diff options
Diffstat (limited to 'hw/vfio/helpers.c')
| -rw-r--r-- | hw/vfio/helpers.c | 702 |
1 files changed, 81 insertions, 621 deletions
diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c index 4b255d4f3a..d0dbab1d17 100644 --- a/hw/vfio/helpers.c +++ b/hw/vfio/helpers.c @@ -22,242 +22,11 @@ #include "qemu/osdep.h" #include <sys/ioctl.h> -#include "hw/vfio/vfio-common.h" -#include "hw/vfio/pci.h" +#include "system/kvm.h" +#include "hw/vfio/vfio-device.h" #include "hw/hw.h" -#include "trace.h" #include "qapi/error.h" -#include "qemu/error-report.h" -#include "qemu/units.h" -#include "monitor/monitor.h" - -/* - * 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; - } -} - -bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, - int action, int fd, Error **errp) -{ - ERRP_GUARD(); - g_autofree struct vfio_irq_set *irq_set = NULL; - int argsz; - 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)) { - return true; - } - - error_setg_errno(errp, errno, "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 false; -} - -/* - * 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, - }, -}; +#include "vfio-helpers.h" int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) { @@ -306,435 +75,126 @@ vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) return vfio_get_cap((void *)info, info->cap_offset, id); } -static int vfio_setup_region_sparse_mmaps(VFIORegion *region, - struct vfio_region_info *info) +struct vfio_info_cap_header * +vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) { - 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++; - } + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; } - region->nr_mmaps = j; - region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap)); - - return 0; + return vfio_get_cap((void *)info, info->cap_offset, id); } -int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, - int index, const char *name) +bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, + unsigned int *avail) { - g_autofree struct vfio_region_info *info = NULL; - int ret; + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_dma_avail *cap; - ret = vfio_get_region_info(vbasedev, index, &info); - if (ret) { - return ret; + /* 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) { + return false; } - 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; - } - } + if (avail != NULL) { + cap = (void *) hdr; + *avail = cap->avail; } - trace_vfio_region_setup(vbasedev->name, index, name, - region->flags, region->fd_offset, region->size); - return 0; + return true; } -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; -} +#ifdef CONFIG_KVM +/* + * We have a single VFIO pseudo device per KVM VM. Once created it lives + * for the life of the VM. Closing the file descriptor only drops our + * reference to it and the device's reference to kvm. Therefore once + * initialized, this file descriptor is only released on QEMU exit and + * we'll re-use it should another vfio device be attached before then. + */ +int vfio_kvm_device_fd = -1; +#endif -int vfio_region_mmap(VFIORegion *region) +int vfio_kvm_device_add_fd(int fd, Error **errp) { - int i, ret, prot = 0; - char *name; +#ifdef CONFIG_KVM + struct kvm_device_attr attr = { + .group = KVM_DEV_VFIO_FILE, + .attr = KVM_DEV_VFIO_FILE_ADD, + .addr = (uint64_t)(unsigned long)&fd, + }; - if (!region->mem) { + if (!kvm_enabled()) { 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++) { - size_t align = MIN(1ULL << ctz64(region->mmaps[i].size), 1 * GiB); - void *map_base, *map_align; - - /* - * Align the mmap for more efficient mapping in the kernel. Ideally - * we'd know the PMD and PUD mapping sizes to use as discrete alignment - * intervals, but we don't. As of Linux v6.12, the largest PUD size - * supporting huge pfnmap is 1GiB (ARCH_SUPPORTS_PUD_PFNMAP is only set - * on x86_64). Align by power-of-two size, capped at 1GiB. - * - * NB. qemu_memalign() and friends actually allocate memory, whereas - * the region size here can exceed host memory, therefore we manually - * create an oversized anonymous mapping and clean it up for alignment. - */ - map_base = mmap(0, region->mmaps[i].size + align, PROT_NONE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (map_base == MAP_FAILED) { - ret = -errno; - goto no_mmap; - } + if (vfio_kvm_device_fd < 0) { + struct kvm_create_device cd = { + .type = KVM_DEV_TYPE_VFIO, + }; - map_align = (void *)ROUND_UP((uintptr_t)map_base, (uintptr_t)align); - munmap(map_base, map_align - map_base); - munmap(map_align + region->mmaps[i].size, - align - (map_align - map_base)); - - region->mmaps[i].mmap = mmap(map_align, region->mmaps[i].size, prot, - MAP_SHARED | MAP_FIXED, - region->vbasedev->fd, - region->fd_offset + - region->mmaps[i].offset); - if (region->mmaps[i].mmap == MAP_FAILED) { - ret = -errno; - goto no_mmap; + if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { + error_setg_errno(errp, errno, "Failed to create KVM VFIO device"); + return -errno; } - 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; - -no_mmap: - 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; -} - -void vfio_region_unmap(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; + vfio_kvm_device_fd = cd.fd; } - 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); -} - -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; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { + error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO device", + fd); return -errno; } - - if ((*info)->argsz > argsz) { - argsz = (*info)->argsz; - *info = g_realloc(*info, argsz); - - goto retry; - } - +#endif 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) +int vfio_kvm_device_del_fd(int fd, Error **errp) { - g_autofree 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; - } - } - - return ret; -} +#ifdef CONFIG_KVM + struct kvm_device_attr attr = { + .group = KVM_DEV_VFIO_FILE, + .attr = KVM_DEV_VFIO_FILE_DEL, + .addr = (uint64_t)(unsigned long)&fd, + }; -bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp) -{ - ERRP_GUARD(); - struct stat st; - - if (vbasedev->fd < 0) { - if (stat(vbasedev->sysfsdev, &st) < 0) { - error_setg_errno(errp, errno, "no such host device"); - error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->sysfsdev); - return false; - } - /* User may specify a name, e.g: VFIO platform device */ - if (!vbasedev->name) { - vbasedev->name = g_path_get_basename(vbasedev->sysfsdev); - } - } else { - if (!vbasedev->iommufd) { - error_setg(errp, "Use FD passing only with iommufd backend"); - return false; - } - /* - * Give a name with fd so any function printing out vbasedev->name - * will not break. - */ - if (!vbasedev->name) { - vbasedev->name = g_strdup_printf("VFIO_FD%d", vbasedev->fd); - } + if (vfio_kvm_device_fd < 0) { + error_setg(errp, "KVM VFIO device isn't created yet"); + return -EINVAL; } - return true; -} - -void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp) -{ - ERRP_GUARD(); - int fd = monitor_fd_param(monitor_cur(), str, errp); - - if (fd < 0) { - error_prepend(errp, "Could not parse remote object fd %s:", str); - return; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { + error_setg_errno(errp, errno, + "Failed to remove fd %d from KVM VFIO device", fd); + return -errno; } - vbasedev->fd = fd; -} - -void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops, - DeviceState *dev, bool ram_discard) -{ - vbasedev->type = type; - vbasedev->ops = ops; - vbasedev->dev = dev; - vbasedev->fd = -1; - - vbasedev->ram_block_discard_allowed = ram_discard; +#endif + return 0; } -int vfio_device_get_aw_bits(VFIODevice *vdev) +struct vfio_device_info *vfio_get_device_info(int fd) { - /* - * iova_ranges is a sorted list. For old kernels that support - * VFIO but not support query of iova ranges, iova_ranges is NULL, - * in this case HOST_IOMMU_DEVICE_CAP_AW_BITS_MAX(64) is returned. - */ - GList *l = g_list_last(vdev->bcontainer->iova_ranges); - - if (l) { - Range *range = l->data; - return range_get_last_bit(range) + 1; - } + struct vfio_device_info *info; + uint32_t argsz = sizeof(*info); - return HOST_IOMMU_DEVICE_CAP_AW_BITS_MAX; -} + info = g_malloc0(argsz); -bool vfio_device_is_mdev(VFIODevice *vbasedev) -{ - g_autofree char *subsys = NULL; - g_autofree char *tmp = NULL; +retry: + info->argsz = argsz; - if (!vbasedev->sysfsdev) { - return false; + if (ioctl(fd, VFIO_DEVICE_GET_INFO, info)) { + g_free(info); + return NULL; } - tmp = g_strdup_printf("%s/subsystem", vbasedev->sysfsdev); - subsys = realpath(tmp, NULL); - return subsys && (strcmp(subsys, "/sys/bus/mdev") == 0); -} - -bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp) -{ - HostIOMMUDevice *hiod = vbasedev->hiod; - - if (!hiod) { - return true; + if (info->argsz > argsz) { + argsz = info->argsz; + info = g_realloc(info, argsz); + goto retry; } - return HOST_IOMMU_DEVICE_GET_CLASS(hiod)->realize(hiod, vbasedev, errp); -} - -VFIODevice *vfio_get_vfio_device(Object *obj) -{ - if (object_dynamic_cast(obj, TYPE_VFIO_PCI)) { - return &VFIO_PCI(obj)->vbasedev; - } else { - return NULL; - } + return info; } |