hw/arm/virt: Allow user-creatable SMMUv3 dev instantiation

Allow cold-plugging of an SMMUv3 device on the virt machine when no
global (legacy) SMMUv3 is present or when a virtio-iommu is specified.

This user-created SMMUv3 device is tied to a specific PCI bus provided
by the user, so ensure the IOMMU ops are configured accordingly.

Due to current limitations in QEMU’s device tree support, specifically
its inability to properly present pxb-pcie based root complexes and
their devices, the device tree support for the new SMMUv3 device is
limited to cases where it is attached to the default pcie.0 root complex.

Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nathan Chen <nathanc@nvidia.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Message-id: 20250829082543.7680-8-skolothumtho@nvidia.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

hw/arm/smmu-common.c

@@ -961,7 +961,12 @@ static void smmu_base_realize(DeviceState *dev, Error **errp)
                 goto out_err;
             }
         }
-        pci_setup_iommu(pci_bus, &smmu_ops, s);
+
+        if (s->smmu_per_bus) {
+            pci_setup_iommu_per_bus(pci_bus, &smmu_ops, s);
+        } else {
+            pci_setup_iommu(pci_bus, &smmu_ops, s);
+        }
         return;
     }
 out_err:
@@ -986,6 +991,7 @@ static void smmu_base_reset_exit(Object *obj, ResetType type)
 
 static const Property smmu_dev_properties[] = {
     DEFINE_PROP_UINT8("bus_num", SMMUState, bus_num, 0),
+    DEFINE_PROP_BOOL("smmu_per_bus", SMMUState, smmu_per_bus, false),
     DEFINE_PROP_LINK("primary-bus", SMMUState, primary_bus,
                      TYPE_PCI_BUS, PCIBus *),
 };

hw/arm/smmuv3.c

@@ -1996,6 +1996,8 @@ static void smmuv3_class_init(ObjectClass *klass, const void *data)
     device_class_set_parent_realize(dc, smmu_realize,
                                     &c->parent_realize);
     device_class_set_props(dc, smmuv3_properties);
+    dc->hotpluggable = false;
+    dc->user_creatable = true;
 }
 
 static int smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,

hw/arm/virt.c

@@ -57,6 +57,7 @@
 #include "qemu/cutils.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
+#include "hw/pci/pci_bus.h"
 #include "hw/pci-host/gpex.h"
 #include "hw/pci-bridge/pci_expander_bridge.h"
 #include "hw/virtio/virtio-pci.h"
@@ -1475,6 +1476,29 @@ static void create_smmuv3_dt_bindings(const VirtMachineState *vms, hwaddr base,
     g_free(node);
 }
 
+static void create_smmuv3_dev_dtb(VirtMachineState *vms,
+                                  DeviceState *dev, PCIBus *bus)
+{
+    PlatformBusDevice *pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev);
+    SysBusDevice *sbdev = SYS_BUS_DEVICE(dev);
+    int irq = platform_bus_get_irqn(pbus, sbdev, 0);
+    hwaddr base = platform_bus_get_mmio_addr(pbus, sbdev, 0);
+    MachineState *ms = MACHINE(vms);
+
+    if (!(vms->bootinfo.firmware_loaded && virt_is_acpi_enabled(vms)) &&
+        strcmp("pcie.0", bus->qbus.name)) {
+        warn_report("SMMUv3 device only supported with pcie.0 for DT");
+        return;
+    }
+    base += vms->memmap[VIRT_PLATFORM_BUS].base;
+    irq += vms->irqmap[VIRT_PLATFORM_BUS];
+
+    vms->iommu_phandle = qemu_fdt_alloc_phandle(ms->fdt);
+    create_smmuv3_dt_bindings(vms, base, SMMU_IO_LEN, irq);
+    qemu_fdt_setprop_cells(ms->fdt, vms->pciehb_nodename, "iommu-map",
+                           0x0, vms->iommu_phandle, 0x0, 0x10000);
+}
+
 static void create_smmu(const VirtMachineState *vms,
                         PCIBus *bus)
 {
@@ -3006,6 +3030,16 @@ static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
         qlist_append_str(reserved_regions, resv_prop_str);
         qdev_prop_set_array(dev, "reserved-regions", reserved_regions);
         g_free(resv_prop_str);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_ARM_SMMUV3)) {
+        if (vms->legacy_smmuv3_present || vms->iommu == VIRT_IOMMU_VIRTIO) {
+            error_setg(errp, "virt machine already has %s set. "
+                       "Doesn't support incompatible iommus",
+                       (vms->legacy_smmuv3_present) ?
+                       "iommu=smmuv3" : "virtio-iommu");
+        } else if (vms->iommu == VIRT_IOMMU_NONE) {
+            /* The new SMMUv3 device is specific to the PCI bus */
+            object_property_set_bool(OBJECT(dev), "smmu_per_bus", true, NULL);
+        }
     }
 }
 
@@ -3029,6 +3063,22 @@ static void virt_machine_device_plug_cb(HotplugHandler *hotplug_dev,
         virtio_md_pci_plug(VIRTIO_MD_PCI(dev), MACHINE(hotplug_dev), errp);
     }
 
+    if (object_dynamic_cast(OBJECT(dev), TYPE_ARM_SMMUV3)) {
+        if (!vms->legacy_smmuv3_present && vms->platform_bus_dev) {
+            PCIBus *bus;
+
+            bus = PCI_BUS(object_property_get_link(OBJECT(dev), "primary-bus",
+                                                   &error_abort));
+            if (pci_bus_bypass_iommu(bus)) {
+                error_setg(errp, "Bypass option cannot be set for SMMUv3 "
+                           "associated PCIe RC");
+                return;
+            }
+
+            create_smmuv3_dev_dtb(vms, dev, bus);
+        }
+    }
+
     if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
         PCIDevice *pdev = PCI_DEVICE(dev);
 
@@ -3231,6 +3281,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data)
     machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE);
     machine_class_allow_dynamic_sysbus_dev(mc, TYPE_VFIO_PLATFORM);
     machine_class_allow_dynamic_sysbus_dev(mc, TYPE_UEFI_VARS_SYSBUS);
+    machine_class_allow_dynamic_sysbus_dev(mc, TYPE_ARM_SMMUV3);
 #ifdef CONFIG_TPM
     machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS);
 #endif

hw/core/sysbus-fdt.c

@@ -31,6 +31,7 @@
 #include "qemu/error-report.h"
 #include "system/device_tree.h"
 #include "system/tpm.h"
+#include "hw/arm/smmuv3.h"
 #include "hw/platform-bus.h"
 #include "hw/vfio/vfio-platform.h"
 #include "hw/vfio/vfio-calxeda-xgmac.h"
@@ -518,6 +519,8 @@ static const BindingEntry bindings[] = {
 #ifdef CONFIG_TPM
     TYPE_BINDING(TYPE_TPM_TIS_SYSBUS, add_tpm_tis_fdt_node),
 #endif
+    /* No generic DT support for smmuv3 dev. Support added for arm virt only */
+    TYPE_BINDING(TYPE_ARM_SMMUV3, no_fdt_node),
     TYPE_BINDING(TYPE_RAMFB_DEVICE, no_fdt_node),
     TYPE_BINDING(TYPE_UEFI_VARS_SYSBUS, add_uefi_vars_node),
     TYPE_BINDING("", NULL), /* last element */

include/hw/arm/smmu-common.h

@@ -161,6 +161,7 @@ struct SMMUState {
     QLIST_HEAD(, SMMUDevice) devices_with_notifiers;
     uint8_t bus_num;
     PCIBus *primary_bus;
+    bool smmu_per_bus; /* SMMU is specific to the primary_bus */
 };
 
 struct SMMUBaseClass {