qemu/hw/virtio/virtio-pmem.c

199 lines
5.9 KiB
C
Raw Normal View History

/*
* Virtio PMEM device
*
* Copyright (C) 2018-2019 Red Hat, Inc.
*
* Authors:
* Pankaj Gupta <pagupta@redhat.com>
* David Hildenbrand <david@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "hw/virtio/virtio-pmem.h"
#include "hw/qdev-properties.h"
#include "hw/virtio/virtio-access.h"
#include "standard-headers/linux/virtio_ids.h"
#include "standard-headers/linux/virtio_pmem.h"
#include "sysemu/hostmem.h"
#include "block/aio.h"
#include "block/thread-pool.h"
#include "trace.h"
typedef struct VirtIODeviceRequest {
VirtQueueElement elem;
int fd;
VirtIOPMEM *pmem;
VirtIODevice *vdev;
struct virtio_pmem_req req;
struct virtio_pmem_resp resp;
} VirtIODeviceRequest;
static int worker_cb(void *opaque)
{
VirtIODeviceRequest *req_data = opaque;
int err = 0;
/* flush raw backing image */
err = fsync(req_data->fd);
trace_virtio_pmem_flush_done(err);
if (err != 0) {
err = 1;
}
virtio_stl_p(req_data->vdev, &req_data->resp.ret, err);
return 0;
}
static void done_cb(void *opaque, int ret)
{
VirtIODeviceRequest *req_data = opaque;
int len = iov_from_buf(req_data->elem.in_sg, req_data->elem.in_num, 0,
&req_data->resp, sizeof(struct virtio_pmem_resp));
/* Callbacks are serialized, so no need to use atomic ops. */
virtqueue_push(req_data->pmem->rq_vq, &req_data->elem, len);
virtio_notify((VirtIODevice *)req_data->pmem, req_data->pmem->rq_vq);
trace_virtio_pmem_response();
g_free(req_data);
}
static void virtio_pmem_flush(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIODeviceRequest *req_data;
VirtIOPMEM *pmem = VIRTIO_PMEM(vdev);
HostMemoryBackend *backend = MEMORY_BACKEND(pmem->memdev);
ThreadPool *pool = aio_get_thread_pool(qemu_get_aio_context());
trace_virtio_pmem_flush_request();
req_data = virtqueue_pop(vq, sizeof(VirtIODeviceRequest));
if (!req_data) {
virtio_error(vdev, "virtio-pmem missing request data");
return;
}
if (req_data->elem.out_num < 1 || req_data->elem.in_num < 1) {
virtio_error(vdev, "virtio-pmem request not proper");
virtqueue_detach_element(vq, (VirtQueueElement *)req_data, 0);
g_free(req_data);
return;
}
req_data->fd = memory_region_get_fd(&backend->mr);
req_data->pmem = pmem;
req_data->vdev = vdev;
thread_pool_submit_aio(pool, worker_cb, req_data, done_cb, req_data);
}
static void virtio_pmem_get_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIOPMEM *pmem = VIRTIO_PMEM(vdev);
struct virtio_pmem_config *pmemcfg = (struct virtio_pmem_config *) config;
virtio_stq_p(vdev, &pmemcfg->start, pmem->start);
virtio_stq_p(vdev, &pmemcfg->size, memory_region_size(&pmem->memdev->mr));
}
static uint64_t virtio_pmem_get_features(VirtIODevice *vdev, uint64_t features,
Error **errp)
{
return features;
}
static void virtio_pmem_realize(DeviceState *dev, Error **errp)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOPMEM *pmem = VIRTIO_PMEM(dev);
if (!pmem->memdev) {
error_setg(errp, "virtio-pmem memdev not set");
return;
}
if (host_memory_backend_is_mapped(pmem->memdev)) {
error_setg(errp, "can't use already busy memdev: %s",
object_get_canonical_path_component(OBJECT(pmem->memdev)));
return;
}
host_memory_backend_set_mapped(pmem->memdev, true);
virtio_init(vdev, TYPE_VIRTIO_PMEM, VIRTIO_ID_PMEM,
sizeof(struct virtio_pmem_config));
pmem->rq_vq = virtio_add_queue(vdev, 128, virtio_pmem_flush);
}
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 virtio_pmem_unrealize(DeviceState *dev)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOPMEM *pmem = VIRTIO_PMEM(dev);
host_memory_backend_set_mapped(pmem->memdev, false);
virtio_delete_queue(pmem->rq_vq);
virtio_cleanup(vdev);
}
static void virtio_pmem_fill_device_info(const VirtIOPMEM *pmem,
VirtioPMEMDeviceInfo *vi)
{
vi->memaddr = pmem->start;
vi->size = memory_region_size(&pmem->memdev->mr);
vi->memdev = object_get_canonical_path(OBJECT(pmem->memdev));
}
static MemoryRegion *virtio_pmem_get_memory_region(VirtIOPMEM *pmem,
Error **errp)
{
if (!pmem->memdev) {
error_setg(errp, "'%s' property must be set", VIRTIO_PMEM_MEMDEV_PROP);
return NULL;
}
return &pmem->memdev->mr;
}
static Property virtio_pmem_properties[] = {
DEFINE_PROP_UINT64(VIRTIO_PMEM_ADDR_PROP, VirtIOPMEM, start, 0),
DEFINE_PROP_LINK(VIRTIO_PMEM_MEMDEV_PROP, VirtIOPMEM, memdev,
TYPE_MEMORY_BACKEND, HostMemoryBackend *),
DEFINE_PROP_END_OF_LIST(),
};
static void virtio_pmem_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
VirtIOPMEMClass *vpc = VIRTIO_PMEM_CLASS(klass);
device_class_set_props(dc, virtio_pmem_properties);
vdc->realize = virtio_pmem_realize;
vdc->unrealize = virtio_pmem_unrealize;
vdc->get_config = virtio_pmem_get_config;
vdc->get_features = virtio_pmem_get_features;
vpc->fill_device_info = virtio_pmem_fill_device_info;
vpc->get_memory_region = virtio_pmem_get_memory_region;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
}
static TypeInfo virtio_pmem_info = {
.name = TYPE_VIRTIO_PMEM,
.parent = TYPE_VIRTIO_DEVICE,
.class_size = sizeof(VirtIOPMEMClass),
.class_init = virtio_pmem_class_init,
.instance_size = sizeof(VirtIOPMEM),
};
static void virtio_register_types(void)
{
type_register_static(&virtio_pmem_info);
}
type_init(virtio_register_types)