Adding qemu as a submodule of KVMFORNFV

This Patch includes the changes to add qemu as a submodule to
kvmfornfv repo and make use of the updated latest qemu for the
execution of all testcase
Change-Id: I1280af507a857675c7f81d30c95255635667bdd7
Signed-off-by:RajithaY<rajithax.yerrumsetty@intel.com>

1 files changed, 0 insertions, 1192 deletions

diff --git a/qemu/hw/vfio/common.c b/qemu/hw/vfio/common.c
deleted file mode 100644
index f27db36fb..000000000
--- a/qemu/hw/vfio/common.c
+++ /dev/null
@@ -1,1192 +0,0 @@
-/*
- * 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 "qemu/osdep.h"
-#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_group_list);
-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", -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 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", -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.
-     */
-    rcu_read_lock();
-    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"",
-                     xlat);
-        goto out;
-    }
-    /*
-     * 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");
-        goto out;
-    }
-
-    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);
-        }
-    }
-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, listener);
-    hwaddr iova, end;
-    Int128 llend, llsize;
-    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;
-    }
-    end = int128_get64(int128_sub(llend, int128_one()));
-
-    if ((iova < container->min_iova) || (end > container->max_iova)) {
-        error_report("vfio: IOMMU container %p can't map guest IOVA region"
-                     " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx,
-                     container, iova, end);
-        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, end);
-        /*
-         * 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).
-         */
-        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 */
-
-    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, vaddr);
-
-    llsize = int128_sub(llend, int128_make64(iova));
-
-    ret = vfio_dma_map(container, iova, int128_get64(llsize),
-                       vaddr, section->readonly);
-    if (ret) {
-        error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
-                     "0x%"HWADDR_PRIx", %p) = %d (%m)",
-                     container, iova, int128_get64(llsize), vaddr, ret);
-        goto fail;
-    }
-
-    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, 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 const 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->listener);
-}
-
-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 &&
-            !(region->size & ~qemu_real_host_page_mask)) {
-
-            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;
-}
-
-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--) {
-                memory_region_del_subregion(region->mem, &region->mmaps[i].mem);
-                munmap(region->mmaps[i].mmap, region->mmaps[i].size);
-                object_unparent(OBJECT(&region->mmaps[i].mem));
-                region->mmaps[i].mmap = NULL;
-            }
-
-            return ret;
-        }
-
-        name = g_strdup_printf("%s mmaps[%d]",
-                               memory_region_name(region->mem), i);
-        memory_region_init_ram_ptr(&region->mmaps[i].mem,
-                                   memory_region_owner(region->mem),
-                                   name, region->mmaps[i].size,
-                                   region->mmaps[i].mmap);
-        g_free(name);
-        memory_region_set_skip_dump(&region->mmaps[i].mem);
-        memory_region_add_subregion(region->mem, region->mmaps[i].offset,
-                                    &region->mmaps[i].mem);
-
-        trace_vfio_region_mmap(memory_region_name(&region->mmaps[i].mem),
-                               region->mmaps[i].offset,
-                               region->mmaps[i].offset +
-                               region->mmaps[i].size - 1);
-    }
-
-    return 0;
-}
-
-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, &region->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(&region->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);
-}
-
-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(&region->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) {
-            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("Failed to create KVM VFIO device: %m");
-            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) ||
-        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) {
-            error_report("vfio: failed to set group container: %m");
-            ret = -errno;
-            goto free_container_exit;
-        }
-
-        ret = ioctl(fd, VFIO_SET_IOMMU,
-                    v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU);
-        if (ret) {
-            error_report("vfio: failed to set iommu for container: %m");
-            ret = -errno;
-            goto free_container_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;
-        }
-    } 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");
-            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;
-        }
-
-        /*
-         * 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);
-
-    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;
-        VFIOGuestIOMMU *giommu, *tmp;
-
-        vfio_listener_release(container);
-        QLIST_REMOVE(container, next);
-
-        QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
-            memory_region_unregister_iommu_notifier(&giommu->n);
-            QLIST_REMOVE(giommu, giommu_next);
-            g_free(giommu);
-        }
-
-        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 (!group || !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, fd;
-
-    fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
-    if (fd < 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 fd;
-    }
-
-    ret = ioctl(fd, VFIO_DEVICE_GET_INFO, &dev_info);
-    if (ret) {
-        error_report("vfio: error getting device info: %m");
-        close(fd);
-        return ret;
-    }
-
-    vbasedev->fd = fd;
-    vbasedev->group = group;
-    QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
-
-    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);
-    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;
-    (*info)->argsz = argsz;
-
-    if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) {
-        g_free(*info);
-        return -errno;
-    }
-
-    return 0;
-}
-
-/*
- * 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 0;
-}
-
-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);
-}