qemu-e2k/include/hw/vfio/vfio-common.h
Alexey Kardashevskiy 318f67ce13 vfio: spapr: Add DMA memory preregistering (SPAPR IOMMU v2)
This makes use of the new "memory registering" feature. The idea is
to provide the userspace ability to notify the host kernel about pages
which are going to be used for DMA. Having this information, the host
kernel can pin them all once per user process, do locked pages
accounting (once) and not spent time on doing that in real time with
possible failures which cannot be handled nicely in some cases.

This adds a prereg memory listener which listens on address_space_memory
and notifies a VFIO container about memory which needs to be
pinned/unpinned. VFIO MMIO regions (i.e. "skip dump" regions) are skipped.

The feature is only enabled for SPAPR IOMMU v2. The host kernel changes
are required. Since v2 does not need/support VFIO_IOMMU_ENABLE, this does
not call it when v2 is detected and enabled.

This enforces guest RAM blocks to be host page size aligned; however
this is not new as KVM already requires memory slots to be host page
size aligned.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[dwg: Fix compile error on 32-bit host]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
2016-07-05 14:30:54 +10:00

166 lines
4.9 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/address-spaces.h"
#include "exec/memory.h"
#include "qemu/queue.h"
#include "qemu/notify.h"
#ifdef CONFIG_LINUX
#include <linux/vfio.h>
#endif
/*#define DEBUG_VFIO*/
#ifdef DEBUG_VFIO
#define DPRINTF(fmt, ...) \
do { fprintf(stderr, "vfio: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
do { } while (0)
#endif
enum {
VFIO_DEVICE_TYPE_PCI = 0,
VFIO_DEVICE_TYPE_PLATFORM = 1,
};
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
*/
hwaddr min_iova, max_iova;
uint64_t iova_pgsizes;
QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
QLIST_HEAD(, VFIOGroup) group_list;
QLIST_ENTRY(VFIOContainer) next;
} VFIOContainer;
typedef struct VFIOGuestIOMMU {
VFIOContainer *container;
MemoryRegion *iommu;
hwaddr iommu_offset;
Notifier n;
QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
} VFIOGuestIOMMU;
typedef struct VFIODeviceOps VFIODeviceOps;
typedef struct VFIODevice {
QLIST_ENTRY(VFIODevice) next;
struct VFIOGroup *group;
char *sysfsdev;
char *name;
int fd;
int type;
bool reset_works;
bool needs_reset;
bool no_mmap;
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;
} VFIOGroup;
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);
void vfio_put_group(VFIOGroup *group);
int vfio_get_device(VFIOGroup *group, const char *name,
VFIODevice *vbasedev);
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);
#endif
extern const MemoryListener vfio_prereg_listener;
#endif /* !HW_VFIO_VFIO_COMMON_H */