Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20171213' into staging

target-arm queue:
 * xilinx_spips: set reset values correctly
 * MAINTAINERS: fix an email address
 * hw/display/tc6393xb: limit irq handler index to TC6393XB_GPIOS
 * nvic: Make systick banked for v8M
 * refactor get_phys_addr() so we can return the right format PAR
   for ATS operations
 * implement v8M TT instruction
 * fix some minor v8M bugs
 * Implement reset for GICv3 ITS
 * xlnx-zcu102: Add support for the ZynqMP QSPI

# gpg: Signature made Wed 13 Dec 2017 18:01:31 GMT
# gpg:                using RSA key 0x3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20171213: (43 commits)
  xilinx_spips: Use memset instead of a for loop to zero registers
  xilinx_spips: Set all of the reset values
  xilinx_spips: Update the QSPI Mod ID reset value
  MAINTAINERS: replace the unavailable email address
  hw/display/tc6393xb: limit irq handler index to TC6393XB_GPIOS
  nvic: Make systick banked
  nvic: Make nvic_sysreg_ns_ops work with any MemoryRegion
  target/arm: Extend PAR format determination
  target/arm: Remove fsr argument from get_phys_addr() and arm_tlb_fill()
  target/arm: Ignore fsr from get_phys_addr() in do_ats_write()
  target/arm: Use ARMMMUFaultInfo in deliver_fault()
  target/arm: Convert get_phys_addr_pmsav8() to not return FSC values
  target/arm: Convert get_phys_addr_pmsav7() to not return FSC values
  target/arm: Convert get_phys_addr_pmsav5() to not return FSC values
  target/arm: Convert get_phys_addr_lpae() to not return FSC values
  target/arm: Convert get_phys_addr_v6() to not return FSC values
  target/arm: Convert get_phys_addr_v5() to not return FSC values
  target/arm: Remove fsr argument from arm_ld*_ptw()
  target/arm: Provide fault type enum and FSR conversion functions
  target/arm: Implement TT instruction
  ...

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

46 files changed, 1833 insertions, 828 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 0255113..45e2e20 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -543,7 +543,7 @@ F: include/hw/*/xlnx*.h
 
 ARM ACPI Subsystem
 M: Shannon Zhao <zhaoshenglong@huawei.com>
-M: Shannon Zhao <shannon.zhao@linaro.org>
+M: Shannon Zhao <shannon.zhaosl@gmail.com>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: hw/arm/virt-acpi-build.c
diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak
index d37edc4..b0d6e65 100644
--- a/default-configs/arm-softmmu.mak
+++ b/default-configs/arm-softmmu.mak
@@ -130,5 +130,5 @@ CONFIG_SMBIOS=y
 CONFIG_ASPEED_SOC=y
 CONFIG_GPIO_KEY=y
 CONFIG_MSF2=y
-
 CONFIG_FW_CFG_DMA=y
+CONFIG_XILINX_AXI=y
diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c
index bbe7d04..b126cf1 100644
--- a/hw/arm/xlnx-zcu102.c
+++ b/hw/arm/xlnx-zcu102.c
@@ -151,6 +151,29 @@ static void xlnx_zynqmp_init(XlnxZCU102 *s, MachineState *machine)
         sysbus_connect_irq(SYS_BUS_DEVICE(&s->soc.spi[i]), 1, cs_line);
     }
 
+    for (i = 0; i < XLNX_ZYNQMP_NUM_QSPI_FLASH; i++) {
+        SSIBus *spi_bus;
+        DeviceState *flash_dev;
+        qemu_irq cs_line;
+        DriveInfo *dinfo = drive_get_next(IF_MTD);
+        int bus = i / XLNX_ZYNQMP_NUM_QSPI_BUS_CS;
+        gchar *bus_name = g_strdup_printf("qspi%d", bus);
+
+        spi_bus = (SSIBus *)qdev_get_child_bus(DEVICE(&s->soc), bus_name);
+        g_free(bus_name);
+
+        flash_dev = ssi_create_slave_no_init(spi_bus, "n25q512a11");
+        if (dinfo) {
+            qdev_prop_set_drive(flash_dev, "drive", blk_by_legacy_dinfo(dinfo),
+                                &error_fatal);
+        }
+        qdev_init_nofail(flash_dev);
+
+        cs_line = qdev_get_gpio_in_named(flash_dev, SSI_GPIO_CS, 0);
+
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->soc.qspi), i + 1, cs_line);
+    }
+
     /* TODO create and connect IDE devices for ide_drive_get() */
 
     xlnx_zcu102_binfo.ram_size = ram_size;
diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c
index c707c66..3256420 100644
--- a/hw/arm/xlnx-zynqmp.c
+++ b/hw/arm/xlnx-zynqmp.c
@@ -40,6 +40,10 @@
 #define SATA_ADDR           0xFD0C0000
 #define SATA_NUM_PORTS      2
 
+#define QSPI_ADDR           0xff0f0000
+#define LQSPI_ADDR          0xc0000000
+#define QSPI_IRQ            15
+
 #define DP_ADDR             0xfd4a0000
 #define DP_IRQ              113
 
@@ -171,6 +175,9 @@ static void xlnx_zynqmp_init(Object *obj)
         qdev_set_parent_bus(DEVICE(&s->spi[i]), sysbus_get_default());
     }
 
+    object_initialize(&s->qspi, sizeof(s->qspi), TYPE_XLNX_ZYNQMP_QSPIPS);
+    qdev_set_parent_bus(DEVICE(&s->qspi), sysbus_get_default());
+
     object_initialize(&s->dp, sizeof(s->dp), TYPE_XLNX_DP);
     qdev_set_parent_bus(DEVICE(&s->dp), sysbus_get_default());
 
@@ -411,6 +418,25 @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp)
         g_free(bus_name);
     }
 
+    object_property_set_bool(OBJECT(&s->qspi), true, "realized", &err);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->qspi), 0, QSPI_ADDR);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->qspi), 1, LQSPI_ADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->qspi), 0, gic_spi[QSPI_IRQ]);
+
+    for (i = 0; i < XLNX_ZYNQMP_NUM_QSPI_BUS; i++) {
+        gchar *bus_name;
+        gchar *target_bus;
+
+        /* Alias controller SPI bus to the SoC itself */
+        bus_name = g_strdup_printf("qspi%d", i);
+        target_bus = g_strdup_printf("spi%d", i);
+        object_property_add_alias(OBJECT(s), bus_name,
+                                  OBJECT(&s->qspi), target_bus,
+                                  &error_abort);
+        g_free(bus_name);
+        g_free(target_bus);
+    }
+
     object_property_set_bool(OBJECT(&s->dp), true, "realized", &err);
     if (err) {
         error_propagate(errp, err);
diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c
index a2438b9..ea14216 100644
--- a/hw/block/m25p80.c
+++ b/hw/block/m25p80.c
@@ -240,6 +240,8 @@ static const FlashPartInfo known_devices[] = {
     { INFO("n25q128a13",  0x20ba18,      0,  64 << 10, 256, ER_4K) },
     { INFO("n25q256a11",  0x20bb19,      0,  64 << 10, 512, ER_4K) },
     { INFO("n25q256a13",  0x20ba19,      0,  64 << 10, 512, ER_4K) },
+    { INFO("n25q512a11",  0x20bb20,      0,  64 << 10, 1024, ER_4K) },
+    { INFO("n25q512a13",  0x20ba20,      0,  64 << 10, 1024, ER_4K) },
     { INFO("n25q128",     0x20ba18,      0,  64 << 10, 256, 0) },
     { INFO("n25q256a",    0x20ba19,      0,  64 << 10, 512, ER_4K) },
     { INFO("n25q512a",    0x20ba20,      0,  64 << 10, 1024, ER_4K) },
@@ -331,7 +333,10 @@ typedef enum {
     WRDI = 0x4,
     RDSR = 0x5,
     WREN = 0x6,
+    BRRD = 0x16,
+    BRWR = 0x17,
     JEDEC_READ = 0x9f,
+    BULK_ERASE_60 = 0x60,
     BULK_ERASE = 0xc7,
     READ_FSR = 0x70,
     RDCR = 0x15,
@@ -355,6 +360,8 @@ typedef enum {
     DPP = 0xa2,
     QPP = 0x32,
     QPP_4 = 0x34,
+    RDID_90 = 0x90,
+    RDID_AB = 0xab,
 
     ERASE_4K = 0x20,
     ERASE4_4K = 0x21,
@@ -405,6 +412,7 @@ typedef enum {
     MAN_MACRONIX,
     MAN_NUMONYX,
     MAN_WINBOND,
+    MAN_SST,
     MAN_GENERIC,
 } Manufacturer;
 
@@ -423,6 +431,7 @@ typedef struct Flash {
     uint8_t data[M25P80_INTERNAL_DATA_BUFFER_SZ];
     uint32_t len;
     uint32_t pos;
+    bool data_read_loop;
     uint8_t needed_bytes;
     uint8_t cmd_in_progress;
     uint32_t cur_addr;
@@ -475,6 +484,8 @@ static inline Manufacturer get_man(Flash *s)
         return MAN_SPANSION;
     case 0xC2:
         return MAN_MACRONIX;
+    case 0xBF:
+        return MAN_SST;
     default:
         return MAN_GENERIC;
     }
@@ -698,6 +709,7 @@ static void complete_collecting_data(Flash *s)
             s->write_enable = false;
         }
         break;
+    case BRWR:
     case EXTEND_ADDR_WRITE:
         s->ear = s->data[0];
         break;
@@ -710,6 +722,31 @@ static void complete_collecting_data(Flash *s)
     case WEVCR:
         s->enh_volatile_cfg = s->data[0];
         break;
+    case RDID_90:
+    case RDID_AB:
+        if (get_man(s) == MAN_SST) {
+            if (s->cur_addr <= 1) {
+                if (s->cur_addr) {
+                    s->data[0] = s->pi->id[2];
+                    s->data[1] = s->pi->id[0];
+                } else {
+                    s->data[0] = s->pi->id[0];
+                    s->data[1] = s->pi->id[2];
+                }
+                s->pos = 0;
+                s->len = 2;
+                s->data_read_loop = true;
+                s->state = STATE_READING_DATA;
+            } else {
+                qemu_log_mask(LOG_GUEST_ERROR,
+                              "M25P80: Invalid read id address\n");
+            }
+        } else {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "M25P80: Read id (command 0x90/0xAB) is not supported"
+                          " by device\n");
+        }
+        break;
     default:
         break;
     }
@@ -925,6 +962,8 @@ static void decode_new_cmd(Flash *s, uint32_t value)
     case PP4:
     case PP4_4:
     case DIE_ERASE:
+    case RDID_90:
+    case RDID_AB:
         s->needed_bytes = get_addr_length(s);
         s->pos = 0;
         s->len = 0;
@@ -983,6 +1022,7 @@ static void decode_new_cmd(Flash *s, uint32_t value)
         }
         s->pos = 0;
         s->len = 1;
+        s->data_read_loop = true;
         s->state = STATE_READING_DATA;
         break;
 
@@ -993,6 +1033,7 @@ static void decode_new_cmd(Flash *s, uint32_t value)
         }
         s->pos = 0;
         s->len = 1;
+        s->data_read_loop = true;
         s->state = STATE_READING_DATA;
         break;
 
@@ -1015,6 +1056,7 @@ static void decode_new_cmd(Flash *s, uint32_t value)
         s->state = STATE_READING_DATA;
         break;
 
+    case BULK_ERASE_60:
     case BULK_ERASE:
         if (s->write_enable) {
             DB_PRINT_L(0, "chip erase\n");
@@ -1032,12 +1074,14 @@ static void decode_new_cmd(Flash *s, uint32_t value)
     case EX_4BYTE_ADDR:
         s->four_bytes_address_mode = false;
         break;
+    case BRRD:
     case EXTEND_ADDR_READ:
         s->data[0] = s->ear;
         s->pos = 0;
         s->len = 1;
         s->state = STATE_READING_DATA;
         break;
+    case BRWR:
     case EXTEND_ADDR_WRITE:
         if (s->write_enable) {
             s->needed_bytes = 1;
@@ -1133,6 +1177,7 @@ static int m25p80_cs(SSISlave *ss, bool select)
         s->pos = 0;
         s->state = STATE_IDLE;
         flash_sync_dirty(s, -1);
+        s->data_read_loop = false;
     }
 
     DB_PRINT_L(0, "%sselect\n", select ? "de" : "");
@@ -1198,7 +1243,9 @@ static uint32_t m25p80_transfer8(SSISlave *ss, uint32_t tx)
         s->pos++;
         if (s->pos == s->len) {
             s->pos = 0;
-            s->state = STATE_IDLE;
+            if (!s->data_read_loop) {
+                s->state = STATE_IDLE;
+            }
         }
         break;
 
@@ -1269,11 +1316,38 @@ static Property m25p80_properties[] = {
     DEFINE_PROP_END_OF_LIST(),
 };
 
+static int m25p80_pre_load(void *opaque)
+{
+    Flash *s = (Flash *)opaque;
+
+    s->data_read_loop = false;
+    return 0;
+}
+
+static bool m25p80_data_read_loop_needed(void *opaque)
+{
+    Flash *s = (Flash *)opaque;
+
+    return s->data_read_loop;
+}
+
+static const VMStateDescription vmstate_m25p80_data_read_loop = {
+    .name = "m25p80/data_read_loop",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = m25p80_data_read_loop_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_BOOL(data_read_loop, Flash),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_m25p80 = {
     .name = "m25p80",
     .version_id = 0,
     .minimum_version_id = 0,
     .pre_save = m25p80_pre_save,
+    .pre_load = m25p80_pre_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT8(state, Flash),
         VMSTATE_UINT8_ARRAY(data, Flash, M25P80_INTERNAL_DATA_BUFFER_SZ),
@@ -1295,6 +1369,10 @@ static const VMStateDescription vmstate_m25p80 = {
         VMSTATE_UINT8(spansion_cr3nv, Flash),
         VMSTATE_UINT8(spansion_cr4nv, Flash),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription * []) {
+        &vmstate_m25p80_data_read_loop,
+        NULL
     }
 };
 
diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c
index 74d10af..0ae6360 100644
--- a/hw/display/tc6393xb.c
+++ b/hw/display/tc6393xb.c
@@ -172,6 +172,7 @@ static void tc6393xb_gpio_handler_update(TC6393xbState *s)
     int bit;
 
     level = s->gpio_level & s->gpio_dir;
+    level &= MAKE_64BIT_MASK(0, TC6393XB_GPIOS);
 
     for (diff = s->prev_level ^ level; diff; diff ^= 1 << bit) {
         bit = ctz32(diff);
diff --git a/hw/intc/arm_gicv3_its_common.c b/hw/intc/arm_gicv3_its_common.c
index f2cce59..2bd2f0f 100644
--- a/hw/intc/arm_gicv3_its_common.c
+++ b/hw/intc/arm_gicv3_its_common.c
@@ -131,8 +131,6 @@ static void gicv3_its_common_reset(DeviceState *dev)
     s->creadr = 0;
     s->iidr = 0;
     memset(&s->baser, 0, sizeof(s->baser));
-
-    gicv3_its_post_load(s, 0);
 }
 
 static void gicv3_its_common_class_init(ObjectClass *klass, void *data)
diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c
index 6fb45df..bf290b8 100644
--- a/hw/intc/arm_gicv3_its_kvm.c
+++ b/hw/intc/arm_gicv3_its_kvm.c
@@ -28,6 +28,16 @@
 
 #define TYPE_KVM_ARM_ITS "arm-its-kvm"
 #define KVM_ARM_ITS(obj) OBJECT_CHECK(GICv3ITSState, (obj), TYPE_KVM_ARM_ITS)
+#define KVM_ARM_ITS_CLASS(klass) \
+     OBJECT_CLASS_CHECK(KVMARMITSClass, (klass), TYPE_KVM_ARM_ITS)
+#define KVM_ARM_ITS_GET_CLASS(obj) \
+     OBJECT_GET_CLASS(KVMARMITSClass, (obj), TYPE_KVM_ARM_ITS)
+
+typedef struct KVMARMITSClass {
+    GICv3ITSCommonClass parent_class;
+    void (*parent_reset)(DeviceState *dev);
+} KVMARMITSClass;
+
 
 static int kvm_its_send_msi(GICv3ITSState *s, uint32_t value, uint16_t devid)
 {
@@ -155,10 +165,6 @@ static void kvm_arm_its_post_load(GICv3ITSState *s)
 {
     int i;
 
-    if (!s->iidr) {
-        return;
-    }
-
     kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
                       GITS_IIDR, &s->iidr, true, &error_abort);
 
@@ -190,6 +196,41 @@ static void kvm_arm_its_post_load(GICv3ITSState *s)
                       GITS_CTLR, &s->ctlr, true, &error_abort);
 }
 
+static void kvm_arm_its_reset(DeviceState *dev)
+{
+    GICv3ITSState *s = ARM_GICV3_ITS_COMMON(dev);
+    KVMARMITSClass *c = KVM_ARM_ITS_GET_CLASS(s);
+    int i;
+
+    c->parent_reset(dev);
+
+    if (kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+                               KVM_DEV_ARM_ITS_CTRL_RESET)) {
+        kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+                          KVM_DEV_ARM_ITS_CTRL_RESET, NULL, true, &error_abort);
+        return;
+    }
+
+    error_report("ITS KVM: full reset is not supported by the host kernel");
+
+    if (!kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                               GITS_CTLR)) {
+        return;
+    }
+
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                      GITS_CTLR, &s->ctlr, true, &error_abort);
+
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                      GITS_CBASER, &s->cbaser, true, &error_abort);
+
+    for (i = 0; i < 8; i++) {
+        kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS,
+                          GITS_BASER + i * 8, &s->baser[i], true,
+                          &error_abort);
+    }
+}
+
 static Property kvm_arm_its_props[] = {
     DEFINE_PROP_LINK("parent-gicv3", GICv3ITSState, gicv3, "kvm-arm-gicv3",
                      GICv3State *),
@@ -200,12 +241,15 @@ static void kvm_arm_its_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     GICv3ITSCommonClass *icc = ARM_GICV3_ITS_COMMON_CLASS(klass);
+    KVMARMITSClass *ic = KVM_ARM_ITS_CLASS(klass);
 
     dc->realize = kvm_arm_its_realize;
     dc->props   = kvm_arm_its_props;
+    ic->parent_reset = dc->reset;
     icc->send_msi = kvm_its_send_msi;
     icc->pre_save = kvm_arm_its_pre_save;
     icc->post_load = kvm_arm_its_post_load;
+    dc->reset = kvm_arm_its_reset;
 }
 
 static const TypeInfo kvm_arm_its_info = {
@@ -213,6 +257,7 @@ static const TypeInfo kvm_arm_its_info = {
     .parent = TYPE_ARM_GICV3_ITS_COMMON,
     .instance_size = sizeof(GICv3ITSState),
     .class_init = kvm_arm_its_class_init,
+    .class_size = sizeof(KVMARMITSClass),
 };
 
 static void kvm_arm_its_register_types(void)
diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c
index 5d9c883..dd49b6c 100644
--- a/hw/intc/armv7m_nvic.c
+++ b/hw/intc/armv7m_nvic.c
@@ -1786,10 +1786,12 @@ static MemTxResult nvic_sysreg_ns_write(void *opaque, hwaddr addr,
                                         uint64_t value, unsigned size,
                                         MemTxAttrs attrs)
 {
+    MemoryRegion *mr = opaque;
+
     if (attrs.secure) {
         /* S accesses to the alias act like NS accesses to the real region */
         attrs.secure = 0;
-        return nvic_sysreg_write(opaque, addr, value, size, attrs);
+        return memory_region_dispatch_write(mr, addr, value, size, attrs);
     } else {
         /* NS attrs are RAZ/WI for privileged, and BusFault for user */
         if (attrs.user) {
@@ -1803,10 +1805,12 @@ static MemTxResult nvic_sysreg_ns_read(void *opaque, hwaddr addr,
                                        uint64_t *data, unsigned size,
                                        MemTxAttrs attrs)
 {
+    MemoryRegion *mr = opaque;
+
     if (attrs.secure) {
         /* S accesses to the alias act like NS accesses to the real region */
         attrs.secure = 0;
-        return nvic_sysreg_read(opaque, addr, data, size, attrs);
+        return memory_region_dispatch_read(mr, addr, data, size, attrs);
     } else {
         /* NS attrs are RAZ/WI for privileged, and BusFault for user */
         if (attrs.user) {
@@ -1823,6 +1827,36 @@ static const MemoryRegionOps nvic_sysreg_ns_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
+static MemTxResult nvic_systick_write(void *opaque, hwaddr addr,
+                                      uint64_t value, unsigned size,
+                                      MemTxAttrs attrs)
+{
+    NVICState *s = opaque;
+    MemoryRegion *mr;
+
+    /* Direct the access to the correct systick */
+    mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0);
+    return memory_region_dispatch_write(mr, addr, value, size, attrs);
+}
+
+static MemTxResult nvic_systick_read(void *opaque, hwaddr addr,
+                                     uint64_t *data, unsigned size,
+                                     MemTxAttrs attrs)
+{
+    NVICState *s = opaque;
+    MemoryRegion *mr;
+
+    /* Direct the access to the correct systick */
+    mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0);
+    return memory_region_dispatch_read(mr, addr, data, size, attrs);
+}
+
+static const MemoryRegionOps nvic_systick_ops = {
+    .read_with_attrs = nvic_systick_read,
+    .write_with_attrs = nvic_systick_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
 static int nvic_post_load(void *opaque, int version_id)
 {
     NVICState *s = opaque;
@@ -2001,17 +2035,16 @@ static void nvic_systick_trigger(void *opaque, int n, int level)
         /* SysTick just asked us to pend its exception.
          * (This is different from an external interrupt line's
          * behaviour.)
-         * TODO: when we implement the banked systicks we must make
-         * this pend the correct banked exception.
+         * n == 0 : NonSecure systick
+         * n == 1 : Secure systick
          */
-        armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK, false);
+        armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK, n);
     }
 }
 
 static void armv7m_nvic_realize(DeviceState *dev, Error **errp)
 {
     NVICState *s = NVIC(dev);
-    SysBusDevice *systick_sbd;
     Error *err = NULL;
     int regionlen;
 
@@ -2028,14 +2061,35 @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp)
     /* include space for internal exception vectors */
     s->num_irq += NVIC_FIRST_IRQ;
 
-    object_property_set_bool(OBJECT(&s->systick), true, "realized", &err);
+    object_property_set_bool(OBJECT(&s->systick[M_REG_NS]), true,
+                             "realized", &err);
     if (err != NULL) {
         error_propagate(errp, err);
         return;
     }
-    systick_sbd = SYS_BUS_DEVICE(&s->systick);
-    sysbus_connect_irq(systick_sbd, 0,
-                       qdev_get_gpio_in_named(dev, "systick-trigger", 0));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), 0,
+                       qdev_get_gpio_in_named(dev, "systick-trigger",
+                                              M_REG_NS));
+
+    if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) {
+        /* We couldn't init the secure systick device in instance_init
+         * as we didn't know then if the CPU had the security extensions;
+         * so we have to do it here.
+         */
+        object_initialize(&s->systick[M_REG_S], sizeof(s->systick[M_REG_S]),
+                          TYPE_SYSTICK);
+        qdev_set_parent_bus(DEVICE(&s->systick[M_REG_S]), sysbus_get_default());
+
+        object_property_set_bool(OBJECT(&s->systick[M_REG_S]), true,
+                                 "realized", &err);
+        if (err != NULL) {
+            error_propagate(errp, err);
+            return;
+        }
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_S]), 0,
+                           qdev_get_gpio_in_named(dev, "systick-trigger",
+                                                  M_REG_S));
+    }
 
     /* The NVIC and System Control Space (SCS) starts at 0xe000e000
      * and looks like this:
@@ -2069,15 +2123,24 @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp)
     memory_region_init_io(&s->sysregmem, OBJECT(s), &nvic_sysreg_ops, s,
                           "nvic_sysregs", 0x1000);
     memory_region_add_subregion(&s->container, 0, &s->sysregmem);
+
+    memory_region_init_io(&s->systickmem, OBJECT(s),
+                          &nvic_systick_ops, s,
+                          "nvic_systick", 0xe0);
+
     memory_region_add_subregion_overlap(&s->container, 0x10,
-                                        sysbus_mmio_get_region(systick_sbd, 0),
-                                        1);
+                                        &s->systickmem, 1);
 
     if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) {
         memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s),
-                              &nvic_sysreg_ns_ops, s,
+                              &nvic_sysreg_ns_ops, &s->sysregmem,
                               "nvic_sysregs_ns", 0x1000);
         memory_region_add_subregion(&s->container, 0x20000, &s->sysreg_ns_mem);
+        memory_region_init_io(&s->systick_ns_mem, OBJECT(s),
+                              &nvic_sysreg_ns_ops, &s->systickmem,
+                              "nvic_systick_ns", 0xe0);
+        memory_region_add_subregion_overlap(&s->container, 0x20010,
+                                            &s->systick_ns_mem, 1);
     }
 
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container);
@@ -2095,12 +2158,17 @@ static void armv7m_nvic_instance_init(Object *obj)
     NVICState *nvic = NVIC(obj);
     SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
 
-    object_initialize(&nvic->systick, sizeof(nvic->systick), TYPE_SYSTICK);
-    qdev_set_parent_bus(DEVICE(&nvic->systick), sysbus_get_default());
+    object_initialize(&nvic->systick[M_REG_NS],
+                      sizeof(nvic->systick[M_REG_NS]), TYPE_SYSTICK);
+    qdev_set_parent_bus(DEVICE(&nvic->systick[M_REG_NS]), sysbus_get_default());
+    /* We can't initialize the secure systick here, as we don't know
+     * yet if we need it.
+     */
 
     sysbus_init_irq(sbd, &nvic->excpout);
     qdev_init_gpio_out_named(dev, &nvic->sysresetreq, "SYSRESETREQ", 1);
-    qdev_init_gpio_in_named(dev, nvic_systick_trigger, "systick-trigger", 1);
+    qdev_init_gpio_in_named(dev, nvic_systick_trigger, "systick-trigger",
+                            M_REG_NUM_BANKS);
 }
 
 static void armv7m_nvic_class_init(ObjectClass *klass, void *data)
diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c
index ef56d35..d8187fa 100644
--- a/hw/ssi/xilinx_spips.c
+++ b/hw/ssi/xilinx_spips.c
@@ -27,11 +27,11 @@
 #include "sysemu/sysemu.h"
 #include "hw/ptimer.h"
 #include "qemu/log.h"
-#include "qemu/fifo8.h"
-#include "hw/ssi/ssi.h"
 #include "qemu/bitops.h"
 #include "hw/ssi/xilinx_spips.h"
 #include "qapi/error.h"
+#include "hw/register.h"
+#include "sysemu/dma.h"
 #include "migration/blocker.h"
 
 #ifndef XILINX_SPIPS_ERR_DEBUG
@@ -48,7 +48,7 @@
 /* config register */
 #define R_CONFIG            (0x00 / 4)
 #define IFMODE              (1U << 31)
-#define ENDIAN              (1 << 26)
+#define R_CONFIG_ENDIAN     (1 << 26)
 #define MODEFAIL_GEN_EN     (1 << 17)
 #define MAN_START_COM       (1 << 16)
 #define MAN_START_EN        (1 << 15)
@@ -66,17 +66,35 @@
 
 /* interrupt mechanism */
 #define R_INTR_STATUS       (0x04 / 4)
+#define R_INTR_STATUS_RESET (0x104)
 #define R_INTR_EN           (0x08 / 4)
 #define R_INTR_DIS          (0x0C / 4)
 #define R_INTR_MASK         (0x10 / 4)
 #define IXR_TX_FIFO_UNDERFLOW   (1 << 6)
+/* Poll timeout not implemented */
+#define IXR_RX_FIFO_EMPTY       (1 << 11)
+#define IXR_GENERIC_FIFO_FULL   (1 << 10)
+#define IXR_GENERIC_FIFO_NOT_FULL (1 << 9)
+#define IXR_TX_FIFO_EMPTY       (1 << 8)
+#define IXR_GENERIC_FIFO_EMPTY  (1 << 7)
 #define IXR_RX_FIFO_FULL        (1 << 5)
 #define IXR_RX_FIFO_NOT_EMPTY   (1 << 4)
 #define IXR_TX_FIFO_FULL        (1 << 3)
 #define IXR_TX_FIFO_NOT_FULL    (1 << 2)
 #define IXR_TX_FIFO_MODE_FAIL   (1 << 1)
 #define IXR_RX_FIFO_OVERFLOW    (1 << 0)
-#define IXR_ALL                 ((IXR_TX_FIFO_UNDERFLOW<<1)-1)
+#define IXR_ALL                 ((1 << 13) - 1)
+#define GQSPI_IXR_MASK          0xFBE
+#define IXR_SELF_CLEAR \
+(IXR_GENERIC_FIFO_EMPTY \
+| IXR_GENERIC_FIFO_FULL  \
+| IXR_GENERIC_FIFO_NOT_FULL \
+| IXR_TX_FIFO_EMPTY \
+| IXR_TX_FIFO_FULL  \
+| IXR_TX_FIFO_NOT_FULL \
+| IXR_RX_FIFO_EMPTY \
+| IXR_RX_FIFO_FULL  \
+| IXR_RX_FIFO_NOT_EMPTY)
 
 #define R_EN                (0x14 / 4)
 #define R_DELAY             (0x18 / 4)
@@ -85,6 +103,9 @@
 #define R_SLAVE_IDLE_COUNT  (0x24 / 4)
 #define R_TX_THRES          (0x28 / 4)
 #define R_RX_THRES          (0x2C / 4)
+#define R_GPIO              (0x30 / 4)
+#define R_LPBK_DLY_ADJ      (0x38 / 4)
+#define R_LPBK_DLY_ADJ_RESET (0x33)
 #define R_TXD1              (0x80 / 4)
 #define R_TXD2              (0x84 / 4)
 #define R_TXD3              (0x88 / 4)
@@ -93,8 +114,9 @@
 #define R_LQSPI_CFG_RESET       0x03A002EB
 #define LQSPI_CFG_LQ_MODE       (1U << 31)
 #define LQSPI_CFG_TWO_MEM       (1 << 30)
-#define LQSPI_CFG_SEP_BUS       (1 << 30)
+#define LQSPI_CFG_SEP_BUS       (1 << 29)
 #define LQSPI_CFG_U_PAGE        (1 << 28)
+#define LQSPI_CFG_ADDR4         (1 << 27)
 #define LQSPI_CFG_MODE_EN       (1 << 25)
 #define LQSPI_CFG_MODE_WIDTH    8
 #define LQSPI_CFG_MODE_SHIFT    16
@@ -102,115 +124,168 @@
 #define LQSPI_CFG_DUMMY_SHIFT   8
 #define LQSPI_CFG_INST_CODE     0xFF
 
+#define R_CMND        (0xc0 / 4)
+    #define R_CMND_RXFIFO_DRAIN   (1 << 19)
+    FIELD(CMND, PARTIAL_BYTE_LEN, 16, 3)
+#define R_CMND_EXT_ADD        (1 << 15)
+    FIELD(CMND, RX_DISCARD, 8, 7)
+    FIELD(CMND, DUMMY_CYCLES, 2, 6)
+#define R_CMND_DMA_EN         (1 << 1)
+#define R_CMND_PUSH_WAIT      (1 << 0)
+#define R_TRANSFER_SIZE     (0xc4 / 4)
 #define R_LQSPI_STS         (0xA4 / 4)
 #define LQSPI_STS_WR_RECVD      (1 << 1)
 
 #define R_MOD_ID            (0xFC / 4)
 
+#define R_GQSPI_SELECT          (0x144 / 4)
+    FIELD(GQSPI_SELECT, GENERIC_QSPI_EN, 0, 1)
+#define R_GQSPI_ISR         (0x104 / 4)
+#define R_GQSPI_IER         (0x108 / 4)
+#define R_GQSPI_IDR         (0x10c / 4)
+#define R_GQSPI_IMR         (0x110 / 4)
+#define R_GQSPI_IMR_RESET   (0xfbe)
+#define R_GQSPI_TX_THRESH   (0x128 / 4)
+#define R_GQSPI_RX_THRESH   (0x12c / 4)
+#define R_GQSPI_GPIO (0x130 / 4)
+#define R_GQSPI_LPBK_DLY_ADJ (0x138 / 4)
+#define R_GQSPI_LPBK_DLY_ADJ_RESET (0x33)
+#define R_GQSPI_CNFG        (0x100 / 4)
+    FIELD(GQSPI_CNFG, MODE_EN, 30, 2)
+    FIELD(GQSPI_CNFG, GEN_FIFO_START_MODE, 29, 1)
+    FIELD(GQSPI_CNFG, GEN_FIFO_START, 28, 1)
+    FIELD(GQSPI_CNFG, ENDIAN, 26, 1)
+    /* Poll timeout not implemented */
+    FIELD(GQSPI_CNFG, EN_POLL_TIMEOUT, 20, 1)
+    /* QEMU doesnt care about any of these last three */
+    FIELD(GQSPI_CNFG, BR, 3, 3)
+    FIELD(GQSPI_CNFG, CPH, 2, 1)
+    FIELD(GQSPI_CNFG, CPL, 1, 1)
+#define R_GQSPI_GEN_FIFO        (0x140 / 4)
+#define R_GQSPI_TXD             (0x11c / 4)
+#define R_GQSPI_RXD             (0x120 / 4)
+#define R_GQSPI_FIFO_CTRL       (0x14c / 4)
+    FIELD(GQSPI_FIFO_CTRL, RX_FIFO_RESET, 2, 1)
+    FIELD(GQSPI_FIFO_CTRL, TX_FIFO_RESET, 1, 1)
+    FIELD(GQSPI_FIFO_CTRL, GENERIC_FIFO_RESET, 0, 1)
+#define R_GQSPI_GFIFO_THRESH    (0x150 / 4)
+#define R_GQSPI_DATA_STS (0x15c / 4)
+/* We use the snapshot register to hold the core state for the currently
+ * or most recently executed command. So the generic fifo format is defined
+ * for the snapshot register
+ */
+#define R_GQSPI_GF_SNAPSHOT (0x160 / 4)
+    FIELD(GQSPI_GF_SNAPSHOT, POLL, 19, 1)
+    FIELD(GQSPI_GF_SNAPSHOT, STRIPE, 18, 1)
+    FIELD(GQSPI_GF_SNAPSHOT, RECIEVE, 17, 1)
+    FIELD(GQSPI_GF_SNAPSHOT, TRANSMIT, 16, 1)
+    FIELD(GQSPI_GF_SNAPSHOT, DATA_BUS_SELECT, 14, 2)
+    FIELD(GQSPI_GF_SNAPSHOT, CHIP_SELECT, 12, 2)
+    FIELD(GQSPI_GF_SNAPSHOT, SPI_MODE, 10, 2)
+    FIELD(GQSPI_GF_SNAPSHOT, EXPONENT, 9, 1)
+    FIELD(GQSPI_GF_SNAPSHOT, DATA_XFER, 8, 1)
+    FIELD(GQSPI_GF_SNAPSHOT, IMMEDIATE_DATA, 0, 8)
+#define R_GQSPI_MOD_ID        (0x1fc / 4)
+#define R_GQSPI_MOD_ID_RESET  (0x10a0000)
+
+#define R_QSPIDMA_DST_CTRL         (0x80c / 4)
+#define R_QSPIDMA_DST_CTRL_RESET   (0x803ffa00)
+#define R_QSPIDMA_DST_I_MASK       (0x820 / 4)
+#define R_QSPIDMA_DST_I_MASK_RESET (0xfe)
+#define R_QSPIDMA_DST_CTRL2        (0x824 / 4)
+#define R_QSPIDMA_DST_CTRL2_RESET  (0x081bfff8)
+
 /* size of TXRX FIFOs */
-#define RXFF_A          32
-#define TXFF_A          32
+#define RXFF_A          (128)
+#define TXFF_A          (128)
 
 #define RXFF_A_Q          (64 * 4)
 #define TXFF_A_Q          (64 * 4)
 
 /* 16MB per linear region */
 #define LQSPI_ADDRESS_BITS 24
-/* Bite off 4k chunks at a time */
-#define LQSPI_CACHE_SIZE 1024
 
 #define SNOOP_CHECKING 0xFF
-#define SNOOP_NONE 0xFE
+#define SNOOP_ADDR 0xF0
+#define SNOOP_NONE 0xEE
 #define SNOOP_STRIPING 0
 
-typedef enum {
-    READ = 0x3,
-    FAST_READ = 0xb,
-    DOR = 0x3b,
-    QOR = 0x6b,
-    DIOR = 0xbb,
-    QIOR = 0xeb,
-
-    PP = 0x2,
-    DPP = 0xa2,
-    QPP = 0x32,
-} FlashCMD;
-
-typedef struct {
-    XilinxSPIPS parent_obj;
-
-    uint8_t lqspi_buf[LQSPI_CACHE_SIZE];
-    hwaddr lqspi_cached_addr;
-    Error *migration_blocker;
-    bool mmio_execution_enabled;
-} XilinxQSPIPS;
-
-typedef struct XilinxSPIPSClass {
-    SysBusDeviceClass parent_class;
-
-    const MemoryRegionOps *reg_ops;
-
-    uint32_t rx_fifo_size;
-    uint32_t tx_fifo_size;
-} XilinxSPIPSClass;
-
 static inline int num_effective_busses(XilinxSPIPS *s)
 {
     return (s->regs[R_LQSPI_CFG] & LQSPI_CFG_SEP_BUS &&
             s->regs[R_LQSPI_CFG] & LQSPI_CFG_TWO_MEM) ? s->num_busses : 1;
 }
 
-static inline bool xilinx_spips_cs_is_set(XilinxSPIPS *s, int i, int field)
-{
-    return ~field & (1 << i) && (s->regs[R_CONFIG] & MANUAL_CS
-                    || !fifo8_is_empty(&s->tx_fifo));
-}
-
-static void xilinx_spips_update_cs_lines(XilinxSPIPS *s)
+static void xilinx_spips_update_cs(XilinxSPIPS *s, int field)
 {
-    int i, j;
-    bool found = false;
-    int field = s->regs[R_CONFIG] >> CS_SHIFT;
+    int i;
 
     for (i = 0; i < s->num_cs; i++) {
-        for (j = 0; j < num_effective_busses(s); j++) {
-            int upage = !!(s->regs[R_LQSPI_STS] & LQSPI_CFG_U_PAGE);
-            int cs_to_set = (j * s->num_cs + i + upage) %
-                                (s->num_cs * s->num_busses);
-
-            if (xilinx_spips_cs_is_set(s, i, field) && !found) {
-                DB_PRINT_L(0, "selecting slave %d\n", i);
-                qemu_set_irq(s->cs_lines[cs_to_set], 0);
-            } else {
-                DB_PRINT_L(0, "deselecting slave %d\n", i);
-                qemu_set_irq(s->cs_lines[cs_to_set], 1);
-            }
-        }
-        if (xilinx_spips_cs_is_set(s, i, field)) {
-            found = true;
+        bool old_state = s->cs_lines_state[i];
+        bool new_state = field & (1 << i);
+
+        if (old_state != new_state) {
+            s->cs_lines_state[i] = new_state;
+            s->rx_discard = ARRAY_FIELD_EX32(s->regs, CMND, RX_DISCARD);
+            DB_PRINT_L(1, "%sselecting slave %d\n", new_state ? "" : "de", i);
         }
+        qemu_set_irq(s->cs_lines[i], !new_state);
     }
-    if (!found) {
+    if (!(field & ((1 << s->num_cs) - 1))) {
         s->snoop_state = SNOOP_CHECKING;
+        s->cmd_dummies = 0;
+        s->link_state = 1;
+        s->link_state_next = 1;
+        s->link_state_next_when = 0;
         DB_PRINT_L(1, "moving to snoop check state\n");
     }
 }
 
+static void xlnx_zynqmp_qspips_update_cs_lines(XlnxZynqMPQSPIPS *s)
+{
+    if (s->regs[R_GQSPI_GF_SNAPSHOT]) {
+        int field = ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, CHIP_SELECT);
+        xilinx_spips_update_cs(XILINX_SPIPS(s), field);
+    }
+}
+
+static void xilinx_spips_update_cs_lines(XilinxSPIPS *s)
+{
+    int field = ~((s->regs[R_CONFIG] & CS) >> CS_SHIFT);
+
+    /* In dual parallel, mirror low CS to both */
+    if (num_effective_busses(s) == 2) {
+        /* Single bit chip-select for qspi */
+        field &= 0x1;
+        field |= field << 1;
+    /* Dual stack U-Page */
+    } else if (s->regs[R_LQSPI_CFG] & LQSPI_CFG_TWO_MEM &&
+               s->regs[R_LQSPI_STS] & LQSPI_CFG_U_PAGE) {
+        /* Single bit chip-select for qspi */
+        field &= 0x1;
+        /* change from CS0 to CS1 */
+        field <<= 1;
+    }
+    /* Auto CS */
+    if (!(s->regs[R_CONFIG] & MANUAL_CS) &&
+        fifo8_is_empty(&s->tx_fifo)) {
+        field = 0;
+    }
+    xilinx_spips_update_cs(s, field);
+}
+
 static void xilinx_spips_update_ixr(XilinxSPIPS *s)
 {
-    if (s->regs[R_LQSPI_CFG] & LQSPI_CFG_LQ_MODE) {
-        return;
+    if (!(s->regs[R_LQSPI_CFG] & LQSPI_CFG_LQ_MODE)) {
+        s->regs[R_INTR_STATUS] &= ~IXR_SELF_CLEAR;
+        s->regs[R_INTR_STATUS] |=
+            (fifo8_is_full(&s->rx_fifo) ? IXR_RX_FIFO_FULL : 0) |
+            (s->rx_fifo.num >= s->regs[R_RX_THRES] ?
+                                    IXR_RX_FIFO_NOT_EMPTY : 0) |
+            (fifo8_is_full(&s->tx_fifo) ? IXR_TX_FIFO_FULL : 0) |
+            (fifo8_is_empty(&s->tx_fifo) ? IXR_TX_FIFO_EMPTY : 0) |
+            (s->tx_fifo.num < s->regs[R_TX_THRES] ? IXR_TX_FIFO_NOT_FULL : 0);
     }
-    /* These are set/cleared as they occur */
-    s->regs[R_INTR_STATUS] &= (IXR_TX_FIFO_UNDERFLOW | IXR_RX_FIFO_OVERFLOW |
-                                IXR_TX_FIFO_MODE_FAIL);
-    /* these are pure functions of fifo state, set them here */
-    s->regs[R_INTR_STATUS] |=
-        (fifo8_is_full(&s->rx_fifo) ? IXR_RX_FIFO_FULL : 0) |
-        (s->rx_fifo.num >= s->regs[R_RX_THRES] ? IXR_RX_FIFO_NOT_EMPTY : 0) |
-        (fifo8_is_full(&s->tx_fifo) ? IXR_TX_FIFO_FULL : 0) |
-        (s->tx_fifo.num < s->regs[R_TX_THRES] ? IXR_TX_FIFO_NOT_FULL : 0);
-    /* drive external interrupt pin */
     int new_irqline = !!(s->regs[R_INTR_MASK] & s->regs[R_INTR_STATUS] &
                                                                 IXR_ALL);
     if (new_irqline != s->irqline) {
@@ -219,14 +294,42 @@ static void xilinx_spips_update_ixr(XilinxSPIPS *s)
     }
 }
 
+static void xlnx_zynqmp_qspips_update_ixr(XlnxZynqMPQSPIPS *s)
+{
+    uint32_t gqspi_int;
+    int new_irqline;
+
+    s->regs[R_GQSPI_ISR] &= ~IXR_SELF_CLEAR;
+    s->regs[R_GQSPI_ISR] |=
+        (fifo32_is_empty(&s->fifo_g) ? IXR_GENERIC_FIFO_EMPTY : 0) |
+        (fifo32_is_full(&s->fifo_g) ? IXR_GENERIC_FIFO_FULL : 0) |
+        (s->fifo_g.fifo.num < s->regs[R_GQSPI_GFIFO_THRESH] ?
+                                    IXR_GENERIC_FIFO_NOT_FULL : 0) |
+        (fifo8_is_empty(&s->rx_fifo_g) ? IXR_RX_FIFO_EMPTY : 0) |
+        (fifo8_is_full(&s->rx_fifo_g) ? IXR_RX_FIFO_FULL : 0) |
+        (s->rx_fifo_g.num >= s->regs[R_GQSPI_RX_THRESH] ?
+                                    IXR_RX_FIFO_NOT_EMPTY : 0) |
+        (fifo8_is_empty(&s->tx_fifo_g) ? IXR_TX_FIFO_EMPTY : 0) |
+        (fifo8_is_full(&s->tx_fifo_g) ? IXR_TX_FIFO_FULL : 0) |
+        (s->tx_fifo_g.num < s->regs[R_GQSPI_TX_THRESH] ?
+                                    IXR_TX_FIFO_NOT_FULL : 0);
+
+    /* GQSPI Interrupt Trigger Status */
+    gqspi_int = (~s->regs[R_GQSPI_IMR]) & s->regs[R_GQSPI_ISR] & GQSPI_IXR_MASK;
+    new_irqline = !!(gqspi_int & IXR_ALL);
+
+    /* drive external interrupt pin */
+    if (new_irqline != s->gqspi_irqline) {
+        s->gqspi_irqline = new_irqline;
+        qemu_set_irq(XILINX_SPIPS(s)->irq, s->gqspi_irqline);
+    }
+}
+
 static void xilinx_spips_reset(DeviceState *d)
 {
     XilinxSPIPS *s = XILINX_SPIPS(d);
 
-    int i;
-    for (i = 0; i < XLNX_SPIPS_R_MAX; i++) {
-        s->regs[i] = 0;
-    }
+    memset(s->regs, 0, sizeof(s->regs));
 
     fifo8_reset(&s->rx_fifo);
     fifo8_reset(&s->rx_fifo);
@@ -238,19 +341,54 @@ static void xilinx_spips_reset(DeviceState *d)
     /* FIXME: move magic number definition somewhere sensible */
     s->regs[R_MOD_ID] = 0x01090106;
     s->regs[R_LQSPI_CFG] = R_LQSPI_CFG_RESET;
+    s->link_state = 1;
+    s->link_state_next = 1;
+    s->link_state_next_when = 0;
     s->snoop_state = SNOOP_CHECKING;
+    s->cmd_dummies = 0;
+    s->man_start_com = false;
     xilinx_spips_update_ixr(s);
     xilinx_spips_update_cs_lines(s);
 }
 
-/* N way (num) in place bit striper. Lay out row wise bits (LSB to MSB)
+static void xlnx_zynqmp_qspips_reset(DeviceState *d)
+{
+    XlnxZynqMPQSPIPS *s = XLNX_ZYNQMP_QSPIPS(d);
+
+    xilinx_spips_reset(d);
+
+    memset(s->regs, 0, sizeof(s->regs));
+
+    fifo8_reset(&s->rx_fifo_g);
+    fifo8_reset(&s->rx_fifo_g);
+    fifo32_reset(&s->fifo_g);
+    s->regs[R_INTR_STATUS] = R_INTR_STATUS_RESET;
+    s->regs[R_GPIO] = 1;
+    s->regs[R_LPBK_DLY_ADJ] = R_LPBK_DLY_ADJ_RESET;
+    s->regs[R_GQSPI_GFIFO_THRESH] = 0x10;
+    s->regs[R_MOD_ID] = 0x01090101;
+    s->regs[R_GQSPI_IMR] = R_GQSPI_IMR_RESET;
+    s->regs[R_GQSPI_TX_THRESH] = 1;
+    s->regs[R_GQSPI_RX_THRESH] = 1;
+    s->regs[R_GQSPI_GPIO] = 1;
+    s->regs[R_GQSPI_LPBK_DLY_ADJ] = R_GQSPI_LPBK_DLY_ADJ_RESET;
+    s->regs[R_GQSPI_MOD_ID] = R_GQSPI_MOD_ID_RESET;
+    s->regs[R_QSPIDMA_DST_CTRL] = R_QSPIDMA_DST_CTRL_RESET;
+    s->regs[R_QSPIDMA_DST_I_MASK] = R_QSPIDMA_DST_I_MASK_RESET;
+    s->regs[R_QSPIDMA_DST_CTRL2] = R_QSPIDMA_DST_CTRL2_RESET;
+    s->man_start_com_g = false;
+    s->gqspi_irqline = 0;
+    xlnx_zynqmp_qspips_update_ixr(s);
+}
+
+/* N way (num) in place bit striper. Lay out row wise bits (MSB to LSB)
  * column wise (from element 0 to N-1). num is the length of x, and dir
  * reverses the direction of the transform. Best illustrated by example:
  * Each digit in the below array is a single bit (num == 3):
  *
- * {{ 76543210, }  ----- stripe (dir == false) -----> {{ FCheb630, }
- *  { hgfedcba, }                                      { GDAfc741, }
- *  { HGFEDCBA, }} <---- upstripe (dir == true) -----  { HEBgda52, }}
+ * {{ 76543210, }  ----- stripe (dir == false) -----> {{ 741gdaFC, }
+ *  { hgfedcba, }                                      { 630fcHEB, }
+ *  { HGFEDCBA, }} <---- upstripe (dir == true) -----  { 52hebGDA, }}
  */
 
 static inline void stripe8(uint8_t *x, int num, bool dir)
@@ -258,34 +396,188 @@ static inline void stripe8(uint8_t *x, int num, bool dir)
     uint8_t r[num];
     memset(r, 0, sizeof(uint8_t) * num);
     int idx[2] = {0, 0};
-    int bit[2] = {0, 0};
+    int bit[2] = {0, 7};
     int d = dir;
 
     for (idx[0] = 0; idx[0] < num; ++idx[0]) {
-        for (bit[0] = 0; bit[0] < 8; ++bit[0]) {
-            r[idx[d]] |= x[idx[!d]] & 1 << bit[!d] ? 1 << bit[d] : 0;
+        for (bit[0] = 7; bit[0] >= 0; bit[0]--) {
+            r[idx[!d]] |= x[idx[d]] & 1 << bit[d] ? 1 << bit[!d] : 0;
             idx[1] = (idx[1] + 1) % num;
             if (!idx[1]) {
-                bit[1]++;
+                bit[1]--;
             }
         }
     }
     memcpy(x, r, sizeof(uint8_t) * num);
 }
 
+static void xlnx_zynqmp_qspips_flush_fifo_g(XlnxZynqMPQSPIPS *s)
+{
+    while (s->regs[R_GQSPI_DATA_STS] || !fifo32_is_empty(&s->fifo_g)) {
+        uint8_t tx_rx[2] = { 0 };
+        int num_stripes = 1;
+        uint8_t busses;
+        int i;
+
+        if (!s->regs[R_GQSPI_DATA_STS]) {
+            uint8_t imm;
+
+            s->regs[R_GQSPI_GF_SNAPSHOT] = fifo32_pop(&s->fifo_g);
+            DB_PRINT_L(0, "GQSPI command: %x\n", s->regs[R_GQSPI_GF_SNAPSHOT]);
+            if (!s->regs[R_GQSPI_GF_SNAPSHOT]) {
+                DB_PRINT_L(0, "Dummy GQSPI Delay Command Entry, Do nothing");
+                continue;
+            }
+            xlnx_zynqmp_qspips_update_cs_lines(s);
+
+            imm = ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, IMMEDIATE_DATA);
+            if (!ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, DATA_XFER)) {
+                /* immedate transfer */
+                if (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, TRANSMIT) ||
+                    ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, RECIEVE)) {
+                    s->regs[R_GQSPI_DATA_STS] = 1;
+                /* CS setup/hold - do nothing */
+                } else {
+                    s->regs[R_GQSPI_DATA_STS] = 0;
+                }
+            } else if (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, EXPONENT)) {
+                if (imm > 31) {
+                    qemu_log_mask(LOG_UNIMP, "QSPI exponential transfer too"
+                                  " long - 2 ^ %" PRId8 " requested\n", imm);
+                }
+                s->regs[R_GQSPI_DATA_STS] = 1ul << imm;
+            } else {
+                s->regs[R_GQSPI_DATA_STS] = imm;
+            }
+        }
+        /* Zero length transfer check */
+        if (!s->regs[R_GQSPI_DATA_STS]) {
+            continue;
+        }
+        if (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, RECIEVE) &&
+            fifo8_is_full(&s->rx_fifo_g)) {
+            /* No space in RX fifo for transfer - try again later */
+            return;
+        }
+        if (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, STRIPE) &&
+            (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, TRANSMIT) ||
+             ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, RECIEVE))) {
+            num_stripes = 2;
+        }
+        if (!ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, DATA_XFER)) {
+            tx_rx[0] = ARRAY_FIELD_EX32(s->regs,
+                                        GQSPI_GF_SNAPSHOT, IMMEDIATE_DATA);
+        } else if (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, TRANSMIT)) {
+            for (i = 0; i < num_stripes; ++i) {
+                if (!fifo8_is_empty(&s->tx_fifo_g)) {
+                    tx_rx[i] = fifo8_pop(&s->tx_fifo_g);
+                    s->tx_fifo_g_align++;
+                } else {
+                    return;
+                }
+            }
+        }
+        if (num_stripes == 1) {
+            /* mirror */
+            tx_rx[1] = tx_rx[0];
+        }
+        busses = ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, DATA_BUS_SELECT);
+        for (i = 0; i < 2; ++i) {
+            DB_PRINT_L(1, "bus %d tx = %02x\n", i, tx_rx[i]);
+            tx_rx[i] = ssi_transfer(XILINX_SPIPS(s)->spi[i], tx_rx[i]);
+            DB_PRINT_L(1, "bus %d rx = %02x\n", i, tx_rx[i]);
+        }
+        if (s->regs[R_GQSPI_DATA_STS] > 1 &&
+            busses == 0x3 && num_stripes == 2) {
+            s->regs[R_GQSPI_DATA_STS] -= 2;
+        } else if (s->regs[R_GQSPI_DATA_STS] > 0) {
+            s->regs[R_GQSPI_DATA_STS]--;
+        }
+        if (ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, RECIEVE)) {
+            for (i = 0; i < 2; ++i) {
+                if (busses & (1 << i)) {
+                    DB_PRINT_L(1, "bus %d push_byte = %02x\n", i, tx_rx[i]);
+                    fifo8_push(&s->rx_fifo_g, tx_rx[i]);
+                    s->rx_fifo_g_align++;
+                }
+            }
+        }
+        if (!s->regs[R_GQSPI_DATA_STS]) {
+            for (; s->tx_fifo_g_align % 4; s->tx_fifo_g_align++) {
+                fifo8_pop(&s->tx_fifo_g);
+            }
+            for (; s->rx_fifo_g_align % 4; s->rx_fifo_g_align++) {
+                fifo8_push(&s->rx_fifo_g, 0);
+            }
+        }
+    }
+}
+
+static int xilinx_spips_num_dummies(XilinxQSPIPS *qs, uint8_t command)
+{
+    if (!qs) {
+        /* The SPI device is not a QSPI device */
+        return -1;
+    }
+
+    switch (command) { /* check for dummies */
+    case READ: /* no dummy bytes/cycles */
+    case PP:
+    case DPP:
+    case QPP:
+    case READ_4:
+    case PP_4:
+    case QPP_4:
+        return 0;
+    case FAST_READ:
+    case DOR:
+    case QOR:
+    case DOR_4:
+    case QOR_4:
+        return 1;
+    case DIOR:
+    case FAST_READ_4:
+    case DIOR_4:
+        return 2;
+    case QIOR:
+    case QIOR_4:
+        return 5;
+    default:
+        return -1;
+    }
+}
+
+static inline uint8_t get_addr_length(XilinxSPIPS *s, uint8_t cmd)
+{
+   switch (cmd) {
+   case PP_4:
+   case QPP_4:
+   case READ_4:
+   case QIOR_4:
+   case FAST_READ_4:
+   case DOR_4:
+   case QOR_4:
+   case DIOR_4:
+       return 4;
+   default:
+       return (s->regs[R_CMND] & R_CMND_EXT_ADD) ? 4 : 3;
+   }
+}
+
 static void xilinx_spips_flush_txfifo(XilinxSPIPS *s)
 {
     int debug_level = 0;
+    XilinxQSPIPS *q = (XilinxQSPIPS *) object_dynamic_cast(OBJECT(s),
+                                                           TYPE_XILINX_QSPIPS);
 
     for (;;) {
         int i;
         uint8_t tx = 0;
         uint8_t tx_rx[num_effective_busses(s)];
+        uint8_t dummy_cycles = 0;
+        uint8_t addr_length;
 
         if (fifo8_is_empty(&s->tx_fifo)) {
-            if (!(s->regs[R_LQSPI_CFG] & LQSPI_CFG_LQ_MODE)) {
-                s->regs[R_INTR_STATUS] |= IXR_TX_FIFO_UNDERFLOW;
-            }
             xilinx_spips_update_ixr(s);
             return;
         } else if (s->snoop_state == SNOOP_STRIPING) {
@@ -293,53 +585,102 @@ static void xilinx_spips_flush_txfifo(XilinxSPIPS *s)
                 tx_rx[i] = fifo8_pop(&s->tx_fifo);
             }
             stripe8(tx_rx, num_effective_busses(s), false);
-        } else {
+        } else if (s->snoop_state >= SNOOP_ADDR) {
             tx = fifo8_pop(&s->tx_fifo);
             for (i = 0; i < num_effective_busses(s); ++i) {
                 tx_rx[i] = tx;
             }
+        } else {
+            /* Extract a dummy byte and generate dummy cycles according to the
+             * link state */
+            tx = fifo8_pop(&s->tx_fifo);
+            dummy_cycles = 8 / s->link_state;
         }
 
         for (i = 0; i < num_effective_busses(s); ++i) {
-            DB_PRINT_L(debug_level, "tx = %02x\n", tx_rx[i]);
-            tx_rx[i] = ssi_transfer(s->spi[i], (uint32_t)tx_rx[i]);
-            DB_PRINT_L(debug_level, "rx = %02x\n", tx_rx[i]);
+            int bus = num_effective_busses(s) - 1 - i;
+            if (dummy_cycles) {
+                int d;
+                for (d = 0; d < dummy_cycles; ++d) {
+                    tx_rx[0] = ssi_transfer(s->spi[bus], (uint32_t)tx_rx[0]);
+                }
+            } else {
+                DB_PRINT_L(debug_level, "tx = %02x\n", tx_rx[i]);
+                tx_rx[i] = ssi_transfer(s->spi[bus], (uint32_t)tx_rx[i]);
+                DB_PRINT_L(debug_level, "rx = %02x\n", tx_rx[i]);
+            }
         }
 
-        if (fifo8_is_full(&s->rx_fifo)) {
+        if (s->regs[R_CMND] & R_CMND_RXFIFO_DRAIN) {
+            DB_PRINT_L(debug_level, "dircarding drained rx byte\n");
+            /* Do nothing */
+        } else if (s->rx_discard) {
+            DB_PRINT_L(debug_level, "dircarding discarded rx byte\n");
+            s->rx_discard -= 8 / s->link_state;
+        } else if (fifo8_is_full(&s->rx_fifo)) {
             s->regs[R_INTR_STATUS] |= IXR_RX_FIFO_OVERFLOW;
             DB_PRINT_L(0, "rx FIFO overflow");
         } else if (s->snoop_state == SNOOP_STRIPING) {
             stripe8(tx_rx, num_effective_busses(s), true);
             for (i = 0; i < num_effective_busses(s); ++i) {
                 fifo8_push(&s->rx_fifo, (uint8_t)tx_rx[i]);
+                DB_PRINT_L(debug_level, "pushing striped rx byte\n");
             }
         } else {
+           DB_PRINT_L(debug_level, "pushing unstriped rx byte\n");
            fifo8_push(&s->rx_fifo, (uint8_t)tx_rx[0]);
         }
 
+        if (s->link_state_next_when) {
+            s->link_state_next_when--;
+            if (!s->link_state_next_when) {
+                s->link_state = s->link_state_next;
+            }
+        }
+
         DB_PRINT_L(debug_level, "initial snoop state: %x\n",
                    (unsigned)s->snoop_state);
         switch (s->snoop_state) {
         case (SNOOP_CHECKING):
-            switch (tx) { /* new instruction code */
-            case READ: /* 3 address bytes, no dummy bytes/cycles */
-            case PP:
+            /* Store the count of dummy bytes in the txfifo */
+            s->cmd_dummies = xilinx_spips_num_dummies(q, tx);
+            addr_length = get_addr_length(s, tx);
+            if (s->cmd_dummies < 0) {
+                s->snoop_state = SNOOP_NONE;
+            } else {
+                s->snoop_state = SNOOP_ADDR + addr_length - 1;
+            }
+            switch (tx) {
             case DPP:
-            case QPP:
-                s->snoop_state = 3;
-                break;
-            case FAST_READ: /* 3 address bytes, 1 dummy byte */
             case DOR:
+            case DOR_4:
+                s->link_state_next = 2;
+                s->link_state_next_when = addr_length + s->cmd_dummies;
+                break;
+            case QPP:
+            case QPP_4:
             case QOR:
-            case DIOR: /* FIXME: these vary between vendor - set to spansion */
-                s->snoop_state = 4;
+            case QOR_4:
+                s->link_state_next = 4;
+                s->link_state_next_when = addr_length + s->cmd_dummies;
+                break;
+            case DIOR:
+            case DIOR_4:
+                s->link_state = 2;
                 break;
-            case QIOR: /* 3 address bytes, 2 dummy bytes */
-                s->snoop_state = 6;
+            case QIOR:
+            case QIOR_4:
+                s->link_state = 4;
                 break;
-            default:
+            }
+            break;
+        case (SNOOP_ADDR):
+            /* Address has been transmitted, transmit dummy cycles now if
+             * needed */
+            if (s->cmd_dummies < 0) {
                 s->snoop_state = SNOOP_NONE;
+            } else {
+                s->snoop_state = s->cmd_dummies;
             }
             break;
         case (SNOOP_STRIPING):
@@ -358,12 +699,128 @@ static void xilinx_spips_flush_txfifo(XilinxSPIPS *s)
     }
 }
 
-static inline void rx_data_bytes(XilinxSPIPS *s, uint8_t *value, int max)
+static inline void tx_data_bytes(Fifo8 *fifo, uint32_t value, int num, bool be)
+{
+    int i;
+    for (i = 0; i < num && !fifo8_is_full(fifo); ++i) {
+        if (be) {
+            fifo8_push(fifo, (uint8_t)(value >> 24));
+            value <<= 8;
+        } else {
+            fifo8_push(fifo, (uint8_t)value);
+            value >>= 8;
+        }
+    }
+}
+
+static void xilinx_spips_check_zero_pump(XilinxSPIPS *s)
+{
+    if (!s->regs[R_TRANSFER_SIZE]) {
+        return;
+    }
+    if (!fifo8_is_empty(&s->tx_fifo) && s->regs[R_CMND] & R_CMND_PUSH_WAIT) {
+        return;
+    }
+    /*
+     * The zero pump must never fill tx fifo such that rx overflow is
+     * possible
+     */
+    while (s->regs[R_TRANSFER_SIZE] &&
+           s->rx_fifo.num + s->tx_fifo.num < RXFF_A_Q - 3) {
+        /* endianess just doesn't matter when zero pumping */
+        tx_data_bytes(&s->tx_fifo, 0, 4, false);
+        s->regs[R_TRANSFER_SIZE] &= ~0x03ull;
+        s->regs[R_TRANSFER_SIZE] -= 4;
+    }
+}
+
+static void xilinx_spips_check_flush(XilinxSPIPS *s)
+{
+    if (s->man_start_com ||
+        (!fifo8_is_empty(&s->tx_fifo) &&
+         !(s->regs[R_CONFIG] & MAN_START_EN))) {
+        xilinx_spips_check_zero_pump(s);
+        xilinx_spips_flush_txfifo(s);
+    }
+    if (fifo8_is_empty(&s->tx_fifo) && !s->regs[R_TRANSFER_SIZE]) {
+        s->man_start_com = false;
+    }
+    xilinx_spips_update_ixr(s);
+}
+
+static void xlnx_zynqmp_qspips_check_flush(XlnxZynqMPQSPIPS *s)
+{
+    bool gqspi_has_work = s->regs[R_GQSPI_DATA_STS] ||
+                          !fifo32_is_empty(&s->fifo_g);
+
+    if (ARRAY_FIELD_EX32(s->regs, GQSPI_SELECT, GENERIC_QSPI_EN)) {
+        if (s->man_start_com_g || (gqspi_has_work &&
+             !ARRAY_FIELD_EX32(s->regs, GQSPI_CNFG, GEN_FIFO_START_MODE))) {
+            xlnx_zynqmp_qspips_flush_fifo_g(s);
+        }
+    } else {
+        xilinx_spips_check_flush(XILINX_SPIPS(s));
+    }
+    if (!gqspi_has_work) {
+        s->man_start_com_g = false;
+    }
+    xlnx_zynqmp_qspips_update_ixr(s);
+}
+
+static inline int rx_data_bytes(Fifo8 *fifo, uint8_t *value, int max)
 {
     int i;
 
-    for (i = 0; i < max && !fifo8_is_empty(&s->rx_fifo); ++i) {
-        value[i] = fifo8_pop(&s->rx_fifo);
+    for (i = 0; i < max && !fifo8_is_empty(fifo); ++i) {
+        value[i] = fifo8_pop(fifo);
+    }
+    return max - i;
+}
+
+static const void *pop_buf(Fifo8 *fifo, uint32_t max, uint32_t *num)
+{
+    void *ret;
+
+    if (max == 0 || max > fifo->num) {
+        abort();
+    }
+    *num = MIN(fifo->capacity - fifo->head, max);
+    ret = &fifo->data[fifo->head];
+    fifo->head += *num;
+    fifo->head %= fifo->capacity;
+    fifo->num -= *num;
+    return ret;
+}
+
+static void xlnx_zynqmp_qspips_notify(void *opaque)
+{
+    XlnxZynqMPQSPIPS *rq = XLNX_ZYNQMP_QSPIPS(opaque);
+    XilinxSPIPS *s = XILINX_SPIPS(rq);
+    Fifo8 *recv_fifo;
+
+    if (ARRAY_FIELD_EX32(rq->regs, GQSPI_SELECT, GENERIC_QSPI_EN)) {
+        if (!(ARRAY_FIELD_EX32(rq->regs, GQSPI_CNFG, MODE_EN) == 2)) {
+            return;
+        }
+        recv_fifo = &rq->rx_fifo_g;
+    } else {
+        if (!(s->regs[R_CMND] & R_CMND_DMA_EN)) {
+            return;
+        }
+        recv_fifo = &s->rx_fifo;
+    }
+    while (recv_fifo->num >= 4
+           && stream_can_push(rq->dma, xlnx_zynqmp_qspips_notify, rq))
+    {
+        size_t ret;
+        uint32_t num;
+        const void *rxd = pop_buf(recv_fifo, 4, &num);
+
+        memcpy(rq->dma_buf, rxd, num);
+
+        ret = stream_push(rq->dma, rq->dma_buf, 4);
+        assert(ret == 4);
+        xlnx_zynqmp_qspips_check_flush(rq);
     }
 }
 
@@ -374,6 +831,7 @@ static uint64_t xilinx_spips_read(void *opaque, hwaddr addr,
     uint32_t mask = ~0;
     uint32_t ret;
     uint8_t rx_buf[4];
+    int shortfall;
 
     addr >>= 2;
     switch (addr) {
@@ -384,6 +842,7 @@ static uint64_t xilinx_spips_read(void *opaque, hwaddr addr,
         ret = s->regs[addr] & IXR_ALL;
         s->regs[addr] = 0;
         DB_PRINT_L(0, "addr=" TARGET_FMT_plx " = %x\n", addr * 4, ret);
+        xilinx_spips_update_ixr(s);
         return ret;
     case R_INTR_MASK:
         mask = IXR_ALL;
@@ -404,10 +863,15 @@ static uint64_t xilinx_spips_read(void *opaque, hwaddr addr,
         break;
     case R_RX_DATA:
         memset(rx_buf, 0, sizeof(rx_buf));
-        rx_data_bytes(s, rx_buf, s->num_txrx_bytes);
-        ret = s->regs[R_CONFIG] & ENDIAN ? cpu_to_be32(*(uint32_t *)rx_buf)
-                        : cpu_to_le32(*(uint32_t *)rx_buf);
+        shortfall = rx_data_bytes(&s->rx_fifo, rx_buf, s->num_txrx_bytes);
+        ret = s->regs[R_CONFIG] & R_CONFIG_ENDIAN ?
+                        cpu_to_be32(*(uint32_t *)rx_buf) :
+                        cpu_to_le32(*(uint32_t *)rx_buf);
+        if (!(s->regs[R_CONFIG] & R_CONFIG_ENDIAN)) {
+            ret <<= 8 * shortfall;
+        }
         DB_PRINT_L(0, "addr=" TARGET_FMT_plx " = %x\n", addr * 4, ret);
+        xilinx_spips_check_flush(s);
         xilinx_spips_update_ixr(s);
         return ret;
     }
@@ -417,16 +881,39 @@ static uint64_t xilinx_spips_read(void *opaque, hwaddr addr,
 
 }
 
-static inline void tx_data_bytes(XilinxSPIPS *s, uint32_t value, int num)
+static uint64_t xlnx_zynqmp_qspips_read(void *opaque,
+                                        hwaddr addr, unsigned size)
 {
-    int i;
-    for (i = 0; i < num && !fifo8_is_full(&s->tx_fifo); ++i) {
-        if (s->regs[R_CONFIG] & ENDIAN) {
-            fifo8_push(&s->tx_fifo, (uint8_t)(value >> 24));
-            value <<= 8;
-        } else {
-            fifo8_push(&s->tx_fifo, (uint8_t)value);
-            value >>= 8;
+    XlnxZynqMPQSPIPS *s = XLNX_ZYNQMP_QSPIPS(opaque);
+    uint32_t reg = addr / 4;
+    uint32_t ret;
+    uint8_t rx_buf[4];
+    int shortfall;
+
+    if (reg <= R_MOD_ID) {
+        return xilinx_spips_read(opaque, addr, size);
+    } else {
+        switch (reg) {
+        case R_GQSPI_RXD:
+            if (fifo8_is_empty(&s->rx_fifo_g)) {
+                qemu_log_mask(LOG_GUEST_ERROR,
+                              "Read from empty GQSPI RX FIFO\n");
+                return 0;
+            }
+            memset(rx_buf, 0, sizeof(rx_buf));
+            shortfall = rx_data_bytes(&s->rx_fifo_g, rx_buf,
+                                      XILINX_SPIPS(s)->num_txrx_bytes);
+            ret = ARRAY_FIELD_EX32(s->regs, GQSPI_CNFG, ENDIAN) ?
+                  cpu_to_be32(*(uint32_t *)rx_buf) :
+                  cpu_to_le32(*(uint32_t *)rx_buf);
+            if (!ARRAY_FIELD_EX32(s->regs, GQSPI_CNFG, ENDIAN)) {
+                ret <<= 8 * shortfall;
+            }
+            xlnx_zynqmp_qspips_check_flush(s);
+            xlnx_zynqmp_qspips_update_ixr(s);
+            return ret;
+        default:
+            return s->regs[reg];
         }
     }
 }
@@ -435,7 +922,6 @@ static void xilinx_spips_write(void *opaque, hwaddr addr,
                                         uint64_t value, unsigned size)
 {
     int mask = ~0;
-    int man_start_com = 0;
     XilinxSPIPS *s = opaque;
 
     DB_PRINT_L(0, "addr=" TARGET_FMT_plx " = %x\n", addr, (unsigned)value);
@@ -443,8 +929,8 @@ static void xilinx_spips_write(void *opaque, hwaddr addr,
     switch (addr) {
     case R_CONFIG:
         mask = ~(R_CONFIG_RSVD | MAN_START_COM);
-        if (value & MAN_START_COM) {
-            man_start_com = 1;
+        if ((value & MAN_START_COM) && (s->regs[R_CONFIG] & MAN_START_EN)) {
+            s->man_start_com = true;
         }
         break;
     case R_INTR_STATUS:
@@ -471,25 +957,26 @@ static void xilinx_spips_write(void *opaque, hwaddr addr,
         mask = 0;
         break;
     case R_TX_DATA:
-        tx_data_bytes(s, (uint32_t)value, s->num_txrx_bytes);
+        tx_data_bytes(&s->tx_fifo, (uint32_t)value, s->num_txrx_bytes,
+                      s->regs[R_CONFIG] & R_CONFIG_ENDIAN);
         goto no_reg_update;
     case R_TXD1:
-        tx_data_bytes(s, (uint32_t)value, 1);
+        tx_data_bytes(&s->tx_fifo, (uint32_t)value, 1,
+                      s->regs[R_CONFIG] & R_CONFIG_ENDIAN);
         goto no_reg_update;
     case R_TXD2:
-        tx_data_bytes(s, (uint32_t)value, 2);
+        tx_data_bytes(&s->tx_fifo, (uint32_t)value, 2,
+                      s->regs[R_CONFIG] & R_CONFIG_ENDIAN);
         goto no_reg_update;
     case R_TXD3:
-        tx_data_bytes(s, (uint32_t)value, 3);
+        tx_data_bytes(&s->tx_fifo, (uint32_t)value, 3,
+                      s->regs[R_CONFIG] & R_CONFIG_ENDIAN);
         goto no_reg_update;
     }
     s->regs[addr] = (s->regs[addr] & ~mask) | (value & mask);
 no_reg_update:
     xilinx_spips_update_cs_lines(s);
-    if ((man_start_com && s->regs[R_CONFIG] & MAN_START_EN) ||
-            (fifo8_is_empty(&s->tx_fifo) && s->regs[R_CONFIG] & MAN_START_EN)) {
-        xilinx_spips_flush_txfifo(s);
-    }
+    xilinx_spips_check_flush(s);
     xilinx_spips_update_cs_lines(s);
     xilinx_spips_update_ixr(s);
 }
@@ -517,6 +1004,7 @@ static void xilinx_qspips_write(void *opaque, hwaddr addr,
                                 uint64_t value, unsigned size)
 {
     XilinxQSPIPS *q = XILINX_QSPIPS(opaque);
+    XilinxSPIPS *s = XILINX_SPIPS(opaque);
 
     xilinx_spips_write(opaque, addr, value, size);
     addr >>= 2;
@@ -524,6 +1012,72 @@ static void xilinx_qspips_write(void *opaque, hwaddr addr,
     if (addr == R_LQSPI_CFG) {
         xilinx_qspips_invalidate_mmio_ptr(q);
     }
+    if (s->regs[R_CMND] & R_CMND_RXFIFO_DRAIN) {
+        fifo8_reset(&s->rx_fifo);
+    }
+}
+
+static void xlnx_zynqmp_qspips_write(void *opaque, hwaddr addr,
+                                        uint64_t value, unsigned size)
+{
+    XlnxZynqMPQSPIPS *s = XLNX_ZYNQMP_QSPIPS(opaque);
+    uint32_t reg = addr / 4;
+
+    if (reg <= R_MOD_ID) {
+        xilinx_qspips_write(opaque, addr, value, size);
+    } else {
+        switch (reg) {
+        case R_GQSPI_CNFG:
+            if (FIELD_EX32(value, GQSPI_CNFG, GEN_FIFO_START) &&
+                ARRAY_FIELD_EX32(s->regs, GQSPI_CNFG, GEN_FIFO_START_MODE)) {
+                s->man_start_com_g = true;
+            }
+            s->regs[reg] = value & ~(R_GQSPI_CNFG_GEN_FIFO_START_MASK);
+            break;
+        case R_GQSPI_GEN_FIFO:
+            if (!fifo32_is_full(&s->fifo_g)) {
+                fifo32_push(&s->fifo_g, value);
+            }
+            break;
+        case R_GQSPI_TXD:
+            tx_data_bytes(&s->tx_fifo_g, (uint32_t)value, 4,
+                          ARRAY_FIELD_EX32(s->regs, GQSPI_CNFG, ENDIAN));
+            break;
+        case R_GQSPI_FIFO_CTRL:
+            if (FIELD_EX32(value, GQSPI_FIFO_CTRL, GENERIC_FIFO_RESET)) {
+                fifo32_reset(&s->fifo_g);
+            }
+            if (FIELD_EX32(value, GQSPI_FIFO_CTRL, TX_FIFO_RESET)) {
+                fifo8_reset(&s->tx_fifo_g);
+            }
+            if (FIELD_EX32(value, GQSPI_FIFO_CTRL, RX_FIFO_RESET)) {
+                fifo8_reset(&s->rx_fifo_g);
+            }
+            break;
+        case R_GQSPI_IDR:
+            s->regs[R_GQSPI_IMR] |= value;
+            break;
+        case R_GQSPI_IER:
+            s->regs[R_GQSPI_IMR] &= ~value;
+            break;
+        case R_GQSPI_ISR:
+            s->regs[R_GQSPI_ISR] &= ~value;
+            break;
+        case R_GQSPI_IMR:
+        case R_GQSPI_RXD:
+        case R_GQSPI_GF_SNAPSHOT:
+        case R_GQSPI_MOD_ID:
+            break;
+        default:
+            s->regs[reg] = value;
+            break;
+        }
+        xlnx_zynqmp_qspips_update_cs_lines(s);
+        xlnx_zynqmp_qspips_check_flush(s);
+        xlnx_zynqmp_qspips_update_cs_lines(s);
+        xlnx_zynqmp_qspips_update_ixr(s);
+    }
+    xlnx_zynqmp_qspips_notify(s);
 }
 
 static const MemoryRegionOps qspips_ops = {
@@ -532,6 +1086,12 @@ static const MemoryRegionOps qspips_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
+static const MemoryRegionOps xlnx_zynqmp_qspips_ops = {
+    .read = xlnx_zynqmp_qspips_read,
+    .write = xlnx_zynqmp_qspips_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
 #define LQSPI_CACHE_SIZE 1024
 
 static void lqspi_load_cache(void *opaque, hwaddr addr)
@@ -563,6 +1123,9 @@ static void lqspi_load_cache(void *opaque, hwaddr addr)
         fifo8_push(&s->tx_fifo, s->regs[R_LQSPI_CFG] & LQSPI_CFG_INST_CODE);
         /* read address */
         DB_PRINT_L(0, "pushing read address %06x\n", flash_addr);
+        if (s->regs[R_LQSPI_CFG] & LQSPI_CFG_ADDR4) {
+            fifo8_push(&s->tx_fifo, (uint8_t)(flash_addr >> 24));
+        }
         fifo8_push(&s->tx_fifo, (uint8_t)(flash_addr >> 16));
         fifo8_push(&s->tx_fifo, (uint8_t)(flash_addr >> 8));
         fifo8_push(&s->tx_fifo, (uint8_t)flash_addr);
@@ -586,11 +1149,11 @@ static void lqspi_load_cache(void *opaque, hwaddr addr)
 
         while (cache_entry < LQSPI_CACHE_SIZE) {
             for (i = 0; i < 64; ++i) {
-                tx_data_bytes(s, 0, 1);
+                tx_data_bytes(&s->tx_fifo, 0, 1, false);
             }
             xilinx_spips_flush_txfifo(s);
             for (i = 0; i < 64; ++i) {
-                rx_data_bytes(s, &q->lqspi_buf[cache_entry++], 1);
+                rx_data_bytes(&s->rx_fifo, &q->lqspi_buf[cache_entry++], 1);
             }
         }
 
@@ -666,6 +1229,7 @@ static void xilinx_spips_realize(DeviceState *dev, Error **errp)
     }
 
     s->cs_lines = g_new0(qemu_irq, s->num_cs * s->num_busses);
+    s->cs_lines_state = g_new0(bool, s->num_cs * s->num_busses);
     for (i = 0, cs = s->cs_lines; i < s->num_busses; ++i, cs += s->num_cs) {
         ssi_auto_connect_slaves(DEVICE(s), cs, s->spi[i]);
     }
@@ -676,7 +1240,7 @@ static void xilinx_spips_realize(DeviceState *dev, Error **errp)
     }
 
     memory_region_init_io(&s->iomem, OBJECT(s), xsc->reg_ops, s,
-                          "spi", XLNX_SPIPS_R_MAX * 4);
+                          "spi", XLNX_ZYNQMP_SPIPS_R_MAX * 4);
     sysbus_init_mmio(sbd, &s->iomem);
 
     s->irqline = -1;
@@ -714,6 +1278,28 @@ static void xilinx_qspips_realize(DeviceState *dev, Error **errp)
     }
 }
 
+static void xlnx_zynqmp_qspips_realize(DeviceState *dev, Error **errp)
+{
+    XlnxZynqMPQSPIPS *s = XLNX_ZYNQMP_QSPIPS(dev);
+    XilinxSPIPSClass *xsc = XILINX_SPIPS_GET_CLASS(s);
+
+    xilinx_qspips_realize(dev, errp);
+    fifo8_create(&s->rx_fifo_g, xsc->rx_fifo_size);
+    fifo8_create(&s->tx_fifo_g, xsc->tx_fifo_size);
+    fifo32_create(&s->fifo_g, 32);
+}
+
+static void xlnx_zynqmp_qspips_init(Object *obj)
+{
+    XlnxZynqMPQSPIPS *rq = XLNX_ZYNQMP_QSPIPS(obj);
+
+    object_property_add_link(obj, "stream-connected-dma", TYPE_STREAM_SLAVE,
+                             (Object **)&rq->dma,
+                             object_property_allow_set_link,
+                             OBJ_PROP_LINK_UNREF_ON_RELEASE,
+                             NULL);
+}
+
 static int xilinx_spips_post_load(void *opaque, int version_id)
 {
     xilinx_spips_update_ixr((XilinxSPIPS *)opaque);
@@ -735,6 +1321,46 @@ static const VMStateDescription vmstate_xilinx_spips = {
     }
 };
 
+static int xlnx_zynqmp_qspips_post_load(void *opaque, int version_id)
+{
+    XlnxZynqMPQSPIPS *s = (XlnxZynqMPQSPIPS *)opaque;
+    XilinxSPIPS *qs = XILINX_SPIPS(s);
+
+    if (ARRAY_FIELD_EX32(s->regs, GQSPI_SELECT, GENERIC_QSPI_EN) &&
+        fifo8_is_empty(&qs->rx_fifo) && fifo8_is_empty(&qs->tx_fifo)) {
+        xlnx_zynqmp_qspips_update_ixr(s);
+        xlnx_zynqmp_qspips_update_cs_lines(s);
+    }
+    return 0;
+}
+
+static const VMStateDescription vmstate_xilinx_qspips = {
+    .name = "xilinx_qspips",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT(parent_obj, XilinxQSPIPS, 0,
+                       vmstate_xilinx_spips, XilinxSPIPS),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription vmstate_xlnx_zynqmp_qspips = {
+    .name = "xlnx_zynqmp_qspips",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .post_load = xlnx_zynqmp_qspips_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT(parent_obj, XlnxZynqMPQSPIPS, 0,
+                       vmstate_xilinx_qspips, XilinxQSPIPS),
+        VMSTATE_FIFO8(tx_fifo_g, XlnxZynqMPQSPIPS),
+        VMSTATE_FIFO8(rx_fifo_g, XlnxZynqMPQSPIPS),
+        VMSTATE_FIFO32(fifo_g, XlnxZynqMPQSPIPS),
+        VMSTATE_UINT32_ARRAY(regs, XlnxZynqMPQSPIPS, XLNX_ZYNQMP_SPIPS_R_MAX),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static Property xilinx_qspips_properties[] = {
     /* We had to turn this off for 2.10 as it is not compatible with migration.
      * It can be enabled but will prevent the device to be migrated.
@@ -779,6 +1405,19 @@ static void xilinx_spips_class_init(ObjectClass *klass, void *data)
     xsc->tx_fifo_size = TXFF_A;
 }
 
+static void xlnx_zynqmp_qspips_class_init(ObjectClass *klass, void * data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    XilinxSPIPSClass *xsc = XILINX_SPIPS_CLASS(klass);
+
+    dc->realize = xlnx_zynqmp_qspips_realize;
+    dc->reset = xlnx_zynqmp_qspips_reset;
+    dc->vmsd = &vmstate_xlnx_zynqmp_qspips;
+    xsc->reg_ops = &xlnx_zynqmp_qspips_ops;
+    xsc->rx_fifo_size = RXFF_A_Q;
+    xsc->tx_fifo_size = TXFF_A_Q;
+}
+
 static const TypeInfo xilinx_spips_info = {
     .name  = TYPE_XILINX_SPIPS,
     .parent = TYPE_SYS_BUS_DEVICE,
@@ -794,10 +1433,19 @@ static const TypeInfo xilinx_qspips_info = {
     .class_init = xilinx_qspips_class_init,
 };
 
+static const TypeInfo xlnx_zynqmp_qspips_info = {
+    .name  = TYPE_XLNX_ZYNQMP_QSPIPS,
+    .parent = TYPE_XILINX_QSPIPS,
+    .instance_size  = sizeof(XlnxZynqMPQSPIPS),
+    .instance_init  = xlnx_zynqmp_qspips_init,
+    .class_init = xlnx_zynqmp_qspips_class_init,
+};
+
 static void xilinx_spips_register_types(void)
 {
     type_register_static(&xilinx_spips_info);
     type_register_static(&xilinx_qspips_info);
+    type_register_static(&xlnx_zynqmp_qspips_info);
 }
 
 type_init(xilinx_spips_register_types)
diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h
index 6eff81a..3e6fb9b 100644
--- a/include/hw/arm/xlnx-zynqmp.h
+++ b/include/hw/arm/xlnx-zynqmp.h
@@ -40,6 +40,10 @@
 #define XLNX_ZYNQMP_NUM_SDHCI 2
 #define XLNX_ZYNQMP_NUM_SPIS 2
 
+#define XLNX_ZYNQMP_NUM_QSPI_BUS 2
+#define XLNX_ZYNQMP_NUM_QSPI_BUS_CS 2
+#define XLNX_ZYNQMP_NUM_QSPI_FLASH 4
+
 #define XLNX_ZYNQMP_NUM_OCM_BANKS 4
 #define XLNX_ZYNQMP_OCM_RAM_0_ADDRESS 0xFFFC0000
 #define XLNX_ZYNQMP_OCM_RAM_SIZE 0x10000
@@ -83,6 +87,7 @@ typedef struct XlnxZynqMPState {
     SysbusAHCIState sata;
     SDHCIState sdhci[XLNX_ZYNQMP_NUM_SDHCI];
     XilinxSPIPS spi[XLNX_ZYNQMP_NUM_SPIS];
+    XlnxZynqMPQSPIPS qspi;
     XlnxDPState dp;
     XlnxDPDMAState dpdma;
 
diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h
index ac7997c..8bc2911 100644
--- a/include/hw/intc/armv7m_nvic.h
+++ b/include/hw/intc/armv7m_nvic.h
@@ -78,13 +78,15 @@ typedef struct NVICState {
 
     MemoryRegion sysregmem;
     MemoryRegion sysreg_ns_mem;
+    MemoryRegion systickmem;
+    MemoryRegion systick_ns_mem;
     MemoryRegion container;
 
     uint32_t num_irq;
     qemu_irq excpout;
     qemu_irq sysresetreq;
 
-    SysTickState systick;
+    SysTickState systick[M_REG_NUM_BANKS];
 } NVICState;
 
 #endif
diff --git a/include/hw/ssi/xilinx_spips.h b/include/hw/ssi/xilinx_spips.h
index 06aa096..d398a4e 100644
--- a/include/hw/ssi/xilinx_spips.h
+++ b/include/hw/ssi/xilinx_spips.h
@@ -26,11 +26,29 @@
 #define XILINX_SPIPS_H
 
 #include "hw/ssi/ssi.h"
-#include "qemu/fifo8.h"
+#include "qemu/fifo32.h"
+#include "hw/stream.h"
 
 typedef struct XilinxSPIPS XilinxSPIPS;
 
 #define XLNX_SPIPS_R_MAX        (0x100 / 4)
+#define XLNX_ZYNQMP_SPIPS_R_MAX (0x830 / 4)
+
+/* Bite off 4k chunks at a time */
+#define LQSPI_CACHE_SIZE 1024
+
+typedef enum {
+    READ = 0x3,         READ_4 = 0x13,
+    FAST_READ = 0xb,    FAST_READ_4 = 0x0c,
+    DOR = 0x3b,         DOR_4 = 0x3c,
+    QOR = 0x6b,         QOR_4 = 0x6c,
+    DIOR = 0xbb,        DIOR_4 = 0xbc,
+    QIOR = 0xeb,        QIOR_4 = 0xec,
+
+    PP = 0x2,           PP_4 = 0x12,
+    DPP = 0xa2,
+    QPP = 0x32,         QPP_4 = 0x34,
+} FlashCMD;
 
 struct XilinxSPIPS {
     SysBusDevice parent_obj;
@@ -45,19 +63,70 @@ struct XilinxSPIPS {
     uint8_t num_busses;
 
     uint8_t snoop_state;
+    int cmd_dummies;
+    uint8_t link_state;
+    uint8_t link_state_next;
+    uint8_t link_state_next_when;
     qemu_irq *cs_lines;
+    bool *cs_lines_state;
     SSIBus **spi;
 
     Fifo8 rx_fifo;
     Fifo8 tx_fifo;
 
     uint8_t num_txrx_bytes;
+    uint32_t rx_discard;
 
     uint32_t regs[XLNX_SPIPS_R_MAX];
+
+    bool man_start_com;
 };
 
+typedef struct {
+    XilinxSPIPS parent_obj;
+
+    uint8_t lqspi_buf[LQSPI_CACHE_SIZE];
+    hwaddr lqspi_cached_addr;
+    Error *migration_blocker;
+    bool mmio_execution_enabled;
+} XilinxQSPIPS;
+
+typedef struct {
+    XilinxQSPIPS parent_obj;
+
+    StreamSlave *dma;
+    uint8_t dma_buf[4];
+    int gqspi_irqline;
+
+    uint32_t regs[XLNX_ZYNQMP_SPIPS_R_MAX];
+
+    /* GQSPI has seperate tx/rx fifos */
+    Fifo8 rx_fifo_g;
+    Fifo8 tx_fifo_g;
+    Fifo32 fifo_g;
+    /*
+     * At the end of each generic command, misaligned extra bytes are discard
+     * or padded to tx and rx respectively to round it out (and avoid need for
+     * individual byte access. Since we use byte fifos, keep track of the
+     * alignment WRT to word access.
+     */
+    uint8_t rx_fifo_g_align;
+    uint8_t tx_fifo_g_align;
+    bool man_start_com_g;
+} XlnxZynqMPQSPIPS;
+
+typedef struct XilinxSPIPSClass {
+    SysBusDeviceClass parent_class;
+
+    const MemoryRegionOps *reg_ops;
+
+    uint32_t rx_fifo_size;
+    uint32_t tx_fifo_size;
+} XilinxSPIPSClass;
+
 #define TYPE_XILINX_SPIPS "xlnx.ps7-spi"
 #define TYPE_XILINX_QSPIPS "xlnx.ps7-qspi"
+#define TYPE_XLNX_ZYNQMP_QSPIPS "xlnx.usmp-gqspi"
 
 #define XILINX_SPIPS(obj) \
      OBJECT_CHECK(XilinxSPIPS, (obj), TYPE_XILINX_SPIPS)
@@ -69,4 +138,7 @@ struct XilinxSPIPS {
 #define XILINX_QSPIPS(obj) \
      OBJECT_CHECK(XilinxQSPIPS, (obj), TYPE_XILINX_QSPIPS)
 
+#define XLNX_ZYNQMP_QSPIPS(obj) \
+     OBJECT_CHECK(XlnxZynqMPQSPIPS, (obj), TYPE_XLNX_ZYNQMP_QSPIPS)
+
 #endif /* XILINX_SPIPS_H */
diff --git a/include/standard-headers/asm-s390/virtio-ccw.h b/include/standard-headers/asm-s390/virtio-ccw.h
index a9a4ebf..967aad3 100644
--- a/include/standard-headers/asm-s390/virtio-ccw.h
+++ b/include/standard-headers/asm-s390/virtio-ccw.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Definitions for virtio-ccw devices.
  *
diff --git a/include/standard-headers/asm-x86/hyperv.h b/include/standard-headers/asm-x86/hyperv.h
index 5f95d5e..ce87d0c 100644
--- a/include/standard-headers/asm-x86/hyperv.h
+++ b/include/standard-headers/asm-x86/hyperv.h
@@ -1,393 +1 @@
-#ifndef _ASM_X86_HYPERV_H
-#define _ASM_X86_HYPERV_H
-
-#include "standard-headers/linux/types.h"
-
-/*
- * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
- * is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
- */
-#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS	0x40000000
-#define HYPERV_CPUID_INTERFACE			0x40000001
-#define HYPERV_CPUID_VERSION			0x40000002
-#define HYPERV_CPUID_FEATURES			0x40000003
-#define HYPERV_CPUID_ENLIGHTMENT_INFO		0x40000004
-#define HYPERV_CPUID_IMPLEMENT_LIMITS		0x40000005
-
-#define HYPERV_HYPERVISOR_PRESENT_BIT		0x80000000
-#define HYPERV_CPUID_MIN			0x40000005
-#define HYPERV_CPUID_MAX			0x4000ffff
-
-/*
- * Feature identification. EAX indicates which features are available
- * to the partition based upon the current partition privileges.
- */
-
-/* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */
-#define HV_X64_MSR_VP_RUNTIME_AVAILABLE		(1 << 0)
-/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
-#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE	(1 << 1)
-/* Partition reference TSC MSR is available */
-#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE              (1 << 9)
-
-/* A partition's reference time stamp counter (TSC) page */
-#define HV_X64_MSR_REFERENCE_TSC		0x40000021
-
-/*
- * There is a single feature flag that signifies if the partition has access
- * to MSRs with local APIC and TSC frequencies.
- */
-#define HV_X64_ACCESS_FREQUENCY_MSRS		(1 << 11)
-
-/*
- * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
- * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
- */
-#define HV_X64_MSR_SYNIC_AVAILABLE		(1 << 2)
-/*
- * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through
- * HV_X64_MSR_STIMER3_COUNT) available
- */
-#define HV_X64_MSR_SYNTIMER_AVAILABLE		(1 << 3)
-/*
- * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
- * are available
- */
-#define HV_X64_MSR_APIC_ACCESS_AVAILABLE	(1 << 4)
-/* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/
-#define HV_X64_MSR_HYPERCALL_AVAILABLE		(1 << 5)
-/* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/
-#define HV_X64_MSR_VP_INDEX_AVAILABLE		(1 << 6)
-/* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/
-#define HV_X64_MSR_RESET_AVAILABLE		(1 << 7)
- /*
-  * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE,
-  * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE,
-  * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available
-  */
-#define HV_X64_MSR_STAT_PAGES_AVAILABLE		(1 << 8)
-
-/* Frequency MSRs available */
-#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE	(1 << 8)
-
-/* Crash MSR available */
-#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10)
-
-/*
- * Feature identification: EBX indicates which flags were specified at
- * partition creation. The format is the same as the partition creation
- * flag structure defined in section Partition Creation Flags.
- */
-#define HV_X64_CREATE_PARTITIONS		(1 << 0)
-#define HV_X64_ACCESS_PARTITION_ID		(1 << 1)
-#define HV_X64_ACCESS_MEMORY_POOL		(1 << 2)
-#define HV_X64_ADJUST_MESSAGE_BUFFERS		(1 << 3)
-#define HV_X64_POST_MESSAGES			(1 << 4)
-#define HV_X64_SIGNAL_EVENTS			(1 << 5)
-#define HV_X64_CREATE_PORT			(1 << 6)
-#define HV_X64_CONNECT_PORT			(1 << 7)
-#define HV_X64_ACCESS_STATS			(1 << 8)
-#define HV_X64_DEBUGGING			(1 << 11)
-#define HV_X64_CPU_POWER_MANAGEMENT		(1 << 12)
-#define HV_X64_CONFIGURE_PROFILER		(1 << 13)
-
-/*
- * Feature identification. EDX indicates which miscellaneous features
- * are available to the partition.
- */
-/* The MWAIT instruction is available (per section MONITOR / MWAIT) */
-#define HV_X64_MWAIT_AVAILABLE				(1 << 0)
-/* Guest debugging support is available */
-#define HV_X64_GUEST_DEBUGGING_AVAILABLE		(1 << 1)
-/* Performance Monitor support is available*/
-#define HV_X64_PERF_MONITOR_AVAILABLE			(1 << 2)
-/* Support for physical CPU dynamic partitioning events is available*/
-#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE	(1 << 3)
-/*
- * Support for passing hypercall input parameter block via XMM
- * registers is available
- */
-#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		(1 << 4)
-/* Support for a virtual guest idle state is available */
-#define HV_X64_GUEST_IDLE_STATE_AVAILABLE		(1 << 5)
-/* Guest crash data handler available */
-#define HV_X64_GUEST_CRASH_MSR_AVAILABLE		(1 << 10)
-
-/*
- * Implementation recommendations. Indicates which behaviors the hypervisor
- * recommends the OS implement for optimal performance.
- */
- /*
-  * Recommend using hypercall for address space switches rather
-  * than MOV to CR3 instruction
-  */
-#define HV_X64_AS_SWITCH_RECOMMENDED		(1 << 0)
-/* Recommend using hypercall for local TLB flushes rather
- * than INVLPG or MOV to CR3 instructions */
-#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED	(1 << 1)
-/*
- * Recommend using hypercall for remote TLB flushes rather
- * than inter-processor interrupts
- */
-#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED	(1 << 2)
-/*
- * Recommend using MSRs for accessing APIC registers
- * EOI, ICR and TPR rather than their memory-mapped counterparts
- */
-#define HV_X64_APIC_ACCESS_RECOMMENDED		(1 << 3)
-/* Recommend using the hypervisor-provided MSR to initiate a system RESET */
-#define HV_X64_SYSTEM_RESET_RECOMMENDED		(1 << 4)
-/*
- * Recommend using relaxed timing for this partition. If used,
- * the VM should disable any watchdog timeouts that rely on the
- * timely delivery of external interrupts
- */
-#define HV_X64_RELAXED_TIMING_RECOMMENDED	(1 << 5)
-
-/*
- * Virtual APIC support
- */
-#define HV_X64_DEPRECATING_AEOI_RECOMMENDED	(1 << 9)
-
-/* Recommend using the newer ExProcessorMasks interface */
-#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED	(1 << 11)
-
-/*
- * Crash notification flag.
- */
-#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63)
-
-/* MSR used to identify the guest OS. */
-#define HV_X64_MSR_GUEST_OS_ID			0x40000000
-
-/* MSR used to setup pages used to communicate with the hypervisor. */
-#define HV_X64_MSR_HYPERCALL			0x40000001
-
-/* MSR used to provide vcpu index */
-#define HV_X64_MSR_VP_INDEX			0x40000002
-
-/* MSR used to reset the guest OS. */
-#define HV_X64_MSR_RESET			0x40000003
-
-/* MSR used to provide vcpu runtime in 100ns units */
-#define HV_X64_MSR_VP_RUNTIME			0x40000010
-
-/* MSR used to read the per-partition time reference counter */
-#define HV_X64_MSR_TIME_REF_COUNT		0x40000020
-
-/* MSR used to retrieve the TSC frequency */
-#define HV_X64_MSR_TSC_FREQUENCY		0x40000022
-
-/* MSR used to retrieve the local APIC timer frequency */
-#define HV_X64_MSR_APIC_FREQUENCY		0x40000023
-
-/* Define the virtual APIC registers */
-#define HV_X64_MSR_EOI				0x40000070
-#define HV_X64_MSR_ICR				0x40000071
-#define HV_X64_MSR_TPR				0x40000072
-#define HV_X64_MSR_APIC_ASSIST_PAGE		0x40000073
-
-/* Define synthetic interrupt controller model specific registers. */
-#define HV_X64_MSR_SCONTROL			0x40000080
-#define HV_X64_MSR_SVERSION			0x40000081
-#define HV_X64_MSR_SIEFP			0x40000082
-#define HV_X64_MSR_SIMP				0x40000083
-#define HV_X64_MSR_EOM				0x40000084
-#define HV_X64_MSR_SINT0			0x40000090
-#define HV_X64_MSR_SINT1			0x40000091
-#define HV_X64_MSR_SINT2			0x40000092
-#define HV_X64_MSR_SINT3			0x40000093
-#define HV_X64_MSR_SINT4			0x40000094
-#define HV_X64_MSR_SINT5			0x40000095
-#define HV_X64_MSR_SINT6			0x40000096
-#define HV_X64_MSR_SINT7			0x40000097
-#define HV_X64_MSR_SINT8			0x40000098
-#define HV_X64_MSR_SINT9			0x40000099
-#define HV_X64_MSR_SINT10			0x4000009A
-#define HV_X64_MSR_SINT11			0x4000009B
-#define HV_X64_MSR_SINT12			0x4000009C
-#define HV_X64_MSR_SINT13			0x4000009D
-#define HV_X64_MSR_SINT14			0x4000009E
-#define HV_X64_MSR_SINT15			0x4000009F
-
-/*
- * Synthetic Timer MSRs. Four timers per vcpu.
- */
-#define HV_X64_MSR_STIMER0_CONFIG		0x400000B0
-#define HV_X64_MSR_STIMER0_COUNT		0x400000B1
-#define HV_X64_MSR_STIMER1_CONFIG		0x400000B2
-#define HV_X64_MSR_STIMER1_COUNT		0x400000B3
-#define HV_X64_MSR_STIMER2_CONFIG		0x400000B4
-#define HV_X64_MSR_STIMER2_COUNT		0x400000B5
-#define HV_X64_MSR_STIMER3_CONFIG		0x400000B6
-#define HV_X64_MSR_STIMER3_COUNT		0x400000B7
-
-/* Hyper-V guest crash notification MSR's */
-#define HV_X64_MSR_CRASH_P0			0x40000100
-#define HV_X64_MSR_CRASH_P1			0x40000101
-#define HV_X64_MSR_CRASH_P2			0x40000102
-#define HV_X64_MSR_CRASH_P3			0x40000103
-#define HV_X64_MSR_CRASH_P4			0x40000104
-#define HV_X64_MSR_CRASH_CTL			0x40000105
-#define HV_X64_MSR_CRASH_CTL_NOTIFY		(1ULL << 63)
-#define HV_X64_MSR_CRASH_PARAMS		\
-		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
-
-#define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
-#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
-#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
-		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
-
-/* Declare the various hypercall operations. */
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE	0x0002
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST	0x0003
-#define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX  0x0013
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX   0x0014
-#define HVCALL_POST_MESSAGE			0x005c
-#define HVCALL_SIGNAL_EVENT			0x005d
-
-#define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE		0x00000001
-#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT	12
-#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK	\
-		(~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
-
-#define HV_X64_MSR_TSC_REFERENCE_ENABLE		0x00000001
-#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT	12
-
-#define HV_PROCESSOR_POWER_STATE_C0		0
-#define HV_PROCESSOR_POWER_STATE_C1		1
-#define HV_PROCESSOR_POWER_STATE_C2		2
-#define HV_PROCESSOR_POWER_STATE_C3		3
-
-#define HV_FLUSH_ALL_PROCESSORS			BIT(0)
-#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	BIT(1)
-#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	BIT(2)
-#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	BIT(3)
-
-enum HV_GENERIC_SET_FORMAT {
-	HV_GENERIC_SET_SPARCE_4K,
-	HV_GENERIC_SET_ALL,
-};
-
-/* hypercall status code */
-#define HV_STATUS_SUCCESS			0
-#define HV_STATUS_INVALID_HYPERCALL_CODE	2
-#define HV_STATUS_INVALID_HYPERCALL_INPUT	3
-#define HV_STATUS_INVALID_ALIGNMENT		4
-#define HV_STATUS_INSUFFICIENT_MEMORY		11
-#define HV_STATUS_INVALID_CONNECTION_ID		18
-#define HV_STATUS_INSUFFICIENT_BUFFERS		19
-
-typedef struct _HV_REFERENCE_TSC_PAGE {
-	uint32_t tsc_sequence;
-	uint32_t res1;
-	uint64_t tsc_scale;
-	int64_t tsc_offset;
-} HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE;
-
-/* Define the number of synthetic interrupt sources. */
-#define HV_SYNIC_SINT_COUNT		(16)
-/* Define the expected SynIC version. */
-#define HV_SYNIC_VERSION_1		(0x1)
-
-#define HV_SYNIC_CONTROL_ENABLE		(1ULL << 0)
-#define HV_SYNIC_SIMP_ENABLE		(1ULL << 0)
-#define HV_SYNIC_SIEFP_ENABLE		(1ULL << 0)
-#define HV_SYNIC_SINT_MASKED		(1ULL << 16)
-#define HV_SYNIC_SINT_AUTO_EOI		(1ULL << 17)
-#define HV_SYNIC_SINT_VECTOR_MASK	(0xFF)
-
-#define HV_SYNIC_STIMER_COUNT		(4)
-
-/* Define synthetic interrupt controller message constants. */
-#define HV_MESSAGE_SIZE			(256)
-#define HV_MESSAGE_PAYLOAD_BYTE_COUNT	(240)
-#define HV_MESSAGE_PAYLOAD_QWORD_COUNT	(30)
-
-/* Define hypervisor message types. */
-enum hv_message_type {
-	HVMSG_NONE			= 0x00000000,
-
-	/* Memory access messages. */
-	HVMSG_UNMAPPED_GPA		= 0x80000000,
-	HVMSG_GPA_INTERCEPT		= 0x80000001,
-
-	/* Timer notification messages. */
-	HVMSG_TIMER_EXPIRED			= 0x80000010,
-
-	/* Error messages. */
-	HVMSG_INVALID_VP_REGISTER_VALUE	= 0x80000020,
-	HVMSG_UNRECOVERABLE_EXCEPTION	= 0x80000021,
-	HVMSG_UNSUPPORTED_FEATURE		= 0x80000022,
-
-	/* Trace buffer complete messages. */
-	HVMSG_EVENTLOG_BUFFERCOMPLETE	= 0x80000040,
-
-	/* Platform-specific processor intercept messages. */
-	HVMSG_X64_IOPORT_INTERCEPT		= 0x80010000,
-	HVMSG_X64_MSR_INTERCEPT		= 0x80010001,
-	HVMSG_X64_CPUID_INTERCEPT		= 0x80010002,
-	HVMSG_X64_EXCEPTION_INTERCEPT	= 0x80010003,
-	HVMSG_X64_APIC_EOI			= 0x80010004,
-	HVMSG_X64_LEGACY_FP_ERROR		= 0x80010005
-};
-
-/* Define synthetic interrupt controller message flags. */
-union hv_message_flags {
-	uint8_t asu8;
-	struct {
-		uint8_t msg_pending:1;
-		uint8_t reserved:7;
-	};
-};
-
-/* Define port identifier type. */
-union hv_port_id {
-	uint32_t asu32;
-	struct {
-		uint32_t id:24;
-		uint32_t reserved:8;
-	} u;
-};
-
-/* Define synthetic interrupt controller message header. */
-struct hv_message_header {
-	uint32_t message_type;
-	uint8_t payload_size;
-	union hv_message_flags message_flags;
-	uint8_t reserved[2];
-	union {
-		uint64_t sender;
-		union hv_port_id port;
-	};
-};
-
-/* Define synthetic interrupt controller message format. */
-struct hv_message {
-	struct hv_message_header header;
-	union {
-		uint64_t payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
-	} u;
-};
-
-/* Define the synthetic interrupt message page layout. */
-struct hv_message_page {
-	struct hv_message sint_message[HV_SYNIC_SINT_COUNT];
-};
-
-/* Define timer message payload structure. */
-struct hv_timer_message_payload {
-	uint32_t timer_index;
-	uint32_t reserved;
-	uint64_t expiration_time;	/* When the timer expired */
-	uint64_t delivery_time;	/* When the message was delivered */
-};
-
-#define HV_STIMER_ENABLE		(1ULL << 0)
-#define HV_STIMER_PERIODIC		(1ULL << 1)
-#define HV_STIMER_LAZY			(1ULL << 2)
-#define HV_STIMER_AUTOENABLE		(1ULL << 3)
-#define HV_STIMER_SINT(config)		(uint8_t)(((config) >> 16) & 0x0F)
-
-#endif
+        /* this is a temporary placeholder until kvm_para.h stops including it */
diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h
index 2fa0f4e..79841b5 100644
--- a/include/standard-headers/linux/input-event-codes.h
+++ b/include/standard-headers/linux/input-event-codes.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Input event codes
  *
@@ -406,6 +407,7 @@
 #define BTN_TOOL_MOUSE		0x146
 #define BTN_TOOL_LENS		0x147
 #define BTN_TOOL_QUINTTAP	0x148	/* Five fingers on trackpad */
+#define BTN_STYLUS3		0x149
 #define BTN_TOUCH		0x14a
 #define BTN_STYLUS		0x14b
 #define BTN_STYLUS2		0x14c
diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h
index 666e201..bc3e6d3 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (c) 1999-2002 Vojtech Pavlik
  *
diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h
index f8d5804..70c2b2a 100644
--- a/include/standard-headers/linux/pci_regs.h
+++ b/include/standard-headers/linux/pci_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  *	pci_regs.h
  *
@@ -746,6 +747,7 @@
 #define PCI_ERR_ROOT_FIRST_FATAL	0x00000010 /* First UNC is Fatal */
 #define PCI_ERR_ROOT_NONFATAL_RCV	0x00000020 /* Non-Fatal Received */
 #define PCI_ERR_ROOT_FATAL_RCV		0x00000040 /* Fatal Received */
+#define PCI_ERR_ROOT_AER_IRQ		0xf8000000 /* Advanced Error Interrupt Message Number */
 #define PCI_ERR_ROOT_ERR_SRC	52	/* Error Source Identification */
 
 /* Virtual Channel */
@@ -939,9 +941,13 @@
 #define PCI_SATA_SIZEOF_LONG	16
 
 /* Resizable BARs */
+#define PCI_REBAR_CAP		4	/* capability register */
+#define  PCI_REBAR_CAP_SIZES		0x00FFFFF0  /* supported BAR sizes */
 #define PCI_REBAR_CTRL		8	/* control register */
-#define  PCI_REBAR_CTRL_NBAR_MASK	(7 << 5)	/* mask for # bars */
-#define  PCI_REBAR_CTRL_NBAR_SHIFT	5	/* shift for # bars */
+#define  PCI_REBAR_CTRL_BAR_IDX		0x00000007  /* BAR index */
+#define  PCI_REBAR_CTRL_NBAR_MASK	0x000000E0  /* # of resizable BARs */
+#define  PCI_REBAR_CTRL_NBAR_SHIFT	5  	    /* shift for # of BARs */
+#define  PCI_REBAR_CTRL_BAR_SIZE	0x00001F00  /* BAR size */
 
 /* Dynamic Power Allocation */
 #define PCI_DPA_CAP		4	/* capability register */
@@ -960,6 +966,7 @@
 
 /* Downstream Port Containment */
 #define PCI_EXP_DPC_CAP			4	/* DPC Capability */
+#define PCI_EXP_DPC_IRQ			0x1f	/* DPC Interrupt Message Number */
 #define  PCI_EXP_DPC_CAP_RP_EXT		0x20	/* Root Port Extensions for DPC */
 #define  PCI_EXP_DPC_CAP_POISONED_TLP	0x40	/* Poisoned TLP Egress Blocking Supported */
 #define  PCI_EXP_DPC_CAP_SW_TRIGGER	0x80	/* Software Triggering Supported */
@@ -995,19 +1002,25 @@
 #define  PCI_PTM_CTRL_ENABLE		0x00000001  /* PTM enable */
 #define  PCI_PTM_CTRL_ROOT		0x00000002  /* Root select */
 
-/* L1 PM Substates */
-#define PCI_L1SS_CAP		    4	/* capability register */
-#define  PCI_L1SS_CAP_PCIPM_L1_2	 1	/* PCI PM L1.2 Support */
-#define  PCI_L1SS_CAP_PCIPM_L1_1	 2	/* PCI PM L1.1 Support */
-#define  PCI_L1SS_CAP_ASPM_L1_2		 4	/* ASPM L1.2 Support */
-#define  PCI_L1SS_CAP_ASPM_L1_1		 8	/* ASPM L1.1 Support */
-#define  PCI_L1SS_CAP_L1_PM_SS		16	/* L1 PM Substates Support */
-#define PCI_L1SS_CTL1		    8	/* Control Register 1 */
-#define  PCI_L1SS_CTL1_PCIPM_L1_2	1	/* PCI PM L1.2 Enable */
-#define  PCI_L1SS_CTL1_PCIPM_L1_1	2	/* PCI PM L1.1 Support */
-#define  PCI_L1SS_CTL1_ASPM_L1_2	4	/* ASPM L1.2 Support */
-#define  PCI_L1SS_CTL1_ASPM_L1_1	8	/* ASPM L1.1 Support */
-#define  PCI_L1SS_CTL1_L1SS_MASK	0x0000000F
-#define PCI_L1SS_CTL2		    0xC	/* Control Register 2 */
+/* ASPM L1 PM Substates */
+#define PCI_L1SS_CAP		0x04	/* Capabilities Register */
+#define  PCI_L1SS_CAP_PCIPM_L1_2	0x00000001  /* PCI-PM L1.2 Supported */
+#define  PCI_L1SS_CAP_PCIPM_L1_1	0x00000002  /* PCI-PM L1.1 Supported */
+#define  PCI_L1SS_CAP_ASPM_L1_2		0x00000004  /* ASPM L1.2 Supported */
+#define  PCI_L1SS_CAP_ASPM_L1_1		0x00000008  /* ASPM L1.1 Supported */
+#define  PCI_L1SS_CAP_L1_PM_SS		0x00000010  /* L1 PM Substates Supported */
+#define  PCI_L1SS_CAP_CM_RESTORE_TIME	0x0000ff00  /* Port Common_Mode_Restore_Time */
+#define  PCI_L1SS_CAP_P_PWR_ON_SCALE	0x00030000  /* Port T_POWER_ON scale */
+#define  PCI_L1SS_CAP_P_PWR_ON_VALUE	0x00f80000  /* Port T_POWER_ON value */
+#define PCI_L1SS_CTL1		0x08	/* Control 1 Register */
+#define  PCI_L1SS_CTL1_PCIPM_L1_2	0x00000001  /* PCI-PM L1.2 Enable */
+#define  PCI_L1SS_CTL1_PCIPM_L1_1	0x00000002  /* PCI-PM L1.1 Enable */
+#define  PCI_L1SS_CTL1_ASPM_L1_2	0x00000004  /* ASPM L1.2 Enable */
+#define  PCI_L1SS_CTL1_ASPM_L1_1	0x00000008  /* ASPM L1.1 Enable */
+#define  PCI_L1SS_CTL1_L1SS_MASK	0x0000000f
+#define  PCI_L1SS_CTL1_CM_RESTORE_TIME	0x0000ff00  /* Common_Mode_Restore_Time */
+#define  PCI_L1SS_CTL1_LTR_L12_TH_VALUE	0x03ff0000  /* LTR_L1.2_THRESHOLD_Value */
+#define  PCI_L1SS_CTL1_LTR_L12_TH_SCALE	0xe0000000  /* LTR_L1.2_THRESHOLD_Scale */
+#define PCI_L1SS_CTL2		0x0c	/* Control 2 Register */
 
 #endif /* LINUX_PCI_REGS_H */
diff --git a/linux-headers/asm-arm/kvm.h b/linux-headers/asm-arm/kvm.h
index fa9fae8..4392955 100644
--- a/linux-headers/asm-arm/kvm.h
+++ b/linux-headers/asm-arm/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (C) 2012 - Virtual Open Systems and Columbia University
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
@@ -151,6 +152,12 @@ struct kvm_arch_memory_slot {
 	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
+/* PL1 Physical Timer Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM_CP15_REG32(0, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CNT		ARM_CP15_REG64(0, 14)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM_CP15_REG64(2, 14)
+
+/* Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
 #define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
@@ -215,6 +222,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES		1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES	2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/linux-headers/asm-arm/kvm_para.h b/linux-headers/asm-arm/kvm_para.h
index 14fab8f..baacc49 100644
--- a/linux-headers/asm-arm/kvm_para.h
+++ b/linux-headers/asm-arm/kvm_para.h
@@ -1 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #include <asm-generic/kvm_para.h>
diff --git a/linux-headers/asm-arm/unistd.h b/linux-headers/asm-arm/unistd.h
index 155571b..18b0825 100644
--- a/linux-headers/asm-arm/unistd.h
+++ b/linux-headers/asm-arm/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  *  arch/arm/include/asm/unistd.h
  *
@@ -35,5 +36,6 @@
 #define __ARM_NR_usr26			(__ARM_NR_BASE+3)
 #define __ARM_NR_usr32			(__ARM_NR_BASE+4)
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
+#define __ARM_NR_get_tls		(__ARM_NR_BASE+6)
 
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h
index d254700..4e80651 100644
--- a/linux-headers/asm-arm64/kvm.h
+++ b/linux-headers/asm-arm64/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (C) 2012,2013 - ARM Ltd
  * Author: Marc Zyngier <marc.zyngier@arm.com>
@@ -195,6 +196,12 @@ struct kvm_arch_memory_slot {
 
 #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
 
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
@@ -227,6 +234,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
diff --git a/linux-headers/asm-arm64/unistd.h b/linux-headers/asm-arm64/unistd.h
index 043d17a..5072cbd 100644
--- a/linux-headers/asm-arm64/unistd.h
+++ b/linux-headers/asm-arm64/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Copyright (C) 2012 ARM Ltd.
  *
diff --git a/linux-headers/asm-powerpc/epapr_hcalls.h b/linux-headers/asm-powerpc/epapr_hcalls.h
index 33b3f89..6cca559 100644
--- a/linux-headers/asm-powerpc/epapr_hcalls.h
+++ b/linux-headers/asm-powerpc/epapr_hcalls.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * ePAPR hcall interface
  *
diff --git a/linux-headers/asm-powerpc/kvm.h b/linux-headers/asm-powerpc/kvm.h
index 8cf8f0c..61d6049 100644
--- a/linux-headers/asm-powerpc/kvm.h
+++ b/linux-headers/asm-powerpc/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, version 2, as
diff --git a/linux-headers/asm-powerpc/kvm_para.h b/linux-headers/asm-powerpc/kvm_para.h
index 2abcc46..9beb49c 100644
--- a/linux-headers/asm-powerpc/kvm_para.h
+++ b/linux-headers/asm-powerpc/kvm_para.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, version 2, as
diff --git a/linux-headers/asm-powerpc/unistd.h b/linux-headers/asm-powerpc/unistd.h
index a1786340..36abf58 100644
--- a/linux-headers/asm-powerpc/unistd.h
+++ b/linux-headers/asm-powerpc/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
 /*
  * This file contains the system call numbers.
  *
diff --git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h
index 7b750ef..32d372e 100644
--- a/linux-headers/asm-s390/kvm.h
+++ b/linux-headers/asm-s390/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __LINUX_KVM_S390_H
 #define __LINUX_KVM_S390_H
 /*
diff --git a/linux-headers/asm-s390/kvm_para.h b/linux-headers/asm-s390/kvm_para.h
index ff1f4e7..0dc86b3 100644
--- a/linux-headers/asm-s390/kvm_para.h
+++ b/linux-headers/asm-s390/kvm_para.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * User API definitions for paravirtual devices on s390
  *
diff --git a/linux-headers/asm-s390/unistd.h b/linux-headers/asm-s390/unistd.h
index 65e7e59..99223b8 100644
--- a/linux-headers/asm-s390/unistd.h
+++ b/linux-headers/asm-s390/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  *  S390 version
  *
@@ -315,7 +316,8 @@
 #define __NR_pwritev2		377
 #define __NR_s390_guarded_storage	378
 #define __NR_statx		379
-#define NR_syscalls 380
+#define __NR_s390_sthyi		380
+#define NR_syscalls 381
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h
index c2824d0..f3a9604 100644
--- a/linux-headers/asm-x86/kvm.h
+++ b/linux-headers/asm-x86/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_KVM_H
 #define _ASM_X86_KVM_H
 
diff --git a/linux-headers/asm-x86/kvm_para.h b/linux-headers/asm-x86/kvm_para.h
index cefa127..4c300f6 100644
--- a/linux-headers/asm-x86/kvm_para.h
+++ b/linux-headers/asm-x86/kvm_para.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_KVM_PARA_H
 #define _ASM_X86_KVM_PARA_H
 
@@ -109,5 +110,4 @@ struct kvm_vcpu_pv_apf_data {
 #define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
 #define KVM_PV_EOI_DISABLED 0x0
 
-
 #endif /* _ASM_X86_KVM_PARA_H */
diff --git a/linux-headers/asm-x86/unistd.h b/linux-headers/asm-x86/unistd.h
index 1f99b12..c04f638 100644
--- a/linux-headers/asm-x86/unistd.h
+++ b/linux-headers/asm-x86/unistd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_UNISTD_H
 #define _ASM_X86_UNISTD_H
 
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index dd8a918..ce6c2f1 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __LINUX_KVM_H
 #define __LINUX_KVM_H
 
@@ -930,6 +931,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/linux-headers/linux/kvm_para.h b/linux-headers/linux/kvm_para.h
index 15b24ff..8bcd0aa 100644
--- a/linux-headers/linux/kvm_para.h
+++ b/linux-headers/linux/kvm_para.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef __LINUX_KVM_PARA_H
 #define __LINUX_KVM_PARA_H
 
diff --git a/linux-headers/linux/psci.h b/linux-headers/linux/psci.h
index 08d443f..ccd1773 100644
--- a/linux-headers/linux/psci.h
+++ b/linux-headers/linux/psci.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * ARM Power State and Coordination Interface (PSCI) header
  *
diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h
index b43cf0d..ce78878 100644
--- a/linux-headers/linux/userfaultfd.h
+++ b/linux-headers/linux/userfaultfd.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  *  include/linux/userfaultfd.h
  *
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 4e7ab4c..4312e96 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * VFIO API definition
  *
diff --git a/linux-headers/linux/vfio_ccw.h b/linux-headers/linux/vfio_ccw.h
index 3a56551..5bf96c3 100644
--- a/linux-headers/linux/vfio_ccw.h
+++ b/linux-headers/linux/vfio_ccw.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  * Interfaces for vfio-ccw
  *
diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h
index 1e86a3d..e336395 100644
--- a/linux-headers/linux/vhost.h
+++ b/linux-headers/linux/vhost.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_VHOST_H
 #define _LINUX_VHOST_H
 /* Userspace interface for in-kernel virtio accelerators. */
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 89d49cd..9631670 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -112,7 +112,7 @@ enum {
 #define ARM_CPU_VIRQ 2
 #define ARM_CPU_VFIQ 3
 
-#define NB_MMU_MODES 7
+#define NB_MMU_MODES 8
 /* ARM-specific extra insn start words:
  * 1: Conditional execution bits
  * 2: Partial exception syndrome for data aborts
@@ -2226,13 +2226,13 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
  * They have the following different MMU indexes:
  *  User
  *  Privileged
- *  Execution priority negative (this is like privileged, but the
- *  MPU HFNMIENA bit means that it may have different access permission
- *  check results to normal privileged code, so can't share a TLB).
+ *  User, execution priority negative (ie the MPU HFNMIENA bit may apply)
+ *  Privileged, execution priority negative (ditto)
  * If the CPU supports the v8M Security Extension then there are also:
  *  Secure User
  *  Secure Privileged
- *  Secure, execution priority negative
+ *  Secure User, execution priority negative
+ *  Secure Privileged, execution priority negative
  *
  * The ARMMMUIdx and the mmu index value used by the core QEMU TLB code
  * are not quite the same -- different CPU types (most notably M profile
@@ -2251,11 +2251,18 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
  * The constant names here are patterned after the general style of the names
  * of the AT/ATS operations.
  * The values used are carefully arranged to make mmu_idx => EL lookup easy.
+ * For M profile we arrange them to have a bit for priv, a bit for negpri
+ * and a bit for secure.
  */
 #define ARM_MMU_IDX_A 0x10 /* A profile */
 #define ARM_MMU_IDX_NOTLB 0x20 /* does not have a TLB */
 #define ARM_MMU_IDX_M 0x40 /* M profile */
 
+/* meanings of the bits for M profile mmu idx values */
+#define ARM_MMU_IDX_M_PRIV 0x1
+#define ARM_MMU_IDX_M_NEGPRI 0x2
+#define ARM_MMU_IDX_M_S 0x4
+
 #define ARM_MMU_IDX_TYPE_MASK (~0x7)
 #define ARM_MMU_IDX_COREIDX_MASK 0x7
 
@@ -2269,10 +2276,12 @@ typedef enum ARMMMUIdx {
     ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A,
     ARMMMUIdx_MUser = 0 | ARM_MMU_IDX_M,
     ARMMMUIdx_MPriv = 1 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MNegPri = 2 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSUser = 3 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSPriv = 4 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSNegPri = 5 | ARM_MMU_IDX_M,
+    ARMMMUIdx_MUserNegPri = 2 | ARM_MMU_IDX_M,
+    ARMMMUIdx_MPrivNegPri = 3 | ARM_MMU_IDX_M,
+    ARMMMUIdx_MSUser = 4 | ARM_MMU_IDX_M,
+    ARMMMUIdx_MSPriv = 5 | ARM_MMU_IDX_M,
+    ARMMMUIdx_MSUserNegPri = 6 | ARM_MMU_IDX_M,
+    ARMMMUIdx_MSPrivNegPri = 7 | ARM_MMU_IDX_M,
     /* Indexes below here don't have TLBs and are used only for AT system
      * instructions or for the first stage of an S12 page table walk.
      */
@@ -2293,10 +2302,12 @@ typedef enum ARMMMUIdxBit {
     ARMMMUIdxBit_S2NS = 1 << 6,
     ARMMMUIdxBit_MUser = 1 << 0,
     ARMMMUIdxBit_MPriv = 1 << 1,
-    ARMMMUIdxBit_MNegPri = 1 << 2,
-    ARMMMUIdxBit_MSUser = 1 << 3,
-    ARMMMUIdxBit_MSPriv = 1 << 4,
-    ARMMMUIdxBit_MSNegPri = 1 << 5,
+    ARMMMUIdxBit_MUserNegPri = 1 << 2,
+    ARMMMUIdxBit_MPrivNegPri = 1 << 3,
+    ARMMMUIdxBit_MSUser = 1 << 4,
+    ARMMMUIdxBit_MSPriv = 1 << 5,
+    ARMMMUIdxBit_MSUserNegPri = 1 << 6,
+    ARMMMUIdxBit_MSPrivNegPri = 1 << 7,
 } ARMMMUIdxBit;
 
 #define MMU_USER_IDX 0
@@ -2322,33 +2333,45 @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
     case ARM_MMU_IDX_A:
         return mmu_idx & 3;
     case ARM_MMU_IDX_M:
-        return (mmu_idx == ARMMMUIdx_MUser || mmu_idx == ARMMMUIdx_MSUser)
-            ? 0 : 1;
+        return mmu_idx & ARM_MMU_IDX_M_PRIV;
     default:
         g_assert_not_reached();
     }
 }
 
-/* Return the MMU index for a v7M CPU in the specified security state */
-static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env,
-                                                     bool secstate)
+/* Return the MMU index for a v7M CPU in the specified security and
+ * privilege state
+ */
+static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env,
+                                                              bool secstate,
+                                                              bool priv)
 {
-    int el = arm_current_el(env);
-    ARMMMUIdx mmu_idx;
+    ARMMMUIdx mmu_idx = ARM_MMU_IDX_M;
 
-    if (el == 0) {
-        mmu_idx = secstate ? ARMMMUIdx_MSUser : ARMMMUIdx_MUser;
-    } else {
-        mmu_idx = secstate ? ARMMMUIdx_MSPriv : ARMMMUIdx_MPriv;
+    if (priv) {
+        mmu_idx |= ARM_MMU_IDX_M_PRIV;
     }
 
     if (armv7m_nvic_neg_prio_requested(env->nvic, secstate)) {
-        mmu_idx = secstate ? ARMMMUIdx_MSNegPri : ARMMMUIdx_MNegPri;
+        mmu_idx |= ARM_MMU_IDX_M_NEGPRI;
+    }
+
+    if (secstate) {
+        mmu_idx |= ARM_MMU_IDX_M_S;
     }
 
     return mmu_idx;
 }
 
+/* Return the MMU index for a v7M CPU in the specified security state */
+static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env,
+                                                     bool secstate)
+{
+    bool priv = arm_current_el(env) != 0;
+
+    return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv);
+}
+
 /* Determine the current mmu_idx to use for normal loads/stores */
 static inline int cpu_mmu_index(CPUARMState *env, bool ifetch)
 {
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 91a9300..d1395f9 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -28,13 +28,13 @@ typedef struct ARMCacheAttrs {
 static bool get_phys_addr(CPUARMState *env, target_ulong address,
                           MMUAccessType access_type, ARMMMUIdx mmu_idx,
                           hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot,
-                          target_ulong *page_size, uint32_t *fsr,
+                          target_ulong *page_size,
                           ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs);
 
 static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
                                MMUAccessType access_type, ARMMMUIdx mmu_idx,
                                hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot,
-                               target_ulong *page_size_ptr, uint32_t *fsr,
+                               target_ulong *page_size_ptr,
                                ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs);
 
 /* Security attributes for an address, as returned by v8m_security_lookup. */
@@ -2160,20 +2160,44 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
     hwaddr phys_addr;
     target_ulong page_size;
     int prot;
-    uint32_t fsr;
     bool ret;
     uint64_t par64;
+    bool format64 = false;
     MemTxAttrs attrs = {};
     ARMMMUFaultInfo fi = {};
     ARMCacheAttrs cacheattrs = {};
 
     ret = get_phys_addr(env, value, access_type, mmu_idx, &phys_addr, &attrs,
-                        &prot, &page_size, &fsr, &fi, &cacheattrs);
-    if (arm_s1_regime_using_lpae_format(env, mmu_idx)) {
-        /* fsr is a DFSR/IFSR value for the long descriptor
-         * translation table format, but with WnR always clear.
-         * Convert it to a 64-bit PAR.
+                        &prot, &page_size, &fi, &cacheattrs);
+
+    if (is_a64(env)) {
+        format64 = true;
+    } else if (arm_feature(env, ARM_FEATURE_LPAE)) {
+        /*
+         * ATS1Cxx:
+         * * TTBCR.EAE determines whether the result is returned using the
+         *   32-bit or the 64-bit PAR format
+         * * Instructions executed in Hyp mode always use the 64bit format
+         *
+         * ATS1S2NSOxx uses the 64bit format if any of the following is true:
+         * * The Non-secure TTBCR.EAE bit is set to 1
+         * * The implementation includes EL2, and the value of HCR.VM is 1
+         *
+         * ATS1Hx always uses the 64bit format (not supported yet).
          */
+        format64 = arm_s1_regime_using_lpae_format(env, mmu_idx);
+
+        if (arm_feature(env, ARM_FEATURE_EL2)) {
+            if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) {
+                format64 |= env->cp15.hcr_el2 & HCR_VM;
+            } else {
+                format64 |= arm_current_el(env) == 2;
+            }
+        }
+    }
+
+    if (format64) {
+        /* Create a 64-bit PAR */
         par64 = (1 << 11); /* LPAE bit always set */
         if (!ret) {
             par64 |= phys_addr & ~0xfffULL;
@@ -2183,6 +2207,8 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
             par64 |= (uint64_t)cacheattrs.attrs << 56; /* ATTR */
             par64 |= cacheattrs.shareability << 7; /* SH */
         } else {
+            uint32_t fsr = arm_fi_to_lfsc(&fi);
+
             par64 |= 1; /* F */
             par64 |= (fsr & 0x3f) << 1; /* FS */
             /* Note that S2WLK and FSTAGE are always zero, because we don't
@@ -2207,6 +2233,8 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
                 par64 |= (1 << 9); /* NS */
             }
         } else {
+            uint32_t fsr = arm_fi_to_sfsc(&fi);
+
             par64 = ((fsr & (1 << 10)) >> 5) | ((fsr & (1 << 12)) >> 6) |
                     ((fsr & 0xf) << 1) | 1;
         }
@@ -5947,6 +5975,28 @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
     g_assert_not_reached();
 }
 
+uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op)
+{
+    /* The TT instructions can be used by unprivileged code, but in
+     * user-only emulation we don't have the MPU.
+     * Luckily since we know we are NonSecure unprivileged (and that in
+     * turn means that the A flag wasn't specified), all the bits in the
+     * register must be zero:
+     *  IREGION: 0 because IRVALID is 0
+     *  IRVALID: 0 because NS
+     *  S: 0 because NS
+     *  NSRW: 0 because NS
+     *  NSR: 0 because NS
+     *  RW: 0 because unpriv and A flag not set
+     *  R: 0 because unpriv and A flag not set
+     *  SRVALID: 0 because NS
+     *  MRVALID: 0 because unpriv and A flag not set
+     *  SREGION: 0 becaus SRVALID is 0
+     *  MREGION: 0 because MRVALID is 0
+     */
+    return 0;
+}
+
 void switch_mode(CPUARMState *env, int mode)
 {
     ARMCPU *cpu = arm_env_get_cpu(env);
@@ -6955,7 +7005,6 @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx,
     target_ulong page_size;
     hwaddr physaddr;
     int prot;
-    uint32_t fsr;
 
     v8m_security_lookup(env, addr, MMU_INST_FETCH, mmu_idx, &sattrs);
     if (!sattrs.nsc || sattrs.ns) {
@@ -6969,7 +7018,7 @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx,
         return false;
     }
     if (get_phys_addr(env, addr, MMU_INST_FETCH, mmu_idx,
-                      &physaddr, &attrs, &prot, &page_size, &fsr, &fi, NULL)) {
+                      &physaddr, &attrs, &prot, &page_size, &fi, NULL)) {
         /* the MPU lookup failed */
         env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_IACCVIOL_MASK;
         armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM, env->v7m.secure);
@@ -7856,11 +7905,13 @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_S1SE1:
     case ARMMMUIdx_S1NSE0:
     case ARMMMUIdx_S1NSE1:
+    case ARMMMUIdx_MPrivNegPri:
+    case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
-    case ARMMMUIdx_MNegPri:
     case ARMMMUIdx_MUser:
+    case ARMMMUIdx_MSPrivNegPri:
+    case ARMMMUIdx_MSUserNegPri:
     case ARMMMUIdx_MSPriv:
-    case ARMMMUIdx_MSNegPri:
     case ARMMMUIdx_MSUser:
         return 1;
     default:
@@ -7883,8 +7934,7 @@ static inline bool regime_translation_disabled(CPUARMState *env,
                 (R_V7M_MPU_CTRL_ENABLE_MASK | R_V7M_MPU_CTRL_HFNMIENA_MASK)) {
         case R_V7M_MPU_CTRL_ENABLE_MASK:
             /* Enabled, but not for HardFault and NMI */
-            return mmu_idx == ARMMMUIdx_MNegPri ||
-                mmu_idx == ARMMMUIdx_MSNegPri;
+            return mmu_idx & ARM_MMU_IDX_M_NEGPRI;
         case R_V7M_MPU_CTRL_ENABLE_MASK | R_V7M_MPU_CTRL_HFNMIENA_MASK:
             /* Enabled for all cases */
             return false;
@@ -8016,6 +8066,9 @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_S1SE0:
     case ARMMMUIdx_S1NSE0:
     case ARMMMUIdx_MUser:
+    case ARMMMUIdx_MSUser:
+    case ARMMMUIdx_MUserNegPri:
+    case ARMMMUIdx_MSUserNegPri:
         return true;
     default:
         return false;
@@ -8240,7 +8293,6 @@ static bool get_level1_table_address(CPUARMState *env, ARMMMUIdx mmu_idx,
 /* Translate a S1 pagetable walk through S2 if needed.  */
 static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
                                hwaddr addr, MemTxAttrs txattrs,
-                               uint32_t *fsr,
                                ARMMMUFaultInfo *fi)
 {
     if ((mmu_idx == ARMMMUIdx_S1NSE0 || mmu_idx == ARMMMUIdx_S1NSE1) &&
@@ -8251,7 +8303,7 @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
         int ret;
 
         ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_S2NS, &s2pa,
-                                 &txattrs, &s2prot, &s2size, fsr, fi, NULL);
+                                 &txattrs, &s2prot, &s2size, fi, NULL);
         if (ret) {
             fi->s2addr = addr;
             fi->stage2 = true;
@@ -8271,8 +8323,7 @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
  * (but not if it was for a debug access).
  */
 static uint32_t arm_ldl_ptw(CPUState *cs, hwaddr addr, bool is_secure,
-                            ARMMMUIdx mmu_idx, uint32_t *fsr,
-                            ARMMMUFaultInfo *fi)
+                            ARMMMUIdx mmu_idx, ARMMMUFaultInfo *fi)
 {
     ARMCPU *cpu = ARM_CPU(cs);
     CPUARMState *env = &cpu->env;
@@ -8281,7 +8332,7 @@ static uint32_t arm_ldl_ptw(CPUState *cs, hwaddr addr, bool is_secure,
 
     attrs.secure = is_secure;
     as = arm_addressspace(cs, attrs);
-    addr = S1_ptw_translate(env, mmu_idx, addr, attrs, fsr, fi);
+    addr = S1_ptw_translate(env, mmu_idx, addr, attrs, fi);
     if (fi->s1ptw) {
         return 0;
     }
@@ -8293,8 +8344,7 @@ static uint32_t arm_ldl_ptw(CPUState *cs, hwaddr addr, bool is_secure,
 }
 
 static uint64_t arm_ldq_ptw(CPUState *cs, hwaddr addr, bool is_secure,
-                            ARMMMUIdx mmu_idx, uint32_t *fsr,
-                            ARMMMUFaultInfo *fi)
+                            ARMMMUIdx mmu_idx, ARMMMUFaultInfo *fi)
 {
     ARMCPU *cpu = ARM_CPU(cs);
     CPUARMState *env = &cpu->env;
@@ -8303,7 +8353,7 @@ static uint64_t arm_ldq_ptw(CPUState *cs, hwaddr addr, bool is_secure,
 
     attrs.secure = is_secure;
     as = arm_addressspace(cs, attrs);
-    addr = S1_ptw_translate(env, mmu_idx, addr, attrs, fsr, fi);
+    addr = S1_ptw_translate(env, mmu_idx, addr, attrs, fi);
     if (fi->s1ptw) {
         return 0;
     }
@@ -8317,11 +8367,11 @@ static uint64_t arm_ldq_ptw(CPUState *cs, hwaddr addr, bool is_secure,
 static bool get_phys_addr_v5(CPUARMState *env, uint32_t address,
                              MMUAccessType access_type, ARMMMUIdx mmu_idx,
                              hwaddr *phys_ptr, int *prot,
-                             target_ulong *page_size, uint32_t *fsr,
+                             target_ulong *page_size,
                              ARMMMUFaultInfo *fi)
 {
     CPUState *cs = CPU(arm_env_get_cpu(env));
-    int code;
+    int level = 1;
     uint32_t table;
     uint32_t desc;
     int type;
@@ -8335,11 +8385,11 @@ static bool get_phys_addr_v5(CPUARMState *env, uint32_t address,
     /* Lookup l1 descriptor.  */
     if (!get_level1_table_address(env, mmu_idx, &table, address)) {
         /* Section translation fault if page walk is disabled by PD0 or PD1 */
-        code = 5;
+        fi->type = ARMFault_Translation;
         goto do_fault;
     }
     desc = arm_ldl_ptw(cs, table, regime_is_secure(env, mmu_idx),
-                       mmu_idx, fsr, fi);
+                       mmu_idx, fi);
     type = (desc & 3);
     domain = (desc >> 5) & 0x0f;
     if (regime_el(env, mmu_idx) == 1) {
@@ -8350,21 +8400,20 @@ static bool get_phys_addr_v5(CPUARMState *env, uint32_t address,
     domain_prot = (dacr >> (domain * 2)) & 3;
     if (type == 0) {
         /* Section translation fault.  */
-        code = 5;
+        fi->type = ARMFault_Translation;
         goto do_fault;
     }
+    if (type != 2) {
+        level = 2;
+    }
     if (domain_prot == 0 || domain_prot == 2) {
-        if (type == 2)
-            code = 9; /* Section domain fault.  */
-        else
-            code = 11; /* Page domain fault.  */
+        fi->type = ARMFault_Domain;
         goto do_fault;
     }
     if (type == 2) {
         /* 1Mb section.  */
         phys_addr = (desc & 0xfff00000) | (address & 0x000fffff);
         ap = (desc >> 10) & 3;
-        code = 13;
         *page_size = 1024 * 1024;
     } else {
         /* Lookup l2 entry.  */
@@ -8376,10 +8425,10 @@ static bool get_phys_addr_v5(CPUARMState *env, uint32_t address,
             table = (desc & 0xfffff000) | ((address >> 8) & 0xffc);
         }
         desc = arm_ldl_ptw(cs, table, regime_is_secure(env, mmu_idx),
-                           mmu_idx, fsr, fi);
+                           mmu_idx, fi);
         switch (desc & 3) {
         case 0: /* Page translation fault.  */
-            code = 7;
+            fi->type = ARMFault_Translation;
             goto do_fault;
         case 1: /* 64k page.  */
             phys_addr = (desc & 0xffff0000) | (address & 0xffff);
@@ -8402,7 +8451,7 @@ static bool get_phys_addr_v5(CPUARMState *env, uint32_t address,
                     /* UNPREDICTABLE in ARMv5; we choose to take a
                      * page translation fault.
                      */
-                    code = 7;
+                    fi->type = ARMFault_Translation;
                     goto do_fault;
                 }
             } else {
@@ -8415,29 +8464,29 @@ static bool get_phys_addr_v5(CPUARMState *env, uint32_t address,
             /* Never happens, but compiler isn't smart enough to tell.  */
             abort();
         }
-        code = 15;
     }
     *prot = ap_to_rw_prot(env, mmu_idx, ap, domain_prot);
     *prot |= *prot ? PAGE_EXEC : 0;
     if (!(*prot & (1 << access_type))) {
         /* Access permission fault.  */
+        fi->type = ARMFault_Permission;
         goto do_fault;
     }
     *phys_ptr = phys_addr;
     return false;
 do_fault:
-    *fsr = code | (domain << 4);
+    fi->domain = domain;
+    fi->level = level;
     return true;
 }
 
 static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
                              MMUAccessType access_type, ARMMMUIdx mmu_idx,
                              hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot,
-                             target_ulong *page_size, uint32_t *fsr,
-                             ARMMMUFaultInfo *fi)
+                             target_ulong *page_size, ARMMMUFaultInfo *fi)
 {
     CPUState *cs = CPU(arm_env_get_cpu(env));
-    int code;
+    int level = 1;
     uint32_t table;
     uint32_t desc;
     uint32_t xn;
@@ -8454,17 +8503,17 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
     /* Lookup l1 descriptor.  */
     if (!get_level1_table_address(env, mmu_idx, &table, address)) {
         /* Section translation fault if page walk is disabled by PD0 or PD1 */
-        code = 5;
+        fi->type = ARMFault_Translation;
         goto do_fault;
     }
     desc = arm_ldl_ptw(cs, table, regime_is_secure(env, mmu_idx),
-                       mmu_idx, fsr, fi);
+                       mmu_idx, fi);
     type = (desc & 3);
     if (type == 0 || (type == 3 && !arm_feature(env, ARM_FEATURE_PXN))) {
         /* Section translation fault, or attempt to use the encoding
          * which is Reserved on implementations without PXN.
          */
-        code = 5;
+        fi->type = ARMFault_Translation;
         goto do_fault;
     }
     if ((type == 1) || !(desc & (1 << 18))) {
@@ -8476,13 +8525,13 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
     } else {
         dacr = env->cp15.dacr_s;
     }
+    if (type == 1) {
+        level = 2;
+    }
     domain_prot = (dacr >> (domain * 2)) & 3;
     if (domain_prot == 0 || domain_prot == 2) {
-        if (type != 1) {
-            code = 9; /* Section domain fault.  */
-        } else {
-            code = 11; /* Page domain fault.  */
-        }
+        /* Section or Page domain fault */
+        fi->type = ARMFault_Domain;
         goto do_fault;
     }
     if (type != 1) {
@@ -8500,7 +8549,6 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
         ap = ((desc >> 10) & 3) | ((desc >> 13) & 4);
         xn = desc & (1 << 4);
         pxn = desc & 1;
-        code = 13;
         ns = extract32(desc, 19, 1);
     } else {
         if (arm_feature(env, ARM_FEATURE_PXN)) {
@@ -8510,11 +8558,11 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
         /* Lookup l2 entry.  */
         table = (desc & 0xfffffc00) | ((address >> 10) & 0x3fc);
         desc = arm_ldl_ptw(cs, table, regime_is_secure(env, mmu_idx),
-                           mmu_idx, fsr, fi);
+                           mmu_idx, fi);
         ap = ((desc >> 4) & 3) | ((desc >> 7) & 4);
         switch (desc & 3) {
         case 0: /* Page translation fault.  */
-            code = 7;
+            fi->type = ARMFault_Translation;
             goto do_fault;
         case 1: /* 64k page.  */
             phys_addr = (desc & 0xffff0000) | (address & 0xffff);
@@ -8530,7 +8578,6 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
             /* Never happens, but compiler isn't smart enough to tell.  */
             abort();
         }
-        code = 15;
     }
     if (domain_prot == 3) {
         *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
@@ -8538,15 +8585,17 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
         if (pxn && !regime_is_user(env, mmu_idx)) {
             xn = 1;
         }
-        if (xn && access_type == MMU_INST_FETCH)
+        if (xn && access_type == MMU_INST_FETCH) {
+            fi->type = ARMFault_Permission;
             goto do_fault;
+        }
 
         if (arm_feature(env, ARM_FEATURE_V6K) &&
                 (regime_sctlr(env, mmu_idx) & SCTLR_AFE)) {
             /* The simplified model uses AP[0] as an access control bit.  */
             if ((ap & 1) == 0) {
                 /* Access flag fault.  */
-                code = (code == 15) ? 6 : 3;
+                fi->type = ARMFault_AccessFlag;
                 goto do_fault;
             }
             *prot = simple_ap_to_rw_prot(env, mmu_idx, ap >> 1);
@@ -8558,6 +8607,7 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
         }
         if (!(*prot & (1 << access_type))) {
             /* Access permission fault.  */
+            fi->type = ARMFault_Permission;
             goto do_fault;
         }
     }
@@ -8571,19 +8621,11 @@ static bool get_phys_addr_v6(CPUARMState *env, uint32_t address,
     *phys_ptr = phys_addr;
     return false;
 do_fault:
-    *fsr = code | (domain << 4);
+    fi->domain = domain;
+    fi->level = level;
     return true;
 }
 
-/* Fault type for long-descriptor MMU fault reporting; this corresponds
- * to bits [5..2] in the STATUS field in long-format DFSR/IFSR.
- */
-typedef enum {
-    translation_fault = 1,
-    access_fault = 2,
-    permission_fault = 3,
-} MMUFaultType;
-
 /*
  * check_s2_mmu_setup
  * @cpu:        ARMCPU
@@ -8685,13 +8727,13 @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs)
 static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
                                MMUAccessType access_type, ARMMMUIdx mmu_idx,
                                hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot,
-                               target_ulong *page_size_ptr, uint32_t *fsr,
+                               target_ulong *page_size_ptr,
                                ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs)
 {
     ARMCPU *cpu = arm_env_get_cpu(env);
     CPUState *cs = CPU(cpu);
     /* Read an LPAE long-descriptor translation table. */
-    MMUFaultType fault_type = translation_fault;
+    ARMFaultType fault_type = ARMFault_Translation;
     uint32_t level;
     uint32_t epd = 0;
     int32_t t0sz, t1sz;
@@ -8801,7 +8843,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         ttbr_select = 1;
     } else {
         /* in the gap between the two regions, this is a Translation fault */
-        fault_type = translation_fault;
+        fault_type = ARMFault_Translation;
         goto do_fault;
     }
 
@@ -8887,7 +8929,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         ok = check_s2_mmu_setup(cpu, aarch64, startlevel,
                                 inputsize, stride);
         if (!ok) {
-            fault_type = translation_fault;
+            fault_type = ARMFault_Translation;
             goto do_fault;
         }
         level = startlevel;
@@ -8921,7 +8963,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         descaddr |= (address >> (stride * (4 - level))) & indexmask;
         descaddr &= ~7ULL;
         nstable = extract32(tableattrs, 4, 1);
-        descriptor = arm_ldq_ptw(cs, descaddr, !nstable, mmu_idx, fsr, fi);
+        descriptor = arm_ldq_ptw(cs, descaddr, !nstable, mmu_idx, fi);
         if (fi->s1ptw) {
             goto do_fault;
         }
@@ -8973,7 +9015,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
     /* Here descaddr is the final physical address, and attributes
      * are all in attrs.
      */
-    fault_type = access_fault;
+    fault_type = ARMFault_AccessFlag;
     if ((attrs & (1 << 8)) == 0) {
         /* Access flag */
         goto do_fault;
@@ -8991,7 +9033,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         *prot = get_S1prot(env, mmu_idx, aarch64, ap, ns, xn, pxn);
     }
 
-    fault_type = permission_fault;
+    fault_type = ARMFault_Permission;
     if (!(*prot & (1 << access_type))) {
         goto do_fault;
     }
@@ -9023,8 +9065,8 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
     return false;
 
 do_fault:
-    /* Long-descriptor format IFSR/DFSR value */
-    *fsr = (1 << 9) | (fault_type << 2) | level;
+    fi->type = fault_type;
+    fi->level = level;
     /* Tag the error as S2 for failed S1 PTW at S2 or ordinary S2.  */
     fi->stage2 = fi->s1ptw || (mmu_idx == ARMMMUIdx_S2NS);
     return true;
@@ -9108,7 +9150,8 @@ static inline bool m_is_system_region(CPUARMState *env, uint32_t address)
 
 static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address,
                                  MMUAccessType access_type, ARMMMUIdx mmu_idx,
-                                 hwaddr *phys_ptr, int *prot, uint32_t *fsr)
+                                 hwaddr *phys_ptr, int *prot,
+                                 ARMMMUFaultInfo *fi)
 {
     ARMCPU *cpu = arm_env_get_cpu(env);
     int n;
@@ -9203,7 +9246,7 @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address,
         if (n == -1) { /* no hits */
             if (!pmsav7_use_background_region(cpu, mmu_idx, is_user)) {
                 /* background fault */
-                *fsr = 0;
+                fi->type = ARMFault_Background;
                 return true;
             }
             get_phys_addr_pmsav7_default(env, mmu_idx, address, prot);
@@ -9261,7 +9304,8 @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address,
         }
     }
 
-    *fsr = 0x00d; /* Permission fault */
+    fi->type = ARMFault_Permission;
+    fi->level = 1;
     return !(*prot & (1 << access_type));
 }
 
@@ -9344,67 +9388,28 @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address,
     }
 }
 
-static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address,
-                                 MMUAccessType access_type, ARMMMUIdx mmu_idx,
-                                 hwaddr *phys_ptr, MemTxAttrs *txattrs,
-                                 int *prot, uint32_t *fsr)
+static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
+                              MMUAccessType access_type, ARMMMUIdx mmu_idx,
+                              hwaddr *phys_ptr, MemTxAttrs *txattrs,
+                              int *prot, ARMMMUFaultInfo *fi, uint32_t *mregion)
 {
+    /* Perform a PMSAv8 MPU lookup (without also doing the SAU check
+     * that a full phys-to-virt translation does).
+     * mregion is (if not NULL) set to the region number which matched,
+     * or -1 if no region number is returned (MPU off, address did not
+     * hit a region, address hit in multiple regions).
+     */
     ARMCPU *cpu = arm_env_get_cpu(env);
     bool is_user = regime_is_user(env, mmu_idx);
     uint32_t secure = regime_is_secure(env, mmu_idx);
     int n;
     int matchregion = -1;
     bool hit = false;
-    V8M_SAttributes sattrs = {};
 
     *phys_ptr = address;
     *prot = 0;
-
-    if (arm_feature(env, ARM_FEATURE_M_SECURITY)) {
-        v8m_security_lookup(env, address, access_type, mmu_idx, &sattrs);
-        if (access_type == MMU_INST_FETCH) {
-            /* Instruction fetches always use the MMU bank and the
-             * transaction attribute determined by the fetch address,
-             * regardless of CPU state. This is painful for QEMU
-             * to handle, because it would mean we need to encode
-             * into the mmu_idx not just the (user, negpri) information
-             * for the current security state but also that for the
-             * other security state, which would balloon the number
-             * of mmu_idx values needed alarmingly.
-             * Fortunately we can avoid this because it's not actually
-             * possible to arbitrarily execute code from memory with
-             * the wrong security attribute: it will always generate
-             * an exception of some kind or another, apart from the
-             * special case of an NS CPU executing an SG instruction
-             * in S&NSC memory. So we always just fail the translation
-             * here and sort things out in the exception handler
-             * (including possibly emulating an SG instruction).
-             */
-            if (sattrs.ns != !secure) {
-                *fsr = sattrs.nsc ? M_FAKE_FSR_NSC_EXEC : M_FAKE_FSR_SFAULT;
-                return true;
-            }
-        } else {
-            /* For data accesses we always use the MMU bank indicated
-             * by the current CPU state, but the security attributes
-             * might downgrade a secure access to nonsecure.
-             */
-            if (sattrs.ns) {
-                txattrs->secure = false;
-            } else if (!secure) {
-                /* NS access to S memory must fault.
-                 * Architecturally we should first check whether the
-                 * MPU information for this address indicates that we
-                 * are doing an unaligned access to Device memory, which
-                 * should generate a UsageFault instead. QEMU does not
-                 * currently check for that kind of unaligned access though.
-                 * If we added it we would need to do so as a special case
-                 * for M_FAKE_FSR_SFAULT in arm_v7m_cpu_do_interrupt().
-                 */
-                *fsr = M_FAKE_FSR_SFAULT;
-                return true;
-            }
-        }
+    if (mregion) {
+        *mregion = -1;
     }
 
     /* Unlike the ARM ARM pseudocode, we don't need to check whether this
@@ -9442,7 +9447,8 @@ static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address,
                 /* Multiple regions match -- always a failure (unlike
                  * PMSAv7 where highest-numbered-region wins)
                  */
-                *fsr = 0x00d; /* permission fault */
+                fi->type = ARMFault_Permission;
+                fi->level = 1;
                 return true;
             }
 
@@ -9470,7 +9476,7 @@ static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address,
 
     if (!hit) {
         /* background fault */
-        *fsr = 0;
+        fi->type = ARMFault_Background;
         return true;
     }
 
@@ -9493,15 +9499,88 @@ static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address,
         /* We don't need to look the attribute up in the MAIR0/MAIR1
          * registers because that only tells us about cacheability.
          */
+        if (mregion) {
+            *mregion = matchregion;
+        }
     }
 
-    *fsr = 0x00d; /* Permission fault */
+    fi->type = ARMFault_Permission;
+    fi->level = 1;
     return !(*prot & (1 << access_type));
 }
 
+
+static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address,
+                                 MMUAccessType access_type, ARMMMUIdx mmu_idx,
+                                 hwaddr *phys_ptr, MemTxAttrs *txattrs,
+                                 int *prot, ARMMMUFaultInfo *fi)
+{
+    uint32_t secure = regime_is_secure(env, mmu_idx);
+    V8M_SAttributes sattrs = {};
+
+    if (arm_feature(env, ARM_FEATURE_M_SECURITY)) {
+        v8m_security_lookup(env, address, access_type, mmu_idx, &sattrs);
+        if (access_type == MMU_INST_FETCH) {
+            /* Instruction fetches always use the MMU bank and the
+             * transaction attribute determined by the fetch address,
+             * regardless of CPU state. This is painful for QEMU
+             * to handle, because it would mean we need to encode
+             * into the mmu_idx not just the (user, negpri) information
+             * for the current security state but also that for the
+             * other security state, which would balloon the number
+             * of mmu_idx values needed alarmingly.
+             * Fortunately we can avoid this because it's not actually
+             * possible to arbitrarily execute code from memory with
+             * the wrong security attribute: it will always generate
+             * an exception of some kind or another, apart from the
+             * special case of an NS CPU executing an SG instruction
+             * in S&NSC memory. So we always just fail the translation
+             * here and sort things out in the exception handler
+             * (including possibly emulating an SG instruction).
+             */
+            if (sattrs.ns != !secure) {
+                if (sattrs.nsc) {
+                    fi->type = ARMFault_QEMU_NSCExec;
+                } else {
+                    fi->type = ARMFault_QEMU_SFault;
+                }
+                *phys_ptr = address;
+                *prot = 0;
+                return true;
+            }
+        } else {
+            /* For data accesses we always use the MMU bank indicated
+             * by the current CPU state, but the security attributes
+             * might downgrade a secure access to nonsecure.
+             */
+            if (sattrs.ns) {
+                txattrs->secure = false;
+            } else if (!secure) {
+                /* NS access to S memory must fault.
+                 * Architecturally we should first check whether the
+                 * MPU information for this address indicates that we
+                 * are doing an unaligned access to Device memory, which
+                 * should generate a UsageFault instead. QEMU does not
+                 * currently check for that kind of unaligned access though.
+                 * If we added it we would need to do so as a special case
+                 * for M_FAKE_FSR_SFAULT in arm_v7m_cpu_do_interrupt().
+                 */
+                fi->type = ARMFault_QEMU_SFault;
+                *phys_ptr = address;
+                *prot = 0;
+                return true;
+            }
+        }
+    }
+
+    return pmsav8_mpu_lookup(env, address, access_type, mmu_idx, phys_ptr,
+                             txattrs, prot, fi, NULL);
+}
+
 static bool get_phys_addr_pmsav5(CPUARMState *env, uint32_t address,
                                  MMUAccessType access_type, ARMMMUIdx mmu_idx,
-                                 hwaddr *phys_ptr, int *prot, uint32_t *fsr)
+                                 hwaddr *phys_ptr, int *prot,
+                                 ARMMMUFaultInfo *fi)
 {
     int n;
     uint32_t mask;
@@ -9530,7 +9609,7 @@ static bool get_phys_addr_pmsav5(CPUARMState *env, uint32_t address,
         }
     }
     if (n < 0) {
-        *fsr = 2;
+        fi->type = ARMFault_Background;
         return true;
     }
 
@@ -9542,11 +9621,13 @@ static bool get_phys_addr_pmsav5(CPUARMState *env, uint32_t address,
     mask = (mask >> (n * 4)) & 0xf;
     switch (mask) {
     case 0:
-        *fsr = 1;
+        fi->type = ARMFault_Permission;
+        fi->level = 1;
         return true;
     case 1:
         if (is_user) {
-            *fsr = 1;
+            fi->type = ARMFault_Permission;
+            fi->level = 1;
             return true;
         }
         *prot = PAGE_READ | PAGE_WRITE;
@@ -9562,7 +9643,8 @@ static bool get_phys_addr_pmsav5(CPUARMState *env, uint32_t address,
         break;
     case 5:
         if (is_user) {
-            *fsr = 1;
+            fi->type = ARMFault_Permission;
+            fi->level = 1;
             return true;
         }
         *prot = PAGE_READ;
@@ -9572,7 +9654,8 @@ static bool get_phys_addr_pmsav5(CPUARMState *env, uint32_t address,
         break;
     default:
         /* Bad permission.  */
-        *fsr = 1;
+        fi->type = ARMFault_Permission;
+        fi->level = 1;
         return true;
     }
     *prot |= PAGE_EXEC;
@@ -9689,14 +9772,13 @@ static ARMCacheAttrs combine_cacheattrs(ARMCacheAttrs s1, ARMCacheAttrs s2)
  * @attrs: set to the memory transaction attributes to use
  * @prot: set to the permissions for the page containing phys_ptr
  * @page_size: set to the size of the page containing phys_ptr
- * @fsr: set to the DFSR/IFSR value on failure
  * @fi: set to fault info if the translation fails
  * @cacheattrs: (if non-NULL) set to the cacheability/shareability attributes
  */
 static bool get_phys_addr(CPUARMState *env, target_ulong address,
                           MMUAccessType access_type, ARMMMUIdx mmu_idx,
                           hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot,
-                          target_ulong *page_size, uint32_t *fsr,
+                          target_ulong *page_size,
                           ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs)
 {
     if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) {
@@ -9711,7 +9793,7 @@ static bool get_phys_addr(CPUARMState *env, target_ulong address,
 
             ret = get_phys_addr(env, address, access_type,
                                 stage_1_mmu_idx(mmu_idx), &ipa, attrs,
-                                prot, page_size, fsr, fi, cacheattrs);
+                                prot, page_size, fi, cacheattrs);
 
             /* If S1 fails or S2 is disabled, return early.  */
             if (ret || regime_translation_disabled(env, ARMMMUIdx_S2NS)) {
@@ -9722,7 +9804,7 @@ static bool get_phys_addr(CPUARMState *env, target_ulong address,
             /* S1 is done. Now do S2 translation.  */
             ret = get_phys_addr_lpae(env, ipa, access_type, ARMMMUIdx_S2NS,
                                      phys_ptr, attrs, &s2_prot,
-                                     page_size, fsr, fi,
+                                     page_size, fi,
                                      cacheattrs != NULL ? &cacheattrs2 : NULL);
             fi->s2addr = ipa;
             /* Combine the S1 and S2 perms.  */
@@ -9768,15 +9850,15 @@ static bool get_phys_addr(CPUARMState *env, target_ulong address,
         if (arm_feature(env, ARM_FEATURE_V8)) {
             /* PMSAv8 */
             ret = get_phys_addr_pmsav8(env, address, access_type, mmu_idx,
-                                       phys_ptr, attrs, prot, fsr);
+                                       phys_ptr, attrs, prot, fi);
         } else if (arm_feature(env, ARM_FEATURE_V7)) {
             /* PMSAv7 */
             ret = get_phys_addr_pmsav7(env, address, access_type, mmu_idx,
-                                       phys_ptr, prot, fsr);
+                                       phys_ptr, prot, fi);
         } else {
             /* Pre-v7 MPU */
             ret = get_phys_addr_pmsav5(env, address, access_type, mmu_idx,
-                                       phys_ptr, prot, fsr);
+                                       phys_ptr, prot, fi);
         }
         qemu_log_mask(CPU_LOG_MMU, "PMSA MPU lookup for %s at 0x%08" PRIx32
                       " mmu_idx %u -> %s (prot %c%c%c)\n",
@@ -9802,14 +9884,15 @@ static bool get_phys_addr(CPUARMState *env, target_ulong address,
     }
 
     if (regime_using_lpae_format(env, mmu_idx)) {
-        return get_phys_addr_lpae(env, address, access_type, mmu_idx, phys_ptr,
-                                  attrs, prot, page_size, fsr, fi, cacheattrs);
+        return get_phys_addr_lpae(env, address, access_type, mmu_idx,
+                                  phys_ptr, attrs, prot, page_size,
+                                  fi, cacheattrs);
     } else if (regime_sctlr(env, mmu_idx) & SCTLR_XP) {
-        return get_phys_addr_v6(env, address, access_type, mmu_idx, phys_ptr,
-                                attrs, prot, page_size, fsr, fi);
+        return get_phys_addr_v6(env, address, access_type, mmu_idx,
+                                phys_ptr, attrs, prot, page_size, fi);
     } else {
-        return get_phys_addr_v5(env, address, access_type, mmu_idx, phys_ptr,
-                                prot, page_size, fsr, fi);
+        return get_phys_addr_v5(env, address, access_type, mmu_idx,
+                                    phys_ptr, prot, page_size, fi);
     }
 }
 
@@ -9818,7 +9901,7 @@ static bool get_phys_addr(CPUARMState *env, target_ulong address,
  * fsr with ARM DFSR/IFSR fault register format value on failure.
  */
 bool arm_tlb_fill(CPUState *cs, vaddr address,
-                  MMUAccessType access_type, int mmu_idx, uint32_t *fsr,
+                  MMUAccessType access_type, int mmu_idx,
                   ARMMMUFaultInfo *fi)
 {
     ARMCPU *cpu = ARM_CPU(cs);
@@ -9831,7 +9914,7 @@ bool arm_tlb_fill(CPUState *cs, vaddr address,
 
     ret = get_phys_addr(env, address, access_type,
                         core_to_arm_mmu_idx(env, mmu_idx), &phys_addr,
-                        &attrs, &prot, &page_size, fsr, fi, NULL);
+                        &attrs, &prot, &page_size, fi, NULL);
     if (!ret) {
         /* Map a single [sub]page.  */
         phys_addr &= TARGET_PAGE_MASK;
@@ -9853,14 +9936,13 @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr,
     target_ulong page_size;
     int prot;
     bool ret;
-    uint32_t fsr;
     ARMMMUFaultInfo fi = {};
     ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false));
 
     *attrs = (MemTxAttrs) {};
 
     ret = get_phys_addr(env, addr, 0, mmu_idx, &phys_addr,
-                        attrs, &prot, &page_size, &fsr, &fi, NULL);
+                        attrs, &prot, &page_size, &fi, NULL);
 
     if (ret) {
         return -1;
@@ -9953,11 +10035,9 @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg)
 
     switch (reg) {
     case 8: /* MSP */
-        return (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK) ?
-            env->v7m.other_sp : env->regs[13];
+        return v7m_using_psp(env) ? env->v7m.other_sp : env->regs[13];
     case 9: /* PSP */
-        return (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK) ?
-            env->regs[13] : env->v7m.other_sp;
+        return v7m_using_psp(env) ? env->regs[13] : env->v7m.other_sp;
     case 16: /* PRIMASK */
         return env->v7m.primask[env->v7m.secure];
     case 17: /* BASEPRI */
@@ -10059,14 +10139,14 @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val)
         }
         break;
     case 8: /* MSP */
-        if (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK) {
+        if (v7m_using_psp(env)) {
             env->v7m.other_sp = val;
         } else {
             env->regs[13] = val;
         }
         break;
     case 9: /* PSP */
-        if (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_SPSEL_MASK) {
+        if (v7m_using_psp(env)) {
             env->regs[13] = val;
         } else {
             env->v7m.other_sp = val;
@@ -10093,8 +10173,11 @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val)
          * thread mode; other bits can be updated by any privileged code.
          * write_v7m_control_spsel() deals with updating the SPSEL bit in
          * env->v7m.control, so we only need update the others.
+         * For v7M, we must just ignore explicit writes to SPSEL in handler
+         * mode; for v8M the write is permitted but will have no effect.
          */
-        if (!arm_v7m_is_handler_mode(env)) {
+        if (arm_feature(env, ARM_FEATURE_V8) ||
+            !arm_v7m_is_handler_mode(env)) {
             write_v7m_control_spsel(env, (val & R_V7M_CONTROL_SPSEL_MASK) != 0);
         }
         env->v7m.control[env->v7m.secure] &= ~R_V7M_CONTROL_NPRIV_MASK;
@@ -10107,6 +10190,92 @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val)
     }
 }
 
+uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op)
+{
+    /* Implement the TT instruction. op is bits [7:6] of the insn. */
+    bool forceunpriv = op & 1;
+    bool alt = op & 2;
+    V8M_SAttributes sattrs = {};
+    uint32_t tt_resp;
+    bool r, rw, nsr, nsrw, mrvalid;
+    int prot;
+    ARMMMUFaultInfo fi = {};
+    MemTxAttrs attrs = {};
+    hwaddr phys_addr;
+    ARMMMUIdx mmu_idx;
+    uint32_t mregion;
+    bool targetpriv;
+    bool targetsec = env->v7m.secure;
+
+    /* Work out what the security state and privilege level we're
+     * interested in is...
+     */
+    if (alt) {
+        targetsec = !targetsec;
+    }
+
+    if (forceunpriv) {
+        targetpriv = false;
+    } else {
+        targetpriv = arm_v7m_is_handler_mode(env) ||
+            !(env->v7m.control[targetsec] & R_V7M_CONTROL_NPRIV_MASK);
+    }
+
+    /* ...and then figure out which MMU index this is */
+    mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, targetsec, targetpriv);
+
+    /* We know that the MPU and SAU don't care about the access type
+     * for our purposes beyond that we don't want to claim to be
+     * an insn fetch, so we arbitrarily call this a read.
+     */
+
+    /* MPU region info only available for privileged or if
+     * inspecting the other MPU state.
+     */
+    if (arm_current_el(env) != 0 || alt) {
+        /* We can ignore the return value as prot is always set */
+        pmsav8_mpu_lookup(env, addr, MMU_DATA_LOAD, mmu_idx,
+                          &phys_addr, &attrs, &prot, &fi, &mregion);
+        if (mregion == -1) {
+            mrvalid = false;
+            mregion = 0;
+        } else {
+            mrvalid = true;
+        }
+        r = prot & PAGE_READ;
+        rw = prot & PAGE_WRITE;
+    } else {
+        r = false;
+        rw = false;
+        mrvalid = false;
+        mregion = 0;
+    }
+
+    if (env->v7m.secure) {
+        v8m_security_lookup(env, addr, MMU_DATA_LOAD, mmu_idx, &sattrs);
+        nsr = sattrs.ns && r;
+        nsrw = sattrs.ns && rw;
+    } else {
+        sattrs.ns = true;
+        nsr = false;
+        nsrw = false;
+    }
+
+    tt_resp = (sattrs.iregion << 24) |
+        (sattrs.irvalid << 23) |
+        ((!sattrs.ns) << 22) |
+        (nsrw << 21) |
+        (nsr << 20) |
+        (rw << 19) |
+        (r << 18) |
+        (sattrs.srvalid << 17) |
+        (mrvalid << 16) |
+        (sattrs.sregion << 8) |
+        mregion;
+
+    return tt_resp;
+}
+
 #endif
 
 void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 439d228..066729e 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -66,6 +66,8 @@ DEF_HELPER_2(v7m_mrs, i32, env, i32)
 DEF_HELPER_2(v7m_bxns, void, env, i32)
 DEF_HELPER_2(v7m_blxns, void, env, i32)
 
+DEF_HELPER_3(v7m_tt, i32, env, i32, i32)
+
 DEF_HELPER_4(access_check_cp_reg, void, env, ptr, i32, i32)
 DEF_HELPER_3(set_cp_reg, void, env, ptr, i32)
 DEF_HELPER_2(get_cp_reg, i32, env, ptr)
diff --git a/target/arm/internals.h b/target/arm/internals.h
index d9cc75e..876854d 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -488,7 +488,39 @@ static inline void arm_clear_exclusive(CPUARMState *env)
 }
 
 /**
+ * ARMFaultType: type of an ARM MMU fault
+ * This corresponds to the v8A pseudocode's Fault enumeration,
+ * with extensions for QEMU internal conditions.
+ */
+typedef enum ARMFaultType {
+    ARMFault_None,
+    ARMFault_AccessFlag,
+    ARMFault_Alignment,
+    ARMFault_Background,
+    ARMFault_Domain,
+    ARMFault_Permission,
+    ARMFault_Translation,
+    ARMFault_AddressSize,
+    ARMFault_SyncExternal,
+    ARMFault_SyncExternalOnWalk,
+    ARMFault_SyncParity,
+    ARMFault_SyncParityOnWalk,
+    ARMFault_AsyncParity,
+    ARMFault_AsyncExternal,
+    ARMFault_Debug,
+    ARMFault_TLBConflict,
+    ARMFault_Lockdown,
+    ARMFault_Exclusive,
+    ARMFault_ICacheMaint,
+    ARMFault_QEMU_NSCExec, /* v8M: NS executing in S&NSC memory */
+    ARMFault_QEMU_SFault, /* v8M: SecureFault INVTRAN, INVEP or AUVIOL */
+} ARMFaultType;
+
+/**
  * ARMMMUFaultInfo: Information describing an ARM MMU Fault
+ * @type: Type of fault
+ * @level: Table walk level (for translation, access flag and permission faults)
+ * @domain: Domain of the fault address (for non-LPAE CPUs only)
  * @s2addr: Address that caused a fault at stage 2
  * @stage2: True if we faulted at stage 2
  * @s1ptw: True if we faulted at stage 2 while doing a stage 1 page-table walk
@@ -496,16 +528,169 @@ static inline void arm_clear_exclusive(CPUARMState *env)
  */
 typedef struct ARMMMUFaultInfo ARMMMUFaultInfo;
 struct ARMMMUFaultInfo {
+    ARMFaultType type;
     target_ulong s2addr;
+    int level;
+    int domain;
     bool stage2;
     bool s1ptw;
     bool ea;
 };
 
+/**
+ * arm_fi_to_sfsc: Convert fault info struct to short-format FSC
+ * Compare pseudocode EncodeSDFSC(), though unlike that function
+ * we set up a whole FSR-format code including domain field and
+ * putting the high bit of the FSC into bit 10.
+ */
+static inline uint32_t arm_fi_to_sfsc(ARMMMUFaultInfo *fi)
+{
+    uint32_t fsc;
+
+    switch (fi->type) {
+    case ARMFault_None:
+        return 0;
+    case ARMFault_AccessFlag:
+        fsc = fi->level == 1 ? 0x3 : 0x6;
+        break;
+    case ARMFault_Alignment:
+        fsc = 0x1;
+        break;
+    case ARMFault_Permission:
+        fsc = fi->level == 1 ? 0xd : 0xf;
+        break;
+    case ARMFault_Domain:
+        fsc = fi->level == 1 ? 0x9 : 0xb;
+        break;
+    case ARMFault_Translation:
+        fsc = fi->level == 1 ? 0x5 : 0x7;
+        break;
+    case ARMFault_SyncExternal:
+        fsc = 0x8 | (fi->ea << 12);
+        break;
+    case ARMFault_SyncExternalOnWalk:
+        fsc = fi->level == 1 ? 0xc : 0xe;
+        fsc |= (fi->ea << 12);
+        break;
+    case ARMFault_SyncParity:
+        fsc = 0x409;
+        break;
+    case ARMFault_SyncParityOnWalk:
+        fsc = fi->level == 1 ? 0x40c : 0x40e;
+        break;
+    case ARMFault_AsyncParity:
+        fsc = 0x408;
+        break;
+    case ARMFault_AsyncExternal:
+        fsc = 0x406 | (fi->ea << 12);
+        break;
+    case ARMFault_Debug:
+        fsc = 0x2;
+        break;
+    case ARMFault_TLBConflict:
+        fsc = 0x400;
+        break;
+    case ARMFault_Lockdown:
+        fsc = 0x404;
+        break;
+    case ARMFault_Exclusive:
+        fsc = 0x405;
+        break;
+    case ARMFault_ICacheMaint:
+        fsc = 0x4;
+        break;
+    case ARMFault_Background:
+        fsc = 0x0;
+        break;
+    case ARMFault_QEMU_NSCExec:
+        fsc = M_FAKE_FSR_NSC_EXEC;
+        break;
+    case ARMFault_QEMU_SFault:
+        fsc = M_FAKE_FSR_SFAULT;
+        break;
+    default:
+        /* Other faults can't occur in a context that requires a
+         * short-format status code.
+         */
+        g_assert_not_reached();
+    }
+
+    fsc |= (fi->domain << 4);
+    return fsc;
+}
+
+/**
+ * arm_fi_to_lfsc: Convert fault info struct to long-format FSC
+ * Compare pseudocode EncodeLDFSC(), though unlike that function
+ * we fill in also the LPAE bit 9 of a DFSR format.
+ */
+static inline uint32_t arm_fi_to_lfsc(ARMMMUFaultInfo *fi)
+{
+    uint32_t fsc;
+
+    switch (fi->type) {
+    case ARMFault_None:
+        return 0;
+    case ARMFault_AddressSize:
+        fsc = fi->level & 3;
+        break;
+    case ARMFault_AccessFlag:
+        fsc = (fi->level & 3) | (0x2 << 2);
+        break;
+    case ARMFault_Permission:
+        fsc = (fi->level & 3) | (0x3 << 2);
+        break;
+    case ARMFault_Translation:
+        fsc = (fi->level & 3) | (0x1 << 2);
+        break;
+    case ARMFault_SyncExternal:
+        fsc = 0x10 | (fi->ea << 12);
+        break;
+    case ARMFault_SyncExternalOnWalk:
+        fsc = (fi->level & 3) | (0x5 << 2) | (fi->ea << 12);
+        break;
+    case ARMFault_SyncParity:
+        fsc = 0x18;
+        break;
+    case ARMFault_SyncParityOnWalk:
+        fsc = (fi->level & 3) | (0x7 << 2);
+        break;
+    case ARMFault_AsyncParity:
+        fsc = 0x19;
+        break;
+    case ARMFault_AsyncExternal:
+        fsc = 0x11 | (fi->ea << 12);
+        break;
+    case ARMFault_Alignment:
+        fsc = 0x21;
+        break;
+    case ARMFault_Debug:
+        fsc = 0x22;
+        break;
+    case ARMFault_TLBConflict:
+        fsc = 0x30;
+        break;
+    case ARMFault_Lockdown:
+        fsc = 0x34;
+        break;
+    case ARMFault_Exclusive:
+        fsc = 0x35;
+        break;
+    default:
+        /* Other faults can't occur in a context that requires a
+         * long-format status code.
+         */
+        g_assert_not_reached();
+    }
+
+    fsc |= 1 << 9;
+    return fsc;
+}
+
 /* Do a page table walk and add page to TLB if possible */
 bool arm_tlb_fill(CPUState *cpu, vaddr address,
                   MMUAccessType access_type, int mmu_idx,
-                  uint32_t *fsr, ARMMMUFaultInfo *fi);
+                  ARMMMUFaultInfo *fi);
 
 /* Return true if the stage 1 translation regime is using LPAE format page
  * tables */
@@ -544,15 +729,17 @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx)
     case ARMMMUIdx_S1NSE1:
     case ARMMMUIdx_S1E2:
     case ARMMMUIdx_S2NS:
+    case ARMMMUIdx_MPrivNegPri:
+    case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
-    case ARMMMUIdx_MNegPri:
     case ARMMMUIdx_MUser:
         return false;
     case ARMMMUIdx_S1E3:
     case ARMMMUIdx_S1SE0:
     case ARMMMUIdx_S1SE1:
+    case ARMMMUIdx_MSPrivNegPri:
+    case ARMMMUIdx_MSUserNegPri:
     case ARMMMUIdx_MSPriv:
-    case ARMMMUIdx_MSNegPri:
     case ARMMMUIdx_MSUser:
         return true;
     default:
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index a40a84a..c2bb4f3 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -116,12 +116,13 @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn,
 }
 
 static void deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type,
-                          uint32_t fsr, uint32_t fsc, ARMMMUFaultInfo *fi)
+                          int mmu_idx, ARMMMUFaultInfo *fi)
 {
     CPUARMState *env = &cpu->env;
     int target_el;
     bool same_el;
-    uint32_t syn, exc;
+    uint32_t syn, exc, fsr, fsc;
+    ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx);
 
     target_el = exception_target_el(env);
     if (fi->stage2) {
@@ -130,14 +131,21 @@ static void deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type,
     }
     same_el = (arm_current_el(env) == target_el);
 
-    if (fsc == 0x3f) {
-        /* Caller doesn't have a long-format fault status code. This
-         * should only happen if this fault will never actually be reported
-         * to an EL that uses a syndrome register. Check that here.
-         * 0x3f is a (currently) reserved FSC code, in case the constructed
-         * syndrome does leak into the guest somehow.
+    if (target_el == 2 || arm_el_is_aa64(env, target_el) ||
+        arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) {
+        /* LPAE format fault status register : bottom 6 bits are
+         * status code in the same form as needed for syndrome
+         */
+        fsr = arm_fi_to_lfsc(fi);
+        fsc = extract32(fsr, 0, 6);
+    } else {
+        fsr = arm_fi_to_sfsc(fi);
+        /* Short format FSR : this fault will never actually be reported
+         * to an EL that uses a syndrome register. Use a (currently)
+         * reserved FSR code in case the constructed syndrome does leak
+         * into the guest somehow.
          */
-        assert(target_el != 2 && !arm_el_is_aa64(env, target_el));
+        fsc = 0x3f;
     }
 
     if (access_type == MMU_INST_FETCH) {
@@ -168,35 +176,18 @@ void tlb_fill(CPUState *cs, target_ulong addr, MMUAccessType access_type,
               int mmu_idx, uintptr_t retaddr)
 {
     bool ret;
-    uint32_t fsr = 0;
     ARMMMUFaultInfo fi = {};
 
-    ret = arm_tlb_fill(cs, addr, access_type, mmu_idx, &fsr, &fi);
+    ret = arm_tlb_fill(cs, addr, access_type, mmu_idx, &fi);
     if (unlikely(ret)) {
         ARMCPU *cpu = ARM_CPU(cs);
-        uint32_t fsc;
 
         if (retaddr) {
             /* now we have a real cpu fault */
             cpu_restore_state(cs, retaddr);
         }
 
-        if (fsr & (1 << 9)) {
-            /* LPAE format fault status register : bottom 6 bits are
-             * status code in the same form as needed for syndrome
-             */
-            fsc = extract32(fsr, 0, 6);
-        } else {
-            /* Short format FSR : this fault will never actually be reported
-             * to an EL that uses a syndrome register. Use a (currently)
-             * reserved FSR code in case the constructed syndrome does leak
-             * into the guest somehow. deliver_fault will assert that
-             * we don't target an EL using the syndrome.
-             */
-            fsc = 0x3f;
-        }
-
-        deliver_fault(cpu, addr, access_type, fsr, fsc, &fi);
+        deliver_fault(cpu, addr, access_type, mmu_idx, &fi);
     }
 }
 
@@ -206,27 +197,15 @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr,
                                  int mmu_idx, uintptr_t retaddr)
 {
     ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
-    uint32_t fsr, fsc;
     ARMMMUFaultInfo fi = {};
-    ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx);
 
     if (retaddr) {
         /* now we have a real cpu fault */
         cpu_restore_state(cs, retaddr);
     }
 
-    /* the DFSR for an alignment fault depends on whether we're using
-     * the LPAE long descriptor format, or the short descriptor format
-     */
-    if (arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) {
-        fsr = (1 << 9) | 0x21;
-    } else {
-        fsr = 0x1;
-    }
-    fsc = 0x21;
-
-    deliver_fault(cpu, vaddr, access_type, fsr, fsc, &fi);
+    fi.type = ARMFault_Alignment;
+    deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi);
 }
 
 /* arm_cpu_do_transaction_failed: handle a memory system error response
@@ -240,10 +219,7 @@ void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
                                    MemTxResult response, uintptr_t retaddr)
 {
     ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
-    uint32_t fsr, fsc;
     ARMMMUFaultInfo fi = {};
-    ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx);
 
     if (retaddr) {
         /* now we have a real cpu fault */
@@ -256,20 +232,8 @@ void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
      * Slave error (1); in QEMU we follow that.
      */
     fi.ea = (response != MEMTX_DECODE_ERROR);
-
-    /* The fault status register format depends on whether we're using
-     * the LPAE long descriptor format, or the short descriptor format.
-     */
-    if (arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) {
-        /* long descriptor form, STATUS 0b010000: synchronous ext abort */
-        fsr = (fi.ea << 12) | (1 << 9) | 0x10;
-    } else {
-        /* short descriptor form, FSR 0b01000 : synchronous ext abort */
-        fsr = (fi.ea << 12) | 0x8;
-    }
-    fsc = 0x10;
-
-    deliver_fault(cpu, addr, access_type, fsr, fsc, &fi);
+    fi.type = ARMFault_SyncExternal;
+    deliver_fault(cpu, addr, access_type, mmu_idx, &fi);
 }
 
 #endif /* !defined(CONFIG_USER_ONLY) */
diff --git a/target/arm/translate.c b/target/arm/translate.c
index f120932..e15192d 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -159,12 +159,16 @@ static inline int get_a32_user_mem_index(DisasContext *s)
         return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0);
     case ARMMMUIdx_MUser:
     case ARMMMUIdx_MPriv:
-    case ARMMMUIdx_MNegPri:
         return arm_to_core_mmu_idx(ARMMMUIdx_MUser);
+    case ARMMMUIdx_MUserNegPri:
+    case ARMMMUIdx_MPrivNegPri:
+        return arm_to_core_mmu_idx(ARMMMUIdx_MUserNegPri);
     case ARMMMUIdx_MSUser:
     case ARMMMUIdx_MSPriv:
-    case ARMMMUIdx_MSNegPri:
         return arm_to_core_mmu_idx(ARMMMUIdx_MSUser);
+    case ARMMMUIdx_MSUserNegPri:
+    case ARMMMUIdx_MSPrivNegPri:
+        return arm_to_core_mmu_idx(ARMMMUIdx_MSUserNegPri);
     case ARMMMUIdx_S2NS:
     default:
         g_assert_not_reached();
@@ -9806,7 +9810,7 @@ static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
         if (insn & (1 << 22)) {
             /* 0b1110_100x_x1xx_xxxx_xxxx_xxxx_xxxx_xxxx
              * - load/store doubleword, load/store exclusive, ldacq/strel,
-             *   table branch.
+             *   table branch, TT.
              */
             if (insn == 0xe97fe97f && arm_dc_feature(s, ARM_FEATURE_M) &&
                 arm_dc_feature(s, ARM_FEATURE_V8)) {
@@ -9883,8 +9887,35 @@ static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
             } else if ((insn & (1 << 23)) == 0) {
                 /* 0b1110_1000_010x_xxxx_xxxx_xxxx_xxxx_xxxx
                  * - load/store exclusive word
+                 * - TT (v8M only)
                  */
                 if (rs == 15) {
+                    if (!(insn & (1 << 20)) &&
+                        arm_dc_feature(s, ARM_FEATURE_M) &&
+                        arm_dc_feature(s, ARM_FEATURE_V8)) {
+                        /* 0b1110_1000_0100_xxxx_1111_xxxx_xxxx_xxxx
+                         *  - TT (v8M only)
+                         */
+                        bool alt = insn & (1 << 7);
+                        TCGv_i32 addr, op, ttresp;
+
+                        if ((insn & 0x3f) || rd == 13 || rd == 15 || rn == 15) {
+                            /* we UNDEF for these UNPREDICTABLE cases */
+                            goto illegal_op;
+                        }
+
+                        if (alt && !s->v8m_secure) {
+                            goto illegal_op;
+                        }
+
+                        addr = load_reg(s, rn);
+                        op = tcg_const_i32(extract32(insn, 6, 2));
+                        ttresp = tcg_temp_new_i32();
+                        gen_helper_v7m_tt(ttresp, cpu_env, addr, op);
+                        tcg_temp_free_i32(addr);
+                        tcg_temp_free_i32(op);
+                        store_reg(s, rd, ttresp);
+                    }
                     goto illegal_op;
                 }
                 addr = tcg_temp_local_new_i32();