHostState *host_bridge,
+                                          PCIBus *rootbus)
+{
+    return "0000:00";
+}
+
+static void gpex_host_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass);
+
+    hc->root_bus_path = gpex_host_root_bus_path;
+    dc->realize = gpex_host_realize;
+    set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+    dc->fw_name = "pci";
+}
+
+static void gpex_host_initfn(Object *obj)
+{
+    GPEXHost *s = GPEX_HOST(obj);
+    GPEXRootState *root = &s->gpex_root;
+
+    object_initialize(root, sizeof(*root), TYPE_GPEX_ROOT_DEVICE);
+    object_property_add_child(obj, "gpex_root", OBJECT(root), NULL);
+    qdev_prop_set_uint32(DEVICE(root), "addr", PCI_DEVFN(0, 0));
+    qdev_prop_set_bit(DEVICE(root), "multifunction", false);
+}
+
+static const TypeInfo gpex_host_info = {
+    .name       = TYPE_GPEX_HOST,
+    .parent     = TYPE_PCIE_HOST_BRIDGE,
+    .instance_size = sizeof(GPEXHost),
+    .instance_init = gpex_host_initfn,
+    .class_init = gpex_host_class_init,
+};
+
+/****************************************************************************
+ * GPEX Root D0:F0
+ */
+
+static const VMStateDescription vmstate_gpex_root = {
+    .name = "gpex_root",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_PCI_DEVICE(parent_obj, GPEXRootState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void gpex_root_class_init(ObjectClass *klass, void *data)
+{
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
+    dc->desc = "QEMU generic PCIe host bridge";
+    dc->vmsd = &vmstate_gpex_root;
+    k->vendor_id = PCI_VENDOR_ID_REDHAT;
+    k->device_id = PCI_DEVICE_ID_REDHAT_PCIE_HOST;
+    k->revision = 0;
+    k->class_id = PCI_CLASS_BRIDGE_HOST;
+    /*
+     * PCI-facing part of the host bridge, not usable without the
+     * host-facing part, which can't be device_add'ed, yet.
+     */
+    dc->cannot_instantiate_with_device_add_yet = true;
+}
+
+static const TypeInfo gpex_root_info = {
+    .name = TYPE_GPEX_ROOT_DEVICE,
+    .parent = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(GPEXRootState),
+    .class_init = gpex_root_class_init,
+};
+
+static void gpex_register(void)
+{
+    type_register_static(&gpex_root_info);
+    type_register_static(&gpex_host_info);
+}
+
+type_init(gpex_register)
diff --git a/include/hw/pci-host/gpex.h b/include/hw/pci-host/gpex.h
new file mode 100644
index 0000000000..68c93488c9
--- /dev/null
+++ b/include/hw/pci-host/gpex.h
@@ -0,0 +1,56 @@
+/*
+ * QEMU Generic PCI Express Bridge Emulation
+ *
+ * Copyright (C) 2015 Alexander Graf <agraf@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>
+ */
+
+#ifndef HW_GPEX_H
+#define HW_GPEX_H
+
+#include "hw/hw.h"
+#include "hw/sysbus.h"
+#include "hw/pci/pci.h"
+#include "hw/pci/pcie_host.h"
+
+#define TYPE_GPEX_HOST "gpex-pcihost"
+#define GPEX_HOST(obj) \
+     OBJECT_CHECK(GPEXHost, (obj), TYPE_GPEX_HOST)
+
+#define TYPE_GPEX_ROOT_DEVICE "gpex-root"
+#define MCH_PCI_DEVICE(obj) \
+     OBJECT_CHECK(GPEXRootState, (obj), TYPE_GPEX_ROOT_DEVICE)
+
+#define GPEX_NUM_IRQS 4
+
+typedef struct GPEXRootState {
+    /*< private >*/
+    PCIDevice parent_obj;
+    /*< public >*/
+} GPEXRootState;
+
+typedef struct GPEXHost {
+    /*< private >*/
+    PCIExpressHost parent_obj;
+    /*< public >*/
+
+    GPEXRootState gpex_root;
+
+    MemoryRegion io_ioport;
+    MemoryRegion io_mmio;
+    qemu_irq irq[GPEX_NUM_IRQS];
+} GPEXHost;
+
+#endif /* HW_GPEX_H */
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 97a83d362f..bdee464e61 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -89,6 +89,7 @@
 #define PCI_DEVICE_ID_REDHAT_SERIAL4     0x0004
 #define PCI_DEVICE_ID_REDHAT_TEST        0x0005
 #define PCI_DEVICE_ID_REDHAT_SDHCI       0x0007
+#define PCI_DEVICE_ID_REDHAT_PCIE_HOST   0x0008
 #define PCI_DEVICE_ID_REDHAT_QXL         0x0100
 
 #define FMT_PCIBUS                      PRIx64
diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h
index 899f05c138..359e14304f 100644
--- a/include/sysemu/device_tree.h
+++ b/include/sysemu/device_tree.h
@@ -110,4 +110,13 @@ int qemu_fdt_setprop_sized_cells_from_array(void *fdt,
                                                 qdt_tmp);                 \
     })
 
+#define FDT_PCI_RANGE_RELOCATABLE          0x80000000
+#define FDT_PCI_RANGE_PREFETCHABLE         0x40000000
+#define FDT_PCI_RANGE_ALIASED              0x20000000
+#define FDT_PCI_RANGE_TYPE_MASK            0x03000000
+#define FDT_PCI_RANGE_MMIO_64BIT           0x03000000
+#define FDT_PCI_RANGE_MMIO                 0x02000000
+#define FDT_PCI_RANGE_IOPORT               0x01000000
+#define FDT_PCI_RANGE_CONFIG               0x00000000
+
 #endif /* __DEVICE_TREE_H__ */
diff --git a/target-arm/cpu.c b/target-arm/cpu.c
index d38af747ac..986f04cfd6 100644
--- a/target-arm/cpu.c
+++ b/target-arm/cpu.c
@@ -544,13 +544,16 @@ static ObjectClass *arm_cpu_class_by_name(const char *cpu_model)
 {
     ObjectClass *oc;
     char *typename;
+    char **cpuname;
 
     if (!cpu_model) {
         return NULL;
     }
 
-    typename = g_strdup_printf("%s-" TYPE_ARM_CPU, cpu_model);
+    cpuname = g_strsplit(cpu_model, ",", 1);
+    typename = g_strdup_printf("%s-" TYPE_ARM_CPU, cpuname[0]);
     oc = object_class_by_name(typename);
+    g_strfreev(cpuname);
     g_free(typename);
     if (!oc || !object_class_dynamic_cast(oc, TYPE_ARM_CPU) ||
         object_class_is_abstract(oc)) {
diff --git a/target-arm/cpu.h b/target-arm/cpu.h
index 1830a12d4a..11845a6644 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -495,6 +495,8 @@ typedef struct CPUARMState {
 ARMCPU *cpu_arm_init(const char *cpu_model);
 int cpu_arm_exec(CPUARMState *s);
 uint32_t do_arm_semihosting(CPUARMState *env);
+void aarch64_sync_32_to_64(CPUARMState *env);
+void aarch64_sync_64_to_32(CPUARMState *env);
 
 static inline bool is_a64(CPUARMState *env)
 {
diff --git a/target-arm/cpu64.c b/target-arm/cpu64.c
index bb778b3d92..823c739f08 100644
--- a/target-arm/cpu64.c
+++ b/target-arm/cpu64.c
@@ -32,6 +32,11 @@ static inline void set_feature(CPUARMState *env, int feature)
     env->features |= 1ULL << feature;
 }
 
+static inline void unset_feature(CPUARMState *env, int feature)
+{
+    env->features &= ~(1ULL << feature);
+}
+
 #ifndef CONFIG_USER_ONLY
 static uint64_t a57_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
@@ -170,8 +175,42 @@ static const ARMCPUInfo aarch64_cpus[] = {
     { .name = NULL }
 };
 
+static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    return arm_feature(&cpu->env, ARM_FEATURE_AARCH64);
+}
+
+static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    /* At this time, this property is only allowed if KVM is enabled.  This
+     * restriction allows us to avoid fixing up functionality that assumes a
+     * uniform execution state like do_interrupt.
+     */
+    if (!kvm_enabled()) {
+        error_setg(errp, "'aarch64' feature cannot be disabled "
+                         "unless KVM is enabled");
+        return;
+    }
+
+    if (value == false) {
+        unset_feature(&cpu->env, ARM_FEATURE_AARCH64);
+    } else {
+        set_feature(&cpu->env, ARM_FEATURE_AARCH64);
+    }
+}
+
 static void aarch64_cpu_initfn(Object *obj)
 {
+    object_property_add_bool(obj, "aarch64", aarch64_cpu_get_aarch64,
+                             aarch64_cpu_set_aarch64, NULL);
+    object_property_set_description(obj, "aarch64",
+                                    "Set on/off to enable/disable aarch64 "
+                                    "execution state ",
+                                    NULL);
 }
 
 static void aarch64_cpu_finalizefn(Object *obj)
diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c
index 8aa40e9763..7e0d038563 100644
--- a/target-arm/helper-a64.c
+++ b/target-arm/helper-a64.c
@@ -466,7 +466,6 @@ void aarch64_cpu_do_interrupt(CPUState *cs)
     unsigned int new_el = arm_excp_target_el(cs, cs->exception_index);
     target_ulong addr = env->cp15.vbar_el[new_el];
     unsigned int new_mode = aarch64_pstate_mode(new_el, true);
-    int i;
 
     if (arm_current_el(env) < new_el) {
         if (env->aarch64) {
@@ -530,9 +529,7 @@ void aarch64_cpu_do_interrupt(CPUState *cs)
         }
         env->elr_el[new_el] = env->regs[15];
 
-        for (i = 0; i < 15; i++) {
-            env->xregs[i] = env->regs[i];
-        }
+        aarch64_sync_32_to_64(env);
 
         env->condexec_bits = 0;
     }
diff --git a/target-arm/helper.c b/target-arm/helper.c
index 1a1a00577e..3bc20af04f 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -4096,6 +4096,11 @@ unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx)
     return 1;
 }
 
+void aarch64_sync_64_to_32(CPUARMState *env)
+{
+    g_assert_not_reached();
+}
+
 #else
 
 /* Map CPU modes onto saved register banks.  */
@@ -4425,6 +4430,212 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs)
     env->thumb = addr & 1;
 }
 
+/* Function used to synchronize QEMU's AArch64 register set with AArch32
+ * register set.  This is necessary when switching between AArch32 and AArch64
+ * execution state.
+ */
+void aarch64_sync_32_to_64(CPUARMState *env)
+{
+    int i;
+    uint32_t mode = env->uncached_cpsr & CPSR_M;
+
+    /* We can blanket copy R[0:7] to X[0:7] */
+    for (i = 0; i < 8; i++) {
+        env->xregs[i] = env->regs[i];
+    }
+
+    /* Unless we are in FIQ mode, x8-x12 come from the user registers r8-r12.
+     * Otherwise, they come from the banked user regs.
+     */
+    if (mode == ARM_CPU_MODE_FIQ) {
+        for (i = 8; i < 13; i++) {
+            env->xregs[i] = env->usr_regs[i - 8];
+        }
+    } else {
+        for (i = 8; i < 13; i++) {
+            env->xregs[i] = env->regs[i];
+        }
+    }
+
+    /* Registers x13-x23 are the various mode SP and FP registers. Registers
+     * r13 and r14 are only copied if we are in that mode, otherwise we copy
+     * from the mode banked register.
+     */
+    if (mode == ARM_CPU_MODE_USR || mode == ARM_CPU_MODE_SYS) {
+        env->xregs[13] = env->regs[13];
+        env->xregs[14] = env->regs[14];
+    } else {
+        env->xregs[13] = env->banked_r13[bank_number(ARM_CPU_MODE_USR)];
+        /* HYP is an exception in that it is copied from r14 */
+        if (mode == ARM_CPU_MODE_HYP) {
+            env->xregs[14] = env->regs[14];
+        } else {
+            env->xregs[14] = env->banked_r14[bank_number(ARM_CPU_MODE_USR)];
+        }
+    }
+
+    if (mode == ARM_CPU_MODE_HYP) {
+        env->xregs[15] = env->regs[13];
+    } else {
+        env->xregs[15] = env->banked_r13[bank_number(ARM_CPU_MODE_HYP)];
+    }
+
+    if (mode == ARM_CPU_MODE_IRQ) {
+        env->xregs[16] = env->regs[13];
+        env->xregs[17] = env->regs[14];
+    } else {
+        env->xregs[16] = env->banked_r13[bank_number(ARM_CPU_MODE_IRQ)];
+        env->xregs[17] = env->banked_r14[bank_number(ARM_CPU_MODE_IRQ)];
+    }
+
+    if (mode == ARM_CPU_MODE_SVC) {
+        env->xregs[18] = env->regs[13];
+        env->xregs[19] = env->regs[14];
+    } else {
+        env->xregs[18] = env->banked_r13[bank_number(ARM_CPU_MODE_SVC)];
+        env->xregs[19] = env->banked_r14[bank_number(ARM_CPU_MODE_SVC)];
+    }
+
+    if (mode == ARM_CPU_MODE_ABT) {
+        env->xregs[20] = env->regs[13];
+        env->xregs[21] = env->regs[14];
+    } else {
+        env->xregs[20] = env->banked_r13[bank_number(ARM_CPU_MODE_ABT)];
+        env->xregs[21] = env->banked_r14[bank_number(ARM_CPU_MODE_ABT)];
+    }
+
+    if (mode == ARM_CPU_MODE_UND) {
+        env->xregs[22] = env->regs[13];
+        env->xregs[23] = env->regs[14];
+    } else {
+        env->xregs[22] = env->banked_r13[bank_number(ARM_CPU_MODE_UND)];
+        env->xregs[23] = env->banked_r14[bank_number(ARM_CPU_MODE_UND)];
+    }
+
+    /* Registers x24-x30 are mapped to r8-r14 in FIQ mode.  If we are in FIQ
+     * mode, then we can copy from r8-r14.  Otherwise, we copy from the
+     * FIQ bank for r8-r14.
+     */
+    if (mode == ARM_CPU_MODE_FIQ) {
+        for (i = 24; i < 31; i++) {
+            env->xregs[i] = env->regs[i - 16];   /* X[24:30] <- R[8:14] */
+        }
+    } else {
+        for (i = 24; i < 29; i++) {
+            env->xregs[i] = env->fiq_regs[i - 24];
+        }
+        env->xregs[29] = env->banked_r13[bank_number(ARM_CPU_MODE_FIQ)];
+        env->xregs[30] = env->banked_r14[bank_number(ARM_CPU_MODE_FIQ)];
+    }
+
+    env->pc = env->regs[15];
+}
+
+/* Function used to synchronize QEMU's AArch32 register set with AArch64
+ * register set.  This is necessary when switching between AArch32 and AArch64
+ * execution state.
+ */
+void aarch64_sync_64_to_32(CPUARMState *env)
+{
+    int i;
+    uint32_t mode = env->uncached_cpsr & CPSR_M;
+
+    /* We can blanket copy X[0:7] to R[0:7] */
+    for (i = 0; i < 8; i++) {
+        env->regs[i] = env->xregs[i];
+    }
+
+    /* Unless we are in FIQ mode, r8-r12 come from the user registers x8-x12.
+     * Otherwise, we copy x8-x12 into the banked user regs.
+     */
+    if (mode == ARM_CPU_MODE_FIQ) {
+        for (i = 8; i < 13; i++) {
+            env->usr_regs[i - 8] = env->xregs[i];
+        }
+    } else {
+        for (i = 8; i < 13; i++) {
+            env->regs[i] = env->xregs[i];
+        }
+    }
+
+    /* Registers r13 & r14 depend on the current mode.
+     * If we are in a given mode, we copy the corresponding x registers to r13
+     * and r14.  Otherwise, we copy the x register to the banked r13 and r14
+     * for the mode.
+     */
+    if (mode == ARM_CPU_MODE_USR || mode == ARM_CPU_MODE_SYS) {
+        env->regs[13] = env->xregs[13];
+        env->regs[14] = env->xregs[14];
+    } else {
+        env->banked_r13[bank_number(ARM_CPU_MODE_USR)] = env->xregs[13];
+
+        /* HYP is an exception in that it does not have its own banked r14 but
+         * shares the USR r14
+         */
+        if (mode == ARM_CPU_MODE_HYP) {
+            env->regs[14] = env->xregs[14];
+        } else {
+            env->banked_r14[bank_number(ARM_CPU_MODE_USR)] = env->xregs[14];
+        }
+    }
+
+    if (mode == ARM_CPU_MODE_HYP) {
+        env->regs[13] = env->xregs[15];
+    } else {
+        env->banked_r13[bank_number(ARM_CPU_MODE_HYP)] = env->xregs[15];
+    }
+
+    if (mode == ARM_CPU_MODE_IRQ) {
+        env->regs[13] = env->xregs[16];
+        env->regs[14] = env->xregs[17];
+    } else {
+        env->banked_r13[bank_number(ARM_CPU_MODE_IRQ)] = env->xregs[16];
+        env->banked_r14[bank_number(ARM_CPU_MODE_IRQ)] = env->xregs[17];
+    }
+
+    if (mode == ARM_CPU_MODE_SVC) {
+        env->regs[13] = env->xregs[18];
+        env->regs[14] = env->xregs[19];
+    } else {
+        env->banked_r13[bank_number(ARM_CPU_MODE_SVC)] = env->xregs[18];
+        env->banked_r14[bank_number(ARM_CPU_MODE_SVC)] = env->xregs[19];
+    }
+
+    if (mode == ARM_CPU_MODE_ABT) {
+        env->regs[13] = env->xregs[20];
+        env->regs[14] = env->xregs[21];
+    } else {
+        env->banked_r13[bank_number(ARM_CPU_MODE_ABT)] = env->xregs[20];
+        env->banked_r14[bank_number(ARM_CPU_MODE_ABT)] = env->xregs[21];
+    }
+
+    if (mode == ARM_CPU_MODE_UND) {
+        env->regs[13] = env->xregs[22];
+        env->regs[14] = env->xregs[23];
+    } else {
+        env->banked_r13[bank_number(ARM_CPU_MODE_UND)] = env->xregs[22];
+        env->banked_r14[bank_number(ARM_CPU_MODE_UND)] = env->xregs[23];
+    }
+
+    /* Registers x24-x30 are mapped to r8-r14 in FIQ mode.  If we are in FIQ
+     * mode, then we can copy to r8-r14.  Otherwise, we copy to the
+     * FIQ bank for r8-r14.
+     */
+    if (mode == ARM_CPU_MODE_FIQ) {
+        for (i = 24; i < 31; i++) {
+            env->regs[i - 16] = env->xregs[i];   /* X[24:30] -> R[8:14] */
+        }
+    } else {
+        for (i = 24; i < 29; i++) {
+            env->fiq_regs[i - 24] = env->xregs[i];
+        }
+        env->banked_r13[bank_number(ARM_CPU_MODE_FIQ)] = env->xregs[29];
+        env->banked_r14[bank_number(ARM_CPU_MODE_FIQ)] = env->xregs[30];
+    }
+
+    env->regs[15] = env->pc;
+}
+
 /* Handle a CPU exception.  */
 void arm_cpu_do_interrupt(CPUState *cs)
 {
diff --git a/target-arm/kvm64.c b/target-arm/kvm64.c
index 033babf551..8cf3a627ec 100644
--- a/target-arm/kvm64.c
+++ b/target-arm/kvm64.c
@@ -82,7 +82,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
     ARMCPU *cpu = ARM_CPU(cs);
 
     if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE ||
-        !arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+        !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) {
         fprintf(stderr, "KVM is not supported for this guest CPU type\n");
         return -EINVAL;
     }
@@ -96,6 +96,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
         cpu->psci_version = 2;
         cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2;
     }
+    if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_EL1_32BIT;
+    }
 
     /* Do KVM_ARM_VCPU_INIT ioctl */
     ret = kvm_arm_vcpu_init(cs);
@@ -133,6 +136,13 @@ int kvm_arch_put_registers(CPUState *cs, int level)
     ARMCPU *cpu = ARM_CPU(cs);
     CPUARMState *env = &cpu->env;
 
+    /* If we are in AArch32 mode then we need to copy the AArch32 regs to the
+     * AArch64 registers before pushing them out to 64-bit KVM.
+     */
+    if (!is_a64(env)) {
+        aarch64_sync_32_to_64(env);
+    }
+
     for (i = 0; i < 31; i++) {
         reg.id = AARCH64_CORE_REG(regs.regs[i]);
         reg.addr = (uintptr_t) &env->xregs[i];
@@ -162,7 +172,11 @@ int kvm_arch_put_registers(CPUState *cs, int level)
     }
 
     /* Note that KVM thinks pstate is 64 bit but we use a uint32_t */
-    val = pstate_read(env);
+    if (is_a64(env)) {
+        val = pstate_read(env);
+    } else {
+        val = cpsr_read(env);
+    }
     reg.id = AARCH64_CORE_REG(regs.pstate);
     reg.addr = (uintptr_t) &val;
     ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
@@ -242,7 +256,14 @@ int kvm_arch_get_registers(CPUState *cs)
     if (ret) {
         return ret;
     }
-    pstate_write(env, val);
+
+    env->aarch64 = ((val & PSTATE_nRW) == 0);
+    if (is_a64(env)) {
+        pstate_write(env, val);
+    } else {
+        env->uncached_cpsr = val & CPSR_M;
+        cpsr_write(env, val, 0xffffffff);
+    }
 
     /* KVM puts SP_EL0 in regs.sp and SP_EL1 in regs.sp_el1. On the
      * QEMU side we keep the current SP in xregs[31] as well.
@@ -256,6 +277,15 @@ int kvm_arch_get_registers(CPUState *cs)
         return ret;
     }
 
+    /* If we are in AArch32 mode then we need to sync the AArch32 regs with the
+     * incoming AArch64 regs received from 64-bit KVM.
+     * We must perform this after all of the registers have been acquired from
+     * the kernel.
+     */
+    if (!is_a64(env)) {
+        aarch64_sync_64_to_32(env);
+    }
+
     reg.id = AARCH64_CORE_REG(elr_el1);
     reg.addr = (uintptr_t) &env->elr_el[1];
     ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c
index 2bed914770..7713022752 100644
--- a/target-arm/op_helper.c
+++ b/target-arm/op_helper.c
@@ -465,7 +465,7 @@ void HELPER(exception_return)(CPUARMState *env)
     int cur_el = arm_current_el(env);
     unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el);
     uint32_t spsr = env->banked_spsr[spsr_idx];
-    int new_el, i;
+    int new_el;
 
     aarch64_save_sp(env, cur_el);
 
@@ -491,9 +491,7 @@ void HELPER(exception_return)(CPUARMState *env)
         if (!arm_singlestep_active(env)) {
             env->uncached_cpsr &= ~PSTATE_SS;
         }
-        for (i = 0; i < 15; i++) {
-            env->regs[i] = env->xregs[i];
-        }
+        aarch64_sync_64_to_32(env);
 
         env->regs[15] = env->elr_el[1] & ~0x1;
     } else {
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index acf4b162bd..9f54501a9e 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -1077,7 +1077,7 @@ static void disas_uncond_b_imm(DisasContext *s, uint32_t insn)
 {
     uint64_t addr = s->pc + sextract32(insn, 0, 26) * 4 - 4;
 
-    if (insn & (1 << 31)) {
+    if (insn & (1U << 31)) {
         /* C5.6.26 BL Branch with link */
         tcg_gen_movi_i64(cpu_reg(s, 30), s->pc);
     }
@@ -1271,7 +1271,7 @@ static void gen_get_nzcv(TCGv_i64 tcg_rt)
     TCGv_i32 nzcv = tcg_temp_new_i32();
 
     /* build bit 31, N */
-    tcg_gen_andi_i32(nzcv, cpu_NF, (1 << 31));
+    tcg_gen_andi_i32(nzcv, cpu_NF, (1U << 31));
     /* build bit 30, Z */
     tcg_gen_setcondi_i32(TCG_COND_EQ, tmp, cpu_ZF, 0);
     tcg_gen_deposit_i32(nzcv, nzcv, tmp, 30, 1);
@@ -1296,7 +1296,7 @@ static void gen_set_nzcv(TCGv_i64 tcg_rt)
     tcg_gen_trunc_i64_i32(nzcv, tcg_rt);
 
     /* bit 31, N */
-    tcg_gen_andi_i32(cpu_NF, nzcv, (1 << 31));
+    tcg_gen_andi_i32(cpu_NF, nzcv, (1U << 31));
     /* bit 30, Z */
     tcg_gen_andi_i32(cpu_ZF, nzcv, (1 << 30));
     tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_ZF, cpu_ZF, 0);
@@ -1917,7 +1917,7 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn)
     int rt = extract32(insn, 0, 5);
     int rn = extract32(insn, 5, 5);
     int rt2 = extract32(insn, 10, 5);
-    int64_t offset = sextract32(insn, 15, 7);
+    uint64_t offset = sextract64(insn, 15, 7);
     int index = extract32(insn, 23, 2);
     bool is_vector = extract32(insn, 26, 1);
     bool is_load = extract32(insn, 22, 1);
@@ -2662,11 +2662,12 @@ static void disas_pc_rel_adr(DisasContext *s, uint32_t insn)
 {
     unsigned int page, rd;
     uint64_t base;
-    int64_t offset;
+    uint64_t offset;
 
     page = extract32(insn, 31, 1);
     /* SignExtend(immhi:immlo) -> offset */
-    offset = ((int64_t)sextract32(insn, 5, 19) << 2) | extract32(insn, 29, 2);
+    offset = sextract64(insn, 5, 19);
+    offset = offset << 2 | extract32(insn, 29, 2);
     rd = extract32(insn, 0, 5);
     base = s->pc - 4;
 
@@ -2820,7 +2821,10 @@ static bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn,
      * by r within the element (which is e bits wide)...
      */
     mask = bitmask64(s + 1);
-    mask = (mask >> r) | (mask << (e - r));
+    if (r) {
+        mask = (mask >> r) | (mask << (e - r));
+        mask &= bitmask64(e);
+    }
     /* ...then replicate the element over the whole 64 bit value */
     mask = bitfield_replicate(mask, e);
     *result = mask;