Series comparison

The following changes since commit 63731c346f071a77e1bb1789bef1ac9d592b6d4f:

Merge tag 'pull-loongarch-20240912' of https://gitlab.com/gaosong/qemu into staging (2024-09-13 11:38:15 +0100)

are available in the Git repository at:

https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240913

for you to fetch changes up to 110684c9a69a02cbabfbddcd3afa921826ad565c:

hw/intc/arm_gic: fix spurious level triggered interrupts (2024-09-13 15:31:50 +0100)

----------------------------------------------------------------
target-arm queue:
 * s390: convert s390 virtio-ccw and CPU to three-phase reset
 * reset: remove now-unused device_class_set_parent_reset()
 * reset: introduce device_class_set_legacy_reset()
 * reset: remove unneeded transitional machinery
 * kvm: Use 'unsigned long' for request argument in functions wrapping ioctl()
 * hvf: arm: Implement and use hvf_get_physical_address_range
   so VMs can have larger-than-36-bit IPA spaces when the host
   supports this
 * target/arm/tcg: refine cache descriptions with a wrapper
 * hw/net/can/xlnx-versal-canfd: fix various bugs
 * MAINTAINERS: update versal, CAN maintainer entries
 * hw/intc/arm_gic: fix spurious level triggered interrupts

----------------------------------------------------------------
Alireza Sanaee (1):
      target/arm/tcg: refine cache descriptions with a wrapper

Danny Canter (3):
      hw/boards: Add hvf_get_physical_address_range to MachineClass
      hvf: Split up hv_vm_create logic per arch
      hvf: arm: Implement and use hvf_get_physical_address_range

Doug Brown (7):
      hw/net/can/xlnx-versal-canfd: Fix interrupt level
      hw/net/can/xlnx-versal-canfd: Fix CAN FD flag check
      hw/net/can/xlnx-versal-canfd: Translate CAN ID registers
      hw/net/can/xlnx-versal-canfd: Handle flags correctly
      hw/net/can/xlnx-versal-canfd: Fix byte ordering
      hw/net/can/xlnx-versal-canfd: Simplify DLC conversions
      hw/net/can/xlnx-versal-canfd: Fix FIFO issues

Francisco Iglesias (3):
      MAINTAINERS: Remove Vikram Garhwal as maintainer
      MAINTAINERS: Update Xilinx Versal OSPI maintainer's email address
      MAINTAINERS: Add my-self as CAN maintainer

Jan Klötzke (1):
      hw/intc/arm_gic: fix spurious level triggered interrupts

Johannes Stoelp (1):
      kvm: Use 'unsigned long' for request argument in functions wrapping ioctl()

Peter Maydell (11):
      hw/s390/ccw-device: Convert to three-phase reset
      hw/s390/virtio-ccw: Convert to three-phase reset
      target/s390: Convert CPU to Resettable interface
      hw: Remove device_class_set_parent_reset()
      target/alpha, hppa: Remove unused parent_reset fields
      hw: Define new device_class_set_legacy_reset()
      hw: Use device_class_set_legacy_reset() instead of opencoding
      hw: Rename DeviceClass::reset field to legacy_reset
      hw: Remove device_phases_reset()
      hw/core/qdev: Simplify legacy_reset handling
      hw/core/resettable: Remove transitional_function machinery

Convert the TYPE_CCW_DEVICE to three-phase reset. This is a
device class which is subclassed, so it needs to be three-phase
before we can convert the subclass.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Acked-by: Thomas Huth <thuth@redhat.com>
Message-id: 20240830145812.1967042-2-peter.maydell@linaro.org
---
 hw/s390x/ccw-device.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/hw/s390x/ccw-device.c b/hw/s390x/ccw-device.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/ccw-device.c
+++ b/hw/s390x/ccw-device.c
@@ -XXX,XX +XXX,XX @@ static Property ccw_device_properties[] = {
     DEFINE_PROP_END_OF_LIST(),
 };
 
-static void ccw_device_reset(DeviceState *d)
+static void ccw_device_reset_hold(Object *obj, ResetType type)
 {
-    CcwDevice *ccw_dev = CCW_DEVICE(d);
+    CcwDevice *ccw_dev = CCW_DEVICE(obj);
 
     css_reset_sch(ccw_dev->sch);
 }
@@ -XXX,XX +XXX,XX @@ static void ccw_device_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     CCWDeviceClass *k = CCW_DEVICE_CLASS(klass);
+    ResettableClass *rc = RESETTABLE_CLASS(klass);
 
     k->realize = ccw_device_realize;
     k->refill_ids = ccw_device_refill_ids;
     device_class_set_props(dc, ccw_device_properties);
-    dc->reset = ccw_device_reset;
+    rc->phases.hold = ccw_device_reset_hold;
     dc->bus_type = TYPE_VIRTUAL_CSS_BUS;
 }
 
-- 
2.34.1

Convert the virtio-ccw code to three-phase reset.  This allows us to
remove a call to device_class_set_parent_reset(), replacing it with
the three-phase equivalent resettable_class_set_parent_phases().
Removing all the device_class_set_parent_reset() uses will allow us
to remove some of the glue code that interworks between three-phase
and legacy reset.

This is a simple conversion, with no behavioural changes.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Acked-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240830145812.1967042-3-peter.maydell@linaro.org
---
 hw/s390x/virtio-ccw.h |  2 +-
 hw/s390x/virtio-ccw.c | 13 ++++++++-----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/hw/s390x/virtio-ccw.h b/hw/s390x/virtio-ccw.h
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/virtio-ccw.h
+++ b/hw/s390x/virtio-ccw.h
@@ -XXX,XX +XXX,XX @@ struct VirtIOCCWDeviceClass {
     CCWDeviceClass parent_class;
     void (*realize)(VirtioCcwDevice *dev, Error **errp);
     void (*unrealize)(VirtioCcwDevice *dev);
-    void (*parent_reset)(DeviceState *dev);
+    ResettablePhases parent_phases;
 };
 
 /* Performance improves when virtqueue kick processing is decoupled from the
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -XXX,XX +XXX,XX @@ static void virtio_ccw_notify(DeviceState *d, uint16_t vector)
     }
 }
 
-static void virtio_ccw_reset(DeviceState *d)
+static void virtio_ccw_reset_hold(Object *obj, ResetType type)
 {
-    VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
+    VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(obj);
     VirtIOCCWDeviceClass *vdc = VIRTIO_CCW_DEVICE_GET_CLASS(dev);
 
     virtio_ccw_reset_virtio(dev);
-    if (vdc->parent_reset) {
-        vdc->parent_reset(d);
+
+    if (vdc->parent_phases.hold) {
+        vdc->parent_phases.hold(obj, type);
     }
 }
 
@@ -XXX,XX +XXX,XX @@ static void virtio_ccw_device_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     CCWDeviceClass *k = CCW_DEVICE_CLASS(dc);
     VirtIOCCWDeviceClass *vdc = VIRTIO_CCW_DEVICE_CLASS(klass);
+    ResettableClass *rc = RESETTABLE_CLASS(klass);
 
     k->unplug = virtio_ccw_busdev_unplug;
     dc->realize = virtio_ccw_busdev_realize;
     dc->unrealize = virtio_ccw_busdev_unrealize;
-    device_class_set_parent_reset(dc, virtio_ccw_reset, &vdc->parent_reset);
+    resettable_class_set_parent_phases(rc, NULL, virtio_ccw_reset_hold, NULL,
+                                       &vdc->parent_phases);
 }
 
 static const TypeInfo virtio_ccw_device_info = {
-- 
2.34.1

Convert the s390 CPU to the Resettable interface.  This is slightly
more involved than the other CPU types were (see commits
9130cade5fc22..d66e64dd006df) because S390 has its own set of
different kinds of reset with different behaviours that it needs to
trigger.

We handle this by adding these reset types to the Resettable
ResetType enum.  Now instead of having an underlying implementation
of reset that is s390-specific and which might be called either
directly or via the DeviceClass::reset method, we can implement only
the Resettable hold phase method, and have the places that need to
trigger an s390-specific reset type do so by calling
resettable_reset().

The other option would have been to smuggle in the s390 reset
type via, for instance, a field in the CPU state that we set
in s390_do_cpu_initial_reset() etc and then examined in the
reset method, but doing it this way seems cleaner.

The motivation for this change is that this is the last caller
of the legacy device_class_set_parent_reset() function, and
removing that will let us clean up some glue code that we added
for the transition to three-phase reset.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Acked-by: Thomas Huth <thuth@redhat.com>
Message-id: 20240830145812.1967042-4-peter.maydell@linaro.org
---
 docs/devel/reset.rst    | 10 ++++++++++
 include/hw/resettable.h |  2 ++
 target/s390x/cpu.h      | 21 ++++-----------------
 target/s390x/cpu.c      | 38 +++++++++++++++++---------------------
 target/s390x/sigp.c     |  8 ++------
 5 files changed, 35 insertions(+), 44 deletions(-)

diff --git a/docs/devel/reset.rst b/docs/devel/reset.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/devel/reset.rst
+++ b/docs/devel/reset.rst
@@ -XXX,XX +XXX,XX @@ The Resettable interface handles reset types with an enum ``ResetType``:
   value on each cold reset, such as RNG seed information, and which they
   must not reinitialize on a snapshot-load reset.
 
+``RESET_TYPE_S390_CPU_NORMAL``
+  This is only used for S390 CPU objects; it clears interrupts, stops
+  processing, and clears the TLB, but does not touch register contents.
+
+``RESET_TYPE_S390_CPU_INITIAL``
+  This is only used for S390 CPU objects; it does everything
+  ``RESET_TYPE_S390_CPU_NORMAL`` does and also clears the PSW, prefix,
+  FPC, timer and control registers. It does not touch gprs, fprs or acrs.
+
+
 Devices which implement reset methods must treat any unknown ``ResetType``
 as equivalent to ``RESET_TYPE_COLD``; this will reduce the amount of
 existing code we need to change if we add more types in future.
diff --git a/include/hw/resettable.h b/include/hw/resettable.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/resettable.h
+++ b/include/hw/resettable.h
@@ -XXX,XX +XXX,XX @@ typedef struct ResettableState ResettableState;
 typedef enum ResetType {
     RESET_TYPE_COLD,
     RESET_TYPE_SNAPSHOT_LOAD,
+    RESET_TYPE_S390_CPU_INITIAL,
+    RESET_TYPE_S390_CPU_NORMAL,
 } ResetType;
 
 /*
diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/s390x/cpu.h
+++ b/target/s390x/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
     uint32_t irqstate_saved_size;
 };
 
-typedef enum cpu_reset_type {
-    S390_CPU_RESET_NORMAL,
-    S390_CPU_RESET_INITIAL,
-    S390_CPU_RESET_CLEAR,
-} cpu_reset_type;
-
 /**
  * S390CPUClass:
  * @parent_realize: The parent class' realize handler.
- * @parent_reset: The parent class' reset handler.
+ * @parent_phases: The parent class' reset phase handlers.
  * @load_normal: Performs a load normal.
- * @cpu_reset: Performs a CPU reset.
- * @initial_cpu_reset: Performs an initial CPU reset.
  *
  * An S/390 CPU model.
  */
@@ -XXX,XX +XXX,XX @@ struct S390CPUClass {
     const char *desc;
 
     DeviceRealize parent_realize;
-    DeviceReset parent_reset;
+    ResettablePhases parent_phases;
     void (*load_normal)(CPUState *cpu);
-    void (*reset)(CPUState *cpu, cpu_reset_type type);
 };
 
 #ifndef CONFIG_USER_ONLY
@@ -XXX,XX +XXX,XX @@ static inline void s390_do_cpu_full_reset(CPUState *cs, run_on_cpu_data arg)
 
 static inline void s390_do_cpu_reset(CPUState *cs, run_on_cpu_data arg)
 {
-    S390CPUClass *scc = S390_CPU_GET_CLASS(cs);
-
-    scc->reset(cs, S390_CPU_RESET_NORMAL);
+    resettable_reset(OBJECT(cs), RESET_TYPE_S390_CPU_NORMAL);
 }
 
 static inline void s390_do_cpu_initial_reset(CPUState *cs, run_on_cpu_data arg)
 {
-    S390CPUClass *scc = S390_CPU_GET_CLASS(cs);
-
-    scc->reset(cs, S390_CPU_RESET_INITIAL);
+    resettable_reset(OBJECT(cs), RESET_TYPE_S390_CPU_INITIAL);
 }
 
 static inline void s390_do_cpu_load_normal(CPUState *cs, run_on_cpu_data arg)
diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/s390x/cpu.c
+++ b/target/s390x/cpu.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/hw_accel.h"
 #include "hw/qdev-properties.h"
 #include "hw/qdev-properties-system.h"
+#include "hw/resettable.h"
 #include "fpu/softfloat-helpers.h"
 #include "disas/capstone.h"
 #include "sysemu/tcg.h"
@@ -XXX,XX +XXX,XX @@ static void s390_query_cpu_fast(CPUState *cpu, CpuInfoFast *value)
 #endif
 }
 
-/* S390CPUClass::reset() */
-static void s390_cpu_reset(CPUState *s, cpu_reset_type type)
+/* S390CPUClass Resettable reset_hold phase method */
+static void s390_cpu_reset_hold(Object *obj, ResetType type)
 {
-    S390CPU *cpu = S390_CPU(s);
+    S390CPU *cpu = S390_CPU(obj);
     S390CPUClass *scc = S390_CPU_GET_CLASS(cpu);
     CPUS390XState *env = &cpu->env;
-    DeviceState *dev = DEVICE(s);
 
-    scc->parent_reset(dev);
+    if (scc->parent_phases.hold) {
+        scc->parent_phases.hold(obj, type);
+    }
     cpu->env.sigp_order = 0;
     s390_cpu_set_state(S390_CPU_STATE_STOPPED, cpu);
 
     switch (type) {
-    case S390_CPU_RESET_CLEAR:
+    default:
+        /* RESET_TYPE_COLD: power on or "clear" reset */
         memset(env, 0, offsetof(CPUS390XState, start_initial_reset_fields));
         /* fall through */
-    case S390_CPU_RESET_INITIAL:
+    case RESET_TYPE_S390_CPU_INITIAL:
         /* initial reset does not clear everything! */
         memset(&env->start_initial_reset_fields, 0,
                offsetof(CPUS390XState, start_normal_reset_fields) -
@@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset(CPUState *s, cpu_reset_type type)
         set_float_detect_tininess(float_tininess_before_rounding,
                                   &env->fpu_status);
        /* fall through */
-    case S390_CPU_RESET_NORMAL:
+    case RESET_TYPE_S390_CPU_NORMAL:
         env->psw.mask &= ~PSW_MASK_RI;
         memset(&env->start_normal_reset_fields, 0,
                offsetof(CPUS390XState, end_reset_fields) -
@@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset(CPUState *s, cpu_reset_type type)
         env->pfault_token = -1UL;
         env->bpbc = false;
         break;
-    default:
-        g_assert_not_reached();
     }
 
     /* Reset state inside the kernel that we cannot access yet from QEMU. */
     if (kvm_enabled()) {
         switch (type) {
-        case S390_CPU_RESET_CLEAR:
+        default:
             kvm_s390_reset_vcpu_clear(cpu);
             break;
-        case S390_CPU_RESET_INITIAL:
+        case RESET_TYPE_S390_CPU_INITIAL:
             kvm_s390_reset_vcpu_initial(cpu);
             break;
-        case S390_CPU_RESET_NORMAL:
+        case RESET_TYPE_S390_CPU_NORMAL:
             kvm_s390_reset_vcpu_normal(cpu);
             break;
         }
@@ -XXX,XX +XXX,XX @@ static Property s390x_cpu_properties[] = {
     DEFINE_PROP_END_OF_LIST()
 };
 
-static void s390_cpu_reset_full(DeviceState *dev)
-{
-    CPUState *s = CPU(dev);
-    return s390_cpu_reset(s, S390_CPU_RESET_CLEAR);
-}
-
 #ifdef CONFIG_TCG
 #include "hw/core/tcg-cpu-ops.h"
 
@@ -XXX,XX +XXX,XX @@ static void s390_cpu_class_init(ObjectClass *oc, void *data)
     S390CPUClass *scc = S390_CPU_CLASS(oc);
     CPUClass *cc = CPU_CLASS(scc);
     DeviceClass *dc = DEVICE_CLASS(oc);
+    ResettableClass *rc = RESETTABLE_CLASS(oc);
 
     device_class_set_parent_realize(dc, s390_cpu_realizefn,
                                     &scc->parent_realize);
     device_class_set_props(dc, s390x_cpu_properties);
     dc->user_creatable = true;
 
-    device_class_set_parent_reset(dc, s390_cpu_reset_full, &scc->parent_reset);
+    resettable_class_set_parent_phases(rc, NULL, s390_cpu_reset_hold, NULL,
+                                       &scc->parent_phases);
 
-    scc->reset = s390_cpu_reset;
     cc->class_by_name = s390_cpu_class_by_name,
     cc->has_work = s390_cpu_has_work;
     cc->mmu_index = s390x_cpu_mmu_index;
diff --git a/target/s390x/sigp.c b/target/s390x/sigp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/s390x/sigp.c
+++ b/target/s390x/sigp.c
@@ -XXX,XX +XXX,XX @@ static void sigp_restart(CPUState *cs, run_on_cpu_data arg)
 
 static void sigp_initial_cpu_reset(CPUState *cs, run_on_cpu_data arg)
 {
-    S390CPU *cpu = S390_CPU(cs);
-    S390CPUClass *scc = S390_CPU_GET_CLASS(cpu);
     SigpInfo *si = arg.host_ptr;
 
     cpu_synchronize_state(cs);
-    scc->reset(cs, S390_CPU_RESET_INITIAL);
+    resettable_reset(OBJECT(cs), RESET_TYPE_S390_CPU_INITIAL);
     cpu_synchronize_post_reset(cs);
     si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
 static void sigp_cpu_reset(CPUState *cs, run_on_cpu_data arg)
 {
-    S390CPU *cpu = S390_CPU(cs);
-    S390CPUClass *scc = S390_CPU_GET_CLASS(cpu);
     SigpInfo *si = arg.host_ptr;
 
     cpu_synchronize_state(cs);
-    scc->reset(cs, S390_CPU_RESET_NORMAL);
+    resettable_reset(OBJECT(cs), RESET_TYPE_S390_CPU_NORMAL);
     cpu_synchronize_post_reset(cs);
     si->cc = SIGP_CC_ORDER_CODE_ACCEPTED;
 }
-- 
2.34.1

There are no callers of device_class_set_parent_reset() left in the tree,
as they've all been converted to use three-phase reset and the
corresponding resettable_class_set_parent_phases() function.
Remove device_class_set_parent_reset().

diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -XXX,XX +XXX,XX @@ char *qdev_get_own_fw_dev_path_from_handler(BusState *bus, DeviceState *dev);
  */
 void device_class_set_props(DeviceClass *dc, Property *props);
 
-/**
- * device_class_set_parent_reset() - legacy set device reset handlers
- * @dc: device class
- * @dev_reset: function pointer to reset handler
- * @parent_reset: function pointer to parents reset handler
- *
- * Modern code should use the ResettableClass interface to
- * implement a multi-phase reset instead.
- *
- * TODO: remove the function when DeviceClass's reset method
- * is not used anymore.
- */
-void device_class_set_parent_reset(DeviceClass *dc,
-                                   DeviceReset dev_reset,
-                                   DeviceReset *parent_reset);
-
 /**
  * device_class_set_parent_realize() - set up for chaining realize fns
  * @dc: The device class
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
                                    offsetof(DeviceState, parent_bus), NULL, 0);
 }
 
-void device_class_set_parent_reset(DeviceClass *dc,
-                                   DeviceReset dev_reset,
-                                   DeviceReset *parent_reset)
-{
-    *parent_reset = dc->reset;
-    dc->reset = dev_reset;
-}
-
 void device_class_set_parent_realize(DeviceClass *dc,
                                      DeviceRealize dev_realize,
                                      DeviceRealize *parent_realize)
-- 
2.34.1

The Alpha and HPPA CPU class structs include a 'parent_reset'
field which is never used; delete them.

(These targets don't seem to implement reset at all; if they did they
should do it using the three-phase reset mechanism, which uses a
'ResettablePhases parent_phases' field instead of the old
'DeviceReset parent_reset' field.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20240830145812.1967042-6-peter.maydell@linaro.org
---
 target/alpha/cpu.h | 2 --
 target/hppa/cpu.h  | 2 --
 2 files changed, 4 deletions(-)

diff --git a/target/alpha/cpu.h b/target/alpha/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/alpha/cpu.h
+++ b/target/alpha/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
 /**
  * AlphaCPUClass:
  * @parent_realize: The parent class' realize handler.
- * @parent_reset: The parent class' reset handler.
  *
  * An Alpha CPU model.
  */
@@ -XXX,XX +XXX,XX @@ struct AlphaCPUClass {
     CPUClass parent_class;
 
     DeviceRealize parent_realize;
-    DeviceReset parent_reset;
 };
 
 #ifndef CONFIG_USER_ONLY
diff --git a/target/hppa/cpu.h b/target/hppa/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/hppa/cpu.h
+++ b/target/hppa/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
 /**
  * HPPACPUClass:
  * @parent_realize: The parent class' realize handler.
- * @parent_reset: The parent class' reset handler.
  *
  * An HPPA CPU model.
  */
@@ -XXX,XX +XXX,XX @@ struct HPPACPUClass {
     CPUClass parent_class;
 
     DeviceRealize parent_realize;
-    DeviceReset parent_reset;
 };
 
 #include "exec/cpu-all.h"
-- 
2.34.1

Define a device_class_set_legacy_reset() function which
sets the DeviceClass::reset field. This serves two purposes:
 * it makes it clearer to the person writing code that
   DeviceClass::reset is now legacy and they should look for
   the new alternative (which is Resettable)
 * it makes it easier to rename the reset field (which in turn
   makes it easier to find places that call it)

The Coccinelle script can be used to automatically convert code that
was doing an open-coded assignment to DeviceClass::reset to call
device_class_set_legacy_reset() instead.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240830145812.1967042-7-peter.maydell@linaro.org
---
 scripts/coccinelle/device-reset.cocci | 30 +++++++++++++++++++++++++++
 include/hw/qdev-core.h                | 13 ++++++++++++
 hw/core/qdev.c                        |  5 +++++
 3 files changed, 48 insertions(+)
 create mode 100644 scripts/coccinelle/device-reset.cocci

diff --git a/scripts/coccinelle/device-reset.cocci b/scripts/coccinelle/device-reset.cocci
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/scripts/coccinelle/device-reset.cocci
@@ -XXX,XX +XXX,XX @@
+// Convert opencoded DeviceClass::reset assignments to calls to
+// device_class_set_legacy_reset()
+//
+// Copyright Linaro Ltd 2024
+// This work is licensed under the terms of the GNU GPLv2 or later.
+//
+// spatch --macro-file scripts/cocci-macro-file.h \
+//        --sp-file scripts/coccinelle/device-reset.cocci \
+//        --keep-comments --smpl-spacing --in-place --include-headers --dir hw
+//
+// For simplicity we assume some things about the code we're modifying
+// that happen to be true for all our targets:
+//  * all cpu_class_set_parent_reset() callsites have a 'DeviceClass *dc' local
+//  * the parent reset field in the target CPU class is 'parent_reset'
+//  * no reset function already has a 'dev' local
+
+@@
+identifier dc, resetfn;
+@@
+  DeviceClass *dc;
+  ...
+- dc->reset = resetfn;
++ device_class_set_legacy_reset(dc, resetfn);
+@@
+identifier dc, resetfn;
+@@
+  DeviceClass *dc;
+  ...
+- dc->reset = &resetfn;
++ device_class_set_legacy_reset(dc, resetfn);
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -XXX,XX +XXX,XX @@ void device_class_set_parent_realize(DeviceClass *dc,
                                      DeviceRealize dev_realize,
                                      DeviceRealize *parent_realize);
 
+/**
+ * device_class_set_legacy_reset(): set the DeviceClass::reset method
+ * @dc: The device class
+ * @dev_reset: the reset function
+ *
+ * This function sets the DeviceClass::reset method. This is widely
+ * used in existing code, but new code should prefer to use the
+ * Resettable API as documented in docs/devel/reset.rst.
+ * In addition, devices which need to chain to their parent class's
+ * reset methods or which need to be subclassed must use Resettable.
+ */
+void device_class_set_legacy_reset(DeviceClass *dc,
+                                   DeviceReset dev_reset);
 
 /**
  * device_class_set_parent_unrealize() - set up for chaining unrealize fns
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
                                    offsetof(DeviceState, parent_bus), NULL, 0);
 }
 
+void device_class_set_legacy_reset(DeviceClass *dc, DeviceReset dev_reset)
+{
+    dc->reset = dev_reset;
+}
+
 void device_class_set_parent_realize(DeviceClass *dc,
                                      DeviceRealize dev_realize,
                                      DeviceRealize *parent_realize)
-- 
2.34.1

Use device_class_set_legacy_reset() instead of opencoding an
assignment to DeviceClass::reset. This change was produced
with:
 spatch --macro-file scripts/cocci-macro-file.h \
    --sp-file scripts/coccinelle/device-reset.cocci \
    --keep-comments --smpl-spacing --in-place --dir hw

diff --git a/hw/acpi/erst.c b/hw/acpi/erst.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/acpi/erst.c
+++ b/hw/acpi/erst.c
@@ -XXX,XX +XXX,XX @@ static void erst_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_REDHAT_ACPI_ERST;
     k->revision = 0x00;
     k->class_id = PCI_CLASS_OTHERS;
-    dc->reset = erst_reset;
+    device_class_set_legacy_reset(dc, erst_reset);
     dc->vmsd = &erst_vmstate;
     dc->user_creatable = true;
     dc->hotpluggable = false;
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -XXX,XX +XXX,XX @@ static void piix4_pm_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_INTEL_82371AB_3;
     k->revision = 0x03;
     k->class_id = PCI_CLASS_BRIDGE_OTHER;
-    dc->reset = piix4_pm_reset;
+    device_class_set_legacy_reset(dc, piix4_pm_reset);
     dc->desc = "PM";
     dc->vmsd = &vmstate_acpi;
     device_class_set_props(dc, piix4_pm_properties);
diff --git a/hw/adc/aspeed_adc.c b/hw/adc/aspeed_adc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/adc/aspeed_adc.c
+++ b/hw/adc/aspeed_adc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_adc_engine_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_adc_engine_realize;
-    dc->reset = aspeed_adc_engine_reset;
+    device_class_set_legacy_reset(dc, aspeed_adc_engine_reset);
     device_class_set_props(dc, aspeed_adc_engine_properties);
     dc->desc = "Aspeed Analog-to-Digital Engine";
     dc->vmsd = &vmstate_aspeed_adc_engine;
diff --git a/hw/adc/max111x.c b/hw/adc/max111x.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/adc/max111x.c
+++ b/hw/adc/max111x.c
@@ -XXX,XX +XXX,XX @@ static void max111x_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     k->transfer = max111x_transfer;
-    dc->reset = max111x_reset;
+    device_class_set_legacy_reset(dc, max111x_reset);
     dc->vmsd = &vmstate_max111x;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
diff --git a/hw/adc/stm32f2xx_adc.c b/hw/adc/stm32f2xx_adc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/adc/stm32f2xx_adc.c
+++ b/hw/adc/stm32f2xx_adc.c
@@ -XXX,XX +XXX,XX @@ static void stm32f2xx_adc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f2xx_adc_reset;
+    device_class_set_legacy_reset(dc, stm32f2xx_adc_reset);
     dc->vmsd = &vmstate_stm32f2xx_adc;
 }
 
diff --git a/hw/adc/zynq-xadc.c b/hw/adc/zynq-xadc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/adc/zynq-xadc.c
+++ b/hw/adc/zynq-xadc.c
@@ -XXX,XX +XXX,XX @@ static void zynq_xadc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_zynq_xadc;
-    dc->reset = zynq_xadc_reset;
+    device_class_set_legacy_reset(dc, zynq_xadc_reset);
 }
 
 static const TypeInfo zynq_xadc_info = {
diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/armsse.c
+++ b/hw/arm/armsse.c
@@ -XXX,XX +XXX,XX @@ static void armsse_class_init(ObjectClass *klass, void *data)
     dc->realize = armsse_realize;
     dc->vmsd = &armsse_vmstate;
     device_class_set_props(dc, info->props);
-    dc->reset = armsse_reset;
+    device_class_set_legacy_reset(dc, armsse_reset);
     iic->check = armsse_idau_check;
     asc->info = info;
 }
diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/highbank.c
+++ b/hw/arm/highbank.c
@@ -XXX,XX +XXX,XX @@ static void highbank_regs_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "Calxeda Highbank registers";
     dc->vmsd = &vmstate_highbank_regs;
-    dc->reset = highbank_regs_reset;
+    device_class_set_legacy_reset(dc, highbank_regs_reset);
 }
 
 static const TypeInfo highbank_regs_info = {
diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/musicpal.c
+++ b/hw/arm/musicpal.c
@@ -XXX,XX +XXX,XX @@ static void mv88w8618_pic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = mv88w8618_pic_reset;
+    device_class_set_legacy_reset(dc, mv88w8618_pic_reset);
     dc->vmsd = &mv88w8618_pic_vmsd;
 }
 
@@ -XXX,XX +XXX,XX @@ static void mv88w8618_pit_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = mv88w8618_pit_reset;
+    device_class_set_legacy_reset(dc, mv88w8618_pit_reset);
     dc->vmsd = &mv88w8618_pit_vmsd;
 }
 
@@ -XXX,XX +XXX,XX @@ static void musicpal_gpio_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = musicpal_gpio_reset;
+    device_class_set_legacy_reset(dc, musicpal_gpio_reset);
     dc->vmsd = &musicpal_gpio_vmsd;
 }
 
diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/pxa2xx.c
+++ b/hw/arm/pxa2xx.c
@@ -XXX,XX +XXX,XX @@ static void pxa2xx_fir_class_init(ObjectClass *klass, void *data)
     dc->realize = pxa2xx_fir_realize;
     dc->vmsd = &pxa2xx_fir_vmsd;
     device_class_set_props(dc, pxa2xx_fir_properties);
-    dc->reset = pxa2xx_fir_reset;
+    device_class_set_legacy_reset(dc, pxa2xx_fir_reset);
 }
 
 static const TypeInfo pxa2xx_fir_info = {
@@ -XXX,XX +XXX,XX @@ static void pxa2xx_ssp_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pxa2xx_ssp_reset;
+    device_class_set_legacy_reset(dc, pxa2xx_ssp_reset);
     dc->vmsd = &vmstate_pxa2xx_ssp;
 }
 
diff --git a/hw/arm/strongarm.c b/hw/arm/strongarm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/strongarm.c
+++ b/hw/arm/strongarm.c
@@ -XXX,XX +XXX,XX @@ static void strongarm_uart_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->desc = "StrongARM UART controller";
-    dc->reset = strongarm_uart_reset;
+    device_class_set_legacy_reset(dc, strongarm_uart_reset);
     dc->vmsd = &vmstate_strongarm_uart_regs;
     device_class_set_props(dc, strongarm_uart_properties);
     dc->realize = strongarm_uart_realize;
@@ -XXX,XX +XXX,XX @@ static void strongarm_ssp_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->desc = "StrongARM SSP controller";
-    dc->reset = strongarm_ssp_reset;
+    device_class_set_legacy_reset(dc, strongarm_ssp_reset);
     dc->vmsd = &vmstate_strongarm_ssp_regs;
 }
 
diff --git a/hw/audio/ac97.c b/hw/audio/ac97.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/ac97.c
+++ b/hw/audio/ac97.c
@@ -XXX,XX +XXX,XX @@ static void ac97_class_init(ObjectClass *klass, void *data)
     dc->desc = "Intel 82801AA AC97 Audio";
     dc->vmsd = &vmstate_ac97;
     device_class_set_props(dc, ac97_properties);
-    dc->reset = ac97_on_reset;
+    device_class_set_legacy_reset(dc, ac97_on_reset);
 }
 
 static const TypeInfo ac97_info = {
diff --git a/hw/audio/cs4231.c b/hw/audio/cs4231.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/cs4231.c
+++ b/hw/audio/cs4231.c
@@ -XXX,XX +XXX,XX @@ static void cs4231_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = cs_reset;
+    device_class_set_legacy_reset(dc, cs_reset);
     dc->vmsd = &vmstate_cs4231;
 }
 
diff --git a/hw/audio/cs4231a.c b/hw/audio/cs4231a.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/cs4231a.c
+++ b/hw/audio/cs4231a.c
@@ -XXX,XX +XXX,XX @@ static void cs4231a_class_initfn (ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS (klass);
 
     dc->realize = cs4231a_realizefn;
-    dc->reset = cs4231a_reset;
+    device_class_set_legacy_reset(dc, cs4231a_reset);
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
     dc->desc = "Crystal Semiconductor CS4231A";
     dc->vmsd = &vmstate_cs4231a;
diff --git a/hw/audio/es1370.c b/hw/audio/es1370.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/es1370.c
+++ b/hw/audio/es1370.c
@@ -XXX,XX +XXX,XX @@ static void es1370_class_init (ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
     dc->desc = "ENSONIQ AudioPCI ES1370";
     dc->vmsd = &vmstate_es1370;
-    dc->reset = es1370_on_reset;
+    device_class_set_legacy_reset(dc, es1370_on_reset);
     device_class_set_props(dc, es1370_properties);
 }
 
diff --git a/hw/audio/hda-codec.c b/hw/audio/hda-codec.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/hda-codec.c
+++ b/hw/audio/hda-codec.c
@@ -XXX,XX +XXX,XX @@ static void hda_audio_base_class_init(ObjectClass *klass, void *data)
     k->command = hda_audio_command;
     k->stream = hda_audio_stream;
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
-    dc->reset = hda_audio_reset;
+    device_class_set_legacy_reset(dc, hda_audio_reset);
     dc->vmsd = &vmstate_hda_audio;
     device_class_set_props(dc, hda_audio_properties);
 }
diff --git a/hw/audio/intel-hda.c b/hw/audio/intel-hda.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/intel-hda.c
+++ b/hw/audio/intel-hda.c
@@ -XXX,XX +XXX,XX @@ static void intel_hda_class_init(ObjectClass *klass, void *data)
     k->exit = intel_hda_exit;
     k->vendor_id = PCI_VENDOR_ID_INTEL;
     k->class_id = PCI_CLASS_MULTIMEDIA_HD_AUDIO;
-    dc->reset = intel_hda_reset;
+    device_class_set_legacy_reset(dc, intel_hda_reset);
     dc->vmsd = &vmstate_intel_hda;
     device_class_set_props(dc, intel_hda_properties);
 }
diff --git a/hw/audio/marvell_88w8618.c b/hw/audio/marvell_88w8618.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/marvell_88w8618.c
+++ b/hw/audio/marvell_88w8618.c
@@ -XXX,XX +XXX,XX @@ static void mv88w8618_audio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = mv88w8618_audio_realize;
-    dc->reset = mv88w8618_audio_reset;
+    device_class_set_legacy_reset(dc, mv88w8618_audio_reset);
     dc->vmsd = &mv88w8618_audio_vmsd;
     dc->user_creatable = false;
 }
diff --git a/hw/audio/pl041.c b/hw/audio/pl041.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/pl041.c
+++ b/hw/audio/pl041.c
@@ -XXX,XX +XXX,XX @@ static void pl041_device_class_init(ObjectClass *klass, void *data)
 
     dc->realize = pl041_realize;
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
-    dc->reset = pl041_device_reset;
+    device_class_set_legacy_reset(dc, pl041_device_reset);
     dc->vmsd = &vmstate_pl041;
     device_class_set_props(dc, pl041_device_properties);
 }
diff --git a/hw/audio/via-ac97.c b/hw/audio/via-ac97.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/audio/via-ac97.c
+++ b/hw/audio/via-ac97.c
@@ -XXX,XX +XXX,XX @@ static void via_ac97_class_init(ObjectClass *klass, void *data)
     device_class_set_props(dc, via_ac97_properties);
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
     dc->desc = "VIA AC97";
-    dc->reset = via_ac97_reset;
+    device_class_set_legacy_reset(dc, via_ac97_reset);
     /* Reason: Part of a south bridge chip */
     dc->user_creatable = false;
 }
diff --git a/hw/block/fdc-isa.c b/hw/block/fdc-isa.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/fdc-isa.c
+++ b/hw/block/fdc-isa.c
@@ -XXX,XX +XXX,XX @@ static void isabus_fdc_class_init(ObjectClass *klass, void *data)
     dc->desc = "virtual floppy controller";
     dc->realize = isabus_fdc_realize;
     dc->fw_name = "fdc";
-    dc->reset = fdctrl_external_reset_isa;
+    device_class_set_legacy_reset(dc, fdctrl_external_reset_isa);
     dc->vmsd = &vmstate_isa_fdc;
     adevc->build_dev_aml = build_fdc_aml;
     device_class_set_props(dc, isa_fdc_properties);
diff --git a/hw/block/fdc-sysbus.c b/hw/block/fdc-sysbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/fdc-sysbus.c
+++ b/hw/block/fdc-sysbus.c
@@ -XXX,XX +XXX,XX @@ static void sysbus_fdc_common_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = sysbus_fdc_realize;
-    dc->reset = fdctrl_external_reset_sysbus;
+    device_class_set_legacy_reset(dc, fdctrl_external_reset_sysbus);
     dc->vmsd = &vmstate_sysbus_fdc;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/m25p80.c
+++ b/hw/block/m25p80.c
@@ -XXX,XX +XXX,XX @@ static void m25p80_class_init(ObjectClass *klass, void *data)
     k->cs_polarity = SSI_CS_LOW;
     dc->vmsd = &vmstate_m25p80;
     device_class_set_props(dc, m25p80_properties);
-    dc->reset = m25p80_reset;
+    device_class_set_legacy_reset(dc, m25p80_reset);
     mc->pi = data;
 }
 
diff --git a/hw/block/nand.c b/hw/block/nand.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/nand.c
+++ b/hw/block/nand.c
@@ -XXX,XX +XXX,XX @@ static void nand_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = nand_realize;
-    dc->reset = nand_reset;
+    device_class_set_legacy_reset(dc, nand_reset);
     dc->vmsd = &vmstate_nand;
     device_class_set_props(dc, nand_properties);
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
diff --git a/hw/block/onenand.c b/hw/block/onenand.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/onenand.c
+++ b/hw/block/onenand.c
@@ -XXX,XX +XXX,XX @@ static void onenand_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = onenand_realize;
-    dc->reset = onenand_system_reset;
+    device_class_set_legacy_reset(dc, onenand_system_reset);
     device_class_set_props(dc, onenand_properties);
 }
 
diff --git a/hw/block/pflash_cfi01.c b/hw/block/pflash_cfi01.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/pflash_cfi01.c
+++ b/hw/block/pflash_cfi01.c
@@ -XXX,XX +XXX,XX @@ static void pflash_cfi01_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pflash_cfi01_system_reset;
+    device_class_set_legacy_reset(dc, pflash_cfi01_system_reset);
     dc->realize = pflash_cfi01_realize;
     device_class_set_props(dc, pflash_cfi01_properties);
     dc->vmsd = &vmstate_pflash;
diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/pflash_cfi02.c
+++ b/hw/block/pflash_cfi02.c
@@ -XXX,XX +XXX,XX @@ static void pflash_cfi02_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = pflash_cfi02_realize;
-    dc->reset = pflash_cfi02_reset;
+    device_class_set_legacy_reset(dc, pflash_cfi02_reset);
     dc->unrealize = pflash_cfi02_unrealize;
     device_class_set_props(dc, pflash_cfi02_properties);
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
diff --git a/hw/block/swim.c b/hw/block/swim.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/swim.c
+++ b/hw/block/swim.c
@@ -XXX,XX +XXX,XX @@ static void sysbus_swim_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = sysbus_swim_realize;
-    dc->reset = sysbus_swim_reset;
+    device_class_set_legacy_reset(dc, sysbus_swim_reset);
     dc->vmsd = &vmstate_sysbus_swim;
 }
 
diff --git a/hw/char/avr_usart.c b/hw/char/avr_usart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/avr_usart.c
+++ b/hw/char/avr_usart.c
@@ -XXX,XX +XXX,XX @@ static void avr_usart_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = avr_usart_reset;
+    device_class_set_legacy_reset(dc, avr_usart_reset);
     device_class_set_props(dc, avr_usart_properties);
     dc->realize = avr_usart_realize;
 }
diff --git a/hw/char/cmsdk-apb-uart.c b/hw/char/cmsdk-apb-uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/cmsdk-apb-uart.c
+++ b/hw/char/cmsdk-apb-uart.c
@@ -XXX,XX +XXX,XX @@ static void cmsdk_apb_uart_class_init(ObjectClass *klass, void *data)
 
     dc->realize = cmsdk_apb_uart_realize;
     dc->vmsd = &cmsdk_apb_uart_vmstate;
-    dc->reset = cmsdk_apb_uart_reset;
+    device_class_set_legacy_reset(dc, cmsdk_apb_uart_reset);
     device_class_set_props(dc, cmsdk_apb_uart_properties);
 }
 
diff --git a/hw/char/digic-uart.c b/hw/char/digic-uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/digic-uart.c
+++ b/hw/char/digic-uart.c
@@ -XXX,XX +XXX,XX @@ static void digic_uart_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = digic_uart_realize;
-    dc->reset = digic_uart_reset;
+    device_class_set_legacy_reset(dc, digic_uart_reset);
     dc->vmsd = &vmstate_digic_uart;
     device_class_set_props(dc, digic_uart_properties);
 }
diff --git a/hw/char/escc.c b/hw/char/escc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/escc.c
+++ b/hw/char/escc.c
@@ -XXX,XX +XXX,XX @@ static void escc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = escc_reset;
+    device_class_set_legacy_reset(dc, escc_reset);
     dc->realize = escc_realize;
     dc->vmsd = &vmstate_escc;
     device_class_set_props(dc, escc_properties);
diff --git a/hw/char/etraxfs_ser.c b/hw/char/etraxfs_ser.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/etraxfs_ser.c
+++ b/hw/char/etraxfs_ser.c
@@ -XXX,XX +XXX,XX @@ static void etraxfs_ser_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = etraxfs_ser_reset;
+    device_class_set_legacy_reset(dc, etraxfs_ser_reset);
     device_class_set_props(dc, etraxfs_ser_properties);
     dc->realize = etraxfs_ser_realize;
 }
diff --git a/hw/char/exynos4210_uart.c b/hw/char/exynos4210_uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/exynos4210_uart.c
+++ b/hw/char/exynos4210_uart.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_uart_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = exynos4210_uart_realize;
-    dc->reset = exynos4210_uart_reset;
+    device_class_set_legacy_reset(dc, exynos4210_uart_reset);
     device_class_set_props(dc, exynos4210_uart_properties);
     dc->vmsd = &vmstate_exynos4210_uart;
 }
diff --git a/hw/char/goldfish_tty.c b/hw/char/goldfish_tty.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/goldfish_tty.c
+++ b/hw/char/goldfish_tty.c
@@ -XXX,XX +XXX,XX @@ static void goldfish_tty_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     device_class_set_props(dc, goldfish_tty_properties);
-    dc->reset = goldfish_tty_reset;
+    device_class_set_legacy_reset(dc, goldfish_tty_reset);
     dc->realize = goldfish_tty_realize;
     dc->unrealize = goldfish_tty_unrealize;
     dc->vmsd = &vmstate_goldfish_tty;
diff --git a/hw/char/grlib_apbuart.c b/hw/char/grlib_apbuart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/grlib_apbuart.c
+++ b/hw/char/grlib_apbuart.c
@@ -XXX,XX +XXX,XX @@ static void grlib_apbuart_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = grlib_apbuart_realize;
-    dc->reset = grlib_apbuart_reset;
+    device_class_set_legacy_reset(dc, grlib_apbuart_reset);
     device_class_set_props(dc, grlib_apbuart_properties);
 }
 
diff --git a/hw/char/ibex_uart.c b/hw/char/ibex_uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/ibex_uart.c
+++ b/hw/char/ibex_uart.c
@@ -XXX,XX +XXX,XX @@ static void ibex_uart_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = ibex_uart_reset;
+    device_class_set_legacy_reset(dc, ibex_uart_reset);
     dc->realize = ibex_uart_realize;
     dc->vmsd = &vmstate_ibex_uart;
     device_class_set_props(dc, ibex_uart_properties);
diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/imx_serial.c
+++ b/hw/char/imx_serial.c
@@ -XXX,XX +XXX,XX @@ static void imx_serial_class_init(ObjectClass *klass, void *data)
 
     dc->realize = imx_serial_realize;
     dc->vmsd = &vmstate_imx_serial;
-    dc->reset = imx_serial_reset_at_boot;
+    device_class_set_legacy_reset(dc, imx_serial_reset_at_boot);
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
     dc->desc = "i.MX series UART";
     device_class_set_props(dc, imx_serial_properties);
diff --git a/hw/char/mcf_uart.c b/hw/char/mcf_uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/mcf_uart.c
+++ b/hw/char/mcf_uart.c
@@ -XXX,XX +XXX,XX @@ static void mcf_uart_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = mcf_uart_realize;
-    dc->reset = mcf_uart_reset;
+    device_class_set_legacy_reset(dc, mcf_uart_reset);
     device_class_set_props(dc, mcf_uart_properties);
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
 }
diff --git a/hw/char/mchp_pfsoc_mmuart.c b/hw/char/mchp_pfsoc_mmuart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/mchp_pfsoc_mmuart.c
+++ b/hw/char/mchp_pfsoc_mmuart.c
@@ -XXX,XX +XXX,XX @@ static void mchp_pfsoc_mmuart_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = mchp_pfsoc_mmuart_realize;
-    dc->reset = mchp_pfsoc_mmuart_reset;
+    device_class_set_legacy_reset(dc, mchp_pfsoc_mmuart_reset);
     dc->vmsd = &mchp_pfsoc_mmuart_vmstate;
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
 }
diff --git a/hw/char/nrf51_uart.c b/hw/char/nrf51_uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/nrf51_uart.c
+++ b/hw/char/nrf51_uart.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_uart_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = nrf51_uart_reset;
+    device_class_set_legacy_reset(dc, nrf51_uart_reset);
     dc->realize = nrf51_uart_realize;
     device_class_set_props(dc, nrf51_uart_properties);
     dc->vmsd = &nrf51_uart_vmstate;
diff --git a/hw/char/pl011.c b/hw/char/pl011.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/pl011.c
+++ b/hw/char/pl011.c
@@ -XXX,XX +XXX,XX @@ static void pl011_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = pl011_realize;
-    dc->reset = pl011_reset;
+    device_class_set_legacy_reset(dc, pl011_reset);
     dc->vmsd = &vmstate_pl011;
     device_class_set_props(dc, pl011_properties);
 }
diff --git a/hw/char/renesas_sci.c b/hw/char/renesas_sci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/renesas_sci.c
+++ b/hw/char/renesas_sci.c
@@ -XXX,XX +XXX,XX @@ static void rsci_class_init(ObjectClass *klass, void *data)
 
     dc->realize = rsci_realize;
     dc->vmsd = &vmstate_rsci;
-    dc->reset = rsci_reset;
+    device_class_set_legacy_reset(dc, rsci_reset);
     device_class_set_props(dc, rsci_properties);
 }
 
diff --git a/hw/char/sclpconsole-lm.c b/hw/char/sclpconsole-lm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/sclpconsole-lm.c
+++ b/hw/char/sclpconsole-lm.c
@@ -XXX,XX +XXX,XX @@ static void console_class_init(ObjectClass *klass, void *data)
     SCLPEventClass *ec = SCLP_EVENT_CLASS(klass);
 
     device_class_set_props(dc, console_properties);
-    dc->reset = console_reset;
+    device_class_set_legacy_reset(dc, console_reset);
     dc->vmsd = &vmstate_sclplmconsole;
     ec->init = console_init;
     ec->get_send_mask = send_mask;
diff --git a/hw/char/sclpconsole.c b/hw/char/sclpconsole.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/sclpconsole.c
+++ b/hw/char/sclpconsole.c
@@ -XXX,XX +XXX,XX @@ static void console_class_init(ObjectClass *klass, void *data)
     SCLPEventClass *ec = SCLP_EVENT_CLASS(klass);
 
     device_class_set_props(dc, console_properties);
-    dc->reset = console_reset;
+    device_class_set_legacy_reset(dc, console_reset);
     dc->vmsd = &vmstate_sclpconsole;
     ec->init = console_init;
     ec->get_send_mask = send_mask;
diff --git a/hw/char/sh_serial.c b/hw/char/sh_serial.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/sh_serial.c
+++ b/hw/char/sh_serial.c
@@ -XXX,XX +XXX,XX @@ static void sh_serial_class_init(ObjectClass *oc, void *data)
 
     device_class_set_props(dc, sh_serial_properties);
     dc->realize = sh_serial_realize;
-    dc->reset = sh_serial_reset;
+    device_class_set_legacy_reset(dc, sh_serial_reset);
     /* Reason: part of SuperH CPU/SoC, needs to be wired up */
     dc->user_creatable = false;
 }
diff --git a/hw/char/shakti_uart.c b/hw/char/shakti_uart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/shakti_uart.c
+++ b/hw/char/shakti_uart.c
@@ -XXX,XX +XXX,XX @@ static Property shakti_uart_properties[] = {
 static void shakti_uart_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
-    dc->reset = shakti_uart_reset;
+    device_class_set_legacy_reset(dc, shakti_uart_reset);
     dc->realize = shakti_uart_realize;
     device_class_set_props(dc, shakti_uart_properties);
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
diff --git a/hw/char/stm32f2xx_usart.c b/hw/char/stm32f2xx_usart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/stm32f2xx_usart.c
+++ b/hw/char/stm32f2xx_usart.c
@@ -XXX,XX +XXX,XX @@ static void stm32f2xx_usart_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f2xx_usart_reset;
+    device_class_set_legacy_reset(dc, stm32f2xx_usart_reset);
     device_class_set_props(dc, stm32f2xx_usart_properties);
     dc->realize = stm32f2xx_usart_realize;
 }
diff --git a/hw/char/xilinx_uartlite.c b/hw/char/xilinx_uartlite.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/xilinx_uartlite.c
+++ b/hw/char/xilinx_uartlite.c
@@ -XXX,XX +XXX,XX @@ static void xilinx_uartlite_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xilinx_uartlite_reset;
+    device_class_set_legacy_reset(dc, xilinx_uartlite_reset);
     dc->realize = xilinx_uartlite_realize;
     device_class_set_props(dc, xilinx_uartlite_properties);
 }
diff --git a/hw/core/or-irq.c b/hw/core/or-irq.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/or-irq.c
+++ b/hw/core/or-irq.c
@@ -XXX,XX +XXX,XX @@ static void or_irq_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = or_irq_reset;
+    device_class_set_legacy_reset(dc, or_irq_reset);
     device_class_set_props(dc, or_irq_properties);
     dc->realize = or_irq_realize;
     dc->vmsd = &vmstate_or_irq;
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
      *   will be registered as the parent reset method and effectively call
      *   parent reset phases.
      */
-    dc->reset = device_phases_reset;
+    device_class_set_legacy_reset(dc, device_phases_reset);
     rc->get_transitional_function = device_get_transitional_reset;
 
     object_class_property_add_bool(class, "realized",
diff --git a/hw/cxl/switch-mailbox-cci.c b/hw/cxl/switch-mailbox-cci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/cxl/switch-mailbox-cci.c
+++ b/hw/cxl/switch-mailbox-cci.c
@@ -XXX,XX +XXX,XX @@ static void cswmbcci_class_init(ObjectClass *oc, void *data)
     pc->device_id = 0xa123;
     pc->revision = 0;
     dc->desc = "CXL Switch Mailbox CCI";
-    dc->reset = cswmbcci_reset;
+    device_class_set_legacy_reset(dc, cswmbcci_reset);
     device_class_set_props(dc, cxl_switch_cci_props);
 }
 
diff --git a/hw/display/artist.c b/hw/display/artist.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/artist.c
+++ b/hw/display/artist.c
@@ -XXX,XX +XXX,XX @@ static void artist_class_init(ObjectClass *klass, void *data)
 
     dc->realize = artist_realizefn;
     dc->vmsd = &vmstate_artist;
-    dc->reset = artist_reset;
+    device_class_set_legacy_reset(dc, artist_reset);
     device_class_set_props(dc, artist_properties);
 }
 
diff --git a/hw/display/ati.c b/hw/display/ati.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/ati.c
+++ b/hw/display/ati.c
@@ -XXX,XX +XXX,XX @@ static void ati_vga_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
-    dc->reset = ati_vga_reset;
+    device_class_set_legacy_reset(dc, ati_vga_reset);
     device_class_set_props(dc, ati_vga_properties);
     dc->hotpluggable = false;
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
diff --git a/hw/display/bcm2835_fb.c b/hw/display/bcm2835_fb.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/bcm2835_fb.c
+++ b/hw/display/bcm2835_fb.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_fb_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, bcm2835_fb_props);
     dc->realize = bcm2835_fb_realize;
-    dc->reset = bcm2835_fb_reset;
+    device_class_set_legacy_reset(dc, bcm2835_fb_reset);
     dc->vmsd = &vmstate_bcm2835_fb;
 }
 
diff --git a/hw/display/cg3.c b/hw/display/cg3.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/cg3.c
+++ b/hw/display/cg3.c
@@ -XXX,XX +XXX,XX @@ static void cg3_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = cg3_realizefn;
-    dc->reset = cg3_reset;
+    device_class_set_legacy_reset(dc, cg3_reset);
     dc->vmsd = &vmstate_cg3;
     device_class_set_props(dc, cg3_properties);
 }
diff --git a/hw/display/dpcd.c b/hw/display/dpcd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/dpcd.c
+++ b/hw/display/dpcd.c
@@ -XXX,XX +XXX,XX @@ static void dpcd_class_init(ObjectClass *oc, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
 
-    dc->reset = dpcd_reset;
+    device_class_set_legacy_reset(dc, dpcd_reset);
     dc->vmsd = &vmstate_dpcd;
 }
 
diff --git a/hw/display/exynos4210_fimd.c b/hw/display/exynos4210_fimd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/exynos4210_fimd.c
+++ b/hw/display/exynos4210_fimd.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_fimd_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &exynos4210_fimd_vmstate;
-    dc->reset = exynos4210_fimd_reset;
+    device_class_set_legacy_reset(dc, exynos4210_fimd_reset);
     dc->realize = exynos4210_fimd_realize;
     device_class_set_props(dc, exynos4210_fimd_properties);
 }
diff --git a/hw/display/g364fb.c b/hw/display/g364fb.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/g364fb.c
+++ b/hw/display/g364fb.c
@@ -XXX,XX +XXX,XX @@ static void g364fb_sysbus_class_init(ObjectClass *klass, void *data)
     dc->realize = g364fb_sysbus_realize;
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
     dc->desc = "G364 framebuffer";
-    dc->reset = g364fb_sysbus_reset;
+    device_class_set_legacy_reset(dc, g364fb_sysbus_reset);
     dc->vmsd = &vmstate_g364fb_sysbus;
     device_class_set_props(dc, g364fb_sysbus_properties);
 }
diff --git a/hw/display/i2c-ddc.c b/hw/display/i2c-ddc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/i2c-ddc.c
+++ b/hw/display/i2c-ddc.c
@@ -XXX,XX +XXX,XX @@ static void i2c_ddc_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
     I2CSlaveClass *isc = I2C_SLAVE_CLASS(oc);
 
-    dc->reset = i2c_ddc_reset;
+    device_class_set_legacy_reset(dc, i2c_ddc_reset);
     dc->vmsd = &vmstate_i2c_ddc;
     device_class_set_props(dc, i2c_ddc_properties);
     isc->event = i2c_ddc_event;
diff --git a/hw/display/jazz_led.c b/hw/display/jazz_led.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/jazz_led.c
+++ b/hw/display/jazz_led.c
@@ -XXX,XX +XXX,XX @@ static void jazz_led_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "Jazz LED display",
     dc->vmsd = &vmstate_jazz_led;
-    dc->reset = jazz_led_reset;
+    device_class_set_legacy_reset(dc, jazz_led_reset);
     dc->realize = jazz_led_realize;
 }
 
diff --git a/hw/display/macfb.c b/hw/display/macfb.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/macfb.c
+++ b/hw/display/macfb.c
@@ -XXX,XX +XXX,XX @@ static void macfb_sysbus_class_init(ObjectClass *klass, void *data)
 
     dc->realize = macfb_sysbus_realize;
     dc->desc = "SysBus Macintosh framebuffer";
-    dc->reset = macfb_sysbus_reset;
+    device_class_set_legacy_reset(dc, macfb_sysbus_reset);
     dc->vmsd = &vmstate_macfb_sysbus;
     device_class_set_props(dc, macfb_sysbus_properties);
 }
@@ -XXX,XX +XXX,XX @@ static void macfb_nubus_class_init(ObjectClass *klass, void *data)
     device_class_set_parent_unrealize(dc, macfb_nubus_unrealize,
                                       &ndc->parent_unrealize);
     dc->desc = "Nubus Macintosh framebuffer";
-    dc->reset = macfb_nubus_reset;
+    device_class_set_legacy_reset(dc, macfb_nubus_reset);
     dc->vmsd = &vmstate_macfb_nubus;
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
     device_class_set_props(dc, macfb_nubus_properties);
diff --git a/hw/display/qxl.c b/hw/display/qxl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/qxl.c
+++ b/hw/display/qxl.c
@@ -XXX,XX +XXX,XX @@ static void qxl_pci_class_init(ObjectClass *klass, void *data)
     k->vendor_id = REDHAT_PCI_VENDOR_ID;
     k->device_id = QXL_DEVICE_ID_STABLE;
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
-    dc->reset = qxl_reset_handler;
+    device_class_set_legacy_reset(dc, qxl_reset_handler);
     dc->vmsd = &qxl_vmstate;
     device_class_set_props(dc, qxl_properties);
 }
diff --git a/hw/display/sii9022.c b/hw/display/sii9022.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/sii9022.c
+++ b/hw/display/sii9022.c
@@ -XXX,XX +XXX,XX @@ static void sii9022_class_init(ObjectClass *klass, void *data)
     k->event = sii9022_event;
     k->recv = sii9022_rx;
     k->send = sii9022_tx;
-    dc->reset = sii9022_reset;
+    device_class_set_legacy_reset(dc, sii9022_reset);
     dc->realize = sii9022_realize;
     dc->vmsd = &vmstate_sii9022;
 }
diff --git a/hw/display/sm501.c b/hw/display/sm501.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/sm501.c
+++ b/hw/display/sm501.c
@@ -XXX,XX +XXX,XX @@ static void sm501_sysbus_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
     dc->desc = "SM501 Multimedia Companion";
     device_class_set_props(dc, sm501_sysbus_properties);
-    dc->reset = sm501_reset_sysbus;
+    device_class_set_legacy_reset(dc, sm501_reset_sysbus);
     dc->vmsd = &vmstate_sm501_sysbus;
 }
 
@@ -XXX,XX +XXX,XX @@ static void sm501_pci_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
     dc->desc = "SM501 Display Controller";
     device_class_set_props(dc, sm501_pci_properties);
-    dc->reset = sm501_reset_pci;
+    device_class_set_legacy_reset(dc, sm501_reset_pci);
     dc->hotpluggable = false;
     dc->vmsd = &vmstate_sm501_pci;
 }
diff --git a/hw/display/tcx.c b/hw/display/tcx.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/tcx.c
+++ b/hw/display/tcx.c
@@ -XXX,XX +XXX,XX @@ static void tcx_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = tcx_realizefn;
-    dc->reset = tcx_reset;
+    device_class_set_legacy_reset(dc, tcx_reset);
     dc->vmsd = &vmstate_tcx;
     device_class_set_props(dc, tcx_properties);
 }
diff --git a/hw/display/vga-isa.c b/hw/display/vga-isa.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/vga-isa.c
+++ b/hw/display/vga-isa.c
@@ -XXX,XX +XXX,XX @@ static void vga_isa_class_initfn(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = vga_isa_realizefn;
-    dc->reset = vga_isa_reset;
+    device_class_set_legacy_reset(dc, vga_isa_reset);
     dc->vmsd = &vmstate_vga_common;
     device_class_set_props(dc, vga_isa_properties);
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
diff --git a/hw/display/vga-mmio.c b/hw/display/vga-mmio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/vga-mmio.c
+++ b/hw/display/vga-mmio.c
@@ -XXX,XX +XXX,XX @@ static void vga_mmio_class_initfn(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = vga_mmio_realizefn;
-    dc->reset = vga_mmio_reset;
+    device_class_set_legacy_reset(dc, vga_mmio_reset);
     dc->vmsd = &vmstate_vga_common;
     device_class_set_props(dc, vga_mmio_properties);
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
diff --git a/hw/display/vga-pci.c b/hw/display/vga-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/vga-pci.c
+++ b/hw/display/vga-pci.c
@@ -XXX,XX +XXX,XX @@ static void secondary_class_init(ObjectClass *klass, void *data)
     k->exit = pci_secondary_vga_exit;
     k->class_id = PCI_CLASS_DISPLAY_OTHER;
     device_class_set_props(dc, secondary_pci_properties);
-    dc->reset = pci_secondary_vga_reset;
+    device_class_set_legacy_reset(dc, pci_secondary_vga_reset);
 }
 
 static const TypeInfo vga_info = {
diff --git a/hw/display/vmware_vga.c b/hw/display/vmware_vga.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/vmware_vga.c
+++ b/hw/display/vmware_vga.c
@@ -XXX,XX +XXX,XX @@ static void vmsvga_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_DISPLAY_VGA;
     k->subsystem_vendor_id = PCI_VENDOR_ID_VMWARE;
     k->subsystem_id = SVGA_PCI_DEVICE_ID;
-    dc->reset = vmsvga_reset;
+    device_class_set_legacy_reset(dc, vmsvga_reset);
     dc->vmsd = &vmstate_vmware_vga;
     device_class_set_props(dc, vga_vmware_properties);
     dc->hotpluggable = false;
diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/xlnx_dp.c
+++ b/hw/display/xlnx_dp.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_dp_class_init(ObjectClass *oc, void *data)
 
     dc->realize = xlnx_dp_realize;
     dc->vmsd = &vmstate_dp;
-    dc->reset = xlnx_dp_reset;
+    device_class_set_legacy_reset(dc, xlnx_dp_reset);
     device_class_set_props(dc, xlnx_dp_device_properties);
 }
 
diff --git a/hw/dma/bcm2835_dma.c b/hw/dma/bcm2835_dma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/bcm2835_dma.c
+++ b/hw/dma/bcm2835_dma.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_dma_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = bcm2835_dma_realize;
-    dc->reset = bcm2835_dma_reset;
+    device_class_set_legacy_reset(dc, bcm2835_dma_reset);
     dc->vmsd = &vmstate_bcm2835_dma;
 }
 
diff --git a/hw/dma/i8257.c b/hw/dma/i8257.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/i8257.c
+++ b/hw/dma/i8257.c
@@ -XXX,XX +XXX,XX @@ static void i8257_class_init(ObjectClass *klass, void *data)
     IsaDmaClass *idc = ISADMA_CLASS(klass);
 
     dc->realize = i8257_realize;
-    dc->reset = i8257_reset;
+    device_class_set_legacy_reset(dc, i8257_reset);
     dc->vmsd = &vmstate_i8257;
     device_class_set_props(dc, i8257_properties);
 
diff --git a/hw/dma/pl080.c b/hw/dma/pl080.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/pl080.c
+++ b/hw/dma/pl080.c
@@ -XXX,XX +XXX,XX @@ static void pl080_class_init(ObjectClass *oc, void *data)
     dc->vmsd = &vmstate_pl080;
     dc->realize = pl080_realize;
     device_class_set_props(dc, pl080_properties);
-    dc->reset = pl080_reset;
+    device_class_set_legacy_reset(dc, pl080_reset);
 }
 
 static const TypeInfo pl080_info = {
diff --git a/hw/dma/pl330.c b/hw/dma/pl330.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/pl330.c
+++ b/hw/dma/pl330.c
@@ -XXX,XX +XXX,XX @@ static void pl330_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = pl330_realize;
-    dc->reset = pl330_reset;
+    device_class_set_legacy_reset(dc, pl330_reset);
     device_class_set_props(dc, pl330_properties);
     dc->vmsd = &vmstate_pl330;
 }
diff --git a/hw/dma/rc4030.c b/hw/dma/rc4030.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/rc4030.c
+++ b/hw/dma/rc4030.c
@@ -XXX,XX +XXX,XX @@ static void rc4030_class_init(ObjectClass *klass, void *class_data)
 
     dc->realize = rc4030_realize;
     dc->unrealize = rc4030_unrealize;
-    dc->reset = rc4030_reset;
+    device_class_set_legacy_reset(dc, rc4030_reset);
     dc->vmsd = &vmstate_rc4030;
 }
 
diff --git a/hw/dma/sparc32_dma.c b/hw/dma/sparc32_dma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/sparc32_dma.c
+++ b/hw/dma/sparc32_dma.c
@@ -XXX,XX +XXX,XX @@ static void sparc32_dma_device_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = sparc32_dma_device_reset;
+    device_class_set_legacy_reset(dc, sparc32_dma_device_reset);
     dc->vmsd = &vmstate_sparc32_dma_device;
 }
 
diff --git a/hw/dma/xilinx_axidma.c b/hw/dma/xilinx_axidma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/xilinx_axidma.c
+++ b/hw/dma/xilinx_axidma.c
@@ -XXX,XX +XXX,XX @@ static void axidma_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = xilinx_axidma_realize;
-    dc->reset = xilinx_axidma_reset;
+    device_class_set_legacy_reset(dc, xilinx_axidma_reset);
     device_class_set_props(dc, axidma_properties);
 }
 
diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/xlnx-zdma.c
+++ b/hw/dma/xlnx-zdma.c
@@ -XXX,XX +XXX,XX @@ static void zdma_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = zdma_reset;
+    device_class_set_legacy_reset(dc, zdma_reset);
     dc->realize = zdma_realize;
     device_class_set_props(dc, zdma_props);
     dc->vmsd = &vmstate_zdma;
diff --git a/hw/dma/xlnx-zynq-devcfg.c b/hw/dma/xlnx-zynq-devcfg.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/xlnx-zynq-devcfg.c
+++ b/hw/dma/xlnx-zynq-devcfg.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_zynq_devcfg_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xlnx_zynq_devcfg_reset;
+    device_class_set_legacy_reset(dc, xlnx_zynq_devcfg_reset);
     dc->vmsd = &vmstate_xlnx_zynq_devcfg;
 }
 
diff --git a/hw/dma/xlnx_csu_dma.c b/hw/dma/xlnx_csu_dma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/xlnx_csu_dma.c
+++ b/hw/dma/xlnx_csu_dma.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_csu_dma_class_init(ObjectClass *klass, void *data)
     StreamSinkClass *ssc = STREAM_SINK_CLASS(klass);
     XlnxCSUDMAClass *xcdc = XLNX_CSU_DMA_CLASS(klass);
 
-    dc->reset = xlnx_csu_dma_reset;
+    device_class_set_legacy_reset(dc, xlnx_csu_dma_reset);
     dc->realize = xlnx_csu_dma_realize;
     dc->vmsd = &vmstate_xlnx_csu_dma;
     device_class_set_props(dc, xlnx_csu_dma_properties);
diff --git a/hw/dma/xlnx_dpdma.c b/hw/dma/xlnx_dpdma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/dma/xlnx_dpdma.c
+++ b/hw/dma/xlnx_dpdma.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_dpdma_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->vmsd = &vmstate_xlnx_dpdma;
-    dc->reset = xlnx_dpdma_reset;
+    device_class_set_legacy_reset(dc, xlnx_dpdma_reset);
 }
 
 static const TypeInfo xlnx_dpdma_info = {
diff --git a/hw/fsi/aspeed_apb2opb.c b/hw/fsi/aspeed_apb2opb.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/fsi/aspeed_apb2opb.c
+++ b/hw/fsi/aspeed_apb2opb.c
@@ -XXX,XX +XXX,XX @@ static void fsi_aspeed_apb2opb_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "ASPEED APB2OPB Bridge";
     dc->realize = fsi_aspeed_apb2opb_realize;
-    dc->reset = fsi_aspeed_apb2opb_reset;
+    device_class_set_legacy_reset(dc, fsi_aspeed_apb2opb_reset);
 }
 
 static const TypeInfo aspeed_apb2opb_info = {
diff --git a/hw/fsi/fsi-master.c b/hw/fsi/fsi-master.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/fsi/fsi-master.c
+++ b/hw/fsi/fsi-master.c
@@ -XXX,XX +XXX,XX @@ static void fsi_master_class_init(ObjectClass *klass, void *data)
     dc->bus_type = TYPE_OP_BUS;
     dc->desc = "FSI Master";
     dc->realize = fsi_master_realize;
-    dc->reset = fsi_master_reset;
+    device_class_set_legacy_reset(dc, fsi_master_reset);
 }
 
 static const TypeInfo fsi_master_info = {
diff --git a/hw/fsi/fsi.c b/hw/fsi/fsi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/fsi/fsi.c
+++ b/hw/fsi/fsi.c
@@ -XXX,XX +XXX,XX @@ static void fsi_slave_class_init(ObjectClass *klass, void *data)
 
     dc->bus_type = TYPE_FSI_BUS;
     dc->desc = "FSI Slave";
-    dc->reset = fsi_slave_reset;
+    device_class_set_legacy_reset(dc, fsi_slave_reset);
 }
 
 static const TypeInfo fsi_slave_info = {
diff --git a/hw/fsi/lbus.c b/hw/fsi/lbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/fsi/lbus.c
+++ b/hw/fsi/lbus.c
@@ -XXX,XX +XXX,XX @@ static void fsi_scratchpad_class_init(ObjectClass *klass, void *data)
 
     dc->bus_type = TYPE_FSI_LBUS;
     dc->realize = fsi_scratchpad_realize;
-    dc->reset = fsi_scratchpad_reset;
+    device_class_set_legacy_reset(dc, fsi_scratchpad_reset);
 }
 
 static const TypeInfo fsi_scratchpad_info = {
diff --git a/hw/gpio/aspeed_gpio.c b/hw/gpio/aspeed_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/aspeed_gpio.c
+++ b/hw/gpio/aspeed_gpio.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_gpio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_gpio_realize;
-    dc->reset = aspeed_gpio_reset;
+    device_class_set_legacy_reset(dc, aspeed_gpio_reset);
     dc->desc = "Aspeed GPIO Controller";
     dc->vmsd = &vmstate_aspeed_gpio;
 }
diff --git a/hw/gpio/bcm2835_gpio.c b/hw/gpio/bcm2835_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/bcm2835_gpio.c
+++ b/hw/gpio/bcm2835_gpio.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_gpio_class_init(ObjectClass *klass, void *data)
 
     dc->vmsd = &vmstate_bcm2835_gpio;
     dc->realize = &bcm2835_gpio_realize;
-    dc->reset = &bcm2835_gpio_reset;
+    device_class_set_legacy_reset(dc, bcm2835_gpio_reset);
 }
 
 static const TypeInfo bcm2835_gpio_info = {
diff --git a/hw/gpio/bcm2838_gpio.c b/hw/gpio/bcm2838_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/bcm2838_gpio.c
+++ b/hw/gpio/bcm2838_gpio.c
@@ -XXX,XX +XXX,XX @@ static void bcm2838_gpio_class_init(ObjectClass *klass, void *data)
 
     dc->vmsd = &vmstate_bcm2838_gpio;
     dc->realize = &bcm2838_gpio_realize;
-    dc->reset = &bcm2838_gpio_reset;
+    device_class_set_legacy_reset(dc, bcm2838_gpio_reset);
 }
 
 static const TypeInfo bcm2838_gpio_info = {
diff --git a/hw/gpio/gpio_key.c b/hw/gpio/gpio_key.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/gpio_key.c
+++ b/hw/gpio/gpio_key.c
@@ -XXX,XX +XXX,XX @@ static void gpio_key_class_init(ObjectClass *klass, void *data)
 
     dc->realize = gpio_key_realize;
     dc->vmsd = &vmstate_gpio_key;
-    dc->reset = &gpio_key_reset;
+    device_class_set_legacy_reset(dc, gpio_key_reset);
 }
 
 static const TypeInfo gpio_key_info = {
diff --git a/hw/gpio/imx_gpio.c b/hw/gpio/imx_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/imx_gpio.c
+++ b/hw/gpio/imx_gpio.c
@@ -XXX,XX +XXX,XX @@ static void imx_gpio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = imx_gpio_realize;
-    dc->reset = imx_gpio_reset;
+    device_class_set_legacy_reset(dc, imx_gpio_reset);
     device_class_set_props(dc, imx_gpio_properties);
     dc->vmsd = &vmstate_imx_gpio;
     dc->desc = "i.MX GPIO controller";
diff --git a/hw/gpio/max7310.c b/hw/gpio/max7310.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/max7310.c
+++ b/hw/gpio/max7310.c
@@ -XXX,XX +XXX,XX @@ static void max7310_class_init(ObjectClass *klass, void *data)
     k->event = max7310_event;
     k->recv = max7310_rx;
     k->send = max7310_tx;
-    dc->reset = max7310_reset;
+    device_class_set_legacy_reset(dc, max7310_reset);
     dc->vmsd = &vmstate_max7310;
 }
 
diff --git a/hw/gpio/mpc8xxx.c b/hw/gpio/mpc8xxx.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/mpc8xxx.c
+++ b/hw/gpio/mpc8xxx.c
@@ -XXX,XX +XXX,XX @@ static void mpc8xxx_gpio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_mpc8xxx_gpio;
-    dc->reset = mpc8xxx_gpio_reset;
+    device_class_set_legacy_reset(dc, mpc8xxx_gpio_reset);
 }
 
 static const TypeInfo mpc8xxx_gpio_info = {
diff --git a/hw/gpio/nrf51_gpio.c b/hw/gpio/nrf51_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/nrf51_gpio.c
+++ b/hw/gpio/nrf51_gpio.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_gpio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_nrf51_gpio;
-    dc->reset = nrf51_gpio_reset;
+    device_class_set_legacy_reset(dc, nrf51_gpio_reset);
     dc->desc = "nRF51 GPIO";
 }
 
diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/omap_gpio.c
+++ b/hw/gpio/omap_gpio.c
@@ -XXX,XX +XXX,XX @@ static void omap_gpio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = omap_gpio_realize;
-    dc->reset = omap_gpif_reset;
+    device_class_set_legacy_reset(dc, omap_gpif_reset);
     device_class_set_props(dc, omap_gpio_properties);
     /* Reason: pointer property "clk" */
     dc->user_creatable = false;
@@ -XXX,XX +XXX,XX @@ static void omap2_gpio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = omap2_gpio_realize;
-    dc->reset = omap2_gpif_reset;
+    device_class_set_legacy_reset(dc, omap2_gpif_reset);
     device_class_set_props(dc, omap2_gpio_properties);
     /* Reason: pointer properties "iclk", "fclk0", ..., "fclk5" */
     dc->user_creatable = false;
diff --git a/hw/gpio/pca9552.c b/hw/gpio/pca9552.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/pca9552.c
+++ b/hw/gpio/pca9552.c
@@ -XXX,XX +XXX,XX @@ static void pca9552_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
     PCA955xClass *pc = PCA955X_CLASS(oc);
 
-    dc->reset = pca9552_reset;
+    device_class_set_legacy_reset(dc, pca9552_reset);
     dc->vmsd = &pca9552_vmstate;
     pc->max_reg = PCA9552_LS3;
     pc->pin_count = 16;
diff --git a/hw/gpio/pca9554.c b/hw/gpio/pca9554.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/pca9554.c
+++ b/hw/gpio/pca9554.c
@@ -XXX,XX +XXX,XX @@ static void pca9554_class_init(ObjectClass *klass, void *data)
     k->recv = pca9554_recv;
     k->send = pca9554_send;
     dc->realize = pca9554_realize;
-    dc->reset = pca9554_reset;
+    device_class_set_legacy_reset(dc, pca9554_reset);
     dc->vmsd = &pca9554_vmstate;
     device_class_set_props(dc, pca9554_properties);
 }
diff --git a/hw/gpio/pcf8574.c b/hw/gpio/pcf8574.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/pcf8574.c
+++ b/hw/gpio/pcf8574.c
@@ -XXX,XX +XXX,XX @@ static void pcf8574_class_init(ObjectClass *klass, void *data)
     k->recv     = pcf8574_rx;
     k->send     = pcf8574_tx;
     dc->realize = pcf8574_realize;
-    dc->reset   = pcf8574_reset;
+    device_class_set_legacy_reset(dc, pcf8574_reset);
     dc->vmsd    = &vmstate_pcf8574;
 }
 
diff --git a/hw/gpio/sifive_gpio.c b/hw/gpio/sifive_gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/gpio/sifive_gpio.c
+++ b/hw/gpio/sifive_gpio.c
@@ -XXX,XX +XXX,XX @@ static void sifive_gpio_class_init(ObjectClass *klass, void *data)
     device_class_set_props(dc, sifive_gpio_properties);
     dc->vmsd = &vmstate_sifive_gpio;
     dc->realize = sifive_gpio_realize;
-    dc->reset = sifive_gpio_reset;
+    device_class_set_legacy_reset(dc, sifive_gpio_reset);
     dc->desc = "SiFive GPIO";
 }
 
diff --git a/hw/hyperv/hyperv.c b/hw/hyperv/hyperv.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/hyperv/hyperv.c
+++ b/hw/hyperv/hyperv.c
@@ -XXX,XX +XXX,XX @@ static void synic_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = synic_realize;
-    dc->reset = synic_reset;
+    device_class_set_legacy_reset(dc, synic_reset);
     dc->user_creatable = false;
 }
 
diff --git a/hw/hyperv/vmbus.c b/hw/hyperv/vmbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/hyperv/vmbus.c
+++ b/hw/hyperv/vmbus.c
@@ -XXX,XX +XXX,XX @@ static void vmbus_dev_class_init(ObjectClass *klass, void *data)
     kdev->bus_type = TYPE_VMBUS;
     kdev->realize = vmbus_dev_realize;
     kdev->unrealize = vmbus_dev_unrealize;
-    kdev->reset = vmbus_dev_reset;
+    device_class_set_legacy_reset(kdev, vmbus_dev_reset);
 }
 
 static void vmbus_dev_instance_init(Object *obj)
diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/aspeed_i2c.c
+++ b/hw/i2c/aspeed_i2c.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &aspeed_i2c_vmstate;
-    dc->reset = aspeed_i2c_reset;
+    device_class_set_legacy_reset(dc, aspeed_i2c_reset);
     device_class_set_props(dc, aspeed_i2c_properties);
     dc->realize = aspeed_i2c_realize;
     dc->desc = "Aspeed I2C Controller";
@@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "Aspeed I2C Bus";
     dc->realize = aspeed_i2c_bus_realize;
-    dc->reset = aspeed_i2c_bus_reset;
+    device_class_set_legacy_reset(dc, aspeed_i2c_bus_reset);
     device_class_set_props(dc, aspeed_i2c_bus_properties);
 }
 
diff --git a/hw/i2c/bcm2835_i2c.c b/hw/i2c/bcm2835_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/bcm2835_i2c.c
+++ b/hw/i2c/bcm2835_i2c.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_i2c_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2835_i2c_reset;
+    device_class_set_legacy_reset(dc, bcm2835_i2c_reset);
     dc->realize = bcm2835_i2c_realize;
     dc->vmsd = &vmstate_bcm2835_i2c;
 }
diff --git a/hw/i2c/exynos4210_i2c.c b/hw/i2c/exynos4210_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/exynos4210_i2c.c
+++ b/hw/i2c/exynos4210_i2c.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_i2c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &exynos4210_i2c_vmstate;
-    dc->reset = exynos4210_i2c_reset;
+    device_class_set_legacy_reset(dc, exynos4210_i2c_reset);
 }
 
 static const TypeInfo exynos4210_i2c_type_info = {
diff --git a/hw/i2c/imx_i2c.c b/hw/i2c/imx_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/imx_i2c.c
+++ b/hw/i2c/imx_i2c.c
@@ -XXX,XX +XXX,XX @@ static void imx_i2c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &imx_i2c_vmstate;
-    dc->reset = imx_i2c_reset;
+    device_class_set_legacy_reset(dc, imx_i2c_reset);
     dc->realize = imx_i2c_realize;
     dc->desc = "i.MX I2C Controller";
 }
diff --git a/hw/i2c/microbit_i2c.c b/hw/i2c/microbit_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/microbit_i2c.c
+++ b/hw/i2c/microbit_i2c.c
@@ -XXX,XX +XXX,XX @@ static void microbit_i2c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &microbit_i2c_vmstate;
-    dc->reset = microbit_i2c_reset;
+    device_class_set_legacy_reset(dc, microbit_i2c_reset);
     dc->realize = microbit_i2c_realize;
     dc->desc = "Microbit I2C controller";
 }
diff --git a/hw/i2c/mpc_i2c.c b/hw/i2c/mpc_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/mpc_i2c.c
+++ b/hw/i2c/mpc_i2c.c
@@ -XXX,XX +XXX,XX @@ static void mpc_i2c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd  = &mpc_i2c_vmstate ;
-    dc->reset = mpc_i2c_reset;
+    device_class_set_legacy_reset(dc, mpc_i2c_reset);
     dc->realize = mpc_i2c_realize;
     dc->desc = "MPC I2C Controller";
 }
diff --git a/hw/i2c/omap_i2c.c b/hw/i2c/omap_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/omap_i2c.c
+++ b/hw/i2c/omap_i2c.c
@@ -XXX,XX +XXX,XX @@ static void omap_i2c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     device_class_set_props(dc, omap_i2c_properties);
-    dc->reset = omap_i2c_reset;
+    device_class_set_legacy_reset(dc, omap_i2c_reset);
     /* Reason: pointer properties "iclk", "fclk" */
     dc->user_creatable = false;
     dc->realize = omap_i2c_realize;
diff --git a/hw/i2c/ppc4xx_i2c.c b/hw/i2c/ppc4xx_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/ppc4xx_i2c.c
+++ b/hw/i2c/ppc4xx_i2c.c
@@ -XXX,XX +XXX,XX @@ static void ppc4xx_i2c_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = ppc4xx_i2c_reset;
+    device_class_set_legacy_reset(dc, ppc4xx_i2c_reset);
 }
 
 static const TypeInfo ppc4xx_i2c_type_info = {
diff --git a/hw/i2c/smbus_eeprom.c b/hw/i2c/smbus_eeprom.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/smbus_eeprom.c
+++ b/hw/i2c/smbus_eeprom.c
@@ -XXX,XX +XXX,XX @@ static void smbus_eeprom_class_initfn(ObjectClass *klass, void *data)
     SMBusDeviceClass *sc = SMBUS_DEVICE_CLASS(klass);
 
     dc->realize = smbus_eeprom_realize;
-    dc->reset = smbus_eeprom_reset;
+    device_class_set_legacy_reset(dc, smbus_eeprom_reset);
     sc->receive_byte = eeprom_receive_byte;
     sc->write_data = eeprom_write_data;
     dc->vmsd = &vmstate_smbus_eeprom;
diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/amd_iommu.c
+++ b/hw/i386/amd_iommu.c
@@ -XXX,XX +XXX,XX @@ static void amdvi_sysbus_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     X86IOMMUClass *dc_class = X86_IOMMU_DEVICE_CLASS(klass);
 
-    dc->reset = amdvi_sysbus_reset;
+    device_class_set_legacy_reset(dc, amdvi_sysbus_reset);
     dc->vmsd = &vmstate_amdvi_sysbus;
     dc->hotpluggable = false;
     dc_class->realize = amdvi_sysbus_realize;
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -XXX,XX +XXX,XX @@ static void vtd_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     X86IOMMUClass *x86_class = X86_IOMMU_DEVICE_CLASS(klass);
 
-    dc->reset = vtd_reset;
+    device_class_set_legacy_reset(dc, vtd_reset);
     dc->vmsd = &vtd_vmstate;
     device_class_set_props(dc, vtd_properties);
     dc->hotpluggable = false;
diff --git a/hw/i386/kvm/i8254.c b/hw/i386/kvm/i8254.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/kvm/i8254.c
+++ b/hw/i386/kvm/i8254.c
@@ -XXX,XX +XXX,XX @@ static void kvm_pit_class_init(ObjectClass *klass, void *data)
                                     &kpc->parent_realize);
     k->set_channel_gate = kvm_pit_set_gate;
     k->get_channel_info = kvm_pit_get_channel_info;
-    dc->reset = kvm_pit_reset;
+    device_class_set_legacy_reset(dc, kvm_pit_reset);
     device_class_set_props(dc, kvm_pit_properties);
 }
 
diff --git a/hw/i386/kvm/i8259.c b/hw/i386/kvm/i8259.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/kvm/i8259.c
+++ b/hw/i386/kvm/i8259.c
@@ -XXX,XX +XXX,XX @@ static void kvm_i8259_class_init(ObjectClass *klass, void *data)
     PICCommonClass *k = PIC_COMMON_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset     = kvm_pic_reset;
+    device_class_set_legacy_reset(dc, kvm_pic_reset);
     device_class_set_parent_realize(dc, kvm_pic_realize, &kpc->parent_realize);
     k->pre_save   = kvm_pic_get;
     k->post_load  = kvm_pic_put;
diff --git a/hw/i386/kvm/ioapic.c b/hw/i386/kvm/ioapic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/kvm/ioapic.c
+++ b/hw/i386/kvm/ioapic.c
@@ -XXX,XX +XXX,XX @@ static void kvm_ioapic_class_init(ObjectClass *klass, void *data)
     k->realize   = kvm_ioapic_realize;
     k->pre_save  = kvm_ioapic_get;
     k->post_load = kvm_ioapic_put;
-    dc->reset    = kvm_ioapic_reset;
+    device_class_set_legacy_reset(dc, kvm_ioapic_reset);
     device_class_set_props(dc, kvm_ioapic_properties);
 }
 
diff --git a/hw/i386/kvm/xen_overlay.c b/hw/i386/kvm/xen_overlay.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/kvm/xen_overlay.c
+++ b/hw/i386/kvm/xen_overlay.c
@@ -XXX,XX +XXX,XX @@ static void xen_overlay_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xen_overlay_reset;
+    device_class_set_legacy_reset(dc, xen_overlay_reset);
     dc->realize = xen_overlay_realize;
     dc->vmsd = &xen_overlay_vmstate;
 }
diff --git a/hw/i386/port92.c b/hw/i386/port92.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/port92.c
+++ b/hw/i386/port92.c
@@ -XXX,XX +XXX,XX @@ static void port92_class_initfn(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = port92_realizefn;
-    dc->reset = port92_reset;
+    device_class_set_legacy_reset(dc, port92_reset);
     dc->vmsd = &vmstate_port92_isa;
     /*
      * Reason: unlike ordinary ISA devices, this one needs additional
diff --git a/hw/i386/vapic.c b/hw/i386/vapic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/vapic.c
+++ b/hw/i386/vapic.c
@@ -XXX,XX +XXX,XX @@ static void vapic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset   = vapic_reset;
+    device_class_set_legacy_reset(dc, vapic_reset);
     dc->vmsd    = &vmstate_vapic;
     dc->realize = vapic_realize;
 }
diff --git a/hw/i386/vmmouse.c b/hw/i386/vmmouse.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/vmmouse.c
+++ b/hw/i386/vmmouse.c
@@ -XXX,XX +XXX,XX @@ static void vmmouse_class_initfn(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = vmmouse_realizefn;
-    dc->reset = vmmouse_reset;
+    device_class_set_legacy_reset(dc, vmmouse_reset);
     dc->vmsd = &vmstate_vmmouse;
     device_class_set_props(dc, vmmouse_properties);
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
diff --git a/hw/i386/xen/xen_platform.c b/hw/i386/xen/xen_platform.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i386/xen/xen_platform.c
+++ b/hw/i386/xen/xen_platform.c
@@ -XXX,XX +XXX,XX @@ static void xen_platform_class_init(ObjectClass *klass, void *data)
     k->revision = 1;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->desc = "XEN platform pci device";
-    dc->reset = platform_reset;
+    device_class_set_legacy_reset(dc, platform_reset);
     dc->vmsd = &vmstate_xen_platform;
 }
 
diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/ahci.c
+++ b/hw/ide/ahci.c
@@ -XXX,XX +XXX,XX @@ static void sysbus_ahci_class_init(ObjectClass *klass, void *data)
     dc->realize = sysbus_ahci_realize;
     dc->vmsd = &vmstate_sysbus_ahci;
     device_class_set_props(dc, sysbus_ahci_properties);
-    dc->reset = sysbus_ahci_reset;
+    device_class_set_legacy_reset(dc, sysbus_ahci_reset);
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
 
diff --git a/hw/ide/cmd646.c b/hw/ide/cmd646.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/cmd646.c
+++ b/hw/ide/cmd646.c
@@ -XXX,XX +XXX,XX @@ static void cmd646_ide_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
-    dc->reset = cmd646_reset;
+    device_class_set_legacy_reset(dc, cmd646_reset);
     dc->vmsd = &vmstate_ide_pci;
     k->realize = pci_cmd646_ide_realize;
     k->exit = pci_cmd646_ide_exitfn;
diff --git a/hw/ide/ich.c b/hw/ide/ich.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/ich.c
+++ b/hw/ide/ich.c
@@ -XXX,XX +XXX,XX @@ static void ich_ahci_class_init(ObjectClass *klass, void *data)
     k->revision = 0x02;
     k->class_id = PCI_CLASS_STORAGE_SATA;
     dc->vmsd = &vmstate_ich9_ahci;
-    dc->reset = pci_ich9_reset;
+    device_class_set_legacy_reset(dc, pci_ich9_reset);
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
 
diff --git a/hw/ide/isa.c b/hw/ide/isa.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/isa.c
+++ b/hw/ide/isa.c
@@ -XXX,XX +XXX,XX @@ static void isa_ide_class_initfn(ObjectClass *klass, void *data)
 
     dc->realize = isa_ide_realizefn;
     dc->fw_name = "ide";
-    dc->reset = isa_ide_reset;
+    device_class_set_legacy_reset(dc, isa_ide_reset);
     device_class_set_props(dc, isa_ide_properties);
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
diff --git a/hw/ide/macio.c b/hw/ide/macio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/macio.c
+++ b/hw/ide/macio.c
@@ -XXX,XX +XXX,XX @@ static void macio_ide_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = macio_ide_realizefn;
-    dc->reset = macio_ide_reset;
+    device_class_set_legacy_reset(dc, macio_ide_reset);
     device_class_set_props(dc, macio_ide_properties);
     dc->vmsd = &vmstate_pmac;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
diff --git a/hw/ide/microdrive.c b/hw/ide/microdrive.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/microdrive.c
+++ b/hw/ide/microdrive.c
@@ -XXX,XX +XXX,XX @@ static void microdrive_class_init(ObjectClass *oc, void *data)
     pcc->io_write = md_common_write;
 
     dc->realize = microdrive_realize;
-    dc->reset = md_reset;
+    device_class_set_legacy_reset(dc, md_reset);
     dc->vmsd = &vmstate_microdrive;
 }
 
diff --git a/hw/ide/mmio.c b/hw/ide/mmio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/mmio.c
+++ b/hw/ide/mmio.c
@@ -XXX,XX +XXX,XX @@ static void mmio_ide_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = mmio_ide_realizefn;
-    dc->reset = mmio_ide_reset;
+    device_class_set_legacy_reset(dc, mmio_ide_reset);
     device_class_set_props(dc, mmio_ide_properties);
     dc->vmsd = &vmstate_ide_mmio;
 }
diff --git a/hw/ide/piix.c b/hw/ide/piix.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -XXX,XX +XXX,XX @@ static void piix3_ide_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
-    dc->reset = piix_ide_reset;
+    device_class_set_legacy_reset(dc, piix_ide_reset);
     dc->vmsd = &vmstate_ide_pci;
     k->realize = pci_piix_ide_realize;
     k->exit = pci_piix_ide_exitfn;
@@ -XXX,XX +XXX,XX @@ static void piix4_ide_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
-    dc->reset = piix_ide_reset;
+    device_class_set_legacy_reset(dc, piix_ide_reset);
     dc->vmsd = &vmstate_ide_pci;
     k->realize = pci_piix_ide_realize;
     k->exit = pci_piix_ide_exitfn;
diff --git a/hw/ide/sii3112.c b/hw/ide/sii3112.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/sii3112.c
+++ b/hw/ide/sii3112.c
@@ -XXX,XX +XXX,XX @@ static void sii3112_pci_class_init(ObjectClass *klass, void *data)
     pd->class_id = PCI_CLASS_STORAGE_RAID;
     pd->revision = 1;
     pd->realize = sii3112_pci_realize;
-    dc->reset = sii3112_reset;
+    device_class_set_legacy_reset(dc, sii3112_reset);
     dc->desc = "SiI3112A SATA controller";
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
diff --git a/hw/ide/via.c b/hw/ide/via.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ide/via.c
+++ b/hw/ide/via.c
@@ -XXX,XX +XXX,XX @@ static void via_ide_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
-    dc->reset = via_ide_reset;
+    device_class_set_legacy_reset(dc, via_ide_reset);
     dc->vmsd = &vmstate_ide_pci;
     /* Reason: only works as function of VIA southbridge */
     dc->user_creatable = false;
diff --git a/hw/input/adb-kbd.c b/hw/input/adb-kbd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/input/adb-kbd.c
+++ b/hw/input/adb-kbd.c
@@ -XXX,XX +XXX,XX @@ static void adb_kbd_class_init(ObjectClass *oc, void *data)
 
     adc->devreq = adb_kbd_request;
     adc->devhasdata = adb_kbd_has_data;
-    dc->reset = adb_kbd_reset;
+    device_class_set_legacy_reset(dc, adb_kbd_reset);
     dc->vmsd = &vmstate_adb_kbd;
 }
 
diff --git a/hw/input/adb-mouse.c b/hw/input/adb-mouse.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/input/adb-mouse.c
+++ b/hw/input/adb-mouse.c
@@ -XXX,XX +XXX,XX @@ static void adb_mouse_class_init(ObjectClass *oc, void *data)
 
     adc->devreq = adb_mouse_request;
     adc->devhasdata = adb_mouse_has_data;
-    dc->reset = adb_mouse_reset;
+    device_class_set_legacy_reset(dc, adb_mouse_reset);
     dc->vmsd = &vmstate_adb_mouse;
 }
 
diff --git a/hw/input/lm832x.c b/hw/input/lm832x.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/input/lm832x.c
+++ b/hw/input/lm832x.c
@@ -XXX,XX +XXX,XX @@ static void lm8323_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     I2CSlaveClass *k = I2C_SLAVE_CLASS(klass);
 
-    dc->reset = lm_kbd_reset;
+    device_class_set_legacy_reset(dc, lm_kbd_reset);
     dc->realize = lm8323_realize;
     k->event = lm_i2c_event;
     k->recv = lm_i2c_rx;
diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/input/pckbd.c
+++ b/hw/input/pckbd.c
@@ -XXX,XX +XXX,XX @@ static void i8042_mmio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = i8042_mmio_realize;
-    dc->reset = i8042_mmio_reset;
+    device_class_set_legacy_reset(dc, i8042_mmio_reset);
     dc->vmsd = &vmstate_kbd_mmio;
     device_class_set_props(dc, i8042_mmio_properties);
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
@@ -XXX,XX +XXX,XX @@ static void i8042_class_initfn(ObjectClass *klass, void *data)
     AcpiDevAmlIfClass *adevc = ACPI_DEV_AML_IF_CLASS(klass);
 
     device_class_set_props(dc, i8042_properties);
-    dc->reset = i8042_reset;
+    device_class_set_legacy_reset(dc, i8042_reset);
     dc->realize = i8042_realizefn;
     dc->vmsd = &vmstate_kbd_isa;
     adevc->build_dev_aml = i8042_build_aml;
diff --git a/hw/intc/allwinner-a10-pic.c b/hw/intc/allwinner-a10-pic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/allwinner-a10-pic.c
+++ b/hw/intc/allwinner-a10-pic.c
@@ -XXX,XX +XXX,XX @@ static void aw_a10_pic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = aw_a10_pic_reset;
+    device_class_set_legacy_reset(dc, aw_a10_pic_reset);
     dc->desc = "allwinner a10 pic";
     dc->vmsd = &vmstate_aw_a10_pic;
  }
diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/apic_common.c
+++ b/hw/intc/apic_common.c
@@ -XXX,XX +XXX,XX @@ static void apic_common_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = apic_reset_common;
+    device_class_set_legacy_reset(dc, apic_reset_common);
     device_class_set_props(dc, apic_properties_common);
     dc->realize = apic_common_realize;
     dc->unrealize = apic_common_unrealize;
diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/armv7m_nvic.c
+++ b/hw/intc/armv7m_nvic.c
@@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_class_init(ObjectClass *klass, void *data)
 
     dc->vmsd  = &vmstate_nvic;
     device_class_set_props(dc, props_nvic);
-    dc->reset = armv7m_nvic_reset;
+    device_class_set_legacy_reset(dc, armv7m_nvic_reset);
     dc->realize = armv7m_nvic_realize;
 }
 
diff --git a/hw/intc/aspeed_intc.c b/hw/intc/aspeed_intc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/aspeed_intc.c
+++ b/hw/intc/aspeed_intc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_intc_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "ASPEED INTC Controller";
     dc->realize = aspeed_intc_realize;
-    dc->reset = aspeed_intc_reset;
+    device_class_set_legacy_reset(dc, aspeed_intc_reset);
     dc->vmsd = NULL;
 }
 
diff --git a/hw/intc/aspeed_vic.c b/hw/intc/aspeed_vic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/aspeed_vic.c
+++ b/hw/intc/aspeed_vic.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_vic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->realize = aspeed_vic_realize;
-    dc->reset = aspeed_vic_reset;
+    device_class_set_legacy_reset(dc, aspeed_vic_reset);
     dc->desc = "ASPEED Interrupt Controller (New)";
     dc->vmsd = &vmstate_aspeed_vic;
 }
diff --git a/hw/intc/bcm2835_ic.c b/hw/intc/bcm2835_ic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/bcm2835_ic.c
+++ b/hw/intc/bcm2835_ic.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_ic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2835_ic_reset;
+    device_class_set_legacy_reset(dc, bcm2835_ic_reset);
     dc->vmsd = &vmstate_bcm2835_ic;
 }
 
diff --git a/hw/intc/bcm2836_control.c b/hw/intc/bcm2836_control.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/bcm2836_control.c
+++ b/hw/intc/bcm2836_control.c
@@ -XXX,XX +XXX,XX @@ static void bcm2836_control_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2836_control_reset;
+    device_class_set_legacy_reset(dc, bcm2836_control_reset);
     dc->vmsd = &vmstate_bcm2836_control;
 }
 
diff --git a/hw/intc/exynos4210_combiner.c b/hw/intc/exynos4210_combiner.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/exynos4210_combiner.c
+++ b/hw/intc/exynos4210_combiner.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_combiner_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_combiner_reset;
+    device_class_set_legacy_reset(dc, exynos4210_combiner_reset);
     device_class_set_props(dc, exynos4210_combiner_properties);
     dc->vmsd = &vmstate_exynos4210_combiner;
 }
diff --git a/hw/intc/goldfish_pic.c b/hw/intc/goldfish_pic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/goldfish_pic.c
+++ b/hw/intc/goldfish_pic.c
@@ -XXX,XX +XXX,XX @@ static void goldfish_pic_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
     InterruptStatsProviderClass *ic = INTERRUPT_STATS_PROVIDER_CLASS(oc);
 
-    dc->reset = goldfish_pic_reset;
+    device_class_set_legacy_reset(dc, goldfish_pic_reset);
     dc->realize = goldfish_pic_realize;
     dc->vmsd = &vmstate_goldfish_pic;
     ic->get_statistics = goldfish_pic_get_statistics;
diff --git a/hw/intc/grlib_irqmp.c b/hw/intc/grlib_irqmp.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/grlib_irqmp.c
+++ b/hw/intc/grlib_irqmp.c
@@ -XXX,XX +XXX,XX @@ static void grlib_irqmp_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = grlib_irqmp_realize;
-    dc->reset = grlib_irqmp_reset;
+    device_class_set_legacy_reset(dc, grlib_irqmp_reset);
     device_class_set_props(dc, grlib_irqmp_properties);
 }
 
diff --git a/hw/intc/heathrow_pic.c b/hw/intc/heathrow_pic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/heathrow_pic.c
+++ b/hw/intc/heathrow_pic.c
@@ -XXX,XX +XXX,XX @@ static void heathrow_class_init(ObjectClass *oc, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
 
-    dc->reset = heathrow_reset;
+    device_class_set_legacy_reset(dc, heathrow_reset);
     dc->vmsd = &vmstate_heathrow;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
diff --git a/hw/intc/i8259.c b/hw/intc/i8259.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/i8259.c
+++ b/hw/intc/i8259.c
@@ -XXX,XX +XXX,XX @@ static void i8259_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     device_class_set_parent_realize(dc, pic_realize, &k->parent_realize);
-    dc->reset = pic_reset;
+    device_class_set_legacy_reset(dc, pic_reset);
 }
 
 static const TypeInfo i8259_info = {
diff --git a/hw/intc/imx_avic.c b/hw/intc/imx_avic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/imx_avic.c
+++ b/hw/intc/imx_avic.c
@@ -XXX,XX +XXX,XX @@ static void imx_avic_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_imx_avic;
-    dc->reset = imx_avic_reset;
+    device_class_set_legacy_reset(dc, imx_avic_reset);
     dc->desc = "i.MX Advanced Vector Interrupt Controller";
 }
 
diff --git a/hw/intc/imx_gpcv2.c b/hw/intc/imx_gpcv2.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/imx_gpcv2.c
+++ b/hw/intc/imx_gpcv2.c
@@ -XXX,XX +XXX,XX @@ static void imx_gpcv2_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = imx_gpcv2_reset;
+    device_class_set_legacy_reset(dc, imx_gpcv2_reset);
     dc->vmsd  = &vmstate_imx_gpcv2;
     dc->desc  = "i.MX GPCv2 Module";
 }
diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -XXX,XX +XXX,XX @@ static void ioapic_class_init(ObjectClass *klass, void *data)
      * migration, otherwise first 24 gsi routes will be invalid.
      */
     k->post_load = ioapic_update_kvm_routes;
-    dc->reset = ioapic_reset_common;
+    device_class_set_legacy_reset(dc, ioapic_reset_common);
     device_class_set_props(dc, ioapic_properties);
 }
 
diff --git a/hw/intc/loongarch_extioi.c b/hw/intc/loongarch_extioi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/loongarch_extioi.c
+++ b/hw/intc/loongarch_extioi.c
@@ -XXX,XX +XXX,XX @@ static void loongarch_extioi_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = loongarch_extioi_realize;
-    dc->reset   = loongarch_extioi_reset;
+    device_class_set_legacy_reset(dc, loongarch_extioi_reset);
     device_class_set_props(dc, extioi_properties);
     dc->vmsd = &vmstate_loongarch_extioi;
 }
diff --git a/hw/intc/loongarch_pch_pic.c b/hw/intc/loongarch_pch_pic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/loongarch_pch_pic.c
+++ b/hw/intc/loongarch_pch_pic.c
@@ -XXX,XX +XXX,XX @@ static void loongarch_pch_pic_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = loongarch_pch_pic_realize;
-    dc->reset = loongarch_pch_pic_reset;
+    device_class_set_legacy_reset(dc, loongarch_pch_pic_reset);
     dc->vmsd = &vmstate_loongarch_pch_pic;
     device_class_set_props(dc, loongarch_pch_pic_properties);
 }
diff --git a/hw/intc/m68k_irqc.c b/hw/intc/m68k_irqc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/m68k_irqc.c
+++ b/hw/intc/m68k_irqc.c
@@ -XXX,XX +XXX,XX @@ static void m68k_irqc_class_init(ObjectClass *oc, void *data)
 
     device_class_set_props(dc, m68k_irqc_properties);
     nc->nmi_monitor_handler = m68k_nmi;
-    dc->reset = m68k_irqc_reset;
+    device_class_set_legacy_reset(dc, m68k_irqc_reset);
     dc->vmsd = &vmstate_m68k_irqc;
     ic->get_statistics = m68k_irqc_get_statistics;
     ic->print_info = m68k_irqc_print_info;
diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/omap_intc.c
+++ b/hw/intc/omap_intc.c
@@ -XXX,XX +XXX,XX @@ static void omap_intc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = omap_inth_reset;
+    device_class_set_legacy_reset(dc, omap_inth_reset);
     device_class_set_props(dc, omap_intc_properties);
     /* Reason: pointer property "clk" */
     dc->user_creatable = false;
@@ -XXX,XX +XXX,XX @@ static void omap2_intc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = omap_inth_reset;
+    device_class_set_legacy_reset(dc, omap_inth_reset);
     device_class_set_props(dc, omap2_intc_properties);
     /* Reason: pointer property "iclk", "fclk" */
     dc->user_creatable = false;
diff --git a/hw/intc/openpic.c b/hw/intc/openpic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/openpic.c
+++ b/hw/intc/openpic.c
@@ -XXX,XX +XXX,XX @@ static void openpic_class_init(ObjectClass *oc, void *data)
 
     dc->realize = openpic_realize;
     device_class_set_props(dc, openpic_properties);
-    dc->reset = openpic_reset;
+    device_class_set_legacy_reset(dc, openpic_reset);
     dc->vmsd = &vmstate_openpic;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
diff --git a/hw/intc/openpic_kvm.c b/hw/intc/openpic_kvm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/openpic_kvm.c
+++ b/hw/intc/openpic_kvm.c
@@ -XXX,XX +XXX,XX @@ static void kvm_openpic_class_init(ObjectClass *oc, void *data)
 
     dc->realize = kvm_openpic_realize;
     device_class_set_props(dc, kvm_openpic_properties);
-    dc->reset = kvm_openpic_reset;
+    device_class_set_legacy_reset(dc, kvm_openpic_reset);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
diff --git a/hw/intc/pl190.c b/hw/intc/pl190.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/pl190.c
+++ b/hw/intc/pl190.c
@@ -XXX,XX +XXX,XX @@ static void pl190_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pl190_reset;
+    device_class_set_legacy_reset(dc, pl190_reset);
     dc->vmsd = &vmstate_pl190;
 }
 
diff --git a/hw/intc/ppc-uic.c b/hw/intc/ppc-uic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/ppc-uic.c
+++ b/hw/intc/ppc-uic.c
@@ -XXX,XX +XXX,XX @@ static void ppc_uic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = ppc_uic_reset;
+    device_class_set_legacy_reset(dc, ppc_uic_reset);
     dc->realize = ppc_uic_realize;
     dc->vmsd = &ppc_uic_vmstate;
     device_class_set_props(dc, ppc_uic_properties);
diff --git a/hw/intc/s390_flic.c b/hw/intc/s390_flic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/s390_flic.c
+++ b/hw/intc/s390_flic.c
@@ -XXX,XX +XXX,XX @@ static void qemu_s390_flic_class_init(ObjectClass *oc, void *data)
     S390FLICStateClass *fsc = S390_FLIC_COMMON_CLASS(oc);
 
     device_class_set_props(dc, qemu_s390_flic_properties);
-    dc->reset = qemu_s390_flic_reset;
+    device_class_set_legacy_reset(dc, qemu_s390_flic_reset);
     dc->vmsd = &qemu_s390_flic_vmstate;
     fsc->register_io_adapter = qemu_s390_register_io_adapter;
     fsc->io_adapter_map = qemu_s390_io_adapter_map;
diff --git a/hw/intc/s390_flic_kvm.c b/hw/intc/s390_flic_kvm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/s390_flic_kvm.c
+++ b/hw/intc/s390_flic_kvm.c
@@ -XXX,XX +XXX,XX @@ static void kvm_s390_flic_class_init(ObjectClass *oc, void *data)
     device_class_set_parent_realize(dc, kvm_s390_flic_realize,
                                     &kfsc->parent_realize);
     dc->vmsd = &kvm_s390_flic_vmstate;
-    dc->reset = kvm_s390_flic_reset;
+    device_class_set_legacy_reset(dc, kvm_s390_flic_reset);
     fsc->register_io_adapter = kvm_s390_register_io_adapter;
     fsc->io_adapter_map = kvm_s390_io_adapter_map;
     fsc->add_adapter_routes = kvm_s390_add_adapter_routes;
diff --git a/hw/intc/sifive_plic.c b/hw/intc/sifive_plic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/sifive_plic.c
+++ b/hw/intc/sifive_plic.c
@@ -XXX,XX +XXX,XX @@ static void sifive_plic_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = sifive_plic_reset;
+    device_class_set_legacy_reset(dc, sifive_plic_reset);
     device_class_set_props(dc, sifive_plic_properties);
     dc->realize = sifive_plic_realize;
     dc->vmsd = &vmstate_sifive_plic;
diff --git a/hw/intc/slavio_intctl.c b/hw/intc/slavio_intctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/slavio_intctl.c
+++ b/hw/intc/slavio_intctl.c
@@ -XXX,XX +XXX,XX @@ static void slavio_intctl_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     InterruptStatsProviderClass *ic = INTERRUPT_STATS_PROVIDER_CLASS(klass);
 
-    dc->reset = slavio_intctl_reset;
+    device_class_set_legacy_reset(dc, slavio_intctl_reset);
     dc->vmsd = &vmstate_intctl;
 #ifdef DEBUG_IRQ_COUNT
     ic->get_statistics = slavio_intctl_get_statistics;
diff --git a/hw/intc/xlnx-pmu-iomod-intc.c b/hw/intc/xlnx-pmu-iomod-intc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/xlnx-pmu-iomod-intc.c
+++ b/hw/intc/xlnx-pmu-iomod-intc.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_pmu_io_intc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xlnx_pmu_io_intc_reset;
+    device_class_set_legacy_reset(dc, xlnx_pmu_io_intc_reset);
     dc->realize = xlnx_pmu_io_intc_realize;
     dc->vmsd = &vmstate_xlnx_pmu_io_intc;
     device_class_set_props(dc, xlnx_pmu_io_intc_properties);
diff --git a/hw/intc/xlnx-zynqmp-ipi.c b/hw/intc/xlnx-zynqmp-ipi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/xlnx-zynqmp-ipi.c
+++ b/hw/intc/xlnx-zynqmp-ipi.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_ipi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xlnx_zynqmp_ipi_reset;
+    device_class_set_legacy_reset(dc, xlnx_zynqmp_ipi_reset);
     dc->realize = xlnx_zynqmp_ipi_realize;
     dc->vmsd = &vmstate_zynqmp_pmu_ipi;
 }
diff --git a/hw/isa/lpc_ich9.c b/hw/isa/lpc_ich9.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/isa/lpc_ich9.c
+++ b/hw/isa/lpc_ich9.c
@@ -XXX,XX +XXX,XX @@ static void ich9_lpc_class_init(ObjectClass *klass, void *data)
     AcpiDevAmlIfClass *amldevc = ACPI_DEV_AML_IF_CLASS(klass);
 
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
-    dc->reset = ich9_lpc_reset;
+    device_class_set_legacy_reset(dc, ich9_lpc_reset);
     k->realize = ich9_lpc_realize;
     dc->vmsd = &vmstate_ich9_lpc;
     device_class_set_props(dc, ich9_lpc_properties);
diff --git a/hw/isa/pc87312.c b/hw/isa/pc87312.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/isa/pc87312.c
+++ b/hw/isa/pc87312.c
@@ -XXX,XX +XXX,XX @@ static void pc87312_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass);
 
-    dc->reset = pc87312_reset;
+    device_class_set_legacy_reset(dc, pc87312_reset);
     dc->vmsd = &vmstate_pc87312;
     device_class_set_parent_realize(dc, pc87312_realize,
                                     &sc->parent_realize);
diff --git a/hw/isa/piix.c b/hw/isa/piix.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/isa/piix.c
+++ b/hw/isa/piix.c
@@ -XXX,XX +XXX,XX @@ static void pci_piix_class_init(ObjectClass *klass, void *data)
     AcpiDevAmlIfClass *adevc = ACPI_DEV_AML_IF_CLASS(klass);
 
     k->config_write = piix_write_config;
-    dc->reset       = piix_reset;
+    device_class_set_legacy_reset(dc, piix_reset);
     dc->desc        = "ISA bridge";
     dc->hotpluggable   = false;
     k->vendor_id    = PCI_VENDOR_ID_INTEL;
diff --git a/hw/isa/vt82c686.c b/hw/isa/vt82c686.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/isa/vt82c686.c
+++ b/hw/isa/vt82c686.c
@@ -XXX,XX +XXX,XX @@ static void via_pm_class_init(ObjectClass *klass, void *data)
     k->device_id = info->device_id;
     k->class_id = PCI_CLASS_BRIDGE_OTHER;
     k->revision = 0x40;
-    dc->reset = via_pm_reset;
+    device_class_set_legacy_reset(dc, via_pm_reset);
     /* Reason: part of VIA south bridge, does not exist stand alone */
     dc->user_creatable = false;
     dc->vmsd = &vmstate_acpi;
@@ -XXX,XX +XXX,XX @@ static void vt82c686b_superio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass);
 
-    dc->reset = vt82c686b_superio_reset;
+    device_class_set_legacy_reset(dc, vt82c686b_superio_reset);
     sc->serial.count = 2;
     sc->parallel.count = 1;
     sc->ide.count = 0; /* emulated by via-ide */
@@ -XXX,XX +XXX,XX @@ static void vt8231_superio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass);
 
-    dc->reset = vt8231_superio_reset;
+    device_class_set_legacy_reset(dc, vt8231_superio_reset);
     sc->serial.count = 1;
     sc->parallel.count = 1;
     sc->ide.count = 0; /* emulated by via-ide */
@@ -XXX,XX +XXX,XX @@ static void vt82c686b_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_VIA_82C686B_ISA;
     k->class_id = PCI_CLASS_BRIDGE_ISA;
     k->revision = 0x40;
-    dc->reset = vt82c686b_isa_reset;
+    device_class_set_legacy_reset(dc, vt82c686b_isa_reset);
     dc->desc = "ISA bridge";
     dc->vmsd = &vmstate_via;
     /* Reason: part of VIA VT82C686 southbridge, needs to be wired up */
@@ -XXX,XX +XXX,XX @@ static void vt8231_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_VIA_8231_ISA;
     k->class_id = PCI_CLASS_BRIDGE_ISA;
     k->revision = 0x10;
-    dc->reset = vt8231_isa_reset;
+    device_class_set_legacy_reset(dc, vt8231_isa_reset);
     dc->desc = "ISA bridge";
     dc->vmsd = &vmstate_via;
     /* Reason: part of VIA VT8231 southbridge, needs to be wired up */
diff --git a/hw/m68k/mcf5206.c b/hw/m68k/mcf5206.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/m68k/mcf5206.c
+++ b/hw/m68k/mcf5206.c
@@ -XXX,XX +XXX,XX @@ static void mcf5206_mbar_class_init(ObjectClass *oc, void *data)
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->desc = "MCF5206 system integration module";
     dc->realize = mcf5206_mbar_realize;
-    dc->reset = m5206_mbar_reset;
+    device_class_set_legacy_reset(dc, m5206_mbar_reset);
 }
 
 static const TypeInfo mcf5206_mbar_info = {
diff --git a/hw/m68k/mcf_intc.c b/hw/m68k/mcf_intc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/m68k/mcf_intc.c
+++ b/hw/m68k/mcf_intc.c
@@ -XXX,XX +XXX,XX @@ static void mcf_intc_class_init(ObjectClass *oc, void *data)
 
     device_class_set_props(dc, mcf_intc_properties);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
-    dc->reset = mcf_intc_reset;
+    device_class_set_legacy_reset(dc, mcf_intc_reset);
 }
 
 static const TypeInfo mcf_intc_gate_info = {
diff --git a/hw/m68k/next-cube.c b/hw/m68k/next-cube.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/m68k/next-cube.c
+++ b/hw/m68k/next-cube.c
@@ -XXX,XX +XXX,XX @@ static void next_pc_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "NeXT Peripheral Controller";
     dc->realize = next_pc_realize;
-    dc->reset = next_pc_reset;
+    device_class_set_legacy_reset(dc, next_pc_reset);
     device_class_set_props(dc, next_pc_properties);
     dc->vmsd = &next_pc_vmstate;
 }
diff --git a/hw/m68k/next-kbd.c b/hw/m68k/next-kbd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/m68k/next-kbd.c
+++ b/hw/m68k/next-kbd.c
@@ -XXX,XX +XXX,XX @@ static void nextkbd_class_init(ObjectClass *oc, void *data)
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
     dc->vmsd = &nextkbd_vmstate;
     dc->realize = nextkbd_realize;
-    dc->reset = nextkbd_reset;
+    device_class_set_legacy_reset(dc, nextkbd_reset);
 }
 
 static const TypeInfo nextkbd_info = {
diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/mem/cxl_type3.c
+++ b/hw/mem/cxl_type3.c
@@ -XXX,XX +XXX,XX @@ static void ct3_class_init(ObjectClass *oc, void *data)
 
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     dc->desc = "CXL Memory Device (Type 3)";
-    dc->reset = ct3d_reset;
+    device_class_set_legacy_reset(dc, ct3d_reset);
     device_class_set_props(dc, ct3_props);
 
     cvc->get_lsa_size = get_lsa_size;
diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/a9scu.c
+++ b/hw/misc/a9scu.c
@@ -XXX,XX +XXX,XX @@ static void a9_scu_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, a9_scu_properties);
     dc->vmsd = &vmstate_a9_scu;
-    dc->reset = a9_scu_reset;
+    device_class_set_legacy_reset(dc, a9_scu_reset);
     dc->realize = a9_scu_realize;
 }
 
diff --git a/hw/misc/allwinner-cpucfg.c b/hw/misc/allwinner-cpucfg.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-cpucfg.c
+++ b/hw/misc/allwinner-cpucfg.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_cpucfg_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_cpucfg_reset;
+    device_class_set_legacy_reset(dc, allwinner_cpucfg_reset);
     dc->vmsd = &allwinner_cpucfg_vmstate;
 }
 
diff --git a/hw/misc/allwinner-h3-ccu.c b/hw/misc/allwinner-h3-ccu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-h3-ccu.c
+++ b/hw/misc/allwinner-h3-ccu.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_h3_ccu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_h3_ccu_reset;
+    device_class_set_legacy_reset(dc, allwinner_h3_ccu_reset);
     dc->vmsd = &allwinner_h3_ccu_vmstate;
 }
 
diff --git a/hw/misc/allwinner-h3-dramc.c b/hw/misc/allwinner-h3-dramc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-h3-dramc.c
+++ b/hw/misc/allwinner-h3-dramc.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_h3_dramc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_h3_dramc_reset;
+    device_class_set_legacy_reset(dc, allwinner_h3_dramc_reset);
     dc->vmsd = &allwinner_h3_dramc_vmstate;
     dc->realize = allwinner_h3_dramc_realize;
     device_class_set_props(dc, allwinner_h3_dramc_properties);
diff --git a/hw/misc/allwinner-h3-sysctrl.c b/hw/misc/allwinner-h3-sysctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-h3-sysctrl.c
+++ b/hw/misc/allwinner-h3-sysctrl.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_h3_sysctrl_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_h3_sysctrl_reset;
+    device_class_set_legacy_reset(dc, allwinner_h3_sysctrl_reset);
     dc->vmsd = &allwinner_h3_sysctrl_vmstate;
 }
 
diff --git a/hw/misc/allwinner-r40-ccu.c b/hw/misc/allwinner-r40-ccu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-r40-ccu.c
+++ b/hw/misc/allwinner-r40-ccu.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_r40_ccu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_r40_ccu_reset;
+    device_class_set_legacy_reset(dc, allwinner_r40_ccu_reset);
     dc->vmsd = &allwinner_r40_ccu_vmstate;
 }
 
diff --git a/hw/misc/allwinner-r40-dramc.c b/hw/misc/allwinner-r40-dramc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-r40-dramc.c
+++ b/hw/misc/allwinner-r40-dramc.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_r40_dramc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_r40_dramc_reset;
+    device_class_set_legacy_reset(dc, allwinner_r40_dramc_reset);
     dc->vmsd = &allwinner_r40_dramc_vmstate;
     dc->realize = allwinner_r40_dramc_realize;
     device_class_set_props(dc, allwinner_r40_dramc_properties);
diff --git a/hw/misc/allwinner-sid.c b/hw/misc/allwinner-sid.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-sid.c
+++ b/hw/misc/allwinner-sid.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_sid_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_sid_reset;
+    device_class_set_legacy_reset(dc, allwinner_sid_reset);
     dc->vmsd = &allwinner_sid_vmstate;
     device_class_set_props(dc, allwinner_sid_properties);
 }
diff --git a/hw/misc/allwinner-sramc.c b/hw/misc/allwinner-sramc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/allwinner-sramc.c
+++ b/hw/misc/allwinner-sramc.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_sramc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_sramc_reset;
+    device_class_set_legacy_reset(dc, allwinner_sramc_reset);
     dc->vmsd = &allwinner_sramc_vmstate;
 }
 
diff --git a/hw/misc/applesmc.c b/hw/misc/applesmc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/applesmc.c
+++ b/hw/misc/applesmc.c
@@ -XXX,XX +XXX,XX @@ static void qdev_applesmc_class_init(ObjectClass *klass, void *data)
 
     dc->realize = applesmc_isa_realize;
     dc->unrealize = applesmc_unrealize;
-    dc->reset = qdev_applesmc_isa_reset;
+    device_class_set_legacy_reset(dc, qdev_applesmc_isa_reset);
     device_class_set_props(dc, applesmc_isa_properties);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     adevc->build_dev_aml = build_applesmc_aml;
diff --git a/hw/misc/arm_l2x0.c b/hw/misc/arm_l2x0.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/arm_l2x0.c
+++ b/hw/misc/arm_l2x0.c
@@ -XXX,XX +XXX,XX @@ static void l2x0_class_init(ObjectClass *klass, void *data)
 
     dc->vmsd = &vmstate_l2x0;
     device_class_set_props(dc, l2x0_properties);
-    dc->reset = l2x0_priv_reset;
+    device_class_set_legacy_reset(dc, l2x0_priv_reset);
 }
 
 static const TypeInfo l2x0_info = {
diff --git a/hw/misc/arm_sysctl.c b/hw/misc/arm_sysctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/arm_sysctl.c
+++ b/hw/misc/arm_sysctl.c
@@ -XXX,XX +XXX,XX @@ static void arm_sysctl_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = arm_sysctl_realize;
-    dc->reset = arm_sysctl_reset;
+    device_class_set_legacy_reset(dc, arm_sysctl_reset);
     dc->vmsd = &vmstate_arm_sysctl;
     device_class_set_props(dc, arm_sysctl_properties);
 }
diff --git a/hw/misc/armsse-cpu-pwrctrl.c b/hw/misc/armsse-cpu-pwrctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/armsse-cpu-pwrctrl.c
+++ b/hw/misc/armsse-cpu-pwrctrl.c
@@ -XXX,XX +XXX,XX @@ static void pwrctrl_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pwrctrl_reset;
+    device_class_set_legacy_reset(dc, pwrctrl_reset);
     dc->vmsd = &pwrctrl_vmstate;
 }
 
diff --git a/hw/misc/armsse-mhu.c b/hw/misc/armsse-mhu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/armsse-mhu.c
+++ b/hw/misc/armsse-mhu.c
@@ -XXX,XX +XXX,XX @@ static void armsse_mhu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = armsse_mhu_reset;
+    device_class_set_legacy_reset(dc, armsse_mhu_reset);
     dc->vmsd = &armsse_mhu_vmstate;
 }
 
diff --git a/hw/misc/aspeed_hace.c b/hw/misc/aspeed_hace.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_hace.c
+++ b/hw/misc/aspeed_hace.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_hace_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_hace_realize;
-    dc->reset = aspeed_hace_reset;
+    device_class_set_legacy_reset(dc, aspeed_hace_reset);
     device_class_set_props(dc, aspeed_hace_properties);
     dc->vmsd = &vmstate_aspeed_hace;
 }
diff --git a/hw/misc/aspeed_i3c.c b/hw/misc/aspeed_i3c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_i3c.c
+++ b/hw/misc/aspeed_i3c.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_i3c_device_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "Aspeed I3C Device";
     dc->realize = aspeed_i3c_device_realize;
-    dc->reset = aspeed_i3c_device_reset;
+    device_class_set_legacy_reset(dc, aspeed_i3c_device_reset);
     device_class_set_props(dc, aspeed_i3c_device_properties);
 }
 
@@ -XXX,XX +XXX,XX @@ static void aspeed_i3c_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_i3c_realize;
-    dc->reset = aspeed_i3c_reset;
+    device_class_set_legacy_reset(dc, aspeed_i3c_reset);
     dc->desc = "Aspeed I3C Controller";
     dc->vmsd = &vmstate_aspeed_i3c;
 }
diff --git a/hw/misc/aspeed_lpc.c b/hw/misc/aspeed_lpc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_lpc.c
+++ b/hw/misc/aspeed_lpc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_lpc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_lpc_realize;
-    dc->reset = aspeed_lpc_reset;
+    device_class_set_legacy_reset(dc, aspeed_lpc_reset);
     dc->desc = "Aspeed LPC Controller",
     dc->vmsd = &vmstate_aspeed_lpc;
     device_class_set_props(dc, aspeed_lpc_properties);
diff --git a/hw/misc/aspeed_peci.c b/hw/misc/aspeed_peci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_peci.c
+++ b/hw/misc/aspeed_peci.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_peci_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_peci_realize;
-    dc->reset = aspeed_peci_reset;
+    device_class_set_legacy_reset(dc, aspeed_peci_reset);
     dc->desc = "Aspeed PECI Controller";
 }
 
diff --git a/hw/misc/aspeed_sbc.c b/hw/misc/aspeed_sbc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_sbc.c
+++ b/hw/misc/aspeed_sbc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_sbc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_sbc_realize;
-    dc->reset = aspeed_sbc_reset;
+    device_class_set_legacy_reset(dc, aspeed_sbc_reset);
     dc->vmsd = &vmstate_aspeed_sbc;
     device_class_set_props(dc, aspeed_sbc_properties);
 }
diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_scu.c
+++ b/hw/misc/aspeed_scu.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_scu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->realize = aspeed_scu_realize;
-    dc->reset = aspeed_scu_reset;
+    device_class_set_legacy_reset(dc, aspeed_scu_reset);
     dc->desc = "ASPEED System Control Unit";
     dc->vmsd = &vmstate_aspeed_scu;
     device_class_set_props(dc, aspeed_scu_properties);
@@ -XXX,XX +XXX,XX @@ static void aspeed_2600_scu_class_init(ObjectClass *klass, void *data)
     AspeedSCUClass *asc = ASPEED_SCU_CLASS(klass);
 
     dc->desc = "ASPEED 2600 System Control Unit";
-    dc->reset = aspeed_ast2600_scu_reset;
+    device_class_set_legacy_reset(dc, aspeed_ast2600_scu_reset);
     asc->resets = ast2600_a3_resets;
     asc->calc_hpll = aspeed_2600_scu_calc_hpll;
     asc->get_apb = aspeed_2600_scu_get_apb_freq;
@@ -XXX,XX +XXX,XX @@ static void aspeed_2700_scu_class_init(ObjectClass *klass, void *data)
     AspeedSCUClass *asc = ASPEED_SCU_CLASS(klass);
 
     dc->desc = "ASPEED 2700 System Control Unit";
-    dc->reset = aspeed_ast2700_scu_reset;
+    device_class_set_legacy_reset(dc, aspeed_ast2700_scu_reset);
     asc->resets = ast2700_a0_resets;
     asc->calc_hpll = aspeed_2600_scu_calc_hpll;
     asc->get_apb = aspeed_2700_scu_get_apb_freq;
@@ -XXX,XX +XXX,XX @@ static void aspeed_2700_scuio_class_init(ObjectClass *klass, void *data)
     AspeedSCUClass *asc = ASPEED_SCU_CLASS(klass);
 
     dc->desc = "ASPEED 2700 System Control Unit I/O";
-    dc->reset = aspeed_ast2700_scu_reset;
+    device_class_set_legacy_reset(dc, aspeed_ast2700_scu_reset);
     asc->resets = ast2700_a0_resets_io;
     asc->calc_hpll = aspeed_2600_scu_calc_hpll;
     asc->get_apb = aspeed_2700_scuio_get_apb_freq;
@@ -XXX,XX +XXX,XX @@ static void aspeed_1030_scu_class_init(ObjectClass *klass, void *data)
     AspeedSCUClass *asc = ASPEED_SCU_CLASS(klass);
 
     dc->desc = "ASPEED 1030 System Control Unit";
-    dc->reset = aspeed_ast1030_scu_reset;
+    device_class_set_legacy_reset(dc, aspeed_ast1030_scu_reset);
     asc->resets = ast1030_a1_resets;
     asc->calc_hpll = aspeed_2600_scu_calc_hpll;
     asc->get_apb = aspeed_1030_scu_get_apb_freq;
diff --git a/hw/misc/aspeed_sdmc.c b/hw/misc/aspeed_sdmc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_sdmc.c
+++ b/hw/misc/aspeed_sdmc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_sdmc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->realize = aspeed_sdmc_realize;
-    dc->reset = aspeed_sdmc_reset;
+    device_class_set_legacy_reset(dc, aspeed_sdmc_reset);
     dc->desc = "ASPEED SDRAM Memory Controller";
     dc->vmsd = &vmstate_aspeed_sdmc;
     device_class_set_props(dc, aspeed_sdmc_properties);
@@ -XXX,XX +XXX,XX @@ static void aspeed_2700_sdmc_class_init(ObjectClass *klass, void *data)
     AspeedSDMCClass *asc = ASPEED_SDMC_CLASS(klass);
 
     dc->desc = "ASPEED 2700 SDRAM Memory Controller";
-    dc->reset = aspeed_2700_sdmc_reset;
+    device_class_set_legacy_reset(dc, aspeed_2700_sdmc_reset);
 
     asc->is_bus64bit = true;
     asc->max_ram_size = 8 * GiB;
diff --git a/hw/misc/aspeed_xdma.c b/hw/misc/aspeed_xdma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_xdma.c
+++ b/hw/misc/aspeed_xdma.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_xdma_class_init(ObjectClass *classp, void *data)
     DeviceClass *dc = DEVICE_CLASS(classp);
 
     dc->realize = aspeed_xdma_realize;
-    dc->reset = aspeed_xdma_reset;
+    device_class_set_legacy_reset(dc, aspeed_xdma_reset);
     dc->vmsd = &aspeed_xdma_vmstate;
 }
 
diff --git a/hw/misc/avr_power.c b/hw/misc/avr_power.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/avr_power.c
+++ b/hw/misc/avr_power.c
@@ -XXX,XX +XXX,XX @@ static void avr_mask_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = avr_mask_reset;
+    device_class_set_legacy_reset(dc, avr_mask_reset);
 }
 
 static const TypeInfo avr_mask_info = {
diff --git a/hw/misc/bcm2835_cprman.c b/hw/misc/bcm2835_cprman.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/bcm2835_cprman.c
+++ b/hw/misc/bcm2835_cprman.c
@@ -XXX,XX +XXX,XX @@ static void pll_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pll_reset;
+    device_class_set_legacy_reset(dc, pll_reset);
     dc->vmsd = &pll_vmstate;
 }
 
@@ -XXX,XX +XXX,XX @@ static void pll_channel_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pll_channel_reset;
+    device_class_set_legacy_reset(dc, pll_channel_reset);
     dc->vmsd = &pll_channel_vmstate;
 }
 
@@ -XXX,XX +XXX,XX @@ static void clock_mux_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = clock_mux_reset;
+    device_class_set_legacy_reset(dc, clock_mux_reset);
     dc->vmsd = &clock_mux_vmstate;
 }
 
@@ -XXX,XX +XXX,XX @@ static void cprman_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = cprman_realize;
-    dc->reset = cprman_reset;
+    device_class_set_legacy_reset(dc, cprman_reset);
     dc->vmsd = &cprman_vmstate;
     device_class_set_props(dc, cprman_properties);
 }
diff --git a/hw/misc/bcm2835_mbox.c b/hw/misc/bcm2835_mbox.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/bcm2835_mbox.c
+++ b/hw/misc/bcm2835_mbox.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_mbox_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = bcm2835_mbox_realize;
-    dc->reset = bcm2835_mbox_reset;
+    device_class_set_legacy_reset(dc, bcm2835_mbox_reset);
     dc->vmsd = &vmstate_bcm2835_mbox;
 }
 
diff --git a/hw/misc/bcm2835_mphi.c b/hw/misc/bcm2835_mphi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/bcm2835_mphi.c
+++ b/hw/misc/bcm2835_mphi.c
@@ -XXX,XX +XXX,XX @@ static void mphi_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = mphi_realize;
-    dc->reset = mphi_reset;
+    device_class_set_legacy_reset(dc, mphi_reset);
     dc->vmsd = &vmstate_mphi_state;
 }
 
diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/bcm2835_powermgt.c
+++ b/hw/misc/bcm2835_powermgt.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2835_powermgt_reset;
+    device_class_set_legacy_reset(dc, bcm2835_powermgt_reset);
     dc->vmsd = &vmstate_bcm2835_powermgt;
 }
 
diff --git a/hw/misc/bcm2835_rng.c b/hw/misc/bcm2835_rng.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/bcm2835_rng.c
+++ b/hw/misc/bcm2835_rng.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_rng_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2835_rng_reset;
+    device_class_set_legacy_reset(dc, bcm2835_rng_reset);
     dc->vmsd = &vmstate_bcm2835_rng;
 }
 
diff --git a/hw/misc/bcm2835_thermal.c b/hw/misc/bcm2835_thermal.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/bcm2835_thermal.c
+++ b/hw/misc/bcm2835_thermal.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_thermal_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = bcm2835_thermal_realize;
-    dc->reset = bcm2835_thermal_reset;
+    device_class_set_legacy_reset(dc, bcm2835_thermal_reset);
     dc->vmsd = &bcm2835_thermal_vmstate;
 }
 
diff --git a/hw/misc/eccmemctl.c b/hw/misc/eccmemctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/eccmemctl.c
+++ b/hw/misc/eccmemctl.c
@@ -XXX,XX +XXX,XX @@ static void ecc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = ecc_realize;
-    dc->reset = ecc_reset;
+    device_class_set_legacy_reset(dc, ecc_reset);
     dc->vmsd = &vmstate_ecc;
     device_class_set_props(dc, ecc_properties);
 }
diff --git a/hw/misc/exynos4210_clk.c b/hw/misc/exynos4210_clk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/exynos4210_clk.c
+++ b/hw/misc/exynos4210_clk.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_clk_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_clk_reset;
+    device_class_set_legacy_reset(dc, exynos4210_clk_reset);
     dc->vmsd = &exynos4210_clk_vmstate;
 }
 
diff --git a/hw/misc/exynos4210_pmu.c b/hw/misc/exynos4210_pmu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/exynos4210_pmu.c
+++ b/hw/misc/exynos4210_pmu.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_pmu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_pmu_reset;
+    device_class_set_legacy_reset(dc, exynos4210_pmu_reset);
     dc->vmsd = &exynos4210_pmu_vmstate;
 }
 
diff --git a/hw/misc/exynos4210_rng.c b/hw/misc/exynos4210_rng.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/exynos4210_rng.c
+++ b/hw/misc/exynos4210_rng.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_rng_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_rng_reset;
+    device_class_set_legacy_reset(dc, exynos4210_rng_reset);
     dc->vmsd = &exynos4210_rng_vmstate;
 }
 
diff --git a/hw/misc/imx25_ccm.c b/hw/misc/imx25_ccm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx25_ccm.c
+++ b/hw/misc/imx25_ccm.c
@@ -XXX,XX +XXX,XX @@ static void imx25_ccm_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
 
-    dc->reset = imx25_ccm_reset;
+    device_class_set_legacy_reset(dc, imx25_ccm_reset);
     dc->vmsd = &vmstate_imx25_ccm;
     dc->desc = "i.MX25 Clock Control Module";
 
diff --git a/hw/misc/imx31_ccm.c b/hw/misc/imx31_ccm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx31_ccm.c
+++ b/hw/misc/imx31_ccm.c
@@ -XXX,XX +XXX,XX @@ static void imx31_ccm_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc  = DEVICE_CLASS(klass);
     IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
 
-    dc->reset = imx31_ccm_reset;
+    device_class_set_legacy_reset(dc, imx31_ccm_reset);
     dc->vmsd  = &vmstate_imx31_ccm;
     dc->desc  = "i.MX31 Clock Control Module";
 
diff --git a/hw/misc/imx6_ccm.c b/hw/misc/imx6_ccm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx6_ccm.c
+++ b/hw/misc/imx6_ccm.c
@@ -XXX,XX +XXX,XX @@ static void imx6_ccm_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
 
-    dc->reset = imx6_ccm_reset;
+    device_class_set_legacy_reset(dc, imx6_ccm_reset);
     dc->vmsd = &vmstate_imx6_ccm;
     dc->desc = "i.MX6 Clock Control Module";
 
diff --git a/hw/misc/imx6_src.c b/hw/misc/imx6_src.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx6_src.c
+++ b/hw/misc/imx6_src.c
@@ -XXX,XX +XXX,XX @@ static void imx6_src_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = imx6_src_realize;
-    dc->reset = imx6_src_reset;
+    device_class_set_legacy_reset(dc, imx6_src_reset);
     dc->vmsd = &vmstate_imx6_src;
     dc->desc = "i.MX6 System Reset Controller";
 }
diff --git a/hw/misc/imx6ul_ccm.c b/hw/misc/imx6ul_ccm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx6ul_ccm.c
+++ b/hw/misc/imx6ul_ccm.c
@@ -XXX,XX +XXX,XX @@ static void imx6ul_ccm_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
 
-    dc->reset = imx6ul_ccm_reset;
+    device_class_set_legacy_reset(dc, imx6ul_ccm_reset);
     dc->vmsd = &vmstate_imx6ul_ccm;
     dc->desc = "i.MX6UL Clock Control Module";
 
diff --git a/hw/misc/imx7_ccm.c b/hw/misc/imx7_ccm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx7_ccm.c
+++ b/hw/misc/imx7_ccm.c
@@ -XXX,XX +XXX,XX @@ static void imx7_ccm_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     IMXCCMClass *ccm = IMX_CCM_CLASS(klass);
 
-    dc->reset = imx7_ccm_reset;
+    device_class_set_legacy_reset(dc, imx7_ccm_reset);
     dc->vmsd  = &vmstate_imx7_ccm;
     dc->desc  = "i.MX7 Clock Control Module";
 
@@ -XXX,XX +XXX,XX @@ static void imx7_analog_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = imx7_analog_reset;
+    device_class_set_legacy_reset(dc, imx7_analog_reset);
     dc->vmsd  = &vmstate_imx7_analog;
     dc->desc  = "i.MX7 Analog Module";
 }
diff --git a/hw/misc/imx7_snvs.c b/hw/misc/imx7_snvs.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx7_snvs.c
+++ b/hw/misc/imx7_snvs.c
@@ -XXX,XX +XXX,XX @@ static void imx7_snvs_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = imx7_snvs_reset;
+    device_class_set_legacy_reset(dc, imx7_snvs_reset);
     dc->vmsd = &vmstate_imx7_snvs;
     dc->desc  = "i.MX7 Secure Non-Volatile Storage Module";
 }
diff --git a/hw/misc/imx7_src.c b/hw/misc/imx7_src.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx7_src.c
+++ b/hw/misc/imx7_src.c
@@ -XXX,XX +XXX,XX @@ static void imx7_src_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = imx7_src_realize;
-    dc->reset = imx7_src_reset;
+    device_class_set_legacy_reset(dc, imx7_src_reset);
     dc->vmsd = &vmstate_imx7_src;
     dc->desc = "i.MX6 System Reset Controller";
 }
diff --git a/hw/misc/imx_rngc.c b/hw/misc/imx_rngc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx_rngc.c
+++ b/hw/misc/imx_rngc.c
@@ -XXX,XX +XXX,XX @@ static void imx_rngc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = imx_rngc_realize;
-    dc->reset = imx_rngc_reset;
+    device_class_set_legacy_reset(dc, imx_rngc_reset);
     dc->desc = RNGC_NAME,
     dc->vmsd = &vmstate_imx_rngc;
 }
diff --git a/hw/misc/iotkit-secctl.c b/hw/misc/iotkit-secctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/iotkit-secctl.c
+++ b/hw/misc/iotkit-secctl.c
@@ -XXX,XX +XXX,XX @@ static void iotkit_secctl_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &iotkit_secctl_vmstate;
-    dc->reset = iotkit_secctl_reset;
+    device_class_set_legacy_reset(dc, iotkit_secctl_reset);
     dc->realize = iotkit_secctl_realize;
     device_class_set_props(dc, iotkit_secctl_props);
 }
diff --git a/hw/misc/iotkit-sysctl.c b/hw/misc/iotkit-sysctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/iotkit-sysctl.c
+++ b/hw/misc/iotkit-sysctl.c
@@ -XXX,XX +XXX,XX @@ static void iotkit_sysctl_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &iotkit_sysctl_vmstate;
-    dc->reset = iotkit_sysctl_reset;
+    device_class_set_legacy_reset(dc, iotkit_sysctl_reset);
     device_class_set_props(dc, iotkit_sysctl_props);
     dc->realize = iotkit_sysctl_realize;
 }
diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/ivshmem.c
+++ b/hw/misc/ivshmem.c
@@ -XXX,XX +XXX,XX @@ static void ivshmem_common_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_IVSHMEM;
     k->class_id = PCI_CLASS_MEMORY_RAM;
     k->revision = 1;
-    dc->reset = ivshmem_reset;
+    device_class_set_legacy_reset(dc, ivshmem_reset);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->desc = "Inter-VM shared memory";
 }
diff --git a/hw/misc/lasi.c b/hw/misc/lasi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/lasi.c
+++ b/hw/misc/lasi.c
@@ -XXX,XX +XXX,XX @@ static void lasi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = lasi_reset;
+    device_class_set_legacy_reset(dc, lasi_reset);
     dc->vmsd = &vmstate_lasi;
 }
 
diff --git a/hw/misc/led.c b/hw/misc/led.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/led.c
+++ b/hw/misc/led.c
@@ -XXX,XX +XXX,XX @@ static void led_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "LED";
     dc->vmsd = &vmstate_led;
-    dc->reset = led_reset;
+    device_class_set_legacy_reset(dc, led_reset);
     dc->realize = led_realize;
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
     device_class_set_props(dc, led_properties);
diff --git a/hw/misc/macio/cuda.c b/hw/misc/macio/cuda.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/macio/cuda.c
+++ b/hw/misc/macio/cuda.c
@@ -XXX,XX +XXX,XX @@ static void cuda_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = cuda_realize;
-    dc->reset = cuda_reset;
+    device_class_set_legacy_reset(dc, cuda_reset);
     dc->vmsd = &vmstate_cuda;
     device_class_set_props(dc, cuda_properties);
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
diff --git a/hw/misc/macio/gpio.c b/hw/misc/macio/gpio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/macio/gpio.c
+++ b/hw/misc/macio/gpio.c
@@ -XXX,XX +XXX,XX @@ static void macio_gpio_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
     NMIClass *nc = NMI_CLASS(oc);
 
-    dc->reset = macio_gpio_reset;
+    device_class_set_legacy_reset(dc, macio_gpio_reset);
     dc->vmsd = &vmstate_macio_gpio;
     nc->nmi_monitor_handler = macio_gpio_nmi;
 }
diff --git a/hw/misc/macio/mac_dbdma.c b/hw/misc/macio/mac_dbdma.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/macio/mac_dbdma.c
+++ b/hw/misc/macio/mac_dbdma.c
@@ -XXX,XX +XXX,XX @@ static void mac_dbdma_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = mac_dbdma_realize;
-    dc->reset = mac_dbdma_reset;
+    device_class_set_legacy_reset(dc, mac_dbdma_reset);
     dc->vmsd = &vmstate_dbdma;
 }
 
diff --git a/hw/misc/macio/pmu.c b/hw/misc/macio/pmu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/macio/pmu.c
+++ b/hw/misc/macio/pmu.c
@@ -XXX,XX +XXX,XX @@ static void pmu_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = pmu_realize;
-    dc->reset = pmu_reset;
+    device_class_set_legacy_reset(dc, pmu_reset);
     dc->vmsd = &vmstate_pmu;
     device_class_set_props(dc, pmu_properties);
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
diff --git a/hw/misc/mips_cmgcr.c b/hw/misc/mips_cmgcr.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/mips_cmgcr.c
+++ b/hw/misc/mips_cmgcr.c
@@ -XXX,XX +XXX,XX @@ static void mips_gcr_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     device_class_set_props(dc, mips_gcr_properties);
     dc->vmsd = &vmstate_mips_gcr;
-    dc->reset = mips_gcr_reset;
+    device_class_set_legacy_reset(dc, mips_gcr_reset);
     dc->realize = mips_gcr_realize;
 }
 
diff --git a/hw/misc/mips_cpc.c b/hw/misc/mips_cpc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/mips_cpc.c
+++ b/hw/misc/mips_cpc.c
@@ -XXX,XX +XXX,XX @@ static void mips_cpc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = mips_cpc_realize;
-    dc->reset = mips_cpc_reset;
+    device_class_set_legacy_reset(dc, mips_cpc_reset);
     dc->vmsd = &vmstate_mips_cpc;
     device_class_set_props(dc, mips_cpc_properties);
 }
diff --git a/hw/misc/mips_itu.c b/hw/misc/mips_itu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/mips_itu.c
+++ b/hw/misc/mips_itu.c
@@ -XXX,XX +XXX,XX @@ static void mips_itu_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, mips_itu_properties);
     dc->realize = mips_itu_realize;
-    dc->reset = mips_itu_reset;
+    device_class_set_legacy_reset(dc, mips_itu_reset);
 }
 
 static const TypeInfo mips_itu_info = {
diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/mps2-fpgaio.c
+++ b/hw/misc/mps2-fpgaio.c
@@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_class_init(ObjectClass *klass, void *data)
 
     dc->vmsd = &mps2_fpgaio_vmstate;
     dc->realize = mps2_fpgaio_realize;
-    dc->reset = mps2_fpgaio_reset;
+    device_class_set_legacy_reset(dc, mps2_fpgaio_reset);
     device_class_set_props(dc, mps2_fpgaio_properties);
 }
 
diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/mps2-scc.c
+++ b/hw/misc/mps2-scc.c
@@ -XXX,XX +XXX,XX @@ static void mps2_scc_class_init(ObjectClass *klass, void *data)
 
     dc->realize = mps2_scc_realize;
     dc->vmsd = &mps2_scc_vmstate;
-    dc->reset = mps2_scc_reset;
+    device_class_set_legacy_reset(dc, mps2_scc_reset);
     device_class_set_props(dc, mps2_scc_properties);
 }
 
diff --git a/hw/misc/msf2-sysreg.c b/hw/misc/msf2-sysreg.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/msf2-sysreg.c
+++ b/hw/misc/msf2-sysreg.c
@@ -XXX,XX +XXX,XX @@ static void msf2_sysreg_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_msf2_sysreg;
-    dc->reset = msf2_sysreg_reset;
+    device_class_set_legacy_reset(dc, msf2_sysreg_reset);
     device_class_set_props(dc, msf2_sysreg_properties);
     dc->realize = msf2_sysreg_realize;
 }
diff --git a/hw/misc/nrf51_rng.c b/hw/misc/nrf51_rng.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/nrf51_rng.c
+++ b/hw/misc/nrf51_rng.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_rng_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, nrf51_rng_properties);
     dc->vmsd = &vmstate_rng;
-    dc->reset = nrf51_rng_reset;
+    device_class_set_legacy_reset(dc, nrf51_rng_reset);
 }
 
 static const TypeInfo nrf51_rng_info = {
diff --git a/hw/misc/pci-testdev.c b/hw/misc/pci-testdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/pci-testdev.c
+++ b/hw/misc/pci-testdev.c
@@ -XXX,XX +XXX,XX @@ static void pci_testdev_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_OTHERS;
     dc->desc = "PCI Test Device";
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
-    dc->reset = qdev_pci_testdev_reset;
+    device_class_set_legacy_reset(dc, qdev_pci_testdev_reset);
     device_class_set_props(dc, pci_testdev_properties);
 }
 
diff --git a/hw/misc/sifive_e_aon.c b/hw/misc/sifive_e_aon.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/sifive_e_aon.c
+++ b/hw/misc/sifive_e_aon.c
@@ -XXX,XX +XXX,XX @@ static void sifive_e_aon_class_init(ObjectClass *oc, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
 
-    dc->reset = sifive_e_aon_reset;
+    device_class_set_legacy_reset(dc, sifive_e_aon_reset);
     device_class_set_props(dc, sifive_e_aon_properties);
 }
 
diff --git a/hw/misc/sifive_u_prci.c b/hw/misc/sifive_u_prci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/sifive_u_prci.c
+++ b/hw/misc/sifive_u_prci.c
@@ -XXX,XX +XXX,XX @@ static void sifive_u_prci_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = sifive_u_prci_realize;
-    dc->reset = sifive_u_prci_reset;
+    device_class_set_legacy_reset(dc, sifive_u_prci_reset);
 }
 
 static const TypeInfo sifive_u_prci_info = {
diff --git a/hw/misc/slavio_misc.c b/hw/misc/slavio_misc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/slavio_misc.c
+++ b/hw/misc/slavio_misc.c
@@ -XXX,XX +XXX,XX @@ static void slavio_misc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = slavio_misc_reset;
+    device_class_set_legacy_reset(dc, slavio_misc_reset);
     dc->vmsd = &vmstate_misc;
 }
 
diff --git a/hw/misc/stm32f2xx_syscfg.c b/hw/misc/stm32f2xx_syscfg.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/stm32f2xx_syscfg.c
+++ b/hw/misc/stm32f2xx_syscfg.c
@@ -XXX,XX +XXX,XX @@ static void stm32f2xx_syscfg_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f2xx_syscfg_reset;
+    device_class_set_legacy_reset(dc, stm32f2xx_syscfg_reset);
 }
 
 static const TypeInfo stm32f2xx_syscfg_info = {
diff --git a/hw/misc/stm32f4xx_exti.c b/hw/misc/stm32f4xx_exti.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/stm32f4xx_exti.c
+++ b/hw/misc/stm32f4xx_exti.c
@@ -XXX,XX +XXX,XX @@ static void stm32f4xx_exti_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f4xx_exti_reset;
+    device_class_set_legacy_reset(dc, stm32f4xx_exti_reset);
     dc->vmsd = &vmstate_stm32f4xx_exti;
 }
 
diff --git a/hw/misc/stm32f4xx_syscfg.c b/hw/misc/stm32f4xx_syscfg.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/stm32f4xx_syscfg.c
+++ b/hw/misc/stm32f4xx_syscfg.c
@@ -XXX,XX +XXX,XX @@ static void stm32f4xx_syscfg_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f4xx_syscfg_reset;
+    device_class_set_legacy_reset(dc, stm32f4xx_syscfg_reset);
     dc->vmsd = &vmstate_stm32f4xx_syscfg;
 }
 
diff --git a/hw/misc/tz-mpc.c b/hw/misc/tz-mpc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/tz-mpc.c
+++ b/hw/misc/tz-mpc.c
@@ -XXX,XX +XXX,XX @@ static void tz_mpc_class_init(ObjectClass *klass, void *data)
 
     dc->realize = tz_mpc_realize;
     dc->vmsd = &tz_mpc_vmstate;
-    dc->reset = tz_mpc_reset;
+    device_class_set_legacy_reset(dc, tz_mpc_reset);
     device_class_set_props(dc, tz_mpc_properties);
 }
 
diff --git a/hw/misc/tz-msc.c b/hw/misc/tz-msc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/tz-msc.c
+++ b/hw/misc/tz-msc.c
@@ -XXX,XX +XXX,XX @@ static void tz_msc_class_init(ObjectClass *klass, void *data)
 
     dc->realize = tz_msc_realize;
     dc->vmsd = &tz_msc_vmstate;
-    dc->reset = tz_msc_reset;
+    device_class_set_legacy_reset(dc, tz_msc_reset);
     device_class_set_props(dc, tz_msc_properties);
 }
 
diff --git a/hw/misc/tz-ppc.c b/hw/misc/tz-ppc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/tz-ppc.c
+++ b/hw/misc/tz-ppc.c
@@ -XXX,XX +XXX,XX @@ static void tz_ppc_class_init(ObjectClass *klass, void *data)
 
     dc->realize = tz_ppc_realize;
     dc->vmsd = &tz_ppc_vmstate;
-    dc->reset = tz_ppc_reset;
+    device_class_set_legacy_reset(dc, tz_ppc_reset);
     device_class_set_props(dc, tz_ppc_properties);
 }
 
diff --git a/hw/misc/virt_ctrl.c b/hw/misc/virt_ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/virt_ctrl.c
+++ b/hw/misc/virt_ctrl.c
@@ -XXX,XX +XXX,XX @@ static void virt_ctrl_class_init(ObjectClass *oc, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
 
-    dc->reset = virt_ctrl_reset;
+    device_class_set_legacy_reset(dc, virt_ctrl_reset);
     dc->realize = virt_ctrl_realize;
     dc->vmsd = &vmstate_virt_ctrl;
 }
diff --git a/hw/misc/xlnx-versal-cfu.c b/hw/misc/xlnx-versal-cfu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/xlnx-versal-cfu.c
+++ b/hw/misc/xlnx-versal-cfu.c
@@ -XXX,XX +XXX,XX @@ static void cfu_apb_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = cfu_apb_reset;
+    device_class_set_legacy_reset(dc, cfu_apb_reset);
     dc->vmsd = &vmstate_cfu_apb;
     device_class_set_props(dc, cfu_props);
 }
diff --git a/hw/net/allwinner-sun8i-emac.c b/hw/net/allwinner-sun8i-emac.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/allwinner-sun8i-emac.c
+++ b/hw/net/allwinner-sun8i-emac.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_sun8i_emac_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = allwinner_sun8i_emac_realize;
-    dc->reset = allwinner_sun8i_emac_reset;
+    device_class_set_legacy_reset(dc, allwinner_sun8i_emac_reset);
     dc->vmsd = &vmstate_aw_emac;
     device_class_set_props(dc, allwinner_sun8i_emac_properties);
 }
diff --git a/hw/net/allwinner_emac.c b/hw/net/allwinner_emac.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/allwinner_emac.c
+++ b/hw/net/allwinner_emac.c
@@ -XXX,XX +XXX,XX @@ static void aw_emac_class_init(ObjectClass *klass, void *data)
 
     dc->realize = aw_emac_realize;
     device_class_set_props(dc, aw_emac_properties);
-    dc->reset = aw_emac_reset;
+    device_class_set_legacy_reset(dc, aw_emac_reset);
     dc->vmsd = &vmstate_aw_emac;
 }
 
diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/cadence_gem.c
+++ b/hw/net/cadence_gem.c
@@ -XXX,XX +XXX,XX @@ static void gem_class_init(ObjectClass *klass, void *data)
     dc->realize = gem_realize;
     device_class_set_props(dc, gem_properties);
     dc->vmsd = &vmstate_cadence_gem;
-    dc->reset = gem_reset;
+    device_class_set_legacy_reset(dc, gem_reset);
 }
 
 static const TypeInfo gem_info = {
diff --git a/hw/net/can/can_kvaser_pci.c b/hw/net/can/can_kvaser_pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/can_kvaser_pci.c
+++ b/hw/net/can/can_kvaser_pci.c
@@ -XXX,XX +XXX,XX @@ static void kvaser_pci_class_init(ObjectClass *klass, void *data)
     k->class_id = 0x00ff00;
     dc->desc = "Kvaser PCICANx";
     dc->vmsd = &vmstate_kvaser_pci;
-    dc->reset = kvaser_pci_reset;
+    device_class_set_legacy_reset(dc, kvaser_pci_reset);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
diff --git a/hw/net/can/can_mioe3680_pci.c b/hw/net/can/can_mioe3680_pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/can_mioe3680_pci.c
+++ b/hw/net/can/can_mioe3680_pci.c
@@ -XXX,XX +XXX,XX @@ static void mioe3680_pci_class_init(ObjectClass *klass, void *data)
     dc->desc = "Mioe3680 PCICANx";
     dc->vmsd = &vmstate_mioe3680_pci;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
-    dc->reset = mioe3680_pci_reset;
+    device_class_set_legacy_reset(dc, mioe3680_pci_reset);
 }
 
 static const TypeInfo mioe3680_pci_info = {
diff --git a/hw/net/can/can_pcm3680_pci.c b/hw/net/can/can_pcm3680_pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/can_pcm3680_pci.c
+++ b/hw/net/can/can_pcm3680_pci.c
@@ -XXX,XX +XXX,XX @@ static void pcm3680i_pci_class_init(ObjectClass *klass, void *data)
     dc->desc = "Pcm3680i PCICANx";
     dc->vmsd = &vmstate_pcm3680i_pci;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
-    dc->reset = pcm3680i_pci_reset;
+    device_class_set_legacy_reset(dc, pcm3680i_pci_reset);
 }
 
 static const TypeInfo pcm3680i_pci_info = {
diff --git a/hw/net/can/ctucan_pci.c b/hw/net/can/ctucan_pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/ctucan_pci.c
+++ b/hw/net/can/ctucan_pci.c
@@ -XXX,XX +XXX,XX @@ static void ctucan_pci_class_init(ObjectClass *klass, void *data)
     dc->desc = "CTU CAN PCI";
     dc->vmsd = &vmstate_ctucan_pci;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
-    dc->reset = ctucan_pci_reset;
+    device_class_set_legacy_reset(dc, ctucan_pci_reset);
 }
 
 static const TypeInfo ctucan_pci_info = {
diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static void canfd_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = canfd_reset;
+    device_class_set_legacy_reset(dc, canfd_reset);
     dc->realize = canfd_realize;
     device_class_set_props(dc, canfd_core_properties);
     dc->vmsd = &vmstate_canfd;
diff --git a/hw/net/dp8393x.c b/hw/net/dp8393x.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/dp8393x.c
+++ b/hw/net/dp8393x.c
@@ -XXX,XX +XXX,XX @@ static void dp8393x_class_init(ObjectClass *klass, void *data)
 
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->realize = dp8393x_realize;
-    dc->reset = dp8393x_reset;
+    device_class_set_legacy_reset(dc, dp8393x_reset);
     dc->vmsd = &vmstate_dp8393x;
     device_class_set_props(dc, dp8393x_properties);
 }
diff --git a/hw/net/etraxfs_eth.c b/hw/net/etraxfs_eth.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/etraxfs_eth.c
+++ b/hw/net/etraxfs_eth.c
@@ -XXX,XX +XXX,XX @@ static void etraxfs_eth_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = etraxfs_eth_realize;
-    dc->reset = etraxfs_eth_reset;
+    device_class_set_legacy_reset(dc, etraxfs_eth_reset);
     device_class_set_props(dc, etraxfs_eth_properties);
     /* Reason: dma_out, dma_in are not user settable */
     dc->user_creatable = false;
diff --git a/hw/net/fsl_etsec/etsec.c b/hw/net/fsl_etsec/etsec.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/fsl_etsec/etsec.c
+++ b/hw/net/fsl_etsec/etsec.c
@@ -XXX,XX +XXX,XX @@ static void etsec_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = etsec_realize;
-    dc->reset = etsec_reset;
+    device_class_set_legacy_reset(dc, etsec_reset);
     device_class_set_props(dc, etsec_properties);
     /* Supported by ppce500 machine */
     dc->user_creatable = true;
diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/ftgmac100.c
+++ b/hw/net/ftgmac100.c
@@ -XXX,XX +XXX,XX @@ static void ftgmac100_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_ftgmac100;
-    dc->reset = ftgmac100_reset;
+    device_class_set_legacy_reset(dc, ftgmac100_reset);
     device_class_set_props(dc, ftgmac100_properties);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->realize = ftgmac100_realize;
@@ -XXX,XX +XXX,XX @@ static void aspeed_mii_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_aspeed_mii;
-    dc->reset = aspeed_mii_reset;
+    device_class_set_legacy_reset(dc, aspeed_mii_reset);
     dc->realize = aspeed_mii_realize;
     dc->desc = "Aspeed MII controller";
     device_class_set_props(dc, aspeed_mii_properties);
diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/imx_fec.c
+++ b/hw/net/imx_fec.c
@@ -XXX,XX +XXX,XX @@ static void imx_eth_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd    = &vmstate_imx_eth;
-    dc->reset   = imx_eth_reset;
+    device_class_set_legacy_reset(dc, imx_eth_reset);
     device_class_set_props(dc, imx_eth_properties);
     dc->realize = imx_eth_realize;
     dc->desc    = "i.MX FEC/ENET Ethernet Controller";
diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/lan9118.c
+++ b/hw/net/lan9118.c
@@ -XXX,XX +XXX,XX @@ static void lan9118_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = lan9118_reset;
+    device_class_set_legacy_reset(dc, lan9118_reset);
     device_class_set_props(dc, lan9118_properties);
     dc->vmsd = &vmstate_lan9118;
     dc->realize = lan9118_realize;
diff --git a/hw/net/lance.c b/hw/net/lance.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/lance.c
+++ b/hw/net/lance.c
@@ -XXX,XX +XXX,XX @@ static void lance_class_init(ObjectClass *klass, void *data)
     dc->realize = lance_realize;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->fw_name = "ethernet";
-    dc->reset = lance_reset;
+    device_class_set_legacy_reset(dc, lance_reset);
     dc->vmsd = &vmstate_lance;
     device_class_set_props(dc, lance_properties);
 }
diff --git a/hw/net/lasi_i82596.c b/hw/net/lasi_i82596.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/lasi_i82596.c
+++ b/hw/net/lasi_i82596.c
@@ -XXX,XX +XXX,XX @@ static void lasi_82596_class_init(ObjectClass *klass, void *data)
     dc->realize = lasi_82596_realize;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->fw_name = "ethernet";
-    dc->reset = lasi_82596_reset;
+    device_class_set_legacy_reset(dc, lasi_82596_reset);
     dc->vmsd = &vmstate_lasi_82596;
     dc->user_creatable = false;
     device_class_set_props(dc, lasi_82596_properties);
diff --git a/hw/net/mcf_fec.c b/hw/net/mcf_fec.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/mcf_fec.c
+++ b/hw/net/mcf_fec.c
@@ -XXX,XX +XXX,XX @@ static void mcf_fec_class_init(ObjectClass *oc, void *data)
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->realize = mcf_fec_realize;
     dc->desc = "MCF Fast Ethernet Controller network device";
-    dc->reset = mcf_fec_reset;
+    device_class_set_legacy_reset(dc, mcf_fec_reset);
     device_class_set_props(dc, mcf_fec_properties);
 }
 
diff --git a/hw/net/mipsnet.c b/hw/net/mipsnet.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/mipsnet.c
+++ b/hw/net/mipsnet.c
@@ -XXX,XX +XXX,XX @@ static void mipsnet_class_init(ObjectClass *klass, void *data)
     dc->realize = mipsnet_realize;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->desc = "MIPS Simulator network device";
-    dc->reset = mipsnet_sysbus_reset;
+    device_class_set_legacy_reset(dc, mipsnet_sysbus_reset);
     dc->vmsd = &vmstate_mipsnet;
     device_class_set_props(dc, mipsnet_properties);
 }
diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/msf2-emac.c
+++ b/hw/net/msf2-emac.c
@@ -XXX,XX +XXX,XX @@ static void msf2_emac_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = msf2_emac_realize;
-    dc->reset = msf2_emac_reset;
+    device_class_set_legacy_reset(dc, msf2_emac_reset);
     dc->vmsd = &vmstate_msf2_emac;
     device_class_set_props(dc, msf2_emac_properties);
 }
diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/npcm7xx_emc.c
+++ b/hw/net/npcm7xx_emc.c
@@ -XXX,XX +XXX,XX @@ static void npcm7xx_emc_class_init(ObjectClass *klass, void *data)
     dc->desc = "NPCM7xx EMC Controller";
     dc->realize = npcm7xx_emc_realize;
     dc->unrealize = npcm7xx_emc_unrealize;
-    dc->reset = npcm7xx_emc_reset;
+    device_class_set_legacy_reset(dc, npcm7xx_emc_reset);
     dc->vmsd = &vmstate_npcm7xx_emc;
     device_class_set_props(dc, npcm7xx_emc_properties);
 }
diff --git a/hw/net/npcm_gmac.c b/hw/net/npcm_gmac.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/npcm_gmac.c
+++ b/hw/net/npcm_gmac.c
@@ -XXX,XX +XXX,XX @@ static void npcm_gmac_class_init(ObjectClass *klass, void *data)
     dc->desc = "NPCM GMAC Controller";
     dc->realize = npcm_gmac_realize;
     dc->unrealize = npcm_gmac_unrealize;
-    dc->reset = npcm_gmac_reset;
+    device_class_set_legacy_reset(dc, npcm_gmac_reset);
     dc->vmsd = &vmstate_npcm_gmac;
     device_class_set_props(dc, npcm_gmac_properties);
 }
diff --git a/hw/net/opencores_eth.c b/hw/net/opencores_eth.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/opencores_eth.c
+++ b/hw/net/opencores_eth.c
@@ -XXX,XX +XXX,XX @@ static void open_eth_class_init(ObjectClass *klass, void *data)
     dc->realize = sysbus_open_eth_realize;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->desc = "Opencores 10/100 Mbit Ethernet";
-    dc->reset = qdev_open_eth_reset;
+    device_class_set_legacy_reset(dc, qdev_open_eth_reset);
     device_class_set_props(dc, open_eth_properties);
 }
 
diff --git a/hw/net/pcnet-pci.c b/hw/net/pcnet-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/pcnet-pci.c
+++ b/hw/net/pcnet-pci.c
@@ -XXX,XX +XXX,XX @@ static void pcnet_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_AMD_LANCE;
     k->revision = 0x10;
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
-    dc->reset = pci_reset;
+    device_class_set_legacy_reset(dc, pci_reset);
     dc->vmsd = &vmstate_pci_pcnet;
     device_class_set_props(dc, pcnet_properties);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
diff --git a/hw/net/rocker/rocker.c b/hw/net/rocker/rocker.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/rocker/rocker.c
+++ b/hw/net/rocker/rocker.c
@@ -XXX,XX +XXX,XX @@ static void rocker_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_NETWORK_OTHER;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     dc->desc = "Rocker Switch";
-    dc->reset = rocker_reset;
+    device_class_set_legacy_reset(dc, rocker_reset);
     device_class_set_props(dc, rocker_properties);
     dc->vmsd = &rocker_vmsd;
 }
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -XXX,XX +XXX,XX @@ static void rtl8139_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_REALTEK_8139;
     k->revision = RTL8139_PCI_REVID; /* >=0x20 is for 8139C+ */
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
-    dc->reset = rtl8139_reset;
+    device_class_set_legacy_reset(dc, rtl8139_reset);
     dc->vmsd = &vmstate_rtl8139;
     device_class_set_props(dc, rtl8139_properties);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
diff --git a/hw/net/smc91c111.c b/hw/net/smc91c111.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/smc91c111.c
+++ b/hw/net/smc91c111.c
@@ -XXX,XX +XXX,XX @@ static void smc91c111_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = smc91c111_realize;
-    dc->reset = smc91c111_reset;
+    device_class_set_legacy_reset(dc, smc91c111_reset);
     dc->vmsd = &vmstate_smc91c111;
     device_class_set_props(dc, smc91c111_properties);
 }
diff --git a/hw/net/stellaris_enet.c b/hw/net/stellaris_enet.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/stellaris_enet.c
+++ b/hw/net/stellaris_enet.c
@@ -XXX,XX +XXX,XX @@ static void stellaris_enet_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = stellaris_enet_realize;
-    dc->reset = stellaris_enet_reset;
+    device_class_set_legacy_reset(dc, stellaris_enet_reset);
     device_class_set_props(dc, stellaris_enet_properties);
     dc->vmsd = &vmstate_stellaris_enet;
 }
diff --git a/hw/net/sungem.c b/hw/net/sungem.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/sungem.c
+++ b/hw/net/sungem.c
@@ -XXX,XX +XXX,XX @@ static void sungem_class_init(ObjectClass *klass, void *data)
     k->revision = 0x01;
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
     dc->vmsd = &vmstate_sungem;
-    dc->reset = sungem_reset;
+    device_class_set_legacy_reset(dc, sungem_reset);
     device_class_set_props(dc, sungem_properties);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
 }
diff --git a/hw/net/sunhme.c b/hw/net/sunhme.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/sunhme.c
+++ b/hw/net/sunhme.c
@@ -XXX,XX +XXX,XX @@ static void sunhme_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_SUN_HME;
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
     dc->vmsd = &vmstate_hme;
-    dc->reset = sunhme_reset;
+    device_class_set_legacy_reset(dc, sunhme_reset);
     device_class_set_props(dc, sunhme_properties);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
 }
diff --git a/hw/net/tulip.c b/hw/net/tulip.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/tulip.c
+++ b/hw/net/tulip.c
@@ -XXX,XX +XXX,XX @@ static void tulip_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
     dc->vmsd = &vmstate_pci_tulip;
     device_class_set_props(dc, tulip_properties);
-    dc->reset = tulip_qdev_reset;
+    device_class_set_legacy_reset(dc, tulip_qdev_reset);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
 }
 
diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/vmxnet3.c
+++ b/hw/net/vmxnet3.c
@@ -XXX,XX +XXX,XX @@ static void vmxnet3_class_init(ObjectClass *class, void *data)
     device_class_set_parent_realize(dc, vmxnet3_realize,
                                     &vc->parent_dc_realize);
     dc->desc = "VMWare Paravirtualized Ethernet v3";
-    dc->reset = vmxnet3_qdev_reset;
+    device_class_set_legacy_reset(dc, vmxnet3_qdev_reset);
     dc->vmsd = &vmstate_vmxnet3;
     device_class_set_props(dc, vmxnet3_properties);
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
diff --git a/hw/net/xilinx_axienet.c b/hw/net/xilinx_axienet.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/xilinx_axienet.c
+++ b/hw/net/xilinx_axienet.c
@@ -XXX,XX +XXX,XX @@ static void xilinx_enet_class_init(ObjectClass *klass, void *data)
 
     dc->realize = xilinx_enet_realize;
     device_class_set_props(dc, xilinx_enet_properties);
-    dc->reset = xilinx_axienet_reset;
+    device_class_set_legacy_reset(dc, xilinx_axienet_reset);
 }
 
 static void xilinx_enet_control_stream_class_init(ObjectClass *klass,
diff --git a/hw/net/xilinx_ethlite.c b/hw/net/xilinx_ethlite.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/xilinx_ethlite.c
+++ b/hw/net/xilinx_ethlite.c
@@ -XXX,XX +XXX,XX @@ static void xilinx_ethlite_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = xilinx_ethlite_realize;
-    dc->reset = xilinx_ethlite_reset;
+    device_class_set_legacy_reset(dc, xilinx_ethlite_reset);
     device_class_set_props(dc, xilinx_ethlite_properties);
 }
 
diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -XXX,XX +XXX,XX @@ static void nvme_class_init(ObjectClass *oc, void *data)
     dc->desc = "Non-Volatile Memory Express";
     device_class_set_props(dc, nvme_props);
     dc->vmsd = &nvme_vmstate;
-    dc->reset = nvme_pci_reset;
+    device_class_set_legacy_reset(dc, nvme_pci_reset);
 }
 
 static void nvme_instance_init(Object *obj)
diff --git a/hw/nvram/eeprom_at24c.c b/hw/nvram/eeprom_at24c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/nvram/eeprom_at24c.c
+++ b/hw/nvram/eeprom_at24c.c
@@ -XXX,XX +XXX,XX @@ void at24c_eeprom_class_init(ObjectClass *klass, void *data)
     k->send = &at24c_eeprom_send;
 
     device_class_set_props(dc, at24c_eeprom_props);
-    dc->reset = at24c_eeprom_reset;
+    device_class_set_legacy_reset(dc, at24c_eeprom_reset);
 }
 
 static
diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/nvram/fw_cfg.c
+++ b/hw/nvram/fw_cfg.c
@@ -XXX,XX +XXX,XX @@ static void fw_cfg_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = fw_cfg_reset;
+    device_class_set_legacy_reset(dc, fw_cfg_reset);
     dc->vmsd = &vmstate_fw_cfg;
 
     device_class_set_props(dc, fw_cfg_properties);
diff --git a/hw/nvram/mac_nvram.c b/hw/nvram/mac_nvram.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/nvram/mac_nvram.c
+++ b/hw/nvram/mac_nvram.c
@@ -XXX,XX +XXX,XX @@ static void macio_nvram_class_init(ObjectClass *oc, void *data)
 
     dc->realize = macio_nvram_realizefn;
     dc->unrealize = macio_nvram_unrealizefn;
-    dc->reset = macio_nvram_reset;
+    device_class_set_legacy_reset(dc, macio_nvram_reset);
     dc->vmsd = &vmstate_macio_nvram;
     device_class_set_props(dc, macio_nvram_properties);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
diff --git a/hw/nvram/nrf51_nvm.c b/hw/nvram/nrf51_nvm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/nvram/nrf51_nvm.c
+++ b/hw/nvram/nrf51_nvm.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_nvm_class_init(ObjectClass *klass, void *data)
     device_class_set_props(dc, nrf51_nvm_properties);
     dc->vmsd = &vmstate_nvm;
     dc->realize = nrf51_nvm_realize;
-    dc->reset = nrf51_nvm_reset;
+    device_class_set_legacy_reset(dc, nrf51_nvm_reset);
 }
 
 static const TypeInfo nrf51_nvm_info = {
diff --git a/hw/pci-bridge/cxl_downstream.c b/hw/pci-bridge/cxl_downstream.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/cxl_downstream.c
+++ b/hw/pci-bridge/cxl_downstream.c
@@ -XXX,XX +XXX,XX @@ static void cxl_dsp_class_init(ObjectClass *oc, void *data)
     k->revision = 0;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->desc = "CXL Switch Downstream Port";
-    dc->reset = cxl_dsp_reset;
+    device_class_set_legacy_reset(dc, cxl_dsp_reset);
 }
 
 static const TypeInfo cxl_dsp_info = {
diff --git a/hw/pci-bridge/cxl_upstream.c b/hw/pci-bridge/cxl_upstream.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/cxl_upstream.c
+++ b/hw/pci-bridge/cxl_upstream.c
@@ -XXX,XX +XXX,XX @@ static void cxl_upstream_class_init(ObjectClass *oc, void *data)
     k->revision = 0;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->desc = "CXL Switch Upstream Port";
-    dc->reset = cxl_usp_reset;
+    device_class_set_legacy_reset(dc, cxl_usp_reset);
     device_class_set_props(dc, cxl_upstream_props);
 }
 
diff --git a/hw/pci-bridge/i82801b11.c b/hw/pci-bridge/i82801b11.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/i82801b11.c
+++ b/hw/pci-bridge/i82801b11.c
@@ -XXX,XX +XXX,XX @@ static void i82801b11_bridge_class_init(ObjectClass *klass, void *data)
     k->realize = i82801b11_bridge_realize;
     k->config_write = pci_bridge_write_config;
     dc->vmsd = &i82801b11_bridge_dev_vmstate;
-    dc->reset = pci_bridge_reset;
+    device_class_set_legacy_reset(dc, pci_bridge_reset);
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
 }
 
diff --git a/hw/pci-bridge/pci_bridge_dev.c b/hw/pci-bridge/pci_bridge_dev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/pci_bridge_dev.c
+++ b/hw/pci-bridge/pci_bridge_dev.c
@@ -XXX,XX +XXX,XX @@ static void pci_bridge_dev_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_REDHAT_BRIDGE;
     k->class_id = PCI_CLASS_BRIDGE_PCI;
     dc->desc = "Standard PCI Bridge";
-    dc->reset = qdev_pci_bridge_dev_reset;
+    device_class_set_legacy_reset(dc, qdev_pci_bridge_dev_reset);
     device_class_set_props(dc, pci_bridge_dev_properties);
     dc->vmsd = &pci_bridge_dev_vmstate;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/pci_expander_bridge.c
+++ b/hw/pci-bridge/pci_expander_bridge.c
@@ -XXX,XX +XXX,XX @@ static void pxb_cxl_dev_class_init(ObjectClass *klass, void *data)
 
     /* Host bridges aren't hotpluggable. FIXME: spec reference */
     dc->hotpluggable = false;
-    dc->reset = pxb_cxl_dev_reset;
+    device_class_set_legacy_reset(dc, pxb_cxl_dev_reset);
 }
 
 static const TypeInfo pxb_cxl_dev_info = {
diff --git a/hw/pci-bridge/pcie_pci_bridge.c b/hw/pci-bridge/pcie_pci_bridge.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/pcie_pci_bridge.c
+++ b/hw/pci-bridge/pcie_pci_bridge.c
@@ -XXX,XX +XXX,XX @@ static void pcie_pci_bridge_class_init(ObjectClass *klass, void *data)
     k->config_write = pcie_pci_bridge_write_config;
     dc->vmsd = &pcie_pci_bridge_dev_vmstate;
     device_class_set_props(dc, pcie_pci_bridge_dev_properties);
-    dc->reset = &pcie_pci_bridge_reset;
+    device_class_set_legacy_reset(dc, pcie_pci_bridge_reset);
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     hc->plug = pci_bridge_dev_plug_cb;
     hc->unplug = pci_bridge_dev_unplug_cb;
diff --git a/hw/pci-bridge/simba.c b/hw/pci-bridge/simba.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/simba.c
+++ b/hw/pci-bridge/simba.c
@@ -XXX,XX +XXX,XX @@ static void simba_pci_bridge_class_init(ObjectClass *klass, void *data)
     k->revision = 0x11;
     k->config_write = pci_bridge_write_config;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
-    dc->reset = pci_bridge_reset;
+    device_class_set_legacy_reset(dc, pci_bridge_reset);
     dc->vmsd = &vmstate_pci_device;
 }
 
diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/xio3130_downstream.c
+++ b/hw/pci-bridge/xio3130_downstream.c
@@ -XXX,XX +XXX,XX @@ static void xio3130_downstream_class_init(ObjectClass *klass, void *data)
     k->revision = XIO3130_REVISION;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->desc = "TI X3130 Downstream Port of PCI Express Switch";
-    dc->reset = xio3130_downstream_reset;
+    device_class_set_legacy_reset(dc, xio3130_downstream_reset);
     dc->vmsd = &vmstate_xio3130_downstream;
     device_class_set_props(dc, xio3130_downstream_props);
 }
diff --git a/hw/pci-bridge/xio3130_upstream.c b/hw/pci-bridge/xio3130_upstream.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-bridge/xio3130_upstream.c
+++ b/hw/pci-bridge/xio3130_upstream.c
@@ -XXX,XX +XXX,XX @@ static void xio3130_upstream_class_init(ObjectClass *klass, void *data)
     k->revision = XIO3130_REVISION;
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->desc = "TI X3130 Upstream Port of PCI Express Switch";
-    dc->reset = xio3130_upstream_reset;
+    device_class_set_legacy_reset(dc, xio3130_upstream_reset);
     dc->vmsd = &vmstate_xio3130_upstream;
 }
 
diff --git a/hw/pci-host/astro.c b/hw/pci-host/astro.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/astro.c
+++ b/hw/pci-host/astro.c
@@ -XXX,XX +XXX,XX @@ static void elroy_pcihost_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = elroy_reset;
+    device_class_set_legacy_reset(dc, elroy_reset);
     device_class_set_props(dc, elroy_pcihost_properties);
     dc->vmsd = &vmstate_elroy;
     dc->user_creatable = false;
@@ -XXX,XX +XXX,XX @@ static void astro_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = astro_reset;
+    device_class_set_legacy_reset(dc, astro_reset);
     dc->vmsd = &vmstate_astro;
     dc->realize = astro_realize;
     /*
diff --git a/hw/pci-host/designware.c b/hw/pci-host/designware.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/designware.c
+++ b/hw/pci-host/designware.c
@@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_class_init(ObjectClass *klass, void *data)
     k->config_read = designware_pcie_root_config_read;
     k->config_write = designware_pcie_root_config_write;
 
-    dc->reset = pci_bridge_reset;
+    device_class_set_legacy_reset(dc, pci_bridge_reset);
     /*
      * PCI-facing part of the host bridge, not usable without the
      * host-facing part, which can't be device_add'ed, yet.
diff --git a/hw/pci-host/dino.c b/hw/pci-host/dino.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/dino.c
+++ b/hw/pci-host/dino.c
@@ -XXX,XX +XXX,XX @@ static void dino_pcihost_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = dino_pcihost_reset;
+    device_class_set_legacy_reset(dc, dino_pcihost_reset);
     dc->realize = dino_pcihost_realize;
     dc->unrealize = dino_pcihost_unrealize;
     device_class_set_props(dc, dino_pcihost_properties);
diff --git a/hw/pci-host/gt64120.c b/hw/pci-host/gt64120.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/gt64120.c
+++ b/hw/pci-host/gt64120.c
@@ -XXX,XX +XXX,XX @@ static void gt64120_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     device_class_set_props(dc, gt64120_properties);
     dc->realize = gt64120_realize;
-    dc->reset = gt64120_reset;
+    device_class_set_legacy_reset(dc, gt64120_reset);
     dc->vmsd = &vmstate_gt64120;
 }
 
diff --git a/hw/pci-host/mv64361.c b/hw/pci-host/mv64361.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/mv64361.c
+++ b/hw/pci-host/mv64361.c
@@ -XXX,XX +XXX,XX @@ static void mv64361_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = mv64361_realize;
-    dc->reset = mv64361_reset;
+    device_class_set_legacy_reset(dc, mv64361_reset);
 }
 
 static const TypeInfo mv64361_type_info = {
diff --git a/hw/pci-host/ppc440_pcix.c b/hw/pci-host/ppc440_pcix.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/ppc440_pcix.c
+++ b/hw/pci-host/ppc440_pcix.c
@@ -XXX,XX +XXX,XX @@ static void ppc440_pcix_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = ppc440_pcix_realize;
-    dc->reset = ppc440_pcix_reset;
+    device_class_set_legacy_reset(dc, ppc440_pcix_reset);
 }
 
 static const TypeInfo ppc440_pcix_info = {
diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/q35.c
+++ b/hw/pci-host/q35.c
@@ -XXX,XX +XXX,XX @@ static void mch_class_init(ObjectClass *klass, void *data)
 
     k->realize = mch_realize;
     k->config_write = mch_write_config;
-    dc->reset = mch_reset;
+    device_class_set_legacy_reset(dc, mch_reset);
     device_class_set_props(dc, mch_props);
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->desc = "Host bridge";
diff --git a/hw/pci-host/sabre.c b/hw/pci-host/sabre.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/sabre.c
+++ b/hw/pci-host/sabre.c
@@ -XXX,XX +XXX,XX @@ static void sabre_class_init(ObjectClass *klass, void *data)
     SysBusDeviceClass *sbc = SYS_BUS_DEVICE_CLASS(klass);
 
     dc->realize = sabre_realize;
-    dc->reset = sabre_reset;
+    device_class_set_legacy_reset(dc, sabre_reset);
     device_class_set_props(dc, sabre_properties);
     set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories);
     dc->fw_name = "pci";
diff --git a/hw/pci-host/versatile.c b/hw/pci-host/versatile.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/versatile.c
+++ b/hw/pci-host/versatile.c
@@ -XXX,XX +XXX,XX @@ static void pci_vpb_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = pci_vpb_realize;
-    dc->reset = pci_vpb_reset;
+    device_class_set_legacy_reset(dc, pci_vpb_reset);
     dc->vmsd = &pci_vpb_vmstate;
     device_class_set_props(dc, pci_vpb_properties);
 }
diff --git a/hw/pci-host/xilinx-pcie.c b/hw/pci-host/xilinx-pcie.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/pci-host/xilinx-pcie.c
+++ b/hw/pci-host/xilinx-pcie.c
@@ -XXX,XX +XXX,XX @@ static void xilinx_pcie_root_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_BRIDGE_HOST;
     k->realize = xilinx_pcie_root_realize;
     k->exit = pci_bridge_exitfn;
-    dc->reset = pci_bridge_reset;
+    device_class_set_legacy_reset(dc, pci_bridge_reset);
     k->config_read = xilinx_pcie_root_config_read;
     k->config_write = xilinx_pcie_root_config_write;
     /*
diff --git a/hw/ppc/pnv_psi.c b/hw/ppc/pnv_psi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/pnv_psi.c
+++ b/hw/ppc/pnv_psi.c
@@ -XXX,XX +XXX,XX @@ static void pnv_psi_power9_class_init(ObjectClass *klass, void *data)
 
     dc->desc    = "PowerNV PSI Controller POWER9";
     dc->realize = pnv_psi_power9_realize;
-    dc->reset   = pnv_psi_power9_reset;
+    device_class_set_legacy_reset(dc, pnv_psi_power9_reset);
 
     ppc->xscom_pcba = PNV9_XSCOM_PSIHB_BASE;
     ppc->xscom_size = PNV9_XSCOM_PSIHB_SIZE;
@@ -XXX,XX +XXX,XX @@ static void pnv_psi_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "PowerNV PSI Controller";
     device_class_set_props(dc, pnv_psi_properties);
-    dc->reset = pnv_psi_reset;
+    device_class_set_legacy_reset(dc, pnv_psi_reset);
     dc->user_creatable = false;
 }
 
diff --git a/hw/ppc/ppc405_boards.c b/hw/ppc/ppc405_boards.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/ppc405_boards.c
+++ b/hw/ppc/ppc405_boards.c
@@ -XXX,XX +XXX,XX @@ static void ref405ep_fpga_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ref405ep_fpga_realize;
-    dc->reset = ref405ep_fpga_reset;
+    device_class_set_legacy_reset(dc, ref405ep_fpga_reset);
     /* Reason: only works as part of a ppc405 board */
     dc->user_creatable = false;
 }
diff --git a/hw/ppc/ppc405_uc.c b/hw/ppc/ppc405_uc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/ppc405_uc.c
+++ b/hw/ppc/ppc405_uc.c
@@ -XXX,XX +XXX,XX @@ static void ppc405_pob_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_pob_realize;
-    dc->reset = ppc405_pob_reset;
+    device_class_set_legacy_reset(dc, ppc405_pob_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
@@ -XXX,XX +XXX,XX @@ static void ppc405_opba_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_opba_realize;
-    dc->reset = ppc405_opba_reset;
+    device_class_set_legacy_reset(dc, ppc405_opba_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
@@ -XXX,XX +XXX,XX @@ static void ppc405_dma_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_dma_realize;
-    dc->reset = ppc405_dma_reset;
+    device_class_set_legacy_reset(dc, ppc405_dma_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
@@ -XXX,XX +XXX,XX @@ static void ppc405_ocm_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_ocm_realize;
-    dc->reset = ppc405_ocm_reset;
+    device_class_set_legacy_reset(dc, ppc405_ocm_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
@@ -XXX,XX +XXX,XX @@ static void ppc405_gpt_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_gpt_realize;
-    dc->reset = ppc405_gpt_reset;
+    device_class_set_legacy_reset(dc, ppc405_gpt_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
@@ -XXX,XX +XXX,XX @@ static void ppc405_cpc_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_cpc_realize;
-    dc->reset = ppc405_cpc_reset;
+    device_class_set_legacy_reset(dc, ppc405_cpc_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
     device_class_set_props(dc, ppc405_cpc_properties);
diff --git a/hw/ppc/ppc4xx_devs.c b/hw/ppc/ppc4xx_devs.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/ppc4xx_devs.c
+++ b/hw/ppc/ppc4xx_devs.c
@@ -XXX,XX +XXX,XX @@ static void ppc4xx_mal_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc4xx_mal_realize;
-    dc->reset = ppc4xx_mal_reset;
+    device_class_set_legacy_reset(dc, ppc4xx_mal_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
     device_class_set_props(dc, ppc4xx_mal_properties);
@@ -XXX,XX +XXX,XX @@ static void ppc405_plb_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_plb_realize;
-    dc->reset = ppc405_plb_reset;
+    device_class_set_legacy_reset(dc, ppc405_plb_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
@@ -XXX,XX +XXX,XX @@ static void ppc405_ebc_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc405_ebc_realize;
-    dc->reset = ppc405_ebc_reset;
+    device_class_set_legacy_reset(dc, ppc405_ebc_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
 }
diff --git a/hw/ppc/ppc4xx_sdram.c b/hw/ppc/ppc4xx_sdram.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/ppc4xx_sdram.c
+++ b/hw/ppc/ppc4xx_sdram.c
@@ -XXX,XX +XXX,XX @@ static void ppc4xx_sdram_ddr_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc4xx_sdram_ddr_realize;
-    dc->reset = ppc4xx_sdram_ddr_reset;
+    device_class_set_legacy_reset(dc, ppc4xx_sdram_ddr_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
     device_class_set_props(dc, ppc4xx_sdram_ddr_props);
@@ -XXX,XX +XXX,XX @@ static void ppc4xx_sdram_ddr2_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = ppc4xx_sdram_ddr2_realize;
-    dc->reset = ppc4xx_sdram_ddr2_reset;
+    device_class_set_legacy_reset(dc, ppc4xx_sdram_ddr2_reset);
     /* Reason: only works as function of a ppc4xx SoC */
     dc->user_creatable = false;
     device_class_set_props(dc, ppc4xx_sdram_ddr2_props);
diff --git a/hw/ppc/ppce500_spin.c b/hw/ppc/ppce500_spin.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/ppce500_spin.c
+++ b/hw/ppc/ppce500_spin.c
@@ -XXX,XX +XXX,XX @@ static void ppce500_spin_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = spin_reset;
+    device_class_set_legacy_reset(dc, spin_reset);
 }
 
 static const TypeInfo ppce500_spin_info = {
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -XXX,XX +XXX,XX @@ static void spapr_cpu_core_class_init(ObjectClass *oc, void *data)
 
     dc->realize = spapr_cpu_core_realize;
     dc->unrealize = spapr_cpu_core_unrealize;
-    dc->reset = spapr_cpu_core_reset;
+    device_class_set_legacy_reset(dc, spapr_cpu_core_reset);
     device_class_set_props(dc, spapr_cpu_core_properties);
     scc->cpu_type = data;
 }
diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/spapr_iommu.c
+++ b/hw/ppc/spapr_iommu.c
@@ -XXX,XX +XXX,XX @@ static void spapr_tce_table_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->realize = spapr_tce_table_realize;
-    dc->reset = spapr_tce_reset;
+    device_class_set_legacy_reset(dc, spapr_tce_reset);
     dc->unrealize = spapr_tce_table_unrealize;
     /* Reason: This is just an internal device for handling the hypercalls */
     dc->user_creatable = false;
diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/spapr_pci.c
+++ b/hw/ppc/spapr_pci.c
@@ -XXX,XX +XXX,XX @@ static void spapr_phb_class_init(ObjectClass *klass, void *data)
     dc->realize = spapr_phb_realize;
     dc->unrealize = spapr_phb_unrealize;
     device_class_set_props(dc, spapr_phb_properties);
-    dc->reset = spapr_phb_reset;
+    device_class_set_legacy_reset(dc, spapr_phb_reset);
     dc->vmsd = &vmstate_spapr_pci;
     /* Supported by TYPE_SPAPR_MACHINE */
     dc->user_creatable = true;
diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ppc/spapr_vio.c
+++ b/hw/ppc/spapr_vio.c
@@ -XXX,XX +XXX,XX @@ static void vio_spapr_device_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *k = DEVICE_CLASS(klass);
     k->realize = spapr_vio_busdev_realize;
-    k->reset = spapr_vio_busdev_reset;
+    device_class_set_legacy_reset(k, spapr_vio_busdev_reset);
     k->bus_type = TYPE_SPAPR_VIO_BUS;
 }
 
diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/remote/proxy.c
+++ b/hw/remote/proxy.c
@@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
     k->config_read = pci_proxy_read_config;
     k->config_write = pci_proxy_write_config;
 
-    dc->reset = proxy_device_reset;
+    device_class_set_legacy_reset(dc, proxy_device_reset);
 
     device_class_set_props(dc, proxy_properties);
 }
diff --git a/hw/rtc/allwinner-rtc.c b/hw/rtc/allwinner-rtc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/allwinner-rtc.c
+++ b/hw/rtc/allwinner-rtc.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_rtc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_rtc_reset;
+    device_class_set_legacy_reset(dc, allwinner_rtc_reset);
     dc->vmsd = &allwinner_rtc_vmstate;
     device_class_set_props(dc, allwinner_rtc_properties);
 }
diff --git a/hw/rtc/aspeed_rtc.c b/hw/rtc/aspeed_rtc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/aspeed_rtc.c
+++ b/hw/rtc/aspeed_rtc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_rtc_class_init(ObjectClass *klass, void *data)
 
     dc->realize = aspeed_rtc_realize;
     dc->vmsd = &vmstate_aspeed_rtc;
-    dc->reset = aspeed_rtc_reset;
+    device_class_set_legacy_reset(dc, aspeed_rtc_reset);
 }
 
 static const TypeInfo aspeed_rtc_info = {
diff --git a/hw/rtc/ds1338.c b/hw/rtc/ds1338.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/ds1338.c
+++ b/hw/rtc/ds1338.c
@@ -XXX,XX +XXX,XX @@ static void ds1338_class_init(ObjectClass *klass, void *data)
     k->event = ds1338_event;
     k->recv = ds1338_recv;
     k->send = ds1338_send;
-    dc->reset = ds1338_reset;
+    device_class_set_legacy_reset(dc, ds1338_reset);
     dc->vmsd = &vmstate_ds1338;
 }
 
diff --git a/hw/rtc/exynos4210_rtc.c b/hw/rtc/exynos4210_rtc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/exynos4210_rtc.c
+++ b/hw/rtc/exynos4210_rtc.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_rtc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_rtc_reset;
+    device_class_set_legacy_reset(dc, exynos4210_rtc_reset);
     dc->vmsd = &vmstate_exynos4210_rtc_state;
 }
 
diff --git a/hw/rtc/goldfish_rtc.c b/hw/rtc/goldfish_rtc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/goldfish_rtc.c
+++ b/hw/rtc/goldfish_rtc.c
@@ -XXX,XX +XXX,XX @@ static void goldfish_rtc_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, goldfish_rtc_properties);
     dc->realize = goldfish_rtc_realize;
-    dc->reset = goldfish_rtc_reset;
+    device_class_set_legacy_reset(dc, goldfish_rtc_reset);
     dc->vmsd = &goldfish_rtc_vmstate;
 }
 
diff --git a/hw/rtc/ls7a_rtc.c b/hw/rtc/ls7a_rtc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/ls7a_rtc.c
+++ b/hw/rtc/ls7a_rtc.c
@@ -XXX,XX +XXX,XX @@ static void ls7a_rtc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->vmsd = &vmstate_ls7a_rtc;
     dc->realize = ls7a_rtc_realize;
-    dc->reset = ls7a_rtc_reset;
+    device_class_set_legacy_reset(dc, ls7a_rtc_reset);
     dc->desc = "ls7a rtc";
 }
 
diff --git a/hw/rtc/m48t59-isa.c b/hw/rtc/m48t59-isa.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/m48t59-isa.c
+++ b/hw/rtc/m48t59-isa.c
@@ -XXX,XX +XXX,XX @@ static void m48txx_isa_class_init(ObjectClass *klass, void *data)
     NvramClass *nc = NVRAM_CLASS(klass);
 
     dc->realize = m48t59_isa_realize;
-    dc->reset = m48t59_reset_isa;
+    device_class_set_legacy_reset(dc, m48t59_reset_isa);
     device_class_set_props(dc, m48t59_isa_properties);
     nc->read = m48txx_isa_read;
     nc->write = m48txx_isa_write;
diff --git a/hw/rtc/m48t59.c b/hw/rtc/m48t59.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/m48t59.c
+++ b/hw/rtc/m48t59.c
@@ -XXX,XX +XXX,XX @@ static void m48txx_sysbus_class_init(ObjectClass *klass, void *data)
     NvramClass *nc = NVRAM_CLASS(klass);
 
     dc->realize = m48t59_realize;
-    dc->reset = m48t59_reset_sysbus;
+    device_class_set_legacy_reset(dc, m48t59_reset_sysbus);
     device_class_set_props(dc, m48t59_sysbus_properties);
     dc->vmsd = &vmstate_m48t59;
     nc->read = m48txx_sysbus_read;
diff --git a/hw/rtc/xlnx-zynqmp-rtc.c b/hw/rtc/xlnx-zynqmp-rtc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/rtc/xlnx-zynqmp-rtc.c
+++ b/hw/rtc/xlnx-zynqmp-rtc.c
@@ -XXX,XX +XXX,XX @@ static void rtc_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = rtc_reset;
+    device_class_set_legacy_reset(dc, rtc_reset);
     dc->vmsd = &vmstate_rtc;
 }
 
diff --git a/hw/s390x/event-facility.c b/hw/s390x/event-facility.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/event-facility.c
+++ b/hw/s390x/event-facility.c
@@ -XXX,XX +XXX,XX @@ static void init_event_facility_class(ObjectClass *klass, void *data)
     SCLPEventFacilityClass *k = EVENT_FACILITY_CLASS(dc);
 
     dc->realize = realize_event_facility;
-    dc->reset = reset_event_facility;
+    device_class_set_legacy_reset(dc, reset_event_facility);
     dc->vmsd = &vmstate_event_facility;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     k->command_handler = command_handler;
diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/ipl.c
+++ b/hw/s390x/ipl.c
@@ -XXX,XX +XXX,XX @@ static void s390_ipl_class_init(ObjectClass *klass, void *data)
 
     dc->realize = s390_ipl_realize;
     device_class_set_props(dc, s390_ipl_properties);
-    dc->reset = s390_ipl_reset;
+    device_class_set_legacy_reset(dc, s390_ipl_reset);
     dc->vmsd = &vmstate_ipl;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     /* Reason: Loads the ROMs and thus can only be used one time - internally */
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -XXX,XX +XXX,XX @@ static void s390_pcihost_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
 
-    dc->reset = s390_pcihost_reset;
+    device_class_set_legacy_reset(dc, s390_pcihost_reset);
     dc->realize = s390_pcihost_realize;
     dc->unrealize = s390_pcihost_unrealize;
     hc->pre_plug = s390_pcihost_pre_plug;
@@ -XXX,XX +XXX,XX @@ static void s390_pci_device_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "zpci device";
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
-    dc->reset = s390_pci_device_reset;
+    device_class_set_legacy_reset(dc, s390_pci_device_reset);
     dc->bus_type = TYPE_S390_PCI_BUS;
     dc->realize = s390_pci_device_realize;
     device_class_set_props(dc, s390_pci_device_properties);
diff --git a/hw/s390x/sclpquiesce.c b/hw/s390x/sclpquiesce.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/s390x/sclpquiesce.c
+++ b/hw/s390x/sclpquiesce.c
@@ -XXX,XX +XXX,XX @@ static void quiesce_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     SCLPEventClass *k = SCLP_EVENT_CLASS(klass);
 
-    dc->reset = quiesce_reset;
+    device_class_set_legacy_reset(dc, quiesce_reset);
     dc->vmsd = &vmstate_sclpquiesce;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     /*
diff --git a/hw/scsi/esp-pci.c b/hw/scsi/esp-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/esp-pci.c
+++ b/hw/scsi/esp-pci.c
@@ -XXX,XX +XXX,XX @@ static void esp_pci_class_init(ObjectClass *klass, void *data)
     k->class_id = PCI_CLASS_STORAGE_SCSI;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     dc->desc = "AMD Am53c974 PCscsi-PCI SCSI adapter";
-    dc->reset = esp_pci_hard_reset;
+    device_class_set_legacy_reset(dc, esp_pci_hard_reset);
     dc->vmsd = &vmstate_esp_pci_scsi;
 }
 
diff --git a/hw/scsi/esp.c b/hw/scsi/esp.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/esp.c
+++ b/hw/scsi/esp.c
@@ -XXX,XX +XXX,XX @@ static void sysbus_esp_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = sysbus_esp_realize;
-    dc->reset = sysbus_esp_hard_reset;
+    device_class_set_legacy_reset(dc, sysbus_esp_hard_reset);
     dc->vmsd = &vmstate_sysbus_esp_scsi;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
diff --git a/hw/scsi/lsi53c895a.c b/hw/scsi/lsi53c895a.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/lsi53c895a.c
+++ b/hw/scsi/lsi53c895a.c
@@ -XXX,XX +XXX,XX @@ static void lsi_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_LSI_53C895A;
     k->class_id = PCI_CLASS_STORAGE_SCSI;
     k->subsystem_id = 0x1000;
-    dc->reset = lsi_scsi_reset;
+    device_class_set_legacy_reset(dc, lsi_scsi_reset);
     dc->vmsd = &vmstate_lsi_scsi;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 }
diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/megasas.c
+++ b/hw/scsi/megasas.c
@@ -XXX,XX +XXX,XX @@ static void megasas_class_init(ObjectClass *oc, void *data)
     e->product_name = info->product_name;
     e->product_version = info->product_version;
     device_class_set_props(dc, info->props);
-    dc->reset = megasas_scsi_reset;
+    device_class_set_legacy_reset(dc, megasas_scsi_reset);
     dc->vmsd = info->vmsd;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     dc->desc = info->desc;
diff --git a/hw/scsi/mptsas.c b/hw/scsi/mptsas.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/mptsas.c
+++ b/hw/scsi/mptsas.c
@@ -XXX,XX +XXX,XX @@ static void mptsas1068_class_init(ObjectClass *oc, void *data)
     pc->subsystem_id = 0x8000;
     pc->class_id = PCI_CLASS_STORAGE_SCSI;
     device_class_set_props(dc, mptsas_properties);
-    dc->reset = mptsas_reset;
+    device_class_set_legacy_reset(dc, mptsas_reset);
     dc->vmsd = &vmstate_mptsas;
     dc->desc = "LSI SAS 1068";
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -XXX,XX +XXX,XX @@ static void scsi_disk_base_class_initfn(ObjectClass *klass, void *data)
     SCSIDiskClass *sdc = SCSI_DISK_BASE_CLASS(klass);
 
     dc->fw_name = "disk";
-    dc->reset = scsi_disk_reset;
+    device_class_set_legacy_reset(dc, scsi_disk_reset);
     sdc->dma_readv = scsi_dma_readv;
     sdc->dma_writev = scsi_dma_writev;
     sdc->need_fua_emulation = scsi_is_cmd_fua;
diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/scsi-generic.c
+++ b/hw/scsi/scsi-generic.c
@@ -XXX,XX +XXX,XX @@ static void scsi_generic_class_initfn(ObjectClass *klass, void *data)
     sc->parse_cdb    = scsi_generic_parse_cdb;
     dc->fw_name = "disk";
     dc->desc = "pass through generic scsi device (/dev/sg*)";
-    dc->reset = scsi_generic_reset;
+    device_class_set_legacy_reset(dc, scsi_generic_reset);
     device_class_set_props(dc, scsi_generic_properties);
     dc->vmsd  = &vmstate_scsi_device;
 }
diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/scsi/vmw_pvscsi.c
+++ b/hw/scsi/vmw_pvscsi.c
@@ -XXX,XX +XXX,XX @@ static void pvscsi_class_init(ObjectClass *klass, void *data)
     k->subsystem_id = 0x1000;
     device_class_set_parent_realize(dc, pvscsi_realize,
                                     &pvs_k->parent_dc_realize);
-    dc->reset = pvscsi_reset;
+    device_class_set_legacy_reset(dc, pvscsi_reset);
     dc->vmsd = &vmstate_pvscsi;
     device_class_set_props(dc, pvscsi_properties);
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/allwinner-sdhost.c
+++ b/hw/sd/allwinner-sdhost.c
@@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = allwinner_sdhost_reset;
+    device_class_set_legacy_reset(dc, allwinner_sdhost_reset);
     dc->vmsd = &vmstate_allwinner_sdhost;
     dc->realize = allwinner_sdhost_realize;
     device_class_set_props(dc, allwinner_sdhost_properties);
diff --git a/hw/sd/aspeed_sdhci.c b/hw/sd/aspeed_sdhci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/aspeed_sdhci.c
+++ b/hw/sd/aspeed_sdhci.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_sdhci_class_init(ObjectClass *classp, void *data)
     DeviceClass *dc = DEVICE_CLASS(classp);
 
     dc->realize = aspeed_sdhci_realize;
-    dc->reset = aspeed_sdhci_reset;
+    device_class_set_legacy_reset(dc, aspeed_sdhci_reset);
     dc->vmsd = &vmstate_aspeed_sdhci;
     device_class_set_props(dc, aspeed_sdhci_properties);
 }
diff --git a/hw/sd/bcm2835_sdhost.c b/hw/sd/bcm2835_sdhost.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/bcm2835_sdhost.c
+++ b/hw/sd/bcm2835_sdhost.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_sdhost_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2835_sdhost_reset;
+    device_class_set_legacy_reset(dc, bcm2835_sdhost_reset);
     dc->vmsd = &vmstate_bcm2835_sdhost;
 }
 
diff --git a/hw/sd/cadence_sdhci.c b/hw/sd/cadence_sdhci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/cadence_sdhci.c
+++ b/hw/sd/cadence_sdhci.c
@@ -XXX,XX +XXX,XX @@ static void cadence_sdhci_class_init(ObjectClass *classp, void *data)
 
     dc->desc = "Cadence SD/SDIO/eMMC Host Controller (SD4HC)";
     dc->realize = cadence_sdhci_realize;
-    dc->reset = cadence_sdhci_reset;
+    device_class_set_legacy_reset(dc, cadence_sdhci_reset);
     dc->vmsd = &vmstate_cadence_sdhci;
 }
 
diff --git a/hw/sd/npcm7xx_sdhci.c b/hw/sd/npcm7xx_sdhci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/npcm7xx_sdhci.c
+++ b/hw/sd/npcm7xx_sdhci.c
@@ -XXX,XX +XXX,XX @@ static void npcm7xx_sdhci_class_init(ObjectClass *classp, void *data)
 
     dc->desc = "NPCM7xx SD/eMMC Host Controller";
     dc->realize = npcm7xx_sdhci_realize;
-    dc->reset = npcm7xx_sdhci_reset;
+    device_class_set_legacy_reset(dc, npcm7xx_sdhci_reset);
     dc->vmsd = &vmstate_npcm7xx_sdhci;
 }
 
diff --git a/hw/sd/pl181.c b/hw/sd/pl181.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/pl181.c
+++ b/hw/sd/pl181.c
@@ -XXX,XX +XXX,XX @@ static void pl181_class_init(ObjectClass *klass, void *data)
     DeviceClass *k = DEVICE_CLASS(klass);
 
     k->vmsd = &vmstate_pl181;
-    k->reset = pl181_reset;
+    device_class_set_legacy_reset(k, pl181_reset);
     /* Reason: output IRQs should be wired up */
     k->user_creatable = false;
 }
diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/pxa2xx_mmci.c
+++ b/hw/sd/pxa2xx_mmci.c
@@ -XXX,XX +XXX,XX @@ static void pxa2xx_mmci_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_pxa2xx_mmci;
-    dc->reset = pxa2xx_mmci_reset;
+    device_class_set_legacy_reset(dc, pxa2xx_mmci_reset);
 }
 
 static void pxa2xx_mmci_bus_class_init(ObjectClass *klass, void *data)
diff --git a/hw/sd/sd.c b/hw/sd/sd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/sd.c
+++ b/hw/sd/sd.c
@@ -XXX,XX +XXX,XX @@ static void sdmmc_common_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, sdmmc_common_properties);
     dc->vmsd = &sd_vmstate;
-    dc->reset = sd_reset;
+    device_class_set_legacy_reset(dc, sd_reset);
     dc->bus_type = TYPE_SD_BUS;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
 
diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/sdhci.c
+++ b/hw/sd/sdhci.c
@@ -XXX,XX +XXX,XX @@ void sdhci_common_class_init(ObjectClass *klass, void *data)
 
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     dc->vmsd = &sdhci_vmstate;
-    dc->reset = sdhci_poweron_reset;
+    device_class_set_legacy_reset(dc, sdhci_poweron_reset);
 }
 
 /* --- qdev SysBus --- */
diff --git a/hw/sd/ssi-sd.c b/hw/sd/ssi-sd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sd/ssi-sd.c
+++ b/hw/sd/ssi-sd.c
@@ -XXX,XX +XXX,XX @@ static void ssi_sd_class_init(ObjectClass *klass, void *data)
     k->transfer = ssi_sd_transfer;
     k->cs_polarity = SSI_CS_LOW;
     dc->vmsd = &vmstate_ssi_sd;
-    dc->reset = ssi_sd_reset;
+    device_class_set_legacy_reset(dc, ssi_sd_reset);
     /* Reason: GPIO chip-select line should be wired up */
     dc->user_creatable = false;
 }
diff --git a/hw/sensor/dps310.c b/hw/sensor/dps310.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sensor/dps310.c
+++ b/hw/sensor/dps310.c
@@ -XXX,XX +XXX,XX @@ static void dps310_class_init(ObjectClass *klass, void *data)
     k->event = dps310_event;
     k->recv = dps310_rx;
     k->send = dps310_tx;
-    dc->reset = dps310_reset;
+    device_class_set_legacy_reset(dc, dps310_reset);
     dc->vmsd = &vmstate_dps310;
 }
 
diff --git a/hw/sensor/emc141x.c b/hw/sensor/emc141x.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sensor/emc141x.c
+++ b/hw/sensor/emc141x.c
@@ -XXX,XX +XXX,XX @@ static void emc141x_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     I2CSlaveClass *k = I2C_SLAVE_CLASS(klass);
 
-    dc->reset = emc141x_reset;
+    device_class_set_legacy_reset(dc, emc141x_reset);
     k->event = emc141x_event;
     k->recv = emc141x_rx;
     k->send = emc141x_tx;
diff --git a/hw/sensor/lsm303dlhc_mag.c b/hw/sensor/lsm303dlhc_mag.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sensor/lsm303dlhc_mag.c
+++ b/hw/sensor/lsm303dlhc_mag.c
@@ -XXX,XX +XXX,XX @@ static void lsm303dlhc_mag_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     I2CSlaveClass *k = I2C_SLAVE_CLASS(klass);
 
-    dc->reset = lsm303dlhc_mag_reset;
+    device_class_set_legacy_reset(dc, lsm303dlhc_mag_reset);
     dc->vmsd = &vmstate_lsm303dlhc_mag;
     k->event = lsm303dlhc_mag_event;
     k->recv = lsm303dlhc_mag_recv;
diff --git a/hw/sparc/sun4m_iommu.c b/hw/sparc/sun4m_iommu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sparc/sun4m_iommu.c
+++ b/hw/sparc/sun4m_iommu.c
@@ -XXX,XX +XXX,XX @@ static void iommu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = iommu_reset;
+    device_class_set_legacy_reset(dc, iommu_reset);
     dc->vmsd = &vmstate_iommu;
     device_class_set_props(dc, iommu_properties);
 }
diff --git a/hw/sparc64/sun4u_iommu.c b/hw/sparc64/sun4u_iommu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/sparc64/sun4u_iommu.c
+++ b/hw/sparc64/sun4u_iommu.c
@@ -XXX,XX +XXX,XX @@ static void iommu_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = iommu_reset;
+    device_class_set_legacy_reset(dc, iommu_reset);
 }
 
 static const TypeInfo iommu_info = {
diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/aspeed_smc.c
+++ b/hw/ssi/aspeed_smc.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_smc_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_smc_realize;
-    dc->reset = aspeed_smc_reset;
+    device_class_set_legacy_reset(dc, aspeed_smc_reset);
     device_class_set_props(dc, aspeed_smc_properties);
     dc->vmsd = &vmstate_aspeed_smc;
 }
diff --git a/hw/ssi/bcm2835_spi.c b/hw/ssi/bcm2835_spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/bcm2835_spi.c
+++ b/hw/ssi/bcm2835_spi.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_spi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = bcm2835_spi_reset;
+    device_class_set_legacy_reset(dc, bcm2835_spi_reset);
     dc->realize = bcm2835_spi_realize;
     dc->vmsd = &vmstate_bcm2835_spi;
 }
diff --git a/hw/ssi/ibex_spi_host.c b/hw/ssi/ibex_spi_host.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/ibex_spi_host.c
+++ b/hw/ssi/ibex_spi_host.c
@@ -XXX,XX +XXX,XX @@ static void ibex_spi_host_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     dc->realize = ibex_spi_host_realize;
-    dc->reset = ibex_spi_host_reset;
+    device_class_set_legacy_reset(dc, ibex_spi_host_reset);
     dc->vmsd = &vmstate_ibex;
     device_class_set_props(dc, ibex_spi_properties);
 }
diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/imx_spi.c
+++ b/hw/ssi/imx_spi.c
@@ -XXX,XX +XXX,XX @@ static void imx_spi_class_init(ObjectClass *klass, void *data)
 
     dc->realize = imx_spi_realize;
     dc->vmsd = &vmstate_imx_spi;
-    dc->reset = imx_spi_reset;
+    device_class_set_legacy_reset(dc, imx_spi_reset);
     dc->desc = "i.MX SPI Controller";
 }
 
diff --git a/hw/ssi/mss-spi.c b/hw/ssi/mss-spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/mss-spi.c
+++ b/hw/ssi/mss-spi.c
@@ -XXX,XX +XXX,XX @@ static void mss_spi_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = mss_spi_realize;
-    dc->reset = mss_spi_reset;
+    device_class_set_legacy_reset(dc, mss_spi_reset);
     dc->vmsd = &vmstate_mss_spi;
 }
 
diff --git a/hw/ssi/pl022.c b/hw/ssi/pl022.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/pl022.c
+++ b/hw/ssi/pl022.c
@@ -XXX,XX +XXX,XX @@ static void pl022_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = pl022_reset;
+    device_class_set_legacy_reset(dc, pl022_reset);
     dc->vmsd = &vmstate_pl022;
     dc->realize = pl022_realize;
 }
diff --git a/hw/ssi/pnv_spi.c b/hw/ssi/pnv_spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/pnv_spi.c
+++ b/hw/ssi/pnv_spi.c
@@ -XXX,XX +XXX,XX @@ static void pnv_spi_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "PowerNV SPI";
     dc->realize = pnv_spi_realize;
-    dc->reset = do_reset;
+    device_class_set_legacy_reset(dc, do_reset);
     device_class_set_props(dc, pnv_spi_properties);
 }
 
diff --git a/hw/ssi/sifive_spi.c b/hw/ssi/sifive_spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/sifive_spi.c
+++ b/hw/ssi/sifive_spi.c
@@ -XXX,XX +XXX,XX @@ static void sifive_spi_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     device_class_set_props(dc, sifive_spi_properties);
-    dc->reset = sifive_spi_reset;
+    device_class_set_legacy_reset(dc, sifive_spi_reset);
     dc->realize = sifive_spi_realize;
 }
 
diff --git a/hw/ssi/stm32f2xx_spi.c b/hw/ssi/stm32f2xx_spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/stm32f2xx_spi.c
+++ b/hw/ssi/stm32f2xx_spi.c
@@ -XXX,XX +XXX,XX @@ static void stm32f2xx_spi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f2xx_spi_reset;
+    device_class_set_legacy_reset(dc, stm32f2xx_spi_reset);
     dc->vmsd = &vmstate_stm32f2xx_spi;
 }
 
diff --git a/hw/ssi/xilinx_spi.c b/hw/ssi/xilinx_spi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/xilinx_spi.c
+++ b/hw/ssi/xilinx_spi.c
@@ -XXX,XX +XXX,XX @@ static void xilinx_spi_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = xilinx_spi_realize;
-    dc->reset = xlx_spi_reset;
+    device_class_set_legacy_reset(dc, xlx_spi_reset);
     device_class_set_props(dc, xilinx_spi_properties);
     dc->vmsd = &vmstate_xilinx_spi;
 }
diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/xilinx_spips.c
+++ b/hw/ssi/xilinx_spips.c
@@ -XXX,XX +XXX,XX @@ static void xilinx_spips_class_init(ObjectClass *klass, void *data)
     XilinxSPIPSClass *xsc = XILINX_SPIPS_CLASS(klass);
 
     dc->realize = xilinx_spips_realize;
-    dc->reset = xilinx_spips_reset;
+    device_class_set_legacy_reset(dc, xilinx_spips_reset);
     device_class_set_props(dc, xilinx_spips_properties);
     dc->vmsd = &vmstate_xilinx_spips;
 
@@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_qspips_class_init(ObjectClass *klass, void * data)
     XilinxSPIPSClass *xsc = XILINX_SPIPS_CLASS(klass);
 
     dc->realize = xlnx_zynqmp_qspips_realize;
-    dc->reset = xlnx_zynqmp_qspips_reset;
+    device_class_set_legacy_reset(dc, xlnx_zynqmp_qspips_reset);
     dc->vmsd = &vmstate_xlnx_zynqmp_qspips;
     device_class_set_props(dc, xilinx_zynqmp_qspips_properties);
     xsc->reg_ops = &xlnx_zynqmp_qspips_ops;
diff --git a/hw/ssi/xlnx-versal-ospi.c b/hw/ssi/xlnx-versal-ospi.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/ssi/xlnx-versal-ospi.c
+++ b/hw/ssi/xlnx-versal-ospi.c
@@ -XXX,XX +XXX,XX @@ static void xlnx_versal_ospi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xlnx_versal_ospi_reset;
+    device_class_set_legacy_reset(dc, xlnx_versal_ospi_reset);
     dc->realize = xlnx_versal_ospi_realize;
     dc->vmsd = &vmstate_xlnx_versal_ospi;
     device_class_set_props(dc, xlnx_versal_ospi_properties);
diff --git a/hw/timer/a9gtimer.c b/hw/timer/a9gtimer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/a9gtimer.c
+++ b/hw/timer/a9gtimer.c
@@ -XXX,XX +XXX,XX @@ static void a9_gtimer_class_init(ObjectClass *klass, void *data)
 
     dc->realize = a9_gtimer_realize;
     dc->vmsd = &vmstate_a9_gtimer;
-    dc->reset = a9_gtimer_reset;
+    device_class_set_legacy_reset(dc, a9_gtimer_reset);
     device_class_set_props(dc, a9_gtimer_properties);
 }
 
diff --git a/hw/timer/allwinner-a10-pit.c b/hw/timer/allwinner-a10-pit.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/allwinner-a10-pit.c
+++ b/hw/timer/allwinner-a10-pit.c
@@ -XXX,XX +XXX,XX @@ static void a10_pit_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = a10_pit_reset;
+    device_class_set_legacy_reset(dc, a10_pit_reset);
     device_class_set_props(dc, a10_pit_properties);
     dc->desc = "allwinner a10 timer";
     dc->vmsd = &vmstate_a10_pit;
diff --git a/hw/timer/arm_mptimer.c b/hw/timer/arm_mptimer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/arm_mptimer.c
+++ b/hw/timer/arm_mptimer.c
@@ -XXX,XX +XXX,XX @@ static void arm_mptimer_class_init(ObjectClass *klass, void *data)
 
     dc->realize = arm_mptimer_realize;
     dc->vmsd = &vmstate_arm_mptimer;
-    dc->reset = arm_mptimer_reset;
+    device_class_set_legacy_reset(dc, arm_mptimer_reset);
     device_class_set_props(dc, arm_mptimer_properties);
 }
 
diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/armv7m_systick.c
+++ b/hw/timer/armv7m_systick.c
@@ -XXX,XX +XXX,XX @@ static void systick_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_systick;
-    dc->reset = systick_reset;
+    device_class_set_legacy_reset(dc, systick_reset);
     dc->realize = systick_realize;
 }
 
diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/aspeed_timer.c
+++ b/hw/timer/aspeed_timer.c
@@ -XXX,XX +XXX,XX @@ static void timer_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = aspeed_timer_realize;
-    dc->reset = aspeed_timer_reset;
+    device_class_set_legacy_reset(dc, aspeed_timer_reset);
     dc->desc = "ASPEED Timer";
     dc->vmsd = &vmstate_aspeed_timer_state;
     device_class_set_props(dc, aspeed_timer_properties);
diff --git a/hw/timer/avr_timer16.c b/hw/timer/avr_timer16.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/avr_timer16.c
+++ b/hw/timer/avr_timer16.c
@@ -XXX,XX +XXX,XX @@ static void avr_timer16_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = avr_timer16_reset;
+    device_class_set_legacy_reset(dc, avr_timer16_reset);
     dc->realize = avr_timer16_realize;
     device_class_set_props(dc, avr_timer16_properties);
 }
diff --git a/hw/timer/bcm2835_systmr.c b/hw/timer/bcm2835_systmr.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/bcm2835_systmr.c
+++ b/hw/timer/bcm2835_systmr.c
@@ -XXX,XX +XXX,XX @@ static void bcm2835_systmr_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = bcm2835_systmr_realize;
-    dc->reset = bcm2835_systmr_reset;
+    device_class_set_legacy_reset(dc, bcm2835_systmr_reset);
     dc->vmsd = &bcm2835_systmr_vmstate;
 }
 
diff --git a/hw/timer/cmsdk-apb-dualtimer.c b/hw/timer/cmsdk-apb-dualtimer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/cmsdk-apb-dualtimer.c
+++ b/hw/timer/cmsdk-apb-dualtimer.c
@@ -XXX,XX +XXX,XX @@ static void cmsdk_apb_dualtimer_class_init(ObjectClass *klass, void *data)
 
     dc->realize = cmsdk_apb_dualtimer_realize;
     dc->vmsd = &cmsdk_apb_dualtimer_vmstate;
-    dc->reset = cmsdk_apb_dualtimer_reset;
+    device_class_set_legacy_reset(dc, cmsdk_apb_dualtimer_reset);
 }
 
 static const TypeInfo cmsdk_apb_dualtimer_info = {
diff --git a/hw/timer/cmsdk-apb-timer.c b/hw/timer/cmsdk-apb-timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/cmsdk-apb-timer.c
+++ b/hw/timer/cmsdk-apb-timer.c
@@ -XXX,XX +XXX,XX @@ static void cmsdk_apb_timer_class_init(ObjectClass *klass, void *data)
 
     dc->realize = cmsdk_apb_timer_realize;
     dc->vmsd = &cmsdk_apb_timer_vmstate;
-    dc->reset = cmsdk_apb_timer_reset;
+    device_class_set_legacy_reset(dc, cmsdk_apb_timer_reset);
 }
 
 static const TypeInfo cmsdk_apb_timer_info = {
diff --git a/hw/timer/digic-timer.c b/hw/timer/digic-timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/digic-timer.c
+++ b/hw/timer/digic-timer.c
@@ -XXX,XX +XXX,XX @@ static void digic_timer_class_init(ObjectClass *klass, void *class_data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = digic_timer_reset;
+    device_class_set_legacy_reset(dc, digic_timer_reset);
     dc->vmsd = &vmstate_digic_timer;
 }
 
diff --git a/hw/timer/exynos4210_mct.c b/hw/timer/exynos4210_mct.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/exynos4210_mct.c
+++ b/hw/timer/exynos4210_mct.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_mct_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_mct_reset;
+    device_class_set_legacy_reset(dc, exynos4210_mct_reset);
     dc->vmsd = &vmstate_exynos4210_mct_state;
 }
 
diff --git a/hw/timer/exynos4210_pwm.c b/hw/timer/exynos4210_pwm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/exynos4210_pwm.c
+++ b/hw/timer/exynos4210_pwm.c
@@ -XXX,XX +XXX,XX @@ static void exynos4210_pwm_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = exynos4210_pwm_reset;
+    device_class_set_legacy_reset(dc, exynos4210_pwm_reset);
     dc->vmsd = &vmstate_exynos4210_pwm_state;
 }
 
diff --git a/hw/timer/grlib_gptimer.c b/hw/timer/grlib_gptimer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/grlib_gptimer.c
+++ b/hw/timer/grlib_gptimer.c
@@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = grlib_gptimer_realize;
-    dc->reset = grlib_gptimer_reset;
+    device_class_set_legacy_reset(dc, grlib_gptimer_reset);
     device_class_set_props(dc, grlib_gptimer_properties);
 }
 
diff --git a/hw/timer/hpet.c b/hw/timer/hpet.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/hpet.c
+++ b/hw/timer/hpet.c
@@ -XXX,XX +XXX,XX @@ static void hpet_device_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = hpet_realize;
-    dc->reset = hpet_reset;
+    device_class_set_legacy_reset(dc, hpet_reset);
     dc->vmsd = &vmstate_hpet;
     device_class_set_props(dc, hpet_device_properties);
 }
diff --git a/hw/timer/i8254.c b/hw/timer/i8254.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/i8254.c
+++ b/hw/timer/i8254.c
@@ -XXX,XX +XXX,XX @@ static void pit_class_initfn(ObjectClass *klass, void *data)
     k->set_channel_gate = pit_set_channel_gate;
     k->get_channel_info = pit_get_channel_info_common;
     k->post_load = pit_post_load;
-    dc->reset = pit_reset;
+    device_class_set_legacy_reset(dc, pit_reset);
 }
 
 static const TypeInfo pit_info = {
diff --git a/hw/timer/ibex_timer.c b/hw/timer/ibex_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/ibex_timer.c
+++ b/hw/timer/ibex_timer.c
@@ -XXX,XX +XXX,XX @@ static void ibex_timer_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = ibex_timer_reset;
+    device_class_set_legacy_reset(dc, ibex_timer_reset);
     dc->vmsd = &vmstate_ibex_timer;
     dc->realize = ibex_timer_realize;
     device_class_set_props(dc, ibex_timer_properties);
diff --git a/hw/timer/imx_epit.c b/hw/timer/imx_epit.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/imx_epit.c
+++ b/hw/timer/imx_epit.c
@@ -XXX,XX +XXX,XX @@ static void imx_epit_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc  = DEVICE_CLASS(klass);
 
     dc->realize = imx_epit_realize;
-    dc->reset = imx_epit_dev_reset;
+    device_class_set_legacy_reset(dc, imx_epit_dev_reset);
     dc->vmsd = &vmstate_imx_timer_epit;
     dc->desc = "i.MX periodic timer";
 }
diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/imx_gpt.c
+++ b/hw/timer/imx_gpt.c
@@ -XXX,XX +XXX,XX @@ static void imx_gpt_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = imx_gpt_realize;
-    dc->reset = imx_gpt_reset;
+    device_class_set_legacy_reset(dc, imx_gpt_reset);
     dc->vmsd = &vmstate_imx_timer_gpt;
     dc->desc = "i.MX general timer";
 }
diff --git a/hw/timer/nrf51_timer.c b/hw/timer/nrf51_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/nrf51_timer.c
+++ b/hw/timer/nrf51_timer.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_timer_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = nrf51_timer_reset;
+    device_class_set_legacy_reset(dc, nrf51_timer_reset);
     dc->vmsd = &vmstate_nrf51_timer;
     device_class_set_props(dc, nrf51_timer_properties);
 }
diff --git a/hw/timer/renesas_cmt.c b/hw/timer/renesas_cmt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/renesas_cmt.c
+++ b/hw/timer/renesas_cmt.c
@@ -XXX,XX +XXX,XX @@ static void rcmt_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_rcmt;
-    dc->reset = rcmt_reset;
+    device_class_set_legacy_reset(dc, rcmt_reset);
     device_class_set_props(dc, rcmt_properties);
 }
 
diff --git a/hw/timer/renesas_tmr.c b/hw/timer/renesas_tmr.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/renesas_tmr.c
+++ b/hw/timer/renesas_tmr.c
@@ -XXX,XX +XXX,XX @@ static void rtmr_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->vmsd = &vmstate_rtmr;
-    dc->reset = rtmr_reset;
+    device_class_set_legacy_reset(dc, rtmr_reset);
     device_class_set_props(dc, rtmr_properties);
 }
 
diff --git a/hw/timer/sifive_pwm.c b/hw/timer/sifive_pwm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/sifive_pwm.c
+++ b/hw/timer/sifive_pwm.c
@@ -XXX,XX +XXX,XX @@ static void sifive_pwm_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = sifive_pwm_reset;
+    device_class_set_legacy_reset(dc, sifive_pwm_reset);
     device_class_set_props(dc, sifive_pwm_properties);
     dc->vmsd = &vmstate_sifive_pwm;
     dc->realize = sifive_pwm_realize;
diff --git a/hw/timer/slavio_timer.c b/hw/timer/slavio_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/slavio_timer.c
+++ b/hw/timer/slavio_timer.c
@@ -XXX,XX +XXX,XX @@ static void slavio_timer_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = slavio_timer_reset;
+    device_class_set_legacy_reset(dc, slavio_timer_reset);
     dc->vmsd = &vmstate_slavio_timer;
     device_class_set_props(dc, slavio_timer_properties);
 }
diff --git a/hw/timer/sse-counter.c b/hw/timer/sse-counter.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/sse-counter.c
+++ b/hw/timer/sse-counter.c
@@ -XXX,XX +XXX,XX @@ static void sse_counter_class_init(ObjectClass *klass, void *data)
 
     dc->realize = sse_counter_realize;
     dc->vmsd = &sse_counter_vmstate;
-    dc->reset = sse_counter_reset;
+    device_class_set_legacy_reset(dc, sse_counter_reset);
 }
 
 static const TypeInfo sse_counter_info = {
diff --git a/hw/timer/sse-timer.c b/hw/timer/sse-timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/sse-timer.c
+++ b/hw/timer/sse-timer.c
@@ -XXX,XX +XXX,XX @@ static void sse_timer_class_init(ObjectClass *klass, void *data)
 
     dc->realize = sse_timer_realize;
     dc->vmsd = &sse_timer_vmstate;
-    dc->reset = sse_timer_reset;
+    device_class_set_legacy_reset(dc, sse_timer_reset);
     device_class_set_props(dc, sse_timer_properties);
 }
 
diff --git a/hw/timer/stm32f2xx_timer.c b/hw/timer/stm32f2xx_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/stm32f2xx_timer.c
+++ b/hw/timer/stm32f2xx_timer.c
@@ -XXX,XX +XXX,XX @@ static void stm32f2xx_timer_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = stm32f2xx_timer_reset;
+    device_class_set_legacy_reset(dc, stm32f2xx_timer_reset);
     device_class_set_props(dc, stm32f2xx_timer_properties);
     dc->vmsd = &vmstate_stm32f2xx_timer;
     dc->realize = stm32f2xx_timer_realize;
diff --git a/hw/tpm/tpm_tis_i2c.c b/hw/tpm/tpm_tis_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/tpm/tpm_tis_i2c.c
+++ b/hw/tpm/tpm_tis_i2c.c
@@ -XXX,XX +XXX,XX @@ static void tpm_tis_i2c_class_init(ObjectClass *klass, void *data)
     TPMIfClass *tc = TPM_IF_CLASS(klass);
 
     dc->realize = tpm_tis_i2c_realizefn;
-    dc->reset = tpm_tis_i2c_reset;
+    device_class_set_legacy_reset(dc, tpm_tis_i2c_reset);
     dc->vmsd = &vmstate_tpm_tis_i2c;
     device_class_set_props(dc, tpm_tis_i2c_properties);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
diff --git a/hw/tpm/tpm_tis_isa.c b/hw/tpm/tpm_tis_isa.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/tpm/tpm_tis_isa.c
+++ b/hw/tpm/tpm_tis_isa.c
@@ -XXX,XX +XXX,XX @@ static void tpm_tis_isa_class_init(ObjectClass *klass, void *data)
     dc->vmsd  = &vmstate_tpm_tis_isa;
     tc->model = TPM_MODEL_TPM_TIS;
     dc->realize = tpm_tis_isa_realizefn;
-    dc->reset = tpm_tis_isa_reset;
+    device_class_set_legacy_reset(dc, tpm_tis_isa_reset);
     tc->request_completed = tpm_tis_isa_request_completed;
     tc->get_version = tpm_tis_isa_get_tpm_version;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
diff --git a/hw/tpm/tpm_tis_sysbus.c b/hw/tpm/tpm_tis_sysbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/tpm/tpm_tis_sysbus.c
+++ b/hw/tpm/tpm_tis_sysbus.c
@@ -XXX,XX +XXX,XX @@ static void tpm_tis_sysbus_class_init(ObjectClass *klass, void *data)
     tc->model = TPM_MODEL_TPM_TIS;
     dc->realize = tpm_tis_sysbus_realizefn;
     dc->user_creatable = true;
-    dc->reset = tpm_tis_sysbus_reset;
+    device_class_set_legacy_reset(dc, tpm_tis_sysbus_reset);
     tc->request_completed = tpm_tis_sysbus_request_completed;
     tc->get_version = tpm_tis_sysbus_get_tpm_version;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
diff --git a/hw/tricore/tricore_testdevice.c b/hw/tricore/tricore_testdevice.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/tricore/tricore_testdevice.c
+++ b/hw/tricore/tricore_testdevice.c
@@ -XXX,XX +XXX,XX @@ static void tricore_testdevice_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     device_class_set_props(dc, tricore_testdevice_properties);
-    dc->reset = tricore_testdevice_reset;
+    device_class_set_legacy_reset(dc, tricore_testdevice_reset);
 }
 
 static const TypeInfo tricore_testdevice_info = {
diff --git a/hw/usb/hcd-dwc3.c b/hw/usb/hcd-dwc3.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-dwc3.c
+++ b/hw/usb/hcd-dwc3.c
@@ -XXX,XX +XXX,XX @@ static void usb_dwc3_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = usb_dwc3_reset;
+    device_class_set_legacy_reset(dc, usb_dwc3_reset);
     dc->realize = usb_dwc3_realize;
     dc->vmsd = &vmstate_usb_dwc3;
     device_class_set_props(dc, usb_dwc3_properties);
diff --git a/hw/usb/hcd-ehci-pci.c b/hw/usb/hcd-ehci-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-ehci-pci.c
+++ b/hw/usb/hcd-ehci-pci.c
@@ -XXX,XX +XXX,XX @@ static void ehci_class_init(ObjectClass *klass, void *data)
     k->config_write = usb_ehci_pci_write_config;
     dc->vmsd = &vmstate_ehci_pci;
     device_class_set_props(dc, ehci_pci_properties);
-    dc->reset = usb_ehci_pci_reset;
+    device_class_set_legacy_reset(dc, usb_ehci_pci_reset);
 }
 
 static const TypeInfo ehci_pci_type_info = {
diff --git a/hw/usb/hcd-ehci-sysbus.c b/hw/usb/hcd-ehci-sysbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-ehci-sysbus.c
+++ b/hw/usb/hcd-ehci-sysbus.c
@@ -XXX,XX +XXX,XX @@ static void ehci_sysbus_class_init(ObjectClass *klass, void *data)
     dc->realize = usb_ehci_sysbus_realize;
     dc->vmsd = &vmstate_ehci_sysbus;
     device_class_set_props(dc, ehci_sysbus_properties);
-    dc->reset = usb_ehci_sysbus_reset;
+    device_class_set_legacy_reset(dc, usb_ehci_sysbus_reset);
     set_bit(DEVICE_CATEGORY_USB, dc->categories);
 }
 
diff --git a/hw/usb/hcd-ohci-pci.c b/hw/usb/hcd-ohci-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-ohci-pci.c
+++ b/hw/usb/hcd-ohci-pci.c
@@ -XXX,XX +XXX,XX @@ static void ohci_pci_class_init(ObjectClass *klass, void *data)
     device_class_set_props(dc, ohci_pci_properties);
     dc->hotpluggable = false;
     dc->vmsd = &vmstate_ohci;
-    dc->reset = usb_ohci_reset_pci;
+    device_class_set_legacy_reset(dc, usb_ohci_reset_pci);
 }
 
 static const TypeInfo ohci_pci_info = {
diff --git a/hw/usb/hcd-ohci-sysbus.c b/hw/usb/hcd-ohci-sysbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-ohci-sysbus.c
+++ b/hw/usb/hcd-ohci-sysbus.c
@@ -XXX,XX +XXX,XX @@ static void ohci_sysbus_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_USB, dc->categories);
     dc->desc = "OHCI USB Controller";
     device_class_set_props(dc, ohci_sysbus_properties);
-    dc->reset = ohci_sysbus_reset;
+    device_class_set_legacy_reset(dc, ohci_sysbus_reset);
 }
 
 static const TypeInfo ohci_sysbus_types[] = {
diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-uhci.c
+++ b/hw/usb/hcd-uhci.c
@@ -XXX,XX +XXX,XX @@ static void uhci_class_init(ObjectClass *klass, void *data)
 
     k->class_id  = PCI_CLASS_SERIAL_USB;
     dc->vmsd = &vmstate_uhci;
-    dc->reset = uhci_reset;
+    device_class_set_legacy_reset(dc, uhci_reset);
     set_bit(DEVICE_CATEGORY_USB, dc->categories);
 }
 
diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-xhci-pci.c
+++ b/hw/usb/hcd-xhci-pci.c
@@ -XXX,XX +XXX,XX @@ static void xhci_class_init(ObjectClass *klass, void *data)
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset   = xhci_pci_reset;
+    device_class_set_legacy_reset(dc, xhci_pci_reset);
     dc->vmsd    = &vmstate_xhci_pci;
     set_bit(DEVICE_CATEGORY_USB, dc->categories);
     k->realize      = usb_xhci_pci_realize;
diff --git a/hw/usb/hcd-xhci-sysbus.c b/hw/usb/hcd-xhci-sysbus.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-xhci-sysbus.c
+++ b/hw/usb/hcd-xhci-sysbus.c
@@ -XXX,XX +XXX,XX @@ static void xhci_sysbus_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = xhci_sysbus_reset;
+    device_class_set_legacy_reset(dc, xhci_sysbus_reset);
     dc->realize = xhci_sysbus_realize;
     dc->vmsd = &vmstate_xhci_sysbus;
     device_class_set_props(dc, xhci_sysbus_props);
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -XXX,XX +XXX,XX @@ static void xhci_class_init(ObjectClass *klass, void *data)
 
     dc->realize = usb_xhci_realize;
     dc->unrealize = usb_xhci_unrealize;
-    dc->reset   = xhci_reset;
+    device_class_set_legacy_reset(dc, xhci_reset);
     device_class_set_props(dc, xhci_properties);
     dc->user_creatable = false;
 }
diff --git a/hw/usb/imx-usb-phy.c b/hw/usb/imx-usb-phy.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/imx-usb-phy.c
+++ b/hw/usb/imx-usb-phy.c
@@ -XXX,XX +XXX,XX @@ static void imx_usbphy_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
-    dc->reset = imx_usbphy_reset;
+    device_class_set_legacy_reset(dc, imx_usbphy_reset);
     dc->vmsd = &vmstate_imx_usbphy;
     dc->desc = "i.MX USB PHY Module";
     dc->realize = imx_usbphy_realize;
diff --git a/hw/usb/tusb6010.c b/hw/usb/tusb6010.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/usb/tusb6010.c
+++ b/hw/usb/tusb6010.c
@@ -XXX,XX +XXX,XX @@ static void tusb6010_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = tusb6010_realize;
-    dc->reset = tusb6010_reset;
+    device_class_set_legacy_reset(dc, tusb6010_reset);
 }
 
 static const TypeInfo tusb6010_info = {
diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/vfio/ap.c
+++ b/hw/vfio/ap.c
@@ -XXX,XX +XXX,XX @@ static void vfio_ap_class_init(ObjectClass *klass, void *data)
     dc->realize = vfio_ap_realize;
     dc->unrealize = vfio_ap_unrealize;
     dc->hotpluggable = true;
-    dc->reset = vfio_ap_reset;
+    device_class_set_legacy_reset(dc, vfio_ap_reset);
     dc->bus_type = TYPE_AP_BUS;
 }
 
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/vfio/ccw.c
+++ b/hw/vfio/ccw.c
@@ -XXX,XX +XXX,XX @@ static void vfio_ccw_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->realize = vfio_ccw_realize;
     dc->unrealize = vfio_ccw_unrealize;
-    dc->reset = vfio_ccw_reset;
+    device_class_set_legacy_reset(dc, vfio_ccw_reset);
 
     cdc->handle_request = vfio_ccw_handle_request;
     cdc->handle_halt = vfio_ccw_handle_halt;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -XXX,XX +XXX,XX @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
 
-    dc->reset = vfio_pci_reset;
+    device_class_set_legacy_reset(dc, vfio_pci_reset);
     device_class_set_props(dc, vfio_pci_dev_properties);
 #ifdef CONFIG_IOMMUFD
     object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/virtio/virtio-mmio.c
+++ b/hw/virtio/virtio-mmio.c
@@ -XXX,XX +XXX,XX @@ static void virtio_mmio_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = virtio_mmio_realizefn;
-    dc->reset = virtio_mmio_reset;
+    device_class_set_legacy_reset(dc, virtio_mmio_reset);
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     device_class_set_props(dc, virtio_mmio_properties);
 }
diff --git a/hw/watchdog/cmsdk-apb-watchdog.c b/hw/watchdog/cmsdk-apb-watchdog.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/cmsdk-apb-watchdog.c
+++ b/hw/watchdog/cmsdk-apb-watchdog.c
@@ -XXX,XX +XXX,XX @@ static void cmsdk_apb_watchdog_class_init(ObjectClass *klass, void *data)
 
     dc->realize = cmsdk_apb_watchdog_realize;
     dc->vmsd = &cmsdk_apb_watchdog_vmstate;
-    dc->reset = cmsdk_apb_watchdog_reset;
+    device_class_set_legacy_reset(dc, cmsdk_apb_watchdog_reset);
 }
 
 static const TypeInfo cmsdk_apb_watchdog_info = {
diff --git a/hw/watchdog/sbsa_gwdt.c b/hw/watchdog/sbsa_gwdt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/sbsa_gwdt.c
+++ b/hw/watchdog/sbsa_gwdt.c
@@ -XXX,XX +XXX,XX @@ static void wdt_sbsa_gwdt_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = wdt_sbsa_gwdt_realize;
-    dc->reset = wdt_sbsa_gwdt_reset;
+    device_class_set_legacy_reset(dc, wdt_sbsa_gwdt_reset);
     dc->hotpluggable = false;
     set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories);
     dc->vmsd = &vmstate_sbsa_gwdt;
diff --git a/hw/watchdog/wdt_aspeed.c b/hw/watchdog/wdt_aspeed.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/wdt_aspeed.c
+++ b/hw/watchdog/wdt_aspeed.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_wdt_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "ASPEED Watchdog Controller";
     dc->realize = aspeed_wdt_realize;
-    dc->reset = aspeed_wdt_reset;
+    device_class_set_legacy_reset(dc, aspeed_wdt_reset);
     set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories);
     dc->vmsd = &vmstate_aspeed_wdt;
     device_class_set_props(dc, aspeed_wdt_properties);
diff --git a/hw/watchdog/wdt_diag288.c b/hw/watchdog/wdt_diag288.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/wdt_diag288.c
+++ b/hw/watchdog/wdt_diag288.c
@@ -XXX,XX +XXX,XX @@ static void wdt_diag288_class_init(ObjectClass *klass, void *data)
 
     dc->realize = wdt_diag288_realize;
     dc->unrealize = wdt_diag288_unrealize;
-    dc->reset = wdt_diag288_reset;
+    device_class_set_legacy_reset(dc, wdt_diag288_reset);
     dc->hotpluggable = false;
     set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories);
     dc->vmsd = &vmstate_diag288;
diff --git a/hw/watchdog/wdt_i6300esb.c b/hw/watchdog/wdt_i6300esb.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/wdt_i6300esb.c
+++ b/hw/watchdog/wdt_i6300esb.c
@@ -XXX,XX +XXX,XX @@ static void i6300esb_class_init(ObjectClass *klass, void *data)
     k->vendor_id = PCI_VENDOR_ID_INTEL;
     k->device_id = PCI_DEVICE_ID_INTEL_ESB_9;
     k->class_id = PCI_CLASS_SYSTEM_OTHER;
-    dc->reset = i6300esb_reset;
+    device_class_set_legacy_reset(dc, i6300esb_reset);
     dc->vmsd = &vmstate_i6300esb;
     set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories);
     dc->desc = "Intel 6300ESB";
diff --git a/hw/watchdog/wdt_ib700.c b/hw/watchdog/wdt_ib700.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/wdt_ib700.c
+++ b/hw/watchdog/wdt_ib700.c
@@ -XXX,XX +XXX,XX @@ static void wdt_ib700_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = wdt_ib700_realize;
-    dc->reset = wdt_ib700_reset;
+    device_class_set_legacy_reset(dc, wdt_ib700_reset);
     dc->vmsd = &vmstate_ib700;
     set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories);
     dc->desc = "iBASE 700";
diff --git a/hw/watchdog/wdt_imx2.c b/hw/watchdog/wdt_imx2.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/watchdog/wdt_imx2.c
+++ b/hw/watchdog/wdt_imx2.c
@@ -XXX,XX +XXX,XX @@ static void imx2_wdt_class_init(ObjectClass *klass, void *data)
 
     device_class_set_props(dc, imx2_wdt_properties);
     dc->realize = imx2_wdt_realize;
-    dc->reset = imx2_wdt_reset;
+    device_class_set_legacy_reset(dc, imx2_wdt_reset);
     dc->vmsd = &vmstate_imx2_wdt;
     dc->desc = "i.MX2 watchdog timer";
     set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories);
-- 
2.34.1

Rename the DeviceClass::reset field to legacy_reset; this is helpful
both in flagging up that it's best not used in new code and in
making it easy to search for where it's being used still.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240830145812.1967042-9-peter.maydell@linaro.org
---
 include/hw/qdev-core.h | 4 ++--
 hw/core/qdev.c         | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -XXX,XX +XXX,XX @@ struct DeviceClass {
 
     /* callbacks */
     /**
-     * @reset: deprecated device reset method pointer
+     * @legacy_reset: deprecated device reset method pointer
      *
      * Modern code should use the ResettableClass interface to
      * implement a multi-phase reset.
      *
      * TODO: remove once every reset callback is unused
      */
-    DeviceReset reset;
+    DeviceReset legacy_reset;
     DeviceRealize realize;
     DeviceUnrealize unrealize;
 
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -XXX,XX +XXX,XX @@ static void device_transitional_reset(Object *obj)
      * devices) or a device's specific method for not-yet transitioned devices.
      * In both case, it does not reset children.
      */
-    if (dc->reset) {
-        dc->reset(DEVICE(obj));
+    if (dc->legacy_reset) {
+        dc->legacy_reset(DEVICE(obj));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ static void device_transitional_reset(Object *obj)
 static ResettableTrFunction device_get_transitional_reset(Object *obj)
 {
     DeviceClass *dc = DEVICE_GET_CLASS(obj);
-    if (dc->reset != device_phases_reset) {
+    if (dc->legacy_reset != device_phases_reset) {
         /*
          * dc->reset has been overridden by a subclass,
          * the device is not ready for multi phase yet.
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
 
 void device_class_set_legacy_reset(DeviceClass *dc, DeviceReset dev_reset)
 {
-    dc->reset = dev_reset;
+    dc->legacy_reset = dev_reset;
 }
 
 void device_class_set_parent_realize(DeviceClass *dc,
-- 
2.34.1

Currently we have transitional machinery between legacy reset
and three phase reset that works in two directions:
 * if you invoke three phase reset on a device which has set
   the DeviceClass::legacy_reset method, we detect this in
   device_get_transitional_reset() and arrange that we call
   the legacy_reset method during the hold phase of reset
 * if you invoke legacy reset on a device which implements
   three phase reset, the default legacy_reset method is
   device_phases_reset(), which does a three-phase reset
   of the device

However, we have now eliminated all the places which could invoke
legacy reset on a device, which means that the function
device_phases_reset() is never called -- it serves only as the value
of DeviceClass::legacy_reset that indicates that the subclass never
overrode the legacy reset method.  So we can delete it, and instead
check for legacy_reset != NULL.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240830145812.1967042-10-peter.maydell@linaro.org
---
 hw/core/qdev.c | 51 ++++++++++++--------------------------------------
 1 file changed, 12 insertions(+), 39 deletions(-)

diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -XXX,XX +XXX,XX @@ device_vmstate_if_get_id(VMStateIf *obj)
     return qdev_get_dev_path(dev);
 }
 
-/**
- * device_phases_reset:
- * Transition reset method for devices to allow moving
- * smoothly from legacy reset method to multi-phases
- */
-static void device_phases_reset(DeviceState *dev)
-{
-    ResettableClass *rc = RESETTABLE_GET_CLASS(dev);
-
-    if (rc->phases.enter) {
-        rc->phases.enter(OBJECT(dev), RESET_TYPE_COLD);
-    }
-    if (rc->phases.hold) {
-        rc->phases.hold(OBJECT(dev), RESET_TYPE_COLD);
-    }
-    if (rc->phases.exit) {
-        rc->phases.exit(OBJECT(dev), RESET_TYPE_COLD);
-    }
-}
-
 static void device_transitional_reset(Object *obj)
 {
     DeviceClass *dc = DEVICE_GET_CLASS(obj);
 
     /*
-     * This will call either @device_phases_reset (for multi-phases transitioned
-     * devices) or a device's specific method for not-yet transitioned devices.
-     * In both case, it does not reset children.
+     * Device still using DeviceClass legacy_reset method. This doesn't
+     * reset children. device_get_transitional_reset() checked that
+     * this isn't NULL.
      */
-    if (dc->legacy_reset) {
-        dc->legacy_reset(DEVICE(obj));
-    }
+    dc->legacy_reset(DEVICE(obj));
 }
 
 /**
@@ -XXX,XX +XXX,XX @@ static void device_transitional_reset(Object *obj)
 static ResettableTrFunction device_get_transitional_reset(Object *obj)
 {
     DeviceClass *dc = DEVICE_GET_CLASS(obj);
-    if (dc->legacy_reset != device_phases_reset) {
+    if (dc->legacy_reset) {
         /*
          * dc->reset has been overridden by a subclass,
          * the device is not ready for multi phase yet.
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
     rc->child_foreach = device_reset_child_foreach;
 
     /*
-     * @device_phases_reset is put as the default reset method below, allowing
-     * to do the multi-phase transition from base classes to leaf classes. It
-     * allows a legacy-reset Device class to extend a multi-phases-reset
-     * Device class for the following reason:
-     * + If a base class B has been moved to multi-phase, then it does not
-     *   override this default reset method and may have defined phase methods.
-     * + A child class C (extending class B) which uses
-     *   device_class_set_parent_reset() (or similar means) to override the
-     *   reset method will still work as expected. @device_phases_reset function
-     *   will be registered as the parent reset method and effectively call
-     *   parent reset phases.
+     * A NULL legacy_reset implies a three-phase reset device. Devices can
+     * only be reset using three-phase aware mechanisms, but we still support
+     * for transitional purposes leaf classes which set the old legacy_reset
+     * method via device_class_set_legacy_reset(). If they do so, then
+     * device_get_transitional_reset() will notice and arrange for the
+     * DeviceClass::legacy_reset() method to be called during the hold phase.
      */
-    device_class_set_legacy_reset(dc, device_phases_reset);
+    dc->legacy_reset = NULL;
     rc->get_transitional_function = device_get_transitional_reset;
 
     object_class_property_add_bool(class, "realized",
-- 
2.34.1

Now that all devices which still implement a the legacy reset method
register it via device_class_legacy_reset(), we can simplify the
handling of these devices.  Instead of using the complex
Resettable::get_transitional_function machinery, we register a hold
phase method which invokes the DeviceClass::legacy_reset method.

This will allow us to remove all the get_transitional_function
handling from resettable.c.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20240830145812.1967042-11-peter.maydell@linaro.org
---
 hw/core/qdev.c | 55 ++++++++++++++++++++------------------------------
 1 file changed, 22 insertions(+), 33 deletions(-)

diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -XXX,XX +XXX,XX @@ device_vmstate_if_get_id(VMStateIf *obj)
     return qdev_get_dev_path(dev);
 }
 
-static void device_transitional_reset(Object *obj)
-{
-    DeviceClass *dc = DEVICE_GET_CLASS(obj);
-
-    /*
-     * Device still using DeviceClass legacy_reset method. This doesn't
-     * reset children. device_get_transitional_reset() checked that
-     * this isn't NULL.
-     */
-    dc->legacy_reset(DEVICE(obj));
-}
-
-/**
- * device_get_transitional_reset:
- * check if the device's class is ready for multi-phase
- */
-static ResettableTrFunction device_get_transitional_reset(Object *obj)
-{
-    DeviceClass *dc = DEVICE_GET_CLASS(obj);
-    if (dc->legacy_reset) {
-        /*
-         * dc->reset has been overridden by a subclass,
-         * the device is not ready for multi phase yet.
-         */
-        return device_transitional_reset;
-    }
-    return NULL;
-}
-
 static void device_class_init(ObjectClass *class, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(class);
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
      * A NULL legacy_reset implies a three-phase reset device. Devices can
      * only be reset using three-phase aware mechanisms, but we still support
      * for transitional purposes leaf classes which set the old legacy_reset
-     * method via device_class_set_legacy_reset(). If they do so, then
-     * device_get_transitional_reset() will notice and arrange for the
-     * DeviceClass::legacy_reset() method to be called during the hold phase.
+     * method via device_class_set_legacy_reset().
      */
     dc->legacy_reset = NULL;
-    rc->get_transitional_function = device_get_transitional_reset;
 
     object_class_property_add_bool(class, "realized",
                                    device_get_realized, device_set_realized);
@@ -XXX,XX +XXX,XX @@ static void device_class_init(ObjectClass *class, void *data)
                                    offsetof(DeviceState, parent_bus), NULL, 0);
 }
 
+static void do_legacy_reset(Object *obj, ResetType type)
+{
+    DeviceClass *dc = DEVICE_GET_CLASS(obj);
+
+    dc->legacy_reset(DEVICE(obj));
+}
+
 void device_class_set_legacy_reset(DeviceClass *dc, DeviceReset dev_reset)
 {
+    /*
+     * A legacy DeviceClass::reset has identical semantics to the
+     * three-phase "hold" method, with no "enter" or "exit"
+     * behaviour. Classes that use this legacy function must be leaf
+     * classes that do not chain up to their parent class reset.
+     * There is no mechanism for resetting a device that does not
+     * use the three-phase APIs, so the only place which calls
+     * the legacy_reset hook is do_legacy_reset().
+     */
+    ResettableClass *rc = RESETTABLE_CLASS(dc);
+
+    rc->phases.enter = NULL;
+    rc->phases.hold = do_legacy_reset;
+    rc->phases.exit = NULL;
     dc->legacy_reset = dev_reset;
 }
 
-- 
2.34.1

We used to need the transitional_function machinery to handle bus
classes and device classes which still used their legacy reset
handling.  We have now converted all bus classes to three phase
reset, and simplified the device class legacy reset so it is just an
adapting wrapper function around registration of a hold phase method.
There are therefore no more users of the transitional_function
machinery and we can remove it.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20240830145812.1967042-12-peter.maydell@linaro.org
---
 include/hw/resettable.h | 13 -------------
 hw/core/resettable.c    | 24 +++---------------------
 2 files changed, 3 insertions(+), 34 deletions(-)

diff --git a/include/hw/resettable.h b/include/hw/resettable.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/resettable.h
+++ b/include/hw/resettable.h
@@ -XXX,XX +XXX,XX @@ typedef enum ResetType {
  * @get_state: Mandatory method which must return a pointer to a
  * ResettableState.
  *
- * @get_transitional_function: transitional method to handle Resettable objects
- * not yet fully moved to this interface. It will be removed as soon as it is
- * not needed anymore. This method is optional and may return a pointer to a
- * function to be used instead of the phases. If the method exists and returns
- * a non-NULL function pointer then that function is executed as a replacement
- * of the 'hold' phase method taking the object as argument. The two other phase
- * methods are not executed.
- *
  * @child_foreach: Executes a given callback on every Resettable child. Child
  * in this context means a child in the qbus tree, so the children of a qbus
  * are the devices on it, and the children of a device are all the buses it
@@ -XXX,XX +XXX,XX @@ typedef void (*ResettableEnterPhase)(Object *obj, ResetType type);
 typedef void (*ResettableHoldPhase)(Object *obj, ResetType type);
 typedef void (*ResettableExitPhase)(Object *obj, ResetType type);
 typedef ResettableState * (*ResettableGetState)(Object *obj);
-typedef void (*ResettableTrFunction)(Object *obj);
-typedef ResettableTrFunction (*ResettableGetTrFunction)(Object *obj);
 typedef void (*ResettableChildCallback)(Object *, void *opaque,
                                         ResetType type);
 typedef void (*ResettableChildForeach)(Object *obj,
@@ -XXX,XX +XXX,XX @@ struct ResettableClass {
     /* State access method */
     ResettableGetState get_state;
 
-    /* Transitional method for legacy reset compatibility */
-    ResettableGetTrFunction get_transitional_function;
-
     /* Hierarchy handling method */
     ResettableChildForeach child_foreach;
 };
diff --git a/hw/core/resettable.c b/hw/core/resettable.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/core/resettable.c
+++ b/hw/core/resettable.c
@@ -XXX,XX +XXX,XX @@ static void resettable_child_foreach(ResettableClass *rc, Object *obj,
     }
 }
 
-/**
- * resettable_get_tr_func:
- * helper to fetch transitional reset callback if any.
- */
-static ResettableTrFunction resettable_get_tr_func(ResettableClass *rc,
-                                                   Object *obj)
-{
-    ResettableTrFunction tr_func = NULL;
-    if (rc->get_transitional_function) {
-        tr_func = rc->get_transitional_function(obj);
-    }
-    return tr_func;
-}
-
 static void resettable_phase_enter(Object *obj, void *opaque, ResetType type)
 {
     ResettableClass *rc = RESETTABLE_GET_CLASS(obj);
@@ -XXX,XX +XXX,XX @@ static void resettable_phase_enter(Object *obj, void *opaque, ResetType type)
     if (action_needed) {
         trace_resettable_phase_enter_exec(obj, obj_typename, type,
                                           !!rc->phases.enter);
-        if (rc->phases.enter && !resettable_get_tr_func(rc, obj)) {
+        if (rc->phases.enter) {
             rc->phases.enter(obj, type);
         }
         s->hold_phase_pending = true;
@@ -XXX,XX +XXX,XX @@ static void resettable_phase_hold(Object *obj, void *opaque, ResetType type)
     /* exec hold phase */
     if (s->hold_phase_pending) {
         s->hold_phase_pending = false;
-        ResettableTrFunction tr_func = resettable_get_tr_func(rc, obj);
         trace_resettable_phase_hold_exec(obj, obj_typename, !!rc->phases.hold);
-        if (tr_func) {
-            trace_resettable_transitional_function(obj, obj_typename);
-            tr_func(obj);
-        } else if (rc->phases.hold) {
+        if (rc->phases.hold) {
             rc->phases.hold(obj, type);
         }
     }
@@ -XXX,XX +XXX,XX @@ static void resettable_phase_exit(Object *obj, void *opaque, ResetType type)
     assert(s->count > 0);
     if (--s->count == 0) {
         trace_resettable_phase_exit_exec(obj, obj_typename, !!rc->phases.exit);
-        if (rc->phases.exit && !resettable_get_tr_func(rc, obj)) {
+        if (rc->phases.exit) {
             rc->phases.exit(obj, type);
         }
     }
-- 
2.34.1

From: Johannes Stoelp <johannes.stoelp@googlemail.com>

Change the data type of the ioctl _request_ argument from 'int' to
'unsigned long' for the various accel/kvm functions which are
essentially wrappers around the ioctl() syscall.

The correct type for ioctl()'s 'request' argument is confused:
 * POSIX defines the request argument as 'int'
 * glibc uses 'unsigned long' in the prototype in sys/ioctl.h
 * the glibc info documentation uses 'int'
 * the Linux manpage uses 'unsigned long'
 * the Linux implementation of the syscall uses 'unsigned int'

If we wrap ioctl() with another function which uses 'int' as the
type for the request argument, then requests with the 0x8000_0000
bit set will be sign-extended when the 'int' is cast to
'unsigned long' for the call to ioctl().

On x86_64 one such example is the KVM_IRQ_LINE_STATUS request.
Bit requests with the _IOC_READ direction bit set, will have the high
bit set.

Fortunately the Linux Kernel truncates the upper 32bit of the request
on 64bit machines (because it uses 'unsigned int', and see also Linus
Torvalds' comments in
  https://sourceware.org/bugzilla/show_bug.cgi?id=14362 )
so this doesn't cause active problems for us.  However it is more
consistent to follow the glibc ioctl() prototype when we define
functions that are essentially wrappers around ioctl().

This resolves a Coverity issue where it points out that in
kvm_get_xsave() we assign a value (KVM_GET_XSAVE or KVM_GET_XSAVE2)
to an 'int' variable which can't hold it without overflow.

Resolves: Coverity CID 1547759
Signed-off-by: Johannes Stoelp <johannes.stoelp@gmail.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 20240815122747.3053871-1-peter.maydell@linaro.org
[PMM: Rebased patch, adjusted commit message, included note about
 Coverity fix, updated the type of the local var in kvm_get_xsave,
 updated the comment in the KVMState struct definition]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/sysemu/kvm.h     |  8 ++++----
 include/sysemu/kvm_int.h | 17 +++++++++++++----
 accel/kvm/kvm-all.c      |  8 ++++----
 target/i386/kvm/kvm.c    |  3 ++-
 accel/kvm/trace-events   |  8 ++++----
 5 files changed, 27 insertions(+), 17 deletions(-)

diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -XXX,XX +XXX,XX @@ static inline int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_t
 
 /* internal API */
 
-int kvm_ioctl(KVMState *s, int type, ...);
+int kvm_ioctl(KVMState *s, unsigned long type, ...);
 
-int kvm_vm_ioctl(KVMState *s, int type, ...);
+int kvm_vm_ioctl(KVMState *s, unsigned long type, ...);
 
-int kvm_vcpu_ioctl(CPUState *cpu, int type, ...);
+int kvm_vcpu_ioctl(CPUState *cpu, unsigned long type, ...);
 
 /**
  * kvm_device_ioctl - call an ioctl on a kvm device
@@ -XXX,XX +XXX,XX @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...);
  *
  * Returns: -errno on error, nonnegative on success
  */
-int kvm_device_ioctl(int fd, int type, ...);
+int kvm_device_ioctl(int fd, unsigned long type, ...);
 
 /**
  * kvm_vm_check_attr - check for existence of a specific vm attribute
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -XXX,XX +XXX,XX @@ struct KVMState
     bool sync_mmu;
     bool guest_state_protected;
     uint64_t manual_dirty_log_protect;
-    /* The man page (and posix) say ioctl numbers are signed int, but
-     * they're not.  Linux, glibc and *BSD all treat ioctl numbers as
-     * unsigned, and treating them as signed here can break things */
-    unsigned irq_set_ioctl;
+    /*
+     * Older POSIX says that ioctl numbers are signed int, but in
+     * practice they are not. (Newer POSIX doesn't specify ioctl
+     * at all.) Linux, glibc and *BSD all treat ioctl numbers as
+     * unsigned, and real-world ioctl values like KVM_GET_XSAVE have
+     * bit 31 set, which means that passing them via an 'int' will
+     * result in sign-extension when they get converted back to the
+     * 'unsigned long' which the ioctl() prototype uses. Luckily Linux
+     * always treats the argument as an unsigned 32-bit int, so any
+     * possible sign-extension is deliberately ignored, but for
+     * consistency we keep to the same type that glibc is using.
+     */
+    unsigned long irq_set_ioctl;
     unsigned int sigmask_len;
     GHashTable *gsimap;
 #ifdef KVM_CAP_IRQ_ROUTING
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -XXX,XX +XXX,XX @@ int kvm_cpu_exec(CPUState *cpu)
     return ret;
 }
 
-int kvm_ioctl(KVMState *s, int type, ...)
+int kvm_ioctl(KVMState *s, unsigned long type, ...)
 {
     int ret;
     void *arg;
@@ -XXX,XX +XXX,XX @@ int kvm_ioctl(KVMState *s, int type, ...)
     return ret;
 }
 
-int kvm_vm_ioctl(KVMState *s, int type, ...)
+int kvm_vm_ioctl(KVMState *s, unsigned long type, ...)
 {
     int ret;
     void *arg;
@@ -XXX,XX +XXX,XX @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
     return ret;
 }
 
-int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
+int kvm_vcpu_ioctl(CPUState *cpu, unsigned long type, ...)
 {
     int ret;
     void *arg;
@@ -XXX,XX +XXX,XX @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
     return ret;
 }
 
-int kvm_device_ioctl(int fd, int type, ...)
+int kvm_device_ioctl(int fd, unsigned long type, ...)
 {
     int ret;
     void *arg;
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -XXX,XX +XXX,XX @@ static int kvm_get_xsave(X86CPU *cpu)
 {
     CPUX86State *env = &cpu->env;
     void *xsave = env->xsave_buf;
-    int type, ret;
+    unsigned long type;
+    int ret;
 
     type = has_xsave2 ? KVM_GET_XSAVE2 : KVM_GET_XSAVE;
     ret = kvm_vcpu_ioctl(CPU(cpu), type, xsave);
diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/accel/kvm/trace-events
+++ b/accel/kvm/trace-events
@@ -XXX,XX +XXX,XX @@
 # See docs/devel/tracing.rst for syntax documentation.
 
 # kvm-all.c
-kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-kvm_vm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-kvm_vcpu_ioctl(int cpu_index, int type, void *arg) "cpu_index %d, type 0x%x, arg %p"
+kvm_ioctl(unsigned long type, void *arg) "type 0x%lx, arg %p"
+kvm_vm_ioctl(unsigned long type, void *arg) "type 0x%lx, arg %p"
+kvm_vcpu_ioctl(int cpu_index, unsigned long type, void *arg) "cpu_index %d, type 0x%lx, arg %p"
 kvm_run_exit(int cpu_index, uint32_t reason) "cpu_index %d, reason %d"
-kvm_device_ioctl(int fd, int type, void *arg) "dev fd %d, type 0x%x, arg %p"
+kvm_device_ioctl(int fd, unsigned long type, void *arg) "dev fd %d, type 0x%lx, arg %p"
 kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s"
 kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s"
 kvm_init_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
-- 
2.34.1

From: Danny Canter <danny_canter@apple.com>

This addition will be necessary for some HVF related work to follow.
For HVF on ARM there exists a set of APIs in macOS 13 to be able to
adjust the IPA size for a given VM. This is useful as by default HVF
uses 36 bits as the IPA size, so to support guests with > 64GB of RAM
we'll need to reach for this.

To have all the info necessary to carry this out however, we need some
plumbing to be able to grab the memory map and compute the highest GPA
prior to creating the VM. This is almost exactly like what kvm_type is
used for on ARM today, and is also what this will be used for. We will
compute the highest GPA and find what IPA size we'd need to satisfy this,
and if it's valid (macOS today caps at 40b) we'll set this to be the IPA
size in coming patches. This new method is only needed (today at least)
on ARM, and obviously only for HVF/macOS, so admittedly it is much less
generic than kvm_type today, but it seemed a somewhat sane way to get
the information we need from the memmap at VM creation time.

Signed-off-by: Danny Canter <danny_canter@apple.com>
Message-id: 20240828111552.93482-2-danny_canter@apple.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
[PMM: removed explicit setting of field to NULL on x86]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/hw/boards.h | 5 +++++
 hw/arm/virt.c       | 9 ++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/hw/boards.h b/include/hw/boards.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -XXX,XX +XXX,XX @@ typedef struct {
  *    Return the type of KVM corresponding to the kvm-type string option or
  *    computed based on other criteria such as the host kernel capabilities.
  *    kvm-type may be NULL if it is not needed.
+ * @hvf_get_physical_address_range:
+ *    Returns the physical address range in bits to use for the HVF virtual
+ *    machine based on the current boards memory map. This may be NULL if it
+ *    is not needed.
  * @numa_mem_supported:
  *    true if '--numa node.mem' option is supported and false otherwise
  * @hotplug_allowed:
@@ -XXX,XX +XXX,XX @@ struct MachineClass {
     void (*reset)(MachineState *state, ShutdownCause reason);
     void (*wakeup)(MachineState *state);
     int (*kvm_type)(MachineState *machine, const char *arg);
+    int (*hvf_get_physical_address_range)(MachineState *machine);
 
     BlockInterfaceType block_default_type;
     int units_per_default_bus;
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine)
 
     /*
      * In accelerated mode, the memory map is computed earlier in kvm_type()
-     * to create a VM with the right number of IPA bits.
+     * for Linux, or hvf_get_physical_address_range() for macOS to create a
+     * VM with the right number of IPA bits.
      */
     if (!vms->memmap) {
         Object *cpuobj;
@@ -XXX,XX +XXX,XX @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
     return fixed_ipa ? 0 : requested_pa_size;
 }
 
+static int virt_hvf_get_physical_address_range(MachineState *ms)
+{
+    return 0;
+}
+
 static void virt_machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
@@ -XXX,XX +XXX,XX @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     mc->valid_cpu_types = valid_cpu_types;
     mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
     mc->kvm_type = virt_kvm_type;
+    mc->hvf_get_physical_address_range = virt_hvf_get_physical_address_range;
     assert(!mc->get_hotplug_handler);
     mc->get_hotplug_handler = virt_machine_get_hotplug_handler;
     hc->pre_plug = virt_machine_device_pre_plug_cb;
-- 
2.34.1

From: Danny Canter <danny_canter@apple.com>

This is preliminary work to split up hv_vm_create
logic per platform so we can support creating VMs
with > 64GB of RAM on Apple Silicon machines. This
is done via ARM HVF's hv_vm_config_create() (and
other APIs that modify this config that will be
coming in future patches). This should have no
behavioral difference at all as hv_vm_config_create()
just assigns the same default values as if you just
passed NULL to the function.

Signed-off-by: Danny Canter <danny_canter@apple.com>
Message-id: 20240828111552.93482-3-danny_canter@apple.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/sysemu/hvf_int.h  | 1 +
 accel/hvf/hvf-accel-ops.c | 6 +-----
 target/arm/hvf/hvf.c      | 9 +++++++++
 target/i386/hvf/hvf.c     | 5 +++++
 4 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/hvf_int.h
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@ void assert_hvf_ok_impl(hv_return_t ret, const char *file, unsigned int line,
 #define assert_hvf_ok(EX) assert_hvf_ok_impl((EX), __FILE__, __LINE__, #EX)
 const char *hvf_return_string(hv_return_t ret);
 int hvf_arch_init(void);
+hv_return_t hvf_arch_vm_create(MachineState *ms, uint32_t pa_range);
 int hvf_arch_init_vcpu(CPUState *cpu);
 void hvf_arch_vcpu_destroy(CPUState *cpu);
 int hvf_vcpu_exec(CPUState *);
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@
 
 HVFState *hvf_state;
 
-#ifdef __aarch64__
-#define HV_VM_DEFAULT NULL
-#endif
-
 /* Memory slots */
 
 hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size)
@@ -XXX,XX +XXX,XX @@ static int hvf_accel_init(MachineState *ms)
     hv_return_t ret;
     HVFState *s;
 
-    ret = hv_vm_create(HV_VM_DEFAULT);
+    ret = hvf_arch_vm_create(ms, 0);
     assert_hvf_ok(ret);
 
     s = g_new0(HVFState, 1);
diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/hvf/hvf.c
+++ b/target/arm/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@ void hvf_arch_vcpu_destroy(CPUState *cpu)
 {
 }
 
+hv_return_t hvf_arch_vm_create(MachineState *ms, uint32_t pa_range)
+{
+    hv_vm_config_t config = hv_vm_config_create();
+    hv_return_t ret = hv_vm_create(config);
+    os_release(config);
+
+    return ret;
+}
+
 int hvf_arch_init_vcpu(CPUState *cpu)
 {
     ARMCPU *arm_cpu = ARM_CPU(cpu);
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@ int hvf_arch_init(void)
     return 0;
 }
 
+hv_return_t hvf_arch_vm_create(MachineState *ms, uint32_t pa_range)
+{
+    return hv_vm_create(HV_VM_DEFAULT);
+}
+
 int hvf_arch_init_vcpu(CPUState *cpu)
 {
     X86CPU *x86cpu = X86_CPU(cpu);
-- 
2.34.1

From: Danny Canter <danny_canter@apple.com>

This patch's main focus is to use the previously added
hvf_get_physical_address_range to inform VM creation
about the IPA size we need for the VM, so we can extend
the default 36b IPA size and support VMs with 64+GB of
RAM. This is done by freezing the memory map, computing
the highest GPA and then (depending on if the platform
supports an IPA size that large) telling the kernel to
use a size >= for the VM. In pursuit of this a couple of
things related to how we handle the physical address range
we expose to guests were altered, but for an explanation of
what we were doing:

Today, to get the IPA size we were reading id_aa64mmfr0_el1's
PARange field from a newly made vcpu. Unfortunately, HVF just
returns the hosts PARange directly for the initial value and
not the IPA size that will actually back the VM, so we believe
we have much more address space than we actually do today it seems.

Starting in macOS 13.0 some APIs were introduced to be able to
query the maximum IPA size the kernel supports, and to set the IPA
size for a given VM. However, this still has a couple of issues
on < macOS 15. Up until macOS 15 (and if the hardware supported
it) the max IPA size was 39 bits which is not a valid PARange
value, so we can't clamp down what we advertise in the vcpu's
id_aa64mmfr0_el1 to our IPA size. Starting in macOS 15 however,
the maximum IPA size is 40 bits (if it's supported in the hardware
as well) which is also a valid PARange value so we can set our IPA
size to the maximum as well as clamp down the PARange we advertise
to the guest. This allows VMs with 64+ GB of RAM and should fix the
oddness of the PARange situation as well.

Signed-off-by: Danny Canter <danny_canter@apple.com>
Message-id: 20240828111552.93482-4-danny_canter@apple.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/hvf_arm.h      | 19 +++++++++++++
 target/arm/internals.h    | 19 +++++++++++++
 accel/hvf/hvf-accel-ops.c | 12 ++++++++-
 hw/arm/virt.c             | 31 +++++++++++++++++++++-
 target/arm/hvf/hvf.c      | 56 ++++++++++++++++++++++++++++++++++++++-
 target/arm/ptw.c          | 15 +++++++++++
 6 files changed, 149 insertions(+), 3 deletions(-)

diff --git a/target/arm/hvf_arm.h b/target/arm/hvf_arm.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/hvf_arm.h
+++ b/target/arm/hvf_arm.h
@@ -XXX,XX +XXX,XX @@ void hvf_arm_init_debug(void);
 
 void hvf_arm_set_cpu_features_from_host(ARMCPU *cpu);
 
+#ifdef CONFIG_HVF
+
+uint32_t hvf_arm_get_default_ipa_bit_size(void);
+uint32_t hvf_arm_get_max_ipa_bit_size(void);
+
+#else
+
+static inline uint32_t hvf_arm_get_default_ipa_bit_size(void)
+{
+    return 0;
+}
+
+static inline uint32_t hvf_arm_get_max_ipa_bit_size(void)
+{
+    return 0;
+}
+
+#endif
+
 #endif
diff --git a/target/arm/internals.h b/target/arm/internals.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -XXX,XX +XXX,XX @@ static inline void update_spsel(CPUARMState *env, uint32_t imm)
  */
 unsigned int arm_pamax(ARMCPU *cpu);
 
+/*
+ * round_down_to_parange_index
+ * @bit_size: uint8_t
+ *
+ * Rounds down the bit_size supplied to the first supported ARM physical
+ * address range and returns the index for this. The index is intended to
+ * be used to set ID_AA64MMFR0_EL1's PARANGE bits.
+ */
+uint8_t round_down_to_parange_index(uint8_t bit_size);
+
+/*
+ * round_down_to_parange_bit_size
+ * @bit_size: uint8_t
+ *
+ * Rounds down the bit_size supplied to the first supported ARM physical
+ * address range bit size and returns this.
+ */
+uint8_t round_down_to_parange_bit_size(uint8_t bit_size);
+
 /* Return true if extended addresses are enabled.
  * This is always the case if our translation regime is 64 bit,
  * but depends on TTBCR.EAE for 32 bit.
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@
 #include "exec/address-spaces.h"
 #include "exec/exec-all.h"
 #include "gdbstub/enums.h"
+#include "hw/boards.h"
 #include "sysemu/cpus.h"
 #include "sysemu/hvf.h"
 #include "sysemu/hvf_int.h"
@@ -XXX,XX +XXX,XX @@ static int hvf_accel_init(MachineState *ms)
     int x;
     hv_return_t ret;
     HVFState *s;
+    int pa_range = 36;
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
 
-    ret = hvf_arch_vm_create(ms, 0);
+    if (mc->hvf_get_physical_address_range) {
+        pa_range = mc->hvf_get_physical_address_range(ms);
+        if (pa_range < 0) {
+            return -EINVAL;
+        }
+    }
+
+    ret = hvf_arch_vm_create(ms, (uint32_t)pa_range);
     assert_hvf_ok(ret);
 
     s = g_new0(HVFState, 1);
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/intc/arm_gicv3_its_common.h"
 #include "hw/irq.h"
 #include "kvm_arm.h"
+#include "hvf_arm.h"
 #include "hw/firmware/smbios.h"
 #include "qapi/visitor.h"
 #include "qapi/qapi-visit-common.h"
@@ -XXX,XX +XXX,XX @@ static int virt_kvm_type(MachineState *ms, const char *type_str)
 
 static int virt_hvf_get_physical_address_range(MachineState *ms)
 {
-    return 0;
+    VirtMachineState *vms = VIRT_MACHINE(ms);
+
+    int default_ipa_size = hvf_arm_get_default_ipa_bit_size();
+    int max_ipa_size = hvf_arm_get_max_ipa_bit_size();
+
+    /* We freeze the memory map to compute the highest gpa */
+    virt_set_memmap(vms, max_ipa_size);
+
+    int requested_ipa_size = 64 - clz64(vms->highest_gpa);
+
+    /*
+     * If we're <= the default IPA size just use the default.
+     * If we're above the default but below the maximum, round up to
+     * the maximum. hvf_arm_get_max_ipa_bit_size() conveniently only
+     * returns values that are valid ARM PARange values.
+     */
+    if (requested_ipa_size <= default_ipa_size) {
+        requested_ipa_size = default_ipa_size;
+    } else if (requested_ipa_size <= max_ipa_size) {
+        requested_ipa_size = max_ipa_size;
+    } else {
+        error_report("-m and ,maxmem option values "
+                     "require an IPA range (%d bits) larger than "
+                     "the one supported by the host (%d bits)",
+                     requested_ipa_size, max_ipa_size);
+        return -1;
+    }
+
+    return requested_ipa_size;
 }
 
 static void virt_machine_class_init(ObjectClass *oc, void *data)
diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/hvf/hvf.c
+++ b/target/arm/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@
 #include <mach/mach_time.h>
 
 #include "exec/address-spaces.h"
+#include "hw/boards.h"
 #include "hw/irq.h"
 #include "qemu/main-loop.h"
 #include "sysemu/cpus.h"
@@ -XXX,XX +XXX,XX @@ void hvf_arm_init_debug(void)
 
 static void hvf_wfi(CPUState *cpu);
 
+static uint32_t chosen_ipa_bit_size;
+
 typedef struct HVFVTimer {
     /* Vtimer value during migration and paused state */
     uint64_t vtimer_val;
@@ -XXX,XX +XXX,XX @@ static uint64_t hvf_get_reg(CPUState *cpu, int rt)
     return val;
 }
 
+static void clamp_id_aa64mmfr0_parange_to_ipa_size(uint64_t *id_aa64mmfr0)
+{
+    uint32_t ipa_size = chosen_ipa_bit_size ?
+            chosen_ipa_bit_size : hvf_arm_get_max_ipa_bit_size();
+
+    /* Clamp down the PARange to the IPA size the kernel supports. */
+    uint8_t index = round_down_to_parange_index(ipa_size);
+    *id_aa64mmfr0 = (*id_aa64mmfr0 & ~R_ID_AA64MMFR0_PARANGE_MASK) | index;
+}
+
 static bool hvf_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
 {
     ARMISARegisters host_isar = {};
@@ -XXX,XX +XXX,XX @@ static bool hvf_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
     r |= hv_vcpu_get_sys_reg(fd, HV_SYS_REG_MIDR_EL1, &ahcf->midr);
     r |= hv_vcpu_destroy(fd);
 
+    clamp_id_aa64mmfr0_parange_to_ipa_size(&host_isar.id_aa64mmfr0);
+
     ahcf->isar = host_isar;
 
     /*
@@ -XXX,XX +XXX,XX @@ static bool hvf_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
     return r == HV_SUCCESS;
 }
 
+uint32_t hvf_arm_get_default_ipa_bit_size(void)
+{
+    uint32_t default_ipa_size;
+    hv_return_t ret = hv_vm_config_get_default_ipa_size(&default_ipa_size);
+    assert_hvf_ok(ret);
+
+    return default_ipa_size;
+}
+
+uint32_t hvf_arm_get_max_ipa_bit_size(void)
+{
+    uint32_t max_ipa_size;
+    hv_return_t ret = hv_vm_config_get_max_ipa_size(&max_ipa_size);
+    assert_hvf_ok(ret);
+
+    /*
+     * We clamp any IPA size we want to back the VM with to a valid PARange
+     * value so the guest doesn't try and map memory outside of the valid range.
+     * This logic just clamps the passed in IPA bit size to the first valid
+     * PARange value <= to it.
+     */
+    return round_down_to_parange_bit_size(max_ipa_size);
+}
+
 void hvf_arm_set_cpu_features_from_host(ARMCPU *cpu)
 {
     if (!arm_host_cpu_features.dtb_compatible) {
@@ -XXX,XX +XXX,XX @@ void hvf_arch_vcpu_destroy(CPUState *cpu)
 
 hv_return_t hvf_arch_vm_create(MachineState *ms, uint32_t pa_range)
 {
+    hv_return_t ret;
     hv_vm_config_t config = hv_vm_config_create();
-    hv_return_t ret = hv_vm_create(config);
+
+    ret = hv_vm_config_set_ipa_size(config, pa_range);
+    if (ret != HV_SUCCESS) {
+        goto cleanup;
+    }
+    chosen_ipa_bit_size = pa_range;
+
+    ret = hv_vm_create(config);
+
+cleanup:
     os_release(config);
 
     return ret;
@@ -XXX,XX +XXX,XX @@ int hvf_arch_init_vcpu(CPUState *cpu)
                               &arm_cpu->isar.id_aa64mmfr0);
     assert_hvf_ok(ret);
 
+    clamp_id_aa64mmfr0_parange_to_ipa_size(&arm_cpu->isar.id_aa64mmfr0);
+    ret = hv_vcpu_set_sys_reg(cpu->accel->fd, HV_SYS_REG_ID_AA64MMFR0_EL1,
+                              arm_cpu->isar.id_aa64mmfr0);
+    assert_hvf_ok(ret);
+
     return 0;
 }
 
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -XXX,XX +XXX,XX @@ static const uint8_t pamax_map[] = {
     [6] = 52,
 };
 
+uint8_t round_down_to_parange_index(uint8_t bit_size)
+{
+    for (int i = ARRAY_SIZE(pamax_map) - 1; i >= 0; i--) {
+        if (pamax_map[i] <= bit_size) {
+            return i;
+        }
+    }
+    g_assert_not_reached();
+}
+
+uint8_t round_down_to_parange_bit_size(uint8_t bit_size)
+{
+    return pamax_map[round_down_to_parange_index(bit_size)];
+}
+
 /*
  * The cpu-specific constant value of PAMax; also used by hw/arm/virt.
  * Note that machvirt_init calls this on a CPU that is inited but not realized!
-- 
2.34.1

From: Alireza Sanaee <alireza.sanaee@huawei.com>

This patch allows for easier manipulation of the cache description
register, CCSIDR. Which is helpful for testing as well. Currently,
numbers get hard-coded and might be prone to errors.

Therefore, this patch adds a wrapper for different types of CPUs
available in tcg to decribe caches. One function `make_ccsidr` supports
two cases by carrying a parameter as FORMAT that can be LEGACY and
CCIDX which determines the specification of the register.

For CCSIDR register, 32 bit version follows specification [1].
Conversely, 64 bit version follows specification [2].

[1] B4.1.19, ARM Architecture Reference Manual ARMv7-A and ARMv7-R
edition, https://developer.arm.com/documentation/ddi0406
[2] D23.2.29, ARM Architecture Reference Manual for A-profile Architecture,
https://developer.arm.com/documentation/ddi0487/latest/

Signed-off-by: Alireza Sanaee <alireza.sanaee@huawei.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20240903144550.280-1-alireza.sanaee@huawei.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu-features.h |  50 ++++++++++++++++++
 target/arm/cpu64.c        |  19 ++++---
 target/arm/tcg/cpu64.c    | 108 +++++++++++++++++++-------------------
 3 files changed, 117 insertions(+), 60 deletions(-)

diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -XXX,XX +XXX,XX @@
 #define TARGET_ARM_FEATURES_H
 
 #include "hw/registerfields.h"
+#include "qemu/host-utils.h"
 
 /*
  * Naming convention for isar_feature functions:
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_any_evt(const ARMISARegisters *id)
     return isar_feature_aa64_evt(id) || isar_feature_aa32_evt(id);
 }
 
+typedef enum {
+    CCSIDR_FORMAT_LEGACY,
+    CCSIDR_FORMAT_CCIDX,
+} CCSIDRFormat;
+
+static inline uint64_t make_ccsidr(CCSIDRFormat format, unsigned assoc,
+                                   unsigned linesize, unsigned cachesize,
+                                   uint8_t flags)
+{
+    unsigned lg_linesize = ctz32(linesize);
+    unsigned sets;
+    uint64_t ccsidr = 0;
+
+    assert(assoc != 0);
+    assert(is_power_of_2(linesize));
+    assert(lg_linesize >= 4 && lg_linesize <= 7 + 4);
+
+    /* sets * associativity * linesize == cachesize. */
+    sets = cachesize / (assoc * linesize);
+    assert(cachesize % (assoc * linesize) == 0);
+
+    if (format == CCSIDR_FORMAT_LEGACY) {
+        /*
+         * The 32-bit CCSIDR format is:
+         *   [27:13] number of sets - 1
+         *   [12:3]  associativity - 1
+         *   [2:0]   log2(linesize) - 4
+         *           so 0 == 16 bytes, 1 == 32 bytes, 2 == 64 bytes, etc
+         */
+        ccsidr = deposit32(ccsidr, 28,  4, flags);
+        ccsidr = deposit32(ccsidr, 13, 15, sets - 1);
+        ccsidr = deposit32(ccsidr,  3, 10, assoc - 1);
+        ccsidr = deposit32(ccsidr,  0,  3, lg_linesize - 4);
+    } else {
+        /*
+         * The 64-bit CCSIDR_EL1 format is:
+         *   [55:32] number of sets - 1
+         *   [23:3]  associativity - 1
+         *   [2:0]   log2(linesize) - 4
+         *           so 0 == 16 bytes, 1 == 32 bytes, 2 == 64 bytes, etc
+         */
+        ccsidr = deposit64(ccsidr, 32, 24, sets - 1);
+        ccsidr = deposit64(ccsidr,  3, 21, assoc - 1);
+        ccsidr = deposit64(ccsidr,  0,  3, lg_linesize - 4);
+    }
+
+    return ccsidr;
+}
+
 /*
  * Forward to the above feature tests given an ARMCPU pointer.
  */
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@
 #include "cpu.h"
 #include "cpregs.h"
 #include "qemu/module.h"
+#include "qemu/units.h"
 #include "sysemu/kvm.h"
 #include "sysemu/hvf.h"
 #include "sysemu/qtest.h"
@@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj)
     cpu->isar.dbgdevid1 = 0x2;
     cpu->isar.reset_pmcr_el0 = 0x41013000;
     cpu->clidr = 0x0a200023;
-    cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
-    cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */
-    cpu->ccsidr[2] = 0x70ffe07a; /* 2048KB L2 cache */
+    /* 32KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 7);
+    /* 48KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 3, 64, 48 * KiB, 2);
+    /* 2048KB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 16, 64, 2 * MiB, 7);
     cpu->dcz_blocksize = 4; /* 64 bytes */
     cpu->gic_num_lrs = 4;
     cpu->gic_vpribits = 5;
@@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj)
     cpu->isar.dbgdevid1 = 0x1;
     cpu->isar.reset_pmcr_el0 = 0x41033000;
     cpu->clidr = 0x0a200023;
-    cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */
-    cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */
-    cpu->ccsidr[2] = 0x707fe07a; /* 1024KB L2 cache */
+    /* 32KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 7);
+    /* 32KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 1, 64, 32 * KiB, 2);
+    /* 1024KB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 16, 64, 1 * MiB, 7);
     cpu->dcz_blocksize = 4; /* 64 bytes */
     cpu->gic_num_lrs = 4;
     cpu->gic_vpribits = 5;
diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -XXX,XX +XXX,XX @@
 #include "cpu-features.h"
 #include "cpregs.h"
 
-static uint64_t make_ccsidr64(unsigned assoc, unsigned linesize,
-                              unsigned cachesize)
-{
-    unsigned lg_linesize = ctz32(linesize);
-    unsigned sets;
-
-    /*
-     * The 64-bit CCSIDR_EL1 format is:
-     *   [55:32] number of sets - 1
-     *   [23:3]  associativity - 1
-     *   [2:0]   log2(linesize) - 4
-     *           so 0 == 16 bytes, 1 == 32 bytes, 2 == 64 bytes, etc
-     */
-    assert(assoc != 0);
-    assert(is_power_of_2(linesize));
-    assert(lg_linesize >= 4 && lg_linesize <= 7 + 4);
-
-    /* sets * associativity * linesize == cachesize. */
-    sets = cachesize / (assoc * linesize);
-    assert(cachesize % (assoc * linesize) == 0);
-
-    return ((uint64_t)(sets - 1) << 32)
-         | ((assoc - 1) << 3)
-         | (lg_linesize - 4);
-}
-
 static void aarch64_a35_initfn(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
@@ -XXX,XX +XXX,XX @@ static void aarch64_a35_initfn(Object *obj)
     cpu->isar.reset_pmcr_el0 = 0x410a3000;
 
     /* From B2.29 Cache ID registers */
-    cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */
-    cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */
-    cpu->ccsidr[2] = 0x703fe03a; /* 512KB L2 cache */
+    /* 32KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 7);
+    /* 32KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 2);
+    /* 512KB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 16, 64, 512 * KiB, 7);
 
     /* From B3.5 VGIC Type register */
     cpu->gic_num_lrs = 4;
@@ -XXX,XX +XXX,XX @@ static void aarch64_a55_initfn(Object *obj)
     cpu->revidr = 0;
 
     /* From B2.23 CCSIDR_EL1 */
-    cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */
-    cpu->ccsidr[1] = 0x200fe01a; /* 32KB L1 icache */
-    cpu->ccsidr[2] = 0x703fe07a; /* 512KB L2 cache */
+    /* 32KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 7);
+    /* 32KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 2);
+    /* 512KB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 16, 64, 512 * KiB, 7);
 
     /* From B2.96 SCTLR_EL3 */
     cpu->reset_sctlr = 0x30c50838;
@@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj)
     cpu->isar.dbgdevid1 = 0x2;
     cpu->isar.reset_pmcr_el0 = 0x41023000;
     cpu->clidr = 0x0a200023;
-    cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
-    cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */
-    cpu->ccsidr[2] = 0x707fe07a; /* 1MB L2 cache */
+    /* 32KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 32 * KiB, 7);
+    /* 48KB L1 dcache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 3, 64, 48 * KiB, 2);
+    /* 1MB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 16, 64, 1 * MiB, 7);
     cpu->dcz_blocksize = 4; /* 64 bytes */
     cpu->gic_num_lrs = 4;
     cpu->gic_vpribits = 5;
@@ -XXX,XX +XXX,XX @@ static void aarch64_a76_initfn(Object *obj)
     cpu->revidr = 0;
 
     /* From B2.18 CCSIDR_EL1 */
-    cpu->ccsidr[0] = 0x701fe01a; /* 64KB L1 dcache */
-    cpu->ccsidr[1] = 0x201fe01a; /* 64KB L1 icache */
-    cpu->ccsidr[2] = 0x707fe03a; /* 512KB L2 cache */
+    /* 64KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 64 * KiB, 7);
+    /* 64KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 64 * KiB, 2);
+    /* 512KB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 8, 64, 512 * KiB, 7);
 
     /* From B2.93 SCTLR_EL3 */
     cpu->reset_sctlr = 0x30c50838;
@@ -XXX,XX +XXX,XX @@ static void aarch64_a64fx_initfn(Object *obj)
     cpu->isar.id_aa64isar1 = 0x0000000000010001;
     cpu->isar.id_aa64zfr0 = 0x0000000000000000;
     cpu->clidr = 0x0000000080000023;
-    cpu->ccsidr[0] = 0x7007e01c; /* 64KB L1 dcache */
-    cpu->ccsidr[1] = 0x2007e01c; /* 64KB L1 icache */
-    cpu->ccsidr[2] = 0x70ffe07c; /* 8MB L2 cache */
+    /* 64KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 256, 64 * KiB, 7);
+    /* 64KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 256, 64 * KiB, 2);
+    /* 8MB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 16, 256, 8 * MiB, 7);
     cpu->dcz_blocksize = 6; /* 256 bytes */
     cpu->gic_num_lrs = 4;
     cpu->gic_vpribits = 5;
@@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_n1_initfn(Object *obj)
     cpu->revidr = 0;
 
     /* From B2.23 CCSIDR_EL1 */
-    cpu->ccsidr[0] = 0x701fe01a; /* 64KB L1 dcache */
-    cpu->ccsidr[1] = 0x201fe01a; /* 64KB L1 icache */
-    cpu->ccsidr[2] = 0x70ffe03a; /* 1MB L2 cache */
+    /* 64KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 64 * KiB, 7);
+    /* 64KB L1 icache */
+    cpu->ccsidr[1] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 4, 64, 64 * KiB, 2);
+    /* 1MB L2 dcache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_LEGACY, 8, 64, 1 * MiB, 7);
 
     /* From B2.98 SCTLR_EL3 */
     cpu->reset_sctlr = 0x30c50838;
@@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_v1_initfn(Object *obj)
      * L2: 8-way set associative, 64 byte line size, either 512K or 1MB.
      * L3: No L3 (this matches the CLIDR_EL1 value).
      */
-    cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB); /* L1 dcache */
-    cpu->ccsidr[1] = cpu->ccsidr[0];                 /* L1 icache */
-    cpu->ccsidr[2] = make_ccsidr64(8, 64, 1 * MiB);  /* L2 cache */
+    /* 64KB L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_CCIDX, 4, 64, 64 * KiB, 0);
+    /* 64KB L1 icache */
+    cpu->ccsidr[1] = cpu->ccsidr[0];
+    /* 1MB L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_CCIDX, 8, 64, 1 * MiB, 0);
 
     /* From 3.2.115 SCTLR_EL3 */
     cpu->reset_sctlr = 0x30c50838;
@@ -XXX,XX +XXX,XX @@ static void aarch64_a710_initfn(Object *obj)
      * L1: 4-way set associative 64-byte line size, total either 32K or 64K.
      * L2: 8-way set associative 64 byte line size, total either 256K or 512K.
      */
-    cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB);   /* L1 dcache */
-    cpu->ccsidr[1] = cpu->ccsidr[0];                   /* L1 icache */
-    cpu->ccsidr[2] = make_ccsidr64(8, 64, 512 * KiB);  /* L2 cache */
+    /* L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_CCIDX, 4, 64, 64 * KiB, 0);
+    /* L1 icache */
+    cpu->ccsidr[1] = cpu->ccsidr[0];
+    /* L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_CCIDX, 8, 64, 512 * KiB, 0);
 
     /* FIXME: Not documented -- copied from neoverse-v1 */
     cpu->reset_sctlr = 0x30c50838;
@@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_n2_initfn(Object *obj)
      * L1: 4-way set associative 64-byte line size, total 64K.
      * L2: 8-way set associative 64 byte line size, total either 512K or 1024K.
      */
-    cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB);   /* L1 dcache */
-    cpu->ccsidr[1] = cpu->ccsidr[0];                   /* L1 icache */
-    cpu->ccsidr[2] = make_ccsidr64(8, 64, 512 * KiB);  /* L2 cache */
-
+    /* L1 dcache */
+    cpu->ccsidr[0] = make_ccsidr(CCSIDR_FORMAT_CCIDX, 4, 64, 64 * KiB, 0);
+    /* L1 icache */
+    cpu->ccsidr[1] = cpu->ccsidr[0];
+    /* L2 cache */
+    cpu->ccsidr[2] = make_ccsidr(CCSIDR_FORMAT_CCIDX, 8, 64, 512 * KiB, 0);
     /* FIXME: Not documented -- copied from neoverse-v1 */
     cpu->reset_sctlr = 0x30c50838;
 
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

The interrupt level should be 0 or 1. The existing code was using the
interrupt flags to determine the level. In the only machine currently
supported (xlnx-versal-virt), the GICv3 was masking off all bits except
bit 0 when applying it, resulting in the IRQ never being delivered.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com>
Reviewed-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Message-id: 20240827034927.66659-2-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static uint8_t canfd_dlc_array[8] = {8, 12, 16, 20, 24, 32, 48, 64};
 
 static void canfd_update_irq(XlnxVersalCANFDState *s)
 {
-    unsigned int irq = s->regs[R_INTERRUPT_STATUS_REGISTER] &
-                        s->regs[R_INTERRUPT_ENABLE_REGISTER];
+    const bool irq = (s->regs[R_INTERRUPT_STATUS_REGISTER] &
+                      s->regs[R_INTERRUPT_ENABLE_REGISTER]) != 0;
     g_autofree char *path = object_get_canonical_path(OBJECT(s));
 
     /* RX watermark interrupts. */
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

When checking the QEMU_CAN_FRMF_TYPE_FD flag, we need to ignore other
potentially set flags. Before this change, received CAN FD frames from
SocketCAN weren't being recognized as CAN FD.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com>
Message-id: 20240827034927.66659-3-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
 
         dlc = frame->can_dlc;
 
-        if (frame->flags == QEMU_CAN_FRMF_TYPE_FD) {
+        if (frame->flags & QEMU_CAN_FRMF_TYPE_FD) {
             is_canfd_frame = true;
 
             /* Store dlc value in Xilinx specific format. */
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

Previously the emulated CAN ID register was being set to the exact same
value stored in qemu_can_frame.can_id. This doesn't work correctly
because the Xilinx IP core uses a different bit arrangement than
qemu_can_frame for all of its ID registers. Correct this problem for
both RX and TX, including RX filtering.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com>
Acked-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Message-id: 20240827034927.66659-4-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 53 ++++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 3 deletions(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
     uint32_t val = 0;
     uint32_t dlc_reg_val = 0;
     uint32_t dlc_value = 0;
+    uint32_t id_reg_val = 0;
+    bool is_rtr = false;
 
     /* Check that reg_num should be within TX register space. */
     assert(reg_num <= R_TB_ID_REGISTER + (NUM_REGS_PER_MSG_SPACE *
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
     dlc_reg_val = s->regs[reg_num + 1];
     dlc_value = FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, DLC);
 
-    frame->can_id = s->regs[reg_num];
+    id_reg_val = s->regs[reg_num];
+    if (FIELD_EX32(id_reg_val, TB_ID_REGISTER, IDE)) {
+        frame->can_id = (FIELD_EX32(id_reg_val, TB_ID_REGISTER, ID) << 18) |
+                        (FIELD_EX32(id_reg_val, TB_ID_REGISTER, ID_EXT)) |
+                        QEMU_CAN_EFF_FLAG;
+        if (FIELD_EX32(id_reg_val, TB_ID_REGISTER, RTR_RRS)) {
+            is_rtr = true;
+        }
+    } else {
+        frame->can_id = FIELD_EX32(id_reg_val, TB_ID_REGISTER, ID);
+        if (FIELD_EX32(id_reg_val, TB_ID_REGISTER, SRR_RTR_RRS)) {
+            is_rtr = true;
+        }
+    }
 
     if (FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, FDF)) {
         /*
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
         } else {
             frame->can_dlc = dlc_value;
         }
+
+        if (is_rtr) {
+            frame->can_id |= QEMU_CAN_RTR_FLAG;
+        }
     }
 
     for (j = 0; j < frame->can_dlc; j++) {
@@ -XXX,XX +XXX,XX @@ static void process_cancellation_requests(XlnxVersalCANFDState *s)
     canfd_update_irq(s);
 }
 
+static uint32_t frame_to_reg_id(const qemu_can_frame *frame)
+{
+    uint32_t id_reg_val = 0;
+    const bool is_canfd_frame = frame->flags & QEMU_CAN_FRMF_TYPE_FD;
+    const bool is_rtr = !is_canfd_frame && (frame->can_id & QEMU_CAN_RTR_FLAG);
+
+    if (frame->can_id & QEMU_CAN_EFF_FLAG) {
+        id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, ID,
+                                 (frame->can_id & QEMU_CAN_EFF_MASK) >> 18);
+        id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, ID_EXT,
+                                 frame->can_id & QEMU_CAN_EFF_MASK);
+        id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, IDE, 1);
+        id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, SRR_RTR_RRS, 1);
+        if (is_rtr) {
+            id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, RTR_RRS, 1);
+        }
+    } else {
+        id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, ID,
+                                 frame->can_id & QEMU_CAN_SFF_MASK);
+        if (is_rtr) {
+            id_reg_val |= FIELD_DP32(0, RB_ID_REGISTER, SRR_RTR_RRS, 1);
+        }
+    }
+
+    return id_reg_val;
+}
+
 static void store_rx_sequential(XlnxVersalCANFDState *s,
                                 const qemu_can_frame *frame,
                                 uint32_t fill_level, uint32_t read_index,
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
                                                     NUM_REGS_PER_MSG_SPACE));
         }
 
-        s->regs[store_location] = frame->can_id;
+        s->regs[store_location] = frame_to_reg_id(frame);
 
         dlc = frame->can_dlc;
 
@@ -XXX,XX +XXX,XX @@ static void update_rx_sequential(XlnxVersalCANFDState *s,
     if (s->regs[R_ACCEPTANCE_FILTER_CONTROL_REGISTER]) {
         uint32_t acceptance_filter_status =
                                 s->regs[R_ACCEPTANCE_FILTER_CONTROL_REGISTER];
+        const uint32_t reg_id = frame_to_reg_id(frame);
 
         for (i = 0; i < 32; i++) {
             if (acceptance_filter_status & 0x1) {
                 uint32_t msg_id_masked = s->regs[R_AFMR_REGISTER + 2 * i] &
-                                         frame->can_id;
+                                         reg_id;
                 uint32_t afir_id_masked = s->regs[R_AFIR_REGISTER + 2 * i] &
                                           s->regs[R_AFMR_REGISTER + 2 * i];
                 uint16_t std_msg_id_masked = FIELD_EX32(msg_id_masked,
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

Add support for QEMU_CAN_FRMF_ESI and QEMU_CAN_FRMF_BRS flags, and
ensure frame->flags is always initialized to 0.

Note that the Xilinx IP core doesn't allow manually setting the ESI bit
during transmits, so it's only implemented for the receive case.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Message-id: 20240827034927.66659-5-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
     uint32_t id_reg_val = 0;
     bool is_rtr = false;
 
+    frame->flags = 0;
+
     /* Check that reg_num should be within TX register space. */
     assert(reg_num <= R_TB_ID_REGISTER + (NUM_REGS_PER_MSG_SPACE *
                                           s->cfg.tx_fifo));
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
          *  15                         49 - 64
          */
 
-        frame->flags = QEMU_CAN_FRMF_TYPE_FD;
+        frame->flags |= QEMU_CAN_FRMF_TYPE_FD;
 
         if (dlc_value < 8) {
             frame->can_dlc = dlc_value;
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
             assert((dlc_value - 8) < ARRAY_SIZE(canfd_dlc_array));
             frame->can_dlc = canfd_dlc_array[dlc_value - 8];
         }
+
+        if (FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, BRS)) {
+            frame->flags |= QEMU_CAN_FRMF_BRS;
+        }
     } else {
         /*
          * FD Format bit not set that means it is a CAN Frame.
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
                     dlc_reg_val = FIELD_DP32(0, RB_DLC_REGISTER, DLC, 8 + i);
                 }
             }
+
+            if (frame->flags & QEMU_CAN_FRMF_BRS) {
+                dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, BRS, 1);
+            }
+            if (frame->flags & QEMU_CAN_FRMF_ESI) {
+                dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, ESI, 1);
+            }
         } else {
             is_canfd_frame = false;
 
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

The endianness of the CAN data was backwards in each group of 4 bytes.
For example, the following data:

00 11 22 33 44 55 66 77

was showing up like this:

33 22 11 00 77 66 55 44

Fix both the TX and RX code to put the data in the correct order.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com>
Acked-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Message-id: 20240827034927.66659-6-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
     }
 
     for (j = 0; j < frame->can_dlc; j++) {
-        val = 8 * i;
+        val = 8 * (3 - i);
 
         frame->data[j] = extract32(s->regs[reg_num + 2 + (j / 4)], val, 8);
         i++;
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
             case 0:
                 rx_reg_num = i / 4;
 
-                data_reg_val = FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES3,
+                data_reg_val = FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES0,
                                           frame->data[i]);
                 break;
             case 1:
-                data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES2,
-                                           frame->data[i]);
-                break;
-            case 2:
                 data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES1,
                                            frame->data[i]);
                 break;
+            case 2:
+                data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES2,
+                                           frame->data[i]);
+                break;
             case 3:
-                data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES0,
+                data_reg_val |= FIELD_DP32(0, RB_DW0_REGISTER, DATA_BYTES3,
                                            frame->data[i]);
                 /*
                  * Last Bytes data which means we have all 4 bytes ready to
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

Use QEMU's helper functions can_dlc2len() and can_len2dlc() for
translating between the raw DLC value and the SocketCAN length value.
This also has the side effect of correctly handling received CAN FD
frames with a DLC of 0-8, which was broken previously.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com>
Message-id: 20240827034927.66659-7-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 67 ++--------------------------------
 1 file changed, 4 insertions(+), 63 deletions(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ REG32(RB_DW15_REGISTER_1, 0x4144)
     FIELD(RB_DW15_REGISTER_1, DATA_BYTES62, 8, 8)
     FIELD(RB_DW15_REGISTER_1, DATA_BYTES63, 0, 8)
 
-static uint8_t canfd_dlc_array[8] = {8, 12, 16, 20, 24, 32, 48, 64};
-
 static void canfd_update_irq(XlnxVersalCANFDState *s)
 {
     const bool irq = (s->regs[R_INTERRUPT_STATUS_REGISTER] &
@@ -XXX,XX +XXX,XX @@ static void regs2frame(XlnxVersalCANFDState *s, qemu_can_frame *frame,
     }
 
     if (FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, FDF)) {
-        /*
-         * CANFD frame.
-         * Converting dlc(0 to 15) 4 Byte data to plain length(i.e. 0 to 64)
-         * 1 Byte data. This is done to make it work with SocketCAN.
-         * On actual CANFD frame, this value can't be more than 0xF.
-         * Conversion table for DLC to plain length:
-         *
-         *  DLC                        Plain Length
-         *  0 - 8                      0 - 8
-         *  9                          9 - 12
-         *  10                         13 - 16
-         *  11                         17 - 20
-         *  12                         21 - 24
-         *  13                         25 - 32
-         *  14                         33 - 48
-         *  15                         49 - 64
-         */
-
         frame->flags |= QEMU_CAN_FRMF_TYPE_FD;
 
-        if (dlc_value < 8) {
-            frame->can_dlc = dlc_value;
-        } else {
-            assert((dlc_value - 8) < ARRAY_SIZE(canfd_dlc_array));
-            frame->can_dlc = canfd_dlc_array[dlc_value - 8];
-        }
-
         if (FIELD_EX32(dlc_reg_val, TB0_DLC_REGISTER, BRS)) {
             frame->flags |= QEMU_CAN_FRMF_BRS;
         }
     } else {
-        /*
-         * FD Format bit not set that means it is a CAN Frame.
-         * Conversion table for classic CAN:
-         *
-         *  DLC                        Plain Length
-         *  0 - 7                      0 - 7
-         *  8 - 15                     8
-         */
-
-        if (dlc_value > 8) {
-            frame->can_dlc = 8;
-            qemu_log_mask(LOG_GUEST_ERROR, "Maximum DLC value for Classic CAN"
-                          " frame is 8. Only 8 byte data will be sent.\n");
-        } else {
-            frame->can_dlc = dlc_value;
-        }
-
         if (is_rtr) {
             frame->can_id |= QEMU_CAN_RTR_FLAG;
         }
     }
 
+    frame->can_dlc = can_dlc2len(dlc_value);
+
     for (j = 0; j < frame->can_dlc; j++) {
         val = 8 * (3 - i);
 
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
                                 bool rx_fifo_id, uint8_t filter_index)
 {
     int i;
-    bool is_canfd_frame;
     uint8_t dlc = frame->can_dlc;
     uint8_t rx_reg_num = 0;
     uint32_t dlc_reg_val = 0;
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
 
         s->regs[store_location] = frame_to_reg_id(frame);
 
-        dlc = frame->can_dlc;
+        dlc_reg_val = FIELD_DP32(0, RB_DLC_REGISTER, DLC, can_len2dlc(dlc));
 
         if (frame->flags & QEMU_CAN_FRMF_TYPE_FD) {
-            is_canfd_frame = true;
-
-            /* Store dlc value in Xilinx specific format. */
-            for (i = 0; i < ARRAY_SIZE(canfd_dlc_array); i++) {
-                if (canfd_dlc_array[i] == frame->can_dlc) {
-                    dlc_reg_val = FIELD_DP32(0, RB_DLC_REGISTER, DLC, 8 + i);
-                }
-            }
+            dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, FDF, 1);
 
             if (frame->flags & QEMU_CAN_FRMF_BRS) {
                 dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, BRS, 1);
@@ -XXX,XX +XXX,XX @@ static void store_rx_sequential(XlnxVersalCANFDState *s,
             if (frame->flags & QEMU_CAN_FRMF_ESI) {
                 dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, ESI, 1);
             }
-        } else {
-            is_canfd_frame = false;
-
-            if (frame->can_dlc > 8) {
-                dlc = 8;
-            }
-
-            dlc_reg_val = FIELD_DP32(0, RB_DLC_REGISTER, DLC, dlc);
         }
 
-        dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, FDF, is_canfd_frame);
         dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, TIMESTAMP, rx_timestamp);
         dlc_reg_val |= FIELD_DP32(0, RB_DLC_REGISTER, MATCHED_FILTER_INDEX,
                                   filter_index);
-- 
2.34.1

From: Doug Brown <doug@schmorgal.com>

The read index should not be changed when storing a new message into the
RX or TX FIFO. Changing it at this point will cause the reader to get
out of sync. The wrapping of the read index is already handled by the
pre-write functions for the FIFO status registers anyway.

Additionally, the calculation for wrapping the store index was off by
one, which caused new messages to be written to the wrong location in
the FIFO. This caused incorrect messages to be delivered.

Signed-off-by: Doug Brown <doug@schmorgal.com>
Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com>
Message-id: 20240827034927.66659-8-doug@schmorgal.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/net/can/xlnx-versal-canfd.c | 36 +++-------------------------------
 1 file changed, 3 insertions(+), 33 deletions(-)

diff --git a/hw/net/can/xlnx-versal-canfd.c b/hw/net/can/xlnx-versal-canfd.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/net/can/xlnx-versal-canfd.c
+++ b/hw/net/can/xlnx-versal-canfd.c
@@ -XXX,XX +XXX,XX @@ static void update_rx_sequential(XlnxVersalCANFDState *s,
             read_index = ARRAY_FIELD_EX32(s->regs, RX_FIFO_STATUS_REGISTER, RI);
             store_index = read_index + fill_level;
 
-            if (read_index == s->cfg.rx0_fifo - 1) {
-                /*
-                 * When ri is s->cfg.rx0_fifo - 1 i.e. max, it goes cyclic that
-                 * means we reset the ri to 0x0.
-                 */
-                read_index = 0;
-                ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, RI,
-                                 read_index);
-            }
-
             if (store_index > s->cfg.rx0_fifo - 1) {
-                store_index -= s->cfg.rx0_fifo - 1;
+                store_index -= s->cfg.rx0_fifo;
             }
 
             store_location = R_RB_ID_REGISTER +
@@ -XXX,XX +XXX,XX @@ static void update_rx_sequential(XlnxVersalCANFDState *s,
                                           RI_1);
             store_index = read_index + fill_level;
 
-            if (read_index == s->cfg.rx1_fifo - 1) {
-                /*
-                 * When ri is s->cfg.rx1_fifo - 1 i.e. max, it goes cyclic that
-                 * means we reset the ri to 0x0.
-                 */
-                read_index = 0;
-                ARRAY_FIELD_DP32(s->regs, RX_FIFO_STATUS_REGISTER, RI_1,
-                                 read_index);
-            }
-
             if (store_index > s->cfg.rx1_fifo - 1) {
-                store_index -= s->cfg.rx1_fifo - 1;
+                store_index -= s->cfg.rx1_fifo;
             }
 
             store_location = R_RB_ID_REGISTER_1 +
@@ -XXX,XX +XXX,XX @@ static void tx_fifo_stamp(XlnxVersalCANFDState *s, uint32_t tb0_regid)
                           " Discarding the message\n");
             ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXEOFLW, 1);
         } else {
-            if (read_index == s->cfg.tx_fifo - 1) {
-                /*
-                 * When ri is s->cfg.tx_fifo - 1 i.e. max, it goes cyclic that
-                 * means we reset the ri to 0x0.
-                 */
-                read_index = 0;
-                ARRAY_FIELD_DP32(s->regs, TX_EVENT_FIFO_STATUS_REGISTER, TXE_RI,
-                                 read_index);
-            }
-
             if (store_index > s->cfg.tx_fifo - 1) {
-                store_index -= s->cfg.tx_fifo - 1;
+                store_index -= s->cfg.tx_fifo;
             }
 
             assert(store_index < s->cfg.tx_fifo);
-- 
2.34.1

From: Francisco Iglesias <francisco.iglesias@amd.com>

Vikram's email is bouncing, pause his maintainership until a new email is
provided.

Signed-off-by: Francisco Iglesias <francisco.iglesias@amd.com>
Message-id: 20240906181645.40359-2-francisco.iglesias@amd.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: tests/qtest/intel-hda-test.c
 F: tests/qtest/fuzz-sb16-test.c
 
 Xilinx CAN
-M: Vikram Garhwal <vikram.garhwal@amd.com>
 M: Francisco Iglesias <francisco.iglesias@amd.com>
 S: Maintained
 F: hw/net/can/xlnx-*
@@ -XXX,XX +XXX,XX @@ F: include/hw/rx/
 
 CAN bus subsystem and hardware
 M: Pavel Pisa <pisa@cmp.felk.cvut.cz>
-M: Vikram Garhwal <fnu.vikram@xilinx.com>
 S: Maintained
 W: https://canbus.pages.fel.cvut.cz/
 F: net/can/*
-- 
2.34.1

From: Jan Klötzke <jan.kloetzke@kernkonzept.com>

On GICv2 and later, level triggered interrupts are pending when either
the interrupt line is asserted or the interrupt was made pending by a
GICD_ISPENDRn write. Making a level triggered interrupt pending by
software persists until either the interrupt is acknowledged or cleared
by writing GICD_ICPENDRn. As long as the interrupt line is asserted,
the interrupt is pending in any case.

This logic is transparently implemented in gic_test_pending() for
GICv1 and GICv2.  The function combines the "pending" irq_state flag
(used for edge triggered interrupts and software requests) and the
line status (tracked in the "level" field).  However, we also
incorrectly set the pending flag on a guest write to GICD_ISENABLERn
if the line of a level triggered interrupt was asserted.  This keeps
the interrupt pending even if the line is de-asserted after some
time.

This incorrect logic is a leftover of the initial 11MPCore GIC
implementation.  That handles things slightly differently to the
architected GICv1 and GICv2.  The 11MPCore TRM does not give a lot of
detail on the corner cases of its GIC's behaviour, and historically
we have not wanted to investigate exactly what it does in reality, so
QEMU's GIC model takes the approach of "retain our existing behaviour
for 11MPCore, and implement the architectural standard for later GIC
revisions".

On that basis, commit 8d999995e45c10 in 2013 is where we added the
"level-triggered interrupt with the line asserted" handling to
gic_test_pending(), and we deliberately kept the old behaviour of
gic_test_pending() for REV_11MPCORE.  That commit should have added
the "only if 11MPCore" condition to the setting of the pending bit on
writes to GICD_ISENABLERn, but forgot it.

Add the missing "if REV_11MPCORE" condition, so that our behaviour
on GICv1 and GICv2 matches the GIC architecture requirements.

Cc: qemu-stable@nongnu.org
Fixes: 8d999995e45c10 ("arm_gic: Fix GIC pending behavior")
Signed-off-by: Jan Klötzke <jan.kloetzke@kernkonzept.com>
Message-id: 20240911114826.3558302-1-jan.kloetzke@kernkonzept.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
[PMM: expanded comment a little and converted to coding-style form;
 expanded commit message with the historical backstory]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/intc/arm_gic.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/arm_gic.c
+++ b/hw/intc/arm_gic.c
@@ -XXX,XX +XXX,XX @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
                     trace_gic_enable_irq(irq + i);
                 }
                 GIC_DIST_SET_ENABLED(irq + i, cm);
-                /* If a raised level triggered IRQ enabled then mark
-                   is as pending.  */
-                if (GIC_DIST_TEST_LEVEL(irq + i, mask)
+                /*
+                 * If a raised level triggered IRQ enabled then mark
+                 * it as pending on 11MPCore. For other GIC revisions we
+                 * handle the "level triggered and line asserted" check
+                 * at the other end in gic_test_pending().
+                 */
+                if (s->revision == REV_11MPCORE
+                        && GIC_DIST_TEST_LEVEL(irq + i, mask)
                         && !GIC_DIST_TEST_EDGE_TRIGGER(irq + i)) {
                     DPRINTF("Set %d pending mask %x\n", irq + i, mask);
                     GIC_DIST_SET_PENDING(irq + i, mask);
-- 
2.34.1

Hi; here's a target-arm pullreq. Apologies for the size: this is
because it has all RTH's work to enable emulation of SME2p1 and
SVE2p1.

thanks
-- PMM

The following changes since commit c77283dd5d79149f4e7e9edd00f65416c648ee59:

Merge tag 'pull-request-2025-07-02' of https://gitlab.com/thuth/qemu into staging (2025-07-03 06:01:41 -0400)

are available in the Git repository at:

https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20250704

for you to fetch changes up to 083fef73585dfa03f72055ace6de8dec4912d0b0:

linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1 (2025-07-04 15:53:23 +0100)

----------------------------------------------------------------
target-arm queue:
 * Implement emulation of SME2p1 and SVE2p1
 * Correctly enforce alignment checks for v8M loads and
   stores done via helper functions
 * Mark the "highbank" and the "midway" machine as deprecated

----------------------------------------------------------------
Peter Maydell (4):
      target/arm: Rename FMOPA_h to FMOPA_w_h
      target/arm: Rename BFMOPA to BFMOPA_w
      target/arm: Implement FMOPA (non-widening) for fp16
      target/arm: Implement SME2 BFMOPA (non-widening)

Richard Henderson (103):
      target/arm: Fix SME vs AdvSIMD exception priority
      target/arm: Fix sve_access_check for SME
      target/arm: Fix 128-bit element ZIP, UZP, TRN
      target/arm: Replace @rda_rn_rm_e0 in sve.decode
      target/arm: Fix FMMLA (64-bit element) for 128-bit VL
      target/arm: Disable FEAT_F64MM if maximum SVE vector size too small
      target/arm: Fix PSEL size operands to tcg_gen_gvec_ands
      target/arm: Fix f16_dotadd vs nan selection
      target/arm: Fix bfdotadd_ebf vs nan selection
      target/arm: Remove CPUARMState.vfp.scratch
      target/arm: Introduce FPST_ZA, FPST_ZA_F16
      target/arm: Use FPST_ZA for sme_fmopa_[hsd]
      target/arm: Rename zarray to za_state.za
      target/arm: Add isar feature tests for SME2p1, SVE2p1
      target/arm: Add ZT0
      target/arm: Add zt0_excp_el to DisasContext
      target/arm: Implement SME2 ZERO ZT0
      target/arm: Add alignment argument to gen_sve_{ldr, str}
      target/arm: Implement SME2 LDR/STR ZT0
      target/arm: Implement SME2 MOVT
      target/arm: Split get_tile_rowcol argument tile_index
      target/arm: Rename MOVA for translate
      target/arm: Split out get_zarray
      target/arm: Introduce ARMCPU.sme_max_vq
      target/arm: Implement SME2 MOVA to/from tile, multiple registers
      target/arm: Implement SME2 MOVA to/from array, multiple registers
      target/arm: Implement SME2 BMOPA
      target/arm: Implement SME2 SMOPS, UMOPS (2-way)
      target/arm: Introduce gen_gvec_sve2_sqdmulh
      target/arm: Implement SME2 Multiple and Single SVE Destructive
      target/arm: Implement SME2 Multiple Vectors SVE Destructive
      target/arm: Implement SME2 ADD/SUB (array results, multiple and single vector)
      target/arm: Implement SME2 ADD/SUB (array results, multiple vectors)
      target/arm: Pass ZA to helper_sve2_fmlal_zz[zx]w_s
      target/arm: Add helper_gvec{_ah}_bfmlsl{_nx}
      target/arm: Implement SME2 FMLAL, BFMLAL
      target/arm: Implement SME2 FDOT
      target/arm: Implement SME2 BFDOT
      target/arm: Implement SME2 FVDOT, BFVDOT
      target/arm: Rename helper_gvec_*dot_[bh] to *_4[bh]
      target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT
      target/arm: Rename SVE SDOT and UDOT patterns
      target/arm: Tighten USDOT (vectors) decode
      target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1
      target/arm: Implement SME2 SVDOT, UVDOT, SUVDOT, USVDOT
      target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL
      target/arm: Rename gvec_fml[as]_[hs] with _nf_ infix
      target/arm: Implement SME2 FMLA, FMLS
      target/arm: Implement SME2 BFMLA, BFMLS
      target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB
      target/arm: Implement SME2 ADD/SUB (array accumulator)
      target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN
      target/arm: Implement SME2 FCVT (widening), FCVTL
      target/arm: Implement SME2 FCVTZS, FCVTZU
      target/arm: Implement SME2 SCVTF, UCVTF
      target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA
      target/arm: Introduce do_[us]sat_[bhs] macros
      target/arm: Use do_[us]sat_[bhs] in sve_helper.c
      target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU
      target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1
      target/arm: Implement SME2 SUNPK, UUNPK
      target/arm: Implement SME2 ZIP, UZP (four registers)
      target/arm: Move do_urshr, do_srshr to vec_internal.h
      target/arm: Implement SME2 SQRSHR, UQRSHR, SQRSHRN
      target/arm: Implement SME2 ZIP, UZP (two registers)
      target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP
      target/arm: Enable SCLAMP, UCLAMP for SVE2p1
      target/arm: Implement FCLAMP for SME2, SVE2p1
      target/arm: Implement SME2p1 Multiple Zero
      target/arm: Introduce pred_count_test
      target/arm: Fold predtest_ones into helper_sve_brkns
      target/arm: Expand do_zero inline
      target/arm: Split out do_whilel from helper_sve_whilel
      target/arm: Split out do_whileg from helper_sve_whileg
      target/arm: Move scale by esz into helper_sve_while*
      target/arm: Split trans_WHILE to lt and gt
      target/arm: Enable PSEL for SVE2p1
      target/arm: Implement SVE2p1 WHILE (predicate pair)
      target/arm: Implement SVE2p1 WHILE (predicate as counter)
      target/arm: Implement SVE2p1 PTRUE (predicate as counter)
      target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1
      target/arm: Implement SVE2p1 PEXT
      target/arm: Implement SME2 SEL
      target/arm: Implement ANDQV, ORQV, EORQV for SVE2p1
      target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV for SVE2p1
      target/arm: Implement BFMLSLB{L, T} for SME2/SVE2p1
      target/arm: Implement CNTP (predicate as counter) for SME2/SVE2p1
      target/arm: Implement DUPQ for SME2p1/SVE2p1
      target/arm: Implement EXTQ for SME2p1/SVE2p1
      target/arm: Implement PMOV for SME2p1/SVE2p1
      target/arm: Implement ZIPQ, UZPQ for SME2p1/SVE2p1
      target/arm: Implement TBLQ, TBXQ for SME2p1/SVE2p1
      target/arm: Implement SME2 counted predicate register load/store
      target/arm: Split the ST_zpri and ST_zprr patterns
      target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1
      target/arm: Move ld1qq and st1qq primitives to sve_ldst_internal.h
      target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1
      target/arm: Implement LD1Q, ST1Q for SVE2p1
      target/arm: Implement MOVAZ for SME2p1
      target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1
      target/arm: Support FPCR.AH in SME FMOPS, BFMOPS
      target/arm: Enable FEAT_SME2p1 on -cpu max
      linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1

Thomas Huth (1):
      hw/arm/highbank: Mark the "highbank" and the "midway" machine as deprecated

William Kosasih (11):
      target/arm: Bring VLSTM/VLLDM helper store/load closer to the ARM pseudocode
      target/arm: Fix BLXNS helper store alignment checks
      target/arm: Fix function_return helper load alignment checks
      target/arm: Fix VLDR helper load alignment checks
      target/arm: Fix VSTR helper store alignment checks
      target/arm: Fix VLDR_SG helper load alignment checks
      target/arm: Fix VSTR_SG helper store alignment checks
      target/arm: Fix VLD4 helper load alignment checks
      target/arm: Fix VLD2 helper load alignment checks
      target/arm: Fix VST4 helper store alignment checks
      target/arm: Fix VST2 helper store alignment checks

From: Thomas Huth <thuth@redhat.com>

We don't have any automatic regression tests for these machines and
when asking the usual suspects on the mailing list we came to the
conclusion that nobody tests these machines manually, too, so it seems
like this is currently just completely unused code. Mark them as depre-
cated to see whether anybody still speaks up during the deprecation
period, otherwise we can likely remove these two machines in a couple
of releases.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Message-id: 20250702113051.46483-1-thuth@redhat.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
[PMM: tweaked deprecation.rst text]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/about/deprecated.rst | 7 +++++++
 hw/arm/highbank.c         | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/about/deprecated.rst
+++ b/docs/about/deprecated.rst
@@ -XXX,XX +XXX,XX @@ they want to use and avoids confusion.  Existing users of the ``spike``
 machine must ensure that they're setting the ``spike`` machine in the
 command line (``-M spike``).
 
+Arm ``highbank`` and ``midway`` machines (since 10.1)
+'''''''''''''''''''''''''''''''''''''''''''''''''''''
+
+There are no known users left for these machines (if you still use it,
+please write a mail to the qemu-devel mailing list). If you just want to
+boot a Cortex-A15 or Cortex-A9 Linux, use the ``virt`` machine instead.
+
 
 System emulator binaries
 ------------------------
diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/highbank.c
+++ b/hw/arm/highbank.c
@@ -XXX,XX +XXX,XX @@ static void highbank_class_init(ObjectClass *oc, const void *data)
     mc->max_cpus = 4;
     mc->ignore_memory_transaction_failures = true;
     mc->default_ram_id = "highbank.dram";
+    mc->deprecation_reason = "no known users left for this machine";
 }
 
 static const TypeInfo highbank_type = {
@@ -XXX,XX +XXX,XX @@ static void midway_class_init(ObjectClass *oc, const void *data)
     mc->max_cpus = 4;
     mc->ignore_memory_transaction_failures = true;
     mc->default_ram_id = "highbank.dram";
+    mc->deprecation_reason = "no known users left for this machine";
 }
 
 static const TypeInfo midway_type = {
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch brings the VLSTM and VLLDM helper functions closer to the ARM
pseudocode by adding MO_ALIGN to the MemOpIdx of the associated store
(`cpu_stl_mmu`) operations and load (`cpu_ldl_mmu`) operations.

Note that this is not a bug fix: an 8-byte alignment check already exists
and remains in place, enforcing stricter alignment than the 4 bytes
requirement in the individual loads and stores. This change merely makes the
helper implementations closer to the ARM pseudocode.

That said, as a side effect, the MMU index is now resolved once instead of
on every `cpu_*_data_ra` call, reducing redundant lookups

Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-2-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
     bool s = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK;
     bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK;
     uintptr_t ra = GETPC();
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
+    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+                                 arm_to_core_mmu_idx(mmu_idx));
 
     assert(env->v7m.secure);
 
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
      * Note that we do not use v7m_stack_write() here, because the
      * accesses should not set the FSR bits for stacking errors if they
      * fail. (In pseudocode terms, they are AccType_NORMAL, not AccType_STACK
-     * or AccType_LAZYFP). Faults in cpu_stl_data_ra() will throw exceptions
+     * or AccType_LAZYFP). Faults in cpu_stl_mmu() will throw exceptions
      * and longjmp out.
      */
     if (!(env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_LSPEN_MASK)) {
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
             if (i >= 16) {
                 faddr += 8; /* skip the slot for the FPSCR */
             }
-            cpu_stl_data_ra(env, faddr, slo, ra);
-            cpu_stl_data_ra(env, faddr + 4, shi, ra);
+            cpu_stl_mmu(env, faddr, slo, oi, ra);
+            cpu_stl_mmu(env, faddr + 4, shi, oi, ra);
         }
-        cpu_stl_data_ra(env, fptr + 0x40, vfp_get_fpscr(env), ra);
+        cpu_stl_mmu(env, fptr + 0x40, vfp_get_fpscr(env), oi, ra);
         if (cpu_isar_feature(aa32_mve, cpu)) {
-            cpu_stl_data_ra(env, fptr + 0x44, env->v7m.vpr, ra);
+            cpu_stl_mmu(env, fptr + 0x44, env->v7m.vpr, oi, ra);
         }
 
         /*
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
 {
     ARMCPU *cpu = env_archcpu(env);
     uintptr_t ra = GETPC();
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
+    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+                                 arm_to_core_mmu_idx(mmu_idx));
 
     /* fptr is the value of Rn, the frame pointer we load the FP regs from */
     assert(env->v7m.secure);
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
                 faddr += 8; /* skip the slot for the FPSCR and VPR */
             }
 
-            slo = cpu_ldl_data_ra(env, faddr, ra);
-            shi = cpu_ldl_data_ra(env, faddr + 4, ra);
+            slo = cpu_ldl_mmu(env, faddr, oi, ra);
+            shi = cpu_ldl_mmu(env, faddr + 4, oi, ra);
 
             dn = (uint64_t) shi << 32 | slo;
             *aa32_vfp_dreg(env, i / 2) = dn;
         }
-        fpscr = cpu_ldl_data_ra(env, fptr + 0x40, ra);
+        fpscr = cpu_ldl_mmu(env, fptr + 0x40, oi, ra);
         vfp_set_fpscr(env, fpscr);
         if (cpu_isar_feature(aa32_mve, cpu)) {
-            env->v7m.vpr = cpu_ldl_data_ra(env, fptr + 0x44, ra);
+            env->v7m.vpr = cpu_ldl_mmu(env, fptr + 0x44, oi, ra);
         }
     }
 
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations (when stacking the
return pc and psr) in the BLXNS instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-3-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
     }
 
     /* Note that these stores can throw exceptions on MPU faults */
-    cpu_stl_data_ra(env, sp, nextinst, GETPC());
-    cpu_stl_data_ra(env, sp + 4, saved_psr, GETPC());
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
+    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+                                 arm_to_core_mmu_idx(mmu_idx));
+    cpu_stl_mmu(env, sp, nextinst, oi, GETPC());
+    cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC());
 
     env->regs[13] = sp;
     env->regs[14] = 0xfeffffff;
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations (when unstacking the
return pc and psr) in the FunctionReturn pseudocode.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-4-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@ static bool do_v7m_function_return(ARMCPU *cpu)
          * do them as secure, so work out what MMU index that is.
          */
         mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true);
-        oi = make_memop_idx(MO_LEUL, arm_to_core_mmu_idx(mmu_idx));
+        oi = make_memop_idx(MO_LEUL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx));
         newpc = cpu_ldl_mmu(env, frameptr, oi, 0);
         newpsr = cpu_ldl_mmu(env, frameptr + 4, oi, 0);
 
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLDR
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-5-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VSTR
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-6-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
         mve_advance_vpt(env);                                           \
     }
 
-#define DO_VSTR(OP, MSIZE, STTYPE, ESIZE, TYPE)                         \
+#define DO_VSTR(OP, MFLAG, MSIZE, STTYPE, ESIZE, TYPE)                  \
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr)    \
     {                                                                   \
         TYPE *d = vd;                                                   \
         uint16_t mask = mve_element_mask(env);                          \
         unsigned b, e;                                                  \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
         for (b = 0, e = 0; b < 16; b += ESIZE, e++) {                   \
             if (mask & (1 << b)) {                                      \
-                cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \
+                cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \
             }                                                           \
             addr += MSIZE;                                              \
         }                                                               \
@@ -XXX,XX +XXX,XX @@ DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t)
 DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t)
 DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t)
 
-DO_VSTR(vstrb, 1, stb, 1, uint8_t)
-DO_VSTR(vstrh, 2, stw, 2, uint16_t)
-DO_VSTR(vstrw, 4, stl, 4, uint32_t)
+DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t)
+DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t)
+DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t)
 
 DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t)
 DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t)
@@ -XXX,XX +XXX,XX @@ DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t)
 DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t)
 DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t)
 
-DO_VSTR(vstrb_h, 1, stb, 2, int16_t)
-DO_VSTR(vstrb_w, 1, stb, 4, int32_t)
-DO_VSTR(vstrh_w, 2, stw, 4, int32_t)
+DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t)
+DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t)
+DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
 
 #undef DO_VLDR
 #undef DO_VSTR
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLDR_SG
instructions.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-7-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 42 ++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 17 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
  * For loads, predicated lanes are zeroed instead of retaining
  * their previous values.
  */
-#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)        \
+#define DO_VLDR_SG(OP, MFLAG, MTYPE, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)\
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm,         \
                           uint32_t base)                                \
     {                                                                   \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned e;                                                     \
         uint32_t addr;                                                  \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H##ESIZE(e)]);                        \
             d[H##ESIZE(e)] = (mask & 1) ?                               \
-                cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0;         \
+                (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0;  \
             if (WB) {                                                   \
                 m[H##ESIZE(e)] = addr;                                  \
             }                                                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned e;                                                     \
         uint32_t addr;                                                  \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H4(e & ~1)]);                         \
             addr += 4 * (e & 1);                                        \
-            d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \
+            d[H4(e)] = (mask & 1) ? cpu_ldl_mmu(env, addr, oi, GETPC()) : 0; \
             if (WB && (e & 1)) {                                        \
                 m[H4(e & ~1)] = addr - 4;                               \
             }                                                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
 #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2))
 #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3))
 
-DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
 DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false)
+DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4,
+           int32_t, uint32_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2,
+           uint16_t, uint16_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4,
+           uint32_t, uint32_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4,
+           uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false)
@@ -XXX,XX +XXX,XX @@ DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false)
 DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
 DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VSTR_SG
instructions.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-8-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
     }
 
 /* We know here TYPE is unsigned so always the same as the offset type */
-#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB)                 \
+#define DO_VSTR_SG(OP, MFLAG, STTYPE, ESIZE, TYPE, ADDRFN, WB)          \
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm,         \
                           uint32_t base)                                \
     {                                                                   \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned e;                                                     \
         uint32_t addr;                                                  \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H##ESIZE(e)]);                        \
             if (mask & 1) {                                             \
-                cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \
+                cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \
             }                                                           \
             if (WB) {                                                   \
                 m[H##ESIZE(e)] = addr;                                  \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned e;                                                     \
         uint32_t addr;                                                  \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
             addr = ADDRFN(base, m[H4(e & ~1)]);                         \
             addr += 4 * (e & 1);                                        \
             if (mask & 1) {                                             \
-                cpu_stl_data_ra(env, addr, d[H4(e)], GETPC());          \
+                cpu_stl_mmu(env, addr, d[H4(e)], oi, GETPC());          \
             }                                                           \
             if (WB && (e & 1)) {                                        \
                 m[H4(e & ~1)] = addr - 4;                               \
@@ -XXX,XX +XXX,XX @@ DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4,
            uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false)
 DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false)
 
-DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false)
+DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
-DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true)
+DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
 
 /*
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLD4
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-9-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint16_t mask = mve_eci_mask(env);                              \
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 4;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             for (e = 0; e < 4; e++, data >>= 8) {                       \
                 uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \
                 qd[H1(off[beat])] = data;                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t addr, data;                                            \
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 8 + (beat & 1) * 4;               \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y);             \
             qd[H2(off[beat])] = data;                                   \
             data >>= 16;                                                \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int y;                                                          \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 4;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             y = (beat + (O1 & 2)) & 3;                                  \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y);             \
             qd[H4(off[beat] >> 2)] = data;                              \
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLD2
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-10-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 2;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             for (e = 0; e < 4; e++, data >>= 8) {                       \
                 qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1));    \
                 qd[H1(off[beat] + (e >> 1))] = data;                    \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         int e;                                                          \
         uint16_t *qd;                                                   \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 4;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             for (e = 0; e < 2; e++, data >>= 16) {                      \
                 qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e);         \
                 qd[H2(off[beat])] = data;                               \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat];                                    \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1));    \
             qd[H4(off[beat] >> 3)] = data;                              \
         }                                                               \
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VST4
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-11-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint16_t mask = mve_eci_mask(env);                              \
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
                 uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \
                 data = (data << 8) | qd[H1(off[beat])];                 \
             }                                                           \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t addr, data;                                            \
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
             data = qd[H2(off[beat])];                                   \
             qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1);         \
             data |= qd[H2(off[beat])] << 16;                            \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int y;                                                          \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
             y = (beat + (O1 & 2)) & 3;                                  \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y);             \
             data = qd[H4(off[beat] >> 2)];                              \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VST2
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-12-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
                 qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1));    \
                 data = (data << 8) | qd[H1(off[beat] + (e >> 1))];      \
             }                                                           \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         int e;                                                          \
         uint16_t *qd;                                                   \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
                 qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e);         \
                 data = (data << 16) | qd[H2(off[beat])];                \
             }                                                           \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
             addr = base + off[beat];                                    \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1));    \
             data = qd[H4(off[beat] >> 3)];                              \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

We failed to raise an exception when
sme_excp_el == 0 and fp_excp_el == 1.

Cc: qemu-stable@nongnu.org
Fixes: 3d74825f4d6 ("target/arm: Add SME enablement checks")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ bool sme_enabled_check(DisasContext *s)
      * to be zero when fp_excp_el has priority.  This is because we need
      * sme_excp_el by itself for cpregs access checks.
      */
-    if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) {
+    if (s->sme_excp_el
+        && (!s->fp_excp_el || s->sme_excp_el <= s->fp_excp_el)) {
         bool ret = sme_access_check(s);
         s->fp_access_checked = (ret ? 1 : -1);
         return ret;
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Do not assume SME implies SVE.  Ensure that the non-streaming
check is present along the SME path, since it is not implied
by sme_*_enabled_check.

Cc: qemu-stable@nongnu.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool fp_access_check_only(DisasContext *s)
     return true;
 }
 
-static bool fp_access_check(DisasContext *s)
+static bool nonstreaming_check(DisasContext *s)
 {
-    if (!fp_access_check_only(s)) {
-        return false;
-    }
     if (s->sme_trap_nonstreaming && s->is_nonstreaming) {
         gen_exception_insn(s, 0, EXCP_UDEF,
                            syn_smetrap(SME_ET_Streaming, false));
@@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s)
     return true;
 }
 
+static bool fp_access_check(DisasContext *s)
+{
+    return fp_access_check_only(s) && nonstreaming_check(s);
+}
+
 /*
  * Return <0 for non-supported element sizes, with MO_16 controlled by
  * FEAT_FP16; return 0 for fp disabled; otherwise return >0 for success.
@@ -XXX,XX +XXX,XX @@ static int fp_access_check_vector_hsd(DisasContext *s, bool is_q, MemOp esz)
  */
 bool sve_access_check(DisasContext *s)
 {
-    if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) {
+    if (dc_isar_feature(aa64_sme, s)) {
         bool ret;
 
-        assert(dc_isar_feature(aa64_sme, s));
-        ret = sme_sm_enabled_check(s);
+        if (s->pstate_sm) {
+            ret = sme_enabled_check(s);
+        } else if (dc_isar_feature(aa64_sve, s)) {
+            goto continue_sve;
+        } else {
+            ret = sme_sm_enabled_check(s);
+        }
+        if (ret) {
+            ret = nonstreaming_check(s);
+        }
         s->sve_access_checked = (ret ? 1 : -1);
         return ret;
     }
+
+ continue_sve:
     if (s->sve_excp_el) {
         /* Assert that we only raise one exception per instruction. */
         assert(!s->sve_access_checked);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

We missed the instructions UDEF when the vector size is too small.
We missed marking the instructions non-streaming with SME.

Cc: qemu-stable@nongnu.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 43 ++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 13 deletions(-)

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(PUNPKHI, aa64_sve, do_perm_pred2, a, 1, gen_helper_sve_punpk_p)
  *** SVE Permute - Interleaving Group
  */
 
+static bool do_interleave_q(DisasContext *s, gen_helper_gvec_3 *fn,
+                            arg_rrr_esz *a, int data)
+{
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        if (vsz < 32) {
+            unallocated_encoding(s);
+        } else {
+            tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd),
+                               vec_full_reg_offset(s, a->rn),
+                               vec_full_reg_offset(s, a->rm),
+                               vsz, vsz, data, fn);
+        }
+    }
+    return true;
+}
+
 static gen_helper_gvec_3 * const zip_fns[4] = {
     gen_helper_sve_zip_b, gen_helper_sve_zip_h,
     gen_helper_sve_zip_s, gen_helper_sve_zip_d,
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ZIP1_z, aa64_sve, gen_gvec_ool_arg_zzz,
 TRANS_FEAT(ZIP2_z, aa64_sve, gen_gvec_ool_arg_zzz,
            zip_fns[a->esz], a, vec_full_reg_size(s) / 2)
 
-TRANS_FEAT(ZIP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_zip_q, a, 0)
-TRANS_FEAT(ZIP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_zip_q, a,
-           QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2)
+TRANS_FEAT_NONSTREAMING(ZIP1_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_zip_q, a, 0)
+TRANS_FEAT_NONSTREAMING(ZIP2_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_zip_q, a,
+                        QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2)
 
 static gen_helper_gvec_3 * const uzp_fns[4] = {
     gen_helper_sve_uzp_b, gen_helper_sve_uzp_h,
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz,
 TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz,
            uzp_fns[a->esz], a, 1 << a->esz)
 
-TRANS_FEAT(UZP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_uzp_q, a, 0)
-TRANS_FEAT(UZP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_uzp_q, a, 16)
+TRANS_FEAT_NONSTREAMING(UZP1_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_uzp_q, a, 0)
+TRANS_FEAT_NONSTREAMING(UZP2_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_uzp_q, a, 16)
 
 static gen_helper_gvec_3 * const trn_fns[4] = {
     gen_helper_sve_trn_b, gen_helper_sve_trn_h,
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN1_z, aa64_sve, gen_gvec_ool_arg_zzz,
 TRANS_FEAT(TRN2_z, aa64_sve, gen_gvec_ool_arg_zzz,
            trn_fns[a->esz], a, 1 << a->esz)
 
-TRANS_FEAT(TRN1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_trn_q, a, 0)
-TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_trn_q, a, 16)
+TRANS_FEAT_NONSTREAMING(TRN1_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_trn_q, a, 0)
+TRANS_FEAT_NONSTREAMING(TRN2_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_trn_q, a, 16)
 
 /*
  *** SVE Permute Vector - Predicated Group
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Replace @rda_rn_rm_e0 with @rda_rn_rm_ex, and require
users to supply an explicit esz.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode | 48 +++++++++++++++++++--------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@
 @rda_rn_rm      ........ esz:2 . rm:5 ... ... rn:5 rd:5 \
                 &rrrr_esz ra=%reg_movprfx
 
-# Four operand with unused vector element size
-@rda_rn_rm_e0   ........ ... rm:5 ... ... rn:5 rd:5 \
-                &rrrr_esz esz=0 ra=%reg_movprfx
-@rdn_ra_rm_e0   ........ ... rm:5 ... ... ra:5 rd:5 \
-                &rrrr_esz esz=0 rn=%reg_movprfx
+# Four operand with explicit vector element size
+@rda_rn_rm_ex   ........ ... rm:5 ... ... rn:5 rd:5 \
+                &rrrr_esz ra=%reg_movprfx
+@rdn_ra_rm_ex   ........ ... rm:5 ... ... ra:5 rd:5 \
+                &rrrr_esz rn=%reg_movprfx
 
 # Three operand with "memory" size, aka immediate left shift
 @rd_rn_msz_rm   ........ ... rm:5 .... imm:2 rn:5 rd:5          &rrri
@@ -XXX,XX +XXX,XX @@ XAR             00000100 .. 1 ..... 001 101 rm:5  rd:5   &rrri_esz \
                 rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr
 
 # SVE2 bitwise ternary operations
-EOR3            00000100 00 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
-BSL             00000100 00 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
-BCAX            00000100 01 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
-BSL1N           00000100 01 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
-BSL2N           00000100 10 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
-NBSL            00000100 11 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
+EOR3            00000100 00 1 ..... 001 110 ..... .....     @rdn_ra_rm_ex esz=0
+BSL             00000100 00 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
+BCAX            00000100 01 1 ..... 001 110 ..... .....     @rdn_ra_rm_ex esz=0
+BSL1N           00000100 01 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
+BSL2N           00000100 10 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
+NBSL            00000100 11 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
 
 ### SVE Index Generation Group
 
@@ -XXX,XX +XXX,XX @@ EORTB           01000101 .. 0 ..... 10010 1 ..... .....  @rd_rn_rm
 
 ## SVE integer matrix multiply accumulate
 
-SMMLA           01000101 00 0 ..... 10011 0 ..... .....  @rda_rn_rm_e0
-USMMLA          01000101 10 0 ..... 10011 0 ..... .....  @rda_rn_rm_e0
-UMMLA           01000101 11 0 ..... 10011 0 ..... .....  @rda_rn_rm_e0
+SMMLA           01000101 00 0 ..... 10011 0 ..... .....  @rda_rn_rm_ex esz=2
+USMMLA          01000101 10 0 ..... 10011 0 ..... .....  @rda_rn_rm_ex esz=2
+UMMLA           01000101 11 0 ..... 10011 0 ..... .....  @rda_rn_rm_ex esz=2
 
 ## SVE2 bitwise permute
 
@@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 USDOT_zzzz      01000100 .. 0 ..... 011 110 ..... .....  @rda_rn_rm
 
 ### SVE2 floating point matrix multiply accumulate
-BFMMLA          01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
-FMMLA_s         01100100 10 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
-FMMLA_d         01100100 11 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
+BFMMLA          01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=1
+FMMLA_s         01100100 10 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=2
+FMMLA_d         01100100 11 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=3
 
 ### SVE2 Memory Gather Load Group
 
@@ -XXX,XX +XXX,XX @@ FCVTLT_sd       01100100 11 0010 11 101 ... ..... .....  @rd_pg_rn_e0
 FLOGB           01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5  &rpr_esz
 
 ### SVE2 floating-point multiply-add long (vectors)
-FMLALB_zzzw     01100100 10 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
-FMLALT_zzzw     01100100 10 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
-FMLSLB_zzzw     01100100 10 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_e0
-FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_e0
+FMLALB_zzzw     01100100 10 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
+FMLALT_zzzw     01100100 10 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_ex esz=2
+FMLSLB_zzzw     01100100 10 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_ex esz=2
+FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
-BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
-BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
+BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
+BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point bfloat16 dot-product
-BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
+BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point multiply-add long (indexed)
 FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-6-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(FMINNMP, aa64_sve2, sve2_fminnmp_zpzz)
 DO_ZPZZ_FP(FMAXP, aa64_sve2, sve2_fmaxp_zpzz)
 DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz)
 
+static bool do_fmmla(DisasContext *s, arg_rrrr_esz *a,
+                     gen_helper_gvec_4_ptr *fn)
+{
+    if (sve_access_check(s)) {
+        if (vec_full_reg_size(s) < 4 * memop_size(a->esz)) {
+            unallocated_encoding(s);
+        } else {
+            gen_gvec_fpst_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, 0, FPST_A64);
+        }
+    }
+    return true;
+}
+
+TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, do_fmmla, a, gen_helper_fmmla_s)
+TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, do_fmmla, a, gen_helper_fmmla_d)
+
 /*
  * SVE Integer Multiply-Add (unpredicated)
  */
 
-TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz,
-                        gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra,
-                        0, FPST_A64)
-TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz,
-                        gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra,
-                        0, FPST_A64)
-
 static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = {
     NULL,                           gen_helper_sve2_sqdmlal_zzzw_h,
     gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d,
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

All F64MM instructions operate on a 256-bit vector.
If only 128-bit vectors is supported by the cpu,
then the cpu cannot enable F64MM.

Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu64.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
     /* From now on sve_max_vq is the actual maximum supported length. */
     cpu->sve_max_vq = max_vq;
     cpu->sve_vq.map = vq_map;
+
+    /* FEAT_F64MM requires the existence of a 256-bit vector size. */
+    if (max_vq < 2) {
+        uint64_t t = GET_IDREG(&cpu->isar, ID_AA64ZFR0);
+        t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 0);
+        SET_IDREG(&cpu->isar, ID_AA64ZFR0, t);
+    }
 }
 
 /*
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Gvec only operates on size 8 and multiples of 16.
Predicates may be any multiple of 2.
Round up the size using the appropriate function.

Cc: qemu-stable@nongnu.org
Fixes: 598ab0b24c0 ("target/arm: Implement PSEL")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_PSEL(DisasContext *s, arg_psel *a)
     tcg_gen_neg_i64(tmp, tmp);
 
     /* Apply to either copy the source, or write zeros. */
+    pl = size_for_gvec(pl);
     tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd),
                       pred_full_reg_offset(s, a->pn), tmp, pl, pl);
     return true;
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Implement FPProcessNaNs4 within f16_dotadd, rather than
simply letting NaNs propagate through the function.

Cc: qemu-stable@nongnu.org
Fixes: 3916841ac75 ("target/arm: Implement FMOPA, FMOPS (widening)")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme_helper.c | 62 +++++++++++++++++++++++++++----------
 1 file changed, 46 insertions(+), 16 deletions(-)

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
      *  - we have pre-set-up copy of s_std which is set to round-to-odd,
      *    for the multiply (see below)
      */
-    float64 e1r = float16_to_float64(e1 & 0xffff, true, s_f16);
-    float64 e1c = float16_to_float64(e1 >> 16, true, s_f16);
-    float64 e2r = float16_to_float64(e2 & 0xffff, true, s_f16);
-    float64 e2c = float16_to_float64(e2 >> 16, true, s_f16);
-    float64 t64;
+    float16 h1r = e1 & 0xffff;
+    float16 h1c = e1 >> 16;
+    float16 h2r = e2 & 0xffff;
+    float16 h2c = e2 >> 16;
     float32 t32;
 
-    /*
-     * The ARM pseudocode function FPDot performs both multiplies
-     * and the add with a single rounding operation.  Emulate this
-     * by performing the first multiply in round-to-odd, then doing
-     * the second multiply as fused multiply-add, and rounding to
-     * float32 all in one step.
-     */
-    t64 = float64_mul(e1r, e2r, s_odd);
-    t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std);
+    /* C.f. FPProcessNaNs4 */
+    if (float16_is_any_nan(h1r) || float16_is_any_nan(h1c) ||
+        float16_is_any_nan(h2r) || float16_is_any_nan(h2c)) {
+        float16 t16;
 
-    /* This conversion is exact, because we've already rounded. */
-    t32 = float64_to_float32(t64, s_std);
+        if (float16_is_signaling_nan(h1r, s_f16)) {
+            t16 = h1r;
+        } else if (float16_is_signaling_nan(h1c, s_f16)) {
+            t16 = h1c;
+        } else if (float16_is_signaling_nan(h2r, s_f16)) {
+            t16 = h2r;
+        } else if (float16_is_signaling_nan(h2c, s_f16)) {
+            t16 = h2c;
+        } else if (float16_is_any_nan(h1r)) {
+            t16 = h1r;
+        } else if (float16_is_any_nan(h1c)) {
+            t16 = h1c;
+        } else if (float16_is_any_nan(h2r)) {
+            t16 = h2r;
+        } else {
+            t16 = h2c;
+        }
+        t32 = float16_to_float32(t16, true, s_f16);
+    } else {
+        float64 e1r = float16_to_float64(h1r, true, s_f16);
+        float64 e1c = float16_to_float64(h1c, true, s_f16);
+        float64 e2r = float16_to_float64(h2r, true, s_f16);
+        float64 e2c = float16_to_float64(h2c, true, s_f16);
+        float64 t64;
+
+        /*
+         * The ARM pseudocode function FPDot performs both multiplies
+         * and the add with a single rounding operation.  Emulate this
+         * by performing the first multiply in round-to-odd, then doing
+         * the second multiply as fused multiply-add, and rounding to
+         * float32 all in one step.
+         */
+        t64 = float64_mul(e1r, e2r, s_odd);
+        t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std);
+
+        /* This conversion is exact, because we've already rounded. */
+        t32 = float64_to_float32(t64, s_std);
+    }
 
     /* The final accumulation step is not fused. */
     return float32_add(sum, t32, s_std);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Implement FPProcessNaNs4 within bfdotadd_ebf, rather than
simply letting NaNs propagate through the function.

Cc: qemu-stable@nongnu.org
Fixes: 0e1850182a1 ("target/arm: Implement FPCR.EBF=1 semantics for bfdotadd()")
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_helper.c | 75 ++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 22 deletions(-)

diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst)
 float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2,
                      float_status *fpst, float_status *fpst_odd)
 {
-    /*
-     * Compare f16_dotadd() in sme_helper.c, but here we have
-     * bfloat16 inputs. In particular that means that we do not
-     * want the FPCR.FZ16 flush semantics, so we use the normal
-     * float_status for the input handling here.
-     */
-    float64 e1r = float32_to_float64(e1 << 16, fpst);
-    float64 e1c = float32_to_float64(e1 & 0xffff0000u, fpst);
-    float64 e2r = float32_to_float64(e2 << 16, fpst);
-    float64 e2c = float32_to_float64(e2 & 0xffff0000u, fpst);
-    float64 t64;
+    float32 s1r = e1 << 16;
+    float32 s1c = e1 & 0xffff0000u;
+    float32 s2r = e2 << 16;
+    float32 s2c = e2 & 0xffff0000u;
     float32 t32;
 
-    /*
-     * The ARM pseudocode function FPDot performs both multiplies
-     * and the add with a single rounding operation.  Emulate this
-     * by performing the first multiply in round-to-odd, then doing
-     * the second multiply as fused multiply-add, and rounding to
-     * float32 all in one step.
-     */
-    t64 = float64_mul(e1r, e2r, fpst_odd);
-    t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst);
+    /* C.f. FPProcessNaNs4 */
+    if (float32_is_any_nan(s1r) || float32_is_any_nan(s1c) ||
+        float32_is_any_nan(s2r) || float32_is_any_nan(s2c)) {
+        if (float32_is_signaling_nan(s1r, fpst)) {
+            t32 = s1r;
+        } else if (float32_is_signaling_nan(s1c, fpst)) {
+            t32 = s1c;
+        } else if (float32_is_signaling_nan(s2r, fpst)) {
+            t32 = s2r;
+        } else if (float32_is_signaling_nan(s2c, fpst)) {
+            t32 = s2c;
+        } else if (float32_is_any_nan(s1r)) {
+            t32 = s1r;
+        } else if (float32_is_any_nan(s1c)) {
+            t32 = s1c;
+        } else if (float32_is_any_nan(s2r)) {
+            t32 = s2r;
+        } else {
+            t32 = s2c;
+        }
+        /*
+         * FPConvertNaN(FPProcessNaN(t32)) will be done as part
+         * of the final addition below.
+         */
+    } else {
+        /*
+         * Compare f16_dotadd() in sme_helper.c, but here we have
+         * bfloat16 inputs. In particular that means that we do not
+         * want the FPCR.FZ16 flush semantics, so we use the normal
+         * float_status for the input handling here.
+         */
+        float64 e1r = float32_to_float64(s1r, fpst);
+        float64 e1c = float32_to_float64(s1c, fpst);
+        float64 e2r = float32_to_float64(s2r, fpst);
+        float64 e2c = float32_to_float64(s2c, fpst);
+        float64 t64;
 
-    /* This conversion is exact, because we've already rounded. */
-    t32 = float64_to_float32(t64, fpst);
+        /*
+         * The ARM pseudocode function FPDot performs both multiplies
+         * and the add with a single rounding operation.  Emulate this
+         * by performing the first multiply in round-to-odd, then doing
+         * the second multiply as fused multiply-add, and rounding to
+         * float32 all in one step.
+         */
+        t64 = float64_mul(e1r, e2r, fpst_odd);
+        t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst);
+
+        /* This conversion is exact, because we've already rounded. */
+        t32 = float64_to_float32(t64, fpst);
+    }
 
     /* The final accumulation step is not fused. */
     return float32_add(sum, t32, fpst);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Rather than repeatedly copying FPST_FPCR to locals
and setting default nan mode, create dedicated float_status.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h            | 12 +++++++++++-
 target/arm/cpu.c            |  4 ++++
 target/arm/tcg/vfp_helper.c | 12 +++++++++++-
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ typedef struct NVICState NVICState;
  *       when FPCR.AH == 1 (bfloat16 conversions and multiplies,
  *       and the reciprocal and square root estimate/step insns);
  *       for half-precision
+ * ZA: the "streaming sve" fp status.
+ * ZA_F16: likewise for half-precision.
  *
  * Half-precision operations are governed by a separate
  * flush-to-zero control bit in FPSCR:FZ16. We pass a separate
@@ -XXX,XX +XXX,XX @@ typedef struct NVICState NVICState;
  * they ignore FPCR.RMode. But they don't ignore FPCR.FZ16,
  * which means we need an FPST_AH_F16 as well.
  *
+ * The "ZA" float_status are for Streaming SVE operations which use
+ * default-NaN and do not generate fp exceptions, which means that they
+ * do not accumulate exception bits back into FPCR.
+ * See e.g. FPAdd vs FPAdd_ZA pseudocode functions, and the setting
+ * of fpcr.DN and fpexec parameters.
+ *
  * To avoid having to transfer exception bits around, we simply
  * say that the FPSCR cumulative exception flags are the logical
  * OR of the flags in the four fp statuses. This relies on the
@@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour {
     FPST_A64_F16,
     FPST_AH,
     FPST_AH_F16,
+    FPST_ZA,
+    FPST_ZA_F16,
     FPST_STD,
     FPST_STD_F16,
 } ARMFPStatusFlavour;
-#define FPST_COUNT  8
+#define FPST_COUNT  10
 
 typedef struct CPUArchState {
     /* Regs for current mode.  */
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj, ResetType type)
     set_flush_inputs_to_zero(1, &env->vfp.fp_status[FPST_STD]);
     set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD]);
     set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD_F16]);
+    set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA]);
+    set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA_F16]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
+    arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32_F16]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+    arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD_F16]);
     arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_AH]);
     set_flush_to_zero(1, &env->vfp.fp_status[FPST_AH]);
diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vfp_helper.c
+++ b/target/arm/tcg/vfp_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t vfp_get_fpsr_from_host(CPUARMState *env)
     a64_flags |= (get_float_exception_flags(&env->vfp.fp_status[FPST_A64_F16])
           & ~(float_flag_input_denormal_flushed | float_flag_input_denormal_used));
     /*
-     * We do not merge in flags from FPST_AH or FPST_AH_F16, because
+     * We do not merge in flags from FPST_{AH,ZA} or FPST_{AH,ZA}_F16, because
      * they are used for insns that must not set the cumulative exception bits.
      */
 
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
         set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64]);
         set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A32_F16]);
         set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64_F16]);
+        set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA]);
+        set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA_F16]);
     }
     if (changed & FPCR_FZ16) {
         bool ftz_enabled = val & FPCR_FZ16;
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]);
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]);
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]);
+        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]);
+        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]);
     }
     if (changed & FPCR_FZ) {
         bool ftz_enabled = val & FPCR_FZ;
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]);
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64]);
+        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA]);
         /* FIZ is A64 only so FZ always makes A32 code flush inputs to zero */
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]);
     }
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
         bool fitz_enabled = (val & FPCR_FIZ) ||
             (val & (FPCR_FZ | FPCR_AH)) == FPCR_FZ;
         set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_A64]);
+        set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_ZA]);
     }
     if (changed & FPCR_DN) {
         bool dnan_enabled = val & FPCR_DN;
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
             /* Change behaviours for A64 FP operations */
             arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
             arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+            arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
+            arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
         } else {
             arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
             arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+            arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
+            arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
         }
     }
     /*
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme_helper.c    | 37 ++++++++--------------------------
 target/arm/tcg/translate-sme.c |  4 ++--
 2 files changed, 10 insertions(+), 31 deletions(-)

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
 }
 
 void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
-                         void *vpm, float_status *fpst_in, uint32_t desc)
+                         void *vpm, float_status *fpst, uint32_t desc)
 {
     intptr_t row, col, oprsz = simd_maxsz(desc);
     uint32_t neg = simd_data(desc) << 31;
     uint16_t *pn = vpn, *pm = vpm;
-    float_status fpst;
-
-    /*
-     * Make a copy of float_status because this operation does not
-     * update the cumulative fp exception status.  It also produces
-     * default nans.
-     */
-    fpst = *fpst_in;
-    set_default_nan_mode(true, &fpst);
 
     for (row = 0; row < oprsz; ) {
         uint16_t pa = pn[H2(row >> 4)];
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
                         if (pb & 1) {
                             uint32_t *a = vza_row + H1_4(col);
                             uint32_t *m = vzm + H1_4(col);
-                            *a = float32_muladd(n, *m, *a, 0, &fpst);
+                            *a = float32_muladd(n, *m, *a, 0, fpst);
                         }
                         col += 4;
                         pb >>= 4;
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
 }
 
 void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
-                         void *vpm, float_status *fpst_in, uint32_t desc)
+                         void *vpm, float_status *fpst, uint32_t desc)
 {
     intptr_t row, col, oprsz = simd_oprsz(desc) / 8;
     uint64_t neg = (uint64_t)simd_data(desc) << 63;
     uint64_t *za = vza, *zn = vzn, *zm = vzm;
     uint8_t *pn = vpn, *pm = vpm;
-    float_status fpst = *fpst_in;
-
-    set_default_nan_mode(true, &fpst);
 
     for (row = 0; row < oprsz; ++row) {
         if (pn[H1(row)] & 1) {
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
             for (col = 0; col < oprsz; ++col) {
                 if (pm[H1(col)] & 1) {
                     uint64_t *a = &za_row[col];
-                    *a = float64_muladd(n, zm[col], *a, 0, &fpst);
+                    *a = float64_muladd(n, zm[col], *a, 0, fpst);
                 }
             }
         }
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
     intptr_t row, col, oprsz = simd_maxsz(desc);
     uint32_t neg = simd_data(desc) * 0x80008000u;
     uint16_t *pn = vpn, *pm = vpm;
-    float_status fpst_odd, fpst_std, fpst_f16;
+    float_status fpst_odd = env->vfp.fp_status[FPST_ZA];
 
-    /*
-     * Make copies of the fp status fields we use, because this operation
-     * does not update the cumulative fp exception status.  It also
-     * produces default NaNs. We also need a second copy of fp_status with
-     * round-to-odd -- see above.
-     */
-    fpst_f16 = env->vfp.fp_status[FPST_A64_F16];
-    fpst_std = env->vfp.fp_status[FPST_A64];
-    set_default_nan_mode(true, &fpst_std);
-    set_default_nan_mode(true, &fpst_f16);
-    fpst_odd = fpst_std;
     set_float_rounding_mode(float_round_to_odd, &fpst_odd);
 
     for (row = 0; row < oprsz; ) {
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
 
                         m = f16mop_adj_pair(m, pcol, 0);
                         *a = f16_dotadd(*a, n, m,
-                                        &fpst_f16, &fpst_std, &fpst_odd);
+                                        &env->vfp.fp_status[FPST_ZA_F16],
+                                        &env->vfp.fp_status[FPST_ZA],
+                                        &fpst_odd);
                     }
                     col += 4;
                     pcol >>= 4;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
 TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a,
            MO_32, gen_helper_sme_fmopa_h)
 TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
-           MO_32, FPST_A64, gen_helper_sme_fmopa_s)
+           MO_32, FPST_ZA, gen_helper_sme_fmopa_s)
 TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
-           MO_64, FPST_A64, gen_helper_sme_fmopa_d)
+           MO_64, FPST_ZA, gen_helper_sme_fmopa_d)
 
 TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa)
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

The whole ZA state will also contain ZT0.
Make things easier in aarch64_set_svcr to zero both
by wrapping them in a common structure.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h               | 48 +++++++++++++++++++---------------
 linux-user/aarch64/signal.c    |  4 +--
 target/arm/cpu.c               |  4 +--
 target/arm/helper.c            |  2 +-
 target/arm/machine.c           |  2 +-
 target/arm/tcg/sme_helper.c    |  6 ++---
 target/arm/tcg/translate-sme.c |  4 +--
 7 files changed, 38 insertions(+), 32 deletions(-)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState {
 
     uint64_t scxtnum_el[4];
 
-    /*
-     * SME ZA storage -- 256 x 256 byte array, with bytes in host word order,
-     * as we do with vfp.zregs[].  This corresponds to the architectural ZA
-     * array, where ZA[N] is in the least-significant bytes of env->zarray[N].
-     * When SVL is less than the architectural maximum, the accessible
-     * storage is restricted, such that if the SVL is X bytes the guest can
-     * see only the bottom X elements of zarray[], and only the least
-     * significant X bytes of each element of the array. (In other words,
-     * the observable part is always square.)
-     *
-     * The ZA storage can also be considered as a set of square tiles of
-     * elements of different sizes. The mapping from tiles to the ZA array
-     * is architecturally defined, such that for tiles of elements of esz
-     * bytes, the Nth row (or "horizontal slice") of tile T is in
-     * ZA[T + N * esz]. Note that this means that each tile is not contiguous
-     * in the ZA storage, because its rows are striped through the ZA array.
-     *
-     * Because this is so large, keep this toward the end of the reset area,
-     * to keep the offsets into the rest of the structure smaller.
-     */
-    ARMVectorReg zarray[ARM_MAX_VQ * 16];
+    struct {
+        /*
+         * SME ZA storage -- 256 x 256 byte array, with bytes in host
+         * word order, as we do with vfp.zregs[].  This corresponds to
+         * the architectural ZA array, where ZA[N] is in the least
+         * significant bytes of env->za_state.za[N].
+         *
+         * When SVL is less than the architectural maximum, the accessible
+         * storage is restricted, such that if the SVL is X bytes the guest
+         * can see only the bottom X elements of zarray[], and only the least
+         * significant X bytes of each element of the array. (In other words,
+         * the observable part is always square.)
+         *
+         * The ZA storage can also be considered as a set of square tiles of
+         * elements of different sizes. The mapping from tiles to the ZA array
+         * is architecturally defined, such that for tiles of elements of esz
+         * bytes, the Nth row (or "horizontal slice") of tile T is in
+         * ZA[T + N * esz]. Note that this means that each tile is not
+         * contiguous in the ZA storage, because its rows are striped through
+         * the ZA array.
+         *
+         * Because this is so large, keep this toward the end of the
+         * reset area, to keep the offsets into the rest of the structure
+         * smaller.
+         */
+        ARMVectorReg za[ARM_MAX_VQ * 16];
+    } za_state;
 
     struct CPUBreakpoint *cpu_breakpoint[16];
     struct CPUWatchpoint *cpu_watchpoint[16];
diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/aarch64/signal.c
+++ b/linux-user/aarch64/signal.c
@@ -XXX,XX +XXX,XX @@ static void target_setup_za_record(struct target_za_context *za,
     for (i = 0; i < vl; ++i) {
         uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i);
         for (j = 0; j < vq * 2; ++j) {
-            __put_user_e(env->zarray[i].d[j], z + j, le);
+            __put_user_e(env->za_state.za[i].d[j], z + j, le);
         }
     }
 }
@@ -XXX,XX +XXX,XX @@ static bool target_restore_za_record(CPUARMState *env,
     for (i = 0; i < vl; ++i) {
         uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i);
         for (j = 0; j < vq * 2; ++j) {
-            __get_user_e(env->zarray[i].d[j], z + j, le);
+            __get_user_e(env->za_state.za[i].d[j], z + j, le);
         }
     }
     return true;
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags)
             qemu_fprintf(f, "ZA[%0*d]=", svl_lg10, i);
             for (j = zcr_len; j >= 0; --j) {
                 qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%c",
-                             env->zarray[i].d[2 * j + 1],
-                             env->zarray[i].d[2 * j],
+                             env->za_state.za[i].d[2 * j + 1],
+                             env->za_state.za[i].d[2 * j],
                              j ? ':' : '\n');
             }
         }
diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ void aarch64_set_svcr(CPUARMState *env, uint64_t new, uint64_t mask)
      * when disabled either.
      */
     if (change & new & R_SVCR_ZA_MASK) {
-        memset(env->zarray, 0, sizeof(env->zarray));
+        memset(&env->za_state, 0, sizeof(env->za_state));
     }
 
     if (tcg_enabled()) {
diff --git a/target/arm/machine.c b/target/arm/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_za = {
     .minimum_version_id = 1,
     .needed = za_needed,
     .fields = (const VMStateField[]) {
-        VMSTATE_STRUCT_ARRAY(env.zarray, ARMCPU, ARM_MAX_VQ * 16, 0,
+        VMSTATE_STRUCT_ARRAY(env.za_state.za, ARMCPU, ARM_MAX_VQ * 16, 0,
                              vmstate_vreg, ARMVectorReg),
         VMSTATE_END_OF_LIST()
     }
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl)
     uint32_t i;
 
     /*
-     * Special case clearing the entire ZA space.
+     * Special case clearing the entire ZArray.
      * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any
      * parts of the ZA storage outside of SVL.
      */
     if (imm == 0xff) {
-        memset(env->zarray, 0, sizeof(env->zarray));
+        memset(env->za_state.za, 0, sizeof(env->za_state.za));
         return;
     }
 
@@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl)
      */
     for (i = 0; i < svl; i++) {
         if (imm & (1 << (i % 8))) {
-            memset(&env->zarray[i], 0, svl);
+            memset(&env->za_state.za[i], 0, svl);
         }
     }
 }
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     offset = tile * sizeof(ARMVectorReg);
 
     /* Include the byte offset of zarray to make this relative to env. */
-    offset += offsetof(CPUARMState, zarray);
+    offset += offsetof(CPUARMState, za_state.za);
     tcg_gen_addi_i32(tmp, tmp, offset);
 
     /* Add the byte offset to env to produce the final pointer. */
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile(DisasContext *s, int esz, int tile)
     TCGv_ptr addr = tcg_temp_new_ptr();
     int offset;
 
-    offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, zarray);
+    offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, za_state.za);
 
     tcg_gen_addi_ptr(addr, tcg_env, offset);
     return addr;
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-15-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu-features.h | 63 +++++++++++++++++++++++++++++++++++++++
 target/arm/cpu.h          |  1 +
 2 files changed, 64 insertions(+)

diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rpres(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64ISAR2, RPRES);
 }
 
+static inline bool isar_feature_aa64_lut(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64ISAR2, LUT);
+}
+
 static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id)
 {
     /* We always set the AdvSIMD and FP fields identically.  */
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) != 0;
 }
 
+static inline bool isar_feature_aa64_sve2p1(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) >=2;
+}
+
 static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id)
 {
     return FIELD_EX64_IDREG(id, ID_AA64ZFR0, AES) != 0;
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64ZFR0, F64MM) != 0;
 }
 
+static inline bool isar_feature_aa64_sve_b16b16(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64ZFR0, B16B16);
+}
+
+static inline bool isar_feature_aa64_sme_b16b16(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, B16B16);
+}
+
+static inline bool isar_feature_aa64_sme_f16f16(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F16F16);
+}
+
 static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id)
 {
     return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F64F64);
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64SMFR0, FA64);
 }
 
+static inline bool isar_feature_aa64_sme2(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) != 0;
+}
+
+static inline bool isar_feature_aa64_sme2p1(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) >= 2;
+}
+
+/*
+ * Combinations of feature tests, for ease of use with TRANS_FEAT.
+ */
+static inline bool isar_feature_aa64_sme_or_sve2p1(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2_or_sve2p1(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2p1_or_sve2p1(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2p1(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2_i16i64(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_i16i64(id);
+}
+
+static inline bool isar_feature_aa64_sme2_f64f64(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_f64f64(id);
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR2, SYSINSTR_128, 36, 4)
 FIELD(ID_AA64ISAR2, PRFMSLC, 40, 4)
 FIELD(ID_AA64ISAR2, RPRFM, 48, 4)
 FIELD(ID_AA64ISAR2, CSSC, 52, 4)
+FIELD(ID_AA64ISAR2, LUT, 56, 4)
 FIELD(ID_AA64ISAR2, ATS1A, 60, 4)
 
 FIELD(ID_AA64PFR0, EL0, 0, 4)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

This is a 512-bit array introduced with SME2.
Save it only when ZA is in use.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-16-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h     |  3 +++
 target/arm/machine.c | 20 ++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState {
     uint64_t scxtnum_el[4];
 
     struct {
+        /* SME2 ZT0 -- 512 bit array, with data ordered like ARMVectorReg. */
+        uint64_t zt0[512 / 64] QEMU_ALIGNED(16);
+
         /*
          * SME ZA storage -- 256 x 256 byte array, with bytes in host
          * word order, as we do with vfp.zregs[].  This corresponds to
diff --git a/target/arm/machine.c b/target/arm/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_za = {
     }
 };
 
+static bool zt0_needed(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    return za_needed(cpu) && cpu_isar_feature(aa64_sme2, cpu);
+}
+
+static const VMStateDescription vmstate_zt0 = {
+    .name = "cpu/zt0",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = zt0_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64_ARRAY(env.za_state.zt0, ARMCPU,
+                             ARRAY_SIZE(((CPUARMState *)0)->za_state.zt0)),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static bool serror_needed(void *opaque)
 {
     ARMCPU *cpu = opaque;
@@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = {
         &vmstate_m_security,
         &vmstate_sve,
         &vmstate_za,
+        &vmstate_zt0,
         &vmstate_serror,
         &vmstate_irq_line_state,
         &vmstate_wfxt_timer,
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Pipe the value through from SMCR_ELx through hflags and into
the disassembly context.  Enable EZT0 in smcr_write.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-17-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h               |  2 ++
 target/arm/tcg/translate.h     |  1 +
 target/arm/cpu.c               |  3 +++
 target/arm/helper.c            |  6 +++++-
 target/arm/tcg/hflags.c        | 34 +++++++++++++++++++++++++++++++++-
 target/arm/tcg/translate-a64.c |  1 +
 6 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ FIELD(SVCR, ZA, 1, 1)
 
 /* Fields for SMCR_ELx. */
 FIELD(SMCR, LEN, 0, 4)
+FIELD(SMCR, EZT0, 30, 1)
 FIELD(SMCR, FA64, 31, 1)
 
 /* Write a new value to v7m.exception, thus transitioning into or out
@@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, NV2_MEM_E20, 35, 1)
 FIELD(TBFLAG_A64, NV2_MEM_BE, 36, 1)
 FIELD(TBFLAG_A64, AH, 37, 1)   /* FPCR.AH */
 FIELD(TBFLAG_A64, NEP, 38, 1)   /* FPCR.NEP */
+FIELD(TBFLAG_A64, ZT0EXC_EL, 39, 2)
 
 /*
  * Helpers for using the above. Note that only the A64 accessors use
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -XXX,XX +XXX,XX @@ typedef struct DisasContext {
     int fp_excp_el; /* FP exception EL or 0 if enabled */
     int sve_excp_el; /* SVE exception EL or 0 if enabled */
     int sme_excp_el; /* SME exception EL or 0 if enabled */
+    int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */
     int vl;          /* current vector length in bytes */
     int svl;         /* current streaming vector length in bytes */
     bool vfp_enabled; /* FP enabled via FPSCR.EN */
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ void arm_emulate_firmware_reset(CPUState *cpustate, int target_el)
                 env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK;
                 env->cp15.scr_el3 |= SCR_ENTP2;
                 env->vfp.smcr_el[3] = 0xf;
+                if (cpu_isar_feature(aa64_sme2, cpu)) {
+                    env->vfp.smcr_el[3] |= R_SMCR_EZT0_MASK;
+                }
             }
             if (cpu_isar_feature(aa64_hcx, cpu)) {
                 env->cp15.scr_el3 |= SCR_HXEN;
diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ static void smcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     int cur_el = arm_current_el(env);
     int old_len = sve_vqm1_for_el(env, cur_el);
+    uint64_t valid_mask = R_SMCR_LEN_MASK | R_SMCR_FA64_MASK;
     int new_len;
 
     QEMU_BUILD_BUG_ON(ARM_MAX_VQ > R_SMCR_LEN_MASK + 1);
-    value &= R_SMCR_LEN_MASK | R_SMCR_FA64_MASK;
+    if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) {
+        valid_mask |= R_SMCR_EZT0_MASK;
+    }
+    value &= valid_mask;
     raw_write(env, ri, value);
 
     /*
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el,
     return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
 }
 
+/*
+ * Return the exception level to which exceptions should be taken for ZT0.
+ * C.f. the ARM pseudocode function CheckSMEZT0Enabled, after the ZA check.
+ */
+static int zt0_exception_el(CPUARMState *env, int el)
+{
+#ifndef CONFIG_USER_ONLY
+    if (el <= 1
+        && !el_is_in_host(env, el)
+        && !FIELD_EX64(env->vfp.smcr_el[1], SMCR, EZT0)) {
+        return 1;
+    }
+    if (el <= 2
+        && arm_is_el2_enabled(env)
+        && !FIELD_EX64(env->vfp.smcr_el[2], SMCR, EZT0)) {
+        return 2;
+    }
+    if (arm_feature(env, ARM_FEATURE_EL3)
+        && !FIELD_EX64(env->vfp.smcr_el[3], SMCR, EZT0)) {
+        return 3;
+    }
+#endif
+    return 0;
+}
+
 static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
                                         ARMMMUIdx mmu_idx)
 {
@@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
             DP_TBFLAG_A64(flags, PSTATE_SM, 1);
             DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el));
         }
-        DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA));
+
+        if (FIELD_EX64(env->svcr, SVCR, ZA)) {
+            DP_TBFLAG_A64(flags, PSTATE_ZA, 1);
+            if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) {
+                int zt0_el = zt0_exception_el(env, el);
+                DP_TBFLAG_A64(flags, ZT0EXC_EL, zt0_el);
+            }
+        }
     }
 
     sctlr = regime_sctlr(env, stage1);
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
     dc->trap_eret = EX_TBFLAG_A64(tb_flags, TRAP_ERET);
     dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL);
     dc->sme_excp_el = EX_TBFLAG_A64(tb_flags, SMEEXC_EL);
+    dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL);
     dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16;
     dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16;
     dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h          |  1 +
 target/arm/tcg/sme.decode      |  1 +
 target/arm/tcg/translate-sme.c | 26 ++++++++++++++++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     SME_ET_Streaming,
     SME_ET_NotStreaming,
     SME_ET_InactiveZA,
+    SME_ET_InaccessibleZT0,
 } SMEExceptionType;
 
 #define ARM_EL_EC_LENGTH 6
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@
 ### SME Misc
 
 ZERO            11000000 00 001 00000000000 imm:8
+ZERO_zt0        11000000 01 001 00000000000 00000001
 
 ### SME Move into/from Array
 
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@
 
 #include "decode-sme.c.inc"
 
+static bool sme2_zt0_enabled_check(DisasContext *s)
+{
+    if (!sme_za_enabled_check(s)) {
+        return false;
+    }
+    if (s->zt0_excp_el) {
+        gen_exception_insn_el(s, 0, EXCP_UDEF,
+                              syn_smetrap(SME_ET_InaccessibleZT0, false),
+                              s->zt0_excp_el);
+        return false;
+    }
+    return true;
+}
 
 /*
  * Resolve tile.size[index] to a host pointer, where tile and index
@@ -XXX,XX +XXX,XX @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a)
     return true;
 }
 
+static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
+{
+    if (!dc_isar_feature(aa64_sme2, s)) {
+        return false;
+    }
+    if (sme_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+        tcg_gen_gvec_dup_imm(MO_64, offsetof(CPUARMState, za_state.zt0),
+                             sizeof_field(CPUARMState, za_state.zt0),
+                             sizeof_field(CPUARMState, za_state.zt0), 0);
+    }
+    return true;
+}
+
 static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Honor AlignmentEnforced() for LDR/STR (vector),
(predicate), and (array vector).

Within the expansion functions, clear @align when we're
done emitting loads at the largest size.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.h |  6 ++--
 target/arm/tcg/translate-sme.c |  5 ++--
 target/arm/tcg/translate-sve.c | 50 ++++++++++++++++++++++++----------
 3 files changed, 42 insertions(+), 19 deletions(-)

diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.h
+++ b/target/arm/tcg/translate-a64.h
@@ -XXX,XX +XXX,XX @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs,
                         uint32_t rn_ofs, uint32_t rm_ofs,
                         uint32_t opr_sz, uint32_t max_sz);
 
-void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
-void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
+void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs,
+                 int len, int rn, int imm, MemOp align);
+void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs,
+                 int len, int rn, int imm, MemOp align);
 
 #endif /* TARGET_ARM_TRANSLATE_A64_H */
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
     return true;
 }
 
-typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int);
+typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp);
 
 static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
 {
@@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
     /* ZA[n] equates to ZA0H.B[n]. */
     base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
 
-    fn(s, base, 0, svl, a->rn, imm * svl);
+    fn(s, base, 0, svl, a->rn, imm * svl,
+       s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     return true;
 }
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz,
  */
 
 void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
-                 int len, int rn, int imm)
+                 int len, int rn, int imm, MemOp align)
 {
     int len_align = QEMU_ALIGN_DOWN(len, 16);
     int len_remain = len % 16;
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
         for (i = 0; i < len_align; i += 16) {
             tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
-                                 MO_LE | MO_128 | MO_ATOM_NONE);
+                                 MO_LE | MO_128 | MO_ATOM_NONE | align);
             tcg_gen_extr_i128_i64(t0, t1, t16);
             tcg_gen_st_i64(t0, base, vofs + i);
             tcg_gen_st_i64(t1, base, vofs + i + 8);
             tcg_gen_addi_i64(clean_addr, clean_addr, 16);
         }
+        if (len_align) {
+            align = MO_UNALN;
+        }
     } else {
         TCGLabel *loop = gen_new_label();
         TCGv_ptr tp, i = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
         t16 = tcg_temp_new_i128();
         tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
-                             MO_LE | MO_128 | MO_ATOM_NONE);
+                             MO_LE | MO_128 | MO_ATOM_NONE | align);
         tcg_gen_addi_i64(clean_addr, clean_addr, 16);
 
         tp = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
         tcg_gen_st_i64(t1, tp, vofs + 8);
 
         tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
+        align = MO_UNALN;
     }
 
     /*
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
      */
     if (len_remain >= 8) {
         t0 = tcg_temp_new_i64();
-        tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+        tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
+                            MO_LEUQ | MO_ATOM_NONE | align);
+        align = MO_UNALN;
         tcg_gen_st_i64(t0, base, vofs + len_align);
         len_remain -= 8;
         len_align += 8;
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
         case 4:
         case 8:
             tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
-                                MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
+                                MO_LE | ctz32(len_remain)
+                                | MO_ATOM_NONE | align);
             break;
 
         case 6:
             t1 = tcg_temp_new_i64();
-            tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
+            tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
+                                MO_LEUL | MO_ATOM_NONE | align);
             tcg_gen_addi_i64(clean_addr, clean_addr, 4);
             tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
             tcg_gen_deposit_i64(t0, t0, t1, 32, 32);
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
 /* Similarly for stores.  */
 void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
-                 int len, int rn, int imm)
+                 int len, int rn, int imm, MemOp align)
 {
     int len_align = QEMU_ALIGN_DOWN(len, 16);
     int len_remain = len % 16;
@@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
             tcg_gen_ld_i64(t1, base, vofs + i + 8);
             tcg_gen_concat_i64_i128(t16, t0, t1);
             tcg_gen_qemu_st_i128(t16, clean_addr, midx,
-                                 MO_LE | MO_128 | MO_ATOM_NONE);
+                                 MO_LE | MO_128 | MO_ATOM_NONE | align);
             tcg_gen_addi_i64(clean_addr, clean_addr, 16);
         }
+        if (len_align) {
+            align = MO_UNALN;
+        }
     } else {
         TCGLabel *loop = gen_new_label();
         TCGv_ptr tp, i = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
         tcg_gen_addi_i64(clean_addr, clean_addr, 16);
 
         tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
+        align = MO_UNALN;
     }
 
     /* Predicate register stores can be any multiple of 2.  */
     if (len_remain >= 8) {
         t0 = tcg_temp_new_i64();
         tcg_gen_ld_i64(t0, base, vofs + len_align);
-        tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+        tcg_gen_qemu_st_i64(t0, clean_addr, midx,
+                            MO_LEUQ | MO_ATOM_NONE | align);
+        align = MO_UNALN;
         len_remain -= 8;
         len_align += 8;
         if (len_remain) {
@@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
         case 4:
         case 8:
             tcg_gen_qemu_st_i64(t0, clean_addr, midx,
-                                MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
+                                MO_LE | ctz32(len_remain)
+                                | MO_ATOM_NONE | align);
             break;
 
         case 6:
-            tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
+            tcg_gen_qemu_st_i64(t0, clean_addr, midx,
+                                MO_LEUL | MO_ATOM_NONE | align);
             tcg_gen_addi_i64(clean_addr, clean_addr, 4);
             tcg_gen_shri_i64(t0, t0, 32);
             tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
@@ -XXX,XX +XXX,XX @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = vec_full_reg_size(s);
         int off = vec_full_reg_offset(s, a->rd);
-        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     }
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = pred_full_reg_size(s);
         int off = pred_full_reg_offset(s, a->rd);
-        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_2 : MO_UNALN);
     }
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = vec_full_reg_size(s);
         int off = vec_full_reg_offset(s, a->rd);
-        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     }
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = pred_full_reg_size(s);
         int off = pred_full_reg_offset(s, a->rd);
-        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_2 : MO_UNALN);
     }
     return true;
 }
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-20-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      |  6 ++++++
 target/arm/tcg/translate-sme.c | 13 +++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ LDST1           1110000 111     st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4  \
 LDR             1110000 100 0 000000 .. 000 ..... 0 ....        @ldstr
 STR             1110000 100 1 000000 .. 000 ..... 0 ....        @ldstr
 
+&ldstzt0        rn
+@ldstzt0        ....... ... . ...... .. ... rn:5  .....         &ldstzt0
+
+LDR_zt0         1110000 100 0 111111 00 000 ..... 00000         @ldstzt0
+STR_zt0         1110000 100 1 111111 00 000 ..... 00000         @ldstzt0
+
 ### SME Add Vector to Array
 
 &adda           zad zn pm pn
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
 TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr)
 TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str)
 
+static bool do_ldst_zt0(DisasContext *s, arg_ldstzt0 *a, GenLdStR *fn)
+{
+    if (sme2_zt0_enabled_check(s)) {
+        fn(s, tcg_env, offsetof(CPUARMState, za_state.zt0),
+           sizeof_field(CPUARMState, za_state.zt0), a->rn, 0,
+           s->align_mem ? MO_ALIGN_16 : MO_UNALN);
+    }
+    return true;
+}
+
+TRANS_FEAT(LDR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_ldr)
+TRANS_FEAT(STR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_str)
+
 static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz,
                     gen_helper_gvec_4 *fn)
 {
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-21-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      |  5 +++++
 target/arm/tcg/translate-sme.c | 13 +++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ MOVA            11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5  \
 MOVA            11000000 11    00001 1 v:1 .. pg:3 0 za_imm:4 zr:5  \
                 &mova to_vec=1 rs=%mova_rs esz=4
 
+### SME Move into/from ZT0
+
+MOVT_rzt        1100 0000 0100 1100 0 off:3 00 11111 rt:5
+MOVT_ztr        1100 0000 0100 1110 0 off:3 00 11111 rt:5
+
 ### SME Memory
 
 &ldst           esz rs pg rn rm za_imm v:bool st:bool
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
     return true;
 }
 
+static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
+                    void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
+{
+    if (sme2_zt0_enabled_check(s)) {
+        func(cpu_reg(s, a->rt), tcg_env,
+             offsetof(CPUARMState, za_state.zt0) + a->off * 8);
+    }
+    return true;
+}
+
+TRANS_FEAT(MOVT_rzt, aa64_sme2, do_movt, a, tcg_gen_ld_i64)
+TRANS_FEAT(MOVT_ztr, aa64_sme2, do_movt, a, tcg_gen_st_i64)
+
 static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
 {
     typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Decode tile number and index offset beforehand and separately.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-22-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 46 +++++++++++++++++++++++-----------
 target/arm/tcg/translate-sme.c | 17 +++++--------
 2 files changed, 38 insertions(+), 25 deletions(-)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_zt0        11000000 01 001 00000000000 00000001
 ### SME Move into/from Array
 
 %mova_rs        13:2 !function=plus_12
-&mova           esz rs pg zr za_imm v:bool to_vec:bool
+&mova           esz rs pg zr za off v:bool to_vec:bool
 
-MOVA            11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4  \
-                &mova to_vec=0 rs=%mova_rs
-MOVA            11000000 11    00000 1 v:1 .. pg:3 zr:5 0 za_imm:4  \
-                &mova to_vec=0 rs=%mova_rs esz=4
+MOVA            11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4  \
+                &mova to_vec=0 rs=%mova_rs esz=0 za=0
+MOVA            11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3  \
+                &mova to_vec=0 rs=%mova_rs esz=1
+MOVA            11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2  \
+                &mova to_vec=0 rs=%mova_rs esz=2
+MOVA            11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1  \
+                &mova to_vec=0 rs=%mova_rs esz=3
+MOVA            11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4  \
+                &mova to_vec=0 rs=%mova_rs esz=4 off=0
 
-MOVA            11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5  \
-                &mova to_vec=1 rs=%mova_rs
-MOVA            11000000 11    00001 1 v:1 .. pg:3 0 za_imm:4 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=4
+MOVA            11000000 00 00001 0 v:1 .. pg:3 0 off:4      zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=0 za=0
+MOVA            11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=1
+MOVA            11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=2
+MOVA            11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=3
+MOVA            11000000 11 00001 1 v:1 .. pg:3 0 za:4       zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=4 off=0
 
 ### SME Move into/from ZT0
 
@@ -XXX,XX +XXX,XX @@ MOVT_ztr        1100 0000 0100 1110 0 off:3 00 11111 rt:5
 
 ### SME Memory
 
-&ldst           esz rs pg rn rm za_imm v:bool st:bool
+&ldst           esz rs pg rn rm za off v:bool st:bool
 
-LDST1           1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4  \
-                &ldst rs=%mova_rs
-LDST1           1110000 111     st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4  \
-                &ldst esz=4 rs=%mova_rs
+LDST1           1110000 0 00 st:1 rm:5 v:1 .. pg:3 rn:5 0 off:4  \
+                &ldst rs=%mova_rs esz=0 za=0
+LDST1           1110000 0 01 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:1 off:3  \
+                &ldst rs=%mova_rs esz=1
+LDST1           1110000 0 10 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:2 off:2  \
+                &ldst rs=%mova_rs esz=2
+LDST1           1110000 0 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:3 off:1  \
+                &ldst rs=%mova_rs esz=3
+LDST1           1110000 1 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:4  \
+                &ldst rs=%mova_rs esz=4 off=0
 
 &ldstr          rv rn imm
 @ldstr          ....... ... . ...... .. ... rn:5 . imm:4 \
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool sme2_zt0_enabled_check(DisasContext *s)
     return true;
 }
 
-/*
- * Resolve tile.size[index] to a host pointer, where tile and index
- * are always decoded together, dependent on the element size.
- */
+/* Resolve tile.size[rs+imm] to a host pointer. */
 static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
-                                int tile_index, bool vertical)
+                                int tile, int imm, bool vertical)
 {
-    int tile = tile_index >> (4 - esz);
-    int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz);
     int pos, len, offset;
     TCGv_i32 tmp;
     TCGv_ptr addr;
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     /* Compute the final index, which is Rs+imm. */
     tmp = tcg_temp_new_i32();
     tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
-    tcg_gen_addi_i32(tmp, tmp, index);
+    tcg_gen_addi_i32(tmp, tmp, imm);
 
     /* Prepare a power-of-two modulo via extraction of @len bits. */
     len = ctz32(streaming_vec_reg_size(s)) - esz;
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
     t_zr = vec_full_reg_ptr(s, a->zr);
     t_pg = pred_full_reg_ptr(s, a->pg);
 
@@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
     t_pg = pred_full_reg_ptr(s, a->pg);
     addr = tcg_temp_new_i64();
 
@@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
     }
 
     /* ZA[n] equates to ZA0H.B[n]. */
-    base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
+    base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
 
     fn(s, base, 0, svl, a->rn, imm * svl,
        s->align_mem ? MO_ALIGN_16 : MO_UNALN);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Prepare for more kinds of MOVA from SME2 by renaming the
existing SME1 MOVA to indicate tile to/from vector.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-23-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 42 +++++++++++++++++-----------------
 target/arm/tcg/translate-sme.c | 12 +++++-----
 2 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_zt0        11000000 01 001 00000000000 00000001
 ### SME Move into/from Array
 
 %mova_rs        13:2 !function=plus_12
-&mova           esz rs pg zr za off v:bool to_vec:bool
+&mova_p         esz rs pg zr za off v:bool
 
-MOVA            11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4  \
-                &mova to_vec=0 rs=%mova_rs esz=0 za=0
-MOVA            11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3  \
-                &mova to_vec=0 rs=%mova_rs esz=1
-MOVA            11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2  \
-                &mova to_vec=0 rs=%mova_rs esz=2
-MOVA            11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1  \
-                &mova to_vec=0 rs=%mova_rs esz=3
-MOVA            11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4  \
-                &mova to_vec=0 rs=%mova_rs esz=4 off=0
+MOVA_tz         11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4  \
+                &mova_p rs=%mova_rs esz=0 za=0
+MOVA_tz         11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3  \
+                &mova_p rs=%mova_rs esz=1
+MOVA_tz         11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2  \
+                &mova_p rs=%mova_rs esz=2
+MOVA_tz         11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1  \
+                &mova_p rs=%mova_rs esz=3
+MOVA_tz         11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4  \
+                &mova_p rs=%mova_rs esz=4 off=0
 
-MOVA            11000000 00 00001 0 v:1 .. pg:3 0 off:4      zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=0 za=0
-MOVA            11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=1
-MOVA            11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=2
-MOVA            11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=3
-MOVA            11000000 11 00001 1 v:1 .. pg:3 0 za:4       zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=4 off=0
+MOVA_zt         11000000 00 00001 0 v:1 .. pg:3 0 off:4      zr:5  \
+                &mova_p rs=%mova_rs esz=0 za=0
+MOVA_zt         11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5  \
+                &mova_p rs=%mova_rs esz=1
+MOVA_zt         11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5  \
+                &mova_p rs=%mova_rs esz=2
+MOVA_zt         11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5  \
+                &mova_p rs=%mova_rs esz=3
+MOVA_zt         11000000 11 00001 1 v:1 .. pg:3 0 za:4       zr:5  \
+                &mova_p rs=%mova_rs esz=4 off=0
 
 ### SME Move into/from ZT0
 
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
     return true;
 }
 
-static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
+static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
         gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h,
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
     TCGv_i32 t_desc;
     int svl;
 
-    if (!dc_isar_feature(aa64_sme, s)) {
-        return false;
-    }
     if (!sme_smza_enabled_check(s)) {
         return true;
     }
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
 
     if (a->v) {
         /* Vertical slice -- use sme mova helpers. */
-        if (a->to_vec) {
+        if (to_vec) {
             zc_fns[a->esz](t_zr, t_za, t_pg, t_desc);
         } else {
             cz_fns[a->esz](t_za, t_zr, t_pg, t_desc);
         }
     } else {
         /* Horizontal slice -- reuse sve sel helpers. */
-        if (a->to_vec) {
+        if (to_vec) {
             h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc);
         } else {
             h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc);
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
     return true;
 }
 
+TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false)
+TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true)
+
 static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
                     void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
 {
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Prepare for MOVA array to/from vector with multiple registers
by adding a div_len parameter, herein always 1, and a vec_mod
parameter, herein always 0.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-24-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sme.c | 47 +++++++++++++++++++++++-----------
 1 file changed, 32 insertions(+), 15 deletions(-)

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool sme2_zt0_enabled_check(DisasContext *s)
 
 /* Resolve tile.size[rs+imm] to a host pointer. */
 static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
-                                int tile, int imm, bool vertical)
+                                int tile, int imm, int div_len,
+                                int vec_mod, bool vertical)
 {
     int pos, len, offset;
     TCGv_i32 tmp;
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     /* Compute the final index, which is Rs+imm. */
     tmp = tcg_temp_new_i32();
     tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
+    /*
+     * Round the vector index down to a multiple of vec_mod if necessary.
+     * We do this before adding the offset, to handle cases like
+     * MOVA (tile to vector, 2 registers) where we want to call this
+     * several times in a loop with an increasing offset. We rely on
+     * the instruction encodings always forcing the initial offset in
+     * [rs + offset] to be a multiple of vec_mod. The pseudocode usually
+     * does the round-down after adding the offset rather than before,
+     * but MOVA is an exception.
+     */
+    if (vec_mod > 1) {
+        tcg_gen_andc_i32(tmp, tmp, tcg_constant_i32(vec_mod - 1));
+    }
     tcg_gen_addi_i32(tmp, tmp, imm);
 
     /* Prepare a power-of-two modulo via extraction of @len bits. */
-    len = ctz32(streaming_vec_reg_size(s)) - esz;
+    len = ctz32(streaming_vec_reg_size(s) / div_len) - esz;
 
     if (!len) {
         /*
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     return addr;
 }
 
+/* Resolve ZArray[rs+imm] to a host pointer. */
+static TCGv_ptr get_zarray(DisasContext *s, int rs, int imm,
+                           int div_len, int vec_mod)
+{
+    /* ZA[n] equates to ZA0H.B[n]. */
+    return get_tile_rowcol(s, MO_8, rs, 0, imm, div_len, vec_mod, false);
+}
+
 /*
  * Resolve tile.size[0] to a host pointer.
  * Used by e.g. outer product insns where we require the entire tile.
@@ -XXX,XX +XXX,XX @@ static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v);
     t_zr = vec_full_reg_ptr(s, a->zr);
     t_pg = pred_full_reg_ptr(s, a->pg);
 
@@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v);
     t_pg = pred_full_reg_ptr(s, a->pg);
     addr = tcg_temp_new_i64();
 
@@ -XXX,XX +XXX,XX @@ typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp);
 
 static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
 {
-    int svl = streaming_vec_reg_size(s);
-    int imm = a->imm;
-    TCGv_ptr base;
+    if (sme_za_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int imm = a->imm;
+        TCGv_ptr base = get_zarray(s, a->rv, imm, 1, 0);
 
-    if (!sme_za_enabled_check(s)) {
-        return true;
+        fn(s, base, 0, svl, a->rn, imm * svl,
+           s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     }
-
-    /* ZA[n] equates to ZA0H.B[n]. */
-    base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
-
-    fn(s, base, 0, svl, a->rn, imm * svl,
-       s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     return true;
 }
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-25-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h   | 1 +
 target/arm/cpu64.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
 
     /* Used to set the maximum vector length the cpu will support.  */
     uint32_t sve_max_vq;
+    uint32_t sme_max_vq;
 
 #ifdef CONFIG_USER_ONLY
     /* Used to set the default vector length at process start. */
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@ void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp)
     }
 
     cpu->sme_vq.map = vq_map;
+    cpu->sme_max_vq = 32 - clz32(vq_map);
 }
 
 static bool cpu_arm_get_sme(Object *obj, Error **errp)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-26-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  9 +++++
 target/arm/tcg/translate.h     |  1 +
 target/arm/tcg/sme.decode      | 37 ++++++++++++++++++
 target/arm/tcg/sme_helper.c    | 64 ++++++++++++++++++++++++++++++
 target/arm/tcg/translate-a64.c |  1 +
 target/arm/tcg/translate-sme.c | 71 ++++++++++++++++++++++++++++++++++
 6 files changed, 183 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-27-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate.h     |  5 +++++
 target/arm/tcg/sme.decode      | 12 ++++++++++++
 target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -XXX,XX +XXX,XX @@ static inline int plus_2(DisasContext *s, int x)
     return x + 2;
 }
 
+static inline int plus_8(DisasContext *s, int x)
+{
+    return x + 8;
+}
+
 static inline int plus_12(DisasContext *s, int x)
 {
     return x + 12;
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_zt0        11000000 01 001 00000000000 00000001
 ### SME Move into/from Array
 
 %mova_rs        13:2 !function=plus_12
+%mova_rv        13:2 !function=plus_8
+&mova_a         rv zr off
 &mova_p         esz rs pg zr za off v:bool
 &mova_t         esz rs zr za off v:bool
 
@@ -XXX,XX +XXX,XX @@ MOVA_zt4        11000000 10 00011 0 v:1 .. 001 000 za:2       zr:3 00 \
 MOVA_zt4        11000000 11 00011 0 v:1 .. 001 00 za:3        zr:3 00 \
                 &mova_t rs=%mova_rs esz=3 off=0
 
+MOVA_az2        11000000 00 00010 00 .. 010 zr:4  000 off:3  \
+                &mova_a rv=%mova_rv
+MOVA_az4        11000000 00 00010 00 .. 011 zr:3 0000 off:3  \
+                &mova_a rv=%mova_rv
+
+MOVA_za2        11000000 00 00011 00 .. 010 00 off:3 zr:4 0  \
+                &mova_a rv=%mova_rv
+MOVA_za4        11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \
+                &mova_a rv=%mova_rv
+
 ### SME Move into/from ZT0
 
 MOVT_rzt        1100 0000 0100 1100 0 off:3 00 11111 rt:5
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false)
 TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true)
 TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true)
 
+static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
+{
+    TCGv_ptr t_za;
+    int svl;
+
+    if (!sme_smza_enabled_check(s)) {
+        return true;
+    }
+
+    svl = streaming_vec_reg_size(s);
+    t_za = get_zarray(s, a->rv, a->off, n, 0);
+
+    for (int i = 0; i < n; ++i) {
+        int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+        int o_zr = vec_full_reg_offset(s, a->zr * n + i);
+
+        if (to_vec) {
+            tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl);
+        } else {
+            tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl);
+        }
+    }
+    return true;
+}
+
+TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false)
+TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false)
+TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true)
+TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true)
+
 static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
                     void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
 {
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-28-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  3 +++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 34 ++++++++++++++++++++++++----------
 target/arm/tcg/translate-sme.c |  2 ++
 4 files changed, 31 insertions(+), 10 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-29-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  4 ++++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 37 +++++++++++++++++++++++++---------
 target/arm/tcg/translate-sme.c |  2 ++
 4 files changed, 35 insertions(+), 10 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

To be used by both SVE2 and SME2.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-30-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.h |  4 ++++
 target/arm/tcg/gengvec64.c     | 11 +++++++++++
 target/arm/tcg/translate-sve.c |  8 +-------
 3 files changed, 16 insertions(+), 7 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-31-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  13 ++++
 target/arm/tcg/helper.h        |   8 ++
 target/arm/tcg/vec_internal.h  |   4 +
 target/arm/tcg/sme.decode      |  40 ++++++++++
 target/arm/tcg/helper-a64.c    |   2 +
 target/arm/tcg/neon_helper.c   |  30 ++++++++
 target/arm/tcg/translate-sme.c | 137 +++++++++++++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    |   7 ++
 8 files changed, 241 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-32-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 36 +++++++++++++++++++
 target/arm/tcg/translate-sme.c | 65 ++++++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ADD_n1         1100000 1 .. 10 .... 1010.0 11000 .... 0    @z2z_4x1
 
 SQDMULH_n1     1100000 1 .. 10 .... 1010.1 00000 .... 0    @z2z_2x1
 SQDMULH_n1     1100000 1 .. 10 .... 1010.1 00000 .... 0    @z2z_4x1
+
+### SME2 Multi-vector Multiple Vectors SVE Destructive
+
+%zm_ax2         17:4 !function=times_2
+%zm_ax4         18:3 !function=times_4
+
+@z2z_2x2        ....... . esz:2 . ....0 ....0. ..... .... . \
+                &z2z_en n=2 zdn=%zd_ax2 zm=%zm_ax2
+@z2z_4x4        ....... . esz:2 . ...00 ....1. ..... ...0 . \
+                &z2z_en n=4 zdn=%zd_ax4 zm=%zm_ax4
+
+SMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 0    @z2z_2x2
+SMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 0    @z2z_4x4
+UMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 1    @z2z_2x2
+UMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 1    @z2z_4x4
+SMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 0    @z2z_2x2
+SMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 0    @z2z_4x4
+UMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 1    @z2z_2x2
+UMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 1    @z2z_4x4
+
+FMAX_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 0    @z2z_2x2
+FMAX_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 0    @z2z_4x4
+FMIN_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 1    @z2z_2x2
+FMIN_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 1    @z2z_4x4
+FMAXNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 0    @z2z_2x2
+FMAXNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 0    @z2z_4x4
+FMINNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 1    @z2z_2x2
+FMINNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 1    @z2z_4x4
+
+SRSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 0    @z2z_2x2
+SRSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 0    @z2z_4x4
+URSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 1    @z2z_2x2
+URSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 1    @z2z_4x4
+
+SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_2x2
+SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_4x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl)
 TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl)
 TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh)
 
+static bool do_z2z_nn(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn)
+{
+    int esz, dn, dm, vsz, n;
+
+    if (!sme_sm_enabled_check(s)) {
+        return true;
+    }
+
+    esz = a->esz;
+    n = a->n;
+    dn = a->zdn;
+    dm = a->zm;
+    vsz = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; i++) {
+        int dofs = vec_full_reg_offset(s, dn + i);
+        int mofs = vec_full_reg_offset(s, dm + i);
+
+        fn(esz, dofs, dofs, mofs, vsz, vsz);
+    }
+    return true;
+}
+
+TRANS_FEAT(SMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smax)
+TRANS_FEAT(SMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smin)
+TRANS_FEAT(UMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umax)
+TRANS_FEAT(UMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umin)
+TRANS_FEAT(SRSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_srshl)
+TRANS_FEAT(URSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_urshl)
+TRANS_FEAT(SQDMULH_nn, aa64_sme2, do_z2z_nn, a, gen_gvec_sve2_sqdmulh)
+
 static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
                            gen_helper_gvec_3_ptr * const fns[4])
 {
@@ -XXX,XX +XXX,XX @@ static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
     return true;
 }
 
+static bool do_z2z_nn_fpst(DisasContext *s, arg_z2z_en *a,
+                           gen_helper_gvec_3_ptr * const fns[4])
+{
+    int esz = a->esz, n, dn, dm, vsz;
+    gen_helper_gvec_3_ptr *fn;
+    TCGv_ptr fpst;
+
+    if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) {
+        return false;
+    }
+    if (!sme_sm_enabled_check(s)) {
+        return true;
+    }
+
+    fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+    fn = fns[esz];
+    n = a->n;
+    dn = a->zdn;
+    dm = a->zm;
+    vsz = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; i++) {
+        int dofs = vec_full_reg_offset(s, dn + i);
+        int mofs = vec_full_reg_offset(s, dm + i);
+
+        tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn);
+    }
+    return true;
+}
+
 static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
     { gen_helper_gvec_fmax_b16,
       gen_helper_gvec_fmax_h,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
       gen_helper_gvec_ah_fmax_d },
 };
 TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah])
+TRANS_FEAT(FMAX_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmax[s->fpcr_ah])
 
 static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
     { gen_helper_gvec_fmin_b16,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
       gen_helper_gvec_ah_fmin_d },
 };
 TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah])
+TRANS_FEAT(FMIN_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmin[s->fpcr_ah])
 
 static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
     gen_helper_gvec_fmaxnum_b16,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
     gen_helper_gvec_fmaxnum_d,
 };
 TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm)
+TRANS_FEAT(FMAXNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmaxnm)
 
 static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
     gen_helper_gvec_fminnum_b16,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
     gen_helper_gvec_fminnum_d,
 };
 TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
+TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-33-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate.h     |  2 ++
 target/arm/tcg/sme.decode      | 15 +++++++++++++++
 target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -XXX,XX +XXX,XX @@ typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
                         uint32_t, uint32_t, uint32_t);
 typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
                         uint32_t, uint32_t, uint32_t);
+typedef void GVecGen3FnVar(unsigned, TCGv_ptr, uint32_t, TCGv_ptr, uint32_t,
+                           TCGv_ptr, uint32_t, uint32_t, uint32_t);
 
 /* Function prototype for gen_ functions for calling Neon helpers */
 typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32);
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ URSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 1    @z2z_4x4
 
 SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_2x2
 SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_4x4
+
+### SME2 Multi-vector Multiple and Single Array Vectors
+
+&azz_n          n off rv zn zm
+@azz_nx1_o3     ........ .... zm:4 ...... zn:5 .. off:3     &azz_n rv=%mova_rv
+
+ADD_azz_n1_s    11000001 0010 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=2
+ADD_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=4
+ADD_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=2
+ADD_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=4
+
+SUB_azz_n1_s    11000001 0010 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
+SUB_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
+SUB_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
+SUB_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
 };
 TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
 TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm)
+
+/* Add/Sub vector Z[m] to each Z[n*N] with result in ZA[d*N]. */
+static bool do_azz_n1(DisasContext *s, arg_azz_n *a, int esz,
+                      GVecGen3FnVar *fn)
+{
+    TCGv_ptr t_za;
+    int svl, n, o_zm;
+
+    if (!sme_smza_enabled_check(s)) {
+        return true;
+    }
+
+    n = a->n;
+    t_za = get_zarray(s, a->rv, a->off, n, 0);
+    o_zm = vec_full_reg_offset(s, a->zm);
+    svl = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; ++i) {
+        int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+        int o_zn = vec_full_reg_offset(s, (a->zn + i) % 32);
+
+        fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl);
+    }
+    return true;
+}
+
+TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var)
+TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-34-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 20 ++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Indicate whether to use FPST_FPCR or FPST_ZA via bit 2 of
simd_data(desc).  For SVE, this bit remains zero.
For do_FMLAL_zzzw, this requires no change.
For do_FMLAL_zzxw, move the index up one bit.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-35-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 2 +-
 target/arm/tcg/vec_helper.c    | 8 +++++---
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel)
 {
     return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzxw_s,
                              a->rd, a->rn, a->rm, a->ra,
-                             (a->index << 2) | (sel << 1) | sub, tcg_env);
+                             (a->index << 3) | (sel << 1) | sub, tcg_env);
 }
 
 TRANS_FEAT(FMLALB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, false)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va,
     intptr_t i, oprsz = simd_oprsz(desc);
     bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
     intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
-    float_status *status = &env->vfp.fp_status[FPST_A64];
+    bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+    float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
     bool fz16 = env->vfp.fpcr & FPCR_FZ16;
     int negx = 0, negf = 0;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va,
     intptr_t i, j, oprsz = simd_oprsz(desc);
     bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
     intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
-    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16);
-    float_status *status = &env->vfp.fp_status[FPST_A64];
+    bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 3, 3) * sizeof(float16);
+    float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
     bool fz16 = env->vfp.fpcr & FPCR_FZ16;
     int negx = 0, negf = 0;
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-36-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h     |  8 +++++
 target/arm/tcg/vec_helper.c | 58 ++++++++++++++++++++++++++++---------
 2 files changed, 53 insertions(+), 13 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-37-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 71 ++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 98 ++++++++++++++++++++++++++++++++++
 2 files changed, 169 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ SUB_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
 SUB_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
 SUB_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
 
+%off3_x2        0:3 !function=times_2
+%off2_x2        0:2 !function=times_2
+
+@azz_nx1_o3x2   ........ ... . zm:4 . .. ... zn:5 .. ...    \
+                &azz_n off=%off3_x2 rv=%mova_rv
+@azz_nx1_o2x2   ........ ... . zm:4 . .. ... zn:5 ... ..    \
+                &azz_n off=%off2_x2 rv=%mova_rv
+
+FMLAL_n1        11000001 001 0 .... 0 .. 011 ..... 00 ...   @azz_nx1_o3x2 n=1
+FMLAL_n1        11000001 001 0 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=2
+FMLAL_n1        11000001 001 1 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=4
+
+FMLSL_n1        11000001 001 0 .... 0 .. 011 ..... 01 ...   @azz_nx1_o3x2 n=1
+FMLSL_n1        11000001 001 0 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=2
+FMLSL_n1        11000001 001 1 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=4
+
+BFMLAL_n1       11000001 001 0 .... 0 .. 011 ..... 10 ...   @azz_nx1_o3x2 n=1
+BFMLAL_n1       11000001 001 0 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=2
+BFMLAL_n1       11000001 001 1 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=4
+
+BFMLSL_n1       11000001 001 0 .... 0 .. 011 ..... 11 ...   @azz_nx1_o3x2 n=1
+BFMLSL_n1       11000001 001 0 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=2
+BFMLSL_n1       11000001 001 1 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ SUB_azz_nn_s    11000001 101 ....0 0 .. 110 ....0 11 ...    @azz_2x2_o3
 SUB_azz_nn_s    11000001 101 ...01 0 .. 110 ...00 11 ...    @azz_4x4_o3
 SUB_azz_nn_d    11000001 111 ....0 0 .. 110 ....0 11 ...    @azz_2x2_o3
 SUB_azz_nn_d    11000001 111 ...01 0 .. 110 ...00 11 ...    @azz_4x4_o3
+
+@azz_2x2_o2x2   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off2_x2
+@azz_4x4_o2x2   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off2_x2
+
+FMLAL_nn        11000001 101 ....0 0 .. 010 ....0 000 ..    @azz_2x2_o2x2
+FMLAL_nn        11000001 101 ...01 0 .. 010 ...00 000 ..    @azz_4x4_o2x2
+
+FMLSL_nn        11000001 101 ....0 0 .. 010 ....0 010 ..    @azz_2x2_o2x2
+FMLSL_nn        11000001 101 ...01 0 .. 010 ...00 010 ..    @azz_4x4_o2x2
+
+BFMLAL_nn       11000001 101 ....0 0 .. 010 ....0 100 ..    @azz_2x2_o2x2
+BFMLAL_nn       11000001 101 ...01 0 .. 010 ...00 100 ..    @azz_4x4_o2x2
+
+BFMLSL_nn       11000001 101 ....0 0 .. 010 ....0 110 ..    @azz_2x2_o2x2
+BFMLSL_nn       11000001 101 ...01 0 .. 010 ...00 110 ..    @azz_4x4_o2x2
+
+### SME2 Multi-vector Indexed
+
+&azx_n          n off rv zn zm idx
+
+%idx3_15_10     15:1 10:2
+%idx2_10_2      10:2 2:1
+
+@azx_1x1_o3x2   ........ .... zm:4 . .. . .. zn:5 .. ...    \
+                &azx_n n=1 rv=%mova_rv off=%off3_x2 idx=%idx3_15_10
+@azx_2x1_o2x2   ........ .... zm:4 . .. . .. ..... .. ...   \
+                &azx_n n=2 rv=%mova_rv off=%off2_x2 zn=%zn_ax2 idx=%idx2_10_2
+@azx_4x1_o2x2   ........ .... zm:4 . .. . .. ..... .. ...   \
+                &azx_n n=4 rv=%mova_rv off=%off2_x2 zn=%zn_ax4 idx=%idx2_10_2
+
+FMLAL_nx        11000001 1000 .... . .. 1 .. ..... 00 ...   @azx_1x1_o3x2
+FMLAL_nx        11000001 1001 .... 0 .. 1 .. ....0 00 ...   @azx_2x1_o2x2
+FMLAL_nx        11000001 1001 .... 1 .. 1 .. ...00 00 ...   @azx_4x1_o2x2
+
+FMLSL_nx        11000001 1000 .... . .. 1 .. ..... 01 ...   @azx_1x1_o3x2
+FMLSL_nx        11000001 1001 .... 0 .. 1 .. ....0 01 ...   @azx_2x1_o2x2
+FMLSL_nx        11000001 1001 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_o2x2
+
+BFMLAL_nx       11000001 1000 .... . .. 1 .. ..... 10 ...   @azx_1x1_o3x2
+BFMLAL_nx       11000001 1001 .... 0 .. 1 .. ....0 10 ...   @azx_2x1_o2x2
+BFMLAL_nx       11000001 1001 .... 1 .. 1 .. ...00 10 ...   @azx_4x1_o2x2
+
+BFMLSL_nx       11000001 1000 .... . .. 1 .. ..... 11 ...   @azx_1x1_o3x2
+BFMLSL_nx       11000001 1001 .... 0 .. 1 .. ....0 11 ...   @azx_2x1_o2x2
+BFMLSL_nx       11000001 1001 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_o2x2
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var)
 TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var)
 TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var)
 TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var)
+
+/*
+ * Expand array multi-vector single (n1), array multi-vector (nn),
+ * and array multi-vector indexed (nx), for floating-point accumulate.
+ *   multi: true for nn, false for n1.
+ *   fpst: >= 0 to set ptr argument for FPST_*, < 0 for ENV.
+ *   data: stuff for simd_data, including any index.
+ */
+#define FPST_ENV  -1
+
+static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel,
+                          int rv, int off, int zn, int zm,
+                          int data, int shsel, bool multi, int fpst,
+                          gen_helper_gvec_4_ptr *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / nreg;
+        TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+        TCGv_ptr t, ptr;
+
+        if (fpst >= 0) {
+            ptr = fpstatus_ptr(fpst);
+        } else {
+            ptr = tcg_env;
+        }
+        t = tcg_temp_new_ptr();
+
+        for (int r = 0; r < nreg; ++r) {
+            TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+            TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+            for (int i = 0; i < nsel; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                int desc = simd_desc(svl, svl, data | (i << shsel));
+
+                tcg_gen_addi_ptr(t, t_za, o_za);
+                fn(t, t_zn, t_zm, t, ptr, tcg_constant_i32(desc));
+            }
+
+            /*
+             * For multiple-and-single vectors, Zn may wrap.
+             * For multiple vectors, both Zn and Zm are aligned.
+             */
+            zn = (zn + 1) % 32;
+            zm += multi;
+        }
+    }
+    return true;
+}
+
+static bool do_fmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         (1 << 2) | sub, 1,
+                         multi, FPST_ENV, gen_helper_sve2_fmlal_zzzw_s);
+}
+
+TRANS_FEAT(FMLAL_n1, aa64_sme2, do_fmlal, a, false, false)
+TRANS_FEAT(FMLSL_n1, aa64_sme2, do_fmlal, a, true, false)
+TRANS_FEAT(FMLAL_nn, aa64_sme2, do_fmlal, a, false, true)
+TRANS_FEAT(FMLSL_nn, aa64_sme2, do_fmlal, a, true, true)
+
+static bool do_fmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         (a->idx << 3) | (1 << 2) | sub, 1,
+                         false, FPST_ENV, gen_helper_sve2_fmlal_zzxw_s);
+}
+
+TRANS_FEAT(FMLAL_nx, aa64_sme2, do_fmlal_nx, a, false)
+TRANS_FEAT(FMLSL_nx, aa64_sme2, do_fmlal_nx, a, true)
+
+static bool do_bfmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         0, 0, multi, FPST_ZA,
+                         (!sub ? gen_helper_gvec_bfmlal
+                          : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl
+                          : gen_helper_gvec_bfmlsl));
+}
+
+TRANS_FEAT(BFMLAL_n1, aa64_sme2, do_bfmlal, a, false, false)
+TRANS_FEAT(BFMLSL_n1, aa64_sme2, do_bfmlal, a, true, false)
+TRANS_FEAT(BFMLAL_nn, aa64_sme2, do_bfmlal, a, false, true)
+TRANS_FEAT(BFMLSL_nn, aa64_sme2, do_bfmlal, a, true, true)
+
+static bool do_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         a->idx << 1, 0, false, FPST_ZA,
+                         !sub ? gen_helper_gvec_bfmlal_idx
+                         : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl_idx
+                         : gen_helper_gvec_bfmlsl_idx);
+}
+
+TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false)
+TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-38-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  5 ++++
 target/arm/tcg/sme.decode      | 14 +++++++++++
 target/arm/tcg/sve.decode      |  7 ++++--
 target/arm/tcg/sme_helper.c    | 44 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 18 ++++++++++++++
 target/arm/tcg/translate-sve.c |  5 ++++
 6 files changed, 91 insertions(+), 2 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-39-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      |  9 +++++++++
 target/arm/tcg/translate-sme.c | 17 +++++++++++++++++
 2 files changed, 26 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-40-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  2 ++
 target/arm/tcg/helper.h        |  2 ++
 target/arm/tcg/sme.decode      |  3 +++
 target/arm/tcg/sme_helper.c    | 30 ++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 24 +++++++++++++++++++++
 target/arm/tcg/vec_helper.c    | 39 ++++++++++++++++++++++++++++++++++
 6 files changed, 100 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Emphasize that these are 4-way dot products.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-41-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h         | 22 +++++++++++-----------
 target/arm/tcg/translate-a64.c  | 14 +++++++-------
 target/arm/tcg/translate-neon.c | 14 +++++++-------
 target/arm/tcg/translate-sve.c  | 18 +++++++++---------
 target/arm/tcg/vec_helper.c     | 22 +++++++++++-----------
 5 files changed, 45 insertions(+), 45 deletions(-)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_4h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_udot_idx_4h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool do_dot_vector_env(DisasContext *s, arg_qrrr_e *a,
     return true;
 }
 
-TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b)
-TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b)
-TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b)
+TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_4b)
+TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_4b)
 TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfdot)
 TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfmmla)
 TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b)
@@ -XXX,XX +XXX,XX @@ static bool do_dot_vector_idx_env(DisasContext *s, arg_qrrx_e *a,
     return true;
 }
 
-TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b)
-TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b)
+TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_4b)
 TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
-           gen_helper_gvec_sudot_idx_b)
+           gen_helper_gvec_sudot_idx_4b)
 TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
-           gen_helper_gvec_usdot_idx_b)
+           gen_helper_gvec_usdot_idx_4b)
 TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx_env, a,
            gen_helper_gvec_bfdot_idx)
 
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
-                        gen_helper_gvec_sdot_b);
+                        gen_helper_gvec_sdot_4b);
 }
 
 static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
-                        gen_helper_gvec_udot_b);
+                        gen_helper_gvec_udot_4b);
 }
 
 static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
-                        gen_helper_gvec_usdot_b);
+                        gen_helper_gvec_usdot_4b);
 }
 
 static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_sdot_idx_b);
+                        gen_helper_gvec_sdot_idx_4b);
 }
 
 static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_udot_idx_b);
+                        gen_helper_gvec_udot_idx_4b);
 }
 
 static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_usdot_idx_b);
+                        gen_helper_gvec_usdot_idx_4b);
 }
 
 static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_sudot_idx_b);
+                        gen_helper_gvec_sudot_idx_4b);
 }
 
 static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin)
 #undef DO_ZZI
 
 static gen_helper_gvec_4 * const dot_fns[2][2] = {
-    { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h },
-    { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h }
+    { gen_helper_gvec_sdot_4b, gen_helper_gvec_sdot_4h },
+    { gen_helper_gvec_udot_4b, gen_helper_gvec_udot_4h }
 };
 TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
            dot_fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0)
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
  */
 
 TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_sdot_idx_b, a)
+           gen_helper_gvec_sdot_idx_4b, a)
 TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_sdot_idx_h, a)
+           gen_helper_gvec_sdot_idx_4h, a)
 TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_udot_idx_b, a)
+           gen_helper_gvec_udot_idx_4b, a)
 TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_udot_idx_h, a)
+           gen_helper_gvec_udot_idx_4h, a)
 
 TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_sudot_idx_b, a)
+           gen_helper_gvec_sudot_idx_4b, a)
 TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_usdot_idx_b, a)
+           gen_helper_gvec_usdot_idx_4b, a)
 
 #define DO_SVE2_RRX(NAME, FUNC) \
     TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC,          \
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
            sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot)
 
 TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
-           a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0)
+           a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0)
 
 TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
                         gen_helper_crypto_aesmc, a->rd, a->rd, 0)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
     clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
 
-DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t)
-DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t)
-DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t)
-DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t)
-DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t)
+DO_DOT(gvec_sdot_4b, int32_t, int8_t, int8_t)
+DO_DOT(gvec_udot_4b, uint32_t, uint8_t, uint8_t)
+DO_DOT(gvec_usdot_4b, uint32_t, uint8_t, int8_t)
+DO_DOT(gvec_sdot_4h, int64_t, int16_t, int16_t)
+DO_DOT(gvec_udot_4h, uint64_t, uint16_t, uint16_t)
 
 #define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
     clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
 
-DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4)
-DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4)
-DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4)
-DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4)
-DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, H8)
-DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, H8)
+DO_DOT_IDX(gvec_sdot_idx_4b, int32_t, int8_t, int8_t, H4)
+DO_DOT_IDX(gvec_udot_idx_4b, uint32_t, uint8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_sudot_idx_4b, int32_t, int8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4)
+DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8)
+DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8)
 
 void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
                          float_status *fpst, uint32_t desc)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-42-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        |  8 ++++
 target/arm/tcg/sme.decode      | 63 ++++++++++++++++++++++++-
 target/arm/tcg/translate-sme.c | 85 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    | 51 ++++++++++++++++++++
 4 files changed, 206 insertions(+), 1 deletion(-)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_sdot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG,
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_2h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_2h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ FDOT_n1         11000001 001 1 .... 0 .. 100 ..... 00 ...   @azz_nx1_o3 n=4
 BFDOT_n1        11000001 001 0 .... 0 .. 100 ..... 10 ...   @azz_nx1_o3 n=2
 BFDOT_n1        11000001 001 1 .... 0 .. 100 ..... 10 ...   @azz_nx1_o3 n=4
 
+USDOT_n1        11000001 001 0 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=2
+USDOT_n1        11000001 001 1 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=4
+
+SUDOT_n1        11000001 001 0 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=2
+SUDOT_n1        11000001 001 1 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=4
+
+SDOT_n1_4b      11000001 001 0 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=2
+SDOT_n1_4b      11000001 001 1 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=4
+SDOT_n1_4h      11000001 011 0 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=2
+SDOT_n1_4h      11000001 011 1 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=4
+SDOT_n1_2h      11000001 011 0 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=2
+SDOT_n1_2h      11000001 011 1 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=4
+
+UDOT_n1_4b      11000001 001 0 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=2
+UDOT_n1_4b      11000001 001 1 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=4
+UDOT_n1_4h      11000001 011 0 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=2
+UDOT_n1_4h      11000001 011 1 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=4
+UDOT_n1_2h      11000001 011 0 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=2
+UDOT_n1_2h      11000001 011 1 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ FDOT_nn         11000001 101 ...01 0 .. 100 ...00 00 ...    @azz_4x4_o3
 BFDOT_nn        11000001 101 ....0 0 .. 100 ....0 10 ...    @azz_2x2_o3
 BFDOT_nn        11000001 101 ...01 0 .. 100 ...00 10 ...    @azz_4x4_o3
 
+USDOT_nn        11000001 101 ....0 0 .. 101 ....0 01 ...    @azz_2x2_o3
+USDOT_nn        11000001 101 ...01 0 .. 101 ...00 01 ...    @azz_4x4_o3
+
+SDOT_nn_4b      11000001 101 ....0 0 .. 101 ....0 00 ...    @azz_2x2_o3
+SDOT_nn_4b      11000001 101 ...01 0 .. 101 ...00 00 ...    @azz_4x4_o3
+SDOT_nn_4h      11000001 111 ....0 0 .. 101 ....0 00 ...    @azz_2x2_o3
+SDOT_nn_4h      11000001 111 ...01 0 .. 101 ...00 00 ...    @azz_4x4_o3
+SDOT_nn_2h      11000001 111 ....0 0 .. 101 ....0 01 ...    @azz_2x2_o3
+SDOT_nn_2h      11000001 111 ...01 0 .. 101 ...00 01 ...    @azz_4x4_o3
+
+UDOT_nn_4b      11000001 101 ....0 0 .. 101 ....0 10 ...    @azz_2x2_o3
+UDOT_nn_4b      11000001 101 ...01 0 .. 101 ...00 10 ...    @azz_4x4_o3
+UDOT_nn_4h      11000001 111 ....0 0 .. 101 ....0 10 ...    @azz_2x2_o3
+UDOT_nn_4h      11000001 111 ...01 0 .. 101 ...00 10 ...    @azz_4x4_o3
+UDOT_nn_2h      11000001 111 ....0 0 .. 101 ....0 11 ...    @azz_2x2_o3
+UDOT_nn_2h      11000001 111 ...01 0 .. 101 ...00 11 ...    @azz_4x4_o3
+
 ### SME2 Multi-vector Indexed
 
 &azx_n          n off rv zn zm idx
@@ -XXX,XX +XXX,XX @@ BFMLSL_nx       11000001 1001 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_o2x2
 @azx_2x1_i2_o3  ........ .... zm:4 . .. . idx:2 .... ... off:3 \
                 &azx_n n=2 rv=%mova_rv zn=%zn_ax2
 @azx_4x1_i2_o3  ........ .... zm:4 . .. . idx:2 .... ... off:3 \
-                &azx_n n=2 rv=%mova_rv zn=%zn_ax4
+                &azx_n n=4 rv=%mova_rv zn=%zn_ax4
+@azx_2x1_i1_o3  ........ .... zm:4 . .. .. idx:1 .... ... off:3 \
+                &azx_n n=2 rv=%mova_rv zn=%zn_ax2
+@azx_4x1_i1_o3  ........ .... zm:4 . .. .. idx:1 .... ... off:3 \
+                &azx_n n=4 rv=%mova_rv zn=%zn_ax4
 
 FDOT_nx         11000001 0101 .... 0 .. 1 .. ....0 01 ...   @azx_2x1_i2_o3
 FDOT_nx         11000001 0101 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_i2_o3
@@ -XXX,XX +XXX,XX @@ BFDOT_nx        11000001 0101 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_i2_o3
 
 FVDOT           11000001 0101 .... 0 .. 0 .. ....0 01 ...   @azx_2x1_i2_o3
 BFVDOT          11000001 0101 .... 0 .. 0 .. ....0 11 ...   @azx_2x1_i2_o3
+
+SDOT_nx_2h      11000001 0101 .... 0 .. 1 .. ....0 00 ...   @azx_2x1_i2_o3
+SDOT_nx_2h      11000001 0101 .... 1 .. 1 .. ...00 00 ...   @azx_4x1_i2_o3
+SDOT_nx_4b      11000001 0101 .... 0 .. 1 .. ....1 00 ...   @azx_2x1_i2_o3
+SDOT_nx_4b      11000001 0101 .... 1 .. 1 .. ...01 00 ...   @azx_4x1_i2_o3
+SDOT_nx_4h      11000001 1101 .... 0 .. 00 . ....0 01 ...   @azx_2x1_i1_o3
+SDOT_nx_4h      11000001 1101 .... 1 .. 00 . ...00 01 ...   @azx_4x1_i1_o3
+
+UDOT_nx_2h      11000001 0101 .... 0 .. 1 .. ....0 10 ...   @azx_2x1_i2_o3
+UDOT_nx_2h      11000001 0101 .... 1 .. 1 .. ...00 10 ...   @azx_4x1_i2_o3
+UDOT_nx_4b      11000001 0101 .... 0 .. 1 .. ....1 10 ...   @azx_2x1_i2_o3
+UDOT_nx_4b      11000001 0101 .... 1 .. 1 .. ...01 10 ...   @azx_4x1_i2_o3
+UDOT_nx_4h      11000001 1101 .... 0 .. 00 . ....0 11 ...   @azx_2x1_i1_o3
+UDOT_nx_4h      11000001 1101 .... 1 .. 00 . ...00 11 ...   @azx_4x1_i1_o3
+
+USDOT_nx        11000001 0101 .... 0 .. 1 .. ....1 01 ...   @azx_2x1_i2_o3
+USDOT_nx        11000001 0101 .... 1 .. 1 .. ...01 01 ...   @azx_4x1_i2_o3
+
+SUDOT_nx        11000001 0101 .... 0 .. 1 .. ....1 11 ...   @azx_2x1_i2_o3
+SUDOT_nx        11000001 0101 .... 1 .. 1 .. ...01 11 ...   @azx_4x1_i2_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
 
 TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
 TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
+
+/*
+ * Expand array multi-vector single (n1), array multi-vector (nn),
+ * and array multi-vector indexed (nx), for integer accumulate.
+ *   multi: true for nn, false for n1.
+ *   data: stuff for simd_data, including any index.
+ */
+static bool do_azz_acc(DisasContext *s, int nreg, int nsel,
+                       int rv, int off, int zn, int zm,
+                       int data, int shsel, bool multi,
+                       gen_helper_gvec_4 *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / nreg;
+        TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+        TCGv_ptr t = tcg_temp_new_ptr();
+
+        for (int r = 0; r < nreg; ++r) {
+            TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+            TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+            for (int i = 0; i < nsel; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                int desc = simd_desc(svl, svl, data | (i << shsel));
+
+                tcg_gen_addi_ptr(t, t_za, o_za);
+                fn(t, t_zn, t_zm, t, tcg_constant_i32(desc));
+            }
+
+            /*
+             * For multiple-and-single vectors, Zn may wrap.
+             * For multiple vectors, both Zn and Zm are aligned.
+             */
+            zn = (zn + 1) % 32;
+            zm += multi;
+        }
+    }
+    return true;
+}
+
+static bool do_dot(DisasContext *s, arg_azz_n *a, bool multi,
+                   gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                      0, 0, multi, fn);
+}
+
+static void gen_helper_gvec_sudot_4b(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m,
+                                     TCGv_ptr a, TCGv_i32 desc)
+{
+    gen_helper_gvec_usdot_4b(d, m, n, a, desc);
+}
+
+TRANS_FEAT(USDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_usdot_4b)
+TRANS_FEAT(SUDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_sudot_4b)
+TRANS_FEAT(SDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_2h)
+TRANS_FEAT(UDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_2h)
+TRANS_FEAT(SDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_4b)
+TRANS_FEAT(SDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_sdot_4h)
+TRANS_FEAT(UDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_udot_4h)
+
+TRANS_FEAT(USDOT_nn, aa64_sme2, do_dot, a, true, gen_helper_gvec_usdot_4b)
+TRANS_FEAT(SDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_2h)
+TRANS_FEAT(UDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_2h)
+TRANS_FEAT(SDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_4b)
+TRANS_FEAT(SDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_sdot_4h)
+TRANS_FEAT(UDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_udot_4h)
+
+static bool do_dot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                      a->idx, 0, false, fn);
+}
+
+TRANS_FEAT(USDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_usdot_idx_4b)
+TRANS_FEAT(SUDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sudot_idx_4b)
+TRANS_FEAT(SDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_2h)
+TRANS_FEAT(UDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_2h)
+TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b)
+TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h)
+TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4)
 DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8)
 DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8)
 
+#undef DO_DOT
+#undef DO_DOT_IDX
+
+/* Similar for 2-way dot product */
+#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i, opr_sz = simd_oprsz(desc);                                \
+    TYPED *d = vd, *a = va;                                               \
+    TYPEN *n = vn;                                                        \
+    TYPEM *m = vm;                                                        \
+    for (i = 0; i < opr_sz / sizeof(TYPED); ++i) {                        \
+        d[i] = (a[i] +                                                    \
+                (TYPED)n[i * 2 + 0] * m[i * 2 + 0] +                      \
+                (TYPED)n[i * 2 + 1] * m[i * 2 + 1]);                      \
+    }                                                                     \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                              \
+}
+
+#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i = 0, opr_sz = simd_oprsz(desc);                            \
+    intptr_t opr_sz_n = opr_sz / sizeof(TYPED);                           \
+    intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n);                  \
+    intptr_t index = simd_data(desc);                                     \
+    TYPED *d = vd, *a = va;                                               \
+    TYPEN *n = vn;                                                        \
+    TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 2;                       \
+    do {                                                                  \
+        TYPED m0 = m_indexed[i * 2 + 0];                                  \
+        TYPED m1 = m_indexed[i * 2 + 1];                                  \
+        do {                                                              \
+            d[i] = (a[i] +                                                \
+                    n[i * 2 + 0] * m0 +                                   \
+                    n[i * 2 + 1] * m1);                                   \
+        } while (++i < segend);                                           \
+        segend = i + (16 / sizeof(TYPED));                                \
+    } while (i < opr_sz_n);                                               \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                              \
+}
+
+DO_DOT(gvec_sdot_2h, int32_t, int16_t, int16_t)
+DO_DOT(gvec_udot_2h, uint32_t, uint16_t, uint16_t)
+
+DO_DOT_IDX(gvec_sdot_idx_2h, int32_t, int16_t, int16_t, H4)
+DO_DOT_IDX(gvec_udot_idx_2h, uint32_t, uint16_t, uint16_t, H4)
+
+#undef DO_DOT
+#undef DO_DOT_IDX
+
 void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
                          float_status *fpst, uint32_t desc)
 {
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Emphasize the 4-way nature of these dot products.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-43-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      | 12 ++++++------
 target/arm/tcg/translate-sve.c | 12 ++++++------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ CDOT_zzzz       01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5  ra=%reg_movprfx
 #### SVE Multiply - Indexed
 
 # SVE integer dot product (indexed)
-SDOT_zzxw_s     01000100 10 1 ..... 000000 ..... .....   @rrxr_2 esz=2
-SDOT_zzxw_d     01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
-UDOT_zzxw_s     01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
-UDOT_zzxw_d     01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
+SDOT_zzxw_4s    01000100 10 1 ..... 000000 ..... .....   @rrxr_2 esz=2
+SDOT_zzxw_4d    01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
+UDOT_zzxw_4s    01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
+UDOT_zzxw_4d    01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
 # SVE2 integer multiply-add (indexed)
 MLA_zzxz_h      01000100 0. 1 ..... 000010 ..... .....   @rrxr_3 esz=1
@@ -XXX,XX +XXX,XX @@ SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... .....   @rrxr_2 esz=2
 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... .....   @rrxr_1 esz=3
 
 # SVE mixed sign dot product (indexed)
-USDOT_zzxw_s    01000100 10 1 ..... 000110 ..... .....   @rrxr_2 esz=2
-SUDOT_zzxw_s    01000100 10 1 ..... 000111 ..... .....   @rrxr_2 esz=2
+USDOT_zzxw_4s   01000100 10 1 ..... 000110 ..... .....   @rrxr_2 esz=2
+SUDOT_zzxw_4s   01000100 10 1 ..... 000111 ..... .....   @rrxr_2 esz=2
 
 # SVE2 saturating multiply-add (indexed)
 SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... .....   @rrxr_3a esz=2
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
  * SVE Multiply - Indexed
  */
 
-TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_sdot_idx_4b, a)
-TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_sdot_idx_4h, a)
-TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(UDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_udot_idx_4b, a)
-TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(UDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_udot_idx_4h, a)
 
-TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_sudot_idx_4b, a)
-TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_usdot_idx_4b, a)
 
 #define DO_SVE2_RRX(NAME, FUNC) \
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Rename to USDOT_zzzz_4s and force size=2 during decode.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-44-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      | 2 +-
 target/arm/tcg/translate-sve.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 
 ## SVE mixed sign dot product
 
-USDOT_zzzz      01000100 .. 0 ..... 011 110 ..... .....  @rda_rn_rm
+USDOT_zzzz_4s   01000100 10 0 ..... 011 110 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating point matrix multiply accumulate
 BFMMLA          01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=1
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4 * const sqrdcmlah_fns[] = {
 TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
            sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot)
 
-TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
-           a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0)
+TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
+           gen_helper_gvec_usdot_4b, a, 0)
 
 TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
                         gen_helper_crypto_aesmc, a->rd, a->rd, 0)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-45-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  8 +++++++-
 target/arm/tcg/translate-sve.c | 10 ++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SDOT_zzxw_4d    01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
 UDOT_zzxw_4s    01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
 UDOT_zzxw_4d    01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
+SDOT_zzxw_2s    01000100 10 0 ..... 110010 ..... .....   @rrxr_2 esz=2
+UDOT_zzxw_2s    01000100 10 0 ..... 110011 ..... .....   @rrxr_2 esz=2
+
 # SVE2 integer multiply-add (indexed)
 MLA_zzxz_h      01000100 0. 1 ..... 000010 ..... .....   @rrxr_3 esz=1
 MLA_zzxz_s      01000100 10 1 ..... 000010 ..... .....   @rrxr_2 esz=2
@@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw     01000100 .. 0 ..... 010 111 ..... .....  @rda_rn_rm
 CMLA_zzzz       01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5  ra=%reg_movprfx
 SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 
-## SVE mixed sign dot product
+## SVE dot product
+
+SDOT_zzzz_2s    01000100 00 0 ..... 110 010 ..... .....  @rda_rn_rm_ex esz=2
+UDOT_zzzz_2s    01000100 00 0 ..... 110 011 ..... .....  @rda_rn_rm_ex esz=2
 
 USDOT_zzzz_4s   01000100 10 0 ..... 011 110 ..... .....  @rda_rn_rm_ex esz=2
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
 TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_usdot_idx_4b, a)
 
+TRANS_FEAT(SDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz,
+           gen_helper_gvec_sdot_idx_2h, a)
+TRANS_FEAT(UDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz,
+           gen_helper_gvec_udot_idx_2h, a)
+
 #define DO_SVE2_RRX(NAME, FUNC) \
     TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC,          \
                a->rd, a->rn, a->rm, a->index)
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
 TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
            gen_helper_gvec_usdot_4b, a, 0)
 
+TRANS_FEAT(SDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz,
+           gen_helper_gvec_sdot_2h, a, 0)
+TRANS_FEAT(UDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz,
+           gen_helper_gvec_udot_2h, a, 0)
+
 TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
                         gen_helper_crypto_aesmc, a->rd, a->rd, 0)
 TRANS_FEAT_NONSTREAMING(AESIMC, aa64_sve2_aes, gen_gvec_ool_zz,
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-46-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 11 +++++++++
 target/arm/tcg/sme.decode      | 11 +++++++++
 target/arm/tcg/sme_helper.c    | 42 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 23 +++++++++++++++++++
 4 files changed, 87 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-47-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  21 +++++
 target/arm/tcg/sme.decode      | 168 +++++++++++++++++++++++++++++++++
 target/arm/tcg/sme_helper.c    |  59 ++++++++++++
 target/arm/tcg/translate-sme.c |  84 +++++++++++++++++
 4 files changed, 332 insertions(+)

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_smlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_usmlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_smlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ UDOT_n1_4h      11000001 011 1 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=4
 UDOT_n1_2h      11000001 011 0 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=2
 UDOT_n1_2h      11000001 011 1 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=4
 
+SMLAL_n1        11000001 011 0 .... 0 .. 011 ..... 00 ...   @azz_nx1_o3x2 n=1
+SMLAL_n1        11000001 011 0 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=2
+SMLAL_n1        11000001 011 1 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=4
+
+SMLSL_n1        11000001 011 0 .... 0 .. 011 ..... 01 ...   @azz_nx1_o3x2 n=1
+SMLSL_n1        11000001 011 0 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=2
+SMLSL_n1        11000001 011 1 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=4
+
+UMLAL_n1        11000001 011 0 .... 0 .. 011 ..... 10 ...   @azz_nx1_o3x2 n=1
+UMLAL_n1        11000001 011 0 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=2
+UMLAL_n1        11000001 011 1 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=4
+
+UMLSL_n1        11000001 011 0 .... 0 .. 011 ..... 11 ...   @azz_nx1_o3x2 n=1
+UMLSL_n1        11000001 011 0 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=2
+UMLSL_n1        11000001 011 1 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=4
+
+%off2_x4        0:2 !function=times_4
+%off1_x4        0:1 !function=times_4
+
+@azz_nx1_o2x4   ........ ... . zm:4 . .. ... zn:5 ... ..    \
+                &azz_n off=%off2_x4 rv=%mova_rv
+@azz_nx1_o1x4   ........ ... . zm:4 . .. ... zn:5 .... .    \
+                &azz_n off=%off1_x4 rv=%mova_rv
+
+SMLALL_n1_s     11000001 001 0 .... 0 .. 001 ..... 000 ..   @azz_nx1_o2x4 n=1
+SMLALL_n1_d     11000001 011 0 .... 0 .. 001 ..... 000 ..   @azz_nx1_o2x4 n=1
+SMLALL_n1_s     11000001 001 0 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=2
+SMLALL_n1_d     11000001 011 0 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=2
+SMLALL_n1_s     11000001 001 1 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=4
+SMLALL_n1_d     11000001 011 1 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=4
+
+SMLSLL_n1_s     11000001 001 0 .... 0 .. 001 ..... 010 ..   @azz_nx1_o2x4 n=1
+SMLSLL_n1_d     11000001 011 0 .... 0 .. 001 ..... 010 ..   @azz_nx1_o2x4 n=1
+SMLSLL_n1_s     11000001 001 0 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=2
+SMLSLL_n1_d     11000001 011 0 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=2
+SMLSLL_n1_s     11000001 001 1 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=4
+SMLSLL_n1_d     11000001 011 1 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=4
+
+UMLALL_n1_s     11000001 001 0 .... 0 .. 001 ..... 100 ..   @azz_nx1_o2x4 n=1
+UMLALL_n1_d     11000001 011 0 .... 0 .. 001 ..... 100 ..   @azz_nx1_o2x4 n=1
+UMLALL_n1_s     11000001 001 0 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=2
+UMLALL_n1_d     11000001 011 0 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=2
+UMLALL_n1_s     11000001 001 1 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=4
+UMLALL_n1_d     11000001 011 1 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=4
+
+UMLSLL_n1_s     11000001 001 0 .... 0 .. 001 ..... 110 ..   @azz_nx1_o2x4 n=1
+UMLSLL_n1_d     11000001 011 0 .... 0 .. 001 ..... 110 ..   @azz_nx1_o2x4 n=1
+UMLSLL_n1_s     11000001 001 0 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=2
+UMLSLL_n1_d     11000001 011 0 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=2
+UMLSLL_n1_s     11000001 001 1 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=4
+UMLSLL_n1_d     11000001 011 1 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=4
+
+USMLALL_n1_s    11000001 001 0 .... 0 .. 001 ..... 001 ..   @azz_nx1_o2x4 n=1
+USMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=2
+USMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=4
+
+SUMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=2
+SUMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ UDOT_nn_4h      11000001 111 ...01 0 .. 101 ...00 10 ...    @azz_4x4_o3
 UDOT_nn_2h      11000001 111 ....0 0 .. 101 ....0 11 ...    @azz_2x2_o3
 UDOT_nn_2h      11000001 111 ...01 0 .. 101 ...00 11 ...    @azz_4x4_o3
 
+SMLAL_nn        11000001 111 ....0 0 .. 010 ....0 000 ..    @azz_2x2_o2x2
+SMLAL_nn        11000001 111 ...01 0 .. 010 ...00 000 ..    @azz_4x4_o2x2
+
+SMLSL_nn        11000001 111 ....0 0 .. 010 ....0 010 ..    @azz_2x2_o2x2
+SMLSL_nn        11000001 111 ...01 0 .. 010 ...00 010 ..    @azz_4x4_o2x2
+
+UMLAL_nn        11000001 111 ....0 0 .. 010 ....0 100 ..    @azz_2x2_o2x2
+UMLAL_nn        11000001 111 ...01 0 .. 010 ...00 100 ..    @azz_4x4_o2x2
+
+UMLSL_nn        11000001 111 ....0 0 .. 010 ....0 110 ..    @azz_2x2_o2x2
+UMLSL_nn        11000001 111 ...01 0 .. 010 ...00 110 ..    @azz_4x4_o2x2
+
+@azz_2x2_o1x4   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off1_x4
+@azz_4x4_o1x4   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off1_x4
+
+SMLALL_nn_s     11000001 101 ....0 0 .. 000 ....0 0000 .    @azz_2x2_o1x4
+SMLALL_nn_d     11000001 111 ....0 0 .. 000 ....0 0000 .    @azz_2x2_o1x4
+SMLALL_nn_s     11000001 101 ...01 0 .. 000 ...00 0000 .    @azz_4x4_o1x4
+SMLALL_nn_d     11000001 111 ...01 0 .. 000 ...00 0000 .    @azz_4x4_o1x4
+
+SMLSLL_nn_s     11000001 101 ....0 0 .. 000 ....0 0100 .    @azz_2x2_o1x4
+SMLSLL_nn_d     11000001 111 ....0 0 .. 000 ....0 0100 .    @azz_2x2_o1x4
+SMLSLL_nn_s     11000001 101 ...01 0 .. 000 ...00 0100 .    @azz_4x4_o1x4
+SMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 0100 .    @azz_4x4_o1x4
+
+UMLALL_nn_s     11000001 101 ....0 0 .. 000 ....0 1000 .    @azz_2x2_o1x4
+UMLALL_nn_d     11000001 111 ....0 0 .. 000 ....0 1000 .    @azz_2x2_o1x4
+UMLALL_nn_s     11000001 101 ...01 0 .. 000 ...00 1000 .    @azz_4x4_o1x4
+UMLALL_nn_d     11000001 111 ...01 0 .. 000 ...00 1000 .    @azz_4x4_o1x4
+
+UMLSLL_nn_s     11000001 101 ....0 0 .. 000 ....0 1100 .    @azz_2x2_o1x4
+UMLSLL_nn_d     11000001 111 ....0 0 .. 000 ....0 1100 .    @azz_2x2_o1x4
+UMLSLL_nn_s     11000001 101 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
+UMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
+
+USMLALL_nn_s    11000001 101 ....0 0 .. 000 ....0 0010 .    @azz_2x2_o1x4
+USMLALL_nn_s    11000001 101 ...01 0 .. 000 ...00 0010 .    @azz_4x4_o1x4
+
 ### SME2 Multi-vector Indexed
 
 &azx_n          n off rv zn zm idx
@@ -XXX,XX +XXX,XX @@ UVDOT_nx_4h     11000001 1101 .... 1 .. 01 . ...00 11 ...   @azx_4x1_i1_o3
 
 SUVDOT_nx_4b    11000001 0101 .... 1 .. 0 .. ...01 11 ...   @azx_4x1_i2_o3
 USVDOT_nx_4b    11000001 0101 .... 1 .. 0 .. ...01 01 ...   @azx_4x1_i2_o3
+
+SMLAL_nx        11000001 1100 .... . .. 1 .. ..... 00 ...   @azx_1x1_o3x2
+SMLAL_nx        11000001 1101 .... 0 .. 1 .. ....0 00 ...   @azx_2x1_o2x2
+SMLAL_nx        11000001 1101 .... 1 .. 1 .. ...00 00 ...   @azx_4x1_o2x2
+
+SMLSL_nx        11000001 1100 .... . .. 1 .. ..... 01 ...   @azx_1x1_o3x2
+SMLSL_nx        11000001 1101 .... 0 .. 1 .. ....0 01 ...   @azx_2x1_o2x2
+SMLSL_nx        11000001 1101 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_o2x2
+
+UMLAL_nx        11000001 1100 .... . .. 1 .. ..... 10 ...   @azx_1x1_o3x2
+UMLAL_nx        11000001 1101 .... 0 .. 1 .. ....0 10 ...   @azx_2x1_o2x2
+UMLAL_nx        11000001 1101 .... 1 .. 1 .. ...00 10 ...   @azx_4x1_o2x2
+
+UMLSL_nx        11000001 1100 .... . .. 1 .. ..... 11 ...   @azx_1x1_o3x2
+UMLSL_nx        11000001 1101 .... 0 .. 1 .. ....0 11 ...   @azx_2x1_o2x2
+UMLSL_nx        11000001 1101 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_o2x2
+
+%idx4_15_10     15:1 10:3
+%idx4_10_1      10:2 1:2
+%idx3_10_1      10:1 1:2
+
+@azx_1x1_i4_o2  ........ .... zm:4 . .. ... zn:5 ... ..     \
+                &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx4_15_10
+@azx_1x1_i3_o2  ........ .... zm:4 . .. ... zn:5 ... ..     \
+                &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx3_15_10
+@azx_2x1_i4_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx4_10_1
+@azx_2x1_i3_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx3_10_1
+@azx_4x1_i4_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx4_10_1
+@azx_4x1_i3_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx3_10_1
+
+SMLALL_nx_s     11000001 0000 .... . .. ... ..... 000 ..    @azx_1x1_i4_o2
+SMLALL_nx_d     11000001 1000 .... . .. 0.. ..... 000 ..    @azx_1x1_i3_o2
+SMLALL_nx_s     11000001 0001 .... 0 .. 0.. ....0 00 ...    @azx_2x1_i4_o1
+SMLALL_nx_d     11000001 1001 .... 0 .. 00. ....0 00 ...    @azx_2x1_i3_o1
+SMLALL_nx_s     11000001 0001 .... 1 .. 0.. ...00 00 ...    @azx_4x1_i4_o1
+SMLALL_nx_d     11000001 1001 .... 1 .. 00. ...00 00 ...    @azx_4x1_i3_o1
+
+SMLSLL_nx_s     11000001 0000 .... . .. ... ..... 010 ..    @azx_1x1_i4_o2
+SMLSLL_nx_d     11000001 1000 .... . .. 0.. ..... 010 ..    @azx_1x1_i3_o2
+SMLSLL_nx_s     11000001 0001 .... 0 .. 0.. ....0 01 ...    @azx_2x1_i4_o1
+SMLSLL_nx_d     11000001 1001 .... 0 .. 00. ....0 01 ...    @azx_2x1_i3_o1
+SMLSLL_nx_s     11000001 0001 .... 1 .. 0.. ...00 01 ...    @azx_4x1_i4_o1
+SMLSLL_nx_d     11000001 1001 .... 1 .. 00. ...00 01 ...    @azx_4x1_i3_o1
+
+UMLALL_nx_s     11000001 0000 .... . .. ... ..... 100 ..    @azx_1x1_i4_o2
+UMLALL_nx_d     11000001 1000 .... . .. 0.. ..... 100 ..    @azx_1x1_i3_o2
+UMLALL_nx_s     11000001 0001 .... 0 .. 0.. ....0 10 ...    @azx_2x1_i4_o1
+UMLALL_nx_d     11000001 1001 .... 0 .. 00. ....0 10 ...    @azx_2x1_i3_o1
+UMLALL_nx_s     11000001 0001 .... 1 .. 0.. ...00 10 ...    @azx_4x1_i4_o1
+UMLALL_nx_d     11000001 1001 .... 1 .. 00. ...00 10 ...    @azx_4x1_i3_o1
+
+UMLSLL_nx_s     11000001 0000 .... . .. ... ..... 110 ..    @azx_1x1_i4_o2
+UMLSLL_nx_d     11000001 1000 .... . .. 0.. ..... 110 ..    @azx_1x1_i3_o2
+UMLSLL_nx_s     11000001 0001 .... 0 .. 0.. ....0 11 ...    @azx_2x1_i4_o1
+UMLSLL_nx_d     11000001 1001 .... 0 .. 00. ....0 11 ...    @azx_2x1_i3_o1
+UMLSLL_nx_s     11000001 0001 .... 1 .. 0.. ...00 11 ...    @azx_4x1_i4_o1
+UMLSLL_nx_d     11000001 1001 .... 1 .. 00. ...00 11 ...    @azx_4x1_i3_o1
+
+USMLALL_nx_s    11000001 0000 .... . .. ... ..... 001 ..    @azx_1x1_i4_o2
+USMLALL_nx_s    11000001 0001 .... 0 .. 0.. ....1 00 ...    @azx_2x1_i4_o1
+USMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 00 ...    @azx_4x1_i4_o1
+
+SUMLALL_nx_s    11000001 0000 .... . .. ... ..... 101 ..    @azx_1x1_i4_o2
+SUMLALL_nx_s    11000001 0001 .... 0 .. 0.. ....1 10 ...    @azx_2x1_i4_o1
+SUMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 10 ...    @azx_4x1_i4_o1
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2)
 DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2)
 
 #undef DO_VDOT_IDX
+
+#define DO_MLALL(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                               \
+    intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW);       \
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2);         \
+    TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm;       \
+    for (intptr_t i = 0; i < elements; ++i) {                   \
+        TYPEW nn = n[HN(i * 4 + sel)];                          \
+        TYPEM mm = m[HN(i * 4 + sel)];                          \
+        d[HW(i)] = a[HW(i)] OP (nn * mm);                       \
+    }                                                           \
+}
+
+DO_MLALL(sme2_smlall_s, int32_t, int8_t, int8_t, H4, H1, +)
+DO_MLALL(sme2_smlall_d, int64_t, int16_t, int16_t, H8, H2, +)
+DO_MLALL(sme2_smlsll_s, int32_t, int8_t, int8_t, H4, H1, -)
+DO_MLALL(sme2_smlsll_d, int64_t, int16_t, int16_t, H8, H2, -)
+
+DO_MLALL(sme2_umlall_s, uint32_t, uint8_t, uint8_t, H4, H1, +)
+DO_MLALL(sme2_umlall_d, uint64_t, uint16_t, uint16_t, H8, H2, +)
+DO_MLALL(sme2_umlsll_s, uint32_t, uint8_t, uint8_t, H4, H1, -)
+DO_MLALL(sme2_umlsll_d, uint64_t, uint16_t, uint16_t, H8, H2, -)
+
+DO_MLALL(sme2_usmlall_s, uint32_t, uint8_t, int8_t, H4, H1, +)
+
+#undef DO_MLALL
+
+#define DO_MLALL_IDX(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                               \
+    intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW);       \
+    intptr_t eltspersegment = 16 / sizeof(TYPEW);               \
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2);         \
+    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 4);     \
+    TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm;       \
+    for (intptr_t i = 0; i < elements; i += eltspersegment) {   \
+        TYPEW mm = m[HN(i * 4 + idx)];                          \
+        for (intptr_t j = 0; j < eltspersegment; ++j) {         \
+            TYPEN nn = n[HN((i + j) * 4 + sel)];                \
+            d[HW(i + j)] = a[HW(i + j)] OP (nn * mm);           \
+        }                                                       \
+    }                                                           \
+}
+
+DO_MLALL_IDX(sme2_smlall_idx_s, int32_t, int8_t, int8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_smlall_idx_d, int64_t, int16_t, int16_t, H8, H2, +)
+DO_MLALL_IDX(sme2_smlsll_idx_s, int32_t, int8_t, int8_t, H4, H1, -)
+DO_MLALL_IDX(sme2_smlsll_idx_d, int64_t, int16_t, int16_t, H8, H2, -)
+
+DO_MLALL_IDX(sme2_umlall_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_umlall_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, +)
+DO_MLALL_IDX(sme2_umlsll_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, -)
+DO_MLALL_IDX(sme2_umlsll_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, -)
+
+DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +)
+
+#undef DO_MLALL_IDX
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h)
 
 TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b)
 TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b)
+
+static bool do_smlal(DisasContext *s, arg_azz_n *a, bool multi,
+                     gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                      0, 0, multi, fn);
+}
+
+TRANS_FEAT(SMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlal_zzzw_s)
+TRANS_FEAT(SMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlsl_zzzw_s)
+TRANS_FEAT(UMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlal_zzzw_s)
+TRANS_FEAT(UMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlsl_zzzw_s)
+
+TRANS_FEAT(SMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlal_zzzw_s)
+TRANS_FEAT(SMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlsl_zzzw_s)
+TRANS_FEAT(UMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlal_zzzw_s)
+TRANS_FEAT(UMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlsl_zzzw_s)
+
+static bool do_smlal_nx(DisasContext *s, arg_azx_n *a,
+                         gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                      a->idx << 1, 0, false, fn);
+}
+
+TRANS_FEAT(SMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlal_idx_s)
+TRANS_FEAT(SMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlsl_idx_s)
+TRANS_FEAT(UMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlal_idx_s)
+TRANS_FEAT(UMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlsl_idx_s)
+
+static bool do_smlall(DisasContext *s, arg_azz_n *a, bool multi,
+                     gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm,
+                      0, 0, multi, fn);
+}
+
+static void gen_helper_sme2_sumlall_s(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m,
+                                      TCGv_ptr a, TCGv_i32 desc)
+{
+    gen_helper_sme2_usmlall_s(d, m, n, a, desc);
+}
+
+TRANS_FEAT(SMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlall_s)
+TRANS_FEAT(SMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlsll_s)
+TRANS_FEAT(UMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlall_s)
+TRANS_FEAT(UMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlsll_s)
+TRANS_FEAT(USMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_usmlall_s)
+TRANS_FEAT(SUMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_sumlall_s)
+
+TRANS_FEAT(SMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlall_d)
+TRANS_FEAT(SMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlsll_d)
+TRANS_FEAT(UMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlall_d)
+TRANS_FEAT(UMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlsll_d)
+
+TRANS_FEAT(SMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlall_s)
+TRANS_FEAT(SMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlsll_s)
+TRANS_FEAT(UMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlall_s)
+TRANS_FEAT(UMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlsll_s)
+TRANS_FEAT(USMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_usmlall_s)
+
+TRANS_FEAT(SMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlall_d)
+TRANS_FEAT(SMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlsll_d)
+TRANS_FEAT(UMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlall_d)
+TRANS_FEAT(UMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlsll_d)
+
+static bool do_smlall_nx(DisasContext *s, arg_azx_n *a,
+                        gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm,
+                      a->idx << 2, 0, false, fn);
+}
+
+TRANS_FEAT(SMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlall_idx_s)
+TRANS_FEAT(SMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_s)
+TRANS_FEAT(UMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlall_idx_s)
+TRANS_FEAT(UMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_s)
+TRANS_FEAT(USMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_usmlall_idx_s)
+TRANS_FEAT(SUMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_sumlall_idx_s)
+
+TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlall_idx_d)
+TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d)
+TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d)
+TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Emphasize the non-fused nature of these multiply-add.
Matches other helpers such as gvec_rsqrts_nf_[hs].

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-48-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h         | 8 ++++----
 target/arm/tcg/translate-neon.c | 4 ++--
 target/arm/tcg/vec_helper.c     | 8 ++++----
 3 files changed, 10 insertions(+), 10 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-49-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 48 +++++++++++++++++
 target/arm/tcg/translate-sme.c | 95 ++++++++++++++++++++++++++++++++++
 2 files changed, 143 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ USMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=4
 SUMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=2
 SUMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=4
 
+FMLA_n1_h       11000001 001 0 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=2
+FMLA_n1_s       11000001 001 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
+FMLA_n1_d       11000001 011 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
+FMLA_n1_h       11000001 001 1 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=4
+FMLA_n1_s       11000001 001 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
+FMLA_n1_d       11000001 011 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
+
+FMLS_n1_h       11000001 001 0 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=2
+FMLS_n1_s       11000001 001 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
+FMLS_n1_d       11000001 011 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
+FMLS_n1_h       11000001 001 1 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=4
+FMLS_n1_s       11000001 001 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
+FMLS_n1_d       11000001 011 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ UMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
 USMLALL_nn_s    11000001 101 ....0 0 .. 000 ....0 0010 .    @azz_2x2_o1x4
 USMLALL_nn_s    11000001 101 ...01 0 .. 000 ...00 0010 .    @azz_4x4_o1x4
 
+FMLA_nn_h       11000001 101 ....0 0 .. 100 ....0 01 ...    @azz_2x2_o3
+FMLA_nn_s       11000001 101 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
+FMLA_nn_d       11000001 111 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
+FMLA_nn_h       11000001 101 ...01 0 .. 100 ...00 01 ...    @azz_4x4_o3
+FMLA_nn_s       11000001 101 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
+FMLA_nn_d       11000001 111 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
+
+FMLS_nn_h       11000001 101 ....0 0 .. 100 ....0 11 ...    @azz_2x2_o3
+FMLS_nn_s       11000001 101 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
+FMLS_nn_d       11000001 111 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
+FMLS_nn_h       11000001 101 ...01 0 .. 100 ...00 11 ...    @azz_4x4_o3
+FMLS_nn_s       11000001 101 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
+FMLS_nn_d       11000001 111 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
+
 ### SME2 Multi-vector Indexed
 
 &azx_n          n off rv zn zm idx
@@ -XXX,XX +XXX,XX @@ USMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 00 ...    @azx_4x1_i4_o1
 SUMLALL_nx_s    11000001 0000 .... . .. ... ..... 101 ..    @azx_1x1_i4_o2
 SUMLALL_nx_s    11000001 0001 .... 0 .. 0.. ....1 10 ...    @azx_2x1_i4_o1
 SUMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 10 ...    @azx_4x1_i4_o1
+
+%idx3_10_3      10:2 3:1
+@azx_2x1_i3_o3  ........ .... zm:4 . .. ... ..... .. off:3  \
+                &azx_n n=2 rv=%mova_rv zn=%zn_ax2 idx=%idx3_10_3
+@azx_4x1_i3_o3  ........ .... zm:4 . .. ... ..... .. off:3  \
+                &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3
+
+FMLA_nx_h       11000001 0001 .... 0 .. 1.. ....0 0 ....    @azx_2x1_i3_o3
+FMLA_nx_s       11000001 0101 .... 0 .. 0.. ....0 00 ...    @azx_2x1_i2_o3
+FMLA_nx_d       11000001 1101 .... 0 .. 00. ....0 00 ...    @azx_2x1_i1_o3
+FMLA_nx_h       11000001 0001 .... 1 .. 1.. ...00 0 ....    @azx_4x1_i3_o3
+FMLA_nx_s       11000001 0101 .... 1 .. 0.. ...00 00 ...    @azx_4x1_i2_o3
+FMLA_nx_d       11000001 1101 .... 1 .. 00. ...00 00 ...    @azx_4x1_i1_o3
+
+FMLS_nx_h       11000001 0001 .... 0 .. 1.. ....0 1 ....    @azx_2x1_i3_o3
+FMLS_nx_s       11000001 0101 .... 0 .. 0.. ....0 10 ...    @azx_2x1_i2_o3
+FMLS_nx_d       11000001 1101 .... 0 .. 00. ....0 10 ...    @azx_2x1_i1_o3
+FMLS_nx_h       11000001 0001 .... 1 .. 1.. ...00 1 ....    @azx_4x1_i3_o3
+FMLS_nx_s       11000001 0101 .... 1 .. 0.. ...00 10 ...    @azx_4x1_i2_o3
+FMLS_nx_d       11000001 1101 .... 1 .. 00. ...00 10 ...    @azx_4x1_i1_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub
  */
 #define FPST_ENV  -1
 
+static bool do_azz_fp(DisasContext *s, int nreg, int nsel,
+                      int rv, int off, int zn, int zm,
+                      int data, int shsel, bool multi, int fpst,
+                      gen_helper_gvec_3_ptr *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / nreg;
+        TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+        TCGv_ptr t, ptr;
+
+        if (fpst >= 0) {
+            ptr = fpstatus_ptr(fpst);
+        } else {
+            ptr = tcg_env;
+        }
+        t = tcg_temp_new_ptr();
+
+        for (int r = 0; r < nreg; ++r) {
+            TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+            TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+            for (int i = 0; i < nsel; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                int desc = simd_desc(svl, svl, data | (i << shsel));
+
+                tcg_gen_addi_ptr(t, t_za, o_za);
+                fn(t, t_zn, t_zm, ptr, tcg_constant_i32(desc));
+            }
+
+            /*
+             * For multiple-and-single vectors, Zn may wrap.
+             * For multiple vectors, both Zn and Zm are aligned.
+             */
+            zn = (zn + 1) % 32;
+            zm += multi;
+        }
+    }
+    return true;
+}
+
 static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel,
                           int rv, int off, int zn, int zm,
                           int data, int shsel, bool multi, int fpst,
@@ -XXX,XX +XXX,XX @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
 TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
 TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
 
+static bool do_fmla(DisasContext *s, arg_azz_n *a, bool multi,
+                    ARMFPStatusFlavour fpst, gen_helper_gvec_3_ptr *fn)
+{
+    return do_azz_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                     0, 0, multi, fpst, fn);
+}
+
+TRANS_FEAT(FMLA_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16,
+           gen_helper_gvec_vfma_h)
+TRANS_FEAT(FMLS_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h)
+TRANS_FEAT(FMLA_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16,
+           gen_helper_gvec_vfma_h)
+TRANS_FEAT(FMLS_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h)
+
+TRANS_FEAT(FMLA_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA,
+           gen_helper_gvec_vfma_s)
+TRANS_FEAT(FMLS_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s)
+TRANS_FEAT(FMLA_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA,
+           gen_helper_gvec_vfma_s)
+TRANS_FEAT(FMLS_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s)
+
+TRANS_FEAT(FMLA_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA,
+           gen_helper_gvec_vfma_d)
+TRANS_FEAT(FMLS_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
+           gen_helper_gvec_vfma_d)
+TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+
+static bool do_fmla_nx(DisasContext *s, arg_azx_n *a,
+                       ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn)
+{
+    return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                         a->idx, 0, false, fpst, fn);
+}
+
+TRANS_FEAT(FMLA_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16,
+           gen_helper_gvec_fmla_idx_h)
+TRANS_FEAT(FMLS_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16,
+           s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_h : gen_helper_gvec_fmls_idx_h)
+TRANS_FEAT(FMLA_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA,
+           gen_helper_gvec_fmla_idx_s)
+TRANS_FEAT(FMLS_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_s : gen_helper_gvec_fmls_idx_s)
+TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
+           gen_helper_gvec_fmla_idx_d)
+TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d)
+
 /*
  * Expand array multi-vector single (n1), array multi-vector (nn),
  * and array multi-vector indexed (nx), for integer accumulate.
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-50-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        |  9 +++++++++
 target/arm/tcg/sme.decode      | 18 ++++++++++++++++++
 target/arm/tcg/translate-sme.c | 14 ++++++++++++++
 target/arm/tcg/vec_helper.c    | 26 ++++++++++++++++++++++++++
 4 files changed, 67 insertions(+)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i
 DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_ah_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, fpst, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmla_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_6(gvec_fmls_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmls_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_fmls_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmls_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmls_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ USMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=4
 SUMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=2
 SUMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=4
 
+BFMLA_n1        11000001 011 0 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=2
 FMLA_n1_h       11000001 001 0 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=2
 FMLA_n1_s       11000001 001 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
 FMLA_n1_d       11000001 011 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
+
+BFMLA_n1        11000001 011 1 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=4
 FMLA_n1_h       11000001 001 1 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=4
 FMLA_n1_s       11000001 001 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
 FMLA_n1_d       11000001 011 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
 
+BFMLS_n1        11000001 011 0 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=2
 FMLS_n1_h       11000001 001 0 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=2
 FMLS_n1_s       11000001 001 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
 FMLS_n1_d       11000001 011 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
+
+BFMLS_n1        11000001 011 1 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=4
 FMLS_n1_h       11000001 001 1 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=4
 FMLS_n1_s       11000001 001 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
 FMLS_n1_d       11000001 011 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
@@ -XXX,XX +XXX,XX @@ UMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
 USMLALL_nn_s    11000001 101 ....0 0 .. 000 ....0 0010 .    @azz_2x2_o1x4
 USMLALL_nn_s    11000001 101 ...01 0 .. 000 ...00 0010 .    @azz_4x4_o1x4
 
+BFMLA_nn        11000001 111 ....0 0 .. 100 ....0 01 ...    @azz_2x2_o3
 FMLA_nn_h       11000001 101 ....0 0 .. 100 ....0 01 ...    @azz_2x2_o3
 FMLA_nn_s       11000001 101 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
 FMLA_nn_d       11000001 111 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
+
+BFMLA_nn        11000001 111 ...01 0 .. 100 ...00 01 ...    @azz_4x4_o3
 FMLA_nn_h       11000001 101 ...01 0 .. 100 ...00 01 ...    @azz_4x4_o3
 FMLA_nn_s       11000001 101 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
 FMLA_nn_d       11000001 111 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
 
+BFMLS_nn        11000001 111 ....0 0 .. 100 ....0 11 ...    @azz_2x2_o3
 FMLS_nn_h       11000001 101 ....0 0 .. 100 ....0 11 ...    @azz_2x2_o3
 FMLS_nn_s       11000001 101 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
 FMLS_nn_d       11000001 111 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
+
+BFMLS_nn        11000001 111 ...01 0 .. 100 ...00 11 ...    @azz_4x4_o3
 FMLS_nn_h       11000001 101 ...01 0 .. 100 ...00 11 ...    @azz_4x4_o3
 FMLS_nn_s       11000001 101 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
 FMLS_nn_d       11000001 111 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
@@ -XXX,XX +XXX,XX @@ SUMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 10 ...    @azx_4x1_i4_o1
 @azx_4x1_i3_o3  ........ .... zm:4 . .. ... ..... .. off:3  \
                 &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3
 
+BFMLA_nx        11000001 0001 .... 0 .. 1.. ....1 0 ....    @azx_2x1_i3_o3
 FMLA_nx_h       11000001 0001 .... 0 .. 1.. ....0 0 ....    @azx_2x1_i3_o3
 FMLA_nx_s       11000001 0101 .... 0 .. 0.. ....0 00 ...    @azx_2x1_i2_o3
 FMLA_nx_d       11000001 1101 .... 0 .. 00. ....0 00 ...    @azx_2x1_i1_o3
+
+BFMLA_nx        11000001 0001 .... 1 .. 1.. ...01 0 ....    @azx_4x1_i3_o3
 FMLA_nx_h       11000001 0001 .... 1 .. 1.. ...00 0 ....    @azx_4x1_i3_o3
 FMLA_nx_s       11000001 0101 .... 1 .. 0.. ...00 00 ...    @azx_4x1_i2_o3
 FMLA_nx_d       11000001 1101 .... 1 .. 00. ...00 00 ...    @azx_4x1_i1_o3
 
+BFMLS_nx        11000001 0001 .... 0 .. 1.. ....1 1 ....    @azx_2x1_i3_o3
 FMLS_nx_h       11000001 0001 .... 0 .. 1.. ....0 1 ....    @azx_2x1_i3_o3
 FMLS_nx_s       11000001 0101 .... 0 .. 0.. ....0 10 ...    @azx_2x1_i2_o3
 FMLS_nx_d       11000001 1101 .... 0 .. 00. ....0 10 ...    @azx_2x1_i1_o3
+
+BFMLS_nx        11000001 0001 .... 1 .. 1.. ...01 1 ....    @azx_4x1_i3_o3
 FMLS_nx_h       11000001 0001 .... 1 .. 1.. ...00 1 ....    @azx_4x1_i3_o3
 FMLS_nx_s       11000001 0101 .... 1 .. 0.. ...00 10 ...    @azx_4x1_i2_o3
 FMLS_nx_d       11000001 1101 .... 1 .. 00. ...00 10 ...    @azx_4x1_i1_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
 TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
            s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
 
+TRANS_FEAT(BFMLA_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA,
+           gen_helper_gvec_bfmla)
+TRANS_FEAT(BFMLS_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls)
+TRANS_FEAT(BFMLA_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA,
+           gen_helper_gvec_bfmla)
+TRANS_FEAT(BFMLS_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls)
+
 static bool do_fmla_nx(DisasContext *s, arg_azx_n *a,
                        ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn)
 {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
 TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
            s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d)
 
+TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
+           gen_helper_gvec_bfmla_idx)
+TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx)
+
 /*
  * Expand array multi-vector single (n1), array multi-vector (nn),
  * and array multi-vector indexed (nx), for integer accumulate.
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2,
     return float16_muladd(op1, op2, dest, 0, stat);
 }
 
+static bfloat16 bfloat16_muladd_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+                                  float_status *stat)
+{
+    return bfloat16_muladd(op1, op2, dest, 0, stat);
+}
+
 static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2,
                                  float_status *stat)
 {
@@ -XXX,XX +XXX,XX @@ static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2,
     return float16_muladd(float16_chs(op1), op2, dest, 0, stat);
 }
 
+static bfloat16 bfloat16_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+                                  float_status *stat)
+{
+    return bfloat16_muladd(bfloat16_chs(op1), op2, dest, 0, stat);
+}
+
 static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2,
                                  float_status *stat)
 {
@@ -XXX,XX +XXX,XX @@ static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2,
     return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
 }
 
+static bfloat16 bfloat16_ah_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+                                     float_status *stat)
+{
+    return bfloat16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
+}
+
 static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2,
                                  float_status *stat)
 {
@@ -XXX,XX +XXX,XX @@ DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32)
 DO_MULADD(gvec_vfma_h, float16_muladd_f, float16)
 DO_MULADD(gvec_vfma_s, float32_muladd_f, float32)
 DO_MULADD(gvec_vfma_d, float64_muladd_f, float64)
+DO_MULADD(gvec_bfmla, bfloat16_muladd_f, bfloat16)
 
 DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
 DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
 DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64)
+DO_MULADD(gvec_bfmls, bfloat16_mulsub_f, bfloat16)
 
 DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16)
 DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32)
 DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64)
+DO_MULADD(gvec_ah_bfmls, bfloat16_ah_mulsub_f, bfloat16)
+
+#undef DO_MULADD
 
 /* For the indexed ops, SVE applies the index per 128-bit vector segment.
  * For AdvSIMD, there is of course only one such vector segment.
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va,                  \
 DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2, 0, 0)
 DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4, 0, 0)
 DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8, 0, 0)
+DO_FMLA_IDX(gvec_bfmla_idx, bfloat16, H2, 0, 0)
 
 DO_FMLA_IDX(gvec_fmls_idx_h, float16, H2, INT16_MIN, 0)
 DO_FMLA_IDX(gvec_fmls_idx_s, float32, H4, INT32_MIN, 0)
 DO_FMLA_IDX(gvec_fmls_idx_d, float64, H8, INT64_MIN, 0)
+DO_FMLA_IDX(gvec_bfmls_idx, bfloat16, H2, INT16_MIN, 0)
 
 DO_FMLA_IDX(gvec_ah_fmls_idx_h, float16, H2, 0, float_muladd_negate_product)
 DO_FMLA_IDX(gvec_ah_fmls_idx_s, float32, H4, 0, float_muladd_negate_product)
 DO_FMLA_IDX(gvec_ah_fmls_idx_d, float64, H8, 0, float_muladd_negate_product)
+DO_FMLA_IDX(gvec_ah_bfmls_idx, bfloat16, H2, 0, float_muladd_negate_product)
 
 #undef DO_FMLA_IDX
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-51-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        |  2 ++
 target/arm/tcg/sme.decode      | 25 +++++++++++++++++++
 target/arm/tcg/translate-sme.c | 44 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    |  2 ++
 4 files changed, 73 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-52-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 12 ++++++++++++
 target/arm/tcg/translate-sme.c | 28 ++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-53-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  5 +++
 target/arm/tcg/vec_internal.h  |  2 +
 target/arm/tcg/sme.decode      | 12 ++++++
 target/arm/tcg/sme_helper.c    | 74 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/sve_helper.c    |  2 +-
 target/arm/tcg/translate-sme.c | 25 ++++++++++++
 6 files changed, 119 insertions(+), 1 deletion(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-54-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  2 ++
 target/arm/tcg/vec_internal.h  |  1 +
 target/arm/tcg/sme.decode      |  5 ++++
 target/arm/tcg/sme_helper.c    | 45 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/sve_helper.c    |  2 +-
 target/arm/tcg/translate-sme.c |  5 ++++
 6 files changed, 59 insertions(+), 1 deletion(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-55-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 9 +++++++++
 target/arm/tcg/translate-sme.c | 5 +++++
 2 files changed, 14 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ SUB_aaz_d       11000001 111 000010 .. 111 ...00 11 ...     @az_4x4_o3
                 &zz_n n=1 zn=%zn_ax2
 @zz_2x1         ........ ... ..... ...... zn:5  .....       \
                 &zz_n n=1 zd=%zd_ax2
+@zz_2x2         ........ ... ..... ...... .... . .....      \
+                &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2
+@zz_4x4         ........ ... ..... ...... .... . .....      \
+                &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4
 
 BFCVT           11000001 011 00000 111000 ....0 .....       @zz_1x2
 BFCVTN          11000001 011 00000 111000 ....1 .....       @zz_1x2
@@ -XXX,XX +XXX,XX @@ FCVTN           11000001 001 00000 111000 ....1 .....       @zz_1x2
 
 FCVT_w          11000001 101 00000 111000 ..... ....0       @zz_2x1
 FCVTL           11000001 101 00000 111000 ..... ....1       @zz_2x1
+
+FCVTZS          11000001 001 00001 111000 ....0 ....0       @zz_2x2
+FCVTZS          11000001 001 10001 111000 ...00 ...00       @zz_4x4
+FCVTZU          11000001 001 00001 111000 ....1 ....0       @zz_2x2
+FCVTZU          11000001 001 10001 111000 ...01 ...00       @zz_4x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0,
            FPST_A64_F16, gen_helper_sme2_fcvt_w)
 TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0,
            FPST_A64_F16, gen_helper_sme2_fcvtl)
+
+TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_gvec_vcvt_rz_fs)
+TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_gvec_vcvt_rz_fu)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-56-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  2 ++
 target/arm/tcg/sme.decode      |  5 +++++
 target/arm/tcg/sme_helper.c    | 22 ++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  5 +++++
 4 files changed, 34 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-57-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 9 +++++++++
 target/arm/tcg/translate-sme.c | 9 +++++++++
 2 files changed, 18 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ SCVTF           11000001 001 00010 111000 ....0 ....0       @zz_2x2
 SCVTF           11000001 001 10010 111000 ...00 ...00       @zz_4x4
 UCVTF           11000001 001 00010 111000 ....1 ....0       @zz_2x2
 UCVTF           11000001 001 10010 111000 ...01 ...00       @zz_4x4
+
+FRINTN          11000001 101 01000 111000 ....0 ....0       @zz_2x2
+FRINTN          11000001 101 11000 111000 ...00 ...00       @zz_4x4
+FRINTP          11000001 101 01001 111000 ....0 ....0       @zz_2x2
+FRINTP          11000001 101 11001 111000 ...00 ...00       @zz_4x4
+FRINTM          11000001 101 01010 111000 ....0 ....0       @zz_2x2
+FRINTM          11000001 101 11010 111000 ...00 ...00       @zz_4x4
+FRINTA          11000001 101 01100 111000 ....0 ....0       @zz_2x2
+FRINTA          11000001 101 11100 111000 ...00 ...00       @zz_4x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0,
            FPST_A64, gen_helper_sme2_scvtf)
 TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0,
            FPST_A64, gen_helper_sme2_ucvtf)
+
+TRANS_FEAT(FRINTN, aa64_sme2, do_zz_fpst, a, float_round_nearest_even,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTP, aa64_sme2, do_zz_fpst, a, float_round_up,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Inputs are a wider type of indeterminate sign.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-58-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_internal.h | 7 +++++++
 1 file changed, 7 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Replace and remove do_sat_bhs.
This avoids multiple repetitions of INT*_MIN/MAX.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-59-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 116 +++++++++++++++---------------------
 1 file changed, 48 insertions(+), 68 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS)
 DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS)
 DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D)
 
-static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max)
-{
-    return val >= max ? max : val <= min ? min : val;
-}
-
-#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX)
-#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX)
-#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX)
+#define DO_SQADD_B(n, m) do_ssat_b((int64_t)n + m)
+#define DO_SQADD_H(n, m) do_ssat_h((int64_t)n + m)
+#define DO_SQADD_S(n, m) do_ssat_s((int64_t)n + m)
 
 static inline int64_t do_sqadd_d(int64_t n, int64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H)
 DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S)
 DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d)
 
-#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX)
-#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX)
-#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX)
+#define DO_UQADD_B(n, m) do_usat_b((int64_t)n + m)
+#define DO_UQADD_H(n, m) do_usat_h((int64_t)n + m)
+#define DO_UQADD_S(n, m) do_usat_s((int64_t)n + m)
 
 static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H)
 DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S)
 DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d)
 
-#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX)
-#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX)
-#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX)
+#define DO_SQSUB_B(n, m) do_ssat_b((int64_t)n - m)
+#define DO_SQSUB_H(n, m) do_ssat_h((int64_t)n - m)
+#define DO_SQSUB_S(n, m) do_ssat_s((int64_t)n - m)
 
 static inline int64_t do_sqsub_d(int64_t n, int64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H)
 DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S)
 DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d)
 
-#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX)
-#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX)
-#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX)
+#define DO_UQSUB_B(n, m) do_usat_b((int64_t)n - m)
+#define DO_UQSUB_H(n, m) do_usat_h((int64_t)n - m)
+#define DO_UQSUB_S(n, m) do_usat_s((int64_t)n - m)
 
 static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H)
 DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S)
 DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d)
 
-#define DO_SUQADD_B(n, m) \
-    do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX)
-#define DO_SUQADD_H(n, m) \
-    do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX)
-#define DO_SUQADD_S(n, m) \
-    do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX)
+#define DO_SUQADD_B(n, m) do_ssat_b((int64_t)(int8_t)n + m)
+#define DO_SUQADD_H(n, m) do_ssat_h((int64_t)(int16_t)n + m)
+#define DO_SUQADD_S(n, m) do_ssat_s((int64_t)(int32_t)n + m)
 
 static inline int64_t do_suqadd_d(int64_t n, uint64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H)
 DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S)
 DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d)
 
-#define DO_USQADD_B(n, m) \
-    do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX)
-#define DO_USQADD_H(n, m) \
-    do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX)
-#define DO_USQADD_S(n, m) \
-    do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX)
+#define DO_USQADD_B(n, m) do_usat_b((int64_t)n + (int8_t)m)
+#define DO_USQADD_H(n, m) do_usat_h((int64_t)n + (int16_t)m)
+#define DO_USQADD_S(n, m) do_usat_s((int64_t)n + (int32_t)m)
 
 static inline uint64_t do_usqadd_d(uint64_t n, int64_t m)
 {
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, uint32_t desc)                    \
     }                                                                   \
 }
 
-#define DO_SQXTN_H(n)  do_sat_bhs(n, INT8_MIN, INT8_MAX)
-#define DO_SQXTN_S(n)  do_sat_bhs(n, INT16_MIN, INT16_MAX)
-#define DO_SQXTN_D(n)  do_sat_bhs(n, INT32_MIN, INT32_MAX)
+DO_XTNB(sve2_sqxtnb_h, int16_t, do_ssat_b)
+DO_XTNB(sve2_sqxtnb_s, int32_t, do_ssat_h)
+DO_XTNB(sve2_sqxtnb_d, int64_t, do_ssat_s)
 
-DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H)
-DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S)
-DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D)
+DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, do_ssat_b)
+DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, do_ssat_h)
+DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, do_ssat_s)
 
-DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H)
-DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S)
-DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D)
+DO_XTNB(sve2_uqxtnb_h, uint16_t, do_usat_b)
+DO_XTNB(sve2_uqxtnb_s, uint32_t, do_usat_h)
+DO_XTNB(sve2_uqxtnb_d, uint64_t, do_usat_s)
 
-#define DO_UQXTN_H(n)  do_sat_bhs(n, 0, UINT8_MAX)
-#define DO_UQXTN_S(n)  do_sat_bhs(n, 0, UINT16_MAX)
-#define DO_UQXTN_D(n)  do_sat_bhs(n, 0, UINT32_MAX)
+DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, do_usat_b)
+DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, do_usat_h)
+DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, do_usat_s)
 
-DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H)
-DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S)
-DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D)
+DO_XTNB(sve2_sqxtunb_h, int16_t, do_usat_b)
+DO_XTNB(sve2_sqxtunb_s, int32_t, do_usat_h)
+DO_XTNB(sve2_sqxtunb_d, int64_t, do_usat_s)
 
-DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H)
-DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S)
-DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D)
-
-DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H)
-DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S)
-DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D)
-
-DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H)
-DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S)
-DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D)
+DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, do_usat_b)
+DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, do_usat_h)
+DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, do_usat_s)
 
 #undef DO_XTNB
 #undef DO_XTNT
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr)
 DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr)
 DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, H1_8, H1_4, do_urshr)
 
-#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX)
-#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX)
-#define DO_SQSHRUN_D(x, sh) \
-    do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX)
+#define DO_SQSHRUN_H(x, sh) do_usat_b((int64_t)(x) >> sh)
+#define DO_SQSHRUN_S(x, sh) do_usat_h((int64_t)(x) >> sh)
+#define DO_SQSHRUN_D(x, sh) do_usat_s((int64_t)(x) >> (sh < 64 ? sh : 63))
 
 DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H)
 DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S)
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H)
 DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S)
 DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRUN_D)
 
-#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX)
-#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX)
-#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX)
+#define DO_SQRSHRUN_H(x, sh) do_usat_b(do_srshr(x, sh))
+#define DO_SQRSHRUN_S(x, sh) do_usat_h(do_srshr(x, sh))
+#define DO_SQRSHRUN_D(x, sh) do_usat_s(do_srshr(x, sh))
 
 DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H)
 DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S)
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H)
 DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S)
 DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQRSHRUN_D)
 
-#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX)
-#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX)
-#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX)
+#define DO_SQSHRN_H(x, sh) do_ssat_b(x >> sh)
+#define DO_SQSHRN_S(x, sh) do_ssat_h(x >> sh)
+#define DO_SQSHRN_D(x, sh) do_ssat_s(x >> sh)
 
 DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H)
 DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S)
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H)
 DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S)
 DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRN_D)
 
-#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX)
-#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX)
-#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX)
+#define DO_SQRSHRN_H(x, sh) do_ssat_b(do_srshr(x, sh))
+#define DO_SQRSHRN_S(x, sh) do_ssat_h(do_srshr(x, sh))
+#define DO_SQRSHRN_D(x, sh) do_ssat_s(do_srshr(x, sh))
 
 DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H)
 DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-60-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  20 ++++++
 target/arm/tcg/sme.decode      |  22 +++++++
 target/arm/tcg/sme_helper.c    | 116 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  35 ++++++++++
 4 files changed, 193 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-61-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      | 20 ++++++++++++++++----
 target/arm/tcg/translate-sve.c |  7 +++++++
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@
 # as propagated via the MOVPRFX instruction.
 %reg_movprfx    0:5
 
+%rn_ax2         6:4 !function=times_2
+
 ###########################################################################
 # Named attribute sets.  These are used to make nice(er) names
 # when creating helpers common to those for the individual
@@ -XXX,XX +XXX,XX @@
 # Two operand
 @pd_pn          ........ esz:2 .. .... ....... rn:4 . rd:4      &rr_esz
 @rd_rn          ........ esz:2 ...... ...... rn:5 rd:5          &rr_esz
+@rd_rnx2        ........ ... ..... ...... ..... rd:5            &rr_esz rn=%rn_ax2
 
 # Two operand with governing predicate, flags setting
 @pd_pg_pn_s     ........ . s:1 ...... .. pg:4 . rn:4 . rd:4     &rpr_s
@@ -XXX,XX +XXX,XX @@ UABA            01000101 .. 0 ..... 11111 1 ..... .....  @rd_rn_rm
 #### SVE2 Narrowing
 
 ## SVE2 saturating extract narrow
-
 # Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0.
-SQXTNB          01000101 .. 1 ..... 010 000 ..... .....  @rd_rn_tszimm_shl
+
+{
+  SQCVTN_sh     01000101 00 1 10001 010 000 ....0 .....  @rd_rnx2 esz=1
+  SQXTNB        01000101 .. 1 ..... 010 000 ..... .....  @rd_rn_tszimm_shl
+}
 SQXTNT          01000101 .. 1 ..... 010 001 ..... .....  @rd_rn_tszimm_shl
-UQXTNB          01000101 .. 1 ..... 010 010 ..... .....  @rd_rn_tszimm_shl
+{
+  UQCVTN_sh     01000101 00 1 10001 010 010 ....0 .....  @rd_rnx2 esz=1
+  UQXTNB        01000101 .. 1 ..... 010 010 ..... .....  @rd_rn_tszimm_shl
+}
 UQXTNT          01000101 .. 1 ..... 010 011 ..... .....  @rd_rn_tszimm_shl
-SQXTUNB         01000101 .. 1 ..... 010 100 ..... .....  @rd_rn_tszimm_shl
+{
+  SQCVTUN_sh    01000101 00 1 10001 010 100 ....0 .....  @rd_rnx2 esz=1
+  SQXTUNB       01000101 .. 1 ..... 010 100 ..... .....  @rd_rn_tszimm_shl
+}
 SQXTUNT         01000101 .. 1 ..... 010 101 ..... .....  @rd_rn_tszimm_shl
 
 ## SVE2 bitwise shift right narrow
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
 }
 
 TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+
+TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+           gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
+TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+           gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0)
+TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+           gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-62-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 13 ++++++++++++
 target/arm/tcg/sme.decode      | 18 ++++++++++++++++
 target/arm/tcg/sme_helper.c    | 38 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 16 ++++++++++++++
 4 files changed, 85 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-63-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 12 ++++++
 target/arm/tcg/sme.decode      | 11 ++++++
 target/arm/tcg/sme_helper.c    | 68 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 39 +++++++++++++++++++
 4 files changed, 130 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Unify two copies of these inline functions.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-64-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_internal.h | 21 +++++++++++++++++++++
 target/arm/tcg/mve_helper.c   | 21 ---------------------
 target/arm/tcg/sve_helper.c   | 21 ---------------------
 3 files changed, 21 insertions(+), 42 deletions(-)

diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -XXX,XX +XXX,XX @@ int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool);
 #define do_usat_h(val)  MIN(MAX(val, 0), UINT16_MAX)
 #define do_usat_s(val)  MIN(MAX(val, 0), UINT32_MAX)
 
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
+{
+    if (likely(sh < 64)) {
+        return (x >> sh) + ((x >> (sh - 1)) & 1);
+    } else if (sh == 64) {
+        return x >> 63;
+    } else {
+        return 0;
+    }
+}
+
+static inline int64_t do_srshr(int64_t x, unsigned sh)
+{
+    if (likely(sh < 64)) {
+        return (x >> sh) + ((x >> (sh - 1)) & 1);
+    } else {
+        /* Rounding the sign bit always produces 0. */
+        return 0;
+    }
+}
+
 /**
  * bfdotadd:
  * @sum: addend
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSHLL_ALL(vshllt, true)
     DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN)         \
     DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
 
-static inline uint64_t do_urshr(uint64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else if (sh == 64) {
-        return x >> 63;
-    } else {
-        return 0;
-    }
-}
-
-static inline int64_t do_srshr(int64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else {
-        /* Rounding the sign bit always produces 0. */
-        return 0;
-    }
-}
-
 DO_VSHRN_ALL(vshrn, DO_SHR)
 DO_VSHRN_ALL(vrshrn, do_urshr)
 
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc)  \
    when N is negative, add 2**M-1.  */
 #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M)
 
-static inline uint64_t do_urshr(uint64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else if (sh == 64) {
-        return x >> 63;
-    } else {
-        return 0;
-    }
-}
-
-static inline int64_t do_srshr(int64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else {
-        /* Rounding the sign bit always produces 0. */
-        return 0;
-    }
-}
-
 DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR)
 DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR)
 DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-65-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  20 ++++++
 target/arm/tcg/sme.decode      |  37 ++++++++++
 target/arm/tcg/sme_helper.c    | 120 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  33 +++++++++
 4 files changed, 210 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-66-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 12 +++++++
 target/arm/tcg/sme.decode      | 12 +++++++
 target/arm/tcg/sme_helper.c    | 62 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 40 ++++++++++++++++++++++
 4 files changed, 126 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-67-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 15 +++++++
 target/arm/tcg/sme.decode      | 17 ++++++++
 target/arm/tcg/sme_helper.c    | 56 +++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 75 ++++++++++++++++++++++++++++++++++
 4 files changed, 163 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

These instructions are present in both SME(1) and SVE2.1 extensions.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-68-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
     tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
 }
 
-TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
+TRANS_FEAT(SCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
 
 static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a)
 {
@@ -XXX,XX +XXX,XX @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
     tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
 }
 
-TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
 
 TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

This is the single vector version within SVE decode space.

Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-69-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  2 ++
 target/arm/tcg/translate-sve.c | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ PSEL            00100101 .1 1 000 .. 01 .... 0 .... 0 ....  \
 
 SCLAMP          01000100 .. 0 ..... 110000 ..... .....          @rda_rn_rm
 UCLAMP          01000100 .. 0 ..... 110001 ..... .....          @rda_rn_rm
+
+FCLAMP          01100100 .. 1 ..... 001001 ..... .....          @rda_rn_rm
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
 
 TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
 
+static bool trans_FCLAMP(DisasContext *s, arg_FCLAMP *a)
+{
+    static gen_helper_gvec_3_ptr * const fn[] = {
+        gen_helper_sme2_bfclamp,
+        gen_helper_sme2_fclamp_h,
+        gen_helper_sme2_fclamp_s,
+        gen_helper_sme2_fclamp_d,
+    };
+
+    /* This insn uses MO_8 to encode BFloat16. */
+    if (a->esz == MO_8
+        ? !dc_isar_feature(aa64_sve_b16b16, s)
+        : !dc_isar_feature(aa64_sme2_or_sve2p1, s)) {
+        return false;
+    }
+
+    /* So far we never optimize rda with MOVPRFX */
+    assert(a->rd == a->ra);
+    return gen_gvec_fpst_zzz(s, fn[a->esz], a->rd, a->rn, a->rm, 1,
+                             a->esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+}
+
 TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
 TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-70-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 23 +++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 20 ++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ UCLAMP          11000001 esz:2 1 zm:5 110001 zn:5 .... 1    \
                 &zzz_en zd=%zd_ax2 n=2
 UCLAMP          11000001 esz:2 1 zm:5 110011 zn:5 ...0 1    \
                 &zzz_en zd=%zd_ax4 n=4
+
+### SME Multiple Zero
+
+&zero_za        rv off ngrp nvec
+
+ZERO_za         11000000 000011 000 .. 0000000000 off:3 \
+                &zero_za ngrp=2 nvec=1 rv=%mova_rv
+ZERO_za         11000000 000011 100 .. 0000000000 off:3 \
+                &zero_za ngrp=4 nvec=1 rv=%mova_rv
+
+ZERO_za         11000000 000011 001 .. 0000000000 ...   \
+                &zero_za ngrp=1 nvec=2 rv=%mova_rv off=%off3_x2
+ZERO_za         11000000 000011 010 .. 0000000000 0..   \
+                &zero_za ngrp=2 nvec=2 rv=%mova_rv off=%off2_x2
+ZERO_za         11000000 000011 011 .. 0000000000 0..   \
+                &zero_za ngrp=4 nvec=2 rv=%mova_rv off=%off2_x2
+
+ZERO_za         11000000 000011 101 .. 0000000000 0..   \
+                &zero_za ngrp=1 nvec=4 rv=%mova_rv off=%off2_x4
+ZERO_za         11000000 000011 110 .. 0000000000 00.   \
+                &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
+ZERO_za         11000000 000011 111 .. 0000000000 00.   \
+                &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
     return true;
 }
 
+static bool trans_ZERO_za(DisasContext *s, arg_ZERO_za *a)
+{
+    if (!dc_isar_feature(aa64_sme2p1, s)) {
+        return false;
+    }
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / a->ngrp;
+        TCGv_ptr t_za = get_zarray(s, a->rv, a->off, a->ngrp, a->nvec);
+
+        for (int r = 0; r < a->ngrp; ++r) {
+            for (int i = 0; i < a->nvec; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                tcg_gen_gvec_dup_imm_var(MO_64, t_za, o_za, svl, svl, 0);
+            }
+        }
+    }
+    return true;
+}
+
 static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

For WHILE, we have the count of enabled predicates, so we don't
need to search to compute the PredTest result.  Reuse the logic
that will shortly be required for counted predicates.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-71-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 81 +++++++++++++++++++++----------------
 1 file changed, 46 insertions(+), 35 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
     return sum;
 }
 
+/* C.f. Arm pseudocode PredCountTest */
+static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
+{
+    uint32_t flags;
+
+    if (count == 0) {
+        flags = 1;                              /* !N, Z, C */
+    } else if (!invert) {
+        flags = (1u << 31) | 2;                 /* N, !Z */
+        flags |= count != elements;             /* C */
+    } else {
+        flags = 2;                              /* !Z, !C */
+        flags |= (count == elements) << 31;     /* N */
+    }
+    return flags;
+}
+
 uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
 {
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
-    uint32_t flags;
-    intptr_t i;
+    intptr_t i, oprbits = oprsz * 8;
+
+    tcg_debug_assert(count <= oprbits);
 
     /* Begin with a zero predicate register.  */
-    flags = do_zero(d, oprsz);
-    if (count == 0) {
-        return flags;
+    do_zero(d, oprsz);
+    if (count) {
+        /* Set all of the requested bits.  */
+        for (i = 0; i < count / 64; ++i) {
+            d->p[i] = esz_mask;
+        }
+        if (count & 63) {
+            d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
+        }
     }
 
-    /* Set all of the requested bits.  */
-    for (i = 0; i < count / 64; ++i) {
-        d->p[i] = esz_mask;
-    }
-    if (count & 63) {
-        d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
-    }
-
-    return predtest_ones(d, oprsz, esz_mask);
+    return pred_count_test(oprbits, count, false);
 }
 
 uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
-    intptr_t i, invcount, oprbits;
+    intptr_t i, invcount, oprbits = oprsz * 8;
     uint64_t bits;
 
-    if (count == 0) {
-        return do_zero(d, oprsz);
-    }
-
-    oprbits = oprsz * 8;
     tcg_debug_assert(count <= oprbits);
 
-    bits = esz_mask;
-    if (oprbits & 63) {
-        bits &= MAKE_64BIT_MASK(0, oprbits & 63);
-    }
-
-    invcount = oprbits - count;
-    for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
-        d->p[i] = bits;
+    /* Begin with a zero predicate register.  */
+    do_zero(d, oprsz);
+    if (count) {
+        /* Set all of the requested bits.  */
         bits = esz_mask;
+        if (oprbits & 63) {
+            bits &= MAKE_64BIT_MASK(0, oprbits & 63);
+        }
+
+        invcount = oprbits - count;
+        for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
+            d->p[i] = bits;
+            bits = esz_mask;
+        }
+        d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
     }
 
-    d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
-
-    while (--i >= 0) {
-        d->p[i] = 0;
-    }
-
-    return predtest_ones(d, oprsz, esz_mask);
+    return pred_count_test(oprbits, count, true);
 }
 
 /* Recursive reduction on a function;
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Merge predtest_ones into its only caller.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-72-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc)
     }
 }
 
-/* As if PredTest(Ones(PL), D, esz).  */
-static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz,
-                              uint64_t esz_mask)
-{
-    uint32_t flags = PREDTEST_INIT;
-    intptr_t i;
-
-    for (i = 0; i < oprsz / 8; i++) {
-        flags = iter_predtest_fwd(d->p[i], esz_mask, flags);
-    }
-    if (oprsz & 7) {
-        uint64_t mask = ~(-1ULL << (8 * (oprsz & 7)));
-        flags = iter_predtest_fwd(d->p[i], esz_mask & mask, flags);
-    }
-    return flags;
-}
-
 uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc)
 {
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     if (last_active_pred(vn, vg, oprsz)) {
-        return predtest_ones(vd, oprsz, -1);
-    } else {
-        return do_zero(vd, oprsz);
+        ARMPredicateReg *d = vd;
+        uint32_t flags = PREDTEST_INIT;
+        intptr_t i;
+
+        /* As if PredTest(Ones(PL), D, MO_8).  */
+        for (i = 0; i < oprsz / 8; i++) {
+            flags = iter_predtest_fwd(d->p[i], -1, flags);
+        }
+        if (oprsz & 7) {
+            uint64_t mask = ~(-1ULL << (8 * (oprsz & 7)));
+            flags = iter_predtest_fwd(d->p[i], mask, flags);
+        }
+        return flags;
     }
+    return do_zero(vd, oprsz);
 }
 
 uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Expand to memset plus the return value, when used.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-73-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ static uint32_t compute_brks_m(uint64_t *d, uint64_t *n, uint64_t *g,
     return flags;
 }
 
-static uint32_t do_zero(ARMPredicateReg *d, intptr_t oprsz)
-{
-    /* It is quicker to zero the whole predicate than loop on OPRSZ.
-     * The compiler should turn this into 4 64-bit integer stores.
-     */
-    memset(d, 0, sizeof(ARMPredicateReg));
-    return PREDTEST_INIT;
-}
-
 void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg,
                        uint32_t pred_desc)
 {
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         compute_brk_z(vd, vm, vg, oprsz, true);
     } else {
-        do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         return compute_brks_z(vd, vm, vg, oprsz, true);
     } else {
-        return do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
+        return PREDTEST_INIT;
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         compute_brk_z(vd, vm, vg, oprsz, false);
     } else {
-        do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         return compute_brks_z(vd, vm, vg, oprsz, false);
     } else {
-        return do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
+        return PREDTEST_INIT;
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc)
 {
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     if (!last_active_pred(vn, vg, oprsz)) {
-        do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc)
         }
         return flags;
     }
-    return do_zero(vd, oprsz);
+    memset(vd, 0, sizeof(ARMPredicateReg));
+    return PREDTEST_INIT;
 }
 
 uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     tcg_debug_assert(count <= oprbits);
 
     /* Begin with a zero predicate register.  */
-    do_zero(d, oprsz);
+    memset(d, 0, sizeof(*d));
     if (count) {
         /* Set all of the requested bits.  */
         for (i = 0; i < count / 64; ++i) {
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     tcg_debug_assert(count <= oprbits);
 
     /* Begin with a zero predicate register.  */
-    do_zero(d, oprsz);
+    memset(d, 0, sizeof(*d));
     if (count) {
         /* Set all of the requested bits.  */
         bits = esz_mask;
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-74-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
     return flags;
 }
 
-uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
+/* D must be cleared on entry. */
+static void do_whilel(ARMPredicateReg *d, uint64_t esz_mask,
+                      uint32_t count, uint32_t oprbits)
 {
-    intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
-    intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
-    uint64_t esz_mask = pred_esz_masks[esz];
-    ARMPredicateReg *d = vd;
-    intptr_t i, oprbits = oprsz * 8;
-
     tcg_debug_assert(count <= oprbits);
-
-    /* Begin with a zero predicate register.  */
-    memset(d, 0, sizeof(*d));
     if (count) {
+        uint32_t i;
+
         /* Set all of the requested bits.  */
         for (i = 0; i < count / 64; ++i) {
             d->p[i] = esz_mask;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
             d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
         }
     }
+}
 
+uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+    uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+    uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+    uint32_t oprbits = oprsz * 8;
+    uint64_t esz_mask = pred_esz_masks[esz];
+    ARMPredicateReg *d = vd;
+
+    memset(d, 0, sizeof(*d));
+    do_whilel(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, false);
 }
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-75-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 39 +++++++++++++++++++------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     return pred_count_test(oprbits, count, false);
 }
 
-uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
+/* D must be cleared on entry. */
+static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask,
+                      uint32_t count, uint32_t oprbits)
 {
-    intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
-    intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
-    uint64_t esz_mask = pred_esz_masks[esz];
-    ARMPredicateReg *d = vd;
-    intptr_t i, invcount, oprbits = oprsz * 8;
-    uint64_t bits;
-
     tcg_debug_assert(count <= oprbits);
-
-    /* Begin with a zero predicate register.  */
-    memset(d, 0, sizeof(*d));
     if (count) {
-        /* Set all of the requested bits.  */
-        bits = esz_mask;
-        if (oprbits & 63) {
-            bits &= MAKE_64BIT_MASK(0, oprbits & 63);
-        }
+        uint32_t i, invcount = oprbits - count;
+        uint64_t bits = esz_mask & MAKE_64BIT_MASK(invcount & 63, 64);
 
-        invcount = oprbits - count;
-        for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
+        for (i = invcount / 64; i < oprbits / 64; ++i) {
             d->p[i] = bits;
             bits = esz_mask;
         }
-        d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
+        if (oprbits & 63) {
+            d->p[i] = bits & MAKE_64BIT_MASK(0, oprbits & 63);
+        }
     }
+}
 
+uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+    uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+    uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+    uint32_t oprbits = oprsz * 8;
+    uint64_t esz_mask = pred_esz_masks[esz];
+    ARMPredicateReg *d = vd;
+
+    memset(d, 0, sizeof(*d));
+    do_whileg(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, true);
 }
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Change the API to pass element count rather than bit count.
This will be helpful later for predicate as counter.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-76-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c    |  2 ++
 target/arm/tcg/translate-sve.c | 13 +++++--------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
 
+    count <<= esz;
     memset(d, 0, sizeof(*d));
     do_whilel(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, false);
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
 
+    count <<= esz;
     memset(d, 0, sizeof(*d));
     do_whileg(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, true);
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     t2 = tcg_temp_new_i32();
     tcg_gen_extrl_i64_i32(t2, t0);
 
-    /* Scale elements to bits.  */
-    tcg_gen_shli_i32(t2, t2, a->esz);
-
     desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8);
     desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
 
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
     op0 = read_cpu_reg(s, a->rn, 1);
     op1 = read_cpu_reg(s, a->rm, 1);
 
-    tmax = tcg_constant_i64(vsz);
+    tmax = tcg_constant_i64(vsz >> a->esz);
     diff = tcg_temp_new_i64();
 
     if (a->rw) {
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
         tcg_gen_sub_i64(diff, op0, op1);
         tcg_gen_sub_i64(t1, op1, op0);
         tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1);
-        /* Round down to a multiple of ESIZE.  */
-        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* Divide, rounding down, by ESIZE.  */
+        tcg_gen_shri_i64(diff, diff, a->esz);
         /* If op1 == op0, diff == 0, and the condition is always true. */
         tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff);
     } else {
         /* WHILEWR */
         tcg_gen_sub_i64(diff, op1, op0);
-        /* Round down to a multiple of ESIZE.  */
-        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* Divide, rounding down, by ESIZE.  */
+        tcg_gen_shri_i64(diff, diff, a->esz);
         /* If op0 >= op1, diff <= 0, the condition is always true. */
         tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff);
     }
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Use TRANS_FEAT to select the correct predicate.
Pass the helper and a boolean to do_WHILE.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-77-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  4 +++-
 target/arm/tcg/translate-sve.c | 23 +++++++++--------------
 2 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SINCDECP_z      00100101 .. 1010 d:1 u:1 10000 00 .... .....    @incdec2_pred
 CTERM           00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000
 
 # SVE integer compare scalar count and limit
-WHILE           00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4
+&while          esz rd rn rm sf u eq
+WHILE_lt        00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4  &while
+WHILE_gt        00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4  &while
 
 # SVE2 pointer conflict compare
 WHILE_ptr       00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a)
     return true;
 }
 
-static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
+typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
+static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
 {
     TCGv_i64 op0, op1, t0, t1, tmax;
     TCGv_i32 t2;
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     TCGCond cond;
     uint64_t maxval;
     /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */
-    bool eq = a->eq == a->lt;
+    bool eq = a->eq == lt;
 
-    /* The greater-than conditions are all SVE2. */
-    if (a->lt
-        ? !dc_isar_feature(aa64_sve, s)
-        : !dc_isar_feature(aa64_sve2, s)) {
-        return false;
-    }
     if (!sve_access_check(s)) {
         return true;
     }
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     t0 = tcg_temp_new_i64();
     t1 = tcg_temp_new_i64();
 
-    if (a->lt) {
+    if (lt) {
         tcg_gen_sub_i64(t0, op1, op0);
         if (a->u) {
             maxval = a->sf ? UINT64_MAX : UINT32_MAX;
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     ptr = tcg_temp_new_ptr();
     tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd));
 
-    if (a->lt) {
-        gen_helper_sve_whilel(t2, ptr, t2, tcg_constant_i32(desc));
-    } else {
-        gen_helper_sve_whileg(t2, ptr, t2, tcg_constant_i32(desc));
-    }
+    fn(t2, ptr, t2, tcg_constant_i32(desc));
+
     do_pred_flags(t2);
     return true;
 }
 
+TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel)
+TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg)
+
 static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
 {
     TCGv_i64 op0, op1, diff, t1, tmax;
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-79-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  3 +++
 target/arm/tcg/sve.decode      |  8 +++++++
 target/arm/tcg/sve_helper.c    | 40 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 14 ++++++++----
 4 files changed, 61 insertions(+), 4 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-80-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  3 ++
 target/arm/tcg/sve.decode      | 11 +++++++
 target/arm/tcg/sve_helper.c    | 53 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 22 ++++++++++----
 4 files changed, 84 insertions(+), 5 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-81-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  1 +
 target/arm/tcg/translate-sve.c | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ PTEST           00100101 01 010000 11 pg:4 0 rn:4 0 0000
 
 # SVE predicate initialize
 PTRUE           00100101 esz:2 01100 s:1 111000 pat:5 0 rd:4
+PTRUE_cnt       00100101 esz:2 1000000111100000010 ...          rd=%pnd
 
 # SVE initialize FFR
 SETFFR          00100101 0010 1100 1001 0000 0000 0000
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag)
 
 TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s)
 
+static bool trans_PTRUE_cnt(DisasContext *s, arg_PTRUE_cnt *a)
+{
+    if (!dc_isar_feature(aa64_sme2_or_sve2p1, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        /* Canonical TRUE is 0 count, invert bit, plus element size. */
+        int val = (1 << 15) | (1 << a->esz);
+
+        /* Write val to the first uint64_t; clear all of the rest. */
+        tcg_gen_gvec_dup_imm(MO_64, pred_full_reg_offset(s, a->rd),
+                             8, size_for_gvec(pred_full_reg_size(s)), val);
+    }
+    return true;
+}
+
 /* Note pat == 31 is #all, to set all elements.  */
 TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve,
                         do_predset, 0, FFR_PRED_NUM, 31, false)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-82-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 25 ++++++++++++++++++
 target/arm/tcg/sve.decode      |  7 ++++++
 target/arm/tcg/sve_helper.c    | 46 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 35 ++++++++++++++++++++++++++
 4 files changed, 113 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-83-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  2 +
 target/arm/tcg/vec_internal.h  | 74 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/sve.decode      |  6 +++
 target/arm/tcg/sve_helper.c    | 28 +++++++++++++
 target/arm/tcg/translate-sve.c | 36 +++++++++++++++++
 5 files changed, 146 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-84-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |   5 +
 target/arm/tcg/sme.decode      |   9 +
 target/arm/tcg/sme_helper.c    | 317 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  31 ++++
 4 files changed, 362 insertions(+)

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i3
 DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sme2_sel_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ UCLAMP          11000001 esz:2 1 zm:5 110001 zn:5 .... 1    \
 UCLAMP          11000001 esz:2 1 zm:5 110011 zn:5 ...0 1    \
                 &zzz_en zd=%zd_ax4 n=4
 
+### SME2 Multi-vector SVE Select
+
+%sel_pg         10:3 !function=plus_8
+
+SEL             11000001 esz:2 1 ....0 100 ... ....0 ....0  \
+                n=2 zd=%zd_ax2 zn=%zn_ax2 zm=%zm_ax2 pg=%sel_pg
+SEL             11000001 esz:2 1 ...01 100 ... ...00 ...00  \
+                n=4 zd=%zd_ax4 zn=%zn_ax4 zm=%zm_ax4 pg=%sel_pg
+
 ### SME Multiple Zero
 
 &zero_za        rv off ngrp nvec
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ FCLAMP(sme2_fclamp_d, float64, H8)
 FCLAMP(sme2_bfclamp, bfloat16, H2)
 
 #undef FCLAMP
+
+void HELPER(sme2_sel_b)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint8_t);
+    DecodeCounter p = decode_counter(png, vl, MO_8);
+
+    if (p.lg2_stride == 0) {
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, n, vl);  /* all true */
+                } else if (elements <= split) {
+                    memcpy(d, m, vl);  /* all false */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H1(e)] = m[H1(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H1(e)] = n[H1(e)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, m, vl);  /* all false */
+                } else if (elements <= split) {
+                    memcpy(d, n, vl);  /* all true */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H1(e)] = n[H1(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H1(e)] = m[H1(e)];
+                    }
+                }
+            }
+        }
+    } else {
+        int estride = 1 << p.lg2_stride;
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e++) {
+                    d[H1(e)] = m[H1(e)];
+                }
+                for (; e < elements; e += estride) {
+                    d[H1(e)] = n[H1(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H1(e + i)] = m[H1(e + i)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e += estride) {
+                    d[H1(e)] = n[H1(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H1(e + i)] = m[H1(e + i)];
+                    }
+                }
+                for (; e < elements; e++) {
+                    d[H1(e)] = m[H1(e)];
+                }
+            }
+        }
+    }
+}
+
+void HELPER(sme2_sel_h)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint16_t);
+    DecodeCounter p = decode_counter(png, vl, MO_16);
+
+    if (p.lg2_stride == 0) {
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, n, vl);  /* all true */
+                } else if (elements <= split) {
+                    memcpy(d, m, vl);  /* all false */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H2(e)] = m[H2(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H2(e)] = n[H2(e)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, m, vl);  /* all false */
+                } else if (elements <= split) {
+                    memcpy(d, n, vl);  /* all true */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H2(e)] = n[H2(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H2(e)] = m[H2(e)];
+                    }
+                }
+            }
+        }
+    } else {
+        int estride = 1 << p.lg2_stride;
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e++) {
+                    d[H2(e)] = m[H2(e)];
+                }
+                for (; e < elements; e += estride) {
+                    d[H2(e)] = n[H2(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H2(e + i)] = m[H2(e + i)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e += estride) {
+                    d[H2(e)] = n[H2(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H2(e + i)] = m[H2(e + i)];
+                    }
+                }
+                for (; e < elements; e++) {
+                    d[H2(e)] = m[H2(e)];
+                }
+            }
+        }
+    }
+}
+
+void HELPER(sme2_sel_s)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint32_t);
+    DecodeCounter p = decode_counter(png, vl, MO_32);
+
+    if (p.lg2_stride == 0) {
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, n, vl);  /* all true */
+                } else if (elements <= split) {
+                    memcpy(d, m, vl);  /* all false */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H4(e)] = m[H4(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H4(e)] = n[H4(e)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, m, vl);  /* all false */
+                } else if (elements <= split) {
+                    memcpy(d, n, vl);  /* all true */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H4(e)] = n[H4(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H4(e)] = m[H4(e)];
+                    }
+                }
+            }
+        }
+    } else {
+        /* p.esz must be MO_64, so stride must be 2. */
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e++) {
+                    d[H4(e)] = m[H4(e)];
+                }
+                for (; e < elements; e += 2) {
+                    d[H4(e)] = n[H4(e)];
+                    d[H4(e + 1)] = m[H4(e + 1)];
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e += 2) {
+                    d[H4(e)] = n[H4(e)];
+                    d[H4(e + 1)] = m[H4(e + 1)];
+                }
+                for (; e < elements; e++) {
+                    d[H4(e)] = m[H4(e)];
+                }
+            }
+        }
+    }
+}
+
+void HELPER(sme2_sel_d)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint64_t);
+    DecodeCounter p = decode_counter(png, vl, MO_64);
+
+    if (p.invert) {
+        for (int r = 0; r < nreg; r++) {
+            uint64_t *d = vd + r * sizeof(ARMVectorReg);
+            uint64_t *n = vn + r * sizeof(ARMVectorReg);
+            uint64_t *m = vm + r * sizeof(ARMVectorReg);
+            int split = p.count - r * elements;
+
+            if (split <= 0) {
+                memcpy(d, n, vl);  /* all true */
+            } else if (elements <= split) {
+                memcpy(d, m, vl);  /* all false */
+            } else {
+                memcpy(d, m, split * sizeof(uint64_t));
+                memcpy(d + split, n + split,
+                       (elements - split) * sizeof(uint64_t));
+            }
+        }
+    } else {
+        for (int r = 0; r < nreg; r++) {
+            uint64_t *d = vd + r * sizeof(ARMVectorReg);
+            uint64_t *n = vn + r * sizeof(ARMVectorReg);
+            uint64_t *m = vm + r * sizeof(ARMVectorReg);
+            int split = p.count - r * elements;
+
+            if (split <= 0) {
+                memcpy(d, m, vl);  /* all false */
+            } else if (elements <= split) {
+                memcpy(d, n, vl);  /* all true */
+            } else {
+                memcpy(d, n, split * sizeof(uint64_t));
+                memcpy(d + split, m + split,
+                       (elements - split) * sizeof(uint64_t));
+            }
+        }
+    }
+}
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const uclamp_fns[] = {
     gen_helper_sme2_uclamp_d,
 };
 TRANS(UCLAMP, do_clamp, a, uclamp_fns)
+
+static bool trans_SEL(DisasContext *s, arg_SEL *a)
+{
+    typedef void sme_sel_fn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32);
+    static sme_sel_fn * const fns[4] = {
+        gen_helper_sme2_sel_b, gen_helper_sme2_sel_h,
+        gen_helper_sme2_sel_s, gen_helper_sme2_sel_d
+    };
+
+    if (!dc_isar_feature(aa64_sme2, s)) {
+        return false;
+    }
+    if (sme_sm_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        uint32_t desc = simd_desc(svl, svl, a->n);
+        TCGv_ptr t_d = tcg_temp_new_ptr();
+        TCGv_ptr t_n = tcg_temp_new_ptr();
+        TCGv_ptr t_m = tcg_temp_new_ptr();
+        TCGv_i32 png = tcg_temp_new_i32();
+
+        tcg_gen_addi_ptr(t_d, tcg_env, vec_full_reg_offset(s, a->zd));
+        tcg_gen_addi_ptr(t_n, tcg_env, vec_full_reg_offset(s, a->zn));
+        tcg_gen_addi_ptr(t_m, tcg_env, vec_full_reg_offset(s, a->zm));
+
+        tcg_gen_ld16u_i32(png, tcg_env, pred_full_reg_offset(s, a->pg)
+                          ^ (HOST_BIG_ENDIAN ? 6 : 0));
+
+        fns[a->esz](t_d, t_n, t_m, png, tcg_constant_i32(desc));
+    }
+    return true;
+}
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-85-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 15 ++++++++++++
 target/arm/tcg/sve.decode      |  5 ++++
 target/arm/tcg/sve_helper.c    | 42 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c |  3 +++
 4 files changed, 65 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-86-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 49 ++++++++++++++++++++++++
 target/arm/tcg/sve.decode      |  8 ++++
 target/arm/tcg/sve_helper.c    | 70 +++++++++++++++++++++-------------
 target/arm/tcg/translate-sve.c | 48 +++++++++++++++++++++++
 4 files changed, 148 insertions(+), 27 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-87-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  6 ++++++
 target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
 BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_ex esz=2
+BFMLSLB_zzzw    01100100 11 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_ex esz=2
+BFMLSLT_zzzw    01100100 11 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point dot-product
 FDOT_zzzz       01100100 00 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point multiply-add long (indexed)
+
 FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 FMLALT_zzxw     01100100 10 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
 FMLSLB_zzxw     01100100 10 1 ..... 0110.0 ..... .....     @rrxr_3a esz=2
 FMLSLT_zzxw     01100100 10 1 ..... 0110.1 ..... .....     @rrxr_3a esz=2
+
 BFMLALB_zzxw    01100100 11 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 BFMLALT_zzxw    01100100 11 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
+BFMLSLB_zzxw    01100100 11 1 ..... 0110.0 ..... .....     @rrxr_3a esz=2
+BFMLSLT_zzxw    01100100 11 1 ..... 0110.1 ..... .....     @rrxr_3a esz=2
 
 ### SVE2 floating-point dot-product (indexed)
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
 TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false)
 TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true)
 
+static bool do_BFMLSL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel)
+{
+    if (s->fpcr_ah) {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl,
+                                  a->rd, a->rn, a->rm, a->ra, sel, FPST_AH);
+    } else {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl,
+                                  a->rd, a->rn, a->rm, a->ra, sel, FPST_A64);
+    }
+}
+
+TRANS_FEAT(BFMLSLB_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, false)
+TRANS_FEAT(BFMLSLT_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, true)
+
+static bool do_BFMLSL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
+{
+    if (s->fpcr_ah) {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl_idx,
+                                  a->rd, a->rn, a->rm, a->ra,
+                                  (a->index << 1) | sel, FPST_AH);
+    } else {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl_idx,
+                                  a->rd, a->rn, a->rm, a->ra,
+                                  (a->index << 1) | sel, FPST_A64);
+    }
+}
+
+TRANS_FEAT(BFMLSLB_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, false)
+TRANS_FEAT(BFMLSLT_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, true)
+
 static bool trans_PSEL(DisasContext *s, arg_psel *a)
 {
     int vl = vec_full_reg_size(s);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-88-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  1 +
 target/arm/tcg/sve.decode      |  3 ++-
 target/arm/tcg/sve_helper.c    | 21 +++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++
 4 files changed, 54 insertions(+), 1 deletion(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-89-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  6 ++++++
 target/arm/tcg/translate-sve.c | 21 +++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ DUP_s           00000101 .. 1 00000 001110 ..... .....          @rd_rn
 DUP_x           00000101 .. 1 ..... 001000 rn:5 rd:5 \
                 &rri imm=%imm7_22_16
 
+# SVE Permute Vector - one source quadwords
+DUPQ            00000101 001 imm:4    1 001001 rn:5 rd:5        &rri_esz esz=0
+DUPQ            00000101 001 imm:3   10 001001 rn:5 rd:5        &rri_esz esz=1
+DUPQ            00000101 001 imm:2  100 001001 rn:5 rd:5        &rri_esz esz=2
+DUPQ            00000101 001 imm:1 1000 001001 rn:5 rd:5        &rri_esz esz=3
+
 # SVE insert SIMD&FP scalar register
 INSR_f          00000101 .. 1 10100 001110 ..... .....          @rdn_rm
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
     return true;
 }
 
+static bool trans_DUPQ(DisasContext *s, arg_DUPQ *a)
+{
+    unsigned vl, dofs, nofs;
+
+    if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    vl = vec_full_reg_size(s);
+    dofs = vec_full_reg_offset(s, a->rd);
+    nofs = vec_reg_offset(s, a->rn, a->imm, a->esz);
+
+    for (unsigned i = 0; i < vl; i += 16) {
+        tcg_gen_gvec_dup_mem(a->esz, dofs + i, nofs + i, 16, 16);
+    }
+    return true;
+}
+
 static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val)
 {
     typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32);
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-90-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  2 ++
 target/arm/tcg/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ DUPQ            00000101 001 imm:3   10 001001 rn:5 rd:5        &rri_esz esz=1
 DUPQ            00000101 001 imm:2  100 001001 rn:5 rd:5        &rri_esz esz=2
 DUPQ            00000101 001 imm:1 1000 001001 rn:5 rd:5        &rri_esz esz=3
 
+EXTQ            00000101 0110 imm:4 001001 rn:5 rd:5            &rri
+
 # SVE insert SIMD&FP scalar register
 INSR_f          00000101 .. 1 10100 001110 ..... .....          @rdn_rm
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm)
 TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm)
 TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm)
 
+static bool trans_EXTQ(DisasContext *s, arg_EXTQ *a)
+{
+    unsigned vl, dofs, sofs0, sofs1, sofs2, imm;
+
+    if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    imm = a->imm;
+    if (imm == 0) {
+        /* So far we never optimize Zdn with MOVPRFX, so zd = zn is a nop. */
+        return true;
+    }
+
+    vl = vec_full_reg_size(s);
+    dofs = vec_full_reg_offset(s, a->rd);
+    sofs2 = vec_full_reg_offset(s, a->rn);
+
+    if (imm & 8) {
+        sofs0 = dofs + 8;
+        sofs1 = sofs2;
+        sofs2 += 8;
+    } else {
+        sofs0 = dofs;
+        sofs1 = dofs + 8;
+    }
+    imm = (imm & 7) << 3;
+
+    for (unsigned i = 0; i < vl; i += 16) {
+        TCGv_i64 s0 = tcg_temp_new_i64();
+        TCGv_i64 s1 = tcg_temp_new_i64();
+        TCGv_i64 s2 = tcg_temp_new_i64();
+
+        tcg_gen_ld_i64(s0, tcg_env, sofs0 + i);
+        tcg_gen_ld_i64(s1, tcg_env, sofs1 + i);
+        tcg_gen_ld_i64(s2, tcg_env, sofs2 + i);
+
+        tcg_gen_extract2_i64(s0, s0, s1, imm);
+        tcg_gen_extract2_i64(s1, s1, s2, imm);
+
+        tcg_gen_st_i64(s0, tcg_env, dofs + i);
+        tcg_gen_st_i64(s1, tcg_env, dofs + i + 8);
+    }
+    return true;
+}
+
 /*
  *** SVE Permute - Unpredicated Group
  */
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-91-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  8 +++
 target/arm/tcg/vec_internal.h  | 34 ++++++++++++
 target/arm/tcg/sve.decode      | 17 ++++++
 target/arm/tcg/sve_helper.c    | 50 +++++++++++++++++
 target/arm/tcg/translate-sve.c | 98 ++++++++++++++++++++++++++++++++++
 5 files changed, 207 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-92-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 10 ++++++++++
 target/arm/tcg/sve.decode      |  6 ++++++
 target/arm/tcg/sve_helper.c    | 29 +++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 19 ++++++++++++++++++-
 4 files changed, 63 insertions(+), 1 deletion(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-93-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 10 ++++++++++
 target/arm/tcg/sve.decode      |  3 +++
 target/arm/tcg/sve_helper.c    | 10 ++++++++++
 target/arm/tcg/translate-sve.c | 14 ++++++++++++++
 4 files changed, 37 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Implement the SVE2p1 consecutive register LD1/ST1,
and the SME2 strided register LD1/ST1.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-94-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  16 ++
 target/arm/tcg/sve.decode      |  50 ++++
 target/arm/tcg/sve_helper.c    | 493 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 103 +++++++
 4 files changed, 662 insertions(+)

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_ld1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_st1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SCLAMP          01000100 .. 0 ..... 110000 ..... .....          @rda_rn_rm
 UCLAMP          01000100 .. 0 ..... 110001 ..... .....          @rda_rn_rm
 
 FCLAMP          01100100 .. 1 ..... 001001 ..... .....          @rda_rn_rm
+
+### SVE2p1 multi-vec contiguous load
+
+&zcrr_ldst      rd png rn rm esz nreg
+&zcri_ldst      rd png rn imm esz nreg
+%png            10:3 !function=plus_8
+%zd_ax2         1:4 !function=times_2
+%zd_ax4         2:3 !function=times_4
+
+LD1_zcrr        10100000000 rm:5 0 esz:2 ... rn:5 .... - \
+                &zcrr_ldst %png rd=%zd_ax2 nreg=2
+LD1_zcrr        10100000000 rm:5 1 esz:2 ... rn:5 ... 0- \
+                &zcrr_ldst %png rd=%zd_ax4 nreg=4
+
+ST1_zcrr        10100000001 rm:5 0 esz:2 ... rn:5 .... - \
+                &zcrr_ldst %png rd=%zd_ax2 nreg=2
+ST1_zcrr        10100000001 rm:5 1 esz:2 ... rn:5 ... 0- \
+                &zcrr_ldst %png rd=%zd_ax4 nreg=4
+
+LD1_zcri        101000000100 imm:s4 0 esz:2 ... rn:5 .... - \
+                &zcri_ldst %png rd=%zd_ax2 nreg=2
+LD1_zcri        101000000100 imm:s4 1 esz:2 ... rn:5 ... 0- \
+                &zcri_ldst %png rd=%zd_ax4 nreg=4
+
+ST1_zcri        101000000110 imm:s4 0 esz:2 ... rn:5 .... - \
+                &zcri_ldst %png rd=%zd_ax2 nreg=2
+ST1_zcri        101000000110 imm:s4 1 esz:2 ... rn:5 ... 0- \
+                &zcri_ldst %png rd=%zd_ax4 nreg=4
+
+# Note: N bit and 0 bit (for nreg4) still mashed in rd.
+# This is handled within gen_ldst_c().
+LD1_zcrr_stride 10100001000 rm:5 0 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=2
+LD1_zcrr_stride 10100001000 rm:5 1 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=4
+
+ST1_zcrr_stride 10100001001 rm:5 0 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=2
+ST1_zcrr_stride 10100001001 rm:5 1 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=4
+
+LD1_zcri_stride 101000010100 imm:s4 0 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=2
+LD1_zcri_stride 101000010100 imm:s4 1 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=4
+
+ST1_zcri_stride 101000010110 imm:s4 0 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=2
+ST1_zcri_stride 101000010110 imm:s4 1 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=4
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64)
 #undef DO_ST1_ZPZ_S
 #undef DO_ST1_ZPZ_D
 
+/*
+ * SVE2.1 consecutive register load/store
+ */
+
+static unsigned sve2p1_cont_ldst_elements(SVEContLdSt *info, vaddr addr,
+                                          uint32_t png, intptr_t reg_max,
+                                          int N, int v_esz)
+{
+    const int esize = 1 << v_esz;
+    intptr_t reg_off_first = -1, reg_off_last = -1, reg_off_split;
+    DecodeCounter p = decode_counter(png, reg_max, v_esz);
+    unsigned b_count = p.count << v_esz;
+    unsigned b_stride = 1 << (v_esz + p.lg2_stride);
+    intptr_t page_split;
+
+    /* Set all of the element indices to -1, and the TLB data to 0. */
+    memset(info, -1, offsetof(SVEContLdSt, page));
+    memset(info->page, 0, sizeof(info->page));
+
+    if (p.invert) {
+        if (b_count >= reg_max * N) {
+            return 0;
+        }
+        reg_off_first = b_count;
+        reg_off_last = reg_max * N - b_stride;
+    } else {
+        if (b_count == 0) {
+            return 0;
+        }
+        reg_off_first = 0;
+        reg_off_last = MIN(b_count - esize, reg_max * N - b_stride);
+    }
+
+    info->reg_off_first[0] = reg_off_first;
+    info->mem_off_first[0] = reg_off_first;
+
+    page_split = -(addr | TARGET_PAGE_MASK);
+    if (reg_off_last + esize <= page_split || reg_off_first >= page_split) {
+        /* The entire operation fits within a single page. */
+        info->reg_off_last[0] = reg_off_last;
+        return b_stride;
+    }
+
+    info->page_split = page_split;
+    reg_off_split = ROUND_DOWN(page_split, esize);
+
+    /*
+     * This is the last full element on the first page, but it is not
+     * necessarily active.  If there is no full element, i.e. the first
+     * active element is the one that's split, this value remains -1.
+     * It is useful as iteration bounds.
+     */
+    if (reg_off_split != 0) {
+        info->reg_off_last[0] = ROUND_DOWN(reg_off_split - esize, b_stride);
+    }
+
+    /* Determine if an unaligned element spans the pages.  */
+    if (page_split & (esize - 1)) {
+        /* It is helpful to know if the split element is active. */
+        if ((reg_off_split & (b_stride - 1)) == 0) {
+            info->reg_off_split = reg_off_split;
+            info->mem_off_split = reg_off_split;
+        }
+        reg_off_split += esize;
+    }
+
+    /*
+     * We do want the first active element on the second page, because
+     * this may affect the address reported in an exception.
+     */
+    reg_off_split = ROUND_UP(reg_off_split, b_stride);
+    if (reg_off_split <= reg_off_last) {
+        info->reg_off_first[1] = reg_off_split;
+        info->mem_off_first[1] = reg_off_split;
+        info->reg_off_last[1] = reg_off_last;
+    }
+    return b_stride;
+}
+
+static void sve2p1_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env,
+                                         target_ulong addr, unsigned estride,
+                                         int esize, int wp_access, uintptr_t ra)
+{
+#ifndef CONFIG_USER_ONLY
+    intptr_t count_off, count_last;
+    int flags0 = info->page[0].flags;
+    int flags1 = info->page[1].flags;
+
+    if (likely(!((flags0 | flags1) & TLB_WATCHPOINT))) {
+        return;
+    }
+
+    /* Indicate that watchpoints are handled. */
+    info->page[0].flags = flags0 & ~TLB_WATCHPOINT;
+    info->page[1].flags = flags1 & ~TLB_WATCHPOINT;
+
+    if (flags0 & TLB_WATCHPOINT) {
+        count_off = info->reg_off_first[0];
+        count_last = info->reg_off_split;
+        if (count_last < 0) {
+            count_last = info->reg_off_last[0];
+        }
+        do {
+            cpu_check_watchpoint(env_cpu(env), addr + count_off,
+                                 esize, info->page[0].attrs, wp_access, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+
+    count_off = info->reg_off_first[1];
+    if ((flags1 & TLB_WATCHPOINT) && count_off >= 0) {
+        count_last = info->reg_off_last[1];
+        do {
+            cpu_check_watchpoint(env_cpu(env), addr + count_off,
+                                 esize, info->page[1].attrs,
+                                 wp_access, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+#endif
+}
+
+static void sve2p1_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env,
+                                       target_ulong addr, unsigned estride,
+                                       int esize, uint32_t mtedesc,
+                                       uintptr_t ra)
+{
+    intptr_t count_off, count_last;
+
+    /*
+     * TODO: estride is always a small power of two, <= 8.
+     * Manipulate the stride within the loops such that
+     *   - first iteration hits addr + off, as required,
+     *   - second iteration hits ALIGN_UP(addr, 16),
+     *   - other iterations advance addr by 16.
+     * This will minimize the probing to once per MTE granule.
+     */
+
+    /* Process the page only if MemAttr == Tagged. */
+    if (info->page[0].tagged) {
+        count_off = info->reg_off_first[0];
+        count_last = info->reg_off_split;
+        if (count_last < 0) {
+            count_last = info->reg_off_last[0];
+        }
+
+        do {
+            mte_check(env, mtedesc, addr + count_off, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+
+    count_off = info->reg_off_first[1];
+    if (count_off >= 0 && info->page[1].tagged) {
+        count_last = info->reg_off_last[1];
+        do {
+            mte_check(env, mtedesc, addr + count_off, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+}
+
+static inline QEMU_ALWAYS_INLINE
+void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr,
+                  uint32_t png, uint32_t desc,
+                  const uintptr_t ra, const MemOp esz,
+                  sve_ldst1_host_fn *host_fn,
+                  sve_ldst1_tlb_fn *tlb_fn)
+{
+    const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2;
+    const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4);
+    uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT);
+    const intptr_t reg_max = simd_oprsz(desc);
+    const unsigned esize = 1 << esz;
+    intptr_t count_off, count_last;
+    intptr_t reg_off, reg_last, reg_n;
+    SVEContLdSt info;
+    unsigned estride, flags;
+    void *host;
+
+    estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz);
+    if (estride == 0) {
+        /* The entire predicate was false; no load occurs.  */
+        for (unsigned n = 0; n < N; n++) {
+            memset(zd + n * rstride, 0, reg_max);
+        }
+        return;
+    }
+
+    /* Probe the page(s).  Exit with exception for any invalid page. */
+    sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra);
+
+    /* Handle watchpoints for all active elements. */
+    sve2p1_cont_ldst_watchpoints(&info, env, addr, estride,
+                                 esize, BP_MEM_READ, ra);
+
+    /*
+     * Handle mte checks for all active elements.
+     * Since TBI must be set for MTE, !mtedesc => !mte_active.
+     */
+    if (mtedesc) {
+        sve2p1_cont_ldst_mte_check(&info, env, estride, addr,
+                                   esize, mtedesc, ra);
+    }
+
+    flags = info.page[0].flags | info.page[1].flags;
+    if (unlikely(flags != 0)) {
+        /*
+         * At least one page includes MMIO.
+         * Any bus operation can fail with cpu_transaction_failed,
+         * which for ARM will raise SyncExternal.  Perform the load
+         * into scratch memory to preserve register state until the end.
+         */
+        ARMVectorReg scratch[4] = { };
+
+        count_off = info.reg_off_first[0];
+        count_last = info.reg_off_last[1];
+        if (count_last < 0) {
+            count_last = info.reg_off_split;
+            if (count_last < 0) {
+                count_last = info.reg_off_last[0];
+            }
+        }
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+
+        do {
+            reg_last = MIN(count_last - count_off, reg_max - esize);
+            do {
+                tlb_fn(env, &scratch[reg_n], reg_off, addr + count_off, ra);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+
+        for (unsigned n = 0; n < N; ++n) {
+            memcpy(&zd[n * rstride], &scratch[n], reg_max);
+        }
+        return;
+    }
+
+    /* The entire operation is in RAM, on valid pages. */
+
+    for (unsigned n = 0; n < N; ++n) {
+        memset(&zd[n * rstride], 0, reg_max);
+    }
+
+    count_off = info.reg_off_first[0];
+    count_last = info.reg_off_last[0];
+    reg_off = count_off % reg_max;
+    reg_n = count_off / reg_max;
+    host = info.page[0].host;
+
+    set_helper_retaddr(ra);
+
+    do {
+        reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+        do {
+            host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+            reg_off += estride;
+            count_off += estride;
+        } while (reg_off <= reg_last);
+        reg_off = 0;
+        reg_n++;
+    } while (count_off <= count_last);
+
+    clear_helper_retaddr();
+
+    /*
+     * Use the slow path to manage the cross-page misalignment.
+     * But we know this is RAM and cannot trap.
+     */
+    count_off = info.reg_off_split;
+    if (unlikely(count_off >= 0)) {
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+    }
+
+    count_off = info.reg_off_first[1];
+    if (unlikely(count_off >= 0)) {
+        count_last = info.reg_off_last[1];
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        host = info.page[1].host;
+
+        set_helper_retaddr(ra);
+
+        do {
+            reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+            do {
+                host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+
+        clear_helper_retaddr();
+    }
+}
+
+void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr,
+                            uint32_t png, uint32_t desc)
+{
+    sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), MO_8,
+                 sve_ld1bb_host, sve_ld1bb_tlb);
+}
+
+#define DO_LD1_2(NAME, ESZ)                                             \
+void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_le_host, sve_##NAME##_le_tlb);            \
+}                                                                       \
+void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_be_host, sve_##NAME##_be_tlb);            \
+}
+
+DO_LD1_2(ld1hh, MO_16)
+DO_LD1_2(ld1ss, MO_32)
+DO_LD1_2(ld1dd, MO_64)
+
+#undef DO_LD1_2
+
+static inline QEMU_ALWAYS_INLINE
+void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr,
+                  uint32_t png, uint32_t desc,
+                  const uintptr_t ra, const int esz,
+                  sve_ldst1_host_fn *host_fn,
+                  sve_ldst1_tlb_fn *tlb_fn)
+{
+    const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2;
+    const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4);
+    uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT);
+    const intptr_t reg_max = simd_oprsz(desc);
+    const unsigned esize = 1 << esz;
+    intptr_t count_off, count_last;
+    intptr_t reg_off, reg_last, reg_n;
+    SVEContLdSt info;
+    unsigned estride, flags;
+    void *host;
+
+    estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz);
+    if (estride == 0) {
+        /* The entire predicate was false; no store occurs.  */
+        return;
+    }
+
+    /* Probe the page(s).  Exit with exception for any invalid page. */
+    sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra);
+
+    /* Handle watchpoints for all active elements. */
+    sve2p1_cont_ldst_watchpoints(&info, env, addr, estride,
+                                 esize, BP_MEM_WRITE, ra);
+
+    /*
+     * Handle mte checks for all active elements.
+     * Since TBI must be set for MTE, !mtedesc => !mte_active.
+     */
+    if (mtedesc) {
+        sve2p1_cont_ldst_mte_check(&info, env, estride, addr,
+                                   esize, mtedesc, ra);
+    }
+
+    flags = info.page[0].flags | info.page[1].flags;
+    if (unlikely(flags != 0)) {
+        /*
+         * At least one page includes MMIO.
+         * Any bus operation can fail with cpu_transaction_failed,
+         * which for ARM will raise SyncExternal.  Perform the load
+         * into scratch memory to preserve register state until the end.
+         */
+        count_off = info.reg_off_first[0];
+        count_last = info.reg_off_last[1];
+        if (count_last < 0) {
+            count_last = info.reg_off_split;
+            if (count_last < 0) {
+                count_last = info.reg_off_last[0];
+            }
+        }
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+
+        do {
+            reg_last = MIN(count_last - count_off, reg_max - esize);
+            do {
+                tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+        return;
+    }
+
+    /* The entire operation is in RAM, on valid pages. */
+
+    count_off = info.reg_off_first[0];
+    count_last = info.reg_off_last[0];
+    reg_off = count_off % reg_max;
+    reg_n = count_off / reg_max;
+    host = info.page[0].host;
+
+    set_helper_retaddr(ra);
+
+    do {
+        reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+        do {
+            host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+            reg_off += estride;
+            count_off += estride;
+        } while (reg_off <= reg_last);
+        reg_off = 0;
+        reg_n++;
+    } while (count_off <= count_last);
+
+    clear_helper_retaddr();
+
+    /*
+     * Use the slow path to manage the cross-page misalignment.
+     * But we know this is RAM and cannot trap.
+     */
+    count_off = info.reg_off_split;
+    if (unlikely(count_off >= 0)) {
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+    }
+
+    count_off = info.reg_off_first[1];
+    if (unlikely(count_off >= 0)) {
+        count_last = info.reg_off_last[1];
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        host = info.page[1].host;
+
+        set_helper_retaddr(ra);
+
+        do {
+            reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+            do {
+                host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+
+        clear_helper_retaddr();
+    }
+}
+
+void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr,
+                           uint32_t png, uint32_t desc)
+{
+    sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), MO_8,
+                 sve_st1bb_host, sve_st1bb_tlb);
+}
+
+#define DO_ST1_2(NAME, ESZ)                                             \
+void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_le_host, sve_##NAME##_le_tlb);            \
+}                                                                       \
+void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_be_host, sve_##NAME##_be_tlb);            \
+}
+
+DO_ST1_2(st1hh, MO_16)
+DO_ST1_2(st1ss, MO_32)
+DO_ST1_2(st1dd, MO_64)
+
+#undef DO_ST1_2
+
 void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc) / 8;
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0)
 TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0)
+
+static bool gen_ldst_c(DisasContext *s, TCGv_i64 addr, int zd, int png,
+                       MemOp esz, bool is_write, int n, bool strided)
+{
+    typedef void ldst_c_fn(TCGv_env, TCGv_ptr, TCGv_i64,
+                           TCGv_i32, TCGv_i32);
+    static ldst_c_fn * const f_ldst[2][2][4] = {
+        { { gen_helper_sve2p1_ld1bb_c,
+            gen_helper_sve2p1_ld1hh_le_c,
+            gen_helper_sve2p1_ld1ss_le_c,
+            gen_helper_sve2p1_ld1dd_le_c, },
+          { gen_helper_sve2p1_ld1bb_c,
+            gen_helper_sve2p1_ld1hh_be_c,
+            gen_helper_sve2p1_ld1ss_be_c,
+            gen_helper_sve2p1_ld1dd_be_c, } },
+
+        { { gen_helper_sve2p1_st1bb_c,
+            gen_helper_sve2p1_st1hh_le_c,
+            gen_helper_sve2p1_st1ss_le_c,
+            gen_helper_sve2p1_st1dd_le_c, },
+          { gen_helper_sve2p1_st1bb_c,
+            gen_helper_sve2p1_st1hh_be_c,
+            gen_helper_sve2p1_st1ss_be_c,
+            gen_helper_sve2p1_st1dd_be_c, } }
+    };
+
+    TCGv_i32 t_png, t_desc;
+    TCGv_ptr t_zd;
+    uint32_t desc, lg2_rstride = 0;
+    bool be = s->be_data == MO_BE;
+
+    assert(n == 2 || n == 4);
+    if (strided) {
+        lg2_rstride = 3;
+        if (n == 4) {
+            /* Validate ZD alignment. */
+            if (zd & 4) {
+                return false;
+            }
+            lg2_rstride = 2;
+        }
+        /* Ignore non-temporal bit */
+        zd &= ~8;
+    }
+
+    if (strided || !dc_isar_feature(aa64_sve2p1, s)
+        ? !sme_sm_enabled_check(s)
+        : !sve_access_check(s)) {
+        return true;
+    }
+
+    if (!s->mte_active[0]) {
+        addr = clean_data_tbi(s, addr);
+    }
+
+    desc = n == 2 ? 0 : 1;
+    desc = desc | (lg2_rstride << 1);
+    desc = make_svemte_desc(s, vec_full_reg_size(s), 1, esz, is_write, desc);
+    t_desc = tcg_constant_i32(desc);
+
+    t_png = tcg_temp_new_i32();
+    tcg_gen_ld16u_i32(t_png, tcg_env,
+                      pred_full_reg_offset(s, png) ^
+                      (HOST_BIG_ENDIAN ? 6 : 0));
+
+    t_zd = tcg_temp_new_ptr();
+    tcg_gen_addi_ptr(t_zd, tcg_env, vec_full_reg_offset(s, zd));
+
+    f_ldst[is_write][be][esz](tcg_env, t_zd, addr, t_png, t_desc);
+    return true;
+}
+
+static bool gen_ldst_zcrr_c(DisasContext *s, arg_zcrr_ldst *a,
+                            bool is_write, bool strided)
+{
+    TCGv_i64 addr = tcg_temp_new_i64();
+
+    tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz);
+    tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn));
+    return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write,
+                      a->nreg, strided);
+}
+
+static bool gen_ldst_zcri_c(DisasContext *s, arg_zcri_ldst *a,
+                            bool is_write, bool strided)
+{
+    TCGv_i64 addr = tcg_temp_new_i64();
+
+    tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn),
+                     a->imm * a->nreg * vec_full_reg_size(s));
+    return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write,
+                      a->nreg, strided);
+}
+
+TRANS_FEAT(LD1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, false, false)
+TRANS_FEAT(LD1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, false, false)
+TRANS_FEAT(ST1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, true, false)
+TRANS_FEAT(ST1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, true, false)
+
+TRANS_FEAT(LD1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, false, true)
+TRANS_FEAT(LD1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, false, true)
+TRANS_FEAT(ST1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, true, true)
+TRANS_FEAT(ST1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, true, true)
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

The msz > esz encodings are reserved, and some of
them are about to be reused.  Split these patterns
so that the new insns do not overlap.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-95-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@
 
 # Stores; user must fill in ESZ, MSZ, NREG as needed.
 @rprr_store         ....... ..    ..     rm:5 ... pg:3 rn:5 rd:5    &rprr_store
-@rpri_store_msz     ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5    &rpri_store
+@rpri_store         ....... ..    .. . imm:s4 ... pg:3 rn:5 rd:5    &rpri_store
 @rprr_store_esz_n0  ....... ..    esz:2  rm:5 ... pg:3 rn:5 rd:5 \
                     &rprr_store nreg=0
 @rprr_scatter_store ....... msz:2 ..     rm:5 ... pg:3 rn:5 rd:5 \
@@ -XXX,XX +XXX,XX @@ STR_zri         1110010 11 0.     ..... 010 ... ..... .....     @rd_rn_i9
 
 # SVE contiguous store (scalar plus immediate)
 # ST1B, ST1H, ST1W, ST1D; require msz <= esz
-ST_zpri         1110010 .. esz:2  0.... 111 ... ..... ..... \
-                @rpri_store_msz nreg=0
+ST_zpri         1110010 00 esz:2  0.... 111 ... ..... ..... \
+                @rpri_store msz=0 nreg=0
+ST_zpri         1110010 01 esz:2  0.... 111 ... ..... ..... \
+                @rpri_store msz=1 nreg=0
+ST_zpri         1110010 10 10     0.... 111 ... ..... ..... \
+                @rpri_store msz=2 esz=2 nreg=0
+ST_zpri         1110010 10 11     0.... 111 ... ..... ..... \
+                @rpri_store msz=2 esz=3 nreg=0
+ST_zpri         1110010 11 11     0.... 111 ... ..... ..... \
+                @rpri_store msz=3 esz=3 nreg=0
 
 # SVE contiguous store (scalar plus scalar)
 # ST1B, ST1H, ST1W, ST1D; require msz <= esz
@@ -XXX,XX +XXX,XX @@ ST_zprr         1110010 00 ..     ..... 010 ... ..... ..... \
                 @rprr_store_esz_n0 msz=0
 ST_zprr         1110010 01 ..     ..... 010 ... ..... ..... \
                 @rprr_store_esz_n0 msz=1
-ST_zprr         1110010 10 ..     ..... 010 ... ..... ..... \
-                @rprr_store_esz_n0 msz=2
+ST_zprr         1110010 10 10     ..... 010 ... ..... ..... \
+                @rprr_store msz=2 esz=2 nreg=0
+ST_zprr         1110010 10 11     ..... 010 ... ..... ..... \
+                @rprr_store msz=2 esz=3 nreg=0
 ST_zprr         1110010 11 11     ..... 010 ... ..... ..... \
                 @rprr_store msz=3 esz=3 nreg=0
 
 # SVE contiguous non-temporal store (scalar plus immediate)  (nreg == 0)
 # SVE store multiple structures (scalar plus immediate)      (nreg != 0)
 ST_zpri         1110010 .. nreg:2 1.... 111 ... ..... ..... \
-                @rpri_store_msz esz=%size_23
+                @rpri_store msz=%size_23 esz=%size_23
 
 # SVE contiguous non-temporal store (scalar plus scalar)     (nreg == 0)
 # SVE store multiple structures (scalar plus scalar)         (nreg != 0)
-ST_zprr         1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \
-                @rprr_store esz=%size_23
+ST_zprr         1110010 .. nreg:2 ..... 011 ... ..... ..... \
+                @rprr_store msz=%size_23 esz=%size_23
 
 # SVE 32-bit scatter store (scalar plus 32-bit scaled offsets)
 # Require msz > 0 && msz <= esz.
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-96-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h        |  22 +++++
 target/arm/tcg/sve_ldst_internal.h |  26 ++++++
 target/arm/tcg/sve.decode          |  20 +++++
 target/arm/tcg/sve_helper.c        |   6 ++
 target/arm/tcg/translate-sve.c     | 136 +++++++++++++++++++++++------
 5 files changed, 183 insertions(+), 27 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Move from sme_helper.c to the shared header.
Add a comment noting the lack of atomicity.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-97-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_ldst_internal.h | 63 ++++++++++++++++++++++++++++++
 target/arm/tcg/sme_helper.c        | 44 +++------------------
 2 files changed, 69 insertions(+), 38 deletions(-)

diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_ldst_internal.h
+++ b/target/arm/tcg/sve_ldst_internal.h
@@ -XXX,XX +XXX,XX @@ DO_LD_PRIM_3(ld1dqu_le, ld1dd_le)
 #define sve_st1dq_be_tlb   sve_st1dd_be_tlb
 #define sve_st1dq_le_tlb   sve_st1dd_le_tlb
 
+/*
+ * The ARMVectorReg elements are stored in host-endian 64-bit units.
+ * For 128-bit quantities, the sequence defined by the Elem[] pseudocode
+ * corresponds to storing the two 64-bit pieces in little-endian order.
+ */
+/* FIXME: Nothing in this file makes any effort at atomicity. */
+
+static inline void sve_ld1qq_be_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_ld1dd_be_host(vd, reg_off + 8, host);
+    sve_ld1dd_be_host(vd, reg_off, host + 8);
+}
+
+static inline void sve_ld1qq_le_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_ld1dd_le_host(vd, reg_off, host);
+    sve_ld1dd_le_host(vd, reg_off + 8, host + 8);
+}
+
+static inline void
+sve_ld1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_ld1dd_be_tlb(env, vd, reg_off + 8, addr, ra);
+    sve_ld1dd_be_tlb(env, vd, reg_off, addr + 8, ra);
+}
+
+static inline void
+sve_ld1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_ld1dd_le_tlb(env, vd, reg_off, addr, ra);
+    sve_ld1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra);
+}
+
+static inline void sve_st1qq_be_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_st1dd_be_host(vd, reg_off + 8, host);
+    sve_st1dd_be_host(vd, reg_off, host + 8);
+}
+
+static inline void sve_st1qq_le_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_st1dd_le_host(vd, reg_off, host);
+    sve_st1dd_le_host(vd, reg_off + 8, host + 8);
+}
+
+static inline void
+sve_st1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_st1dd_be_tlb(env, vd, reg_off + 8, addr, ra);
+    sve_st1dd_be_tlb(env, vd, reg_off, addr + 8, ra);
+}
+
+static inline void
+sve_st1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_st1dd_le_tlb(env, vd, reg_off, addr, ra);
+    sve_st1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra);
+}
+
 #undef DO_LD_TLB
 #undef DO_ST_TLB
 #undef DO_LD_HOST
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za,           \
     TLB(env, useronly_clean_ptr(addr), val, ra);                            \
 }
 
-/*
- * The ARMVectorReg elements are stored in host-endian 64-bit units.
- * For 128-bit quantities, the sequence defined by the Elem[] pseudocode
- * corresponds to storing the two 64-bit pieces in little-endian order.
- */
-#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB)                                 \
-static inline void HNAME##_host(void *za, intptr_t off, void *host)         \
-{                                                                           \
-    uint64_t val0 = HOST(host), val1 = HOST(host + 8);                      \
-    uint64_t *ptr = za + off;                                               \
-    ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1;                   \
-}                                                                           \
+#define DO_LDQ(HNAME, VNAME) \
 static inline void VNAME##_v_host(void *za, intptr_t off, void *host)       \
 {                                                                           \
     HNAME##_host(za, tile_vslice_offset(off), host);                        \
 }                                                                           \
-static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off,    \
-                               target_ulong addr, uintptr_t ra)             \
-{                                                                           \
-    uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra);                 \
-    uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra);             \
-    uint64_t *ptr = za + off;                                               \
-    ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1;                   \
-}                                                                           \
 static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off,  \
                                target_ulong addr, uintptr_t ra)             \
 {                                                                           \
     HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra);                \
 }
 
-#define DO_STQ(HNAME, VNAME, BE, HOST, TLB)                                 \
-static inline void HNAME##_host(void *za, intptr_t off, void *host)         \
-{                                                                           \
-    uint64_t *ptr = za + off;                                               \
-    HOST(host, ptr[BE]);                                                    \
-    HOST(host + 8, ptr[!BE]);                                               \
-}                                                                           \
+#define DO_STQ(HNAME, VNAME) \
 static inline void VNAME##_v_host(void *za, intptr_t off, void *host)       \
 {                                                                           \
     HNAME##_host(za, tile_vslice_offset(off), host);                        \
 }                                                                           \
-static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off,    \
-                               target_ulong addr, uintptr_t ra)             \
-{                                                                           \
-    uint64_t *ptr = za + off;                                               \
-    TLB(env, useronly_clean_ptr(addr), ptr[BE], ra);                        \
-    TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra);                   \
-}                                                                           \
 static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off,  \
                                target_ulong addr, uintptr_t ra)             \
 {                                                                           \
@@ -XXX,XX +XXX,XX @@ DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra)
 DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra)
 DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra)
 
-DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra)
-DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra)
+DO_LDQ(sve_ld1qq_be, sme_ld1q_be)
+DO_LDQ(sve_ld1qq_le, sme_ld1q_le)
 
 DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra)
 DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra)
@@ -XXX,XX +XXX,XX @@ DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra)
 DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra)
 DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra)
 
-DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra)
-DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra)
+DO_STQ(sve_st1qq_be, sme_st1q_be)
+DO_STQ(sve_st1qq_le, sme_st1q_le)
 
 #undef DO_LD
 #undef DO_ST
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-98-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  32 +++++++++
 target/arm/tcg/sve.decode      |  31 +++++++++
 target/arm/tcg/sve_helper.c    |   8 +++
 target/arm/tcg/translate-sve.c | 116 ++++++++++++++++++++++++---------
 4 files changed, 156 insertions(+), 31 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-99-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 16 ++++++++++++++++
 target/arm/tcg/sve.decode      |  8 ++++++++
 target/arm/tcg/sve_helper.c    |  6 ++++++
 target/arm/tcg/translate-sve.c | 34 ++++++++++++++++++++++++++++++++--
 4 files changed, 62 insertions(+), 2 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-100-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme.decode      | 36 ++++++++++++++++++++
 target/arm/tcg/sme_helper.c    | 60 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 46 +++++++++++++++++++-------
 4 files changed, 137 insertions(+), 11 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-101-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        | 24 ++++++++++
 target/arm/tcg/sme.decode      | 42 ++++++++++++++++
 target/arm/tcg/translate-sme.c | 56 ++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    | 88 ++++++++++++++++++++++++++++++++++
 4 files changed, 210 insertions(+)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_za         11000000 000011 110 .. 0000000000 00.   \
                 &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
 ZERO_za         11000000 000011 111 .. 0000000000 00.   \
                 &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
+
+### SME Lookup Table Read
+
+&lut            zd zn idx
+
+# LUTI2, consecutive
+LUTI2_c_1b      1100 0000 1100 11 idx:4    00 00 zn:5 zd:5      &lut
+LUTI2_c_1h      1100 0000 1100 11 idx:4    01 00 zn:5 zd:5      &lut
+LUTI2_c_1s      1100 0000 1100 11 idx:4    10 00 zn:5 zd:5      &lut
+
+LUTI2_c_2b      1100 0000 1000 11 idx:3  1 00 00 zn:5 .... 0    &lut zd=%zd_ax2
+LUTI2_c_2h      1100 0000 1000 11 idx:3  1 01 00 zn:5 .... 0    &lut zd=%zd_ax2
+LUTI2_c_2s      1100 0000 1000 11 idx:3  1 10 00 zn:5 .... 0    &lut zd=%zd_ax2
+
+LUTI2_c_4b      1100 0000 1000 11 idx:2 10 00 00 zn:5 ... 00    &lut zd=%zd_ax4
+LUTI2_c_4h      1100 0000 1000 11 idx:2 10 01 00 zn:5 ... 00    &lut zd=%zd_ax4
+LUTI2_c_4s      1100 0000 1000 11 idx:2 10 10 00 zn:5 ... 00    &lut zd=%zd_ax4
+
+# LUTI2, strided (must check zd alignment)
+LUTI2_s_2b      1100 0000 1001 11 idx:3  1 00 00 zn:5 zd:5      &lut
+LUTI2_s_2h      1100 0000 1001 11 idx:3  1 01 00 zn:5 zd:5      &lut
+
+LUTI2_s_4b      1100 0000 1001 11 idx:2 10 00 00 zn:5 zd:5      &lut
+LUTI2_s_4h      1100 0000 1001 11 idx:2 10 01 00 zn:5 zd:5      &lut
+
+# LUTI4, consecutive
+LUTI4_c_1b      1100 0000 1100 101 idx:3    00 00 zn:5 zd:5     &lut
+LUTI4_c_1h      1100 0000 1100 101 idx:3    01 00 zn:5 zd:5     &lut
+LUTI4_c_1s      1100 0000 1100 101 idx:3    10 00 zn:5 zd:5     &lut
+
+LUTI4_c_2b      1100 0000 1000 101 idx:2  1 00 00 zn:5 .... 0   &lut zd=%zd_ax2
+LUTI4_c_2h      1100 0000 1000 101 idx:2  1 01 00 zn:5 .... 0   &lut zd=%zd_ax2
+LUTI4_c_2s      1100 0000 1000 101 idx:2  1 10 00 zn:5 .... 0   &lut zd=%zd_ax2
+
+LUTI4_c_4h      1100 0000 1000 101 idx:1 10 01 00 zn:5 ... 00   &lut zd=%zd_ax4
+LUTI4_c_4s      1100 0000 1000 101 idx:1 10 10 00 zn:5 ... 00   &lut zd=%zd_ax4
+
+# LUTI4, strided (must check zd alignment)
+LUTI4_s_2b      1100 0000 1001 101 idx:2  1 00 00 zn:5 zd:5     &lut
+LUTI4_s_2h      1100 0000 1001 101 idx:2  1 01 00 zn:5 zd:5     &lut
+
+LUTI4_s_4h      1100 0000 1001 101 idx:1 10 01 00 zn:5 zd:5     &lut
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_SEL(DisasContext *s, arg_SEL *a)
     }
     return true;
 }
+
+static bool do_lut(DisasContext *s, arg_lut *a,
+                   gen_helper_gvec_2_ptr *fn, bool strided)
+{
+    if (sme_sm_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd),
+                           vec_full_reg_offset(s, a->zn),
+                           tcg_env, svl, svl, strided | (a->idx << 1), fn);
+    }
+    return true;
+}
+
+TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, false)
+TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, false)
+TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, false)
+
+TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, false)
+TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, false)
+TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, false)
+
+TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, false)
+TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, false)
+TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, false)
+
+TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, false)
+TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, false)
+TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, false)
+
+TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, false)
+TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, false)
+TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, false)
+
+TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, false)
+TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, false)
+
+static bool do_lut_s4(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+    return !(a->zd & 0b01100) && do_lut(s, a, fn, true);
+}
+
+static bool do_lut_s8(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+    return !(a->zd & 0b01000) && do_lut(s, a, fn, true);
+}
+
+TRANS_FEAT(LUTI2_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2b)
+TRANS_FEAT(LUTI2_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2h)
+
+TRANS_FEAT(LUTI2_s_4b, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4b)
+TRANS_FEAT(LUTI2_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4h)
+
+TRANS_FEAT(LUTI4_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2b)
+TRANS_FEAT(LUTI4_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2h)
+
+TRANS_FEAT(LUTI4_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti4_4h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+static inline void do_lut_b(void *zd, uint64_t *indexes, uint64_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint8_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H1(e)] = extractn(table, index * tsize, 8);
+        }
+    }
+}
+
+static inline void do_lut_h(void *zd, uint64_t *indexes, uint64_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint16_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H2(e)] = extractn(table, index * tsize, 16);
+        }
+    }
+}
+
+static inline void do_lut_s(void *zd, uint64_t *indexes, uint32_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint32_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H4(e)] = table[H4(index)];
+        }
+    }
+}
+
+#define DO_SME2_LUT(ISIZE, NREG, SUFF, ESIZE) \
+void helper_sme2_luti##ISIZE##_##NREG##SUFF                             \
+    (void *zd, void *zn, CPUARMState *env, uint32_t desc)               \
+{                                                                       \
+    unsigned vl = simd_oprsz(desc);                                     \
+    unsigned strided = extract32(desc, SIMD_DATA_SHIFT, 1);             \
+    unsigned idx = extract32(desc, SIMD_DATA_SHIFT + 1, 4);             \
+    unsigned elements = vl / ESIZE;                                     \
+    unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8);              \
+    unsigned segments = (ESIZE * 8) / (ISIZE * NREG);                   \
+    unsigned segment = idx & (segments - 1);                            \
+    ARMVectorReg indexes;                                               \
+    memcpy(&indexes, zn, vl);                                           \
+    do_lut_##SUFF(zd, indexes.d, (void *)env->za_state.zt0, elements,   \
+                  segment * NREG * elements,                            \
+                  dstride * sizeof(ARMVectorReg), ISIZE, 32, NREG);     \
+}
+
+DO_SME2_LUT(2,1,b, 1)
+DO_SME2_LUT(2,1,h, 2)
+DO_SME2_LUT(2,1,s, 4)
+DO_SME2_LUT(2,2,b, 1)
+DO_SME2_LUT(2,2,h, 2)
+DO_SME2_LUT(2,2,s, 4)
+DO_SME2_LUT(2,4,b, 1)
+DO_SME2_LUT(2,4,h, 2)
+DO_SME2_LUT(2,4,s, 4)
+
+DO_SME2_LUT(4,1,b, 1)
+DO_SME2_LUT(4,1,h, 2)
+DO_SME2_LUT(4,1,s, 4)
+DO_SME2_LUT(4,2,b, 1)
+DO_SME2_LUT(4,2,h, 2)
+DO_SME2_LUT(4,2,s, 4)
+DO_SME2_LUT(4,4,b, 1)
+DO_SME2_LUT(4,4,h, 2)
+DO_SME2_LUT(4,4,s, 4)
+
+#undef DO_SME2_LUT
-- 
2.43.0

The pattern we currently have as FMOPA_h is the "widening" insn
that takes fp16 inputs and produces single-precision outputs.
This is unlike FMOPA_s and FMOPA_d, which are non-widening
produce outputs the same size as their inputs.

SME2 introduces a non-widening fp16 FMOPA operation; rename
FMOPA_h to FMOPA_w_h (for 'widening'), so we can use FMOPA_h
for the non-widening version, giving it a name in line with
the other non-widening ops FMOPA_s and FMOPA_d.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-102-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 2 +-
 target/arm/tcg/sme.decode      | 2 +-
 target/arm/tcg/sme_helper.c    | 4 ++--
 target/arm/tcg/translate-sme.c | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

Our current BFMOPA opcode pattern is the widening version
of the insn. Rename it to BFMOPA_w, to make way for
the non-widening version added in SME2.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-103-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 2 +-
 target/arm/tcg/sme.decode      | 2 +-
 target/arm/tcg/sme_helper.c    | 4 ++--
 target/arm/tcg/translate-sme.c | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

For non-widening, we can use float_muladd_negate_product,
For widening, which uses dot-product, we need to handle
the negation explicitly.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-104-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  19 +++++
 target/arm/tcg/vec_internal.h  |   5 ++
 target/arm/tcg/sme_helper.c    | 141 +++++++++++++++++++++++++++------
 target/arm/tcg/translate-sme.c |  27 ++++---
 4 files changed, 160 insertions(+), 32 deletions(-)

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-105-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 51 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  4 +++
 4 files changed, 63 insertions(+)

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-106-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 51 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  5 ++++
 4 files changed, 64 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-107-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/system/arm/emulation.rst |  6 ++++++
 target/arm/tcg/cpu64.c        | 10 ++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -XXX,XX +XXX,XX @@ the following architecture extensions:
 - FEAT_SM3 (Advanced SIMD SM3 instructions)
 - FEAT_SM4 (Advanced SIMD SM4 instructions)
 - FEAT_SME (Scalable Matrix Extension)
+- FEAT_SME2 (Scalable Matrix Extension version 2)
+- FEAT_SME2p1 (Scalable Matrix Extension version 2.1)
+- FEAT_SME_B16B16 (Non-widening BFloat16 arithmetic for SME2)
 - FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode)
+- FEAT_SME_F16F16 (Non-widening half-precision FP16 arithmetic for SME2)
 - FEAT_SME_F64F64 (Double-precision floating-point outer product instructions)
 - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions)
 - FEAT_SVE (Scalable Vector Extension)
 - FEAT_SVE_AES (Scalable Vector AES instructions)
+- FEAT_SVE_B16B16 (Non-widening BFloat16 arithmetic for SVE2)
 - FEAT_SVE_BitPerm (Scalable Vector Bit Permutes instructions)
 - FEAT_SVE_PMULL128 (Scalable Vector PMULL instructions)
 - FEAT_SVE_SHA3 (Scalable Vector SHA3 instructions)
 - FEAT_SVE_SM4 (Scalable Vector SM4 instructions)
 - FEAT_SVE2 (Scalable Vector Extension version 2)
+- FEAT_SVE2p1 (Scalable Vector Extension version 2.1)
 - FEAT_SPECRES (Speculation restriction instructions)
 - FEAT_SSBS (Speculative Store Bypass Safe)
 - FEAT_SSBS2 (MRS and MSR instructions for SSBS version 2)
diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj)
      */
     t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3);       /* FEAT_MTE3 */
     t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0);  /* FEAT_RASv1p1 + FEAT_DoubleFault */
-    t = FIELD_DP64(t, ID_AA64PFR1, SME, 1);       /* FEAT_SME */
+    t = FIELD_DP64(t, ID_AA64PFR1, SME, 2);       /* FEAT_SME2 */
     t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_3 */
     t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1);       /* FEAT_NMI */
     SET_IDREG(isar, ID_AA64PFR1, t);
@@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj)
     FIELD_DP64_IDREG(isar, ID_AA64MMFR3, SPEC_FPACC, 1); /* FEAT_FPACC_SPEC */
 
     t = GET_IDREG(isar, ID_AA64ZFR0);
-    t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1);
+    t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 2);    /* FEAT_SVE2p1 */
     t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2);       /* FEAT_SVE_PMULL128 */
     t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1);   /* FEAT_SVE_BitPerm */
     t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 2);  /* FEAT_BF16, FEAT_EBF16 */
+    t = FIELD_DP64(t, ID_AA64ZFR0, B16B16, 1);    /* FEAT_SVE_B16B16 */
     t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1);      /* FEAT_SVE_SHA3 */
     t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1);       /* FEAT_SVE_SM4 */
     t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1);      /* FEAT_I8MM */
@@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj)
 
     t = GET_IDREG(isar, ID_AA64SMFR0);
     t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1);   /* FEAT_SME */
+    t = FIELD_DP64(t, ID_AA64SMFR0, BI32I32, 1);  /* FEAT_SME2 */
     t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1);   /* FEAT_SME */
     t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1);   /* FEAT_SME */
     t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf);  /* FEAT_SME */
+    t = FIELD_DP64(t, ID_AA64SMFR0, F16F16, 1);   /* FEAT_SME_F16F16 */
+    t = FIELD_DP64(t, ID_AA64SMFR0, B16B16, 1);   /* FEAT_SME_B16B16 */
+    t = FIELD_DP64(t, ID_AA64SMFR0, I16I32, 5);   /* FEAT_SME2 */
     t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1);   /* FEAT_SME_F64F64 */
     t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */
+    t = FIELD_DP64(t, ID_AA64SMFR0, SMEVER, 2);   /* FEAT_SME2p1 */
     t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1);     /* FEAT_SME_FA64 */
     SET_IDREG(isar, ID_AA64SMFR0, t);
 
-- 
2.43.0

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-108-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 linux-user/elfload.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -XXX,XX +XXX,XX @@ uint64_t get_elf_hwcap2(void)
     GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64);
     GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC);
     GET_FEATURE_ID(aa64_mops, ARM_HWCAP2_A64_MOPS);
+    GET_FEATURE_ID(aa64_sve2p1, ARM_HWCAP2_A64_SVE2P1);
+    GET_FEATURE_ID(aa64_sme2, (ARM_HWCAP2_A64_SME2 |
+                               ARM_HWCAP2_A64_SME_I16I32 |
+                               ARM_HWCAP2_A64_SME_BI32I32));
+    GET_FEATURE_ID(aa64_sme2p1, ARM_HWCAP2_A64_SME2P1);
+    GET_FEATURE_ID(aa64_sme_b16b16, ARM_HWCAP2_A64_SME_B16B16);
+    GET_FEATURE_ID(aa64_sme_f16f16, ARM_HWCAP2_A64_SME_F16F16);
+    GET_FEATURE_ID(aa64_sve_b16b16, ARM_HWCAP2_A64_SVE_B16B16);
 
     return hwcaps;
 }
-- 
2.43.0