diff options
Diffstat (limited to 'include/hw/vfio')
-rw-r--r-- | include/hw/vfio/vfio-common.h | 286 | ||||
-rw-r--r-- | include/hw/vfio/vfio-container-base.h | 143 | ||||
-rw-r--r-- | include/hw/vfio/vfio-container.h | 38 | ||||
-rw-r--r-- | include/hw/vfio/vfio-cpr.h | 57 | ||||
-rw-r--r-- | include/hw/vfio/vfio-device.h | 286 | ||||
-rw-r--r-- | include/hw/vfio/vfio-migration.h | 16 | ||||
-rw-r--r-- | include/hw/vfio/vfio-platform.h | 4 | ||||
-rw-r--r-- | include/hw/vfio/vfio-region.h | 48 |
8 files changed, 568 insertions, 310 deletions
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h deleted file mode 100644 index 4cb1ab8..0000000 --- a/include/hw/vfio/vfio-common.h +++ /dev/null @@ -1,286 +0,0 @@ -/* - * 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" -#include "hw/vfio/vfio-container-base.h" - -#define VFIO_MSG_PREFIX "vfio %s: " - -enum { - VFIO_DEVICE_TYPE_PCI = 0, - VFIO_DEVICE_TYPE_PLATFORM = 1, - VFIO_DEVICE_TYPE_CCW = 2, - 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; - NotifierWithReturn migration_state; - uint32_t device_state; - int data_fd; - void *data_buffer; - size_t data_buffer_size; - uint64_t mig_flags; - uint64_t precopy_init_size; - uint64_t precopy_dirty_size; - bool initial_data_sent; -} VFIOMigration; - -struct VFIOGroup; - -typedef struct VFIOContainer { - VFIOContainerBase bcontainer; - int fd; /* /dev/vfio/vfio, empowered by the attached groups */ - unsigned iommu_type; - QLIST_HEAD(, VFIOGroup) group_list; -} VFIOContainer; - -typedef struct VFIOHostDMAWindow { - hwaddr min_iova; - hwaddr max_iova; - uint64_t iova_pgsizes; - QLIST_ENTRY(VFIOHostDMAWindow) hostwin_next; -} VFIOHostDMAWindow; - -typedef struct IOMMUFDBackend IOMMUFDBackend; - -typedef struct VFIOIOMMUFDContainer { - VFIOContainerBase bcontainer; - IOMMUFDBackend *be; - uint32_t ioas_id; -} VFIOIOMMUFDContainer; - -typedef struct VFIODeviceOps VFIODeviceOps; - -typedef struct VFIODevice { - QLIST_ENTRY(VFIODevice) next; - QLIST_ENTRY(VFIODevice) container_next; - QLIST_ENTRY(VFIODevice) global_next; - struct VFIOGroup *group; - VFIOContainerBase *bcontainer; - char *sysfsdev; - char *name; - DeviceState *dev; - int fd; - int type; - bool reset_works; - bool needs_reset; - bool no_mmap; - bool ram_block_discard_allowed; - OnOffAuto enable_migration; - bool migration_events; - VFIODeviceOps *ops; - unsigned int num_irqs; - unsigned int num_regions; - unsigned int flags; - VFIOMigration *migration; - Error *migration_blocker; - OnOffAuto pre_copy_dirty_page_tracking; - bool dirty_pages_supported; - bool dirty_tracking; - int devid; - IOMMUFDBackend *iommufd; -} 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); - - /** - * @vfio_save_config - * - * Save device config state - * - * @vdev: #VFIODevice for which to save the config - * @f: #QEMUFile where to send the data - * @errp: pointer to Error*, to store an error if it happens. - * - * Returns zero to indicate success and negative for error - */ - int (*vfio_save_config)(VFIODevice *vdev, QEMUFile *f, Error **errp); - - /** - * @vfio_load_config - * - * Load device config state - * - * @vdev: #VFIODevice for which to load the config - * @f: #QEMUFile where to get the data - * - * Returns zero to indicate success and negative for error - */ - 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; - -VFIOAddressSpace *vfio_get_address_space(AddressSpace *as); -void vfio_put_address_space(VFIOAddressSpace *space); - -/* SPAPR specific */ -int vfio_spapr_container_init(VFIOContainer *container, Error **errp); -void vfio_spapr_container_deinit(VFIOContainer *container); - -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); -bool 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); -struct vfio_device_info *vfio_get_device_info(int fd); -bool vfio_attach_device(char *name, VFIODevice *vbasedev, - AddressSpace *as, Error **errp); -void vfio_detach_device(VFIODevice *vbasedev); - -int vfio_kvm_device_add_fd(int fd, Error **errp); -int vfio_kvm_device_del_fd(int fd, Error **errp); - -bool vfio_cpr_register_container(VFIOContainerBase *bcontainer, Error **errp); -void vfio_cpr_unregister_container(VFIOContainerBase *bcontainer); - -extern const MemoryRegionOps vfio_region_ops; -typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; -typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; -extern VFIOGroupList vfio_group_list; -extern VFIODeviceList vfio_device_list; -extern const MemoryListener vfio_memory_listener; -extern int vfio_kvm_device_fd; - -bool vfio_mig_active(void); -int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp); -void vfio_unblock_multiple_devices_migration(void); -bool vfio_viommu_preset(VFIODevice *vbasedev); -int64_t vfio_mig_bytes_transferred(void); -void vfio_reset_bytes_transferred(void); -bool vfio_device_state_is_running(VFIODevice *vbasedev); -bool vfio_device_state_is_precopy(VFIODevice *vbasedev); - -#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); -struct vfio_info_cap_header * -vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id); -#endif - -bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp); -void vfio_migration_exit(VFIODevice *vbasedev); - -int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); -bool -vfio_devices_all_running_and_mig_active(const VFIOContainerBase *bcontainer); -bool -vfio_devices_all_device_dirty_tracking(const VFIOContainerBase *bcontainer); -int vfio_devices_query_dirty_bitmap(const VFIOContainerBase *bcontainer, - VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); -int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova, - uint64_t size, ram_addr_t ram_addr, Error **errp); - -/* Returns 0 on success, or a negative errno. */ -bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp); -void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp); -void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops, - DeviceState *dev, bool ram_discard); -#endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h index 2776481..3cd86ec 100644 --- a/include/hw/vfio/vfio-container-base.h +++ b/include/hw/vfio/vfio-container-base.h @@ -13,7 +13,7 @@ #ifndef HW_VFIO_VFIO_CONTAINER_BASE_H #define HW_VFIO_VFIO_CONTAINER_BASE_H -#include "exec/memory.h" +#include "system/memory.h" typedef struct VFIODevice VFIODevice; typedef struct VFIOIOMMUClass VFIOIOMMUClass; @@ -34,7 +34,7 @@ typedef struct VFIOAddressSpace { * This is the base object for vfio container backends */ typedef struct VFIOContainerBase { - const VFIOIOMMUClass *ops; + Object parent; VFIOAddressSpace *space; MemoryListener listener; Error *error; @@ -44,6 +44,7 @@ typedef struct VFIOContainerBase { unsigned long pgsizes; unsigned int dma_max_mappings; bool dirty_pages_supported; + bool dirty_pages_started; /* Protected by BQL */ QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainerBase) next; @@ -70,12 +71,17 @@ typedef struct VFIORamDiscardListener { QLIST_ENTRY(VFIORamDiscardListener) next; } VFIORamDiscardListener; +VFIOAddressSpace *vfio_address_space_get(AddressSpace *as); +void vfio_address_space_put(VFIOAddressSpace *space); +void vfio_address_space_insert(VFIOAddressSpace *space, + VFIOContainerBase *bcontainer); + int vfio_container_dma_map(VFIOContainerBase *bcontainer, hwaddr iova, ram_addr_t size, - void *vaddr, bool readonly); + void *vaddr, bool readonly, MemoryRegion *mr); int vfio_container_dma_unmap(VFIOContainerBase *bcontainer, hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb); + IOMMUTLBEntry *iotlb, bool unmap_all); bool vfio_container_add_section_window(VFIOContainerBase *bcontainer, MemoryRegionSection *section, Error **errp); @@ -83,42 +89,126 @@ void vfio_container_del_section_window(VFIOContainerBase *bcontainer, MemoryRegionSection *section); int vfio_container_set_dirty_page_tracking(VFIOContainerBase *bcontainer, bool start, Error **errp); +bool vfio_container_dirty_tracking_is_started( + const VFIOContainerBase *bcontainer); +bool vfio_container_devices_dirty_tracking_is_supported( + const VFIOContainerBase *bcontainer); int vfio_container_query_dirty_bitmap(const VFIOContainerBase *bcontainer, - VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); + uint64_t iova, uint64_t size, ram_addr_t ram_addr, Error **errp); -void vfio_container_init(VFIOContainerBase *bcontainer, - VFIOAddressSpace *space, - const VFIOIOMMUClass *ops); -void vfio_container_destroy(VFIOContainerBase *bcontainer); +GList *vfio_container_get_iova_ranges(const VFIOContainerBase *bcontainer); +static inline uint64_t +vfio_container_get_page_size_mask(const VFIOContainerBase *bcontainer) +{ + assert(bcontainer); + return bcontainer->pgsizes; +} #define TYPE_VFIO_IOMMU "vfio-iommu" #define TYPE_VFIO_IOMMU_LEGACY TYPE_VFIO_IOMMU "-legacy" #define TYPE_VFIO_IOMMU_SPAPR TYPE_VFIO_IOMMU "-spapr" #define TYPE_VFIO_IOMMU_IOMMUFD TYPE_VFIO_IOMMU "-iommufd" +#define TYPE_VFIO_IOMMU_USER TYPE_VFIO_IOMMU "-user" -/* - * VFIOContainerBase is not an abstract QOM object because it felt - * unnecessary to expose all the IOMMU backends to the QEMU machine - * and human interface. However, we can still abstract the IOMMU - * backend handlers using a QOM interface class. This provides more - * flexibility when referencing the various implementations. - */ -DECLARE_CLASS_CHECKERS(VFIOIOMMUClass, VFIO_IOMMU, TYPE_VFIO_IOMMU) +OBJECT_DECLARE_TYPE(VFIOContainerBase, VFIOIOMMUClass, VFIO_IOMMU) struct VFIOIOMMUClass { - InterfaceClass parent_class; + ObjectClass parent_class; - /* basic feature */ + /** + * @setup + * + * Perform basic setup of the container, including configuring IOMMU + * capabilities, IOVA ranges, supported page sizes, etc. + * + * @bcontainer: #VFIOContainerBase + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns true to indicate success and false for error. + */ bool (*setup)(VFIOContainerBase *bcontainer, Error **errp); + + /** + * @listener_begin + * + * Called at the beginning of an address space update transaction. + * See #MemoryListener. + * + * @bcontainer: #VFIOContainerBase + */ + void (*listener_begin)(VFIOContainerBase *bcontainer); + + /** + * @listener_commit + * + * Called at the end of an address space update transaction, + * See #MemoryListener. + * + * @bcontainer: #VFIOContainerBase + */ + void (*listener_commit)(VFIOContainerBase *bcontainer); + + /** + * @dma_map + * + * Map an address range into the container. Note that the memory region is + * referenced within an RCU read lock region across this call. + * + * @bcontainer: #VFIOContainerBase to use + * @iova: start address to map + * @size: size of the range to map + * @vaddr: process virtual address of mapping + * @readonly: true if mapping should be readonly + * @mr: the memory region for this mapping + * + * Returns 0 to indicate success and -errno otherwise. + */ int (*dma_map)(const VFIOContainerBase *bcontainer, hwaddr iova, ram_addr_t size, - void *vaddr, bool readonly); + void *vaddr, bool readonly, MemoryRegion *mr); + /** + * @dma_unmap + * + * Unmap an address range from the container. + * + * @bcontainer: #VFIOContainerBase to use for unmap + * @iova: start address to unmap + * @size: size of the range to unmap + * @iotlb: The IOMMU TLB mapping entry (or NULL) + * @unmap_all: if set, unmap the entire address space + * + * Returns 0 to indicate success and -errno otherwise. + */ int (*dma_unmap)(const VFIOContainerBase *bcontainer, hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb); + IOMMUTLBEntry *iotlb, bool unmap_all); + + + /** + * @attach_device + * + * Associate the given device with a container and do some related + * initialization of the device context. + * + * @name: name of the device + * @vbasedev: the device + * @as: address space to use + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns true to indicate success and false for error. + */ bool (*attach_device)(const char *name, VFIODevice *vbasedev, AddressSpace *as, Error **errp); + + /* + * @detach_device + * + * Detach the given device from its container and clean up any necessary + * state. + * + * @vbasedev: the device to disassociate + */ void (*detach_device)(VFIODevice *vbasedev); /* migration feature */ @@ -133,7 +223,7 @@ struct VFIOIOMMUClass { * @start: indicates whether to start or stop dirty pages tracking * @errp: pointer to Error*, to store an error if it happens. * - * Returns zero to indicate success and negative for error + * Returns zero to indicate success and negative for error. */ int (*set_dirty_page_tracking)(const VFIOContainerBase *bcontainer, bool start, Error **errp); @@ -148,7 +238,7 @@ struct VFIOIOMMUClass { * @size: size of iova range * @errp: pointer to Error*, to store an error if it happens. * - * Returns zero to indicate success and negative for error + * Returns zero to indicate success and negative for error. */ int (*query_dirty_bitmap)(const VFIOContainerBase *bcontainer, VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); @@ -163,4 +253,11 @@ struct VFIOIOMMUClass { MemoryRegionSection *section); void (*release)(VFIOContainerBase *bcontainer); }; + +VFIORamDiscardListener *vfio_find_ram_discard_listener( + VFIOContainerBase *bcontainer, MemoryRegionSection *section); + +void vfio_container_region_add(VFIOContainerBase *bcontainer, + MemoryRegionSection *section, bool cpr_remap); + #endif /* HW_VFIO_VFIO_CONTAINER_BASE_H */ diff --git a/include/hw/vfio/vfio-container.h b/include/hw/vfio/vfio-container.h new file mode 100644 index 0000000..21e5807 --- /dev/null +++ b/include/hw/vfio/vfio-container.h @@ -0,0 +1,38 @@ +/* + * VFIO container + * + * Copyright Red Hat, Inc. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_CONTAINER_H +#define HW_VFIO_CONTAINER_H + +#include "hw/vfio/vfio-container-base.h" +#include "hw/vfio/vfio-cpr.h" + +typedef struct VFIOContainer VFIOContainer; +typedef struct VFIODevice VFIODevice; + +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 VFIOContainer { + VFIOContainerBase bcontainer; + int fd; /* /dev/vfio/vfio, empowered by the attached groups */ + unsigned iommu_type; + QLIST_HEAD(, VFIOGroup) group_list; + VFIOContainerCPR cpr; +} VFIOContainer; + +OBJECT_DECLARE_SIMPLE_TYPE(VFIOContainer, VFIO_IOMMU_LEGACY); + +#endif /* HW_VFIO_CONTAINER_H */ diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h new file mode 100644 index 0000000..8bf85b9 --- /dev/null +++ b/include/hw/vfio/vfio-cpr.h @@ -0,0 +1,57 @@ +/* + * VFIO CPR + * + * Copyright (c) 2025 Oracle and/or its affiliates. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_VFIO_CPR_H +#define HW_VFIO_VFIO_CPR_H + +#include "migration/misc.h" +#include "system/memory.h" + +struct VFIOContainer; +struct VFIOContainerBase; +struct VFIOGroup; + +typedef struct VFIOContainerCPR { + Error *blocker; + bool vaddr_unmapped; + NotifierWithReturn transfer_notifier; + MemoryListener remap_listener; + int (*saved_dma_map)(const struct VFIOContainerBase *bcontainer, + hwaddr iova, ram_addr_t size, + void *vaddr, bool readonly, MemoryRegion *mr); +} VFIOContainerCPR; + +typedef struct VFIODeviceCPR { + Error *mdev_blocker; +} VFIODeviceCPR; + +bool vfio_legacy_cpr_register_container(struct VFIOContainer *container, + Error **errp); +void vfio_legacy_cpr_unregister_container(struct VFIOContainer *container); + +int vfio_cpr_reboot_notifier(NotifierWithReturn *notifier, MigrationEvent *e, + Error **errp); + +bool vfio_cpr_register_container(struct VFIOContainerBase *bcontainer, + Error **errp); +void vfio_cpr_unregister_container(struct VFIOContainerBase *bcontainer); + +int vfio_cpr_group_get_device_fd(int d, const char *name); + +bool vfio_cpr_container_match(struct VFIOContainer *container, + struct VFIOGroup *group, int fd); + +void vfio_cpr_giommu_remap(struct VFIOContainerBase *bcontainer, + MemoryRegionSection *section); + +bool vfio_cpr_ram_discard_register_listener( + struct VFIOContainerBase *bcontainer, MemoryRegionSection *section); + +extern const VMStateDescription vfio_cpr_pci_vmstate; + +#endif /* HW_VFIO_VFIO_CPR_H */ diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h new file mode 100644 index 0000000..c616652 --- /dev/null +++ b/include/hw/vfio/vfio-device.h @@ -0,0 +1,286 @@ +/* + * VFIO Device interface + * + * 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 "system/memory.h" +#include "qemu/queue.h" +#ifdef CONFIG_LINUX +#include <linux/vfio.h> +#endif +#include "system/system.h" +#include "hw/vfio/vfio-container-base.h" +#include "hw/vfio/vfio-cpr.h" +#include "system/host_iommu_device.h" +#include "system/iommufd.h" + +#define VFIO_MSG_PREFIX "vfio %s: " + +enum { + VFIO_DEVICE_TYPE_PCI = 0, + VFIO_DEVICE_TYPE_PLATFORM = 1, + VFIO_DEVICE_TYPE_CCW = 2, + VFIO_DEVICE_TYPE_AP = 3, +}; + +typedef struct VFIODeviceOps VFIODeviceOps; +typedef struct VFIODeviceIOOps VFIODeviceIOOps; +typedef struct VFIOMigration VFIOMigration; + +typedef struct IOMMUFDBackend IOMMUFDBackend; +typedef struct VFIOIOASHwpt VFIOIOASHwpt; +typedef struct VFIOUserProxy VFIOUserProxy; + +typedef struct VFIODevice { + QLIST_ENTRY(VFIODevice) next; + QLIST_ENTRY(VFIODevice) container_next; + QLIST_ENTRY(VFIODevice) global_next; + struct VFIOGroup *group; + VFIOContainerBase *bcontainer; + char *sysfsdev; + char *name; + DeviceState *dev; + int fd; + int type; + bool mdev; + bool reset_works; + bool needs_reset; + bool no_mmap; + bool ram_block_discard_allowed; + OnOffAuto enable_migration; + OnOffAuto migration_multifd_transfer; + bool migration_events; + bool use_region_fds; + VFIODeviceOps *ops; + VFIODeviceIOOps *io_ops; + unsigned int num_irqs; + unsigned int num_regions; + unsigned int flags; + VFIOMigration *migration; + Error *migration_blocker; + OnOffAuto pre_copy_dirty_page_tracking; + OnOffAuto device_dirty_page_tracking; + bool dirty_pages_supported; + bool dirty_tracking; /* Protected by BQL */ + bool iommu_dirty_tracking; + HostIOMMUDevice *hiod; + int devid; + IOMMUFDBackend *iommufd; + VFIOIOASHwpt *hwpt; + QLIST_ENTRY(VFIODevice) hwpt_next; + struct vfio_region_info **reginfo; + int *region_fds; + VFIODeviceCPR cpr; + VFIOUserProxy *proxy; +} 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); + + /** + * @vfio_save_config + * + * Save device config state + * + * @vdev: #VFIODevice for which to save the config + * @f: #QEMUFile where to send the data + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns zero to indicate success and negative for error + */ + int (*vfio_save_config)(VFIODevice *vdev, QEMUFile *f, Error **errp); + + /** + * @vfio_load_config + * + * Load device config state + * + * @vdev: #VFIODevice for which to load the config + * @f: #QEMUFile where to get the data + * + * Returns zero to indicate success and negative for error + */ + int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f); +}; + +/* + * Given a return value of either a short number of bytes read or -errno, + * construct a meaningful error message. + */ +#define strreaderror(ret) \ + (ret < 0 ? strerror(-ret) : "short read") + +/* + * Given a return value of either a short number of bytes written or -errno, + * construct a meaningful error message. + */ +#define strwriteerror(ret) \ + (ret < 0 ? strerror(-ret) : "short write") + +void vfio_device_irq_disable(VFIODevice *vbasedev, int index); +void vfio_device_irq_unmask(VFIODevice *vbasedev, int index); +void vfio_device_irq_mask(VFIODevice *vbasedev, int index); +bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex, + int action, int fd, Error **errp); + +void vfio_device_reset_handler(void *opaque); +bool vfio_device_is_mdev(VFIODevice *vbasedev); +bool vfio_device_hiod_create_and_realize(VFIODevice *vbasedev, + const char *typename, Error **errp); +bool vfio_device_attach(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp); +bool vfio_device_attach_by_iommu_type(const char *iommu_type, char *name, + VFIODevice *vbasedev, AddressSpace *as, + Error **errp); +void vfio_device_detach(VFIODevice *vbasedev); +VFIODevice *vfio_get_vfio_device(Object *obj); + +typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; +extern VFIODeviceList vfio_device_list; + +#ifdef CONFIG_LINUX +/* + * How devices communicate with the server. The default option is through + * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote + * process. + */ +struct VFIODeviceIOOps { + /** + * @device_feature + * + * Fill in feature info for the given device. + * + * @vdev: #VFIODevice to use + * @feat: feature information to fill in + * + * Returns 0 on success or -errno. + */ + int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *feat); + + /** + * @get_region_info + * + * Get the information for a given region on the device. + * + * @vdev: #VFIODevice to use + * @info: set @info->index to the region index to look up; the rest of the + * struct will be filled in on success + * @fd: pointer to the fd for the region; will be -1 if not found + * + * Returns 0 on success or -errno. + */ + int (*get_region_info)(VFIODevice *vdev, + struct vfio_region_info *info, int *fd); + + /** + * @get_irq_info + * + * @vdev: #VFIODevice to use + * @irq: set @irq->index to the IRQ index to look up; the rest of the struct + * will be filled in on success + * + * Returns 0 on success or -errno. + */ + int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq); + + /** + * @set_irqs + * + * Configure IRQs. + * + * @vdev: #VFIODevice to use + * @irqs: IRQ configuration as defined by VFIO docs. + * + * Returns 0 on success or -errno. + */ + int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs); + + /** + * @region_read + * + * Read part of a region. + * + * @vdev: #VFIODevice to use + * @nr: region index + * @off: offset within the region + * @size: size in bytes to read + * @data: buffer to read into + * + * Returns number of bytes read on success or -errno. + */ + int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size, + void *data); + + /** + * @region_write + * + * Write part of a region. + * + * @vdev: #VFIODevice to use + * @nr: region index + * @off: offset within the region + * @size: size in bytes to write + * @data: buffer to write from + * @post: true if this is a posted write + * + * Returns number of bytes write on success or -errno. + */ + int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size, + void *data, bool post); +}; + +void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainerBase *bcontainer, + struct vfio_device_info *info); + +void vfio_device_unprepare(VFIODevice *vbasedev); + +int vfio_device_get_region_info(VFIODevice *vbasedev, int index, + struct vfio_region_info **info); +int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type, + uint32_t subtype, struct vfio_region_info **info); + +/** + * Return the fd for mapping this region. This is either the device's fd (for + * e.g. kernel vfio), or a per-region fd (for vfio-user). + * + * @vbasedev: #VFIODevice to use + * @index: region index + * + * Returns the fd. + */ +int vfio_device_get_region_fd(VFIODevice *vbasedev, int index); + +bool vfio_device_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type); + +int vfio_device_get_irq_info(VFIODevice *vbasedev, int index, + struct vfio_irq_info *info); +#endif + +/* Returns 0 on success, or a negative errno. */ +bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp); +void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp); +void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops, + DeviceState *dev, bool ram_discard); +int vfio_device_get_aw_bits(VFIODevice *vdev); +#endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/include/hw/vfio/vfio-migration.h b/include/hw/vfio/vfio-migration.h new file mode 100644 index 0000000..0d4ecd3 --- /dev/null +++ b/include/hw/vfio/vfio-migration.h @@ -0,0 +1,16 @@ +/* + * VFIO migration interface + * + * Copyright Red Hat, Inc. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_VFIO_MIGRATION_H +#define HW_VFIO_VFIO_MIGRATION_H + +bool vfio_migration_active(void); +int64_t vfio_migration_bytes_transferred(void); +void vfio_migration_reset_bytes_transferred(void); + +#endif /* HW_VFIO_VFIO_MIGRATION_H */ diff --git a/include/hw/vfio/vfio-platform.h b/include/hw/vfio/vfio-platform.h index c414c3d..256d850 100644 --- a/include/hw/vfio/vfio-platform.h +++ b/include/hw/vfio/vfio-platform.h @@ -17,7 +17,7 @@ #define HW_VFIO_VFIO_PLATFORM_H #include "hw/sysbus.h" -#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio-device.h" #include "qemu/event_notifier.h" #include "qemu/queue.h" #include "qom/object.h" @@ -47,6 +47,8 @@ typedef struct VFIOINTp { /* function type for user side eventfd handler */ typedef void (*eventfd_user_side_handler_t)(VFIOINTp *intp); +typedef struct VFIORegion VFIORegion; + struct VFIOPlatformDevice { SysBusDevice sbdev; VFIODevice vbasedev; /* not a QOM object */ diff --git a/include/hw/vfio/vfio-region.h b/include/hw/vfio/vfio-region.h new file mode 100644 index 0000000..ede6e0c --- /dev/null +++ b/include/hw/vfio/vfio-region.h @@ -0,0 +1,48 @@ +/* + * VFIO region + * + * Copyright Red Hat, Inc. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_REGION_H +#define HW_VFIO_REGION_H + +#include "system/memory.h" + +typedef struct VFIOMmap { + MemoryRegion mem; + void *mmap; + off_t offset; + size_t size; +} VFIOMmap; + +typedef struct VFIODevice VFIODevice; + +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 */ + bool post_wr; /* writes can be posted */ +} VFIORegion; + + +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); + +#endif /* HW_VFIO_REGION_H */ |