xemu/hw/vfio/ap.c
Markus Armbruster b69c3c21a5 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>
2020-05-15 07:08:14 +02:00

188 lines
4.8 KiB
C

/*
* VFIO based AP matrix device assignment
*
* Copyright 2018 IBM Corp.
* Author(s): Tony Krowiak <akrowiak@linux.ibm.com>
* Halil Pasic <pasic@linux.ibm.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 <linux/vfio.h>
#include <sys/ioctl.h>
#include "qapi/error.h"
#include "hw/sysbus.h"
#include "hw/vfio/vfio.h"
#include "hw/vfio/vfio-common.h"
#include "hw/s390x/ap-device.h"
#include "qemu/error-report.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/config-file.h"
#include "cpu.h"
#include "kvm_s390x.h"
#include "migration/vmstate.h"
#include "hw/qdev-properties.h"
#include "hw/s390x/ap-bridge.h"
#include "exec/address-spaces.h"
#define VFIO_AP_DEVICE_TYPE "vfio-ap"
typedef struct VFIOAPDevice {
APDevice apdev;
VFIODevice vdev;
} VFIOAPDevice;
#define VFIO_AP_DEVICE(obj) \
OBJECT_CHECK(VFIOAPDevice, (obj), VFIO_AP_DEVICE_TYPE)
static void vfio_ap_compute_needs_reset(VFIODevice *vdev)
{
vdev->needs_reset = false;
}
/*
* We don't need vfio_hot_reset_multi and vfio_eoi operations for
* vfio-ap device now.
*/
struct VFIODeviceOps vfio_ap_ops = {
.vfio_compute_needs_reset = vfio_ap_compute_needs_reset,
};
static void vfio_ap_put_device(VFIOAPDevice *vapdev)
{
g_free(vapdev->vdev.name);
vfio_put_base_device(&vapdev->vdev);
}
static VFIOGroup *vfio_ap_get_group(VFIOAPDevice *vapdev, Error **errp)
{
GError *gerror = NULL;
char *symlink, *group_path;
int groupid;
symlink = g_strdup_printf("%s/iommu_group", vapdev->vdev.sysfsdev);
group_path = g_file_read_link(symlink, &gerror);
g_free(symlink);
if (!group_path) {
error_setg(errp, "%s: no iommu_group found for %s: %s",
VFIO_AP_DEVICE_TYPE, vapdev->vdev.sysfsdev, gerror->message);
return NULL;
}
if (sscanf(basename(group_path), "%d", &groupid) != 1) {
error_setg(errp, "vfio: failed to read %s", group_path);
g_free(group_path);
return NULL;
}
g_free(group_path);
return vfio_get_group(groupid, &address_space_memory, errp);
}
static void vfio_ap_realize(DeviceState *dev, Error **errp)
{
int ret;
char *mdevid;
VFIOGroup *vfio_group;
APDevice *apdev = AP_DEVICE(dev);
VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
vfio_group = vfio_ap_get_group(vapdev, errp);
if (!vfio_group) {
return;
}
vapdev->vdev.ops = &vfio_ap_ops;
vapdev->vdev.type = VFIO_DEVICE_TYPE_AP;
mdevid = basename(vapdev->vdev.sysfsdev);
vapdev->vdev.name = g_strdup_printf("%s", mdevid);
vapdev->vdev.dev = dev;
/*
* vfio-ap devices operate in a way compatible with
* memory ballooning, as no pages are pinned in the host.
* This needs to be set before vfio_get_device() for vfio common to
* handle the balloon inhibitor.
*/
vapdev->vdev.balloon_allowed = true;
ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp);
if (ret) {
goto out_get_dev_err;
}
return;
out_get_dev_err:
vfio_ap_put_device(vapdev);
vfio_put_group(vfio_group);
}
static void vfio_ap_unrealize(DeviceState *dev)
{
APDevice *apdev = AP_DEVICE(dev);
VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
VFIOGroup *group = vapdev->vdev.group;
vfio_ap_put_device(vapdev);
vfio_put_group(group);
}
static Property vfio_ap_properties[] = {
DEFINE_PROP_STRING("sysfsdev", VFIOAPDevice, vdev.sysfsdev),
DEFINE_PROP_END_OF_LIST(),
};
static void vfio_ap_reset(DeviceState *dev)
{
int ret;
APDevice *apdev = AP_DEVICE(dev);
VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev);
ret = ioctl(vapdev->vdev.fd, VFIO_DEVICE_RESET);
if (ret) {
error_report("%s: failed to reset %s device: %s", __func__,
vapdev->vdev.name, strerror(errno));
}
}
static const VMStateDescription vfio_ap_vmstate = {
.name = "vfio-ap",
.unmigratable = 1,
};
static void vfio_ap_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
device_class_set_props(dc, vfio_ap_properties);
dc->vmsd = &vfio_ap_vmstate;
dc->desc = "VFIO-based AP device assignment";
set_bit(DEVICE_CATEGORY_MISC, dc->categories);
dc->realize = vfio_ap_realize;
dc->unrealize = vfio_ap_unrealize;
dc->hotpluggable = true;
dc->reset = vfio_ap_reset;
dc->bus_type = TYPE_AP_BUS;
}
static const TypeInfo vfio_ap_info = {
.name = VFIO_AP_DEVICE_TYPE,
.parent = AP_DEVICE_TYPE,
.instance_size = sizeof(VFIOAPDevice),
.class_init = vfio_ap_class_init,
};
static void vfio_ap_type_init(void)
{
type_register_static(&vfio_ap_info);
}
type_init(vfio_ap_type_init)