qemu/hw/scsi/vhost-scsi.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

335 lines
9.7 KiB
C

/*
* vhost_scsi host device
*
* Copyright IBM, Corp. 2011
*
* Authors:
* Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
*
* Changes for QEMU mainline + tcm_vhost kernel upstream:
* Nicholas Bellinger <nab@risingtidesystems.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include <linux/vhost.h>
#include <sys/ioctl.h>
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/module.h"
#include "monitor/monitor.h"
#include "migration/blocker.h"
#include "hw/virtio/vhost-scsi.h"
#include "hw/virtio/vhost.h"
#include "hw/virtio/virtio-scsi.h"
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-access.h"
#include "hw/fw-path-provider.h"
#include "hw/qdev-properties.h"
#include "qemu/cutils.h"
#include "sysemu/sysemu.h"
/* Features supported by host kernel. */
static const int kernel_feature_bits[] = {
VIRTIO_F_NOTIFY_ON_EMPTY,
VIRTIO_RING_F_INDIRECT_DESC,
VIRTIO_RING_F_EVENT_IDX,
VIRTIO_SCSI_F_HOTPLUG,
VHOST_INVALID_FEATURE_BIT
};
static int vhost_scsi_set_endpoint(VHostSCSI *s)
{
VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
const VhostOps *vhost_ops = vsc->dev.vhost_ops;
struct vhost_scsi_target backend;
int ret;
memset(&backend, 0, sizeof(backend));
pstrcpy(backend.vhost_wwpn, sizeof(backend.vhost_wwpn), vs->conf.wwpn);
ret = vhost_ops->vhost_scsi_set_endpoint(&vsc->dev, &backend);
if (ret < 0) {
return -errno;
}
return 0;
}
static void vhost_scsi_clear_endpoint(VHostSCSI *s)
{
VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
struct vhost_scsi_target backend;
const VhostOps *vhost_ops = vsc->dev.vhost_ops;
memset(&backend, 0, sizeof(backend));
pstrcpy(backend.vhost_wwpn, sizeof(backend.vhost_wwpn), vs->conf.wwpn);
vhost_ops->vhost_scsi_clear_endpoint(&vsc->dev, &backend);
}
static int vhost_scsi_start(VHostSCSI *s)
{
int ret, abi_version;
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
const VhostOps *vhost_ops = vsc->dev.vhost_ops;
ret = vhost_ops->vhost_scsi_get_abi_version(&vsc->dev, &abi_version);
if (ret < 0) {
return -errno;
}
if (abi_version > VHOST_SCSI_ABI_VERSION) {
error_report("vhost-scsi: The running tcm_vhost kernel abi_version:"
" %d is greater than vhost_scsi userspace supports: %d,"
" please upgrade your version of QEMU", abi_version,
VHOST_SCSI_ABI_VERSION);
return -ENOSYS;
}
ret = vhost_scsi_common_start(vsc);
if (ret < 0) {
return ret;
}
ret = vhost_scsi_set_endpoint(s);
if (ret < 0) {
error_report("Error setting vhost-scsi endpoint");
vhost_scsi_common_stop(vsc);
}
return ret;
}
static void vhost_scsi_stop(VHostSCSI *s)
{
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
vhost_scsi_clear_endpoint(s);
vhost_scsi_common_stop(vsc);
}
static void vhost_scsi_set_status(VirtIODevice *vdev, uint8_t val)
{
VHostSCSI *s = VHOST_SCSI(vdev);
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s);
bool start = (val & VIRTIO_CONFIG_S_DRIVER_OK);
if (!vdev->vm_running) {
start = false;
}
if (vsc->dev.started == start) {
return;
}
if (start) {
int ret;
ret = vhost_scsi_start(s);
if (ret < 0) {
error_report("unable to start vhost-scsi: %s", strerror(-ret));
exit(1);
}
} else {
vhost_scsi_stop(s);
}
}
static void vhost_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
}
static int vhost_scsi_pre_save(void *opaque)
{
VHostSCSICommon *vsc = opaque;
/* At this point, backend must be stopped, otherwise
* it might keep writing to memory. */
assert(!vsc->dev.started);
return 0;
}
static const VMStateDescription vmstate_virtio_vhost_scsi = {
.name = "virtio-vhost_scsi",
.minimum_version_id = 1,
.version_id = 1,
.fields = (VMStateField[]) {
VMSTATE_VIRTIO_DEVICE,
VMSTATE_END_OF_LIST()
},
.pre_save = vhost_scsi_pre_save,
};
static void vhost_scsi_realize(DeviceState *dev, Error **errp)
{
VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(dev);
Error *err = NULL;
int vhostfd = -1;
int ret;
if (!vs->conf.wwpn) {
error_setg(errp, "vhost-scsi: missing wwpn");
return;
}
if (vs->conf.vhostfd) {
vhostfd = monitor_fd_param(cur_mon, vs->conf.vhostfd, errp);
if (vhostfd == -1) {
error_prepend(errp, "vhost-scsi: unable to parse vhostfd: ");
return;
}
} else {
vhostfd = open("/dev/vhost-scsi", O_RDWR);
if (vhostfd < 0) {
error_setg(errp, "vhost-scsi: open vhost char device failed: %s",
strerror(errno));
return;
}
}
virtio_scsi_common_realize(dev,
vhost_dummy_handle_output,
vhost_dummy_handle_output,
vhost_dummy_handle_output,
&err);
if (err != NULL) {
error_propagate(errp, err);
goto close_fd;
}
if (!vsc->migratable) {
error_setg(&vsc->migration_blocker,
"vhost-scsi does not support migration in all cases. "
"When external environment supports it (Orchestrator migrates "
"target SCSI device state or use shared storage over network), "
"set 'migratable' property to true to enable migration.");
migrate_add_blocker(vsc->migration_blocker, &err);
if (err) {
error_propagate(errp, err);
error_free(vsc->migration_blocker);
goto free_virtio;
}
}
vsc->dev.nvqs = VHOST_SCSI_VQ_NUM_FIXED + vs->conf.num_queues;
vsc->dev.vqs = g_new0(struct vhost_virtqueue, vsc->dev.nvqs);
vsc->dev.vq_index = 0;
vsc->dev.backend_features = 0;
ret = vhost_dev_init(&vsc->dev, (void *)(uintptr_t)vhostfd,
VHOST_BACKEND_TYPE_KERNEL, 0);
if (ret < 0) {
error_setg(errp, "vhost-scsi: vhost initialization failed: %s",
strerror(-ret));
goto free_vqs;
}
/* At present, channel and lun both are 0 for bootable vhost-scsi disk */
vsc->channel = 0;
vsc->lun = 0;
/* Note: we can also get the minimum tpgt from kernel */
vsc->target = vs->conf.boot_tpgt;
return;
free_vqs:
if (!vsc->migratable) {
migrate_del_blocker(vsc->migration_blocker);
}
g_free(vsc->dev.vqs);
free_virtio:
virtio_scsi_common_unrealize(dev);
close_fd:
close(vhostfd);
return;
}
static void vhost_scsi_unrealize(DeviceState *dev)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(dev);
struct vhost_virtqueue *vqs = vsc->dev.vqs;
if (!vsc->migratable) {
migrate_del_blocker(vsc->migration_blocker);
error_free(vsc->migration_blocker);
}
/* This will stop vhost backend. */
vhost_scsi_set_status(vdev, 0);
vhost_dev_cleanup(&vsc->dev);
g_free(vqs);
virtio_scsi_common_unrealize(dev);
}
static Property vhost_scsi_properties[] = {
DEFINE_PROP_STRING("vhostfd", VirtIOSCSICommon, conf.vhostfd),
DEFINE_PROP_STRING("wwpn", VirtIOSCSICommon, conf.wwpn),
DEFINE_PROP_UINT32("boot_tpgt", VirtIOSCSICommon, conf.boot_tpgt, 0),
DEFINE_PROP_UINT32("num_queues", VirtIOSCSICommon, conf.num_queues, 1),
DEFINE_PROP_UINT32("virtqueue_size", VirtIOSCSICommon, conf.virtqueue_size,
128),
DEFINE_PROP_BOOL("seg_max_adjust", VirtIOSCSICommon, conf.seg_max_adjust,
true),
DEFINE_PROP_UINT32("max_sectors", VirtIOSCSICommon, conf.max_sectors,
0xFFFF),
DEFINE_PROP_UINT32("cmd_per_lun", VirtIOSCSICommon, conf.cmd_per_lun, 128),
DEFINE_PROP_BIT64("t10_pi", VHostSCSICommon, host_features,
VIRTIO_SCSI_F_T10_PI,
false),
DEFINE_PROP_BOOL("migratable", VHostSCSICommon, migratable, false),
DEFINE_PROP_END_OF_LIST(),
};
static void vhost_scsi_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
FWPathProviderClass *fwc = FW_PATH_PROVIDER_CLASS(klass);
device_class_set_props(dc, vhost_scsi_properties);
dc->vmsd = &vmstate_virtio_vhost_scsi;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
vdc->realize = vhost_scsi_realize;
vdc->unrealize = vhost_scsi_unrealize;
vdc->get_features = vhost_scsi_common_get_features;
vdc->set_config = vhost_scsi_common_set_config;
vdc->set_status = vhost_scsi_set_status;
fwc->get_dev_path = vhost_scsi_common_get_fw_dev_path;
}
static void vhost_scsi_instance_init(Object *obj)
{
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(obj);
vsc->feature_bits = kernel_feature_bits;
device_add_bootindex_property(obj, &vsc->bootindex, "bootindex", NULL,
DEVICE(vsc));
}
static const TypeInfo vhost_scsi_info = {
.name = TYPE_VHOST_SCSI,
.parent = TYPE_VHOST_SCSI_COMMON,
.instance_size = sizeof(VHostSCSI),
.class_init = vhost_scsi_class_init,
.instance_init = vhost_scsi_instance_init,
.interfaces = (InterfaceInfo[]) {
{ TYPE_FW_PATH_PROVIDER },
{ }
},
};
static void virtio_register_types(void)
{
type_register_static(&vhost_scsi_info);
}
type_init(virtio_register_types)