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.c35
-rw-r--r--target/arm/cpu.h6
-rw-r--r--target/arm/cpu64.c6
-rw-r--r--target/arm/cpu_tcg.c42
-rw-r--r--target/arm/debug_helper.c3
-rw-r--r--target/arm/helper.c871
-rw-r--r--target/arm/internals.h4
-rw-r--r--target/arm/m_helper.c16
-rw-r--r--target/arm/machine.c28
-rw-r--r--target/arm/ptw.c152
-rw-r--r--target/arm/tlb_helper.c4
-rw-r--r--target/arm/translate.c2
-rw-r--r--target/hexagon/cpu.c6
-rw-r--r--target/hexagon/genptr.c56
-rw-r--r--target/hexagon/hex_regs.h2
-rw-r--r--target/hexagon/idef-parser/README.rst4
-rw-r--r--target/hexagon/idef-parser/idef-parser.y2
-rw-r--r--target/hexagon/meson.build1
-rw-r--r--target/ppc/excp_helper.c11
-rw-r--r--target/ppc/helper_regs.c14
-rw-r--r--target/riscv/cpu.c11
-rw-r--r--target/riscv/cpu.h10
-rw-r--r--target/riscv/cpu_bits.h37
-rw-r--r--target/riscv/cpu_helper.c36
-rw-r--r--target/riscv/csr.c393
-rw-r--r--target/riscv/debug.c205
-rw-r--r--target/riscv/debug.h13
-rw-r--r--target/riscv/helper.h2
-rw-r--r--target/riscv/insn32.decode4
-rw-r--r--target/riscv/insn_trans/trans_privileged.c.inc4
-rw-r--r--target/riscv/insn_trans/trans_rvi.c.inc8
-rw-r--r--target/riscv/insn_trans/trans_rvv.c.inc4
-rw-r--r--target/riscv/insn_trans/trans_rvzawrs.c.inc51
-rw-r--r--target/riscv/machine.c36
-rw-r--r--target/riscv/op_helper.c28
-rw-r--r--target/riscv/pmp.c90
-rw-r--r--target/riscv/pmp.h6
-rw-r--r--target/riscv/translate.c54
-rw-r--r--target/sparc/translate.c21
39 files changed, 1864 insertions, 414 deletions
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 2fa022f62b..5f63316dbf 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -26,7 +26,6 @@
 #include "target/arm/idau.h"
 #include "qemu/module.h"
 #include "qapi/error.h"
-#include "qapi/visitor.h"
 #include "cpu.h"
 #ifdef CONFIG_TCG
 #include "hw/core/tcg-cpu-ops.h"
@@ -309,6 +308,10 @@ static void arm_cpu_reset_hold(Object *obj)
         env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1,
                                          CPACR, CP11, 3);
 #endif
+        if (arm_feature(env, ARM_FEATURE_V8)) {
+            env->cp15.rvbar = cpu->rvbar_prop;
+            env->regs[15] = cpu->rvbar_prop;
+        }
     }
 
 #if defined(CONFIG_USER_ONLY)
@@ -487,6 +490,14 @@ static void arm_cpu_reset_hold(Object *obj)
                        sizeof(*env->pmsav7.dracr) * cpu->pmsav7_dregion);
             }
         }
+
+        if (cpu->pmsav8r_hdregion > 0) {
+            memset(env->pmsav8.hprbar, 0,
+                   sizeof(*env->pmsav8.hprbar) * cpu->pmsav8r_hdregion);
+            memset(env->pmsav8.hprlar, 0,
+                   sizeof(*env->pmsav8.hprlar) * cpu->pmsav8r_hdregion);
+        }
+
         env->pmsav7.rnr[M_REG_NS] = 0;
         env->pmsav7.rnr[M_REG_S] = 0;
         env->pmsav8.mair0[M_REG_NS] = 0;
@@ -1345,7 +1356,7 @@ void arm_cpu_post_init(Object *obj)
         qdev_property_add_static(DEVICE(obj), &arm_cpu_reset_hivecs_property);
     }
 
-    if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+    if (arm_feature(&cpu->env, ARM_FEATURE_V8)) {
         object_property_add_uint64_ptr(obj, "rvbar",
                                        &cpu->rvbar_prop,
                                        OBJ_PROP_FLAG_READWRITE);
@@ -1998,11 +2009,10 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
     /* MPU can be configured out of a PMSA CPU either by setting has-mpu
      * to false or by setting pmsav7-dregion to 0.
      */
-    if (!cpu->has_mpu) {
-        cpu->pmsav7_dregion = 0;
-    }
-    if (cpu->pmsav7_dregion == 0) {
+    if (!cpu->has_mpu || cpu->pmsav7_dregion == 0) {
         cpu->has_mpu = false;
+        cpu->pmsav7_dregion = 0;
+        cpu->pmsav8r_hdregion = 0;
     }
 
     if (arm_feature(env, ARM_FEATURE_PMSA) &&
@@ -2029,6 +2039,19 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
                 env->pmsav7.dracr = g_new0(uint32_t, nr);
             }
         }
+
+        if (cpu->pmsav8r_hdregion > 0xff) {
+            error_setg(errp, "PMSAv8 MPU EL2 #regions invalid %" PRIu32,
+                              cpu->pmsav8r_hdregion);
+            return;
+        }
+
+        if (cpu->pmsav8r_hdregion) {
+            env->pmsav8.hprbar = g_new0(uint32_t,
+                                        cpu->pmsav8r_hdregion);
+            env->pmsav8.hprlar = g_new0(uint32_t,
+                                        cpu->pmsav8r_hdregion);
+        }
     }
 
     if (arm_feature(env, ARM_FEATURE_M_SECURITY)) {
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 2b4bd20f9d..bf2bce046d 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -309,6 +309,7 @@ typedef struct CPUArchState {
             };
             uint64_t sctlr_el[4];
         };
+        uint64_t vsctlr; /* Virtualization System control register. */
         uint64_t cpacr_el1; /* Architectural feature access control register */
         uint64_t cptr_el[4];  /* ARMv8 feature trap registers */
         uint32_t c1_xscaleauxcr; /* XScale auxiliary control register.  */
@@ -745,8 +746,11 @@ typedef struct CPUArchState {
          */
         uint32_t *rbar[M_REG_NUM_BANKS];
         uint32_t *rlar[M_REG_NUM_BANKS];
+        uint32_t *hprbar;
+        uint32_t *hprlar;
         uint32_t mair0[M_REG_NUM_BANKS];
         uint32_t mair1[M_REG_NUM_BANKS];
+        uint32_t hprselr;
     } pmsav8;
 
     /* v8M SAU */
@@ -906,6 +910,8 @@ struct ArchCPU {
     bool has_mpu;
     /* PMSAv7 MPU number of supported regions */
     uint32_t pmsav7_dregion;
+    /* PMSAv8 MPU number of supported hyp regions */
+    uint32_t pmsav8r_hdregion;
     /* v8M SAU number of supported regions */
     uint32_t sau_sregion;
 
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 2cf2ca4ce5..0e021960fb 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -21,13 +21,7 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "cpu.h"
-#ifdef CONFIG_TCG
-#include "hw/core/tcg-cpu-ops.h"
-#endif /* CONFIG_TCG */
 #include "qemu/module.h"
-#if !defined(CONFIG_USER_ONLY)
-#include "hw/loader.h"
-#endif
 #include "sysemu/kvm.h"
 #include "sysemu/hvf.h"
 #include "kvm_arm.h"
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index 568cbcfc52..ccde5080eb 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -854,6 +854,47 @@ static void cortex_r5_initfn(Object *obj)
     define_arm_cp_regs(cpu, cortexr5_cp_reginfo);
 }
 
+static void cortex_r52_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    set_feature(&cpu->env, ARM_FEATURE_V8);
+    set_feature(&cpu->env, ARM_FEATURE_EL2);
+    set_feature(&cpu->env, ARM_FEATURE_PMSA);
+    set_feature(&cpu->env, ARM_FEATURE_NEON);
+    set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER);
+    cpu->midr = 0x411fd133; /* r1p3 */
+    cpu->revidr = 0x00000000;
+    cpu->reset_fpsid = 0x41034023;
+    cpu->isar.mvfr0 = 0x10110222;
+    cpu->isar.mvfr1 = 0x12111111;
+    cpu->isar.mvfr2 = 0x00000043;
+    cpu->ctr = 0x8144c004;
+    cpu->reset_sctlr = 0x30c50838;
+    cpu->isar.id_pfr0 = 0x00000131;
+    cpu->isar.id_pfr1 = 0x10111001;
+    cpu->isar.id_dfr0 = 0x03010006;
+    cpu->id_afr0 = 0x00000000;
+    cpu->isar.id_mmfr0 = 0x00211040;
+    cpu->isar.id_mmfr1 = 0x40000000;
+    cpu->isar.id_mmfr2 = 0x01200000;
+    cpu->isar.id_mmfr3 = 0xf0102211;
+    cpu->isar.id_mmfr4 = 0x00000010;
+    cpu->isar.id_isar0 = 0x02101110;
+    cpu->isar.id_isar1 = 0x13112111;
+    cpu->isar.id_isar2 = 0x21232142;
+    cpu->isar.id_isar3 = 0x01112131;
+    cpu->isar.id_isar4 = 0x00010142;
+    cpu->isar.id_isar5 = 0x00010001;
+    cpu->isar.dbgdidr = 0x77168000;
+    cpu->clidr = (1 << 27) | (1 << 24) | 0x3;
+    cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */
+    cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */
+
+    cpu->pmsav7_dregion = 16;
+    cpu->pmsav8r_hdregion = 16;
+}
+
 static void cortex_r5f_initfn(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
@@ -1163,6 +1204,7 @@ static const ARMCPUInfo arm_tcg_cpus[] = {
                              .class_init = arm_v7m_class_init },
     { .name = "cortex-r5",   .initfn = cortex_r5_initfn },
     { .name = "cortex-r5f",  .initfn = cortex_r5f_initfn },
+    { .name = "cortex-r52",  .initfn = cortex_r52_initfn },
     { .name = "ti925t",      .initfn = ti925t_initfn },
     { .name = "sa1100",      .initfn = sa1100_initfn },
     { .name = "sa1110",      .initfn = sa1110_initfn },
diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index c21739242c..2f6ddc0da5 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -437,6 +437,9 @@ static uint32_t arm_debug_exception_fsr(CPUARMState *env)
 
     if (target_el == 2 || arm_el_is_aa64(env, target_el)) {
         using_lpae = true;
+    } else if (arm_feature(env, ARM_FEATURE_PMSA) &&
+               arm_feature(env, ARM_FEATURE_V8)) {
+        using_lpae = true;
     } else {
         if (arm_feature(env, ARM_FEATURE_LPAE) &&
             (env->cp15.tcr_el[target_el] & TTBCR_EAE)) {
diff --git a/target/arm/helper.c b/target/arm/helper.c
index bac2ea62c4..cee3804354 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -7,13 +7,11 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu/units.h"
 #include "qemu/log.h"
 #include "trace.h"
 #include "cpu.h"
 #include "internals.h"
 #include "exec/helper-proto.h"
-#include "qemu/host-utils.h"
 #include "qemu/main-loop.h"
 #include "qemu/timer.h"
 #include "qemu/bitops.h"
@@ -22,17 +20,12 @@
 #include "exec/exec-all.h"
 #include <zlib.h> /* For crc32 */
 #include "hw/irq.h"
-#include "semihosting/semihost.h"
-#include "sysemu/cpus.h"
 #include "sysemu/cpu-timers.h"
 #include "sysemu/kvm.h"
-#include "qemu/range.h"
 #include "qapi/qapi-commands-machine-target.h"
 #include "qapi/error.h"
 #include "qemu/guest-random.h"
 #ifdef CONFIG_TCG
-#include "arm_ldst.h"
-#include "exec/cpu_ldst.h"
 #include "semihosting/common-semi.h"
 #endif
 #include "cpregs.h"
@@ -83,7 +76,8 @@ uint64_t read_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri)
 static void write_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri,
                              uint64_t v)
 {
-    /* Raw write of a coprocessor register (as needed for migration, etc).
+    /*
+     * Raw write of a coprocessor register (as needed for migration, etc).
      * Note that constant registers are treated as write-ignored; the
      * caller should check for success by whether a readback gives the
      * value written.
@@ -101,7 +95,8 @@ static void write_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri,
 
 static bool raw_accessors_invalid(const ARMCPRegInfo *ri)
 {
-   /* Return true if the regdef would cause an assertion if you called
+   /*
+    * Return true if the regdef would cause an assertion if you called
     * read_raw_cp_reg() or write_raw_cp_reg() on it (ie if it is a
     * program bug for it not to have the NO_RAW flag).
     * NB that returning false here doesn't necessarily mean that calling
@@ -184,7 +179,8 @@ bool write_list_to_cpustate(ARMCPU *cpu)
         if (ri->type & ARM_CP_NO_RAW) {
             continue;
         }
-        /* Write value and confirm it reads back as written
+        /*
+         * Write value and confirm it reads back as written
          * (to catch read-only registers and partially read-only
          * registers where the incoming migration value doesn't match)
          */
@@ -202,7 +198,7 @@ static void add_cpreg_to_list(gpointer key, gpointer opaque)
     uint32_t regidx = (uintptr_t)key;
     const ARMCPRegInfo *ri = get_arm_cp_reginfo(cpu->cp_regs, regidx);
 
-    if (!(ri->type & (ARM_CP_NO_RAW|ARM_CP_ALIAS))) {
+    if (!(ri->type & (ARM_CP_NO_RAW | ARM_CP_ALIAS))) {
         cpu->cpreg_indexes[cpu->cpreg_array_len] = cpreg_to_kvm_id(regidx);
         /* The value array need not be initialized at this point */
         cpu->cpreg_array_len++;
@@ -216,7 +212,7 @@ static void count_cpreg(gpointer key, gpointer opaque)
 
     ri = g_hash_table_lookup(cpu->cp_regs, key);
 
-    if (!(ri->type & (ARM_CP_NO_RAW|ARM_CP_ALIAS))) {
+    if (!(ri->type & (ARM_CP_NO_RAW | ARM_CP_ALIAS))) {
         cpu->cpreg_array_len++;
     }
 }
@@ -237,7 +233,8 @@ static gint cpreg_key_compare(gconstpointer a, gconstpointer b)
 
 void init_cpreg_list(ARMCPU *cpu)
 {
-    /* Initialise the cpreg_tuples[] array based on the cp_regs hash.
+    /*
+     * Initialise the cpreg_tuples[] array based on the cp_regs hash.
      * Note that we require cpreg_tuples[] to be sorted by key ID.
      */
     GList *keys;
@@ -279,7 +276,8 @@ static CPAccessResult access_el3_aa32ns(CPUARMState *env,
     return CP_ACCESS_OK;
 }
 
-/* Some secure-only AArch32 registers trap to EL3 if used from
+/*
+ * Some secure-only AArch32 registers trap to EL3 if used from
  * Secure EL1 (but are just ordinary UNDEF in other non-EL3 contexts).
  * Note that an access from Secure EL1 can only happen if EL3 is AArch64.
  * We assume that the .access field is set to PL1_RW.
@@ -301,7 +299,8 @@ static CPAccessResult access_trap_aa32s_el1(CPUARMState *env,
     return CP_ACCESS_TRAP_UNCATEGORIZED;
 }
 
-/* Check for traps to performance monitor registers, which are controlled
+/*
+ * Check for traps to performance monitor registers, which are controlled
  * by MDCR_EL2.TPM for EL2 and MDCR_EL3.TPM for EL3.
  */
 static CPAccessResult access_tpm(CPUARMState *env, const ARMCPRegInfo *ri,
@@ -399,7 +398,8 @@ static void fcse_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
     ARMCPU *cpu = env_archcpu(env);
 
     if (raw_read(env, ri) != value) {
-        /* Unlike real hardware the qemu TLB uses virtual addresses,
+        /*
+         * Unlike real hardware the qemu TLB uses virtual addresses,
          * not modified virtual addresses, so this causes a TLB flush.
          */
         tlb_flush(CPU(cpu));
@@ -414,7 +414,8 @@ static void contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     if (raw_read(env, ri) != value && !arm_feature(env, ARM_FEATURE_PMSA)
         && !extended_addresses_enabled(env)) {
-        /* For VMSA (when not using the LPAE long descriptor page table
+        /*
+         * For VMSA (when not using the LPAE long descriptor page table
          * format) this register includes the ASID, so do a TLB flush.
          * For PMSA it is purely a process ID and no action is needed.
          */
@@ -606,7 +607,8 @@ static void tlbiipas2is_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
 }
 
 static const ARMCPRegInfo cp_reginfo[] = {
-    /* Define the secure and non-secure FCSE identifier CP registers
+    /*
+     * Define the secure and non-secure FCSE identifier CP registers
      * separately because there is no secure bank in V8 (no _EL3).  This allows
      * the secure register to be properly reset and migrated. There is also no
      * v8 EL1 version of the register so the non-secure instance stands alone.
@@ -621,7 +623,8 @@ static const ARMCPRegInfo cp_reginfo[] = {
       .access = PL1_RW, .secure = ARM_CP_SECSTATE_S,
       .fieldoffset = offsetof(CPUARMState, cp15.fcseidr_s),
       .resetvalue = 0, .writefn = fcse_write, .raw_writefn = raw_write, },
-    /* Define the secure and non-secure context identifier CP registers
+    /*
+     * Define the secure and non-secure context identifier CP registers
      * separately because there is no secure bank in V8 (no _EL3).  This allows
      * the secure register to be properly reset and migrated.  In the
      * non-secure case, the 32-bit register will have reset and migration
@@ -642,7 +645,8 @@ static const ARMCPRegInfo cp_reginfo[] = {
 };
 
 static const ARMCPRegInfo not_v8_cp_reginfo[] = {
-    /* NB: Some of these registers exist in v8 but with more precise
+    /*
+     * NB: Some of these registers exist in v8 but with more precise
      * definitions that don't use CP_ANY wildcards (mostly in v8_cp_reginfo[]).
      */
     /* MMU Domain access control / MPU write buffer control */
@@ -652,7 +656,8 @@ static const ARMCPRegInfo not_v8_cp_reginfo[] = {
       .writefn = dacr_write, .raw_writefn = raw_write,
       .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.dacr_s),
                              offsetoflow32(CPUARMState, cp15.dacr_ns) } },
-    /* ARMv7 allocates a range of implementation defined TLB LOCKDOWN regs.
+    /*
+     * ARMv7 allocates a range of implementation defined TLB LOCKDOWN regs.
      * For v6 and v5, these mappings are overly broad.
      */
     { .name = "TLB_LOCKDOWN", .cp = 15, .crn = 10, .crm = 0,
@@ -670,7 +675,8 @@ static const ARMCPRegInfo not_v8_cp_reginfo[] = {
 };
 
 static const ARMCPRegInfo not_v6_cp_reginfo[] = {
-    /* Not all pre-v6 cores implemented this WFI, so this is slightly
+    /*
+     * Not all pre-v6 cores implemented this WFI, so this is slightly
      * over-broad.
      */
     { .name = "WFI_v5", .cp = 15, .crn = 7, .crm = 8, .opc1 = 0, .opc2 = 2,
@@ -678,12 +684,14 @@ static const ARMCPRegInfo not_v6_cp_reginfo[] = {
 };
 
 static const ARMCPRegInfo not_v7_cp_reginfo[] = {
-    /* Standard v6 WFI (also used in some pre-v6 cores); not in v7 (which
+    /*
+     * Standard v6 WFI (also used in some pre-v6 cores); not in v7 (which
      * is UNPREDICTABLE; we choose to NOP as most implementations do).
      */
     { .name = "WFI_v6", .cp = 15, .crn = 7, .crm = 0, .opc1 = 0, .opc2 = 4,
       .access = PL1_W, .type = ARM_CP_WFI },
-    /* L1 cache lockdown. Not architectural in v6 and earlier but in practice
+    /*
+     * L1 cache lockdown. Not architectural in v6 and earlier but in practice
      * implemented in 926, 946, 1026, 1136, 1176 and 11MPCore. StrongARM and
      * OMAPCP will override this space.
      */
@@ -697,14 +705,16 @@ static const ARMCPRegInfo not_v7_cp_reginfo[] = {
     { .name = "DUMMY", .cp = 15, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = CP_ANY,
       .access = PL1_R, .type = ARM_CP_CONST | ARM_CP_NO_RAW,
       .resetvalue = 0 },
-    /* We don't implement pre-v7 debug but most CPUs had at least a DBGDIDR;
+    /*
+     * We don't implement pre-v7 debug but most CPUs had at least a DBGDIDR;
      * implementing it as RAZ means the "debug architecture version" bits
      * will read as a reserved value, which should cause Linux to not try
      * to use the debug hardware.
      */
     { .name = "DBGDIDR", .cp = 14, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 0,
       .access = PL0_R, .type = ARM_CP_CONST, .resetvalue = 0 },
-    /* MMU TLB control. Note that the wildcarding means we cover not just
+    /*
+     * MMU TLB control. Note that the wildcarding means we cover not just
      * the unified TLB ops but also the dside/iside/inner-shareable variants.
      */
     { .name = "TLBIALL", .cp = 15, .crn = 8, .crm = CP_ANY,
@@ -732,7 +742,8 @@ static void cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     /* In ARMv8 most bits of CPACR_EL1 are RES0. */
     if (!arm_feature(env, ARM_FEATURE_V8)) {
-        /* ARMv7 defines bits for unimplemented coprocessors as RAZ/WI.
+        /*
+         * ARMv7 defines bits for unimplemented coprocessors as RAZ/WI.
          * ASEDIS [31] and D32DIS [30] are both UNK/SBZP without VFP.
          * TRCDIS [28] is RAZ/WI since we do not implement a trace macrocell.
          */
@@ -748,7 +759,8 @@ static void cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                 value |= R_CPACR_ASEDIS_MASK;
             }
 
-            /* VFPv3 and upwards with NEON implement 32 double precision
+            /*
+             * VFPv3 and upwards with NEON implement 32 double precision
              * registers (D0-D31).
              */
             if (!cpu_isar_feature(aa32_simd_r32, env_archcpu(env))) {
@@ -790,7 +802,8 @@ static uint64_t cpacr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 
 static void cpacr_reset(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-    /* Call cpacr_write() so that we reset with the correct RAO bits set
+    /*
+     * Call cpacr_write() so that we reset with the correct RAO bits set
      * for our CPU features.
      */
     cpacr_write(env, ri, 0);
@@ -831,7 +844,8 @@ static const ARMCPRegInfo v6_cp_reginfo[] = {
     { .name = "MVA_prefetch",
       .cp = 15, .crn = 7, .crm = 13, .opc1 = 0, .opc2 = 1,
       .access = PL1_W, .type = ARM_CP_NOP },
-    /* We need to break the TB after ISB to execute self-modifying code
+    /*
+     * We need to break the TB after ISB to execute self-modifying code
      * correctly and also to take any pending interrupts immediately.
      * So use arm_cp_write_ignore() function instead of ARM_CP_NOP flag.
      */
@@ -846,7 +860,8 @@ static const ARMCPRegInfo v6_cp_reginfo[] = {
       .bank_fieldoffsets = { offsetof(CPUARMState, cp15.ifar_s),
                              offsetof(CPUARMState, cp15.ifar_ns) },
       .resetvalue = 0, },
-    /* Watchpoint Fault Address Register : should actually only be present
+    /*
+     * Watchpoint Fault Address Register : should actually only be present
      * for 1136, 1176, 11MPCore.
      */
     { .name = "WFAR", .cp = 15, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 1,
@@ -1051,7 +1066,8 @@ static bool event_supported(uint16_t number)
 static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                    bool isread)
 {
-    /* Performance monitor registers user accessibility is controlled
+    /*
+     * Performance monitor registers user accessibility is controlled
      * by PMUSERENR. MDCR_EL2.TPM and MDCR_EL3.TPM allow configurable
      * trapping to EL2 or EL3 for other accesses.
      */
@@ -1139,7 +1155,8 @@ static CPAccessResult pmreg_access_ccntr(CPUARMState *env,
     (MDCR_HPME | MDCR_HPMD | MDCR_HPMN | MDCR_HCCD | MDCR_HLP)
 #define MDCR_EL3_PMU_ENABLE_BITS (MDCR_SPME | MDCR_SCCD)
 
-/* Returns true if the counter (pass 31 for PMCCNTR) should count events using
+/*
+ * 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)
@@ -1503,7 +1520,8 @@ static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                          uint64_t value)
 {
-    /* The value of PMSELR.SEL affects the behavior of PMXEVTYPER and
+    /*
+     * The value of PMSELR.SEL affects the behavior of PMXEVTYPER and
      * PMXEVCNTR. We allow [0..31] to be written to PMSELR here; in the
      * meanwhile, we check PMSELR.SEL when PMXEVTYPER and PMXEVCNTR are
      * accessed.
@@ -1614,7 +1632,8 @@ static void pmevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri,
         env->cp15.c14_pmevtyper[counter] = value & PMXEVTYPER_MASK;
         pmevcntr_op_finish(env, counter);
     }
-    /* Attempts to access PMXEVTYPER are CONSTRAINED UNPREDICTABLE when
+    /*
+     * 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.
      */
@@ -1715,8 +1734,10 @@ static uint64_t pmevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri,
         }
         return ret;
     } else {
-      /* We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR
-       * are CONSTRAINED UNPREDICTABLE. */
+      /*
+       * We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR
+       * are CONSTRAINED UNPREDICTABLE.
+       */
         return 0;
     }
 }
@@ -1791,7 +1812,8 @@ static void pmintenclr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void vbar_write(CPUARMState *env, const ARMCPRegInfo *ri,
                        uint64_t value)
 {
-    /* Note that even though the AArch64 view of this register has bits
+    /*
+     * Note that even though the AArch64 view of this register has bits
      * [10:0] all RES0 we can only mask the bottom 5, to comply with the
      * architectural requirements for bits which are RES0 only in some
      * contexts. (ARMv8 would permit us to do no masking at all, but ARMv7
@@ -1854,7 +1876,8 @@ static void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
     if (!arm_feature(env, ARM_FEATURE_EL2)) {
         valid_mask &= ~SCR_HCE;
 
-        /* On ARMv7, SMD (or SCD as it is called in v7) is only
+        /*
+         * On ARMv7, SMD (or SCD as it is called in v7) is only
          * supported if EL2 exists. The bit is UNK/SBZP when
          * EL2 is unavailable. In QEMU ARMv7, we force it to always zero
          * when EL2 is unavailable.
@@ -1911,7 +1934,8 @@ static uint64_t ccsidr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     ARMCPU *cpu = env_archcpu(env);
 
-    /* Acquire the CSSELR index from the bank corresponding to the CCSIDR
+    /*
+     * Acquire the CSSELR index from the bank corresponding to the CCSIDR
      * bank
      */
     uint32_t index = A32_BANKED_REG_GET(env, csselr,
@@ -1986,7 +2010,8 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
     /* the old v6 WFI, UNPREDICTABLE in v7 but we choose to NOP */
     { .name = "NOP", .cp = 15, .crn = 7, .crm = 0, .opc1 = 0, .opc2 = 4,
       .access = PL1_W, .type = ARM_CP_NOP },
-    /* Performance monitors are implementation defined in v7,
+    /*
+     * Performance monitors are implementation defined in v7,
      * but with an ARM recommended set of registers, which we
      * follow.
      *
@@ -2140,7 +2165,8 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .writefn = csselr_write, .resetvalue = 0,
       .bank_fieldoffsets = { offsetof(CPUARMState, cp15.csselr_s),
                              offsetof(CPUARMState, cp15.csselr_ns) } },
-    /* Auxiliary ID register: this actually has an IMPDEF value but for now
+    /*
+     * Auxiliary ID register: this actually has an IMPDEF value but for now
      * just RAZ for all cores:
      */
     { .name = "AIDR", .state = ARM_CP_STATE_BOTH,
@@ -2148,7 +2174,8 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .access = PL1_R, .type = ARM_CP_CONST,
       .accessfn = access_aa64_tid1,
       .resetvalue = 0 },
-    /* Auxiliary fault status registers: these also are IMPDEF, and we
+    /*
+     * Auxiliary fault status registers: these also are IMPDEF, and we
      * choose to RAZ/WI for all cores.
      */
     { .name = "AFSR0_EL1", .state = ARM_CP_STATE_BOTH,
@@ -2159,7 +2186,8 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 0, .crn = 5, .crm = 1, .opc2 = 1,
       .access = PL1_RW, .accessfn = access_tvm_trvm,
       .type = ARM_CP_CONST, .resetvalue = 0 },
-    /* MAIR can just read-as-written because we don't implement caches
+    /*
+     * MAIR can just read-as-written because we don't implement caches
      * and so don't need to care about memory attributes.
      */
     { .name = "MAIR_EL1", .state = ARM_CP_STATE_AA64,
@@ -2171,10 +2199,12 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 6, .crn = 10, .crm = 2, .opc2 = 0,
       .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.mair_el[3]),
       .resetvalue = 0 },
-    /* For non-long-descriptor page tables these are PRRR and NMRR;
+    /*
+     * For non-long-descriptor page tables these are PRRR and NMRR;
      * regardless they still act as reads-as-written for QEMU.
      */
-     /* MAIR0/1 are defined separately from their 64-bit counterpart which
+     /*
+      * MAIR0/1 are defined separately from their 64-bit counterpart which
       * allows them to assign the correct fieldoffset based on the endianness
       * handled in the field definitions.
       */
@@ -2313,11 +2343,11 @@ static const ARMCPRegInfo v6k_cp_reginfo[] = {
       .resetfn = arm_cp_reset_ignore },
     { .name = "TPIDRRO_EL0", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 3, .opc2 = 3, .crn = 13, .crm = 0,
-      .access = PL0_R|PL1_W,
+      .access = PL0_R | PL1_W,
       .fieldoffset = offsetof(CPUARMState, cp15.tpidrro_el[0]),
       .resetvalue = 0},
     { .name = "TPIDRURO", .cp = 15, .crn = 13, .crm = 0, .opc1 = 0, .opc2 = 3,
-      .access = PL0_R|PL1_W,
+      .access = PL0_R | PL1_W,
       .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.tpidruro_s),
                              offsetoflow32(CPUARMState, cp15.tpidruro_ns) },
       .resetfn = arm_cp_reset_ignore },
@@ -2337,7 +2367,8 @@ static const ARMCPRegInfo v6k_cp_reginfo[] = {
 static CPAccessResult gt_cntfrq_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                        bool isread)
 {
-    /* CNTFRQ: not visible from PL0 if both PL0PCTEN and PL0VCTEN are zero.
+    /*
+     * CNTFRQ: not visible from PL0 if both PL0PCTEN and PL0VCTEN are zero.
      * Writable only at the highest implemented exception level.
      */
     int el = arm_current_el(env);
@@ -2496,7 +2527,8 @@ static CPAccessResult gt_stimer_access(CPUARMState *env,
                                        const ARMCPRegInfo *ri,
                                        bool isread)
 {
-    /* The AArch64 register view of the secure physical timer is
+    /*
+     * The AArch64 register view of the secure physical timer is
      * always accessible from EL3, and configurably accessible from
      * Secure EL1.
      */
@@ -2531,7 +2563,8 @@ static void gt_recalc_timer(ARMCPU *cpu, int timeridx)
     ARMGenericTimer *gt = &cpu->env.cp15.c14_timer[timeridx];
 
     if (gt->ctl & 1) {
-        /* Timer enabled: calculate and set current ISTATUS, irq, and
+        /*
+         * Timer enabled: calculate and set current ISTATUS, irq, and
          * reset timer to when ISTATUS next has to change
          */
         uint64_t offset = timeridx == GTIMER_VIRT ?
@@ -2554,7 +2587,8 @@ static void gt_recalc_timer(ARMCPU *cpu, int timeridx)
             /* Next transition is when we hit cval */
             nexttick = gt->cval + offset;
         }
-        /* Note that the desired next expiry time might be beyond the
+        /*
+         * Note that the desired next expiry time might be beyond the
          * signed-64-bit range of a QEMUTimer -- in this case we just
          * set the timer for as far in the future as possible. When the
          * timer expires we will reset the timer for any remaining period.
@@ -2671,7 +2705,8 @@ static void gt_ctl_write(CPUARMState *env, const ARMCPRegInfo *ri,
         /* Enable toggled */
         gt_recalc_timer(cpu, timeridx);
     } else if ((oldval ^ value) & 2) {
-        /* IMASK toggled: don't need to recalculate,
+        /*
+         * IMASK toggled: don't need to recalculate,
          * just set the interrupt line based on ISTATUS
          */
         int irqstate = (oldval & 4) && !(value & 2);
@@ -2982,7 +3017,8 @@ static void arm_gt_cntfrq_reset(CPUARMState *env, const ARMCPRegInfo *opaque)
 }
 
 static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
-    /* Note that CNTFRQ is purely reads-as-written for the benefit
+    /*
+     * Note that CNTFRQ is purely reads-as-written for the benefit
      * of software; writing it doesn't actually change the timer frequency.
      * Our reset value matches the fixed frequency we implement the timer at.
      */
@@ -3145,7 +3181,8 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .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
+    /*
+     * Secure timer -- this is actually restricted to only EL3
      * and configurably Secure-EL1 via the accessfn.
      */
     { .name = "CNTPS_TVAL_EL1", .state = ARM_CP_STATE_AA64,
@@ -3184,7 +3221,8 @@ static CPAccessResult e2h_access(CPUARMState *env, const ARMCPRegInfo *ri,
 
 #else
 
-/* In user-mode most of the generic timer registers are inaccessible
+/*
+ * In user-mode most of the generic timer registers are inaccessible
  * however modern kernels (4.12+) allow access to cntvct_el0
  */
 
@@ -3192,7 +3230,8 @@ static uint64_t gt_virt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     ARMCPU *cpu = env_archcpu(env);
 
-    /* Currently we have no support for QEMUTimer in linux-user so we
+    /*
+     * Currently we have no support for QEMUTimer in linux-user so we
      * can't call gt_get_countervalue(env), instead we directly
      * call the lower level functions.
      */
@@ -3233,7 +3272,8 @@ static CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                  bool isread)
 {
     if (ri->opc2 & 4) {
-        /* The ATS12NSO* operations must trap to EL3 or EL2 if executed in
+        /*
+         * The ATS12NSO* operations must trap to EL3 or EL2 if executed in
          * Secure EL1 (which can only happen if EL3 is AArch64).
          * They are simply UNDEF if executed from NS EL1.
          * They function normally from EL2 or EL3.
@@ -3394,7 +3434,8 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
             }
         }
     } else {
-        /* fsr is a DFSR/IFSR value for the short descriptor
+        /*
+         * fsr is a DFSR/IFSR value for the short descriptor
          * translation table format (with WnR always clear).
          * Convert it to a 32-bit PAR.
          */
@@ -3682,8 +3723,225 @@ static void pmsav7_rgnr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     raw_write(env, ri, value);
 }
 
+static void prbar_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    tlb_flush(CPU(cpu)); /* Mappings may have changed - purge! */
+    env->pmsav8.rbar[M_REG_NS][env->pmsav7.rnr[M_REG_NS]] = value;
+}
+
+static uint64_t prbar_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pmsav8.rbar[M_REG_NS][env->pmsav7.rnr[M_REG_NS]];
+}
+
+static void prlar_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    tlb_flush(CPU(cpu)); /* Mappings may have changed - purge! */
+    env->pmsav8.rlar[M_REG_NS][env->pmsav7.rnr[M_REG_NS]] = value;
+}
+
+static uint64_t prlar_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pmsav8.rlar[M_REG_NS][env->pmsav7.rnr[M_REG_NS]];
+}
+
+static void prselr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                           uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    /*
+     * Ignore writes that would select not implemented region.
+     * This is architecturally UNPREDICTABLE.
+     */
+    if (value >= cpu->pmsav7_dregion) {
+        return;
+    }
+
+    env->pmsav7.rnr[M_REG_NS] = value;
+}
+
+static void hprbar_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    tlb_flush(CPU(cpu)); /* Mappings may have changed - purge! */
+    env->pmsav8.hprbar[env->pmsav8.hprselr] = value;
+}
+
+static uint64_t hprbar_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pmsav8.hprbar[env->pmsav8.hprselr];
+}
+
+static void hprlar_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    tlb_flush(CPU(cpu)); /* Mappings may have changed - purge! */
+    env->pmsav8.hprlar[env->pmsav8.hprselr] = value;
+}
+
+static uint64_t hprlar_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    return env->pmsav8.hprlar[env->pmsav8.hprselr];
+}
+
+static void hprenr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    uint32_t n;
+    uint32_t bit;
+    ARMCPU *cpu = env_archcpu(env);
+
+    /* Ignore writes to unimplemented regions */
+    int rmax = MIN(cpu->pmsav8r_hdregion, 32);
+    value &= MAKE_64BIT_MASK(0, rmax);
+
+    tlb_flush(CPU(cpu)); /* Mappings may have changed - purge! */
+
+    /* Register alias is only valid for first 32 indexes */
+    for (n = 0; n < rmax; ++n) {
+        bit = extract32(value, n, 1);
+        env->pmsav8.hprlar[n] = deposit32(
+                    env->pmsav8.hprlar[n], 0, 1, bit);
+    }
+}
+
+static uint64_t hprenr_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    uint32_t n;
+    uint32_t result = 0x0;
+    ARMCPU *cpu = env_archcpu(env);
+
+    /* Register alias is only valid for first 32 indexes */
+    for (n = 0; n < MIN(cpu->pmsav8r_hdregion, 32); ++n) {
+        if (env->pmsav8.hprlar[n] & 0x1) {
+            result |= (0x1 << n);
+        }
+    }
+    return result;
+}
+
+static void hprselr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                           uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    /*
+     * Ignore writes that would select not implemented region.
+     * This is architecturally UNPREDICTABLE.
+     */
+    if (value >= cpu->pmsav8r_hdregion) {
+        return;
+    }
+
+    env->pmsav8.hprselr = value;
+}
+
+static void pmsav8r_regn_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                          uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    uint8_t index = (extract32(ri->opc0, 0, 1) << 4) |
+                    (extract32(ri->crm, 0, 3) << 1) | extract32(ri->opc2, 2, 1);
+
+    tlb_flush(CPU(cpu)); /* Mappings may have changed - purge! */
+
+    if (ri->opc1 & 4) {
+        if (index >= cpu->pmsav8r_hdregion) {
+            return;
+        }
+        if (ri->opc2 & 0x1) {
+            env->pmsav8.hprlar[index] = value;
+        } else {
+            env->pmsav8.hprbar[index] = value;
+        }
+    } else {
+        if (index >= cpu->pmsav7_dregion) {
+            return;
+        }
+        if (ri->opc2 & 0x1) {
+            env->pmsav8.rlar[M_REG_NS][index] = value;
+        } else {
+            env->pmsav8.rbar[M_REG_NS][index] = value;
+        }
+    }
+}
+
+static uint64_t pmsav8r_regn_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    uint8_t index = (extract32(ri->opc0, 0, 1) << 4) |
+                    (extract32(ri->crm, 0, 3) << 1) | extract32(ri->opc2, 2, 1);
+
+    if (ri->opc1 & 4) {
+        if (index >= cpu->pmsav8r_hdregion) {
+            return 0x0;
+        }
+        if (ri->opc2 & 0x1) {
+            return env->pmsav8.hprlar[index];
+        } else {
+            return env->pmsav8.hprbar[index];
+        }
+    } else {
+        if (index >= cpu->pmsav7_dregion) {
+            return 0x0;
+        }
+        if (ri->opc2 & 0x1) {
+            return env->pmsav8.rlar[M_REG_NS][index];
+        } else {
+            return env->pmsav8.rbar[M_REG_NS][index];
+        }
+    }
+}
+
+static const ARMCPRegInfo pmsav8r_cp_reginfo[] = {
+    { .name = "PRBAR",
+      .cp = 15, .opc1 = 0, .crn = 6, .crm = 3, .opc2 = 0,
+      .access = PL1_RW, .type = ARM_CP_NO_RAW,
+      .accessfn = access_tvm_trvm,
+      .readfn = prbar_read, .writefn = prbar_write },
+    { .name = "PRLAR",
+      .cp = 15, .opc1 = 0, .crn = 6, .crm = 3, .opc2 = 1,
+      .access = PL1_RW, .type = ARM_CP_NO_RAW,
+      .accessfn = access_tvm_trvm,
+      .readfn = prlar_read, .writefn = prlar_write },
+    { .name = "PRSELR", .resetvalue = 0,
+      .cp = 15, .opc1 = 0, .crn = 6, .crm = 2, .opc2 = 1,
+      .access = PL1_RW, .accessfn = access_tvm_trvm,
+      .writefn = prselr_write,
+      .fieldoffset = offsetof(CPUARMState, pmsav7.rnr[M_REG_NS]) },
+    { .name = "HPRBAR", .resetvalue = 0,
+      .cp = 15, .opc1 = 4, .crn = 6, .crm = 3, .opc2 = 0,
+      .access = PL2_RW, .type = ARM_CP_NO_RAW,
+      .readfn = hprbar_read, .writefn = hprbar_write },
+    { .name = "HPRLAR",
+      .cp = 15, .opc1 = 4, .crn = 6, .crm = 3, .opc2 = 1,
+      .access = PL2_RW, .type = ARM_CP_NO_RAW,
+      .readfn = hprlar_read, .writefn = hprlar_write },
+    { .name = "HPRSELR", .resetvalue = 0,
+      .cp = 15, .opc1 = 4, .crn = 6, .crm = 2, .opc2 = 1,
+      .access = PL2_RW,
+      .writefn = hprselr_write,
+      .fieldoffset = offsetof(CPUARMState, pmsav8.hprselr) },
+    { .name = "HPRENR",
+      .cp = 15, .opc1 = 4, .crn = 6, .crm = 1, .opc2 = 1,
+      .access = PL2_RW, .type = ARM_CP_NO_RAW,
+      .readfn = hprenr_read, .writefn = hprenr_write },
+};
+
 static const ARMCPRegInfo pmsav7_cp_reginfo[] = {
-    /* Reset for all these registers is handled in arm_cpu_reset(),
+    /*
+     * Reset for all these registers is handled in arm_cpu_reset(),
      * because the PMSAv7 is also used by M-profile CPUs, which do
      * not register cpregs but still need the state to be reset.
      */
@@ -3784,7 +4042,8 @@ static void vmsa_ttbcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     }
 
     if (arm_feature(env, ARM_FEATURE_LPAE)) {
-        /* With LPAE the TTBCR could result in a change of ASID
+        /*
+         * With LPAE the TTBCR could result in a change of ASID
          * via the TTBCR.A1 bit, so do a TLB flush.
          */
         tlb_flush(CPU(cpu));
@@ -3901,7 +4160,8 @@ static const ARMCPRegInfo vmsa_cp_reginfo[] = {
                              offsetoflow32(CPUARMState, cp15.tcr_el[1])} },
 };
 
-/* Note that unlike TTBCR, writing to TTBCR2 does not require flushing
+/*
+ * Note that unlike TTBCR, writing to TTBCR2 does not require flushing
  * qemu tlbs nor adjusting cached masks.
  */
 static const ARMCPRegInfo ttbcr2_reginfo = {
@@ -3939,7 +4199,8 @@ static void omap_wfi_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void omap_cachemaint_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                   uint64_t value)
 {
-    /* On OMAP there are registers indicating the max/min index of dcache lines
+    /*
+     * On OMAP there are registers indicating the max/min index of dcache lines
      * containing a dirty line; cache flush operations have to reset these.
      */
     env->cp15.c15_i_max = 0x000;
@@ -3971,7 +4232,8 @@ static const ARMCPRegInfo omap_cp_reginfo[] = {
       .crm = 8, .opc1 = 0, .opc2 = 0, .access = PL1_RW,
       .type = ARM_CP_NO_RAW,
       .readfn = arm_cp_read_zero, .writefn = omap_wfi_write, },
-    /* TODO: Peripheral port remap register:
+    /*
+     * TODO: Peripheral port remap register:
      * On OMAP2 mcr p15, 0, rn, c15, c2, 4 sets up the interrupt controller
      * base address at $rn & ~0xfff and map size of 0x200 << ($rn & 0xfff),
      * when MMU is off.
@@ -4000,7 +4262,8 @@ static const ARMCPRegInfo xscale_cp_reginfo[] = {
       .cp = 15, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 1, .access = PL1_RW,
       .fieldoffset = offsetof(CPUARMState, cp15.c1_xscaleauxcr),
       .resetvalue = 0, },
-    /* XScale specific cache-lockdown: since we have no cache we NOP these
+    /*
+     * XScale specific cache-lockdown: since we have no cache we NOP these
      * and hope the guest does not really rely on cache behaviour.
      */
     { .name = "XSCALE_LOCK_ICACHE_LINE",
@@ -4018,7 +4281,8 @@ static const ARMCPRegInfo xscale_cp_reginfo[] = {
 };
 
 static const ARMCPRegInfo dummy_c15_cp_reginfo[] = {
-    /* RAZ/WI the whole crn=15 space, when we don't have a more specific
+    /*
+     * RAZ/WI the whole crn=15 space, when we don't have a more specific
      * implementation of this implementation-defined space.
      * Ideally this should eventually disappear in favour of actually
      * implementing the correct behaviour for all cores.
@@ -4044,21 +4308,22 @@ static const ARMCPRegInfo cache_block_ops_cp_reginfo[] = {
       .resetvalue = 0 },
     /* The cache ops themselves: these all NOP for QEMU */
     { .name = "IICR", .cp = 15, .crm = 5, .opc1 = 0,
-      .access = PL1_W, .type = ARM_CP_NOP|ARM_CP_64BIT },
+      .access = PL1_W, .type = ARM_CP_NOP | ARM_CP_64BIT },
     { .name = "IDCR", .cp = 15, .crm = 6, .opc1 = 0,
-      .access = PL1_W, .type = ARM_CP_NOP|ARM_CP_64BIT },
+      .access = PL1_W, .type = ARM_CP_NOP | ARM_CP_64BIT },
     { .name = "CDCR", .cp = 15, .crm = 12, .opc1 = 0,
-      .access = PL0_W, .type = ARM_CP_NOP|ARM_CP_64BIT },
+      .access = PL0_W, .type = ARM_CP_NOP | ARM_CP_64BIT },
     { .name = "PIR", .cp = 15, .crm = 12, .opc1 = 1,
-      .access = PL0_W, .type = ARM_CP_NOP|ARM_CP_64BIT },
+      .access = PL0_W, .type = ARM_CP_NOP | ARM_CP_64BIT },
     { .name = "PDR", .cp = 15, .crm = 12, .opc1 = 2,
-      .access = PL0_W, .type = ARM_CP_NOP|ARM_CP_64BIT },
+      .access = PL0_W, .type = ARM_CP_NOP | ARM_CP_64BIT },
     { .name = "CIDCR", .cp = 15, .crm = 14, .opc1 = 0,
-      .access = PL1_W, .type = ARM_CP_NOP|ARM_CP_64BIT },
+      .access = PL1_W, .type = ARM_CP_NOP | ARM_CP_64BIT },
 };
 
 static const ARMCPRegInfo cache_test_clean_cp_reginfo[] = {
-    /* The cache test-and-clean instructions always return (1 << 30)
+    /*
+     * The cache test-and-clean instructions always return (1 << 30)
      * to indicate that there are no dirty cache lines.
      */
     { .name = "TC_DCACHE", .cp = 15, .crn = 7, .crm = 10, .opc1 = 0, .opc2 = 3,
@@ -4094,7 +4359,8 @@ static uint64_t mpidr_read_val(CPUARMState *env)
 
     if (arm_feature(env, ARM_FEATURE_V7MP)) {
         mpidr |= (1U << 31);
-        /* Cores which are uniprocessor (non-coherent)
+        /*
+         * Cores which are uniprocessor (non-coherent)
          * but still implement the MP extensions set
          * bit 30. (For instance, Cortex-R5).
          */
@@ -4306,7 +4572,8 @@ static CPAccessResult access_tocu(CPUARMState *env, const ARMCPRegInfo *ri,
     return do_cacheop_pou_access(env, HCR_TOCU | HCR_TPU);
 }
 
-/* See: D4.7.2 TLB maintenance requirements and the TLB maintenance instructions
+/*
+ * See: D4.7.2 TLB maintenance requirements and the TLB maintenance instructions
  * Page D4-1736 (DDI0487A.b)
  */
 
@@ -4439,7 +4706,8 @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                  uint64_t value)
 {
-    /* Invalidate by VA, EL2
+    /*
+     * Invalidate by VA, EL2
      * Currently handles both VAE2 and VALE2, since we don't support
      * flush-last-level-only.
      */
@@ -4453,7 +4721,8 @@ static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                  uint64_t value)
 {
-    /* Invalidate by VA, EL3
+    /*
+     * Invalidate by VA, EL3
      * Currently handles both VAE3 and VALE3, since we don't support
      * flush-last-level-only.
      */
@@ -4478,7 +4747,8 @@ static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                  uint64_t value)
 {
-    /* Invalidate by VA, EL1&0 (AArch64 version).
+    /*
+     * Invalidate by VA, EL1&0 (AArch64 version).
      * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1,
      * since we don't support flush-for-specific-ASID-only or
      * flush-last-level-only.
@@ -4799,7 +5069,8 @@ static CPAccessResult sp_el0_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                     bool isread)
 {
     if (!(env->pstate & PSTATE_SP)) {
-        /* Access to SP_EL0 is undefined if it's being used as
+        /*
+         * Access to SP_EL0 is undefined if it's being used as
          * the stack pointer.
          */
         return CP_ACCESS_TRAP_UNCATEGORIZED;
@@ -4839,7 +5110,8 @@ static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     }
 
     if (raw_read(env, ri) == value) {
-        /* Skip the TLB flush if nothing actually changed; Linux likes
+        /*
+         * Skip the TLB flush if nothing actually changed; Linux likes
          * to do a lot of pointless SCTLR writes.
          */
         return;
@@ -4907,7 +5179,8 @@ static void mdcr_el2_write(CPUARMState *env, const ARMCPRegInfo *ri,
 }
 
 static const ARMCPRegInfo v8_cp_reginfo[] = {
-    /* Minimal set of EL0-visible registers. This will need to be expanded
+    /*
+     * Minimal set of EL0-visible registers. This will need to be expanded
      * significantly for system emulation of AArch64 CPUs.
      */
     { .name = "NZCV", .state = ARM_CP_STATE_AA64,
@@ -5190,7 +5463,8 @@ static const ARMCPRegInfo v8_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 0, .opc2 = 0,
       .access = PL1_RW,
       .fieldoffset = offsetof(CPUARMState, banked_spsr[BANK_SVC]) },
-    /* We rely on the access checks not allowing the guest to write to the
+    /*
+     * We rely on the access checks not allowing the guest to write to the
      * state field when SPSel indicates that it's being used as the stack
      * pointer.
      */
@@ -5268,7 +5542,8 @@ static void do_hcr_write(CPUARMState *env, uint64_t value, uint64_t valid_mask)
     if (arm_feature(env, ARM_FEATURE_EL3)) {
         valid_mask &= ~HCR_HCD;
     } else if (cpu->psci_conduit != QEMU_PSCI_CONDUIT_SMC) {
-        /* Architecturally HCR.TSC is RES0 if EL3 is not implemented.
+        /*
+         * Architecturally HCR.TSC is RES0 if EL3 is not implemented.
          * However, if we're using the SMC PSCI conduit then QEMU is
          * effectively acting like EL3 firmware and so the guest at
          * EL2 should retain the ability to prevent EL1 from being
@@ -5698,7 +5973,8 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
       .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF,
       .writefn = tlbi_aa64_vae2is_write },
 #ifndef CONFIG_USER_ONLY
-    /* Unlike the other EL2-related AT operations, these must
+    /*
+     * Unlike the other EL2-related AT operations, these must
      * UNDEF from EL3 if EL2 is not implemented, which is why we
      * define them here rather than with the rest of the AT ops.
      */
@@ -5712,7 +5988,8 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
       .access = PL2_W, .accessfn = at_s1e2_access,
       .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC | ARM_CP_EL3_NO_EL2_UNDEF,
       .writefn = ats_write64 },
-    /* The AArch32 ATS1H* operations are CONSTRAINED UNPREDICTABLE
+    /*
+     * The AArch32 ATS1H* operations are CONSTRAINED UNPREDICTABLE
      * if EL2 is not implemented; we choose to UNDEF. Behaviour at EL3
      * with SCR.NS == 0 outside Monitor mode is UNPREDICTABLE; we choose
      * to behave as if SCR.NS was 1.
@@ -5725,7 +6002,8 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
       .writefn = ats1h_write, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC },
     { .name = "CNTHCTL_EL2", .state = ARM_CP_STATE_BOTH,
       .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 1, .opc2 = 0,
-      /* ARMv7 requires bit 0 and 1 to reset to 1. ARMv8 defines the
+      /*
+       * ARMv7 requires bit 0 and 1 to reset to 1. ARMv8 defines the
        * reset values as IMPDEF. We choose to reset to 3 to comply with
        * both ARMv7 and ARMv8.
        */
@@ -5808,7 +6086,8 @@ static const ARMCPRegInfo el2_sec_cp_reginfo[] = {
 static CPAccessResult nsacr_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                    bool isread)
 {
-    /* The NSACR is RW at EL3, and RO for NS EL1 and NS EL2.
+    /*
+     * The NSACR is RW at EL3, and RO for NS EL1 and NS EL2.
      * At Secure EL1 it traps to EL3 or EL2.
      */
     if (arm_current_el(env) == 3) {
@@ -6612,7 +6891,8 @@ static void define_pmu_regs(ARMCPU *cpu)
     }
 }
 
-/* We don't know until after realize whether there's a GICv3
+/*
+ * We don't know until after realize whether there's a GICv3
  * attached, and that is what registers the gicv3 sysregs.
  * So we have to fill in the GIC fields in ID_PFR/ID_PFR1_EL1/ID_AA64PFR0_EL1
  * at runtime.
@@ -6641,7 +6921,8 @@ static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri)
 }
 #endif
 
-/* Shared logic between LORID and the rest of the LOR* registers.
+/*
+ * Shared logic between LORID and the rest of the LOR* registers.
  * Secure state exclusion has already been dealt with.
  */
 static CPAccessResult access_lor_ns(CPUARMState *env,
@@ -7468,7 +7749,8 @@ void register_cp_regs_for_features(ARMCPU *cpu)
 
     define_arm_cp_regs(cpu, cp_reginfo);
     if (!arm_feature(env, ARM_FEATURE_V8)) {
-        /* Must go early as it is full of wildcards that may be
+        /*
+         * Must go early as it is full of wildcards that may be
          * overridden by later definitions.
          */
         define_arm_cp_regs(cpu, not_v8_cp_reginfo);
@@ -7482,7 +7764,8 @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .access = PL1_R, .type = ARM_CP_CONST,
               .accessfn = access_aa32_tid3,
               .resetvalue = cpu->isar.id_pfr0 },
-            /* ID_PFR1 is not a plain ARM_CP_CONST because we don't know
+            /*
+             * ID_PFR1 is not a plain ARM_CP_CONST because we don't know
              * the value of the GIC field until after we define these regs.
              */
             { .name = "ID_PFR1", .state = ARM_CP_STATE_BOTH,
@@ -7864,31 +8147,89 @@ void register_cp_regs_for_features(ARMCPU *cpu)
 #ifdef CONFIG_USER_ONLY
         static const ARMCPRegUserSpaceInfo v8_user_idregs[] = {
             { .name = "ID_AA64PFR0_EL1",
-              .exported_bits = 0x000f000f00ff0000,
-              .fixed_bits    = 0x0000000000000011 },
+              .exported_bits = R_ID_AA64PFR0_FP_MASK |
+                               R_ID_AA64PFR0_ADVSIMD_MASK |
+                               R_ID_AA64PFR0_SVE_MASK |
+                               R_ID_AA64PFR0_DIT_MASK,
+              .fixed_bits = (0x1u << R_ID_AA64PFR0_EL0_SHIFT) |
+                            (0x1u << R_ID_AA64PFR0_EL1_SHIFT) },
             { .name = "ID_AA64PFR1_EL1",
-              .exported_bits = 0x00000000000000f0 },
+              .exported_bits = R_ID_AA64PFR1_BT_MASK |
+                               R_ID_AA64PFR1_SSBS_MASK |
+                               R_ID_AA64PFR1_MTE_MASK |
+                               R_ID_AA64PFR1_SME_MASK },
             { .name = "ID_AA64PFR*_EL1_RESERVED",
-              .is_glob = true                     },
-            { .name = "ID_AA64ZFR0_EL1"           },
+              .is_glob = true },
+            { .name = "ID_AA64ZFR0_EL1",
+              .exported_bits = R_ID_AA64ZFR0_SVEVER_MASK |
+                               R_ID_AA64ZFR0_AES_MASK |
+                               R_ID_AA64ZFR0_BITPERM_MASK |
+                               R_ID_AA64ZFR0_BFLOAT16_MASK |
+                               R_ID_AA64ZFR0_SHA3_MASK |
+                               R_ID_AA64ZFR0_SM4_MASK |
+                               R_ID_AA64ZFR0_I8MM_MASK |
+                               R_ID_AA64ZFR0_F32MM_MASK |
+                               R_ID_AA64ZFR0_F64MM_MASK },
+            { .name = "ID_AA64SMFR0_EL1",
+              .exported_bits = R_ID_AA64SMFR0_F32F32_MASK |
+                               R_ID_AA64SMFR0_B16F32_MASK |
+                               R_ID_AA64SMFR0_F16F32_MASK |
+                               R_ID_AA64SMFR0_I8I32_MASK |
+                               R_ID_AA64SMFR0_F64F64_MASK |
+                               R_ID_AA64SMFR0_I16I64_MASK |
+                               R_ID_AA64SMFR0_FA64_MASK },
             { .name = "ID_AA64MMFR0_EL1",
-              .fixed_bits    = 0x00000000ff000000 },
-            { .name = "ID_AA64MMFR1_EL1"          },
+              .exported_bits = R_ID_AA64MMFR0_ECV_MASK,
+              .fixed_bits = (0xfu << R_ID_AA64MMFR0_TGRAN64_SHIFT) |
+                            (0xfu << R_ID_AA64MMFR0_TGRAN4_SHIFT) },
+            { .name = "ID_AA64MMFR1_EL1",
+              .exported_bits = R_ID_AA64MMFR1_AFP_MASK },
+            { .name = "ID_AA64MMFR2_EL1",
+              .exported_bits = R_ID_AA64MMFR2_AT_MASK },
             { .name = "ID_AA64MMFR*_EL1_RESERVED",
-              .is_glob = true                     },
+              .is_glob = true },
             { .name = "ID_AA64DFR0_EL1",
-              .fixed_bits    = 0x0000000000000006 },
-            { .name = "ID_AA64DFR1_EL1"           },
+              .fixed_bits = (0x6u << R_ID_AA64DFR0_DEBUGVER_SHIFT) },
+            { .name = "ID_AA64DFR1_EL1" },
             { .name = "ID_AA64DFR*_EL1_RESERVED",
-              .is_glob = true                     },
+              .is_glob = true },
             { .name = "ID_AA64AFR*",
-              .is_glob = true                     },
+              .is_glob = true },
             { .name = "ID_AA64ISAR0_EL1",
-              .exported_bits = 0x00fffffff0fffff0 },
+              .exported_bits = R_ID_AA64ISAR0_AES_MASK |
+                               R_ID_AA64ISAR0_SHA1_MASK |
+                               R_ID_AA64ISAR0_SHA2_MASK |
+                               R_ID_AA64ISAR0_CRC32_MASK |
+                               R_ID_AA64ISAR0_ATOMIC_MASK |
+                               R_ID_AA64ISAR0_RDM_MASK |
+                               R_ID_AA64ISAR0_SHA3_MASK |
+                               R_ID_AA64ISAR0_SM3_MASK |
+                               R_ID_AA64ISAR0_SM4_MASK |
+                               R_ID_AA64ISAR0_DP_MASK |
+                               R_ID_AA64ISAR0_FHM_MASK |
+                               R_ID_AA64ISAR0_TS_MASK |
+                               R_ID_AA64ISAR0_RNDR_MASK },
             { .name = "ID_AA64ISAR1_EL1",
-              .exported_bits = 0x000000f0ffffffff },
+              .exported_bits = R_ID_AA64ISAR1_DPB_MASK |
+                               R_ID_AA64ISAR1_APA_MASK |
+                               R_ID_AA64ISAR1_API_MASK |
+                               R_ID_AA64ISAR1_JSCVT_MASK |
+                               R_ID_AA64ISAR1_FCMA_MASK |
+                               R_ID_AA64ISAR1_LRCPC_MASK |
+                               R_ID_AA64ISAR1_GPA_MASK |
+                               R_ID_AA64ISAR1_GPI_MASK |
+                               R_ID_AA64ISAR1_FRINTTS_MASK |
+                               R_ID_AA64ISAR1_SB_MASK |
+                               R_ID_AA64ISAR1_BF16_MASK |
+                               R_ID_AA64ISAR1_DGH_MASK |
+                               R_ID_AA64ISAR1_I8MM_MASK },
+            { .name = "ID_AA64ISAR2_EL1",
+              .exported_bits = R_ID_AA64ISAR2_WFXT_MASK |
+                               R_ID_AA64ISAR2_RPRES_MASK |
+                               R_ID_AA64ISAR2_GPA3_MASK |
+                               R_ID_AA64ISAR2_APA3_MASK },
             { .name = "ID_AA64ISAR*_EL1_RESERVED",
-              .is_glob = true                     },
+              .is_glob = true },
         };
         modify_arm_cp_regs(v8_idregs, v8_user_idregs);
 #endif
@@ -7896,7 +8237,7 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         if (!arm_feature(env, ARM_FEATURE_EL3) &&
             !arm_feature(env, ARM_FEATURE_EL2)) {
             ARMCPRegInfo rvbar = {
-                .name = "RVBAR_EL1", .state = ARM_CP_STATE_AA64,
+                .name = "RVBAR_EL1", .state = ARM_CP_STATE_BOTH,
                 .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1,
                 .access = PL1_R,
                 .fieldoffset = offsetof(CPUARMState, cp15.rvbar),
@@ -7987,13 +8328,20 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         }
         /* RVBAR_EL2 is only implemented if EL2 is the highest EL */
         if (!arm_feature(env, ARM_FEATURE_EL3)) {
-            ARMCPRegInfo rvbar = {
-                .name = "RVBAR_EL2", .state = ARM_CP_STATE_AA64,
-                .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 1,
-                .access = PL2_R,
-                .fieldoffset = offsetof(CPUARMState, cp15.rvbar),
+            ARMCPRegInfo rvbar[] = {
+                {
+                    .name = "RVBAR_EL2", .state = ARM_CP_STATE_AA64,
+                    .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 1,
+                    .access = PL2_R,
+                    .fieldoffset = offsetof(CPUARMState, cp15.rvbar),
+                },
+                {   .name = "RVBAR", .type = ARM_CP_ALIAS,
+                    .cp = 15, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1,
+                    .access = PL2_R,
+                    .fieldoffset = offsetof(CPUARMState, cp15.rvbar),
+                },
             };
-            define_one_arm_cp_reg(cpu, &rvbar);
+            define_arm_cp_regs(cpu, rvbar);
         }
     }
 
@@ -8016,7 +8364,8 @@ void register_cp_regs_for_features(ARMCPU *cpu)
 
         define_arm_cp_regs(cpu, el3_regs);
     }
-    /* The behaviour of NSACR is sufficiently various that we don't
+    /*
+     * The behaviour of NSACR is sufficiently various that we don't
      * try to describe it in a single reginfo:
      *  if EL3 is 64 bit, then trap to EL3 from S EL1,
      *     reads as constant 0xc00 from NS EL1 and NS EL2
@@ -8108,13 +8457,15 @@ void register_cp_regs_for_features(ARMCPU *cpu)
     if (cpu_isar_feature(aa32_jazelle, cpu)) {
         define_arm_cp_regs(cpu, jazelle_regs);
     }
-    /* Slightly awkwardly, the OMAP and StrongARM cores need all of
+    /*
+     * Slightly awkwardly, the OMAP and StrongARM cores need all of
      * cp15 crn=0 to be writes-ignored, whereas for other cores they should
      * be read-only (ie write causes UNDEF exception).
      */
     {
         ARMCPRegInfo id_pre_v8_midr_cp_reginfo[] = {
-            /* Pre-v8 MIDR space.
+            /*
+             * Pre-v8 MIDR space.
              * Note that the MIDR isn't a simple constant register because
              * of the TI925 behaviour where writes to another register can
              * cause the MIDR value to change.
@@ -8153,10 +8504,7 @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .access = PL1_R, .type = ARM_CP_NO_RAW, .resetvalue = cpu->midr,
               .fieldoffset = offsetof(CPUARMState, cp15.c0_cpuid),
               .readfn = midr_read },
-            /* crn = 0 op1 = 0 crm = 0 op2 = 4,7 : AArch32 aliases of MIDR */
-            { .name = "MIDR", .type = ARM_CP_ALIAS | ARM_CP_CONST,
-              .cp = 15, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 4,
-              .access = PL1_R, .resetvalue = cpu->midr },
+            /* crn = 0 op1 = 0 crm = 0 op2 = 7 : AArch32 aliases of MIDR */
             { .name = "MIDR", .type = ARM_CP_ALIAS | ARM_CP_CONST,
               .cp = 15, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 7,
               .access = PL1_R, .resetvalue = cpu->midr },
@@ -8166,6 +8514,11 @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .accessfn = access_aa64_tid1,
               .type = ARM_CP_CONST, .resetvalue = cpu->revidr },
         };
+        ARMCPRegInfo id_v8_midr_alias_cp_reginfo = {
+            .name = "MIDR", .type = ARM_CP_ALIAS | ARM_CP_CONST,
+            .cp = 15, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 4,
+            .access = PL1_R, .resetvalue = cpu->midr
+        };
         ARMCPRegInfo id_cp_reginfo[] = {
             /* These are common to v8 and pre-v8 */
             { .name = "CTR",
@@ -8198,6 +8551,13 @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .access = PL1_R, .type = ARM_CP_CONST,
               .resetvalue = cpu->pmsav7_dregion << 8
         };
+        /* HMPUIR is specific to PMSA V8 */
+        ARMCPRegInfo id_hmpuir_reginfo = {
+            .name = "HMPUIR",
+            .cp = 15, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 4,
+            .access = PL2_R, .type = ARM_CP_CONST,
+            .resetvalue = cpu->pmsav8r_hdregion
+        };
         static const ARMCPRegInfo crn0_wi_reginfo = {
             .name = "CRN0_WI", .cp = 15, .crn = 0, .crm = CP_ANY,
             .opc1 = CP_ANY, .opc2 = CP_ANY, .access = PL1_W,
@@ -8206,15 +8566,20 @@ void register_cp_regs_for_features(ARMCPU *cpu)
 #ifdef CONFIG_USER_ONLY
         static const ARMCPRegUserSpaceInfo id_v8_user_midr_cp_reginfo[] = {
             { .name = "MIDR_EL1",
-              .exported_bits = 0x00000000ffffffff },
-            { .name = "REVIDR_EL1"                },
+              .exported_bits = R_MIDR_EL1_REVISION_MASK |
+                               R_MIDR_EL1_PARTNUM_MASK |
+                               R_MIDR_EL1_ARCHITECTURE_MASK |
+                               R_MIDR_EL1_VARIANT_MASK |
+                               R_MIDR_EL1_IMPLEMENTER_MASK },
+            { .name = "REVIDR_EL1" },
         };
         modify_arm_cp_regs(id_v8_midr_cp_reginfo, id_v8_user_midr_cp_reginfo);
 #endif
         if (arm_feature(env, ARM_FEATURE_OMAPCP) ||
             arm_feature(env, ARM_FEATURE_STRONGARM)) {
             size_t i;
-            /* Register the blanket "writes ignored" value first to cover the
+            /*
+             * Register the blanket "writes ignored" value first to cover the
              * whole space. Then update the specific ID registers to allow write
              * access, so that they ignore writes rather than causing them to
              * UNDEF.
@@ -8231,12 +8596,83 @@ void register_cp_regs_for_features(ARMCPU *cpu)
         }
         if (arm_feature(env, ARM_FEATURE_V8)) {
             define_arm_cp_regs(cpu, id_v8_midr_cp_reginfo);
+            if (!arm_feature(env, ARM_FEATURE_PMSA)) {
+                define_one_arm_cp_reg(cpu, &id_v8_midr_alias_cp_reginfo);
+            }
         } else {
             define_arm_cp_regs(cpu, id_pre_v8_midr_cp_reginfo);
         }
         define_arm_cp_regs(cpu, id_cp_reginfo);
         if (!arm_feature(env, ARM_FEATURE_PMSA)) {
             define_one_arm_cp_reg(cpu, &id_tlbtr_reginfo);
+        } else if (arm_feature(env, ARM_FEATURE_PMSA) &&
+                   arm_feature(env, ARM_FEATURE_V8)) {
+            uint32_t i = 0;
+            char *tmp_string;
+
+            define_one_arm_cp_reg(cpu, &id_mpuir_reginfo);
+            define_one_arm_cp_reg(cpu, &id_hmpuir_reginfo);
+            define_arm_cp_regs(cpu, pmsav8r_cp_reginfo);
+
+            /* Register alias is only valid for first 32 indexes */
+            for (i = 0; i < MIN(cpu->pmsav7_dregion, 32); ++i) {
+                uint8_t crm = 0b1000 | extract32(i, 1, 3);
+                uint8_t opc1 = extract32(i, 4, 1);
+                uint8_t opc2 = extract32(i, 0, 1) << 2;
+
+                tmp_string = g_strdup_printf("PRBAR%u", i);
+                ARMCPRegInfo tmp_prbarn_reginfo = {
+                    .name = tmp_string, .type = ARM_CP_ALIAS | ARM_CP_NO_RAW,
+                    .cp = 15, .opc1 = opc1, .crn = 6, .crm = crm, .opc2 = opc2,
+                    .access = PL1_RW, .resetvalue = 0,
+                    .accessfn = access_tvm_trvm,
+                    .writefn = pmsav8r_regn_write, .readfn = pmsav8r_regn_read
+                };
+                define_one_arm_cp_reg(cpu, &tmp_prbarn_reginfo);
+                g_free(tmp_string);
+
+                opc2 = extract32(i, 0, 1) << 2 | 0x1;
+                tmp_string = g_strdup_printf("PRLAR%u", i);
+                ARMCPRegInfo tmp_prlarn_reginfo = {
+                    .name = tmp_string, .type = ARM_CP_ALIAS | ARM_CP_NO_RAW,
+                    .cp = 15, .opc1 = opc1, .crn = 6, .crm = crm, .opc2 = opc2,
+                    .access = PL1_RW, .resetvalue = 0,
+                    .accessfn = access_tvm_trvm,
+                    .writefn = pmsav8r_regn_write, .readfn = pmsav8r_regn_read
+                };
+                define_one_arm_cp_reg(cpu, &tmp_prlarn_reginfo);
+                g_free(tmp_string);
+            }
+
+            /* Register alias is only valid for first 32 indexes */
+            for (i = 0; i < MIN(cpu->pmsav8r_hdregion, 32); ++i) {
+                uint8_t crm = 0b1000 | extract32(i, 1, 3);
+                uint8_t opc1 = 0b100 | extract32(i, 4, 1);
+                uint8_t opc2 = extract32(i, 0, 1) << 2;
+
+                tmp_string = g_strdup_printf("HPRBAR%u", i);
+                ARMCPRegInfo tmp_hprbarn_reginfo = {
+                    .name = tmp_string,
+                    .type = ARM_CP_NO_RAW,
+                    .cp = 15, .opc1 = opc1, .crn = 6, .crm = crm, .opc2 = opc2,
+                    .access = PL2_RW, .resetvalue = 0,
+                    .writefn = pmsav8r_regn_write, .readfn = pmsav8r_regn_read
+                };
+                define_one_arm_cp_reg(cpu, &tmp_hprbarn_reginfo);
+                g_free(tmp_string);
+
+                opc2 = extract32(i, 0, 1) << 2 | 0x1;
+                tmp_string = g_strdup_printf("HPRLAR%u", i);
+                ARMCPRegInfo tmp_hprlarn_reginfo = {
+                    .name = tmp_string,
+                    .type = ARM_CP_NO_RAW,
+                    .cp = 15, .opc1 = opc1, .crn = 6, .crm = crm, .opc2 = opc2,
+                    .access = PL2_RW, .resetvalue = 0,
+                    .writefn = pmsav8r_regn_write, .readfn = pmsav8r_regn_read
+                };
+                define_one_arm_cp_reg(cpu, &tmp_hprlarn_reginfo);
+                g_free(tmp_string);
+            }
         } else if (arm_feature(env, ARM_FEATURE_V7)) {
             define_one_arm_cp_reg(cpu, &id_mpuir_reginfo);
         }
@@ -8314,7 +8750,7 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             ARMCPRegInfo cbar = {
                 .name = "CBAR",
                 .cp = 15, .crn = 15, .crm = 0, .opc1 = 4, .opc2 = 0,
-                .access = PL1_R|PL3_W, .resetvalue = cpu->reset_cbar,
+                .access = PL1_R | PL3_W, .resetvalue = cpu->reset_cbar,
                 .fieldoffset = offsetof(CPUARMState,
                                         cp15.c15_config_base_address)
             };
@@ -8351,13 +8787,25 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             .raw_writefn = raw_write,
         };
         if (arm_feature(env, ARM_FEATURE_XSCALE)) {
-            /* Normally we would always end the TB on an SCTLR write, but Linux
+            /*
+             * Normally we would always end the TB on an SCTLR write, but Linux
              * arch/arm/mach-pxa/sleep.S expects two instructions following
              * an MMU enable to execute from cache.  Imitate this behaviour.
              */
             sctlr.type |= ARM_CP_SUPPRESS_TB_END;
         }
         define_one_arm_cp_reg(cpu, &sctlr);
+
+        if (arm_feature(env, ARM_FEATURE_PMSA) &&
+            arm_feature(env, ARM_FEATURE_V8)) {
+            ARMCPRegInfo vsctlr = {
+                .name = "VSCTLR", .state = ARM_CP_STATE_AA32,
+                .cp = 15, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 0,
+                .access = PL2_RW, .resetvalue = 0x0,
+                .fieldoffset = offsetoflow32(CPUARMState, cp15.vsctlr),
+            };
+            define_one_arm_cp_reg(cpu, &vsctlr);
+        }
     }
 
     if (cpu_isar_feature(aa64_lor, cpu)) {
@@ -8746,7 +9194,8 @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r,
 void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu,
                                        const ARMCPRegInfo *r, void *opaque)
 {
-    /* Define implementations of coprocessor registers.
+    /*
+     * Define implementations of coprocessor registers.
      * We store these in a hashtable because typically
      * there are less than 150 registers in a space which
      * is 16*16*16*8*8 = 262144 in size.
@@ -8813,7 +9262,8 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu,
     default:
         g_assert_not_reached();
     }
-    /* The AArch64 pseudocode CheckSystemAccess() specifies that op1
+    /*
+     * The AArch64 pseudocode CheckSystemAccess() specifies that op1
      * encodes a minimum access level for the register. We roll this
      * runtime check into our general permission check code, so check
      * here that the reginfo's specified permissions are strict enough
@@ -8855,7 +9305,8 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu,
         assert((r->access & ~mask) == 0);
     }
 
-    /* Check that the register definition has enough info to handle
+    /*
+     * Check that the register definition has enough info to handle
      * reads and writes if they are permitted.
      */
     if (!(r->type & (ARM_CP_SPECIAL_MASK | ARM_CP_CONST))) {
@@ -8880,7 +9331,8 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu,
                         continue;
                     }
                     if (state == ARM_CP_STATE_AA32) {
-                        /* Under AArch32 CP registers can be common
+                        /*
+                         * Under AArch32 CP registers can be common
                          * (same for secure and non-secure world) or banked.
                          */
                         char *name;
@@ -8906,8 +9358,10 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu,
                             g_assert_not_reached();
                         }
                     } else {
-                        /* AArch64 registers get mapped to non-secure instance
-                         * of AArch32 */
+                        /*
+                         * AArch64 registers get mapped to non-secure instance
+                         * of AArch32
+                         */
                         add_cpreg_to_hashtable(cpu, r, opaque, state,
                                                ARM_CP_SECSTATE_NS,
                                                crm, opc1, opc2, r->name);
@@ -8993,7 +9447,8 @@ void arm_cp_reset_ignore(CPUARMState *env, const ARMCPRegInfo *opaque)
 
 static int bad_mode_switch(CPUARMState *env, int mode, CPSRWriteType write_type)
 {
-    /* Return true if it is not valid for us to switch to
+    /*
+     * Return true if it is not valid for us to switch to
      * this CPU mode (ie all the UNPREDICTABLE cases in
      * the ARM ARM CPSRWriteByInstr pseudocode).
      */
@@ -9014,10 +9469,12 @@ static int bad_mode_switch(CPUARMState *env, int mode, CPSRWriteType write_type)
     case ARM_CPU_MODE_UND:
     case ARM_CPU_MODE_IRQ:
     case ARM_CPU_MODE_FIQ:
-        /* Note that we don't implement the IMPDEF NSACR.RFR which in v7
+        /*
+         * Note that we don't implement the IMPDEF NSACR.RFR which in v7
          * allows FIQ mode to be Secure-only. (In v8 this doesn't exist.)
          */
-        /* If HCR.TGE is set then changes from Monitor to NS PL1 via MSR
+        /*
+         * If HCR.TGE is set then changes from Monitor to NS PL1 via MSR
          * and CPS are treated as illegal mode changes.
          */
         if (write_type == CPSRWriteByInstr &&
@@ -9059,10 +9516,12 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
         env->CF = (val >> 29) & 1;
         env->VF = (val << 3) & 0x80000000;
     }
-    if (mask & CPSR_Q)
+    if (mask & CPSR_Q) {
         env->QF = ((val & CPSR_Q) != 0);
-    if (mask & CPSR_T)
+    }
+    if (mask & CPSR_T) {
         env->thumb = ((val & CPSR_T) != 0);
+    }
     if (mask & CPSR_IT_0_1) {
         env->condexec_bits &= ~3;
         env->condexec_bits |= (val >> 25) & 3;
@@ -9075,7 +9534,8 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
         env->GE = (val >> 16) & 0xf;
     }
 
-    /* In a V7 implementation that includes the security extensions but does
+    /*
+     * In a V7 implementation that includes the security extensions but does
      * not include Virtualization Extensions the SCR.FW and SCR.AW bits control
      * whether non-secure software is allowed to change the CPSR_F and CPSR_A
      * bits respectively.
@@ -9091,7 +9551,8 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
         changed_daif = (env->daif ^ val) & mask;
 
         if (changed_daif & CPSR_A) {
-            /* Check to see if we are allowed to change the masking of async
+            /*
+             * Check to see if we are allowed to change the masking of async
              * abort exceptions from a non-secure state.
              */
             if (!(env->cp15.scr_el3 & SCR_AW)) {
@@ -9103,7 +9564,8 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
         }
 
         if (changed_daif & CPSR_F) {
-            /* Check to see if we are allowed to change the masking of FIQ
+            /*
+             * Check to see if we are allowed to change the masking of FIQ
              * exceptions from a non-secure state.
              */
             if (!(env->cp15.scr_el3 & SCR_FW)) {
@@ -9113,7 +9575,8 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
                 mask &= ~CPSR_F;
             }
 
-            /* Check whether non-maskable FIQ (NMFI) support is enabled.
+            /*
+             * Check whether non-maskable FIQ (NMFI) support is enabled.
              * If this bit is set software is not allowed to mask
              * FIQs, but is allowed to set CPSR_F to 0.
              */
@@ -9133,7 +9596,8 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
     if (write_type != CPSRWriteRaw &&
         ((env->uncached_cpsr ^ val) & mask & CPSR_M)) {
         if ((env->uncached_cpsr & CPSR_M) == ARM_CPU_MODE_USR) {
-            /* Note that we can only get here in USR mode if this is a
+            /*
+             * Note that we can only get here in USR mode if this is a
              * gdb stub write; for this case we follow the architectural
              * behaviour for guest writes in USR mode of ignoring an attempt
              * to switch mode. (Those are caught by translate.c for writes
@@ -9141,7 +9605,8 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask,
              */
             mask &= ~CPSR_M;
         } else if (bad_mode_switch(env, val & CPSR_M, write_type)) {
-            /* Attempt to switch to an invalid mode: this is UNPREDICTABLE in
+            /*
+             * Attempt to switch to an invalid mode: this is UNPREDICTABLE in
              * v7, and has defined behaviour in v8:
              *  + leave CPSR.M untouched
              *  + allow changes to the other CPSR fields
@@ -9261,15 +9726,16 @@ static void switch_mode(CPUARMState *env, int mode)
     int i;
 
     old_mode = env->uncached_cpsr & CPSR_M;
-    if (mode == old_mode)
+    if (mode == old_mode) {
         return;
+    }
 
     if (old_mode == ARM_CPU_MODE_FIQ) {
-        memcpy (env->fiq_regs, env->regs + 8, 5 * sizeof(uint32_t));
-        memcpy (env->regs + 8, env->usr_regs, 5 * sizeof(uint32_t));
+        memcpy(env->fiq_regs, env->regs + 8, 5 * sizeof(uint32_t));
+        memcpy(env->regs + 8, env->usr_regs, 5 * sizeof(uint32_t));
     } else if (mode == ARM_CPU_MODE_FIQ) {
-        memcpy (env->usr_regs, env->regs + 8, 5 * sizeof(uint32_t));
-        memcpy (env->regs + 8, env->fiq_regs, 5 * sizeof(uint32_t));
+        memcpy(env->usr_regs, env->regs + 8, 5 * sizeof(uint32_t));
+        memcpy(env->regs + 8, env->fiq_regs, 5 * sizeof(uint32_t));
     }
 
     i = bank_number(old_mode);
@@ -9284,7 +9750,8 @@ static void switch_mode(CPUARMState *env, int mode)
     env->regs[14] = env->banked_r14[r14_bank_number(mode)];
 }
 
-/* Physical Interrupt Target EL Lookup Table
+/*
+ * Physical Interrupt Target EL Lookup Table
  *
  * [ From ARM ARM section G1.13.4 (Table G1-15) ]
  *
@@ -9358,7 +9825,8 @@ uint32_t arm_phys_excp_target_el(CPUState *cs, uint32_t excp_idx,
     if (arm_feature(env, ARM_FEATURE_EL3)) {
         rw = ((env->cp15.scr_el3 & SCR_RW) == SCR_RW);
     } else {
-        /* Either EL2 is the highest EL (and so the EL2 register width
+        /*
+         * Either EL2 is the highest EL (and so the EL2 register width
          * is given by is64); or there is no EL2 or EL3, in which case
          * the value of 'rw' does not affect the table lookup anyway.
          */
@@ -9633,7 +10101,8 @@ void aarch64_sync_64_to_32(CPUARMState *env)
         env->banked_r13[bank_number(ARM_CPU_MODE_UND)] = env->xregs[23];
     }
 
-    /* Registers x24-x30 are mapped to r8-r14 in FIQ mode.  If we are in FIQ
+    /*
+     * Registers x24-x30 are mapped to r8-r14 in FIQ mode.  If we are in FIQ
      * mode, then we can copy to r8-r14.  Otherwise, we copy to the
      * FIQ bank for r8-r14.
      */
@@ -9865,10 +10334,11 @@ static void arm_cpu_do_interrupt_aarch32(CPUState *cs)
         new_mode = ARM_CPU_MODE_UND;
         addr = 0x04;
         mask = CPSR_I;
-        if (env->thumb)
+        if (env->thumb) {
             offset = 2;
-        else
+        } else {
             offset = 4;
+        }
         break;
     case EXCP_SWI:
         new_mode = ARM_CPU_MODE_SVC;
@@ -9979,7 +10449,8 @@ static void arm_cpu_do_interrupt_aarch32(CPUState *cs)
         /* High vectors. When enabled, base address cannot be remapped. */
         addr += 0xffff0000;
     } else {
-        /* ARM v7 architectures provide a vector base address register to remap
+        /*
+         * ARM v7 architectures provide a vector base address register to remap
          * the interrupt vector table.
          * This register is only followed in non-monitor mode, and is banked.
          * Note: only bits 31:5 are valid.
@@ -10113,7 +10584,8 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs)
     aarch64_sve_change_el(env, cur_el, new_el, is_a64(env));
 
     if (cur_el < new_el) {
-        /* Entry vector offset depends on whether the implemented EL
+        /*
+         * Entry vector offset depends on whether the implemented EL
          * immediately lower than the target level is using AArch32 or AArch64
          */
         bool is_aa64;
@@ -10314,7 +10786,8 @@ static void handle_semihosting(CPUState *cs)
 }
 #endif
 
-/* Handle a CPU exception for A and R profile CPUs.
+/*
+ * Handle a CPU exception for A and R profile CPUs.
  * Do any appropriate logging, handle PSCI calls, and then hand off
  * to the AArch64-entry or AArch32-entry function depending on the
  * target exception level's register width.
@@ -10359,7 +10832,8 @@ void arm_cpu_do_interrupt(CPUState *cs)
     }
 #endif
 
-    /* Hooks may change global state so BQL should be held, also the
+    /*
+     * Hooks may change global state so BQL should be held, also the
      * BQL needs to be held for any modification of
      * cs->interrupt_request.
      */
@@ -10640,9 +11114,11 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
     };
 }
 
-/* Note that signed overflow is undefined in C.  The following routines are
-   careful to use unsigned types where modulo arithmetic is required.
-   Failure to do so _will_ break on newer gcc.  */
+/*
+ * Note that signed overflow is undefined in C.  The following routines are
+ * careful to use unsigned types where modulo arithmetic is required.
+ * Failure to do so _will_ break on newer gcc.
+ */
 
 /* Signed saturating arithmetic.  */
 
@@ -10653,10 +11129,11 @@ static inline uint16_t add16_sat(uint16_t a, uint16_t b)
 
     res = a + b;
     if (((res ^ a) & 0x8000) && !((a ^ b) & 0x8000)) {
-        if (a & 0x8000)
+        if (a & 0x8000) {
             res = 0x8000;
-        else
+        } else {
             res = 0x7fff;
+        }
     }
     return res;
 }
@@ -10668,10 +11145,11 @@ static inline uint8_t add8_sat(uint8_t a, uint8_t b)
 
     res = a + b;
     if (((res ^ a) & 0x80) && !((a ^ b) & 0x80)) {
-        if (a & 0x80)
+        if (a & 0x80) {
             res = 0x80;
-        else
+        } else {
             res = 0x7f;
+        }
     }
     return res;
 }
@@ -10683,10 +11161,11 @@ static inline uint16_t sub16_sat(uint16_t a, uint16_t b)
 
     res = a - b;
     if (((res ^ a) & 0x8000) && ((a ^ b) & 0x8000)) {
-        if (a & 0x8000)
+        if (a & 0x8000) {
             res = 0x8000;
-        else
+        } else {
             res = 0x7fff;
+        }
     }
     return res;
 }
@@ -10698,10 +11177,11 @@ static inline uint8_t sub8_sat(uint8_t a, uint8_t b)
 
     res = a - b;
     if (((res ^ a) & 0x80) && ((a ^ b) & 0x80)) {
-        if (a & 0x80)
+        if (a & 0x80) {
             res = 0x80;
-        else
+        } else {
             res = 0x7f;
+        }
     }
     return res;
 }
@@ -10719,34 +11199,38 @@ static inline uint16_t add16_usat(uint16_t a, uint16_t b)
 {
     uint16_t res;
     res = a + b;
-    if (res < a)
+    if (res < a) {
         res = 0xffff;
+    }
     return res;
 }
 
 static inline uint16_t sub16_usat(uint16_t a, uint16_t b)
 {
-    if (a > b)
+    if (a > b) {
         return a - b;
-    else
+    } else {
         return 0;
+    }
 }
 
 static inline uint8_t add8_usat(uint8_t a, uint8_t b)
 {
     uint8_t res;
     res = a + b;
-    if (res < a)
+    if (res < a) {
         res = 0xff;
+    }
     return res;
 }
 
 static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
 {
-    if (a > b)
+    if (a > b) {
         return a - b;
-    else
+    } else {
         return 0;
+    }
 }
 
 #define ADD16(a, b, n) RESULT(add16_usat(a, b), n, 16);
@@ -10764,7 +11248,7 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
     RESULT(sum, n, 16); \
     if (sum >= 0) \
         ge |= 3 << (n * 2); \
-    } while(0)
+    } while (0)
 
 #define SARITH8(a, b, n, op) do { \
     int32_t sum; \
@@ -10772,7 +11256,7 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
     RESULT(sum, n, 8); \
     if (sum >= 0) \
         ge |= 1 << n; \
-    } while(0)
+    } while (0)
 
 
 #define ADD16(a, b, n) SARITH16(a, b, n, +)
@@ -10791,7 +11275,7 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
     RESULT(sum, n, 16); \
     if ((sum >> 16) == 1) \
         ge |= 3 << (n * 2); \
-    } while(0)
+    } while (0)
 
 #define ADD8(a, b, n) do { \
     uint32_t sum; \
@@ -10799,7 +11283,7 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
     RESULT(sum, n, 8); \
     if ((sum >> 8) == 1) \
         ge |= 1 << n; \
-    } while(0)
+    } while (0)
 
 #define SUB16(a, b, n) do { \
     uint32_t sum; \
@@ -10807,7 +11291,7 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
     RESULT(sum, n, 16); \
     if ((sum >> 16) == 0) \
         ge |= 3 << (n * 2); \
-    } while(0)
+    } while (0)
 
 #define SUB8(a, b, n) do { \
     uint32_t sum; \
@@ -10815,7 +11299,7 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
     RESULT(sum, n, 8); \
     if ((sum >> 8) == 0) \
         ge |= 1 << n; \
-    } while(0)
+    } while (0)
 
 #define PFX u
 #define ARITH_GE
@@ -10850,10 +11334,11 @@ static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
 
 static inline uint8_t do_usad(uint8_t a, uint8_t b)
 {
-    if (a > b)
+    if (a > b) {
         return a - b;
-    else
+    } else {
         return b - a;
+    }
 }
 
 /* Unsigned sum of absolute byte differences.  */
@@ -10873,18 +11358,23 @@ uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b)
     uint32_t mask;
 
     mask = 0;
-    if (flags & 1)
+    if (flags & 1) {
         mask |= 0xff;
-    if (flags & 2)
+    }
+    if (flags & 2) {
         mask |= 0xff00;
-    if (flags & 4)
+    }
+    if (flags & 4) {
         mask |= 0xff0000;
-    if (flags & 8)
+    }
+    if (flags & 8) {
         mask |= 0xff000000;
+    }
     return (a & mask) | (b & ~mask);
 }
 
-/* CRC helpers.
+/*
+ * CRC helpers.
  * The upper bytes of val (above the number specified by 'bytes') must have
  * been zeroed out by the caller.
  */
@@ -10908,7 +11398,8 @@ uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes)
     return crc32c(acc, buf, bytes) ^ 0xffffffff;
 }
 
-/* Return the exception level to which FP-disabled exceptions should
+/*
+ * Return the exception level to which FP-disabled exceptions should
  * be taken, or 0 if FP is enabled.
  */
 int fp_exception_el(CPUARMState *env, int cur_el)
@@ -10916,7 +11407,8 @@ int fp_exception_el(CPUARMState *env, int cur_el)
 #ifndef CONFIG_USER_ONLY
     uint64_t hcr_el2;
 
-    /* CPACR and the CPTR registers don't exist before v6, so FP is
+    /*
+     * CPACR and the CPTR registers don't exist before v6, so FP is
      * always accessible
      */
     if (!arm_feature(env, ARM_FEATURE_V6)) {
@@ -10941,7 +11433,8 @@ int fp_exception_el(CPUARMState *env, int cur_el)
 
     hcr_el2 = arm_hcr_el2_eff(env);
 
-    /* The CPACR controls traps to EL1, or PL1 if we're 32 bit:
+    /*
+     * The CPACR controls traps to EL1, or PL1 if we're 32 bit:
      * 0, 2 : trap EL0 and EL1/PL1 accesses
      * 1    : trap only EL0 accesses
      * 3    : trap no accesses
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 161e42d50f..d9555309df 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -257,6 +257,10 @@ unsigned int arm_pamax(ARMCPU *cpu);
 static inline bool extended_addresses_enabled(CPUARMState *env)
 {
     uint64_t tcr = env->cp15.tcr_el[arm_is_secure(env) ? 3 : 1];
+    if (arm_feature(env, ARM_FEATURE_PMSA) &&
+        arm_feature(env, ARM_FEATURE_V8)) {
+        return true;
+    }
     return arm_el_is_aa64(env, 1) ||
            (arm_feature(env, ARM_FEATURE_LPAE) && (tcr & TTBCR_EAE));
 }
diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c
index 355cd4d60a..033a4d9261 100644
--- a/target/arm/m_helper.c
+++ b/target/arm/m_helper.c
@@ -7,30 +7,14 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu/units.h"
-#include "target/arm/idau.h"
-#include "trace.h"
 #include "cpu.h"
 #include "internals.h"
-#include "exec/gdbstub.h"
 #include "exec/helper-proto.h"
-#include "qemu/host-utils.h"
 #include "qemu/main-loop.h"
 #include "qemu/bitops.h"
-#include "qemu/crc32c.h"
-#include "qemu/qemu-print.h"
 #include "qemu/log.h"
 #include "exec/exec-all.h"
-#include <zlib.h> /* For crc32 */
-#include "semihosting/semihost.h"
-#include "sysemu/cpus.h"
-#include "sysemu/kvm.h"
-#include "qemu/range.h"
-#include "qapi/qapi-commands-machine-target.h"
-#include "qapi/error.h"
-#include "qemu/guest-random.h"
 #ifdef CONFIG_TCG
-#include "arm_ldst.h"
 #include "exec/cpu_ldst.h"
 #include "semihosting/common-semi.h"
 #endif
diff --git a/target/arm/machine.c b/target/arm/machine.c
index 54c5c62433..5f26152652 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -487,6 +487,30 @@ static bool pmsav8_needed(void *opaque)
         arm_feature(env, ARM_FEATURE_V8);
 }
 
+static bool pmsav8r_needed(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+    CPUARMState *env = &cpu->env;
+
+    return arm_feature(env, ARM_FEATURE_PMSA) &&
+        arm_feature(env, ARM_FEATURE_V8) &&
+        !arm_feature(env, ARM_FEATURE_M);
+}
+
+static const VMStateDescription vmstate_pmsav8r = {
+    .name = "cpu/pmsav8/pmsav8r",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = pmsav8r_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_VARRAY_UINT32(env.pmsav8.hprbar, ARMCPU,
+                        pmsav8r_hdregion, 0, vmstate_info_uint32, uint32_t),
+        VMSTATE_VARRAY_UINT32(env.pmsav8.hprlar, ARMCPU,
+                        pmsav8r_hdregion, 0, vmstate_info_uint32, uint32_t),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 static const VMStateDescription vmstate_pmsav8 = {
     .name = "cpu/pmsav8",
     .version_id = 1,
@@ -500,6 +524,10 @@ static const VMStateDescription vmstate_pmsav8 = {
         VMSTATE_UINT32(env.pmsav8.mair0[M_REG_NS], ARMCPU),
         VMSTATE_UINT32(env.pmsav8.mair1[M_REG_NS], ARMCPU),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription * []) {
+        &vmstate_pmsav8r,
+        NULL
     }
 };
 
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index f812734bfb..4bda0590c7 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -1758,9 +1758,13 @@ static bool pmsav7_use_background_region(ARMCPU *cpu, ARMMMUIdx mmu_idx,
 
     if (arm_feature(env, ARM_FEATURE_M)) {
         return env->v7m.mpu_ctrl[is_secure] & R_V7M_MPU_CTRL_PRIVDEFENA_MASK;
-    } else {
-        return regime_sctlr(env, mmu_idx) & SCTLR_BR;
     }
+
+    if (mmu_idx == ARMMMUIdx_Stage2) {
+        return false;
+    }
+
+    return regime_sctlr(env, mmu_idx) & SCTLR_BR;
 }
 
 static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address,
@@ -1952,6 +1956,26 @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address,
     return !(result->f.prot & (1 << access_type));
 }
 
+static uint32_t *regime_rbar(CPUARMState *env, ARMMMUIdx mmu_idx,
+                             uint32_t secure)
+{
+    if (regime_el(env, mmu_idx) == 2) {
+        return env->pmsav8.hprbar;
+    } else {
+        return env->pmsav8.rbar[secure];
+    }
+}
+
+static uint32_t *regime_rlar(CPUARMState *env, ARMMMUIdx mmu_idx,
+                             uint32_t secure)
+{
+    if (regime_el(env, mmu_idx) == 2) {
+        return env->pmsav8.hprlar;
+    } else {
+        return env->pmsav8.rlar[secure];
+    }
+}
+
 bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
                        MMUAccessType access_type, ARMMMUIdx mmu_idx,
                        bool secure, GetPhysAddrResult *result,
@@ -1974,6 +1998,13 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
     bool hit = false;
     uint32_t addr_page_base = address & TARGET_PAGE_MASK;
     uint32_t addr_page_limit = addr_page_base + (TARGET_PAGE_SIZE - 1);
+    int region_counter;
+
+    if (regime_el(env, mmu_idx) == 2) {
+        region_counter = cpu->pmsav8r_hdregion;
+    } else {
+        region_counter = cpu->pmsav7_dregion;
+    }
 
     result->f.lg_page_size = TARGET_PAGE_BITS;
     result->f.phys_addr = address;
@@ -1982,6 +2013,10 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
         *mregion = -1;
     }
 
+    if (mmu_idx == ARMMMUIdx_Stage2) {
+        fi->stage2 = true;
+    }
+
     /*
      * Unlike the ARM ARM pseudocode, we don't need to check whether this
      * was an exception vector read from the vector table (which is always
@@ -1998,17 +2033,26 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
             hit = true;
         }
 
-        for (n = (int)cpu->pmsav7_dregion - 1; n >= 0; n--) {
+        uint32_t bitmask;
+        if (arm_feature(env, ARM_FEATURE_M)) {
+            bitmask = 0x1f;
+        } else {
+            bitmask = 0x3f;
+            fi->level = 0;
+        }
+
+        for (n = region_counter - 1; n >= 0; n--) {
             /* region search */
             /*
-             * Note that the base address is bits [31:5] from the register
-             * with bits [4:0] all zeroes, but the limit address is bits
-             * [31:5] from the register with bits [4:0] all ones.
+             * Note that the base address is bits [31:x] from the register
+             * with bits [x-1:0] all zeroes, but the limit address is bits
+             * [31:x] from the register with bits [x:0] all ones. Where x is
+             * 5 for Cortex-M and 6 for Cortex-R
              */
-            uint32_t base = env->pmsav8.rbar[secure][n] & ~0x1f;
-            uint32_t limit = env->pmsav8.rlar[secure][n] | 0x1f;
+            uint32_t base = regime_rbar(env, mmu_idx, secure)[n] & ~bitmask;
+            uint32_t limit = regime_rlar(env, mmu_idx, secure)[n] | bitmask;
 
-            if (!(env->pmsav8.rlar[secure][n] & 0x1)) {
+            if (!(regime_rlar(env, mmu_idx, secure)[n] & 0x1)) {
                 /* Region disabled */
                 continue;
             }
@@ -2042,7 +2086,9 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
                  * PMSAv7 where highest-numbered-region wins)
                  */
                 fi->type = ARMFault_Permission;
-                fi->level = 1;
+                if (arm_feature(env, ARM_FEATURE_M)) {
+                    fi->level = 1;
+                }
                 return true;
             }
 
@@ -2052,8 +2098,11 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
     }
 
     if (!hit) {
-        /* background fault */
-        fi->type = ARMFault_Background;
+        if (arm_feature(env, ARM_FEATURE_M)) {
+            fi->type = ARMFault_Background;
+        } else {
+            fi->type = ARMFault_Permission;
+        }
         return true;
     }
 
@@ -2061,12 +2110,14 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
         /* hit using the background region */
         get_phys_addr_pmsav7_default(env, mmu_idx, address, &result->f.prot);
     } else {
-        uint32_t ap = extract32(env->pmsav8.rbar[secure][matchregion], 1, 2);
-        uint32_t xn = extract32(env->pmsav8.rbar[secure][matchregion], 0, 1);
+        uint32_t matched_rbar = regime_rbar(env, mmu_idx, secure)[matchregion];
+        uint32_t matched_rlar = regime_rlar(env, mmu_idx, secure)[matchregion];
+        uint32_t ap = extract32(matched_rbar, 1, 2);
+        uint32_t xn = extract32(matched_rbar, 0, 1);
         bool pxn = false;
 
         if (arm_feature(env, ARM_FEATURE_V8_1M)) {
-            pxn = extract32(env->pmsav8.rlar[secure][matchregion], 4, 1);
+            pxn = extract32(matched_rlar, 4, 1);
         }
 
         if (m_is_system_region(env, address)) {
@@ -2074,21 +2125,46 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address,
             xn = 1;
         }
 
-        result->f.prot = simple_ap_to_rw_prot(env, mmu_idx, ap);
+        if (regime_el(env, mmu_idx) == 2) {
+            result->f.prot = simple_ap_to_rw_prot_is_user(ap,
+                                            mmu_idx != ARMMMUIdx_E2);
+        } else {
+            result->f.prot = simple_ap_to_rw_prot(env, mmu_idx, ap);
+        }
+
+        if (!arm_feature(env, ARM_FEATURE_M)) {
+            uint8_t attrindx = extract32(matched_rlar, 1, 3);
+            uint64_t mair = env->cp15.mair_el[regime_el(env, mmu_idx)];
+            uint8_t sh = extract32(matched_rlar, 3, 2);
+
+            if (regime_sctlr(env, mmu_idx) & SCTLR_WXN &&
+                result->f.prot & PAGE_WRITE && mmu_idx != ARMMMUIdx_Stage2) {
+                xn = 0x1;
+            }
+
+            if ((regime_el(env, mmu_idx) == 1) &&
+                regime_sctlr(env, mmu_idx) & SCTLR_UWXN && ap == 0x1) {
+                pxn = 0x1;
+            }
+
+            result->cacheattrs.is_s2_format = false;
+            result->cacheattrs.attrs = extract64(mair, attrindx * 8, 8);
+            result->cacheattrs.shareability = sh;
+        }
+
         if (result->f.prot && !xn && !(pxn && !is_user)) {
             result->f.prot |= PAGE_EXEC;
         }
-        /*
-         * We don't need to look the attribute up in the MAIR0/MAIR1
-         * registers because that only tells us about cacheability.
-         */
+
         if (mregion) {
             *mregion = matchregion;
         }
     }
 
     fi->type = ARMFault_Permission;
-    fi->level = 1;
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        fi->level = 1;
+    }
     return !(result->f.prot & (1 << access_type));
 }
 
@@ -2361,7 +2437,11 @@ static uint8_t combined_attrs_nofwb(uint64_t hcr,
 {
     uint8_t s1lo, s2lo, s1hi, s2hi, s2_mair_attrs, ret_attrs;
 
-    s2_mair_attrs = convert_stage2_attrs(hcr, s2.attrs);
+    if (s2.is_s2_format) {
+        s2_mair_attrs = convert_stage2_attrs(hcr, s2.attrs);
+    } else {
+        s2_mair_attrs = s2.attrs;
+    }
 
     s1lo = extract32(s1.attrs, 0, 4);
     s2lo = extract32(s2_mair_attrs, 0, 4);
@@ -2418,6 +2498,8 @@ static uint8_t force_cacheattr_nibble_wb(uint8_t attr)
  */
 static uint8_t combined_attrs_fwb(ARMCacheAttrs s1, ARMCacheAttrs s2)
 {
+    assert(s2.is_s2_format && !s1.is_s2_format);
+
     switch (s2.attrs) {
     case 7:
         /* Use stage 1 attributes */
@@ -2467,7 +2549,7 @@ static ARMCacheAttrs combine_cacheattrs(uint64_t hcr,
     ARMCacheAttrs ret;
     bool tagged = false;
 
-    assert(s2.is_s2_format && !s1.is_s2_format);
+    assert(!s1.is_s2_format);
     ret.is_s2_format = false;
 
     if (s1.attrs == 0xf0) {
@@ -2643,7 +2725,13 @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw,
     cacheattrs1 = result->cacheattrs;
     memset(result, 0, sizeof(*result));
 
-    ret = get_phys_addr_lpae(env, ptw, ipa, access_type, is_el0, result, fi);
+    if (arm_feature(env, ARM_FEATURE_PMSA)) {
+        ret = get_phys_addr_pmsav8(env, ipa, access_type,
+                                   ptw->in_mmu_idx, is_secure, result, fi);
+    } else {
+        ret = get_phys_addr_lpae(env, ptw, ipa, access_type,
+                                 is_el0, result, fi);
+    }
     fi->s2addr = ipa;
 
     /* Combine the S1 and S2 perms.  */
@@ -2655,10 +2743,20 @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw,
     }
 
     /*
-     * Use the maximum of the S1 & S2 page size, so that invalidation
-     * of pages > TARGET_PAGE_SIZE works correctly.
+     * If either S1 or S2 returned a result smaller than TARGET_PAGE_SIZE,
+     * this means "don't put this in the TLB"; in this case, return a
+     * result with lg_page_size == 0 to achieve that. Otherwise,
+     * use the maximum of the S1 & S2 page size, so that invalidation
+     * of pages > TARGET_PAGE_SIZE works correctly. (This works even though
+     * we know the combined result permissions etc only cover the minimum
+     * of the S1 and S2 page size, because we know that the common TLB code
+     * never actually creates TLB entries bigger than TARGET_PAGE_SIZE,
+     * and passing a larger page size value only affects invalidations.)
      */
-    if (result->f.lg_page_size < s1_lgpgsz) {
+    if (result->f.lg_page_size < TARGET_PAGE_BITS ||
+        s1_lgpgsz < TARGET_PAGE_BITS) {
+        result->f.lg_page_size = 0;
+    } else if (result->f.lg_page_size < s1_lgpgsz) {
         result->f.lg_page_size = s1_lgpgsz;
     }
 
diff --git a/target/arm/tlb_helper.c b/target/arm/tlb_helper.c
index 0f4f4fc809..60abcbebe6 100644
--- a/target/arm/tlb_helper.c
+++ b/target/arm/tlb_helper.c
@@ -19,6 +19,10 @@ bool regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx)
     if (el == 2 || arm_el_is_aa64(env, el)) {
         return true;
     }
+    if (arm_feature(env, ARM_FEATURE_PMSA) &&
+        arm_feature(env, ARM_FEATURE_V8)) {
+        return true;
+    }
     if (arm_feature(env, ARM_FEATURE_LPAE)
         && (regime_tcr(env, mmu_idx) & TTBCR_EAE)) {
         return true;
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 74a903072f..1dcaefb8e7 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -1184,7 +1184,7 @@ static inline void gen_hlt(DisasContext *s, int imm)
      * semihosting, to provide some semblance of security
      * (and for consistency with our 32-bit semihosting).
      */
-    if (semihosting_enabled(s->current_el != 0) &&
+    if (semihosting_enabled(s->current_el == 0) &&
         (imm == (s->thumb ? 0x3c : 0xf000))) {
         gen_exception_internal_insn(s, EXCP_SEMIHOST);
         return;
diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c
index 658ca4ff78..807037c586 100644
--- a/target/hexagon/cpu.c
+++ b/target/hexagon/cpu.c
@@ -86,7 +86,7 @@ static target_ulong adjust_stack_ptrs(CPUHexagonState *env, target_ulong addr)
     return addr;
 }
 
-/* HEX_REG_P3_0 (aka C4) is an alias for the predicate registers */
+/* HEX_REG_P3_0_ALIASED (aka C4) is an alias for the predicate registers */
 static target_ulong read_p3_0(CPUHexagonState *env)
 {
     int32_t control_reg = 0;
@@ -102,7 +102,7 @@ static void print_reg(FILE *f, CPUHexagonState *env, int regnum)
 {
     target_ulong value;
 
-    if (regnum == HEX_REG_P3_0) {
+    if (regnum == HEX_REG_P3_0_ALIASED) {
         value = read_p3_0(env);
     } else {
         value = regnum < 32 ? adjust_stack_ptrs(env, env->gpr[regnum])
@@ -198,7 +198,7 @@ static void hexagon_dump(CPUHexagonState *env, FILE *f, int flags)
     print_reg(f, env, HEX_REG_M0);
     print_reg(f, env, HEX_REG_M1);
     print_reg(f, env, HEX_REG_USR);
-    print_reg(f, env, HEX_REG_P3_0);
+    print_reg(f, env, HEX_REG_P3_0_ALIASED);
     print_reg(f, env, HEX_REG_GP);
     print_reg(f, env, HEX_REG_UGP);
     print_reg(f, env, HEX_REG_PC);
diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c
index 6cf2e0ed43..90db99024f 100644
--- a/target/hexagon/genptr.c
+++ b/target/hexagon/genptr.c
@@ -43,6 +43,33 @@ TCGv gen_read_preg(TCGv pred, uint8_t num)
     return pred;
 }
 
+#define IMMUTABLE (~0)
+
+static const target_ulong reg_immut_masks[TOTAL_PER_THREAD_REGS] = {
+    [HEX_REG_USR] = 0xc13000c0,
+    [HEX_REG_PC] = IMMUTABLE,
+    [HEX_REG_GP] = 0x3f,
+    [HEX_REG_UPCYCLELO] = IMMUTABLE,
+    [HEX_REG_UPCYCLEHI] = IMMUTABLE,
+    [HEX_REG_UTIMERLO] = IMMUTABLE,
+    [HEX_REG_UTIMERHI] = IMMUTABLE,
+};
+
+static inline void gen_masked_reg_write(TCGv new_val, TCGv cur_val,
+                                        target_ulong reg_mask)
+{
+    if (reg_mask) {
+        TCGv tmp = tcg_temp_new();
+
+        /* new_val = (new_val & ~reg_mask) | (cur_val & reg_mask) */
+        tcg_gen_andi_tl(new_val, new_val, ~reg_mask);
+        tcg_gen_andi_tl(tmp, cur_val, reg_mask);
+        tcg_gen_or_tl(new_val, new_val, tmp);
+
+        tcg_temp_free(tmp);
+    }
+}
+
 static inline void gen_log_predicated_reg_write(int rnum, TCGv val,
                                                 uint32_t slot)
 {
@@ -69,6 +96,9 @@ static inline void gen_log_predicated_reg_write(int rnum, TCGv val,
 
 void gen_log_reg_write(int rnum, TCGv val)
 {
+    const target_ulong reg_mask = reg_immut_masks[rnum];
+
+    gen_masked_reg_write(val, hex_gpr[rnum], reg_mask);
     tcg_gen_mov_tl(hex_new_value[rnum], val);
     if (HEX_DEBUG) {
         /* Do this so HELPER(debug_commit_end) will know */
@@ -114,19 +144,29 @@ static void gen_log_predicated_reg_write_pair(int rnum, TCGv_i64 val,
 
 static void gen_log_reg_write_pair(int rnum, TCGv_i64 val)
 {
+    const target_ulong reg_mask_low = reg_immut_masks[rnum];
+    const target_ulong reg_mask_high = reg_immut_masks[rnum + 1];
+    TCGv val32 = tcg_temp_new();
+
     /* Low word */
-    tcg_gen_extrl_i64_i32(hex_new_value[rnum], val);
+    tcg_gen_extrl_i64_i32(val32, val);
+    gen_masked_reg_write(val32, hex_gpr[rnum], reg_mask_low);
+    tcg_gen_mov_tl(hex_new_value[rnum], val32);
     if (HEX_DEBUG) {
         /* Do this so HELPER(debug_commit_end) will know */
         tcg_gen_movi_tl(hex_reg_written[rnum], 1);
     }
 
     /* High word */
-    tcg_gen_extrh_i64_i32(hex_new_value[rnum + 1], val);
+    tcg_gen_extrh_i64_i32(val32, val);
+    gen_masked_reg_write(val32, hex_gpr[rnum + 1], reg_mask_high);
+    tcg_gen_mov_tl(hex_new_value[rnum + 1], val32);
     if (HEX_DEBUG) {
         /* Do this so HELPER(debug_commit_end) will know */
         tcg_gen_movi_tl(hex_reg_written[rnum + 1], 1);
     }
+
+    tcg_temp_free(val32);
 }
 
 void gen_log_pred_write(DisasContext *ctx, int pnum, TCGv val)
@@ -163,7 +203,7 @@ static inline void gen_read_p3_0(TCGv control_reg)
 
 /*
  * Certain control registers require special handling on read
- *     HEX_REG_P3_0          aliased to the predicate registers
+ *     HEX_REG_P3_0_ALIASED  aliased to the predicate registers
  *                           -> concat the 4 predicate registers together
  *     HEX_REG_PC            actual value stored in DisasContext
  *                           -> assign from ctx->base.pc_next
@@ -173,7 +213,7 @@ static inline void gen_read_p3_0(TCGv control_reg)
 static inline void gen_read_ctrl_reg(DisasContext *ctx, const int reg_num,
                                      TCGv dest)
 {
-    if (reg_num == HEX_REG_P3_0) {
+    if (reg_num == HEX_REG_P3_0_ALIASED) {
         gen_read_p3_0(dest);
     } else if (reg_num == HEX_REG_PC) {
         tcg_gen_movi_tl(dest, ctx->base.pc_next);
@@ -194,7 +234,7 @@ static inline void gen_read_ctrl_reg(DisasContext *ctx, const int reg_num,
 static inline void gen_read_ctrl_reg_pair(DisasContext *ctx, const int reg_num,
                                           TCGv_i64 dest)
 {
-    if (reg_num == HEX_REG_P3_0) {
+    if (reg_num == HEX_REG_P3_0_ALIASED) {
         TCGv p3_0 = tcg_temp_new();
         gen_read_p3_0(p3_0);
         tcg_gen_concat_i32_i64(dest, p3_0, hex_gpr[reg_num + 1]);
@@ -238,7 +278,7 @@ static void gen_write_p3_0(DisasContext *ctx, TCGv control_reg)
 
 /*
  * Certain control registers require special handling on write
- *     HEX_REG_P3_0          aliased to the predicate registers
+ *     HEX_REG_P3_0_ALIASED  aliased to the predicate registers
  *                           -> break the value across 4 predicate registers
  *     HEX_REG_QEMU_*_CNT    changes in current TB in DisasContext
  *                            -> clear the changes
@@ -246,7 +286,7 @@ static void gen_write_p3_0(DisasContext *ctx, TCGv control_reg)
 static inline void gen_write_ctrl_reg(DisasContext *ctx, int reg_num,
                                       TCGv val)
 {
-    if (reg_num == HEX_REG_P3_0) {
+    if (reg_num == HEX_REG_P3_0_ALIASED) {
         gen_write_p3_0(ctx, val);
     } else {
         gen_log_reg_write(reg_num, val);
@@ -266,7 +306,7 @@ static inline void gen_write_ctrl_reg(DisasContext *ctx, int reg_num,
 static inline void gen_write_ctrl_reg_pair(DisasContext *ctx, int reg_num,
                                            TCGv_i64 val)
 {
-    if (reg_num == HEX_REG_P3_0) {
+    if (reg_num == HEX_REG_P3_0_ALIASED) {
         TCGv val32 = tcg_temp_new();
         tcg_gen_extrl_i64_i32(val32, val);
         gen_write_p3_0(ctx, val32);
diff --git a/target/hexagon/hex_regs.h b/target/hexagon/hex_regs.h
index a63c2c0fd5..bddfc28021 100644
--- a/target/hexagon/hex_regs.h
+++ b/target/hexagon/hex_regs.h
@@ -58,7 +58,7 @@ enum {
     HEX_REG_LC0              = 33,
     HEX_REG_SA1              = 34,
     HEX_REG_LC1              = 35,
-    HEX_REG_P3_0             = 36,
+    HEX_REG_P3_0_ALIASED     = 36,
     HEX_REG_M0               = 38,
     HEX_REG_M1               = 39,
     HEX_REG_USR              = 40,
diff --git a/target/hexagon/idef-parser/README.rst b/target/hexagon/idef-parser/README.rst
index 65e6bf4ee5..ff6d14150a 100644
--- a/target/hexagon/idef-parser/README.rst
+++ b/target/hexagon/idef-parser/README.rst
@@ -552,11 +552,11 @@ to compare our buggy CPU state against, running
 
 ::
 
-    meson configure -Dhexagon_idef_parser_enabled=false
+    meson configure -Dhexagon_idef_parser=false
 
 will disable the idef-parser for all instructions and fallback on manual
 tinycode generator overrides, or on helper function implementations. Recompiling
-gives us ``qemu-hexagon`` which passes all tests. If ``qemu-heaxgon-buggy`` is
+gives us ``qemu-hexagon`` which passes all tests. If ``qemu-hexagon-buggy`` is
 our binary with the incorrect tinycode generators, we can compare the CPU state
 between the two versions
 
diff --git a/target/hexagon/idef-parser/idef-parser.y b/target/hexagon/idef-parser/idef-parser.y
index 8be44a0ad1..c14cb39500 100644
--- a/target/hexagon/idef-parser/idef-parser.y
+++ b/target/hexagon/idef-parser/idef-parser.y
@@ -99,6 +99,8 @@
 /* Input file containing the description of each hexagon instruction */
 input : instructions
       {
+          /* Suppress warning about unused yynerrs */
+          (void) yynerrs;
           YYACCEPT;
       }
       ;
diff --git a/target/hexagon/meson.build b/target/hexagon/meson.build
index e8f250fcac..c9d31d095c 100644
--- a/target/hexagon/meson.build
+++ b/target/hexagon/meson.build
@@ -197,7 +197,6 @@ if idef_parser_enabled and 'hexagon-linux-user' in target_dirs
          idef_parser_dir / 'parser-helpers.c'],
         include_directories: ['idef-parser', '../../include/'],
         dependencies: [glib_dep],
-        c_args: ['-Wextra'],
         native: true
     )
 
diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c
index add4d54ae7..287659c74d 100644
--- a/target/ppc/excp_helper.c
+++ b/target/ppc/excp_helper.c
@@ -2163,22 +2163,13 @@ static int ppc_next_unmasked_interrupt(CPUPPCState *env)
 void ppc_maybe_interrupt(CPUPPCState *env)
 {
     CPUState *cs = env_cpu(env);
-    bool locked = false;
-
-    if (!qemu_mutex_iothread_locked()) {
-        locked = true;
-        qemu_mutex_lock_iothread();
-    }
+    QEMU_IOTHREAD_LOCK_GUARD();
 
     if (ppc_next_unmasked_interrupt(env)) {
         cpu_interrupt(cs, CPU_INTERRUPT_HARD);
     } else {
         cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
     }
-
-    if (locked) {
-        qemu_mutex_unlock_iothread();
-    }
 }
 
 #if defined(TARGET_PPC64)
diff --git a/target/ppc/helper_regs.c b/target/ppc/helper_regs.c
index c0aee5855b..779e7db513 100644
--- a/target/ppc/helper_regs.c
+++ b/target/ppc/helper_regs.c
@@ -22,6 +22,7 @@
 #include "qemu/main-loop.h"
 #include "exec/exec-all.h"
 #include "sysemu/kvm.h"
+#include "sysemu/tcg.h"
 #include "helper_regs.h"
 #include "power8-pmu.h"
 #include "cpu-models.h"
@@ -203,17 +204,10 @@ void cpu_interrupt_exittb(CPUState *cs)
 {
     /*
      * We don't need to worry about translation blocks
-     * when running with KVM.
+     * unless running with TCG.
      */
-    if (kvm_enabled()) {
-        return;
-    }
-
-    if (!qemu_mutex_iothread_locked()) {
-        qemu_mutex_lock_iothread();
-        cpu_interrupt(cs, CPU_INTERRUPT_EXITTB);
-        qemu_mutex_unlock_iothread();
-    } else {
+    if (tcg_enabled()) {
+        QEMU_IOTHREAD_LOCK_GUARD();
         cpu_interrupt(cs, CPU_INTERRUPT_EXITTB);
     }
 }
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index 6fe176e483..cc75ca7667 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -76,6 +76,7 @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zicsr, true, PRIV_VERSION_1_10_0, ext_icsr),
     ISA_EXT_DATA_ENTRY(zifencei, true, PRIV_VERSION_1_10_0, ext_ifencei),
     ISA_EXT_DATA_ENTRY(zihintpause, true, PRIV_VERSION_1_10_0, ext_zihintpause),
+    ISA_EXT_DATA_ENTRY(zawrs, true, PRIV_VERSION_1_12_0, ext_zawrs),
     ISA_EXT_DATA_ENTRY(zfh, true, PRIV_VERSION_1_12_0, ext_zfh),
     ISA_EXT_DATA_ENTRY(zfhmin, true, PRIV_VERSION_1_12_0, ext_zfhmin),
     ISA_EXT_DATA_ENTRY(zfinx, true, PRIV_VERSION_1_12_0, ext_zfinx),
@@ -382,6 +383,10 @@ static void riscv_cpu_dump_state(CPUState *cs, FILE *f, int flags)
             CSR_MHARTID,
             CSR_MSTATUS,
             CSR_MSTATUSH,
+            /*
+             * CSR_SSTATUS is intentionally omitted here as its value
+             * can be figured out by looking at CSR_MSTATUS
+             */
             CSR_HSTATUS,
             CSR_VSSTATUS,
             CSR_MIP,
@@ -762,6 +767,11 @@ static void riscv_cpu_realize(DeviceState *dev, Error **errp)
             return;
         }
 
+        if ((cpu->cfg.ext_zawrs) && !cpu->cfg.ext_a) {
+            error_setg(errp, "Zawrs extension requires A extension");
+            return;
+        }
+
         if ((cpu->cfg.ext_zfh || cpu->cfg.ext_zfhmin) && !cpu->cfg.ext_f) {
             error_setg(errp, "Zfh/Zfhmin extensions require F extension");
             return;
@@ -1017,6 +1027,7 @@ static Property riscv_cpu_extensions[] = {
     DEFINE_PROP_BOOL("Zifencei", RISCVCPU, cfg.ext_ifencei, true),
     DEFINE_PROP_BOOL("Zicsr", RISCVCPU, cfg.ext_icsr, true),
     DEFINE_PROP_BOOL("Zihintpause", RISCVCPU, cfg.ext_zihintpause, true),
+    DEFINE_PROP_BOOL("Zawrs", RISCVCPU, cfg.ext_zawrs, true),
     DEFINE_PROP_BOOL("Zfh", RISCVCPU, cfg.ext_zfh, false),
     DEFINE_PROP_BOOL("Zfhmin", RISCVCPU, cfg.ext_zfhmin, false),
     DEFINE_PROP_BOOL("Zve32f", RISCVCPU, cfg.ext_zve32f, false),
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 443d15a47c..f5609b62a2 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -329,6 +329,9 @@ struct CPUArchState {
     target_ulong tdata3[RV_MAX_TRIGGERS];
     struct CPUBreakpoint *cpu_breakpoint[RV_MAX_TRIGGERS];
     struct CPUWatchpoint *cpu_watchpoint[RV_MAX_TRIGGERS];
+    QEMUTimer *itrigger_timer[RV_MAX_TRIGGERS];
+    int64_t last_icount;
+    bool itrigger_enabled;
 
     /* machine specific rdtime callback */
     uint64_t (*rdtime_fn)(void *);
@@ -366,6 +369,9 @@ struct CPUArchState {
 
     /* CSRs for execution enviornment configuration */
     uint64_t menvcfg;
+    uint64_t mstateen[SMSTATEEN_MAX_COUNT];
+    uint64_t hstateen[SMSTATEEN_MAX_COUNT];
+    uint64_t sstateen[SMSTATEEN_MAX_COUNT];
     target_ulong senvcfg;
     uint64_t henvcfg;
 #endif
@@ -441,11 +447,13 @@ struct RISCVCPUConfig {
     bool ext_ifencei;
     bool ext_icsr;
     bool ext_zihintpause;
+    bool ext_smstateen;
     bool ext_sstc;
     bool ext_svinval;
     bool ext_svnapot;
     bool ext_svpbmt;
     bool ext_zdinx;
+    bool ext_zawrs;
     bool ext_zfh;
     bool ext_zfhmin;
     bool ext_zfinx;
@@ -621,6 +629,8 @@ FIELD(TB_FLAGS, PM_MASK_ENABLED, 22, 1)
 FIELD(TB_FLAGS, PM_BASE_ENABLED, 23, 1)
 FIELD(TB_FLAGS, VTA, 24, 1)
 FIELD(TB_FLAGS, VMA, 25, 1)
+/* Native debug itrigger */
+FIELD(TB_FLAGS, ITRIGGER, 26, 1)
 
 #ifdef TARGET_RISCV32
 #define riscv_cpu_mxl(env)  ((void)(env), MXL_RV32)
diff --git a/target/riscv/cpu_bits.h b/target/riscv/cpu_bits.h
index d8f5f0abed..8b0d7e20ea 100644
--- a/target/riscv/cpu_bits.h
+++ b/target/riscv/cpu_bits.h
@@ -197,6 +197,12 @@
 /* Supervisor Configuration CSRs */
 #define CSR_SENVCFG         0x10A
 
+/* Supervisor state CSRs */
+#define CSR_SSTATEEN0       0x10C
+#define CSR_SSTATEEN1       0x10D
+#define CSR_SSTATEEN2       0x10E
+#define CSR_SSTATEEN3       0x10F
+
 /* Supervisor Trap Handling */
 #define CSR_SSCRATCH        0x140
 #define CSR_SEPC            0x141
@@ -244,6 +250,16 @@
 #define CSR_HENVCFG         0x60A
 #define CSR_HENVCFGH        0x61A
 
+/* Hypervisor state CSRs */
+#define CSR_HSTATEEN0       0x60C
+#define CSR_HSTATEEN0H      0x61C
+#define CSR_HSTATEEN1       0x60D
+#define CSR_HSTATEEN1H      0x61D
+#define CSR_HSTATEEN2       0x60E
+#define CSR_HSTATEEN2H      0x61E
+#define CSR_HSTATEEN3       0x60F
+#define CSR_HSTATEEN3H      0x61F
+
 /* Virtual CSRs */
 #define CSR_VSSTATUS        0x200
 #define CSR_VSIE            0x204
@@ -289,6 +305,27 @@
 #define CSR_MENVCFG         0x30A
 #define CSR_MENVCFGH        0x31A
 
+/* Machine state CSRs */
+#define CSR_MSTATEEN0       0x30C
+#define CSR_MSTATEEN0H      0x31C
+#define CSR_MSTATEEN1       0x30D
+#define CSR_MSTATEEN1H      0x31D
+#define CSR_MSTATEEN2       0x30E
+#define CSR_MSTATEEN2H      0x31E
+#define CSR_MSTATEEN3       0x30F
+#define CSR_MSTATEEN3H      0x31F
+
+/* Common defines for all smstateen */
+#define SMSTATEEN_MAX_COUNT 4
+#define SMSTATEEN0_CS       (1ULL << 0)
+#define SMSTATEEN0_FCSR     (1ULL << 1)
+#define SMSTATEEN0_HSCONTXT (1ULL << 57)
+#define SMSTATEEN0_IMSIC    (1ULL << 58)
+#define SMSTATEEN0_AIA      (1ULL << 59)
+#define SMSTATEEN0_SVSLCT   (1ULL << 60)
+#define SMSTATEEN0_HSENVCFG (1ULL << 62)
+#define SMSTATEEN_STATEEN   (1ULL << 63)
+
 /* Enhanced Physical Memory Protection (ePMP) */
 #define CSR_MSECCFG         0x747
 #define CSR_MSECCFGH        0x757
diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index 278d163803..8ea3442b4a 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -27,7 +27,9 @@
 #include "tcg/tcg-op.h"
 #include "trace.h"
 #include "semihosting/common-semi.h"
+#include "sysemu/cpu-timers.h"
 #include "cpu_bits.h"
+#include "debug.h"
 
 int riscv_cpu_mmu_index(CPURISCVState *env, bool ifetch)
 {
@@ -103,6 +105,9 @@ void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc,
         flags = FIELD_DP32(flags, TB_FLAGS, MSTATUS_HS_VS,
                            get_field(env->mstatus_hs, MSTATUS_VS));
     }
+    if (riscv_feature(env, RISCV_FEATURE_DEBUG) && !icount_enabled()) {
+        flags = FIELD_DP32(flags, TB_FLAGS, ITRIGGER, env->itrigger_enabled);
+    }
 #endif
 
     flags = FIELD_DP32(flags, TB_FLAGS, XL, env->xl);
@@ -610,7 +615,6 @@ uint64_t riscv_cpu_update_mip(RISCVCPU *cpu, uint64_t mask, uint64_t value)
     CPURISCVState *env = &cpu->env;
     CPUState *cs = CPU(cpu);
     uint64_t gein, vsgein = 0, vstip = 0, old = env->mip;
-    bool locked = false;
 
     if (riscv_cpu_virt_enabled(env)) {
         gein = get_field(env->hstatus, HSTATUS_VGEIN);
@@ -621,10 +625,7 @@ uint64_t riscv_cpu_update_mip(RISCVCPU *cpu, uint64_t mask, uint64_t value)
     mask = ((mask == MIP_VSTIP) && env->vstime_irq) ? 0 : mask;
     vstip = env->vstime_irq ? MIP_VSTIP : 0;
 
-    if (!qemu_mutex_iothread_locked()) {
-        locked = true;
-        qemu_mutex_lock_iothread();
-    }
+    QEMU_IOTHREAD_LOCK_GUARD();
 
     env->mip = (env->mip & ~mask) | (value & mask);
 
@@ -634,10 +635,6 @@ uint64_t riscv_cpu_update_mip(RISCVCPU *cpu, uint64_t mask, uint64_t value)
         cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
     }
 
-    if (locked) {
-        qemu_mutex_unlock_iothread();
-    }
-
     return old;
 }
 
@@ -670,6 +667,9 @@ void riscv_cpu_set_mode(CPURISCVState *env, target_ulong newpriv)
     if (newpriv == PRV_H) {
         newpriv = PRV_U;
     }
+    if (icount_enabled() && newpriv != env->priv) {
+        riscv_itrigger_update_priv(env);
+    }
     /* tlb_flush is unnecessary as mode is contained in mmu_idx */
     env->priv = newpriv;
     env->xl = cpu_recompute_xl(env);
@@ -706,24 +706,26 @@ static int get_physical_address_pmp(CPURISCVState *env, int *prot,
                                     int mode)
 {
     pmp_priv_t pmp_priv;
-    target_ulong tlb_size_pmp = 0;
+    int pmp_index = -1;
 
     if (!riscv_feature(env, RISCV_FEATURE_PMP)) {
         *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
         return TRANSLATE_SUCCESS;
     }
 
-    if (!pmp_hart_has_privs(env, addr, size, 1 << access_type, &pmp_priv,
-                            mode)) {
+    pmp_index = pmp_hart_has_privs(env, addr, size, 1 << access_type,
+                                   &pmp_priv, mode);
+    if (pmp_index < 0) {
         *prot = 0;
         return TRANSLATE_PMP_FAIL;
     }
 
     *prot = pmp_priv_to_page_prot(pmp_priv);
-    if (tlb_size != NULL) {
-        if (pmp_is_range_in_tlb(env, addr & ~(*tlb_size - 1), &tlb_size_pmp)) {
-            *tlb_size = tlb_size_pmp;
-        }
+    if ((tlb_size != NULL) && pmp_index != MAX_RISCV_PMPS) {
+        target_ulong tlb_sa = addr & ~(TARGET_PAGE_SIZE - 1);
+        target_ulong tlb_ea = tlb_sa + TARGET_PAGE_SIZE - 1;
+
+        *tlb_size = pmp_get_tlb_size(env, pmp_index, tlb_sa, tlb_ea);
     }
 
     return TRANSLATE_SUCCESS;
@@ -1248,6 +1250,7 @@ bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
         }
     }
 
+    pmu_tlb_fill_incr_ctr(cpu, access_type);
     if (riscv_cpu_virt_enabled(env) ||
         ((riscv_cpu_two_stage_lookup(mmu_idx) || two_stage_lookup) &&
          access_type != MMU_INST_FETCH)) {
@@ -1311,7 +1314,6 @@ bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
             }
         }
     } else {
-        pmu_tlb_fill_incr_ctr(cpu, access_type);
         /* Single stage lookup */
         ret = get_physical_address(env, &pa, &prot, address, NULL,
                                    access_type, mmu_idx, true, false, false);
diff --git a/target/riscv/csr.c b/target/riscv/csr.c
index 5c9a7ee287..0db2c233e5 100644
--- a/target/riscv/csr.c
+++ b/target/riscv/csr.c
@@ -41,6 +41,42 @@ void riscv_set_csr_ops(int csrno, riscv_csr_operations *ops)
 }
 
 /* Predicates */
+#if !defined(CONFIG_USER_ONLY)
+static RISCVException smstateen_acc_ok(CPURISCVState *env, int index,
+                                       uint64_t bit)
+{
+    bool virt = riscv_cpu_virt_enabled(env);
+    CPUState *cs = env_cpu(env);
+    RISCVCPU *cpu = RISCV_CPU(cs);
+
+    if (env->priv == PRV_M || !cpu->cfg.ext_smstateen) {
+        return RISCV_EXCP_NONE;
+    }
+
+    if (!(env->mstateen[index] & bit)) {
+        return RISCV_EXCP_ILLEGAL_INST;
+    }
+
+    if (virt) {
+        if (!(env->hstateen[index] & bit)) {
+            return RISCV_EXCP_VIRT_INSTRUCTION_FAULT;
+        }
+
+        if (env->priv == PRV_U && !(env->sstateen[index] & bit)) {
+            return RISCV_EXCP_VIRT_INSTRUCTION_FAULT;
+        }
+    }
+
+    if (env->priv == PRV_U && riscv_has_ext(env, RVS)) {
+        if (!(env->sstateen[index] & bit)) {
+            return RISCV_EXCP_ILLEGAL_INST;
+        }
+    }
+
+    return RISCV_EXCP_NONE;
+}
+#endif
+
 static RISCVException fs(CPURISCVState *env, int csrno)
 {
 #if !defined(CONFIG_USER_ONLY)
@@ -283,6 +319,72 @@ static RISCVException umode32(CPURISCVState *env, int csrno)
     return umode(env, csrno);
 }
 
+static RISCVException mstateen(CPURISCVState *env, int csrno)
+{
+    CPUState *cs = env_cpu(env);
+    RISCVCPU *cpu = RISCV_CPU(cs);
+
+    if (!cpu->cfg.ext_smstateen) {
+        return RISCV_EXCP_ILLEGAL_INST;
+    }
+
+    return any(env, csrno);
+}
+
+static RISCVException hstateen_pred(CPURISCVState *env, int csrno, int base)
+{
+    CPUState *cs = env_cpu(env);
+    RISCVCPU *cpu = RISCV_CPU(cs);
+
+    if (!cpu->cfg.ext_smstateen) {
+        return RISCV_EXCP_ILLEGAL_INST;
+    }
+
+    if (env->priv < PRV_M) {
+        if (!(env->mstateen[csrno - base] & SMSTATEEN_STATEEN)) {
+            return RISCV_EXCP_ILLEGAL_INST;
+        }
+    }
+
+    return hmode(env, csrno);
+}
+
+static RISCVException hstateen(CPURISCVState *env, int csrno)
+{
+    return hstateen_pred(env, csrno, CSR_HSTATEEN0);
+}
+
+static RISCVException hstateenh(CPURISCVState *env, int csrno)
+{
+    return hstateen_pred(env, csrno, CSR_HSTATEEN0H);
+}
+
+static RISCVException sstateen(CPURISCVState *env, int csrno)
+{
+    bool virt = riscv_cpu_virt_enabled(env);
+    int index = csrno - CSR_SSTATEEN0;
+    CPUState *cs = env_cpu(env);
+    RISCVCPU *cpu = RISCV_CPU(cs);
+
+    if (!cpu->cfg.ext_smstateen) {
+        return RISCV_EXCP_ILLEGAL_INST;
+    }
+
+    if (env->priv < PRV_M) {
+        if (!(env->mstateen[index] & SMSTATEEN_STATEEN)) {
+            return RISCV_EXCP_ILLEGAL_INST;
+        }
+
+        if (virt) {
+            if (!(env->hstateen[index] & SMSTATEEN_STATEEN)) {
+                return RISCV_EXCP_VIRT_INSTRUCTION_FAULT;
+            }
+        }
+    }
+
+    return smode(env, csrno);
+}
+
 /* Checks if PointerMasking registers could be accessed */
 static RISCVException pointer_masking(CPURISCVState *env, int csrno)
 {
@@ -838,7 +940,7 @@ static RISCVException sstc(CPURISCVState *env, int csrno)
     }
 
     if (riscv_cpu_virt_enabled(env)) {
-        if (!(get_field(env->hcounteren, COUNTEREN_TM) &
+        if (!(get_field(env->hcounteren, COUNTEREN_TM) &&
               get_field(env->henvcfg, HENVCFG_STCE))) {
             return RISCV_EXCP_VIRT_INSTRUCTION_FAULT;
         }
@@ -1808,6 +1910,13 @@ static RISCVException write_menvcfgh(CPURISCVState *env, int csrno,
 static RISCVException read_senvcfg(CPURISCVState *env, int csrno,
                                  target_ulong *val)
 {
+    RISCVException ret;
+
+    ret = smstateen_acc_ok(env, 0, SMSTATEEN0_HSENVCFG);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
+
     *val = env->senvcfg;
     return RISCV_EXCP_NONE;
 }
@@ -1816,15 +1925,27 @@ static RISCVException write_senvcfg(CPURISCVState *env, int csrno,
                                   target_ulong val)
 {
     uint64_t mask = SENVCFG_FIOM | SENVCFG_CBIE | SENVCFG_CBCFE | SENVCFG_CBZE;
+    RISCVException ret;
 
-    env->senvcfg = (env->senvcfg & ~mask) | (val & mask);
+    ret = smstateen_acc_ok(env, 0, SMSTATEEN0_HSENVCFG);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
 
+    env->senvcfg = (env->senvcfg & ~mask) | (val & mask);
     return RISCV_EXCP_NONE;
 }
 
 static RISCVException read_henvcfg(CPURISCVState *env, int csrno,
                                  target_ulong *val)
 {
+    RISCVException ret;
+
+    ret = smstateen_acc_ok(env, 0, SMSTATEEN0_HSENVCFG);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
+
     *val = env->henvcfg;
     return RISCV_EXCP_NONE;
 }
@@ -1833,6 +1954,12 @@ static RISCVException write_henvcfg(CPURISCVState *env, int csrno,
                                   target_ulong val)
 {
     uint64_t mask = HENVCFG_FIOM | HENVCFG_CBIE | HENVCFG_CBCFE | HENVCFG_CBZE;
+    RISCVException ret;
+
+    ret = smstateen_acc_ok(env, 0, SMSTATEEN0_HSENVCFG);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
 
     if (riscv_cpu_mxl(env) == MXL_RV64) {
         mask |= HENVCFG_PBMTE | HENVCFG_STCE;
@@ -1846,6 +1973,13 @@ static RISCVException write_henvcfg(CPURISCVState *env, int csrno,
 static RISCVException read_henvcfgh(CPURISCVState *env, int csrno,
                                  target_ulong *val)
 {
+    RISCVException ret;
+
+    ret = smstateen_acc_ok(env, 0, SMSTATEEN0_HSENVCFG);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
+
     *val = env->henvcfg >> 32;
     return RISCV_EXCP_NONE;
 }
@@ -1855,12 +1989,208 @@ static RISCVException write_henvcfgh(CPURISCVState *env, int csrno,
 {
     uint64_t mask = HENVCFG_PBMTE | HENVCFG_STCE;
     uint64_t valh = (uint64_t)val << 32;
+    RISCVException ret;
+
+    ret = smstateen_acc_ok(env, 0, SMSTATEEN0_HSENVCFG);
+    if (ret != RISCV_EXCP_NONE) {
+        return ret;
+    }
 
     env->henvcfg = (env->henvcfg & ~mask) | (valh & mask);
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException read_mstateen(CPURISCVState *env, int csrno,
+                                    target_ulong *val)
+{
+    *val = env->mstateen[csrno - CSR_MSTATEEN0];
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_mstateen(CPURISCVState *env, int csrno,
+                                     uint64_t wr_mask, target_ulong new_val)
+{
+    uint64_t *reg;
+
+    reg = &env->mstateen[csrno - CSR_MSTATEEN0];
+    *reg = (*reg & ~wr_mask) | (new_val & wr_mask);
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_mstateen0(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    uint64_t wr_mask = SMSTATEEN_STATEEN | SMSTATEEN0_HSENVCFG;
+
+    return write_mstateen(env, csrno, wr_mask, new_val);
+}
+
+static RISCVException write_mstateen_1_3(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    return write_mstateen(env, csrno, SMSTATEEN_STATEEN, new_val);
+}
+
+static RISCVException read_mstateenh(CPURISCVState *env, int csrno,
+                                      target_ulong *val)
+{
+    *val = env->mstateen[csrno - CSR_MSTATEEN0H] >> 32;
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_mstateenh(CPURISCVState *env, int csrno,
+                                      uint64_t wr_mask, target_ulong new_val)
+{
+    uint64_t *reg, val;
+
+    reg = &env->mstateen[csrno - CSR_MSTATEEN0H];
+    val = (uint64_t)new_val << 32;
+    val |= *reg & 0xFFFFFFFF;
+    *reg = (*reg & ~wr_mask) | (val & wr_mask);
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_mstateen0h(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    uint64_t wr_mask = SMSTATEEN_STATEEN | SMSTATEEN0_HSENVCFG;
+
+    return write_mstateenh(env, csrno, wr_mask, new_val);
+}
+
+static RISCVException write_mstateenh_1_3(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    return write_mstateenh(env, csrno, SMSTATEEN_STATEEN, new_val);
+}
+
+static RISCVException read_hstateen(CPURISCVState *env, int csrno,
+                                    target_ulong *val)
+{
+    int index = csrno - CSR_HSTATEEN0;
+
+    *val = env->hstateen[index] & env->mstateen[index];
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_hstateen(CPURISCVState *env, int csrno,
+                                     uint64_t mask, target_ulong new_val)
+{
+    int index = csrno - CSR_HSTATEEN0;
+    uint64_t *reg, wr_mask;
+
+    reg = &env->hstateen[index];
+    wr_mask = env->mstateen[index] & mask;
+    *reg = (*reg & ~wr_mask) | (new_val & wr_mask);
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_hstateen0(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    uint64_t wr_mask = SMSTATEEN_STATEEN | SMSTATEEN0_HSENVCFG;
+
+    return write_hstateen(env, csrno, wr_mask, new_val);
+}
+
+static RISCVException write_hstateen_1_3(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    return write_hstateen(env, csrno, SMSTATEEN_STATEEN, new_val);
+}
+
+static RISCVException read_hstateenh(CPURISCVState *env, int csrno,
+                                     target_ulong *val)
+{
+    int index = csrno - CSR_HSTATEEN0H;
+
+    *val = (env->hstateen[index] >> 32) & (env->mstateen[index] >> 32);
 
     return RISCV_EXCP_NONE;
 }
 
+static RISCVException write_hstateenh(CPURISCVState *env, int csrno,
+                                      uint64_t mask, target_ulong new_val)
+{
+    int index = csrno - CSR_HSTATEEN0H;
+    uint64_t *reg, wr_mask, val;
+
+    reg = &env->hstateen[index];
+    val = (uint64_t)new_val << 32;
+    val |= *reg & 0xFFFFFFFF;
+    wr_mask = env->mstateen[index] & mask;
+    *reg = (*reg & ~wr_mask) | (val & wr_mask);
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_hstateen0h(CPURISCVState *env, int csrno,
+                                       target_ulong new_val)
+{
+    uint64_t wr_mask = SMSTATEEN_STATEEN | SMSTATEEN0_HSENVCFG;
+
+    return write_hstateenh(env, csrno, wr_mask, new_val);
+}
+
+static RISCVException write_hstateenh_1_3(CPURISCVState *env, int csrno,
+                                       target_ulong new_val)
+{
+    return write_hstateenh(env, csrno, SMSTATEEN_STATEEN, new_val);
+}
+
+static RISCVException read_sstateen(CPURISCVState *env, int csrno,
+                                    target_ulong *val)
+{
+    bool virt = riscv_cpu_virt_enabled(env);
+    int index = csrno - CSR_SSTATEEN0;
+
+    *val = env->sstateen[index] & env->mstateen[index];
+    if (virt) {
+        *val &= env->hstateen[index];
+    }
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_sstateen(CPURISCVState *env, int csrno,
+                                     uint64_t mask, target_ulong new_val)
+{
+    bool virt = riscv_cpu_virt_enabled(env);
+    int index = csrno - CSR_SSTATEEN0;
+    uint64_t wr_mask;
+    uint64_t *reg;
+
+    wr_mask = env->mstateen[index] & mask;
+    if (virt) {
+        wr_mask &= env->hstateen[index];
+    }
+
+    reg = &env->sstateen[index];
+    *reg = (*reg & ~wr_mask) | (new_val & wr_mask);
+
+    return RISCV_EXCP_NONE;
+}
+
+static RISCVException write_sstateen0(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    uint64_t wr_mask = SMSTATEEN_STATEEN | SMSTATEEN0_HSENVCFG;
+
+    return write_sstateen(env, csrno, wr_mask, new_val);
+}
+
+static RISCVException write_sstateen_1_3(CPURISCVState *env, int csrno,
+                                      target_ulong new_val)
+{
+    return write_sstateen(env, csrno, SMSTATEEN_STATEEN, new_val);
+}
+
 static RISCVException rmw_mip64(CPURISCVState *env, int csrno,
                                 uint64_t *ret_val,
                                 uint64_t new_val, uint64_t wr_mask)
@@ -3744,6 +4074,65 @@ riscv_csr_operations csr_ops[CSR_TABLE_SIZE] = {
     [CSR_HENVCFGH] = { "henvcfgh", hmode32, read_henvcfgh, write_henvcfgh,
                        .min_priv_ver = PRIV_VERSION_1_12_0              },
 
+    /* Smstateen extension CSRs */
+    [CSR_MSTATEEN0] = { "mstateen0", mstateen, read_mstateen, write_mstateen0,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN0H] = { "mstateen0h", mstateen, read_mstateenh,
+                          write_mstateen0h,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN1] = { "mstateen1", mstateen, read_mstateen,
+                        write_mstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN1H] = { "mstateen1h", mstateen, read_mstateenh,
+                         write_mstateenh_1_3,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN2] = { "mstateen2", mstateen, read_mstateen,
+                        write_mstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN2H] = { "mstateen2h", mstateen, read_mstateenh,
+                         write_mstateenh_1_3,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN3] = { "mstateen3", mstateen, read_mstateen,
+                        write_mstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_MSTATEEN3H] = { "mstateen3h", mstateen, read_mstateenh,
+                         write_mstateenh_1_3,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN0] = { "hstateen0", hstateen, read_hstateen, write_hstateen0,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN0H] = { "hstateen0h", hstateenh, read_hstateenh,
+                         write_hstateen0h,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN1] = { "hstateen1", hstateen, read_hstateen,
+                        write_hstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN1H] = { "hstateen1h", hstateenh, read_hstateenh,
+                         write_hstateenh_1_3,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN2] = { "hstateen2", hstateen, read_hstateen,
+                        write_hstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN2H] = { "hstateen2h", hstateenh, read_hstateenh,
+                         write_hstateenh_1_3,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN3] = { "hstateen3", hstateen, read_hstateen,
+                        write_hstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_HSTATEEN3H] = { "hstateen3h", hstateenh, read_hstateenh,
+                         write_hstateenh_1_3,
+                         .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_SSTATEEN0] = { "sstateen0", sstateen, read_sstateen, write_sstateen0,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_SSTATEEN1] = { "sstateen1", sstateen, read_sstateen,
+                        write_sstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_SSTATEEN2] = { "sstateen2", sstateen, read_sstateen,
+                        write_sstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+    [CSR_SSTATEEN3] = { "sstateen3", sstateen, read_sstateen,
+                        write_sstateen_1_3,
+                        .min_priv_ver = PRIV_VERSION_1_12_0 },
+
     /* Supervisor Trap Setup */
     [CSR_SSTATUS]    = { "sstatus",    smode, read_sstatus,    write_sstatus,
                          NULL,                read_sstatus_i128               },
diff --git a/target/riscv/debug.c b/target/riscv/debug.c
index e44848d0d7..bf4840a6a3 100644
--- a/target/riscv/debug.c
+++ b/target/riscv/debug.c
@@ -29,6 +29,8 @@
 #include "cpu.h"
 #include "trace.h"
 #include "exec/exec-all.h"
+#include "exec/helper-proto.h"
+#include "sysemu/cpu-timers.h"
 
 /*
  * The following M-mode trigger CSRs are implemented:
@@ -496,10 +498,209 @@ static void type6_reg_write(CPURISCVState *env, target_ulong index,
     return;
 }
 
+/* icount trigger type */
+static inline int
+itrigger_get_count(CPURISCVState *env, int index)
+{
+    return get_field(env->tdata1[index], ITRIGGER_COUNT);
+}
+
+static inline void
+itrigger_set_count(CPURISCVState *env, int index, int value)
+{
+    env->tdata1[index] = set_field(env->tdata1[index],
+                                   ITRIGGER_COUNT, value);
+}
+
+static bool check_itrigger_priv(CPURISCVState *env, int index)
+{
+    target_ulong tdata1 = env->tdata1[index];
+    if (riscv_cpu_virt_enabled(env)) {
+        /* check VU/VS bit against current privilege level */
+        return (get_field(tdata1, ITRIGGER_VS) == env->priv) ||
+               (get_field(tdata1, ITRIGGER_VU) == env->priv);
+    } else {
+        /* check U/S/M bit against current privilege level */
+        return (get_field(tdata1, ITRIGGER_M) == env->priv) ||
+               (get_field(tdata1, ITRIGGER_S) == env->priv) ||
+               (get_field(tdata1, ITRIGGER_U) == env->priv);
+    }
+}
+
+bool riscv_itrigger_enabled(CPURISCVState *env)
+{
+    int count;
+    for (int i = 0; i < RV_MAX_TRIGGERS; i++) {
+        if (get_trigger_type(env, i) != TRIGGER_TYPE_INST_CNT) {
+            continue;
+        }
+        if (check_itrigger_priv(env, i)) {
+            continue;
+        }
+        count = itrigger_get_count(env, i);
+        if (!count) {
+            continue;
+        }
+        return true;
+    }
+
+    return false;
+}
+
+void helper_itrigger_match(CPURISCVState *env)
+{
+    int count;
+    for (int i = 0; i < RV_MAX_TRIGGERS; i++) {
+        if (get_trigger_type(env, i) != TRIGGER_TYPE_INST_CNT) {
+            continue;
+        }
+        if (check_itrigger_priv(env, i)) {
+            continue;
+        }
+        count = itrigger_get_count(env, i);
+        if (!count) {
+            continue;
+        }
+        itrigger_set_count(env, i, count--);
+        if (!count) {
+            env->itrigger_enabled = riscv_itrigger_enabled(env);
+            do_trigger_action(env, i);
+        }
+    }
+}
+
+static void riscv_itrigger_update_count(CPURISCVState *env)
+{
+    int count, executed;
+    /*
+     * Record last icount, so that we can evaluate the executed instructions
+     * since last priviledge mode change or timer expire.
+     */
+    int64_t last_icount = env->last_icount, current_icount;
+    current_icount = env->last_icount = icount_get_raw();
+
+    for (int i = 0; i < RV_MAX_TRIGGERS; i++) {
+        if (get_trigger_type(env, i) != TRIGGER_TYPE_INST_CNT) {
+            continue;
+        }
+        count = itrigger_get_count(env, i);
+        if (!count) {
+            continue;
+        }
+        /*
+         * Only when priviledge is changed or itrigger timer expires,
+         * the count field in itrigger tdata1 register is updated.
+         * And the count field in itrigger only contains remaining value.
+         */
+        if (check_itrigger_priv(env, i)) {
+            /*
+             * If itrigger enabled in this priviledge mode, the number of
+             * executed instructions since last priviledge change
+             * should be reduced from current itrigger count.
+             */
+            executed = current_icount - last_icount;
+            itrigger_set_count(env, i, count - executed);
+            if (count == executed) {
+                do_trigger_action(env, i);
+            }
+        } else {
+            /*
+             * If itrigger is not enabled in this priviledge mode,
+             * the number of executed instructions will be discard and
+             * the count field in itrigger will not change.
+             */
+            timer_mod(env->itrigger_timer[i],
+                      current_icount + count);
+        }
+    }
+}
+
+static void riscv_itrigger_timer_cb(void *opaque)
+{
+    riscv_itrigger_update_count((CPURISCVState *)opaque);
+}
+
+void riscv_itrigger_update_priv(CPURISCVState *env)
+{
+    riscv_itrigger_update_count(env);
+}
+
+static target_ulong itrigger_validate(CPURISCVState *env,
+                                      target_ulong ctrl)
+{
+    target_ulong val;
+
+    /* validate the generic part first */
+    val = tdata1_validate(env, ctrl, TRIGGER_TYPE_INST_CNT);
+
+    /* validate unimplemented (always zero) bits */
+    warn_always_zero_bit(ctrl, ITRIGGER_ACTION, "action");
+    warn_always_zero_bit(ctrl, ITRIGGER_HIT, "hit");
+    warn_always_zero_bit(ctrl, ITRIGGER_PENDING, "pending");
+
+    /* keep the mode and attribute bits */
+    val |= ctrl & (ITRIGGER_VU | ITRIGGER_VS | ITRIGGER_U | ITRIGGER_S |
+                   ITRIGGER_M | ITRIGGER_COUNT);
+
+    return val;
+}
+
+static void itrigger_reg_write(CPURISCVState *env, target_ulong index,
+                               int tdata_index, target_ulong val)
+{
+    target_ulong new_val;
+
+    switch (tdata_index) {
+    case TDATA1:
+        /* set timer for icount */
+        new_val = itrigger_validate(env, val);
+        if (new_val != env->tdata1[index]) {
+            env->tdata1[index] = new_val;
+            if (icount_enabled()) {
+                env->last_icount = icount_get_raw();
+                /* set the count to timer */
+                timer_mod(env->itrigger_timer[index],
+                          env->last_icount + itrigger_get_count(env, index));
+            } else {
+                env->itrigger_enabled = riscv_itrigger_enabled(env);
+            }
+        }
+        break;
+    case TDATA2:
+        qemu_log_mask(LOG_UNIMP,
+                      "tdata2 is not supported for icount trigger\n");
+        break;
+    case TDATA3:
+        qemu_log_mask(LOG_UNIMP,
+                      "tdata3 is not supported for icount trigger\n");
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    return;
+}
+
+static int itrigger_get_adjust_count(CPURISCVState *env)
+{
+    int count = itrigger_get_count(env, env->trigger_cur), executed;
+    if ((count != 0) && check_itrigger_priv(env, env->trigger_cur)) {
+        executed = icount_get_raw() - env->last_icount;
+        count += executed;
+    }
+    return count;
+}
+
 target_ulong tdata_csr_read(CPURISCVState *env, int tdata_index)
 {
+    int trigger_type;
     switch (tdata_index) {
     case TDATA1:
+        trigger_type = extract_trigger_type(env, env->tdata1[env->trigger_cur]);
+        if ((trigger_type == TRIGGER_TYPE_INST_CNT) && icount_enabled()) {
+            return deposit64(env->tdata1[env->trigger_cur], 10, 14,
+                             itrigger_get_adjust_count(env));
+        }
         return env->tdata1[env->trigger_cur];
     case TDATA2:
         return env->tdata2[env->trigger_cur];
@@ -528,6 +729,8 @@ void tdata_csr_write(CPURISCVState *env, int tdata_index, target_ulong val)
         type6_reg_write(env, env->trigger_cur, tdata_index, val);
         break;
     case TRIGGER_TYPE_INST_CNT:
+        itrigger_reg_write(env, env->trigger_cur, tdata_index, val);
+        break;
     case TRIGGER_TYPE_INT:
     case TRIGGER_TYPE_EXCP:
     case TRIGGER_TYPE_EXT_SRC:
@@ -725,5 +928,7 @@ void riscv_trigger_init(CPURISCVState *env)
         env->tdata3[i] = 0;
         env->cpu_breakpoint[i] = NULL;
         env->cpu_watchpoint[i] = NULL;
+        env->itrigger_timer[i] = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                              riscv_itrigger_timer_cb, env);
     }
 }
diff --git a/target/riscv/debug.h b/target/riscv/debug.h
index a1226b4d29..c471748d5a 100644
--- a/target/riscv/debug.h
+++ b/target/riscv/debug.h
@@ -118,6 +118,17 @@ enum {
     SIZE_NUM = 16
 };
 
+/* itrigger filed masks */
+#define ITRIGGER_ACTION       0x3f
+#define ITRIGGER_U            BIT(6)
+#define ITRIGGER_S            BIT(7)
+#define ITRIGGER_PENDING      BIT(8)
+#define ITRIGGER_M            BIT(9)
+#define ITRIGGER_COUNT        (0x3fff << 10)
+#define ITRIGGER_HIT          BIT(24)
+#define ITRIGGER_VU           BIT(25)
+#define ITRIGGER_VS           BIT(26)
+
 bool tdata_available(CPURISCVState *env, int tdata_index);
 
 target_ulong tselect_csr_read(CPURISCVState *env);
@@ -134,4 +145,6 @@ bool riscv_cpu_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp);
 
 void riscv_trigger_init(CPURISCVState *env);
 
+bool riscv_itrigger_enabled(CPURISCVState *env);
+void riscv_itrigger_update_priv(CPURISCVState *env);
 #endif /* RISCV_DEBUG_H */
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index a03014fe67..227c7122ef 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -109,6 +109,8 @@ DEF_HELPER_1(sret, tl, env)
 DEF_HELPER_1(mret, tl, env)
 DEF_HELPER_1(wfi, void, env)
 DEF_HELPER_1(tlb_flush, void, env)
+/* Native Debug */
+DEF_HELPER_1(itrigger_match, void, env)
 #endif
 
 /* Hypervisor functions */
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index d0253b8104..b7e7613ea2 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -718,6 +718,10 @@ vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm11
 vsetivli        11 .......... ..... 111 ..... 1010111  @r2_zimm10
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
 
+# *** Zawrs Standard Extension ***
+wrs_nto    000000001101 00000 000 00000 1110011
+wrs_sto    000000011101 00000 000 00000 1110011
+
 # *** RV32 Zba Standard Extension ***
 sh1add     0010000 .......... 010 ..... 0110011 @r
 sh2add     0010000 .......... 100 ..... 0110011 @r
diff --git a/target/riscv/insn_trans/trans_privileged.c.inc b/target/riscv/insn_trans/trans_privileged.c.inc
index 3281408a87..59501b2780 100644
--- a/target/riscv/insn_trans/trans_privileged.c.inc
+++ b/target/riscv/insn_trans/trans_privileged.c.inc
@@ -78,7 +78,7 @@ static bool trans_sret(DisasContext *ctx, arg_sret *a)
     if (has_ext(ctx, RVS)) {
         decode_save_opc(ctx);
         gen_helper_sret(cpu_pc, cpu_env);
-        tcg_gen_exit_tb(NULL, 0); /* no chaining */
+        exit_tb(ctx); /* no chaining */
         ctx->base.is_jmp = DISAS_NORETURN;
     } else {
         return false;
@@ -94,7 +94,7 @@ static bool trans_mret(DisasContext *ctx, arg_mret *a)
 #ifndef CONFIG_USER_ONLY
     decode_save_opc(ctx);
     gen_helper_mret(cpu_pc, cpu_env);
-    tcg_gen_exit_tb(NULL, 0); /* no chaining */
+    exit_tb(ctx); /* no chaining */
     ctx->base.is_jmp = DISAS_NORETURN;
     return true;
 #else
diff --git a/target/riscv/insn_trans/trans_rvi.c.inc b/target/riscv/insn_trans/trans_rvi.c.inc
index c49dbec0eb..5c69b88d1e 100644
--- a/target/riscv/insn_trans/trans_rvi.c.inc
+++ b/target/riscv/insn_trans/trans_rvi.c.inc
@@ -66,7 +66,7 @@ static bool trans_jalr(DisasContext *ctx, arg_jalr *a)
     }
 
     gen_set_gpri(ctx, a->rd, ctx->pc_succ_insn);
-    tcg_gen_lookup_and_goto_ptr();
+    lookup_and_goto_ptr(ctx);
 
     if (misaligned) {
         gen_set_label(misaligned);
@@ -803,7 +803,7 @@ static bool trans_pause(DisasContext *ctx, arg_pause *a)
      * end the TB and return to main loop
      */
     gen_set_pc_imm(ctx, ctx->pc_succ_insn);
-    tcg_gen_exit_tb(NULL, 0);
+    exit_tb(ctx);
     ctx->base.is_jmp = DISAS_NORETURN;
 
     return true;
@@ -827,7 +827,7 @@ static bool trans_fence_i(DisasContext *ctx, arg_fence_i *a)
      * however we need to end the translation block
      */
     gen_set_pc_imm(ctx, ctx->pc_succ_insn);
-    tcg_gen_exit_tb(NULL, 0);
+    exit_tb(ctx);
     ctx->base.is_jmp = DISAS_NORETURN;
     return true;
 }
@@ -838,7 +838,7 @@ static bool do_csr_post(DisasContext *ctx)
     decode_save_opc(ctx);
     /* We may have changed important cpu state -- exit to main loop. */
     gen_set_pc_imm(ctx, ctx->pc_succ_insn);
-    tcg_gen_exit_tb(NULL, 0);
+    exit_tb(ctx);
     ctx->base.is_jmp = DISAS_NORETURN;
     return true;
 }
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 4dea4413ae..d455acedbf 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -196,7 +196,7 @@ static bool do_vsetvl(DisasContext *s, int rd, int rs1, TCGv s2)
     mark_vs_dirty(s);
 
     gen_set_pc_imm(s, s->pc_succ_insn);
-    tcg_gen_lookup_and_goto_ptr();
+    lookup_and_goto_ptr(s);
     s->base.is_jmp = DISAS_NORETURN;
 
     if (rd == 0 && rs1 == 0) {
@@ -222,7 +222,7 @@ static bool do_vsetivli(DisasContext *s, int rd, TCGv s1, TCGv s2)
     gen_set_gpr(s, rd, dst);
     mark_vs_dirty(s);
     gen_set_pc_imm(s, s->pc_succ_insn);
-    tcg_gen_lookup_and_goto_ptr();
+    lookup_and_goto_ptr(s);
     s->base.is_jmp = DISAS_NORETURN;
 
     return true;
diff --git a/target/riscv/insn_trans/trans_rvzawrs.c.inc b/target/riscv/insn_trans/trans_rvzawrs.c.inc
new file mode 100644
index 0000000000..8254e7dfe2
--- /dev/null
+++ b/target/riscv/insn_trans/trans_rvzawrs.c.inc
@@ -0,0 +1,51 @@
+/*
+ * RISC-V translation routines for the RISC-V Zawrs Extension.
+ *
+ * Copyright (c) 2022 Christoph Muellner, christoph.muellner@vrull.io
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2 or later, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+static bool trans_wrs(DisasContext *ctx)
+{
+    if (!ctx->cfg_ptr->ext_zawrs) {
+        return false;
+    }
+
+    /*
+     * The specification says:
+     * While stalled, an implementation is permitted to occasionally
+     * terminate the stall and complete execution for any reason.
+     *
+     * So let's just exit TB and return to the main loop.
+     */
+
+    /* Clear the load reservation  (if any).  */
+    tcg_gen_movi_tl(load_res, -1);
+
+    gen_set_pc_imm(ctx, ctx->pc_succ_insn);
+    tcg_gen_exit_tb(NULL, 0);
+    ctx->base.is_jmp = DISAS_NORETURN;
+
+    return true;
+}
+
+#define GEN_TRANS_WRS(insn)                                     \
+static bool trans_ ## insn(DisasContext *ctx, arg_ ## insn *a)  \
+{                                                               \
+    (void)a;                                                    \
+    return trans_wrs(ctx);                                      \
+}
+
+GEN_TRANS_WRS(wrs_nto)
+GEN_TRANS_WRS(wrs_sto)
diff --git a/target/riscv/machine.c b/target/riscv/machine.c
index c2a94a82b3..65a8549ec2 100644
--- a/target/riscv/machine.c
+++ b/target/riscv/machine.c
@@ -21,6 +21,8 @@
 #include "qemu/error-report.h"
 #include "sysemu/kvm.h"
 #include "migration/cpu.h"
+#include "sysemu/cpu-timers.h"
+#include "debug.h"
 
 static bool pmp_needed(void *opaque)
 {
@@ -229,11 +231,24 @@ static bool debug_needed(void *opaque)
     return riscv_feature(env, RISCV_FEATURE_DEBUG);
 }
 
+static int debug_post_load(void *opaque, int version_id)
+{
+    RISCVCPU *cpu = opaque;
+    CPURISCVState *env = &cpu->env;
+
+    if (icount_enabled()) {
+        env->itrigger_enabled = riscv_itrigger_enabled(env);
+    }
+
+    return 0;
+}
+
 static const VMStateDescription vmstate_debug = {
     .name = "cpu/debug",
     .version_id = 2,
     .minimum_version_id = 2,
     .needed = debug_needed,
+    .post_load = debug_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINTTL(env.trigger_cur, RISCVCPU),
         VMSTATE_UINTTL_ARRAY(env.tdata1, RISCVCPU, RV_MAX_TRIGGERS),
@@ -253,6 +268,26 @@ static int riscv_cpu_post_load(void *opaque, int version_id)
     return 0;
 }
 
+static bool smstateen_needed(void *opaque)
+{
+    RISCVCPU *cpu = opaque;
+
+    return cpu->cfg.ext_smstateen;
+}
+
+static const VMStateDescription vmstate_smstateen = {
+    .name = "cpu/smtateen",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = smstateen_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64_ARRAY(env.mstateen, RISCVCPU, 4),
+        VMSTATE_UINT64_ARRAY(env.hstateen, RISCVCPU, 4),
+        VMSTATE_UINT64_ARRAY(env.sstateen, RISCVCPU, 4),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static bool envcfg_needed(void *opaque)
 {
     RISCVCPU *cpu = opaque;
@@ -364,6 +399,7 @@ const VMStateDescription vmstate_riscv_cpu = {
         &vmstate_kvmtimer,
         &vmstate_envcfg,
         &vmstate_debug,
+        &vmstate_smstateen,
         NULL
     }
 };
diff --git a/target/riscv/op_helper.c b/target/riscv/op_helper.c
index 09f1f5185d..878bcb03b8 100644
--- a/target/riscv/op_helper.c
+++ b/target/riscv/op_helper.c
@@ -149,21 +149,24 @@ target_ulong helper_sret(CPURISCVState *env)
     }
 
     mstatus = env->mstatus;
+    prev_priv = get_field(mstatus, MSTATUS_SPP);
+    mstatus = set_field(mstatus, MSTATUS_SIE,
+                        get_field(mstatus, MSTATUS_SPIE));
+    mstatus = set_field(mstatus, MSTATUS_SPIE, 1);
+    mstatus = set_field(mstatus, MSTATUS_SPP, PRV_U);
+    if (env->priv_ver >= PRIV_VERSION_1_12_0) {
+        mstatus = set_field(mstatus, MSTATUS_MPRV, 0);
+    }
+    env->mstatus = mstatus;
 
     if (riscv_has_ext(env, RVH) && !riscv_cpu_virt_enabled(env)) {
         /* We support Hypervisor extensions and virtulisation is disabled */
         target_ulong hstatus = env->hstatus;
 
-        prev_priv = get_field(mstatus, MSTATUS_SPP);
         prev_virt = get_field(hstatus, HSTATUS_SPV);
 
         hstatus = set_field(hstatus, HSTATUS_SPV, 0);
-        mstatus = set_field(mstatus, MSTATUS_SPP, 0);
-        mstatus = set_field(mstatus, SSTATUS_SIE,
-                            get_field(mstatus, SSTATUS_SPIE));
-        mstatus = set_field(mstatus, SSTATUS_SPIE, 1);
 
-        env->mstatus = mstatus;
         env->hstatus = hstatus;
 
         if (prev_virt) {
@@ -171,14 +174,6 @@ target_ulong helper_sret(CPURISCVState *env)
         }
 
         riscv_cpu_set_virt_enabled(env, prev_virt);
-    } else {
-        prev_priv = get_field(mstatus, MSTATUS_SPP);
-
-        mstatus = set_field(mstatus, MSTATUS_SIE,
-                            get_field(mstatus, MSTATUS_SPIE));
-        mstatus = set_field(mstatus, MSTATUS_SPIE, 1);
-        mstatus = set_field(mstatus, MSTATUS_SPP, PRV_U);
-        env->mstatus = mstatus;
     }
 
     riscv_cpu_set_mode(env, prev_priv);
@@ -202,7 +197,7 @@ target_ulong helper_mret(CPURISCVState *env)
 
     if (riscv_feature(env, RISCV_FEATURE_PMP) &&
         !pmp_get_num_rules(env) && (prev_priv != PRV_M)) {
-        riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
+        riscv_raise_exception(env, RISCV_EXCP_INST_ACCESS_FAULT, GETPC());
     }
 
     target_ulong prev_virt = get_field(env->mstatus, MSTATUS_MPV);
@@ -211,6 +206,9 @@ target_ulong helper_mret(CPURISCVState *env)
     mstatus = set_field(mstatus, MSTATUS_MPIE, 1);
     mstatus = set_field(mstatus, MSTATUS_MPP, PRV_U);
     mstatus = set_field(mstatus, MSTATUS_MPV, 0);
+    if ((env->priv_ver >= PRIV_VERSION_1_12_0) && (prev_priv != PRV_M)) {
+        mstatus = set_field(mstatus, MSTATUS_MPRV, 0);
+    }
     env->mstatus = mstatus;
     riscv_cpu_set_mode(env, prev_priv);
 
diff --git a/target/riscv/pmp.c b/target/riscv/pmp.c
index 2b43e399b8..d1126a6066 100644
--- a/target/riscv/pmp.c
+++ b/target/riscv/pmp.c
@@ -292,8 +292,11 @@ static bool pmp_hart_has_privs_default(CPURISCVState *env, target_ulong addr,
 
 /*
  * Check if the address has required RWX privs to complete desired operation
+ * Return PMP rule index if a pmp rule match
+ * Return MAX_RISCV_PMPS if default match
+ * Return negtive value if no match
  */
-bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
+int pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
     target_ulong size, pmp_priv_t privs, pmp_priv_t *allowed_privs,
     target_ulong mode)
 {
@@ -305,8 +308,10 @@ bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
 
     /* Short cut if no rules */
     if (0 == pmp_get_num_rules(env)) {
-        return pmp_hart_has_privs_default(env, addr, size, privs,
-                                          allowed_privs, mode);
+        if (pmp_hart_has_privs_default(env, addr, size, privs,
+                                       allowed_privs, mode)) {
+            ret = MAX_RISCV_PMPS;
+        }
     }
 
     if (size == 0) {
@@ -333,7 +338,7 @@ bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
         if ((s + e) == 1) {
             qemu_log_mask(LOG_GUEST_ERROR,
                           "pmp violation - access is partially inside\n");
-            ret = 0;
+            ret = -1;
             break;
         }
 
@@ -436,18 +441,22 @@ bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
                 }
             }
 
-            ret = ((privs & *allowed_privs) == privs);
+            if ((privs & *allowed_privs) == privs) {
+                ret = i;
+            }
             break;
         }
     }
 
     /* No rule matched */
     if (ret == -1) {
-        return pmp_hart_has_privs_default(env, addr, size, privs,
-                                          allowed_privs, mode);
+        if (pmp_hart_has_privs_default(env, addr, size, privs,
+                                       allowed_privs, mode)) {
+            ret = MAX_RISCV_PMPS;
+        }
     }
 
-    return ret == 1 ? true : false;
+    return ret;
 }
 
 /*
@@ -586,64 +595,25 @@ target_ulong mseccfg_csr_read(CPURISCVState *env)
  * Calculate the TLB size if the start address or the end address of
  * PMP entry is presented in the TLB page.
  */
-static target_ulong pmp_get_tlb_size(CPURISCVState *env, int pmp_index,
-                                     target_ulong tlb_sa, target_ulong tlb_ea)
+target_ulong pmp_get_tlb_size(CPURISCVState *env, int pmp_index,
+                              target_ulong tlb_sa, target_ulong tlb_ea)
 {
     target_ulong pmp_sa = env->pmp_state.addr[pmp_index].sa;
     target_ulong pmp_ea = env->pmp_state.addr[pmp_index].ea;
 
-    if (pmp_sa >= tlb_sa && pmp_ea <= tlb_ea) {
-        return pmp_ea - pmp_sa + 1;
-    }
-
-    if (pmp_sa >= tlb_sa && pmp_sa <= tlb_ea && pmp_ea >= tlb_ea) {
-        return tlb_ea - pmp_sa + 1;
-    }
-
-    if (pmp_ea <= tlb_ea && pmp_ea >= tlb_sa && pmp_sa <= tlb_sa) {
-        return pmp_ea - tlb_sa + 1;
-    }
-
-    return 0;
-}
-
-/*
- * Check is there a PMP entry which range covers this page. If so,
- * try to find the minimum granularity for the TLB size.
- */
-bool pmp_is_range_in_tlb(CPURISCVState *env, hwaddr tlb_sa,
-                         target_ulong *tlb_size)
-{
-    int i;
-    target_ulong val;
-    target_ulong tlb_ea = (tlb_sa + TARGET_PAGE_SIZE - 1);
-
-    for (i = 0; i < MAX_RISCV_PMPS; i++) {
-        val = pmp_get_tlb_size(env, i, tlb_sa, tlb_ea);
-        if (val) {
-            if (*tlb_size == 0 || *tlb_size > val) {
-                *tlb_size = val;
-            }
-        }
-    }
-
-    if (*tlb_size != 0) {
+    if (pmp_sa <= tlb_sa && pmp_ea >= tlb_ea) {
+        return TARGET_PAGE_SIZE;
+    } else {
         /*
-         * At this point we have a tlb_size that is the smallest possible size
-         * That fits within a TARGET_PAGE_SIZE and the PMP region.
-         *
-         * If the size is less then TARGET_PAGE_SIZE we drop the size to 1.
-         * This means the result isn't cached in the TLB and is only used for
-         * a single translation.
-         */
-        if (*tlb_size < TARGET_PAGE_SIZE) {
-            *tlb_size = 1;
-        }
-
-        return true;
+        * At this point we have a tlb_size that is the smallest possible size
+        * That fits within a TARGET_PAGE_SIZE and the PMP region.
+        *
+        * If the size is less then TARGET_PAGE_SIZE we drop the size to 1.
+        * This means the result isn't cached in the TLB and is only used for
+        * a single translation.
+        */
+        return 1;
     }
-
-    return false;
 }
 
 /*
diff --git a/target/riscv/pmp.h b/target/riscv/pmp.h
index a8dd797476..da32c61c85 100644
--- a/target/riscv/pmp.h
+++ b/target/riscv/pmp.h
@@ -72,11 +72,11 @@ target_ulong mseccfg_csr_read(CPURISCVState *env);
 void pmpaddr_csr_write(CPURISCVState *env, uint32_t addr_index,
     target_ulong val);
 target_ulong pmpaddr_csr_read(CPURISCVState *env, uint32_t addr_index);
-bool pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
+int pmp_hart_has_privs(CPURISCVState *env, target_ulong addr,
     target_ulong size, pmp_priv_t privs, pmp_priv_t *allowed_privs,
     target_ulong mode);
-bool pmp_is_range_in_tlb(CPURISCVState *env, hwaddr tlb_sa,
-                         target_ulong *tlb_size);
+target_ulong pmp_get_tlb_size(CPURISCVState *env, int pmp_index,
+                              target_ulong tlb_sa, target_ulong tlb_ea);
 void pmp_update_rule_addr(CPURISCVState *env, uint32_t pmp_index);
 void pmp_update_rule_nums(CPURISCVState *env);
 uint32_t pmp_get_num_rules(CPURISCVState *env);
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index db123da5ec..df38db7553 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -76,6 +76,7 @@ typedef struct DisasContext {
        to reset this known value.  */
     int frm;
     RISCVMXL ol;
+    bool virt_inst_excp;
     bool virt_enabled;
     const RISCVCPUConfig *cfg_ptr;
     bool hlsx;
@@ -111,6 +112,8 @@ typedef struct DisasContext {
     /* PointerMasking extension */
     bool pm_mask_enabled;
     bool pm_base_enabled;
+    /* Use icount trigger for native debug */
+    bool itrigger;
     /* TCG of the current insn_start */
     TCGOp *insn_start;
 } DisasContext;
@@ -243,7 +246,11 @@ static void gen_exception_illegal(DisasContext *ctx)
 {
     tcg_gen_st_i32(tcg_constant_i32(ctx->opcode), cpu_env,
                    offsetof(CPURISCVState, bins));
-    generate_exception(ctx, RISCV_EXCP_ILLEGAL_INST);
+    if (ctx->virt_inst_excp) {
+        generate_exception(ctx, RISCV_EXCP_VIRT_INSTRUCTION_FAULT);
+    } else {
+        generate_exception(ctx, RISCV_EXCP_ILLEGAL_INST);
+    }
 }
 
 static void gen_exception_inst_addr_mis(DisasContext *ctx)
@@ -252,15 +259,39 @@ static void gen_exception_inst_addr_mis(DisasContext *ctx)
     generate_exception(ctx, RISCV_EXCP_INST_ADDR_MIS);
 }
 
+static void lookup_and_goto_ptr(DisasContext *ctx)
+{
+#ifndef CONFIG_USER_ONLY
+    if (ctx->itrigger) {
+        gen_helper_itrigger_match(cpu_env);
+    }
+#endif
+    tcg_gen_lookup_and_goto_ptr();
+}
+
+static void exit_tb(DisasContext *ctx)
+{
+#ifndef CONFIG_USER_ONLY
+    if (ctx->itrigger) {
+        gen_helper_itrigger_match(cpu_env);
+    }
+#endif
+    tcg_gen_exit_tb(NULL, 0);
+}
+
 static void gen_goto_tb(DisasContext *ctx, int n, target_ulong dest)
 {
-    if (translator_use_goto_tb(&ctx->base, dest)) {
+     /*
+      * Under itrigger, instruction executes one by one like singlestep,
+      * direct block chain benefits will be small.
+      */
+    if (translator_use_goto_tb(&ctx->base, dest) && !ctx->itrigger) {
         tcg_gen_goto_tb(n);
         gen_set_pc_imm(ctx, dest);
         tcg_gen_exit_tb(ctx->base.tb, n);
     } else {
         gen_set_pc_imm(ctx, dest);
-        tcg_gen_lookup_and_goto_ptr();
+        lookup_and_goto_ptr(ctx);
     }
 }
 
@@ -1029,6 +1060,7 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc)
 #include "insn_trans/trans_rvh.c.inc"
 #include "insn_trans/trans_rvv.c.inc"
 #include "insn_trans/trans_rvb.c.inc"
+#include "insn_trans/trans_rvzawrs.c.inc"
 #include "insn_trans/trans_rvzfh.c.inc"
 #include "insn_trans/trans_rvk.c.inc"
 #include "insn_trans/trans_privileged.c.inc"
@@ -1062,16 +1094,13 @@ static void decode_opc(CPURISCVState *env, DisasContext *ctx, uint16_t opcode)
         { has_XVentanaCondOps_p,  decode_XVentanaCodeOps },
     };
 
+    ctx->virt_inst_excp = false;
     /* Check for compressed insn */
     if (insn_len(opcode) == 2) {
-        if (!has_ext(ctx, RVC)) {
-            gen_exception_illegal(ctx);
-        } else {
-            ctx->opcode = opcode;
-            ctx->pc_succ_insn = ctx->base.pc_next + 2;
-            if (decode_insn16(ctx, opcode)) {
-                return;
-            }
+        ctx->opcode = opcode;
+        ctx->pc_succ_insn = ctx->base.pc_next + 2;
+        if (has_ext(ctx, RVC) && decode_insn16(ctx, opcode)) {
+            return;
         }
     } else {
         uint32_t opcode32 = opcode;
@@ -1136,6 +1165,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     memset(ctx->ftemp, 0, sizeof(ctx->ftemp));
     ctx->pm_mask_enabled = FIELD_EX32(tb_flags, TB_FLAGS, PM_MASK_ENABLED);
     ctx->pm_base_enabled = FIELD_EX32(tb_flags, TB_FLAGS, PM_BASE_ENABLED);
+    ctx->itrigger = FIELD_EX32(tb_flags, TB_FLAGS, ITRIGGER);
     ctx->zero = tcg_constant_tl(0);
 }
 
@@ -1175,7 +1205,7 @@ static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
 
     /* Only the first insn within a TB is allowed to cross a page boundary. */
     if (ctx->base.is_jmp == DISAS_NEXT) {
-        if (!is_same_page(&ctx->base, ctx->base.pc_next)) {
+        if (ctx->itrigger || !is_same_page(&ctx->base, ctx->base.pc_next)) {
             ctx->base.is_jmp = DISAS_TOO_MANY;
         } else {
             unsigned page_ofs = ctx->base.pc_next & ~TARGET_PAGE_MASK;
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index 34858eb95f..150aeecd14 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -163,13 +163,6 @@ static inline void gen_update_fprs_dirty(DisasContext *dc, int rd)
 /* floating point registers moves */
 static TCGv_i32 gen_load_fpr_F(DisasContext *dc, unsigned int src)
 {
-#if TCG_TARGET_REG_BITS == 32
-    if (src & 1) {
-        return TCGV_LOW(cpu_fpr[src / 2]);
-    } else {
-        return TCGV_HIGH(cpu_fpr[src / 2]);
-    }
-#else
     TCGv_i32 ret = get_temp_i32(dc);
     if (src & 1) {
         tcg_gen_extrl_i64_i32(ret, cpu_fpr[src / 2]);
@@ -177,22 +170,16 @@ static TCGv_i32 gen_load_fpr_F(DisasContext *dc, unsigned int src)
         tcg_gen_extrh_i64_i32(ret, cpu_fpr[src / 2]);
     }
     return ret;
-#endif
 }
 
 static void gen_store_fpr_F(DisasContext *dc, unsigned int dst, TCGv_i32 v)
 {
-#if TCG_TARGET_REG_BITS == 32
-    if (dst & 1) {
-        tcg_gen_mov_i32(TCGV_LOW(cpu_fpr[dst / 2]), v);
-    } else {
-        tcg_gen_mov_i32(TCGV_HIGH(cpu_fpr[dst / 2]), v);
-    }
-#else
-    TCGv_i64 t = (TCGv_i64)v;
+    TCGv_i64 t = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(t, v);
     tcg_gen_deposit_i64(cpu_fpr[dst / 2], cpu_fpr[dst / 2], t,
                         (dst & 1 ? 0 : 32), 32);
-#endif
+    tcg_temp_free_i64(t);
     gen_update_fprs_dirty(dc, dst);
 }