Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200213' into staging

target-arm queue:
 * i.MX: Fix inverted sense of register bits in watchdog timer
 * i.MX: Add support for WDT on i.MX6
 * arm/virt: cleanups to ACPI tables
 * Implement ARMv8.1-VMID16 extension
 * Implement ARMv8.1-PAN
 * Implement ARMv8.2-UAO
 * Implement ARMv8.2-ATS1E1
 * ast2400/2500/2600: Wire up EHCI controllers
 * hw/char/exynos4210_uart: Fix memleaks in exynos4210_uart_init
 * hw/arm/raspi: Clean up the board code

# gpg: Signature made Thu 13 Feb 2020 14:40:34 GMT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20200213: (46 commits)
  target/arm: Implement ARMv8.1-VMID16 extension
  hw/arm/raspi: Extract the cores count from the board revision
  hw/arm/raspi: Use a unique raspi_machine_class_init() method
  hw/arm/raspi: Extract the board model from the board revision
  hw/arm/raspi: Set default RAM size to size encoded in board revision
  hw/arm/raspi: Let class_init() directly call raspi_machine_init()
  hw/arm/raspi: Make board_rev a field of RaspiMachineClass
  hw/arm/raspi: Make machines children of abstract RaspiMachineClass
  hw/arm/raspi: Trivial code movement
  hw/arm/raspi: Extract the processor type from the board revision
  hw/arm/raspi: Extract the RAM size from the board revision
  hw/arm/raspi: Extract the version from the board revision
  hw/arm/raspi: Correct the board descriptions
  hw/arm/raspi: Use BCM2708 machine type with pre Device Tree kernels
  hw/char/exynos4210_uart: Fix memleaks in exynos4210_uart_init
  hw/arm: ast2600: Wire up EHCI controllers
  hw/arm: ast2400/ast2500: Wire up EHCI controllers
  target/arm: Enable ARMv8.2-UAO in -cpu max
  target/arm: Implement UAO semantics
  target/arm: Update MSR access to UAO
  ...

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

23 files changed, 731 insertions, 187 deletions

diff --git a/hw/arm/aspeed_ast2600.c b/hw/arm/aspeed_ast2600.c
index 90cf1c7..446b44d 100644
--- a/hw/arm/aspeed_ast2600.c
+++ b/hw/arm/aspeed_ast2600.c
@@ -31,6 +31,8 @@ static const hwaddr aspeed_soc_ast2600_memmap[] = {
     [ASPEED_FMC]       = 0x1E620000,
     [ASPEED_SPI1]      = 0x1E630000,
     [ASPEED_SPI2]      = 0x1E641000,
+    [ASPEED_EHCI1]     = 0x1E6A1000,
+    [ASPEED_EHCI2]     = 0x1E6A3000,
     [ASPEED_MII1]      = 0x1E650000,
     [ASPEED_MII2]      = 0x1E650008,
     [ASPEED_MII3]      = 0x1E650010,
@@ -79,6 +81,8 @@ static const int aspeed_soc_ast2600_irqmap[] = {
     [ASPEED_ADC]       = 78,
     [ASPEED_XDMA]      = 6,
     [ASPEED_SDHCI]     = 43,
+    [ASPEED_EHCI1]     = 5,
+    [ASPEED_EHCI2]     = 9,
     [ASPEED_EMMC]      = 15,
     [ASPEED_GPIO]      = 40,
     [ASPEED_GPIO_1_8V] = 11,
@@ -166,6 +170,11 @@ static void aspeed_soc_ast2600_init(Object *obj)
                               sizeof(s->spi[i]), typename);
     }
 
+    for (i = 0; i < sc->ehcis_num; i++) {
+        sysbus_init_child_obj(obj, "ehci[*]", OBJECT(&s->ehci[i]),
+                              sizeof(s->ehci[i]), TYPE_PLATFORM_EHCI);
+    }
+
     snprintf(typename, sizeof(typename), "aspeed.sdmc-%s", socname);
     sysbus_init_child_obj(obj, "sdmc", OBJECT(&s->sdmc), sizeof(s->sdmc),
                           typename);
@@ -416,6 +425,19 @@ static void aspeed_soc_ast2600_realize(DeviceState *dev, Error **errp)
                         s->spi[i].ctrl->flash_window_base);
     }
 
+    /* EHCI */
+    for (i = 0; i < sc->ehcis_num; i++) {
+        object_property_set_bool(OBJECT(&s->ehci[i]), true, "realized", &err);
+        if (err) {
+            error_propagate(errp, err);
+            return;
+        }
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->ehci[i]), 0,
+                        sc->memmap[ASPEED_EHCI1 + i]);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->ehci[i]), 0,
+                           aspeed_soc_get_irq(s, ASPEED_EHCI1 + i));
+    }
+
     /* SDMC - SDRAM Memory Controller */
     object_property_set_bool(OBJECT(&s->sdmc), true, "realized", &err);
     if (err) {
@@ -534,6 +556,7 @@ static void aspeed_soc_ast2600_class_init(ObjectClass *oc, void *data)
     sc->silicon_rev  = AST2600_A0_SILICON_REV;
     sc->sram_size    = 0x10000;
     sc->spis_num     = 2;
+    sc->ehcis_num    = 2;
     sc->wdts_num     = 4;
     sc->macs_num     = 4;
     sc->irqmap       = aspeed_soc_ast2600_irqmap;
diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c
index b5e809a..696c7fd 100644
--- a/hw/arm/aspeed_soc.c
+++ b/hw/arm/aspeed_soc.c
@@ -30,6 +30,7 @@ static const hwaddr aspeed_soc_ast2400_memmap[] = {
     [ASPEED_IOMEM]  = 0x1E600000,
     [ASPEED_FMC]    = 0x1E620000,
     [ASPEED_SPI1]   = 0x1E630000,
+    [ASPEED_EHCI1]  = 0x1E6A1000,
     [ASPEED_VIC]    = 0x1E6C0000,
     [ASPEED_SDMC]   = 0x1E6E0000,
     [ASPEED_SCU]    = 0x1E6E2000,
@@ -59,6 +60,8 @@ static const hwaddr aspeed_soc_ast2500_memmap[] = {
     [ASPEED_FMC]    = 0x1E620000,
     [ASPEED_SPI1]   = 0x1E630000,
     [ASPEED_SPI2]   = 0x1E631000,
+    [ASPEED_EHCI1]  = 0x1E6A1000,
+    [ASPEED_EHCI2]  = 0x1E6A3000,
     [ASPEED_VIC]    = 0x1E6C0000,
     [ASPEED_SDMC]   = 0x1E6E0000,
     [ASPEED_SCU]    = 0x1E6E2000,
@@ -91,6 +94,8 @@ static const int aspeed_soc_ast2400_irqmap[] = {
     [ASPEED_UART5]  = 10,
     [ASPEED_VUART]  = 8,
     [ASPEED_FMC]    = 19,
+    [ASPEED_EHCI1]  = 5,
+    [ASPEED_EHCI2]  = 13,
     [ASPEED_SDMC]   = 0,
     [ASPEED_SCU]    = 21,
     [ASPEED_ADC]    = 31,
@@ -180,6 +185,11 @@ static void aspeed_soc_init(Object *obj)
                               sizeof(s->spi[i]), typename);
     }
 
+    for (i = 0; i < sc->ehcis_num; i++) {
+        sysbus_init_child_obj(obj, "ehci[*]", OBJECT(&s->ehci[i]),
+                              sizeof(s->ehci[i]), TYPE_PLATFORM_EHCI);
+    }
+
     snprintf(typename, sizeof(typename), "aspeed.sdmc-%s", socname);
     sysbus_init_child_obj(obj, "sdmc", OBJECT(&s->sdmc), sizeof(s->sdmc),
                           typename);
@@ -364,6 +374,19 @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp)
                         s->spi[i].ctrl->flash_window_base);
     }
 
+    /* EHCI */
+    for (i = 0; i < sc->ehcis_num; i++) {
+        object_property_set_bool(OBJECT(&s->ehci[i]), true, "realized", &err);
+        if (err) {
+            error_propagate(errp, err);
+            return;
+        }
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->ehci[i]), 0,
+                        sc->memmap[ASPEED_EHCI1 + i]);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->ehci[i]), 0,
+                           aspeed_soc_get_irq(s, ASPEED_EHCI1 + i));
+    }
+
     /* SDMC - SDRAM Memory Controller */
     object_property_set_bool(OBJECT(&s->sdmc), true, "realized", &err);
     if (err) {
@@ -472,6 +495,7 @@ static void aspeed_soc_ast2400_class_init(ObjectClass *oc, void *data)
     sc->silicon_rev  = AST2400_A1_SILICON_REV;
     sc->sram_size    = 0x8000;
     sc->spis_num     = 1;
+    sc->ehcis_num    = 1;
     sc->wdts_num     = 2;
     sc->macs_num     = 2;
     sc->irqmap       = aspeed_soc_ast2400_irqmap;
@@ -496,6 +520,7 @@ static void aspeed_soc_ast2500_class_init(ObjectClass *oc, void *data)
     sc->silicon_rev  = AST2500_A1_SILICON_REV;
     sc->sram_size    = 0x9000;
     sc->spis_num     = 2;
+    sc->ehcis_num    = 2;
     sc->wdts_num     = 3;
     sc->macs_num     = 2;
     sc->irqmap       = aspeed_soc_ast2500_irqmap;
diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c
index 552145b..ecc6285 100644
--- a/hw/arm/fsl-imx6.c
+++ b/hw/arm/fsl-imx6.c
@@ -91,6 +91,12 @@ static void fsl_imx6_init(Object *obj)
         sysbus_init_child_obj(obj, name, &s->spi[i], sizeof(s->spi[i]),
                               TYPE_IMX_SPI);
     }
+    for (i = 0; i < FSL_IMX6_NUM_WDTS; i++) {
+        snprintf(name, NAME_SIZE, "wdt%d", i);
+        sysbus_init_child_obj(obj, name, &s->wdt[i], sizeof(s->wdt[i]),
+                              TYPE_IMX2_WDT);
+    }
+
 
     sysbus_init_child_obj(obj, "eth", &s->eth, sizeof(s->eth), TYPE_IMX_ENET);
 }
@@ -383,6 +389,21 @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp)
                        qdev_get_gpio_in(DEVICE(&s->a9mpcore),
                                         FSL_IMX6_ENET_MAC_1588_IRQ));
 
+    /*
+     * Watchdog
+     */
+    for (i = 0; i < FSL_IMX6_NUM_WDTS; i++) {
+        static const hwaddr FSL_IMX6_WDOGn_ADDR[FSL_IMX6_NUM_WDTS] = {
+            FSL_IMX6_WDOG1_ADDR,
+            FSL_IMX6_WDOG2_ADDR,
+        };
+
+        object_property_set_bool(OBJECT(&s->wdt[i]), true, "realized",
+                                 &error_abort);
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, FSL_IMX6_WDOGn_ADDR[i]);
+    }
+
     /* ROM memory */
     memory_region_init_rom(&s->rom, NULL, "imx6.rom",
                            FSL_IMX6_ROM_SIZE, &err);
diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c
index 3996f6c..90ad9b8 100644
--- a/hw/arm/raspi.c
+++ b/hw/arm/raspi.c
@@ -13,9 +13,11 @@
 
 #include "qemu/osdep.h"
 #include "qemu/units.h"
+#include "qemu/cutils.h"
 #include "qapi/error.h"
 #include "cpu.h"
 #include "hw/arm/bcm2836.h"
+#include "hw/registerfields.h"
 #include "qemu/error-report.h"
 #include "hw/boards.h"
 #include "hw/loader.h"
@@ -29,13 +31,104 @@
 #define FIRMWARE_ADDR_3 0x80000 /* Pi 3 loads kernel.img here by default */
 #define SPINTABLE_ADDR  0xd8 /* Pi 3 bootloader spintable */
 
-/* Table of Linux board IDs for different Pi versions */
-static const int raspi_boardid[] = {[1] = 0xc42, [2] = 0xc43, [3] = 0xc44};
+/* Registered machine type (matches RPi Foundation bootloader and U-Boot) */
+#define MACH_TYPE_BCM2708   3138
 
-typedef struct RasPiState {
+typedef struct RaspiMachineState {
+    /*< private >*/
+    MachineState parent_obj;
+    /*< public >*/
     BCM283XState soc;
     MemoryRegion ram;
-} RasPiState;
+} RaspiMachineState;
+
+typedef struct RaspiMachineClass {
+    /*< private >*/
+    MachineClass parent_obj;
+    /*< public >*/
+    uint32_t board_rev;
+} RaspiMachineClass;
+
+#define TYPE_RASPI_MACHINE       MACHINE_TYPE_NAME("raspi-common")
+#define RASPI_MACHINE(obj) \
+    OBJECT_CHECK(RaspiMachineState, (obj), TYPE_RASPI_MACHINE)
+
+#define RASPI_MACHINE_CLASS(klass) \
+     OBJECT_CLASS_CHECK(RaspiMachineClass, (klass), TYPE_RASPI_MACHINE)
+#define RASPI_MACHINE_GET_CLASS(obj) \
+     OBJECT_GET_CLASS(RaspiMachineClass, (obj), TYPE_RASPI_MACHINE)
+
+/*
+ * Board revision codes:
+ * www.raspberrypi.org/documentation/hardware/raspberrypi/revision-codes/
+ */
+FIELD(REV_CODE, REVISION,           0, 4);
+FIELD(REV_CODE, TYPE,               4, 8);
+FIELD(REV_CODE, PROCESSOR,         12, 4);
+FIELD(REV_CODE, MANUFACTURER,      16, 4);
+FIELD(REV_CODE, MEMORY_SIZE,       20, 3);
+FIELD(REV_CODE, STYLE,             23, 1);
+
+static uint64_t board_ram_size(uint32_t board_rev)
+{
+    assert(FIELD_EX32(board_rev, REV_CODE, STYLE)); /* Only new style */
+    return 256 * MiB << FIELD_EX32(board_rev, REV_CODE, MEMORY_SIZE);
+}
+
+static int board_processor_id(uint32_t board_rev)
+{
+    assert(FIELD_EX32(board_rev, REV_CODE, STYLE)); /* Only new style */
+    return FIELD_EX32(board_rev, REV_CODE, PROCESSOR);
+}
+
+static int board_version(uint32_t board_rev)
+{
+    return board_processor_id(board_rev) + 1;
+}
+
+static const char *board_soc_type(uint32_t board_rev)
+{
+    static const char *soc_types[] = {
+        NULL, TYPE_BCM2836, TYPE_BCM2837,
+    };
+    int proc_id = board_processor_id(board_rev);
+
+    if (proc_id >= ARRAY_SIZE(soc_types) || !soc_types[proc_id]) {
+        error_report("Unsupported processor id '%d' (board revision: 0x%x)",
+                     proc_id, board_rev);
+        exit(1);
+    }
+    return soc_types[proc_id];
+}
+
+static int cores_count(uint32_t board_rev)
+{
+    static const int soc_cores_count[] = {
+        0, BCM283X_NCPUS, BCM283X_NCPUS,
+    };
+    int proc_id = board_processor_id(board_rev);
+
+    if (proc_id >= ARRAY_SIZE(soc_cores_count) || !soc_cores_count[proc_id]) {
+        error_report("Unsupported processor id '%d' (board revision: 0x%x)",
+                     proc_id, board_rev);
+        exit(1);
+    }
+    return soc_cores_count[proc_id];
+}
+
+static const char *board_type(uint32_t board_rev)
+{
+    static const char *types[] = {
+        "A", "B", "A+", "B+", "2B", "Alpha", "CM1", NULL, "3B", "Zero",
+        "CM3", NULL, "Zero W", "3B+", "3A+", NULL, "CM3+", "4B",
+    };
+    assert(FIELD_EX32(board_rev, REV_CODE, STYLE)); /* Only new style */
+    int bt = FIELD_EX32(board_rev, REV_CODE, TYPE);
+    if (bt >= ARRAY_SIZE(types) || !types[bt]) {
+        return "Unknown";
+    }
+    return types[bt];
+}
 
 static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info)
 {
@@ -116,7 +209,7 @@ static void setup_boot(MachineState *machine, int version, size_t ram_size)
     static struct arm_boot_info binfo;
     int r;
 
-    binfo.board_id = raspi_boardid[version];
+    binfo.board_id = MACH_TYPE_BCM2708;
     binfo.ram_size = ram_size;
     binfo.nb_cpus = machine->smp.cpus;
 
@@ -164,25 +257,26 @@ static void setup_boot(MachineState *machine, int version, size_t ram_size)
     arm_load_kernel(ARM_CPU(first_cpu), machine, &binfo);
 }
 
-static void raspi_init(MachineState *machine, int version)
+static void raspi_machine_init(MachineState *machine)
 {
-    RasPiState *s = g_new0(RasPiState, 1);
+    RaspiMachineClass *mc = RASPI_MACHINE_GET_CLASS(machine);
+    RaspiMachineState *s = RASPI_MACHINE(machine);
+    uint32_t board_rev = mc->board_rev;
+    int version = board_version(board_rev);
+    uint64_t ram_size = board_ram_size(board_rev);
     uint32_t vcram_size;
     DriveInfo *di;
     BlockBackend *blk;
     BusState *bus;
     DeviceState *carddev;
 
-    if (machine->ram_size > 1 * GiB) {
-        error_report("Requested ram size is too large for this machine: "
-                     "maximum is 1GB");
+    if (machine->ram_size != ram_size) {
+        char *size_str = size_to_str(ram_size);
+        error_report("Invalid RAM size, should be %s", size_str);
+        g_free(size_str);
         exit(1);
     }
 
-    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
-                            version == 3 ? TYPE_BCM2837 : TYPE_BCM2836,
-                            &error_abort, NULL);
-
     /* Allocate and map RAM */
     memory_region_allocate_system_memory(&s->ram, OBJECT(machine), "ram",
                                          machine->ram_size);
@@ -190,9 +284,10 @@ static void raspi_init(MachineState *machine, int version)
     memory_region_add_subregion_overlap(get_system_memory(), 0, &s->ram, 0);
 
     /* Setup the SOC */
+    object_initialize_child(OBJECT(machine), "soc", &s->soc, sizeof(s->soc),
+                            board_soc_type(board_rev), &error_abort, NULL);
     object_property_add_const_link(OBJECT(&s->soc), "ram", OBJECT(&s->ram),
                                    &error_abort);
-    int board_rev = version == 3 ? 0xa02082 : 0xa21041;
     object_property_set_int(OBJECT(&s->soc), board_rev, "board-rev",
                             &error_abort);
     object_property_set_bool(OBJECT(&s->soc), true, "realized", &error_abort);
@@ -214,45 +309,46 @@ static void raspi_init(MachineState *machine, int version)
     setup_boot(machine, version, machine->ram_size - vcram_size);
 }
 
-static void raspi2_init(MachineState *machine)
+static void raspi_machine_class_init(ObjectClass *oc, void *data)
 {
-    raspi_init(machine, 2);
-}
+    MachineClass *mc = MACHINE_CLASS(oc);
+    RaspiMachineClass *rmc = RASPI_MACHINE_CLASS(oc);
+    uint32_t board_rev = (uint32_t)(uintptr_t)data;
 
-static void raspi2_machine_init(MachineClass *mc)
-{
-    mc->desc = "Raspberry Pi 2";
-    mc->init = raspi2_init;
+    rmc->board_rev = board_rev;
+    mc->desc = g_strdup_printf("Raspberry Pi %s", board_type(board_rev));
+    mc->init = raspi_machine_init;
     mc->block_default_type = IF_SD;
     mc->no_parallel = 1;
     mc->no_floppy = 1;
     mc->no_cdrom = 1;
-    mc->max_cpus = BCM283X_NCPUS;
-    mc->min_cpus = BCM283X_NCPUS;
-    mc->default_cpus = BCM283X_NCPUS;
-    mc->default_ram_size = 1 * GiB;
-    mc->ignore_memory_transaction_failures = true;
+    mc->default_cpus = mc->min_cpus = mc->max_cpus = cores_count(board_rev);
+    mc->default_ram_size = board_ram_size(board_rev);
+    if (board_version(board_rev) == 2) {
+        mc->ignore_memory_transaction_failures = true;
+    }
 };
-DEFINE_MACHINE("raspi2", raspi2_machine_init)
 
+static const TypeInfo raspi_machine_types[] = {
+    {
+        .name           = MACHINE_TYPE_NAME("raspi2"),
+        .parent         = TYPE_RASPI_MACHINE,
+        .class_init     = raspi_machine_class_init,
+        .class_data     = (void *)0xa21041,
 #ifdef TARGET_AARCH64
-static void raspi3_init(MachineState *machine)
-{
-    raspi_init(machine, 3);
-}
-
-static void raspi3_machine_init(MachineClass *mc)
-{
-    mc->desc = "Raspberry Pi 3";
-    mc->init = raspi3_init;
-    mc->block_default_type = IF_SD;
-    mc->no_parallel = 1;
-    mc->no_floppy = 1;
-    mc->no_cdrom = 1;
-    mc->max_cpus = BCM283X_NCPUS;
-    mc->min_cpus = BCM283X_NCPUS;
-    mc->default_cpus = BCM283X_NCPUS;
-    mc->default_ram_size = 1 * GiB;
-}
-DEFINE_MACHINE("raspi3", raspi3_machine_init)
+    }, {
+        .name           = MACHINE_TYPE_NAME("raspi3"),
+        .parent         = TYPE_RASPI_MACHINE,
+        .class_init     = raspi_machine_class_init,
+        .class_data     = (void *)0xa02082,
 #endif
+    }, {
+        .name           = TYPE_RASPI_MACHINE,
+        .parent         = TYPE_MACHINE,
+        .instance_size  = sizeof(RaspiMachineState),
+        .class_size     = sizeof(RaspiMachineClass),
+        .abstract       = true,
+    }
+};
+
+DEFINE_TYPES(raspi_machine_types)
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index bd5f771..fb4b166 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -78,11 +78,6 @@ static void acpi_dsdt_add_uart(Aml *scope, const MemMapEntry *uart_memmap,
                              AML_EXCLUSIVE, &uart_irq, 1));
     aml_append(dev, aml_name_decl("_CRS", crs));
 
-    /* The _ADR entry is used to link this device to the UART described
-     * in the SPCR table, i.e. SPCR.base_address.address == _ADR.
-     */
-    aml_append(dev, aml_name_decl("_ADR", aml_int(uart_memmap->base)));
-
     aml_append(scope, dev);
 }
 
@@ -156,7 +151,7 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
 {
     int ecam_id = VIRT_ECAM_ID(highmem_ecam);
     Aml *method, *crs, *ifctx, *UUID, *ifctx1, *elsectx, *buf;
-    int i, bus_no;
+    int i, slot_no;
     hwaddr base_mmio = memmap[VIRT_PCIE_MMIO].base;
     hwaddr size_mmio = memmap[VIRT_PCIE_MMIO].size;
     hwaddr base_pio = memmap[VIRT_PCIE_PIO].base;
@@ -170,18 +165,17 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
     aml_append(dev, aml_name_decl("_CID", aml_string("PNP0A03")));
     aml_append(dev, aml_name_decl("_SEG", aml_int(0)));
     aml_append(dev, aml_name_decl("_BBN", aml_int(0)));
-    aml_append(dev, aml_name_decl("_ADR", aml_int(0)));
     aml_append(dev, aml_name_decl("_UID", aml_string("PCI0")));
     aml_append(dev, aml_name_decl("_STR", aml_unicode("PCIe 0 Device")));
     aml_append(dev, aml_name_decl("_CCA", aml_int(1)));
 
     /* Declare the PCI Routing Table. */
-    Aml *rt_pkg = aml_varpackage(nr_pcie_buses * PCI_NUM_PINS);
-    for (bus_no = 0; bus_no < nr_pcie_buses; bus_no++) {
+    Aml *rt_pkg = aml_varpackage(PCI_SLOT_MAX * PCI_NUM_PINS);
+    for (slot_no = 0; slot_no < PCI_SLOT_MAX; slot_no++) {
         for (i = 0; i < PCI_NUM_PINS; i++) {
-            int gsi = (i + bus_no) % PCI_NUM_PINS;
+            int gsi = (i + slot_no) % PCI_NUM_PINS;
             Aml *pkg = aml_package(4);
-            aml_append(pkg, aml_int((bus_no << 16) | 0xFFFF));
+            aml_append(pkg, aml_int((slot_no << 16) | 0xFFFF));
             aml_append(pkg, aml_int(i));
             aml_append(pkg, aml_name("GSI%d", gsi));
             aml_append(pkg, aml_int(0));
@@ -195,7 +189,7 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
         uint32_t irqs =  irq + i;
         Aml *dev_gsi = aml_device("GSI%d", i);
         aml_append(dev_gsi, aml_name_decl("_HID", aml_string("PNP0C0F")));
-        aml_append(dev_gsi, aml_name_decl("_UID", aml_int(0)));
+        aml_append(dev_gsi, aml_name_decl("_UID", aml_int(i)));
         crs = aml_resource_template();
         aml_append(crs,
                    aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH,
@@ -242,7 +236,6 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
                              size_mmio_high));
     }
 
-    aml_append(method, aml_name_decl("RBUF", rbuf));
     aml_append(method, aml_return(rbuf));
     aml_append(dev, method);
 
@@ -317,10 +310,6 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
     aml_append(method, aml_return(buf));
     aml_append(dev, method);
 
-    Aml *dev_rp0 = aml_device("%s", "RP0");
-    aml_append(dev_rp0, aml_name_decl("_ADR", aml_int(0)));
-    aml_append(dev, dev_rp0);
-
     Aml *dev_res0 = aml_device("%s", "RES0");
     aml_append(dev_res0, aml_name_decl("_HID", aml_string("PNP0C02")));
     crs = aml_resource_template();
@@ -338,7 +327,6 @@ static void acpi_dsdt_add_gpio(Aml *scope, const MemMapEntry *gpio_memmap,
 {
     Aml *dev = aml_device("GPO0");
     aml_append(dev, aml_name_decl("_HID", aml_string("ARMH0061")));
-    aml_append(dev, aml_name_decl("_ADR", aml_int(0)));
     aml_append(dev, aml_name_decl("_UID", aml_int(0)));
 
     Aml *crs = aml_resource_template();
@@ -368,7 +356,6 @@ static void acpi_dsdt_add_power_button(Aml *scope)
 {
     Aml *dev = aml_device(ACPI_POWER_BUTTON_DEVICE);
     aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C0C")));
-    aml_append(dev, aml_name_decl("_ADR", aml_int(0)));
     aml_append(dev, aml_name_decl("_UID", aml_int(0)));
     aml_append(scope, dev);
 }
diff --git a/hw/char/exynos4210_uart.c b/hw/char/exynos4210_uart.c
index 25d6588..96d5180 100644
--- a/hw/char/exynos4210_uart.c
+++ b/hw/char/exynos4210_uart.c
@@ -674,8 +674,6 @@ static void exynos4210_uart_init(Object *obj)
     SysBusDevice *dev = SYS_BUS_DEVICE(obj);
     Exynos4210UartState *s = EXYNOS4210_UART(dev);
 
-    s->fifo_timeout_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                                         exynos4210_uart_timeout_int, s);
     s->wordtime = NANOSECONDS_PER_SECOND * 10 / 9600;
 
     /* memory mapping */
@@ -691,6 +689,9 @@ static void exynos4210_uart_realize(DeviceState *dev, Error **errp)
 {
     Exynos4210UartState *s = EXYNOS4210_UART(dev);
 
+    s->fifo_timeout_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                         exynos4210_uart_timeout_int, s);
+
     qemu_chr_fe_set_handlers(&s->chr, exynos4210_uart_can_receive,
                              exynos4210_uart_receive, exynos4210_uart_event,
                              NULL, s, NULL, true);
diff --git a/hw/misc/imx2_wdt.c b/hw/misc/imx2_wdt.c
index 5576778..2aedfe8 100644
--- a/hw/misc/imx2_wdt.c
+++ b/hw/misc/imx2_wdt.c
@@ -29,7 +29,7 @@ static void imx2_wdt_write(void *opaque, hwaddr addr,
                            uint64_t value, unsigned int size)
 {
     if (addr == IMX2_WDT_WCR &&
-        (value & (IMX2_WDT_WCR_WDA | IMX2_WDT_WCR_SRS))) {
+        (~value & (IMX2_WDT_WCR_WDA | IMX2_WDT_WCR_SRS))) {
         watchdog_perform_action();
     }
 }
diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h
index 90ac7f7..78b9f6a 100644
--- a/include/hw/arm/aspeed_soc.h
+++ b/include/hw/arm/aspeed_soc.h
@@ -26,8 +26,10 @@
 #include "target/arm/cpu.h"
 #include "hw/gpio/aspeed_gpio.h"
 #include "hw/sd/aspeed_sdhci.h"
+#include "hw/usb/hcd-ehci.h"
 
 #define ASPEED_SPIS_NUM  2
+#define ASPEED_EHCIS_NUM 2
 #define ASPEED_WDTS_NUM  4
 #define ASPEED_CPUS_NUM  2
 #define ASPEED_MACS_NUM  4
@@ -50,6 +52,7 @@ typedef struct AspeedSoCState {
     AspeedXDMAState xdma;
     AspeedSMCState fmc;
     AspeedSMCState spi[ASPEED_SPIS_NUM];
+    EHCISysBusState ehci[ASPEED_EHCIS_NUM];
     AspeedSDMCState sdmc;
     AspeedWDTState wdt[ASPEED_WDTS_NUM];
     FTGMAC100State ftgmac100[ASPEED_MACS_NUM];
@@ -71,6 +74,7 @@ typedef struct AspeedSoCClass {
     uint32_t silicon_rev;
     uint64_t sram_size;
     int spis_num;
+    int ehcis_num;
     int wdts_num;
     int macs_num;
     const int *irqmap;
@@ -94,6 +98,8 @@ enum {
     ASPEED_FMC,
     ASPEED_SPI1,
     ASPEED_SPI2,
+    ASPEED_EHCI1,
+    ASPEED_EHCI2,
     ASPEED_VIC,
     ASPEED_SDMC,
     ASPEED_SCU,
diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h
index 1265a55..60eadcc 100644
--- a/include/hw/arm/fsl-imx6.h
+++ b/include/hw/arm/fsl-imx6.h
@@ -21,6 +21,7 @@
 #include "hw/cpu/a9mpcore.h"
 #include "hw/misc/imx6_ccm.h"
 #include "hw/misc/imx6_src.h"
+#include "hw/misc/imx2_wdt.h"
 #include "hw/char/imx_serial.h"
 #include "hw/timer/imx_gpt.h"
 #include "hw/timer/imx_epit.h"
@@ -42,6 +43,7 @@
 #define FSL_IMX6_NUM_GPIOS 7
 #define FSL_IMX6_NUM_ESDHCS 4
 #define FSL_IMX6_NUM_ECSPIS 5
+#define FSL_IMX6_NUM_WDTS 2
 
 typedef struct FslIMX6State {
     /*< private >*/
@@ -59,6 +61,7 @@ typedef struct FslIMX6State {
     IMXGPIOState   gpio[FSL_IMX6_NUM_GPIOS];
     SDHCIState     esdhc[FSL_IMX6_NUM_ESDHCS];
     IMXSPIState    spi[FSL_IMX6_NUM_ECSPIS];
+    IMX2WdtState   wdt[FSL_IMX6_NUM_WDTS];
     IMXFECState    eth;
     MemoryRegion   rom;
     MemoryRegion   caam;
diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h
index 18ac562..d593b60 100644
--- a/target/arm/cpu-param.h
+++ b/target/arm/cpu-param.h
@@ -29,6 +29,6 @@
 # define TARGET_PAGE_BITS_MIN  10
 #endif
 
-#define NB_MMU_MODES 9
+#define NB_MMU_MODES 12
 
 #endif
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index b0762a7..de733ac 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2709,6 +2709,10 @@ static void arm_max_initfn(Object *obj)
             t = FIELD_DP32(t, MVFR2, FPMISC, 4);   /* FP MaxNum */
             cpu->isar.mvfr2 = t;
 
+            t = cpu->id_mmfr3;
+            t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */
+            cpu->id_mmfr3 = t;
+
             t = cpu->id_mmfr4;
             t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */
             cpu->id_mmfr4 = t;
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 0b3036c..e943ffe 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -871,6 +871,7 @@ struct ARMCPU {
         uint64_t id_aa64pfr1;
         uint64_t id_aa64mmfr0;
         uint64_t id_aa64mmfr1;
+        uint64_t id_aa64mmfr2;
     } isar;
     uint32_t midr;
     uint32_t revidr;
@@ -1186,12 +1187,7 @@ void pmu_init(ARMCPU *cpu);
 #define CPSR_IT_2_7 (0xfc00U)
 #define CPSR_GE (0xfU << 16)
 #define CPSR_IL (1U << 20)
-/* Note that the RESERVED bits include bit 21, which is PSTATE_SS in
- * an AArch64 SPSR but RES0 in AArch32 SPSR and CPSR. In QEMU we use
- * env->uncached_cpsr bit 21 to store PSTATE.SS when executing in AArch32,
- * where it is live state but not accessible to the AArch32 code.
- */
-#define CPSR_RESERVED (0x7U << 21)
+#define CPSR_PAN (1U << 22)
 #define CPSR_J (1U << 24)
 #define CPSR_IT_0_1 (3U << 25)
 #define CPSR_Q (1U << 27)
@@ -1209,8 +1205,6 @@ void pmu_init(ARMCPU *cpu);
 #define CPSR_USER (CPSR_NZCV | CPSR_Q | CPSR_GE)
 /* Execution state bits.  MRS read as zero, MSR writes ignored.  */
 #define CPSR_EXEC (CPSR_T | CPSR_IT | CPSR_J | CPSR_IL)
-/* Mask of bits which may be set by exception return copying them from SPSR */
-#define CPSR_ERET_MASK (~CPSR_RESERVED)
 
 /* Bit definitions for M profile XPSR. Most are the same as CPSR. */
 #define XPSR_EXCP 0x1ffU
@@ -1258,6 +1252,8 @@ void pmu_init(ARMCPU *cpu);
 #define PSTATE_BTYPE (3U << 10)
 #define PSTATE_IL (1U << 20)
 #define PSTATE_SS (1U << 21)
+#define PSTATE_PAN (1U << 22)
+#define PSTATE_UAO (1U << 23)
 #define PSTATE_V (1U << 28)
 #define PSTATE_C (1U << 29)
 #define PSTATE_Z (1U << 30)
@@ -1727,6 +1723,15 @@ FIELD(ID_ISAR6, FHM, 8, 4)
 FIELD(ID_ISAR6, SB, 12, 4)
 FIELD(ID_ISAR6, SPECRES, 16, 4)
 
+FIELD(ID_MMFR3, CMAINTVA, 0, 4)
+FIELD(ID_MMFR3, CMAINTSW, 4, 4)
+FIELD(ID_MMFR3, BPMAINT, 8, 4)
+FIELD(ID_MMFR3, MAINTBCST, 12, 4)
+FIELD(ID_MMFR3, PAN, 16, 4)
+FIELD(ID_MMFR3, COHWALK, 20, 4)
+FIELD(ID_MMFR3, CMEMSZ, 24, 4)
+FIELD(ID_MMFR3, SUPERSEC, 28, 4)
+
 FIELD(ID_MMFR4, SPECSEI, 0, 4)
 FIELD(ID_MMFR4, AC2, 4, 4)
 FIELD(ID_MMFR4, XNX, 8, 4)
@@ -1800,6 +1805,22 @@ FIELD(ID_AA64MMFR1, PAN, 20, 4)
 FIELD(ID_AA64MMFR1, SPECSEI, 24, 4)
 FIELD(ID_AA64MMFR1, XNX, 28, 4)
 
+FIELD(ID_AA64MMFR2, CNP, 0, 4)
+FIELD(ID_AA64MMFR2, UAO, 4, 4)
+FIELD(ID_AA64MMFR2, LSM, 8, 4)
+FIELD(ID_AA64MMFR2, IESB, 12, 4)
+FIELD(ID_AA64MMFR2, VARANGE, 16, 4)
+FIELD(ID_AA64MMFR2, CCIDX, 20, 4)
+FIELD(ID_AA64MMFR2, NV, 24, 4)
+FIELD(ID_AA64MMFR2, ST, 28, 4)
+FIELD(ID_AA64MMFR2, AT, 32, 4)
+FIELD(ID_AA64MMFR2, IDS, 36, 4)
+FIELD(ID_AA64MMFR2, FWB, 40, 4)
+FIELD(ID_AA64MMFR2, TTL, 48, 4)
+FIELD(ID_AA64MMFR2, BBM, 52, 4)
+FIELD(ID_AA64MMFR2, EVT, 56, 4)
+FIELD(ID_AA64MMFR2, E0PD, 60, 4)
+
 FIELD(ID_DFR0, COPDBG, 0, 4)
 FIELD(ID_DFR0, COPSDBG, 4, 4)
 FIELD(ID_DFR0, MMAPDBG, 8, 4)
@@ -2751,20 +2772,24 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
  *  5. we want to be able to use the TLB for accesses done as part of a
  *     stage1 page table walk, rather than having to walk the stage2 page
  *     table over and over.
+ *  6. we need separate EL1/EL2 mmu_idx for handling the Privileged Access
+ *     Never (PAN) bit within PSTATE.
  *
  * This gives us the following list of cases:
  *
  * NS EL0 EL1&0 stage 1+2 (aka NS PL0)
  * NS EL1 EL1&0 stage 1+2 (aka NS PL1)
+ * NS EL1 EL1&0 stage 1+2 +PAN
  * NS EL0 EL2&0
- * NS EL2 EL2&0
+ * NS EL2 EL2&0 +PAN
  * NS EL2 (aka NS PL2)
  * S EL0 EL1&0 (aka S PL0)
  * S EL1 EL1&0 (not used if EL3 is 32 bit)
+ * S EL1 EL1&0 +PAN
  * S EL3 (aka S PL1)
  * NS EL1&0 stage 2
  *
- * for a total of 9 different mmu_idx.
+ * for a total of 12 different mmu_idx.
  *
  * R profile CPUs have an MPU, but can use the same set of MMU indexes
  * as A profile. They only need to distinguish NS EL0 and NS EL1 (and
@@ -2819,19 +2844,22 @@ typedef enum ARMMMUIdx {
     /*
      * A-profile.
      */
-    ARMMMUIdx_E10_0 =  0 | ARM_MMU_IDX_A,
-    ARMMMUIdx_E20_0 =  1 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E10_0      =  0 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_0      =  1 | ARM_MMU_IDX_A,
 
-    ARMMMUIdx_E10_1 =  2 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E10_1      =  2 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E10_1_PAN  =  3 | ARM_MMU_IDX_A,
 
-    ARMMMUIdx_E2 =     3 | ARM_MMU_IDX_A,
-    ARMMMUIdx_E20_2 =  4 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E2         =  4 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_2      =  5 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_2_PAN  =  6 | ARM_MMU_IDX_A,
 
-    ARMMMUIdx_SE10_0 = 5 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE10_1 = 6 | ARM_MMU_IDX_A,
-    ARMMMUIdx_SE3 =    7 | ARM_MMU_IDX_A,
+    ARMMMUIdx_SE10_0     = 7 | ARM_MMU_IDX_A,
+    ARMMMUIdx_SE10_1     = 8 | ARM_MMU_IDX_A,
+    ARMMMUIdx_SE10_1_PAN = 9 | ARM_MMU_IDX_A,
+    ARMMMUIdx_SE3        = 10 | ARM_MMU_IDX_A,
 
-    ARMMMUIdx_Stage2 = 8 | ARM_MMU_IDX_A,
+    ARMMMUIdx_Stage2     = 11 | ARM_MMU_IDX_A,
 
     /*
      * These are not allocated TLBs and are used only for AT system
@@ -2839,6 +2867,7 @@ typedef enum ARMMMUIdx {
      */
     ARMMMUIdx_Stage1_E0 = 0 | ARM_MMU_IDX_NOTLB,
     ARMMMUIdx_Stage1_E1 = 1 | ARM_MMU_IDX_NOTLB,
+    ARMMMUIdx_Stage1_E1_PAN = 2 | ARM_MMU_IDX_NOTLB,
 
     /*
      * M-profile.
@@ -2864,10 +2893,13 @@ typedef enum ARMMMUIdxBit {
     TO_CORE_BIT(E10_0),
     TO_CORE_BIT(E20_0),
     TO_CORE_BIT(E10_1),
+    TO_CORE_BIT(E10_1_PAN),
     TO_CORE_BIT(E2),
     TO_CORE_BIT(E20_2),
+    TO_CORE_BIT(E20_2_PAN),
     TO_CORE_BIT(SE10_0),
     TO_CORE_BIT(SE10_1),
+    TO_CORE_BIT(SE10_1_PAN),
     TO_CORE_BIT(SE3),
     TO_CORE_BIT(Stage2),
 
@@ -3432,6 +3464,16 @@ static inline bool isar_feature_aa32_vminmaxnm(const ARMISARegisters *id)
     return FIELD_EX64(id->mvfr2, MVFR2, FPMISC) >= 4;
 }
 
+static inline bool isar_feature_aa32_pan(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->mvfr0, ID_MMFR3, PAN) != 0;
+}
+
+static inline bool isar_feature_aa32_ats1e1(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->mvfr0, ID_MMFR3, PAN) >= 2;
+}
+
 /*
  * 64-bit feature tests via id registers.
  */
@@ -3591,6 +3633,21 @@ static inline bool isar_feature_aa64_lor(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0;
 }
 
+static inline bool isar_feature_aa64_pan(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) != 0;
+}
+
+static inline bool isar_feature_aa64_ats1e1(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 2;
+}
+
+static inline bool isar_feature_aa64_uao(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0;
+}
+
 static inline bool isar_feature_aa64_bti(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0;
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index c80fb5f..f0d98bc 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -673,8 +673,14 @@ static void aarch64_max_initfn(Object *obj)
         t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* HPD */
         t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1);
         t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1);
+        t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 2); /* ATS1E1 */
+        t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* VMID16 */
         cpu->isar.id_aa64mmfr1 = t;
 
+        t = cpu->isar.id_aa64mmfr2;
+        t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1);
+        cpu->isar.id_aa64mmfr2 = t;
+
         /* Replicate the same data to the 32-bit id registers.  */
         u = cpu->isar.id_isar5;
         u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */
@@ -693,6 +699,10 @@ static void aarch64_max_initfn(Object *obj)
         u = FIELD_DP32(u, ID_ISAR6, SPECRES, 1);
         cpu->isar.id_isar6 = u;
 
+        u = cpu->id_mmfr3;
+        u = FIELD_DP32(u, ID_MMFR3, PAN, 2); /* ATS1E1 */
+        cpu->id_mmfr3 = u;
+
         /*
          * FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet,
          * so do not set MVFR1.FPHP.  Strictly speaking this is not legal,
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index bf45f8a..509ae93 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -959,7 +959,7 @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc)
 {
     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];
+    uint32_t mask, spsr = env->banked_spsr[spsr_idx];
     int new_el;
     bool return_to_aa64 = (spsr & PSTATE_nRW) == 0;
 
@@ -1014,7 +1014,8 @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc)
          * will sort the register banks out for us, and we've already
          * caught all the bad-mode cases in el_from_spsr().
          */
-        cpsr_write(env, spsr, ~0, CPSRWriteRaw);
+        mask = aarch32_cpsr_valid_mask(env->features, &env_archcpu(env)->isar);
+        cpsr_write(env, spsr, mask, CPSRWriteRaw);
         if (!arm_singlestep_active(env)) {
             env->uncached_cpsr &= ~PSTATE_SS;
         }
@@ -1031,6 +1032,7 @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc)
                       cur_el, new_el, env->regs[15]);
     } else {
         env->aarch64 = 1;
+        spsr &= aarch64_pstate_valid_mask(&env_archcpu(env)->isar);
         pstate_write(env, spsr);
         if (!arm_singlestep_active(env)) {
             env->pstate &= ~PSTATE_SS;
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 7d15d5c..366dbcf 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -671,6 +671,7 @@ static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     tlb_flush_by_mmuidx(cs,
                         ARMMMUIdxBit_E10_1 |
+                        ARMMMUIdxBit_E10_1_PAN |
                         ARMMMUIdxBit_E10_0 |
                         ARMMMUIdxBit_Stage2);
 }
@@ -682,6 +683,7 @@ static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     tlb_flush_by_mmuidx_all_cpus_synced(cs,
                                         ARMMMUIdxBit_E10_1 |
+                                        ARMMMUIdxBit_E10_1_PAN |
                                         ARMMMUIdxBit_E10_0 |
                                         ARMMMUIdxBit_Stage2);
 }
@@ -2700,6 +2702,7 @@ static int gt_phys_redir_timeridx(CPUARMState *env)
     switch (arm_mmu_idx(env)) {
     case ARMMMUIdx_E20_0:
     case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_E20_2_PAN:
         return GTIMER_HYP;
     default:
         return GTIMER_PHYS;
@@ -2711,6 +2714,7 @@ static int gt_virt_redir_timeridx(CPUARMState *env)
     switch (arm_mmu_idx(env)) {
     case ARMMMUIdx_E20_0:
     case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_E20_2_PAN:
         return GTIMER_HYPVIRT;
     default:
         return GTIMER_VIRT;
@@ -3261,8 +3265,7 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
         bool take_exc = false;
 
         if (fi.s1ptw && current_el == 1 && !arm_is_secure(env)
-            && (mmu_idx == ARMMMUIdx_Stage1_E1 ||
-                mmu_idx == ARMMMUIdx_Stage1_E0)) {
+            && arm_mmu_idx_is_stage1_of_2(mmu_idx)) {
             /*
              * Synchronous stage 2 fault on an access made as part of the
              * translation table walk for AT S1E0* or AT S1E1* insn
@@ -3338,7 +3341,9 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
         format64 = arm_s1_regime_using_lpae_format(env, mmu_idx);
 
         if (arm_feature(env, ARM_FEATURE_EL2)) {
-            if (mmu_idx == ARMMMUIdx_E10_0 || mmu_idx == ARMMMUIdx_E10_1) {
+            if (mmu_idx == ARMMMUIdx_E10_0 ||
+                mmu_idx == ARMMMUIdx_E10_1 ||
+                mmu_idx == ARMMMUIdx_E10_1_PAN) {
                 format64 |= env->cp15.hcr_el2 & (HCR_VM | HCR_DC);
             } else {
                 format64 |= arm_current_el(env) == 2;
@@ -3404,16 +3409,21 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
 
     switch (ri->opc2 & 6) {
     case 0:
-        /* stage 1 current state PL1: ATS1CPR, ATS1CPW */
+        /* stage 1 current state PL1: ATS1CPR, ATS1CPW, ATS1CPRP, ATS1CPWP */
         switch (el) {
         case 3:
             mmu_idx = ARMMMUIdx_SE3;
             break;
         case 2:
-            mmu_idx = ARMMMUIdx_Stage1_E1;
-            break;
+            g_assert(!secure);  /* TODO: ARMv8.4-SecEL2 */
+            /* fall through */
         case 1:
-            mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_Stage1_E1;
+            if (ri->crm == 9 && (env->uncached_cpsr & CPSR_PAN)) {
+                mmu_idx = (secure ? ARMMMUIdx_SE10_1_PAN
+                           : ARMMMUIdx_Stage1_E1_PAN);
+            } else {
+                mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_Stage1_E1;
+            }
             break;
         default:
             g_assert_not_reached();
@@ -3482,8 +3492,13 @@ static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri,
     switch (ri->opc2 & 6) {
     case 0:
         switch (ri->opc1) {
-        case 0: /* AT S1E1R, AT S1E1W */
-            mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_Stage1_E1;
+        case 0: /* AT S1E1R, AT S1E1W, AT S1E1RP, AT S1E1WP */
+            if (ri->crm == 9 && (env->pstate & PSTATE_PAN)) {
+                mmu_idx = (secure ? ARMMMUIdx_SE10_1_PAN
+                           : ARMMMUIdx_Stage1_E1_PAN);
+            } else {
+                mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_Stage1_E1;
+            }
             break;
         case 4: /* AT S1E2R, AT S1E2W */
             mmu_idx = ARMMMUIdx_E2;
@@ -3798,7 +3813,9 @@ static void vmsa_tcr_ttbr_el2_write(CPUARMState *env, const ARMCPRegInfo *ri,
     if (extract64(raw_read(env, ri) ^ value, 48, 16) &&
         (arm_hcr_el2_eff(env) & HCR_E2H)) {
         tlb_flush_by_mmuidx(env_cpu(env),
-                            ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E20_0);
+                            ARMMMUIdxBit_E20_2 |
+                            ARMMMUIdxBit_E20_2_PAN |
+                            ARMMMUIdxBit_E20_0);
     }
     raw_write(env, ri, value);
 }
@@ -3816,6 +3833,7 @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     if (raw_read(env, ri) != value) {
         tlb_flush_by_mmuidx(cs,
                             ARMMMUIdxBit_E10_1 |
+                            ARMMMUIdxBit_E10_1_PAN |
                             ARMMMUIdxBit_E10_0 |
                             ARMMMUIdxBit_Stage2);
         raw_write(env, ri, value);
@@ -4155,6 +4173,42 @@ static void aa64_daif_write(CPUARMState *env, const ARMCPRegInfo *ri,
     env->daif = value & PSTATE_DAIF;
 }
 
+static uint64_t aa64_pan_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pstate & PSTATE_PAN;
+}
+
+static void aa64_pan_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                           uint64_t value)
+{
+    env->pstate = (env->pstate & ~PSTATE_PAN) | (value & PSTATE_PAN);
+}
+
+static const ARMCPRegInfo pan_reginfo = {
+    .name = "PAN", .state = ARM_CP_STATE_AA64,
+    .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 2, .opc2 = 3,
+    .type = ARM_CP_NO_RAW, .access = PL1_RW,
+    .readfn = aa64_pan_read, .writefn = aa64_pan_write
+};
+
+static uint64_t aa64_uao_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pstate & PSTATE_UAO;
+}
+
+static void aa64_uao_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                           uint64_t value)
+{
+    env->pstate = (env->pstate & ~PSTATE_UAO) | (value & PSTATE_UAO);
+}
+
+static const ARMCPRegInfo uao_reginfo = {
+    .name = "UAO", .state = ARM_CP_STATE_AA64,
+    .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 2, .opc2 = 4,
+    .type = ARM_CP_NO_RAW, .access = PL1_RW,
+    .readfn = aa64_uao_read, .writefn = aa64_uao_write
+};
+
 static CPAccessResult aa64_cacheop_access(CPUARMState *env,
                                           const ARMCPRegInfo *ri,
                                           bool isread)
@@ -4176,12 +4230,18 @@ static int vae1_tlbmask(CPUARMState *env)
 {
     /* Since we exclude secure first, we may read HCR_EL2 directly. */
     if (arm_is_secure_below_el3(env)) {
-        return ARMMMUIdxBit_SE10_1 | ARMMMUIdxBit_SE10_0;
+        return ARMMMUIdxBit_SE10_1 |
+               ARMMMUIdxBit_SE10_1_PAN |
+               ARMMMUIdxBit_SE10_0;
     } else if ((env->cp15.hcr_el2 & (HCR_E2H | HCR_TGE))
                == (HCR_E2H | HCR_TGE)) {
-        return ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E20_0;
+        return ARMMMUIdxBit_E20_2 |
+               ARMMMUIdxBit_E20_2_PAN |
+               ARMMMUIdxBit_E20_0;
     } else {
-        return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_0;
+        return ARMMMUIdxBit_E10_1 |
+               ARMMMUIdxBit_E10_1_PAN |
+               ARMMMUIdxBit_E10_0;
     }
 }
 
@@ -4215,18 +4275,28 @@ static int alle1_tlbmask(CPUARMState *env)
      * stage 1 translations.
      */
     if (arm_is_secure_below_el3(env)) {
-        return ARMMMUIdxBit_SE10_1 | ARMMMUIdxBit_SE10_0;
+        return ARMMMUIdxBit_SE10_1 |
+               ARMMMUIdxBit_SE10_1_PAN |
+               ARMMMUIdxBit_SE10_0;
     } else if (arm_feature(env, ARM_FEATURE_EL2)) {
-        return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_0 | ARMMMUIdxBit_Stage2;
+        return ARMMMUIdxBit_E10_1 |
+               ARMMMUIdxBit_E10_1_PAN |
+               ARMMMUIdxBit_E10_0 |
+               ARMMMUIdxBit_Stage2;
     } else {
-        return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_0;
+        return ARMMMUIdxBit_E10_1 |
+               ARMMMUIdxBit_E10_1_PAN |
+               ARMMMUIdxBit_E10_0;
     }
 }
 
 static int e2_tlbmask(CPUARMState *env)
 {
     /* TODO: ARMv8.4-SecEL2 */
-    return ARMMMUIdxBit_E20_0 | ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E2;
+    return ARMMMUIdxBit_E20_0 |
+           ARMMMUIdxBit_E20_2 |
+           ARMMMUIdxBit_E20_2_PAN |
+           ARMMMUIdxBit_E2;
 }
 
 static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -6310,6 +6380,35 @@ static CPAccessResult access_lor_other(CPUARMState *env,
     return access_lor_ns(env);
 }
 
+/*
+ * A trivial implementation of ARMv8.1-LOR leaves all of these
+ * registers fixed at 0, which indicates that there are zero
+ * supported Limited Ordering regions.
+ */
+static const ARMCPRegInfo lor_reginfo[] = {
+    { .name = "LORSA_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 0,
+      .access = PL1_RW, .accessfn = access_lor_other,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    { .name = "LOREA_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 1,
+      .access = PL1_RW, .accessfn = access_lor_other,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    { .name = "LORN_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 2,
+      .access = PL1_RW, .accessfn = access_lor_other,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    { .name = "LORC_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 3,
+      .access = PL1_RW, .accessfn = access_lor_other,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    { .name = "LORID_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7,
+      .access = PL1_R, .accessfn = access_lorid,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    REGINFO_SENTINEL
+};
+
 #ifdef TARGET_AARCH64
 static CPAccessResult access_pauth(CPUARMState *env, const ARMCPRegInfo *ri,
                                    bool isread)
@@ -6612,6 +6711,32 @@ static const ARMCPRegInfo vhe_reginfo[] = {
     REGINFO_SENTINEL
 };
 
+#ifndef CONFIG_USER_ONLY
+static const ARMCPRegInfo ats1e1_reginfo[] = {
+    { .name = "AT_S1E1R", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 9, .opc2 = 0,
+      .access = PL1_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC,
+      .writefn = ats_write64 },
+    { .name = "AT_S1E1W", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 9, .opc2 = 1,
+      .access = PL1_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC,
+      .writefn = ats_write64 },
+    REGINFO_SENTINEL
+};
+
+static const ARMCPRegInfo ats1cp_reginfo[] = {
+    { .name = "ATS1CPRP",
+      .cp = 15, .opc1 = 0, .crn = 7, .crm = 9, .opc2 = 0,
+      .access = PL1_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC,
+      .writefn = ats_write },
+    { .name = "ATS1CPWP",
+      .cp = 15, .opc1 = 0, .crn = 7, .crm = 9, .opc2 = 1,
+      .access = PL1_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC,
+      .writefn = ats_write },
+    REGINFO_SENTINEL
+};
+#endif
+
 void register_cp_regs_for_features(ARMCPU *cpu)
 {
     /* Register all the coprocessor registers based on feature bits */
@@ -6966,11 +7091,11 @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .access = PL1_R, .type = ARM_CP_CONST,
               .accessfn = access_aa64_tid3,
               .resetvalue = cpu->isar.id_aa64mmfr1 },
-            { .name = "ID_AA64MMFR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64,
+            { .name = "ID_AA64MMFR2_EL1", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 2,
               .access = PL1_R, .type = ARM_CP_CONST,
               .accessfn = access_aa64_tid3,
-              .resetvalue = 0 },
+              .resetvalue = cpu->isar.id_aa64mmfr2 },
             { .name = "ID_AA64MMFR3_EL1_RESERVED", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 3,
               .access = PL1_R, .type = ARM_CP_CONST,
@@ -7544,36 +7669,22 @@ void register_cp_regs_for_features(ARMCPU *cpu)
     }
 
     if (cpu_isar_feature(aa64_lor, cpu)) {
-        /*
-         * A trivial implementation of ARMv8.1-LOR leaves all of these
-         * registers fixed at 0, which indicates that there are zero
-         * supported Limited Ordering regions.
-         */
-        static const ARMCPRegInfo lor_reginfo[] = {
-            { .name = "LORSA_EL1", .state = ARM_CP_STATE_AA64,
-              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 0,
-              .access = PL1_RW, .accessfn = access_lor_other,
-              .type = ARM_CP_CONST, .resetvalue = 0 },
-            { .name = "LOREA_EL1", .state = ARM_CP_STATE_AA64,
-              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 1,
-              .access = PL1_RW, .accessfn = access_lor_other,
-              .type = ARM_CP_CONST, .resetvalue = 0 },
-            { .name = "LORN_EL1", .state = ARM_CP_STATE_AA64,
-              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 2,
-              .access = PL1_RW, .accessfn = access_lor_other,
-              .type = ARM_CP_CONST, .resetvalue = 0 },
-            { .name = "LORC_EL1", .state = ARM_CP_STATE_AA64,
-              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 3,
-              .access = PL1_RW, .accessfn = access_lor_other,
-              .type = ARM_CP_CONST, .resetvalue = 0 },
-            { .name = "LORID_EL1", .state = ARM_CP_STATE_AA64,
-              .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7,
-              .access = PL1_R, .accessfn = access_lorid,
-              .type = ARM_CP_CONST, .resetvalue = 0 },
-            REGINFO_SENTINEL
-        };
         define_arm_cp_regs(cpu, lor_reginfo);
     }
+    if (cpu_isar_feature(aa64_pan, cpu)) {
+        define_one_arm_cp_reg(cpu, &pan_reginfo);
+    }
+#ifndef CONFIG_USER_ONLY
+    if (cpu_isar_feature(aa64_ats1e1, cpu)) {
+        define_arm_cp_regs(cpu, ats1e1_reginfo);
+    }
+    if (cpu_isar_feature(aa32_ats1e1, cpu)) {
+        define_arm_cp_regs(cpu, ats1cp_reginfo);
+    }
+#endif
+    if (cpu_isar_feature(aa64_uao, cpu)) {
+        define_one_arm_cp_reg(cpu, &uao_reginfo);
+    }
 
     if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) {
         define_arm_cp_regs(cpu, vhe_reginfo);
@@ -8717,8 +8828,12 @@ static void take_aarch32_exception(CPUARMState *env, int new_mode,
                                    uint32_t mask, uint32_t offset,
                                    uint32_t newpc)
 {
+    int new_el;
+
     /* Change the CPU state so as to actually take the exception. */
     switch_mode(env, new_mode);
+    new_el = arm_current_el(env);
+
     /*
      * For exceptions taken to AArch32 we must clear the SS bit in both
      * PSTATE and in the old-state value we save to SPSR_<mode>, so zero it now.
@@ -8731,7 +8846,7 @@ static void take_aarch32_exception(CPUARMState *env, int new_mode,
     env->uncached_cpsr = (env->uncached_cpsr & ~CPSR_M) | new_mode;
     /* Set new mode endianness */
     env->uncached_cpsr &= ~CPSR_E;
-    if (env->cp15.sctlr_el[arm_current_el(env)] & SCTLR_EE) {
+    if (env->cp15.sctlr_el[new_el] & SCTLR_EE) {
         env->uncached_cpsr |= CPSR_E;
     }
     /* J and IL must always be cleared for exception entry */
@@ -8742,6 +8857,25 @@ static void take_aarch32_exception(CPUARMState *env, int new_mode,
         env->thumb = (env->cp15.sctlr_el[2] & SCTLR_TE) != 0;
         env->elr_el[2] = env->regs[15];
     } else {
+        /* CPSR.PAN is normally preserved preserved unless...  */
+        if (cpu_isar_feature(aa64_pan, env_archcpu(env))) {
+            switch (new_el) {
+            case 3:
+                if (!arm_is_secure_below_el3(env)) {
+                    /* ... the target is EL3, from non-secure state.  */
+                    env->uncached_cpsr &= ~CPSR_PAN;
+                    break;
+                }
+                /* ... the target is EL3, from secure state ... */
+                /* fall through */
+            case 1:
+                /* ... the target is EL1 and SCTLR.SPAN is 0.  */
+                if (!(env->cp15.sctlr_el[new_el] & SCTLR_SPAN)) {
+                    env->uncached_cpsr |= CPSR_PAN;
+                }
+                break;
+            }
+        }
         /*
          * this is a lie, as there was no c1_sys on V4T/V5, but who cares
          * and we should just guard the thumb mode on V4
@@ -9004,6 +9138,7 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs)
     unsigned int new_el = env->exception.target_el;
     target_ulong addr = env->cp15.vbar_el[new_el];
     unsigned int new_mode = aarch64_pstate_mode(new_el, true);
+    unsigned int old_mode;
     unsigned int cur_el = arm_current_el(env);
 
     /*
@@ -9083,20 +9218,43 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs)
     }
 
     if (is_a64(env)) {
-        env->banked_spsr[aarch64_banked_spsr_index(new_el)] = pstate_read(env);
+        old_mode = pstate_read(env);
         aarch64_save_sp(env, arm_current_el(env));
         env->elr_el[new_el] = env->pc;
     } else {
-        env->banked_spsr[aarch64_banked_spsr_index(new_el)] = cpsr_read(env);
+        old_mode = cpsr_read(env);
         env->elr_el[new_el] = env->regs[15];
 
         aarch64_sync_32_to_64(env);
 
         env->condexec_bits = 0;
     }
+    env->banked_spsr[aarch64_banked_spsr_index(new_el)] = old_mode;
+
     qemu_log_mask(CPU_LOG_INT, "...with ELR 0x%" PRIx64 "\n",
                   env->elr_el[new_el]);
 
+    if (cpu_isar_feature(aa64_pan, cpu)) {
+        /* The value of PSTATE.PAN is normally preserved, except when ... */
+        new_mode |= old_mode & PSTATE_PAN;
+        switch (new_el) {
+        case 2:
+            /* ... the target is EL2 with HCR_EL2.{E2H,TGE} == '11' ...  */
+            if ((arm_hcr_el2_eff(env) & (HCR_E2H | HCR_TGE))
+                != (HCR_E2H | HCR_TGE)) {
+                break;
+            }
+            /* fall through */
+        case 1:
+            /* ... the target is EL1 ... */
+            /* ... and SCTLR_ELx.SPAN == 0, then set to 1.  */
+            if ((env->cp15.sctlr_el[new_el] & SCTLR_SPAN) == 0) {
+                new_mode |= PSTATE_PAN;
+            }
+            break;
+        }
+    }
+
     pstate_write(env, PSTATE_DAIF | new_mode);
     env->aarch64 = 1;
     aarch64_restore_sp(env, new_el);
@@ -9207,6 +9365,7 @@ static uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
     switch (mmu_idx) {
     case ARMMMUIdx_E20_0:
     case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_E20_2_PAN:
     case ARMMMUIdx_Stage2:
     case ARMMMUIdx_E2:
         return 2;
@@ -9215,10 +9374,13 @@ static uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_SE10_0:
         return arm_el_is_aa64(env, 3) ? 1 : 3;
     case ARMMMUIdx_SE10_1:
+    case ARMMMUIdx_SE10_1_PAN:
     case ARMMMUIdx_Stage1_E0:
     case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_MPrivNegPri:
     case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
@@ -9285,8 +9447,7 @@ static inline bool regime_translation_disabled(CPUARMState *env,
         }
     }
 
-    if ((env->cp15.hcr_el2 & HCR_DC) &&
-        (mmu_idx == ARMMMUIdx_Stage1_E0 || mmu_idx == ARMMMUIdx_Stage1_E1)) {
+    if ((env->cp15.hcr_el2 & HCR_DC) && arm_mmu_idx_is_stage1_of_2(mmu_idx)) {
         /* HCR.DC means SCTLR_EL1.M behaves as 0 */
         return true;
     }
@@ -9335,6 +9496,8 @@ static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx)
         return ARMMMUIdx_Stage1_E0;
     case ARMMMUIdx_E10_1:
         return ARMMMUIdx_Stage1_E1;
+    case ARMMMUIdx_E10_1_PAN:
+        return ARMMMUIdx_Stage1_E1_PAN;
     default:
         return mmu_idx;
     }
@@ -9381,6 +9544,7 @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx)
         return false;
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
         g_assert_not_reached();
     }
 }
@@ -9517,6 +9681,9 @@ static int get_S1prot(CPUARMState *env, ARMMMUIdx mmu_idx, bool is_aa64,
     if (is_user) {
         prot_rw = user_rw;
     } else {
+        if (user_rw && regime_is_pan(env, mmu_idx)) {
+            return 0;
+        }
         prot_rw = simple_ap_to_rw_prot_is_user(ap, false);
     }
 
@@ -9595,7 +9762,7 @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
                                hwaddr addr, MemTxAttrs txattrs,
                                ARMMMUFaultInfo *fi)
 {
-    if ((mmu_idx == ARMMMUIdx_Stage1_E0 || mmu_idx == ARMMMUIdx_Stage1_E1) &&
+    if (arm_mmu_idx_is_stage1_of_2(mmu_idx) &&
         !regime_translation_disabled(env, ARMMMUIdx_Stage2)) {
         target_ulong s2size;
         hwaddr s2pa;
@@ -11273,7 +11440,9 @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
                    target_ulong *page_size,
                    ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs)
 {
-    if (mmu_idx == ARMMMUIdx_E10_0 || mmu_idx == ARMMMUIdx_E10_1) {
+    if (mmu_idx == ARMMMUIdx_E10_0 ||
+        mmu_idx == ARMMMUIdx_E10_1 ||
+        mmu_idx == ARMMMUIdx_E10_1_PAN) {
         /* Call ourselves recursively to do the stage 1 and then stage 2
          * translations.
          */
@@ -11800,10 +11969,13 @@ int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
     case ARMMMUIdx_SE10_0:
         return 0;
     case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_SE10_1:
+    case ARMMMUIdx_SE10_1_PAN:
         return 1;
     case ARMMMUIdx_E2:
     case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_E20_2_PAN:
         return 2;
     case ARMMMUIdx_SE3:
         return 3;
@@ -11838,13 +12010,22 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el)
         return ARMMMUIdx_E10_0;
     case 1:
         if (arm_is_secure_below_el3(env)) {
+            if (env->pstate & PSTATE_PAN) {
+                return ARMMMUIdx_SE10_1_PAN;
+            }
             return ARMMMUIdx_SE10_1;
         }
+        if (env->pstate & PSTATE_PAN) {
+            return ARMMMUIdx_E10_1_PAN;
+        }
         return ARMMMUIdx_E10_1;
     case 2:
         /* TODO: ARMv8.4-SecEL2 */
         /* Note that TGE does not apply at EL2.  */
         if ((env->cp15.hcr_el2 & HCR_E2H) && arm_el_is_aa64(env, 2)) {
+            if (env->pstate & PSTATE_PAN) {
+                return ARMMMUIdx_E20_2_PAN;
+            }
             return ARMMMUIdx_E20_2;
         }
         return ARMMMUIdx_E2;
@@ -12017,25 +12198,29 @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
     }
 
     /* Compute the condition for using AccType_UNPRIV for LDTR et al. */
-    /* TODO: ARMv8.2-UAO */
-    switch (mmu_idx) {
-    case ARMMMUIdx_E10_1:
-    case ARMMMUIdx_SE10_1:
-        /* TODO: ARMv8.3-NV */
-        flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1);
-        break;
-    case ARMMMUIdx_E20_2:
-        /* TODO: ARMv8.4-SecEL2 */
-        /*
-         * Note that E20_2 is gated by HCR_EL2.E2H == 1, but E20_0 is
-         * gated by HCR_EL2.<E2H,TGE> == '11', and so is LDTR.
-         */
-        if (env->cp15.hcr_el2 & HCR_TGE) {
+    if (!(env->pstate & PSTATE_UAO)) {
+        switch (mmu_idx) {
+        case ARMMMUIdx_E10_1:
+        case ARMMMUIdx_E10_1_PAN:
+        case ARMMMUIdx_SE10_1:
+        case ARMMMUIdx_SE10_1_PAN:
+            /* TODO: ARMv8.3-NV */
             flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1);
+            break;
+        case ARMMMUIdx_E20_2:
+        case ARMMMUIdx_E20_2_PAN:
+            /* TODO: ARMv8.4-SecEL2 */
+            /*
+             * Note that EL20_2 is gated by HCR_EL2.E2H == 1, but EL20_0 is
+             * gated by HCR_EL2.<E2H,TGE> == '11', and so is LDTR.
+             */
+            if (env->cp15.hcr_el2 & HCR_TGE) {
+                flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1);
+            }
+            break;
+        default:
+            break;
         }
-        break;
-    default:
-        break;
     }
 
     return rebuild_hflags_common(env, fp_el, mmu_idx, flags);
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 6d4a942..58c4d70 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -843,12 +843,16 @@ static inline bool regime_has_2_ranges(ARMMMUIdx mmu_idx)
     switch (mmu_idx) {
     case ARMMMUIdx_Stage1_E0:
     case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_E20_0:
     case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_E20_2_PAN:
     case ARMMMUIdx_SE10_0:
     case ARMMMUIdx_SE10_1:
+    case ARMMMUIdx_SE10_1_PAN:
         return true;
     default:
         return false;
@@ -861,10 +865,13 @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx)
     switch (mmu_idx) {
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
     case ARMMMUIdx_E20_0:
     case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_E20_2_PAN:
     case ARMMMUIdx_Stage1_E0:
     case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E2:
     case ARMMMUIdx_Stage2:
     case ARMMMUIdx_MPrivNegPri:
@@ -875,6 +882,7 @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_SE3:
     case ARMMMUIdx_SE10_0:
     case ARMMMUIdx_SE10_1:
+    case ARMMMUIdx_SE10_1_PAN:
     case ARMMMUIdx_MSPrivNegPri:
     case ARMMMUIdx_MSUserNegPri:
     case ARMMMUIdx_MSPriv:
@@ -885,6 +893,19 @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx)
     }
 }
 
+static inline bool regime_is_pan(CPUARMState *env, ARMMMUIdx mmu_idx)
+{
+    switch (mmu_idx) {
+    case ARMMMUIdx_Stage1_E1_PAN:
+    case ARMMMUIdx_E10_1_PAN:
+    case ARMMMUIdx_E20_2_PAN:
+    case ARMMMUIdx_SE10_1_PAN:
+        return true;
+    default:
+        return false;
+    }
+}
+
 /* Return the FSR value for a debug exception (watchpoint, hardware
  * breakpoint or BKPT insn) targeting the specified exception level.
  */
@@ -1034,6 +1055,70 @@ static inline ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env)
 ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env);
 #endif
 
+/**
+ * arm_mmu_idx_is_stage1_of_2:
+ * @mmu_idx: The ARMMMUIdx to test
+ *
+ * Return true if @mmu_idx is a NOTLB mmu_idx that is the
+ * first stage of a two stage regime.
+ */
+static inline bool arm_mmu_idx_is_stage1_of_2(ARMMMUIdx mmu_idx)
+{
+    switch (mmu_idx) {
+    case ARMMMUIdx_Stage1_E0:
+    case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_Stage1_E1_PAN:
+        return true;
+    default:
+        return false;
+    }
+}
+
+static inline uint32_t aarch32_cpsr_valid_mask(uint64_t features,
+                                               const ARMISARegisters *id)
+{
+    uint32_t valid = CPSR_M | CPSR_AIF | CPSR_IL | CPSR_NZCV;
+
+    if ((features >> ARM_FEATURE_V4T) & 1) {
+        valid |= CPSR_T;
+    }
+    if ((features >> ARM_FEATURE_V5) & 1) {
+        valid |= CPSR_Q; /* V5TE in reality*/
+    }
+    if ((features >> ARM_FEATURE_V6) & 1) {
+        valid |= CPSR_E | CPSR_GE;
+    }
+    if ((features >> ARM_FEATURE_THUMB2) & 1) {
+        valid |= CPSR_IT;
+    }
+    if (isar_feature_jazelle(id)) {
+        valid |= CPSR_J;
+    }
+    if (isar_feature_aa32_pan(id)) {
+        valid |= CPSR_PAN;
+    }
+
+    return valid;
+}
+
+static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id)
+{
+    uint32_t valid;
+
+    valid = PSTATE_M | PSTATE_DAIF | PSTATE_IL | PSTATE_SS | PSTATE_NZCV;
+    if (isar_feature_aa64_bti(id)) {
+        valid |= PSTATE_BTYPE;
+    }
+    if (isar_feature_aa64_pan(id)) {
+        valid |= PSTATE_PAN;
+    }
+    if (isar_feature_aa64_uao(id)) {
+        valid |= PSTATE_UAO;
+    }
+
+    return valid;
+}
+
 /*
  * Parameters of a given virtual address, as extracted from the
  * translation control register (TCR) for a given regime.
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
index fb21ab9..3bae9e4 100644
--- a/target/arm/kvm64.c
+++ b/target/arm/kvm64.c
@@ -549,6 +549,8 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
                               ARM64_SYS_REG(3, 0, 0, 7, 0));
         err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr1,
                               ARM64_SYS_REG(3, 0, 0, 7, 1));
+        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr2,
+                              ARM64_SYS_REG(3, 0, 0, 7, 2));
 
         /*
          * Note that if AArch32 support is not present in the host,
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index 27d16ad..af3020b 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -387,7 +387,14 @@ void HELPER(exception_bkpt_insn)(CPUARMState *env, uint32_t syndrome)
 
 uint32_t HELPER(cpsr_read)(CPUARMState *env)
 {
-    return cpsr_read(env) & ~(CPSR_EXEC | CPSR_RESERVED);
+    /*
+     * We store the ARMv8 PSTATE.SS bit in env->uncached_cpsr.
+     * This is convenient for populating SPSR_ELx, but must be
+     * hidden from aarch32 mode, where it is not visible.
+     *
+     * TODO: ARMv8.4-DIT -- need to move SS somewhere else.
+     */
+    return cpsr_read(env) & ~(CPSR_EXEC | PSTATE_SS);
 }
 
 void HELPER(cpsr_write)(CPUARMState *env, uint32_t val, uint32_t mask)
@@ -400,11 +407,14 @@ void HELPER(cpsr_write)(CPUARMState *env, uint32_t val, uint32_t mask)
 /* Write the CPSR for a 32-bit exception return */
 void HELPER(cpsr_write_eret)(CPUARMState *env, uint32_t val)
 {
+    uint32_t mask;
+
     qemu_mutex_lock_iothread();
     arm_call_pre_el_change_hook(env_archcpu(env));
     qemu_mutex_unlock_iothread();
 
-    cpsr_write(env, val, CPSR_ERET_MASK, CPSRWriteExceptionReturn);
+    mask = aarch32_cpsr_valid_mask(env->features, &env_archcpu(env)->isar);
+    cpsr_write(env, val, mask, CPSRWriteExceptionReturn);
 
     /* Generated code has already stored the new PC value, but
      * without masking out its low bits, because which bits need
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 6e82486..7c26c3b 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -124,12 +124,15 @@ static int get_a64_user_mem_index(DisasContext *s)
          */
         switch (useridx) {
         case ARMMMUIdx_E10_1:
+        case ARMMMUIdx_E10_1_PAN:
             useridx = ARMMMUIdx_E10_0;
             break;
         case ARMMMUIdx_E20_2:
+        case ARMMMUIdx_E20_2_PAN:
             useridx = ARMMMUIdx_E20_0;
             break;
         case ARMMMUIdx_SE10_1:
+        case ARMMMUIdx_SE10_1_PAN:
             useridx = ARMMMUIdx_SE10_0;
             break;
         default:
@@ -1599,6 +1602,34 @@ static void handle_msr_i(DisasContext *s, uint32_t insn,
         s->base.is_jmp = DISAS_NEXT;
         break;
 
+    case 0x03: /* UAO */
+        if (!dc_isar_feature(aa64_uao, s) || s->current_el == 0) {
+            goto do_unallocated;
+        }
+        if (crm & 1) {
+            set_pstate_bits(PSTATE_UAO);
+        } else {
+            clear_pstate_bits(PSTATE_UAO);
+        }
+        t1 = tcg_const_i32(s->current_el);
+        gen_helper_rebuild_hflags_a64(cpu_env, t1);
+        tcg_temp_free_i32(t1);
+        break;
+
+    case 0x04: /* PAN */
+        if (!dc_isar_feature(aa64_pan, s) || s->current_el == 0) {
+            goto do_unallocated;
+        }
+        if (crm & 1) {
+            set_pstate_bits(PSTATE_PAN);
+        } else {
+            clear_pstate_bits(PSTATE_PAN);
+        }
+        t1 = tcg_const_i32(s->current_el);
+        gen_helper_rebuild_hflags_a64(cpu_env, t1);
+        tcg_temp_free_i32(t1);
+        break;
+
     case 0x05: /* SPSel */
         if (s->current_el == 0) {
             goto do_unallocated;
diff --git a/target/arm/translate.c b/target/arm/translate.c
index e11a587..20f89ac 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -155,10 +155,12 @@ static inline int get_a32_user_mem_index(DisasContext *s)
     case ARMMMUIdx_E2:        /* this one is UNPREDICTABLE */
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E10_1_PAN:
         return arm_to_core_mmu_idx(ARMMMUIdx_E10_0);
     case ARMMMUIdx_SE3:
     case ARMMMUIdx_SE10_0:
     case ARMMMUIdx_SE10_1:
+    case ARMMMUIdx_SE10_1_PAN:
         return arm_to_core_mmu_idx(ARMMMUIdx_SE10_0);
     case ARMMMUIdx_MUser:
     case ARMMMUIdx_MPriv:
@@ -2732,39 +2734,33 @@ static inline void gen_mulxy(TCGv_i32 t0, TCGv_i32 t1, int x, int y)
 /* Return the mask of PSR bits set by a MSR instruction.  */
 static uint32_t msr_mask(DisasContext *s, int flags, int spsr)
 {
-    uint32_t mask;
+    uint32_t mask = 0;
 
-    mask = 0;
-    if (flags & (1 << 0))
+    if (flags & (1 << 0)) {
         mask |= 0xff;
-    if (flags & (1 << 1))
-        mask |= 0xff00;
-    if (flags & (1 << 2))
-        mask |= 0xff0000;
-    if (flags & (1 << 3))
-        mask |= 0xff000000;
-
-    /* Mask out undefined bits.  */
-    mask &= ~CPSR_RESERVED;
-    if (!arm_dc_feature(s, ARM_FEATURE_V4T)) {
-        mask &= ~CPSR_T;
     }
-    if (!arm_dc_feature(s, ARM_FEATURE_V5)) {
-        mask &= ~CPSR_Q; /* V5TE in reality*/
+    if (flags & (1 << 1)) {
+        mask |= 0xff00;
     }
-    if (!arm_dc_feature(s, ARM_FEATURE_V6)) {
-        mask &= ~(CPSR_E | CPSR_GE);
+    if (flags & (1 << 2)) {
+        mask |= 0xff0000;
     }
-    if (!arm_dc_feature(s, ARM_FEATURE_THUMB2)) {
-        mask &= ~CPSR_IT;
+    if (flags & (1 << 3)) {
+        mask |= 0xff000000;
     }
-    /* Mask out execution state and reserved bits.  */
+
+    /* Mask out undefined and reserved bits.  */
+    mask &= aarch32_cpsr_valid_mask(s->features, s->isar);
+
+    /* Mask out execution state.  */
     if (!spsr) {
-        mask &= ~(CPSR_EXEC | CPSR_RESERVED);
+        mask &= ~CPSR_EXEC;
     }
+
     /* Mask out privileged bits.  */
-    if (IS_USER(s))
+    if (IS_USER(s)) {
         mask &= CPSR_USER;
+    }
     return mask;
 }
 
diff --git a/tests/data/acpi/virt/DSDT b/tests/data/acpi/virt/DSDT
index d0f3afe..d6f5c61 100644
--- a/tests/data/acpi/virt/DSDT
+++ b/tests/data/acpi/virt/DSDT
diff --git a/tests/data/acpi/virt/DSDT.memhp b/tests/data/acpi/virt/DSDT.memhp
index 41ccc64..c527ac4 100644
--- a/tests/data/acpi/virt/DSDT.memhp
+++ b/tests/data/acpi/virt/DSDT.memhp
diff --git a/tests/data/acpi/virt/DSDT.numamem b/tests/data/acpi/virt/DSDT.numamem
index d0f3afe..d6f5c61 100644
--- a/tests/data/acpi/virt/DSDT.numamem
+++ b/tests/data/acpi/virt/DSDT.numamem