diff --git a/configure b/configure
index 6a040821c6..89bd662a6a 100755
--- a/configure
+++ b/configure
@@ -6439,7 +6439,7 @@ target_name=$(echo $target | cut -d '-' -f 1)
 target_bigendian="no"
 
 case "$target_name" in
-  armeb|hppa|lm32|m68k|microblaze|mips|mipsn32|mips64|moxie|or1k|ppc|ppcemb|ppc64|ppc64abi32|s390x|sh4eb|sparc|sparc64|sparc32plus|xtensaeb)
+  armeb|aarch64_be|hppa|lm32|m68k|microblaze|mips|mipsn32|mips64|moxie|or1k|ppc|ppcemb|ppc64|ppc64abi32|s390x|sh4eb|sparc|sparc64|sparc32plus|xtensaeb)
   target_bigendian=yes
   ;;
 esac
@@ -6494,7 +6494,8 @@ case "$target_name" in
     mttcg="yes"
     gdb_xml_files="arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml"
   ;;
-  aarch64)
+  aarch64|aarch64_be)
+    TARGET_ARCH=aarch64
     TARGET_BASE_ARCH=arm
     bflt="yes"
     mttcg="yes"
diff --git a/default-configs/aarch64_be-linux-user.mak b/default-configs/aarch64_be-linux-user.mak
new file mode 100644
index 0000000000..a69d9d2e41
--- /dev/null
+++ b/default-configs/aarch64_be-linux-user.mak
@@ -0,0 +1 @@
+# Default configuration for aarch64_be-linux-user
diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c
index 59ef33efa9..b0d4088290 100644
--- a/hw/arm/fsl-imx6.c
+++ b/hw/arm/fsl-imx6.c
@@ -385,6 +385,7 @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp)
                                             spi_table[i].irq));
     }
 
+    qdev_set_nic_properties(DEVICE(&s->eth), &nd_table[0]);
     object_property_set_bool(OBJECT(&s->eth), true, "realized", &err);
     if (err) {
         error_propagate(errp, err);
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index 3d78ff68e6..f7fa795278 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -453,6 +453,7 @@ build_spcr(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     AcpiSerialPortConsoleRedirection *spcr;
     const MemMapEntry *uart_memmap = &vms->memmap[VIRT_UART];
     int irq = vms->irqmap[VIRT_UART] + ARM_SPI_BASE;
+    int spcr_start = table_data->len;
 
     spcr = acpi_data_push(table_data, sizeof(*spcr));
 
@@ -476,8 +477,8 @@ build_spcr(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     spcr->pci_device_id = 0xffff;  /* PCI Device ID: not a PCI device */
     spcr->pci_vendor_id = 0xffff;  /* PCI Vendor ID: not a PCI device */
 
-    build_header(linker, table_data, (void *)spcr, "SPCR", sizeof(*spcr), 2,
-                 NULL, NULL);
+    build_header(linker, table_data, (void *)(table_data->data + spcr_start),
+                 "SPCR", table_data->len - spcr_start, 2, NULL, NULL);
 }
 
 static void
@@ -512,8 +513,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
         mem_base += numa_info[i].node_mem;
     }
 
-    build_header(linker, table_data, (void *)srat, "SRAT",
-                 table_data->len - srat_start, 3, NULL, NULL);
+    build_header(linker, table_data, (void *)(table_data->data + srat_start),
+                 "SRAT", table_data->len - srat_start, 3, NULL, NULL);
 }
 
 static void
@@ -522,6 +523,7 @@ build_mcfg(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     AcpiTableMcfg *mcfg;
     const MemMapEntry *memmap = vms->memmap;
     int len = sizeof(*mcfg) + sizeof(mcfg->allocation[0]);
+    int mcfg_start = table_data->len;
 
     mcfg = acpi_data_push(table_data, len);
     mcfg->allocation[0].address = cpu_to_le64(memmap[VIRT_PCIE_ECAM].base);
@@ -532,7 +534,8 @@ build_mcfg(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
     mcfg->allocation[0].end_bus_number = (memmap[VIRT_PCIE_ECAM].size
                                           / PCIE_MMCFG_SIZE_MIN) - 1;
 
-    build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1, NULL, NULL);
+    build_header(linker, table_data, (void *)(table_data->data + mcfg_start),
+                 "MCFG", table_data->len - mcfg_start, 1, NULL, NULL);
 }
 
 /* GTDT */
@@ -651,6 +654,7 @@ build_madt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
 static void build_fadt(GArray *table_data, BIOSLinker *linker,
                        VirtMachineState *vms, unsigned dsdt_tbl_offset)
 {
+    int fadt_start = table_data->len;
     AcpiFadtDescriptorRev5_1 *fadt = acpi_data_push(table_data, sizeof(*fadt));
     unsigned xdsdt_entry_offset = (char *)&fadt->x_dsdt - table_data->data;
     uint16_t bootflags;
@@ -681,8 +685,8 @@ static void build_fadt(GArray *table_data, BIOSLinker *linker,
         ACPI_BUILD_TABLE_FILE, xdsdt_entry_offset, sizeof(fadt->x_dsdt),
         ACPI_BUILD_TABLE_FILE, dsdt_tbl_offset);
 
-    build_header(linker, table_data,
-                 (void *)fadt, "FACP", sizeof(*fadt), 5, NULL, NULL);
+    build_header(linker, table_data, (void *)(table_data->data + fadt_start),
+                 "FACP", table_data->len - fadt_start, 5, NULL, NULL);
 }
 
 /* DSDT */
diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c
index 5a0e2a3c1a..d701e49ff9 100644
--- a/hw/intc/arm_gic.c
+++ b/hw/intc/arm_gic.c
@@ -1261,7 +1261,8 @@ static MemTxResult gic_cpu_read(GICState *s, int cpu, int offset,
     default:
         qemu_log_mask(LOG_GUEST_ERROR,
                       "gic_cpu_read: Bad offset %x\n", (int)offset);
-        return MEMTX_ERROR;
+        *data = 0;
+        break;
     }
     return MEMTX_OK;
 }
@@ -1329,7 +1330,7 @@ static MemTxResult gic_cpu_write(GICState *s, int cpu, int offset,
     default:
         qemu_log_mask(LOG_GUEST_ERROR,
                       "gic_cpu_write: Bad offset %x\n", (int)offset);
-        return MEMTX_ERROR;
+        return MEMTX_OK;
     }
     gic_update(s);
     return MEMTX_OK;
diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c
index 3ea3dd0d40..93fe936862 100644
--- a/hw/intc/arm_gicv3_dist.c
+++ b/hw/intc/arm_gicv3_dist.c
@@ -817,6 +817,13 @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data,
                       "%s: invalid guest read at offset " TARGET_FMT_plx
                       "size %u\n", __func__, offset, size);
         trace_gicv3_dist_badread(offset, size, attrs.secure);
+        /* The spec requires that reserved registers are RAZ/WI;
+         * so use MEMTX_ERROR returns from leaf functions as a way to
+         * trigger the guest-error logging but don't return it to
+         * the caller, or we'll cause a spurious guest data abort.
+         */
+        r = MEMTX_OK;
+        *data = 0;
     } else {
         trace_gicv3_dist_read(offset, *data, size, attrs.secure);
     }
@@ -852,6 +859,12 @@ MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data,
                       "%s: invalid guest write at offset " TARGET_FMT_plx
                       "size %u\n", __func__, offset, size);
         trace_gicv3_dist_badwrite(offset, data, size, attrs.secure);
+        /* The spec requires that reserved registers are RAZ/WI;
+         * so use MEMTX_ERROR returns from leaf functions as a way to
+         * trigger the guest-error logging but don't return it to
+         * the caller, or we'll cause a spurious guest data abort.
+         */
+        r = MEMTX_OK;
     } else {
         trace_gicv3_dist_write(offset, data, size, attrs.secure);
     }
diff --git a/hw/intc/arm_gicv3_its_common.c b/hw/intc/arm_gicv3_its_common.c
index 2bd2f0f3c9..284c0a7584 100644
--- a/hw/intc/arm_gicv3_its_common.c
+++ b/hw/intc/arm_gicv3_its_common.c
@@ -67,7 +67,8 @@ static MemTxResult gicv3_its_trans_read(void *opaque, hwaddr offset,
                                         MemTxAttrs attrs)
 {
     qemu_log_mask(LOG_GUEST_ERROR, "ITS read at offset 0x%"PRIx64"\n", offset);
-    return MEMTX_ERROR;
+    *data = 0;
+    return MEMTX_OK;
 }
 
 static MemTxResult gicv3_its_trans_write(void *opaque, hwaddr offset,
@@ -82,15 +83,12 @@ static MemTxResult gicv3_its_trans_write(void *opaque, hwaddr offset,
         if (ret <= 0) {
             qemu_log_mask(LOG_GUEST_ERROR,
                           "ITS: Error sending MSI: %s\n", strerror(-ret));
-            return MEMTX_DECODE_ERROR;
         }
-
-        return MEMTX_OK;
     } else {
         qemu_log_mask(LOG_GUEST_ERROR,
                       "ITS write at bad offset 0x%"PRIx64"\n", offset);
-        return MEMTX_DECODE_ERROR;
     }
+    return MEMTX_OK;
 }
 
 static const MemoryRegionOps gicv3_its_trans_ops = {
diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c
index 77e5cfa327..8a8684d76e 100644
--- a/hw/intc/arm_gicv3_redist.c
+++ b/hw/intc/arm_gicv3_redist.c
@@ -455,6 +455,13 @@ MemTxResult gicv3_redist_read(void *opaque, hwaddr offset, uint64_t *data,
                       "size %u\n", __func__, offset, size);
         trace_gicv3_redist_badread(gicv3_redist_affid(cs), offset,
                                    size, attrs.secure);
+        /* The spec requires that reserved registers are RAZ/WI;
+         * so use MEMTX_ERROR returns from leaf functions as a way to
+         * trigger the guest-error logging but don't return it to
+         * the caller, or we'll cause a spurious guest data abort.
+         */
+        r = MEMTX_OK;
+        *data = 0;
     } else {
         trace_gicv3_redist_read(gicv3_redist_affid(cs), offset, *data,
                                 size, attrs.secure);
@@ -505,6 +512,12 @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data,
                       "size %u\n", __func__, offset, size);
         trace_gicv3_redist_badwrite(gicv3_redist_affid(cs), offset, data,
                                     size, attrs.secure);
+        /* The spec requires that reserved registers are RAZ/WI;
+         * so use MEMTX_ERROR returns from leaf functions as a way to
+         * trigger the guest-error logging but don't return it to
+         * the caller, or we'll cause a spurious guest data abort.
+         */
+        r = MEMTX_OK;
     } else {
         trace_gicv3_redist_write(gicv3_redist_affid(cs), offset, data,
                                  size, attrs.secure);
diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c
index 90e6ee35ba..4fb48f62ba 100644
--- a/hw/net/imx_fec.c
+++ b/hw/net/imx_fec.c
@@ -196,6 +196,31 @@ static const char *imx_eth_reg_name(IMXFECState *s, uint32_t index)
     }
 }
 
+/*
+ * Versions of this device with more than one TX descriptor save the
+ * 2nd and 3rd descriptors in a subsection, to maintain migration
+ * compatibility with previous versions of the device that only
+ * supported a single descriptor.
+ */
+static bool imx_eth_is_multi_tx_ring(void *opaque)
+{
+    IMXFECState *s = IMX_FEC(opaque);
+
+    return s->tx_ring_num > 1;
+}
+
+static const VMStateDescription vmstate_imx_eth_txdescs = {
+    .name = "imx.fec/txdescs",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = imx_eth_is_multi_tx_ring,
+    .fields = (VMStateField[]) {
+         VMSTATE_UINT32(tx_descriptor[1], IMXFECState),
+         VMSTATE_UINT32(tx_descriptor[2], IMXFECState),
+         VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_imx_eth = {
     .name = TYPE_IMX_FEC,
     .version_id = 2,
@@ -203,15 +228,18 @@ static const VMStateDescription vmstate_imx_eth = {
     .fields = (VMStateField[]) {
         VMSTATE_UINT32_ARRAY(regs, IMXFECState, ENET_MAX),
         VMSTATE_UINT32(rx_descriptor, IMXFECState),
-        VMSTATE_UINT32(tx_descriptor, IMXFECState),
-
+        VMSTATE_UINT32(tx_descriptor[0], IMXFECState),
         VMSTATE_UINT32(phy_status, IMXFECState),
         VMSTATE_UINT32(phy_control, IMXFECState),
         VMSTATE_UINT32(phy_advertise, IMXFECState),
         VMSTATE_UINT32(phy_int, IMXFECState),
         VMSTATE_UINT32(phy_int_mask, IMXFECState),
         VMSTATE_END_OF_LIST()
-    }
+    },
+    .subsections = (const VMStateDescription * []) {
+        &vmstate_imx_eth_txdescs,
+        NULL
+    },
 };
 
 #define PHY_INT_ENERGYON            (1 << 7)
@@ -405,9 +433,8 @@ static void imx_eth_update(IMXFECState *s)
 static void imx_fec_do_tx(IMXFECState *s)
 {
     int frame_size = 0, descnt = 0;
-    uint8_t frame[ENET_MAX_FRAME_SIZE];
-    uint8_t *ptr = frame;
-    uint32_t addr = s->tx_descriptor;
+    uint8_t *ptr = s->frame;
+    uint32_t addr = s->tx_descriptor[0];
 
     while (descnt++ < IMX_MAX_DESC) {
         IMXFECBufDesc bd;
@@ -431,8 +458,8 @@ static void imx_fec_do_tx(IMXFECState *s)
         frame_size += len;
         if (bd.flags & ENET_BD_L) {
             /* Last buffer in frame.  */
-            qemu_send_packet(qemu_get_queue(s->nic), frame, frame_size);
-            ptr = frame;
+            qemu_send_packet(qemu_get_queue(s->nic), s->frame, frame_size);
+            ptr = s->frame;
             frame_size = 0;
             s->regs[ENET_EIR] |= ENET_INT_TXF;
         }
@@ -448,17 +475,47 @@ static void imx_fec_do_tx(IMXFECState *s)
         }
     }
 
-    s->tx_descriptor = addr;
+    s->tx_descriptor[0] = addr;
 
     imx_eth_update(s);
 }
 
-static void imx_enet_do_tx(IMXFECState *s)
+static void imx_enet_do_tx(IMXFECState *s, uint32_t index)
 {
     int frame_size = 0, descnt = 0;
-    uint8_t frame[ENET_MAX_FRAME_SIZE];
-    uint8_t *ptr = frame;
-    uint32_t addr = s->tx_descriptor;
+
+    uint8_t *ptr = s->frame;
+    uint32_t addr, int_txb, int_txf, tdsr;
+    size_t ring;
+
+    switch (index) {
+    case ENET_TDAR:
+        ring    = 0;
+        int_txb = ENET_INT_TXB;
+        int_txf = ENET_INT_TXF;
+        tdsr    = ENET_TDSR;
+        break;
+    case ENET_TDAR1:
+        ring    = 1;
+        int_txb = ENET_INT_TXB1;
+        int_txf = ENET_INT_TXF1;
+        tdsr    = ENET_TDSR1;
+        break;
+    case ENET_TDAR2:
+        ring    = 2;
+        int_txb = ENET_INT_TXB2;
+        int_txf = ENET_INT_TXF2;
+        tdsr    = ENET_TDSR2;
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: bogus value for index %x\n",
+                      __func__, index);
+        abort();
+        break;
+    }
+
+    addr = s->tx_descriptor[ring];
 
     while (descnt++ < IMX_MAX_DESC) {
         IMXENETBufDesc bd;
@@ -482,13 +539,13 @@ static void imx_enet_do_tx(IMXFECState *s)
         frame_size += len;
         if (bd.flags & ENET_BD_L) {
             if (bd.option & ENET_BD_PINS) {
-                struct ip_header *ip_hd = PKT_GET_IP_HDR(frame);
+                struct ip_header *ip_hd = PKT_GET_IP_HDR(s->frame);
                 if (IP_HEADER_VERSION(ip_hd) == 4) {
-                    net_checksum_calculate(frame, frame_size);
+                    net_checksum_calculate(s->frame, frame_size);
                 }
             }
             if (bd.option & ENET_BD_IINS) {
-                struct ip_header *ip_hd = PKT_GET_IP_HDR(frame);
+                struct ip_header *ip_hd = PKT_GET_IP_HDR(s->frame);
                 /* We compute checksum only for IPv4 frames */
                 if (IP_HEADER_VERSION(ip_hd) == 4) {
                     uint16_t csum;
@@ -498,57 +555,59 @@ static void imx_enet_do_tx(IMXFECState *s)
                 }
             }
             /* Last buffer in frame.  */
-            qemu_send_packet(qemu_get_queue(s->nic), frame, len);
-            ptr = frame;
+
+            qemu_send_packet(qemu_get_queue(s->nic), s->frame, frame_size);
+            ptr = s->frame;
+
             frame_size = 0;
             if (bd.option & ENET_BD_TX_INT) {
-                s->regs[ENET_EIR] |= ENET_INT_TXF;
+                s->regs[ENET_EIR] |= int_txf;
             }
         }
         if (bd.option & ENET_BD_TX_INT) {
-            s->regs[ENET_EIR] |= ENET_INT_TXB;
+            s->regs[ENET_EIR] |= int_txb;
         }
         bd.flags &= ~ENET_BD_R;
         /* Write back the modified descriptor.  */
         imx_enet_write_bd(&bd, addr);
         /* Advance to the next descriptor.  */
         if ((bd.flags & ENET_BD_W) != 0) {
-            addr = s->regs[ENET_TDSR];
+            addr = s->regs[tdsr];
         } else {
             addr += sizeof(bd);
         }
     }
 
-    s->tx_descriptor = addr;
+    s->tx_descriptor[ring] = addr;
 
     imx_eth_update(s);
 }
 
-static void imx_eth_do_tx(IMXFECState *s)
+static void imx_eth_do_tx(IMXFECState *s, uint32_t index)
 {
     if (!s->is_fec && (s->regs[ENET_ECR] & ENET_ECR_EN1588)) {
-        imx_enet_do_tx(s);
+        imx_enet_do_tx(s, index);
     } else {
         imx_fec_do_tx(s);
     }
 }
 
-static void imx_eth_enable_rx(IMXFECState *s)
+static void imx_eth_enable_rx(IMXFECState *s, bool flush)
 {
     IMXFECBufDesc bd;
-    bool tmp;
+    bool rx_ring_full;
 
     imx_fec_read_bd(&bd, s->rx_descriptor);
 
-    tmp = ((bd.flags & ENET_BD_E) != 0);
+    rx_ring_full = !(bd.flags & ENET_BD_E);
 
-    if (!tmp) {
+    if (rx_ring_full) {
         FEC_PRINTF("RX buffer full\n");
-    } else if (!s->regs[ENET_RDAR]) {
+    } else if (flush) {
         qemu_flush_queued_packets(qemu_get_queue(s->nic));
     }
 
-    s->regs[ENET_RDAR] = tmp ? ENET_RDAR_RDAR : 0;
+    s->regs[ENET_RDAR] = rx_ring_full ? 0 : ENET_RDAR_RDAR;
 }
 
 static void imx_eth_reset(DeviceState *d)
@@ -585,7 +644,7 @@ static void imx_eth_reset(DeviceState *d)
     }
 
     s->rx_descriptor = 0;
-    s->tx_descriptor = 0;
+    memset(s->tx_descriptor, 0, sizeof(s->tx_descriptor));
 
     /* We also reset the PHY */
     phy_reset(s);
@@ -791,6 +850,7 @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value,
                            unsigned size)
 {
     IMXFECState *s = IMX_FEC(opaque);
+    const bool single_tx_ring = !imx_eth_is_multi_tx_ring(s);
     uint32_t index = offset >> 2;
 
     FEC_PRINTF("reg[%s] <= 0x%" PRIx32 "\n", imx_eth_reg_name(s, index),
@@ -807,16 +867,24 @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value,
         if (s->regs[ENET_ECR] & ENET_ECR_ETHEREN) {
             if (!s->regs[index]) {
                 s->regs[index] = ENET_RDAR_RDAR;
-                imx_eth_enable_rx(s);
+                imx_eth_enable_rx(s, true);
             }
         } else {
             s->regs[index] = 0;
         }
         break;
-    case ENET_TDAR:
+    case ENET_TDAR1:    /* FALLTHROUGH */
+    case ENET_TDAR2:    /* FALLTHROUGH */
+        if (unlikely(single_tx_ring)) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "[%s]%s: trying to access TDAR2 or TDAR1\n",
+                          TYPE_IMX_FEC, __func__);
+            return;
+        }
+    case ENET_TDAR:     /* FALLTHROUGH */
         if (s->regs[ENET_ECR] & ENET_ECR_ETHEREN) {
             s->regs[index] = ENET_TDAR_TDAR;
-            imx_eth_do_tx(s);
+            imx_eth_do_tx(s, index);
         }
         s->regs[index] = 0;
         break;
@@ -828,8 +896,12 @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value,
         if ((s->regs[index] & ENET_ECR_ETHEREN) == 0) {
             s->regs[ENET_RDAR] = 0;
             s->rx_descriptor = s->regs[ENET_RDSR];
-            s->regs[ENET_TDAR] = 0;
-            s->tx_descriptor = s->regs[ENET_TDSR];
+            s->regs[ENET_TDAR]  = 0;
+            s->regs[ENET_TDAR1] = 0;
+            s->regs[ENET_TDAR2] = 0;
+            s->tx_descriptor[0] = s->regs[ENET_TDSR];
+            s->tx_descriptor[1] = s->regs[ENET_TDSR1];
+            s->tx_descriptor[2] = s->regs[ENET_TDSR2];
         }
         break;
     case ENET_MMFR:
@@ -907,7 +979,29 @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value,
         } else {
             s->regs[index] = value & ~7;
         }
-        s->tx_descriptor = s->regs[index];
+        s->tx_descriptor[0] = s->regs[index];
+        break;
+    case ENET_TDSR1:
+        if (unlikely(single_tx_ring)) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "[%s]%s: trying to access TDSR1\n",
+                          TYPE_IMX_FEC, __func__);
+            return;
+        }
+
+        s->regs[index] = value & ~7;
+        s->tx_descriptor[1] = s->regs[index];
+        break;
+    case ENET_TDSR2:
+        if (unlikely(single_tx_ring)) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "[%s]%s: trying to access TDSR2\n",
+                          TYPE_IMX_FEC, __func__);
+            return;
+        }
+
+        s->regs[index] = value & ~7;
+        s->tx_descriptor[2] = s->regs[index];
         break;
     case ENET_MRBR:
         s->regs[index] = value & 0x00003ff0;
@@ -930,7 +1024,7 @@ static int imx_eth_can_receive(NetClientState *nc)
 
     FEC_PRINTF("\n");
 
-    return s->regs[ENET_RDAR] ? 1 : 0;
+    return !!s->regs[ENET_RDAR];
 }
 
 static ssize_t imx_fec_receive(NetClientState *nc, const uint8_t *buf,
@@ -1020,7 +1114,7 @@ static ssize_t imx_fec_receive(NetClientState *nc, const uint8_t *buf,
         }
     }
     s->rx_descriptor = addr;
-    imx_eth_enable_rx(s);
+    imx_eth_enable_rx(s, false);
     imx_eth_update(s);
     return len;
 }
@@ -1037,6 +1131,7 @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf,
     uint8_t *crc_ptr;
     unsigned int buf_len;
     size_t size = len;
+    bool shift16 = s->regs[ENET_RACC] & ENET_RACC_SHIFT16;
 
     FEC_PRINTF("len %d\n", (int)size);
 
@@ -1051,9 +1146,13 @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf,
     crc = cpu_to_be32(crc32(~0, buf, size));
     crc_ptr = (uint8_t *) &crc;
 
-    /* Huge frames are truncted.  */
-    if (size > ENET_MAX_FRAME_SIZE) {
-        size = ENET_MAX_FRAME_SIZE;
+    if (shift16) {
+        size += 2;
+    }
+
+    /* Huge frames are truncated. */
+    if (size > s->regs[ENET_FTRL]) {
+        size = s->regs[ENET_FTRL];
         flags |= ENET_BD_TR | ENET_BD_LG;
     }
 
@@ -1076,7 +1175,7 @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf,
                           TYPE_IMX_FEC, __func__);
             break;
         }
-        buf_len = (size <= s->regs[ENET_MRBR]) ? size : s->regs[ENET_MRBR];
+        buf_len = MIN(size, s->regs[ENET_MRBR]);
         bd.length = buf_len;
         size -= buf_len;
 
@@ -1087,6 +1186,24 @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf,
             buf_len += size - 4;
         }
         buf_addr = bd.data;
+
+        if (shift16) {
+            /*
+             * If SHIFT16 bit of ENETx_RACC register is set we need to
+             * align the payload to 4-byte boundary.
+             */
+            const uint8_t zeros[2] = { 0 };
+
+            dma_memory_write(&address_space_memory, buf_addr,
+                             zeros, sizeof(zeros));
+
+            buf_addr += sizeof(zeros);
+            buf_len  -= sizeof(zeros);
+
+            /* We only do this once per Ethernet frame */
+            shift16 = false;
+        }
+
         dma_memory_write(&address_space_memory, buf_addr, buf, buf_len);
         buf += buf_len;
         if (size < 4) {
@@ -1116,7 +1233,7 @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf,
         }
     }
     s->rx_descriptor = addr;
-    imx_eth_enable_rx(s);
+    imx_eth_enable_rx(s, false);
     imx_eth_update(s);
     return len;
 }
@@ -1164,15 +1281,13 @@ static void imx_eth_realize(DeviceState *dev, Error **errp)
     SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
 
     memory_region_init_io(&s->iomem, OBJECT(dev), &imx_eth_ops, s,
-                          TYPE_IMX_FEC, 0x400);
+                          TYPE_IMX_FEC, FSL_IMX25_FEC_SIZE);
     sysbus_init_mmio(sbd, &s->iomem);
     sysbus_init_irq(sbd, &s->irq[0]);
     sysbus_init_irq(sbd, &s->irq[1]);
 
     qemu_macaddr_default_if_unset(&s->conf.macaddr);
 
-    s->conf.peers.ncs[0] = nd_table[0].netdev;
-
     s->nic = qemu_new_nic(&imx_eth_net_info, &s->conf,
                           object_get_typename(OBJECT(dev)),
                           DEVICE(dev)->id, s);
@@ -1182,6 +1297,7 @@ static void imx_eth_realize(DeviceState *dev, Error **errp)
 
 static Property imx_eth_properties[] = {
     DEFINE_NIC_PROPERTIES(IMXFECState, conf),
+    DEFINE_PROP_UINT32("tx-ring-num", IMXFECState, tx_ring_num, 1),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c
index 3deccf02c9..82f8ec0d50 100644
--- a/hw/sd/pxa2xx_mmci.c
+++ b/hw/sd/pxa2xx_mmci.c
@@ -19,6 +19,8 @@
 #include "hw/qdev.h"
 #include "hw/qdev-properties.h"
 #include "qemu/error-report.h"
+#include "qemu/log.h"
+#include "trace.h"
 
 #define TYPE_PXA2XX_MMCI "pxa2xx-mmci"
 #define PXA2XX_MMCI(obj) OBJECT_CHECK(PXA2xxMMCIState, (obj), TYPE_PXA2XX_MMCI)
@@ -278,45 +280,56 @@ static void pxa2xx_mmci_wakequeues(PXA2xxMMCIState *s)
 static uint64_t pxa2xx_mmci_read(void *opaque, hwaddr offset, unsigned size)
 {
     PXA2xxMMCIState *s = (PXA2xxMMCIState *) opaque;
-    uint32_t ret;
+    uint32_t ret = 0;
 
     switch (offset) {
     case MMC_STRPCL:
-        return 0;
+        break;
     case MMC_STAT:
-        return s->status;
+        ret = s->status;
+        break;
     case MMC_CLKRT:
-        return s->clkrt;
+        ret = s->clkrt;
+        break;
     case MMC_SPI:
-        return s->spi;
+        ret = s->spi;
+        break;
     case MMC_CMDAT:
-        return s->cmdat;
+        ret = s->cmdat;
+        break;
     case MMC_RESTO:
-        return s->resp_tout;
+        ret = s->resp_tout;
+        break;
     case MMC_RDTO:
-        return s->read_tout;
+        ret = s->read_tout;
+        break;
     case MMC_BLKLEN:
-        return s->blklen;
+        ret = s->blklen;
+        break;
     case MMC_NUMBLK:
-        return s->numblk;
+        ret = s->numblk;
+        break;
     case MMC_PRTBUF:
-        return 0;
+        break;
     case MMC_I_MASK:
-        return s->intmask;
+        ret = s->intmask;
+        break;
     case MMC_I_REG:
-        return s->intreq;
+        ret = s->intreq;
+        break;
     case MMC_CMD:
-        return s->cmd | 0x40;
+        ret = s->cmd | 0x40;
+        break;
     case MMC_ARGH:
-        return s->arg >> 16;
+        ret = s->arg >> 16;
+        break;
     case MMC_ARGL:
-        return s->arg & 0xffff;
+        ret = s->arg & 0xffff;
+        break;
     case MMC_RES:
-        if (s->resp_len < 9)
-            return s->resp_fifo[s->resp_len ++];
-        return 0;
+        ret = (s->resp_len < 9) ? s->resp_fifo[s->resp_len++] : 0;
+        break;
     case MMC_RXFIFO:
-        ret = 0;
         while (size-- && s->rx_len) {
             ret |= s->rx_fifo[s->rx_start++] << (size << 3);
             s->rx_start &= 0x1f;
@@ -324,16 +337,20 @@ static uint64_t pxa2xx_mmci_read(void *opaque, hwaddr offset, unsigned size)
         }
         s->intreq &= ~INT_RXFIFO_REQ;
         pxa2xx_mmci_fifo_update(s);
-        return ret;
+        break;
     case MMC_RDWAIT:
-        return 0;
+        break;
     case MMC_BLKS_REM:
-        return s->numblk;
+        ret = s->numblk;
+        break;
     default:
-        hw_error("%s: Bad offset " REG_FMT "\n", __FUNCTION__, offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: incorrect register 0x%02" HWADDR_PRIx "\n",
+                      __func__, offset);
     }
+    trace_pxa2xx_mmci_read(size, offset, ret);
 
-    return 0;
+    return ret;
 }
 
 static void pxa2xx_mmci_write(void *opaque,
@@ -341,6 +358,7 @@ static void pxa2xx_mmci_write(void *opaque,
 {
     PXA2xxMMCIState *s = (PXA2xxMMCIState *) opaque;
 
+    trace_pxa2xx_mmci_write(size, offset, value);
     switch (offset) {
     case MMC_STRPCL:
         if (value & STRPCL_STRT_CLK) {
@@ -368,8 +386,10 @@ static void pxa2xx_mmci_write(void *opaque,
 
     case MMC_SPI:
         s->spi = value & 0xf;
-        if (value & SPI_SPI_MODE)
-            printf("%s: attempted to use card in SPI mode\n", __FUNCTION__);
+        if (value & SPI_SPI_MODE) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: attempted to use card in SPI mode\n", __func__);
+        }
         break;
 
     case MMC_CMDAT:
@@ -442,7 +462,9 @@ static void pxa2xx_mmci_write(void *opaque,
         break;
 
     default:
-        hw_error("%s: Bad offset " REG_FMT "\n", __FUNCTION__, offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: incorrect reg 0x%02" HWADDR_PRIx " "
+                      "(value 0x%08" PRIx64 ")\n", __func__, offset, value);
     }
 }
 
diff --git a/hw/sd/trace-events b/hw/sd/trace-events
index 1fc0bcf44b..6eca3470e2 100644
--- a/hw/sd/trace-events
+++ b/hw/sd/trace-events
@@ -3,3 +3,7 @@
 # hw/sd/milkymist-memcard.c
 milkymist_memcard_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x"
 milkymist_memcard_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x"
+
+# hw/sd/pxa2xx_mmci.c
+pxa2xx_mmci_read(uint8_t size, uint32_t addr, uint32_t value) "size %d addr 0x%02x value 0x%08x"
+pxa2xx_mmci_write(uint8_t size, uint32_t addr, uint32_t value) "size %d addr 0x%02x value 0x%08x"
diff --git a/hw/timer/pxa2xx_timer.c b/hw/timer/pxa2xx_timer.c
index 68ba5a70b3..a489bf5159 100644
--- a/hw/timer/pxa2xx_timer.c
+++ b/hw/timer/pxa2xx_timer.c
@@ -13,6 +13,7 @@
 #include "sysemu/sysemu.h"
 #include "hw/arm/pxa.h"
 #include "hw/sysbus.h"
+#include "qemu/log.h"
 
 #define OSMR0	0x00
 #define OSMR1	0x04
@@ -252,8 +253,14 @@ static uint64_t pxa2xx_timer_read(void *opaque, hwaddr offset,
     case OSNR:
         return s->snapshot;
     default:
+        qemu_log_mask(LOG_UNIMP,
+                      "%s: unknown register 0x%02" HWADDR_PRIx "\n",
+                      __func__, offset);
+        break;
     badreg:
-        hw_error("pxa2xx_timer_read: Bad offset " REG_FMT "\n", offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: incorrect register 0x%02" HWADDR_PRIx "\n",
+                      __func__, offset);
     }
 
     return 0;
@@ -377,8 +384,14 @@ static void pxa2xx_timer_write(void *opaque, hwaddr offset,
         }
         break;
     default:
+        qemu_log_mask(LOG_UNIMP,
+                      "%s: unknown register 0x%02" HWADDR_PRIx " "
+                      "(value 0x%08" PRIx64 ")\n",  __func__, offset, value);
+        break;
     badreg:
-        hw_error("pxa2xx_timer_write: Bad offset " REG_FMT "\n", offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: incorrect register 0x%02" HWADDR_PRIx " "
+                      "(value 0x%08" PRIx64 ")\n", __func__, offset, value);
     }
 }
 
diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h
index d0e8e9d956..65a73714ef 100644
--- a/include/hw/arm/fsl-imx25.h
+++ b/include/hw/arm/fsl-imx25.h
@@ -192,7 +192,6 @@ typedef struct FslIMX25State {
 #define FSL_IMX25_UART5_ADDR    0x5002C000
 #define FSL_IMX25_UART5_SIZE    0x4000
 #define FSL_IMX25_FEC_ADDR      0x50038000
-#define FSL_IMX25_FEC_SIZE      0x4000
 #define FSL_IMX25_CCM_ADDR      0x53F80000
 #define FSL_IMX25_CCM_SIZE      0x4000
 #define FSL_IMX25_GPT4_ADDR     0x53F84000
diff --git a/include/hw/net/imx_fec.h b/include/hw/net/imx_fec.h
index 62ad473b05..7b3faa4019 100644
--- a/include/hw/net/imx_fec.h
+++ b/include/hw/net/imx_fec.h
@@ -52,6 +52,8 @@
 #define ENET_TFWR              81
 #define ENET_FRBR              83
 #define ENET_FRSR              84
+#define ENET_TDSR1             89
+#define ENET_TDSR2             92
 #define ENET_RDSR              96
 #define ENET_TDSR              97
 #define ENET_MRBR              98
@@ -66,6 +68,8 @@
 #define ENET_FTRL              108
 #define ENET_TACC              112
 #define ENET_RACC              113
+#define ENET_TDAR1             121
+#define ENET_TDAR2             123
 #define ENET_MIIGSK_CFGR       192
 #define ENET_MIIGSK_ENR        194
 #define ENET_ATCR              256
@@ -86,7 +90,6 @@
 #define ENET_TCCR3             393
 #define ENET_MAX               400
 
-#define ENET_MAX_FRAME_SIZE    2032
 
 /* EIR and EIMR */
 #define ENET_INT_HB            (1 << 31)
@@ -106,13 +109,18 @@
 #define ENET_INT_WAKEUP        (1 << 17)
 #define ENET_INT_TS_AVAIL      (1 << 16)
 #define ENET_INT_TS_TIMER      (1 << 15)
+#define ENET_INT_TXF2          (1 <<  7)
+#define ENET_INT_TXB2          (1 <<  6)
+#define ENET_INT_TXF1          (1 <<  3)
+#define ENET_INT_TXB1          (1 <<  2)
 
 #define ENET_INT_MAC           (ENET_INT_HB | ENET_INT_BABR | ENET_INT_BABT | \
                                 ENET_INT_GRA | ENET_INT_TXF | ENET_INT_TXB | \
                                 ENET_INT_RXF | ENET_INT_RXB | ENET_INT_MII | \
                                 ENET_INT_EBERR | ENET_INT_LC | ENET_INT_RL | \
                                 ENET_INT_UN | ENET_INT_PLR | ENET_INT_WAKEUP | \
-                                ENET_INT_TS_AVAIL)
+                                ENET_INT_TS_AVAIL | ENET_INT_TXF1 | \
+                                ENET_INT_TXB1 | ENET_INT_TXF2 | ENET_INT_TXB2)
 
 /* RDAR */
 #define ENET_RDAR_RDAR         (1 << 24)
@@ -155,6 +163,8 @@
 #define ENET_RCR_NLC           (1 << 30)
 #define ENET_RCR_GRS           (1 << 31)
 
+#define ENET_MAX_FRAME_SIZE    (1 << ENET_RCR_MAX_FL_LENGTH)
+
 /* TCR */
 #define ENET_TCR_GTS           (1 << 0)
 #define ENET_TCR_FDEN          (1 << 2)
@@ -169,6 +179,8 @@
 #define ENET_TWFR_TFWR_LENGTH  (6)
 #define ENET_TWFR_STRFWD       (1 << 8)
 
+#define ENET_RACC_SHIFT16      BIT(7)
+
 /* Buffer Descriptor.  */
 typedef struct {
     uint16_t length;
@@ -231,6 +243,10 @@ typedef struct {
 
 #define ENET_BD_BDU            (1 << 31)
 
+#define ENET_TX_RING_NUM       3
+
+#define FSL_IMX25_FEC_SIZE      0x4000
+
 typedef struct IMXFECState {
     /*< private >*/
     SysBusDevice parent_obj;
@@ -243,7 +259,9 @@ typedef struct IMXFECState {
 
     uint32_t regs[ENET_MAX];
     uint32_t rx_descriptor;
-    uint32_t tx_descriptor;
+
+    uint32_t tx_descriptor[ENET_TX_RING_NUM];
+    uint32_t tx_ring_num;
 
     uint32_t phy_status;
     uint32_t phy_control;
@@ -252,6 +270,9 @@ typedef struct IMXFECState {
     uint32_t phy_int_mask;
 
     bool is_fec;
+
+    /* Buffer used to assemble a Tx frame */
+    uint8_t frame[ENET_MAX_FRAME_SIZE];
 } IMXFECState;
 
 #endif
diff --git a/linux-user/aarch64/target_syscall.h b/linux-user/aarch64/target_syscall.h
index 1b62953eeb..604ab99b14 100644
--- a/linux-user/aarch64/target_syscall.h
+++ b/linux-user/aarch64/target_syscall.h
@@ -8,7 +8,11 @@ struct target_pt_regs {
     uint64_t        pstate;
 };
 
+#if defined(TARGET_WORDS_BIGENDIAN)
+#define UNAME_MACHINE "aarch64_be"
+#else
 #define UNAME_MACHINE "aarch64"
+#endif
 #define UNAME_MINIMUM_RELEASE "3.8.0"
 #define TARGET_CLONE_BACKWARDS
 #define TARGET_MINSIGSTKSZ       2048
diff --git a/linux-user/arm/nwfpe/fpa11.c b/linux-user/arm/nwfpe/fpa11.c
index 441e3b1cf6..f6f8163eab 100644
--- a/linux-user/arm/nwfpe/fpa11.c
+++ b/linux-user/arm/nwfpe/fpa11.c
@@ -137,8 +137,17 @@ unsigned int EmulateAll(unsigned int opcode, FPA11* qfpa, CPUARMState* qregs)
   unsigned int nRc = 0;
 //  unsigned long flags;
   FPA11 *fpa11;
+  unsigned int cp;
 //  save_flags(flags); sti();
 
+  /* Check that this is really an FPA11 instruction: the coprocessor
+   * field in bits [11:8] must be 1 or 2.
+   */
+  cp = (opcode >> 8) & 0xf;
+  if (cp != 1 && cp != 2) {
+    return 0;
+  }
+
   qemufpa=qfpa;
   user_registers=qregs;
 
diff --git a/linux-user/main.c b/linux-user/main.c
index 99a551b04f..450eb3ce65 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -4629,6 +4629,12 @@ int main(int argc, char **argv, char **envp)
         }
         env->pc = regs->pc;
         env->xregs[31] = regs->sp;
+#ifdef TARGET_WORDS_BIGENDIAN
+        env->cp15.sctlr_el[1] |= SCTLR_E0E;
+        for (i = 1; i < 4; ++i) {
+            env->cp15.sctlr_el[i] |= SCTLR_EE;
+        }
+#endif
     }
 #elif defined(TARGET_ARM)
     {
diff --git a/linux-user/signal.c b/linux-user/signal.c
index 74fa03f96d..f85f0dd780 100644
--- a/linux-user/signal.c
+++ b/linux-user/signal.c
@@ -1599,9 +1599,13 @@ static void target_setup_frame(int usig, struct target_sigaction *ka,
     if (ka->sa_flags & TARGET_SA_RESTORER) {
         return_addr = ka->sa_restorer;
     } else {
-        /* mov x8,#__NR_rt_sigreturn; svc #0 */
-        __put_user(0xd2801168, &frame->tramp[0]);
-        __put_user(0xd4000001, &frame->tramp[1]);
+        /*
+         * mov x8,#__NR_rt_sigreturn; svc #0
+         * Since these are instructions they need to be put as little-endian
+         * regardless of target default or current CPU endianness.
+         */
+        __put_user_e(0xd2801168, &frame->tramp[0], le);
+        __put_user_e(0xd4000001, &frame->tramp[1], le);
         return_addr = frame_addr + offsetof(struct target_rt_sigframe, tramp);
     }
     env->xregs[0] = usig;
diff --git a/scripts/qemu-binfmt-conf.sh b/scripts/qemu-binfmt-conf.sh
index 8afc3eb5bb..ea5a748745 100755
--- a/scripts/qemu-binfmt-conf.sh
+++ b/scripts/qemu-binfmt-conf.sh
@@ -2,9 +2,9 @@
 # enable automatic i386/ARM/M68K/MIPS/SPARC/PPC/s390/HPPA
 # program execution by the kernel
 
-qemu_target_list="i386 i486 alpha arm sparc32plus ppc ppc64 ppc64le m68k \
+qemu_target_list="i386 i486 alpha arm armeb sparc32plus ppc ppc64 ppc64le m68k \
 mips mipsel mipsn32 mipsn32el mips64 mips64el \
-sh4 sh4eb s390x aarch64 hppa"
+sh4 sh4eb s390x aarch64 aarch64_be hppa"
 
 i386_magic='\x7fELF\x01\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x03\x00'
 i386_mask='\xff\xff\xff\xff\xff\xfe\xfe\xff\xff\xff\xff\xff\xff\xff\xff\xff\xfe\xff\xff\xff'
@@ -24,7 +24,7 @@ arm_family=arm
 
 armeb_magic='\x7fELF\x01\x02\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x28'
 armeb_mask='\xff\xff\xff\xff\xff\xff\xff\x00\xff\xff\xff\xff\xff\xff\xff\xff\xff\xfe\xff\xff'
-armeb_family=arm
+armeb_family=armeb
 
 sparc_magic='\x7fELF\x01\x02\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x02'
 sparc_mask='\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xfe\xff\xff'
@@ -92,6 +92,10 @@ aarch64_magic='\x7fELF\x02\x01\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x
 aarch64_mask='\xff\xff\xff\xff\xff\xff\xff\x00\xff\xff\xff\xff\xff\xff\xff\xff\xfe\xff\xff\xff'
 aarch64_family=arm
 
+aarch64_be_magic='\x7fELF\x02\x02\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\xb7'
+aarch64_be_mask='\xff\xff\xff\xff\xff\xff\xff\x00\xff\xff\xff\xff\xff\xff\xff\xff\xff\xfe\xff\xff'
+aarch64_be_family=armeb
+
 hppa_magic='\x7f\x45\x4c\x46\x01\x02\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x02\x00\x0f'
 hppa_mask='\xff\xff\xff\xff\xff\xff\xff\x00\xff\xff\xff\xff\xff\xff\xff\xff\xff\xfe\xff\xff'
 hppa_family=hppa
@@ -111,9 +115,12 @@ qemu_get_family() {
     ppc64el|ppc64le)
         echo "ppcle"
         ;;
-    arm|armel|armhf|arm64|armv[4-9]*)
+    arm|armel|armhf|arm64|armv[4-9]*l|aarch64)
         echo "arm"
         ;;
+    armeb|armv[4-9]*b|aarch64_be)
+        echo "armeb"
+        ;;
     sparc*)
         echo "sparc"
         ;;
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index b84ebcae6e..3e00a9ead1 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -506,8 +506,11 @@ static uint64_t do_paired_cmpxchg64_be(CPUARMState *env, uint64_t addr,
     Int128 oldv, cmpv, newv;
     bool success;
 
-    cmpv = int128_make128(env->exclusive_val, env->exclusive_high);
-    newv = int128_make128(new_lo, new_hi);
+    /* high and low need to be switched here because this is not actually a
+     * 128bit store but two doublewords stored consecutively
+     */
+    cmpv = int128_make128(env->exclusive_high, env->exclusive_val);
+    newv = int128_make128(new_hi, new_lo);
 
     if (parallel) {
 #ifndef CONFIG_ATOMIC128
diff --git a/target/arm/translate.c b/target/arm/translate.c
index c690658493..781be1e219 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -9775,9 +9775,8 @@ gen_thumb2_data_op(DisasContext *s, int op, int conds, uint32_t shifter_out,
     return 0;
 }
 
-/* Translate a 32-bit thumb instruction.  Returns nonzero if the instruction
-   is not legal.  */
-static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
+/* Translate a 32-bit thumb instruction. */
+static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
 {
     uint32_t imm, shift, offset;
     uint32_t rd, rn, rm, rs;
@@ -11016,16 +11015,16 @@ static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
                     /* UNPREDICTABLE, unallocated hint or
                      * PLD/PLDW/PLI (literal)
                      */
-                    return 0;
+                    return;
                 }
                 if (op1 & 1) {
-                    return 0; /* PLD/PLDW/PLI or unallocated hint */
+                    return; /* PLD/PLDW/PLI or unallocated hint */
                 }
                 if ((op2 == 0) || ((op2 & 0x3c) == 0x30)) {
-                    return 0; /* PLD/PLDW/PLI or unallocated hint */
+                    return; /* PLD/PLDW/PLI or unallocated hint */
                 }
                 /* UNDEF space, or an UNPREDICTABLE */
-                return 1;
+                goto illegal_op;
             }
         }
         memidx = get_mem_index(s);
@@ -11151,9 +11150,10 @@ static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
     default:
         goto illegal_op;
     }
-    return 0;
+    return;
 illegal_op:
-    return 1;
+    gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(),
+                       default_exception_el(s));
 }
 
 static void disas_thumb_insn(DisasContext *s, uint32_t insn)
@@ -12275,10 +12275,7 @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
     if (is_16bit) {
         disas_thumb_insn(dc, insn);
     } else {
-        if (disas_thumb2_insn(dc, insn)) {
-            gen_exception_insn(dc, 4, EXCP_UDEF, syn_uncategorized(),
-                               default_exception_el(dc));
-        }
+        disas_thumb2_insn(dc, insn);
     }
 
     /* Advance the Thumb condexec condition.  */