[PATCH V7 19/29] vfio-pci: cpr part 1 (fd and dma)

[Steve Sistare]

Enable vfio-pci devices to be saved and restored across an exec restart
of qemu.

At vfio creation time, save the value of vfio container, group, and device
descriptors in cpr state.

In cpr-save and cpr-exec, suspend the use of virtual addresses in DMA
mappings with VFIO_DMA_UNMAP_FLAG_VADDR, because guest ram will be remapped
at a different VA after exec.  DMA to already-mapped pages continues.  Save
the msi message area as part of vfio-pci vmstate, save the interrupt and
notifier eventfd's in cpr state, and clear the close-on-exec flag for the
vfio descriptors.  The flag is not cleared earlier because the descriptors
should not persist across miscellaneous fork and exec calls that may be
performed during normal operation.

On qemu restart, vfio_realize() finds the saved descriptors, uses
the descriptors, and notes that the device is being reused.  Device and
iommu state is already configured, so operations in vfio_realize that
would modify the configuration are skipped for a reused device, including
vfio ioctl's and writes to PCI configuration space.  The result is that
vfio_realize constructs qemu data structures that reflect the current
state of the device.  However, the reconstruction is not complete until
cpr-load is called. cpr-load loads the msi data and finds eventfds in cpr
state.  It rebuilds vector data structures and attaches the interrupts to
the new KVM instance.  cpr-load then invokes the main vfio listener callback,
which walks the flattened ranges of the vfio_address_spaces and calls
VFIO_DMA_MAP_FLAG_VADDR to inform the kernel of the new VA's.  Lastly, it
starts the VM and suppresses vfio pci device reset.

This functionality is delivered by 3 patches for clarity.  Part 1 handles
device file descriptors and DMA.  Part 2 adds eventfd and MSI/MSI-X vector
support.  Part 3 adds INTX support.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 MAINTAINERS                   |   1 +
 hw/pci/pci.c                  |  10 ++++
 hw/vfio/common.c              | 115 ++++++++++++++++++++++++++++++++++++++----
 hw/vfio/cpr.c                 |  94 ++++++++++++++++++++++++++++++++++
 hw/vfio/meson.build           |   1 +
 hw/vfio/pci.c                 |  77 ++++++++++++++++++++++++++++
 hw/vfio/trace-events          |   1 +
 include/hw/pci/pci.h          |   1 +
 include/hw/vfio/vfio-common.h |   8 +++
 include/migration/cpr.h       |   3 ++
 migration/cpr.c               |  10 +++-
 migration/target.c            |  14 +++++
 12 files changed, 324 insertions(+), 11 deletions(-)
 create mode 100644 hw/vfio/cpr.c

diff --git a/MAINTAINERS b/MAINTAINERS
index cfe7480..feed239 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2992,6 +2992,7 @@ CPR
 M: Steve Sistare <steven.sistare@oracle.com>
 M: Mark Kanda <mark.kanda@oracle.com>
 S: Maintained
+F: hw/vfio/cpr.c
 F: include/migration/cpr.h
 F: migration/cpr.c
 F: qapi/cpr.json
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 0fd21e1..e35df4f 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -307,6 +307,16 @@ static void pci_do_device_reset(PCIDevice *dev)
 {
     int r;
 
+    /*
+     * A reused vfio-pci device is already configured, so do not reset it
+     * during qemu_system_reset prior to cpr-load, else interrupts may be
+     * lost.  By contrast, pure-virtual pci devices may be reset here and
+     * updated with new state in cpr-load with no ill effects.
+     */
+    if (dev->reused) {
+        return;
+    }
+
     pci_device_deassert_intx(dev);
     assert(dev->irq_state == 0);
 
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 5b87f95..90f66ad 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -31,6 +31,7 @@
 #include "exec/memory.h"
 #include "exec/ram_addr.h"
 #include "hw/hw.h"
+#include "migration/cpr.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qemu/range.h"
@@ -459,6 +460,8 @@ static int vfio_dma_unmap(VFIOContainer *container,
         .size = size,
     };
 
+    assert(!container->reused);
+
     if (iotlb && container->dirty_pages_supported &&
         vfio_devices_all_running_and_saving(container)) {
         return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
@@ -495,12 +498,24 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr 
iova,
 {
     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,
     };
 
+    /*
+     * Set the new vaddr for any mappings registered during cpr-load.
+     * Reused is cleared thereafter.
+     */
+    if (container->reused) {
+        map.flags = VFIO_DMA_MAP_FLAG_VADDR;
+        if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map)) {
+            goto fail;
+        }
+        return 0;
+    }
+
+    map.flags = VFIO_DMA_MAP_FLAG_READ;
     if (!readonly) {
         map.flags |= VFIO_DMA_MAP_FLAG_WRITE;
     }
@@ -516,7 +531,9 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr 
iova,
         return 0;
     }
 
-    error_report("VFIO_MAP_DMA failed: %s", strerror(errno));
+fail:
+    error_report("vfio_dma_map %s (iova %lu, size %ld, va %p): %s",
+        (container->reused ? "VADDR" : ""), iova, size, vaddr, 
strerror(errno));
     return -errno;
 }
 
@@ -865,6 +882,12 @@ static void vfio_listener_region_add(MemoryListener 
*listener,
                                      MemoryRegionSection *section)
 {
     VFIOContainer *container = container_of(listener, VFIOContainer, listener);
+    vfio_container_region_add(container, section);
+}
+
+void vfio_container_region_add(VFIOContainer *container,
+                               MemoryRegionSection *section)
+{
     hwaddr iova, end;
     Int128 llend, llsize;
     void *vaddr;
@@ -985,6 +1008,7 @@ static void vfio_listener_region_add(MemoryListener 
*listener,
         int iommu_idx;
 
         trace_vfio_listener_region_add_iommu(iova, end);
+
         /*
          * FIXME: For VFIO iommu types which have KVM acceleration to
          * avoid bouncing all map/unmaps through qemu this way, this
@@ -1459,6 +1483,12 @@ static void vfio_listener_release(VFIOContainer 
*container)
     }
 }
 
+void vfio_listener_register(VFIOContainer *container)
+{
+    container->listener = vfio_memory_listener;
+    memory_listener_register(&container->listener, container->space->as);
+}
+
 static struct vfio_info_cap_header *
 vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id)
 {
@@ -1878,6 +1908,18 @@ static int vfio_init_container(VFIOContainer *container, 
int group_fd,
 {
     int iommu_type, ret;
 
+    /*
+     * If container is reused, just set its type and skip the ioctls, as the
+     * container and group are already configured in the kernel.
+     * VFIO_TYPE1v2_IOMMU is the only type that supports reuse/cpr.
+     * If you ever add new types or spapr cpr support, kind reader, please
+     * also implement VFIO_GET_IOMMU.
+     */
+    if (container->reused) {
+        container->iommu_type = VFIO_TYPE1v2_IOMMU;
+        return 0;
+    }
+
     iommu_type = vfio_get_iommu_type(container, errp);
     if (iommu_type < 0) {
         return iommu_type;
@@ -1982,9 +2024,12 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
 {
     VFIOContainer *container;
     int ret, fd;
+    bool reused;
     VFIOAddressSpace *space;
 
     space = vfio_get_address_space(as);
+    fd = cpr_find_fd("vfio_container_for_group", group->groupid);
+    reused = (fd > 0);
 
     /*
      * VFIO is currently incompatible with discarding of RAM insofar as the
@@ -2017,8 +2062,16 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
      * details once we know which type of IOMMU we are using.
      */
 
+    /*
+     * If the container is reused, then the group is already attached in the
+     * kernel.  If a container with matching fd is found, then update the
+     * userland group list and return.  It not, then after the loop, create
+     * the container struct and group list.
+     */
+
     QLIST_FOREACH(container, &space->containers, next) {
-        if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
+        if ((reused && container->fd == fd) ||
+            !ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {
             ret = vfio_ram_block_discard_disable(container, true);
             if (ret) {
                 error_setg_errno(errp, -ret,
@@ -2032,12 +2085,19 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
             }
             group->container = container;
             QLIST_INSERT_HEAD(&container->group_list, group, container_next);
-            vfio_kvm_device_add_group(group);
+            if (!reused) {
+                vfio_kvm_device_add_group(group);
+                cpr_save_fd("vfio_container_for_group", group->groupid,
+                            container->fd);
+            }
             return 0;
         }
     }
 
-    fd = qemu_open_old("/dev/vfio/vfio", O_RDWR);
+    if (!reused) {
+        fd = qemu_open_old("/dev/vfio/vfio", O_RDWR);
+    }
+
     if (fd < 0) {
         error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio");
         ret = -errno;
@@ -2055,6 +2115,7 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
     container = g_malloc0(sizeof(*container));
     container->space = space;
     container->fd = fd;
+    container->reused = reused;
     container->error = NULL;
     container->dirty_pages_supported = false;
     container->dma_max_mappings = 0;
@@ -2181,9 +2242,16 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
     group->container = container;
     QLIST_INSERT_HEAD(&container->group_list, group, container_next);
 
-    container->listener = vfio_memory_listener;
-
-    memory_listener_register(&container->listener, container->space->as);
+    /*
+     * If reused, register the listener later, after all state that may
+     * affect regions and mapping boundaries has been cpr-load'ed.  Later,
+     * the listener will invoke its callback on each flat section and call
+     * vfio_dma_map to supply the new vaddr, and the calls will match the
+     * mappings remembered by the kernel.
+     */
+    if (!reused) {
+        vfio_listener_register(container);
+    }
 
     if (container->error) {
         ret = -1;
@@ -2193,6 +2261,9 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
     }
 
     container->initialized = true;
+    if (!reused) {
+        cpr_save_fd("vfio_container_for_group", group->groupid, fd);
+    }
 
     return 0;
 listener_release_exit:
@@ -2222,6 +2293,7 @@ static void vfio_disconnect_container(VFIOGroup *group)
 
     QLIST_REMOVE(group, container_next);
     group->container = NULL;
+    cpr_delete_fd("vfio_container_for_group", group->groupid);
 
     /*
      * Explicitly release the listener first before unset container,
@@ -2270,6 +2342,7 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, 
Error **errp)
     VFIOGroup *group;
     char path[32];
     struct vfio_group_status status = { .argsz = sizeof(status) };
+    bool reused;
 
     QLIST_FOREACH(group, &vfio_group_list, next) {
         if (group->groupid == groupid) {
@@ -2287,7 +2360,13 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, 
Error **errp)
     group = g_malloc0(sizeof(*group));
 
     snprintf(path, sizeof(path), "/dev/vfio/%d", groupid);
-    group->fd = qemu_open_old(path, O_RDWR);
+
+    group->fd = cpr_find_fd("vfio_group", groupid);
+    reused = (group->fd >= 0);
+    if (!reused) {
+        group->fd = qemu_open_old(path, O_RDWR);
+    }
+
     if (group->fd < 0) {
         error_setg_errno(errp, errno, "failed to open %s", path);
         goto free_group_exit;
@@ -2321,6 +2400,10 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, 
Error **errp)
 
     QLIST_INSERT_HEAD(&vfio_group_list, group, next);
 
+    if (!reused) {
+        cpr_save_fd("vfio_group", groupid, group->fd);
+    }
+
     return group;
 
 close_fd_exit:
@@ -2345,6 +2428,7 @@ void vfio_put_group(VFIOGroup *group)
     vfio_disconnect_container(group);
     QLIST_REMOVE(group, next);
     trace_vfio_put_group(group->fd);
+    cpr_delete_fd("vfio_group", group->groupid);
     close(group->fd);
     g_free(group);
 
@@ -2358,8 +2442,14 @@ int vfio_get_device(VFIOGroup *group, const char *name,
 {
     struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) };
     int ret, fd;
+    bool reused;
+
+    fd = cpr_find_fd(name, 0);
+    reused = (fd >= 0);
+    if (!reused) {
+        fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
+    }
 
-    fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name);
     if (fd < 0) {
         error_setg_errno(errp, errno, "error getting device from group %d",
                          group->groupid);
@@ -2404,6 +2494,10 @@ int vfio_get_device(VFIOGroup *group, const char *name,
     vbasedev->num_irqs = dev_info.num_irqs;
     vbasedev->num_regions = dev_info.num_regions;
     vbasedev->flags = dev_info.flags;
+    vbasedev->reused = reused;
+    if (!reused) {
+        cpr_save_fd(name, 0, fd);
+    }
 
     trace_vfio_get_device(name, dev_info.flags, dev_info.num_regions,
                           dev_info.num_irqs);
@@ -2420,6 +2514,7 @@ void vfio_put_base_device(VFIODevice *vbasedev)
     QLIST_REMOVE(vbasedev, next);
     vbasedev->group = NULL;
     trace_vfio_put_base_device(vbasedev->fd);
+    cpr_delete_fd(vbasedev->name, 0);
     close(vbasedev->fd);
 }
 
diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c
new file mode 100644
index 0000000..2c39cd5
--- /dev/null
+++ b/hw/vfio/cpr.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+#include <linux/vfio.h>
+#include "hw/vfio/vfio-common.h"
+#include "sysemu/kvm.h"
+#include "qapi/error.h"
+#include "trace.h"
+
+static int
+vfio_dma_unmap_vaddr_all(VFIOContainer *container, Error **errp)
+{
+    struct vfio_iommu_type1_dma_unmap unmap = {
+        .argsz = sizeof(unmap),
+        .flags = VFIO_DMA_UNMAP_FLAG_VADDR | VFIO_DMA_UNMAP_FLAG_ALL,
+        .iova = 0,
+        .size = 0,
+    };
+    if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
+        error_setg_errno(errp, errno, "vfio_dma_unmap_vaddr_all");
+        return -errno;
+    }
+    return 0;
+}
+
+bool vfio_is_cpr_capable(VFIOContainer *container, Error **errp)
+{
+    if (!ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UPDATE_VADDR) ||
+        !ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UNMAP_ALL)) {
+        error_setg(errp, "VFIO container does not support VFIO_UPDATE_VADDR "
+                         "or VFIO_UNMAP_ALL");
+        return false;
+    } else {
+        return true;
+    }
+}
+
+/*
+ * Verify that all containers support CPR, and unmap all dma vaddr's.
+ */
+int vfio_cpr_save(Error **errp)
+{
+    ERRP_GUARD();
+    VFIOAddressSpace *space;
+    VFIOContainer *container;
+
+    QLIST_FOREACH(space, &vfio_address_spaces, list) {
+        QLIST_FOREACH(container, &space->containers, next) {
+            if (!vfio_is_cpr_capable(container, errp)) {
+                return -1;
+            }
+            if (vfio_dma_unmap_vaddr_all(container, errp)) {
+                return -1;
+            }
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * Register the listener for each container, which causes its callback to be
+ * invoked for every flat section.  The callback will see that the container
+ * is reused, and call vfo_dma_map with the new vaddr.
+ */
+int vfio_cpr_load(Error **errp)
+{
+    VFIOAddressSpace *space;
+    VFIOContainer *container;
+    VFIOGroup *group;
+    VFIODevice *vbasedev;
+
+    QLIST_FOREACH(space, &vfio_address_spaces, list) {
+        QLIST_FOREACH(container, &space->containers, next) {
+            if (!vfio_is_cpr_capable(container, errp)) {
+                return -1;
+            }
+            vfio_listener_register(container);
+            container->reused = false;
+        }
+    }
+    QLIST_FOREACH(group, &vfio_group_list, next) {
+        QLIST_FOREACH(vbasedev, &group->device_list, next) {
+            vbasedev->reused = false;
+        }
+    }
+    return 0;
+}
diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build
index da9af29..e247b2b 100644
--- a/hw/vfio/meson.build
+++ b/hw/vfio/meson.build
@@ -5,6 +5,7 @@ vfio_ss.add(files(
   'migration.c',
 ))
 vfio_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files(
+  'cpr.c',
   'display.c',
   'pci-quirks.c',
   'pci.c',
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index a90cce2..acac8a7 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -30,6 +30,7 @@
 #include "hw/qdev-properties-system.h"
 #include "migration/vmstate.h"
 #include "qapi/qmp/qdict.h"
+#include "migration/cpr.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
@@ -2926,6 +2927,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
         vfio_put_group(group);
         goto error;
     }
+    pdev->reused = vdev->vbasedev.reused;
 
     vfio_populate_device(vdev, &err);
     if (err) {
@@ -3195,6 +3197,11 @@ static void vfio_pci_reset(DeviceState *dev)
 {
     VFIOPCIDevice *vdev = VFIO_PCI(dev);
 
+    /* Do not reset the device during qemu_system_reset prior to cpr-load */
+    if (vdev->pdev.reused) {
+        return;
+    }
+
     trace_vfio_pci_reset(vdev->vbasedev.name);
 
     vfio_pci_pre_reset(vdev);
@@ -3302,6 +3309,75 @@ static Property vfio_pci_dev_properties[] = {
     DEFINE_PROP_END_OF_LIST(),
 };
 
+static void vfio_merge_config(VFIOPCIDevice *vdev)
+{
+    PCIDevice *pdev = &vdev->pdev;
+    int size = MIN(pci_config_size(pdev), vdev->config_size);
+    g_autofree uint8_t *phys_config = g_malloc(size);
+    uint32_t mask;
+    int ret, i;
+
+    ret = pread(vdev->vbasedev.fd, phys_config, size, vdev->config_offset);
+    if (ret < size) {
+        ret = ret < 0 ? errno : EFAULT;
+        error_report("failed to read device config space: %s", strerror(ret));
+        return;
+    }
+
+    for (i = 0; i < size; i++) {
+        mask = vdev->emulated_config_bits[i];
+        pdev->config[i] = (pdev->config[i] & mask) | (phys_config[i] & ~mask);
+    }
+}
+
+/*
+ * The kernel may change non-emulated config bits.  Exclude them from the
+ * changed-bits check in get_pci_config_device.
+ */
+static int vfio_pci_pre_load(void *opaque)
+{
+    VFIOPCIDevice *vdev = opaque;
+    PCIDevice *pdev = &vdev->pdev;
+    int size = MIN(pci_config_size(pdev), vdev->config_size);
+    int i;
+
+    for (i = 0; i < size; i++) {
+        pdev->cmask[i] &= vdev->emulated_config_bits[i];
+    }
+
+    return 0;
+}
+
+static int vfio_pci_post_load(void *opaque, int version_id)
+{
+    VFIOPCIDevice *vdev = opaque;
+    PCIDevice *pdev = &vdev->pdev;
+
+    vfio_merge_config(vdev);
+
+    pdev->reused = false;
+
+    return 0;
+}
+
+static bool vfio_pci_needed(void *opaque)
+{
+    return cpr_get_mode() == CPR_MODE_RESTART;
+}
+
+static const VMStateDescription vfio_pci_vmstate = {
+    .name = "vfio-pci",
+    .unmigratable = 1,
+    .version_id = 0,
+    .minimum_version_id = 0,
+    .pre_load = vfio_pci_pre_load,
+    .post_load = vfio_pci_post_load,
+    .needed = vfio_pci_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -3309,6 +3385,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, 
void *data)
 
     dc->reset = vfio_pci_reset;
     device_class_set_props(dc, vfio_pci_dev_properties);
+    dc->vmsd = &vfio_pci_vmstate;
     dc->desc = "VFIO-based PCI device assignment";
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     pdc->realize = vfio_realize;
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 0ef1b5f..63dd0fe 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -118,6 +118,7 @@ vfio_region_sparse_mmap_header(const char *name, int index, 
int nr_areas) "Devic
 vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) 
"sparse entry %d [0x%lx - 0x%lx]"
 vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t 
subtype) "%s index %d, %08x/%0x8"
 vfio_dma_unmap_overflow_workaround(void) ""
+vfio_region_remap(const char *name, int fd, uint64_t iova_start, uint64_t 
iova_end, void *vaddr) "%s fd %d 0x%"PRIx64" - 0x%"PRIx64" [%p]"
 
 # platform.c
 vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group 
#%d"
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index cc63dd4..8557e82 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -361,6 +361,7 @@ struct PCIDevice {
     /* ID of standby device in net_failover pair */
     char *failover_pair_id;
     uint32_t acpi_index;
+    bool reused;
 };
 
 void pci_register_bar(PCIDevice *pci_dev, int region_num,
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 1641753..bc23c29 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -85,6 +85,7 @@ typedef struct VFIOContainer {
     Error *error;
     bool initialized;
     bool dirty_pages_supported;
+    bool reused;
     uint64_t dirty_pgsizes;
     uint64_t max_dirty_bitmap_size;
     unsigned long pgsizes;
@@ -136,6 +137,7 @@ typedef struct VFIODevice {
     bool no_mmap;
     bool ram_block_discard_allowed;
     bool enable_migration;
+    bool reused;
     VFIODeviceOps *ops;
     unsigned int num_irqs;
     unsigned int num_regions;
@@ -212,6 +214,9 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, 
Error **errp);
 void vfio_put_group(VFIOGroup *group);
 int vfio_get_device(VFIOGroup *group, const char *name,
                     VFIODevice *vbasedev, Error **errp);
+int vfio_cpr_save(Error **errp);
+int vfio_cpr_load(Error **errp);
+bool vfio_is_cpr_capable(VFIOContainer *container, Error **errp);
 
 extern const MemoryRegionOps vfio_region_ops;
 typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
@@ -236,6 +241,9 @@ struct vfio_info_cap_header *
 vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id);
 #endif
 extern const MemoryListener vfio_prereg_listener;
+void vfio_listener_register(VFIOContainer *container);
+void vfio_container_region_add(VFIOContainer *container,
+                               MemoryRegionSection *section);
 
 int vfio_spapr_create_window(VFIOContainer *container,
                              MemoryRegionSection *section,
diff --git a/include/migration/cpr.h b/include/migration/cpr.h
index a4da24e..a4007cf 100644
--- a/include/migration/cpr.h
+++ b/include/migration/cpr.h
@@ -25,4 +25,7 @@ int cpr_state_save(Error **errp);
 int cpr_state_load(Error **errp);
 void cpr_state_print(void);
 
+int cpr_vfio_save(Error **errp);
+int cpr_vfio_load(Error **errp);
+
 #endif
diff --git a/migration/cpr.c b/migration/cpr.c
index 37eca66..cee82cf 100644
--- a/migration/cpr.c
+++ b/migration/cpr.c
@@ -7,6 +7,7 @@
 
 #include "qemu/osdep.h"
 #include "exec/memory.h"
+#include "hw/vfio/vfio-common.h"
 #include "io/channel-buffer.h"
 #include "io/channel-file.h"
 #include "migration.h"
@@ -101,7 +102,9 @@ void qmp_cpr_exec(strList *args, Error **errp)
         error_setg(errp, "cpr-exec requires cpr-save with restart mode");
         return;
     }
-
+    if (cpr_vfio_save(errp)) {
+        return;
+    }
     cpr_walk_fd(preserve_fd, 0);
     if (cpr_state_save(errp)) {
         return;
@@ -139,6 +142,11 @@ void qmp_cpr_load(const char *filename, Error **errp)
         goto out;
     }
 
+    if (cpr_get_mode() == CPR_MODE_RESTART &&
+        cpr_vfio_load(errp)) {
+        goto out;
+    }
+
     state = global_state_get_runstate();
     if (state == RUN_STATE_RUNNING) {
         vm_start();
diff --git a/migration/target.c b/migration/target.c
index 4390bf0..984bc9e 100644
--- a/migration/target.c
+++ b/migration/target.c
@@ -8,6 +8,7 @@
 #include "qemu/osdep.h"
 #include "qapi/qapi-types-migration.h"
 #include "migration.h"
+#include "migration/cpr.h"
 #include CONFIG_DEVICES
 
 #ifdef CONFIG_VFIO
@@ -22,8 +23,21 @@ void populate_vfio_info(MigrationInfo *info)
         info->vfio->transferred = vfio_mig_bytes_transferred();
     }
 }
+
+int cpr_vfio_save(Error **errp)
+{
+    return vfio_cpr_save(errp);
+}
+
+int cpr_vfio_load(Error **errp)
+{
+    return vfio_cpr_load(errp);
+}
+
 #else
 
 void populate_vfio_info(MigrationInfo *info) {}
+int cpr_vfio_save(Error **errp) { return 0; }
+int cpr_vfio_load(Error **errp) { return 0; }
 
 #endif /* CONFIG_VFIO */
-- 
1.8.3.1