summary refs log tree commit diff stats
path: root/target/arm
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm')
-rw-r--r--target/arm/cpu.c25
-rw-r--r--target/arm/cpu.h21
-rw-r--r--target/arm/cpu64.c356
-rw-r--r--target/arm/helper.c10
-rw-r--r--target/arm/kvm.c25
-rw-r--r--target/arm/kvm32.c6
-rw-r--r--target/arm/kvm64.c323
-rw-r--r--target/arm/kvm_arm.h39
-rw-r--r--target/arm/monitor.c158
-rw-r--r--target/arm/translate-vfp.inc.c5
10 files changed, 913 insertions, 55 deletions
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index ab3e1a0361..7a4ac9339b 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -200,7 +200,8 @@ static void arm_cpu_reset(CPUState *s)
         env->cp15.cpacr_el1 = deposit64(env->cp15.cpacr_el1, 16, 2, 3);
         env->cp15.cptr_el[3] |= CPTR_EZ;
         /* with maximum vector length */
-        env->vfp.zcr_el[1] = cpu->sve_max_vq - 1;
+        env->vfp.zcr_el[1] = cpu_isar_feature(aa64_sve, cpu) ?
+                             cpu->sve_max_vq - 1 : 0;
         env->vfp.zcr_el[2] = env->vfp.zcr_el[1];
         env->vfp.zcr_el[3] = env->vfp.zcr_el[1];
         /*
@@ -1197,6 +1198,19 @@ static void arm_cpu_finalizefn(Object *obj)
 #endif
 }
 
+void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp)
+{
+    Error *local_err = NULL;
+
+    if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+        arm_cpu_sve_finalize(cpu, &local_err);
+        if (local_err != NULL) {
+            error_propagate(errp, local_err);
+            return;
+        }
+    }
+}
+
 static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
@@ -1253,6 +1267,12 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
         return;
     }
 
+    arm_cpu_finalize_features(cpu, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
     if (arm_feature(env, ARM_FEATURE_AARCH64) &&
         cpu->has_vfp != cpu->has_neon) {
         /*
@@ -2650,6 +2670,9 @@ static void arm_host_initfn(Object *obj)
     ARMCPU *cpu = ARM_CPU(obj);
 
     kvm_arm_set_cpu_features_from_host(cpu);
+    if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+        aarch64_add_sve_properties(obj);
+    }
     arm_cpu_post_init(obj);
 }
 
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index d844ea21d8..e1a66a2d1c 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -184,8 +184,13 @@ typedef struct {
 
 #ifdef TARGET_AARCH64
 # define ARM_MAX_VQ    16
+void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp);
+uint32_t arm_cpu_vq_map_next_smaller(ARMCPU *cpu, uint32_t vq);
 #else
 # define ARM_MAX_VQ    1
+static inline void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) { }
+static inline uint32_t arm_cpu_vq_map_next_smaller(ARMCPU *cpu, uint32_t vq)
+{ return 0; }
 #endif
 
 typedef struct ARMVectorReg {
@@ -918,6 +923,18 @@ struct ARMCPU {
 
     /* Used to set the maximum vector length the cpu will support.  */
     uint32_t sve_max_vq;
+
+    /*
+     * In sve_vq_map each set bit is a supported vector length of
+     * (bit-number + 1) * 16 bytes, i.e. each bit number + 1 is the vector
+     * length in quadwords.
+     *
+     * While processing properties during initialization, corresponding
+     * sve_vq_init bits are set for bits in sve_vq_map that have been
+     * set by properties.
+     */
+    DECLARE_BITMAP(sve_vq_map, ARM_MAX_VQ);
+    DECLARE_BITMAP(sve_vq_init, ARM_MAX_VQ);
 };
 
 void arm_cpu_post_init(Object *obj);
@@ -960,11 +977,13 @@ int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
 void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq);
 void aarch64_sve_change_el(CPUARMState *env, int old_el,
                            int new_el, bool el0_a64);
+void aarch64_add_sve_properties(Object *obj);
 #else
 static inline void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) { }
 static inline void aarch64_sve_change_el(CPUARMState *env, int o,
                                          int n, bool a)
 { }
+static inline void aarch64_add_sve_properties(Object *obj) { }
 #endif
 
 #if !defined(CONFIG_TCG)
@@ -1837,6 +1856,8 @@ static inline int arm_feature(CPUARMState *env, int feature)
     return (env->features & (1ULL << feature)) != 0;
 }
 
+void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp);
+
 #if !defined(CONFIG_USER_ONLY)
 /* Return true if exception levels below EL3 are in secure state,
  * or would be following an exception return to that level.
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index d7f5bf610a..68baf0482f 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -256,27 +256,357 @@ static void aarch64_a72_initfn(Object *obj)
     define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
 }
 
-static void cpu_max_get_sve_vq(Object *obj, Visitor *v, const char *name,
+void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
+{
+    /*
+     * If any vector lengths are explicitly enabled with sve<N> properties,
+     * then all other lengths are implicitly disabled.  If sve-max-vq is
+     * specified then it is the same as explicitly enabling all lengths
+     * up to and including the specified maximum, which means all larger
+     * lengths will be implicitly disabled.  If no sve<N> properties
+     * are enabled and sve-max-vq is not specified, then all lengths not
+     * explicitly disabled will be enabled.  Additionally, all power-of-two
+     * vector lengths less than the maximum enabled length will be
+     * automatically enabled and all vector lengths larger than the largest
+     * disabled power-of-two vector length will be automatically disabled.
+     * Errors are generated if the user provided input that interferes with
+     * any of the above.  Finally, if SVE is not disabled, then at least one
+     * vector length must be enabled.
+     */
+    DECLARE_BITMAP(kvm_supported, ARM_MAX_VQ);
+    DECLARE_BITMAP(tmp, ARM_MAX_VQ);
+    uint32_t vq, max_vq = 0;
+
+    /* Collect the set of vector lengths supported by KVM. */
+    bitmap_zero(kvm_supported, ARM_MAX_VQ);
+    if (kvm_enabled() && kvm_arm_sve_supported(CPU(cpu))) {
+        kvm_arm_sve_get_vls(CPU(cpu), kvm_supported);
+    } else if (kvm_enabled()) {
+        assert(!cpu_isar_feature(aa64_sve, cpu));
+    }
+
+    /*
+     * Process explicit sve<N> properties.
+     * From the properties, sve_vq_map<N> implies sve_vq_init<N>.
+     * Check first for any sve<N> enabled.
+     */
+    if (!bitmap_empty(cpu->sve_vq_map, ARM_MAX_VQ)) {
+        max_vq = find_last_bit(cpu->sve_vq_map, ARM_MAX_VQ) + 1;
+
+        if (cpu->sve_max_vq && max_vq > cpu->sve_max_vq) {
+            error_setg(errp, "cannot enable sve%d", max_vq * 128);
+            error_append_hint(errp, "sve%d is larger than the maximum vector "
+                              "length, sve-max-vq=%d (%d bits)\n",
+                              max_vq * 128, cpu->sve_max_vq,
+                              cpu->sve_max_vq * 128);
+            return;
+        }
+
+        if (kvm_enabled()) {
+            /*
+             * For KVM we have to automatically enable all supported unitialized
+             * lengths, even when the smaller lengths are not all powers-of-two.
+             */
+            bitmap_andnot(tmp, kvm_supported, cpu->sve_vq_init, max_vq);
+            bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq);
+        } else {
+            /* Propagate enabled bits down through required powers-of-two. */
+            for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) {
+                if (!test_bit(vq - 1, cpu->sve_vq_init)) {
+                    set_bit(vq - 1, cpu->sve_vq_map);
+                }
+            }
+        }
+    } else if (cpu->sve_max_vq == 0) {
+        /*
+         * No explicit bits enabled, and no implicit bits from sve-max-vq.
+         */
+        if (!cpu_isar_feature(aa64_sve, cpu)) {
+            /* SVE is disabled and so are all vector lengths.  Good. */
+            return;
+        }
+
+        if (kvm_enabled()) {
+            /* Disabling a supported length disables all larger lengths. */
+            for (vq = 1; vq <= ARM_MAX_VQ; ++vq) {
+                if (test_bit(vq - 1, cpu->sve_vq_init) &&
+                    test_bit(vq - 1, kvm_supported)) {
+                    break;
+                }
+            }
+            max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ;
+            bitmap_andnot(cpu->sve_vq_map, kvm_supported,
+                          cpu->sve_vq_init, max_vq);
+            if (max_vq == 0 || bitmap_empty(cpu->sve_vq_map, max_vq)) {
+                error_setg(errp, "cannot disable sve%d", vq * 128);
+                error_append_hint(errp, "Disabling sve%d results in all "
+                                  "vector lengths being disabled.\n",
+                                  vq * 128);
+                error_append_hint(errp, "With SVE enabled, at least one "
+                                  "vector length must be enabled.\n");
+                return;
+            }
+        } else {
+            /* Disabling a power-of-two disables all larger lengths. */
+            if (test_bit(0, cpu->sve_vq_init)) {
+                error_setg(errp, "cannot disable sve128");
+                error_append_hint(errp, "Disabling sve128 results in all "
+                                  "vector lengths being disabled.\n");
+                error_append_hint(errp, "With SVE enabled, at least one "
+                                  "vector length must be enabled.\n");
+                return;
+            }
+            for (vq = 2; vq <= ARM_MAX_VQ; vq <<= 1) {
+                if (test_bit(vq - 1, cpu->sve_vq_init)) {
+                    break;
+                }
+            }
+            max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ;
+            bitmap_complement(cpu->sve_vq_map, cpu->sve_vq_init, max_vq);
+        }
+
+        max_vq = find_last_bit(cpu->sve_vq_map, max_vq) + 1;
+    }
+
+    /*
+     * Process the sve-max-vq property.
+     * Note that we know from the above that no bit above
+     * sve-max-vq is currently set.
+     */
+    if (cpu->sve_max_vq != 0) {
+        max_vq = cpu->sve_max_vq;
+
+        if (!test_bit(max_vq - 1, cpu->sve_vq_map) &&
+            test_bit(max_vq - 1, cpu->sve_vq_init)) {
+            error_setg(errp, "cannot disable sve%d", max_vq * 128);
+            error_append_hint(errp, "The maximum vector length must be "
+                              "enabled, sve-max-vq=%d (%d bits)\n",
+                              max_vq, max_vq * 128);
+            return;
+        }
+
+        /* Set all bits not explicitly set within sve-max-vq. */
+        bitmap_complement(tmp, cpu->sve_vq_init, max_vq);
+        bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq);
+    }
+
+    /*
+     * We should know what max-vq is now.  Also, as we're done
+     * manipulating sve-vq-map, we ensure any bits above max-vq
+     * are clear, just in case anybody looks.
+     */
+    assert(max_vq != 0);
+    bitmap_clear(cpu->sve_vq_map, max_vq, ARM_MAX_VQ - max_vq);
+
+    if (kvm_enabled()) {
+        /* Ensure the set of lengths matches what KVM supports. */
+        bitmap_xor(tmp, cpu->sve_vq_map, kvm_supported, max_vq);
+        if (!bitmap_empty(tmp, max_vq)) {
+            vq = find_last_bit(tmp, max_vq) + 1;
+            if (test_bit(vq - 1, cpu->sve_vq_map)) {
+                if (cpu->sve_max_vq) {
+                    error_setg(errp, "cannot set sve-max-vq=%d",
+                               cpu->sve_max_vq);
+                    error_append_hint(errp, "This KVM host does not support "
+                                      "the vector length %d-bits.\n",
+                                      vq * 128);
+                    error_append_hint(errp, "It may not be possible to use "
+                                      "sve-max-vq with this KVM host. Try "
+                                      "using only sve<N> properties.\n");
+                } else {
+                    error_setg(errp, "cannot enable sve%d", vq * 128);
+                    error_append_hint(errp, "This KVM host does not support "
+                                      "the vector length %d-bits.\n",
+                                      vq * 128);
+                }
+            } else {
+                error_setg(errp, "cannot disable sve%d", vq * 128);
+                error_append_hint(errp, "The KVM host requires all "
+                                  "supported vector lengths smaller "
+                                  "than %d bits to also be enabled.\n",
+                                  max_vq * 128);
+            }
+            return;
+        }
+    } else {
+        /* Ensure all required powers-of-two are enabled. */
+        for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) {
+            if (!test_bit(vq - 1, cpu->sve_vq_map)) {
+                error_setg(errp, "cannot disable sve%d", vq * 128);
+                error_append_hint(errp, "sve%d is required as it "
+                                  "is a power-of-two length smaller than "
+                                  "the maximum, sve%d\n",
+                                  vq * 128, max_vq * 128);
+                return;
+            }
+        }
+    }
+
+    /*
+     * Now that we validated all our vector lengths, the only question
+     * left to answer is if we even want SVE at all.
+     */
+    if (!cpu_isar_feature(aa64_sve, cpu)) {
+        error_setg(errp, "cannot enable sve%d", max_vq * 128);
+        error_append_hint(errp, "SVE must be enabled to enable vector "
+                          "lengths.\n");
+        error_append_hint(errp, "Add sve=on to the CPU property list.\n");
+        return;
+    }
+
+    /* From now on sve_max_vq is the actual maximum supported length. */
+    cpu->sve_max_vq = max_vq;
+}
+
+uint32_t arm_cpu_vq_map_next_smaller(ARMCPU *cpu, uint32_t vq)
+{
+    uint32_t bitnum;
+
+    /*
+     * We allow vq == ARM_MAX_VQ + 1 to be input because the caller may want
+     * to find the maximum vq enabled, which may be ARM_MAX_VQ, but this
+     * function always returns the next smaller than the input.
+     */
+    assert(vq && vq <= ARM_MAX_VQ + 1);
+
+    bitnum = find_last_bit(cpu->sve_vq_map, vq - 1);
+    return bitnum == vq - 1 ? 0 : bitnum + 1;
+}
+
+static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name,
+                                   void *opaque, Error **errp)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    uint32_t value;
+
+    /* All vector lengths are disabled when SVE is off. */
+    if (!cpu_isar_feature(aa64_sve, cpu)) {
+        value = 0;
+    } else {
+        value = cpu->sve_max_vq;
+    }
+    visit_type_uint32(v, name, &value, errp);
+}
+
+static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name,
+                                   void *opaque, Error **errp)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    Error *err = NULL;
+    uint32_t max_vq;
+
+    visit_type_uint32(v, name, &max_vq, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    if (kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
+        error_setg(errp, "cannot set sve-max-vq");
+        error_append_hint(errp, "SVE not supported by KVM on this host\n");
+        return;
+    }
+
+    if (max_vq == 0 || max_vq > ARM_MAX_VQ) {
+        error_setg(errp, "unsupported SVE vector length");
+        error_append_hint(errp, "Valid sve-max-vq in range [1-%d]\n",
+                          ARM_MAX_VQ);
+        return;
+    }
+
+    cpu->sve_max_vq = max_vq;
+}
+
+static void cpu_arm_get_sve_vq(Object *obj, Visitor *v, const char *name,
                                void *opaque, Error **errp)
 {
     ARMCPU *cpu = ARM_CPU(obj);
-    visit_type_uint32(v, name, &cpu->sve_max_vq, errp);
+    uint32_t vq = atoi(&name[3]) / 128;
+    bool value;
+
+    /* All vector lengths are disabled when SVE is off. */
+    if (!cpu_isar_feature(aa64_sve, cpu)) {
+        value = false;
+    } else {
+        value = test_bit(vq - 1, cpu->sve_vq_map);
+    }
+    visit_type_bool(v, name, &value, errp);
 }
 
-static void cpu_max_set_sve_vq(Object *obj, Visitor *v, const char *name,
+static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name,
                                void *opaque, Error **errp)
 {
     ARMCPU *cpu = ARM_CPU(obj);
+    uint32_t vq = atoi(&name[3]) / 128;
     Error *err = NULL;
+    bool value;
 
-    visit_type_uint32(v, name, &cpu->sve_max_vq, &err);
+    visit_type_bool(v, name, &value, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
 
-    if (!err && (cpu->sve_max_vq == 0 || cpu->sve_max_vq > ARM_MAX_VQ)) {
-        error_setg(&err, "unsupported SVE vector length");
-        error_append_hint(&err, "Valid sve-max-vq in range [1-%d]\n",
-                          ARM_MAX_VQ);
+    if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
+        error_setg(errp, "cannot enable %s", name);
+        error_append_hint(errp, "SVE not supported by KVM on this host\n");
+        return;
+    }
+
+    if (value) {
+        set_bit(vq - 1, cpu->sve_vq_map);
+    } else {
+        clear_bit(vq - 1, cpu->sve_vq_map);
+    }
+    set_bit(vq - 1, cpu->sve_vq_init);
+}
+
+static void cpu_arm_get_sve(Object *obj, Visitor *v, const char *name,
+                            void *opaque, Error **errp)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    bool value = cpu_isar_feature(aa64_sve, cpu);
+
+    visit_type_bool(v, name, &value, errp);
+}
+
+static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name,
+                            void *opaque, Error **errp)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    Error *err = NULL;
+    bool value;
+    uint64_t t;
+
+    visit_type_bool(v, name, &value, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
+        error_setg(errp, "'sve' feature not supported by KVM on this host");
+        return;
+    }
+
+    t = cpu->isar.id_aa64pfr0;
+    t = FIELD_DP64(t, ID_AA64PFR0, SVE, value);
+    cpu->isar.id_aa64pfr0 = t;
+}
+
+void aarch64_add_sve_properties(Object *obj)
+{
+    uint32_t vq;
+
+    object_property_add(obj, "sve", "bool", cpu_arm_get_sve,
+                        cpu_arm_set_sve, NULL, NULL, &error_fatal);
+
+    for (vq = 1; vq <= ARM_MAX_VQ; ++vq) {
+        char name[8];
+        sprintf(name, "sve%d", vq * 128);
+        object_property_add(obj, name, "bool", cpu_arm_get_sve_vq,
+                            cpu_arm_set_sve_vq, NULL, NULL, &error_fatal);
     }
-    error_propagate(errp, err);
 }
 
 /* -cpu max: if KVM is enabled, like -cpu host (best possible with this host);
@@ -389,11 +719,11 @@ static void aarch64_max_initfn(Object *obj)
         cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */
         cpu->dcz_blocksize = 7; /*  512 bytes */
 #endif
-
-        cpu->sve_max_vq = ARM_MAX_VQ;
-        object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_vq,
-                            cpu_max_set_sve_vq, NULL, NULL, &error_fatal);
     }
+
+    aarch64_add_sve_properties(obj);
+    object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq,
+                        cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal);
 }
 
 struct ARMCPUInfo {
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 63815fc4cf..be67e2c66d 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -5361,6 +5361,13 @@ int sve_exception_el(CPUARMState *env, int el)
     return 0;
 }
 
+static uint32_t sve_zcr_get_valid_len(ARMCPU *cpu, uint32_t start_len)
+{
+    uint32_t start_vq = (start_len & 0xf) + 1;
+
+    return arm_cpu_vq_map_next_smaller(cpu, start_vq + 1) - 1;
+}
+
 /*
  * Given that SVE is enabled, return the vector length for EL.
  */
@@ -5378,7 +5385,8 @@ uint32_t sve_zcr_len_for_el(CPUARMState *env, int el)
     if (arm_feature(env, ARM_FEATURE_EL3)) {
         zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]);
     }
-    return zcr_len;
+
+    return sve_zcr_get_valid_len(cpu, zcr_len);
 }
 
 static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index b473c63edb..5b82cefef6 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -51,6 +51,11 @@ int kvm_arm_vcpu_init(CPUState *cs)
     return kvm_vcpu_ioctl(cs, KVM_ARM_VCPU_INIT, &init);
 }
 
+int kvm_arm_vcpu_finalize(CPUState *cs, int feature)
+{
+    return kvm_vcpu_ioctl(cs, KVM_ARM_VCPU_FINALIZE, &feature);
+}
+
 void kvm_arm_init_serror_injection(CPUState *cs)
 {
     cap_has_inject_serror_esr = kvm_check_extension(cs->kvm_state,
@@ -61,7 +66,7 @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try,
                                       int *fdarray,
                                       struct kvm_vcpu_init *init)
 {
-    int ret, kvmfd = -1, vmfd = -1, cpufd = -1;
+    int ret = 0, kvmfd = -1, vmfd = -1, cpufd = -1;
 
     kvmfd = qemu_open("/dev/kvm", O_RDWR);
     if (kvmfd < 0) {
@@ -81,7 +86,14 @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try,
         goto finish;
     }
 
-    ret = ioctl(vmfd, KVM_ARM_PREFERRED_TARGET, init);
+    if (init->target == -1) {
+        struct kvm_vcpu_init preferred;
+
+        ret = ioctl(vmfd, KVM_ARM_PREFERRED_TARGET, &preferred);
+        if (!ret) {
+            init->target = preferred.target;
+        }
+    }
     if (ret >= 0) {
         ret = ioctl(cpufd, KVM_ARM_VCPU_INIT, init);
         if (ret < 0) {
@@ -93,10 +105,12 @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try,
          * creating one kind of guest CPU which is its preferred
          * CPU type.
          */
+        struct kvm_vcpu_init try;
+
         while (*cpus_to_try != QEMU_KVM_ARM_TARGET_NONE) {
-            init->target = *cpus_to_try++;
-            memset(init->features, 0, sizeof(init->features));
-            ret = ioctl(cpufd, KVM_ARM_VCPU_INIT, init);
+            try.target = *cpus_to_try++;
+            memcpy(try.features, init->features, sizeof(init->features));
+            ret = ioctl(cpufd, KVM_ARM_VCPU_INIT, &try);
             if (ret >= 0) {
                 break;
             }
@@ -104,6 +118,7 @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try,
         if (ret < 0) {
             goto err;
         }
+        init->target = try.target;
     } else {
         /* Treat a NULL cpus_to_try argument the same as an empty
          * list, which means we will fail the call since this must
diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c
index 2451a2d4bb..32bf8d6757 100644
--- a/target/arm/kvm32.c
+++ b/target/arm/kvm32.c
@@ -53,7 +53,11 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
         QEMU_KVM_ARM_TARGET_CORTEX_A15,
         QEMU_KVM_ARM_TARGET_NONE
     };
-    struct kvm_vcpu_init init;
+    /*
+     * target = -1 informs kvm_arm_create_scratch_host_vcpu()
+     * to use the preferred target
+     */
+    struct kvm_vcpu_init init = { .target = -1, };
 
     if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) {
         return false;
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
index 28f6db57d5..876184b8fe 100644
--- a/target/arm/kvm64.c
+++ b/target/arm/kvm64.c
@@ -488,7 +488,9 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
      * and then query that CPU for the relevant ID registers.
      */
     int fdarray[3];
+    bool sve_supported;
     uint64_t features = 0;
+    uint64_t t;
     int err;
 
     /* Old kernels may not know about the PREFERRED_TARGET ioctl: however
@@ -502,7 +504,11 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
         KVM_ARM_TARGET_CORTEX_A57,
         QEMU_KVM_ARM_TARGET_NONE
     };
-    struct kvm_vcpu_init init;
+    /*
+     * target = -1 informs kvm_arm_create_scratch_host_vcpu()
+     * to use the preferred target
+     */
+    struct kvm_vcpu_init init = { .target = -1, };
 
     if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) {
         return false;
@@ -574,13 +580,23 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
                               ARM64_SYS_REG(3, 0, 0, 3, 2));
     }
 
+    sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0;
+
     kvm_arm_destroy_scratch_host_vcpu(fdarray);
 
     if (err < 0) {
         return false;
     }
 
-   /* We can assume any KVM supporting CPU is at least a v8
+    /* Add feature bits that can't appear until after VCPU init. */
+    if (sve_supported) {
+        t = ahcf->isar.id_aa64pfr0;
+        t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1);
+        ahcf->isar.id_aa64pfr0 = t;
+    }
+
+    /*
+     * We can assume any KVM supporting CPU is at least a v8
      * with VFPv4+Neon; this in turn implies most of the other
      * feature bits.
      */
@@ -602,6 +618,107 @@ bool kvm_arm_aarch32_supported(CPUState *cpu)
     return kvm_check_extension(s, KVM_CAP_ARM_EL1_32BIT);
 }
 
+bool kvm_arm_sve_supported(CPUState *cpu)
+{
+    KVMState *s = KVM_STATE(current_machine->accelerator);
+
+    return kvm_check_extension(s, KVM_CAP_ARM_SVE);
+}
+
+QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1);
+
+void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map)
+{
+    /* Only call this function if kvm_arm_sve_supported() returns true. */
+    static uint64_t vls[KVM_ARM64_SVE_VLS_WORDS];
+    static bool probed;
+    uint32_t vq = 0;
+    int i, j;
+
+    bitmap_clear(map, 0, ARM_MAX_VQ);
+
+    /*
+     * KVM ensures all host CPUs support the same set of vector lengths.
+     * So we only need to create the scratch VCPUs once and then cache
+     * the results.
+     */
+    if (!probed) {
+        struct kvm_vcpu_init init = {
+            .target = -1,
+            .features[0] = (1 << KVM_ARM_VCPU_SVE),
+        };
+        struct kvm_one_reg reg = {
+            .id = KVM_REG_ARM64_SVE_VLS,
+            .addr = (uint64_t)&vls[0],
+        };
+        int fdarray[3], ret;
+
+        probed = true;
+
+        if (!kvm_arm_create_scratch_host_vcpu(NULL, fdarray, &init)) {
+            error_report("failed to create scratch VCPU with SVE enabled");
+            abort();
+        }
+        ret = ioctl(fdarray[2], KVM_GET_ONE_REG, &reg);
+        kvm_arm_destroy_scratch_host_vcpu(fdarray);
+        if (ret) {
+            error_report("failed to get KVM_REG_ARM64_SVE_VLS: %s",
+                         strerror(errno));
+            abort();
+        }
+
+        for (i = KVM_ARM64_SVE_VLS_WORDS - 1; i >= 0; --i) {
+            if (vls[i]) {
+                vq = 64 - clz64(vls[i]) + i * 64;
+                break;
+            }
+        }
+        if (vq > ARM_MAX_VQ) {
+            warn_report("KVM supports vector lengths larger than "
+                        "QEMU can enable");
+        }
+    }
+
+    for (i = 0; i < KVM_ARM64_SVE_VLS_WORDS; ++i) {
+        if (!vls[i]) {
+            continue;
+        }
+        for (j = 1; j <= 64; ++j) {
+            vq = j + i * 64;
+            if (vq > ARM_MAX_VQ) {
+                return;
+            }
+            if (vls[i] & (1UL << (j - 1))) {
+                set_bit(vq - 1, map);
+            }
+        }
+    }
+}
+
+static int kvm_arm_sve_set_vls(CPUState *cs)
+{
+    uint64_t vls[KVM_ARM64_SVE_VLS_WORDS] = {0};
+    struct kvm_one_reg reg = {
+        .id = KVM_REG_ARM64_SVE_VLS,
+        .addr = (uint64_t)&vls[0],
+    };
+    ARMCPU *cpu = ARM_CPU(cs);
+    uint32_t vq;
+    int i, j;
+
+    assert(cpu->sve_max_vq <= KVM_ARM64_SVE_VQ_MAX);
+
+    for (vq = 1; vq <= cpu->sve_max_vq; ++vq) {
+        if (test_bit(vq - 1, cpu->sve_vq_map)) {
+            i = (vq - 1) / 64;
+            j = (vq - 1) % 64;
+            vls[i] |= 1UL << j;
+        }
+    }
+
+    return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+}
+
 #define ARM_CPU_ID_MPIDR       3, 0, 0, 0, 5
 
 int kvm_arch_init_vcpu(CPUState *cs)
@@ -613,7 +730,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
 
     if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE ||
         !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) {
-        fprintf(stderr, "KVM is not supported for this guest CPU type\n");
+        error_report("KVM is not supported for this guest CPU type");
         return -EINVAL;
     }
 
@@ -630,13 +747,17 @@ int kvm_arch_init_vcpu(CPUState *cs)
         cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_EL1_32BIT;
     }
     if (!kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PMU_V3)) {
-            cpu->has_pmu = false;
+        cpu->has_pmu = false;
     }
     if (cpu->has_pmu) {
         cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PMU_V3;
     } else {
         unset_feature(&env->features, ARM_FEATURE_PMU);
     }
+    if (cpu_isar_feature(aa64_sve, cpu)) {
+        assert(kvm_arm_sve_supported(cs));
+        cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_SVE;
+    }
 
     /* Do KVM_ARM_VCPU_INIT ioctl */
     ret = kvm_arm_vcpu_init(cs);
@@ -644,6 +765,17 @@ int kvm_arch_init_vcpu(CPUState *cs)
         return ret;
     }
 
+    if (cpu_isar_feature(aa64_sve, cpu)) {
+        ret = kvm_arm_sve_set_vls(cs);
+        if (ret) {
+            return ret;
+        }
+        ret = kvm_arm_vcpu_finalize(cs, KVM_ARM_VCPU_SVE);
+        if (ret) {
+            return ret;
+        }
+    }
+
     /*
      * When KVM is in use, PSCI is emulated in-kernel and not by qemu.
      * Currently KVM has its own idea about MPIDR assignment, so we
@@ -671,11 +803,12 @@ int kvm_arch_destroy_vcpu(CPUState *cs)
 bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx)
 {
     /* Return true if the regidx is a register we should synchronize
-     * via the cpreg_tuples array (ie is not a core reg we sync by
-     * hand in kvm_arch_get/put_registers())
+     * via the cpreg_tuples array (ie is not a core or sve reg that
+     * we sync by hand in kvm_arch_get/put_registers())
      */
     switch (regidx & KVM_REG_ARM_COPROC_MASK) {
     case KVM_REG_ARM_CORE:
+    case KVM_REG_ARM64_SVE:
         return false;
     default:
         return true;
@@ -721,10 +854,8 @@ int kvm_arm_cpreg_level(uint64_t regidx)
 
 static int kvm_arch_put_fpsimd(CPUState *cs)
 {
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
+    CPUARMState *env = &ARM_CPU(cs)->env;
     struct kvm_one_reg reg;
-    uint32_t fpr;
     int i, ret;
 
     for (i = 0; i < 32; i++) {
@@ -742,17 +873,73 @@ static int kvm_arch_put_fpsimd(CPUState *cs)
         }
     }
 
-    reg.addr = (uintptr_t)(&fpr);
-    fpr = vfp_get_fpsr(env);
-    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
-    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
-    if (ret) {
-        return ret;
+    return 0;
+}
+
+/*
+ * SVE registers are encoded in KVM's memory in an endianness-invariant format.
+ * The byte at offset i from the start of the in-memory representation contains
+ * the bits [(7 + 8 * i) : (8 * i)] of the register value. As this means the
+ * lowest offsets are stored in the lowest memory addresses, then that nearly
+ * matches QEMU's representation, which is to use an array of host-endian
+ * uint64_t's, where the lower offsets are at the lower indices. To complete
+ * the translation we just need to byte swap the uint64_t's on big-endian hosts.
+ */
+static uint64_t *sve_bswap64(uint64_t *dst, uint64_t *src, int nr)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+    int i;
+
+    for (i = 0; i < nr; ++i) {
+        dst[i] = bswap64(src[i]);
     }
 
-    reg.addr = (uintptr_t)(&fpr);
-    fpr = vfp_get_fpcr(env);
-    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
+    return dst;
+#else
+    return src;
+#endif
+}
+
+/*
+ * KVM SVE registers come in slices where ZREGs have a slice size of 2048 bits
+ * and PREGS and the FFR have a slice size of 256 bits. However we simply hard
+ * code the slice index to zero for now as it's unlikely we'll need more than
+ * one slice for quite some time.
+ */
+static int kvm_arch_put_sve(CPUState *cs)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+    CPUARMState *env = &cpu->env;
+    uint64_t tmp[ARM_MAX_VQ * 2];
+    uint64_t *r;
+    struct kvm_one_reg reg;
+    int n, ret;
+
+    for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) {
+        r = sve_bswap64(tmp, &env->vfp.zregs[n].d[0], cpu->sve_max_vq * 2);
+        reg.addr = (uintptr_t)r;
+        reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0);
+        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+        if (ret) {
+            return ret;
+        }
+    }
+
+    for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) {
+        r = sve_bswap64(tmp, r = &env->vfp.pregs[n].p[0],
+                        DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
+        reg.addr = (uintptr_t)r;
+        reg.id = KVM_REG_ARM64_SVE_PREG(n, 0);
+        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+        if (ret) {
+            return ret;
+        }
+    }
+
+    r = sve_bswap64(tmp, &env->vfp.pregs[FFR_PRED_NUM].p[0],
+                    DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
+    reg.addr = (uintptr_t)r;
+    reg.id = KVM_REG_ARM64_SVE_FFR(0);
     ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
     if (ret) {
         return ret;
@@ -765,6 +952,7 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 {
     struct kvm_one_reg reg;
     uint64_t val;
+    uint32_t fpr;
     int i, ret;
     unsigned int el;
 
@@ -855,7 +1043,27 @@ int kvm_arch_put_registers(CPUState *cs, int level)
         }
     }
 
-    ret = kvm_arch_put_fpsimd(cs);
+    if (cpu_isar_feature(aa64_sve, cpu)) {
+        ret = kvm_arch_put_sve(cs);
+    } else {
+        ret = kvm_arch_put_fpsimd(cs);
+    }
+    if (ret) {
+        return ret;
+    }
+
+    reg.addr = (uintptr_t)(&fpr);
+    fpr = vfp_get_fpsr(env);
+    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
+    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+    if (ret) {
+        return ret;
+    }
+
+    reg.addr = (uintptr_t)(&fpr);
+    fpr = vfp_get_fpcr(env);
+    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
+    ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
     if (ret) {
         return ret;
     }
@@ -878,10 +1086,8 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 
 static int kvm_arch_get_fpsimd(CPUState *cs)
 {
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
+    CPUARMState *env = &ARM_CPU(cs)->env;
     struct kvm_one_reg reg;
-    uint32_t fpr;
     int i, ret;
 
     for (i = 0; i < 32; i++) {
@@ -899,21 +1105,53 @@ static int kvm_arch_get_fpsimd(CPUState *cs)
         }
     }
 
-    reg.addr = (uintptr_t)(&fpr);
-    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
-    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
-    if (ret) {
-        return ret;
+    return 0;
+}
+
+/*
+ * KVM SVE registers come in slices where ZREGs have a slice size of 2048 bits
+ * and PREGS and the FFR have a slice size of 256 bits. However we simply hard
+ * code the slice index to zero for now as it's unlikely we'll need more than
+ * one slice for quite some time.
+ */
+static int kvm_arch_get_sve(CPUState *cs)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+    CPUARMState *env = &cpu->env;
+    struct kvm_one_reg reg;
+    uint64_t *r;
+    int n, ret;
+
+    for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) {
+        r = &env->vfp.zregs[n].d[0];
+        reg.addr = (uintptr_t)r;
+        reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0);
+        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+        if (ret) {
+            return ret;
+        }
+        sve_bswap64(r, r, cpu->sve_max_vq * 2);
     }
-    vfp_set_fpsr(env, fpr);
 
-    reg.addr = (uintptr_t)(&fpr);
-    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
+    for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) {
+        r = &env->vfp.pregs[n].p[0];
+        reg.addr = (uintptr_t)r;
+        reg.id = KVM_REG_ARM64_SVE_PREG(n, 0);
+        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+        if (ret) {
+            return ret;
+        }
+        sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
+    }
+
+    r = &env->vfp.pregs[FFR_PRED_NUM].p[0];
+    reg.addr = (uintptr_t)r;
+    reg.id = KVM_REG_ARM64_SVE_FFR(0);
     ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
     if (ret) {
         return ret;
     }
-    vfp_set_fpcr(env, fpr);
+    sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
 
     return 0;
 }
@@ -923,6 +1161,7 @@ int kvm_arch_get_registers(CPUState *cs)
     struct kvm_one_reg reg;
     uint64_t val;
     unsigned int el;
+    uint32_t fpr;
     int i, ret;
 
     ARMCPU *cpu = ARM_CPU(cs);
@@ -1012,10 +1251,30 @@ int kvm_arch_get_registers(CPUState *cs)
         env->spsr = env->banked_spsr[i];
     }
 
-    ret = kvm_arch_get_fpsimd(cs);
+    if (cpu_isar_feature(aa64_sve, cpu)) {
+        ret = kvm_arch_get_sve(cs);
+    } else {
+        ret = kvm_arch_get_fpsimd(cs);
+    }
+    if (ret) {
+        return ret;
+    }
+
+    reg.addr = (uintptr_t)(&fpr);
+    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
+    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+    if (ret) {
+        return ret;
+    }
+    vfp_set_fpsr(env, fpr);
+
+    reg.addr = (uintptr_t)(&fpr);
+    reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
+    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
     if (ret) {
         return ret;
     }
+    vfp_set_fpcr(env, fpr);
 
     ret = kvm_get_vcpu_events(cpu);
     if (ret) {
diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h
index b4e19457a0..8e14d400e8 100644
--- a/target/arm/kvm_arm.h
+++ b/target/arm/kvm_arm.h
@@ -28,6 +28,20 @@
 int kvm_arm_vcpu_init(CPUState *cs);
 
 /**
+ * kvm_arm_vcpu_finalize
+ * @cs: CPUState
+ * @feature: int
+ *
+ * Finalizes the configuration of the specified VCPU feature by
+ * invoking the KVM_ARM_VCPU_FINALIZE ioctl. Features requiring
+ * this are documented in the "KVM_ARM_VCPU_FINALIZE" section of
+ * KVM's API documentation.
+ *
+ * Returns: 0 if success else < 0 error code
+ */
+int kvm_arm_vcpu_finalize(CPUState *cs, int feature);
+
+/**
  * kvm_arm_register_device:
  * @mr: memory region for this device
  * @devid: the KVM device ID
@@ -199,6 +213,17 @@ typedef struct ARMHostCPUFeatures {
 bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf);
 
 /**
+ * kvm_arm_sve_get_vls:
+ * @cs: CPUState
+ * @map: bitmap to fill in
+ *
+ * Get all the SVE vector lengths supported by the KVM host, setting
+ * the bits corresponding to their length in quadwords minus one
+ * (vq - 1) in @map up to ARM_MAX_VQ.
+ */
+void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map);
+
+/**
  * kvm_arm_set_cpu_features_from_host:
  * @cpu: ARMCPU to set the features for
  *
@@ -226,6 +251,14 @@ bool kvm_arm_aarch32_supported(CPUState *cs);
 bool kvm_arm_pmu_supported(CPUState *cs);
 
 /**
+ * bool kvm_arm_sve_supported:
+ * @cs: CPUState
+ *
+ * Returns true if the KVM VCPU can enable SVE and false otherwise.
+ */
+bool kvm_arm_sve_supported(CPUState *cs);
+
+/**
  * kvm_arm_get_max_vm_ipa_size - Returns the number of bits in the
  * IPA address space supported by KVM
  *
@@ -276,6 +309,11 @@ static inline bool kvm_arm_pmu_supported(CPUState *cs)
     return false;
 }
 
+static inline bool kvm_arm_sve_supported(CPUState *cs)
+{
+    return false;
+}
+
 static inline int kvm_arm_get_max_vm_ipa_size(MachineState *ms)
 {
     return -ENOENT;
@@ -289,6 +327,7 @@ static inline int kvm_arm_vgic_probe(void)
 static inline void kvm_arm_pmu_set_irq(CPUState *cs, int irq) {}
 static inline void kvm_arm_pmu_init(CPUState *cs) {}
 
+static inline void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map) {}
 #endif
 
 static inline const char *gic_class_name(void)
diff --git a/target/arm/monitor.c b/target/arm/monitor.c
index 6457c3c87f..fa054f8a36 100644
--- a/target/arm/monitor.c
+++ b/target/arm/monitor.c
@@ -21,8 +21,16 @@
  */
 
 #include "qemu/osdep.h"
+#include "hw/boards.h"
 #include "kvm_arm.h"
+#include "qapi/error.h"
+#include "qapi/visitor.h"
+#include "qapi/qobject-input-visitor.h"
+#include "qapi/qapi-commands-machine-target.h"
 #include "qapi/qapi-commands-misc-target.h"
+#include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qdict.h"
+#include "qom/qom-qobject.h"
 
 static GICCapability *gic_cap_new(int version)
 {
@@ -81,3 +89,153 @@ GICCapabilityList *qmp_query_gic_capabilities(Error **errp)
 
     return head;
 }
+
+QEMU_BUILD_BUG_ON(ARM_MAX_VQ > 16);
+
+/*
+ * These are cpu model features we want to advertise. The order here
+ * matters as this is the order in which qmp_query_cpu_model_expansion
+ * will attempt to set them. If there are dependencies between features,
+ * then the order that considers those dependencies must be used.
+ */
+static const char *cpu_model_advertised_features[] = {
+    "aarch64", "pmu", "sve",
+    "sve128", "sve256", "sve384", "sve512",
+    "sve640", "sve768", "sve896", "sve1024", "sve1152", "sve1280",
+    "sve1408", "sve1536", "sve1664", "sve1792", "sve1920", "sve2048",
+    NULL
+};
+
+CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type,
+                                                     CpuModelInfo *model,
+                                                     Error **errp)
+{
+    CpuModelExpansionInfo *expansion_info;
+    const QDict *qdict_in = NULL;
+    QDict *qdict_out;
+    ObjectClass *oc;
+    Object *obj;
+    const char *name;
+    int i;
+
+    if (type != CPU_MODEL_EXPANSION_TYPE_FULL) {
+        error_setg(errp, "The requested expansion type is not supported");
+        return NULL;
+    }
+
+    if (!kvm_enabled() && !strcmp(model->name, "host")) {
+        error_setg(errp, "The CPU type '%s' requires KVM", model->name);
+        return NULL;
+    }
+
+    oc = cpu_class_by_name(TYPE_ARM_CPU, model->name);
+    if (!oc) {
+        error_setg(errp, "The CPU type '%s' is not a recognized ARM CPU type",
+                   model->name);
+        return NULL;
+    }
+
+    if (kvm_enabled()) {
+        const char *cpu_type = current_machine->cpu_type;
+        int len = strlen(cpu_type) - strlen(ARM_CPU_TYPE_SUFFIX);
+        bool supported = false;
+
+        if (!strcmp(model->name, "host") || !strcmp(model->name, "max")) {
+            /* These are kvmarm's recommended cpu types */
+            supported = true;
+        } else if (strlen(model->name) == len &&
+                   !strncmp(model->name, cpu_type, len)) {
+            /* KVM is enabled and we're using this type, so it works. */
+            supported = true;
+        }
+        if (!supported) {
+            error_setg(errp, "We cannot guarantee the CPU type '%s' works "
+                             "with KVM on this host", model->name);
+            return NULL;
+        }
+    }
+
+    if (model->props) {
+        qdict_in = qobject_to(QDict, model->props);
+        if (!qdict_in) {
+            error_setg(errp, QERR_INVALID_PARAMETER_TYPE, "props", "dict");
+            return NULL;
+        }
+    }
+
+    obj = object_new(object_class_get_name(oc));
+
+    if (qdict_in) {
+        Visitor *visitor;
+        Error *err = NULL;
+
+        visitor = qobject_input_visitor_new(model->props);
+        visit_start_struct(visitor, NULL, NULL, 0, &err);
+        if (err) {
+            visit_free(visitor);
+            object_unref(obj);
+            error_propagate(errp, err);
+            return NULL;
+        }
+
+        i = 0;
+        while ((name = cpu_model_advertised_features[i++]) != NULL) {
+            if (qdict_get(qdict_in, name)) {
+                object_property_set(obj, visitor, name, &err);
+                if (err) {
+                    break;
+                }
+            }
+        }
+
+        if (!err) {
+            visit_check_struct(visitor, &err);
+        }
+        if (!err) {
+            arm_cpu_finalize_features(ARM_CPU(obj), &err);
+        }
+        visit_end_struct(visitor, NULL);
+        visit_free(visitor);
+        if (err) {
+            object_unref(obj);
+            error_propagate(errp, err);
+            return NULL;
+        }
+    } else {
+        Error *err = NULL;
+        arm_cpu_finalize_features(ARM_CPU(obj), &err);
+        assert(err == NULL);
+    }
+
+    expansion_info = g_new0(CpuModelExpansionInfo, 1);
+    expansion_info->model = g_malloc0(sizeof(*expansion_info->model));
+    expansion_info->model->name = g_strdup(model->name);
+
+    qdict_out = qdict_new();
+
+    i = 0;
+    while ((name = cpu_model_advertised_features[i++]) != NULL) {
+        ObjectProperty *prop = object_property_find(obj, name, NULL);
+        if (prop) {
+            Error *err = NULL;
+            QObject *value;
+
+            assert(prop->get);
+            value = object_property_get_qobject(obj, name, &err);
+            assert(!err);
+
+            qdict_put_obj(qdict_out, name, value);
+        }
+    }
+
+    if (!qdict_size(qdict_out)) {
+        qobject_unref(qdict_out);
+    } else {
+        expansion_info->model->props = QOBJECT(qdict_out);
+        expansion_info->model->has_props = true;
+    }
+
+    object_unref(obj);
+
+    return expansion_info;
+}
diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
index 9ae980bef6..85c5ef897b 100644
--- a/target/arm/translate-vfp.inc.c
+++ b/target/arm/translate-vfp.inc.c
@@ -703,9 +703,10 @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a)
     if (arm_dc_feature(s, ARM_FEATURE_M)) {
         /*
          * The only M-profile VFP vmrs/vmsr sysreg is FPSCR.
-         * Writes to R15 are UNPREDICTABLE; we choose to undef.
+         * Accesses to R15 are UNPREDICTABLE; we choose to undef.
+         * (FPSCR -> r15 is a special case which writes to the PSR flags.)
          */
-        if (a->rt == 15 || a->reg != ARM_VFP_FPSCR) {
+        if (a->rt == 15 && (!a->l || a->reg != ARM_VFP_FPSCR)) {
             return false;
         }
     }