vfio-user: add vfio-user class and container

Introduce basic plumbing for vfio-user with CONFIG_VFIO_USER.

We introduce VFIOUserContainer in hw/vfio-user/container.c, which is a
container type for the "IOMMU" type "vfio-iommu-user", and share some
common container code from hw/vfio/container.c.

Add hw/vfio-user/pci.c for instantiating VFIOUserPCIDevice objects,
sharing some common code from hw/vfio/pci.c.

Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250625193012.2316242-2-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

1 files changed, 185 insertions, 0 deletions

diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
new file mode 100644
index 0000000000..86d7055747
--- /dev/null
+++ b/hw/vfio-user/pci.c
@@ -0,0 +1,185 @@
+/*
+ * vfio PCI device over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include <sys/ioctl.h>
+#include "qemu/osdep.h"
+#include "qapi-visit-sockets.h"
+
+#include "hw/qdev-properties.h"
+#include "hw/vfio/pci.h"
+
+#define TYPE_VFIO_USER_PCI "vfio-user-pci"
+OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)
+
+struct VFIOUserPCIDevice {
+    VFIOPCIDevice device;
+    SocketAddress *socket;
+};
+
+/*
+ * Emulated devices don't use host hot reset
+ */
+static void vfio_user_compute_needs_reset(VFIODevice *vbasedev)
+{
+    vbasedev->needs_reset = false;
+}
+
+static Object *vfio_user_pci_get_object(VFIODevice *vbasedev)
+{
+    VFIOUserPCIDevice *vdev = container_of(vbasedev, VFIOUserPCIDevice,
+                                           device.vbasedev);
+
+    return OBJECT(vdev);
+}
+
+static VFIODeviceOps vfio_user_pci_ops = {
+    .vfio_compute_needs_reset = vfio_user_compute_needs_reset,
+    .vfio_eoi = vfio_pci_intx_eoi,
+    .vfio_get_object = vfio_user_pci_get_object,
+    /* No live migration support yet. */
+    .vfio_save_config = NULL,
+    .vfio_load_config = NULL,
+};
+
+static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
+{
+    ERRP_GUARD();
+    VFIOUserPCIDevice *udev = VFIO_USER_PCI(pdev);
+    VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
+    VFIODevice *vbasedev = &vdev->vbasedev;
+    const char *sock_name;
+    AddressSpace *as;
+
+    if (!udev->socket) {
+        error_setg(errp, "No socket specified");
+        error_append_hint(errp, "e.g. -device '{"
+            "\"driver\":\"vfio-user-pci\", "
+            "\"socket\": {\"path\": \"/tmp/vfio-user.sock\", "
+            "\"type\": \"unix\"}'"
+            "}'\n");
+        return;
+    }
+
+    sock_name = udev->socket->u.q_unix.path;
+
+    vbasedev->name = g_strdup_printf("vfio-user:%s", sock_name);
+
+    /*
+     * vfio-user devices are effectively mdevs (don't use a host iommu).
+     */
+    vbasedev->mdev = true;
+
+    as = pci_device_iommu_address_space(pdev);
+    if (!vfio_device_attach_by_iommu_type(TYPE_VFIO_IOMMU_USER,
+                                          vbasedev->name, vbasedev,
+                                          as, errp)) {
+        error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name);
+        return;
+    }
+}
+
+static void vfio_user_instance_init(Object *obj)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(obj);
+    VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+    VFIODevice *vbasedev = &vdev->vbasedev;
+
+    device_add_bootindex_property(obj, &vdev->bootindex,
+                                  "bootindex", NULL,
+                                  &pci_dev->qdev);
+    vdev->host.domain = ~0U;
+    vdev->host.bus = ~0U;
+    vdev->host.slot = ~0U;
+    vdev->host.function = ~0U;
+
+    vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_user_pci_ops,
+                     DEVICE(vdev), false);
+
+    vdev->nv_gpudirect_clique = 0xFF;
+
+    /*
+     * QEMU_PCI_CAP_EXPRESS initialization does not depend on QEMU command
+     * line, therefore, no need to wait to realize like other devices.
+     */
+    pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
+}
+
+static void vfio_user_instance_finalize(Object *obj)
+{
+    VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+
+    vfio_pci_put_device(vdev);
+}
+
+static const Property vfio_user_pci_dev_properties[] = {
+    DEFINE_PROP_UINT32("x-pci-vendor-id", VFIOPCIDevice,
+                       vendor_id, PCI_ANY_ID),
+    DEFINE_PROP_UINT32("x-pci-device-id", VFIOPCIDevice,
+                       device_id, PCI_ANY_ID),
+    DEFINE_PROP_UINT32("x-pci-sub-vendor-id", VFIOPCIDevice,
+                       sub_vendor_id, PCI_ANY_ID),
+    DEFINE_PROP_UINT32("x-pci-sub-device-id", VFIOPCIDevice,
+                       sub_device_id, PCI_ANY_ID),
+};
+
+static void vfio_user_pci_set_socket(Object *obj, Visitor *v, const char *name,
+                                     void *opaque, Error **errp)
+{
+    VFIOUserPCIDevice *udev = VFIO_USER_PCI(obj);
+    bool success;
+
+    qapi_free_SocketAddress(udev->socket);
+
+    udev->socket = NULL;
+
+    success = visit_type_SocketAddress(v, name, &udev->socket, errp);
+
+    if (!success) {
+        return;
+    }
+
+    if (udev->socket->type != SOCKET_ADDRESS_TYPE_UNIX) {
+        error_setg(errp, "Unsupported socket type %s",
+                   SocketAddressType_str(udev->socket->type));
+        qapi_free_SocketAddress(udev->socket);
+        udev->socket = NULL;
+        return;
+    }
+}
+
+static void vfio_user_pci_dev_class_init(ObjectClass *klass, const void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *pdc = PCI_DEVICE_CLASS(klass);
+
+    device_class_set_props(dc, vfio_user_pci_dev_properties);
+
+    object_class_property_add(klass, "socket", "SocketAddress", NULL,
+                              vfio_user_pci_set_socket, NULL, NULL);
+    object_class_property_set_description(klass, "socket",
+                                          "SocketAddress (UNIX sockets only)");
+
+    dc->desc = "VFIO over socket PCI device assignment";
+    pdc->realize = vfio_user_pci_realize;
+}
+
+static const TypeInfo vfio_user_pci_dev_info = {
+    .name = TYPE_VFIO_USER_PCI,
+    .parent = TYPE_VFIO_PCI_BASE,
+    .instance_size = sizeof(VFIOUserPCIDevice),
+    .class_init = vfio_user_pci_dev_class_init,
+    .instance_init = vfio_user_instance_init,
+    .instance_finalize = vfio_user_instance_finalize,
+};
+
+static void register_vfio_user_dev_type(void)
+{
+    type_register_static(&vfio_user_pci_dev_info);
+}
+
+ type_init(register_vfio_user_dev_type)