summary refs log tree commit diff stats
path: root/target
diff options
context:
space:
mode:
Diffstat (limited to 'target')
-rw-r--r--target/arm/cpu-param.h2
-rw-r--r--target/arm/cpu-qom.h1
-rw-r--r--target/arm/cpu.c162
-rw-r--r--target/arm/cpu.h421
-rw-r--r--target/arm/cpu64.c1
-rw-r--r--target/arm/debug_helper.c50
-rw-r--r--target/arm/helper-a64.c2
-rw-r--r--target/arm/helper.c1207
-rw-r--r--target/arm/internals.h73
-rw-r--r--target/arm/monitor.c15
-rw-r--r--target/arm/pauth_helper.c14
-rw-r--r--target/arm/translate-a64.c47
-rw-r--r--target/arm/translate.c76
-rw-r--r--target/arm/translate.h4
14 files changed, 1390 insertions, 685 deletions
diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h
index 6e6948e960..18ac562346 100644
--- a/target/arm/cpu-param.h
+++ b/target/arm/cpu-param.h
@@ -29,6 +29,6 @@
 # define TARGET_PAGE_BITS_MIN  10
 #endif
 
-#define NB_MMU_MODES 8
+#define NB_MMU_MODES 9
 
 #endif
diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h
index 7f5b244bde..3a9d31ea9d 100644
--- a/target/arm/cpu-qom.h
+++ b/target/arm/cpu-qom.h
@@ -76,6 +76,7 @@ void arm_gt_ptimer_cb(void *opaque);
 void arm_gt_vtimer_cb(void *opaque);
 void arm_gt_htimer_cb(void *opaque);
 void arm_gt_stimer_cb(void *opaque);
+void arm_gt_hvtimer_cb(void *opaque);
 
 #define ARM_AFF0_SHIFT 0
 #define ARM_AFF0_MASK  (0xFFULL << ARM_AFF0_SHIFT)
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index f86e71a260..b0762a76c4 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -410,58 +410,173 @@ static void arm_cpu_reset(CPUState *s)
     arm_rebuild_hflags(env);
 }
 
+static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
+                                     unsigned int target_el,
+                                     unsigned int cur_el, bool secure,
+                                     uint64_t hcr_el2)
+{
+    CPUARMState *env = cs->env_ptr;
+    bool pstate_unmasked;
+    bool unmasked = false;
+
+    /*
+     * Don't take exceptions if they target a lower EL.
+     * This check should catch any exceptions that would not be taken
+     * but left pending.
+     */
+    if (cur_el > target_el) {
+        return false;
+    }
+
+    switch (excp_idx) {
+    case EXCP_FIQ:
+        pstate_unmasked = !(env->daif & PSTATE_F);
+        break;
+
+    case EXCP_IRQ:
+        pstate_unmasked = !(env->daif & PSTATE_I);
+        break;
+
+    case EXCP_VFIQ:
+        if (secure || !(hcr_el2 & HCR_FMO) || (hcr_el2 & HCR_TGE)) {
+            /* VFIQs are only taken when hypervized and non-secure.  */
+            return false;
+        }
+        return !(env->daif & PSTATE_F);
+    case EXCP_VIRQ:
+        if (secure || !(hcr_el2 & HCR_IMO) || (hcr_el2 & HCR_TGE)) {
+            /* VIRQs are only taken when hypervized and non-secure.  */
+            return false;
+        }
+        return !(env->daif & PSTATE_I);
+    default:
+        g_assert_not_reached();
+    }
+
+    /*
+     * Use the target EL, current execution state and SCR/HCR settings to
+     * determine whether the corresponding CPSR bit is used to mask the
+     * interrupt.
+     */
+    if ((target_el > cur_el) && (target_el != 1)) {
+        /* Exceptions targeting a higher EL may not be maskable */
+        if (arm_feature(env, ARM_FEATURE_AARCH64)) {
+            /*
+             * 64-bit masking rules are simple: exceptions to EL3
+             * can't be masked, and exceptions to EL2 can only be
+             * masked from Secure state. The HCR and SCR settings
+             * don't affect the masking logic, only the interrupt routing.
+             */
+            if (target_el == 3 || !secure) {
+                unmasked = true;
+            }
+        } else {
+            /*
+             * The old 32-bit-only environment has a more complicated
+             * masking setup. HCR and SCR bits not only affect interrupt
+             * routing but also change the behaviour of masking.
+             */
+            bool hcr, scr;
+
+            switch (excp_idx) {
+            case EXCP_FIQ:
+                /*
+                 * If FIQs are routed to EL3 or EL2 then there are cases where
+                 * we override the CPSR.F in determining if the exception is
+                 * masked or not. If neither of these are set then we fall back
+                 * to the CPSR.F setting otherwise we further assess the state
+                 * below.
+                 */
+                hcr = hcr_el2 & HCR_FMO;
+                scr = (env->cp15.scr_el3 & SCR_FIQ);
+
+                /*
+                 * When EL3 is 32-bit, the SCR.FW bit controls whether the
+                 * CPSR.F bit masks FIQ interrupts when taken in non-secure
+                 * state. If SCR.FW is set then FIQs can be masked by CPSR.F
+                 * when non-secure but only when FIQs are only routed to EL3.
+                 */
+                scr = scr && !((env->cp15.scr_el3 & SCR_FW) && !hcr);
+                break;
+            case EXCP_IRQ:
+                /*
+                 * When EL3 execution state is 32-bit, if HCR.IMO is set then
+                 * we may override the CPSR.I masking when in non-secure state.
+                 * The SCR.IRQ setting has already been taken into consideration
+                 * when setting the target EL, so it does not have a further
+                 * affect here.
+                 */
+                hcr = hcr_el2 & HCR_IMO;
+                scr = false;
+                break;
+            default:
+                g_assert_not_reached();
+            }
+
+            if ((scr || hcr) && !secure) {
+                unmasked = true;
+            }
+        }
+    }
+
+    /*
+     * The PSTATE bits only mask the interrupt if we have not overriden the
+     * ability above.
+     */
+    return unmasked || pstate_unmasked;
+}
+
 bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 {
     CPUClass *cc = CPU_GET_CLASS(cs);
     CPUARMState *env = cs->env_ptr;
     uint32_t cur_el = arm_current_el(env);
     bool secure = arm_is_secure(env);
+    uint64_t hcr_el2 = arm_hcr_el2_eff(env);
     uint32_t target_el;
     uint32_t excp_idx;
-    bool ret = false;
+
+    /* The prioritization of interrupts is IMPLEMENTATION DEFINED. */
 
     if (interrupt_request & CPU_INTERRUPT_FIQ) {
         excp_idx = EXCP_FIQ;
         target_el = arm_phys_excp_target_el(cs, excp_idx, cur_el, secure);
-        if (arm_excp_unmasked(cs, excp_idx, target_el)) {
-            cs->exception_index = excp_idx;
-            env->exception.target_el = target_el;
-            cc->do_interrupt(cs);
-            ret = true;
+        if (arm_excp_unmasked(cs, excp_idx, target_el,
+                              cur_el, secure, hcr_el2)) {
+            goto found;
         }
     }
     if (interrupt_request & CPU_INTERRUPT_HARD) {
         excp_idx = EXCP_IRQ;
         target_el = arm_phys_excp_target_el(cs, excp_idx, cur_el, secure);
-        if (arm_excp_unmasked(cs, excp_idx, target_el)) {
-            cs->exception_index = excp_idx;
-            env->exception.target_el = target_el;
-            cc->do_interrupt(cs);
-            ret = true;
+        if (arm_excp_unmasked(cs, excp_idx, target_el,
+                              cur_el, secure, hcr_el2)) {
+            goto found;
         }
     }
     if (interrupt_request & CPU_INTERRUPT_VIRQ) {
         excp_idx = EXCP_VIRQ;
         target_el = 1;
-        if (arm_excp_unmasked(cs, excp_idx, target_el)) {
-            cs->exception_index = excp_idx;
-            env->exception.target_el = target_el;
-            cc->do_interrupt(cs);
-            ret = true;
+        if (arm_excp_unmasked(cs, excp_idx, target_el,
+                              cur_el, secure, hcr_el2)) {
+            goto found;
         }
     }
     if (interrupt_request & CPU_INTERRUPT_VFIQ) {
         excp_idx = EXCP_VFIQ;
         target_el = 1;
-        if (arm_excp_unmasked(cs, excp_idx, target_el)) {
-            cs->exception_index = excp_idx;
-            env->exception.target_el = target_el;
-            cc->do_interrupt(cs);
-            ret = true;
+        if (arm_excp_unmasked(cs, excp_idx, target_el,
+                              cur_el, secure, hcr_el2)) {
+            goto found;
         }
     }
+    return false;
 
-    return ret;
+ found:
+    cs->exception_index = excp_idx;
+    env->exception.target_el = target_el;
+    cc->do_interrupt(cs);
+    return true;
 }
 
 #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
@@ -1272,7 +1387,6 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
         }
     }
 
-
     {
         uint64_t scale;
 
@@ -1295,6 +1409,8 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
                                               arm_gt_htimer_cb, cpu);
         cpu->gt_timer[GTIMER_SEC] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
                                               arm_gt_stimer_cb, cpu);
+        cpu->gt_timer[GTIMER_HYPVIRT] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                                  arm_gt_hvtimer_cb, cpu);
     }
 #endif
 
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 608fcbd0b7..0b3036c484 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -144,11 +144,12 @@ typedef struct ARMGenericTimer {
     uint64_t ctl; /* Timer Control register */
 } ARMGenericTimer;
 
-#define GTIMER_PHYS 0
-#define GTIMER_VIRT 1
-#define GTIMER_HYP  2
-#define GTIMER_SEC  3
-#define NUM_GTIMERS 4
+#define GTIMER_PHYS     0
+#define GTIMER_VIRT     1
+#define GTIMER_HYP      2
+#define GTIMER_SEC      3
+#define GTIMER_HYPVIRT  4
+#define NUM_GTIMERS     5
 
 typedef struct {
     uint64_t raw_tcr;
@@ -1424,13 +1425,6 @@ static inline void xpsr_write(CPUARMState *env, uint32_t val, uint32_t mask)
 #define HCR_ATA       (1ULL << 56)
 #define HCR_DCT       (1ULL << 57)
 
-/*
- * When we actually implement ARMv8.1-VHE we should add HCR_E2H to
- * HCR_MASK and then clear it again if the feature bit is not set in
- * hcr_write().
- */
-#define HCR_MASK      ((1ULL << 34) - 1)
-
 #define SCR_NS                (1U << 0)
 #define SCR_IRQ               (1U << 1)
 #define SCR_FIQ               (1U << 2)
@@ -2582,6 +2576,19 @@ struct ARMCPRegInfo {
      * fieldoffset is 0 then no reset will be done.
      */
     CPResetFn *resetfn;
+
+    /*
+     * "Original" writefn and readfn.
+     * For ARMv8.1-VHE register aliases, we overwrite the read/write
+     * accessor functions of various EL1/EL0 to perform the runtime
+     * check for which sysreg should actually be modified, and then
+     * forwards the operation.  Before overwriting the accessors,
+     * the original function is copied here, so that accesses that
+     * really do go to the EL1/EL0 version proceed normally.
+     * (The corresponding EL2 register is linked via opaque.)
+     */
+    CPReadFn *orig_readfn;
+    CPWriteFn *orig_writefn;
 };
 
 /* Macros which are lvalues for the field in CPUARMState for the
@@ -2702,117 +2709,6 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
 #define ARM_CPUID_TI915T      0x54029152
 #define ARM_CPUID_TI925T      0x54029252
 
-static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
-                                     unsigned int target_el)
-{
-    CPUARMState *env = cs->env_ptr;
-    unsigned int cur_el = arm_current_el(env);
-    bool secure = arm_is_secure(env);
-    bool pstate_unmasked;
-    int8_t unmasked = 0;
-    uint64_t hcr_el2;
-
-    /* Don't take exceptions if they target a lower EL.
-     * This check should catch any exceptions that would not be taken but left
-     * pending.
-     */
-    if (cur_el > target_el) {
-        return false;
-    }
-
-    hcr_el2 = arm_hcr_el2_eff(env);
-
-    switch (excp_idx) {
-    case EXCP_FIQ:
-        pstate_unmasked = !(env->daif & PSTATE_F);
-        break;
-
-    case EXCP_IRQ:
-        pstate_unmasked = !(env->daif & PSTATE_I);
-        break;
-
-    case EXCP_VFIQ:
-        if (secure || !(hcr_el2 & HCR_FMO) || (hcr_el2 & HCR_TGE)) {
-            /* VFIQs are only taken when hypervized and non-secure.  */
-            return false;
-        }
-        return !(env->daif & PSTATE_F);
-    case EXCP_VIRQ:
-        if (secure || !(hcr_el2 & HCR_IMO) || (hcr_el2 & HCR_TGE)) {
-            /* VIRQs are only taken when hypervized and non-secure.  */
-            return false;
-        }
-        return !(env->daif & PSTATE_I);
-    default:
-        g_assert_not_reached();
-    }
-
-    /* Use the target EL, current execution state and SCR/HCR settings to
-     * determine whether the corresponding CPSR bit is used to mask the
-     * interrupt.
-     */
-    if ((target_el > cur_el) && (target_el != 1)) {
-        /* Exceptions targeting a higher EL may not be maskable */
-        if (arm_feature(env, ARM_FEATURE_AARCH64)) {
-            /* 64-bit masking rules are simple: exceptions to EL3
-             * can't be masked, and exceptions to EL2 can only be
-             * masked from Secure state. The HCR and SCR settings
-             * don't affect the masking logic, only the interrupt routing.
-             */
-            if (target_el == 3 || !secure) {
-                unmasked = 1;
-            }
-        } else {
-            /* The old 32-bit-only environment has a more complicated
-             * masking setup. HCR and SCR bits not only affect interrupt
-             * routing but also change the behaviour of masking.
-             */
-            bool hcr, scr;
-
-            switch (excp_idx) {
-            case EXCP_FIQ:
-                /* If FIQs are routed to EL3 or EL2 then there are cases where
-                 * we override the CPSR.F in determining if the exception is
-                 * masked or not. If neither of these are set then we fall back
-                 * to the CPSR.F setting otherwise we further assess the state
-                 * below.
-                 */
-                hcr = hcr_el2 & HCR_FMO;
-                scr = (env->cp15.scr_el3 & SCR_FIQ);
-
-                /* When EL3 is 32-bit, the SCR.FW bit controls whether the
-                 * CPSR.F bit masks FIQ interrupts when taken in non-secure
-                 * state. If SCR.FW is set then FIQs can be masked by CPSR.F
-                 * when non-secure but only when FIQs are only routed to EL3.
-                 */
-                scr = scr && !((env->cp15.scr_el3 & SCR_FW) && !hcr);
-                break;
-            case EXCP_IRQ:
-                /* When EL3 execution state is 32-bit, if HCR.IMO is set then
-                 * we may override the CPSR.I masking when in non-secure state.
-                 * The SCR.IRQ setting has already been taken into consideration
-                 * when setting the target EL, so it does not have a further
-                 * affect here.
-                 */
-                hcr = hcr_el2 & HCR_IMO;
-                scr = false;
-                break;
-            default:
-                g_assert_not_reached();
-            }
-
-            if ((scr || hcr) && !secure) {
-                unmasked = 1;
-            }
-        }
-    }
-
-    /* The PSTATE bits only mask the interrupt if we have not overriden the
-     * ability above.
-     */
-    return unmasked || pstate_unmasked;
-}
-
 #define ARM_CPU_TYPE_SUFFIX "-" TYPE_ARM_CPU
 #define ARM_CPU_TYPE_NAME(name) (name ARM_CPU_TYPE_SUFFIX)
 #define CPU_RESOLVING_TYPE TYPE_ARM_CPU
@@ -2826,18 +2722,21 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
  *  + NonSecure EL1 & 0 stage 1
  *  + NonSecure EL1 & 0 stage 2
  *  + NonSecure EL2
- *  + Secure EL1 & EL0
+ *  + NonSecure EL2 & 0   (ARMv8.1-VHE)
+ *  + Secure EL1 & 0
  *  + Secure EL3
  * If EL3 is 32-bit:
  *  + NonSecure PL1 & 0 stage 1
  *  + NonSecure PL1 & 0 stage 2
  *  + NonSecure PL2
- *  + Secure PL0 & PL1
+ *  + Secure PL0
+ *  + Secure PL1
  * (reminder: for 32 bit EL3, Secure PL1 is *EL3*, not EL1.)
  *
  * For QEMU, an mmu_idx is not quite the same as a translation regime because:
- *  1. we need to split the "EL1 & 0" regimes into two mmu_idxes, because they
- *     may differ in access permissions even if the VA->PA map is the same
+ *  1. we need to split the "EL1 & 0" and "EL2 & 0" regimes into two mmu_idxes,
+ *     because they may differ in access permissions even if the VA->PA map is
+ *     the same
  *  2. we want to cache in our TLB the full VA->IPA->PA lookup for a stage 1+2
  *     translation, which means that we have one mmu_idx that deals with two
  *     concatenated translation regimes [this sort of combined s1+2 TLB is
@@ -2849,19 +2748,23 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
  *  4. we can also safely fold together the "32 bit EL3" and "64 bit EL3"
  *     translation regimes, because they map reasonably well to each other
  *     and they can't both be active at the same time.
- * This gives us the following list of mmu_idx values:
+ *  5. we want to be able to use the TLB for accesses done as part of a
+ *     stage1 page table walk, rather than having to walk the stage2 page
+ *     table over and over.
+ *
+ * This gives us the following list of cases:
  *
- * NS EL0 (aka NS PL0) stage 1+2
- * NS EL1 (aka NS PL1) stage 1+2
+ * NS EL0 EL1&0 stage 1+2 (aka NS PL0)
+ * NS EL1 EL1&0 stage 1+2 (aka NS PL1)
+ * NS EL0 EL2&0
+ * NS EL2 EL2&0
  * NS EL2 (aka NS PL2)
+ * S EL0 EL1&0 (aka S PL0)
+ * S EL1 EL1&0 (not used if EL3 is 32 bit)
  * S EL3 (aka S PL1)
- * S EL0 (aka S PL0)
- * S EL1 (not used if EL3 is 32 bit)
- * NS EL0+1 stage 2
+ * NS EL1&0 stage 2
  *
- * (The last of these is an mmu_idx because we want to be able to use the TLB
- * for the accesses done as part of a stage 1 page table walk, rather than
- * having to walk the stage 2 page table over and over.)
+ * for a total of 9 different mmu_idx.
  *
  * R profile CPUs have an MPU, but can use the same set of MMU indexes
  * as A profile. They only need to distinguish NS EL0 and NS EL1 (and
@@ -2899,106 +2802,88 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx,
  * For M profile we arrange them to have a bit for priv, a bit for negpri
  * and a bit for secure.
  */
-#define ARM_MMU_IDX_A 0x10 /* A profile */
-#define ARM_MMU_IDX_NOTLB 0x20 /* does not have a TLB */
-#define ARM_MMU_IDX_M 0x40 /* M profile */
+#define ARM_MMU_IDX_A     0x10  /* A profile */
+#define ARM_MMU_IDX_NOTLB 0x20  /* does not have a TLB */
+#define ARM_MMU_IDX_M     0x40  /* M profile */
 
-/* meanings of the bits for M profile mmu idx values */
-#define ARM_MMU_IDX_M_PRIV 0x1
+/* Meanings of the bits for M profile mmu idx values */
+#define ARM_MMU_IDX_M_PRIV   0x1
 #define ARM_MMU_IDX_M_NEGPRI 0x2
-#define ARM_MMU_IDX_M_S 0x4
+#define ARM_MMU_IDX_M_S      0x4  /* Secure */
 
-#define ARM_MMU_IDX_TYPE_MASK (~0x7)
-#define ARM_MMU_IDX_COREIDX_MASK 0x7
+#define ARM_MMU_IDX_TYPE_MASK \
+    (ARM_MMU_IDX_A | ARM_MMU_IDX_M | ARM_MMU_IDX_NOTLB)
+#define ARM_MMU_IDX_COREIDX_MASK 0xf
 
 typedef enum ARMMMUIdx {
-    ARMMMUIdx_S12NSE0 = 0 | ARM_MMU_IDX_A,
-    ARMMMUIdx_S12NSE1 = 1 | ARM_MMU_IDX_A,
-    ARMMMUIdx_S1E2 = 2 | ARM_MMU_IDX_A,
-    ARMMMUIdx_S1E3 = 3 | ARM_MMU_IDX_A,
-    ARMMMUIdx_S1SE0 = 4 | ARM_MMU_IDX_A,
-    ARMMMUIdx_S1SE1 = 5 | ARM_MMU_IDX_A,
-    ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A,
-    ARMMMUIdx_MUser = 0 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MPriv = 1 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MUserNegPri = 2 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MPrivNegPri = 3 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSUser = 4 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSPriv = 5 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSUserNegPri = 6 | ARM_MMU_IDX_M,
-    ARMMMUIdx_MSPrivNegPri = 7 | ARM_MMU_IDX_M,
-    /* Indexes below here don't have TLBs and are used only for AT system
-     * instructions or for the first stage of an S12 page table walk.
+    /*
+     * A-profile.
      */
-    ARMMMUIdx_S1NSE0 = 0 | ARM_MMU_IDX_NOTLB,
-    ARMMMUIdx_S1NSE1 = 1 | ARM_MMU_IDX_NOTLB,
-} ARMMMUIdx;
+    ARMMMUIdx_E10_0 =  0 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_0 =  1 | ARM_MMU_IDX_A,
 
-/* Bit macros for the core-mmu-index values for each index,
- * for use when calling tlb_flush_by_mmuidx() and friends.
- */
-typedef enum ARMMMUIdxBit {
-    ARMMMUIdxBit_S12NSE0 = 1 << 0,
-    ARMMMUIdxBit_S12NSE1 = 1 << 1,
-    ARMMMUIdxBit_S1E2 = 1 << 2,
-    ARMMMUIdxBit_S1E3 = 1 << 3,
-    ARMMMUIdxBit_S1SE0 = 1 << 4,
-    ARMMMUIdxBit_S1SE1 = 1 << 5,
-    ARMMMUIdxBit_S2NS = 1 << 6,
-    ARMMMUIdxBit_MUser = 1 << 0,
-    ARMMMUIdxBit_MPriv = 1 << 1,
-    ARMMMUIdxBit_MUserNegPri = 1 << 2,
-    ARMMMUIdxBit_MPrivNegPri = 1 << 3,
-    ARMMMUIdxBit_MSUser = 1 << 4,
-    ARMMMUIdxBit_MSPriv = 1 << 5,
-    ARMMMUIdxBit_MSUserNegPri = 1 << 6,
-    ARMMMUIdxBit_MSPrivNegPri = 1 << 7,
-} ARMMMUIdxBit;
+    ARMMMUIdx_E10_1 =  2 | ARM_MMU_IDX_A,
 
-#define MMU_USER_IDX 0
+    ARMMMUIdx_E2 =     3 | ARM_MMU_IDX_A,
+    ARMMMUIdx_E20_2 =  4 | ARM_MMU_IDX_A,
 
-static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx)
-{
-    return mmu_idx & ARM_MMU_IDX_COREIDX_MASK;
-}
+    ARMMMUIdx_SE10_0 = 5 | ARM_MMU_IDX_A,
+    ARMMMUIdx_SE10_1 = 6 | ARM_MMU_IDX_A,
+    ARMMMUIdx_SE3 =    7 | ARM_MMU_IDX_A,
 
-static inline ARMMMUIdx core_to_arm_mmu_idx(CPUARMState *env, int mmu_idx)
-{
-    if (arm_feature(env, ARM_FEATURE_M)) {
-        return mmu_idx | ARM_MMU_IDX_M;
-    } else {
-        return mmu_idx | ARM_MMU_IDX_A;
-    }
-}
+    ARMMMUIdx_Stage2 = 8 | ARM_MMU_IDX_A,
 
-/* Return the exception level we're running at if this is our mmu_idx */
-static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
-{
-    switch (mmu_idx & ARM_MMU_IDX_TYPE_MASK) {
-    case ARM_MMU_IDX_A:
-        return mmu_idx & 3;
-    case ARM_MMU_IDX_M:
-        return mmu_idx & ARM_MMU_IDX_M_PRIV;
-    default:
-        g_assert_not_reached();
-    }
-}
+    /*
+     * These are not allocated TLBs and are used only for AT system
+     * instructions or for the first stage of an S12 page table walk.
+     */
+    ARMMMUIdx_Stage1_E0 = 0 | ARM_MMU_IDX_NOTLB,
+    ARMMMUIdx_Stage1_E1 = 1 | ARM_MMU_IDX_NOTLB,
+
+    /*
+     * M-profile.
+     */
+    ARMMMUIdx_MUser = ARM_MMU_IDX_M,
+    ARMMMUIdx_MPriv = ARM_MMU_IDX_M | ARM_MMU_IDX_M_PRIV,
+    ARMMMUIdx_MUserNegPri = ARMMMUIdx_MUser | ARM_MMU_IDX_M_NEGPRI,
+    ARMMMUIdx_MPrivNegPri = ARMMMUIdx_MPriv | ARM_MMU_IDX_M_NEGPRI,
+    ARMMMUIdx_MSUser = ARMMMUIdx_MUser | ARM_MMU_IDX_M_S,
+    ARMMMUIdx_MSPriv = ARMMMUIdx_MPriv | ARM_MMU_IDX_M_S,
+    ARMMMUIdx_MSUserNegPri = ARMMMUIdx_MUserNegPri | ARM_MMU_IDX_M_S,
+    ARMMMUIdx_MSPrivNegPri = ARMMMUIdx_MPrivNegPri | ARM_MMU_IDX_M_S,
+} ARMMMUIdx;
 
 /*
- * Return the MMU index for a v7M CPU with all relevant information
- * manually specified.
+ * Bit macros for the core-mmu-index values for each index,
+ * for use when calling tlb_flush_by_mmuidx() and friends.
  */
-ARMMMUIdx arm_v7m_mmu_idx_all(CPUARMState *env,
-                              bool secstate, bool priv, bool negpri);
+#define TO_CORE_BIT(NAME) \
+    ARMMMUIdxBit_##NAME = 1 << (ARMMMUIdx_##NAME & ARM_MMU_IDX_COREIDX_MASK)
 
-/* Return the MMU index for a v7M CPU in the specified security and
- * privilege state.
- */
-ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env,
-                                                bool secstate, bool priv);
+typedef enum ARMMMUIdxBit {
+    TO_CORE_BIT(E10_0),
+    TO_CORE_BIT(E20_0),
+    TO_CORE_BIT(E10_1),
+    TO_CORE_BIT(E2),
+    TO_CORE_BIT(E20_2),
+    TO_CORE_BIT(SE10_0),
+    TO_CORE_BIT(SE10_1),
+    TO_CORE_BIT(SE3),
+    TO_CORE_BIT(Stage2),
+
+    TO_CORE_BIT(MUser),
+    TO_CORE_BIT(MPriv),
+    TO_CORE_BIT(MUserNegPri),
+    TO_CORE_BIT(MPrivNegPri),
+    TO_CORE_BIT(MSUser),
+    TO_CORE_BIT(MSPriv),
+    TO_CORE_BIT(MSUserNegPri),
+    TO_CORE_BIT(MSPrivNegPri),
+} ARMMMUIdxBit;
 
-/* Return the MMU index for a v7M CPU in the specified security state */
-ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate);
+#undef TO_CORE_BIT
+
+#define MMU_USER_IDX 0
 
 /**
  * cpu_mmu_index:
@@ -3159,15 +3044,7 @@ static inline bool arm_sctlr_b(CPUARMState *env)
         (env->cp15.sctlr_el[1] & SCTLR_B) != 0;
 }
 
-static inline uint64_t arm_sctlr(CPUARMState *env, int el)
-{
-    if (el == 0) {
-        /* FIXME: ARMv8.1-VHE S2 translation regime.  */
-        return env->cp15.sctlr_el[1];
-    } else {
-        return env->cp15.sctlr_el[el];
-    }
-}
+uint64_t arm_sctlr(CPUARMState *env, int el);
 
 static inline bool arm_cpu_data_is_big_endian_a32(CPUARMState *env,
                                                   bool sctlr_b)
@@ -3221,55 +3098,73 @@ typedef ARMCPU ArchCPU;
  * We put flags which are shared between 32 and 64 bit mode at the top
  * of the word, and flags which apply to only one mode at the bottom.
  *
+ *  31          20    18    14          9              0
+ * +--------------+-----+-----+----------+--------------+
+ * |              |     |   TBFLAG_A32   |              |
+ * |              |     +-----+----------+  TBFLAG_AM32 |
+ * |  TBFLAG_ANY  |           |TBFLAG_M32|              |
+ * |              |         +-+----------+--------------|
+ * |              |         |         TBFLAG_A64        |
+ * +--------------+---------+---------------------------+
+ *  31          20        15                           0
+ *
  * Unless otherwise noted, these bits are cached in env->hflags.
  */
 FIELD(TBFLAG_ANY, AARCH64_STATE, 31, 1)
-FIELD(TBFLAG_ANY, MMUIDX, 28, 3)
-FIELD(TBFLAG_ANY, SS_ACTIVE, 27, 1)
-FIELD(TBFLAG_ANY, PSTATE_SS, 26, 1)     /* Not cached. */
+FIELD(TBFLAG_ANY, SS_ACTIVE, 30, 1)
+FIELD(TBFLAG_ANY, PSTATE_SS, 29, 1)     /* Not cached. */
+FIELD(TBFLAG_ANY, BE_DATA, 28, 1)
+FIELD(TBFLAG_ANY, MMUIDX, 24, 4)
 /* Target EL if we take a floating-point-disabled exception */
-FIELD(TBFLAG_ANY, FPEXC_EL, 24, 2)
-FIELD(TBFLAG_ANY, BE_DATA, 23, 1)
+FIELD(TBFLAG_ANY, FPEXC_EL, 22, 2)
+/* For A-profile only, target EL for debug exceptions.  */
+FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 20, 2)
+
 /*
- * For A-profile only, target EL for debug exceptions.
- * Note that this overlaps with the M-profile-only HANDLER and STACKCHECK bits.
+ * Bit usage when in AArch32 state, both A- and M-profile.
  */
-FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 21, 2)
+FIELD(TBFLAG_AM32, CONDEXEC, 0, 8)      /* Not cached. */
+FIELD(TBFLAG_AM32, THUMB, 8, 1)         /* Not cached. */
 
-/* Bit usage when in AArch32 state: */
-FIELD(TBFLAG_A32, THUMB, 0, 1)          /* Not cached. */
-FIELD(TBFLAG_A32, VECLEN, 1, 3)         /* Not cached. */
-FIELD(TBFLAG_A32, VECSTRIDE, 4, 2)      /* Not cached. */
+/*
+ * Bit usage when in AArch32 state, for A-profile only.
+ */
+FIELD(TBFLAG_A32, VECLEN, 9, 3)         /* Not cached. */
+FIELD(TBFLAG_A32, VECSTRIDE, 12, 2)     /* Not cached. */
 /*
  * We store the bottom two bits of the CPAR as TB flags and handle
  * checks on the other bits at runtime. This shares the same bits as
  * VECSTRIDE, which is OK as no XScale CPU has VFP.
  * Not cached, because VECLEN+VECSTRIDE are not cached.
  */
-FIELD(TBFLAG_A32, XSCALE_CPAR, 4, 2)
+FIELD(TBFLAG_A32, XSCALE_CPAR, 12, 2)
+FIELD(TBFLAG_A32, VFPEN, 14, 1)         /* Partially cached, minus FPEXC. */
+FIELD(TBFLAG_A32, SCTLR_B, 15, 1)
+FIELD(TBFLAG_A32, HSTR_ACTIVE, 16, 1)
 /*
  * Indicates whether cp register reads and writes by guest code should access
  * the secure or nonsecure bank of banked registers; note that this is not
  * the same thing as the current security state of the processor!
  */
-FIELD(TBFLAG_A32, NS, 6, 1)
-FIELD(TBFLAG_A32, VFPEN, 7, 1)          /* Partially cached, minus FPEXC. */
-FIELD(TBFLAG_A32, CONDEXEC, 8, 8)       /* Not cached. */
-FIELD(TBFLAG_A32, SCTLR_B, 16, 1)
-FIELD(TBFLAG_A32, HSTR_ACTIVE, 17, 1)
-
-/* For M profile only, set if FPCCR.LSPACT is set */
-FIELD(TBFLAG_A32, LSPACT, 18, 1)        /* Not cached. */
-/* For M profile only, set if we must create a new FP context */
-FIELD(TBFLAG_A32, NEW_FP_CTXT_NEEDED, 19, 1) /* Not cached. */
-/* For M profile only, set if FPCCR.S does not match current security state */
-FIELD(TBFLAG_A32, FPCCR_S_WRONG, 20, 1) /* Not cached. */
-/* For M profile only, Handler (ie not Thread) mode */
-FIELD(TBFLAG_A32, HANDLER, 21, 1)
-/* For M profile only, whether we should generate stack-limit checks */
-FIELD(TBFLAG_A32, STACKCHECK, 22, 1)
-
-/* Bit usage when in AArch64 state */
+FIELD(TBFLAG_A32, NS, 17, 1)
+
+/*
+ * Bit usage when in AArch32 state, for M-profile only.
+ */
+/* Handler (ie not Thread) mode */
+FIELD(TBFLAG_M32, HANDLER, 9, 1)
+/* Whether we should generate stack-limit checks */
+FIELD(TBFLAG_M32, STACKCHECK, 10, 1)
+/* Set if FPCCR.LSPACT is set */
+FIELD(TBFLAG_M32, LSPACT, 11, 1)                 /* Not cached. */
+/* Set if we must create a new FP context */
+FIELD(TBFLAG_M32, NEW_FP_CTXT_NEEDED, 12, 1)     /* Not cached. */
+/* Set if FPCCR.S does not match current security state */
+FIELD(TBFLAG_M32, FPCCR_S_WRONG, 13, 1)          /* Not cached. */
+
+/*
+ * Bit usage when in AArch64 state
+ */
 FIELD(TBFLAG_A64, TBII, 0, 2)
 FIELD(TBFLAG_A64, SVEEXC_EL, 2, 2)
 FIELD(TBFLAG_A64, ZCR_LEN, 4, 4)
@@ -3277,6 +3172,7 @@ FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1)
 FIELD(TBFLAG_A64, BT, 9, 1)
 FIELD(TBFLAG_A64, BTYPE, 10, 2)         /* Not cached. */
 FIELD(TBFLAG_A64, TBID, 12, 2)
+FIELD(TBFLAG_A64, UNPRIV, 14, 1)
 
 static inline bool bswap_code(bool sctlr_b)
 {
@@ -3685,6 +3581,11 @@ static inline bool isar_feature_aa64_sve(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0;
 }
 
+static inline bool isar_feature_aa64_vh(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0;
+}
+
 static inline bool isar_feature_aa64_lor(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0;
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 2d97bf45e1..c80fb5fd43 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -672,6 +672,7 @@ static void aarch64_max_initfn(Object *obj)
         t = cpu->isar.id_aa64mmfr1;
         t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* HPD */
         t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1);
+        t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1);
         cpu->isar.id_aa64mmfr1 = t;
 
         /* Replicate the same data to the 32-bit id registers.  */
diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index dde80273ff..2e3e90c6a5 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -20,6 +20,7 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn)
     int ctx_cmps = extract32(cpu->dbgdidr, 20, 4);
     int bt;
     uint32_t contextidr;
+    uint64_t hcr_el2;
 
     /*
      * Links to unimplemented or non-context aware breakpoints are
@@ -40,24 +41,44 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn)
     }
 
     bt = extract64(bcr, 20, 4);
-
-    /*
-     * We match the whole register even if this is AArch32 using the
-     * short descriptor format (in which case it holds both PROCID and ASID),
-     * since we don't implement the optional v7 context ID masking.
-     */
-    contextidr = extract64(env->cp15.contextidr_el[1], 0, 32);
+    hcr_el2 = arm_hcr_el2_eff(env);
 
     switch (bt) {
     case 3: /* linked context ID match */
-        if (arm_current_el(env) > 1) {
-            /* Context matches never fire in EL2 or (AArch64) EL3 */
+        switch (arm_current_el(env)) {
+        default:
+            /* Context matches never fire in AArch64 EL3 */
             return false;
+        case 2:
+            if (!(hcr_el2 & HCR_E2H)) {
+                /* Context matches never fire in EL2 without E2H enabled. */
+                return false;
+            }
+            contextidr = env->cp15.contextidr_el[2];
+            break;
+        case 1:
+            contextidr = env->cp15.contextidr_el[1];
+            break;
+        case 0:
+            if ((hcr_el2 & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+                contextidr = env->cp15.contextidr_el[2];
+            } else {
+                contextidr = env->cp15.contextidr_el[1];
+            }
+            break;
         }
-        return (contextidr == extract64(env->cp15.dbgbvr[lbn], 0, 32));
-    case 5: /* linked address mismatch (reserved in AArch64) */
+        break;
+
+    case 7:  /* linked contextidr_el1 match */
+        contextidr = env->cp15.contextidr_el[1];
+        break;
+    case 13: /* linked contextidr_el2 match */
+        contextidr = env->cp15.contextidr_el[2];
+        break;
+
     case 9: /* linked VMID match (reserved if no EL2) */
     case 11: /* linked context ID and VMID match (reserved if no EL2) */
+    case 15: /* linked full context ID match */
     default:
         /*
          * Links to Unlinked context breakpoints must generate no
@@ -66,7 +87,12 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn)
         return false;
     }
 
-    return false;
+    /*
+     * We match the whole register even if this is AArch32 using the
+     * short descriptor format (in which case it holds both PROCID and ASID),
+     * since we don't implement the optional v7 context ID masking.
+     */
+    return contextidr == (uint32_t)env->cp15.dbgbvr[lbn];
 }
 
 static bool bp_wp_matches(ARMCPU *cpu, int n, bool is_wp)
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index 36aa6badfd..bf45f8a785 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -70,7 +70,7 @@ static void daif_check(CPUARMState *env, uint32_t op,
                        uint32_t imm, uintptr_t ra)
 {
     /* DAIF update to PSTATE. This is OK from EL0 only if UMA is set.  */
-    if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UMA)) {
+    if (arm_current_el(env) == 0 && !(arm_sctlr(env, 0) & SCTLR_UMA)) {
         raise_exception_ra(env, EXCP_UDEF,
                            syn_aa64_sysregtrap(0, extract32(op, 0, 3),
                                                extract32(op, 3, 3), 4,
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 19a57a17da..7d15d5c933 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -614,56 +614,54 @@ static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri,
                           uint64_t value)
 {
     /* Invalidate all (TLBIALL) */
-    ARMCPU *cpu = env_archcpu(env);
+    CPUState *cs = env_cpu(env);
 
     if (tlb_force_broadcast(env)) {
-        tlbiall_is_write(env, NULL, value);
-        return;
+        tlb_flush_all_cpus_synced(cs);
+    } else {
+        tlb_flush(cs);
     }
-
-    tlb_flush(CPU(cpu));
 }
 
 static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri,
                           uint64_t value)
 {
     /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */
-    ARMCPU *cpu = env_archcpu(env);
+    CPUState *cs = env_cpu(env);
 
+    value &= TARGET_PAGE_MASK;
     if (tlb_force_broadcast(env)) {
-        tlbimva_is_write(env, NULL, value);
-        return;
+        tlb_flush_page_all_cpus_synced(cs, value);
+    } else {
+        tlb_flush_page(cs, value);
     }
-
-    tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK);
 }
 
 static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri,
                            uint64_t value)
 {
     /* Invalidate by ASID (TLBIASID) */
-    ARMCPU *cpu = env_archcpu(env);
+    CPUState *cs = env_cpu(env);
 
     if (tlb_force_broadcast(env)) {
-        tlbiasid_is_write(env, NULL, value);
-        return;
+        tlb_flush_all_cpus_synced(cs);
+    } else {
+        tlb_flush(cs);
     }
-
-    tlb_flush(CPU(cpu));
 }
 
 static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri,
                            uint64_t value)
 {
     /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */
-    ARMCPU *cpu = env_archcpu(env);
+    CPUState *cs = env_cpu(env);
 
+    value &= TARGET_PAGE_MASK;
     if (tlb_force_broadcast(env)) {
-        tlbimvaa_is_write(env, NULL, value);
-        return;
+        tlb_flush_page_all_cpus_synced(cs, value);
+    } else {
+        tlb_flush_page(cs, value);
     }
-
-    tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK);
 }
 
 static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -672,9 +670,9 @@ static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = env_cpu(env);
 
     tlb_flush_by_mmuidx(cs,
-                        ARMMMUIdxBit_S12NSE1 |
-                        ARMMMUIdxBit_S12NSE0 |
-                        ARMMMUIdxBit_S2NS);
+                        ARMMMUIdxBit_E10_1 |
+                        ARMMMUIdxBit_E10_0 |
+                        ARMMMUIdxBit_Stage2);
 }
 
 static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -683,9 +681,9 @@ static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = env_cpu(env);
 
     tlb_flush_by_mmuidx_all_cpus_synced(cs,
-                                        ARMMMUIdxBit_S12NSE1 |
-                                        ARMMMUIdxBit_S12NSE0 |
-                                        ARMMMUIdxBit_S2NS);
+                                        ARMMMUIdxBit_E10_1 |
+                                        ARMMMUIdxBit_E10_0 |
+                                        ARMMMUIdxBit_Stage2);
 }
 
 static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -706,7 +704,7 @@ static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     pageaddr = sextract64(value << 12, 0, 40);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S2NS);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2);
 }
 
 static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -722,7 +720,7 @@ static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     pageaddr = sextract64(value << 12, 0, 40);
 
     tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                             ARMMMUIdxBit_S2NS);
+                                             ARMMMUIdxBit_Stage2);
 }
 
 static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -730,7 +728,7 @@ static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     CPUState *cs = env_cpu(env);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E2);
+    tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E2);
 }
 
 static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -738,7 +736,7 @@ static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     CPUState *cs = env_cpu(env);
 
-    tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E2);
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E2);
 }
 
 static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -747,7 +745,7 @@ static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
     CPUState *cs = env_cpu(env);
     uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E2);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E2);
 }
 
 static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -757,7 +755,7 @@ static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12);
 
     tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                             ARMMMUIdxBit_S1E2);
+                                             ARMMMUIdxBit_E2);
 }
 
 static const ARMCPRegInfo cp_reginfo[] = {
@@ -2326,10 +2324,18 @@ static CPAccessResult gt_cntfrq_access(CPUARMState *env, const ARMCPRegInfo *ri,
      * Writable only at the highest implemented exception level.
      */
     int el = arm_current_el(env);
+    uint64_t hcr;
+    uint32_t cntkctl;
 
     switch (el) {
     case 0:
-        if (!extract32(env->cp15.c14_cntkctl, 0, 2)) {
+        hcr = arm_hcr_el2_eff(env);
+        if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+            cntkctl = env->cp15.cnthctl_el2;
+        } else {
+            cntkctl = env->cp15.c14_cntkctl;
+        }
+        if (!extract32(cntkctl, 0, 2)) {
             return CP_ACCESS_TRAP;
         }
         break;
@@ -2357,17 +2363,47 @@ static CPAccessResult gt_counter_access(CPUARMState *env, int timeridx,
 {
     unsigned int cur_el = arm_current_el(env);
     bool secure = arm_is_secure(env);
+    uint64_t hcr = arm_hcr_el2_eff(env);
 
-    /* CNT[PV]CT: not visible from PL0 if ELO[PV]CTEN is zero */
-    if (cur_el == 0 &&
-        !extract32(env->cp15.c14_cntkctl, timeridx, 1)) {
-        return CP_ACCESS_TRAP;
-    }
+    switch (cur_el) {
+    case 0:
+        /* If HCR_EL2.<E2H,TGE> == '11': check CNTHCTL_EL2.EL0[PV]CTEN. */
+        if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+            return (extract32(env->cp15.cnthctl_el2, timeridx, 1)
+                    ? CP_ACCESS_OK : CP_ACCESS_TRAP_EL2);
+        }
 
-    if (arm_feature(env, ARM_FEATURE_EL2) &&
-        timeridx == GTIMER_PHYS && !secure && cur_el < 2 &&
-        !extract32(env->cp15.cnthctl_el2, 0, 1)) {
-        return CP_ACCESS_TRAP_EL2;
+        /* CNT[PV]CT: not visible from PL0 if EL0[PV]CTEN is zero */
+        if (!extract32(env->cp15.c14_cntkctl, timeridx, 1)) {
+            return CP_ACCESS_TRAP;
+        }
+
+        /* If HCR_EL2.<E2H,TGE> == '10': check CNTHCTL_EL2.EL1PCTEN. */
+        if (hcr & HCR_E2H) {
+            if (timeridx == GTIMER_PHYS &&
+                !extract32(env->cp15.cnthctl_el2, 10, 1)) {
+                return CP_ACCESS_TRAP_EL2;
+            }
+        } else {
+            /* If HCR_EL2.<E2H> == 0: check CNTHCTL_EL2.EL1PCEN. */
+            if (arm_feature(env, ARM_FEATURE_EL2) &&
+                timeridx == GTIMER_PHYS && !secure &&
+                !extract32(env->cp15.cnthctl_el2, 1, 1)) {
+                return CP_ACCESS_TRAP_EL2;
+            }
+        }
+        break;
+
+    case 1:
+        /* Check CNTHCTL_EL2.EL1PCTEN, which changes location based on E2H. */
+        if (arm_feature(env, ARM_FEATURE_EL2) &&
+            timeridx == GTIMER_PHYS && !secure &&
+            (hcr & HCR_E2H
+             ? !extract32(env->cp15.cnthctl_el2, 10, 1)
+             : !extract32(env->cp15.cnthctl_el2, 0, 1))) {
+            return CP_ACCESS_TRAP_EL2;
+        }
+        break;
     }
     return CP_ACCESS_OK;
 }
@@ -2377,19 +2413,41 @@ static CPAccessResult gt_timer_access(CPUARMState *env, int timeridx,
 {
     unsigned int cur_el = arm_current_el(env);
     bool secure = arm_is_secure(env);
+    uint64_t hcr = arm_hcr_el2_eff(env);
 
-    /* CNT[PV]_CVAL, CNT[PV]_CTL, CNT[PV]_TVAL: not visible from PL0 if
-     * EL0[PV]TEN is zero.
-     */
-    if (cur_el == 0 &&
-        !extract32(env->cp15.c14_cntkctl, 9 - timeridx, 1)) {
-        return CP_ACCESS_TRAP;
-    }
+    switch (cur_el) {
+    case 0:
+        if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+            /* If HCR_EL2.<E2H,TGE> == '11': check CNTHCTL_EL2.EL0[PV]TEN. */
+            return (extract32(env->cp15.cnthctl_el2, 9 - timeridx, 1)
+                    ? CP_ACCESS_OK : CP_ACCESS_TRAP_EL2);
+        }
 
-    if (arm_feature(env, ARM_FEATURE_EL2) &&
-        timeridx == GTIMER_PHYS && !secure && cur_el < 2 &&
-        !extract32(env->cp15.cnthctl_el2, 1, 1)) {
-        return CP_ACCESS_TRAP_EL2;
+        /*
+         * CNT[PV]_CVAL, CNT[PV]_CTL, CNT[PV]_TVAL: not visible from
+         * EL0 if EL0[PV]TEN is zero.
+         */
+        if (!extract32(env->cp15.c14_cntkctl, 9 - timeridx, 1)) {
+            return CP_ACCESS_TRAP;
+        }
+        /* fall through */
+
+    case 1:
+        if (arm_feature(env, ARM_FEATURE_EL2) &&
+            timeridx == GTIMER_PHYS && !secure) {
+            if (hcr & HCR_E2H) {
+                /* If HCR_EL2.<E2H,TGE> == '10': check CNTHCTL_EL2.EL1PTEN. */
+                if (!extract32(env->cp15.cnthctl_el2, 11, 1)) {
+                    return CP_ACCESS_TRAP_EL2;
+                }
+            } else {
+                /* If HCR_EL2.<E2H> == 0: check CNTHCTL_EL2.EL1PCEN. */
+                if (!extract32(env->cp15.cnthctl_el2, 1, 1)) {
+                    return CP_ACCESS_TRAP_EL2;
+                }
+            }
+        }
+        break;
     }
     return CP_ACCESS_OK;
 }
@@ -2515,9 +2573,31 @@ static uint64_t gt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri)
     return gt_get_countervalue(env);
 }
 
+static uint64_t gt_virt_cnt_offset(CPUARMState *env)
+{
+    uint64_t hcr;
+
+    switch (arm_current_el(env)) {
+    case 2:
+        hcr = arm_hcr_el2_eff(env);
+        if (hcr & HCR_E2H) {
+            return 0;
+        }
+        break;
+    case 0:
+        hcr = arm_hcr_el2_eff(env);
+        if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+            return 0;
+        }
+        break;
+    }
+
+    return env->cp15.cntvoff_el2;
+}
+
 static uint64_t gt_virt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-    return gt_get_countervalue(env) - env->cp15.cntvoff_el2;
+    return gt_get_countervalue(env) - gt_virt_cnt_offset(env);
 }
 
 static void gt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -2532,7 +2612,14 @@ static void gt_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static uint64_t gt_tval_read(CPUARMState *env, const ARMCPRegInfo *ri,
                              int timeridx)
 {
-    uint64_t offset = timeridx == GTIMER_VIRT ? env->cp15.cntvoff_el2 : 0;
+    uint64_t offset = 0;
+
+    switch (timeridx) {
+    case GTIMER_VIRT:
+    case GTIMER_HYPVIRT:
+        offset = gt_virt_cnt_offset(env);
+        break;
+    }
 
     return (uint32_t)(env->cp15.c14_timer[timeridx].cval -
                       (gt_get_countervalue(env) - offset));
@@ -2542,7 +2629,14 @@ static void gt_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
                           int timeridx,
                           uint64_t value)
 {
-    uint64_t offset = timeridx == GTIMER_VIRT ? env->cp15.cntvoff_el2 : 0;
+    uint64_t offset = 0;
+
+    switch (timeridx) {
+    case GTIMER_VIRT:
+    case GTIMER_HYPVIRT:
+        offset = gt_virt_cnt_offset(env);
+        break;
+    }
 
     trace_arm_gt_tval_write(timeridx, value);
     env->cp15.c14_timer[timeridx].cval = gt_get_countervalue(env) - offset +
@@ -2601,6 +2695,70 @@ static void gt_phys_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
     gt_ctl_write(env, ri, GTIMER_PHYS, value);
 }
 
+static int gt_phys_redir_timeridx(CPUARMState *env)
+{
+    switch (arm_mmu_idx(env)) {
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E20_2:
+        return GTIMER_HYP;
+    default:
+        return GTIMER_PHYS;
+    }
+}
+
+static int gt_virt_redir_timeridx(CPUARMState *env)
+{
+    switch (arm_mmu_idx(env)) {
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E20_2:
+        return GTIMER_HYPVIRT;
+    default:
+        return GTIMER_VIRT;
+    }
+}
+
+static uint64_t gt_phys_redir_cval_read(CPUARMState *env,
+                                        const ARMCPRegInfo *ri)
+{
+    int timeridx = gt_phys_redir_timeridx(env);
+    return env->cp15.c14_timer[timeridx].cval;
+}
+
+static void gt_phys_redir_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                     uint64_t value)
+{
+    int timeridx = gt_phys_redir_timeridx(env);
+    gt_cval_write(env, ri, timeridx, value);
+}
+
+static uint64_t gt_phys_redir_tval_read(CPUARMState *env,
+                                        const ARMCPRegInfo *ri)
+{
+    int timeridx = gt_phys_redir_timeridx(env);
+    return gt_tval_read(env, ri, timeridx);
+}
+
+static void gt_phys_redir_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                     uint64_t value)
+{
+    int timeridx = gt_phys_redir_timeridx(env);
+    gt_tval_write(env, ri, timeridx, value);
+}
+
+static uint64_t gt_phys_redir_ctl_read(CPUARMState *env,
+                                       const ARMCPRegInfo *ri)
+{
+    int timeridx = gt_phys_redir_timeridx(env);
+    return env->cp15.c14_timer[timeridx].ctl;
+}
+
+static void gt_phys_redir_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                    uint64_t value)
+{
+    int timeridx = gt_phys_redir_timeridx(env);
+    gt_ctl_write(env, ri, timeridx, value);
+}
+
 static void gt_virt_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     gt_timer_reset(env, ri, GTIMER_VIRT);
@@ -2639,6 +2797,48 @@ static void gt_cntvoff_write(CPUARMState *env, const ARMCPRegInfo *ri,
     gt_recalc_timer(cpu, GTIMER_VIRT);
 }
 
+static uint64_t gt_virt_redir_cval_read(CPUARMState *env,
+                                        const ARMCPRegInfo *ri)
+{
+    int timeridx = gt_virt_redir_timeridx(env);
+    return env->cp15.c14_timer[timeridx].cval;
+}
+
+static void gt_virt_redir_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                     uint64_t value)
+{
+    int timeridx = gt_virt_redir_timeridx(env);
+    gt_cval_write(env, ri, timeridx, value);
+}
+
+static uint64_t gt_virt_redir_tval_read(CPUARMState *env,
+                                        const ARMCPRegInfo *ri)
+{
+    int timeridx = gt_virt_redir_timeridx(env);
+    return gt_tval_read(env, ri, timeridx);
+}
+
+static void gt_virt_redir_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                     uint64_t value)
+{
+    int timeridx = gt_virt_redir_timeridx(env);
+    gt_tval_write(env, ri, timeridx, value);
+}
+
+static uint64_t gt_virt_redir_ctl_read(CPUARMState *env,
+                                       const ARMCPRegInfo *ri)
+{
+    int timeridx = gt_virt_redir_timeridx(env);
+    return env->cp15.c14_timer[timeridx].ctl;
+}
+
+static void gt_virt_redir_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                    uint64_t value)
+{
+    int timeridx = gt_virt_redir_timeridx(env);
+    gt_ctl_write(env, ri, timeridx, value);
+}
+
 static void gt_hyp_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     gt_timer_reset(env, ri, GTIMER_HYP);
@@ -2695,6 +2895,34 @@ static void gt_sec_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
     gt_ctl_write(env, ri, GTIMER_SEC, value);
 }
 
+static void gt_hv_timer_reset(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    gt_timer_reset(env, ri, GTIMER_HYPVIRT);
+}
+
+static void gt_hv_cval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value)
+{
+    gt_cval_write(env, ri, GTIMER_HYPVIRT, value);
+}
+
+static uint64_t gt_hv_tval_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return gt_tval_read(env, ri, GTIMER_HYPVIRT);
+}
+
+static void gt_hv_tval_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value)
+{
+    gt_tval_write(env, ri, GTIMER_HYPVIRT, value);
+}
+
+static void gt_hv_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                            uint64_t value)
+{
+    gt_ctl_write(env, ri, GTIMER_HYPVIRT, value);
+}
+
 void arm_gt_ptimer_cb(void *opaque)
 {
     ARMCPU *cpu = opaque;
@@ -2723,6 +2951,13 @@ void arm_gt_stimer_cb(void *opaque)
     gt_recalc_timer(cpu, GTIMER_SEC);
 }
 
+void arm_gt_hvtimer_cb(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    gt_recalc_timer(cpu, GTIMER_HYPVIRT);
+}
+
 static void arm_gt_cntfrq_reset(CPUARMState *env, const ARMCPRegInfo *opaque)
 {
     ARMCPU *cpu = env_archcpu(env);
@@ -2760,7 +2995,8 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .accessfn = gt_ptimer_access,
       .fieldoffset = offsetoflow32(CPUARMState,
                                    cp15.c14_timer[GTIMER_PHYS].ctl),
-      .writefn = gt_phys_ctl_write, .raw_writefn = raw_write,
+      .readfn = gt_phys_redir_ctl_read, .raw_readfn = raw_read,
+      .writefn = gt_phys_redir_ctl_write, .raw_writefn = raw_write,
     },
     { .name = "CNTP_CTL_S",
       .cp = 15, .crn = 14, .crm = 2, .opc1 = 0, .opc2 = 1,
@@ -2777,14 +3013,16 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .accessfn = gt_ptimer_access,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].ctl),
       .resetvalue = 0,
-      .writefn = gt_phys_ctl_write, .raw_writefn = raw_write,
+      .readfn = gt_phys_redir_ctl_read, .raw_readfn = raw_read,
+      .writefn = gt_phys_redir_ctl_write, .raw_writefn = raw_write,
     },
     { .name = "CNTV_CTL", .cp = 15, .crn = 14, .crm = 3, .opc1 = 0, .opc2 = 1,
       .type = ARM_CP_IO | ARM_CP_ALIAS, .access = PL0_RW,
       .accessfn = gt_vtimer_access,
       .fieldoffset = offsetoflow32(CPUARMState,
                                    cp15.c14_timer[GTIMER_VIRT].ctl),
-      .writefn = gt_virt_ctl_write, .raw_writefn = raw_write,
+      .readfn = gt_virt_redir_ctl_read, .raw_readfn = raw_read,
+      .writefn = gt_virt_redir_ctl_write, .raw_writefn = raw_write,
     },
     { .name = "CNTV_CTL_EL0", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 3, .opc2 = 1,
@@ -2792,14 +3030,15 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .accessfn = gt_vtimer_access,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].ctl),
       .resetvalue = 0,
-      .writefn = gt_virt_ctl_write, .raw_writefn = raw_write,
+      .readfn = gt_virt_redir_ctl_read, .raw_readfn = raw_read,
+      .writefn = gt_virt_redir_ctl_write, .raw_writefn = raw_write,
     },
     /* TimerValue views: a 32 bit downcounting view of the underlying state */
     { .name = "CNTP_TVAL", .cp = 15, .crn = 14, .crm = 2, .opc1 = 0, .opc2 = 0,
       .secure = ARM_CP_SECSTATE_NS,
       .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL0_RW,
       .accessfn = gt_ptimer_access,
-      .readfn = gt_phys_tval_read, .writefn = gt_phys_tval_write,
+      .readfn = gt_phys_redir_tval_read, .writefn = gt_phys_redir_tval_write,
     },
     { .name = "CNTP_TVAL_S",
       .cp = 15, .crn = 14, .crm = 2, .opc1 = 0, .opc2 = 0,
@@ -2812,18 +3051,18 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 2, .opc2 = 0,
       .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL0_RW,
       .accessfn = gt_ptimer_access, .resetfn = gt_phys_timer_reset,
-      .readfn = gt_phys_tval_read, .writefn = gt_phys_tval_write,
+      .readfn = gt_phys_redir_tval_read, .writefn = gt_phys_redir_tval_write,
     },
     { .name = "CNTV_TVAL", .cp = 15, .crn = 14, .crm = 3, .opc1 = 0, .opc2 = 0,
       .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL0_RW,
       .accessfn = gt_vtimer_access,
-      .readfn = gt_virt_tval_read, .writefn = gt_virt_tval_write,
+      .readfn = gt_virt_redir_tval_read, .writefn = gt_virt_redir_tval_write,
     },
     { .name = "CNTV_TVAL_EL0", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 3, .opc2 = 0,
       .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL0_RW,
       .accessfn = gt_vtimer_access, .resetfn = gt_virt_timer_reset,
-      .readfn = gt_virt_tval_read, .writefn = gt_virt_tval_write,
+      .readfn = gt_virt_redir_tval_read, .writefn = gt_virt_redir_tval_write,
     },
     /* The counter itself */
     { .name = "CNTPCT", .cp = 15, .crm = 14, .opc1 = 0,
@@ -2853,7 +3092,8 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_ALIAS,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].cval),
       .accessfn = gt_ptimer_access,
-      .writefn = gt_phys_cval_write, .raw_writefn = raw_write,
+      .readfn = gt_phys_redir_cval_read, .raw_readfn = raw_read,
+      .writefn = gt_phys_redir_cval_write, .raw_writefn = raw_write,
     },
     { .name = "CNTP_CVAL_S", .cp = 15, .crm = 14, .opc1 = 2,
       .secure = ARM_CP_SECSTATE_S,
@@ -2869,14 +3109,16 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .type = ARM_CP_IO,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].cval),
       .resetvalue = 0, .accessfn = gt_ptimer_access,
-      .writefn = gt_phys_cval_write, .raw_writefn = raw_write,
+      .readfn = gt_phys_redir_cval_read, .raw_readfn = raw_read,
+      .writefn = gt_phys_redir_cval_write, .raw_writefn = raw_write,
     },
     { .name = "CNTV_CVAL", .cp = 15, .crm = 14, .opc1 = 3,
       .access = PL0_RW,
       .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_ALIAS,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].cval),
       .accessfn = gt_vtimer_access,
-      .writefn = gt_virt_cval_write, .raw_writefn = raw_write,
+      .readfn = gt_virt_redir_cval_read, .raw_readfn = raw_read,
+      .writefn = gt_virt_redir_cval_write, .raw_writefn = raw_write,
     },
     { .name = "CNTV_CVAL_EL0", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 3, .opc2 = 2,
@@ -2884,7 +3126,8 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .type = ARM_CP_IO,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].cval),
       .resetvalue = 0, .accessfn = gt_vtimer_access,
-      .writefn = gt_virt_cval_write, .raw_writefn = raw_write,
+      .readfn = gt_virt_redir_cval_read, .raw_readfn = raw_read,
+      .writefn = gt_virt_redir_cval_write, .raw_writefn = raw_write,
     },
     /* Secure timer -- this is actually restricted to only EL3
      * and configurably Secure-EL1 via the accessfn.
@@ -2915,6 +3158,15 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
     REGINFO_SENTINEL
 };
 
+static CPAccessResult e2h_access(CPUARMState *env, const ARMCPRegInfo *ri,
+                                 bool isread)
+{
+    if (!(arm_hcr_el2_eff(env) & HCR_E2H)) {
+        return CP_ACCESS_TRAP;
+    }
+    return CP_ACCESS_OK;
+}
+
 #else
 
 /* In user-mode most of the generic timer registers are inaccessible
@@ -3009,7 +3261,8 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
         bool take_exc = false;
 
         if (fi.s1ptw && current_el == 1 && !arm_is_secure(env)
-            && (mmu_idx == ARMMMUIdx_S1NSE1 || mmu_idx == ARMMMUIdx_S1NSE0)) {
+            && (mmu_idx == ARMMMUIdx_Stage1_E1 ||
+                mmu_idx == ARMMMUIdx_Stage1_E0)) {
             /*
              * Synchronous stage 2 fault on an access made as part of the
              * translation table walk for AT S1E0* or AT S1E1* insn
@@ -3085,7 +3338,7 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
         format64 = arm_s1_regime_using_lpae_format(env, mmu_idx);
 
         if (arm_feature(env, ARM_FEATURE_EL2)) {
-            if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) {
+            if (mmu_idx == ARMMMUIdx_E10_0 || mmu_idx == ARMMMUIdx_E10_1) {
                 format64 |= env->cp15.hcr_el2 & (HCR_VM | HCR_DC);
             } else {
                 format64 |= arm_current_el(env) == 2;
@@ -3154,13 +3407,13 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
         /* stage 1 current state PL1: ATS1CPR, ATS1CPW */
         switch (el) {
         case 3:
-            mmu_idx = ARMMMUIdx_S1E3;
+            mmu_idx = ARMMMUIdx_SE3;
             break;
         case 2:
-            mmu_idx = ARMMMUIdx_S1NSE1;
+            mmu_idx = ARMMMUIdx_Stage1_E1;
             break;
         case 1:
-            mmu_idx = secure ? ARMMMUIdx_S1SE1 : ARMMMUIdx_S1NSE1;
+            mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_Stage1_E1;
             break;
         default:
             g_assert_not_reached();
@@ -3170,13 +3423,13 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
         /* stage 1 current state PL0: ATS1CUR, ATS1CUW */
         switch (el) {
         case 3:
-            mmu_idx = ARMMMUIdx_S1SE0;
+            mmu_idx = ARMMMUIdx_SE10_0;
             break;
         case 2:
-            mmu_idx = ARMMMUIdx_S1NSE0;
+            mmu_idx = ARMMMUIdx_Stage1_E0;
             break;
         case 1:
-            mmu_idx = secure ? ARMMMUIdx_S1SE0 : ARMMMUIdx_S1NSE0;
+            mmu_idx = secure ? ARMMMUIdx_SE10_0 : ARMMMUIdx_Stage1_E0;
             break;
         default:
             g_assert_not_reached();
@@ -3184,11 +3437,11 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
         break;
     case 4:
         /* stage 1+2 NonSecure PL1: ATS12NSOPR, ATS12NSOPW */
-        mmu_idx = ARMMMUIdx_S12NSE1;
+        mmu_idx = ARMMMUIdx_E10_1;
         break;
     case 6:
         /* stage 1+2 NonSecure PL0: ATS12NSOUR, ATS12NSOUW */
-        mmu_idx = ARMMMUIdx_S12NSE0;
+        mmu_idx = ARMMMUIdx_E10_0;
         break;
     default:
         g_assert_not_reached();
@@ -3205,7 +3458,7 @@ static void ats1h_write(CPUARMState *env, const ARMCPRegInfo *ri,
     MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD;
     uint64_t par64;
 
-    par64 = do_ats_write(env, value, access_type, ARMMMUIdx_S1E2);
+    par64 = do_ats_write(env, value, access_type, ARMMMUIdx_E2);
 
     A32_BANKED_CURRENT_REG_SET(env, par, par64);
 }
@@ -3230,26 +3483,26 @@ static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri,
     case 0:
         switch (ri->opc1) {
         case 0: /* AT S1E1R, AT S1E1W */
-            mmu_idx = secure ? ARMMMUIdx_S1SE1 : ARMMMUIdx_S1NSE1;
+            mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_Stage1_E1;
             break;
         case 4: /* AT S1E2R, AT S1E2W */
-            mmu_idx = ARMMMUIdx_S1E2;
+            mmu_idx = ARMMMUIdx_E2;
             break;
         case 6: /* AT S1E3R, AT S1E3W */
-            mmu_idx = ARMMMUIdx_S1E3;
+            mmu_idx = ARMMMUIdx_SE3;
             break;
         default:
             g_assert_not_reached();
         }
         break;
     case 2: /* AT S1E0R, AT S1E0W */
-        mmu_idx = secure ? ARMMMUIdx_S1SE0 : ARMMMUIdx_S1NSE0;
+        mmu_idx = secure ? ARMMMUIdx_SE10_0 : ARMMMUIdx_Stage1_E0;
         break;
     case 4: /* AT S12E1R, AT S12E1W */
-        mmu_idx = secure ? ARMMMUIdx_S1SE1 : ARMMMUIdx_S12NSE1;
+        mmu_idx = secure ? ARMMMUIdx_SE10_1 : ARMMMUIdx_E10_1;
         break;
     case 6: /* AT S12E0R, AT S12E0W */
-        mmu_idx = secure ? ARMMMUIdx_S1SE0 : ARMMMUIdx_S12NSE0;
+        mmu_idx = secure ? ARMMMUIdx_SE10_0 : ARMMMUIdx_E10_0;
         break;
     default:
         g_assert_not_reached();
@@ -3510,7 +3763,7 @@ static void vmsa_ttbcr_reset(CPUARMState *env, const ARMCPRegInfo *ri)
     tcr->base_mask = 0xffffc000u;
 }
 
-static void vmsa_tcr_el1_write(CPUARMState *env, const ARMCPRegInfo *ri,
+static void vmsa_tcr_el12_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                uint64_t value)
 {
     ARMCPU *cpu = env_archcpu(env);
@@ -3533,18 +3786,38 @@ static void vmsa_ttbr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     raw_write(env, ri, value);
 }
 
+static void vmsa_tcr_ttbr_el2_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                    uint64_t value)
+{
+    /*
+     * If we are running with E2&0 regime, then an ASID is active.
+     * Flush if that might be changing.  Note we're not checking
+     * TCR_EL2.A1 to know if this is really the TTBRx_EL2 that
+     * holds the active ASID, only checking the field that might.
+     */
+    if (extract64(raw_read(env, ri) ^ value, 48, 16) &&
+        (arm_hcr_el2_eff(env) & HCR_E2H)) {
+        tlb_flush_by_mmuidx(env_cpu(env),
+                            ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E20_0);
+    }
+    raw_write(env, ri, value);
+}
+
 static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                         uint64_t value)
 {
     ARMCPU *cpu = env_archcpu(env);
     CPUState *cs = CPU(cpu);
 
-    /* Accesses to VTTBR may change the VMID so we must flush the TLB.  */
+    /*
+     * A change in VMID to the stage2 page table (Stage2) invalidates
+     * the combined stage 1&2 tlbs (EL10_1 and EL10_0).
+     */
     if (raw_read(env, ri) != value) {
         tlb_flush_by_mmuidx(cs,
-                            ARMMMUIdxBit_S12NSE1 |
-                            ARMMMUIdxBit_S12NSE0 |
-                            ARMMMUIdxBit_S2NS);
+                            ARMMMUIdxBit_E10_1 |
+                            ARMMMUIdxBit_E10_0 |
+                            ARMMMUIdxBit_Stage2);
         raw_write(env, ri, value);
     }
 }
@@ -3586,7 +3859,7 @@ static const ARMCPRegInfo vmsa_cp_reginfo[] = {
                              offsetof(CPUARMState, cp15.ttbr1_ns) } },
     { .name = "TCR_EL1", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 2,
-      .access = PL1_RW, .writefn = vmsa_tcr_el1_write,
+      .access = PL1_RW, .writefn = vmsa_tcr_el12_write,
       .resetfn = vmsa_ttbcr_reset, .raw_writefn = raw_write,
       .fieldoffset = offsetof(CPUARMState, cp15.tcr_el[1]) },
     { .name = "TTBCR", .cp = 15, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 2,
@@ -3870,7 +4143,7 @@ static void aa64_fpsr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static CPAccessResult aa64_daif_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                        bool isread)
 {
-    if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UMA)) {
+    if (arm_current_el(env) == 0 && !(arm_sctlr(env, 0) & SCTLR_UMA)) {
         return CP_ACCESS_TRAP;
     }
     return CP_ACCESS_OK;
@@ -3889,7 +4162,7 @@ static CPAccessResult aa64_cacheop_access(CPUARMState *env,
     /* Cache invalidate/clean: NOP, but EL0 must UNDEF unless
      * SCTLR_EL1.UCI is set.
      */
-    if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UCI)) {
+    if (arm_current_el(env) == 0 && !(arm_sctlr(env, 0) & SCTLR_UCI)) {
         return CP_ACCESS_TRAP;
     }
     return CP_ACCESS_OK;
@@ -3899,79 +4172,79 @@ static CPAccessResult aa64_cacheop_access(CPUARMState *env,
  * Page D4-1736 (DDI0487A.b)
  */
 
+static int vae1_tlbmask(CPUARMState *env)
+{
+    /* Since we exclude secure first, we may read HCR_EL2 directly. */
+    if (arm_is_secure_below_el3(env)) {
+        return ARMMMUIdxBit_SE10_1 | ARMMMUIdxBit_SE10_0;
+    } else if ((env->cp15.hcr_el2 & (HCR_E2H | HCR_TGE))
+               == (HCR_E2H | HCR_TGE)) {
+        return ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E20_0;
+    } else {
+        return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_0;
+    }
+}
+
 static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                       uint64_t value)
 {
     CPUState *cs = env_cpu(env);
-    bool sec = arm_is_secure_below_el3(env);
+    int mask = vae1_tlbmask(env);
 
-    if (sec) {
-        tlb_flush_by_mmuidx_all_cpus_synced(cs,
-                                            ARMMMUIdxBit_S1SE1 |
-                                            ARMMMUIdxBit_S1SE0);
-    } else {
-        tlb_flush_by_mmuidx_all_cpus_synced(cs,
-                                            ARMMMUIdxBit_S12NSE1 |
-                                            ARMMMUIdxBit_S12NSE0);
-    }
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, mask);
 }
 
 static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                     uint64_t value)
 {
     CPUState *cs = env_cpu(env);
+    int mask = vae1_tlbmask(env);
 
     if (tlb_force_broadcast(env)) {
-        tlbi_aa64_vmalle1is_write(env, NULL, value);
-        return;
-    }
-
-    if (arm_is_secure_below_el3(env)) {
-        tlb_flush_by_mmuidx(cs,
-                            ARMMMUIdxBit_S1SE1 |
-                            ARMMMUIdxBit_S1SE0);
+        tlb_flush_by_mmuidx_all_cpus_synced(cs, mask);
     } else {
-        tlb_flush_by_mmuidx(cs,
-                            ARMMMUIdxBit_S12NSE1 |
-                            ARMMMUIdxBit_S12NSE0);
+        tlb_flush_by_mmuidx(cs, mask);
     }
 }
 
-static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                                  uint64_t value)
+static int alle1_tlbmask(CPUARMState *env)
 {
-    /* Note that the 'ALL' scope must invalidate both stage 1 and
+    /*
+     * Note that the 'ALL' scope must invalidate both stage 1 and
      * stage 2 translations, whereas most other scopes only invalidate
      * stage 1 translations.
      */
-    ARMCPU *cpu = env_archcpu(env);
-    CPUState *cs = CPU(cpu);
-
     if (arm_is_secure_below_el3(env)) {
-        tlb_flush_by_mmuidx(cs,
-                            ARMMMUIdxBit_S1SE1 |
-                            ARMMMUIdxBit_S1SE0);
+        return ARMMMUIdxBit_SE10_1 | ARMMMUIdxBit_SE10_0;
+    } else if (arm_feature(env, ARM_FEATURE_EL2)) {
+        return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_0 | ARMMMUIdxBit_Stage2;
     } else {
-        if (arm_feature(env, ARM_FEATURE_EL2)) {
-            tlb_flush_by_mmuidx(cs,
-                                ARMMMUIdxBit_S12NSE1 |
-                                ARMMMUIdxBit_S12NSE0 |
-                                ARMMMUIdxBit_S2NS);
-        } else {
-            tlb_flush_by_mmuidx(cs,
-                                ARMMMUIdxBit_S12NSE1 |
-                                ARMMMUIdxBit_S12NSE0);
-        }
+        return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_0;
     }
 }
 
+static int e2_tlbmask(CPUARMState *env)
+{
+    /* TODO: ARMv8.4-SecEL2 */
+    return ARMMMUIdxBit_E20_0 | ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E2;
+}
+
+static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                                  uint64_t value)
+{
+    CPUState *cs = env_cpu(env);
+    int mask = alle1_tlbmask(env);
+
+    tlb_flush_by_mmuidx(cs, mask);
+}
+
 static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                   uint64_t value)
 {
-    ARMCPU *cpu = env_archcpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUState *cs = env_cpu(env);
+    int mask = e2_tlbmask(env);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E2);
+    tlb_flush_by_mmuidx(cs, mask);
 }
 
 static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -3980,42 +4253,25 @@ static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri,
     ARMCPU *cpu = env_archcpu(env);
     CPUState *cs = CPU(cpu);
 
-    tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E3);
+    tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_SE3);
 }
 
 static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                     uint64_t value)
 {
-    /* Note that the 'ALL' scope must invalidate both stage 1 and
-     * stage 2 translations, whereas most other scopes only invalidate
-     * stage 1 translations.
-     */
     CPUState *cs = env_cpu(env);
-    bool sec = arm_is_secure_below_el3(env);
-    bool has_el2 = arm_feature(env, ARM_FEATURE_EL2);
-
-    if (sec) {
-        tlb_flush_by_mmuidx_all_cpus_synced(cs,
-                                            ARMMMUIdxBit_S1SE1 |
-                                            ARMMMUIdxBit_S1SE0);
-    } else if (has_el2) {
-        tlb_flush_by_mmuidx_all_cpus_synced(cs,
-                                            ARMMMUIdxBit_S12NSE1 |
-                                            ARMMMUIdxBit_S12NSE0 |
-                                            ARMMMUIdxBit_S2NS);
-    } else {
-          tlb_flush_by_mmuidx_all_cpus_synced(cs,
-                                              ARMMMUIdxBit_S12NSE1 |
-                                              ARMMMUIdxBit_S12NSE0);
-    }
+    int mask = alle1_tlbmask(env);
+
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, mask);
 }
 
 static void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                     uint64_t value)
 {
     CPUState *cs = env_cpu(env);
+    int mask = e2_tlbmask(env);
 
-    tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E2);
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, mask);
 }
 
 static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4023,7 +4279,7 @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     CPUState *cs = env_cpu(env);
 
-    tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E3);
+    tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_SE3);
 }
 
 static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4033,11 +4289,11 @@ static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri,
      * Currently handles both VAE2 and VALE2, since we don't support
      * flush-last-level-only.
      */
-    ARMCPU *cpu = env_archcpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUState *cs = env_cpu(env);
+    int mask = e2_tlbmask(env);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E2);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, mask);
 }
 
 static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4051,26 +4307,17 @@ 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, ARMMMUIdxBit_S1E3);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_SE3);
 }
 
 static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                    uint64_t value)
 {
-    ARMCPU *cpu = env_archcpu(env);
-    CPUState *cs = CPU(cpu);
-    bool sec = arm_is_secure_below_el3(env);
+    CPUState *cs = env_cpu(env);
+    int mask = vae1_tlbmask(env);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
-    if (sec) {
-        tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                                 ARMMMUIdxBit_S1SE1 |
-                                                 ARMMMUIdxBit_S1SE0);
-    } else {
-        tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                                 ARMMMUIdxBit_S12NSE1 |
-                                                 ARMMMUIdxBit_S12NSE0);
-    }
+    tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, mask);
 }
 
 static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4081,23 +4328,14 @@ static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri,
      * since we don't support flush-for-specific-ASID-only or
      * flush-last-level-only.
      */
-    ARMCPU *cpu = env_archcpu(env);
-    CPUState *cs = CPU(cpu);
+    CPUState *cs = env_cpu(env);
+    int mask = vae1_tlbmask(env);
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
     if (tlb_force_broadcast(env)) {
-        tlbi_aa64_vae1is_write(env, NULL, value);
-        return;
-    }
-
-    if (arm_is_secure_below_el3(env)) {
-        tlb_flush_page_by_mmuidx(cs, pageaddr,
-                                 ARMMMUIdxBit_S1SE1 |
-                                 ARMMMUIdxBit_S1SE0);
+        tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, mask);
     } else {
-        tlb_flush_page_by_mmuidx(cs, pageaddr,
-                                 ARMMMUIdxBit_S12NSE1 |
-                                 ARMMMUIdxBit_S12NSE0);
+        tlb_flush_page_by_mmuidx(cs, pageaddr, mask);
     }
 }
 
@@ -4108,7 +4346,7 @@ static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
     tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                             ARMMMUIdxBit_S1E2);
+                                             ARMMMUIdxBit_E2);
 }
 
 static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4118,7 +4356,7 @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     uint64_t pageaddr = sextract64(value << 12, 0, 56);
 
     tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                             ARMMMUIdxBit_S1E3);
+                                             ARMMMUIdxBit_SE3);
 }
 
 static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4140,7 +4378,7 @@ static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     pageaddr = sextract64(value << 12, 0, 48);
 
-    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S2NS);
+    tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2);
 }
 
 static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -4156,17 +4394,33 @@ static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
     pageaddr = sextract64(value << 12, 0, 48);
 
     tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
-                                             ARMMMUIdxBit_S2NS);
+                                             ARMMMUIdxBit_Stage2);
 }
 
 static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                       bool isread)
 {
-    /* We don't implement EL2, so the only control on DC ZVA is the
-     * bit in the SCTLR which can prohibit access for EL0.
-     */
-    if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_DZE)) {
-        return CP_ACCESS_TRAP;
+    int cur_el = arm_current_el(env);
+
+    if (cur_el < 2) {
+        uint64_t hcr = arm_hcr_el2_eff(env);
+
+        if (cur_el == 0) {
+            if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+                if (!(env->cp15.sctlr_el[2] & SCTLR_DZE)) {
+                    return CP_ACCESS_TRAP_EL2;
+                }
+            } else {
+                if (!(env->cp15.sctlr_el[1] & SCTLR_DZE)) {
+                    return CP_ACCESS_TRAP;
+                }
+                if (hcr & HCR_TDZ) {
+                    return CP_ACCESS_TRAP_EL2;
+                }
+            }
+        } else if (hcr & HCR_TDZ) {
+            return CP_ACCESS_TRAP_EL2;
+        }
     }
     return CP_ACCESS_OK;
 }
@@ -4721,7 +4975,8 @@ static const ARMCPRegInfo el3_no_el2_v8_cp_reginfo[] = {
 static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
 {
     ARMCPU *cpu = env_archcpu(env);
-    uint64_t valid_mask = HCR_MASK;
+    /* Begin with bits defined in base ARMv8.0.  */
+    uint64_t valid_mask = MAKE_64BIT_MASK(0, 34);
 
     if (arm_feature(env, ARM_FEATURE_EL3)) {
         valid_mask &= ~HCR_HCD;
@@ -4735,6 +4990,9 @@ static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
          */
         valid_mask &= ~HCR_TSC;
     }
+    if (cpu_isar_feature(aa64_vh, cpu)) {
+        valid_mask |= HCR_E2H;
+    }
     if (cpu_isar_feature(aa64_lor, cpu)) {
         valid_mask |= HCR_TLOR;
     }
@@ -4938,10 +5196,8 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
       .resetvalue = 0 },
     { .name = "TCR_EL2", .state = ARM_CP_STATE_BOTH,
       .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 2,
-      .access = PL2_RW,
-      /* no .writefn needed as this can't cause an ASID change;
-       * no .raw_writefn or .resetfn needed as we never use mask/base_mask
-       */
+      .access = PL2_RW, .writefn = vmsa_tcr_el12_write,
+      /* no .raw_writefn or .resetfn needed as we never use mask/base_mask */
       .fieldoffset = offsetof(CPUARMState, cp15.tcr_el[2]) },
     { .name = "VTCR", .state = ARM_CP_STATE_AA32,
       .cp = 15, .opc1 = 4, .crn = 2, .crm = 1, .opc2 = 2,
@@ -4975,7 +5231,7 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
       .fieldoffset = offsetof(CPUARMState, cp15.tpidr_el[2]) },
     { .name = "TTBR0_EL2", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 0,
-      .access = PL2_RW, .resetvalue = 0,
+      .access = PL2_RW, .resetvalue = 0, .writefn = vmsa_tcr_ttbr_el2_write,
       .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el[2]) },
     { .name = "HTTBR", .cp = 15, .opc1 = 4, .crm = 2,
       .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_ALIAS,
@@ -5244,14 +5500,182 @@ static const ARMCPRegInfo el3_cp_reginfo[] = {
     REGINFO_SENTINEL
 };
 
+#ifndef CONFIG_USER_ONLY
+/* Test if system register redirection is to occur in the current state.  */
+static bool redirect_for_e2h(CPUARMState *env)
+{
+    return arm_current_el(env) == 2 && (arm_hcr_el2_eff(env) & HCR_E2H);
+}
+
+static uint64_t el2_e2h_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    CPReadFn *readfn;
+
+    if (redirect_for_e2h(env)) {
+        /* Switch to the saved EL2 version of the register.  */
+        ri = ri->opaque;
+        readfn = ri->readfn;
+    } else {
+        readfn = ri->orig_readfn;
+    }
+    if (readfn == NULL) {
+        readfn = raw_read;
+    }
+    return readfn(env, ri);
+}
+
+static void el2_e2h_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    CPWriteFn *writefn;
+
+    if (redirect_for_e2h(env)) {
+        /* Switch to the saved EL2 version of the register.  */
+        ri = ri->opaque;
+        writefn = ri->writefn;
+    } else {
+        writefn = ri->orig_writefn;
+    }
+    if (writefn == NULL) {
+        writefn = raw_write;
+    }
+    writefn(env, ri, value);
+}
+
+static void define_arm_vh_e2h_redirects_aliases(ARMCPU *cpu)
+{
+    struct E2HAlias {
+        uint32_t src_key, dst_key, new_key;
+        const char *src_name, *dst_name, *new_name;
+        bool (*feature)(const ARMISARegisters *id);
+    };
+
+#define K(op0, op1, crn, crm, op2) \
+    ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP, crn, crm, op0, op1, op2)
+
+    static const struct E2HAlias aliases[] = {
+        { K(3, 0,  1, 0, 0), K(3, 4,  1, 0, 0), K(3, 5, 1, 0, 0),
+          "SCTLR", "SCTLR_EL2", "SCTLR_EL12" },
+        { K(3, 0,  1, 0, 2), K(3, 4,  1, 1, 2), K(3, 5, 1, 0, 2),
+          "CPACR", "CPTR_EL2", "CPACR_EL12" },
+        { K(3, 0,  2, 0, 0), K(3, 4,  2, 0, 0), K(3, 5, 2, 0, 0),
+          "TTBR0_EL1", "TTBR0_EL2", "TTBR0_EL12" },
+        { K(3, 0,  2, 0, 1), K(3, 4,  2, 0, 1), K(3, 5, 2, 0, 1),
+          "TTBR1_EL1", "TTBR1_EL2", "TTBR1_EL12" },
+        { K(3, 0,  2, 0, 2), K(3, 4,  2, 0, 2), K(3, 5, 2, 0, 2),
+          "TCR_EL1", "TCR_EL2", "TCR_EL12" },
+        { K(3, 0,  4, 0, 0), K(3, 4,  4, 0, 0), K(3, 5, 4, 0, 0),
+          "SPSR_EL1", "SPSR_EL2", "SPSR_EL12" },
+        { K(3, 0,  4, 0, 1), K(3, 4,  4, 0, 1), K(3, 5, 4, 0, 1),
+          "ELR_EL1", "ELR_EL2", "ELR_EL12" },
+        { K(3, 0,  5, 1, 0), K(3, 4,  5, 1, 0), K(3, 5, 5, 1, 0),
+          "AFSR0_EL1", "AFSR0_EL2", "AFSR0_EL12" },
+        { K(3, 0,  5, 1, 1), K(3, 4,  5, 1, 1), K(3, 5, 5, 1, 1),
+          "AFSR1_EL1", "AFSR1_EL2", "AFSR1_EL12" },
+        { K(3, 0,  5, 2, 0), K(3, 4,  5, 2, 0), K(3, 5, 5, 2, 0),
+          "ESR_EL1", "ESR_EL2", "ESR_EL12" },
+        { K(3, 0,  6, 0, 0), K(3, 4,  6, 0, 0), K(3, 5, 6, 0, 0),
+          "FAR_EL1", "FAR_EL2", "FAR_EL12" },
+        { K(3, 0, 10, 2, 0), K(3, 4, 10, 2, 0), K(3, 5, 10, 2, 0),
+          "MAIR_EL1", "MAIR_EL2", "MAIR_EL12" },
+        { K(3, 0, 10, 3, 0), K(3, 4, 10, 3, 0), K(3, 5, 10, 3, 0),
+          "AMAIR0", "AMAIR_EL2", "AMAIR_EL12" },
+        { K(3, 0, 12, 0, 0), K(3, 4, 12, 0, 0), K(3, 5, 12, 0, 0),
+          "VBAR", "VBAR_EL2", "VBAR_EL12" },
+        { K(3, 0, 13, 0, 1), K(3, 4, 13, 0, 1), K(3, 5, 13, 0, 1),
+          "CONTEXTIDR_EL1", "CONTEXTIDR_EL2", "CONTEXTIDR_EL12" },
+        { K(3, 0, 14, 1, 0), K(3, 4, 14, 1, 0), K(3, 5, 14, 1, 0),
+          "CNTKCTL", "CNTHCTL_EL2", "CNTKCTL_EL12" },
+
+        /*
+         * Note that redirection of ZCR is mentioned in the description
+         * of ZCR_EL2, and aliasing in the description of ZCR_EL1, but
+         * not in the summary table.
+         */
+        { K(3, 0,  1, 2, 0), K(3, 4,  1, 2, 0), K(3, 5, 1, 2, 0),
+          "ZCR_EL1", "ZCR_EL2", "ZCR_EL12", isar_feature_aa64_sve },
+
+        /* TODO: ARMv8.2-SPE -- PMSCR_EL2 */
+        /* TODO: ARMv8.4-Trace -- TRFCR_EL2 */
+    };
+#undef K
+
+    size_t i;
+
+    for (i = 0; i < ARRAY_SIZE(aliases); i++) {
+        const struct E2HAlias *a = &aliases[i];
+        ARMCPRegInfo *src_reg, *dst_reg;
+
+        if (a->feature && !a->feature(&cpu->isar)) {
+            continue;
+        }
+
+        src_reg = g_hash_table_lookup(cpu->cp_regs, &a->src_key);
+        dst_reg = g_hash_table_lookup(cpu->cp_regs, &a->dst_key);
+        g_assert(src_reg != NULL);
+        g_assert(dst_reg != NULL);
+
+        /* Cross-compare names to detect typos in the keys.  */
+        g_assert(strcmp(src_reg->name, a->src_name) == 0);
+        g_assert(strcmp(dst_reg->name, a->dst_name) == 0);
+
+        /* None of the core system registers use opaque; we will.  */
+        g_assert(src_reg->opaque == NULL);
+
+        /* Create alias before redirection so we dup the right data. */
+        if (a->new_key) {
+            ARMCPRegInfo *new_reg = g_memdup(src_reg, sizeof(ARMCPRegInfo));
+            uint32_t *new_key = g_memdup(&a->new_key, sizeof(uint32_t));
+            bool ok;
+
+            new_reg->name = a->new_name;
+            new_reg->type |= ARM_CP_ALIAS;
+            /* Remove PL1/PL0 access, leaving PL2/PL3 R/W in place.  */
+            new_reg->access &= PL2_RW | PL3_RW;
+
+            ok = g_hash_table_insert(cpu->cp_regs, new_key, new_reg);
+            g_assert(ok);
+        }
+
+        src_reg->opaque = dst_reg;
+        src_reg->orig_readfn = src_reg->readfn ?: raw_read;
+        src_reg->orig_writefn = src_reg->writefn ?: raw_write;
+        if (!src_reg->raw_readfn) {
+            src_reg->raw_readfn = raw_read;
+        }
+        if (!src_reg->raw_writefn) {
+            src_reg->raw_writefn = raw_write;
+        }
+        src_reg->readfn = el2_e2h_read;
+        src_reg->writefn = el2_e2h_write;
+    }
+}
+#endif
+
 static CPAccessResult ctr_el0_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                      bool isread)
 {
-    /* Only accessible in EL0 if SCTLR.UCT is set (and only in AArch64,
-     * but the AArch32 CTR has its own reginfo struct)
-     */
-    if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UCT)) {
-        return CP_ACCESS_TRAP;
+    int cur_el = arm_current_el(env);
+
+    if (cur_el < 2) {
+        uint64_t hcr = arm_hcr_el2_eff(env);
+
+        if (cur_el == 0) {
+            if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) {
+                if (!(env->cp15.sctlr_el[2] & SCTLR_UCT)) {
+                    return CP_ACCESS_TRAP_EL2;
+                }
+            } else {
+                if (!(env->cp15.sctlr_el[1] & SCTLR_UCT)) {
+                    return CP_ACCESS_TRAP;
+                }
+                if (hcr & HCR_TID2) {
+                    return CP_ACCESS_TRAP_EL2;
+                }
+            }
+        } else if (hcr & HCR_TID2) {
+            return CP_ACCESS_TRAP_EL2;
+        }
     }
 
     if (arm_current_el(env) < 2 && arm_hcr_el2_eff(env) & HCR_TID2) {
@@ -5367,7 +5791,9 @@ static const ARMCPRegInfo debug_lpae_cp_reginfo[] = {
 int sve_exception_el(CPUARMState *env, int el)
 {
 #ifndef CONFIG_USER_ONLY
-    if (el <= 1) {
+    uint64_t hcr_el2 = arm_hcr_el2_eff(env);
+
+    if (el <= 1 && (hcr_el2 & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) {
         bool disabled = false;
 
         /* The CPACR.ZEN controls traps to EL1:
@@ -5382,8 +5808,7 @@ int sve_exception_el(CPUARMState *env, int el)
         }
         if (disabled) {
             /* route_to_el2 */
-            return (arm_feature(env, ARM_FEATURE_EL2)
-                    && (arm_hcr_el2_eff(env) & HCR_TGE) ? 2 : 1);
+            return hcr_el2 & HCR_TGE ? 2 : 1;
         }
 
         /* Check CPACR.FPEN.  */
@@ -6122,6 +6547,71 @@ static const ARMCPRegInfo jazelle_regs[] = {
     REGINFO_SENTINEL
 };
 
+static const ARMCPRegInfo vhe_reginfo[] = {
+    { .name = "CONTEXTIDR_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 13, .crm = 0, .opc2 = 1,
+      .access = PL2_RW,
+      .fieldoffset = offsetof(CPUARMState, cp15.contextidr_el[2]) },
+    { .name = "TTBR1_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 1,
+      .access = PL2_RW, .writefn = vmsa_tcr_ttbr_el2_write,
+      .fieldoffset = offsetof(CPUARMState, cp15.ttbr1_el[2]) },
+#ifndef CONFIG_USER_ONLY
+    { .name = "CNTHV_CVAL_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 3, .opc2 = 2,
+      .fieldoffset =
+        offsetof(CPUARMState, cp15.c14_timer[GTIMER_HYPVIRT].cval),
+      .type = ARM_CP_IO, .access = PL2_RW,
+      .writefn = gt_hv_cval_write, .raw_writefn = raw_write },
+    { .name = "CNTHV_TVAL_EL2", .state = ARM_CP_STATE_BOTH,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 3, .opc2 = 0,
+      .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL2_RW,
+      .resetfn = gt_hv_timer_reset,
+      .readfn = gt_hv_tval_read, .writefn = gt_hv_tval_write },
+    { .name = "CNTHV_CTL_EL2", .state = ARM_CP_STATE_BOTH,
+      .type = ARM_CP_IO,
+      .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 3, .opc2 = 1,
+      .access = PL2_RW,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_HYPVIRT].ctl),
+      .writefn = gt_hv_ctl_write, .raw_writefn = raw_write },
+    { .name = "CNTP_CTL_EL02", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 5, .crn = 14, .crm = 2, .opc2 = 1,
+      .type = ARM_CP_IO | ARM_CP_ALIAS,
+      .access = PL2_RW, .accessfn = e2h_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].ctl),
+      .writefn = gt_phys_ctl_write, .raw_writefn = raw_write },
+    { .name = "CNTV_CTL_EL02", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 5, .crn = 14, .crm = 3, .opc2 = 1,
+      .type = ARM_CP_IO | ARM_CP_ALIAS,
+      .access = PL2_RW, .accessfn = e2h_access,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].ctl),
+      .writefn = gt_virt_ctl_write, .raw_writefn = raw_write },
+    { .name = "CNTP_TVAL_EL02", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 5, .crn = 14, .crm = 2, .opc2 = 0,
+      .type = ARM_CP_NO_RAW | ARM_CP_IO | ARM_CP_ALIAS,
+      .access = PL2_RW, .accessfn = e2h_access,
+      .readfn = gt_phys_tval_read, .writefn = gt_phys_tval_write },
+    { .name = "CNTV_TVAL_EL02", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 5, .crn = 14, .crm = 3, .opc2 = 0,
+      .type = ARM_CP_NO_RAW | ARM_CP_IO | ARM_CP_ALIAS,
+      .access = PL2_RW, .accessfn = e2h_access,
+      .readfn = gt_virt_tval_read, .writefn = gt_virt_tval_write },
+    { .name = "CNTP_CVAL_EL02", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 5, .crn = 14, .crm = 2, .opc2 = 2,
+      .type = ARM_CP_IO | ARM_CP_ALIAS,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].cval),
+      .access = PL2_RW, .accessfn = e2h_access,
+      .writefn = gt_phys_cval_write, .raw_writefn = raw_write },
+    { .name = "CNTV_CVAL_EL02", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 5, .crn = 14, .crm = 3, .opc2 = 2,
+      .type = ARM_CP_IO | ARM_CP_ALIAS,
+      .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].cval),
+      .access = PL2_RW, .accessfn = e2h_access,
+      .writefn = gt_virt_cval_write, .raw_writefn = raw_write },
+#endif
+    REGINFO_SENTINEL
+};
+
 void register_cp_regs_for_features(ARMCPU *cpu)
 {
     /* Register all the coprocessor registers based on feature bits */
@@ -7085,6 +7575,10 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         define_arm_cp_regs(cpu, lor_reginfo);
     }
 
+    if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) {
+        define_arm_cp_regs(cpu, vhe_reginfo);
+    }
+
     if (cpu_isar_feature(aa64_sve, cpu)) {
         define_one_arm_cp_reg(cpu, &zcr_el1_reginfo);
         if (arm_feature(env, ARM_FEATURE_EL2)) {
@@ -7126,6 +7620,16 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         : cpu_isar_feature(aa32_predinv, cpu)) {
         define_arm_cp_regs(cpu, predinv_reginfo);
     }
+
+#ifndef CONFIG_USER_ONLY
+    /*
+     * Register redirections and aliases must be done last,
+     * after the registers from the other extensions have been defined.
+     */
+    if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) {
+        define_arm_vh_e2h_redirects_aliases(cpu);
+    }
+#endif
 }
 
 void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu)
@@ -7421,13 +7925,10 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu,
             mask = PL0_RW;
             break;
         case 4:
+        case 5:
             /* min_EL EL2 */
             mask = PL2_RW;
             break;
-        case 5:
-            /* unallocated encoding, so not possible */
-            assert(false);
-            break;
         case 6:
             /* min_EL EL3 */
             mask = PL3_RW;
@@ -7946,6 +8447,12 @@ uint32_t arm_phys_excp_target_el(CPUState *cs, uint32_t excp_idx,
         break;
     };
 
+    /*
+     * For these purposes, TGE and AMO/IMO/FMO both force the
+     * interrupt to EL2.  Fold TGE into the bit extracted above.
+     */
+    hcr |= (hcr_el2 & HCR_TGE) != 0;
+
     /* Perform a table-lookup for the target EL given the current state */
     target_el = target_el_table[is64][scr][rw][hcr][secure][cur_el];
 
@@ -8510,14 +9017,19 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs)
          * immediately lower than the target level is using AArch32 or AArch64
          */
         bool is_aa64;
+        uint64_t hcr;
 
         switch (new_el) {
         case 3:
             is_aa64 = (env->cp15.scr_el3 & SCR_RW) != 0;
             break;
         case 2:
-            is_aa64 = (env->cp15.hcr_el2 & HCR_RW) != 0;
-            break;
+            hcr = arm_hcr_el2_eff(env);
+            if ((hcr & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) {
+                is_aa64 = (hcr & HCR_RW) != 0;
+                break;
+            }
+            /* fall through */
         case 1:
             is_aa64 = is_a64(env);
             break;
@@ -8690,19 +9202,23 @@ void arm_cpu_do_interrupt(CPUState *cs)
 #endif /* !CONFIG_USER_ONLY */
 
 /* Return the exception level which controls this address translation regime */
-static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
+static uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
 {
     switch (mmu_idx) {
-    case ARMMMUIdx_S2NS:
-    case ARMMMUIdx_S1E2:
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_Stage2:
+    case ARMMMUIdx_E2:
         return 2;
-    case ARMMMUIdx_S1E3:
+    case ARMMMUIdx_SE3:
         return 3;
-    case ARMMMUIdx_S1SE0:
+    case ARMMMUIdx_SE10_0:
         return arm_el_is_aa64(env, 3) ? 1 : 3;
-    case ARMMMUIdx_S1SE1:
-    case ARMMMUIdx_S1NSE0:
-    case ARMMMUIdx_S1NSE1:
+    case ARMMMUIdx_SE10_1:
+    case ARMMMUIdx_Stage1_E0:
+    case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E10_1:
     case ARMMMUIdx_MPrivNegPri:
     case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
@@ -8717,14 +9233,24 @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
     }
 }
 
-#ifndef CONFIG_USER_ONLY
+uint64_t arm_sctlr(CPUARMState *env, int el)
+{
+    /* Only EL0 needs to be adjusted for EL1&0 or EL2&0. */
+    if (el == 0) {
+        ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0);
+        el = (mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1);
+    }
+    return env->cp15.sctlr_el[el];
+}
 
 /* Return the SCTLR value which controls this address translation regime */
-static inline uint32_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx)
+static inline uint64_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx)
 {
     return env->cp15.sctlr_el[regime_el(env, mmu_idx)];
 }
 
+#ifndef CONFIG_USER_ONLY
+
 /* Return true if the specified stage of address translation is disabled */
 static inline bool regime_translation_disabled(CPUARMState *env,
                                                ARMMMUIdx mmu_idx)
@@ -8747,7 +9273,7 @@ static inline bool regime_translation_disabled(CPUARMState *env,
         }
     }
 
-    if (mmu_idx == ARMMMUIdx_S2NS) {
+    if (mmu_idx == ARMMMUIdx_Stage2) {
         /* HCR.DC means HCR.VM behaves as 1 */
         return (env->cp15.hcr_el2 & (HCR_DC | HCR_VM)) == 0;
     }
@@ -8760,7 +9286,7 @@ static inline bool regime_translation_disabled(CPUARMState *env,
     }
 
     if ((env->cp15.hcr_el2 & HCR_DC) &&
-        (mmu_idx == ARMMMUIdx_S1NSE0 || mmu_idx == ARMMMUIdx_S1NSE1)) {
+        (mmu_idx == ARMMMUIdx_Stage1_E0 || mmu_idx == ARMMMUIdx_Stage1_E1)) {
         /* HCR.DC means SCTLR_EL1.M behaves as 0 */
         return true;
     }
@@ -8778,7 +9304,7 @@ static inline bool regime_translation_big_endian(CPUARMState *env,
 static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx,
                                    int ttbrn)
 {
-    if (mmu_idx == ARMMMUIdx_S2NS) {
+    if (mmu_idx == ARMMMUIdx_Stage2) {
         return env->cp15.vttbr_el2;
     }
     if (ttbrn == 0) {
@@ -8793,7 +9319,7 @@ static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx,
 /* Return the TCR controlling this translation regime */
 static inline TCR *regime_tcr(CPUARMState *env, ARMMMUIdx mmu_idx)
 {
-    if (mmu_idx == ARMMMUIdx_S2NS) {
+    if (mmu_idx == ARMMMUIdx_Stage2) {
         return &env->cp15.vtcr_el2;
     }
     return &env->cp15.tcr_el[regime_el(env, mmu_idx)];
@@ -8804,10 +9330,14 @@ static inline TCR *regime_tcr(CPUARMState *env, ARMMMUIdx mmu_idx)
  */
 static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx)
 {
-    if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) {
-        mmu_idx += (ARMMMUIdx_S1NSE0 - ARMMMUIdx_S12NSE0);
+    switch (mmu_idx) {
+    case ARMMMUIdx_E10_0:
+        return ARMMMUIdx_Stage1_E0;
+    case ARMMMUIdx_E10_1:
+        return ARMMMUIdx_Stage1_E1;
+    default:
+        return mmu_idx;
     }
-    return mmu_idx;
 }
 
 /* Return true if the translation regime is using LPAE format page tables */
@@ -8839,8 +9369,9 @@ bool arm_s1_regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx)
 static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx)
 {
     switch (mmu_idx) {
-    case ARMMMUIdx_S1SE0:
-    case ARMMMUIdx_S1NSE0:
+    case ARMMMUIdx_SE10_0:
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_Stage1_E0:
     case ARMMMUIdx_MUser:
     case ARMMMUIdx_MSUser:
     case ARMMMUIdx_MUserNegPri:
@@ -8848,8 +9379,8 @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx)
         return true;
     default:
         return false;
-    case ARMMMUIdx_S12NSE0:
-    case ARMMMUIdx_S12NSE1:
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E10_1:
         g_assert_not_reached();
     }
 }
@@ -8980,7 +9511,7 @@ static int get_S1prot(CPUARMState *env, ARMMMUIdx mmu_idx, bool is_aa64,
     bool have_wxn;
     int wxn = 0;
 
-    assert(mmu_idx != ARMMMUIdx_S2NS);
+    assert(mmu_idx != ARMMMUIdx_Stage2);
 
     user_rw = simple_ap_to_rw_prot_is_user(ap, true);
     if (is_user) {
@@ -9005,15 +9536,8 @@ static int get_S1prot(CPUARMState *env, ARMMMUIdx mmu_idx, bool is_aa64,
     }
 
     if (is_aa64) {
-        switch (regime_el(env, mmu_idx)) {
-        case 1:
-            if (!is_user) {
-                xn = pxn || (user_rw & PAGE_WRITE);
-            }
-            break;
-        case 2:
-        case 3:
-            break;
+        if (regime_has_2_ranges(mmu_idx) && !is_user) {
+            xn = pxn || (user_rw & PAGE_WRITE);
         }
     } else if (arm_feature(env, ARM_FEATURE_V7)) {
         switch (regime_el(env, mmu_idx)) {
@@ -9071,8 +9595,8 @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
                                hwaddr addr, MemTxAttrs txattrs,
                                ARMMMUFaultInfo *fi)
 {
-    if ((mmu_idx == ARMMMUIdx_S1NSE0 || mmu_idx == ARMMMUIdx_S1NSE1) &&
-        !regime_translation_disabled(env, ARMMMUIdx_S2NS)) {
+    if ((mmu_idx == ARMMMUIdx_Stage1_E0 || mmu_idx == ARMMMUIdx_Stage1_E1) &&
+        !regime_translation_disabled(env, ARMMMUIdx_Stage2)) {
         target_ulong s2size;
         hwaddr s2pa;
         int s2prot;
@@ -9089,7 +9613,7 @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
             pcacheattrs = &cacheattrs;
         }
 
-        ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_S2NS, &s2pa,
+        ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_Stage2, &s2pa,
                                  &txattrs, &s2prot, &s2size, fi, pcacheattrs);
         if (ret) {
             assert(fi->type != ARMFault_None);
@@ -9547,7 +10071,6 @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va,
                                         ARMMMUIdx mmu_idx)
 {
     uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr;
-    uint32_t el = regime_el(env, mmu_idx);
     bool tbi, tbid, epd, hpd, using16k, using64k;
     int select, tsz;
 
@@ -9557,11 +10080,11 @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va,
      */
     select = extract64(va, 55, 1);
 
-    if (el > 1) {
+    if (!regime_has_2_ranges(mmu_idx)) {
         tsz = extract32(tcr, 0, 6);
         using64k = extract32(tcr, 14, 1);
         using16k = extract32(tcr, 15, 1);
-        if (mmu_idx == ARMMMUIdx_S2NS) {
+        if (mmu_idx == ARMMMUIdx_Stage2) {
             /* VTCR_EL2 */
             tbi = tbid = hpd = false;
         } else {
@@ -9622,7 +10145,7 @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va,
     int select, tsz;
     bool epd, hpd;
 
-    if (mmu_idx == ARMMMUIdx_S2NS) {
+    if (mmu_idx == ARMMMUIdx_Stage2) {
         /* VTCR */
         bool sext = extract32(tcr, 4, 1);
         bool sign = extract32(tcr, 3, 1);
@@ -9713,10 +10236,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         param = aa64_va_parameters(env, address, mmu_idx,
                                    access_type != MMU_INST_FETCH);
         level = 0;
-        /* If we are in 64-bit EL2 or EL3 then there is no TTBR1, so mark it
-         * invalid.
-         */
-        ttbr1_valid = (el < 2);
+        ttbr1_valid = regime_has_2_ranges(mmu_idx);
         addrsize = 64 - 8 * param.tbi;
         inputsize = 64 - param.tsz;
     } else {
@@ -9724,7 +10244,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         level = 1;
         /* There is no TTBR1 for EL2 */
         ttbr1_valid = (el != 2);
-        addrsize = (mmu_idx == ARMMMUIdx_S2NS ? 40 : 32);
+        addrsize = (mmu_idx == ARMMMUIdx_Stage2 ? 40 : 32);
         inputsize = addrsize - param.tsz;
     }
 
@@ -9775,7 +10295,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         goto do_fault;
     }
 
-    if (mmu_idx != ARMMMUIdx_S2NS) {
+    if (mmu_idx != ARMMMUIdx_Stage2) {
         /* The starting level depends on the virtual address size (which can
          * be up to 48 bits) and the translation granule size. It indicates
          * the number of strides (stride bits at a time) needed to
@@ -9875,7 +10395,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         attrs = extract64(descriptor, 2, 10)
             | (extract64(descriptor, 52, 12) << 10);
 
-        if (mmu_idx == ARMMMUIdx_S2NS) {
+        if (mmu_idx == ARMMMUIdx_Stage2) {
             /* Stage 2 table descriptors do not include any attribute fields */
             break;
         }
@@ -9906,7 +10426,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
     ap = extract32(attrs, 4, 2);
     xn = extract32(attrs, 12, 1);
 
-    if (mmu_idx == ARMMMUIdx_S2NS) {
+    if (mmu_idx == ARMMMUIdx_Stage2) {
         ns = true;
         *prot = get_S2prot(env, ap, xn);
     } else {
@@ -9933,7 +10453,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
     }
 
     if (cacheattrs != NULL) {
-        if (mmu_idx == ARMMMUIdx_S2NS) {
+        if (mmu_idx == ARMMMUIdx_Stage2) {
             cacheattrs->attrs = convert_stage2_attrs(env,
                                                      extract32(attrs, 0, 4));
         } else {
@@ -9954,7 +10474,7 @@ do_fault:
     fi->type = fault_type;
     fi->level = level;
     /* Tag the error as S2 for failed S1 PTW at S2 or ordinary S2.  */
-    fi->stage2 = fi->s1ptw || (mmu_idx == ARMMMUIdx_S2NS);
+    fi->stage2 = fi->s1ptw || (mmu_idx == ARMMMUIdx_Stage2);
     return true;
 }
 
@@ -10753,7 +11273,7 @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
                    target_ulong *page_size,
                    ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs)
 {
-    if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) {
+    if (mmu_idx == ARMMMUIdx_E10_0 || mmu_idx == ARMMMUIdx_E10_1) {
         /* Call ourselves recursively to do the stage 1 and then stage 2
          * translations.
          */
@@ -10768,13 +11288,13 @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
                                 prot, page_size, fi, cacheattrs);
 
             /* If S1 fails or S2 is disabled, return early.  */
-            if (ret || regime_translation_disabled(env, ARMMMUIdx_S2NS)) {
+            if (ret || regime_translation_disabled(env, ARMMMUIdx_Stage2)) {
                 *phys_ptr = ipa;
                 return ret;
             }
 
             /* S1 is done. Now do S2 translation.  */
-            ret = get_phys_addr_lpae(env, ipa, access_type, ARMMMUIdx_S2NS,
+            ret = get_phys_addr_lpae(env, ipa, access_type, ARMMMUIdx_Stage2,
                                      phys_ptr, attrs, &s2_prot,
                                      page_size, fi,
                                      cacheattrs != NULL ? &cacheattrs2 : NULL);
@@ -10816,7 +11336,7 @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
     /* Fast Context Switch Extension. This doesn't exist at all in v8.
      * In v7 and earlier it affects all stage 1 translations.
      */
-    if (address < 0x02000000 && mmu_idx != ARMMMUIdx_S2NS
+    if (address < 0x02000000 && mmu_idx != ARMMMUIdx_Stage2
         && !arm_feature(env, ARM_FEATURE_V8)) {
         if (regime_el(env, mmu_idx) == 3) {
             address += env->cp15.fcseidr_s;
@@ -11177,8 +11697,6 @@ uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes)
 int fp_exception_el(CPUARMState *env, int cur_el)
 {
 #ifndef CONFIG_USER_ONLY
-    int fpen;
-
     /* CPACR and the CPTR registers don't exist before v6, so FP is
      * always accessible
      */
@@ -11206,30 +11724,34 @@ int fp_exception_el(CPUARMState *env, int cur_el)
      * 0, 2 : trap EL0 and EL1/PL1 accesses
      * 1    : trap only EL0 accesses
      * 3    : trap no accesses
+     * This register is ignored if E2H+TGE are both set.
      */
-    fpen = extract32(env->cp15.cpacr_el1, 20, 2);
-    switch (fpen) {
-    case 0:
-    case 2:
-        if (cur_el == 0 || cur_el == 1) {
-            /* Trap to PL1, which might be EL1 or EL3 */
-            if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) {
+    if ((arm_hcr_el2_eff(env) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) {
+        int fpen = extract32(env->cp15.cpacr_el1, 20, 2);
+
+        switch (fpen) {
+        case 0:
+        case 2:
+            if (cur_el == 0 || cur_el == 1) {
+                /* Trap to PL1, which might be EL1 or EL3 */
+                if (arm_is_secure(env) && !arm_el_is_aa64(env, 3)) {
+                    return 3;
+                }
+                return 1;
+            }
+            if (cur_el == 3 && !is_a64(env)) {
+                /* Secure PL1 running at EL3 */
                 return 3;
             }
-            return 1;
-        }
-        if (cur_el == 3 && !is_a64(env)) {
-            /* Secure PL1 running at EL3 */
-            return 3;
-        }
-        break;
-    case 1:
-        if (cur_el == 0) {
-            return 1;
+            break;
+        case 1:
+            if (cur_el == 0) {
+                return 1;
+            }
+            break;
+        case 3:
+            break;
         }
-        break;
-    case 3:
-        break;
     }
 
     /*
@@ -11265,6 +11787,31 @@ int fp_exception_el(CPUARMState *env, int cur_el)
     return 0;
 }
 
+/* Return the exception level we're running at if this is our mmu_idx */
+int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
+{
+    if (mmu_idx & ARM_MMU_IDX_M) {
+        return mmu_idx & ARM_MMU_IDX_M_PRIV;
+    }
+
+    switch (mmu_idx) {
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_SE10_0:
+        return 0;
+    case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_SE10_1:
+        return 1;
+    case ARMMMUIdx_E2:
+    case ARMMMUIdx_E20_2:
+        return 2;
+    case ARMMMUIdx_SE3:
+        return 3;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 #ifndef CONFIG_TCG
 ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate)
 {
@@ -11278,10 +11825,33 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el)
         return arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure);
     }
 
-    if (el < 2 && arm_is_secure_below_el3(env)) {
-        return ARMMMUIdx_S1SE0 + el;
-    } else {
-        return ARMMMUIdx_S12NSE0 + el;
+    /* See ARM pseudo-function ELIsInHost.  */
+    switch (el) {
+    case 0:
+        if (arm_is_secure_below_el3(env)) {
+            return ARMMMUIdx_SE10_0;
+        }
+        if ((env->cp15.hcr_el2 & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)
+            && arm_el_is_aa64(env, 2)) {
+            return ARMMMUIdx_E20_0;
+        }
+        return ARMMMUIdx_E10_0;
+    case 1:
+        if (arm_is_secure_below_el3(env)) {
+            return ARMMMUIdx_SE10_1;
+        }
+        return ARMMMUIdx_E10_1;
+    case 2:
+        /* TODO: ARMv8.4-SecEL2 */
+        /* Note that TGE does not apply at EL2.  */
+        if ((env->cp15.hcr_el2 & HCR_E2H) && arm_el_is_aa64(env, 2)) {
+            return ARMMMUIdx_E20_2;
+        }
+        return ARMMMUIdx_E2;
+    case 3:
+        return ARMMMUIdx_SE3;
+    default:
+        g_assert_not_reached();
     }
 }
 
@@ -11336,11 +11906,8 @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el,
 {
     uint32_t flags = 0;
 
-    /* v8M always enables the fpu.  */
-    flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1);
-
     if (arm_v7m_is_handler_mode(env)) {
-        flags = FIELD_DP32(flags, TBFLAG_A32, HANDLER, 1);
+        flags = FIELD_DP32(flags, TBFLAG_M32, HANDLER, 1);
     }
 
     /*
@@ -11351,7 +11918,7 @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el,
     if (arm_feature(env, ARM_FEATURE_V8) &&
         !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) &&
           (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) {
-        flags = FIELD_DP32(flags, TBFLAG_A32, STACKCHECK, 1);
+        flags = FIELD_DP32(flags, TBFLAG_M32, STACKCHECK, 1);
     }
 
     return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
@@ -11394,8 +11961,8 @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
 
     flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1);
 
-    /* FIXME: ARMv8.1-VHE S2 translation regime.  */
-    if (regime_el(env, stage1) < 2) {
+    /* Get control bits for tagged addresses.  */
+    if (regime_has_2_ranges(mmu_idx)) {
         ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1);
         tbid = (p1.tbi << 1) | p0.tbi;
         tbii = tbid & ~((p1.tbid << 1) | p0.tbid);
@@ -11424,7 +11991,7 @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
         flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len);
     }
 
-    sctlr = arm_sctlr(env, el);
+    sctlr = regime_sctlr(env, stage1);
 
     if (arm_cpu_data_is_big_endian_a64(el, sctlr)) {
         flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1);
@@ -11449,6 +12016,28 @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
         }
     }
 
+    /* Compute the condition for using AccType_UNPRIV for LDTR et al. */
+    /* TODO: ARMv8.2-UAO */
+    switch (mmu_idx) {
+    case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_SE10_1:
+        /* TODO: ARMv8.3-NV */
+        flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1);
+        break;
+    case ARMMMUIdx_E20_2:
+        /* TODO: ARMv8.4-SecEL2 */
+        /*
+         * Note that E20_2 is gated by HCR_EL2.E2H == 1, but E20_0 is
+         * gated by HCR_EL2.<E2H,TGE> == '11', and so is LDTR.
+         */
+        if (env->cp15.hcr_el2 & HCR_TGE) {
+            flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1);
+        }
+        break;
+    default:
+        break;
+    }
+
     return rebuild_hflags_common(env, fp_el, mmu_idx, flags);
 }
 
@@ -11544,7 +12133,7 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
             if (arm_feature(env, ARM_FEATURE_M_SECURITY) &&
                 FIELD_EX32(env->v7m.fpccr[M_REG_S], V7M_FPCCR, S)
                 != env->v7m.secure) {
-                flags = FIELD_DP32(flags, TBFLAG_A32, FPCCR_S_WRONG, 1);
+                flags = FIELD_DP32(flags, TBFLAG_M32, FPCCR_S_WRONG, 1);
             }
 
             if ((env->v7m.fpccr[env->v7m.secure] & R_V7M_FPCCR_ASPEN_MASK) &&
@@ -11556,12 +12145,12 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
                  * active FP context; we must create a new FP context before
                  * executing any FP insn.
                  */
-                flags = FIELD_DP32(flags, TBFLAG_A32, NEW_FP_CTXT_NEEDED, 1);
+                flags = FIELD_DP32(flags, TBFLAG_M32, NEW_FP_CTXT_NEEDED, 1);
             }
 
             bool is_secure = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK;
             if (env->v7m.fpccr[is_secure] & R_V7M_FPCCR_LSPACT_MASK) {
-                flags = FIELD_DP32(flags, TBFLAG_A32, LSPACT, 1);
+                flags = FIELD_DP32(flags, TBFLAG_M32, LSPACT, 1);
             }
         } else {
             /*
@@ -11582,8 +12171,8 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
             }
         }
 
-        flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb);
-        flags = FIELD_DP32(flags, TBFLAG_A32, CONDEXEC, env->condexec_bits);
+        flags = FIELD_DP32(flags, TBFLAG_AM32, THUMB, env->thumb);
+        flags = FIELD_DP32(flags, TBFLAG_AM32, CONDEXEC, env->condexec_bits);
         pstate_for_ss = env->uncached_cpsr;
     }
 
diff --git a/target/arm/internals.h b/target/arm/internals.h
index f5313dd3d4..6d4a942bde 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -769,6 +769,39 @@ bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
                       MMUAccessType access_type, int mmu_idx,
                       bool probe, uintptr_t retaddr);
 
+static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx)
+{
+    return mmu_idx & ARM_MMU_IDX_COREIDX_MASK;
+}
+
+static inline ARMMMUIdx core_to_arm_mmu_idx(CPUARMState *env, int mmu_idx)
+{
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        return mmu_idx | ARM_MMU_IDX_M;
+    } else {
+        return mmu_idx | ARM_MMU_IDX_A;
+    }
+}
+
+int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx);
+
+/*
+ * Return the MMU index for a v7M CPU with all relevant information
+ * manually specified.
+ */
+ARMMMUIdx arm_v7m_mmu_idx_all(CPUARMState *env,
+                              bool secstate, bool priv, bool negpri);
+
+/*
+ * Return the MMU index for a v7M CPU in the specified security and
+ * privilege state.
+ */
+ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env,
+                                                bool secstate, bool priv);
+
+/* Return the MMU index for a v7M CPU in the specified security state */
+ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate);
+
 /* Return true if the stage 1 translation regime is using LPAE format page
  * tables */
 bool arm_s1_regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx);
@@ -804,24 +837,44 @@ static inline void arm_call_el_change_hook(ARMCPU *cpu)
     }
 }
 
+/* Return true if this address translation regime has two ranges.  */
+static inline bool regime_has_2_ranges(ARMMMUIdx mmu_idx)
+{
+    switch (mmu_idx) {
+    case ARMMMUIdx_Stage1_E0:
+    case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_SE10_0:
+    case ARMMMUIdx_SE10_1:
+        return true;
+    default:
+        return false;
+    }
+}
+
 /* Return true if this address translation regime is secure */
 static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx)
 {
     switch (mmu_idx) {
-    case ARMMMUIdx_S12NSE0:
-    case ARMMMUIdx_S12NSE1:
-    case ARMMMUIdx_S1NSE0:
-    case ARMMMUIdx_S1NSE1:
-    case ARMMMUIdx_S1E2:
-    case ARMMMUIdx_S2NS:
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E10_1:
+    case ARMMMUIdx_E20_0:
+    case ARMMMUIdx_E20_2:
+    case ARMMMUIdx_Stage1_E0:
+    case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_E2:
+    case ARMMMUIdx_Stage2:
     case ARMMMUIdx_MPrivNegPri:
     case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
     case ARMMMUIdx_MUser:
         return false;
-    case ARMMMUIdx_S1E3:
-    case ARMMMUIdx_S1SE0:
-    case ARMMMUIdx_S1SE1:
+    case ARMMMUIdx_SE3:
+    case ARMMMUIdx_SE10_0:
+    case ARMMMUIdx_SE10_1:
     case ARMMMUIdx_MSPrivNegPri:
     case ARMMMUIdx_MSUserNegPri:
     case ARMMMUIdx_MSPriv:
@@ -975,7 +1028,7 @@ ARMMMUIdx arm_mmu_idx(CPUARMState *env);
 #ifdef CONFIG_USER_ONLY
 static inline ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env)
 {
-    return ARMMMUIdx_S1NSE0;
+    return ARMMMUIdx_Stage1_E0;
 }
 #else
 ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env);
diff --git a/target/arm/monitor.c b/target/arm/monitor.c
index 9725dfff16..c2dc7908de 100644
--- a/target/arm/monitor.c
+++ b/target/arm/monitor.c
@@ -137,17 +137,20 @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type,
     }
 
     if (kvm_enabled()) {
-        const char *cpu_type = current_machine->cpu_type;
-        int len = strlen(cpu_type) - strlen(ARM_CPU_TYPE_SUFFIX);
         bool supported = false;
 
         if (!strcmp(model->name, "host") || !strcmp(model->name, "max")) {
             /* These are kvmarm's recommended cpu types */
             supported = true;
-        } else if (strlen(model->name) == len &&
-                   !strncmp(model->name, cpu_type, len)) {
-            /* KVM is enabled and we're using this type, so it works. */
-            supported = true;
+        } else if (current_machine->cpu_type) {
+            const char *cpu_type = current_machine->cpu_type;
+            int len = strlen(cpu_type) - strlen(ARM_CPU_TYPE_SUFFIX);
+
+            if (strlen(model->name) == len &&
+                !strncmp(model->name, cpu_type, len)) {
+                /* KVM is enabled and we're using this type, so it works. */
+                supported = true;
+            }
         }
         if (!supported) {
             error_setg(errp, "We cannot guarantee the CPU type '%s' works "
diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c
index 0a5f41e10c..9746e32bf8 100644
--- a/target/arm/pauth_helper.c
+++ b/target/arm/pauth_helper.c
@@ -371,7 +371,10 @@ static void pauth_check_trap(CPUARMState *env, int el, uintptr_t ra)
     if (el < 2 && arm_feature(env, ARM_FEATURE_EL2)) {
         uint64_t hcr = arm_hcr_el2_eff(env);
         bool trap = !(hcr & HCR_API);
-        /* FIXME: ARMv8.1-VHE: trap only applies to EL1&0 regime.  */
+        if (el == 0) {
+            /* Trap only applies to EL1&0 regime.  */
+            trap &= (hcr & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE);
+        }
         /* FIXME: ARMv8.3-NV: HCR_NV trap takes precedence for ERETA[AB].  */
         if (trap) {
             pauth_trap(env, 2, ra);
@@ -386,14 +389,7 @@ static void pauth_check_trap(CPUARMState *env, int el, uintptr_t ra)
 
 static bool pauth_key_enabled(CPUARMState *env, int el, uint32_t bit)
 {
-    uint32_t sctlr;
-    if (el == 0) {
-        /* FIXME: ARMv8.1-VHE S2 translation regime.  */
-        sctlr = env->cp15.sctlr_el[1];
-    } else {
-        sctlr = env->cp15.sctlr_el[el];
-    }
-    return (sctlr & bit) != 0;
+    return (arm_sctlr(env, el) & bit) != 0;
 }
 
 uint64_t HELPER(pacia)(CPUARMState *env, uint64_t x, uint64_t y)
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 766a03335b..6e82486884 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -105,25 +105,36 @@ void a64_translate_init(void)
         offsetof(CPUARMState, exclusive_high), "exclusive_high");
 }
 
-static inline int get_a64_user_mem_index(DisasContext *s)
+/*
+ * Return the core mmu_idx to use for A64 "unprivileged load/store" insns
+ */
+static int get_a64_user_mem_index(DisasContext *s)
 {
-    /* Return the core mmu_idx to use for A64 "unprivileged load/store" insns:
-     *  if EL1, access as if EL0; otherwise access at current EL
+    /*
+     * If AccType_UNPRIV is not used, the insn uses AccType_NORMAL,
+     * which is the usual mmu_idx for this cpu state.
      */
-    ARMMMUIdx useridx;
+    ARMMMUIdx useridx = s->mmu_idx;
 
-    switch (s->mmu_idx) {
-    case ARMMMUIdx_S12NSE1:
-        useridx = ARMMMUIdx_S12NSE0;
-        break;
-    case ARMMMUIdx_S1SE1:
-        useridx = ARMMMUIdx_S1SE0;
-        break;
-    case ARMMMUIdx_S2NS:
-        g_assert_not_reached();
-    default:
-        useridx = s->mmu_idx;
-        break;
+    if (s->unpriv) {
+        /*
+         * We have pre-computed the condition for AccType_UNPRIV.
+         * Therefore we should never get here with a mmu_idx for
+         * which we do not know the corresponding user mmu_idx.
+         */
+        switch (useridx) {
+        case ARMMMUIdx_E10_1:
+            useridx = ARMMMUIdx_E10_0;
+            break;
+        case ARMMMUIdx_E20_2:
+            useridx = ARMMMUIdx_E20_0;
+            break;
+        case ARMMMUIdx_SE10_1:
+            useridx = ARMMMUIdx_SE10_0;
+            break;
+        default:
+            g_assert_not_reached();
+        }
     }
     return arm_to_core_mmu_idx(useridx);
 }
@@ -175,8 +186,7 @@ static void gen_top_byte_ignore(DisasContext *s, TCGv_i64 dst,
     if (tbi == 0) {
         /* Load unmodified address */
         tcg_gen_mov_i64(dst, src);
-    } else if (s->current_el >= 2) {
-        /* FIXME: ARMv8.1-VHE S2 translation regime.  */
+    } else if (!regime_has_2_ranges(s->mmu_idx)) {
         /* Force tag byte to all zero */
         tcg_gen_extract_i64(dst, src, 0, 56);
     } else {
@@ -14172,6 +14182,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
     dc->pauth_active = FIELD_EX32(tb_flags, TBFLAG_A64, PAUTH_ACTIVE);
     dc->bt = FIELD_EX32(tb_flags, TBFLAG_A64, BT);
     dc->btype = FIELD_EX32(tb_flags, TBFLAG_A64, BTYPE);
+    dc->unpriv = FIELD_EX32(tb_flags, TBFLAG_A64, UNPRIV);
     dc->vec_len = 0;
     dc->vec_stride = 0;
     dc->cp_regs = arm_cpu->cp_regs;
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 2f4aea927f..e11a5871d0 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -152,14 +152,14 @@ static inline int get_a32_user_mem_index(DisasContext *s)
      *  otherwise, access as if at PL0.
      */
     switch (s->mmu_idx) {
-    case ARMMMUIdx_S1E2:        /* this one is UNPREDICTABLE */
-    case ARMMMUIdx_S12NSE0:
-    case ARMMMUIdx_S12NSE1:
-        return arm_to_core_mmu_idx(ARMMMUIdx_S12NSE0);
-    case ARMMMUIdx_S1E3:
-    case ARMMMUIdx_S1SE0:
-    case ARMMMUIdx_S1SE1:
-        return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0);
+    case ARMMMUIdx_E2:        /* this one is UNPREDICTABLE */
+    case ARMMMUIdx_E10_0:
+    case ARMMMUIdx_E10_1:
+        return arm_to_core_mmu_idx(ARMMMUIdx_E10_0);
+    case ARMMMUIdx_SE3:
+    case ARMMMUIdx_SE10_0:
+    case ARMMMUIdx_SE10_1:
+        return arm_to_core_mmu_idx(ARMMMUIdx_SE10_0);
     case ARMMMUIdx_MUser:
     case ARMMMUIdx_MPriv:
         return arm_to_core_mmu_idx(ARMMMUIdx_MUser);
@@ -172,7 +172,6 @@ static inline int get_a32_user_mem_index(DisasContext *s)
     case ARMMMUIdx_MSUserNegPri:
     case ARMMMUIdx_MSPrivNegPri:
         return arm_to_core_mmu_idx(ARMMMUIdx_MSUserNegPri);
-    case ARMMMUIdx_S2NS:
     default:
         g_assert_not_reached();
     }
@@ -10848,38 +10847,48 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
      */
     dc->secure_routed_to_el3 = arm_feature(env, ARM_FEATURE_EL3) &&
                                !arm_el_is_aa64(env, 3);
-    dc->thumb = FIELD_EX32(tb_flags, TBFLAG_A32, THUMB);
-    dc->sctlr_b = FIELD_EX32(tb_flags, TBFLAG_A32, SCTLR_B);
-    dc->hstr_active = FIELD_EX32(tb_flags, TBFLAG_A32, HSTR_ACTIVE);
+    dc->thumb = FIELD_EX32(tb_flags, TBFLAG_AM32, THUMB);
     dc->be_data = FIELD_EX32(tb_flags, TBFLAG_ANY, BE_DATA) ? MO_BE : MO_LE;
-    condexec = FIELD_EX32(tb_flags, TBFLAG_A32, CONDEXEC);
+    condexec = FIELD_EX32(tb_flags, TBFLAG_AM32, CONDEXEC);
     dc->condexec_mask = (condexec & 0xf) << 1;
     dc->condexec_cond = condexec >> 4;
+
     core_mmu_idx = FIELD_EX32(tb_flags, TBFLAG_ANY, MMUIDX);
     dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx);
     dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx);
 #if !defined(CONFIG_USER_ONLY)
     dc->user = (dc->current_el == 0);
 #endif
-    dc->ns = FIELD_EX32(tb_flags, TBFLAG_A32, NS);
     dc->fp_excp_el = FIELD_EX32(tb_flags, TBFLAG_ANY, FPEXC_EL);
-    dc->vfp_enabled = FIELD_EX32(tb_flags, TBFLAG_A32, VFPEN);
-    dc->vec_len = FIELD_EX32(tb_flags, TBFLAG_A32, VECLEN);
-    if (arm_feature(env, ARM_FEATURE_XSCALE)) {
-        dc->c15_cpar = FIELD_EX32(tb_flags, TBFLAG_A32, XSCALE_CPAR);
-        dc->vec_stride = 0;
+
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        dc->vfp_enabled = 1;
+        dc->be_data = MO_TE;
+        dc->v7m_handler_mode = FIELD_EX32(tb_flags, TBFLAG_M32, HANDLER);
+        dc->v8m_secure = arm_feature(env, ARM_FEATURE_M_SECURITY) &&
+            regime_is_secure(env, dc->mmu_idx);
+        dc->v8m_stackcheck = FIELD_EX32(tb_flags, TBFLAG_M32, STACKCHECK);
+        dc->v8m_fpccr_s_wrong =
+            FIELD_EX32(tb_flags, TBFLAG_M32, FPCCR_S_WRONG);
+        dc->v7m_new_fp_ctxt_needed =
+            FIELD_EX32(tb_flags, TBFLAG_M32, NEW_FP_CTXT_NEEDED);
+        dc->v7m_lspact = FIELD_EX32(tb_flags, TBFLAG_M32, LSPACT);
     } else {
-        dc->vec_stride = FIELD_EX32(tb_flags, TBFLAG_A32, VECSTRIDE);
-        dc->c15_cpar = 0;
-    }
-    dc->v7m_handler_mode = FIELD_EX32(tb_flags, TBFLAG_A32, HANDLER);
-    dc->v8m_secure = arm_feature(env, ARM_FEATURE_M_SECURITY) &&
-        regime_is_secure(env, dc->mmu_idx);
-    dc->v8m_stackcheck = FIELD_EX32(tb_flags, TBFLAG_A32, STACKCHECK);
-    dc->v8m_fpccr_s_wrong = FIELD_EX32(tb_flags, TBFLAG_A32, FPCCR_S_WRONG);
-    dc->v7m_new_fp_ctxt_needed =
-        FIELD_EX32(tb_flags, TBFLAG_A32, NEW_FP_CTXT_NEEDED);
-    dc->v7m_lspact = FIELD_EX32(tb_flags, TBFLAG_A32, LSPACT);
+        dc->be_data =
+            FIELD_EX32(tb_flags, TBFLAG_ANY, BE_DATA) ? MO_BE : MO_LE;
+        dc->debug_target_el =
+            FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL);
+        dc->sctlr_b = FIELD_EX32(tb_flags, TBFLAG_A32, SCTLR_B);
+        dc->hstr_active = FIELD_EX32(tb_flags, TBFLAG_A32, HSTR_ACTIVE);
+        dc->ns = FIELD_EX32(tb_flags, TBFLAG_A32, NS);
+        dc->vfp_enabled = FIELD_EX32(tb_flags, TBFLAG_A32, VFPEN);
+        if (arm_feature(env, ARM_FEATURE_XSCALE)) {
+            dc->c15_cpar = FIELD_EX32(tb_flags, TBFLAG_A32, XSCALE_CPAR);
+        } else {
+            dc->vec_len = FIELD_EX32(tb_flags, TBFLAG_A32, VECLEN);
+            dc->vec_stride = FIELD_EX32(tb_flags, TBFLAG_A32, VECSTRIDE);
+        }
+    }
     dc->cp_regs = cpu->cp_regs;
     dc->features = env->features;
 
@@ -10901,9 +10910,6 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE);
     dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE_SS);
     dc->is_ldex = false;
-    if (!arm_feature(env, ARM_FEATURE_M)) {
-        dc->debug_target_el = FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL);
-    }
 
     dc->page_start = dc->base.pc_first & TARGET_PAGE_MASK;
 
@@ -11340,10 +11346,10 @@ static const TranslatorOps thumb_translator_ops = {
 /* generate intermediate code for basic block 'tb'.  */
 void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int max_insns)
 {
-    DisasContext dc;
+    DisasContext dc = { };
     const TranslatorOps *ops = &arm_translator_ops;
 
-    if (FIELD_EX32(tb->flags, TBFLAG_A32, THUMB)) {
+    if (FIELD_EX32(tb->flags, TBFLAG_AM32, THUMB)) {
         ops = &thumb_translator_ops;
     }
 #ifdef TARGET_AARCH64
diff --git a/target/arm/translate.h b/target/arm/translate.h
index b837b7fcbf..5b167c416a 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -73,6 +73,8 @@ typedef struct DisasContext {
      * ie A64 LDX*, LDAX*, A32/T32 LDREX*, LDAEX*.
      */
     bool is_ldex;
+    /* True if AccType_UNPRIV should be used for LDTR et al */
+    bool unpriv;
     /* True if v8.3-PAuth is active.  */
     bool pauth_active;
     /* True with v8.5-BTI and SCTLR_ELx.BT* set.  */
@@ -126,7 +128,7 @@ static inline int default_exception_el(DisasContext *s)
      * exceptions can only be routed to ELs above 1, so we target the higher of
      * 1 or the current EL.
      */
-    return (s->mmu_idx == ARMMMUIdx_S1SE0 && s->secure_routed_to_el3)
+    return (s->mmu_idx == ARMMMUIdx_SE10_0 && s->secure_routed_to_el3)
             ? 3 : MAX(1, s->current_el);
 }