summary refs log tree commit diff stats
path: root/target/arm/helper.c
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm/helper.c')
-rw-r--r--target/arm/helper.c1216
1 files changed, 951 insertions, 265 deletions
diff --git a/target/arm/helper.c b/target/arm/helper.c
index f00c141ef9..92666e5208 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -15,6 +15,7 @@
 #include "arm_ldst.h"
 #include <zlib.h> /* For crc32 */
 #include "exec/semihost.h"
+#include "sysemu/cpus.h"
 #include "sysemu/kvm.h"
 #include "fpu/softfloat.h"
 #include "qemu/range.h"
@@ -976,10 +977,29 @@ static const ARMCPRegInfo v6_cp_reginfo[] = {
 /* Definitions for the PMU registers */
 #define PMCRN_MASK  0xf800
 #define PMCRN_SHIFT 11
+#define PMCRDP  0x10
 #define PMCRD   0x8
 #define PMCRC   0x4
+#define PMCRP   0x2
 #define PMCRE   0x1
 
+#define PMXEVTYPER_P          0x80000000
+#define PMXEVTYPER_U          0x40000000
+#define PMXEVTYPER_NSK        0x20000000
+#define PMXEVTYPER_NSU        0x10000000
+#define PMXEVTYPER_NSH        0x08000000
+#define PMXEVTYPER_M          0x04000000
+#define PMXEVTYPER_MT         0x02000000
+#define PMXEVTYPER_EVTCOUNT   0x0000ffff
+#define PMXEVTYPER_MASK       (PMXEVTYPER_P | PMXEVTYPER_U | PMXEVTYPER_NSK | \
+                               PMXEVTYPER_NSU | PMXEVTYPER_NSH | \
+                               PMXEVTYPER_M | PMXEVTYPER_MT | \
+                               PMXEVTYPER_EVTCOUNT)
+
+#define PMCCFILTR             0xf8000000
+#define PMCCFILTR_M           PMXEVTYPER_M
+#define PMCCFILTR_EL0         (PMCCFILTR | PMCCFILTR_M)
+
 static inline uint32_t pmu_num_counters(CPUARMState *env)
 {
   return (env->cp15.c9_pmcr & PMCRN_MASK) >> PMCRN_SHIFT;
@@ -991,6 +1011,128 @@ static inline uint64_t pmu_counter_mask(CPUARMState *env)
   return (1 << 31) | ((1 << pmu_num_counters(env)) - 1);
 }
 
+typedef struct pm_event {
+    uint16_t number; /* PMEVTYPER.evtCount is 16 bits wide */
+    /* If the event is supported on this CPU (used to generate PMCEID[01]) */
+    bool (*supported)(CPUARMState *);
+    /*
+     * Retrieve the current count of the underlying event. The programmed
+     * counters hold a difference from the return value from this function
+     */
+    uint64_t (*get_count)(CPUARMState *);
+} pm_event;
+
+static bool event_always_supported(CPUARMState *env)
+{
+    return true;
+}
+
+static uint64_t swinc_get_count(CPUARMState *env)
+{
+    /*
+     * SW_INCR events are written directly to the pmevcntr's by writes to
+     * PMSWINC, so there is no underlying count maintained by the PMU itself
+     */
+    return 0;
+}
+
+/*
+ * Return the underlying cycle count for the PMU cycle counters. If we're in
+ * usermode, simply return 0.
+ */
+static uint64_t cycles_get_count(CPUARMState *env)
+{
+#ifndef CONFIG_USER_ONLY
+    return muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL),
+                   ARM_CPU_FREQ, NANOSECONDS_PER_SECOND);
+#else
+    return cpu_get_host_ticks();
+#endif
+}
+
+#ifndef CONFIG_USER_ONLY
+static bool instructions_supported(CPUARMState *env)
+{
+    return use_icount == 1 /* Precise instruction counting */;
+}
+
+static uint64_t instructions_get_count(CPUARMState *env)
+{
+    return (uint64_t)cpu_get_icount_raw();
+}
+#endif
+
+static const pm_event pm_events[] = {
+    { .number = 0x000, /* SW_INCR */
+      .supported = event_always_supported,
+      .get_count = swinc_get_count,
+    },
+#ifndef CONFIG_USER_ONLY
+    { .number = 0x008, /* INST_RETIRED, Instruction architecturally executed */
+      .supported = instructions_supported,
+      .get_count = instructions_get_count,
+    },
+    { .number = 0x011, /* CPU_CYCLES, Cycle */
+      .supported = event_always_supported,
+      .get_count = cycles_get_count,
+    }
+#endif
+};
+
+/*
+ * Note: Before increasing MAX_EVENT_ID beyond 0x3f into the 0x40xx range of
+ * events (i.e. the statistical profiling extension), this implementation
+ * should first be updated to something sparse instead of the current
+ * supported_event_map[] array.
+ */
+#define MAX_EVENT_ID 0x11
+#define UNSUPPORTED_EVENT UINT16_MAX
+static uint16_t supported_event_map[MAX_EVENT_ID + 1];
+
+/*
+ * Called upon initialization to build PMCEID0_EL0 or PMCEID1_EL0 (indicated by
+ * 'which'). We also use it to build a map of ARM event numbers to indices in
+ * our pm_events array.
+ *
+ * Note: Events in the 0x40XX range are not currently supported.
+ */
+uint64_t get_pmceid(CPUARMState *env, unsigned which)
+{
+    uint64_t pmceid = 0;
+    unsigned int i;
+
+    assert(which <= 1);
+
+    for (i = 0; i < ARRAY_SIZE(supported_event_map); i++) {
+        supported_event_map[i] = UNSUPPORTED_EVENT;
+    }
+
+    for (i = 0; i < ARRAY_SIZE(pm_events); i++) {
+        const pm_event *cnt = &pm_events[i];
+        assert(cnt->number <= MAX_EVENT_ID);
+        /* We do not currently support events in the 0x40xx range */
+        assert(cnt->number <= 0x3f);
+
+        if ((cnt->number & 0x20) == (which << 6) &&
+                cnt->supported(env)) {
+            pmceid |= (1 << (cnt->number & 0x1f));
+            supported_event_map[cnt->number] = i;
+        }
+    }
+    return pmceid;
+}
+
+/*
+ * Check at runtime whether a PMU event is supported for the current machine
+ */
+static bool event_supported(uint16_t number)
+{
+    if (number > MAX_EVENT_ID) {
+        return false;
+    }
+    return supported_event_map[number] != UNSUPPORTED_EVENT;
+}
+
 static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                    bool isread)
 {
@@ -1044,8 +1186,6 @@ static CPAccessResult pmreg_access_swinc(CPUARMState *env,
     return pmreg_access(env, ri, isread);
 }
 
-#ifndef CONFIG_USER_ONLY
-
 static CPAccessResult pmreg_access_selr(CPUARMState *env,
                                         const ARMCPRegInfo *ri,
                                         bool isread)
@@ -1075,68 +1215,222 @@ static CPAccessResult pmreg_access_ccntr(CPUARMState *env,
     return pmreg_access(env, ri, isread);
 }
 
-static inline bool arm_ccnt_enabled(CPUARMState *env)
+/* Returns true if the counter (pass 31 for PMCCNTR) should count events using
+ * the current EL, security state, and register configuration.
+ */
+static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter)
 {
-    /* This does not support checking PMCCFILTR_EL0 register */
+    uint64_t filter;
+    bool e, p, u, nsk, nsu, nsh, m;
+    bool enabled, prohibited, filtered;
+    bool secure = arm_is_secure(env);
+    int el = arm_current_el(env);
+    uint8_t hpmn = env->cp15.mdcr_el2 & MDCR_HPMN;
 
-    if (!(env->cp15.c9_pmcr & PMCRE) || !(env->cp15.c9_pmcnten & (1 << 31))) {
-        return false;
+    if (!arm_feature(env, ARM_FEATURE_EL2) ||
+            (counter < hpmn || counter == 31)) {
+        e = env->cp15.c9_pmcr & PMCRE;
+    } else {
+        e = env->cp15.mdcr_el2 & MDCR_HPME;
     }
+    enabled = e && (env->cp15.c9_pmcnten & (1 << counter));
 
-    return true;
+    if (!secure) {
+        if (el == 2 && (counter < hpmn || counter == 31)) {
+            prohibited = env->cp15.mdcr_el2 & MDCR_HPMD;
+        } else {
+            prohibited = false;
+        }
+    } else {
+        prohibited = arm_feature(env, ARM_FEATURE_EL3) &&
+           (env->cp15.mdcr_el3 & MDCR_SPME);
+    }
+
+    if (prohibited && counter == 31) {
+        prohibited = env->cp15.c9_pmcr & PMCRDP;
+    }
+
+    if (counter == 31) {
+        filter = env->cp15.pmccfiltr_el0;
+    } else {
+        filter = env->cp15.c14_pmevtyper[counter];
+    }
+
+    p   = filter & PMXEVTYPER_P;
+    u   = filter & PMXEVTYPER_U;
+    nsk = arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_NSK);
+    nsu = arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_NSU);
+    nsh = arm_feature(env, ARM_FEATURE_EL2) && (filter & PMXEVTYPER_NSH);
+    m   = arm_el_is_aa64(env, 1) &&
+              arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_M);
+
+    if (el == 0) {
+        filtered = secure ? u : u != nsu;
+    } else if (el == 1) {
+        filtered = secure ? p : p != nsk;
+    } else if (el == 2) {
+        filtered = !nsh;
+    } else { /* EL3 */
+        filtered = m != p;
+    }
+
+    if (counter != 31) {
+        /*
+         * If not checking PMCCNTR, ensure the counter is setup to an event we
+         * support
+         */
+        uint16_t event = filter & PMXEVTYPER_EVTCOUNT;
+        if (!event_supported(event)) {
+            return false;
+        }
+    }
+
+    return enabled && !prohibited && !filtered;
+}
+
+/*
+ * Ensure c15_ccnt is the guest-visible count so that operations such as
+ * enabling/disabling the counter or filtering, modifying the count itself,
+ * etc. can be done logically. This is essentially a no-op if the counter is
+ * not enabled at the time of the call.
+ */
+void pmccntr_op_start(CPUARMState *env)
+{
+    uint64_t cycles = cycles_get_count(env);
+
+    if (pmu_counter_enabled(env, 31)) {
+        uint64_t eff_cycles = cycles;
+        if (env->cp15.c9_pmcr & PMCRD) {
+            /* Increment once every 64 processor clock cycles */
+            eff_cycles /= 64;
+        }
+
+        env->cp15.c15_ccnt = eff_cycles - env->cp15.c15_ccnt_delta;
+    }
+    env->cp15.c15_ccnt_delta = cycles;
 }
 
-void pmccntr_sync(CPUARMState *env)
+/*
+ * If PMCCNTR is enabled, recalculate the delta between the clock and the
+ * guest-visible count. A call to pmccntr_op_finish should follow every call to
+ * pmccntr_op_start.
+ */
+void pmccntr_op_finish(CPUARMState *env)
 {
-    uint64_t temp_ticks;
+    if (pmu_counter_enabled(env, 31)) {
+        uint64_t prev_cycles = env->cp15.c15_ccnt_delta;
+
+        if (env->cp15.c9_pmcr & PMCRD) {
+            /* Increment once every 64 processor clock cycles */
+            prev_cycles /= 64;
+        }
+
+        env->cp15.c15_ccnt_delta = prev_cycles - env->cp15.c15_ccnt;
+    }
+}
+
+static void pmevcntr_op_start(CPUARMState *env, uint8_t counter)
+{
+
+    uint16_t event = env->cp15.c14_pmevtyper[counter] & PMXEVTYPER_EVTCOUNT;
+    uint64_t count = 0;
+    if (event_supported(event)) {
+        uint16_t event_idx = supported_event_map[event];
+        count = pm_events[event_idx].get_count(env);
+    }
+
+    if (pmu_counter_enabled(env, counter)) {
+        env->cp15.c14_pmevcntr[counter] =
+            count - env->cp15.c14_pmevcntr_delta[counter];
+    }
+    env->cp15.c14_pmevcntr_delta[counter] = count;
+}
 
-    temp_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL),
-                          ARM_CPU_FREQ, NANOSECONDS_PER_SECOND);
+static void pmevcntr_op_finish(CPUARMState *env, uint8_t counter)
+{
+    if (pmu_counter_enabled(env, counter)) {
+        env->cp15.c14_pmevcntr_delta[counter] -=
+            env->cp15.c14_pmevcntr[counter];
+    }
+}
 
-    if (env->cp15.c9_pmcr & PMCRD) {
-        /* Increment once every 64 processor clock cycles */
-        temp_ticks /= 64;
+void pmu_op_start(CPUARMState *env)
+{
+    unsigned int i;
+    pmccntr_op_start(env);
+    for (i = 0; i < pmu_num_counters(env); i++) {
+        pmevcntr_op_start(env, i);
     }
+}
 
-    if (arm_ccnt_enabled(env)) {
-        env->cp15.c15_ccnt = temp_ticks - env->cp15.c15_ccnt;
+void pmu_op_finish(CPUARMState *env)
+{
+    unsigned int i;
+    pmccntr_op_finish(env);
+    for (i = 0; i < pmu_num_counters(env); i++) {
+        pmevcntr_op_finish(env, i);
     }
 }
 
+void pmu_pre_el_change(ARMCPU *cpu, void *ignored)
+{
+    pmu_op_start(&cpu->env);
+}
+
+void pmu_post_el_change(ARMCPU *cpu, void *ignored)
+{
+    pmu_op_finish(&cpu->env);
+}
+
 static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                        uint64_t value)
 {
-    pmccntr_sync(env);
+    pmu_op_start(env);
 
     if (value & PMCRC) {
         /* The counter has been reset */
         env->cp15.c15_ccnt = 0;
     }
 
+    if (value & PMCRP) {
+        unsigned int i;
+        for (i = 0; i < pmu_num_counters(env); i++) {
+            env->cp15.c14_pmevcntr[i] = 0;
+        }
+    }
+
     /* only the DP, X, D and E bits are writable */
     env->cp15.c9_pmcr &= ~0x39;
     env->cp15.c9_pmcr |= (value & 0x39);
 
-    pmccntr_sync(env);
+    pmu_op_finish(env);
 }
 
-static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri)
+static void pmswinc_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
 {
-    uint64_t total_ticks;
-
-    if (!arm_ccnt_enabled(env)) {
-        /* Counter is disabled, do not change value */
-        return env->cp15.c15_ccnt;
+    unsigned int i;
+    for (i = 0; i < pmu_num_counters(env); i++) {
+        /* Increment a counter's count iff: */
+        if ((value & (1 << i)) && /* counter's bit is set */
+                /* counter is enabled and not filtered */
+                pmu_counter_enabled(env, i) &&
+                /* counter is SW_INCR */
+                (env->cp15.c14_pmevtyper[i] & PMXEVTYPER_EVTCOUNT) == 0x0) {
+            pmevcntr_op_start(env, i);
+            env->cp15.c14_pmevcntr[i]++;
+            pmevcntr_op_finish(env, i);
+        }
     }
+}
 
-    total_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL),
-                           ARM_CPU_FREQ, NANOSECONDS_PER_SECOND);
-
-    if (env->cp15.c9_pmcr & PMCRD) {
-        /* Increment once every 64 processor clock cycles */
-        total_ticks /= 64;
-    }
-    return total_ticks - env->cp15.c15_ccnt;
+static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    uint64_t ret;
+    pmccntr_op_start(env);
+    ret = env->cp15.c15_ccnt;
+    pmccntr_op_finish(env);
+    return ret;
 }
 
 static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -1153,22 +1447,9 @@ static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void pmccntr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                         uint64_t value)
 {
-    uint64_t total_ticks;
-
-    if (!arm_ccnt_enabled(env)) {
-        /* Counter is disabled, set the absolute value */
-        env->cp15.c15_ccnt = value;
-        return;
-    }
-
-    total_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL),
-                           ARM_CPU_FREQ, NANOSECONDS_PER_SECOND);
-
-    if (env->cp15.c9_pmcr & PMCRD) {
-        /* Increment once every 64 processor clock cycles */
-        total_ticks /= 64;
-    }
-    env->cp15.c15_ccnt = total_ticks - value;
+    pmccntr_op_start(env);
+    env->cp15.c15_ccnt = value;
+    pmccntr_op_finish(env);
 }
 
 static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -1179,20 +1460,28 @@ static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri,
     pmccntr_write(env, ri, deposit64(cur_val, 0, 32, value));
 }
 
-#else /* CONFIG_USER_ONLY */
-
-void pmccntr_sync(CPUARMState *env)
+static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                            uint64_t value)
 {
+    pmccntr_op_start(env);
+    env->cp15.pmccfiltr_el0 = value & PMCCFILTR_EL0;
+    pmccntr_op_finish(env);
 }
 
-#endif
-
-static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+static void pmccfiltr_write_a32(CPUARMState *env, const ARMCPRegInfo *ri,
                             uint64_t value)
 {
-    pmccntr_sync(env);
-    env->cp15.pmccfiltr_el0 = value & 0xfc000000;
-    pmccntr_sync(env);
+    pmccntr_op_start(env);
+    /* M is not accessible from AArch32 */
+    env->cp15.pmccfiltr_el0 = (env->cp15.pmccfiltr_el0 & PMCCFILTR_M) |
+        (value & PMCCFILTR);
+    pmccntr_op_finish(env);
+}
+
+static uint64_t pmccfiltr_read_a32(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    /* M is not visible in AArch32 */
+    return env->cp15.pmccfiltr_el0 & PMCCFILTR;
 }
 
 static void pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -1216,30 +1505,181 @@ static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     env->cp15.c9_pmovsr &= ~value;
 }
 
-static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                             uint64_t value)
+static void pmovsset_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
 {
+    value &= pmu_counter_mask(env);
+    env->cp15.c9_pmovsr |= value;
+}
+
+static void pmevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value, const uint8_t counter)
+{
+    if (counter == 31) {
+        pmccfiltr_write(env, ri, value);
+    } else if (counter < pmu_num_counters(env)) {
+        pmevcntr_op_start(env, counter);
+
+        /*
+         * If this counter's event type is changing, store the current
+         * underlying count for the new type in c14_pmevcntr_delta[counter] so
+         * pmevcntr_op_finish has the correct baseline when it converts back to
+         * a delta.
+         */
+        uint16_t old_event = env->cp15.c14_pmevtyper[counter] &
+            PMXEVTYPER_EVTCOUNT;
+        uint16_t new_event = value & PMXEVTYPER_EVTCOUNT;
+        if (old_event != new_event) {
+            uint64_t count = 0;
+            if (event_supported(new_event)) {
+                uint16_t event_idx = supported_event_map[new_event];
+                count = pm_events[event_idx].get_count(env);
+            }
+            env->cp15.c14_pmevcntr_delta[counter] = count;
+        }
+
+        env->cp15.c14_pmevtyper[counter] = value & PMXEVTYPER_MASK;
+        pmevcntr_op_finish(env, counter);
+    }
     /* Attempts to access PMXEVTYPER are CONSTRAINED UNPREDICTABLE when
      * PMSELR value is equal to or greater than the number of implemented
      * counters, but not equal to 0x1f. We opt to behave as a RAZ/WI.
      */
-    if (env->cp15.c9_pmselr == 0x1f) {
-        pmccfiltr_write(env, ri, value);
+}
+
+static uint64_t pmevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri,
+                               const uint8_t counter)
+{
+    if (counter == 31) {
+        return env->cp15.pmccfiltr_el0;
+    } else if (counter < pmu_num_counters(env)) {
+        return env->cp15.c14_pmevtyper[counter];
+    } else {
+      /*
+       * We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER
+       * are CONSTRAINED UNPREDICTABLE. See comments in pmevtyper_write().
+       */
+        return 0;
     }
 }
 
+static void pmevtyper_writefn(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint64_t value)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    pmevtyper_write(env, ri, value, counter);
+}
+
+static void pmevtyper_rawwrite(CPUARMState *env, const ARMCPRegInfo *ri,
+                               uint64_t value)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    env->cp15.c14_pmevtyper[counter] = value;
+
+    /*
+     * pmevtyper_rawwrite is called between a pair of pmu_op_start and
+     * pmu_op_finish calls when loading saved state for a migration. Because
+     * we're potentially updating the type of event here, the value written to
+     * c14_pmevcntr_delta by the preceeding pmu_op_start call may be for a
+     * different counter type. Therefore, we need to set this value to the
+     * current count for the counter type we're writing so that pmu_op_finish
+     * has the correct count for its calculation.
+     */
+    uint16_t event = value & PMXEVTYPER_EVTCOUNT;
+    if (event_supported(event)) {
+        uint16_t event_idx = supported_event_map[event];
+        env->cp15.c14_pmevcntr_delta[counter] =
+            pm_events[event_idx].get_count(env);
+    }
+}
+
+static uint64_t pmevtyper_readfn(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    return pmevtyper_read(env, ri, counter);
+}
+
+static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value)
+{
+    pmevtyper_write(env, ri, value, env->cp15.c9_pmselr & 31);
+}
+
 static uint64_t pmxevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-    /* We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER
-     * are CONSTRAINED UNPREDICTABLE. See comments in pmxevtyper_write().
+    return pmevtyper_read(env, ri, env->cp15.c9_pmselr & 31);
+}
+
+static void pmevcntr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value, uint8_t counter)
+{
+    if (counter < pmu_num_counters(env)) {
+        pmevcntr_op_start(env, counter);
+        env->cp15.c14_pmevcntr[counter] = value;
+        pmevcntr_op_finish(env, counter);
+    }
+    /*
+     * We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR
+     * are CONSTRAINED UNPREDICTABLE.
      */
-    if (env->cp15.c9_pmselr == 0x1f) {
-        return env->cp15.pmccfiltr_el0;
+}
+
+static uint64_t pmevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri,
+                              uint8_t counter)
+{
+    if (counter < pmu_num_counters(env)) {
+        uint64_t ret;
+        pmevcntr_op_start(env, counter);
+        ret = env->cp15.c14_pmevcntr[counter];
+        pmevcntr_op_finish(env, counter);
+        return ret;
     } else {
+      /* We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR
+       * are CONSTRAINED UNPREDICTABLE. */
         return 0;
     }
 }
 
+static void pmevcntr_writefn(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    pmevcntr_write(env, ri, value, counter);
+}
+
+static uint64_t pmevcntr_readfn(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    return pmevcntr_read(env, ri, counter);
+}
+
+static void pmevcntr_rawwrite(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    assert(counter < pmu_num_counters(env));
+    env->cp15.c14_pmevcntr[counter] = value;
+    pmevcntr_write(env, ri, value, counter);
+}
+
+static uint64_t pmevcntr_rawread(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7);
+    assert(counter < pmu_num_counters(env));
+    return env->cp15.c14_pmevcntr[counter];
+}
+
+static void pmxevcntr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                             uint64_t value)
+{
+    pmevcntr_write(env, ri, value, env->cp15.c9_pmselr & 31);
+}
+
+static uint64_t pmxevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return pmevcntr_read(env, ri, env->cp15.c9_pmselr & 31);
+}
+
 static void pmuserenr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                             uint64_t value)
 {
@@ -1368,7 +1808,7 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .access = PL1_W, .type = ARM_CP_NOP },
     /* Performance monitors are implementation defined in v7,
      * but with an ARM recommended set of registers, which we
-     * follow (although we don't actually implement any counters)
+     * follow.
      *
      * Performance registers fall into three categories:
      *  (a) always UNDEF in PL0, RW in PL1 (PMINTENSET, PMINTENCLR)
@@ -1413,10 +1853,13 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr),
       .writefn = pmovsr_write,
       .raw_writefn = raw_write },
-    /* Unimplemented so WI. */
     { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4,
-      .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NOP },
-#ifndef CONFIG_USER_ONLY
+      .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW,
+      .writefn = pmswinc_write },
+    { .name = "PMSWINC_EL0", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 4,
+      .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW,
+      .writefn = pmswinc_write },
     { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5,
       .access = PL0_RW, .type = ARM_CP_ALIAS,
       .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmselr),
@@ -1435,26 +1878,39 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 0,
       .access = PL0_RW, .accessfn = pmreg_access_ccntr,
       .type = ARM_CP_IO,
-      .readfn = pmccntr_read, .writefn = pmccntr_write, },
-#endif
+      .fieldoffset = offsetof(CPUARMState, cp15.c15_ccnt),
+      .readfn = pmccntr_read, .writefn = pmccntr_write,
+      .raw_readfn = raw_read, .raw_writefn = raw_write, },
+    { .name = "PMCCFILTR", .cp = 15, .opc1 = 0, .crn = 14, .crm = 15, .opc2 = 7,
+      .writefn = pmccfiltr_write_a32, .readfn = pmccfiltr_read_a32,
+      .access = PL0_RW, .accessfn = pmreg_access,
+      .type = ARM_CP_ALIAS | ARM_CP_IO,
+      .resetvalue = 0, },
     { .name = "PMCCFILTR_EL0", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 15, .opc2 = 7,
-      .writefn = pmccfiltr_write,
+      .writefn = pmccfiltr_write, .raw_writefn = raw_write,
       .access = PL0_RW, .accessfn = pmreg_access,
       .type = ARM_CP_IO,
       .fieldoffset = offsetof(CPUARMState, cp15.pmccfiltr_el0),
       .resetvalue = 0, },
     { .name = "PMXEVTYPER", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 1,
-      .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access,
+      .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO,
+      .accessfn = pmreg_access,
       .writefn = pmxevtyper_write, .readfn = pmxevtyper_read },
     { .name = "PMXEVTYPER_EL0", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 1,
-      .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access,
+      .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO,
+      .accessfn = pmreg_access,
       .writefn = pmxevtyper_write, .readfn = pmxevtyper_read },
-    /* Unimplemented, RAZ/WI. */
     { .name = "PMXEVCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 2,
-      .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0,
-      .accessfn = pmreg_access_xevcntr },
+      .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO,
+      .accessfn = pmreg_access_xevcntr,
+      .writefn = pmxevcntr_write, .readfn = pmxevcntr_read },
+    { .name = "PMXEVCNTR_EL0", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 2,
+      .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO,
+      .accessfn = pmreg_access_xevcntr,
+      .writefn = pmxevcntr_write, .readfn = pmxevcntr_read },
     { .name = "PMUSERENR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 0,
       .access = PL0_R | PL1_RW, .accessfn = access_tpm,
       .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmuserenr),
@@ -1585,6 +2041,24 @@ static const ARMCPRegInfo v7mp_cp_reginfo[] = {
     REGINFO_SENTINEL
 };
 
+static const ARMCPRegInfo pmovsset_cp_reginfo[] = {
+    /* PMOVSSET is not implemented in v7 before v7ve */
+    { .name = "PMOVSSET", .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 3,
+      .access = PL0_RW, .accessfn = pmreg_access,
+      .type = ARM_CP_ALIAS,
+      .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmovsr),
+      .writefn = pmovsset_write,
+      .raw_writefn = raw_write },
+    { .name = "PMOVSSET_EL0", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 14, .opc2 = 3,
+      .access = PL0_RW, .accessfn = pmreg_access,
+      .type = ARM_CP_ALIAS,
+      .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr),
+      .writefn = pmovsset_write,
+      .raw_writefn = raw_write },
+    REGINFO_SENTINEL
+};
+
 static void teecr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                         uint64_t value)
 {
@@ -4284,7 +4758,7 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
 #endif
     /* The only field of MDCR_EL2 that has a defined architectural reset value
      * is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N; but we
-     * don't impelment any PMU event counters, so using zero as a reset
+     * don't implement any PMU event counters, so using zero as a reset
      * value for MDCR_EL2 is okay
      */
     { .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH,
@@ -5061,6 +5535,70 @@ static CPAccessResult access_lor_other(CPUARMState *env,
     return access_lor_ns(env);
 }
 
+#ifdef TARGET_AARCH64
+static CPAccessResult access_pauth(CPUARMState *env, const ARMCPRegInfo *ri,
+                                   bool isread)
+{
+    int el = arm_current_el(env);
+
+    if (el < 2 &&
+        arm_feature(env, ARM_FEATURE_EL2) &&
+        !(arm_hcr_el2_eff(env) & HCR_APK)) {
+        return CP_ACCESS_TRAP_EL2;
+    }
+    if (el < 3 &&
+        arm_feature(env, ARM_FEATURE_EL3) &&
+        !(env->cp15.scr_el3 & SCR_APK)) {
+        return CP_ACCESS_TRAP_EL3;
+    }
+    return CP_ACCESS_OK;
+}
+
+static const ARMCPRegInfo pauth_reginfo[] = {
+    { .name = "APDAKEYLO_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 0,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apda_key.lo) },
+    { .name = "APDAKEYHI_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 1,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apda_key.hi) },
+    { .name = "APDBKEYLO_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 2,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apdb_key.lo) },
+    { .name = "APDBKEYHI_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 3,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apdb_key.hi) },
+    { .name = "APGAKEYLO_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 3, .opc2 = 0,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apga_key.lo) },
+    { .name = "APGAKEYHI_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 3, .opc2 = 1,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apga_key.hi) },
+    { .name = "APIAKEYLO_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 0,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apia_key.lo) },
+    { .name = "APIAKEYHI_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 1,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apia_key.hi) },
+    { .name = "APIBKEYLO_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 2,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apib_key.lo) },
+    { .name = "APIBKEYHI_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 3,
+      .access = PL1_RW, .accessfn = access_pauth,
+      .fieldoffset = offsetof(CPUARMState, apib_key.hi) },
+    REGINFO_SENTINEL
+};
+#endif
+
 void register_cp_regs_for_features(ARMCPU *cpu)
 {
     /* Register all the coprocessor registers based on feature bits */
@@ -5163,12 +5701,15 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         !arm_feature(env, ARM_FEATURE_PMSA)) {
         define_arm_cp_regs(cpu, v7mp_cp_reginfo);
     }
+    if (arm_feature(env, ARM_FEATURE_V7VE)) {
+        define_arm_cp_regs(cpu, pmovsset_cp_reginfo);
+    }
     if (arm_feature(env, ARM_FEATURE_V7)) {
         /* v7 performance monitor control register: same implementor
-         * field as main ID register, and we implement only the cycle
-         * count register.
+         * field as main ID register, and we implement four counters in
+         * addition to the cycle count register.
          */
-#ifndef CONFIG_USER_ONLY
+        unsigned int i, pmcrn = 4;
         ARMCPRegInfo pmcr = {
             .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0,
             .access = PL0_RW,
@@ -5183,12 +5724,48 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             .access = PL0_RW, .accessfn = pmreg_access,
             .type = ARM_CP_IO,
             .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr),
-            .resetvalue = cpu->midr & 0xff000000,
+            .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT),
             .writefn = pmcr_write, .raw_writefn = raw_write,
         };
         define_one_arm_cp_reg(cpu, &pmcr);
         define_one_arm_cp_reg(cpu, &pmcr64);
-#endif
+        for (i = 0; i < pmcrn; i++) {
+            char *pmevcntr_name = g_strdup_printf("PMEVCNTR%d", i);
+            char *pmevcntr_el0_name = g_strdup_printf("PMEVCNTR%d_EL0", i);
+            char *pmevtyper_name = g_strdup_printf("PMEVTYPER%d", i);
+            char *pmevtyper_el0_name = g_strdup_printf("PMEVTYPER%d_EL0", i);
+            ARMCPRegInfo pmev_regs[] = {
+                { .name = pmevcntr_name, .cp = 15, .crn = 15,
+                  .crm = 8 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7,
+                  .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS,
+                  .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn,
+                  .accessfn = pmreg_access },
+                { .name = pmevcntr_el0_name, .state = ARM_CP_STATE_AA64,
+                  .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 8 | (3 & (i >> 3)),
+                  .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access,
+                  .type = ARM_CP_IO,
+                  .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn,
+                  .raw_readfn = pmevcntr_rawread,
+                  .raw_writefn = pmevcntr_rawwrite },
+                { .name = pmevtyper_name, .cp = 15, .crn = 15,
+                  .crm = 12 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7,
+                  .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS,
+                  .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn,
+                  .accessfn = pmreg_access },
+                { .name = pmevtyper_el0_name, .state = ARM_CP_STATE_AA64,
+                  .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 12 | (3 & (i >> 3)),
+                  .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access,
+                  .type = ARM_CP_IO,
+                  .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn,
+                  .raw_writefn = pmevtyper_rawwrite },
+                REGINFO_SENTINEL
+            };
+            define_arm_cp_regs(cpu, pmev_regs);
+            g_free(pmevcntr_name);
+            g_free(pmevcntr_el0_name);
+            g_free(pmevtyper_name);
+            g_free(pmevtyper_el0_name);
+        }
         ARMCPRegInfo clidr = {
             .name = "CLIDR", .state = ARM_CP_STATE_BOTH,
             .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 1,
@@ -5200,6 +5777,21 @@ void register_cp_regs_for_features(ARMCPU *cpu)
     } else {
         define_arm_cp_regs(cpu, not_v7_cp_reginfo);
     }
+    if (FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) >= 4 &&
+            FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) != 0xf) {
+        ARMCPRegInfo v81_pmu_regs[] = {
+            { .name = "PMCEID2", .state = ARM_CP_STATE_AA32,
+              .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 4,
+              .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST,
+              .resetvalue = extract64(cpu->pmceid0, 32, 32) },
+            { .name = "PMCEID3", .state = ARM_CP_STATE_AA32,
+              .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 5,
+              .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST,
+              .resetvalue = extract64(cpu->pmceid1, 32, 32) },
+            REGINFO_SENTINEL
+        };
+        define_arm_cp_regs(cpu, v81_pmu_regs);
+    }
     if (arm_feature(env, ARM_FEATURE_V8)) {
         /* AArch64 ID registers, which all have impdef reset values.
          * Note that within the ID register ranges the unused slots
@@ -5376,7 +5968,7 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             { .name = "PMCEID0", .state = ARM_CP_STATE_AA32,
               .cp = 15, .opc1 = 0, .crn = 9, .crm = 12, .opc2 = 6,
               .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST,
-              .resetvalue = cpu->pmceid0 },
+              .resetvalue = extract64(cpu->pmceid0, 0, 32) },
             { .name = "PMCEID0_EL0", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 6,
               .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST,
@@ -5384,7 +5976,7 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             { .name = "PMCEID1", .state = ARM_CP_STATE_AA32,
               .cp = 15, .opc1 = 0, .crn = 9, .crm = 12, .opc2 = 7,
               .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST,
-              .resetvalue = cpu->pmceid1 },
+              .resetvalue = extract64(cpu->pmceid1, 0, 32) },
             { .name = "PMCEID1_EL0", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 7,
               .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST,
@@ -5845,6 +6437,12 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             define_one_arm_cp_reg(cpu, &zcr_el3_reginfo);
         }
     }
+
+#ifdef TARGET_AARCH64
+    if (cpu_isar_feature(aa64_pauth, cpu)) {
+        define_arm_cp_regs(cpu, pauth_reginfo);
+    }
+#endif
 }
 
 void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu)
@@ -6297,7 +6895,7 @@ static int bad_mode_switch(CPUARMState *env, int mode, CPSRWriteType write_type)
         return 0;
     case ARM_CPU_MODE_HYP:
         return !arm_feature(env, ARM_FEATURE_EL2)
-            || arm_current_el(env) < 2 || arm_is_secure(env);
+            || arm_current_el(env) < 2 || arm_is_secure_below_el3(env);
     case ARM_CPU_MODE_MON:
         return arm_current_el(env) < 3;
     default:
@@ -7117,7 +7715,7 @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain,
             limit = env->v7m.msplim[M_REG_S];
         }
     } else {
-        mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false));
+        mmu_idx = arm_mmu_idx(env);
         frame_sp_p = &env->regs[13];
         limit = v7m_sp_limit(env);
     }
@@ -7298,7 +7896,7 @@ static bool v7m_push_stack(ARMCPU *cpu)
     CPUARMState *env = &cpu->env;
     uint32_t xpsr = xpsr_read(env);
     uint32_t frameptr = env->regs[13];
-    ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false));
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
 
     /* Align stack pointer if the guest wants that */
     if ((frameptr & 4) &&
@@ -8957,48 +9555,6 @@ static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx)
     return mmu_idx;
 }
 
-/* Returns TBI0 value for current regime el */
-uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx)
-{
-    TCR *tcr;
-    uint32_t el;
-
-    /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert
-     * a stage 1+2 mmu index into the appropriate stage 1 mmu index.
-     */
-    mmu_idx = stage_1_mmu_idx(mmu_idx);
-
-    tcr = regime_tcr(env, mmu_idx);
-    el = regime_el(env, mmu_idx);
-
-    if (el > 1) {
-        return extract64(tcr->raw_tcr, 20, 1);
-    } else {
-        return extract64(tcr->raw_tcr, 37, 1);
-    }
-}
-
-/* Returns TBI1 value for current regime el */
-uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx)
-{
-    TCR *tcr;
-    uint32_t el;
-
-    /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert
-     * a stage 1+2 mmu index into the appropriate stage 1 mmu index.
-     */
-    mmu_idx = stage_1_mmu_idx(mmu_idx);
-
-    tcr = regime_tcr(env, mmu_idx);
-    el = regime_el(env, mmu_idx);
-
-    if (el > 1) {
-        return 0;
-    } else {
-        return extract64(tcr->raw_tcr, 38, 1);
-    }
-}
-
 /* Return the TTBR associated with this translation regime */
 static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx,
                                    int ttbrn)
@@ -9744,6 +10300,138 @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs)
     return (hiattr << 6) | (hihint << 4) | (loattr << 2) | lohint;
 }
 
+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;
+
+    /*
+     * Bit 55 is always between the two regions, and is canonical for
+     * determining if address tagging is enabled.
+     */
+    select = extract64(va, 55, 1);
+
+    if (el > 1) {
+        tsz = extract32(tcr, 0, 6);
+        using64k = extract32(tcr, 14, 1);
+        using16k = extract32(tcr, 15, 1);
+        if (mmu_idx == ARMMMUIdx_S2NS) {
+            /* VTCR_EL2 */
+            tbi = tbid = hpd = false;
+        } else {
+            tbi = extract32(tcr, 20, 1);
+            hpd = extract32(tcr, 24, 1);
+            tbid = extract32(tcr, 29, 1);
+        }
+        epd = false;
+    } else if (!select) {
+        tsz = extract32(tcr, 0, 6);
+        epd = extract32(tcr, 7, 1);
+        using64k = extract32(tcr, 14, 1);
+        using16k = extract32(tcr, 15, 1);
+        tbi = extract64(tcr, 37, 1);
+        hpd = extract64(tcr, 41, 1);
+        tbid = extract64(tcr, 51, 1);
+    } else {
+        int tg = extract32(tcr, 30, 2);
+        using16k = tg == 1;
+        using64k = tg == 3;
+        tsz = extract32(tcr, 16, 6);
+        epd = extract32(tcr, 23, 1);
+        tbi = extract64(tcr, 38, 1);
+        hpd = extract64(tcr, 42, 1);
+        tbid = extract64(tcr, 52, 1);
+    }
+    tsz = MIN(tsz, 39);  /* TODO: ARMv8.4-TTST */
+    tsz = MAX(tsz, 16);  /* TODO: ARMv8.2-LVA  */
+
+    return (ARMVAParameters) {
+        .tsz = tsz,
+        .select = select,
+        .tbi = tbi,
+        .tbid = tbid,
+        .epd = epd,
+        .hpd = hpd,
+        .using16k = using16k,
+        .using64k = using64k,
+    };
+}
+
+ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
+                                   ARMMMUIdx mmu_idx, bool data)
+{
+    ARMVAParameters ret = aa64_va_parameters_both(env, va, mmu_idx);
+
+    /* Present TBI as a composite with TBID.  */
+    ret.tbi &= (data || !ret.tbid);
+    return ret;
+}
+
+static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va,
+                                          ARMMMUIdx mmu_idx)
+{
+    uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr;
+    uint32_t el = regime_el(env, mmu_idx);
+    int select, tsz;
+    bool epd, hpd;
+
+    if (mmu_idx == ARMMMUIdx_S2NS) {
+        /* VTCR */
+        bool sext = extract32(tcr, 4, 1);
+        bool sign = extract32(tcr, 3, 1);
+
+        /*
+         * If the sign-extend bit is not the same as t0sz[3], the result
+         * is unpredictable. Flag this as a guest error.
+         */
+        if (sign != sext) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "AArch32: VTCR.S / VTCR.T0SZ[3] mismatch\n");
+        }
+        tsz = sextract32(tcr, 0, 4) + 8;
+        select = 0;
+        hpd = false;
+        epd = false;
+    } else if (el == 2) {
+        /* HTCR */
+        tsz = extract32(tcr, 0, 3);
+        select = 0;
+        hpd = extract64(tcr, 24, 1);
+        epd = false;
+    } else {
+        int t0sz = extract32(tcr, 0, 3);
+        int t1sz = extract32(tcr, 16, 3);
+
+        if (t1sz == 0) {
+            select = va > (0xffffffffu >> t0sz);
+        } else {
+            /* Note that we will detect errors later.  */
+            select = va >= ~(0xffffffffu >> t1sz);
+        }
+        if (!select) {
+            tsz = t0sz;
+            epd = extract32(tcr, 7, 1);
+            hpd = extract64(tcr, 41, 1);
+        } else {
+            tsz = t1sz;
+            epd = extract32(tcr, 23, 1);
+            hpd = extract64(tcr, 42, 1);
+        }
+        /* For aarch32, hpd0 is not enabled without t2e as well.  */
+        hpd &= extract32(tcr, 6, 1);
+    }
+
+    return (ARMVAParameters) {
+        .tsz = tsz,
+        .select = select,
+        .epd = epd,
+        .hpd = hpd,
+    };
+}
+
 static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
                                MMUAccessType access_type, ARMMMUIdx mmu_idx,
                                hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot,
@@ -9755,26 +10443,20 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
     /* Read an LPAE long-descriptor translation table. */
     ARMFaultType fault_type = ARMFault_Translation;
     uint32_t level;
-    uint32_t epd = 0;
-    int32_t t0sz, t1sz;
-    uint32_t tg;
+    ARMVAParameters param;
     uint64_t ttbr;
-    int ttbr_select;
     hwaddr descaddr, indexmask, indexmask_grainsize;
     uint32_t tableattrs;
-    target_ulong page_size;
+    target_ulong page_size, top_bits;
     uint32_t attrs;
-    int32_t stride = 9;
-    int32_t addrsize;
-    int inputsize;
-    int32_t tbi = 0;
+    int32_t stride;
+    int addrsize, inputsize;
     TCR *tcr = regime_tcr(env, mmu_idx);
     int ap, ns, xn, pxn;
     uint32_t el = regime_el(env, mmu_idx);
-    bool ttbr1_valid = true;
+    bool ttbr1_valid;
     uint64_t descaddrmask;
     bool aarch64 = arm_el_is_aa64(env, el);
-    bool hpd = false;
 
     /* TODO:
      * This code does not handle the different format TCR for VTCR_EL2.
@@ -9783,91 +10465,44 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
      * support for those page table walks.
      */
     if (aarch64) {
+        param = aa64_va_parameters(env, address, mmu_idx,
+                                   access_type != MMU_INST_FETCH);
         level = 0;
-        addrsize = 64;
-        if (el > 1) {
-            if (mmu_idx != ARMMMUIdx_S2NS) {
-                tbi = extract64(tcr->raw_tcr, 20, 1);
-            }
-        } else {
-            if (extract64(address, 55, 1)) {
-                tbi = extract64(tcr->raw_tcr, 38, 1);
-            } else {
-                tbi = extract64(tcr->raw_tcr, 37, 1);
-            }
-        }
-        tbi *= 8;
-
         /* If we are in 64-bit EL2 or EL3 then there is no TTBR1, so mark it
          * invalid.
          */
-        if (el > 1) {
-            ttbr1_valid = false;
-        }
+        ttbr1_valid = (el < 2);
+        addrsize = 64 - 8 * param.tbi;
+        inputsize = 64 - param.tsz;
     } else {
+        param = aa32_va_parameters(env, address, mmu_idx);
         level = 1;
-        addrsize = 32;
         /* There is no TTBR1 for EL2 */
-        if (el == 2) {
-            ttbr1_valid = false;
-        }
+        ttbr1_valid = (el != 2);
+        addrsize = (mmu_idx == ARMMMUIdx_S2NS ? 40 : 32);
+        inputsize = addrsize - param.tsz;
     }
 
-    /* Determine whether this address is in the region controlled by
-     * TTBR0 or TTBR1 (or if it is in neither region and should fault).
-     * This is a Non-secure PL0/1 stage 1 translation, so controlled by
-     * TTBCR/TTBR0/TTBR1 in accordance with ARM ARM DDI0406C table B-32:
+    /*
+     * We determined the region when collecting the parameters, but we
+     * have not yet validated that the address is valid for the region.
+     * Extract the top bits and verify that they all match select.
      */
-    if (aarch64) {
-        /* AArch64 translation.  */
-        t0sz = extract32(tcr->raw_tcr, 0, 6);
-        t0sz = MIN(t0sz, 39);
-        t0sz = MAX(t0sz, 16);
-    } else if (mmu_idx != ARMMMUIdx_S2NS) {
-        /* AArch32 stage 1 translation.  */
-        t0sz = extract32(tcr->raw_tcr, 0, 3);
-    } else {
-        /* AArch32 stage 2 translation.  */
-        bool sext = extract32(tcr->raw_tcr, 4, 1);
-        bool sign = extract32(tcr->raw_tcr, 3, 1);
-        /* Address size is 40-bit for a stage 2 translation,
-         * and t0sz can be negative (from -8 to 7),
-         * so we need to adjust it to use the TTBR selecting logic below.
-         */
-        addrsize = 40;
-        t0sz = sextract32(tcr->raw_tcr, 0, 4) + 8;
-
-        /* If the sign-extend bit is not the same as t0sz[3], the result
-         * is unpredictable. Flag this as a guest error.  */
-        if (sign != sext) {
-            qemu_log_mask(LOG_GUEST_ERROR,
-                          "AArch32: VTCR.S / VTCR.T0SZ[3] mismatch\n");
-        }
-    }
-    t1sz = extract32(tcr->raw_tcr, 16, 6);
-    if (aarch64) {
-        t1sz = MIN(t1sz, 39);
-        t1sz = MAX(t1sz, 16);
-    }
-    if (t0sz && !extract64(address, addrsize - t0sz, t0sz - tbi)) {
-        /* there is a ttbr0 region and we are in it (high bits all zero) */
-        ttbr_select = 0;
-    } else if (ttbr1_valid && t1sz &&
-               !extract64(~address, addrsize - t1sz, t1sz - tbi)) {
-        /* there is a ttbr1 region and we are in it (high bits all one) */
-        ttbr_select = 1;
-    } else if (!t0sz) {
-        /* ttbr0 region is "everything not in the ttbr1 region" */
-        ttbr_select = 0;
-    } else if (!t1sz && ttbr1_valid) {
-        /* ttbr1 region is "everything not in the ttbr0 region" */
-        ttbr_select = 1;
-    } else {
-        /* in the gap between the two regions, this is a Translation fault */
+    top_bits = sextract64(address, inputsize, addrsize - inputsize);
+    if (-top_bits != param.select || (param.select && !ttbr1_valid)) {
+        /* In the gap between the two regions, this is a Translation fault */
         fault_type = ARMFault_Translation;
         goto do_fault;
     }
 
+    if (param.using64k) {
+        stride = 13;
+    } else if (param.using16k) {
+        stride = 11;
+    } else {
+        stride = 9;
+    }
+
     /* Note that QEMU ignores shareability and cacheability attributes,
      * so we don't need to do anything with the SH, ORGN, IRGN fields
      * in the TTBCR.  Similarly, TTBCR:A1 selects whether we get the
@@ -9875,56 +10510,13 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
      * implement any ASID-like capability so we can ignore it (instead
      * we will always flush the TLB any time the ASID is changed).
      */
-    if (ttbr_select == 0) {
-        ttbr = regime_ttbr(env, mmu_idx, 0);
-        if (el < 2) {
-            epd = extract32(tcr->raw_tcr, 7, 1);
-        }
-        inputsize = addrsize - t0sz;
-
-        tg = extract32(tcr->raw_tcr, 14, 2);
-        if (tg == 1) { /* 64KB pages */
-            stride = 13;
-        }
-        if (tg == 2) { /* 16KB pages */
-            stride = 11;
-        }
-        if (aarch64 && el > 1) {
-            hpd = extract64(tcr->raw_tcr, 24, 1);
-        } else {
-            hpd = extract64(tcr->raw_tcr, 41, 1);
-        }
-        if (!aarch64) {
-            /* For aarch32, hpd0 is not enabled without t2e as well.  */
-            hpd &= extract64(tcr->raw_tcr, 6, 1);
-        }
-    } else {
-        /* We should only be here if TTBR1 is valid */
-        assert(ttbr1_valid);
-
-        ttbr = regime_ttbr(env, mmu_idx, 1);
-        epd = extract32(tcr->raw_tcr, 23, 1);
-        inputsize = addrsize - t1sz;
-
-        tg = extract32(tcr->raw_tcr, 30, 2);
-        if (tg == 3)  { /* 64KB pages */
-            stride = 13;
-        }
-        if (tg == 1) { /* 16KB pages */
-            stride = 11;
-        }
-        hpd = extract64(tcr->raw_tcr, 42, 1);
-        if (!aarch64) {
-            /* For aarch32, hpd1 is not enabled without t2e as well.  */
-            hpd &= extract64(tcr->raw_tcr, 6, 1);
-        }
-    }
+    ttbr = regime_ttbr(env, mmu_idx, param.select);
 
     /* Here we should have set up all the parameters for the translation:
      * inputsize, ttbr, epd, stride, tbi
      */
 
-    if (epd) {
+    if (param.epd) {
         /* Translation table walk disabled => Translation fault on TLB miss
          * Note: This is always 0 on 64-bit EL2 and EL3.
          */
@@ -10037,7 +10629,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
         }
         /* Merge in attributes from table descriptors */
         attrs |= nstable << 3; /* NS */
-        if (hpd) {
+        if (param.hpd) {
             /* HPD disables all the table attributes except NSTable.  */
             break;
         }
@@ -11073,7 +11665,7 @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr,
     int prot;
     bool ret;
     ARMMMUFaultInfo fi = {};
-    ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false));
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
 
     *attrs = (MemTxAttrs) {};
 
@@ -12949,10 +13541,66 @@ int fp_exception_el(CPUARMState *env, int cur_el)
     return 0;
 }
 
+ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env,
+                                                bool secstate, bool priv)
+{
+    ARMMMUIdx mmu_idx = ARM_MMU_IDX_M;
+
+    if (priv) {
+        mmu_idx |= ARM_MMU_IDX_M_PRIV;
+    }
+
+    if (armv7m_nvic_neg_prio_requested(env->nvic, secstate)) {
+        mmu_idx |= ARM_MMU_IDX_M_NEGPRI;
+    }
+
+    if (secstate) {
+        mmu_idx |= ARM_MMU_IDX_M_S;
+    }
+
+    return mmu_idx;
+}
+
+/* Return the MMU index for a v7M CPU in the specified security state */
+ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate)
+{
+    bool priv = arm_current_el(env) != 0;
+
+    return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv);
+}
+
+ARMMMUIdx arm_mmu_idx(CPUARMState *env)
+{
+    int el;
+
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        return arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure);
+    }
+
+    el = arm_current_el(env);
+    if (el < 2 && arm_is_secure_below_el3(env)) {
+        return ARMMMUIdx_S1SE0 + el;
+    } else {
+        return ARMMMUIdx_S12NSE0 + el;
+    }
+}
+
+int cpu_mmu_index(CPUARMState *env, bool ifetch)
+{
+    return arm_to_core_mmu_idx(arm_mmu_idx(env));
+}
+
+#ifndef CONFIG_USER_ONLY
+ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env)
+{
+    return stage_1_mmu_idx(arm_mmu_idx(env));
+}
+#endif
+
 void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
                           target_ulong *cs_base, uint32_t *pflags)
 {
-    ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false));
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
     int current_el = arm_current_el(env);
     int fp_el = fp_exception_el(env, current_el);
     uint32_t flags = 0;
@@ -12962,11 +13610,30 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
 
         *pc = env->pc;
         flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1);
-        /* Get control bits for tagged addresses */
-        flags = FIELD_DP32(flags, TBFLAG_A64, TBI0,
-                           arm_regime_tbi0(env, mmu_idx));
-        flags = FIELD_DP32(flags, TBFLAG_A64, TBI1,
-                           arm_regime_tbi1(env, mmu_idx));
+
+#ifndef CONFIG_USER_ONLY
+        /*
+         * Get control bits for tagged addresses.  Note that the
+         * translator only uses this for instruction addresses.
+         */
+        {
+            ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx);
+            ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1);
+            int tbii, tbid;
+
+            /* FIXME: ARMv8.1-VHE S2 translation regime.  */
+            if (regime_el(env, stage1) < 2) {
+                ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1);
+                tbid = (p1.tbi << 1) | p0.tbi;
+                tbii = tbid & ~((p1.tbid << 1) | p0.tbid);
+            } else {
+                tbid = p0.tbi;
+                tbii = tbid & !p0.tbid;
+            }
+
+            flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii);
+        }
+#endif
 
         if (cpu_isar_feature(aa64_sve, cpu)) {
             int sve_el = sve_exception_el(env, current_el);
@@ -12983,6 +13650,25 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
             flags = FIELD_DP32(flags, TBFLAG_A64, SVEEXC_EL, sve_el);
             flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len);
         }
+
+        if (cpu_isar_feature(aa64_pauth, cpu)) {
+            /*
+             * In order to save space in flags, we record only whether
+             * pauth is "inactive", meaning all insns are implemented as
+             * a nop, or "active" when some action must be performed.
+             * The decision of which action to take is left to a helper.
+             */
+            uint64_t sctlr;
+            if (current_el == 0) {
+                /* FIXME: ARMv8.1-VHE S2 translation regime.  */
+                sctlr = env->cp15.sctlr_el[1];
+            } else {
+                sctlr = env->cp15.sctlr_el[current_el];
+            }
+            if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) {
+                flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1);
+            }
+        }
     } else {
         *pc = env->regs[15];
         flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb);