qemu/include/hw/vfio/vfio-common.h

234 lines
7.1 KiB
C
Raw Normal View History

/*
* 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 "exec/memory.h"
#include "qemu/queue.h"
#include "qemu/notify.h"
#include "ui/console.h"
#include "hw/display/ramfb.h"
#ifdef CONFIG_LINUX
#include <linux/vfio.h>
#endif
#include "sysemu/sysemu.h"
#define VFIO_MSG_PREFIX "vfio %s: "
enum {
VFIO_DEVICE_TYPE_PCI = 0,
VFIO_DEVICE_TYPE_PLATFORM = 1,
VFIO_DEVICE_TYPE_CCW = 2,
s390x/vfio: ap: Introduce VFIO AP device Introduces a VFIO based AP device. The device is defined via the QEMU command line by specifying: -device vfio-ap,sysfsdev=<path-to-mediated-matrix-device> There may be only one vfio-ap device configured for a guest. The mediated matrix device is created by the VFIO AP device driver by writing a UUID to a sysfs attribute file (see docs/vfio-ap.txt). The mediated matrix device will be named after the UUID. Symbolic links to the $uuid are created in many places, so the path to the mediated matrix device $uuid can be specified in any of the following ways: /sys/devices/vfio_ap/matrix/$uuid /sys/devices/vfio_ap/matrix/mdev_supported_types/vfio_ap-passthrough/devices/$uuid /sys/bus/mdev/devices/$uuid /sys/bus/mdev/drivers/vfio_mdev/$uuid When the vfio-ap device is realized, it acquires and opens the VFIO iommu group to which the mediated matrix device is bound. This causes a VFIO group notification event to be signaled. The vfio_ap device driver's group notification handler will get called at which time the device driver will configure the the AP devices to which the guest will be granted access. Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com> Tested-by: Pierre Morel <pmorel@linux.ibm.com> Acked-by: Halil Pasic <pasic@linux.ibm.com> Tested-by: Pierre Morel <pmorel@linux.ibm.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Message-Id: <20181010170309.12045-6-akrowiak@linux.ibm.com> Reviewed-by: Thomas Huth <thuth@redhat.com> [CH: added missing g_free and device category] Signed-off-by: Cornelia Huck <cohuck@redhat.com>
2018-10-10 20:03:07 +03:00
VFIO_DEVICE_TYPE_AP = 3,
};
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 VFIOMigration {
struct VFIODevice *vbasedev;
VMChangeStateEntry *vm_state;
VFIORegion region;
uint32_t device_state;
int vm_running;
Notifier migration_state;
vfio: Add save state functions to SaveVMHandlers Added .save_live_pending, .save_live_iterate and .save_live_complete_precopy functions. These functions handles pre-copy and stop-and-copy phase. In _SAVING|_RUNNING device state or pre-copy phase: - read pending_bytes. If pending_bytes > 0, go through below steps. - read data_offset - indicates kernel driver to write data to staging buffer. - read data_size - amount of data in bytes written by vendor driver in migration region. - read data_size bytes of data from data_offset in the migration region. - Write data packet to file stream as below: {VFIO_MIG_FLAG_DEV_DATA_STATE, data_size, actual data, VFIO_MIG_FLAG_END_OF_STATE } In _SAVING device state or stop-and-copy phase a. read config space of device and save to migration file stream. This doesn't need to be from vendor driver. Any other special config state from driver can be saved as data in following iteration. b. read pending_bytes. If pending_bytes > 0, go through below steps. c. read data_offset - indicates kernel driver to write data to staging buffer. d. read data_size - amount of data in bytes written by vendor driver in migration region. e. read data_size bytes of data from data_offset in the migration region. f. Write data packet as below: {VFIO_MIG_FLAG_DEV_DATA_STATE, data_size, actual data} g. iterate through steps b to f while (pending_bytes > 0) h. Write {VFIO_MIG_FLAG_END_OF_STATE} When data region is mapped, its user's responsibility to read data from data_offset of data_size before moving to next steps. Added fix suggested by Artem Polyakov to reset pending_bytes in vfio_save_iterate(). Added fix suggested by Zhi Wang to add 0 as data size in migration stream and add END_OF_STATE delimiter to indicate phase complete. Suggested-by: Artem Polyakov <artemp@nvidia.com> Suggested-by: Zhi Wang <zhi.wang.linux@gmail.com> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com> Reviewed-by: Neo Jia <cjia@nvidia.com> Reviewed-by: Yan Zhao <yan.y.zhao@intel.com> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2020-10-26 12:36:18 +03:00
uint64_t pending_bytes;
} VFIOMigration;
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;
Error *error;
bool initialized;
bool dirty_pages_supported;
uint64_t dirty_pgsizes;
uint64_t max_dirty_bitmap_size;
unsigned long pgsizes;
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;
vfio: Add sysfsdev property for pci & platform vfio-pci currently requires a host= parameter, which comes in the form of a PCI address in [domain:]<bus:slot.function> notation. We expect to find a matching entry in sysfs for that under /sys/bus/pci/devices/. vfio-platform takes a similar approach, but defines the host= parameter to be a string, which can be matched directly under /sys/bus/platform/devices/. On the PCI side, we have some interest in using vfio to expose vGPU devices. These are not actual discrete PCI devices, so they don't have a compatible host PCI bus address or a device link where QEMU wants to look for it. There's also really no requirement that vfio can only be used to expose physical devices, a new vfio bus and iommu driver could expose a completely emulated device. To fit within the vfio framework, it would need a kernel struct device and associated IOMMU group, but those are easy constraints to manage. To support such devices, which would include vGPUs, that honor the VFIO PCI programming API, but are not necessarily backed by a unique PCI address, add support for specifying any device in sysfs. The vfio API already has support for probing the device type to ensure compatibility with either vfio-pci or vfio-platform. With this, a vfio-pci device could either be specified as: -device vfio-pci,host=02:00.0 or -device vfio-pci,sysfsdev=/sys/devices/pci0000:00/0000:00:1c.0/0000:02:00.0 or even -device vfio-pci,sysfsdev=/sys/bus/pci/devices/0000:02:00.0 When vGPU support comes along, this might look something more like: -device vfio-pci,sysfsdev=/sys/devices/virtual/intel-vgpu/vgpu0@0000:00:02.0 NB - This is only a made up example path The same change is made for vfio-platform, specifying sysfsdev has precedence over the old host option. Tested-by: Eric Auger <eric.auger@linaro.org> Reviewed-by: Eric Auger <eric.auger@linaro.org> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2016-03-10 19:39:07 +03:00
char *sysfsdev;
char *name;
DeviceState *dev;
int fd;
int type;
bool reset_works;
bool needs_reset;
bool no_mmap;
bool ram_block_discard_allowed;
VFIODeviceOps *ops;
unsigned int num_irqs;
unsigned int num_regions;
unsigned int flags;
VFIOMigration *migration;
Error *migration_blocker;
} VFIODevice;
struct VFIODeviceOps {
void (*vfio_compute_needs_reset)(VFIODevice *vdev);
int (*vfio_hot_reset_multi)(VFIODevice *vdev);
void (*vfio_eoi)(VFIODevice *vdev);
Object *(*vfio_get_object)(VFIODevice *vdev);
void (*vfio_save_config)(VFIODevice *vdev, QEMUFile *f);
int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f);
};
typedef struct VFIOGroup {
int fd;
int groupid;
VFIOContainer *container;
QLIST_HEAD(, VFIODevice) device_list;
QLIST_ENTRY(VFIOGroup) next;
QLIST_ENTRY(VFIOGroup) container_next;
bool ram_block_discard_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;
RAMFBState *ramfb;
struct vfio_region_info *edid_info;
struct vfio_region_gfx_edid *edid_regs;
uint8_t *edid_blob;
QEMUTimer *edid_link_timer;
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);
int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex,
int action, int fd, Error **errp);
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_unmap(VFIORegion *region);
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;
typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
extern VFIOGroupList vfio_group_list;
bool vfio_mig_active(void);
int64_t vfio_mig_bytes_transferred(void);
#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);
struct vfio_info_cap_header *
vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id);
bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info,
unsigned int *avail);
struct vfio_info_cap_header *
vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id);
#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);
int vfio_migration_probe(VFIODevice *vbasedev, Error **errp);
void vfio_migration_finalize(VFIODevice *vbasedev);
#endif /* HW_VFIO_VFIO_COMMON_H */