diff options
| -rw-r--r-- | hw/vfio/Makefile.objs | 1 | ||||
| -rw-r--r-- | hw/vfio/common.c | 959 | ||||
| -rw-r--r-- | hw/vfio/pci.c | 1028 | ||||
| -rw-r--r-- | include/hw/vfio/vfio-common.h | 151 | ||||
| -rw-r--r-- | trace-events | 1 |
5 files changed, 1113 insertions, 1027 deletions
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs index 31c7dabb02..e31f30ec09 100644 --- a/hw/vfio/Makefile.objs +++ b/hw/vfio/Makefile.objs @@ -1,3 +1,4 @@ ifeq ($(CONFIG_LINUX), y) +obj-$(CONFIG_SOFTMMU) += common.o obj-$(CONFIG_PCI) += pci.o endif diff --git a/hw/vfio/common.c b/hw/vfio/common.c new file mode 100644 index 0000000000..4f15c86b80 --- /dev/null +++ b/hw/vfio/common.c @@ -0,0 +1,959 @@ +/* + * generic functions used by VFIO devices + * + * 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) + */ + +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <linux/vfio.h> + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "hw/hw.h" +#include "qemu/error-report.h" +#include "sysemu/kvm.h" +#include "trace.h" + +struct vfio_group_head vfio_group_list = + QLIST_HEAD_INITIALIZER(vfio_address_spaces); +struct vfio_as_head vfio_address_spaces = + QLIST_HEAD_INITIALIZER(vfio_address_spaces); + +#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. + */ +static 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); +} + +/* + * 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; + default: + hw_error("vfio: unsupported write size, %d 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; + default: + hw_error("vfio: unsupported read size, %d 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, +}; + +/* + * 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) +{ + struct vfio_iommu_type1_dma_unmap unmap = { + .argsz = sizeof(unmap), + .flags = 0, + .iova = iova, + .size = size, + }; + + if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { + error_report("VFIO_UNMAP_DMA: %d\n", -errno); + return -errno; + } + + 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 the VGA ROM space. + */ + if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || + (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 && + ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { + return 0; + } + + error_report("VFIO_MAP_DMA: %d\n", -errno); + return -errno; +} + +static bool vfio_listener_skipped_section(MemoryRegionSection *section) +{ + return (!memory_region_is_ram(section->mr) && + !memory_region_is_iommu(section->mr)) || + /* + * Sizing an enabled 64-bit BAR can cause spurious mappings to + * addresses in the upper part of the 64-bit address space. These + * are never accessed by the CPU and beyond the address width of + * some IOMMU hardware. TODO: VFIO should tell us the IOMMU width. + */ + section->offset_within_address_space & (1ULL << 63); +} + +static void vfio_iommu_map_notify(Notifier *n, void *data) +{ + VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n); + VFIOContainer *container = giommu->container; + IOMMUTLBEntry *iotlb = data; + MemoryRegion *mr; + hwaddr xlat; + hwaddr len = iotlb->addr_mask + 1; + void *vaddr; + int ret; + + trace_vfio_iommu_map_notify(iotlb->iova, + iotlb->iova + iotlb->addr_mask); + + /* + * The IOMMU TLB entry we have just covers translation through + * this IOMMU to its immediate target. We need to translate + * it the rest of the way through to memory. + */ + mr = address_space_translate(&address_space_memory, + iotlb->translated_addr, + &xlat, &len, iotlb->perm & IOMMU_WO); + if (!memory_region_is_ram(mr)) { + error_report("iommu map to non memory area %"HWADDR_PRIx"\n", + xlat); + return; + } + /* + * Translation truncates length to the IOMMU page size, + * check that it did not truncate too much. + */ + if (len & iotlb->addr_mask) { + error_report("iommu has granularity incompatible with target AS\n"); + return; + } + + if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) { + vaddr = memory_region_get_ram_ptr(mr) + xlat; + ret = vfio_dma_map(container, iotlb->iova, + iotlb->addr_mask + 1, vaddr, + !(iotlb->perm & IOMMU_WO) || mr->readonly); + if (ret) { + error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx", %p) = %d (%m)", + container, iotlb->iova, + iotlb->addr_mask + 1, vaddr, ret); + } + } else { + ret = vfio_dma_unmap(container, iotlb->iova, iotlb->addr_mask + 1); + if (ret) { + error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx") = %d (%m)", + container, iotlb->iova, + iotlb->addr_mask + 1, ret); + } + } +} + +static void vfio_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, + iommu_data.type1.listener); + hwaddr iova, end; + Int128 llend; + void *vaddr; + int ret; + + if (vfio_listener_skipped_section(section)) { + trace_vfio_listener_region_add_skip( + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(int128_sub(section->size, int128_one()))); + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); + + if (int128_ge(int128_make64(iova), llend)) { + return; + } + + 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()))); + /* + * FIXME: We should do some checking to see if the + * capabilities of the host VFIO IOMMU are adequate to model + * the guest IOMMU + * + * FIXME: For VFIO iommu types which have KVM acceleration to + * avoid bouncing all map/unmaps through qemu this way, this + * 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); + + 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); + + trace_vfio_listener_region_add_ram(iova, end - 1, vaddr); + + ret = vfio_dma_map(container, iova, end - iova, vaddr, section->readonly); + if (ret) { + error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx", %p) = %d (%m)", + container, iova, end - iova, vaddr, ret); + + /* + * 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"); + } + } +} + +static void vfio_listener_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, + iommu_data.type1.listener); + hwaddr iova, end; + int ret; + + if (vfio_listener_skipped_section(section)) { + trace_vfio_listener_region_del_skip( + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(int128_sub(section->size, int128_one()))); + return; + } + + if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != + (section->offset_within_region & ~TARGET_PAGE_MASK))) { + error_report("%s received unaligned region", __func__); + return; + } + + if (memory_region_is_iommu(section->mr)) { + VFIOGuestIOMMU *giommu; + + QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) { + if (giommu->iommu == section->mr) { + memory_region_unregister_iommu_notifier(&giommu->n); + QLIST_REMOVE(giommu, giommu_next); + g_free(giommu); + break; + } + } + + /* + * FIXME: We assume the one big unmap below is adequate to + * remove any individual page mappings in the IOMMU which + * might have been copied into VFIO. This works for a page table + * based IOMMU where a big unmap flattens a large range of IO-PTEs. + * That may not be true for all IOMMU types. + */ + } + + iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); + end = (section->offset_within_address_space + int128_get64(section->size)) & + TARGET_PAGE_MASK; + + if (iova >= end) { + return; + } + + trace_vfio_listener_region_del(iova, end - 1); + + ret = vfio_dma_unmap(container, iova, end - iova); + memory_region_unref(section->mr); + if (ret) { + error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx") = %d (%m)", + container, iova, end - iova, ret); + } +} + +const MemoryListener vfio_memory_listener = { + .region_add = vfio_listener_region_add, + .region_del = vfio_listener_region_del, +}; + +void vfio_listener_release(VFIOContainer *container) +{ + memory_listener_unregister(&container->iommu_data.type1.listener); +} + +int vfio_mmap_region(Object *obj, VFIORegion *region, + MemoryRegion *mem, MemoryRegion *submem, + void **map, size_t size, off_t offset, + const char *name) +{ + int ret = 0; + VFIODevice *vbasedev = region->vbasedev; + + if (VFIO_ALLOW_MMAP && size && region->flags & + VFIO_REGION_INFO_FLAG_MMAP) { + int prot = 0; + + if (region->flags & VFIO_REGION_INFO_FLAG_READ) { + prot |= PROT_READ; + } + + if (region->flags & VFIO_REGION_INFO_FLAG_WRITE) { + prot |= PROT_WRITE; + } + + *map = mmap(NULL, size, prot, MAP_SHARED, + vbasedev->fd, + region->fd_offset + offset); + if (*map == MAP_FAILED) { + *map = NULL; + ret = -errno; + goto empty_region; + } + + memory_region_init_ram_ptr(submem, obj, name, size, *map); + memory_region_set_skip_dump(submem); + } else { +empty_region: + /* Create a zero sized sub-region to make cleanup easy. */ + memory_region_init(submem, obj, name, 0); + } + + memory_region_add_subregion(mem, offset, submem); + + return ret; +} + +void vfio_reset_handler(void *opaque) +{ + VFIOGroup *group; + VFIODevice *vbasedev; + + QLIST_FOREACH(group, &vfio_group_list, next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); + } + } + + QLIST_FOREACH(group, &vfio_group_list, next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); + } + } + } +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ +#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, + }; + + if (!kvm_enabled()) { + return; + } + + if (vfio_kvm_device_fd < 0) { + struct kvm_create_device cd = { + .type = KVM_DEV_TYPE_VFIO, + }; + + if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { + error_report("KVM_CREATE_DEVICE: %m\n"); + return; + } + + 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); + } +#endif +} + +static void vfio_kvm_device_del_group(VFIOGroup *group) +{ +#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, + }; + + if (vfio_kvm_device_fd < 0) { + return; + } + + 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); + } +#endif +} + +static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) +{ + VFIOAddressSpace *space; + + QLIST_FOREACH(space, &vfio_address_spaces, list) { + if (space->as == as) { + return space; + } + } + + /* No suitable VFIOAddressSpace, create a new one */ + space = g_malloc0(sizeof(*space)); + space->as = as; + QLIST_INIT(&space->containers); + + QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); + + return space; +} + +static void vfio_put_address_space(VFIOAddressSpace *space) +{ + if (QLIST_EMPTY(&space->containers)) { + QLIST_REMOVE(space, list); + g_free(space); + } +} + +static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) +{ + VFIOContainer *container; + int ret, fd; + VFIOAddressSpace *space; + + space = vfio_get_address_space(as); + + QLIST_FOREACH(container, &space->containers, next) { + if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { + group->container = container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + return 0; + } + } + + fd = qemu_open("/dev/vfio/vfio", O_RDWR); + if (fd < 0) { + error_report("vfio: failed to open /dev/vfio/vfio: %m"); + ret = -errno; + goto put_space_exit; + } + + ret = ioctl(fd, VFIO_GET_API_VERSION); + if (ret != VFIO_API_VERSION) { + error_report("vfio: 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; + if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) { + ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); + if (ret) { + error_report("vfio: failed to set group container: %m"); + ret = -errno; + goto free_container_exit; + } + + ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU); + if (ret) { + error_report("vfio: failed to set iommu for container: %m"); + ret = -errno; + 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; + } + + container->iommu_data.type1.initialized = true; + + } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { + ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); + if (ret) { + error_report("vfio: failed to set group container: %m"); + ret = -errno; + goto free_container_exit; + } + ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU); + if (ret) { + error_report("vfio: failed to set iommu for container: %m"); + ret = -errno; + goto free_container_exit; + } + + /* + * 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. + */ + ret = ioctl(fd, VFIO_IOMMU_ENABLE); + if (ret) { + error_report("vfio: failed to enable container: %m"); + ret = -errno; + 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); + + } else { + error_report("vfio: No available IOMMU models"); + ret = -EINVAL; + goto free_container_exit; + } + + QLIST_INIT(&container->group_list); + QLIST_INSERT_HEAD(&space->containers, container, next); + + group->container = container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + + return 0; +listener_release_exit: + vfio_listener_release(container); + +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; + + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { + error_report("vfio: error disconnecting group %d from container", + group->groupid); + } + + QLIST_REMOVE(group, container_next); + group->container = NULL; + + if (QLIST_EMPTY(&container->group_list)) { + VFIOAddressSpace *space = container->space; + + if (container->iommu_data.release) { + container->iommu_data.release(container); + } + QLIST_REMOVE(container, next); + 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) +{ + 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_report("vfio: 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(path, O_RDWR); + if (group->fd < 0) { + error_report("vfio: error opening %s: %m", path); + goto free_group_exit; + } + + if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { + error_report("vfio: error getting group status: %m"); + goto close_fd_exit; + } + + if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { + error_report("vfio: error, group %d is not viable, please ensure " + "all devices within the iommu_group are bound to their " + "vfio bus driver.", groupid); + goto close_fd_exit; + } + + group->groupid = groupid; + QLIST_INIT(&group->device_list); + + if (vfio_connect_container(group, as)) { + error_report("vfio: 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); + + vfio_kvm_device_add_group(group); + + return group; + +close_fd_exit: + close(group->fd); + +free_group_exit: + g_free(group); + + return NULL; +} + +void vfio_put_group(VFIOGroup *group) +{ + if (!QLIST_EMPTY(&group->device_list)) { + return; + } + + 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)) { + qemu_unregister_reset(vfio_reset_handler, NULL); + } +} + +int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev) +{ + struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) }; + int ret; + + ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); + if (ret < 0) { + error_report("vfio: error getting device %s from group %d: %m", + name, group->groupid); + error_printf("Verify all devices in group %d are bound to vfio-<bus> " + "or pci-stub and not already in use\n", group->groupid); + return ret; + } + + vbasedev->fd = ret; + vbasedev->group = group; + QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_INFO, &dev_info); + if (ret) { + error_report("vfio: error getting device info: %m"); + goto error; + } + + vbasedev->num_irqs = dev_info.num_irqs; + vbasedev->num_regions = dev_info.num_regions; + vbasedev->flags = dev_info.flags; + + trace_vfio_get_device(name, dev_info.flags, dev_info.num_regions, + dev_info.num_irqs); + + vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET); + + ret = vbasedev->ops->vfio_populate_device(vbasedev); + +error: + if (ret) { + vfio_put_base_device(vbasedev); + } + return ret; +} + +void vfio_put_base_device(VFIODevice *vbasedev) +{ + QLIST_REMOVE(vbasedev, next); + vbasedev->group = NULL; + trace_vfio_put_base_device(vbasedev->fd); + close(vbasedev->fd); +} + +static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid, + int req, void *param) +{ + VFIOGroup *group; + VFIOContainer *container; + int ret = -1; + + group = vfio_get_group(groupid, as); + if (!group) { + error_report("vfio: group %d not registered", groupid); + return ret; + } + + container = group->container; + if (group->container) { + ret = ioctl(container->fd, req, param); + if (ret < 0) { + error_report("vfio: failed to ioctl container: ret=%d, %s", + ret, strerror(errno)); + } + } + + vfio_put_group(group); + + return ret; +} + +int vfio_container_ioctl(AddressSpace *as, int32_t groupid, + int req, void *param) +{ + /* We allow only certain ioctls to the container */ + switch (req) { + case VFIO_CHECK_EXTENSION: + case VFIO_IOMMU_SPAPR_TCE_GET_INFO: + break; + default: + /* Return an error on unknown requests */ + error_report("vfio: unsupported ioctl %X", req); + return -1; + } + + return vfio_container_do_ioctl(as, groupid, req, param); +} diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 423d9bb9da..e380959dab 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -41,16 +41,7 @@ #include "sysemu/sysemu.h" #include "trace.h" #include "hw/vfio/vfio.h" - -/* Extra debugging, trap acceleration paths for more logging */ -#define VFIO_ALLOW_MMAP 1 -#define VFIO_ALLOW_KVM_INTX 1 -#define VFIO_ALLOW_KVM_MSI 1 -#define VFIO_ALLOW_KVM_MSIX 1 - -enum { - VFIO_DEVICE_TYPE_PCI = 0, -}; +#include "hw/vfio/vfio-common.h" struct VFIOPCIDevice; @@ -77,17 +68,6 @@ typedef struct VFIOQuirk { } data; } VFIOQuirk; -typedef struct VFIORegion { - struct VFIODevice *vbasedev; - off_t fd_offset; /* offset of region within device fd */ - MemoryRegion mem; /* slow, read/write access */ - MemoryRegion mmap_mem; /* direct mapped access */ - void *mmap; - size_t size; - uint32_t flags; /* VFIO region flags (rd/wr/mmap) */ - uint8_t nr; /* cache the region number for debug */ -} VFIORegion; - typedef struct VFIOBAR { VFIORegion region; bool ioport; @@ -143,45 +123,6 @@ enum { VFIO_INT_MSIX = 3, }; -typedef struct VFIOAddressSpace { - AddressSpace *as; - QLIST_HEAD(, VFIOContainer) containers; - QLIST_ENTRY(VFIOAddressSpace) list; -} VFIOAddressSpace; - -static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces = - QLIST_HEAD_INITIALIZER(vfio_address_spaces); - -struct VFIOGroup; - -typedef struct VFIOType1 { - MemoryListener listener; - int error; - bool initialized; -} VFIOType1; - -typedef struct VFIOContainer { - VFIOAddressSpace *space; - int fd; /* /dev/vfio/vfio, empowered by the attached groups */ - struct { - /* enable abstraction to support various iommu backends */ - union { - VFIOType1 type1; - }; - void (*release)(struct VFIOContainer *); - } iommu_data; - QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; - QLIST_HEAD(, VFIOGroup) group_list; - QLIST_ENTRY(VFIOContainer) next; -} VFIOContainer; - -typedef struct VFIOGuestIOMMU { - VFIOContainer *container; - MemoryRegion *iommu; - Notifier n; - QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; -} VFIOGuestIOMMU; - /* Cache of MSI-X setup plus extra mmap and memory region for split BAR map */ typedef struct VFIOMSIXInfo { uint8_t table_bar; @@ -193,29 +134,6 @@ typedef struct VFIOMSIXInfo { void *mmap; } VFIOMSIXInfo; -typedef struct VFIODeviceOps VFIODeviceOps; - -typedef struct VFIODevice { - QLIST_ENTRY(VFIODevice) next; - struct VFIOGroup *group; - char *name; - int fd; - int type; - bool reset_works; - bool needs_reset; - VFIODeviceOps *ops; - unsigned int num_irqs; - unsigned int num_regions; - unsigned int flags; -} VFIODevice; - -struct VFIODeviceOps { - void (*vfio_compute_needs_reset)(VFIODevice *vdev); - int (*vfio_hot_reset_multi)(VFIODevice *vdev); - void (*vfio_eoi)(VFIODevice *vdev); - int (*vfio_populate_device)(VFIODevice *vdev); -}; - typedef struct VFIOPCIDevice { PCIDevice pdev; VFIODevice vbasedev; @@ -247,15 +165,6 @@ typedef struct VFIOPCIDevice { bool rom_read_failed; } VFIOPCIDevice; -typedef struct VFIOGroup { - int fd; - int groupid; - VFIOContainer *container; - QLIST_HEAD(, VFIODevice) device_list; - QLIST_ENTRY(VFIOGroup) next; - QLIST_ENTRY(VFIOGroup) container_next; -} VFIOGroup; - typedef struct VFIORomBlacklistEntry { uint16_t vendor_id; uint16_t device_id; @@ -281,76 +190,14 @@ static const VFIORomBlacklistEntry romblacklist[] = { #define MSIX_CAP_LENGTH 12 -static QLIST_HEAD(, VFIOGroup) - vfio_group_list = QLIST_HEAD_INITIALIZER(vfio_group_list); - -#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. - */ -static int vfio_kvm_device_fd = -1; -#endif - static void vfio_disable_interrupts(VFIOPCIDevice *vdev); static uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len); static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr, uint32_t val, int len); static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled); -static void vfio_put_base_device(VFIODevice *vbasedev); static int vfio_populate_device(VFIODevice *vbasedev); /* - * Common VFIO interrupt disable - */ -static 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); -} - -/* - * INTx - */ -static 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); -} - -#ifdef CONFIG_KVM /* Unused outside of CONFIG_KVM code */ -static 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); -} -#endif - -/* * Disabling BAR mmaping can be slow, but toggling it around INTx can * also be a huge overhead. We try to get the best of both worlds by * waiting until an interrupt to disable mmaps (subsequent transitions @@ -1080,105 +927,6 @@ static void vfio_update_msi(VFIOPCIDevice *vdev) } } -/* - * IO Port/MMIO - Beware of the endians, VFIO is always little endian - */ -static 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; - default: - hw_error("vfio: unsupported write size, %d 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); -} - -static 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; - default: - hw_error("vfio: unsupported read size, %d 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; -} - -static const MemoryRegionOps vfio_region_ops = { - .read = vfio_region_read, - .write = vfio_region_write, - .endianness = DEVICE_LITTLE_ENDIAN, -}; - static void vfio_pci_load_rom(VFIOPCIDevice *vdev) { struct vfio_region_info reg_info = { @@ -2377,305 +2125,6 @@ static void vfio_pci_write_config(PCIDevice *pdev, uint32_t addr, } /* - * 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) -{ - struct vfio_iommu_type1_dma_unmap unmap = { - .argsz = sizeof(unmap), - .flags = 0, - .iova = iova, - .size = size, - }; - - if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - error_report("VFIO_UNMAP_DMA: %d\n", -errno); - return -errno; - } - - 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 the VGA ROM space. - */ - if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || - (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 && - ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { - return 0; - } - - error_report("VFIO_MAP_DMA: %d\n", -errno); - return -errno; -} - -static bool vfio_listener_skipped_section(MemoryRegionSection *section) -{ - return (!memory_region_is_ram(section->mr) && - !memory_region_is_iommu(section->mr)) || - /* - * Sizing an enabled 64-bit BAR can cause spurious mappings to - * addresses in the upper part of the 64-bit address space. These - * are never accessed by the CPU and beyond the address width of - * some IOMMU hardware. TODO: VFIO should tell us the IOMMU width. - */ - section->offset_within_address_space & (1ULL << 63); -} - -static void vfio_iommu_map_notify(Notifier *n, void *data) -{ - VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n); - VFIOContainer *container = giommu->container; - IOMMUTLBEntry *iotlb = data; - MemoryRegion *mr; - hwaddr xlat; - hwaddr len = iotlb->addr_mask + 1; - void *vaddr; - int ret; - - trace_vfio_iommu_map_notify(iotlb->iova, - iotlb->iova + iotlb->addr_mask); - - /* - * The IOMMU TLB entry we have just covers translation through - * this IOMMU to its immediate target. We need to translate - * it the rest of the way through to memory. - */ - mr = address_space_translate(&address_space_memory, - iotlb->translated_addr, - &xlat, &len, iotlb->perm & IOMMU_WO); - if (!memory_region_is_ram(mr)) { - error_report("iommu map to non memory area %"HWADDR_PRIx"\n", - xlat); - return; - } - /* - * Translation truncates length to the IOMMU page size, - * check that it did not truncate too much. - */ - if (len & iotlb->addr_mask) { - error_report("iommu has granularity incompatible with target AS\n"); - return; - } - - if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) { - vaddr = memory_region_get_ram_ptr(mr) + xlat; - - ret = vfio_dma_map(container, iotlb->iova, - iotlb->addr_mask + 1, vaddr, - !(iotlb->perm & IOMMU_WO) || mr->readonly); - if (ret) { - error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx", %p) = %d (%m)", - container, iotlb->iova, - iotlb->addr_mask + 1, vaddr, ret); - } - } else { - ret = vfio_dma_unmap(container, iotlb->iova, iotlb->addr_mask + 1); - if (ret) { - error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iotlb->iova, - iotlb->addr_mask + 1, ret); - } - } -} - -static void vfio_listener_region_add(MemoryListener *listener, - MemoryRegionSection *section) -{ - VFIOContainer *container = container_of(listener, VFIOContainer, - iommu_data.type1.listener); - hwaddr iova, end; - Int128 llend; - void *vaddr; - int ret; - - if (vfio_listener_skipped_section(section)) { - trace_vfio_listener_region_add_skip( - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(int128_sub(section->size, int128_one()))); - return; - } - - if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != - (section->offset_within_region & ~TARGET_PAGE_MASK))) { - error_report("%s received unaligned region", __func__); - return; - } - - iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(TARGET_PAGE_MASK)); - - if (int128_ge(int128_make64(iova), llend)) { - return; - } - - 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()))); - /* - * FIXME: We should do some checking to see if the - * capabilities of the host VFIO IOMMU are adequate to model - * the guest IOMMU - * - * FIXME: For VFIO iommu types which have KVM acceleration to - * avoid bouncing all map/unmaps through qemu this way, this - * 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); - - 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); - - trace_vfio_listener_region_add_ram(iova, end - 1, vaddr); - - ret = vfio_dma_map(container, iova, end - iova, vaddr, section->readonly); - if (ret) { - error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx", %p) = %d (%m)", - container, iova, end - iova, vaddr, ret); - - /* - * 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"); - } - } -} - -static void vfio_listener_region_del(MemoryListener *listener, - MemoryRegionSection *section) -{ - VFIOContainer *container = container_of(listener, VFIOContainer, - iommu_data.type1.listener); - hwaddr iova, end; - int ret; - - if (vfio_listener_skipped_section(section)) { - trace_vfio_listener_region_del_skip( - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(int128_sub(section->size, int128_one()))); - return; - } - - if (unlikely((section->offset_within_address_space & ~TARGET_PAGE_MASK) != - (section->offset_within_region & ~TARGET_PAGE_MASK))) { - error_report("%s received unaligned region", __func__); - return; - } - - if (memory_region_is_iommu(section->mr)) { - VFIOGuestIOMMU *giommu; - - QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) { - if (giommu->iommu == section->mr) { - memory_region_unregister_iommu_notifier(&giommu->n); - QLIST_REMOVE(giommu, giommu_next); - g_free(giommu); - break; - } - } - - /* - * FIXME: We assume the one big unmap below is adequate to - * remove any individual page mappings in the IOMMU which - * might have been copied into VFIO. This works for a page table - * based IOMMU where a big unmap flattens a large range of IO-PTEs. - * That may not be true for all IOMMU types. - */ - } - - iova = TARGET_PAGE_ALIGN(section->offset_within_address_space); - end = (section->offset_within_address_space + int128_get64(section->size)) & - TARGET_PAGE_MASK; - - if (iova >= end) { - return; - } - - trace_vfio_listener_region_del(iova, end - 1); - - ret = vfio_dma_unmap(container, iova, end - iova); - memory_region_unref(section->mr); - if (ret) { - error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iova, end - iova, ret); - } -} - -static MemoryListener vfio_memory_listener = { - .region_add = vfio_listener_region_add, - .region_del = vfio_listener_region_del, -}; - -static void vfio_listener_release(VFIOContainer *container) -{ - memory_listener_unregister(&container->iommu_data.type1.listener); -} - -/* * Interrupt setup */ static void vfio_disable_interrupts(VFIOPCIDevice *vdev) @@ -2849,47 +2298,6 @@ static void vfio_unmap_bar(VFIOPCIDevice *vdev, int nr) } } -static int vfio_mmap_region(Object *obj, VFIORegion *region, - MemoryRegion *mem, MemoryRegion *submem, - void **map, size_t size, off_t offset, - const char *name) -{ - int ret = 0; - VFIODevice *vbasedev = region->vbasedev; - - if (VFIO_ALLOW_MMAP && size && region->flags & - VFIO_REGION_INFO_FLAG_MMAP) { - int prot = 0; - - if (region->flags & VFIO_REGION_INFO_FLAG_READ) { - prot |= PROT_READ; - } - - if (region->flags & VFIO_REGION_INFO_FLAG_WRITE) { - prot |= PROT_WRITE; - } - - *map = mmap(NULL, size, prot, MAP_SHARED, - vbasedev->fd, region->fd_offset + offset); - if (*map == MAP_FAILED) { - *map = NULL; - ret = -errno; - goto empty_region; - } - - memory_region_init_ram_ptr(submem, obj, name, size, *map); - memory_region_set_skip_dump(submem); - } else { -empty_region: - /* Create a zero sized sub-region to make cleanup easy. */ - memory_region_init(submem, obj, name, 0); - } - - memory_region_add_subregion(mem, offset, submem); - - return ret; -} - static void vfio_map_bar(VFIOPCIDevice *vdev, int nr) { VFIOBAR *bar = &vdev->bars[nr]; @@ -3529,345 +2937,6 @@ static VFIODeviceOps vfio_pci_ops = { .vfio_populate_device = vfio_populate_device, }; -static void vfio_reset_handler(void *opaque) -{ - VFIOGroup *group; - VFIODevice *vbasedev; - - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); - } - } - - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->needs_reset) { - vbasedev->ops->vfio_hot_reset_multi(vbasedev); - } - } - } -} - -static void vfio_kvm_device_add_group(VFIOGroup *group) -{ -#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, - }; - - if (!kvm_enabled()) { - return; - } - - if (vfio_kvm_device_fd < 0) { - struct kvm_create_device cd = { - .type = KVM_DEV_TYPE_VFIO, - }; - - if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { - error_report("KVM_CREATE_DEVICE: %m\n"); - return; - } - - 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); - } -#endif -} - -static void vfio_kvm_device_del_group(VFIOGroup *group) -{ -#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, - }; - - if (vfio_kvm_device_fd < 0) { - return; - } - - 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); - } -#endif -} - -static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) -{ - VFIOAddressSpace *space; - - QLIST_FOREACH(space, &vfio_address_spaces, list) { - if (space->as == as) { - return space; - } - } - - /* No suitable VFIOAddressSpace, create a new one */ - space = g_malloc0(sizeof(*space)); - space->as = as; - QLIST_INIT(&space->containers); - - QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); - - return space; -} - -static void vfio_put_address_space(VFIOAddressSpace *space) -{ - if (QLIST_EMPTY(&space->containers)) { - QLIST_REMOVE(space, list); - g_free(space); - } -} - -static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) -{ - VFIOContainer *container; - int ret, fd; - VFIOAddressSpace *space; - - space = vfio_get_address_space(as); - - QLIST_FOREACH(container, &space->containers, next) { - if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - return 0; - } - } - - fd = qemu_open("/dev/vfio/vfio", O_RDWR); - if (fd < 0) { - error_report("vfio: failed to open /dev/vfio/vfio: %m"); - ret = -errno; - goto put_space_exit; - } - - ret = ioctl(fd, VFIO_GET_API_VERSION); - if (ret != VFIO_API_VERSION) { - error_report("vfio: 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; - - if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU)) { - ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); - if (ret) { - error_report("vfio: failed to set group container: %m"); - ret = -errno; - goto free_container_exit; - } - - ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU); - if (ret) { - error_report("vfio: failed to set iommu for container: %m"); - ret = -errno; - 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; - } - - container->iommu_data.type1.initialized = true; - - } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { - ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); - if (ret) { - error_report("vfio: failed to set group container: %m"); - ret = -errno; - goto free_container_exit; - } - - ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU); - if (ret) { - error_report("vfio: failed to set iommu for container: %m"); - ret = -errno; - goto free_container_exit; - } - - /* - * 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. - */ - ret = ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_report("vfio: failed to enable container: %m"); - ret = -errno; - 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); - - } else { - error_report("vfio: No available IOMMU models"); - ret = -EINVAL; - goto free_container_exit; - } - - QLIST_INIT(&container->group_list); - QLIST_INSERT_HEAD(&space->containers, container, next); - - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - - return 0; - -listener_release_exit: - vfio_listener_release(container); - -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; - - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { - error_report("vfio: error disconnecting group %d from container", - group->groupid); - } - - QLIST_REMOVE(group, container_next); - group->container = NULL; - - if (QLIST_EMPTY(&container->group_list)) { - VFIOAddressSpace *space = container->space; - - if (container->iommu_data.release) { - container->iommu_data.release(container); - } - QLIST_REMOVE(container, next); - trace_vfio_disconnect_container(container->fd); - close(container->fd); - g_free(container); - - vfio_put_address_space(space); - } -} - -static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as) -{ - 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_report("vfio: 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(path, O_RDWR); - if (group->fd < 0) { - error_report("vfio: error opening %s: %m", path); - goto free_group_exit; - } - - if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { - error_report("vfio: error getting group status: %m"); - goto close_fd_exit; - } - - if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { - error_report("vfio: error, group %d is not viable, please ensure " - "all devices within the iommu_group are bound to their " - "vfio bus driver.", groupid); - goto close_fd_exit; - } - - group->groupid = groupid; - QLIST_INIT(&group->device_list); - - if (vfio_connect_container(group, as)) { - error_report("vfio: 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); - - vfio_kvm_device_add_group(group); - - return group; - -close_fd_exit: - close(group->fd); - -free_group_exit: - g_free(group); - - return NULL; -} - -static void vfio_put_group(VFIOGroup *group) -{ - if (!QLIST_EMPTY(&group->device_list)) { - return; - } - - 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)) { - qemu_unregister_reset(vfio_reset_handler, NULL); - } -} - static int vfio_populate_device(VFIODevice *vbasedev) { VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev); @@ -3992,57 +3061,6 @@ error: return ret; } -static int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev) -{ - struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) }; - int ret; - - ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); - if (ret < 0) { - error_report("vfio: error getting device %s from group %d: %m", - name, group->groupid); - error_printf("Verify all devices in group %d are bound to vfio-<bus> " - "or pci-stub and not already in use\n", group->groupid); - return ret; - } - - vbasedev->fd = ret; - vbasedev->group = group; - QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); - - ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_INFO, &dev_info); - if (ret) { - error_report("vfio: error getting device info: %m"); - goto error; - } - - vbasedev->num_irqs = dev_info.num_irqs; - vbasedev->num_regions = dev_info.num_regions; - vbasedev->flags = dev_info.flags; - - trace_vfio_get_device(name, dev_info.flags, - dev_info.num_regions, dev_info.num_irqs); - - vbasedev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET); - - ret = vbasedev->ops->vfio_populate_device(vbasedev); - -error: - if (ret) { - vfio_put_base_device(vbasedev); - } - return ret; -} - -void vfio_put_base_device(VFIODevice *vbasedev) -{ - QLIST_REMOVE(vbasedev, next); - vbasedev->group = NULL; - trace_vfio_put_base_device(vbasedev->fd); - close(vbasedev->fd); -} - static void vfio_put_device(VFIOPCIDevice *vdev) { g_free(vdev->vbasedev.name); @@ -4426,47 +3444,3 @@ static void register_vfio_pci_dev_type(void) } type_init(register_vfio_pci_dev_type) - -static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid, - int req, void *param) -{ - VFIOGroup *group; - VFIOContainer *container; - int ret = -1; - - group = vfio_get_group(groupid, as); - if (!group) { - error_report("vfio: group %d not registered", groupid); - return ret; - } - - container = group->container; - if (group->container) { - ret = ioctl(container->fd, req, param); - if (ret < 0) { - error_report("vfio: failed to ioctl container: ret=%d, %s", - ret, strerror(errno)); - } - } - - vfio_put_group(group); - - return ret; -} - -int vfio_container_ioctl(AddressSpace *as, int32_t groupid, - int req, void *param) -{ - /* We allow only certain ioctls to the container */ - switch (req) { - case VFIO_CHECK_EXTENSION: - case VFIO_IOMMU_SPAPR_TCE_GET_INFO: - break; - default: - /* Return an error on unknown requests */ - error_report("vfio: unsupported ioctl %X", req); - return -1; - } - - return vfio_container_do_ioctl(as, groupid, req, param); -} diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h new file mode 100644 index 0000000000..1d5bfe8fcb --- /dev/null +++ b/include/hw/vfio/vfio-common.h @@ -0,0 +1,151 @@ +/* + * 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 "qemu-common.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "qemu/queue.h" +#include "qemu/notify.h" + +/*#define DEBUG_VFIO*/ +#ifdef DEBUG_VFIO +#define DPRINTF(fmt, ...) \ + do { fprintf(stderr, "vfio: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +/* Extra debugging, trap acceleration paths for more logging */ +#define VFIO_ALLOW_MMAP 1 +#define VFIO_ALLOW_KVM_INTX 1 +#define VFIO_ALLOW_KVM_MSI 1 +#define VFIO_ALLOW_KVM_MSIX 1 + +enum { + VFIO_DEVICE_TYPE_PCI = 0, +}; + +typedef struct VFIORegion { + struct VFIODevice *vbasedev; + off_t fd_offset; /* offset of region within device fd */ + MemoryRegion mem; /* slow, read/write access */ + MemoryRegion mmap_mem; /* direct mapped access */ + void *mmap; + size_t size; + uint32_t flags; /* VFIO region flags (rd/wr/mmap) */ + uint8_t nr; /* cache the region number for debug */ +} VFIORegion; + +typedef struct VFIOAddressSpace { + AddressSpace *as; + QLIST_HEAD(, VFIOContainer) containers; + QLIST_ENTRY(VFIOAddressSpace) list; +} VFIOAddressSpace; + +struct VFIOGroup; + +typedef struct VFIOType1 { + MemoryListener listener; + int error; + bool initialized; +} VFIOType1; + +typedef struct VFIOContainer { + VFIOAddressSpace *space; + int fd; /* /dev/vfio/vfio, empowered by the attached groups */ + struct { + /* enable abstraction to support various iommu backends */ + union { + VFIOType1 type1; + }; + void (*release)(struct VFIOContainer *); + } iommu_data; + QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; + QLIST_HEAD(, VFIOGroup) group_list; + QLIST_ENTRY(VFIOContainer) next; +} VFIOContainer; + +typedef struct VFIOGuestIOMMU { + VFIOContainer *container; + MemoryRegion *iommu; + Notifier n; + QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; +} VFIOGuestIOMMU; + +typedef struct VFIODeviceOps VFIODeviceOps; + +typedef struct VFIODevice { + QLIST_ENTRY(VFIODevice) next; + struct VFIOGroup *group; + char *name; + int fd; + int type; + bool reset_works; + bool needs_reset; + VFIODeviceOps *ops; + unsigned int num_irqs; + unsigned int num_regions; + unsigned int flags; +} VFIODevice; + +struct VFIODeviceOps { + void (*vfio_compute_needs_reset)(VFIODevice *vdev); + int (*vfio_hot_reset_multi)(VFIODevice *vdev); + void (*vfio_eoi)(VFIODevice *vdev); + int (*vfio_populate_device)(VFIODevice *vdev); +}; + +typedef struct VFIOGroup { + int fd; + int groupid; + VFIOContainer *container; + QLIST_HEAD(, VFIODevice) device_list; + QLIST_ENTRY(VFIOGroup) next; + QLIST_ENTRY(VFIOGroup) container_next; +} VFIOGroup; + +void vfio_put_base_device(VFIODevice *vbasedev); +void vfio_disable_irqindex(VFIODevice *vbasedev, int index); +void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); +void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); +void vfio_region_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size); +uint64_t vfio_region_read(void *opaque, + hwaddr addr, unsigned size); +void vfio_listener_release(VFIOContainer *container); +int vfio_mmap_region(Object *vdev, VFIORegion *region, + MemoryRegion *mem, MemoryRegion *submem, + void **map, size_t size, off_t offset, + const char *name); +void vfio_reset_handler(void *opaque); +VFIOGroup *vfio_get_group(int groupid, AddressSpace *as); +void vfio_put_group(VFIOGroup *group); +int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev); + +extern const MemoryRegionOps vfio_region_ops; +extern const MemoryListener vfio_memory_listener; +extern QLIST_HEAD(vfio_group_head, VFIOGroup) vfio_group_list; +extern QLIST_HEAD(vfio_as_head, VFIOAddressSpace) vfio_address_spaces; + +#endif /* !HW_VFIO_VFIO_COMMON_H */ diff --git a/trace-events b/trace-events index 0e7aa53407..8acbcce0f0 100644 --- a/trace-events +++ b/trace-events @@ -1416,6 +1416,7 @@ vfio_pci_reset(const char *name) " (%s)" vfio_pci_reset_flr(const char *name) "%s FLR/VFIO_DEVICE_RESET" vfio_pci_reset_pm(const char *name) "%s PCI PM Reset" +# hw/vfio/vfio-common.c vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64 vfio_iommu_map_notify(uint64_t iova_start, uint64_t iova_end) "iommu map @ %"PRIx64" - %"PRIx64 |