Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20170420' into staging

target-arm queue:
 * implement M profile exception return properly
 * cadence GEM: fix multiqueue handling bugs
 * pxa2xx.c: QOMify a device
 * arm/kvm: Remove trailing newlines from error_report()
 * stellaris: Don't hw_error() on bad register accesses
 * Add assertion about FSC format for syndrome registers
 * Move excnames[] array into arm_log_exceptions()
 * exynos: minor code cleanups
 * hw/arm/boot: take Linux/arm64 TEXT_OFFSET header field into account
 * Fix APSR writes via M profile MSR

# gpg: Signature made Thu 20 Apr 2017 17:39:35 BST
# gpg:                using RSA key 0x3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20170420: (24 commits)
  arm: Remove workarounds for old M-profile exception return implementation
  arm: Implement M profile exception return properly
  arm: Track M profile handler mode state in TB flags
  arm: Abstract out "are we singlestepping" test to utility function
  arm: Move condition-failed codepath generation out of if()
  arm: Move gen_set_condexec() and gen_set_pc_im() up in the file
  arm: Factor out "generate right kind of step exception"
  arm: Thumb shift operations should not permit interworking branches
  arm: Don't implement BXJ on M-profile CPUs
  xlnx-zynqmp: Set the Cadence GEM revision
  cadence_gem: Make the revision a property
  cadence_gem: Correct the interupt logic
  cadence_gem: Correct the multi-queue can rx logic
  cadence_gem: Read the correct queue descriptor
  hw/arm: Qomify pxa2xx.c
  arm/kvm: Remove trailing newlines from error_report()
  stellaris: Don't hw_error() on bad register accesses
  target/arm: Add assertion about FSC format for syndrome registers
  arm: Move excnames[] array into arm_log_exceptions()
  target/arm: Add missing entries to excnames[] for log strings
  ...

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

20 files changed, 341 insertions, 212 deletions

diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index ff621e4b6a..c2720c8046 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -31,6 +31,9 @@
 #define KERNEL_LOAD_ADDR 0x00010000
 #define KERNEL64_LOAD_ADDR 0x00080000
 
+#define ARM64_TEXT_OFFSET_OFFSET    8
+#define ARM64_MAGIC_OFFSET          56
+
 typedef enum {
     FIXUP_NONE = 0,     /* do nothing */
     FIXUP_TERMINATOR,   /* end of insns */
@@ -768,6 +771,49 @@ static uint64_t arm_load_elf(struct arm_boot_info *info, uint64_t *pentry,
     return ret;
 }
 
+static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base,
+                                   hwaddr *entry)
+{
+    hwaddr kernel_load_offset = KERNEL64_LOAD_ADDR;
+    uint8_t *buffer;
+    int size;
+
+    /* On aarch64, it's the bootloader's job to uncompress the kernel. */
+    size = load_image_gzipped_buffer(filename, LOAD_IMAGE_MAX_GUNZIP_BYTES,
+                                     &buffer);
+
+    if (size < 0) {
+        gsize len;
+
+        /* Load as raw file otherwise */
+        if (!g_file_get_contents(filename, (char **)&buffer, &len, NULL)) {
+            return -1;
+        }
+        size = len;
+    }
+
+    /* check the arm64 magic header value -- very old kernels may not have it */
+    if (memcmp(buffer + ARM64_MAGIC_OFFSET, "ARM\x64", 4) == 0) {
+        uint64_t hdrvals[2];
+
+        /* The arm64 Image header has text_offset and image_size fields at 8 and
+         * 16 bytes into the Image header, respectively. The text_offset field
+         * is only valid if the image_size is non-zero.
+         */
+        memcpy(&hdrvals, buffer + ARM64_TEXT_OFFSET_OFFSET, sizeof(hdrvals));
+        if (hdrvals[1] != 0) {
+            kernel_load_offset = le64_to_cpu(hdrvals[0]);
+        }
+    }
+
+    *entry = mem_base + kernel_load_offset;
+    rom_add_blob_fixed(filename, buffer, size, *entry);
+
+    g_free(buffer);
+
+    return size;
+}
+
 static void arm_load_kernel_notify(Notifier *notifier, void *data)
 {
     CPUState *cs;
@@ -776,7 +822,7 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
     int is_linux = 0;
     uint64_t elf_entry, elf_low_addr, elf_high_addr;
     int elf_machine;
-    hwaddr entry, kernel_load_offset;
+    hwaddr entry;
     static const ARMInsnFixup *primary_loader;
     ArmLoadKernelNotifier *n = DO_UPCAST(ArmLoadKernelNotifier,
                                          notifier, notifier);
@@ -841,14 +887,12 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
 
     if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
         primary_loader = bootloader_aarch64;
-        kernel_load_offset = KERNEL64_LOAD_ADDR;
         elf_machine = EM_AARCH64;
     } else {
         primary_loader = bootloader;
         if (!info->write_board_setup) {
             primary_loader += BOOTLOADER_NO_BOARD_SETUP_OFFSET;
         }
-        kernel_load_offset = KERNEL_LOAD_ADDR;
         elf_machine = EM_ARM;
     }
 
@@ -900,17 +944,15 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
         kernel_size = load_uimage(info->kernel_filename, &entry, NULL,
                                   &is_linux, NULL, NULL);
     }
-    /* On aarch64, it's the bootloader's job to uncompress the kernel. */
     if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) && kernel_size < 0) {
-        entry = info->loader_start + kernel_load_offset;
-        kernel_size = load_image_gzipped(info->kernel_filename, entry,
-                                         info->ram_size - kernel_load_offset);
+        kernel_size = load_aarch64_image(info->kernel_filename,
+                                         info->loader_start, &entry);
         is_linux = 1;
-    }
-    if (kernel_size < 0) {
-        entry = info->loader_start + kernel_load_offset;
+    } else if (kernel_size < 0) {
+        /* 32-bit ARM */
+        entry = info->loader_start + KERNEL_LOAD_ADDR;
         kernel_size = load_image_targphys(info->kernel_filename, entry,
-                                          info->ram_size - kernel_load_offset);
+                                          info->ram_size - KERNEL_LOAD_ADDR);
         is_linux = 1;
     }
     if (kernel_size < 0) {
diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c
index 0efa194054..4853c31802 100644
--- a/hw/arm/exynos4_boards.c
+++ b/hw/arm/exynos4_boards.c
@@ -22,6 +22,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/error-report.h"
 #include "qemu-common.h"
 #include "cpu.h"
 #include "sysemu/sysemu.h"
@@ -101,9 +102,9 @@ static Exynos4210State *exynos4_boards_init_common(MachineState *machine,
     MachineClass *mc = MACHINE_GET_CLASS(machine);
 
     if (smp_cpus != EXYNOS4210_NCPUS && !qtest_enabled()) {
-        fprintf(stderr, "%s board supports only %d CPU cores. Ignoring smp_cpus"
-                " value.\n",
-                mc->name, EXYNOS4210_NCPUS);
+        error_report("%s board supports only %d CPU cores, ignoring smp_cpus"
+                     " value",
+                     mc->name, EXYNOS4210_NCPUS);
     }
 
     exynos4_board_binfo.ram_size = exynos4_board_ram_size[board_type];
diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c
index cfee3929d9..eea551dc16 100644
--- a/hw/arm/pxa2xx.c
+++ b/hw/arm/pxa2xx.c
@@ -755,19 +755,18 @@ static void pxa2xx_ssp_reset(DeviceState *d)
     s->rx_start = s->rx_level = 0;
 }
 
-static int pxa2xx_ssp_init(SysBusDevice *sbd)
+static void pxa2xx_ssp_init(Object *obj)
 {
-    DeviceState *dev = DEVICE(sbd);
-    PXA2xxSSPState *s = PXA2XX_SSP(dev);
-
+    DeviceState *dev = DEVICE(obj);
+    PXA2xxSSPState *s = PXA2XX_SSP(obj);
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
     sysbus_init_irq(sbd, &s->irq);
 
-    memory_region_init_io(&s->iomem, OBJECT(s), &pxa2xx_ssp_ops, s,
+    memory_region_init_io(&s->iomem, obj, &pxa2xx_ssp_ops, s,
                           "pxa2xx-ssp", 0x1000);
     sysbus_init_mmio(sbd, &s->iomem);
 
     s->bus = ssi_create_bus(dev, "ssi");
-    return 0;
 }
 
 /* Real-Time Clock */
@@ -2321,10 +2320,8 @@ PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size)
 
 static void pxa2xx_ssp_class_init(ObjectClass *klass, void *data)
 {
-    SysBusDeviceClass *sdc = SYS_BUS_DEVICE_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    sdc->init = pxa2xx_ssp_init;
     dc->reset = pxa2xx_ssp_reset;
     dc->vmsd = &vmstate_pxa2xx_ssp;
 }
@@ -2333,6 +2330,7 @@ static const TypeInfo pxa2xx_ssp_info = {
     .name          = TYPE_PXA2XX_SSP,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(PXA2xxSSPState),
+    .instance_init = pxa2xx_ssp_init,
     .class_init    = pxa2xx_ssp_class_init,
 };
 
diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c
index 9edcd49740..ea7a8094e1 100644
--- a/hw/arm/stellaris.c
+++ b/hw/arm/stellaris.c
@@ -108,7 +108,10 @@ static void gptm_reload(gptm_state *s, int n, int reset)
     } else if (s->mode[n] == 0xa) {
         /* PWM mode.  Not implemented.  */
     } else {
-        hw_error("TODO: 16-bit timer mode 0x%x\n", s->mode[n]);
+        qemu_log_mask(LOG_UNIMP,
+                      "GPTM: 16-bit timer mode unimplemented: 0x%x\n",
+                      s->mode[n]);
+        return;
     }
     s->tick[n] = tick;
     timer_mod(s->timer[n], tick);
@@ -149,7 +152,9 @@ static void gptm_tick(void *opaque)
     } else if (s->mode[n] == 0xa) {
         /* PWM mode.  Not implemented.  */
     } else {
-        hw_error("TODO: 16-bit timer mode 0x%x\n", s->mode[n]);
+        qemu_log_mask(LOG_UNIMP,
+                      "GPTM: 16-bit timer mode unimplemented: 0x%x\n",
+                      s->mode[n]);
     }
     gptm_update_irq(s);
 }
@@ -286,7 +291,8 @@ static void gptm_write(void *opaque, hwaddr offset,
         s->match_prescale[0] = value;
         break;
     default:
-        hw_error("gptm_write: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "GPTM: read at bad offset 0x%x\n", (int)offset);
     }
     gptm_update_irq(s);
 }
@@ -425,7 +431,10 @@ static int ssys_board_class(const ssys_state *s)
         }
         /* for unknown classes, fall through */
     default:
-        hw_error("ssys_board_class: Unknown class 0x%08x\n", did0);
+        /* This can only happen if the hardwired constant did0 value
+         * in this board's stellaris_board_info struct is wrong.
+         */
+        g_assert_not_reached();
     }
 }
 
@@ -479,8 +488,7 @@ static uint64_t ssys_read(void *opaque, hwaddr offset,
             case DID0_CLASS_SANDSTORM:
                 return pllcfg_sandstorm[xtal];
             default:
-                hw_error("ssys_read: Unhandled class for PLLCFG read.\n");
-                return 0;
+                g_assert_not_reached();
             }
         }
     case 0x070: /* RCC2 */
@@ -512,7 +520,8 @@ static uint64_t ssys_read(void *opaque, hwaddr offset,
     case 0x1e4: /* USER1 */
         return s->user1;
     default:
-        hw_error("ssys_read: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SSYS: read at bad offset 0x%x\n", (int)offset);
         return 0;
     }
 }
@@ -614,7 +623,8 @@ static void ssys_write(void *opaque, hwaddr offset,
         s->ldoarst = value;
         break;
     default:
-        hw_error("ssys_write: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SSYS: write at bad offset 0x%x\n", (int)offset);
     }
     ssys_update(s);
 }
@@ -748,7 +758,8 @@ static uint64_t stellaris_i2c_read(void *opaque, hwaddr offset,
     case 0x20: /* MCR */
         return s->mcr;
     default:
-        hw_error("strllaris_i2c_read: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_i2c: read at bad offset 0x%x\n", (int)offset);
         return 0;
     }
 }
@@ -823,17 +834,18 @@ static void stellaris_i2c_write(void *opaque, hwaddr offset,
         s->mris &= ~value;
         break;
     case 0x20: /* MCR */
-        if (value & 1)
-            hw_error(
-                      "stellaris_i2c_write: Loopback not implemented\n");
-        if (value & 0x20)
-            hw_error(
-                      "stellaris_i2c_write: Slave mode not implemented\n");
+        if (value & 1) {
+            qemu_log_mask(LOG_UNIMP, "stellaris_i2c: Loopback not implemented");
+        }
+        if (value & 0x20) {
+            qemu_log_mask(LOG_UNIMP,
+                          "stellaris_i2c: Slave mode not implemented");
+        }
         s->mcr = value & 0x31;
         break;
     default:
-        hw_error("stellaris_i2c_write: Bad offset 0x%x\n",
-                  (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_i2c: write at bad offset 0x%x\n", (int)offset);
     }
     stellaris_i2c_update(s);
 }
@@ -1057,8 +1069,8 @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset,
     case 0x30: /* SAC */
         return s->sac;
     default:
-        hw_error("strllaris_adc_read: Bad offset 0x%x\n",
-                  (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_adc: read at bad offset 0x%x\n", (int)offset);
         return 0;
     }
 }
@@ -1078,8 +1090,9 @@ static void stellaris_adc_write(void *opaque, hwaddr offset,
             return;
         case 0x04: /* SSCTL */
             if (value != 6) {
-                hw_error("ADC: Unimplemented sequence %" PRIx64 "\n",
-                          value);
+                qemu_log_mask(LOG_UNIMP,
+                              "ADC: Unimplemented sequence %" PRIx64 "\n",
+                              value);
             }
             s->ssctl[n] = value;
             return;
@@ -1110,13 +1123,14 @@ static void stellaris_adc_write(void *opaque, hwaddr offset,
         s->sspri = value;
         break;
     case 0x28: /* PSSI */
-        hw_error("Not implemented:  ADC sample initiate\n");
+        qemu_log_mask(LOG_UNIMP, "ADC: sample initiate unimplemented");
         break;
     case 0x30: /* SAC */
         s->sac = value;
         break;
     default:
-        hw_error("stellaris_adc_write: Bad offset 0x%x\n", (int)offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "stellaris_adc: write at bad offset 0x%x\n", (int)offset);
     }
     stellaris_adc_update(s);
 }
diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c
index bc4e66b862..e41b6fe422 100644
--- a/hw/arm/xlnx-zynqmp.c
+++ b/hw/arm/xlnx-zynqmp.c
@@ -30,6 +30,8 @@
 #define ARM_PHYS_TIMER_PPI  30
 #define ARM_VIRT_TIMER_PPI  27
 
+#define GEM_REVISION        0x40070106
+
 #define GIC_BASE_ADDR       0xf9000000
 #define GIC_DIST_ADDR       0xf9010000
 #define GIC_CPU_ADDR        0xf9020000
@@ -334,8 +336,10 @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp)
             qemu_check_nic_model(nd, TYPE_CADENCE_GEM);
             qdev_set_nic_properties(DEVICE(&s->gem[i]), nd);
         }
+        object_property_set_int(OBJECT(&s->gem[i]), GEM_REVISION, "revision",
+                                &error_abort);
         object_property_set_int(OBJECT(&s->gem[i]), 2, "num-priority-queues",
-                                  &error_abort);
+                                &error_abort);
         object_property_set_bool(OBJECT(&s->gem[i]), true, "realized", &err);
         if (err) {
             error_propagate(errp, err);
diff --git a/hw/char/exynos4210_uart.c b/hw/char/exynos4210_uart.c
index b75f28d473..bff706ab3a 100644
--- a/hw/char/exynos4210_uart.c
+++ b/hw/char/exynos4210_uart.c
@@ -102,7 +102,7 @@ typedef struct Exynos4210UartReg {
     uint32_t            reset_value;
 } Exynos4210UartReg;
 
-static Exynos4210UartReg exynos4210_uart_regs[] = {
+static const Exynos4210UartReg exynos4210_uart_regs[] = {
     {"ULCON",    ULCON,    0x00000000},
     {"UCON",     UCON,     0x00003000},
     {"UFCON",    UFCON,    0x00000000},
@@ -220,7 +220,7 @@ static uint8_t fifo_retrieve(Exynos4210UartFIFO *q)
     return  ret;
 }
 
-static int fifo_elements_number(Exynos4210UartFIFO *q)
+static int fifo_elements_number(const Exynos4210UartFIFO *q)
 {
     if (q->sp < q->rp) {
         return q->size - q->rp + q->sp;
@@ -229,7 +229,7 @@ static int fifo_elements_number(Exynos4210UartFIFO *q)
     return q->sp - q->rp;
 }
 
-static int fifo_empty_elements_number(Exynos4210UartFIFO *q)
+static int fifo_empty_elements_number(const Exynos4210UartFIFO *q)
 {
     return q->size - fifo_elements_number(q);
 }
@@ -245,7 +245,7 @@ static void fifo_reset(Exynos4210UartFIFO *q)
     q->rp = 0;
 }
 
-static uint32_t exynos4210_uart_Tx_FIFO_trigger_level(Exynos4210UartState *s)
+static uint32_t exynos4210_uart_Tx_FIFO_trigger_level(const Exynos4210UartState *s)
 {
     uint32_t level = 0;
     uint32_t reg;
diff --git a/hw/misc/exynos4210_pmu.c b/hw/misc/exynos4210_pmu.c
index e30dbc7d3d..63a8ccd355 100644
--- a/hw/misc/exynos4210_pmu.c
+++ b/hw/misc/exynos4210_pmu.c
@@ -401,8 +401,8 @@ static uint64_t exynos4210_pmu_read(void *opaque, hwaddr offset,
                                     unsigned size)
 {
     Exynos4210PmuState *s = (Exynos4210PmuState *)opaque;
-    unsigned i;
     const Exynos4210PmuReg *reg_p = exynos4210_pmu_regs;
+    unsigned int i;
 
     for (i = 0; i < PMU_NUM_OF_REGISTERS; i++) {
         if (reg_p->offset == offset) {
@@ -420,8 +420,8 @@ static void exynos4210_pmu_write(void *opaque, hwaddr offset,
                                  uint64_t val, unsigned size)
 {
     Exynos4210PmuState *s = (Exynos4210PmuState *)opaque;
-    unsigned i;
     const Exynos4210PmuReg *reg_p = exynos4210_pmu_regs;
+    unsigned int i;
 
     for (i = 0; i < PMU_NUM_OF_REGISTERS; i++) {
         if (reg_p->offset == offset) {
diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c
index d4de8ad9f1..3943187572 100644
--- a/hw/net/cadence_gem.c
+++ b/hw/net/cadence_gem.c
@@ -300,6 +300,8 @@
 #define DESC_1_RX_SOF 0x00004000
 #define DESC_1_RX_EOF 0x00008000
 
+#define GEM_MODID_VALUE 0x00020118
+
 static inline unsigned tx_desc_get_buffer(unsigned *desc)
 {
     return desc[0];
@@ -481,14 +483,17 @@ static int gem_can_receive(NetClientState *nc)
     }
 
     for (i = 0; i < s->num_priority_queues; i++) {
-        if (rx_desc_get_ownership(s->rx_desc[i]) == 1) {
-            if (s->can_rx_state != 2) {
-                s->can_rx_state = 2;
-                DB_PRINT("can't receive - busy buffer descriptor (q%d) 0x%x\n",
-                         i, s->rx_desc_addr[i]);
-             }
-            return 0;
+        if (rx_desc_get_ownership(s->rx_desc[i]) != 1) {
+            break;
+        }
+    };
+
+    if (i == s->num_priority_queues) {
+        if (s->can_rx_state != 2) {
+            s->can_rx_state = 2;
+            DB_PRINT("can't receive - all the buffer descriptors are busy\n");
         }
+        return 0;
     }
 
     if (s->can_rx_state != 0) {
@@ -506,7 +511,18 @@ static void gem_update_int_status(CadenceGEMState *s)
 {
     int i;
 
-    if ((s->num_priority_queues == 1) && s->regs[GEM_ISR]) {
+    if (!s->regs[GEM_ISR]) {
+        /* ISR isn't set, clear all the interrupts */
+        for (i = 0; i < s->num_priority_queues; ++i) {
+            qemu_set_irq(s->irq[i], 0);
+        }
+        return;
+    }
+
+    /* If we get here we know s->regs[GEM_ISR] is set, so we don't need to
+     * check it again.
+     */
+    if (s->num_priority_queues == 1) {
         /* No priority queues, just trigger the interrupt */
         DB_PRINT("asserting int.\n");
         qemu_set_irq(s->irq[0], 1);
@@ -790,8 +806,8 @@ static void gem_get_rx_desc(CadenceGEMState *s, int q)
 {
     DB_PRINT("read descriptor 0x%x\n", (unsigned)s->rx_desc_addr[q]);
     /* read current descriptor */
-    cpu_physical_memory_read(s->rx_desc_addr[0],
-                             (uint8_t *)s->rx_desc[0], sizeof(s->rx_desc[0]));
+    cpu_physical_memory_read(s->rx_desc_addr[q],
+                             (uint8_t *)s->rx_desc[q], sizeof(s->rx_desc[q]));
 
     /* Descriptor owned by software ? */
     if (rx_desc_get_ownership(s->rx_desc[q]) == 1) {
@@ -1209,7 +1225,7 @@ static void gem_reset(DeviceState *d)
     s->regs[GEM_TXPAUSE] = 0x0000ffff;
     s->regs[GEM_TXPARTIALSF] = 0x000003ff;
     s->regs[GEM_RXPARTIALSF] = 0x000003ff;
-    s->regs[GEM_MODID] = 0x00020118;
+    s->regs[GEM_MODID] = s->revision;
     s->regs[GEM_DESCONF] = 0x02500111;
     s->regs[GEM_DESCONF2] = 0x2ab13fff;
     s->regs[GEM_DESCONF5] = 0x002f2145;
@@ -1271,7 +1287,6 @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size)
 {
     CadenceGEMState *s;
     uint32_t retval;
-    int i;
     s = (CadenceGEMState *)opaque;
 
     offset >>= 2;
@@ -1282,9 +1297,7 @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size)
     switch (offset) {
     case GEM_ISR:
         DB_PRINT("lowering irqs on ISR read\n");
-        for (i = 0; i < s->num_priority_queues; ++i) {
-            qemu_set_irq(s->irq[i], 0);
-        }
+        /* The interrupts get updated at the end of the function. */
         break;
     case GEM_PHYMNTNC:
         if (retval & GEM_PHYMNTNC_OP_R) {
@@ -1508,6 +1521,8 @@ static const VMStateDescription vmstate_cadence_gem = {
 
 static Property gem_properties[] = {
     DEFINE_NIC_PROPERTIES(CadenceGEMState, conf),
+    DEFINE_PROP_UINT32("revision", CadenceGEMState, revision,
+                       GEM_MODID_VALUE),
     DEFINE_PROP_UINT8("num-priority-queues", CadenceGEMState,
                       num_priority_queues, 1),
     DEFINE_PROP_UINT8("num-type1-screeners", CadenceGEMState,
diff --git a/hw/timer/exynos4210_mct.c b/hw/timer/exynos4210_mct.c
index 0c189348ae..a2ec3920f8 100644
--- a/hw/timer/exynos4210_mct.c
+++ b/hw/timer/exynos4210_mct.c
@@ -53,6 +53,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
@@ -1372,8 +1373,9 @@ break;
     case L0_TCNTO: case L1_TCNTO:
     case L0_ICNTO: case L1_ICNTO:
     case L0_FRCNTO: case L1_FRCNTO:
-        fprintf(stderr, "\n[exynos4210.mct: write to RO register "
-                TARGET_FMT_plx "]\n\n", offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.mct: write to RO register " TARGET_FMT_plx,
+                      offset);
         break;
 
     case L0_INT_CSTAT: case L1_INT_CSTAT:
diff --git a/hw/timer/exynos4210_pwm.c b/hw/timer/exynos4210_pwm.c
index f5765075c7..87f63f057e 100644
--- a/hw/timer/exynos4210_pwm.c
+++ b/hw/timer/exynos4210_pwm.c
@@ -21,6 +21,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "qemu-common.h"
@@ -252,9 +253,9 @@ static uint64_t exynos4210_pwm_read(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.pwm: bad read offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.pwm: bad read offset " TARGET_FMT_plx,
+                      offset);
         break;
     }
     return value;
@@ -343,9 +344,9 @@ static void exynos4210_pwm_write(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.pwm: bad write offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.pwm: bad write offset " TARGET_FMT_plx,
+                      offset);
         break;
 
     }
diff --git a/hw/timer/exynos4210_rtc.c b/hw/timer/exynos4210_rtc.c
index 1a648c5d9e..4607833e3e 100644
--- a/hw/timer/exynos4210_rtc.c
+++ b/hw/timer/exynos4210_rtc.c
@@ -26,6 +26,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "hw/sysbus.h"
 #include "qemu/timer.h"
 #include "qemu-common.h"
@@ -370,9 +371,9 @@ static uint64_t exynos4210_rtc_read(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.rtc: bad read offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.rtc: bad read offset " TARGET_FMT_plx,
+                      offset);
         break;
     }
     return value;
@@ -433,9 +434,9 @@ static void exynos4210_rtc_write(void *opaque, hwaddr offset,
         if (value > TICNT_THRESHOLD) {
             s->reg_ticcnt = value;
         } else {
-            fprintf(stderr,
-                    "[exynos4210.rtc: bad TICNT value %u ]\n",
-                    (uint32_t)value);
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "exynos4210.rtc: bad TICNT value %u",
+                          (uint32_t)value);
         }
         break;
 
@@ -500,9 +501,9 @@ static void exynos4210_rtc_write(void *opaque, hwaddr offset,
         break;
 
     default:
-        fprintf(stderr,
-                "[exynos4210.rtc: bad write offset " TARGET_FMT_plx "]\n",
-                offset);
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "exynos4210.rtc: bad write offset " TARGET_FMT_plx,
+                      offset);
         break;
 
     }
diff --git a/include/hw/net/cadence_gem.h b/include/hw/net/cadence_gem.h
index c469ffe69b..35de622063 100644
--- a/include/hw/net/cadence_gem.h
+++ b/include/hw/net/cadence_gem.h
@@ -50,6 +50,7 @@ typedef struct CadenceGEMState {
     uint8_t num_priority_queues;
     uint8_t num_type1_screeners;
     uint8_t num_type2_screeners;
+    uint32_t revision;
 
     /* GEM registers backing store */
     uint32_t regs[CADENCE_GEM_MAXREG];
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 04b062cb7e..b357aee778 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -304,33 +304,6 @@ bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 }
 
 #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
-static void arm_v7m_unassigned_access(CPUState *cpu, hwaddr addr,
-                                      bool is_write, bool is_exec, int opaque,
-                                      unsigned size)
-{
-    ARMCPU *arm = ARM_CPU(cpu);
-    CPUARMState *env = &arm->env;
-
-    /* ARMv7-M interrupt return works by loading a magic value into the PC.
-     * On real hardware the load causes the return to occur.  The qemu
-     * implementation performs the jump normally, then does the exception
-     * return by throwing a special exception when when the CPU tries to
-     * execute code at the magic address.
-     */
-    if (env->v7m.exception != 0 && addr >= 0xfffffff0 && is_exec) {
-        cpu->exception_index = EXCP_EXCEPTION_EXIT;
-        cpu_loop_exit(cpu);
-    }
-
-    /* In real hardware an attempt to access parts of the address space
-     * with nothing there will usually cause an external abort.
-     * However our QEMU board models are often missing device models where
-     * the guest can boot anyway with the default read-as-zero/writes-ignored
-     * behaviour that you get without a QEMU unassigned_access hook.
-     * So just return here to retain that default behaviour.
-     */
-}
-
 static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 {
     CPUClass *cc = CPU_GET_CLASS(cs);
@@ -338,17 +311,7 @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
     CPUARMState *env = &cpu->env;
     bool ret = false;
 
-    /* ARMv7-M interrupt return works by loading a magic value
-     * into the PC.  On real hardware the load causes the
-     * return to occur.  The qemu implementation performs the
-     * jump normally, then does the exception return when the
-     * CPU tries to execute code at the magic address.
-     * This will cause the magic PC value to be pushed to
-     * the stack if an interrupt occurred at the wrong time.
-     * We avoid this by disabling interrupts when
-     * pc contains a magic address.
-     *
-     * ARMv7-M interrupt masking works differently than -A or -R.
+    /* ARMv7-M interrupt masking works differently than -A or -R.
      * There is no FIQ/IRQ distinction. Instead of I and F bits
      * masking FIQ and IRQ interrupts, an exception is taken only
      * if it is higher priority than the current execution priority
@@ -356,8 +319,7 @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
      * currently active exception).
      */
     if (interrupt_request & CPU_INTERRUPT_HARD
-        && (armv7m_nvic_can_take_pending_exception(env->nvic))
-        && (env->regs[15] < 0xfffffff0)) {
+        && (armv7m_nvic_can_take_pending_exception(env->nvic))) {
         cs->exception_index = EXCP_IRQ;
         cc->do_interrupt(cs);
         ret = true;
@@ -1091,7 +1053,6 @@ static void arm_v7m_class_init(ObjectClass *oc, void *data)
     cc->do_interrupt = arm_v7m_cpu_do_interrupt;
 #endif
 
-    cc->do_unassigned_access = arm_v7m_unassigned_access;
     cc->cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt;
 }
 
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index a8aabce7dd..1055bfef3d 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -58,6 +58,7 @@
 #define EXCP_SEMIHOST       16   /* semihosting call */
 #define EXCP_NOCP           17   /* v7M NOCP UsageFault */
 #define EXCP_INVSTATE       18   /* v7M INVSTATE UsageFault */
+/* NB: add new EXCP_ defines to the array in arm_log_exception() too */
 
 #define ARMV7M_EXCP_RESET   1
 #define ARMV7M_EXCP_NMI     2
@@ -2290,6 +2291,9 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env)
 #define ARM_TBFLAG_NS_MASK          (1 << ARM_TBFLAG_NS_SHIFT)
 #define ARM_TBFLAG_BE_DATA_SHIFT    20
 #define ARM_TBFLAG_BE_DATA_MASK     (1 << ARM_TBFLAG_BE_DATA_SHIFT)
+/* For M profile only, Handler (ie not Thread) mode */
+#define ARM_TBFLAG_HANDLER_SHIFT    21
+#define ARM_TBFLAG_HANDLER_MASK     (1 << ARM_TBFLAG_HANDLER_SHIFT)
 
 /* Bit usage when in AArch64 state */
 #define ARM_TBFLAG_TBI0_SHIFT 0        /* TBI0 for EL0/1 or TBI for EL2/3 */
@@ -2326,6 +2330,8 @@ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env)
     (((F) & ARM_TBFLAG_NS_MASK) >> ARM_TBFLAG_NS_SHIFT)
 #define ARM_TBFLAG_BE_DATA(F) \
     (((F) & ARM_TBFLAG_BE_DATA_MASK) >> ARM_TBFLAG_BE_DATA_SHIFT)
+#define ARM_TBFLAG_HANDLER(F) \
+    (((F) & ARM_TBFLAG_HANDLER_MASK) >> ARM_TBFLAG_HANDLER_SHIFT)
 #define ARM_TBFLAG_TBI0(F) \
     (((F) & ARM_TBFLAG_TBI0_MASK) >> ARM_TBFLAG_TBI0_SHIFT)
 #define ARM_TBFLAG_TBI1(F) \
@@ -2516,6 +2522,10 @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
     }
     *flags |= fp_exception_el(env) << ARM_TBFLAG_FPEXC_EL_SHIFT;
 
+    if (env->v7m.exception != 0) {
+        *flags |= ARM_TBFLAG_HANDLER_MASK;
+    }
+
     *cs_base = 0;
 }
 
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 8cb7a9451c..8a3e4480aa 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -6271,6 +6271,25 @@ static void arm_log_exception(int idx)
 {
     if (qemu_loglevel_mask(CPU_LOG_INT)) {
         const char *exc = NULL;
+        static const char * const excnames[] = {
+            [EXCP_UDEF] = "Undefined Instruction",
+            [EXCP_SWI] = "SVC",
+            [EXCP_PREFETCH_ABORT] = "Prefetch Abort",
+            [EXCP_DATA_ABORT] = "Data Abort",
+            [EXCP_IRQ] = "IRQ",
+            [EXCP_FIQ] = "FIQ",
+            [EXCP_BKPT] = "Breakpoint",
+            [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit",
+            [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage",
+            [EXCP_HVC] = "Hypervisor Call",
+            [EXCP_HYP_TRAP] = "Hypervisor Trap",
+            [EXCP_SMC] = "Secure Monitor Call",
+            [EXCP_VIRQ] = "Virtual IRQ",
+            [EXCP_VFIQ] = "Virtual FIQ",
+            [EXCP_SEMIHOST] = "Semihosting call",
+            [EXCP_NOCP] = "v7M NOCP UsageFault",
+            [EXCP_INVSTATE] = "v7M INVSTATE UsageFault",
+        };
 
         if (idx >= 0 && idx < ARRAY_SIZE(excnames)) {
             exc = excnames[idx];
diff --git a/target/arm/internals.h b/target/arm/internals.h
index f742a419ff..1f6efef7c4 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -51,27 +51,6 @@ static inline bool excp_is_internal(int excp)
         || excp == EXCP_SEMIHOST;
 }
 
-/* Exception names for debug logging; note that not all of these
- * precisely correspond to architectural exceptions.
- */
-static const char * const excnames[] = {
-    [EXCP_UDEF] = "Undefined Instruction",
-    [EXCP_SWI] = "SVC",
-    [EXCP_PREFETCH_ABORT] = "Prefetch Abort",
-    [EXCP_DATA_ABORT] = "Data Abort",
-    [EXCP_IRQ] = "IRQ",
-    [EXCP_FIQ] = "FIQ",
-    [EXCP_BKPT] = "Breakpoint",
-    [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit",
-    [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage",
-    [EXCP_HVC] = "Hypervisor Call",
-    [EXCP_HYP_TRAP] = "Hypervisor Trap",
-    [EXCP_SMC] = "Secure Monitor Call",
-    [EXCP_VIRQ] = "Virtual IRQ",
-    [EXCP_VFIQ] = "Virtual FIQ",
-    [EXCP_SEMIHOST] = "Semihosting call",
-};
-
 /* Scale factor for generic timers, ie number of ns per tick.
  * This gives a 62.5MHz timer.
  */
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
index 61111091ad..a16abc8d12 100644
--- a/target/arm/kvm64.c
+++ b/target/arm/kvm64.c
@@ -940,7 +940,7 @@ bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit)
              * single step at this point so something has gone wrong.
              */
             error_report("%s: guest single-step while debugging unsupported"
-                         " (%"PRIx64", %"PRIx32")\n",
+                         " (%"PRIx64", %"PRIx32")",
                          __func__, env->pc, debug_exit->hsr);
             return false;
         }
@@ -965,7 +965,7 @@ bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit)
         break;
     }
     default:
-        error_report("%s: unhandled debug exit (%"PRIx32", %"PRIx64")\n",
+        error_report("%s: unhandled debug exit (%"PRIx32", %"PRIx64")",
                      __func__, debug_exit->hsr, env->pc);
     }
 
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index d64c8670fa..156b825040 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -130,7 +130,7 @@ void tlb_fill(CPUState *cs, target_ulong addr, MMUAccessType access_type,
     if (unlikely(ret)) {
         ARMCPU *cpu = ARM_CPU(cs);
         CPUARMState *env = &cpu->env;
-        uint32_t syn, exc;
+        uint32_t syn, exc, fsc;
         unsigned int target_el;
         bool same_el;
 
@@ -145,19 +145,32 @@ void tlb_fill(CPUState *cs, target_ulong addr, MMUAccessType access_type,
             env->cp15.hpfar_el2 = extract64(fi.s2addr, 12, 47) << 4;
         }
         same_el = arm_current_el(env) == target_el;
-        /* AArch64 syndrome does not have an LPAE bit */
-        syn = fsr & ~(1 << 9);
+
+        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. Check that here,
+             * and 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;
+        }
 
         /* For insn and data aborts we assume there is no instruction syndrome
          * information; this is always true for exceptions reported to EL1.
          */
         if (access_type == MMU_INST_FETCH) {
-            syn = syn_insn_abort(same_el, 0, fi.s1ptw, syn);
+            syn = syn_insn_abort(same_el, 0, fi.s1ptw, fsc);
             exc = EXCP_PREFETCH_ABORT;
         } else {
             syn = merge_syn_data_abort(env->exception.syndrome, target_el,
                                        same_el, fi.s1ptw,
-                                       access_type == MMU_DATA_STORE, syn);
+                                       access_type == MMU_DATA_STORE, fsc);
             if (access_type == MMU_DATA_STORE
                 && arm_feature(env, ARM_FEATURE_V6)) {
                 fsr |= (1 << 11);
diff --git a/target/arm/translate.c b/target/arm/translate.c
index e32e38cadd..0b5a0bca06 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -296,6 +296,30 @@ static void gen_step_complete_exception(DisasContext *s)
     s->is_jmp = DISAS_EXC;
 }
 
+static void gen_singlestep_exception(DisasContext *s)
+{
+    /* Generate the right kind of exception for singlestep, which is
+     * either the architectural singlestep or EXCP_DEBUG for QEMU's
+     * gdb singlestepping.
+     */
+    if (s->ss_active) {
+        gen_step_complete_exception(s);
+    } else {
+        gen_exception_internal(EXCP_DEBUG);
+    }
+}
+
+static inline bool is_singlestepping(DisasContext *s)
+{
+    /* Return true if we are singlestepping either because of
+     * architectural singlestep or QEMU gdbstub singlestep. This does
+     * not include the command line '-singlestep' mode which is rather
+     * misnamed as it only means "one instruction per TB" and doesn't
+     * affect the code we generate.
+     */
+    return s->singlestep_enabled || s->ss_active;
+}
+
 static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b)
 {
     TCGv_i32 tmp1 = tcg_temp_new_i32();
@@ -880,6 +904,21 @@ static const uint8_t table_logic_cc[16] = {
     1, /* mvn */
 };
 
+static inline void gen_set_condexec(DisasContext *s)
+{
+    if (s->condexec_mask) {
+        uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1);
+        TCGv_i32 tmp = tcg_temp_new_i32();
+        tcg_gen_movi_i32(tmp, val);
+        store_cpu_field(tmp, condexec_bits);
+    }
+}
+
+static inline void gen_set_pc_im(DisasContext *s, target_ulong val)
+{
+    tcg_gen_movi_i32(cpu_R[15], val);
+}
+
 /* Set PC and Thumb state from an immediate address.  */
 static inline void gen_bx_im(DisasContext *s, uint32_t addr)
 {
@@ -904,6 +943,51 @@ static inline void gen_bx(DisasContext *s, TCGv_i32 var)
     store_cpu_field(var, thumb);
 }
 
+/* Set PC and Thumb state from var. var is marked as dead.
+ * For M-profile CPUs, include logic to detect exception-return
+ * branches and handle them. This is needed for Thumb POP/LDM to PC, LDR to PC,
+ * and BX reg, and no others, and happens only for code in Handler mode.
+ */
+static inline void gen_bx_excret(DisasContext *s, TCGv_i32 var)
+{
+    /* Generate the same code here as for a simple bx, but flag via
+     * s->is_jmp that we need to do the rest of the work later.
+     */
+    gen_bx(s, var);
+    if (s->v7m_handler_mode && arm_dc_feature(s, ARM_FEATURE_M)) {
+        s->is_jmp = DISAS_BX_EXCRET;
+    }
+}
+
+static inline void gen_bx_excret_final_code(DisasContext *s)
+{
+    /* Generate the code to finish possible exception return and end the TB */
+    TCGLabel *excret_label = gen_new_label();
+
+    /* Is the new PC value in the magic range indicating exception return? */
+    tcg_gen_brcondi_i32(TCG_COND_GEU, cpu_R[15], 0xff000000, excret_label);
+    /* No: end the TB as we would for a DISAS_JMP */
+    if (is_singlestepping(s)) {
+        gen_singlestep_exception(s);
+    } else {
+        tcg_gen_exit_tb(0);
+    }
+    gen_set_label(excret_label);
+    /* Yes: this is an exception return.
+     * At this point in runtime env->regs[15] and env->thumb will hold
+     * the exception-return magic number, which do_v7m_exception_exit()
+     * will read. Nothing else will be able to see those values because
+     * the cpu-exec main loop guarantees that we will always go straight
+     * from raising the exception to the exception-handling code.
+     *
+     * gen_ss_advance(s) does nothing on M profile currently but
+     * calling it is conceptually the right thing as we have executed
+     * this instruction (compare SWI, HVC, SMC handling).
+     */
+    gen_ss_advance(s);
+    gen_exception_internal(EXCP_EXCEPTION_EXIT);
+}
+
 /* Variant of store_reg which uses branch&exchange logic when storing
    to r15 in ARM architecture v7 and above. The source must be a temporary
    and will be marked as dead. */
@@ -923,7 +1007,7 @@ static inline void store_reg_bx(DisasContext *s, int reg, TCGv_i32 var)
 static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var)
 {
     if (reg == 15 && ENABLE_ARCH_5) {
-        gen_bx(s, var);
+        gen_bx_excret(s, var);
     } else {
         store_reg(s, reg, var);
     }
@@ -1056,11 +1140,6 @@ DO_GEN_ST(8, MO_UB)
 DO_GEN_ST(16, MO_UW)
 DO_GEN_ST(32, MO_UL)
 
-static inline void gen_set_pc_im(DisasContext *s, target_ulong val)
-{
-    tcg_gen_movi_i32(cpu_R[15], val);
-}
-
 static inline void gen_hvc(DisasContext *s, int imm16)
 {
     /* The pre HVC helper handles cases when HVC gets trapped
@@ -1094,17 +1173,6 @@ static inline void gen_smc(DisasContext *s)
     s->is_jmp = DISAS_SMC;
 }
 
-static inline void
-gen_set_condexec (DisasContext *s)
-{
-    if (s->condexec_mask) {
-        uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1);
-        TCGv_i32 tmp = tcg_temp_new_i32();
-        tcg_gen_movi_i32(tmp, val);
-        store_cpu_field(tmp, condexec_bits);
-    }
-}
-
 static void gen_exception_internal_insn(DisasContext *s, int offset, int excp)
 {
     gen_set_condexec(s);
@@ -4092,7 +4160,7 @@ static inline void gen_goto_tb(DisasContext *s, int n, target_ulong dest)
 
 static inline void gen_jmp (DisasContext *s, uint32_t dest)
 {
-    if (unlikely(s->singlestep_enabled || s->ss_active)) {
+    if (unlikely(is_singlestepping(s))) {
         /* An indirect jump so that we still trigger the debug exception.  */
         if (s->thumb)
             dest |= 1;
@@ -9858,7 +9926,7 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                         tmp = tcg_temp_new_i32();
                         gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
                         if (i == 15) {
-                            gen_bx(s, tmp);
+                            gen_bx_excret(s, tmp);
                         } else if (i == rn) {
                             loaded_var = tmp;
                             loaded_base = 1;
@@ -9959,7 +10027,7 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
             gen_arm_shift_reg(tmp, op, tmp2, logic_cc);
             if (logic_cc)
                 gen_logic_CC(tmp);
-            store_reg_bx(s, rd, tmp);
+            store_reg(s, rd, tmp);
             break;
         case 1: /* Sign/zero extend.  */
             op = (insn >> 20) & 7;
@@ -10485,7 +10553,12 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                         }
                         break;
                     case 4: /* bxj */
-                        /* Trivial implementation equivalent to bx.  */
+                        /* Trivial implementation equivalent to bx.
+                         * This instruction doesn't exist at all for M-profile.
+                         */
+                        if (arm_dc_feature(s, ARM_FEATURE_M)) {
+                            goto illegal_op;
+                        }
                         tmp = load_reg(s, rn);
                         gen_bx(s, tmp);
                         break;
@@ -10885,7 +10958,7 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                 goto illegal_op;
             }
             if (rs == 15) {
-                gen_bx(s, tmp);
+                gen_bx_excret(s, tmp);
             } else {
                 store_reg(s, rs, tmp);
             }
@@ -11075,9 +11148,11 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
                     tmp2 = tcg_temp_new_i32();
                     tcg_gen_movi_i32(tmp2, val);
                     store_reg(s, 14, tmp2);
+                    gen_bx(s, tmp);
+                } else {
+                    /* Only BX works as exception-return, not BLX */
+                    gen_bx_excret(s, tmp);
                 }
-                /* already thumb, no need to check */
-                gen_bx(s, tmp);
                 break;
             }
             break;
@@ -11752,6 +11827,7 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
     dc->vec_len = ARM_TBFLAG_VECLEN(tb->flags);
     dc->vec_stride = ARM_TBFLAG_VECSTRIDE(tb->flags);
     dc->c15_cpar = ARM_TBFLAG_XSCALE_CPAR(tb->flags);
+    dc->v7m_handler_mode = ARM_TBFLAG_HANDLER(tb->flags);
     dc->cp_regs = cpu->cp_regs;
     dc->features = env->features;
 
@@ -11851,14 +11927,6 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
             dc->is_jmp = DISAS_EXC;
             break;
         }
-#else
-        if (arm_dc_feature(dc, ARM_FEATURE_M)) {
-            /* Branches to the magic exception-return addresses should
-             * already have been caught via the arm_v7m_unassigned_access hook,
-             * and never get here.
-             */
-            assert(dc->pc < 0xfffffff0);
-        }
 #endif
 
         if (unlikely(!QTAILQ_EMPTY(&cs->breakpoints))) {
@@ -11953,9 +12021,8 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
             ((dc->pc >= next_page_start - 3) && insn_crosses_page(env, dc));
 
     } while (!dc->is_jmp && !tcg_op_buf_full() &&
-             !cs->singlestep_enabled &&
+             !is_singlestepping(dc) &&
              !singlestep &&
-             !dc->ss_active &&
              !end_of_page &&
              num_insns < max_insns);
 
@@ -11971,9 +12038,16 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
     /* At this stage dc->condjmp will only be set when the skipped
        instruction was a conditional branch or trap, and the PC has
        already been written.  */
-    if (unlikely(cs->singlestep_enabled || dc->ss_active)) {
+    gen_set_condexec(dc);
+    if (dc->is_jmp == DISAS_BX_EXCRET) {
+        /* Exception return branches need some special case code at the
+         * end of the TB, which is complex enough that it has to
+         * handle the single-step vs not and the condition-failed
+         * insn codepath itself.
+         */
+        gen_bx_excret_final_code(dc);
+    } else if (unlikely(is_singlestepping(dc))) {
         /* Unconditional and "condition passed" instruction codepath. */
-        gen_set_condexec(dc);
         switch (dc->is_jmp) {
         case DISAS_SWI:
             gen_ss_advance(dc);
@@ -11993,24 +12067,8 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
             gen_set_pc_im(dc, dc->pc);
             /* fall through */
         default:
-            if (dc->ss_active) {
-                gen_step_complete_exception(dc);
-            } else {
-                /* FIXME: Single stepping a WFI insn will not halt
-                   the CPU.  */
-                gen_exception_internal(EXCP_DEBUG);
-            }
-        }
-        if (dc->condjmp) {
-            /* "Condition failed" instruction codepath. */
-            gen_set_label(dc->condlabel);
-            gen_set_condexec(dc);
-            gen_set_pc_im(dc, dc->pc);
-            if (dc->ss_active) {
-                gen_step_complete_exception(dc);
-            } else {
-                gen_exception_internal(EXCP_DEBUG);
-            }
+            /* FIXME: Single stepping a WFI insn will not halt the CPU. */
+            gen_singlestep_exception(dc);
         }
     } else {
         /* While branches must always occur at the end of an IT block,
@@ -12021,7 +12079,6 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
             - Hardware watchpoints.
            Hardware breakpoints have already been handled and skip this code.
          */
-        gen_set_condexec(dc);
         switch(dc->is_jmp) {
         case DISAS_NEXT:
             gen_goto_tb(dc, 1, dc->pc);
@@ -12061,11 +12118,17 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
             gen_exception(EXCP_SMC, syn_aa32_smc(), 3);
             break;
         }
-        if (dc->condjmp) {
-            gen_set_label(dc->condlabel);
-            gen_set_condexec(dc);
+    }
+
+    if (dc->condjmp) {
+        /* "Condition failed" instruction codepath for the branch/trap insn */
+        gen_set_label(dc->condlabel);
+        gen_set_condexec(dc);
+        if (unlikely(is_singlestepping(dc))) {
+            gen_set_pc_im(dc, dc->pc);
+            gen_singlestep_exception(dc);
+        } else {
             gen_goto_tb(dc, 1, dc->pc);
-            dc->condjmp = 0;
         }
     }
 
diff --git a/target/arm/translate.h b/target/arm/translate.h
index abb0760158..629dab945e 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -31,6 +31,7 @@ typedef struct DisasContext {
     bool vfp_enabled; /* FP enabled via FPSCR.EN */
     int vec_len;
     int vec_stride;
+    bool v7m_handler_mode;
     /* Immediate value in AArch32 SVC insn; must be set if is_jmp == DISAS_SWI
      * so that top level loop can generate correct syndrome information.
      */
@@ -134,6 +135,10 @@ static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn)
 #define DISAS_HVC 8
 #define DISAS_SMC 9
 #define DISAS_YIELD 10
+/* M profile branch which might be an exception return (and so needs
+ * custom end-of-TB code)
+ */
+#define DISAS_BX_EXCRET 11
 
 #ifdef TARGET_AARCH64
 void a64_translate_init(void);