qemu/hw/virtio/vhost-vsock.c

240 lines
6.7 KiB
C
Raw Normal View History

/*
* Virtio vsock device
*
* Copyright 2015 Red Hat, Inc.
*
* Authors:
* Stefan Hajnoczi <stefanha@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* (at your option) any later version. See the COPYING file in the
* top-level directory.
*/
#include "qemu/osdep.h"
#include "standard-headers/linux/virtio_vsock.h"
#include "qapi/error.h"
#include "hw/virtio/virtio-access.h"
#include "qemu/error-report.h"
#include "qemu/sockets.h"
#include "hw/qdev-properties.h"
#include "hw/virtio/vhost-vsock.h"
#include "monitor/monitor.h"
static void vhost_vsock_get_config(VirtIODevice *vdev, uint8_t *config)
{
VHostVSock *vsock = VHOST_VSOCK(vdev);
struct virtio_vsock_config vsockcfg = {};
virtio_stq_p(vdev, &vsockcfg.guest_cid, vsock->conf.guest_cid);
memcpy(config, &vsockcfg, sizeof(vsockcfg));
}
static int vhost_vsock_set_guest_cid(VirtIODevice *vdev)
{
VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev);
VHostVSock *vsock = VHOST_VSOCK(vdev);
const VhostOps *vhost_ops = vvc->vhost_dev.vhost_ops;
int ret;
if (!vhost_ops->vhost_vsock_set_guest_cid) {
return -ENOSYS;
}
ret = vhost_ops->vhost_vsock_set_guest_cid(&vvc->vhost_dev,
vsock->conf.guest_cid);
if (ret < 0) {
return -errno;
}
return 0;
}
static int vhost_vsock_set_running(VirtIODevice *vdev, int start)
{
VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev);
const VhostOps *vhost_ops = vvc->vhost_dev.vhost_ops;
int ret;
if (!vhost_ops->vhost_vsock_set_running) {
return -ENOSYS;
}
ret = vhost_ops->vhost_vsock_set_running(&vvc->vhost_dev, start);
if (ret < 0) {
return -errno;
}
return 0;
}
static void vhost_vsock_set_status(VirtIODevice *vdev, uint8_t status)
{
VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev);
bool should_start = virtio_device_should_start(vdev, status);
int ret;
if (vhost_dev_is_started(&vvc->vhost_dev) == should_start) {
return;
}
if (should_start) {
ret = vhost_vsock_common_start(vdev);
if (ret < 0) {
return;
}
ret = vhost_vsock_set_running(vdev, 1);
if (ret < 0) {
vhost_vsock_common_stop(vdev);
error_report("Error starting vhost vsock: %d", -ret);
return;
}
} else {
ret = vhost_vsock_set_running(vdev, 0);
if (ret < 0) {
error_report("vhost vsock set running failed: %d", ret);
return;
}
vhost_vsock_common_stop(vdev);
}
}
static uint64_t vhost_vsock_get_features(VirtIODevice *vdev,
uint64_t requested_features,
Error **errp)
{
return vhost_vsock_common_get_features(vdev, requested_features, errp);
}
static const VMStateDescription vmstate_virtio_vhost_vsock = {
.name = "virtio-vhost_vsock",
.minimum_version_id = VHOST_VSOCK_SAVEVM_VERSION,
.version_id = VHOST_VSOCK_SAVEVM_VERSION,
.fields = (VMStateField[]) {
VMSTATE_VIRTIO_DEVICE,
VMSTATE_END_OF_LIST()
},
.pre_save = vhost_vsock_common_pre_save,
.post_load = vhost_vsock_common_post_load,
};
static void vhost_vsock_device_realize(DeviceState *dev, Error **errp)
{
VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(dev);
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VHostVSock *vsock = VHOST_VSOCK(dev);
int vhostfd;
int ret;
/* Refuse to use reserved CID numbers */
if (vsock->conf.guest_cid <= 2) {
error_setg(errp, "guest-cid property must be greater than 2");
return;
}
if (vsock->conf.guest_cid > UINT32_MAX) {
error_setg(errp, "guest-cid property must be a 32-bit number");
return;
}
if (vsock->conf.vhostfd) {
vhostfd = monitor_fd_param(monitor_cur(), vsock->conf.vhostfd, errp);
if (vhostfd == -1) {
error_prepend(errp, "vhost-vsock: unable to parse vhostfd: ");
return;
}
if (!g_unix_set_fd_nonblocking(vhostfd, true, NULL)) {
error_setg_errno(errp, errno,
"vhost-vsock: unable to set non-blocking mode");
return;
}
} else {
vhostfd = open("/dev/vhost-vsock", O_RDWR);
if (vhostfd < 0) {
error_setg_errno(errp, errno,
"vhost-vsock: failed to open vhost device");
return;
}
if (!g_unix_set_fd_nonblocking(vhostfd, true, NULL)) {
error_setg_errno(errp, errno,
"Failed to set FD nonblocking");
return;
}
}
vhost_vsock_common_realize(vdev);
ret = vhost_dev_init(&vvc->vhost_dev, (void *)(uintptr_t)vhostfd,
VHOST_BACKEND_TYPE_KERNEL, 0, errp);
if (ret < 0) {
/*
* vhostfd is closed by vhost_dev_cleanup, which is called
* by vhost_dev_init on initialization error.
*/
goto err_virtio;
}
ret = vhost_vsock_set_guest_cid(vdev);
if (ret < 0) {
error_setg_errno(errp, -ret, "vhost-vsock: unable to set guest cid");
goto err_vhost_dev;
}
return;
err_vhost_dev:
/* vhost_dev_cleanup() closes the vhostfd passed to vhost_dev_init() */
vhost_dev_cleanup(&vvc->vhost_dev);
err_virtio:
vhost_vsock_common_unrealize(vdev);
}
qdev: Unrealize must not fail Devices may have component devices and buses. Device realization may fail. Realization is recursive: a device's realize() method realizes its components, and device_set_realized() realizes its buses (which should in turn realize the devices on that bus, except bus_set_realized() doesn't implement that, yet). When realization of a component or bus fails, we need to roll back: unrealize everything we realized so far. If any of these unrealizes failed, the device would be left in an inconsistent state. Must not happen. device_set_realized() lets it happen: it ignores errors in the roll back code starting at label child_realize_fail. Since realization is recursive, unrealization must be recursive, too. But how could a partly failed unrealize be rolled back? We'd have to re-realize, which can fail. This design is fundamentally broken. device_set_realized() does not roll back at all. Instead, it keeps unrealizing, ignoring further errors. It can screw up even for a device with no buses: if the lone dc->unrealize() fails, it still unregisters vmstate, and calls listeners' unrealize() callback. bus_set_realized() does not roll back either. Instead, it stops unrealizing. Fortunately, no unrealize method can fail, as we'll see below. To fix the design error, drop parameter @errp from all the unrealize methods. Any unrealize method that uses @errp now needs an update. This leads us to unrealize() methods that can fail. Merely passing it to another unrealize method cannot cause failure, though. Here are the ones that do other things with @errp: * virtio_serial_device_unrealize() Fails when qbus_set_hotplug_handler() fails, but still does all the other work. On failure, the device would stay realized with its resources completely gone. Oops. Can't happen, because qbus_set_hotplug_handler() can't actually fail here. Pass &error_abort to qbus_set_hotplug_handler() instead. * hw/ppc/spapr_drc.c's unrealize() Fails when object_property_del() fails, but all the other work is already done. On failure, the device would stay realized with its vmstate registration gone. Oops. Can't happen, because object_property_del() can't actually fail here. Pass &error_abort to object_property_del() instead. * spapr_phb_unrealize() Fails and bails out when remove_drcs() fails, but other work is already done. On failure, the device would stay realized with some of its resources gone. Oops. remove_drcs() fails only when chassis_from_bus()'s object_property_get_uint() fails, and it can't here. Pass &error_abort to remove_drcs() instead. Therefore, no unrealize method can fail before this patch. device_set_realized()'s recursive unrealization via bus uses object_property_set_bool(). Can't drop @errp there, so pass &error_abort. We similarly unrealize with object_property_set_bool() elsewhere, always ignoring errors. Pass &error_abort instead. Several unrealize methods no longer handle errors from other unrealize methods: virtio_9p_device_unrealize(), virtio_input_device_unrealize(), scsi_qdev_unrealize(), ... Much of the deleted error handling looks wrong anyway. One unrealize methods no longer ignore such errors: usb_ehci_pci_exit(). Several realize methods no longer ignore errors when rolling back: v9fs_device_realize_common(), pci_qdev_unrealize(), spapr_phb_realize(), usb_qdev_realize(), vfio_ccw_realize(), virtio_device_realize(). Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200505152926.18877-17-armbru@redhat.com>
2020-05-05 18:29:24 +03:00
static void vhost_vsock_device_unrealize(DeviceState *dev)
{
VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(dev);
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
/* This will stop vhost backend if appropriate. */
vhost_vsock_set_status(vdev, 0);
vhost_dev_cleanup(&vvc->vhost_dev);
vhost_vsock_common_unrealize(vdev);
}
static Property vhost_vsock_properties[] = {
DEFINE_PROP_UINT64("guest-cid", VHostVSock, conf.guest_cid, 0),
DEFINE_PROP_STRING("vhostfd", VHostVSock, conf.vhostfd),
DEFINE_PROP_END_OF_LIST(),
};
static void vhost_vsock_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
device_class_set_props(dc, vhost_vsock_properties);
dc->vmsd = &vmstate_virtio_vhost_vsock;
vdc->realize = vhost_vsock_device_realize;
vdc->unrealize = vhost_vsock_device_unrealize;
vdc->get_features = vhost_vsock_get_features;
vdc->get_config = vhost_vsock_get_config;
vdc->set_status = vhost_vsock_set_status;
}
static const TypeInfo vhost_vsock_info = {
.name = TYPE_VHOST_VSOCK,
.parent = TYPE_VHOST_VSOCK_COMMON,
.instance_size = sizeof(VHostVSock),
.class_init = vhost_vsock_class_init,
};
static void vhost_vsock_register_types(void)
{
type_register_static(&vhost_vsock_info);
}
type_init(vhost_vsock_register_types)