diff --git a/configure b/configure
index 681abfc669..9ac2600230 100755
--- a/configure
+++ b/configure
@@ -5028,7 +5028,7 @@ case "$target_name" in
   aarch64)
     TARGET_BASE_ARCH=arm
     bflt="yes"
-    gdb_xml_files="aarch64-core.xml aarch64-fpu.xml"
+    gdb_xml_files="aarch64-core.xml aarch64-fpu.xml arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml"
   ;;
   cris)
   ;;
diff --git a/hw/display/blizzard.c b/hw/display/blizzard.c
index 55c0ddf00b..92b1fac563 100644
--- a/hw/display/blizzard.c
+++ b/hw/display/blizzard.c
@@ -134,14 +134,6 @@ static const int blizzard_iformat_bpp[0x10] = {
     0, 0, 0, 0, 0, 0,
 };
 
-static inline void blizzard_rgb2yuv(int r, int g, int b,
-                int *y, int *u, int *v)
-{
-    *y = 0x10 + ((0x838 * r + 0x1022 * g + 0x322 * b) >> 13);
-    *u = 0x80 + ((0xe0e * b - 0x04c1 * r - 0x94e * g) >> 13);
-    *v = 0x80 + ((0xe0e * r - 0x0bc7 * g - 0x247 * b) >> 13);
-}
-
 static void blizzard_window(BlizzardState *s)
 {
     DisplaySurface *surface = qemu_console_surface(s->con);
diff --git a/hw/display/pxa2xx_lcd.c b/hw/display/pxa2xx_lcd.c
index 611fb174cd..ac3c018822 100644
--- a/hw/display/pxa2xx_lcd.c
+++ b/hw/display/pxa2xx_lcd.c
@@ -279,14 +279,6 @@ static inline void pxa2xx_dma_ber_set(PXA2xxLCDState *s, int ch)
         s->liidr = s->dma_ch[ch].id;
 }
 
-/* Set Read Status interrupt high and poke associated registers */
-static inline void pxa2xx_dma_rdst_set(PXA2xxLCDState *s)
-{
-    s->status[0] |= LCSR0_RDST;
-    if (s->irqlevel && !(s->control[0] & LCCR0_RDSTM))
-        s->status[0] |= LCSR0_SINT;
-}
-
 /* Load new Frame Descriptors from DMA */
 static void pxa2xx_descriptor_load(PXA2xxLCDState *s)
 {
diff --git a/hw/input/tsc210x.c b/hw/input/tsc210x.c
index aa5b6886ea..fae3385636 100644
--- a/hw/input/tsc210x.c
+++ b/hw/input/tsc210x.c
@@ -215,36 +215,6 @@ typedef struct {
     int fsref;
 } TSC210xRateInfo;
 
-/*  { rate,  dsor,  fsref } */
-static const TSC210xRateInfo tsc2101_rates[] = {
-    /* Fsref / 6.0 */
-    { 7350,	7,	1 },
-    { 8000,	7,	0 },
-    /* Fsref / 5.5 */
-    { 8018,	6,	1 },
-    { 8727,	6,	0 },
-    /* Fsref / 5.0 */
-    { 8820,	5,	1 },
-    { 9600,	5,	0 },
-    /* Fsref / 4.0 */
-    { 11025,	4,	1 },
-    { 12000,	4,	0 },
-    /* Fsref / 3.0 */
-    { 14700,	3,	1 },
-    { 16000,	3,	0 },
-    /* Fsref / 2.0 */
-    { 22050,	2,	1 },
-    { 24000,	2,	0 },
-    /* Fsref / 1.5 */
-    { 29400,	1,	1 },
-    { 32000,	1,	0 },
-    /* Fsref */
-    { 44100,	0,	1 },
-    { 48000,	0,	0 },
-
-    { 0,	0, 	0 },
-};
-
 /*  { rate,   dsor, fsref }	*/
 static const TSC210xRateInfo tsc2102_rates[] = {
     /* Fsref / 6.0 */
diff --git a/hw/intc/imx_avic.c b/hw/intc/imx_avic.c
index ec5f9ad815..e48f66c8fa 100644
--- a/hw/intc/imx_avic.c
+++ b/hw/intc/imx_avic.c
@@ -97,15 +97,6 @@ static inline int imx_avic_prio(IMXAVICState *s, int irq)
     return 0xf & (s->prio[word] >> part);
 }
 
-static inline void imx_avic_set_prio(IMXAVICState *s, int irq, int prio)
-{
-    uint32_t word = irq / PRIO_PER_WORD;
-    uint32_t part = 4 * (irq % PRIO_PER_WORD);
-    uint32_t mask = ~(0xf << part);
-    s->prio[word] &= mask;
-    s->prio[word] |= prio << part;
-}
-
 /* Update interrupts.  */
 static void imx_avic_update(IMXAVICState *s)
 {
diff --git a/target-arm/cpu.c b/target-arm/cpu.c
index 407f977742..8ab6d9532e 100644
--- a/target-arm/cpu.c
+++ b/target-arm/cpu.c
@@ -41,7 +41,9 @@ static void arm_cpu_set_pc(CPUState *cs, vaddr value)
 static bool arm_cpu_has_work(CPUState *cs)
 {
     return cs->interrupt_request &
-        (CPU_INTERRUPT_FIQ | CPU_INTERRUPT_HARD | CPU_INTERRUPT_EXITTB);
+        (CPU_INTERRUPT_FIQ | CPU_INTERRUPT_HARD
+         | CPU_INTERRUPT_VFIQ | CPU_INTERRUPT_VIRQ
+         | CPU_INTERRUPT_EXITTB);
 }
 
 static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque)
@@ -173,11 +175,6 @@ static void arm_cpu_reset(CPUState *s)
     set_float_detect_tininess(float_tininess_before_rounding,
                               &env->vfp.standard_fp_status);
     tlb_flush(s, 1);
-    /* Reset is a state change for some CPUARMState fields which we
-     * bake assumptions about into translated code, so we need to
-     * tb_flush().
-     */
-    tb_flush(env);
 
 #ifndef CONFIG_USER_ONLY
     if (kvm_enabled()) {
@@ -185,18 +182,17 @@ static void arm_cpu_reset(CPUState *s)
     }
 #endif
 
+    hw_breakpoint_update_all(cpu);
     hw_watchpoint_update_all(cpu);
 }
 
 bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 {
     CPUClass *cc = CPU_GET_CLASS(cs);
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
     bool ret = false;
 
     if (interrupt_request & CPU_INTERRUPT_FIQ
-        && !(env->daif & PSTATE_F)) {
+        && arm_excp_unmasked(cs, EXCP_FIQ)) {
         cs->exception_index = EXCP_FIQ;
         cc->do_interrupt(cs);
         ret = true;
@@ -211,12 +207,23 @@ bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
        We avoid this by disabling interrupts when
        pc contains a magic address.  */
     if (interrupt_request & CPU_INTERRUPT_HARD
-        && !(env->daif & PSTATE_I)
-        && (!IS_M(env) || env->regs[15] < 0xfffffff0)) {
+        && arm_excp_unmasked(cs, EXCP_IRQ)) {
         cs->exception_index = EXCP_IRQ;
         cc->do_interrupt(cs);
         ret = true;
     }
+    if (interrupt_request & CPU_INTERRUPT_VIRQ
+        && arm_excp_unmasked(cs, EXCP_VIRQ)) {
+        cs->exception_index = EXCP_VIRQ;
+        cc->do_interrupt(cs);
+        ret = true;
+    }
+    if (interrupt_request & CPU_INTERRUPT_VFIQ
+        && arm_excp_unmasked(cs, EXCP_VFIQ)) {
+        cs->exception_index = EXCP_VFIQ;
+        cc->do_interrupt(cs);
+        ret = true;
+    }
 
     return ret;
 }
@@ -225,21 +232,29 @@ bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 static void arm_cpu_set_irq(void *opaque, int irq, int level)
 {
     ARMCPU *cpu = opaque;
+    CPUARMState *env = &cpu->env;
     CPUState *cs = CPU(cpu);
+    static const int mask[] = {
+        [ARM_CPU_IRQ] = CPU_INTERRUPT_HARD,
+        [ARM_CPU_FIQ] = CPU_INTERRUPT_FIQ,
+        [ARM_CPU_VIRQ] = CPU_INTERRUPT_VIRQ,
+        [ARM_CPU_VFIQ] = CPU_INTERRUPT_VFIQ
+    };
 
     switch (irq) {
-    case ARM_CPU_IRQ:
-        if (level) {
-            cpu_interrupt(cs, CPU_INTERRUPT_HARD);
-        } else {
-            cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
+    case ARM_CPU_VIRQ:
+    case ARM_CPU_VFIQ:
+        if (!arm_feature(env, ARM_FEATURE_EL2)) {
+            hw_error("%s: Virtual interrupt line %d with no EL2 support\n",
+                     __func__, irq);
         }
-        break;
+        /* fall through */
+    case ARM_CPU_IRQ:
     case ARM_CPU_FIQ:
         if (level) {
-            cpu_interrupt(cs, CPU_INTERRUPT_FIQ);
+            cpu_interrupt(cs, mask[irq]);
         } else {
-            cpu_reset_interrupt(cs, CPU_INTERRUPT_FIQ);
+            cpu_reset_interrupt(cs, mask[irq]);
         }
         break;
     default:
@@ -289,9 +304,12 @@ static void arm_cpu_initfn(Object *obj)
 #ifndef CONFIG_USER_ONLY
     /* Our inbound IRQ and FIQ lines */
     if (kvm_enabled()) {
-        qdev_init_gpio_in(DEVICE(cpu), arm_cpu_kvm_set_irq, 2);
+        /* VIRQ and VFIQ are unused with KVM but we add them to maintain
+         * the same interface as non-KVM CPUs.
+         */
+        qdev_init_gpio_in(DEVICE(cpu), arm_cpu_kvm_set_irq, 4);
     } else {
-        qdev_init_gpio_in(DEVICE(cpu), arm_cpu_set_irq, 2);
+        qdev_init_gpio_in(DEVICE(cpu), arm_cpu_set_irq, 4);
     }
 
     cpu->gt_timer[GTIMER_PHYS] = timer_new(QEMU_CLOCK_VIRTUAL, GTIMER_SCALE,
diff --git a/target-arm/cpu.h b/target-arm/cpu.h
index d1e1ccb605..65a3417951 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -51,6 +51,11 @@
 #define EXCP_EXCEPTION_EXIT  8   /* Return from v7M exception.  */
 #define EXCP_KERNEL_TRAP     9   /* Jumped to kernel code page.  */
 #define EXCP_STREX          10
+#define EXCP_HVC            11   /* HyperVisor Call */
+#define EXCP_HYP_TRAP       12
+#define EXCP_SMC            13   /* Secure Monitor Call */
+#define EXCP_VIRQ           14
+#define EXCP_VFIQ           15
 
 #define ARMV7M_EXCP_RESET   1
 #define ARMV7M_EXCP_NMI     2
@@ -65,6 +70,8 @@
 
 /* ARM-specific interrupt pending bits.  */
 #define CPU_INTERRUPT_FIQ   CPU_INTERRUPT_TGT_EXT_1
+#define CPU_INTERRUPT_VIRQ  CPU_INTERRUPT_TGT_EXT_2
+#define CPU_INTERRUPT_VFIQ  CPU_INTERRUPT_TGT_EXT_3
 
 /* The usual mapping for an AArch64 system register to its AArch32
  * counterpart is for the 32 bit world to have access to the lower
@@ -80,9 +87,11 @@
 #define offsetofhigh32(S, M) (offsetof(S, M) + sizeof(uint32_t))
 #endif
 
-/* Meanings of the ARMCPU object's two inbound GPIO lines */
+/* Meanings of the ARMCPU object's four inbound GPIO lines */
 #define ARM_CPU_IRQ 0
 #define ARM_CPU_FIQ 1
+#define ARM_CPU_VIRQ 2
+#define ARM_CPU_VFIQ 3
 
 typedef void ARMWriteCPFunc(void *opaque, int cp_info,
                             int srcreg, int operand, uint32_t value);
@@ -172,7 +181,6 @@ typedef struct CPUARMState {
         uint64_t c1_sys; /* System control register.  */
         uint64_t c1_coproc; /* Coprocessor access register.  */
         uint32_t c1_xscaleauxcr; /* XScale auxiliary control register.  */
-        uint32_t c1_scr; /* secure config register.  */
         uint64_t ttbr0_el1; /* MMU translation table base 0. */
         uint64_t ttbr1_el1; /* MMU translation table base 1. */
         uint64_t c2_control; /* MMU translation table base control.  */
@@ -184,6 +192,8 @@ typedef struct CPUARMState {
                         MPU write buffer control.  */
         uint32_t pmsav5_data_ap; /* PMSAv5 MPU data access permissions */
         uint32_t pmsav5_insn_ap; /* PMSAv5 MPU insn access permissions */
+        uint64_t hcr_el2; /* Hypervisor configuration register */
+        uint64_t scr_el3; /* Secure configuration register.  */
         uint32_t ifsr_el2; /* Fault status registers.  */
         uint64_t esr_el[4];
         uint32_t c6_region[8]; /* MPU base/size registers.  */
@@ -323,6 +333,7 @@ typedef struct CPUARMState {
     int eabi;
 #endif
 
+    struct CPUBreakpoint *cpu_breakpoint[16];
     struct CPUWatchpoint *cpu_watchpoint[16];
 
     CPU_COMMON
@@ -498,6 +509,12 @@ void pmccntr_sync(CPUARMState *env);
 #define PSTATE_MODE_EL1t 4
 #define PSTATE_MODE_EL0t 0
 
+/* Map EL and handler into a PSTATE_MODE.  */
+static inline unsigned int aarch64_pstate_mode(unsigned int el, bool handler)
+{
+    return (el << 2) | handler;
+}
+
 /* Return the current PSTATE value. For the moment we don't support 32<->64 bit
  * interprocessing, so we don't attempt to sync with the cpsr state used by
  * the 32 bit decoder.
@@ -565,6 +582,58 @@ static inline void xpsr_write(CPUARMState *env, uint32_t val, uint32_t mask)
     }
 }
 
+#define HCR_VM        (1ULL << 0)
+#define HCR_SWIO      (1ULL << 1)
+#define HCR_PTW       (1ULL << 2)
+#define HCR_FMO       (1ULL << 3)
+#define HCR_IMO       (1ULL << 4)
+#define HCR_AMO       (1ULL << 5)
+#define HCR_VF        (1ULL << 6)
+#define HCR_VI        (1ULL << 7)
+#define HCR_VSE       (1ULL << 8)
+#define HCR_FB        (1ULL << 9)
+#define HCR_BSU_MASK  (3ULL << 10)
+#define HCR_DC        (1ULL << 12)
+#define HCR_TWI       (1ULL << 13)
+#define HCR_TWE       (1ULL << 14)
+#define HCR_TID0      (1ULL << 15)
+#define HCR_TID1      (1ULL << 16)
+#define HCR_TID2      (1ULL << 17)
+#define HCR_TID3      (1ULL << 18)
+#define HCR_TSC       (1ULL << 19)
+#define HCR_TIDCP     (1ULL << 20)
+#define HCR_TACR      (1ULL << 21)
+#define HCR_TSW       (1ULL << 22)
+#define HCR_TPC       (1ULL << 23)
+#define HCR_TPU       (1ULL << 24)
+#define HCR_TTLB      (1ULL << 25)
+#define HCR_TVM       (1ULL << 26)
+#define HCR_TGE       (1ULL << 27)
+#define HCR_TDZ       (1ULL << 28)
+#define HCR_HCD       (1ULL << 29)
+#define HCR_TRVM      (1ULL << 30)
+#define HCR_RW        (1ULL << 31)
+#define HCR_CD        (1ULL << 32)
+#define HCR_ID        (1ULL << 33)
+#define HCR_MASK      ((1ULL << 34) - 1)
+
+#define SCR_NS                (1U << 0)
+#define SCR_IRQ               (1U << 1)
+#define SCR_FIQ               (1U << 2)
+#define SCR_EA                (1U << 3)
+#define SCR_FW                (1U << 4)
+#define SCR_AW                (1U << 5)
+#define SCR_NET               (1U << 6)
+#define SCR_SMD               (1U << 7)
+#define SCR_HCE               (1U << 8)
+#define SCR_SIF               (1U << 9)
+#define SCR_RW                (1U << 10)
+#define SCR_ST                (1U << 11)
+#define SCR_TWI               (1U << 12)
+#define SCR_TWE               (1U << 13)
+#define SCR_AARCH32_MASK      (0x3fff & ~(SCR_RW | SCR_ST))
+#define SCR_AARCH64_MASK      (0x3fff & ~SCR_NET)
+
 /* Return the current FPSCR value.  */
 uint32_t vfp_get_fpscr(CPUARMState *env);
 void vfp_set_fpscr(CPUARMState *env, uint32_t val);
@@ -701,6 +770,7 @@ static inline bool arm_el_is_aa64(CPUARMState *env, int el)
 }
 
 void arm_cpu_list(FILE *f, fprintf_function cpu_fprintf);
+unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx);
 
 /* Interface between CPU and Interrupt controller.  */
 void armv7m_nvic_set_pending(void *opaque, int irq);
@@ -1111,6 +1181,61 @@ bool write_cpustate_to_list(ARMCPU *cpu);
 #  define TARGET_VIRT_ADDR_SPACE_BITS 32
 #endif
 
+static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx)
+{
+    CPUARMState *env = cs->env_ptr;
+    unsigned int cur_el = arm_current_pl(env);
+    unsigned int target_el = arm_excp_target_el(cs, excp_idx);
+    /* FIXME: Use actual secure state.  */
+    bool secure = false;
+    /* If in EL1/0, Physical IRQ routing to EL2 only happens from NS state.  */
+    bool irq_can_hyp = !secure && cur_el < 2 && target_el == 2;
+    /* 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.
+     */
+    bool irq_unmasked = !(env->daif & PSTATE_I)
+                        && (!IS_M(env) || env->regs[15] < 0xfffffff0);
+
+    /* Don't take exceptions if they target a lower EL.  */
+    if (cur_el > target_el) {
+        return false;
+    }
+
+    switch (excp_idx) {
+    case EXCP_FIQ:
+        if (irq_can_hyp && (env->cp15.hcr_el2 & HCR_FMO)) {
+            return true;
+        }
+        return !(env->daif & PSTATE_F);
+    case EXCP_IRQ:
+        if (irq_can_hyp && (env->cp15.hcr_el2 & HCR_IMO)) {
+            return true;
+        }
+        return irq_unmasked;
+    case EXCP_VFIQ:
+        if (!secure && !(env->cp15.hcr_el2 & HCR_FMO)) {
+            /* VFIQs are only taken when hypervized and non-secure.  */
+            return false;
+        }
+        return !(env->daif & PSTATE_F);
+    case EXCP_VIRQ:
+        if (!secure && !(env->cp15.hcr_el2 & HCR_IMO)) {
+            /* VIRQs are only taken when hypervized and non-secure.  */
+            return false;
+        }
+        return irq_unmasked;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static inline CPUARMState *cpu_init(const char *cpu_model)
 {
     ARMCPU *cpu = cpu_arm_init(cpu_model);
@@ -1223,6 +1348,11 @@ static inline bool arm_singlestep_active(CPUARMState *env)
 #define ARM_TBFLAG_SS_ACTIVE_MASK (1 << ARM_TBFLAG_SS_ACTIVE_SHIFT)
 #define ARM_TBFLAG_PSTATE_SS_SHIFT 19
 #define ARM_TBFLAG_PSTATE_SS_MASK (1 << ARM_TBFLAG_PSTATE_SS_SHIFT)
+/* We store the bottom two bits of the CPAR as TB flags and handle
+ * checks on the other bits at runtime
+ */
+#define ARM_TBFLAG_XSCALE_CPAR_SHIFT 20
+#define ARM_TBFLAG_XSCALE_CPAR_MASK (3 << ARM_TBFLAG_XSCALE_CPAR_SHIFT)
 
 /* Bit usage when in AArch64 state */
 #define ARM_TBFLAG_AA64_EL_SHIFT    0
@@ -1257,6 +1387,8 @@ static inline bool arm_singlestep_active(CPUARMState *env)
     (((F) & ARM_TBFLAG_SS_ACTIVE_MASK) >> ARM_TBFLAG_SS_ACTIVE_SHIFT)
 #define ARM_TBFLAG_PSTATE_SS(F) \
     (((F) & ARM_TBFLAG_PSTATE_SS_MASK) >> ARM_TBFLAG_PSTATE_SS_SHIFT)
+#define ARM_TBFLAG_XSCALE_CPAR(F) \
+    (((F) & ARM_TBFLAG_XSCALE_CPAR_MASK) >> ARM_TBFLAG_XSCALE_CPAR_SHIFT)
 #define ARM_TBFLAG_AA64_EL(F) \
     (((F) & ARM_TBFLAG_AA64_EL_MASK) >> ARM_TBFLAG_AA64_EL_SHIFT)
 #define ARM_TBFLAG_AA64_FPEN(F) \
@@ -1334,6 +1466,8 @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
                 *flags |= ARM_TBFLAG_PSTATE_SS_MASK;
             }
         }
+        *flags |= (extract32(env->cp15.c15_cpar, 0, 2)
+                   << ARM_TBFLAG_XSCALE_CPAR_SHIFT);
     }
 
     *cs_base = 0;
diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c
index 2e9ef64786..8228e29486 100644
--- a/target-arm/helper-a64.c
+++ b/target-arm/helper-a64.c
@@ -443,10 +443,12 @@ void aarch64_cpu_do_interrupt(CPUState *cs)
 {
     ARMCPU *cpu = ARM_CPU(cs);
     CPUARMState *env = &cpu->env;
-    target_ulong addr = env->cp15.vbar_el[1];
+    unsigned int new_el = arm_excp_target_el(cs, cs->exception_index);
+    target_ulong addr = env->cp15.vbar_el[new_el];
+    unsigned int new_mode = aarch64_pstate_mode(new_el, true);
     int i;
 
-    if (arm_current_pl(env) == 0) {
+    if (arm_current_pl(env) < new_el) {
         if (env->aarch64) {
             addr += 0x400;
         } else {
@@ -464,23 +466,27 @@ void aarch64_cpu_do_interrupt(CPUState *cs)
                       env->exception.syndrome);
     }
 
-    env->cp15.esr_el[1] = env->exception.syndrome;
-    env->cp15.far_el[1] = env->exception.vaddress;
-
     switch (cs->exception_index) {
     case EXCP_PREFETCH_ABORT:
     case EXCP_DATA_ABORT:
+        env->cp15.far_el[new_el] = env->exception.vaddress;
         qemu_log_mask(CPU_LOG_INT, "...with FAR 0x%" PRIx64 "\n",
-                      env->cp15.far_el[1]);
-        break;
+                      env->cp15.far_el[new_el]);
+        /* fall through */
     case EXCP_BKPT:
     case EXCP_UDEF:
     case EXCP_SWI:
+    case EXCP_HVC:
+    case EXCP_HYP_TRAP:
+    case EXCP_SMC:
+        env->cp15.esr_el[new_el] = env->exception.syndrome;
         break;
     case EXCP_IRQ:
+    case EXCP_VIRQ:
         addr += 0x80;
         break;
     case EXCP_FIQ:
+    case EXCP_VFIQ:
         addr += 0x100;
         break;
     default:
@@ -488,15 +494,15 @@ void aarch64_cpu_do_interrupt(CPUState *cs)
     }
 
     if (is_a64(env)) {
-        env->banked_spsr[aarch64_banked_spsr_index(1)] = pstate_read(env);
+        env->banked_spsr[aarch64_banked_spsr_index(new_el)] = pstate_read(env);
         aarch64_save_sp(env, arm_current_pl(env));
-        env->elr_el[1] = env->pc;
+        env->elr_el[new_el] = env->pc;
     } else {
         env->banked_spsr[0] = cpsr_read(env);
         if (!env->thumb) {
-            env->cp15.esr_el[1] |= 1 << 25;
+            env->cp15.esr_el[new_el] |= 1 << 25;
         }
-        env->elr_el[1] = env->regs[15];
+        env->elr_el[new_el] = env->regs[15];
 
         for (i = 0; i < 15; i++) {
             env->xregs[i] = env->regs[i];
@@ -505,9 +511,9 @@ void aarch64_cpu_do_interrupt(CPUState *cs)
         env->condexec_bits = 0;
     }
 
-    pstate_write(env, PSTATE_DAIF | PSTATE_MODE_EL1h);
+    pstate_write(env, PSTATE_DAIF | new_mode);
     env->aarch64 = 1;
-    aarch64_restore_sp(env, 1);
+    aarch64_restore_sp(env, new_el);
 
     env->pc = addr;
     cs->interrupt_request |= CPU_INTERRUPT_EXITTB;
diff --git a/target-arm/helper.c b/target-arm/helper.c
index ece967397f..2669e15cb8 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -747,6 +747,32 @@ static void vbar_write(CPUARMState *env, const ARMCPRegInfo *ri,
     raw_write(env, ri, value & ~0x1FULL);
 }
 
+static void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
+{
+    /* We only mask off bits that are RES0 both for AArch64 and AArch32.
+     * For bits that vary between AArch32/64, code needs to check the
+     * current execution mode before directly using the feature bit.
+     */
+    uint32_t valid_mask = SCR_AARCH64_MASK | SCR_AARCH32_MASK;
+
+    if (!arm_feature(env, ARM_FEATURE_EL2)) {
+        valid_mask &= ~SCR_HCE;
+
+        /* On ARMv7, SMD (or SCD as it is called in v7) is only
+         * supported if EL2 exists. The bit is UNK/SBZP when
+         * EL2 is unavailable. In QEMU ARMv7, we force it to always zero
+         * when EL2 is unavailable.
+         */
+        if (arm_feature(env, ARM_FEATURE_V7)) {
+            valid_mask &= ~SCR_SMD;
+        }
+    }
+
+    /* Clear all-context RES0 bits.  */
+    value &= valid_mask;
+    raw_write(env, ri, value);
+}
+
 static uint64_t ccsidr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     ARMCPU *cpu = arm_env_get_cpu(env);
@@ -873,8 +899,8 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .fieldoffset = offsetof(CPUARMState, cp15.vbar_el[1]),
       .resetvalue = 0 },
     { .name = "SCR", .cp = 15, .crn = 1, .crm = 1, .opc1 = 0, .opc2 = 0,
-      .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c1_scr),
-      .resetvalue = 0, },
+      .access = PL1_RW, .fieldoffset = offsetoflow32(CPUARMState, cp15.scr_el3),
+      .resetvalue = 0, .writefn = scr_write },
     { .name = "CCSIDR", .state = ARM_CP_STATE_BOTH,
       .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 0,
       .access = PL1_R, .readfn = ccsidr_read, .type = ARM_CP_NO_MIGRATE },
@@ -1714,12 +1740,7 @@ static const ARMCPRegInfo omap_cp_reginfo[] = {
 static void xscale_cpar_write(CPUARMState *env, const ARMCPRegInfo *ri,
                               uint64_t value)
 {
-    value &= 0x3fff;
-    if (env->cp15.c15_cpar != value) {
-        /* Changes cp0 to cp13 behavior, so needs a TB flush.  */
-        tb_flush(env);
-        env->cp15.c15_cpar = value;
-    }
+    env->cp15.c15_cpar = value & 0x3fff;
 }
 
 static const ARMCPRegInfo xscale_cp_reginfo[] = {
@@ -2230,10 +2251,44 @@ static const ARMCPRegInfo v8_el3_no_el2_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 0,
       .access = PL2_RW,
       .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore },
+    { .name = "HCR_EL2", .state = ARM_CP_STATE_AA64,
+      .type = ARM_CP_NO_MIGRATE,
+      .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0,
+      .access = PL2_RW,
+      .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore },
     REGINFO_SENTINEL
 };
 
+static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
+{
+    ARMCPU *cpu = arm_env_get_cpu(env);
+    uint64_t valid_mask = HCR_MASK;
+
+    if (arm_feature(env, ARM_FEATURE_EL3)) {
+        valid_mask &= ~HCR_HCD;
+    } else {
+        valid_mask &= ~HCR_TSC;
+    }
+
+    /* Clear RES0 bits.  */
+    value &= valid_mask;
+
+    /* These bits change the MMU setup:
+     * HCR_VM enables stage 2 translation
+     * HCR_PTW forbids certain page-table setups
+     * HCR_DC Disables stage1 and enables stage2 translation
+     */
+    if ((raw_read(env, ri) ^ value) & (HCR_VM | HCR_PTW | HCR_DC)) {
+        tlb_flush(CPU(cpu), 1);
+    }
+    raw_write(env, ri, value);
+}
+
 static const ARMCPRegInfo v8_el2_cp_reginfo[] = {
+    { .name = "HCR_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0,
+      .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2),
+      .writefn = hcr_write },
     { .name = "ELR_EL2", .state = ARM_CP_STATE_AA64,
       .type = ARM_CP_NO_MIGRATE,
       .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 0, .opc2 = 1,
@@ -2280,6 +2335,11 @@ static const ARMCPRegInfo v8_el3_cp_reginfo[] = {
       .access = PL3_RW, .writefn = vbar_write,
       .fieldoffset = offsetof(CPUARMState, cp15.vbar_el[3]),
       .resetvalue = 0 },
+    { .name = "SCR_EL3", .state = ARM_CP_STATE_AA64,
+      .type = ARM_CP_NO_MIGRATE,
+      .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 1, .opc2 = 0,
+      .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.scr_el3),
+      .writefn = scr_write },
     REGINFO_SENTINEL
 };
 
@@ -2492,6 +2552,124 @@ static void dbgwcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     hw_watchpoint_update(cpu, i);
 }
 
+void hw_breakpoint_update(ARMCPU *cpu, int n)
+{
+    CPUARMState *env = &cpu->env;
+    uint64_t bvr = env->cp15.dbgbvr[n];
+    uint64_t bcr = env->cp15.dbgbcr[n];
+    vaddr addr;
+    int bt;
+    int flags = BP_CPU;
+
+    if (env->cpu_breakpoint[n]) {
+        cpu_breakpoint_remove_by_ref(CPU(cpu), env->cpu_breakpoint[n]);
+        env->cpu_breakpoint[n] = NULL;
+    }
+
+    if (!extract64(bcr, 0, 1)) {
+        /* E bit clear : watchpoint disabled */
+        return;
+    }
+
+    bt = extract64(bcr, 20, 4);
+
+    switch (bt) {
+    case 4: /* unlinked address mismatch (reserved if AArch64) */
+    case 5: /* linked address mismatch (reserved if AArch64) */
+        qemu_log_mask(LOG_UNIMP,
+                      "arm: address mismatch breakpoint types not implemented");
+        return;
+    case 0: /* unlinked address match */
+    case 1: /* linked address match */
+    {
+        /* Bits [63:49] are hardwired to the value of bit [48]; that is,
+         * we behave as if the register was sign extended. Bits [1:0] are
+         * RES0. The BAS field is used to allow setting breakpoints on 16
+         * bit wide instructions; it is CONSTRAINED UNPREDICTABLE whether
+         * a bp will fire if the addresses covered by the bp and the addresses
+         * covered by the insn overlap but the insn doesn't start at the
+         * start of the bp address range. We choose to require the insn and
+         * the bp to have the same address. The constraints on writing to
+         * BAS enforced in dbgbcr_write mean we have only four cases:
+         *  0b0000  => no breakpoint
+         *  0b0011  => breakpoint on addr
+         *  0b1100  => breakpoint on addr + 2
+         *  0b1111  => breakpoint on addr
+         * See also figure D2-3 in the v8 ARM ARM (DDI0487A.c).
+         */
+        int bas = extract64(bcr, 5, 4);
+        addr = sextract64(bvr, 0, 49) & ~3ULL;
+        if (bas == 0) {
+            return;
+        }
+        if (bas == 0xc) {
+            addr += 2;
+        }
+        break;
+    }
+    case 2: /* unlinked context ID match */
+    case 8: /* unlinked VMID match (reserved if no EL2) */
+    case 10: /* unlinked context ID and VMID match (reserved if no EL2) */
+        qemu_log_mask(LOG_UNIMP,
+                      "arm: unlinked context breakpoint types not implemented");
+        return;
+    case 9: /* linked VMID match (reserved if no EL2) */
+    case 11: /* linked context ID and VMID match (reserved if no EL2) */
+    case 3: /* linked context ID match */
+    default:
+        /* We must generate no events for Linked context matches (unless
+         * they are linked to by some other bp/wp, which is handled in
+         * updates for the linking bp/wp). We choose to also generate no events
+         * for reserved values.
+         */
+        return;
+    }
+
+    cpu_breakpoint_insert(CPU(cpu), addr, flags, &env->cpu_breakpoint[n]);
+}
+
+void hw_breakpoint_update_all(ARMCPU *cpu)
+{
+    int i;
+    CPUARMState *env = &cpu->env;
+
+    /* Completely clear out existing QEMU breakpoints and our array, to
+     * avoid possible stale entries following migration load.
+     */
+    cpu_breakpoint_remove_all(CPU(cpu), BP_CPU);
+    memset(env->cpu_breakpoint, 0, sizeof(env->cpu_breakpoint));
+
+    for (i = 0; i < ARRAY_SIZE(cpu->env.cpu_breakpoint); i++) {
+        hw_breakpoint_update(cpu, i);
+    }
+}
+
+static void dbgbvr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    ARMCPU *cpu = arm_env_get_cpu(env);
+    int i = ri->crm;
+
+    raw_write(env, ri, value);
+    hw_breakpoint_update(cpu, i);
+}
+
+static void dbgbcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    ARMCPU *cpu = arm_env_get_cpu(env);
+    int i = ri->crm;
+
+    /* BAS[3] is a read-only copy of BAS[2], and BAS[1] a read-only
+     * copy of BAS[0].
+     */
+    value = deposit64(value, 6, 1, extract64(value, 5, 1));
+    value = deposit64(value, 8, 1, extract64(value, 7, 1));
+
+    raw_write(env, ri, value);
+    hw_breakpoint_update(cpu, i);
+}
+
 static void define_debug_regs(ARMCPU *cpu)
 {
     /* Define v7 and v8 architectural debug registers.
@@ -2533,11 +2711,15 @@ static void define_debug_regs(ARMCPU *cpu)
             { .name = "DBGBVR", .state = ARM_CP_STATE_BOTH,
               .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 4,
               .access = PL1_RW,
-              .fieldoffset = offsetof(CPUARMState, cp15.dbgbvr[i]) },
+              .fieldoffset = offsetof(CPUARMState, cp15.dbgbvr[i]),
+              .writefn = dbgbvr_write, .raw_writefn = raw_write
+            },
             { .name = "DBGBCR", .state = ARM_CP_STATE_BOTH,
               .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 5,
               .access = PL1_RW,
-              .fieldoffset = offsetof(CPUARMState, cp15.dbgbcr[i]) },
+              .fieldoffset = offsetof(CPUARMState, cp15.dbgbcr[i]),
+              .writefn = dbgbcr_write, .raw_writefn = raw_write
+            },
             REGINFO_SENTINEL
         };
         define_arm_cp_regs(cpu, dbgregs);
@@ -3522,6 +3704,11 @@ uint32_t HELPER(get_r13_banked)(CPUARMState *env, uint32_t mode)
     return 0;
 }
 
+unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx)
+{
+    return 1;
+}
+
 #else
 
 /* Map CPU modes onto saved register banks.  */
@@ -3577,6 +3764,57 @@ void switch_mode(CPUARMState *env, int mode)
     env->spsr = env->banked_spsr[i];
 }
 
+/*
+ * Determine the target EL for a given exception type.
+ */
+unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+    CPUARMState *env = &cpu->env;
+    unsigned int cur_el = arm_current_pl(env);
+    unsigned int target_el;
+    /* FIXME: Use actual secure state.  */
+    bool secure = false;
+
+    if (!env->aarch64) {
+        /* TODO: Add EL2 and 3 exception handling for AArch32.  */
+        return 1;
+    }
+
+    switch (excp_idx) {
+    case EXCP_HVC:
+    case EXCP_HYP_TRAP:
+        target_el = 2;
+        break;
+    case EXCP_SMC:
+        target_el = 3;
+        break;
+    case EXCP_FIQ:
+    case EXCP_IRQ:
+    {
+        const uint64_t hcr_mask = excp_idx == EXCP_FIQ ? HCR_FMO : HCR_IMO;
+        const uint32_t scr_mask = excp_idx == EXCP_FIQ ? SCR_FIQ : SCR_IRQ;
+
+        target_el = 1;
+        if (!secure && (env->cp15.hcr_el2 & hcr_mask)) {
+            target_el = 2;
+        }
+        if (env->cp15.scr_el3 & scr_mask) {
+            target_el = 3;
+        }
+        break;
+    }
+    case EXCP_VIRQ:
+    case EXCP_VFIQ:
+        target_el = 1;
+        break;
+    default:
+        target_el = MAX(cur_el, 1);
+        break;
+    }
+    return target_el;
+}
+
 static void v7m_push(CPUARMState *env, uint32_t val)
 {
     CPUState *cs = CPU(arm_env_get_cpu(env));
diff --git a/target-arm/helper.h b/target-arm/helper.h
index 1d7003b70a..dec3728798 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -50,6 +50,8 @@ DEF_HELPER_2(exception_internal, void, env, i32)
 DEF_HELPER_3(exception_with_syndrome, void, env, i32, i32)
 DEF_HELPER_1(wfi, void, env)
 DEF_HELPER_1(wfe, void, env)
+DEF_HELPER_1(pre_hvc, void, env)
+DEF_HELPER_2(pre_smc, void, env, i32)
 
 DEF_HELPER_3(cpsr_write, void, env, i32, i32)
 DEF_HELPER_1(cpsr_read, i32, env)
diff --git a/target-arm/internals.h b/target-arm/internals.h
index 64751a0798..b7547bbb76 100644
--- a/target-arm/internals.h
+++ b/target-arm/internals.h
@@ -53,6 +53,11 @@ static const char * const excnames[] = {
     [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit",
     [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage",
     [EXCP_STREX] = "QEMU intercept of STREX",
+    [EXCP_HVC] = "Hypervisor Call",
+    [EXCP_HYP_TRAP] = "Hypervisor Trap",
+    [EXCP_SMC] = "Secure Monitor Call",
+    [EXCP_VIRQ] = "Virtual IRQ",
+    [EXCP_VFIQ] = "Virtual FIQ",
 };
 
 static inline void arm_log_exception(int idx)
@@ -215,6 +220,16 @@ static inline uint32_t syn_aa64_svc(uint32_t imm16)
     return (EC_AA64_SVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
 }
 
+static inline uint32_t syn_aa64_hvc(uint32_t imm16)
+{
+    return (EC_AA64_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+}
+
+static inline uint32_t syn_aa64_smc(uint32_t imm16)
+{
+    return (EC_AA64_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+}
+
 static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_thumb)
 {
     return (EC_AA32_SVC << ARM_EL_EC_SHIFT) | (imm16 & 0xffff)
@@ -313,6 +328,12 @@ static inline uint32_t syn_watchpoint(int same_el, int cm, int wnr)
         | (cm << 8) | (wnr << 6) | 0x22;
 }
 
+static inline uint32_t syn_breakpoint(int same_el)
+{
+    return (EC_BREAKPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
+        | ARM_EL_IL | 0x22;
+}
+
 /* Update a QEMU watchpoint based on the information the guest has set in the
  * DBGWCR<n>_EL1 and DBGWVR<n>_EL1 registers.
  */
@@ -322,6 +343,15 @@ void hw_watchpoint_update(ARMCPU *cpu, int n);
  * suitable for use after migration or on reset.
  */
 void hw_watchpoint_update_all(ARMCPU *cpu);
+/* Update a QEMU breakpoint based on the information the guest has set in the
+ * DBGBCR<n>_EL1 and DBGBVR<n>_EL1 registers.
+ */
+void hw_breakpoint_update(ARMCPU *cpu, int n);
+/* Update the QEMU breakpoints for every guest breakpoint. This does a
+ * complete delete-and-reinstate of the QEMU breakpoint list and so is
+ * suitable for use after migration or on reset.
+ */
+void hw_breakpoint_update_all(ARMCPU *cpu);
 
 /* Callback function for when a watchpoint or breakpoint triggers. */
 void arm_debug_excp_handler(CPUState *cs);
diff --git a/target-arm/machine.c b/target-arm/machine.c
index 8dfe87cb6b..ddb7d05c28 100644
--- a/target-arm/machine.c
+++ b/target-arm/machine.c
@@ -214,6 +214,7 @@ static int cpu_post_load(void *opaque, int version_id)
         }
     }
 
+    hw_breakpoint_update_all(cpu);
     hw_watchpoint_update_all(cpu);
 
     return 0;
diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c
index b956216c4b..03ac92afdc 100644
--- a/target-arm/op_helper.c
+++ b/target-arm/op_helper.c
@@ -301,6 +301,17 @@ void HELPER(set_user_reg)(CPUARMState *env, uint32_t regno, uint32_t val)
 void HELPER(access_check_cp_reg)(CPUARMState *env, void *rip, uint32_t syndrome)
 {
     const ARMCPRegInfo *ri = rip;
+
+    if (arm_feature(env, ARM_FEATURE_XSCALE) && ri->cp < 14
+        && extract32(env->cp15.c15_cpar, ri->cp, 1) == 0) {
+        env->exception.syndrome = syndrome;
+        raise_exception(env, EXCP_UDEF);
+    }
+
+    if (!ri->accessfn) {
+        return;
+    }
+
     switch (ri->accessfn(env, ri)) {
     case CP_ACCESS_OK:
         return;
@@ -374,6 +385,63 @@ void HELPER(clear_pstate_ss)(CPUARMState *env)
     env->pstate &= ~PSTATE_SS;
 }
 
+void HELPER(pre_hvc)(CPUARMState *env)
+{
+    int cur_el = arm_current_pl(env);
+    /* FIXME: Use actual secure state.  */
+    bool secure = false;
+    bool undef;
+
+    /* We've already checked that EL2 exists at translation time.
+     * EL3.HCE has priority over EL2.HCD.
+     */
+    if (arm_feature(env, ARM_FEATURE_EL3)) {
+        undef = !(env->cp15.scr_el3 & SCR_HCE);
+    } else {
+        undef = env->cp15.hcr_el2 & HCR_HCD;
+    }
+
+    /* In ARMv7 and ARMv8/AArch32, HVC is undef in secure state.
+     * For ARMv8/AArch64, HVC is allowed in EL3.
+     * Note that we've already trapped HVC from EL0 at translation
+     * time.
+     */
+    if (secure && (!is_a64(env) || cur_el == 1)) {
+        undef = true;
+    }
+
+    if (undef) {
+        env->exception.syndrome = syn_uncategorized();
+        raise_exception(env, EXCP_UDEF);
+    }
+}
+
+void HELPER(pre_smc)(CPUARMState *env, uint32_t syndrome)
+{
+    int cur_el = arm_current_pl(env);
+    /* FIXME: Use real secure state.  */
+    bool secure = false;
+    bool smd = env->cp15.scr_el3 & SCR_SMD;
+    /* On ARMv8 AArch32, SMD only applies to NS state.
+     * On ARMv7 SMD only applies to NS state and only if EL2 is available.
+     * For ARMv7 non EL2, we force SMD to zero so we don't need to re-check
+     * the EL2 condition here.
+     */
+    bool undef = is_a64(env) ? smd : (!secure && smd);
+
+    /* In NS EL1, HCR controlled routing to EL2 has priority over SMD.  */
+    if (!secure && cur_el == 1 && (env->cp15.hcr_el2 & HCR_TSC)) {
+        env->exception.syndrome = syndrome;
+        raise_exception(env, EXCP_HYP_TRAP);
+    }
+
+    /* We've already checked that EL3 exists at translation time.  */
+    if (undef) {
+        env->exception.syndrome = syn_uncategorized();
+        raise_exception(env, EXCP_UDEF);
+    }
+}
+
 void HELPER(exception_return)(CPUARMState *env)
 {
     int cur_el = arm_current_pl(env);
@@ -511,32 +579,43 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn)
     return false;
 }
 
-static bool wp_matches(ARMCPU *cpu, int n)
+static bool bp_wp_matches(ARMCPU *cpu, int n, bool is_wp)
 {
     CPUARMState *env = &cpu->env;
-    uint64_t wcr = env->cp15.dbgwcr[n];
+    uint64_t cr;
     int pac, hmc, ssc, wt, lbn;
     /* TODO: check against CPU security state when we implement TrustZone */
     bool is_secure = false;
 
-    if (!env->cpu_watchpoint[n]
-        || !(env->cpu_watchpoint[n]->flags & BP_WATCHPOINT_HIT)) {
-        return false;
-    }
+    if (is_wp) {
+        if (!env->cpu_watchpoint[n]
+            || !(env->cpu_watchpoint[n]->flags & BP_WATCHPOINT_HIT)) {
+            return false;
+        }
+        cr = env->cp15.dbgwcr[n];
+    } else {
+        uint64_t pc = is_a64(env) ? env->pc : env->regs[15];
 
+        if (!env->cpu_breakpoint[n] || env->cpu_breakpoint[n]->pc != pc) {
+            return false;
+        }
+        cr = env->cp15.dbgbcr[n];
+    }
     /* The WATCHPOINT_HIT flag guarantees us that the watchpoint is
-     * enabled and that the address and access type match; check the
-     * remaining fields, including linked breakpoints.
-     * Note that some combinations of {PAC, HMC SSC} are reserved and
+     * enabled and that the address and access type match; for breakpoints
+     * we know the address matched; check the remaining fields, including
+     * linked breakpoints. We rely on WCR and BCR having the same layout
+     * for the LBN, SSC, HMC, PAC/PMC and is-linked fields.
+     * Note that some combinations of {PAC, HMC, SSC} are reserved and
      * must act either like some valid combination or as if the watchpoint
      * were disabled. We choose the former, and use this together with
      * the fact that EL3 must always be Secure and EL2 must always be
      * Non-Secure to simplify the code slightly compared to the full
      * table in the ARM ARM.
      */
-    pac = extract64(wcr, 1, 2);
-    hmc = extract64(wcr, 13, 1);
-    ssc = extract64(wcr, 14, 2);
+    pac = extract64(cr, 1, 2);
+    hmc = extract64(cr, 13, 1);
+    ssc = extract64(cr, 14, 2);
 
     switch (ssc) {
     case 0:
@@ -560,6 +639,7 @@ static bool wp_matches(ARMCPU *cpu, int n)
      * Implementing this would require reworking the core watchpoint code
      * to plumb the mmu_idx through to this point. Luckily Linux does not
      * rely on this behaviour currently.
+     * For breakpoints we do want to use the current CPU state.
      */
     switch (arm_current_pl(env)) {
     case 3:
@@ -582,8 +662,8 @@ static bool wp_matches(ARMCPU *cpu, int n)
         g_assert_not_reached();
     }
 
-    wt = extract64(wcr, 20, 1);
-    lbn = extract64(wcr, 16, 4);
+    wt = extract64(cr, 20, 1);
+    lbn = extract64(cr, 16, 4);
 
     if (wt && !linked_bp_matches(cpu, lbn)) {
         return false;
@@ -606,7 +686,28 @@ static bool check_watchpoints(ARMCPU *cpu)
     }
 
     for (n = 0; n < ARRAY_SIZE(env->cpu_watchpoint); n++) {
-        if (wp_matches(cpu, n)) {
+        if (bp_wp_matches(cpu, n, true)) {
+            return true;
+        }
+    }
+    return false;
+}
+
+static bool check_breakpoints(ARMCPU *cpu)
+{
+    CPUARMState *env = &cpu->env;
+    int n;
+
+    /* If breakpoints are disabled globally or we can't take debug
+     * exceptions here then breakpoint firings are ignored.
+     */
+    if (extract32(env->cp15.mdscr_el1, 15, 1) == 0
+        || !arm_generate_debug_exceptions(env)) {
+        return false;
+    }
+
+    for (n = 0; n < ARRAY_SIZE(env->cpu_breakpoint); n++) {
+        if (bp_wp_matches(cpu, n, false)) {
             return true;
         }
     }
@@ -641,6 +742,18 @@ void arm_debug_excp_handler(CPUState *cs)
                 cpu_resume_from_signal(cs, NULL);
             }
         }
+    } else {
+        if (check_breakpoints(cpu)) {
+            bool same_el = (arm_debug_target_el(env) == arm_current_pl(env));
+            env->exception.syndrome = syn_breakpoint(same_el);
+            if (extended_addresses_enabled(env)) {
+                env->exception.fsr = (1 << 9) | 0x22;
+            } else {
+                env->exception.fsr = 0x2;
+            }
+            /* FAR is UNKNOWN, so doesn't need setting */
+            raise_exception(env, EXCP_PREFETCH_ABORT);
+        }
     }
 }
 
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 8e66b6c972..35ae3ea281 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -1470,23 +1470,49 @@ static void disas_exc(DisasContext *s, uint32_t insn)
     int opc = extract32(insn, 21, 3);
     int op2_ll = extract32(insn, 0, 5);
     int imm16 = extract32(insn, 5, 16);
+    TCGv_i32 tmp;
 
     switch (opc) {
     case 0:
-        /* SVC, HVC, SMC; since we don't support the Virtualization
-         * or TrustZone extensions these all UNDEF except SVC.
-         */
-        if (op2_ll != 1) {
-            unallocated_encoding(s);
-            break;
-        }
         /* For SVC, HVC and SMC we advance the single-step state
          * machine before taking the exception. This is architecturally
          * mandated, to ensure that single-stepping a system call
          * instruction works properly.
          */
-        gen_ss_advance(s);
-        gen_exception_insn(s, 0, EXCP_SWI, syn_aa64_svc(imm16));
+        switch (op2_ll) {
+        case 1:
+            gen_ss_advance(s);
+            gen_exception_insn(s, 0, EXCP_SWI, syn_aa64_svc(imm16));
+            break;
+        case 2:
+            if (!arm_dc_feature(s, ARM_FEATURE_EL2) || s->current_pl == 0) {
+                unallocated_encoding(s);
+                break;
+            }
+            /* The pre HVC helper handles cases when HVC gets trapped
+             * as an undefined insn by runtime configuration.
+             */
+            gen_a64_set_pc_im(s->pc - 4);
+            gen_helper_pre_hvc(cpu_env);
+            gen_ss_advance(s);
+            gen_exception_insn(s, 0, EXCP_HVC, syn_aa64_hvc(imm16));
+            break;
+        case 3:
+            if (!arm_dc_feature(s, ARM_FEATURE_EL3) || s->current_pl == 0) {
+                unallocated_encoding(s);
+                break;
+            }
+            gen_a64_set_pc_im(s->pc - 4);
+            tmp = tcg_const_i32(syn_aa64_smc(imm16));
+            gen_helper_pre_smc(cpu_env, tmp);
+            tcg_temp_free_i32(tmp);
+            gen_ss_advance(s);
+            gen_exception_insn(s, 0, EXCP_SMC, syn_aa64_smc(imm16));
+            break;
+        default:
+            unallocated_encoding(s);
+            break;
+        }
         break;
     case 1:
         if (op2_ll != 0) {
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 2c0b1deaea..8a2994fcb4 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -7001,22 +7001,18 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
     const ARMCPRegInfo *ri;
 
     cpnum = (insn >> 8) & 0xf;
-    if (arm_feature(env, ARM_FEATURE_XSCALE)
-	    && ((env->cp15.c15_cpar ^ 0x3fff) & (1 << cpnum)))
-	return 1;
 
-    /* First check for coprocessor space used for actual instructions */
-    switch (cpnum) {
-      case 0:
-      case 1:
-	if (arm_feature(env, ARM_FEATURE_IWMMXT)) {
-	    return disas_iwmmxt_insn(env, s, insn);
-	} else if (arm_feature(env, ARM_FEATURE_XSCALE)) {
-	    return disas_dsp_insn(env, s, insn);
-	}
-	return 1;
-    default:
-        break;
+    /* First check for coprocessor space used for XScale/iwMMXt insns */
+    if (arm_feature(env, ARM_FEATURE_XSCALE) && (cpnum < 2)) {
+        if (extract32(s->c15_cpar, cpnum, 1) == 0) {
+            return 1;
+        }
+        if (arm_feature(env, ARM_FEATURE_IWMMXT)) {
+            return disas_iwmmxt_insn(env, s, insn);
+        } else if (arm_feature(env, ARM_FEATURE_XSCALE)) {
+            return disas_dsp_insn(env, s, insn);
+        }
+        return 1;
     }
 
     /* Otherwise treat as a generic register access */
@@ -7049,9 +7045,12 @@ static int disas_coproc_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
             return 1;
         }
 
-        if (ri->accessfn) {
+        if (ri->accessfn ||
+            (arm_feature(env, ARM_FEATURE_XSCALE) && cpnum < 14)) {
             /* Emit code to perform further access permissions checks at
              * runtime; this may result in an exception.
+             * Note that on XScale all cp0..c13 registers do an access check
+             * call in order to handle c15_cpar.
              */
             TCGv_ptr tmpptr;
             TCGv_i32 tcg_syn;
@@ -7675,9 +7674,11 @@ static void disas_arm_insn(CPUARMState * env, DisasContext *s)
         } else if ((insn & 0x0e000f00) == 0x0c000100) {
             if (arm_feature(env, ARM_FEATURE_IWMMXT)) {
                 /* iWMMXt register transfer.  */
-                if (env->cp15.c15_cpar & (1 << 1))
-                    if (!disas_iwmmxt_insn(env, s, insn))
+                if (extract32(s->c15_cpar, 1, 1)) {
+                    if (!disas_iwmmxt_insn(env, s, insn)) {
                         return;
+                    }
+                }
             }
         } else if ((insn & 0x0fe00000) == 0x0c400000) {
             /* Coprocessor double register transfer.  */
@@ -10942,6 +10943,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
     dc->vfp_enabled = ARM_TBFLAG_VFPEN(tb->flags);
     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->cp_regs = cpu->cp_regs;
     dc->current_pl = arm_current_pl(env);
     dc->features = env->features;
diff --git a/target-arm/translate.h b/target-arm/translate.h
index b90d27514d..85c6f9dcb2 100644
--- a/target-arm/translate.h
+++ b/target-arm/translate.h
@@ -52,6 +52,8 @@ typedef struct DisasContext {
     bool is_ldex;
     /* True if a single-step exception will be taken to the current EL */
     bool ss_same_el;
+    /* Bottom two bits of XScale c15_cpar coprocessor access control reg */
+    int c15_cpar;
 #define TMP_A64_MAX 16
     int tmp_a64_count;
     TCGv_i64 tmp_a64[TMP_A64_MAX];