diff options
Diffstat (limited to 'hw/vfio/common.c')
| -rw-r--r-- | hw/vfio/common.c | 1847 |
1 files changed, 119 insertions, 1728 deletions
diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 134649226d..5ff5acf1d8 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -46,8 +46,8 @@ #include "migration/qemu-file.h" #include "sysemu/tpm.h" -VFIOGroupList vfio_group_list = - QLIST_HEAD_INITIALIZER(vfio_group_list); +VFIODeviceList vfio_device_list = + QLIST_HEAD_INITIALIZER(vfio_device_list); static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces = QLIST_HEAD_INITIALIZER(vfio_address_spaces); @@ -59,304 +59,24 @@ static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces = * initialized, this file descriptor is only released on QEMU exit and * we'll re-use it should another vfio device be attached before then. */ -static int vfio_kvm_device_fd = -1; +int vfio_kvm_device_fd = -1; #endif /* - * Common VFIO interrupt disable - */ -void vfio_disable_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, - .index = index, - .start = 0, - .count = 0, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, - .index = index, - .start = 0, - .count = 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, - .index = index, - .start = 0, - .count = 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -static inline const char *action_to_str(int action) -{ - switch (action) { - case VFIO_IRQ_SET_ACTION_MASK: - return "MASK"; - case VFIO_IRQ_SET_ACTION_UNMASK: - return "UNMASK"; - case VFIO_IRQ_SET_ACTION_TRIGGER: - return "TRIGGER"; - default: - return "UNKNOWN ACTION"; - } -} - -static const char *index_to_str(VFIODevice *vbasedev, int index) -{ - if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { - return NULL; - } - - switch (index) { - case VFIO_PCI_INTX_IRQ_INDEX: - return "INTX"; - case VFIO_PCI_MSI_IRQ_INDEX: - return "MSI"; - case VFIO_PCI_MSIX_IRQ_INDEX: - return "MSIX"; - case VFIO_PCI_ERR_IRQ_INDEX: - return "ERR"; - case VFIO_PCI_REQ_IRQ_INDEX: - return "REQ"; - default: - return NULL; - } -} - -static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state) -{ - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - /* - * We support coordinated discarding of RAM via the RamDiscardManager. - */ - return ram_block_uncoordinated_discard_disable(state); - default: - /* - * VFIO_SPAPR_TCE_IOMMU most probably works just fine with - * RamDiscardManager, however, it is completely untested. - * - * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does - * completely the opposite of managing mapping/pinning dynamically as - * required by RamDiscardManager. We would have to special-case sections - * with a RamDiscardManager. - */ - return ram_block_discard_disable(state); - } -} - -int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, - int action, int fd, Error **errp) -{ - struct vfio_irq_set *irq_set; - int argsz, ret = 0; - const char *name; - int32_t *pfd; - - argsz = sizeof(*irq_set) + sizeof(*pfd); - - irq_set = g_malloc0(argsz); - irq_set->argsz = argsz; - irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | action; - irq_set->index = index; - irq_set->start = subindex; - irq_set->count = 1; - pfd = (int32_t *)&irq_set->data; - *pfd = fd; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { - ret = -errno; - } - g_free(irq_set); - - if (!ret) { - return 0; - } - - error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); - - name = index_to_str(vbasedev, index); - if (name) { - error_prepend(errp, "%s-%d: ", name, subindex); - } else { - error_prepend(errp, "index %d-%d: ", index, subindex); - } - error_prepend(errp, - "Failed to %s %s eventfd signaling for interrupt ", - fd < 0 ? "tear down" : "set up", action_to_str(action)); - return ret; -} - -/* - * IO Port/MMIO - Beware of the endians, VFIO is always little endian - */ -void vfio_region_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size) -{ - VFIORegion *region = opaque; - VFIODevice *vbasedev = region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - - switch (size) { - case 1: - buf.byte = data; - break; - case 2: - buf.word = cpu_to_le16(data); - break; - case 4: - buf.dword = cpu_to_le32(data); - break; - case 8: - buf.qword = cpu_to_le64(data); - break; - default: - hw_error("vfio: unsupported write size, %u bytes", size); - break; - } - - if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 - ",%d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, data, size); - } - - trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); - - /* - * A read or write to a BAR always signals an INTx EOI. This will - * do nothing if not pending (including not in INTx mode). We assume - * that a BAR access is in response to an interrupt and that BAR - * accesses will service the interrupt. Unfortunately, we don't know - * which access will service the interrupt, so we're potentially - * getting quite a few host interrupts per guest interrupt. - */ - vbasedev->ops->vfio_eoi(vbasedev); -} - -uint64_t vfio_region_read(void *opaque, - hwaddr addr, unsigned size) -{ - VFIORegion *region = opaque; - VFIODevice *vbasedev = region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - uint64_t data = 0; - - if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, size); - return (uint64_t)-1; - } - switch (size) { - case 1: - data = buf.byte; - break; - case 2: - data = le16_to_cpu(buf.word); - break; - case 4: - data = le32_to_cpu(buf.dword); - break; - case 8: - data = le64_to_cpu(buf.qword); - break; - default: - hw_error("vfio: unsupported read size, %u bytes", size); - break; - } - - trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); - - /* Same as write above */ - vbasedev->ops->vfio_eoi(vbasedev); - - return data; -} - -const MemoryRegionOps vfio_region_ops = { - .read = vfio_region_read, - .write = vfio_region_write, - .endianness = DEVICE_LITTLE_ENDIAN, - .valid = { - .min_access_size = 1, - .max_access_size = 8, - }, - .impl = { - .min_access_size = 1, - .max_access_size = 8, - }, -}; - -/* * Device state interfaces */ -typedef struct { - unsigned long *bitmap; - hwaddr size; - hwaddr pages; -} VFIOBitmap; - -static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) -{ - vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size(); - vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / - BITS_PER_BYTE; - vbmap->bitmap = g_try_malloc0(vbmap->size); - if (!vbmap->bitmap) { - return -ENOMEM; - } - - return 0; -} - -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr); - bool vfio_mig_active(void) { - VFIOGroup *group; VFIODevice *vbasedev; - if (QLIST_EMPTY(&vfio_group_list)) { + if (QLIST_EMPTY(&vfio_device_list)) { return false; } - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration_blocker) { - return false; - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration_blocker) { + return false; } } return true; @@ -371,19 +91,16 @@ static Error *multiple_devices_migration_blocker; */ static bool vfio_multiple_devices_migration_is_supported(void) { - VFIOGroup *group; VFIODevice *vbasedev; unsigned int device_num = 0; bool all_support_p2p = true; - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration) { - device_num++; + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration) { + device_num++; - if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { - all_support_p2p = false; - } + if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { + all_support_p2p = false; } } } @@ -435,7 +152,7 @@ void vfio_unblock_multiple_devices_migration(void) bool vfio_viommu_preset(VFIODevice *vbasedev) { - return vbasedev->group->container->space->as != &address_space_memory; + return vbasedev->container->space->as != &address_space_memory; } static void vfio_set_migration_error(int err) @@ -469,7 +186,6 @@ bool vfio_device_state_is_precopy(VFIODevice *vbasedev) static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; MigrationState *ms = migrate_get_current(); @@ -478,34 +194,29 @@ static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) return false; } - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration = vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration = vbasedev->migration; - if (!migration) { - return false; - } + if (!migration) { + return false; + } - if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF && - (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev))) { - return false; - } + if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF && + (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev))) { + return false; } } return true; } -static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_pages_supported) { - return false; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_pages_supported) { + return false; } } @@ -516,178 +227,33 @@ static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) * Check if all VFIO devices are running and migration is active, which is * essentially equivalent to the migration being in pre-copy phase. */ -static bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; if (!migration_is_active(migrate_get_current())) { return false; } - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration = vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration = vbasedev->migration; - if (!migration) { - return false; - } - - if (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev)) { - continue; - } else { - return false; - } + if (!migration) { + return false; } - } - return true; -} - -static int vfio_dma_unmap_bitmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap *unmap; - struct vfio_bitmap *bitmap; - VFIOBitmap vbmap; - int ret; - - ret = vfio_bitmap_alloc(&vbmap, size); - if (ret) { - return ret; - } - - unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); - - unmap->argsz = sizeof(*unmap) + sizeof(*bitmap); - unmap->iova = iova; - unmap->size = size; - unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; - bitmap = (struct vfio_bitmap *)&unmap->data; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize - * to qemu_real_host_page_size. - */ - bitmap->pgsize = qemu_real_host_page_size(); - bitmap->size = vbmap.size; - bitmap->data = (__u64 *)vbmap.bitmap; - - if (vbmap.size > container->max_dirty_bitmap_size) { - error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size); - ret = -E2BIG; - goto unmap_exit; - } - - ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); - if (!ret) { - cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, - iotlb->translated_addr, vbmap.pages); - } else { - error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); - } - -unmap_exit: - g_free(unmap); - g_free(vbmap.bitmap); - - return ret; -} -/* - * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 - */ -static int vfio_dma_unmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap unmap = { - .argsz = sizeof(unmap), - .flags = 0, - .iova = iova, - .size = size, - }; - bool need_dirty_sync = false; - int ret; - - if (iotlb && vfio_devices_all_running_and_mig_active(container)) { - if (!vfio_devices_all_device_dirty_tracking(container) && - container->dirty_pages_supported) { - return vfio_dma_unmap_bitmap(container, iova, size, iotlb); - } - - need_dirty_sync = true; - } - - while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - /* - * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c - * v4.15) where an overflow in its wrap-around check prevents us from - * unmapping the last page of the address space. Test for the error - * condition and re-try the unmap excluding the last page. The - * expectation is that we've never mapped the last page anyway and this - * unmap request comes via vIOMMU support which also makes it unlikely - * that this page is used. This bug was introduced well after type1 v2 - * support was introduced, so we shouldn't need to test for v1. A fix - * is queued for kernel v5.0 so this workaround can be removed once - * affected kernels are sufficiently deprecated. - */ - if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) && - container->iommu_type == VFIO_TYPE1v2_IOMMU) { - trace_vfio_dma_unmap_overflow_workaround(); - unmap.size -= 1ULL << ctz64(container->pgsizes); + if (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev)) { continue; - } - error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); - return -errno; - } - - if (need_dirty_sync) { - ret = vfio_get_dirty_bitmap(container, iova, size, - iotlb->translated_addr); - if (ret) { - return ret; + } else { + return false; } } - - return 0; -} - -static int vfio_dma_map(VFIOContainer *container, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) -{ - struct vfio_iommu_type1_dma_map map = { - .argsz = sizeof(map), - .flags = VFIO_DMA_MAP_FLAG_READ, - .vaddr = (__u64)(uintptr_t)vaddr, - .iova = iova, - .size = size, - }; - - if (!readonly) { - map.flags |= VFIO_DMA_MAP_FLAG_WRITE; - } - - /* - * Try the mapping, if it fails with EBUSY, unmap the region and try - * again. This shouldn't be necessary, but we sometimes see it in - * the VGA ROM space. - */ - if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || - (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 && - ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { - return 0; - } - - error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); - return -errno; + return true; } -static void vfio_host_win_add(VFIOContainer *container, - hwaddr min_iova, hwaddr max_iova, - uint64_t iova_pgsizes) +void vfio_host_win_add(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova, uint64_t iova_pgsizes) { VFIOHostDMAWindow *hostwin; @@ -708,8 +274,8 @@ static void vfio_host_win_add(VFIOContainer *container, QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next); } -static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, - hwaddr max_iova) +int vfio_host_win_del(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova) { VFIOHostDMAWindow *hostwin; @@ -1084,62 +650,8 @@ static void vfio_listener_region_add(MemoryListener *listener, return; } - if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - hwaddr pgsize = 0; - - /* For now intersections are not allowed, we may relax this later */ - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (ranges_overlap(hostwin->min_iova, - hostwin->max_iova - hostwin->min_iova + 1, - section->offset_within_address_space, - int128_get64(section->size))) { - error_setg(&err, - "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" - "host DMA window [0x%"PRIx64",0x%"PRIx64"]", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, - hostwin->min_iova, hostwin->max_iova); - goto fail; - } - } - - ret = vfio_spapr_create_window(container, section, &pgsize); - if (ret) { - error_setg_errno(&err, -ret, "Failed to create SPAPR window"); - goto fail; - } - - vfio_host_win_add(container, section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, pgsize); -#ifdef CONFIG_KVM - if (kvm_enabled()) { - VFIOGroup *group; - IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); - struct kvm_vfio_spapr_tce param; - struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, - .addr = (uint64_t)(unsigned long)¶m, - }; - - if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_FD, - ¶m.tablefd)) { - QLIST_FOREACH(group, &container->group_list, container_next) { - param.groupfd = group->fd; - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("vfio: failed to setup fd %d " - "for a group with fd %d: %s", - param.tablefd, param.groupfd, - strerror(errno)); - return; - } - trace_vfio_spapr_group_attach(param.groupfd, param.tablefd); - } - } - } -#endif + if (vfio_container_add_section_window(container, section, &err)) { + goto fail; } hostwin = vfio_find_hostwin(container, iova, end); @@ -1251,7 +763,7 @@ static void vfio_listener_region_add(MemoryListener *listener, fail: if (memory_region_is_ram_device(section->mr)) { - error_report("failed to vfio_dma_map. pci p2p may not work"); + error_reportf_err(err, "PCI p2p may not work: "); return; } /* @@ -1356,44 +868,7 @@ static void vfio_listener_region_del(MemoryListener *listener, memory_region_unref(section->mr); - if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - vfio_spapr_remove_window(container, - section->offset_within_address_space); - if (vfio_host_win_del(container, - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1) < 0) { - hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, - __func__, section->offset_within_address_space); - } - } -} - -static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) -{ - int ret; - struct vfio_iommu_type1_dirty_bitmap dirty = { - .argsz = sizeof(dirty), - }; - - if (!container->dirty_pages_supported) { - return 0; - } - - if (start) { - dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_START; - } else { - dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; - } - - ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); - if (ret) { - ret = -errno; - error_report("Failed to set dirty tracking flag 0x%x errno: %d", - dirty.flags, errno); - } - - return ret; + vfio_container_del_section_window(container, section); } typedef struct VFIODirtyRanges { @@ -1416,20 +891,17 @@ static bool vfio_section_is_vfio_pci(MemoryRegionSection *section, { VFIOPCIDevice *pcidev; VFIODevice *vbasedev; - VFIOGroup *group; Object *owner; owner = memory_region_owner(section->mr); - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { - continue; - } - pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev); - if (OBJECT(pcidev) == owner) { - return true; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { + continue; + } + pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (OBJECT(pcidev) == owner) { + return true; } } @@ -1525,24 +997,21 @@ static void vfio_devices_dma_logging_stop(VFIOContainer *container) sizeof(uint64_t))] = {}; struct vfio_device_feature *feature = (struct vfio_device_feature *)buf; VFIODevice *vbasedev; - VFIOGroup *group; feature->argsz = sizeof(buf); feature->flags = VFIO_DEVICE_FEATURE_SET | VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP; - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_tracking) { - continue; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_tracking) { + continue; + } - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { - warn_report("%s: Failed to stop DMA logging, err %d (%s)", - vbasedev->name, -errno, strerror(errno)); - } - vbasedev->dirty_tracking = false; + if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { + warn_report("%s: Failed to stop DMA logging, err %d (%s)", + vbasedev->name, -errno, strerror(errno)); } + vbasedev->dirty_tracking = false; } } @@ -1625,7 +1094,6 @@ static int vfio_devices_dma_logging_start(VFIOContainer *container) struct vfio_device_feature *feature; VFIODirtyRanges ranges; VFIODevice *vbasedev; - VFIOGroup *group; int ret = 0; vfio_dirty_tracking_init(container, &ranges); @@ -1635,21 +1103,19 @@ static int vfio_devices_dma_logging_start(VFIOContainer *container) return -errno; } - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dirty_tracking) { - continue; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->dirty_tracking) { + continue; + } - ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); - if (ret) { - ret = -errno; - error_report("%s: Failed to start DMA logging, err %d (%s)", - vbasedev->name, ret, strerror(errno)); - goto out; - } - vbasedev->dirty_tracking = true; + ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); + if (ret) { + ret = -errno; + error_report("%s: Failed to start DMA logging, err %d (%s)", + vbasedev->name, ret, strerror(errno)); + goto out; } + vbasedev->dirty_tracking = true; } out: @@ -1724,71 +1190,31 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova, return 0; } -static int vfio_devices_query_dirty_bitmap(VFIOContainer *container, - VFIOBitmap *vbmap, hwaddr iova, - hwaddr size) +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size) { VFIODevice *vbasedev; - VFIOGroup *group; int ret; - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - ret = vfio_device_dma_logging_report(vbasedev, iova, size, - vbmap->bitmap); - if (ret) { - error_report("%s: Failed to get DMA logging report, iova: " - "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx - ", err: %d (%s)", - vbasedev->name, iova, size, ret, strerror(-ret)); + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + ret = vfio_device_dma_logging_report(vbasedev, iova, size, + vbmap->bitmap); + if (ret) { + error_report("%s: Failed to get DMA logging report, iova: " + "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx + ", err: %d (%s)", + vbasedev->name, iova, size, ret, strerror(-ret)); - return ret; - } + return ret; } } return 0; } -static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, - hwaddr iova, hwaddr size) -{ - struct vfio_iommu_type1_dirty_bitmap *dbitmap; - struct vfio_iommu_type1_dirty_bitmap_get *range; - int ret; - - dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range)); - - dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range); - dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; - range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; - range->iova = iova; - range->size = size; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pgsize - * to qemu_real_host_page_size. - */ - range->bitmap.pgsize = qemu_real_host_page_size(); - range->bitmap.size = vbmap->size; - range->bitmap.data = (__u64 *)vbmap->bitmap; - - ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); - if (ret) { - ret = -errno; - error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 - " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, - (uint64_t)range->size, errno); - } - - g_free(dbitmap); - - return ret; -} - -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr) +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr) { bool all_device_dirty_tracking = vfio_devices_all_device_dirty_tracking(container); @@ -1977,7 +1403,7 @@ static void vfio_listener_log_sync(MemoryListener *listener, } } -static const MemoryListener vfio_memory_listener = { +const MemoryListener vfio_memory_listener = { .name = "vfio", .region_add = vfio_listener_region_add, .region_del = vfio_listener_region_del, @@ -1986,338 +1412,34 @@ static const MemoryListener vfio_memory_listener = { .log_sync = vfio_listener_log_sync, }; -static void vfio_listener_release(VFIOContainer *container) -{ - memory_listener_unregister(&container->listener); - if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - memory_listener_unregister(&container->prereg_listener); - } -} - -static struct vfio_info_cap_header * -vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - - for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) { - if (hdr->id == id) { - return hdr; - } - } - - return NULL; -} - -struct vfio_info_cap_header * -vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -static struct vfio_info_cap_header * -vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -struct vfio_info_cap_header * -vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, - unsigned int *avail) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_dma_avail *cap; - - /* If the capability cannot be found, assume no DMA limiting */ - hdr = vfio_get_iommu_type1_info_cap(info, - VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); - if (hdr == NULL) { - return false; - } - - if (avail != NULL) { - cap = (void *) hdr; - *avail = cap->avail; - } - - return true; -} - -static int vfio_setup_region_sparse_mmaps(VFIORegion *region, - struct vfio_region_info *info) -{ - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_sparse_mmap *sparse; - int i, j; - - hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP); - if (!hdr) { - return -ENODEV; - } - - sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header); - - trace_vfio_region_sparse_mmap_header(region->vbasedev->name, - region->nr, sparse->nr_areas); - - region->mmaps = g_new0(VFIOMmap, sparse->nr_areas); - - for (i = 0, j = 0; i < sparse->nr_areas; i++) { - if (sparse->areas[i].size) { - trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, - sparse->areas[i].offset + - sparse->areas[i].size - 1); - region->mmaps[j].offset = sparse->areas[i].offset; - region->mmaps[j].size = sparse->areas[i].size; - j++; - } - } - - region->nr_mmaps = j; - region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap)); - - return 0; -} - -int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, - int index, const char *name) -{ - struct vfio_region_info *info; - int ret; - - ret = vfio_get_region_info(vbasedev, index, &info); - if (ret) { - return ret; - } - - region->vbasedev = vbasedev; - region->flags = info->flags; - region->size = info->size; - region->fd_offset = info->offset; - region->nr = index; - - if (region->size) { - region->mem = g_new0(MemoryRegion, 1); - memory_region_init_io(region->mem, obj, &vfio_region_ops, - region, name, region->size); - - if (!vbasedev->no_mmap && - region->flags & VFIO_REGION_INFO_FLAG_MMAP) { - - ret = vfio_setup_region_sparse_mmaps(region, info); - - if (ret) { - region->nr_mmaps = 1; - region->mmaps = g_new0(VFIOMmap, region->nr_mmaps); - region->mmaps[0].offset = 0; - region->mmaps[0].size = region->size; - } - } - } - - g_free(info); - - trace_vfio_region_setup(vbasedev->name, index, name, - region->flags, region->fd_offset, region->size); - return 0; -} - -static void vfio_subregion_unmap(VFIORegion *region, int index) -{ - trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), - region->mmaps[index].offset, - region->mmaps[index].offset + - region->mmaps[index].size - 1); - memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); - munmap(region->mmaps[index].mmap, region->mmaps[index].size); - object_unparent(OBJECT(®ion->mmaps[index].mem)); - region->mmaps[index].mmap = NULL; -} - -int vfio_region_mmap(VFIORegion *region) -{ - int i, prot = 0; - char *name; - - if (!region->mem) { - return 0; - } - - prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; - prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; - - for (i = 0; i < region->nr_mmaps; i++) { - region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot, - MAP_SHARED, region->vbasedev->fd, - region->fd_offset + - region->mmaps[i].offset); - if (region->mmaps[i].mmap == MAP_FAILED) { - int ret = -errno; - - trace_vfio_region_mmap_fault(memory_region_name(region->mem), i, - region->fd_offset + - region->mmaps[i].offset, - region->fd_offset + - region->mmaps[i].offset + - region->mmaps[i].size - 1, ret); - - region->mmaps[i].mmap = NULL; - - for (i--; i >= 0; i--) { - vfio_subregion_unmap(region, i); - } - - return ret; - } - - name = g_strdup_printf("%s mmaps[%d]", - memory_region_name(region->mem), i); - memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, - memory_region_owner(region->mem), - name, region->mmaps[i].size, - region->mmaps[i].mmap); - g_free(name); - memory_region_add_subregion(region->mem, region->mmaps[i].offset, - ®ion->mmaps[i].mem); - - trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), - region->mmaps[i].offset, - region->mmaps[i].offset + - region->mmaps[i].size - 1); - } - - return 0; -} - -void vfio_region_unmap(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - vfio_subregion_unmap(region, i); - } - } -} - -void vfio_region_exit(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem); - } - } - - trace_vfio_region_exit(region->vbasedev->name, region->nr); -} - -void vfio_region_finalize(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - munmap(region->mmaps[i].mmap, region->mmaps[i].size); - object_unparent(OBJECT(®ion->mmaps[i].mem)); - } - } - - object_unparent(OBJECT(region->mem)); - - g_free(region->mem); - g_free(region->mmaps); - - trace_vfio_region_finalize(region->vbasedev->name, region->nr); - - region->mem = NULL; - region->mmaps = NULL; - region->nr_mmaps = 0; - region->size = 0; - region->flags = 0; - region->nr = 0; -} - -void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_set_enabled(®ion->mmaps[i].mem, enabled); - } - } - - trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), - enabled); -} - void vfio_reset_handler(void *opaque) { - VFIOGroup *group; VFIODevice *vbasedev; - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); } } - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized && vbasedev->needs_reset) { - vbasedev->ops->vfio_hot_reset_multi(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized && vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); } } } -static void vfio_kvm_device_add_group(VFIOGroup *group) +int vfio_kvm_device_add_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_ADD, - .addr = (uint64_t)(unsigned long)&group->fd, + .group = KVM_DEV_VFIO_FILE, + .attr = KVM_DEV_VFIO_FILE_ADD, + .addr = (uint64_t)(unsigned long)&fd, }; if (!kvm_enabled()) { - return; + return 0; } if (vfio_kvm_device_fd < 0) { @@ -2326,41 +1448,46 @@ static void vfio_kvm_device_add_group(VFIOGroup *group) }; if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { - error_report("Failed to create KVM VFIO device: %m"); - return; + error_setg_errno(errp, errno, "Failed to create KVM VFIO device"); + return -errno; } vfio_kvm_device_fd = cd.fd; } if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to add group %d to KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO device", + fd); + return -errno; } #endif + return 0; } -static void vfio_kvm_device_del_group(VFIOGroup *group) +int vfio_kvm_device_del_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_DEL, - .addr = (uint64_t)(unsigned long)&group->fd, + .group = KVM_DEV_VFIO_FILE, + .attr = KVM_DEV_VFIO_FILE_DEL, + .addr = (uint64_t)(unsigned long)&fd, }; if (vfio_kvm_device_fd < 0) { - return; + error_setg(errp, "KVM VFIO device isn't created yet"); + return -EINVAL; } if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to remove group %d from KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, + "Failed to remove fd %d from KVM VFIO device", fd); + return -errno; } #endif + return 0; } -static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) { VFIOAddressSpace *space; @@ -2375,516 +1502,22 @@ static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) space->as = as; QLIST_INIT(&space->containers); + if (QLIST_EMPTY(&vfio_address_spaces)) { + qemu_register_reset(vfio_reset_handler, NULL); + } + QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); return space; } -static void vfio_put_address_space(VFIOAddressSpace *space) +void vfio_put_address_space(VFIOAddressSpace *space) { if (QLIST_EMPTY(&space->containers)) { QLIST_REMOVE(space, list); g_free(space); } -} - -/* - * vfio_get_iommu_type - selects the richest iommu_type (v2 first) - */ -static int vfio_get_iommu_type(VFIOContainer *container, - Error **errp) -{ - int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, - VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; - int i; - - for (i = 0; i < ARRAY_SIZE(iommu_types); i++) { - if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { - return iommu_types[i]; - } - } - error_setg(errp, "No available IOMMU models"); - return -EINVAL; -} - -static int vfio_init_container(VFIOContainer *container, int group_fd, - Error **errp) -{ - int iommu_type, ret; - - iommu_type = vfio_get_iommu_type(container, errp); - if (iommu_type < 0) { - return iommu_type; - } - - ret = ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); - if (ret) { - error_setg_errno(errp, errno, "Failed to set group container"); - return -errno; - } - - while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { - if (iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - /* - * On sPAPR, despite the IOMMU subdriver always advertises v1 and - * v2, the running platform may not support v2 and there is no - * way to guess it until an IOMMU group gets added to the container. - * So in case it fails with v2, try v1 as a fallback. - */ - iommu_type = VFIO_SPAPR_TCE_IOMMU; - continue; - } - error_setg_errno(errp, errno, "Failed to set iommu for container"); - return -errno; - } - - container->iommu_type = iommu_type; - return 0; -} - -static int vfio_get_iommu_info(VFIOContainer *container, - struct vfio_iommu_type1_info **info) -{ - - size_t argsz = sizeof(struct vfio_iommu_type1_info); - - *info = g_new0(struct vfio_iommu_type1_info, 1); -again: - (*info)->argsz = argsz; - - if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { - g_free(*info); - *info = NULL; - return -errno; - } - - if (((*info)->argsz > argsz)) { - argsz = (*info)->argsz; - *info = g_realloc(*info, argsz); - goto again; - } - - return 0; -} - -static struct vfio_info_cap_header * -vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - void *ptr = info; - - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) { - if (hdr->id == id) { - return hdr; - } - } - - return NULL; -} - -static void vfio_get_iommu_info_migration(VFIOContainer *container, - struct vfio_iommu_type1_info *info) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_cap_migration *cap_mig; - - hdr = vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION); - if (!hdr) { - return; - } - - cap_mig = container_of(hdr, struct vfio_iommu_type1_info_cap_migration, - header); - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. - */ - if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { - container->dirty_pages_supported = true; - container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size; - container->dirty_pgsizes = cap_mig->pgsize_bitmap; - } -} - -static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, - Error **errp) -{ - VFIOContainer *container; - int ret, fd; - VFIOAddressSpace *space; - - space = vfio_get_address_space(as); - - /* - * VFIO is currently incompatible with discarding of RAM insofar as the - * madvise to purge (zap) the page from QEMU's address space does not - * interact with the memory API and therefore leaves stale virtual to - * physical mappings in the IOMMU if the page was previously pinned. We - * therefore set discarding broken for each group added to a container, - * whether the container is used individually or shared. This provides - * us with options to allow devices within a group to opt-in and allow - * discarding, so long as it is done consistently for a group (for instance - * if the device is an mdev device where it is known that the host vendor - * driver will never pin pages outside of the working set of the guest - * driver, which would thus not be discarding candidates). - * - * The first opportunity to induce pinning occurs here where we attempt to - * attach the group to existing containers within the AddressSpace. If any - * pages are already zapped from the virtual address space, such as from - * previous discards, new pinning will cause valid mappings to be - * re-established. Likewise, when the overall MemoryListener for a new - * container is registered, a replay of mappings within the AddressSpace - * will occur, re-establishing any previously zapped pages as well. - * - * Especially virtio-balloon is currently only prevented from discarding - * new memory, it will not yet set ram_block_discard_set_required() and - * therefore, neither stops us here or deals with the sudden memory - * consumption of inflated memory. - * - * We do support discarding of memory coordinated via the RamDiscardManager - * with some IOMMU types. vfio_ram_block_discard_disable() handles the - * details once we know which type of IOMMU we are using. - */ - - QLIST_FOREACH(container, &space->containers, next) { - if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { - ret = vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, - "Cannot set discarding of RAM broken"); - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, - &container->fd)) { - error_report("vfio: error disconnecting group %d from" - " container", group->groupid); - } - return ret; - } - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - vfio_kvm_device_add_group(group); - return 0; - } - } - - fd = qemu_open_old("/dev/vfio/vfio", O_RDWR); - if (fd < 0) { - error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); - ret = -errno; - goto put_space_exit; - } - - ret = ioctl(fd, VFIO_GET_API_VERSION); - if (ret != VFIO_API_VERSION) { - error_setg(errp, "supported vfio version: %d, " - "reported version: %d", VFIO_API_VERSION, ret); - ret = -EINVAL; - goto close_fd_exit; - } - - container = g_malloc0(sizeof(*container)); - container->space = space; - container->fd = fd; - container->error = NULL; - container->dirty_pages_supported = false; - container->dma_max_mappings = 0; - QLIST_INIT(&container->giommu_list); - QLIST_INIT(&container->hostwin_list); - QLIST_INIT(&container->vrdl_list); - - ret = vfio_init_container(container, group->fd, errp); - if (ret) { - goto free_container_exit; - } - - ret = vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); - goto free_container_exit; - } - - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - { - struct vfio_iommu_type1_info *info; - - ret = vfio_get_iommu_info(container, &info); - if (ret) { - error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); - goto enable_discards_exit; - } - - if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { - container->pgsizes = info->iova_pgsizes; - } else { - container->pgsizes = qemu_real_host_page_size(); - } - - if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { - container->dma_max_mappings = 65535; - } - vfio_get_iommu_info_migration(container, info); - g_free(info); - - /* - * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE - * information to get the actual window extent rather than assume - * a 64-bit IOVA address space. - */ - vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); - - break; - } - case VFIO_SPAPR_TCE_v2_IOMMU: - case VFIO_SPAPR_TCE_IOMMU: - { - struct vfio_iommu_spapr_tce_info info; - bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU; - - /* - * The host kernel code implementing VFIO_IOMMU_DISABLE is called - * when container fd is closed so we do not call it explicitly - * in this file. - */ - if (!v2) { - ret = ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_setg_errno(errp, errno, "failed to enable container"); - ret = -errno; - goto enable_discards_exit; - } - } else { - container->prereg_listener = vfio_prereg_listener; - - memory_listener_register(&container->prereg_listener, - &address_space_memory); - if (container->error) { - memory_listener_unregister(&container->prereg_listener); - ret = -1; - error_propagate_prepend(errp, container->error, - "RAM memory listener initialization failed: "); - goto enable_discards_exit; - } - } - - info.argsz = sizeof(info); - ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); - if (ret) { - error_setg_errno(errp, errno, - "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); - ret = -errno; - if (v2) { - memory_listener_unregister(&container->prereg_listener); - } - goto enable_discards_exit; - } - - if (v2) { - container->pgsizes = info.ddw.pgsizes; - /* - * There is a default window in just created container. - * To make region_add/del simpler, we better remove this - * window now and let those iommu_listener callbacks - * create/remove them when needed. - */ - ret = vfio_spapr_remove_window(container, info.dma32_window_start); - if (ret) { - error_setg_errno(errp, -ret, - "failed to remove existing window"); - goto enable_discards_exit; - } - } else { - /* The default table uses 4K pages */ - container->pgsizes = 0x1000; - vfio_host_win_add(container, info.dma32_window_start, - info.dma32_window_start + - info.dma32_window_size - 1, - 0x1000); - } - } - } - - vfio_kvm_device_add_group(group); - - QLIST_INIT(&container->group_list); - QLIST_INSERT_HEAD(&space->containers, container, next); - - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - - container->listener = vfio_memory_listener; - - memory_listener_register(&container->listener, container->space->as); - - if (container->error) { - ret = -1; - error_propagate_prepend(errp, container->error, - "memory listener initialization failed: "); - goto listener_release_exit; - } - - container->initialized = true; - - return 0; -listener_release_exit: - QLIST_REMOVE(group, container_next); - QLIST_REMOVE(container, next); - vfio_kvm_device_del_group(group); - vfio_listener_release(container); - -enable_discards_exit: - vfio_ram_block_discard_disable(container, false); - -free_container_exit: - g_free(container); - -close_fd_exit: - close(fd); - -put_space_exit: - vfio_put_address_space(space); - - return ret; -} - -static void vfio_disconnect_container(VFIOGroup *group) -{ - VFIOContainer *container = group->container; - - QLIST_REMOVE(group, container_next); - group->container = NULL; - - /* - * Explicitly release the listener first before unset container, - * since unset may destroy the backend container if it's the last - * group. - */ - if (QLIST_EMPTY(&container->group_list)) { - vfio_listener_release(container); - } - - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { - error_report("vfio: error disconnecting group %d from container", - group->groupid); - } - - if (QLIST_EMPTY(&container->group_list)) { - VFIOAddressSpace *space = container->space; - VFIOGuestIOMMU *giommu, *tmp; - VFIOHostDMAWindow *hostwin, *next; - - QLIST_REMOVE(container, next); - - QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) { - memory_region_unregister_iommu_notifier( - MEMORY_REGION(giommu->iommu_mr), &giommu->n); - QLIST_REMOVE(giommu, giommu_next); - g_free(giommu); - } - - QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, - next) { - QLIST_REMOVE(hostwin, hostwin_next); - g_free(hostwin); - } - - trace_vfio_disconnect_container(container->fd); - close(container->fd); - g_free(container); - - vfio_put_address_space(space); - } -} - -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp) -{ - VFIOGroup *group; - char path[32]; - struct vfio_group_status status = { .argsz = sizeof(status) }; - - QLIST_FOREACH(group, &vfio_group_list, next) { - if (group->groupid == groupid) { - /* Found it. Now is it already in the right context? */ - if (group->container->space->as == as) { - return group; - } else { - error_setg(errp, "group %d used in multiple address spaces", - group->groupid); - return NULL; - } - } - } - - group = g_malloc0(sizeof(*group)); - - snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); - group->fd = qemu_open_old(path, O_RDWR); - if (group->fd < 0) { - error_setg_errno(errp, errno, "failed to open %s", path); - goto free_group_exit; - } - - if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { - error_setg_errno(errp, errno, "failed to get group %d status", groupid); - goto close_fd_exit; - } - - if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { - error_setg(errp, "group %d is not viable", groupid); - error_append_hint(errp, - "Please ensure all devices within the iommu_group " - "are bound to their vfio bus driver.\n"); - goto close_fd_exit; - } - - group->groupid = groupid; - QLIST_INIT(&group->device_list); - - if (vfio_connect_container(group, as, errp)) { - error_prepend(errp, "failed to setup container for group %d: ", - groupid); - goto close_fd_exit; - } - - if (QLIST_EMPTY(&vfio_group_list)) { - qemu_register_reset(vfio_reset_handler, NULL); - } - - QLIST_INSERT_HEAD(&vfio_group_list, group, next); - - return group; - -close_fd_exit: - close(group->fd); - -free_group_exit: - g_free(group); - - return NULL; -} - -void vfio_put_group(VFIOGroup *group) -{ - if (!group || !QLIST_EMPTY(&group->device_list)) { - return; - } - - if (!group->ram_block_discard_allowed) { - vfio_ram_block_discard_disable(group->container, false); - } - vfio_kvm_device_del_group(group); - vfio_disconnect_container(group); - QLIST_REMOVE(group, next); - trace_vfio_put_group(group->fd); - close(group->fd); - g_free(group); - - if (QLIST_EMPTY(&vfio_group_list)) { + if (QLIST_EMPTY(&vfio_address_spaces)) { qemu_unregister_reset(vfio_reset_handler, NULL); } } @@ -2912,245 +1545,3 @@ retry: return info; } - -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp) -{ - g_autofree struct vfio_device_info *info = NULL; - int fd; - - fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); - if (fd < 0) { - error_setg_errno(errp, errno, "error getting device from group %d", - group->groupid); - error_append_hint(errp, - "Verify all devices in group %d are bound to vfio-<bus> " - "or pci-stub and not already in use\n", group->groupid); - return fd; - } - - info = vfio_get_device_info(fd); - if (!info) { - error_setg_errno(errp, errno, "error getting device info"); - close(fd); - return -1; - } - - /* - * Set discarding of RAM as not broken for this group if the driver knows - * the device operates compatibly with discarding. Setting must be - * consistent per group, but since compatibility is really only possible - * with mdev currently, we expect singleton groups. - */ - if (vbasedev->ram_block_discard_allowed != - group->ram_block_discard_allowed) { - if (!QLIST_EMPTY(&group->device_list)) { - error_setg(errp, "Inconsistent setting of support for discarding " - "RAM (e.g., balloon) within group"); - close(fd); - return -1; - } - - if (!group->ram_block_discard_allowed) { - group->ram_block_discard_allowed = true; - vfio_ram_block_discard_disable(group->container, false); - } - } - - vbasedev->fd = fd; - vbasedev->group = group; - QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); - - vbasedev->num_irqs = info->num_irqs; - vbasedev->num_regions = info->num_regions; - vbasedev->flags = info->flags; - - trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs); - - vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET); - - return 0; -} - -void vfio_put_base_device(VFIODevice *vbasedev) -{ - if (!vbasedev->group) { - return; - } - QLIST_REMOVE(vbasedev, next); - vbasedev->group = NULL; - trace_vfio_put_base_device(vbasedev->fd); - close(vbasedev->fd); -} - -int vfio_get_region_info(VFIODevice *vbasedev, int index, - struct vfio_region_info **info) -{ - size_t argsz = sizeof(struct vfio_region_info); - - *info = g_malloc0(argsz); - - (*info)->index = index; -retry: - (*info)->argsz = argsz; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { - g_free(*info); - *info = NULL; - return -errno; - } - - if ((*info)->argsz > argsz) { - argsz = (*info)->argsz; - *info = g_realloc(*info, argsz); - - goto retry; - } - - return 0; -} - -int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, - uint32_t subtype, struct vfio_region_info **info) -{ - int i; - - for (i = 0; i < vbasedev->num_regions; i++) { - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_type *cap_type; - - if (vfio_get_region_info(vbasedev, i, info)) { - continue; - } - - hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); - if (!hdr) { - g_free(*info); - continue; - } - - cap_type = container_of(hdr, struct vfio_region_info_cap_type, header); - - trace_vfio_get_dev_region(vbasedev->name, i, - cap_type->type, cap_type->subtype); - - if (cap_type->type == type && cap_type->subtype == subtype) { - return 0; - } - - g_free(*info); - } - - *info = NULL; - return -ENODEV; -} - -bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type) -{ - struct vfio_region_info *info = NULL; - bool ret = false; - - if (!vfio_get_region_info(vbasedev, region, &info)) { - if (vfio_get_region_info_cap(info, cap_type)) { - ret = true; - } - g_free(info); - } - - return ret; -} - -/* - * Interfaces for IBM EEH (Enhanced Error Handling) - */ -static bool vfio_eeh_container_ok(VFIOContainer *container) -{ - /* - * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO - * implementation is broken if there are multiple groups in a - * container. The hardware works in units of Partitionable - * Endpoints (== IOMMU groups) and the EEH operations naively - * iterate across all groups in the container, without any logic - * to make sure the groups have their state synchronized. For - * certain operations (ENABLE) that might be ok, until an error - * occurs, but for others (GET_STATE) it's clearly broken. - */ - - /* - * XXX Once fixed kernels exist, test for them here - */ - - if (QLIST_EMPTY(&container->group_list)) { - return false; - } - - if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { - return false; - } - - return true; -} - -static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) -{ - struct vfio_eeh_pe_op pe_op = { - .argsz = sizeof(pe_op), - .op = op, - }; - int ret; - - if (!vfio_eeh_container_ok(container)) { - error_report("vfio/eeh: EEH_PE_OP 0x%x: " - "kernel requires a container with exactly one group", op); - return -EPERM; - } - - ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); - if (ret < 0) { - error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); - return -errno; - } - - return ret; -} - -static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) -{ - VFIOAddressSpace *space = vfio_get_address_space(as); - VFIOContainer *container = NULL; - - if (QLIST_EMPTY(&space->containers)) { - /* No containers to act on */ - goto out; - } - - container = QLIST_FIRST(&space->containers); - - if (QLIST_NEXT(container, next)) { - /* We don't yet have logic to synchronize EEH state across - * multiple containers */ - container = NULL; - goto out; - } - -out: - vfio_put_address_space(space); - return container; -} - -bool vfio_eeh_as_ok(AddressSpace *as) -{ - VFIOContainer *container = vfio_eeh_as_container(as); - - return (container != NULL) && vfio_eeh_container_ok(container); -} - -int vfio_eeh_as_op(AddressSpace *as, uint32_t op) -{ - VFIOContainer *container = vfio_eeh_as_container(as); - - if (!container) { - return -ENODEV; - } - return vfio_eeh_container_op(container, op); -} |