238e917285
If a vfio assigned device makes use of a physical IOMMU, then memory ballooning is necessarily inhibited due to the page pinning, lack of page level granularity at the IOMMU, and sufficient notifiers to both remove the page on balloon inflation and add it back on deflation. However, not all devices are backed by a physical IOMMU. In the case of mediated devices, if a vendor driver is well synchronized with the guest driver, such that only pages actively used by the guest driver are pinned by the host mdev vendor driver, then there should be no overlap between pages available for the balloon driver and pages actively in use by the device. Under these conditions, ballooning should be safe. vfio-ccw devices are always mediated devices and always operate under the constraints above. Therefore we can consider all vfio-ccw devices as balloon compatible. The situation is far from straightforward with vfio-pci. These devices can be physical devices with physical IOMMU backing or mediated devices where it is unknown whether a physical IOMMU is in use or whether the vendor driver is well synchronized to the working set of the guest driver. The safest approach is therefore to assume all vfio-pci devices are incompatible with ballooning, but allow user opt-in should they have further insight into mediated devices. Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
199 lines
5.9 KiB
C
199 lines
5.9 KiB
C
/*
|
|
* common header for vfio based device assignment support
|
|
*
|
|
* Copyright Red Hat, Inc. 2012
|
|
*
|
|
* Authors:
|
|
* Alex Williamson <alex.williamson@redhat.com>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2. See
|
|
* the COPYING file in the top-level directory.
|
|
*
|
|
* Based on qemu-kvm device-assignment:
|
|
* Adapted for KVM by Qumranet.
|
|
* Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
|
|
* Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
|
|
* Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
|
|
* Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
|
|
* Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
|
|
*/
|
|
|
|
#ifndef HW_VFIO_VFIO_COMMON_H
|
|
#define HW_VFIO_VFIO_COMMON_H
|
|
|
|
#include "qemu-common.h"
|
|
#include "exec/memory.h"
|
|
#include "qemu/queue.h"
|
|
#include "qemu/notify.h"
|
|
#include "ui/console.h"
|
|
#ifdef CONFIG_LINUX
|
|
#include <linux/vfio.h>
|
|
#endif
|
|
|
|
#define ERR_PREFIX "vfio error: %s: "
|
|
#define WARN_PREFIX "vfio warning: %s: "
|
|
|
|
enum {
|
|
VFIO_DEVICE_TYPE_PCI = 0,
|
|
VFIO_DEVICE_TYPE_PLATFORM = 1,
|
|
VFIO_DEVICE_TYPE_CCW = 2,
|
|
};
|
|
|
|
typedef struct VFIOMmap {
|
|
MemoryRegion mem;
|
|
void *mmap;
|
|
off_t offset;
|
|
size_t size;
|
|
} VFIOMmap;
|
|
|
|
typedef struct VFIORegion {
|
|
struct VFIODevice *vbasedev;
|
|
off_t fd_offset; /* offset of region within device fd */
|
|
MemoryRegion *mem; /* slow, read/write access */
|
|
size_t size;
|
|
uint32_t flags; /* VFIO region flags (rd/wr/mmap) */
|
|
uint32_t nr_mmaps;
|
|
VFIOMmap *mmaps;
|
|
uint8_t nr; /* cache the region number for debug */
|
|
} VFIORegion;
|
|
|
|
typedef struct VFIOAddressSpace {
|
|
AddressSpace *as;
|
|
QLIST_HEAD(, VFIOContainer) containers;
|
|
QLIST_ENTRY(VFIOAddressSpace) list;
|
|
} VFIOAddressSpace;
|
|
|
|
struct VFIOGroup;
|
|
|
|
typedef struct VFIOContainer {
|
|
VFIOAddressSpace *space;
|
|
int fd; /* /dev/vfio/vfio, empowered by the attached groups */
|
|
MemoryListener listener;
|
|
MemoryListener prereg_listener;
|
|
unsigned iommu_type;
|
|
int error;
|
|
bool initialized;
|
|
/*
|
|
* This assumes the host IOMMU can support only a single
|
|
* contiguous IOVA window. We may need to generalize that in
|
|
* future
|
|
*/
|
|
QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
|
|
QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
|
|
QLIST_HEAD(, VFIOGroup) group_list;
|
|
QLIST_ENTRY(VFIOContainer) next;
|
|
} VFIOContainer;
|
|
|
|
typedef struct VFIOGuestIOMMU {
|
|
VFIOContainer *container;
|
|
IOMMUMemoryRegion *iommu;
|
|
hwaddr iommu_offset;
|
|
IOMMUNotifier n;
|
|
QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
|
|
} VFIOGuestIOMMU;
|
|
|
|
typedef struct VFIOHostDMAWindow {
|
|
hwaddr min_iova;
|
|
hwaddr max_iova;
|
|
uint64_t iova_pgsizes;
|
|
QLIST_ENTRY(VFIOHostDMAWindow) hostwin_next;
|
|
} VFIOHostDMAWindow;
|
|
|
|
typedef struct VFIODeviceOps VFIODeviceOps;
|
|
|
|
typedef struct VFIODevice {
|
|
QLIST_ENTRY(VFIODevice) next;
|
|
struct VFIOGroup *group;
|
|
char *sysfsdev;
|
|
char *name;
|
|
DeviceState *dev;
|
|
int fd;
|
|
int type;
|
|
bool reset_works;
|
|
bool needs_reset;
|
|
bool no_mmap;
|
|
bool balloon_allowed;
|
|
VFIODeviceOps *ops;
|
|
unsigned int num_irqs;
|
|
unsigned int num_regions;
|
|
unsigned int flags;
|
|
} VFIODevice;
|
|
|
|
struct VFIODeviceOps {
|
|
void (*vfio_compute_needs_reset)(VFIODevice *vdev);
|
|
int (*vfio_hot_reset_multi)(VFIODevice *vdev);
|
|
void (*vfio_eoi)(VFIODevice *vdev);
|
|
};
|
|
|
|
typedef struct VFIOGroup {
|
|
int fd;
|
|
int groupid;
|
|
VFIOContainer *container;
|
|
QLIST_HEAD(, VFIODevice) device_list;
|
|
QLIST_ENTRY(VFIOGroup) next;
|
|
QLIST_ENTRY(VFIOGroup) container_next;
|
|
bool balloon_allowed;
|
|
} VFIOGroup;
|
|
|
|
typedef struct VFIODMABuf {
|
|
QemuDmaBuf buf;
|
|
uint32_t pos_x, pos_y, pos_updates;
|
|
uint32_t hot_x, hot_y, hot_updates;
|
|
int dmabuf_id;
|
|
QTAILQ_ENTRY(VFIODMABuf) next;
|
|
} VFIODMABuf;
|
|
|
|
typedef struct VFIODisplay {
|
|
QemuConsole *con;
|
|
struct {
|
|
VFIORegion buffer;
|
|
DisplaySurface *surface;
|
|
} region;
|
|
struct {
|
|
QTAILQ_HEAD(, VFIODMABuf) bufs;
|
|
VFIODMABuf *primary;
|
|
VFIODMABuf *cursor;
|
|
} dmabuf;
|
|
} VFIODisplay;
|
|
|
|
void vfio_put_base_device(VFIODevice *vbasedev);
|
|
void vfio_disable_irqindex(VFIODevice *vbasedev, int index);
|
|
void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index);
|
|
void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index);
|
|
void vfio_region_write(void *opaque, hwaddr addr,
|
|
uint64_t data, unsigned size);
|
|
uint64_t vfio_region_read(void *opaque,
|
|
hwaddr addr, unsigned size);
|
|
int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region,
|
|
int index, const char *name);
|
|
int vfio_region_mmap(VFIORegion *region);
|
|
void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled);
|
|
void vfio_region_exit(VFIORegion *region);
|
|
void vfio_region_finalize(VFIORegion *region);
|
|
void vfio_reset_handler(void *opaque);
|
|
VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);
|
|
void vfio_put_group(VFIOGroup *group);
|
|
int vfio_get_device(VFIOGroup *group, const char *name,
|
|
VFIODevice *vbasedev, Error **errp);
|
|
|
|
extern const MemoryRegionOps vfio_region_ops;
|
|
extern QLIST_HEAD(vfio_group_head, VFIOGroup) vfio_group_list;
|
|
extern QLIST_HEAD(vfio_as_head, VFIOAddressSpace) vfio_address_spaces;
|
|
|
|
#ifdef CONFIG_LINUX
|
|
int vfio_get_region_info(VFIODevice *vbasedev, int index,
|
|
struct vfio_region_info **info);
|
|
int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
|
|
uint32_t subtype, struct vfio_region_info **info);
|
|
bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type);
|
|
#endif
|
|
extern const MemoryListener vfio_prereg_listener;
|
|
|
|
int vfio_spapr_create_window(VFIOContainer *container,
|
|
MemoryRegionSection *section,
|
|
hwaddr *pgsize);
|
|
int vfio_spapr_remove_window(VFIOContainer *container,
|
|
hwaddr offset_within_address_space);
|
|
|
|
#endif /* HW_VFIO_VFIO_COMMON_H */
|