Merge tag 'pull-target-arm-20220707' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * hw/arm/virt: dt: add rng-seed property
 * Fix MTE check in sve_ldnfff1_r
 * Record tagged bit for user-only in sve_probe_page
 * Correctly implement OS Lock and OS DoubleLock
 * Implement DBGDEVID, DBGDEVID1, DBGDEVID2 registers
 * Fix qemu-system-arm handling of LPAE block descriptors for highmem

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmLG0O8ZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3h1MEACnTd+jfssa/MdtQPP8N+cp
# cvrdrW+V9iho1vLPGG3d6yni6T8IMdulA5OvSkiNz2IaspY3z3u/t01PCpqEF0tA
# nl3HxA65ddehzG8QHpORiP2DIJfuYUcMaruK2zMcC//0EXBOVI215hkR7oNyC0r9
# PrYb+tiDVL1t3xzXWNKMoolZwUjS6M6dloxEu2b/d0tOBvtBLI0E7y9taANHCnmZ
# 8r7ih0WRELo1rzveZVOXqnZGLUjFzbCurHCmshN6xr2V6iilBaLoaGHovZ2c489Z
# Fz/Ui1tyvDUoajr/Ck57GYo0BwDf9dKYkl5RkchdeY+cA88CgJAVK5pT0Rrybpf0
# lMgSAalIFcnIr2kjdnWRUqL02t+HgnOnsBTSUpgiwMNKwjfMN5NDi9294GuMCu2h
# 7UyuAkQvfTwoQyFzJYzuapcnB6i5BvQjq6GxSmogzuR6kNSFptNOGimMhqCO4kN0
# fixOHOOE/aj7QoXq33V9u3ESY1IleDMX6+Zff2RLmVQYZpQKW6LpCfuwgnZrZEN3
# 4hPiL+00bY9pWlXvvEHdu0/XYx8kPXtmdzgzpm80edCLUMFOVMDQMQE1Zy/qzC7S
# 8ryfC2EvSQuigD1+s6I9WxCnHVv5Byz+DXgRCjRsitDPVu2kFcEgAibzz9K1WVUW
# qwQP4WGUzFD/LNUwO/Vryw==
# =TzwD
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 07 Jul 2022 05:56:23 PM +0530
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [full]

* tag 'pull-target-arm-20220707' of https://git.linaro.org/people/pmaydell/qemu-arm:
  target/arm: Fix qemu-system-arm handling of LPAE block descriptors for highmem
  target/arm: Correctly implement Feat_DoubleLock
  target/arm: Implement AArch32 DBGDEVID, DBGDEVID1, DBGDEVID2
  target/arm: Suppress debug exceptions when OS Lock set
  target/arm: Move define_debug_regs() to debug_helper.c
  target/arm: Fix code style issues in debug helper functions
  target/arm: Record tagged bit for user-only in sve_probe_page
  target/arm: Fix MTE check in sve_ldnfff1_r
  hw/arm/virt: dt: add rng-seed property

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

13 files changed, 684 insertions, 538 deletions

diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst
index 19a91b575f..7ee26626d5 100644
--- a/docs/about/deprecated.rst
+++ b/docs/about/deprecated.rst
@@ -225,6 +225,14 @@ Use the more generic event ``DEVICE_UNPLUG_GUEST_ERROR`` instead.
 System emulator machines
 ------------------------
 
+Arm ``virt`` machine ``dtb-kaslr-seed`` property
+''''''''''''''''''''''''''''''''''''''''''''''''
+
+The ``dtb-kaslr-seed`` property on the ``virt`` board has been
+deprecated; use the new name ``dtb-randomness`` instead. The new name
+better reflects the way this property affects all random data within
+the device tree blob, not just the ``kaslr-seed`` node.
+
 PPC 405 ``taihu`` machine (since 7.0)
 '''''''''''''''''''''''''''''''''''''
 
diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst
index 3d1058a80c..3b6ba69a9a 100644
--- a/docs/system/arm/virt.rst
+++ b/docs/system/arm/virt.rst
@@ -126,13 +126,18 @@ ras
   Set ``on``/``off`` to enable/disable reporting host memory errors to a guest
   using ACPI and guest external abort exceptions. The default is off.
 
+dtb-randomness
+  Set ``on``/``off`` to pass random seeds via the guest DTB
+  rng-seed and kaslr-seed nodes (in both "/chosen" and
+  "/secure-chosen") to use for features like the random number
+  generator and address space randomisation. The default is
+  ``on``. You will want to disable it if your trusted boot chain
+  will verify the DTB it is passed, since this option causes the
+  DTB to be non-deterministic. It would be the responsibility of
+  the firmware to come up with a seed and pass it on if it wants to.
+
 dtb-kaslr-seed
-  Set ``on``/``off`` to pass a random seed via the guest dtb
-  kaslr-seed node (in both "/chosen" and /secure-chosen) to use
-  for features like address space randomisation. The default is
-  ``on``. You will want to disable it if your trusted boot chain will
-  verify the DTB it is passed. It would be the responsibility of the
-  firmware to come up with a seed and pass it on if it wants to.
+  A deprecated synonym for dtb-randomness.
 
 Linux guest kernel configuration
 """"""""""""""""""""""""""""""""
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 5502aa60c8..9633f822f3 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -221,14 +221,18 @@ static bool cpu_type_valid(const char *cpu)
     return false;
 }
 
-static void create_kaslr_seed(MachineState *ms, const char *node)
+static void create_randomness(MachineState *ms, const char *node)
 {
-    uint64_t seed;
+    struct {
+        uint64_t kaslr;
+        uint8_t rng[32];
+    } seed;
 
     if (qemu_guest_getrandom(&seed, sizeof(seed), NULL)) {
         return;
     }
-    qemu_fdt_setprop_u64(ms->fdt, node, "kaslr-seed", seed);
+    qemu_fdt_setprop_u64(ms->fdt, node, "kaslr-seed", seed.kaslr);
+    qemu_fdt_setprop(ms->fdt, node, "rng-seed", seed.rng, sizeof(seed.rng));
 }
 
 static void create_fdt(VirtMachineState *vms)
@@ -251,14 +255,14 @@ static void create_fdt(VirtMachineState *vms)
 
     /* /chosen must exist for load_dtb to fill in necessary properties later */
     qemu_fdt_add_subnode(fdt, "/chosen");
-    if (vms->dtb_kaslr_seed) {
-        create_kaslr_seed(ms, "/chosen");
+    if (vms->dtb_randomness) {
+        create_randomness(ms, "/chosen");
     }
 
     if (vms->secure) {
         qemu_fdt_add_subnode(fdt, "/secure-chosen");
-        if (vms->dtb_kaslr_seed) {
-            create_kaslr_seed(ms, "/secure-chosen");
+        if (vms->dtb_randomness) {
+            create_randomness(ms, "/secure-chosen");
         }
     }
 
@@ -2340,18 +2344,18 @@ static void virt_set_its(Object *obj, bool value, Error **errp)
     vms->its = value;
 }
 
-static bool virt_get_dtb_kaslr_seed(Object *obj, Error **errp)
+static bool virt_get_dtb_randomness(Object *obj, Error **errp)
 {
     VirtMachineState *vms = VIRT_MACHINE(obj);
 
-    return vms->dtb_kaslr_seed;
+    return vms->dtb_randomness;
 }
 
-static void virt_set_dtb_kaslr_seed(Object *obj, bool value, Error **errp)
+static void virt_set_dtb_randomness(Object *obj, bool value, Error **errp)
 {
     VirtMachineState *vms = VIRT_MACHINE(obj);
 
-    vms->dtb_kaslr_seed = value;
+    vms->dtb_randomness = value;
 }
 
 static char *virt_get_oem_id(Object *obj, Error **errp)
@@ -2980,12 +2984,18 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
                                           "Set on/off to enable/disable "
                                           "ITS instantiation");
 
+    object_class_property_add_bool(oc, "dtb-randomness",
+                                   virt_get_dtb_randomness,
+                                   virt_set_dtb_randomness);
+    object_class_property_set_description(oc, "dtb-randomness",
+                                          "Set off to disable passing random or "
+                                          "non-deterministic dtb nodes to guest");
+
     object_class_property_add_bool(oc, "dtb-kaslr-seed",
-                                   virt_get_dtb_kaslr_seed,
-                                   virt_set_dtb_kaslr_seed);
+                                   virt_get_dtb_randomness,
+                                   virt_set_dtb_randomness);
     object_class_property_set_description(oc, "dtb-kaslr-seed",
-                                          "Set off to disable passing of kaslr-seed "
-                                          "dtb node to guest");
+                                          "Deprecated synonym of dtb-randomness");
 
     object_class_property_add_str(oc, "x-oem-id",
                                   virt_get_oem_id,
@@ -3053,8 +3063,8 @@ static void virt_instance_init(Object *obj)
     /* MTE is disabled by default.  */
     vms->mte = false;
 
-    /* Supply a kaslr-seed by default */
-    vms->dtb_kaslr_seed = true;
+    /* Supply kaslr-seed and rng-seed by default */
+    vms->dtb_randomness = true;
 
     vms->irqmap = a15irqmap;
 
diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
index 15feabac63..6ec479ca2b 100644
--- a/include/hw/arm/virt.h
+++ b/include/hw/arm/virt.h
@@ -152,7 +152,7 @@ struct VirtMachineState {
     bool virt;
     bool ras;
     bool mte;
-    bool dtb_kaslr_seed;
+    bool dtb_randomness;
     OnOffAuto acpi;
     VirtGICType gic_version;
     VirtIOMMUType iommu;
diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h
index d30758ee71..7e78c2c05c 100644
--- a/target/arm/cpregs.h
+++ b/target/arm/cpregs.h
@@ -442,6 +442,9 @@ void arm_cp_write_ignore(CPUARMState *env, const ARMCPRegInfo *ri,
 /* CPReadFn that can be used for read-as-zero behaviour */
 uint64_t arm_cp_read_zero(CPUARMState *env, const ARMCPRegInfo *ri);
 
+/* CPWriteFn that just writes the value to ri->fieldoffset */
+void raw_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value);
+
 /*
  * CPResetFn that does nothing, for use if no reset is required even
  * if fieldoffset is non zero.
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 4a4342f262..1f4f3e0485 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -500,6 +500,7 @@ typedef struct CPUArchState {
         uint64_t dbgwcr[16]; /* watchpoint control registers */
         uint64_t mdscr_el1;
         uint64_t oslsr_el1; /* OS Lock Status */
+        uint64_t osdlr_el1; /* OS DoubleLock status */
         uint64_t mdcr_el2;
         uint64_t mdcr_el3;
         /* Stores the architectural value of the counter *the last time it was
@@ -988,6 +989,8 @@ struct ArchCPU {
         uint32_t mvfr2;
         uint32_t id_dfr0;
         uint32_t dbgdidr;
+        uint32_t dbgdevid;
+        uint32_t dbgdevid1;
         uint64_t id_aa64isar0;
         uint64_t id_aa64isar1;
         uint64_t id_aa64pfr0;
@@ -2251,6 +2254,15 @@ FIELD(DBGDIDR, CTX_CMPS, 20, 4)
 FIELD(DBGDIDR, BRPS, 24, 4)
 FIELD(DBGDIDR, WRPS, 28, 4)
 
+FIELD(DBGDEVID, PCSAMPLE, 0, 4)
+FIELD(DBGDEVID, WPADDRMASK, 4, 4)
+FIELD(DBGDEVID, BPADDRMASK, 8, 4)
+FIELD(DBGDEVID, VECTORCATCH, 12, 4)
+FIELD(DBGDEVID, VIRTEXTNS, 16, 4)
+FIELD(DBGDEVID, DOUBLELOCK, 20, 4)
+FIELD(DBGDEVID, AUXREGS, 24, 4)
+FIELD(DBGDEVID, CIDMASK, 28, 4)
+
 FIELD(MVFR0, SIMDREG, 0, 4)
 FIELD(MVFR0, FPSP, 4, 4)
 FIELD(MVFR0, FPDP, 8, 4)
@@ -3719,11 +3731,21 @@ static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id)
     return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0;
 }
 
+static inline bool isar_feature_aa32_debugv7p1(const ARMISARegisters *id)
+{
+    return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 5;
+}
+
 static inline bool isar_feature_aa32_debugv8p2(const ARMISARegisters *id)
 {
     return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 8;
 }
 
+static inline bool isar_feature_aa32_doublelock(const ARMISARegisters *id)
+{
+    return FIELD_EX32(id->dbgdevid, DBGDEVID, DOUBLELOCK) > 0;
+}
+
 /*
  * 64-bit feature tests via id registers.
  */
@@ -4148,6 +4170,11 @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64);
 }
 
+static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id)
+{
+    return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0;
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 19188d6cc2..b4fd4b7ec8 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -79,6 +79,8 @@ static void aarch64_a57_initfn(Object *obj)
     cpu->isar.id_aa64isar0 = 0x00011120;
     cpu->isar.id_aa64mmfr0 = 0x00001124;
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.dbgdevid = 0x01110f13;
+    cpu->isar.dbgdevid1 = 0x2;
     cpu->isar.reset_pmcr_el0 = 0x41013000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
@@ -134,6 +136,8 @@ static void aarch64_a53_initfn(Object *obj)
     cpu->isar.id_aa64isar0 = 0x00011120;
     cpu->isar.id_aa64mmfr0 = 0x00001122; /* 40 bit physical addr */
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.dbgdevid = 0x00110f13;
+    cpu->isar.dbgdevid1 = 0x1;
     cpu->isar.reset_pmcr_el0 = 0x41033000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */
@@ -187,6 +191,8 @@ static void aarch64_a72_initfn(Object *obj)
     cpu->isar.id_aa64isar0 = 0x00011120;
     cpu->isar.id_aa64mmfr0 = 0x00001124;
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.dbgdevid = 0x01110f13;
+    cpu->isar.dbgdevid1 = 0x2;
     cpu->isar.reset_pmcr_el0 = 0x41023000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index b751a19c8a..3099b38e32 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -563,6 +563,8 @@ static void cortex_a7_initfn(Object *obj)
     cpu->isar.id_isar3 = 0x11112131;
     cpu->isar.id_isar4 = 0x10011142;
     cpu->isar.dbgdidr = 0x3515f005;
+    cpu->isar.dbgdevid = 0x01110f13;
+    cpu->isar.dbgdevid1 = 0x1;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */
     cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */
@@ -606,6 +608,8 @@ static void cortex_a15_initfn(Object *obj)
     cpu->isar.id_isar3 = 0x11112131;
     cpu->isar.id_isar4 = 0x10011142;
     cpu->isar.dbgdidr = 0x3515f021;
+    cpu->isar.dbgdevid = 0x01110f13;
+    cpu->isar.dbgdevid1 = 0x0;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */
     cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */
@@ -1098,6 +1102,8 @@ static void arm_max_initfn(Object *obj)
     cpu->isar.id_isar5 = 0x00011121;
     cpu->isar.id_isar6 = 0;
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.dbgdevid = 0x00110f13;
+    cpu->isar.dbgdevid1 = 0x2;
     cpu->isar.reset_pmcr_el0 = 0x41013000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index b18a6bd3a2..d09fccb0a4 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -6,8 +6,10 @@
  * SPDX-License-Identifier: GPL-2.0-or-later
  */
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "cpu.h"
 #include "internals.h"
+#include "cpregs.h"
 #include "exec/exec-all.h"
 #include "exec/helper-proto.h"
 
@@ -140,6 +142,9 @@ static bool aa32_generate_debug_exceptions(CPUARMState *env)
  */
 bool arm_generate_debug_exceptions(CPUARMState *env)
 {
+    if ((env->cp15.oslsr_el1 & 1) || (env->cp15.osdlr_el1 & 1)) {
+        return false;
+    }
     if (is_a64(env)) {
         return aa64_generate_debug_exceptions(env);
     } else {
@@ -528,6 +533,581 @@ void HELPER(exception_swstep)(CPUARMState *env, uint32_t syndrome)
     raise_exception_debug(env, EXCP_UDEF, syndrome);
 }
 
+/*
+ * Check for traps to "powerdown debug" registers, which are controlled
+ * by MDCR.TDOSA
+ */
+static CPAccessResult access_tdosa(CPUARMState *env, const ARMCPRegInfo *ri,
+                                   bool isread)
+{
+    int el = arm_current_el(env);
+    uint64_t mdcr_el2 = arm_mdcr_el2_eff(env);
+    bool mdcr_el2_tdosa = (mdcr_el2 & MDCR_TDOSA) || (mdcr_el2 & MDCR_TDE) ||
+        (arm_hcr_el2_eff(env) & HCR_TGE);
+
+    if (el < 2 && mdcr_el2_tdosa) {
+        return CP_ACCESS_TRAP_EL2;
+    }
+    if (el < 3 && (env->cp15.mdcr_el3 & MDCR_TDOSA)) {
+        return CP_ACCESS_TRAP_EL3;
+    }
+    return CP_ACCESS_OK;
+}
+
+/*
+ * Check for traps to "debug ROM" registers, which are controlled
+ * by MDCR_EL2.TDRA for EL2 but by the more general MDCR_EL3.TDA for EL3.
+ */
+static CPAccessResult access_tdra(CPUARMState *env, const ARMCPRegInfo *ri,
+                                  bool isread)
+{
+    int el = arm_current_el(env);
+    uint64_t mdcr_el2 = arm_mdcr_el2_eff(env);
+    bool mdcr_el2_tdra = (mdcr_el2 & MDCR_TDRA) || (mdcr_el2 & MDCR_TDE) ||
+        (arm_hcr_el2_eff(env) & HCR_TGE);
+
+    if (el < 2 && mdcr_el2_tdra) {
+        return CP_ACCESS_TRAP_EL2;
+    }
+    if (el < 3 && (env->cp15.mdcr_el3 & MDCR_TDA)) {
+        return CP_ACCESS_TRAP_EL3;
+    }
+    return CP_ACCESS_OK;
+}
+
+/*
+ * Check for traps to general debug registers, which are controlled
+ * by MDCR_EL2.TDA for EL2 and MDCR_EL3.TDA for EL3.
+ */
+static CPAccessResult access_tda(CPUARMState *env, const ARMCPRegInfo *ri,
+                                  bool isread)
+{
+    int el = arm_current_el(env);
+    uint64_t mdcr_el2 = arm_mdcr_el2_eff(env);
+    bool mdcr_el2_tda = (mdcr_el2 & MDCR_TDA) || (mdcr_el2 & MDCR_TDE) ||
+        (arm_hcr_el2_eff(env) & HCR_TGE);
+
+    if (el < 2 && mdcr_el2_tda) {
+        return CP_ACCESS_TRAP_EL2;
+    }
+    if (el < 3 && (env->cp15.mdcr_el3 & MDCR_TDA)) {
+        return CP_ACCESS_TRAP_EL3;
+    }
+    return CP_ACCESS_OK;
+}
+
+static void oslar_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                        uint64_t value)
+{
+    /*
+     * Writes to OSLAR_EL1 may update the OS lock status, which can be
+     * read via a bit in OSLSR_EL1.
+     */
+    int oslock;
+
+    if (ri->state == ARM_CP_STATE_AA32) {
+        oslock = (value == 0xC5ACCE55);
+    } else {
+        oslock = value & 1;
+    }
+
+    env->cp15.oslsr_el1 = deposit32(env->cp15.oslsr_el1, 1, 1, oslock);
+}
+
+static void osdlr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                        uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    /*
+     * Only defined bit is bit 0 (DLK); if Feat_DoubleLock is not
+     * implemented this is RAZ/WI.
+     */
+    if(arm_feature(env, ARM_FEATURE_AARCH64)
+       ? cpu_isar_feature(aa64_doublelock, cpu)
+       : cpu_isar_feature(aa32_doublelock, cpu)) {
+        env->cp15.osdlr_el1 = value & 1;
+    }
+}
+
+static const ARMCPRegInfo debug_cp_reginfo[] = {
+    /*
+     * DBGDRAR, DBGDSAR: always RAZ since we don't implement memory mapped
+     * debug components. The AArch64 version of DBGDRAR is named MDRAR_EL1;
+     * unlike DBGDRAR it is never accessible from EL0.
+     * DBGDSAR is deprecated and must RAZ from v8 anyway, so it has no AArch64
+     * accessor.
+     */
+    { .name = "DBGDRAR", .cp = 14, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 0,
+      .access = PL0_R, .accessfn = access_tdra,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    { .name = "MDRAR_EL1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 0,
+      .access = PL1_R, .accessfn = access_tdra,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    { .name = "DBGDSAR", .cp = 14, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 0,
+      .access = PL0_R, .accessfn = access_tdra,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    /* Monitor debug system control register; the 32-bit alias is DBGDSCRext. */
+    { .name = "MDSCR_EL1", .state = ARM_CP_STATE_BOTH,
+      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 2,
+      .access = PL1_RW, .accessfn = access_tda,
+      .fieldoffset = offsetof(CPUARMState, cp15.mdscr_el1),
+      .resetvalue = 0 },
+    /*
+     * MDCCSR_EL0[30:29] map to EDSCR[30:29].  Simply RAZ as the external
+     * Debug Communication Channel is not implemented.
+     */
+    { .name = "MDCCSR_EL0", .state = ARM_CP_STATE_AA64,
+      .opc0 = 2, .opc1 = 3, .crn = 0, .crm = 1, .opc2 = 0,
+      .access = PL0_R, .accessfn = access_tda,
+      .type = ARM_CP_CONST, .resetvalue = 0 },
+    /*
+     * DBGDSCRint[15,12,5:2] map to MDSCR_EL1[15,12,5:2].  Map all bits as
+     * it is unlikely a guest will care.
+     * We don't implement the configurable EL0 access.
+     */
+    { .name = "DBGDSCRint", .state = ARM_CP_STATE_AA32,
+      .cp = 14, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 0,
+      .type = ARM_CP_ALIAS,
+      .access = PL1_R, .accessfn = access_tda,
+      .fieldoffset = offsetof(CPUARMState, cp15.mdscr_el1), },
+    { .name = "OSLAR_EL1", .state = ARM_CP_STATE_BOTH,
+      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 4,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .accessfn = access_tdosa,
+      .writefn = oslar_write },
+    { .name = "OSLSR_EL1", .state = ARM_CP_STATE_BOTH,
+      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 1, .opc2 = 4,
+      .access = PL1_R, .resetvalue = 10,
+      .accessfn = access_tdosa,
+      .fieldoffset = offsetof(CPUARMState, cp15.oslsr_el1) },
+    /* Dummy OSDLR_EL1: 32-bit Linux will read this */
+    { .name = "OSDLR_EL1", .state = ARM_CP_STATE_BOTH,
+      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 3, .opc2 = 4,
+      .access = PL1_RW, .accessfn = access_tdosa,
+      .writefn = osdlr_write,
+      .fieldoffset = offsetof(CPUARMState, cp15.osdlr_el1) },
+    /*
+     * Dummy DBGVCR: Linux wants to clear this on startup, but we don't
+     * implement vector catch debug events yet.
+     */
+    { .name = "DBGVCR",
+      .cp = 14, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 0,
+      .access = PL1_RW, .accessfn = access_tda,
+      .type = ARM_CP_NOP },
+    /*
+     * Dummy DBGVCR32_EL2 (which is only for a 64-bit hypervisor
+     * to save and restore a 32-bit guest's DBGVCR)
+     */
+    { .name = "DBGVCR32_EL2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 2, .opc1 = 4, .crn = 0, .crm = 7, .opc2 = 0,
+      .access = PL2_RW, .accessfn = access_tda,
+      .type = ARM_CP_NOP | ARM_CP_EL3_NO_EL2_KEEP },
+    /*
+     * Dummy MDCCINT_EL1, since we don't implement the Debug Communications
+     * Channel but Linux may try to access this register. The 32-bit
+     * alias is DBGDCCINT.
+     */
+    { .name = "MDCCINT_EL1", .state = ARM_CP_STATE_BOTH,
+      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 0,
+      .access = PL1_RW, .accessfn = access_tda,
+      .type = ARM_CP_NOP },
+};
+
+static const ARMCPRegInfo debug_lpae_cp_reginfo[] = {
+    /* 64 bit access versions of the (dummy) debug registers */
+    { .name = "DBGDRAR", .cp = 14, .crm = 1, .opc1 = 0,
+      .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 },
+    { .name = "DBGDSAR", .cp = 14, .crm = 2, .opc1 = 0,
+      .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 },
+};
+
+void hw_watchpoint_update(ARMCPU *cpu, int n)
+{
+    CPUARMState *env = &cpu->env;
+    vaddr len = 0;
+    vaddr wvr = env->cp15.dbgwvr[n];
+    uint64_t wcr = env->cp15.dbgwcr[n];
+    int mask;
+    int flags = BP_CPU | BP_STOP_BEFORE_ACCESS;
+
+    if (env->cpu_watchpoint[n]) {
+        cpu_watchpoint_remove_by_ref(CPU(cpu), env->cpu_watchpoint[n]);
+        env->cpu_watchpoint[n] = NULL;
+    }
+
+    if (!FIELD_EX64(wcr, DBGWCR, E)) {
+        /* E bit clear : watchpoint disabled */
+        return;
+    }
+
+    switch (FIELD_EX64(wcr, DBGWCR, LSC)) {
+    case 0:
+        /* LSC 00 is reserved and must behave as if the wp is disabled */
+        return;
+    case 1:
+        flags |= BP_MEM_READ;
+        break;
+    case 2:
+        flags |= BP_MEM_WRITE;
+        break;
+    case 3:
+        flags |= BP_MEM_ACCESS;
+        break;
+    }
+
+    /*
+     * Attempts to use both MASK and BAS fields simultaneously are
+     * CONSTRAINED UNPREDICTABLE; we opt to ignore BAS in this case,
+     * thus generating a watchpoint for every byte in the masked region.
+     */
+    mask = FIELD_EX64(wcr, DBGWCR, MASK);
+    if (mask == 1 || mask == 2) {
+        /*
+         * Reserved values of MASK; we must act as if the mask value was
+         * some non-reserved value, or as if the watchpoint were disabled.
+         * We choose the latter.
+         */
+        return;
+    } else if (mask) {
+        /* Watchpoint covers an aligned area up to 2GB in size */
+        len = 1ULL << mask;
+        /*
+         * If masked bits in WVR are not zero it's CONSTRAINED UNPREDICTABLE
+         * whether the watchpoint fires when the unmasked bits match; we opt
+         * to generate the exceptions.
+         */
+        wvr &= ~(len - 1);
+    } else {
+        /* Watchpoint covers bytes defined by the byte address select bits */
+        int bas = FIELD_EX64(wcr, DBGWCR, BAS);
+        int basstart;
+
+        if (extract64(wvr, 2, 1)) {
+            /*
+             * Deprecated case of an only 4-aligned address. BAS[7:4] are
+             * ignored, and BAS[3:0] define which bytes to watch.
+             */
+            bas &= 0xf;
+        }
+
+        if (bas == 0) {
+            /* This must act as if the watchpoint is disabled */
+            return;
+        }
+
+        /*
+         * The BAS bits are supposed to be programmed to indicate a contiguous
+         * range of bytes. Otherwise it is CONSTRAINED UNPREDICTABLE whether
+         * we fire for each byte in the word/doubleword addressed by the WVR.
+         * We choose to ignore any non-zero bits after the first range of 1s.
+         */
+        basstart = ctz32(bas);
+        len = cto32(bas >> basstart);
+        wvr += basstart;
+    }
+
+    cpu_watchpoint_insert(CPU(cpu), wvr, len, flags,
+                          &env->cpu_watchpoint[n]);
+}
+
+void hw_watchpoint_update_all(ARMCPU *cpu)
+{
+    int i;
+    CPUARMState *env = &cpu->env;
+
+    /*
+     * Completely clear out existing QEMU watchpoints and our array, to
+     * avoid possible stale entries following migration load.
+     */
+    cpu_watchpoint_remove_all(CPU(cpu), BP_CPU);
+    memset(env->cpu_watchpoint, 0, sizeof(env->cpu_watchpoint));
+
+    for (i = 0; i < ARRAY_SIZE(cpu->env.cpu_watchpoint); i++) {
+        hw_watchpoint_update(cpu, i);
+    }
+}
+
+static void dbgwvr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    int i = ri->crm;
+
+    /*
+     * Bits [1:0] are RES0.
+     *
+     * It is IMPLEMENTATION DEFINED whether [63:49] ([63:53] with FEAT_LVA)
+     * are hardwired to the value of bit [48] ([52] with FEAT_LVA), or if
+     * they contain the value written.  It is CONSTRAINED UNPREDICTABLE
+     * whether the RESS bits are ignored when comparing an address.
+     *
+     * Therefore we are allowed to compare the entire register, which lets
+     * us avoid considering whether or not FEAT_LVA is actually enabled.
+     */
+    value &= ~3ULL;
+
+    raw_write(env, ri, value);
+    hw_watchpoint_update(cpu, i);
+}
+
+static void dbgwcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    int i = ri->crm;
+
+    raw_write(env, ri, value);
+    hw_watchpoint_update(cpu, i);
+}
+
+void hw_breakpoint_update(ARMCPU *cpu, int n)
+{
+    CPUARMState *env = &cpu->env;
+    uint64_t bvr = env->cp15.dbgbvr[n];
+    uint64_t bcr = env->cp15.dbgbcr[n];
+    vaddr addr;
+    int bt;
+    int flags = BP_CPU;
+
+    if (env->cpu_breakpoint[n]) {
+        cpu_breakpoint_remove_by_ref(CPU(cpu), env->cpu_breakpoint[n]);
+        env->cpu_breakpoint[n] = NULL;
+    }
+
+    if (!extract64(bcr, 0, 1)) {
+        /* E bit clear : watchpoint disabled */
+        return;
+    }
+
+    bt = extract64(bcr, 20, 4);
+
+    switch (bt) {
+    case 4: /* unlinked address mismatch (reserved if AArch64) */
+    case 5: /* linked address mismatch (reserved if AArch64) */
+        qemu_log_mask(LOG_UNIMP,
+                      "arm: address mismatch breakpoint types not implemented\n");
+        return;
+    case 0: /* unlinked address match */
+    case 1: /* linked address match */
+    {
+        /*
+         * Bits [1:0] are RES0.
+         *
+         * It is IMPLEMENTATION DEFINED whether bits [63:49]
+         * ([63:53] for FEAT_LVA) are hardwired to a copy of the sign bit
+         * of the VA field ([48] or [52] for FEAT_LVA), or whether the
+         * value is read as written.  It is CONSTRAINED UNPREDICTABLE
+         * whether the RESS bits are ignored when comparing an address.
+         * Therefore we are allowed to compare the entire register, which
+         * lets us avoid considering whether FEAT_LVA is actually enabled.
+         *
+         * The BAS field is used to allow setting breakpoints on 16-bit
+         * wide instructions; it is CONSTRAINED UNPREDICTABLE whether
+         * a bp will fire if the addresses covered by the bp and the addresses
+         * covered by the insn overlap but the insn doesn't start at the
+         * start of the bp address range. We choose to require the insn and
+         * the bp to have the same address. The constraints on writing to
+         * BAS enforced in dbgbcr_write mean we have only four cases:
+         *  0b0000  => no breakpoint
+         *  0b0011  => breakpoint on addr
+         *  0b1100  => breakpoint on addr + 2
+         *  0b1111  => breakpoint on addr
+         * See also figure D2-3 in the v8 ARM ARM (DDI0487A.c).
+         */
+        int bas = extract64(bcr, 5, 4);
+        addr = bvr & ~3ULL;
+        if (bas == 0) {
+            return;
+        }
+        if (bas == 0xc) {
+            addr += 2;
+        }
+        break;
+    }
+    case 2: /* unlinked context ID match */
+    case 8: /* unlinked VMID match (reserved if no EL2) */
+    case 10: /* unlinked context ID and VMID match (reserved if no EL2) */
+        qemu_log_mask(LOG_UNIMP,
+                      "arm: unlinked context breakpoint types not implemented\n");
+        return;
+    case 9: /* linked VMID match (reserved if no EL2) */
+    case 11: /* linked context ID and VMID match (reserved if no EL2) */
+    case 3: /* linked context ID match */
+    default:
+        /*
+         * We must generate no events for Linked context matches (unless
+         * they are linked to by some other bp/wp, which is handled in
+         * updates for the linking bp/wp). We choose to also generate no events
+         * for reserved values.
+         */
+        return;
+    }
+
+    cpu_breakpoint_insert(CPU(cpu), addr, flags, &env->cpu_breakpoint[n]);
+}
+
+void hw_breakpoint_update_all(ARMCPU *cpu)
+{
+    int i;
+    CPUARMState *env = &cpu->env;
+
+    /*
+     * Completely clear out existing QEMU breakpoints and our array, to
+     * avoid possible stale entries following migration load.
+     */
+    cpu_breakpoint_remove_all(CPU(cpu), BP_CPU);
+    memset(env->cpu_breakpoint, 0, sizeof(env->cpu_breakpoint));
+
+    for (i = 0; i < ARRAY_SIZE(cpu->env.cpu_breakpoint); i++) {
+        hw_breakpoint_update(cpu, i);
+    }
+}
+
+static void dbgbvr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    int i = ri->crm;
+
+    raw_write(env, ri, value);
+    hw_breakpoint_update(cpu, i);
+}
+
+static void dbgbcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                         uint64_t value)
+{
+    ARMCPU *cpu = env_archcpu(env);
+    int i = ri->crm;
+
+    /*
+     * BAS[3] is a read-only copy of BAS[2], and BAS[1] a read-only
+     * copy of BAS[0].
+     */
+    value = deposit64(value, 6, 1, extract64(value, 5, 1));
+    value = deposit64(value, 8, 1, extract64(value, 7, 1));
+
+    raw_write(env, ri, value);
+    hw_breakpoint_update(cpu, i);
+}
+
+void define_debug_regs(ARMCPU *cpu)
+{
+    /*
+     * Define v7 and v8 architectural debug registers.
+     * These are just dummy implementations for now.
+     */
+    int i;
+    int wrps, brps, ctx_cmps;
+
+    /*
+     * The Arm ARM says DBGDIDR is optional and deprecated if EL1 cannot
+     * use AArch32.  Given that bit 15 is RES1, if the value is 0 then
+     * the register must not exist for this cpu.
+     */
+    if (cpu->isar.dbgdidr != 0) {
+        ARMCPRegInfo dbgdidr = {
+            .name = "DBGDIDR", .cp = 14, .crn = 0, .crm = 0,
+            .opc1 = 0, .opc2 = 0,
+            .access = PL0_R, .accessfn = access_tda,
+            .type = ARM_CP_CONST, .resetvalue = cpu->isar.dbgdidr,
+        };
+        define_one_arm_cp_reg(cpu, &dbgdidr);
+    }
+
+    /*
+     * DBGDEVID is present in the v7 debug architecture if
+     * DBGDIDR.DEVID_imp is 1 (bit 15); from v7.1 and on it is
+     * mandatory (and bit 15 is RES1). DBGDEVID1 and DBGDEVID2 exist
+     * from v7.1 of the debug architecture. Because no fields have yet
+     * been defined in DBGDEVID2 (and quite possibly none will ever
+     * be) we don't define an ARMISARegisters field for it.
+     * These registers exist only if EL1 can use AArch32, but that
+     * happens naturally because they are only PL1 accessible anyway.
+     */
+    if (extract32(cpu->isar.dbgdidr, 15, 1)) {
+        ARMCPRegInfo dbgdevid = {
+            .name = "DBGDEVID",
+            .cp = 14, .opc1 = 0, .crn = 7, .opc2 = 2, .crn = 7,
+            .access = PL1_R, .accessfn = access_tda,
+            .type = ARM_CP_CONST, .resetvalue = cpu->isar.dbgdevid,
+        };
+        define_one_arm_cp_reg(cpu, &dbgdevid);
+    }
+    if (cpu_isar_feature(aa32_debugv7p1, cpu)) {
+        ARMCPRegInfo dbgdevid12[] = {
+            {
+                .name = "DBGDEVID1",
+                .cp = 14, .opc1 = 0, .crn = 7, .opc2 = 1, .crn = 7,
+                .access = PL1_R, .accessfn = access_tda,
+                .type = ARM_CP_CONST, .resetvalue = cpu->isar.dbgdevid1,
+            }, {
+                .name = "DBGDEVID2",
+                .cp = 14, .opc1 = 0, .crn = 7, .opc2 = 0, .crn = 7,
+                .access = PL1_R, .accessfn = access_tda,
+                .type = ARM_CP_CONST, .resetvalue = 0,
+            },
+        };
+        define_arm_cp_regs(cpu, dbgdevid12);
+    }
+
+    brps = arm_num_brps(cpu);
+    wrps = arm_num_wrps(cpu);
+    ctx_cmps = arm_num_ctx_cmps(cpu);
+
+    assert(ctx_cmps <= brps);
+
+    define_arm_cp_regs(cpu, debug_cp_reginfo);
+
+    if (arm_feature(&cpu->env, ARM_FEATURE_LPAE)) {
+        define_arm_cp_regs(cpu, debug_lpae_cp_reginfo);
+    }
+
+    for (i = 0; i < brps; i++) {
+        char *dbgbvr_el1_name = g_strdup_printf("DBGBVR%d_EL1", i);
+        char *dbgbcr_el1_name = g_strdup_printf("DBGBCR%d_EL1", i);
+        ARMCPRegInfo dbgregs[] = {
+            { .name = dbgbvr_el1_name, .state = ARM_CP_STATE_BOTH,
+              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 4,
+              .access = PL1_RW, .accessfn = access_tda,
+              .fieldoffset = offsetof(CPUARMState, cp15.dbgbvr[i]),
+              .writefn = dbgbvr_write, .raw_writefn = raw_write
+            },
+            { .name = dbgbcr_el1_name, .state = ARM_CP_STATE_BOTH,
+              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 5,
+              .access = PL1_RW, .accessfn = access_tda,
+              .fieldoffset = offsetof(CPUARMState, cp15.dbgbcr[i]),
+              .writefn = dbgbcr_write, .raw_writefn = raw_write
+            },
+        };
+        define_arm_cp_regs(cpu, dbgregs);
+        g_free(dbgbvr_el1_name);
+        g_free(dbgbcr_el1_name);
+    }
+
+    for (i = 0; i < wrps; i++) {
+        char *dbgwvr_el1_name = g_strdup_printf("DBGWVR%d_EL1", i);
+        char *dbgwcr_el1_name = g_strdup_printf("DBGWCR%d_EL1", i);
+        ARMCPRegInfo dbgregs[] = {
+            { .name = dbgwvr_el1_name, .state = ARM_CP_STATE_BOTH,
+              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 6,
+              .access = PL1_RW, .accessfn = access_tda,
+              .fieldoffset = offsetof(CPUARMState, cp15.dbgwvr[i]),
+              .writefn = dbgwvr_write, .raw_writefn = raw_write
+            },
+            { .name = dbgwcr_el1_name, .state = ARM_CP_STATE_BOTH,
+              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 7,
+              .access = PL1_RW, .accessfn = access_tda,
+              .fieldoffset = offsetof(CPUARMState, cp15.dbgwcr[i]),
+              .writefn = dbgwcr_write, .raw_writefn = raw_write
+            },
+        };
+        define_arm_cp_regs(cpu, dbgregs);
+        g_free(dbgwvr_el1_name);
+        g_free(dbgwcr_el1_name);
+    }
+}
+
 #if !defined(CONFIG_USER_ONLY)
 
 vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len)
diff --git a/target/arm/helper.c b/target/arm/helper.c
index f6dcb1a115..e6f37e160f 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -51,8 +51,7 @@ static uint64_t raw_read(CPUARMState *env, const ARMCPRegInfo *ri)
     }
 }
 
-static void raw_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                      uint64_t value)
+void raw_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
 {
     assert(ri->fieldoffset);
     if (cpreg_field_is_64bit(ri)) {
@@ -302,71 +301,6 @@ static CPAccessResult access_trap_aa32s_el1(CPUARMState *env,
     return CP_ACCESS_TRAP_UNCATEGORIZED;
 }
 
-static uint64_t arm_mdcr_el2_eff(CPUARMState *env)
-{
-    return arm_is_el2_enabled(env) ? env->cp15.mdcr_el2 : 0;
-}
-
-/* Check for traps to "powerdown debug" registers, which are controlled
- * by MDCR.TDOSA
- */
-static CPAccessResult access_tdosa(CPUARMState *env, const ARMCPRegInfo *ri,
-                                   bool isread)
-{
-    int el = arm_current_el(env);
-    uint64_t mdcr_el2 = arm_mdcr_el2_eff(env);
-    bool mdcr_el2_tdosa = (mdcr_el2 & MDCR_TDOSA) || (mdcr_el2 & MDCR_TDE) ||
-        (arm_hcr_el2_eff(env) & HCR_TGE);
-
-    if (el < 2 && mdcr_el2_tdosa) {
-        return CP_ACCESS_TRAP_EL2;
-    }
-    if (el < 3 && (env->cp15.mdcr_el3 & MDCR_TDOSA)) {
-        return CP_ACCESS_TRAP_EL3;
-    }
-    return CP_ACCESS_OK;
-}
-
-/* Check for traps to "debug ROM" registers, which are controlled
- * by MDCR_EL2.TDRA for EL2 but by the more general MDCR_EL3.TDA for EL3.
- */
-static CPAccessResult access_tdra(CPUARMState *env, const ARMCPRegInfo *ri,
-                                  bool isread)
-{
-    int el = arm_current_el(env);
-    uint64_t mdcr_el2 = arm_mdcr_el2_eff(env);
-    bool mdcr_el2_tdra = (mdcr_el2 & MDCR_TDRA) || (mdcr_el2 & MDCR_TDE) ||
-        (arm_hcr_el2_eff(env) & HCR_TGE);
-
-    if (el < 2 && mdcr_el2_tdra) {
-        return CP_ACCESS_TRAP_EL2;
-    }
-    if (el < 3 && (env->cp15.mdcr_el3 & MDCR_TDA)) {
-        return CP_ACCESS_TRAP_EL3;
-    }
-    return CP_ACCESS_OK;
-}
-
-/* Check for traps to general debug registers, which are controlled
- * by MDCR_EL2.TDA for EL2 and MDCR_EL3.TDA for EL3.
- */
-static CPAccessResult access_tda(CPUARMState *env, const ARMCPRegInfo *ri,
-                                  bool isread)
-{
-    int el = arm_current_el(env);
-    uint64_t mdcr_el2 = arm_mdcr_el2_eff(env);
-    bool mdcr_el2_tda = (mdcr_el2 & MDCR_TDA) || (mdcr_el2 & MDCR_TDE) ||
-        (arm_hcr_el2_eff(env) & HCR_TGE);
-
-    if (el < 2 && mdcr_el2_tda) {
-        return CP_ACCESS_TRAP_EL2;
-    }
-    if (el < 3 && (env->cp15.mdcr_el3 & MDCR_TDA)) {
-        return CP_ACCESS_TRAP_EL3;
-    }
-    return CP_ACCESS_OK;
-}
-
 /* Check for traps to performance monitor registers, which are controlled
  * by MDCR_EL2.TPM for EL2 and MDCR_EL3.TPM for EL3.
  */
@@ -5979,111 +5913,6 @@ static CPAccessResult ctr_el0_access(CPUARMState *env, const ARMCPRegInfo *ri,
     return CP_ACCESS_OK;
 }
 
-static void oslar_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                        uint64_t value)
-{
-    /* Writes to OSLAR_EL1 may update the OS lock status, which can be
-     * read via a bit in OSLSR_EL1.
-     */
-    int oslock;
-
-    if (ri->state == ARM_CP_STATE_AA32) {
-        oslock = (value == 0xC5ACCE55);
-    } else {
-        oslock = value & 1;
-    }
-
-    env->cp15.oslsr_el1 = deposit32(env->cp15.oslsr_el1, 1, 1, oslock);
-}
-
-static const ARMCPRegInfo debug_cp_reginfo[] = {
-    /* DBGDRAR, DBGDSAR: always RAZ since we don't implement memory mapped
-     * debug components. The AArch64 version of DBGDRAR is named MDRAR_EL1;
-     * unlike DBGDRAR it is never accessible from EL0.
-     * DBGDSAR is deprecated and must RAZ from v8 anyway, so it has no AArch64
-     * accessor.
-     */
-    { .name = "DBGDRAR", .cp = 14, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 0,
-      .access = PL0_R, .accessfn = access_tdra,
-      .type = ARM_CP_CONST, .resetvalue = 0 },
-    { .name = "MDRAR_EL1", .state = ARM_CP_STATE_AA64,
-      .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 0,
-      .access = PL1_R, .accessfn = access_tdra,
-      .type = ARM_CP_CONST, .resetvalue = 0 },
-    { .name = "DBGDSAR", .cp = 14, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 0,
-      .access = PL0_R, .accessfn = access_tdra,
-      .type = ARM_CP_CONST, .resetvalue = 0 },
-    /* Monitor debug system control register; the 32-bit alias is DBGDSCRext. */
-    { .name = "MDSCR_EL1", .state = ARM_CP_STATE_BOTH,
-      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 2,
-      .access = PL1_RW, .accessfn = access_tda,
-      .fieldoffset = offsetof(CPUARMState, cp15.mdscr_el1),
-      .resetvalue = 0 },
-    /*
-     * MDCCSR_EL0[30:29] map to EDSCR[30:29].  Simply RAZ as the external
-     * Debug Communication Channel is not implemented.
-     */
-    { .name = "MDCCSR_EL0", .state = ARM_CP_STATE_AA64,
-      .opc0 = 2, .opc1 = 3, .crn = 0, .crm = 1, .opc2 = 0,
-      .access = PL0_R, .accessfn = access_tda,
-      .type = ARM_CP_CONST, .resetvalue = 0 },
-    /*
-     * DBGDSCRint[15,12,5:2] map to MDSCR_EL1[15,12,5:2].  Map all bits as
-     * it is unlikely a guest will care.
-     * We don't implement the configurable EL0 access.
-     */
-    { .name = "DBGDSCRint", .state = ARM_CP_STATE_AA32,
-      .cp = 14, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 0,
-      .type = ARM_CP_ALIAS,
-      .access = PL1_R, .accessfn = access_tda,
-      .fieldoffset = offsetof(CPUARMState, cp15.mdscr_el1), },
-    { .name = "OSLAR_EL1", .state = ARM_CP_STATE_BOTH,
-      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 4,
-      .access = PL1_W, .type = ARM_CP_NO_RAW,
-      .accessfn = access_tdosa,
-      .writefn = oslar_write },
-    { .name = "OSLSR_EL1", .state = ARM_CP_STATE_BOTH,
-      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 1, .opc2 = 4,
-      .access = PL1_R, .resetvalue = 10,
-      .accessfn = access_tdosa,
-      .fieldoffset = offsetof(CPUARMState, cp15.oslsr_el1) },
-    /* Dummy OSDLR_EL1: 32-bit Linux will read this */
-    { .name = "OSDLR_EL1", .state = ARM_CP_STATE_BOTH,
-      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 1, .crm = 3, .opc2 = 4,
-      .access = PL1_RW, .accessfn = access_tdosa,
-      .type = ARM_CP_NOP },
-    /* Dummy DBGVCR: Linux wants to clear this on startup, but we don't
-     * implement vector catch debug events yet.
-     */
-    { .name = "DBGVCR",
-      .cp = 14, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 0,
-      .access = PL1_RW, .accessfn = access_tda,
-      .type = ARM_CP_NOP },
-    /* Dummy DBGVCR32_EL2 (which is only for a 64-bit hypervisor
-     * to save and restore a 32-bit guest's DBGVCR)
-     */
-    { .name = "DBGVCR32_EL2", .state = ARM_CP_STATE_AA64,
-      .opc0 = 2, .opc1 = 4, .crn = 0, .crm = 7, .opc2 = 0,
-      .access = PL2_RW, .accessfn = access_tda,
-      .type = ARM_CP_NOP | ARM_CP_EL3_NO_EL2_KEEP },
-    /* Dummy MDCCINT_EL1, since we don't implement the Debug Communications
-     * Channel but Linux may try to access this register. The 32-bit
-     * alias is DBGDCCINT.
-     */
-    { .name = "MDCCINT_EL1", .state = ARM_CP_STATE_BOTH,
-      .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 0,
-      .access = PL1_RW, .accessfn = access_tda,
-      .type = ARM_CP_NOP },
-};
-
-static const ARMCPRegInfo debug_lpae_cp_reginfo[] = {
-    /* 64 bit access versions of the (dummy) debug registers */
-    { .name = "DBGDRAR", .cp = 14, .crm = 1, .opc1 = 0,
-      .access = PL0_R, .type = ARM_CP_CONST|ARM_CP_64BIT, .resetvalue = 0 },
-    { .name = "DBGDSAR", .cp = 14, .crm = 2, .opc1 = 0,
-      .access = PL0_R, .type = ARM_CP_CONST|ARM_CP_64BIT, .resetvalue = 0 },
-};
-
 /*
  * Check for traps to RAS registers, which are controlled
  * by HCR_EL2.TERR and SCR_EL3.TERR.
@@ -6462,346 +6291,6 @@ static const ARMCPRegInfo sme_reginfo[] = {
 };
 #endif /* TARGET_AARCH64 */
 
-void hw_watchpoint_update(ARMCPU *cpu, int n)
-{
-    CPUARMState *env = &cpu->env;
-    vaddr len = 0;
-    vaddr wvr = env->cp15.dbgwvr[n];
-    uint64_t wcr = env->cp15.dbgwcr[n];
-    int mask;
-    int flags = BP_CPU | BP_STOP_BEFORE_ACCESS;
-
-    if (env->cpu_watchpoint[n]) {
-        cpu_watchpoint_remove_by_ref(CPU(cpu), env->cpu_watchpoint[n]);
-        env->cpu_watchpoint[n] = NULL;
-    }
-
-    if (!FIELD_EX64(wcr, DBGWCR, E)) {
-        /* E bit clear : watchpoint disabled */
-        return;
-    }
-
-    switch (FIELD_EX64(wcr, DBGWCR, LSC)) {
-    case 0:
-        /* LSC 00 is reserved and must behave as if the wp is disabled */
-        return;
-    case 1:
-        flags |= BP_MEM_READ;
-        break;
-    case 2:
-        flags |= BP_MEM_WRITE;
-        break;
-    case 3:
-        flags |= BP_MEM_ACCESS;
-        break;
-    }
-
-    /* Attempts to use both MASK and BAS fields simultaneously are
-     * CONSTRAINED UNPREDICTABLE; we opt to ignore BAS in this case,
-     * thus generating a watchpoint for every byte in the masked region.
-     */
-    mask = FIELD_EX64(wcr, DBGWCR, MASK);
-    if (mask == 1 || mask == 2) {
-        /* Reserved values of MASK; we must act as if the mask value was
-         * some non-reserved value, or as if the watchpoint were disabled.
-         * We choose the latter.
-         */
-        return;
-    } else if (mask) {
-        /* Watchpoint covers an aligned area up to 2GB in size */
-        len = 1ULL << mask;
-        /* If masked bits in WVR are not zero it's CONSTRAINED UNPREDICTABLE
-         * whether the watchpoint fires when the unmasked bits match; we opt
-         * to generate the exceptions.
-         */
-        wvr &= ~(len - 1);
-    } else {
-        /* Watchpoint covers bytes defined by the byte address select bits */
-        int bas = FIELD_EX64(wcr, DBGWCR, BAS);
-        int basstart;
-
-        if (extract64(wvr, 2, 1)) {
-            /* Deprecated case of an only 4-aligned address. BAS[7:4] are
-             * ignored, and BAS[3:0] define which bytes to watch.
-             */
-            bas &= 0xf;
-        }
-
-        if (bas == 0) {
-            /* This must act as if the watchpoint is disabled */
-            return;
-        }
-
-        /* The BAS bits are supposed to be programmed to indicate a contiguous
-         * range of bytes. Otherwise it is CONSTRAINED UNPREDICTABLE whether
-         * we fire for each byte in the word/doubleword addressed by the WVR.
-         * We choose to ignore any non-zero bits after the first range of 1s.
-         */
-        basstart = ctz32(bas);
-        len = cto32(bas >> basstart);
-        wvr += basstart;
-    }
-
-    cpu_watchpoint_insert(CPU(cpu), wvr, len, flags,
-                          &env->cpu_watchpoint[n]);
-}
-
-void hw_watchpoint_update_all(ARMCPU *cpu)
-{
-    int i;
-    CPUARMState *env = &cpu->env;
-
-    /* Completely clear out existing QEMU watchpoints and our array, to
-     * avoid possible stale entries following migration load.
-     */
-    cpu_watchpoint_remove_all(CPU(cpu), BP_CPU);
-    memset(env->cpu_watchpoint, 0, sizeof(env->cpu_watchpoint));
-
-    for (i = 0; i < ARRAY_SIZE(cpu->env.cpu_watchpoint); i++) {
-        hw_watchpoint_update(cpu, i);
-    }
-}
-
-static void dbgwvr_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                         uint64_t value)
-{
-    ARMCPU *cpu = env_archcpu(env);
-    int i = ri->crm;
-
-    /*
-     * Bits [1:0] are RES0.
-     *
-     * It is IMPLEMENTATION DEFINED whether [63:49] ([63:53] with FEAT_LVA)
-     * are hardwired to the value of bit [48] ([52] with FEAT_LVA), or if
-     * they contain the value written.  It is CONSTRAINED UNPREDICTABLE
-     * whether the RESS bits are ignored when comparing an address.
-     *
-     * Therefore we are allowed to compare the entire register, which lets
-     * us avoid considering whether or not FEAT_LVA is actually enabled.
-     */
-    value &= ~3ULL;
-
-    raw_write(env, ri, value);
-    hw_watchpoint_update(cpu, i);
-}
-
-static void dbgwcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                         uint64_t value)
-{
-    ARMCPU *cpu = env_archcpu(env);
-    int i = ri->crm;
-
-    raw_write(env, ri, value);
-    hw_watchpoint_update(cpu, i);
-}
-
-void hw_breakpoint_update(ARMCPU *cpu, int n)
-{
-    CPUARMState *env = &cpu->env;
-    uint64_t bvr = env->cp15.dbgbvr[n];
-    uint64_t bcr = env->cp15.dbgbcr[n];
-    vaddr addr;
-    int bt;
-    int flags = BP_CPU;
-
-    if (env->cpu_breakpoint[n]) {
-        cpu_breakpoint_remove_by_ref(CPU(cpu), env->cpu_breakpoint[n]);
-        env->cpu_breakpoint[n] = NULL;
-    }
-
-    if (!extract64(bcr, 0, 1)) {
-        /* E bit clear : watchpoint disabled */
-        return;
-    }
-
-    bt = extract64(bcr, 20, 4);
-
-    switch (bt) {
-    case 4: /* unlinked address mismatch (reserved if AArch64) */
-    case 5: /* linked address mismatch (reserved if AArch64) */
-        qemu_log_mask(LOG_UNIMP,
-                      "arm: address mismatch breakpoint types not implemented\n");
-        return;
-    case 0: /* unlinked address match */
-    case 1: /* linked address match */
-    {
-        /*
-         * Bits [1:0] are RES0.
-         *
-         * It is IMPLEMENTATION DEFINED whether bits [63:49]
-         * ([63:53] for FEAT_LVA) are hardwired to a copy of the sign bit
-         * of the VA field ([48] or [52] for FEAT_LVA), or whether the
-         * value is read as written.  It is CONSTRAINED UNPREDICTABLE
-         * whether the RESS bits are ignored when comparing an address.
-         * Therefore we are allowed to compare the entire register, which
-         * lets us avoid considering whether FEAT_LVA is actually enabled.
-         *
-         * The BAS field is used to allow setting breakpoints on 16-bit
-         * wide instructions; it is CONSTRAINED UNPREDICTABLE whether
-         * a bp will fire if the addresses covered by the bp and the addresses
-         * covered by the insn overlap but the insn doesn't start at the
-         * start of the bp address range. We choose to require the insn and
-         * the bp to have the same address. The constraints on writing to
-         * BAS enforced in dbgbcr_write mean we have only four cases:
-         *  0b0000  => no breakpoint
-         *  0b0011  => breakpoint on addr
-         *  0b1100  => breakpoint on addr + 2
-         *  0b1111  => breakpoint on addr
-         * See also figure D2-3 in the v8 ARM ARM (DDI0487A.c).
-         */
-        int bas = extract64(bcr, 5, 4);
-        addr = bvr & ~3ULL;
-        if (bas == 0) {
-            return;
-        }
-        if (bas == 0xc) {
-            addr += 2;
-        }
-        break;
-    }
-    case 2: /* unlinked context ID match */
-    case 8: /* unlinked VMID match (reserved if no EL2) */
-    case 10: /* unlinked context ID and VMID match (reserved if no EL2) */
-        qemu_log_mask(LOG_UNIMP,
-                      "arm: unlinked context breakpoint types not implemented\n");
-        return;
-    case 9: /* linked VMID match (reserved if no EL2) */
-    case 11: /* linked context ID and VMID match (reserved if no EL2) */
-    case 3: /* linked context ID match */
-    default:
-        /* We must generate no events for Linked context matches (unless
-         * they are linked to by some other bp/wp, which is handled in
-         * updates for the linking bp/wp). We choose to also generate no events
-         * for reserved values.
-         */
-        return;
-    }
-
-    cpu_breakpoint_insert(CPU(cpu), addr, flags, &env->cpu_breakpoint[n]);
-}
-
-void hw_breakpoint_update_all(ARMCPU *cpu)
-{
-    int i;
-    CPUARMState *env = &cpu->env;
-
-    /* Completely clear out existing QEMU breakpoints and our array, to
-     * avoid possible stale entries following migration load.
-     */
-    cpu_breakpoint_remove_all(CPU(cpu), BP_CPU);
-    memset(env->cpu_breakpoint, 0, sizeof(env->cpu_breakpoint));
-
-    for (i = 0; i < ARRAY_SIZE(cpu->env.cpu_breakpoint); i++) {
-        hw_breakpoint_update(cpu, i);
-    }
-}
-
-static void dbgbvr_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                         uint64_t value)
-{
-    ARMCPU *cpu = env_archcpu(env);
-    int i = ri->crm;
-
-    raw_write(env, ri, value);
-    hw_breakpoint_update(cpu, i);
-}
-
-static void dbgbcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
-                         uint64_t value)
-{
-    ARMCPU *cpu = env_archcpu(env);
-    int i = ri->crm;
-
-    /* BAS[3] is a read-only copy of BAS[2], and BAS[1] a read-only
-     * copy of BAS[0].
-     */
-    value = deposit64(value, 6, 1, extract64(value, 5, 1));
-    value = deposit64(value, 8, 1, extract64(value, 7, 1));
-
-    raw_write(env, ri, value);
-    hw_breakpoint_update(cpu, i);
-}
-
-static void define_debug_regs(ARMCPU *cpu)
-{
-    /* Define v7 and v8 architectural debug registers.
-     * These are just dummy implementations for now.
-     */
-    int i;
-    int wrps, brps, ctx_cmps;
-
-    /*
-     * The Arm ARM says DBGDIDR is optional and deprecated if EL1 cannot
-     * use AArch32.  Given that bit 15 is RES1, if the value is 0 then
-     * the register must not exist for this cpu.
-     */
-    if (cpu->isar.dbgdidr != 0) {
-        ARMCPRegInfo dbgdidr = {
-            .name = "DBGDIDR", .cp = 14, .crn = 0, .crm = 0,
-            .opc1 = 0, .opc2 = 0,
-            .access = PL0_R, .accessfn = access_tda,
-            .type = ARM_CP_CONST, .resetvalue = cpu->isar.dbgdidr,
-        };
-        define_one_arm_cp_reg(cpu, &dbgdidr);
-    }
-
-    brps = arm_num_brps(cpu);
-    wrps = arm_num_wrps(cpu);
-    ctx_cmps = arm_num_ctx_cmps(cpu);
-
-    assert(ctx_cmps <= brps);
-
-    define_arm_cp_regs(cpu, debug_cp_reginfo);
-
-    if (arm_feature(&cpu->env, ARM_FEATURE_LPAE)) {
-        define_arm_cp_regs(cpu, debug_lpae_cp_reginfo);
-    }
-
-    for (i = 0; i < brps; i++) {
-        char *dbgbvr_el1_name = g_strdup_printf("DBGBVR%d_EL1", i);
-        char *dbgbcr_el1_name = g_strdup_printf("DBGBCR%d_EL1", i);
-        ARMCPRegInfo dbgregs[] = {
-            { .name = dbgbvr_el1_name, .state = ARM_CP_STATE_BOTH,
-              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 4,
-              .access = PL1_RW, .accessfn = access_tda,
-              .fieldoffset = offsetof(CPUARMState, cp15.dbgbvr[i]),
-              .writefn = dbgbvr_write, .raw_writefn = raw_write
-            },
-            { .name = dbgbcr_el1_name, .state = ARM_CP_STATE_BOTH,
-              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 5,
-              .access = PL1_RW, .accessfn = access_tda,
-              .fieldoffset = offsetof(CPUARMState, cp15.dbgbcr[i]),
-              .writefn = dbgbcr_write, .raw_writefn = raw_write
-            },
-        };
-        define_arm_cp_regs(cpu, dbgregs);
-        g_free(dbgbvr_el1_name);
-        g_free(dbgbcr_el1_name);
-    }
-
-    for (i = 0; i < wrps; i++) {
-        char *dbgwvr_el1_name = g_strdup_printf("DBGWVR%d_EL1", i);
-        char *dbgwcr_el1_name = g_strdup_printf("DBGWCR%d_EL1", i);
-        ARMCPRegInfo dbgregs[] = {
-            { .name = dbgwvr_el1_name, .state = ARM_CP_STATE_BOTH,
-              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 6,
-              .access = PL1_RW, .accessfn = access_tda,
-              .fieldoffset = offsetof(CPUARMState, cp15.dbgwvr[i]),
-              .writefn = dbgwvr_write, .raw_writefn = raw_write
-            },
-            { .name = dbgwcr_el1_name, .state = ARM_CP_STATE_BOTH,
-              .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 7,
-              .access = PL1_RW, .accessfn = access_tda,
-              .fieldoffset = offsetof(CPUARMState, cp15.dbgwcr[i]),
-              .writefn = dbgwcr_write, .raw_writefn = raw_write
-            },
-        };
-        define_arm_cp_regs(cpu, dbgregs);
-        g_free(dbgwvr_el1_name);
-        g_free(dbgwcr_el1_name);
-    }
-}
-
 static void define_pmu_regs(ARMCPU *cpu)
 {
     /*
diff --git a/target/arm/internals.h b/target/arm/internals.h
index c66f74a0db..00e2e710f6 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -1307,6 +1307,15 @@ int exception_target_el(CPUARMState *env);
 bool arm_singlestep_active(CPUARMState *env);
 bool arm_generate_debug_exceptions(CPUARMState *env);
 
+/* Add the cpreg definitions for debug related system registers */
+void define_debug_regs(ARMCPU *cpu);
+
+/* Effective value of MDCR_EL2 */
+static inline uint64_t arm_mdcr_el2_eff(CPUARMState *env)
+{
+    return arm_is_el2_enabled(env) ? env->cp15.mdcr_el2 : 0;
+}
+
 /* Powers of 2 for sve_vq_map et al. */
 #define SVE_VQ_POW2_MAP                                 \
     ((1 << (1 - 1)) | (1 << (2 - 1)) |                  \
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index da478104f0..e71fc1f429 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -1257,7 +1257,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
          * clear the lower bits here before ORing in the low vaddr bits.
          */
         page_size = (1ULL << ((stride * (4 - level)) + 3));
-        descaddr &= ~(page_size - 1);
+        descaddr &= ~(hwaddr)(page_size - 1);
         descaddr |= (address & (page_size - 1));
         /* Extract attributes from the descriptor */
         attrs = extract64(descriptor, 2, 10)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 1654c0bbf9..0c6379e6e8 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -5337,6 +5337,9 @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env,
 
 #ifdef CONFIG_USER_ONLY
     memset(&info->attrs, 0, sizeof(info->attrs));
+    /* Require both MAP_ANON and PROT_MTE -- see allocation_tag_mem. */
+    arm_tlb_mte_tagged(&info->attrs) =
+        (flags & PAGE_ANON) && (flags & PAGE_MTE);
 #else
     /*
      * Find the iotlbentry for addr and return the transaction attributes.
@@ -5986,7 +5989,7 @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr,
      * Disable MTE checking if the Tagged bit is not set.  Since TBI must
      * be set within MTEDESC for MTE, !mtedesc => !mte_active.
      */
-    if (arm_tlb_mte_tagged(&info.page[0].attrs)) {
+    if (!arm_tlb_mte_tagged(&info.page[0].attrs)) {
         mtedesc = 0;
     }