summary refs log tree commit diff stats
path: root/target/arm
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm')
-rw-r--r--target/arm/arm-powerctl.c202
-rw-r--r--target/arm/arm-powerctl.h2
-rw-r--r--target/arm/arm_ldst.h10
-rw-r--r--target/arm/cpu.c45
-rw-r--r--target/arm/cpu.h29
-rw-r--r--target/arm/helper.c293
-rw-r--r--target/arm/internals.h5
-rw-r--r--target/arm/kvm.c7
-rw-r--r--target/arm/machine.c41
-rw-r--r--target/arm/op_helper.c72
-rw-r--r--target/arm/psci.c4
-rw-r--r--target/arm/translate-a64.c22
-rw-r--r--target/arm/translate.c213
-rw-r--r--target/arm/translate.h14
14 files changed, 681 insertions, 278 deletions
diff --git a/target/arm/arm-powerctl.c b/target/arm/arm-powerctl.c
index fbb7a15daa..25207cb850 100644
--- a/target/arm/arm-powerctl.c
+++ b/target/arm/arm-powerctl.c
@@ -14,6 +14,7 @@
 #include "internals.h"
 #include "arm-powerctl.h"
 #include "qemu/log.h"
+#include "qemu/main-loop.h"
 #include "exec/exec-all.h"
 
 #ifndef DEBUG_ARM_POWERCTL
@@ -48,11 +49,93 @@ CPUState *arm_get_cpu_by_id(uint64_t id)
     return NULL;
 }
 
+struct CpuOnInfo {
+    uint64_t entry;
+    uint64_t context_id;
+    uint32_t target_el;
+    bool target_aa64;
+};
+
+
+static void arm_set_cpu_on_async_work(CPUState *target_cpu_state,
+                                      run_on_cpu_data data)
+{
+    ARMCPU *target_cpu = ARM_CPU(target_cpu_state);
+    struct CpuOnInfo *info = (struct CpuOnInfo *) data.host_ptr;
+
+    /* Initialize the cpu we are turning on */
+    cpu_reset(target_cpu_state);
+    target_cpu_state->halted = 0;
+
+    if (info->target_aa64) {
+        if ((info->target_el < 3) && arm_feature(&target_cpu->env,
+                                                 ARM_FEATURE_EL3)) {
+            /*
+             * As target mode is AArch64, we need to set lower
+             * exception level (the requested level 2) to AArch64
+             */
+            target_cpu->env.cp15.scr_el3 |= SCR_RW;
+        }
+
+        if ((info->target_el < 2) && arm_feature(&target_cpu->env,
+                                                 ARM_FEATURE_EL2)) {
+            /*
+             * As target mode is AArch64, we need to set lower
+             * exception level (the requested level 1) to AArch64
+             */
+            target_cpu->env.cp15.hcr_el2 |= HCR_RW;
+        }
+
+        target_cpu->env.pstate = aarch64_pstate_mode(info->target_el, true);
+    } else {
+        /* We are requested to boot in AArch32 mode */
+        static const uint32_t mode_for_el[] = { 0,
+                                                ARM_CPU_MODE_SVC,
+                                                ARM_CPU_MODE_HYP,
+                                                ARM_CPU_MODE_SVC };
+
+        cpsr_write(&target_cpu->env, mode_for_el[info->target_el], CPSR_M,
+                   CPSRWriteRaw);
+    }
+
+    if (info->target_el == 3) {
+        /* Processor is in secure mode */
+        target_cpu->env.cp15.scr_el3 &= ~SCR_NS;
+    } else {
+        /* Processor is not in secure mode */
+        target_cpu->env.cp15.scr_el3 |= SCR_NS;
+    }
+
+    /* We check if the started CPU is now at the correct level */
+    assert(info->target_el == arm_current_el(&target_cpu->env));
+
+    if (info->target_aa64) {
+        target_cpu->env.xregs[0] = info->context_id;
+        target_cpu->env.thumb = false;
+    } else {
+        target_cpu->env.regs[0] = info->context_id;
+        target_cpu->env.thumb = info->entry & 1;
+        info->entry &= 0xfffffffe;
+    }
+
+    /* Start the new CPU at the requested address */
+    cpu_set_pc(target_cpu_state, info->entry);
+
+    g_free(info);
+
+    /* Finally set the power status */
+    assert(qemu_mutex_iothread_locked());
+    target_cpu->power_state = PSCI_ON;
+}
+
 int arm_set_cpu_on(uint64_t cpuid, uint64_t entry, uint64_t context_id,
                    uint32_t target_el, bool target_aa64)
 {
     CPUState *target_cpu_state;
     ARMCPU *target_cpu;
+    struct CpuOnInfo *info;
+
+    assert(qemu_mutex_iothread_locked());
 
     DPRINTF("cpu %" PRId64 " (EL %d, %s) @ 0x%" PRIx64 " with R0 = 0x%" PRIx64
             "\n", cpuid, target_el, target_aa64 ? "aarch64" : "aarch32", entry,
@@ -77,7 +160,7 @@ int arm_set_cpu_on(uint64_t cpuid, uint64_t entry, uint64_t context_id,
     }
 
     target_cpu = ARM_CPU(target_cpu_state);
-    if (!target_cpu->powered_off) {
+    if (target_cpu->power_state == PSCI_ON) {
         qemu_log_mask(LOG_GUEST_ERROR,
                       "[ARM]%s: CPU %" PRId64 " is already on\n",
                       __func__, cpuid);
@@ -109,74 +192,54 @@ int arm_set_cpu_on(uint64_t cpuid, uint64_t entry, uint64_t context_id,
         return QEMU_ARM_POWERCTL_INVALID_PARAM;
     }
 
-    /* Initialize the cpu we are turning on */
-    cpu_reset(target_cpu_state);
-    target_cpu->powered_off = false;
-    target_cpu_state->halted = 0;
-
-    if (target_aa64) {
-        if ((target_el < 3) && arm_feature(&target_cpu->env, ARM_FEATURE_EL3)) {
-            /*
-             * As target mode is AArch64, we need to set lower
-             * exception level (the requested level 2) to AArch64
-             */
-            target_cpu->env.cp15.scr_el3 |= SCR_RW;
-        }
-
-        if ((target_el < 2) && arm_feature(&target_cpu->env, ARM_FEATURE_EL2)) {
-            /*
-             * As target mode is AArch64, we need to set lower
-             * exception level (the requested level 1) to AArch64
-             */
-            target_cpu->env.cp15.hcr_el2 |= HCR_RW;
-        }
-
-        target_cpu->env.pstate = aarch64_pstate_mode(target_el, true);
-    } else {
-        /* We are requested to boot in AArch32 mode */
-        static uint32_t mode_for_el[] = { 0,
-                                          ARM_CPU_MODE_SVC,
-                                          ARM_CPU_MODE_HYP,
-                                          ARM_CPU_MODE_SVC };
-
-        cpsr_write(&target_cpu->env, mode_for_el[target_el], CPSR_M,
-                   CPSRWriteRaw);
-    }
-
-    if (target_el == 3) {
-        /* Processor is in secure mode */
-        target_cpu->env.cp15.scr_el3 &= ~SCR_NS;
-    } else {
-        /* Processor is not in secure mode */
-        target_cpu->env.cp15.scr_el3 |= SCR_NS;
-    }
-
-    /* We check if the started CPU is now at the correct level */
-    assert(target_el == arm_current_el(&target_cpu->env));
-
-    if (target_aa64) {
-        target_cpu->env.xregs[0] = context_id;
-        target_cpu->env.thumb = false;
-    } else {
-        target_cpu->env.regs[0] = context_id;
-        target_cpu->env.thumb = entry & 1;
-        entry &= 0xfffffffe;
+    /*
+     * If another CPU has powered the target on we are in the state
+     * ON_PENDING and additional attempts to power on the CPU should
+     * fail (see 6.6 Implementation CPU_ON/CPU_OFF races in the PSCI
+     * spec)
+     */
+    if (target_cpu->power_state == PSCI_ON_PENDING) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "[ARM]%s: CPU %" PRId64 " is already powering on\n",
+                      __func__, cpuid);
+        return QEMU_ARM_POWERCTL_ON_PENDING;
     }
 
-    /* Start the new CPU at the requested address */
-    cpu_set_pc(target_cpu_state, entry);
+    /* To avoid racing with a CPU we are just kicking off we do the
+     * final bit of preparation for the work in the target CPUs
+     * context.
+     */
+    info = g_new(struct CpuOnInfo, 1);
+    info->entry = entry;
+    info->context_id = context_id;
+    info->target_el = target_el;
+    info->target_aa64 = target_aa64;
 
-    qemu_cpu_kick(target_cpu_state);
+    async_run_on_cpu(target_cpu_state, arm_set_cpu_on_async_work,
+                     RUN_ON_CPU_HOST_PTR(info));
 
     /* We are good to go */
     return QEMU_ARM_POWERCTL_RET_SUCCESS;
 }
 
+static void arm_set_cpu_off_async_work(CPUState *target_cpu_state,
+                                       run_on_cpu_data data)
+{
+    ARMCPU *target_cpu = ARM_CPU(target_cpu_state);
+
+    assert(qemu_mutex_iothread_locked());
+    target_cpu->power_state = PSCI_OFF;
+    target_cpu_state->halted = 1;
+    target_cpu_state->exception_index = EXCP_HLT;
+}
+
 int arm_set_cpu_off(uint64_t cpuid)
 {
     CPUState *target_cpu_state;
     ARMCPU *target_cpu;
 
+    assert(qemu_mutex_iothread_locked());
+
     DPRINTF("cpu %" PRId64 "\n", cpuid);
 
     /* change to the cpu we are powering up */
@@ -185,27 +248,34 @@ int arm_set_cpu_off(uint64_t cpuid)
         return QEMU_ARM_POWERCTL_INVALID_PARAM;
     }
     target_cpu = ARM_CPU(target_cpu_state);
-    if (target_cpu->powered_off) {
+    if (target_cpu->power_state == PSCI_OFF) {
         qemu_log_mask(LOG_GUEST_ERROR,
                       "[ARM]%s: CPU %" PRId64 " is already off\n",
                       __func__, cpuid);
         return QEMU_ARM_POWERCTL_IS_OFF;
     }
 
-    target_cpu->powered_off = true;
-    target_cpu_state->halted = 1;
-    target_cpu_state->exception_index = EXCP_HLT;
-    cpu_loop_exit(target_cpu_state);
-    /* notreached */
+    /* Queue work to run under the target vCPUs context */
+    async_run_on_cpu(target_cpu_state, arm_set_cpu_off_async_work,
+                     RUN_ON_CPU_NULL);
 
     return QEMU_ARM_POWERCTL_RET_SUCCESS;
 }
 
+static void arm_reset_cpu_async_work(CPUState *target_cpu_state,
+                                     run_on_cpu_data data)
+{
+    /* Reset the cpu */
+    cpu_reset(target_cpu_state);
+}
+
 int arm_reset_cpu(uint64_t cpuid)
 {
     CPUState *target_cpu_state;
     ARMCPU *target_cpu;
 
+    assert(qemu_mutex_iothread_locked());
+
     DPRINTF("cpu %" PRId64 "\n", cpuid);
 
     /* change to the cpu we are resetting */
@@ -214,15 +284,17 @@ int arm_reset_cpu(uint64_t cpuid)
         return QEMU_ARM_POWERCTL_INVALID_PARAM;
     }
     target_cpu = ARM_CPU(target_cpu_state);
-    if (target_cpu->powered_off) {
+
+    if (target_cpu->power_state == PSCI_OFF) {
         qemu_log_mask(LOG_GUEST_ERROR,
                       "[ARM]%s: CPU %" PRId64 " is off\n",
                       __func__, cpuid);
         return QEMU_ARM_POWERCTL_IS_OFF;
     }
 
-    /* Reset the cpu */
-    cpu_reset(target_cpu_state);
+    /* Queue work to run under the target vCPUs context */
+    async_run_on_cpu(target_cpu_state, arm_reset_cpu_async_work,
+                     RUN_ON_CPU_NULL);
 
     return QEMU_ARM_POWERCTL_RET_SUCCESS;
 }
diff --git a/target/arm/arm-powerctl.h b/target/arm/arm-powerctl.h
index 98ee04989b..04353923c0 100644
--- a/target/arm/arm-powerctl.h
+++ b/target/arm/arm-powerctl.h
@@ -17,6 +17,7 @@
 #define QEMU_ARM_POWERCTL_INVALID_PARAM QEMU_PSCI_RET_INVALID_PARAMS
 #define QEMU_ARM_POWERCTL_ALREADY_ON QEMU_PSCI_RET_ALREADY_ON
 #define QEMU_ARM_POWERCTL_IS_OFF QEMU_PSCI_RET_DENIED
+#define QEMU_ARM_POWERCTL_ON_PENDING QEMU_PSCI_RET_ON_PENDING
 
 /*
  * arm_get_cpu_by_id:
@@ -43,6 +44,7 @@ CPUState *arm_get_cpu_by_id(uint64_t cpuid);
  * Returns: QEMU_ARM_POWERCTL_RET_SUCCESS on success.
  * QEMU_ARM_POWERCTL_INVALID_PARAM if bad parameters are provided.
  * QEMU_ARM_POWERCTL_ALREADY_ON if the CPU was already started.
+ * QEMU_ARM_POWERCTL_ON_PENDING if the CPU is still powering up
  */
 int arm_set_cpu_on(uint64_t cpuid, uint64_t entry, uint64_t context_id,
                    uint32_t target_el, bool target_aa64);
diff --git a/target/arm/arm_ldst.h b/target/arm/arm_ldst.h
index a76d89f62c..01587b3ebb 100644
--- a/target/arm/arm_ldst.h
+++ b/target/arm/arm_ldst.h
@@ -39,7 +39,15 @@ static inline uint32_t arm_ldl_code(CPUARMState *env, target_ulong addr,
 static inline uint16_t arm_lduw_code(CPUARMState *env, target_ulong addr,
                                      bool sctlr_b)
 {
-    uint16_t insn = cpu_lduw_code(env, addr);
+    uint16_t insn;
+#ifndef CONFIG_USER_ONLY
+    /* In big-endian (BE32) mode, adjacent Thumb instructions have been swapped
+       within each word.  Undo that now.  */
+    if (sctlr_b) {
+        addr ^= 2;
+    }
+#endif
+    insn = cpu_lduw_code(env, addr);
     if (bswap_code(sctlr_b)) {
         return bswap16(insn);
     }
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index e9f10f7747..f7157dc0e5 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -45,7 +45,7 @@ static bool arm_cpu_has_work(CPUState *cs)
 {
     ARMCPU *cpu = ARM_CPU(cs);
 
-    return !cpu->powered_off
+    return (cpu->power_state != PSCI_OFF)
         && cs->interrupt_request &
         (CPU_INTERRUPT_FIQ | CPU_INTERRUPT_HARD
          | CPU_INTERRUPT_VFIQ | CPU_INTERRUPT_VIRQ
@@ -132,7 +132,7 @@ static void arm_cpu_reset(CPUState *s)
     env->vfp.xregs[ARM_VFP_MVFR1] = cpu->mvfr1;
     env->vfp.xregs[ARM_VFP_MVFR2] = cpu->mvfr2;
 
-    cpu->powered_off = cpu->start_powered_off;
+    cpu->power_state = cpu->start_powered_off ? PSCI_OFF : PSCI_ON;
     s->halted = cpu->start_powered_off;
 
     if (arm_feature(env, ARM_FEATURE_IWMMXT)) {
@@ -446,6 +446,21 @@ print_insn_thumb1(bfd_vma pc, disassemble_info *info)
   return print_insn_arm(pc | 1, info);
 }
 
+static int arm_read_memory_func(bfd_vma memaddr, bfd_byte *b,
+                                int length, struct disassemble_info *info)
+{
+    assert(info->read_memory_inner_func);
+    assert((info->flags & INSN_ARM_BE32) == 0 || length == 2 || length == 4);
+
+    if ((info->flags & INSN_ARM_BE32) != 0 && length == 2) {
+        assert(info->endian == BFD_ENDIAN_LITTLE);
+        return info->read_memory_inner_func(memaddr ^ 2, (bfd_byte *)b, 2,
+                                            info);
+    } else {
+        return info->read_memory_inner_func(memaddr, b, length, info);
+    }
+}
+
 static void arm_disas_set_info(CPUState *cpu, disassemble_info *info)
 {
     ARMCPU *ac = ARM_CPU(cpu);
@@ -471,6 +486,14 @@ static void arm_disas_set_info(CPUState *cpu, disassemble_info *info)
         info->endian = BFD_ENDIAN_BIG;
 #endif
     }
+    if (info->read_memory_inner_func == NULL) {
+        info->read_memory_inner_func = info->read_memory_func;
+        info->read_memory_func = arm_read_memory_func;
+    }
+    info->flags &= ~INSN_ARM_BE32;
+    if (arm_sctlr_b(env)) {
+        info->flags |= INSN_ARM_BE32;
+    }
 }
 
 static void arm_cpu_initfn(Object *obj)
@@ -541,6 +564,9 @@ static Property arm_cpu_has_el2_property =
 static Property arm_cpu_has_el3_property =
             DEFINE_PROP_BOOL("has_el3", ARMCPU, has_el3, true);
 
+static Property arm_cpu_cfgend_property =
+            DEFINE_PROP_BOOL("cfgend", ARMCPU, cfgend, false);
+
 /* use property name "pmu" to match other archs and virt tools */
 static Property arm_cpu_has_pmu_property =
             DEFINE_PROP_BOOL("pmu", ARMCPU, has_pmu, true);
@@ -608,6 +634,8 @@ static void arm_cpu_post_init(Object *obj)
         }
     }
 
+    qdev_property_add_static(DEVICE(obj), &arm_cpu_cfgend_property,
+                             &error_abort);
 }
 
 static void arm_cpu_finalizefn(Object *obj)
@@ -728,6 +756,14 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
             cpu->reset_sctlr |= (1 << 13);
     }
 
+    if (cpu->cfgend) {
+        if (arm_feature(&cpu->env, ARM_FEATURE_V7)) {
+            cpu->reset_sctlr |= SCTLR_EE;
+        } else {
+            cpu->reset_sctlr |= SCTLR_B;
+        }
+    }
+
     if (!cpu->has_el3) {
         /* If the has_el3 CPU property is disabled then we need to disable the
          * feature.
@@ -745,7 +781,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
         unset_feature(env, ARM_FEATURE_EL2);
     }
 
-    if (!cpu->has_pmu || !kvm_enabled()) {
+    if (!cpu->has_pmu) {
         cpu->has_pmu = false;
         unset_feature(env, ARM_FEATURE_PMU);
     }
@@ -1639,6 +1675,9 @@ static void arm_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_stop_before_watchpoint = true;
     cc->debug_excp_handler = arm_debug_excp_handler;
     cc->debug_check_watchpoint = arm_debug_check_watchpoint;
+#if !defined(CONFIG_USER_ONLY)
+    cc->adjust_watchpoint_address = arm_adjust_watchpoint_address;
+#endif
 
     cc->disas_set_info = arm_disas_set_info;
 }
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 39bff86daf..38a8e00908 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -30,6 +30,9 @@
 #  define TARGET_LONG_BITS 32
 #endif
 
+/* ARM processors have a weak memory model */
+#define TCG_GUEST_DEFAULT_MO      (0)
+
 #define CPUArchState struct CPUARMState
 
 #include "qemu-common.h"
@@ -307,9 +310,9 @@ typedef struct CPUARMState {
         uint64_t c9_pmcr; /* performance monitor control register */
         uint64_t c9_pmcnten; /* perf monitor counter enables */
         uint32_t c9_pmovsr; /* perf monitor overflow status */
-        uint32_t c9_pmxevtyper; /* perf monitor event type */
         uint32_t c9_pmuserenr; /* perf monitor user enable */
-        uint32_t c9_pminten; /* perf monitor interrupt enables */
+        uint64_t c9_pmselr; /* perf monitor counter selection register */
+        uint64_t c9_pminten; /* perf monitor interrupt enables */
         union { /* Memory attribute redirection */
             struct {
 #ifdef HOST_WORDS_BIGENDIAN
@@ -526,6 +529,15 @@ typedef struct CPUARMState {
  */
 typedef void ARMELChangeHook(ARMCPU *cpu, void *opaque);
 
+
+/* These values map onto the return values for
+ * QEMU_PSCI_0_2_FN_AFFINITY_INFO */
+typedef enum ARMPSCIState {
+    PSCI_OFF = 0,
+    PSCI_ON = 1,
+    PSCI_ON_PENDING = 2
+} ARMPSCIState;
+
 /**
  * ARMCPU:
  * @env: #CPUARMState
@@ -582,8 +594,10 @@ struct ARMCPU {
 
     /* Should CPU start in PSCI powered-off state? */
     bool start_powered_off;
-    /* CPU currently in PSCI powered-off state */
-    bool powered_off;
+
+    /* Current power state, access guarded by BQL */
+    ARMPSCIState power_state;
+
     /* CPU has virtualization extension */
     bool has_el2;
     /* CPU has security extension */
@@ -676,6 +690,13 @@ struct ARMCPU {
     int gic_vpribits; /* number of virtual priority bits */
     int gic_vprebits; /* number of virtual preemption bits */
 
+    /* Whether the cfgend input is high (i.e. this CPU should reset into
+     * big-endian mode).  This setting isn't used directly: instead it modifies
+     * the reset_sctlr value to have SCTLR_B or SCTLR_EE set, depending on the
+     * architecture version.
+     */
+    bool cfgend;
+
     ARMELChangeHook *el_change_hook;
     void *el_change_hook_opaque;
 };
diff --git a/target/arm/helper.c b/target/arm/helper.c
index c23df1b133..bcedb4a808 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -536,41 +536,33 @@ static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void tlbiall_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                              uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush(other_cs);
-    }
+    tlb_flush_all_cpus_synced(cs);
 }
 
 static void tlbiasid_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                              uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush(other_cs);
-    }
+    tlb_flush_all_cpus_synced(cs);
 }
 
 static void tlbimva_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                              uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page(other_cs, value & TARGET_PAGE_MASK);
-    }
+    tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK);
 }
 
 static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                              uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page(other_cs, value & TARGET_PAGE_MASK);
-    }
+    tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK);
 }
 
 static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -578,19 +570,21 @@ static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     CPUState *cs = ENV_GET_CPU(env);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdx_S12NSE1, ARMMMUIdx_S12NSE0,
-                        ARMMMUIdx_S2NS, -1);
+    tlb_flush_by_mmuidx(cs,
+                        (1 << ARMMMUIdx_S12NSE1) |
+                        (1 << ARMMMUIdx_S12NSE0) |
+                        (1 << ARMMMUIdx_S2NS));
 }
 
 static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                   uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S12NSE1,
-                            ARMMMUIdx_S12NSE0, ARMMMUIdx_S2NS, -1);
-    }
+    tlb_flush_by_mmuidx_all_cpus_synced(cs,
+                                        (1 << ARMMMUIdx_S12NSE1) |
+                                        (1 << ARMMMUIdx_S12NSE0) |
+                                        (1 << ARMMMUIdx_S2NS));
 }
 
 static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -611,13 +605,13 @@ static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     pageaddr = sextract64(value << 12, 0, 40);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S2NS, -1);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S2NS));
 }
 
 static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
     uint64_t pageaddr;
 
     if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
@@ -626,9 +620,8 @@ static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     pageaddr = sextract64(value << 12, 0, 40);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S2NS, -1);
-    }
+    tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                             (1 << ARMMMUIdx_S2NS));
 }
 
 static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -636,17 +629,15 @@ static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     CPUState *cs = ENV_GET_CPU(env);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdx_S1E2, -1);
+    tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                  uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S1E2, -1);
-    }
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -655,18 +646,17 @@ static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = ENV_GET_CPU(env);
     uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S1E2, -1);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                  uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
     uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S1E2, -1);
-    }
+    tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                             (1 << ARMMMUIdx_S1E2));
 }
 
 static const ARMCPRegInfo cp_reginfo[] = {
@@ -975,6 +965,17 @@ static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri)
     return total_ticks - env->cp15.c15_ccnt;
 }
 
+static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    /* The value of PMSELR.SEL affects the behavior of PMXEVTYPER and
+     * PMXEVCNTR. We allow [0..31] to be written to PMSELR here; in the
+     * meanwhile, we check PMSELR.SEL when PMXEVTYPER and PMXEVCNTR are
+     * accessed.
+     */
+    env->cp15.c9_pmselr = value & 0x1f;
+}
+
 static void pmccntr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                         uint64_t value)
 {
@@ -1043,7 +1044,25 @@ static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri,
                              uint64_t value)
 {
-    env->cp15.c9_pmxevtyper = value & 0xff;
+    /* Attempts to access PMXEVTYPER are CONSTRAINED UNPREDICTABLE when
+     * PMSELR value is equal to or greater than the number of implemented
+     * counters, but not equal to 0x1f. We opt to behave as a RAZ/WI.
+     */
+    if (env->cp15.c9_pmselr == 0x1f) {
+        pmccfiltr_write(env, ri, value);
+    }
+}
+
+static uint64_t pmxevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    /* We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER
+     * are CONSTRAINED UNPREDICTABLE. See comments in pmxevtyper_write().
+     */
+    if (env->cp15.c9_pmselr == 0x1f) {
+        return env->cp15.pmccfiltr_el0;
+    } else {
+        return 0;
+    }
 }
 
 static void pmuserenr_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -1194,13 +1213,17 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
     /* Unimplemented so WI. */
     { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4,
       .access = PL0_W, .accessfn = pmreg_access, .type = ARM_CP_NOP },
-    /* Since we don't implement any events, writing to PMSELR is UNPREDICTABLE.
-     * We choose to RAZ/WI.
-     */
-    { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5,
-      .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0,
-      .accessfn = pmreg_access },
 #ifndef CONFIG_USER_ONLY
+    { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5,
+      .access = PL0_RW, .type = ARM_CP_ALIAS,
+      .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmselr),
+      .accessfn = pmreg_access, .writefn = pmselr_write,
+      .raw_writefn = raw_write},
+    { .name = "PMSELR_EL0", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 5,
+      .access = PL0_RW, .accessfn = pmreg_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c9_pmselr),
+      .writefn = pmselr_write, .raw_writefn = raw_write, },
     { .name = "PMCCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 0,
       .access = PL0_RW, .resetvalue = 0, .type = ARM_CP_IO,
       .readfn = pmccntr_read, .writefn = pmccntr_write32,
@@ -1219,10 +1242,12 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .fieldoffset = offsetof(CPUARMState, cp15.pmccfiltr_el0),
       .resetvalue = 0, },
     { .name = "PMXEVTYPER", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 1,
-      .access = PL0_RW,
-      .fieldoffset = offsetof(CPUARMState, cp15.c9_pmxevtyper),
-      .accessfn = pmreg_access, .writefn = pmxevtyper_write,
-      .raw_writefn = raw_write },
+      .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access,
+      .writefn = pmxevtyper_write, .readfn = pmxevtyper_read },
+    { .name = "PMXEVTYPER_EL0", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 1,
+      .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access,
+      .writefn = pmxevtyper_write, .readfn = pmxevtyper_read },
     /* Unimplemented, RAZ/WI. */
     { .name = "PMXEVCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 2,
       .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0,
@@ -1240,9 +1265,17 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .writefn = pmuserenr_write, .raw_writefn = raw_write },
     { .name = "PMINTENSET", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 1,
       .access = PL1_RW, .accessfn = access_tpm,
-      .fieldoffset = offsetof(CPUARMState, cp15.c9_pminten),
+      .type = ARM_CP_ALIAS,
+      .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pminten),
       .resetvalue = 0,
       .writefn = pmintenset_write, .raw_writefn = raw_write },
+    { .name = "PMINTENSET_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 1,
+      .access = PL1_RW, .accessfn = access_tpm,
+      .type = ARM_CP_IO,
+      .fieldoffset = offsetof(CPUARMState, cp15.c9_pminten),
+      .writefn = pmintenset_write, .raw_writefn = raw_write,
+      .resetvalue = 0x0 },
     { .name = "PMINTENCLR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 2,
       .access = PL1_RW, .accessfn = access_tpm, .type = ARM_CP_ALIAS,
       .fieldoffset = offsetof(CPUARMState, cp15.c9_pminten),
@@ -2499,8 +2532,10 @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     /* Accesses to VTTBR may change the VMID so we must flush the TLB.  */
     if (raw_read(env, ri) != value) {
-        tlb_flush_by_mmuidx(cs, ARMMMUIdx_S12NSE1, ARMMMUIdx_S12NSE0,
-                            ARMMMUIdx_S2NS, -1);
+        tlb_flush_by_mmuidx(cs,
+                            (1 << ARMMMUIdx_S12NSE1) |
+                            (1 << ARMMMUIdx_S12NSE0) |
+                            (1 << ARMMMUIdx_S2NS));
         raw_write(env, ri, value);
     }
 }
@@ -2855,29 +2890,33 @@ static CPAccessResult aa64_cacheop_access(CPUARMState *env,
 static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                     uint64_t value)
 {
-    ARMCPU *cpu = arm_env_get_cpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUState *cs = ENV_GET_CPU(env);
 
     if (arm_is_secure_below_el3(env)) {
-        tlb_flush_by_mmuidx(cs, ARMMMUIdx_S1SE1, ARMMMUIdx_S1SE0, -1);
+        tlb_flush_by_mmuidx(cs,
+                            (1 << ARMMMUIdx_S1SE1) |
+                            (1 << ARMMMUIdx_S1SE0));
     } else {
-        tlb_flush_by_mmuidx(cs, ARMMMUIdx_S12NSE1, ARMMMUIdx_S12NSE0, -1);
+        tlb_flush_by_mmuidx(cs,
+                            (1 << ARMMMUIdx_S12NSE1) |
+                            (1 << ARMMMUIdx_S12NSE0));
     }
 }
 
 static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                       uint64_t value)
 {
+    CPUState *cs = ENV_GET_CPU(env);
     bool sec = arm_is_secure_below_el3(env);
-    CPUState *other_cs;
 
-    CPU_FOREACH(other_cs) {
-        if (sec) {
-            tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S1SE1, ARMMMUIdx_S1SE0, -1);
-        } else {
-            tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S12NSE1,
-                                ARMMMUIdx_S12NSE0, -1);
-        }
+    if (sec) {
+        tlb_flush_by_mmuidx_all_cpus_synced(cs,
+                                            (1 << ARMMMUIdx_S1SE1) |
+                                            (1 << ARMMMUIdx_S1SE0));
+    } else {
+        tlb_flush_by_mmuidx_all_cpus_synced(cs,
+                                            (1 << ARMMMUIdx_S12NSE1) |
+                                            (1 << ARMMMUIdx_S12NSE0));
     }
 }
 
@@ -2892,13 +2931,19 @@ static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = CPU(cpu);
 
     if (arm_is_secure_below_el3(env)) {
-        tlb_flush_by_mmuidx(cs, ARMMMUIdx_S1SE1, ARMMMUIdx_S1SE0, -1);
+        tlb_flush_by_mmuidx(cs,
+                            (1 << ARMMMUIdx_S1SE1) |
+                            (1 << ARMMMUIdx_S1SE0));
     } else {
         if (arm_feature(env, ARM_FEATURE_EL2)) {
-            tlb_flush_by_mmuidx(cs, ARMMMUIdx_S12NSE1, ARMMMUIdx_S12NSE0,
-                                ARMMMUIdx_S2NS, -1);
+            tlb_flush_by_mmuidx(cs,
+                                (1 << ARMMMUIdx_S12NSE1) |
+                                (1 << ARMMMUIdx_S12NSE0) |
+                                (1 << ARMMMUIdx_S2NS));
         } else {
-            tlb_flush_by_mmuidx(cs, ARMMMUIdx_S12NSE1, ARMMMUIdx_S12NSE0, -1);
+            tlb_flush_by_mmuidx(cs,
+                                (1 << ARMMMUIdx_S12NSE1) |
+                                (1 << ARMMMUIdx_S12NSE0));
         }
     }
 }
@@ -2909,7 +2954,7 @@ static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri,
     ARMCPU *cpu = arm_env_get_cpu(env);
     CPUState *cs = CPU(cpu);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdx_S1E2, -1);
+    tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -2918,7 +2963,7 @@ static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri,
     ARMCPU *cpu = arm_env_get_cpu(env);
     CPUState *cs = CPU(cpu);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdx_S1E3, -1);
+    tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E3));
 }
 
 static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -2928,41 +2973,40 @@ static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
      * stage 2 translations, whereas most other scopes only invalidate
      * stage 1 translations.
      */
+    CPUState *cs = ENV_GET_CPU(env);
     bool sec = arm_is_secure_below_el3(env);
     bool has_el2 = arm_feature(env, ARM_FEATURE_EL2);
-    CPUState *other_cs;
-
-    CPU_FOREACH(other_cs) {
-        if (sec) {
-            tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S1SE1, ARMMMUIdx_S1SE0, -1);
-        } else if (has_el2) {
-            tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S12NSE1,
-                                ARMMMUIdx_S12NSE0, ARMMMUIdx_S2NS, -1);
-        } else {
-            tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S12NSE1,
-                                ARMMMUIdx_S12NSE0, -1);
-        }
+
+    if (sec) {
+        tlb_flush_by_mmuidx_all_cpus_synced(cs,
+                                            (1 << ARMMMUIdx_S1SE1) |
+                                            (1 << ARMMMUIdx_S1SE0));
+    } else if (has_el2) {
+        tlb_flush_by_mmuidx_all_cpus_synced(cs,
+                                            (1 << ARMMMUIdx_S12NSE1) |
+                                            (1 << ARMMMUIdx_S12NSE0) |
+                                            (1 << ARMMMUIdx_S2NS));
+    } else {
+          tlb_flush_by_mmuidx_all_cpus_synced(cs,
+                                              (1 << ARMMMUIdx_S12NSE1) |
+                                              (1 << ARMMMUIdx_S12NSE0));
     }
 }
 
 static void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                     uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S1E2, -1);
-    }
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                     uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_by_mmuidx(other_cs, ARMMMUIdx_S1E3, -1);
-    }
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E3));
 }
 
 static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -2978,11 +3022,13 @@ static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri,
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
     if (arm_is_secure_below_el3(env)) {
-        tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S1SE1,
-                                 ARMMMUIdx_S1SE0, -1);
+        tlb_flush_page_by_mmuidx(cs, pageaddr,
+                                 (1 << ARMMMUIdx_S1SE1) |
+                                 (1 << ARMMMUIdx_S1SE0));
     } else {
-        tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S12NSE1,
-                                 ARMMMUIdx_S12NSE0, -1);
+        tlb_flush_page_by_mmuidx(cs, pageaddr,
+                                 (1 << ARMMMUIdx_S12NSE1) |
+                                 (1 << ARMMMUIdx_S12NSE0));
     }
 }
 
@@ -2997,7 +3043,7 @@ static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = CPU(cpu);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S1E2, -1);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -3011,47 +3057,46 @@ static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = CPU(cpu);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S1E3, -1);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E3));
 }
 
 static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                    uint64_t value)
 {
+    ARMCPU *cpu = arm_env_get_cpu(env);
+    CPUState *cs = CPU(cpu);
     bool sec = arm_is_secure_below_el3(env);
-    CPUState *other_cs;
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    CPU_FOREACH(other_cs) {
-        if (sec) {
-            tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S1SE1,
-                                     ARMMMUIdx_S1SE0, -1);
-        } else {
-            tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S12NSE1,
-                                     ARMMMUIdx_S12NSE0, -1);
-        }
+    if (sec) {
+        tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                                 (1 << ARMMMUIdx_S1SE1) |
+                                                 (1 << ARMMMUIdx_S1SE0));
+    } else {
+        tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                                 (1 << ARMMMUIdx_S12NSE1) |
+                                                 (1 << ARMMMUIdx_S12NSE0));
     }
 }
 
 static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                    uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S1E2, -1);
-    }
+    tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                             (1 << ARMMMUIdx_S1E2));
 }
 
 static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                    uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S1E3, -1);
-    }
+    tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                             (1 << ARMMMUIdx_S1E3));
 }
 
 static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -3073,13 +3118,13 @@ static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     pageaddr = sextract64(value << 12, 0, 48);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdx_S2NS, -1);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S2NS));
 }
 
 static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                       uint64_t value)
 {
-    CPUState *other_cs;
+    CPUState *cs = ENV_GET_CPU(env);
     uint64_t pageaddr;
 
     if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
@@ -3088,9 +3133,8 @@ static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     pageaddr = sextract64(value << 12, 0, 48);
 
-    CPU_FOREACH(other_cs) {
-        tlb_flush_page_by_mmuidx(other_cs, pageaddr, ARMMMUIdx_S2NS, -1);
-    }
+    tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
+                                             (1 << ARMMMUIdx_S2NS));
 }
 
 static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4590,12 +4634,7 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             { .name = "ID_AA64DFR0_EL1", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 5, .opc2 = 0,
               .access = PL1_R, .type = ARM_CP_CONST,
-              /* We mask out the PMUVer field, because we don't currently
-               * implement the PMU. Not advertising it prevents the guest
-               * from trying to use it and getting UNDEFs on registers we
-               * don't implement.
-               */
-              .resetvalue = cpu->id_aa64dfr0 & ~0xf00 },
+              .resetvalue = cpu->id_aa64dfr0 },
             { .name = "ID_AA64DFR1_EL1", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 5, .opc2 = 1,
               .access = PL1_R, .type = ARM_CP_CONST,
@@ -6731,6 +6770,12 @@ void arm_cpu_do_interrupt(CPUState *cs)
         arm_cpu_do_interrupt_aarch32(cs);
     }
 
+    /* Hooks may change global state so BQL should be held, also the
+     * BQL needs to be held for any modification of
+     * cs->interrupt_request.
+     */
+    g_assert(qemu_mutex_iothread_locked());
+
     arm_call_el_change_hook(cpu);
 
     if (!kvm_enabled()) {
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 2e65bc12fa..f742a419ff 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -444,6 +444,11 @@ void hw_breakpoint_update_all(ARMCPU *cpu);
 /* Callback function for checking if a watchpoint should trigger. */
 bool arm_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp);
 
+/* Adjust addresses (in BE32 mode) before testing against watchpoint
+ * addresses.
+ */
+vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len);
+
 /* Callback function for when a watchpoint or breakpoint triggers. */
 void arm_debug_excp_handler(CPUState *cs);
 
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index c00b94e42a..395e986973 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -488,8 +488,8 @@ int kvm_arm_sync_mpstate_to_kvm(ARMCPU *cpu)
 {
     if (cap_has_mp_state) {
         struct kvm_mp_state mp_state = {
-            .mp_state =
-            cpu->powered_off ? KVM_MP_STATE_STOPPED : KVM_MP_STATE_RUNNABLE
+            .mp_state = (cpu->power_state == PSCI_OFF) ?
+            KVM_MP_STATE_STOPPED : KVM_MP_STATE_RUNNABLE
         };
         int ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MP_STATE, &mp_state);
         if (ret) {
@@ -515,7 +515,8 @@ int kvm_arm_sync_mpstate_to_qemu(ARMCPU *cpu)
                     __func__, ret, strerror(-ret));
             abort();
         }
-        cpu->powered_off = (mp_state.mp_state == KVM_MP_STATE_STOPPED);
+        cpu->power_state = (mp_state.mp_state == KVM_MP_STATE_STOPPED) ?
+            PSCI_OFF : PSCI_ON;
     }
 
     return 0;
diff --git a/target/arm/machine.c b/target/arm/machine.c
index fa5ec76090..d8094a840b 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -211,6 +211,38 @@ static const VMStateInfo vmstate_cpsr = {
     .put = put_cpsr,
 };
 
+static int get_power(QEMUFile *f, void *opaque, size_t size,
+                    VMStateField *field)
+{
+    ARMCPU *cpu = opaque;
+    bool powered_off = qemu_get_byte(f);
+    cpu->power_state = powered_off ? PSCI_OFF : PSCI_ON;
+    return 0;
+}
+
+static int put_power(QEMUFile *f, void *opaque, size_t size,
+                    VMStateField *field, QJSON *vmdesc)
+{
+    ARMCPU *cpu = opaque;
+
+    /* Migration should never happen while we transition power states */
+
+    if (cpu->power_state == PSCI_ON ||
+        cpu->power_state == PSCI_OFF) {
+        bool powered_off = (cpu->power_state == PSCI_OFF) ? true : false;
+        qemu_put_byte(f, powered_off);
+        return 0;
+    } else {
+        return 1;
+    }
+}
+
+static const VMStateInfo vmstate_powered_off = {
+    .name = "powered_off",
+    .get = get_power,
+    .put = put_power,
+};
+
 static void cpu_pre_save(void *opaque)
 {
     ARMCPU *cpu = opaque;
@@ -329,7 +361,14 @@ const VMStateDescription vmstate_arm_cpu = {
         VMSTATE_UINT64(env.exception.vaddress, ARMCPU),
         VMSTATE_TIMER_PTR(gt_timer[GTIMER_PHYS], ARMCPU),
         VMSTATE_TIMER_PTR(gt_timer[GTIMER_VIRT], ARMCPU),
-        VMSTATE_BOOL(powered_off, ARMCPU),
+        {
+            .name = "power_state",
+            .version_id = 0,
+            .size = sizeof(bool),
+            .info = &vmstate_powered_off,
+            .flags = VMS_SINGLE,
+            .offset = 0,
+        },
         VMSTATE_END_OF_LIST()
     },
     .subsections = (const VMStateDescription*[]) {
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index ba796d898e..d64c8670fa 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -18,6 +18,7 @@
  */
 #include "qemu/osdep.h"
 #include "qemu/log.h"
+#include "qemu/main-loop.h"
 #include "cpu.h"
 #include "exec/helper-proto.h"
 #include "internals.h"
@@ -435,6 +436,13 @@ void HELPER(yield)(CPUARMState *env)
     ARMCPU *cpu = arm_env_get_cpu(env);
     CPUState *cs = CPU(cpu);
 
+    /* When running in MTTCG we don't generate jumps to the yield and
+     * WFE helpers as it won't affect the scheduling of other vCPUs.
+     * If we wanted to more completely model WFE/SEV so we don't busy
+     * spin unnecessarily we would need to do something more involved.
+     */
+    g_assert(!parallel_cpus);
+
     /* This is a non-trappable hint instruction that generally indicates
      * that the guest is currently busy-looping. Yield control back to the
      * top level loop so that a more deserving VCPU has a chance to run.
@@ -487,7 +495,9 @@ void HELPER(cpsr_write_eret)(CPUARMState *env, uint32_t val)
      */
     env->regs[15] &= (env->thumb ? ~1 : ~3);
 
+    qemu_mutex_lock_iothread();
     arm_call_el_change_hook(arm_env_get_cpu(env));
+    qemu_mutex_unlock_iothread();
 }
 
 /* Access to user mode registers from privileged modes.  */
@@ -735,28 +745,58 @@ void HELPER(set_cp_reg)(CPUARMState *env, void *rip, uint32_t value)
 {
     const ARMCPRegInfo *ri = rip;
 
-    ri->writefn(env, ri, value);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        ri->writefn(env, ri, value);
+        qemu_mutex_unlock_iothread();
+    } else {
+        ri->writefn(env, ri, value);
+    }
 }
 
 uint32_t HELPER(get_cp_reg)(CPUARMState *env, void *rip)
 {
     const ARMCPRegInfo *ri = rip;
+    uint32_t res;
 
-    return ri->readfn(env, ri);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        res = ri->readfn(env, ri);
+        qemu_mutex_unlock_iothread();
+    } else {
+        res = ri->readfn(env, ri);
+    }
+
+    return res;
 }
 
 void HELPER(set_cp_reg64)(CPUARMState *env, void *rip, uint64_t value)
 {
     const ARMCPRegInfo *ri = rip;
 
-    ri->writefn(env, ri, value);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        ri->writefn(env, ri, value);
+        qemu_mutex_unlock_iothread();
+    } else {
+        ri->writefn(env, ri, value);
+    }
 }
 
 uint64_t HELPER(get_cp_reg64)(CPUARMState *env, void *rip)
 {
     const ARMCPRegInfo *ri = rip;
+    uint64_t res;
 
-    return ri->readfn(env, ri);
+    if (ri->type & ARM_CP_IO) {
+        qemu_mutex_lock_iothread();
+        res = ri->readfn(env, ri);
+        qemu_mutex_unlock_iothread();
+    } else {
+        res = ri->readfn(env, ri);
+    }
+
+    return res;
 }
 
 void HELPER(msr_i_pstate)(CPUARMState *env, uint32_t op, uint32_t imm)
@@ -989,7 +1029,9 @@ void HELPER(exception_return)(CPUARMState *env)
                       cur_el, new_el, env->pc);
     }
 
+    qemu_mutex_lock_iothread();
     arm_call_el_change_hook(arm_env_get_cpu(env));
+    qemu_mutex_unlock_iothread();
 
     return;
 
@@ -1225,6 +1267,28 @@ bool arm_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp)
     return check_watchpoints(cpu);
 }
 
+vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+    CPUARMState *env = &cpu->env;
+
+    /* In BE32 system mode, target memory is stored byteswapped (on a
+     * little-endian host system), and by the time we reach here (via an
+     * opcode helper) the addresses of subword accesses have been adjusted
+     * to account for that, which means that watchpoints will not match.
+     * Undo the adjustment here.
+     */
+    if (arm_sctlr_b(env)) {
+        if (len == 1) {
+            addr ^= 3;
+        } else if (len == 2) {
+            addr ^= 2;
+        }
+    }
+
+    return addr;
+}
+
 void arm_debug_excp_handler(CPUState *cs)
 {
     /* Called by core code when a watchpoint or breakpoint fires;
diff --git a/target/arm/psci.c b/target/arm/psci.c
index 64bf82eea1..ade9fe2ede 100644
--- a/target/arm/psci.c
+++ b/target/arm/psci.c
@@ -127,7 +127,9 @@ void arm_handle_psci_call(ARMCPU *cpu)
                 break;
             }
             target_cpu = ARM_CPU(target_cpu_state);
-            ret = target_cpu->powered_off ? 1 : 0;
+
+            g_assert(qemu_mutex_iothread_locked());
+            ret = target_cpu->power_state;
             break;
         default:
             /* Everything above affinity level 0 is always on. */
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index d0352e2045..e15eae6d41 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -379,20 +379,6 @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest)
     }
 }
 
-static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn)
-{
-    /* We don't need to save all of the syndrome so we mask and shift
-     * out uneeded bits to help the sleb128 encoder do a better job.
-     */
-    syn &= ARM_INSN_START_WORD2_MASK;
-    syn >>= ARM_INSN_START_WORD2_SHIFT;
-
-    /* We check and clear insn_start_idx to catch multiple updates.  */
-    assert(s->insn_start_idx != 0);
-    tcg_set_insn_param(s->insn_start_idx, 2, syn);
-    s->insn_start_idx = 0;
-}
-
 static void unallocated_encoding(DisasContext *s)
 {
     /* Unallocated and reserved encodings are uncategorized */
@@ -1342,10 +1328,14 @@ static void handle_hint(DisasContext *s, uint32_t insn,
         s->is_jmp = DISAS_WFI;
         return;
     case 1: /* YIELD */
-        s->is_jmp = DISAS_YIELD;
+        if (!parallel_cpus) {
+            s->is_jmp = DISAS_YIELD;
+        }
         return;
     case 2: /* WFE */
-        s->is_jmp = DISAS_WFE;
+        if (!parallel_cpus) {
+            s->is_jmp = DISAS_WFE;
+        }
         return;
     case 4: /* SEV */
     case 5: /* SEVL */
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 493c627bcf..abc1f77ee4 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -102,6 +102,49 @@ void arm_translate_init(void)
     a64_translate_init();
 }
 
+/* Flags for the disas_set_da_iss info argument:
+ * lower bits hold the Rt register number, higher bits are flags.
+ */
+typedef enum ISSInfo {
+    ISSNone = 0,
+    ISSRegMask = 0x1f,
+    ISSInvalid = (1 << 5),
+    ISSIsAcqRel = (1 << 6),
+    ISSIsWrite = (1 << 7),
+    ISSIs16Bit = (1 << 8),
+} ISSInfo;
+
+/* Save the syndrome information for a Data Abort */
+static void disas_set_da_iss(DisasContext *s, TCGMemOp memop, ISSInfo issinfo)
+{
+    uint32_t syn;
+    int sas = memop & MO_SIZE;
+    bool sse = memop & MO_SIGN;
+    bool is_acqrel = issinfo & ISSIsAcqRel;
+    bool is_write = issinfo & ISSIsWrite;
+    bool is_16bit = issinfo & ISSIs16Bit;
+    int srt = issinfo & ISSRegMask;
+
+    if (issinfo & ISSInvalid) {
+        /* Some callsites want to conditionally provide ISS info,
+         * eg "only if this was not a writeback"
+         */
+        return;
+    }
+
+    if (srt == 15) {
+        /* For AArch32, insns where the src/dest is R15 never generate
+         * ISS information. Catching that here saves checking at all
+         * the call sites.
+         */
+        return;
+    }
+
+    syn = syn_data_abort_with_iss(0, sas, sse, srt, 0, is_acqrel,
+                                  0, 0, 0, is_write, 0, is_16bit);
+    disas_set_insn_syndrome(s, syn);
+}
+
 static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s)
 {
     /* Return the mmu_idx to use for A32/T32 "unprivileged load/store"
@@ -933,6 +976,14 @@ static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val,      \
                                      TCGv_i32 a32, int index)            \
 {                                                                        \
     gen_aa32_ld_i32(s, val, a32, index, OPC | s->be_data);               \
+}                                                                        \
+static inline void gen_aa32_ld##SUFF##_iss(DisasContext *s,              \
+                                           TCGv_i32 val,                 \
+                                           TCGv_i32 a32, int index,      \
+                                           ISSInfo issinfo)              \
+{                                                                        \
+    gen_aa32_ld##SUFF(s, val, a32, index);                               \
+    disas_set_da_iss(s, OPC, issinfo);                                   \
 }
 
 #define DO_GEN_ST(SUFF, OPC)                                             \
@@ -940,6 +991,14 @@ static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val,      \
                                      TCGv_i32 a32, int index)            \
 {                                                                        \
     gen_aa32_st_i32(s, val, a32, index, OPC | s->be_data);               \
+}                                                                        \
+static inline void gen_aa32_st##SUFF##_iss(DisasContext *s,              \
+                                           TCGv_i32 val,                 \
+                                           TCGv_i32 a32, int index,      \
+                                           ISSInfo issinfo)              \
+{                                                                        \
+    gen_aa32_st##SUFF(s, val, a32, index);                               \
+    disas_set_da_iss(s, OPC, issinfo | ISSIsWrite);                      \
 }
 
 static inline void gen_aa32_frob64(DisasContext *s, TCGv_i64 val)
@@ -4345,20 +4404,32 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
     gen_rfe(s, pc, load_cpu_field(spsr));
 }
 
+/*
+ * For WFI we will halt the vCPU until an IRQ. For WFE and YIELD we
+ * only call the helper when running single threaded TCG code to ensure
+ * the next round-robin scheduled vCPU gets a crack. In MTTCG mode we
+ * just skip this instruction. Currently the SEV/SEVL instructions
+ * which are *one* of many ways to wake the CPU from WFE are not
+ * implemented so we can't sleep like WFI does.
+ */
 static void gen_nop_hint(DisasContext *s, int val)
 {
     switch (val) {
     case 1: /* yield */
-        gen_set_pc_im(s, s->pc);
-        s->is_jmp = DISAS_YIELD;
+        if (!parallel_cpus) {
+            gen_set_pc_im(s, s->pc);
+            s->is_jmp = DISAS_YIELD;
+        }
         break;
     case 3: /* wfi */
         gen_set_pc_im(s, s->pc);
         s->is_jmp = DISAS_WFI;
         break;
     case 2: /* wfe */
-        gen_set_pc_im(s, s->pc);
-        s->is_jmp = DISAS_WFE;
+        if (!parallel_cpus) {
+            gen_set_pc_im(s, s->pc);
+            s->is_jmp = DISAS_WFE;
+        }
         break;
     case 4: /* sev */
     case 5: /* sevl */
@@ -8682,16 +8753,19 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                                 tmp = tcg_temp_new_i32();
                                 switch (op1) {
                                 case 0: /* lda */
-                                    gen_aa32_ld32u(s, tmp, addr,
-                                                   get_mem_index(s));
+                                    gen_aa32_ld32u_iss(s, tmp, addr,
+                                                       get_mem_index(s),
+                                                       rd | ISSIsAcqRel);
                                     break;
                                 case 2: /* ldab */
-                                    gen_aa32_ld8u(s, tmp, addr,
-                                                  get_mem_index(s));
+                                    gen_aa32_ld8u_iss(s, tmp, addr,
+                                                      get_mem_index(s),
+                                                      rd | ISSIsAcqRel);
                                     break;
                                 case 3: /* ldah */
-                                    gen_aa32_ld16u(s, tmp, addr,
-                                                   get_mem_index(s));
+                                    gen_aa32_ld16u_iss(s, tmp, addr,
+                                                       get_mem_index(s),
+                                                       rd | ISSIsAcqRel);
                                     break;
                                 default:
                                     abort();
@@ -8702,16 +8776,19 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                                 tmp = load_reg(s, rm);
                                 switch (op1) {
                                 case 0: /* stl */
-                                    gen_aa32_st32(s, tmp, addr,
-                                                  get_mem_index(s));
+                                    gen_aa32_st32_iss(s, tmp, addr,
+                                                      get_mem_index(s),
+                                                      rm | ISSIsAcqRel);
                                     break;
                                 case 2: /* stlb */
-                                    gen_aa32_st8(s, tmp, addr,
-                                                 get_mem_index(s));
+                                    gen_aa32_st8_iss(s, tmp, addr,
+                                                     get_mem_index(s),
+                                                     rm | ISSIsAcqRel);
                                     break;
                                 case 3: /* stlh */
-                                    gen_aa32_st16(s, tmp, addr,
-                                                  get_mem_index(s));
+                                    gen_aa32_st16_iss(s, tmp, addr,
+                                                      get_mem_index(s),
+                                                      rm | ISSIsAcqRel);
                                     break;
                                 default:
                                     abort();
@@ -8782,11 +8859,18 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
             } else {
                 int address_offset;
                 bool load = insn & (1 << 20);
+                bool wbit = insn & (1 << 21);
+                bool pbit = insn & (1 << 24);
                 bool doubleword = false;
+                ISSInfo issinfo;
+
                 /* Misc load/store */
                 rn = (insn >> 16) & 0xf;
                 rd = (insn >> 12) & 0xf;
 
+                /* ISS not valid if writeback */
+                issinfo = (pbit & !wbit) ? rd : ISSInvalid;
+
                 if (!load && (sh & 2)) {
                     /* doubleword */
                     ARCH(5TE);
@@ -8799,8 +8883,9 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                 }
 
                 addr = load_reg(s, rn);
-                if (insn & (1 << 24))
+                if (pbit) {
                     gen_add_datah_offset(s, insn, 0, addr);
+                }
                 address_offset = 0;
 
                 if (doubleword) {
@@ -8829,30 +8914,33 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                     tmp = tcg_temp_new_i32();
                     switch (sh) {
                     case 1:
-                        gen_aa32_ld16u(s, tmp, addr, get_mem_index(s));
+                        gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s),
+                                           issinfo);
                         break;
                     case 2:
-                        gen_aa32_ld8s(s, tmp, addr, get_mem_index(s));
+                        gen_aa32_ld8s_iss(s, tmp, addr, get_mem_index(s),
+                                          issinfo);
                         break;
                     default:
                     case 3:
-                        gen_aa32_ld16s(s, tmp, addr, get_mem_index(s));
+                        gen_aa32_ld16s_iss(s, tmp, addr, get_mem_index(s),
+                                           issinfo);
                         break;
                     }
                 } else {
                     /* store */
                     tmp = load_reg(s, rd);
-                    gen_aa32_st16(s, tmp, addr, get_mem_index(s));
+                    gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), issinfo);
                     tcg_temp_free_i32(tmp);
                 }
                 /* Perform base writeback before the loaded value to
                    ensure correct behavior with overlapping index registers.
                    ldrd with base writeback is undefined if the
                    destination and index registers overlap.  */
-                if (!(insn & (1 << 24))) {
+                if (!pbit) {
                     gen_add_datah_offset(s, insn, address_offset, addr);
                     store_reg(s, rn, addr);
-                } else if (insn & (1 << 21)) {
+                } else if (wbit) {
                     if (address_offset)
                         tcg_gen_addi_i32(addr, addr, address_offset);
                     store_reg(s, rn, addr);
@@ -9195,17 +9283,17 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                 /* load */
                 tmp = tcg_temp_new_i32();
                 if (insn & (1 << 22)) {
-                    gen_aa32_ld8u(s, tmp, tmp2, i);
+                    gen_aa32_ld8u_iss(s, tmp, tmp2, i, rd);
                 } else {
-                    gen_aa32_ld32u(s, tmp, tmp2, i);
+                    gen_aa32_ld32u_iss(s, tmp, tmp2, i, rd);
                 }
             } else {
                 /* store */
                 tmp = load_reg(s, rd);
                 if (insn & (1 << 22)) {
-                    gen_aa32_st8(s, tmp, tmp2, i);
+                    gen_aa32_st8_iss(s, tmp, tmp2, i, rd);
                 } else {
-                    gen_aa32_st32(s, tmp, tmp2, i);
+                    gen_aa32_st32_iss(s, tmp, tmp2, i, rd);
                 }
                 tcg_temp_free_i32(tmp);
             }
@@ -9666,13 +9754,16 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                         tmp = tcg_temp_new_i32();
                         switch (op) {
                         case 0: /* ldab */
-                            gen_aa32_ld8u(s, tmp, addr, get_mem_index(s));
+                            gen_aa32_ld8u_iss(s, tmp, addr, get_mem_index(s),
+                                              rs | ISSIsAcqRel);
                             break;
                         case 1: /* ldah */
-                            gen_aa32_ld16u(s, tmp, addr, get_mem_index(s));
+                            gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s),
+                                               rs | ISSIsAcqRel);
                             break;
                         case 2: /* lda */
-                            gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
+                            gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s),
+                                               rs | ISSIsAcqRel);
                             break;
                         default:
                             abort();
@@ -9682,13 +9773,16 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                         tmp = load_reg(s, rs);
                         switch (op) {
                         case 0: /* stlb */
-                            gen_aa32_st8(s, tmp, addr, get_mem_index(s));
+                            gen_aa32_st8_iss(s, tmp, addr, get_mem_index(s),
+                                             rs | ISSIsAcqRel);
                             break;
                         case 1: /* stlh */
-                            gen_aa32_st16(s, tmp, addr, get_mem_index(s));
+                            gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s),
+                                              rs | ISSIsAcqRel);
                             break;
                         case 2: /* stl */
-                            gen_aa32_st32(s, tmp, addr, get_mem_index(s));
+                            gen_aa32_st32_iss(s, tmp, addr, get_mem_index(s),
+                                              rs | ISSIsAcqRel);
                             break;
                         default:
                             abort();
@@ -10634,6 +10728,8 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
         int postinc = 0;
         int writeback = 0;
         int memidx;
+        ISSInfo issinfo;
+
         if ((insn & 0x01100000) == 0x01000000) {
             if (disas_neon_ls_insn(s, insn)) {
                 goto illegal_op;
@@ -10737,24 +10833,27 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
                 }
             }
         }
+
+        issinfo = writeback ? ISSInvalid : rs;
+
         if (insn & (1 << 20)) {
             /* Load.  */
             tmp = tcg_temp_new_i32();
             switch (op) {
             case 0:
-                gen_aa32_ld8u(s, tmp, addr, memidx);
+                gen_aa32_ld8u_iss(s, tmp, addr, memidx, issinfo);
                 break;
             case 4:
-                gen_aa32_ld8s(s, tmp, addr, memidx);
+                gen_aa32_ld8s_iss(s, tmp, addr, memidx, issinfo);
                 break;
             case 1:
-                gen_aa32_ld16u(s, tmp, addr, memidx);
+                gen_aa32_ld16u_iss(s, tmp, addr, memidx, issinfo);
                 break;
             case 5:
-                gen_aa32_ld16s(s, tmp, addr, memidx);
+                gen_aa32_ld16s_iss(s, tmp, addr, memidx, issinfo);
                 break;
             case 2:
-                gen_aa32_ld32u(s, tmp, addr, memidx);
+                gen_aa32_ld32u_iss(s, tmp, addr, memidx, issinfo);
                 break;
             default:
                 tcg_temp_free_i32(tmp);
@@ -10771,13 +10870,13 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
             tmp = load_reg(s, rs);
             switch (op) {
             case 0:
-                gen_aa32_st8(s, tmp, addr, memidx);
+                gen_aa32_st8_iss(s, tmp, addr, memidx, issinfo);
                 break;
             case 1:
-                gen_aa32_st16(s, tmp, addr, memidx);
+                gen_aa32_st16_iss(s, tmp, addr, memidx, issinfo);
                 break;
             case 2:
-                gen_aa32_st32(s, tmp, addr, memidx);
+                gen_aa32_st32_iss(s, tmp, addr, memidx, issinfo);
                 break;
             default:
                 tcg_temp_free_i32(tmp);
@@ -10914,7 +11013,8 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
             addr = tcg_temp_new_i32();
             tcg_gen_movi_i32(addr, val);
             tmp = tcg_temp_new_i32();
-            gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s),
+                               rd | ISSIs16Bit);
             tcg_temp_free_i32(addr);
             store_reg(s, rd, tmp);
             break;
@@ -11117,28 +11217,28 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
 
         switch (op) {
         case 0: /* str */
-            gen_aa32_st32(s, tmp, addr, get_mem_index(s));
+            gen_aa32_st32_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 1: /* strh */
-            gen_aa32_st16(s, tmp, addr, get_mem_index(s));
+            gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 2: /* strb */
-            gen_aa32_st8(s, tmp, addr, get_mem_index(s));
+            gen_aa32_st8_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 3: /* ldrsb */
-            gen_aa32_ld8s(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld8s_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 4: /* ldr */
-            gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 5: /* ldrh */
-            gen_aa32_ld16u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 6: /* ldrb */
-            gen_aa32_ld8u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld8u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         case 7: /* ldrsh */
-            gen_aa32_ld16s(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld16s_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             break;
         }
         if (op >= 3) { /* load */
@@ -11182,12 +11282,12 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
         if (insn & (1 << 11)) {
             /* load */
             tmp = tcg_temp_new_i32();
-            gen_aa32_ld8u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld8u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             store_reg(s, rd, tmp);
         } else {
             /* store */
             tmp = load_reg(s, rd);
-            gen_aa32_st8(s, tmp, addr, get_mem_index(s));
+            gen_aa32_st8_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             tcg_temp_free_i32(tmp);
         }
         tcg_temp_free_i32(addr);
@@ -11204,12 +11304,12 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
         if (insn & (1 << 11)) {
             /* load */
             tmp = tcg_temp_new_i32();
-            gen_aa32_ld16u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             store_reg(s, rd, tmp);
         } else {
             /* store */
             tmp = load_reg(s, rd);
-            gen_aa32_st16(s, tmp, addr, get_mem_index(s));
+            gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             tcg_temp_free_i32(tmp);
         }
         tcg_temp_free_i32(addr);
@@ -11225,12 +11325,12 @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
         if (insn & (1 << 11)) {
             /* load */
             tmp = tcg_temp_new_i32();
-            gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
+            gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             store_reg(s, rd, tmp);
         } else {
             /* store */
             tmp = load_reg(s, rd);
-            gen_aa32_st32(s, tmp, addr, get_mem_index(s));
+            gen_aa32_st32_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit);
             tcg_temp_free_i32(tmp);
         }
         tcg_temp_free_i32(addr);
@@ -11712,6 +11812,7 @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb)
         store_cpu_field(tmp, condexec_bits);
       }
     do {
+        dc->insn_start_idx = tcg_op_buf_count();
         tcg_gen_insn_start(dc->pc,
                            (dc->condexec_cond << 4) | (dc->condexec_mask >> 1),
                            0);
diff --git a/target/arm/translate.h b/target/arm/translate.h
index 285e96f087..abb0760158 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -104,6 +104,20 @@ static inline int default_exception_el(DisasContext *s)
             ? 3 : MAX(1, s->current_el);
 }
 
+static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn)
+{
+    /* We don't need to save all of the syndrome so we mask and shift
+     * out unneeded bits to help the sleb128 encoder do a better job.
+     */
+    syn &= ARM_INSN_START_WORD2_MASK;
+    syn >>= ARM_INSN_START_WORD2_SHIFT;
+
+    /* We check and clear insn_start_idx to catch multiple updates.  */
+    assert(s->insn_start_idx != 0);
+    tcg_set_insn_param(s->insn_start_idx, 2, syn);
+    s->insn_start_idx = 0;
+}
+
 /* target-specific extra values for is_jmp */
 /* These instructions trap after executing, so the A32/T32 decoder must
  * defer them until after the conditional execution state has been updated.