qemu/include/hw/xen/xen-bus.h

141 lines
4.6 KiB
C
Raw Normal View History

/*
* Copyright (c) 2018 Citrix Systems Inc.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef HW_XEN_BUS_H
#define HW_XEN_BUS_H
#include "hw/xen/xen_common.h"
#include "hw/sysbus.h"
#include "qemu/notify.h"
#include "qom/object.h"
typedef void (*XenWatchHandler)(void *opaque);
typedef struct XenWatchList XenWatchList;
typedef struct XenWatch XenWatch;
typedef struct XenEventChannel XenEventChannel;
struct XenDevice {
DeviceState qdev;
domid_t frontend_id;
char *name;
struct xs_handle *xsh;
XenWatchList *watch_list;
char *backend_path, *frontend_path;
enum xenbus_state backend_state, frontend_state;
Notifier exit;
XenWatch *backend_state_watch, *frontend_state_watch;
bool backend_online;
XenWatch *backend_online_watch;
xengnttab_handle *xgth;
bool feature_grant_copy;
xen: perform XenDevice clean-up in XenBus watch handler Cleaning up offline XenDevice objects directly in xen_device_backend_changed() is dangerous as xen_device_unrealize() will modify the watch list that is being walked. Even the QLIST_FOREACH_SAFE() used in notifier_list_notify() is insufficient as *two* notifiers (for the frontend and backend watches) are removed, thus potentially rendering the 'next' pointer unsafe. The solution is to use the XenBus backend_watch handler to do the clean-up instead, as it is invoked whilst walking a separate watch list. This patch therefore adds a new 'inactive_devices' list to XenBus, to which offline devices are added by xen_device_backend_changed(). The XenBus backend_watch registration is also changed to not only invoke xen_bus_enumerate() but also a new xen_bus_cleanup() function, which will walk 'inactive_devices' and perform the necessary actions. For safety an extra 'online' check is also added to xen_bus_type_enumerate() to make sure that no attempt is made to create a new XenDevice object for a backend that is offline. NOTE: This patch also includes some cosmetic changes: - substitute the local variable name 'backend_state' in xen_bus_type_enumerate() with 'state', since there is no ambiguity with any other state in that context. - change xen_device_state_is_active() to xen_device_frontend_is_active() (and pass a XenDevice directly) since the state tests contained therein only apply to a frontend. - use 'state' rather then 'xendev->backend_state' in xen_device_backend_changed() to shorten the code. Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Reviewed-by: Anthony PERARD <anthony.perard@citrix.com> Message-Id: <20190913082159.31338-4-paul.durrant@citrix.com> Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>
2019-09-13 11:21:58 +03:00
bool inactive;
QLIST_HEAD(, XenEventChannel) event_channels;
xen: perform XenDevice clean-up in XenBus watch handler Cleaning up offline XenDevice objects directly in xen_device_backend_changed() is dangerous as xen_device_unrealize() will modify the watch list that is being walked. Even the QLIST_FOREACH_SAFE() used in notifier_list_notify() is insufficient as *two* notifiers (for the frontend and backend watches) are removed, thus potentially rendering the 'next' pointer unsafe. The solution is to use the XenBus backend_watch handler to do the clean-up instead, as it is invoked whilst walking a separate watch list. This patch therefore adds a new 'inactive_devices' list to XenBus, to which offline devices are added by xen_device_backend_changed(). The XenBus backend_watch registration is also changed to not only invoke xen_bus_enumerate() but also a new xen_bus_cleanup() function, which will walk 'inactive_devices' and perform the necessary actions. For safety an extra 'online' check is also added to xen_bus_type_enumerate() to make sure that no attempt is made to create a new XenDevice object for a backend that is offline. NOTE: This patch also includes some cosmetic changes: - substitute the local variable name 'backend_state' in xen_bus_type_enumerate() with 'state', since there is no ambiguity with any other state in that context. - change xen_device_state_is_active() to xen_device_frontend_is_active() (and pass a XenDevice directly) since the state tests contained therein only apply to a frontend. - use 'state' rather then 'xendev->backend_state' in xen_device_backend_changed() to shorten the code. Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Reviewed-by: Anthony PERARD <anthony.perard@citrix.com> Message-Id: <20190913082159.31338-4-paul.durrant@citrix.com> Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>
2019-09-13 11:21:58 +03:00
QLIST_ENTRY(XenDevice) list;
};
typedef struct XenDevice XenDevice;
typedef char *(*XenDeviceGetName)(XenDevice *xendev, Error **errp);
typedef void (*XenDeviceRealize)(XenDevice *xendev, Error **errp);
typedef void (*XenDeviceFrontendChanged)(XenDevice *xendev,
enum xenbus_state frontend_state,
Error **errp);
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
typedef void (*XenDeviceUnrealize)(XenDevice *xendev);
struct XenDeviceClass {
/*< private >*/
DeviceClass parent_class;
/*< public >*/
const char *backend;
const char *device;
XenDeviceGetName get_name;
XenDeviceRealize realize;
XenDeviceFrontendChanged frontend_changed;
XenDeviceUnrealize unrealize;
};
typedef struct XenDeviceClass XenDeviceClass;
#define TYPE_XEN_DEVICE "xen-device"
DECLARE_OBJ_CHECKERS(XenDevice, XenDeviceClass,
XEN_DEVICE, TYPE_XEN_DEVICE)
struct XenBus {
BusState qbus;
domid_t backend_id;
struct xs_handle *xsh;
XenWatchList *watch_list;
XenWatch *backend_watch;
xen: perform XenDevice clean-up in XenBus watch handler Cleaning up offline XenDevice objects directly in xen_device_backend_changed() is dangerous as xen_device_unrealize() will modify the watch list that is being walked. Even the QLIST_FOREACH_SAFE() used in notifier_list_notify() is insufficient as *two* notifiers (for the frontend and backend watches) are removed, thus potentially rendering the 'next' pointer unsafe. The solution is to use the XenBus backend_watch handler to do the clean-up instead, as it is invoked whilst walking a separate watch list. This patch therefore adds a new 'inactive_devices' list to XenBus, to which offline devices are added by xen_device_backend_changed(). The XenBus backend_watch registration is also changed to not only invoke xen_bus_enumerate() but also a new xen_bus_cleanup() function, which will walk 'inactive_devices' and perform the necessary actions. For safety an extra 'online' check is also added to xen_bus_type_enumerate() to make sure that no attempt is made to create a new XenDevice object for a backend that is offline. NOTE: This patch also includes some cosmetic changes: - substitute the local variable name 'backend_state' in xen_bus_type_enumerate() with 'state', since there is no ambiguity with any other state in that context. - change xen_device_state_is_active() to xen_device_frontend_is_active() (and pass a XenDevice directly) since the state tests contained therein only apply to a frontend. - use 'state' rather then 'xendev->backend_state' in xen_device_backend_changed() to shorten the code. Signed-off-by: Paul Durrant <paul.durrant@citrix.com> Reviewed-by: Anthony PERARD <anthony.perard@citrix.com> Message-Id: <20190913082159.31338-4-paul.durrant@citrix.com> Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>
2019-09-13 11:21:58 +03:00
QLIST_HEAD(, XenDevice) inactive_devices;
};
struct XenBusClass {
/*< private >*/
BusClass parent_class;
};
#define TYPE_XEN_BUS "xen-bus"
OBJECT_DECLARE_TYPE(XenBus, XenBusClass,
XEN_BUS)
void xen_bus_init(void);
void xen_device_backend_set_state(XenDevice *xendev,
enum xenbus_state state);
enum xenbus_state xen_device_backend_get_state(XenDevice *xendev);
void xen_device_backend_printf(XenDevice *xendev, const char *key,
const char *fmt, ...)
GCC_FMT_ATTR(3, 4);
void xen_device_frontend_printf(XenDevice *xendev, const char *key,
const char *fmt, ...)
GCC_FMT_ATTR(3, 4);
int xen_device_frontend_scanf(XenDevice *xendev, const char *key,
const char *fmt, ...);
void xen_device_set_max_grant_refs(XenDevice *xendev, unsigned int nr_refs,
Error **errp);
void *xen_device_map_grant_refs(XenDevice *xendev, uint32_t *refs,
unsigned int nr_refs, int prot,
Error **errp);
void xen_device_unmap_grant_refs(XenDevice *xendev, void *map,
unsigned int nr_refs, Error **errp);
typedef struct XenDeviceGrantCopySegment {
union {
void *virt;
struct {
uint32_t ref;
off_t offset;
} foreign;
} source, dest;
size_t len;
} XenDeviceGrantCopySegment;
void xen_device_copy_grant_refs(XenDevice *xendev, bool to_domain,
XenDeviceGrantCopySegment segs[],
unsigned int nr_segs, Error **errp);
typedef bool (*XenEventHandler)(void *opaque);
XenEventChannel *xen_device_bind_event_channel(XenDevice *xendev,
unsigned int port,
XenEventHandler handler,
void *opaque, Error **errp);
void xen_device_set_event_channel_context(XenDevice *xendev,
XenEventChannel *channel,
AioContext *ctx,
Error **errp);
void xen_device_notify_event_channel(XenDevice *xendev,
XenEventChannel *channel,
Error **errp);
void xen_device_unbind_event_channel(XenDevice *xendev,
XenEventChannel *channel,
Error **errp);
#endif /* HW_XEN_BUS_H */