diff options
Diffstat (limited to 'hw/vfio/common.c')
| -rw-r--r-- | hw/vfio/common.c | 140 |
1 files changed, 86 insertions, 54 deletions
diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 0d341a33ff..6797208cc1 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -312,11 +312,15 @@ out: rcu_read_unlock(); } +static hwaddr vfio_container_granularity(VFIOContainer *container) +{ + return (hwaddr)1 << ctz64(container->iova_pgsizes); +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { - VFIOContainer *container = container_of(listener, VFIOContainer, - iommu_data.type1.listener); + VFIOContainer *container = container_of(listener, VFIOContainer, listener); hwaddr iova, end; Int128 llend; void *vaddr; @@ -344,14 +348,22 @@ static void vfio_listener_region_add(MemoryListener *listener, if (int128_ge(int128_make64(iova), llend)) { return; } + end = int128_get64(llend); + + if ((iova < container->min_iova) || ((end - 1) > container->max_iova)) { + error_report("vfio: IOMMU container %p can't map guest IOVA region" + " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx, + container, iova, end - 1); + ret = -EFAULT; + goto fail; + } memory_region_ref(section->mr); if (memory_region_is_iommu(section->mr)) { VFIOGuestIOMMU *giommu; - trace_vfio_listener_region_add_iommu(iova, - int128_get64(int128_sub(llend, int128_one()))); + trace_vfio_listener_region_add_iommu(iova, end - 1); /* * FIXME: We should do some checking to see if the * capabilities of the host VFIO IOMMU are adequate to model @@ -362,33 +374,22 @@ static void vfio_listener_region_add(MemoryListener *listener, * would be the right place to wire that up (tell the KVM * device emulation the VFIO iommu handles to use). */ - /* - * This assumes that the guest IOMMU is empty of - * mappings at this point. - * - * One way of doing this is: - * 1. Avoid sharing IOMMUs between emulated devices or different - * IOMMU groups. - * 2. Implement VFIO_IOMMU_ENABLE in the host kernel to fail if - * there are some mappings in IOMMU. - * - * VFIO on SPAPR does that. Other IOMMU models may do that different, - * they must make sure there are no existing mappings or - * loop through existing mappings to map them into VFIO. - */ giommu = g_malloc0(sizeof(*giommu)); giommu->iommu = section->mr; giommu->container = container; giommu->n.notify = vfio_iommu_map_notify; QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next); + memory_region_register_iommu_notifier(giommu->iommu, &giommu->n); + memory_region_iommu_replay(giommu->iommu, &giommu->n, + vfio_container_granularity(container), + false); return; } /* Here we assume that memory_region_is_ram(section->mr)==true */ - end = int128_get64(llend); vaddr = memory_region_get_ram_ptr(section->mr) + section->offset_within_region + (iova - section->offset_within_address_space); @@ -400,27 +401,30 @@ static void vfio_listener_region_add(MemoryListener *listener, error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " "0x%"HWADDR_PRIx", %p) = %d (%m)", container, iova, end - iova, vaddr, ret); + goto fail; + } - /* - * On the initfn path, store the first error in the container so we - * can gracefully fail. Runtime, there's not much we can do other - * than throw a hardware error. - */ - if (!container->iommu_data.type1.initialized) { - if (!container->iommu_data.type1.error) { - container->iommu_data.type1.error = ret; - } - } else { - hw_error("vfio: DMA mapping failed, unable to continue"); + return; + +fail: + /* + * On the initfn path, store the first error in the container so we + * can gracefully fail. Runtime, there's not much we can do other + * than throw a hardware error. + */ + if (!container->initialized) { + if (!container->error) { + container->error = ret; } + } else { + hw_error("vfio: DMA mapping failed, unable to continue"); } } static void vfio_listener_region_del(MemoryListener *listener, MemoryRegionSection *section) { - VFIOContainer *container = container_of(listener, VFIOContainer, - iommu_data.type1.listener); + VFIOContainer *container = container_of(listener, VFIOContainer, listener); hwaddr iova, end; int ret; @@ -485,7 +489,7 @@ static const MemoryListener vfio_memory_listener = { static void vfio_listener_release(VFIOContainer *container) { - memory_listener_unregister(&container->iommu_data.type1.listener); + memory_listener_unregister(&container->listener); } int vfio_mmap_region(Object *obj, VFIORegion *region, @@ -668,6 +672,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU) || ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU)) { bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU); + struct vfio_iommu_type1_info info; ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); if (ret) { @@ -684,21 +689,27 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) goto free_container_exit; } - container->iommu_data.type1.listener = vfio_memory_listener; - container->iommu_data.release = vfio_listener_release; - - memory_listener_register(&container->iommu_data.type1.listener, - container->space->as); - - if (container->iommu_data.type1.error) { - ret = container->iommu_data.type1.error; - error_report("vfio: memory listener initialization failed for container"); - goto listener_release_exit; + /* + * FIXME: This assumes that a Type1 IOMMU can map any 64-bit + * IOVA whatsoever. That's not actually true, but the current + * kernel interface doesn't tell us what it can map, and the + * existing Type1 IOMMUs generally support any IOVA we're + * going to actually try in practice. + */ + container->min_iova = 0; + container->max_iova = (hwaddr)-1; + + /* Assume just 4K IOVA page size */ + container->iova_pgsizes = 0x1000; + info.argsz = sizeof(info); + ret = ioctl(fd, VFIO_IOMMU_GET_INFO, &info); + /* Ignore errors */ + if ((ret == 0) && (info.flags & VFIO_IOMMU_INFO_PGSIZES)) { + container->iova_pgsizes = info.iova_pgsizes; } - - container->iommu_data.type1.initialized = true; - } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { + struct vfio_iommu_spapr_tce_info info; + ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); if (ret) { error_report("vfio: failed to set group container: %m"); @@ -724,18 +735,41 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) goto free_container_exit; } - container->iommu_data.type1.listener = vfio_memory_listener; - container->iommu_data.release = vfio_listener_release; - - memory_listener_register(&container->iommu_data.type1.listener, - container->space->as); + /* + * This only considers the host IOMMU's 32-bit window. At + * some point we need to add support for the optional 64-bit + * window and dynamic windows + */ + info.argsz = sizeof(info); + ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); + if (ret) { + error_report("vfio: VFIO_IOMMU_SPAPR_TCE_GET_INFO failed: %m"); + ret = -errno; + goto free_container_exit; + } + container->min_iova = info.dma32_window_start; + container->max_iova = container->min_iova + info.dma32_window_size - 1; + /* Assume just 4K IOVA pages for now */ + container->iova_pgsizes = 0x1000; } else { error_report("vfio: No available IOMMU models"); ret = -EINVAL; goto free_container_exit; } + container->listener = vfio_memory_listener; + + memory_listener_register(&container->listener, container->space->as); + + if (container->error) { + ret = container->error; + error_report("vfio: memory listener initialization failed for container"); + goto listener_release_exit; + } + + container->initialized = true; + QLIST_INIT(&container->group_list); QLIST_INSERT_HEAD(&space->containers, container, next); @@ -774,9 +808,7 @@ static void vfio_disconnect_container(VFIOGroup *group) VFIOAddressSpace *space = container->space; VFIOGuestIOMMU *giommu, *tmp; - if (container->iommu_data.release) { - container->iommu_data.release(container); - } + vfio_listener_release(container); QLIST_REMOVE(container, next); QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) { |