[RFC v3 15/19] vfio-user: proxy container connect/disconnect

[John Johnson <john.g.johnson@oracle.com>]

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
---
 hw/vfio/user.h                |  1 +
 include/hw/vfio/vfio-common.h |  3 ++
 hw/vfio/common.c              | 98 +++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/pci.c                 | 24 +++++++++++
 hw/vfio/user.c                |  3 ++
 5 files changed, 129 insertions(+)

diff --git a/hw/vfio/user.h b/hw/vfio/user.h
index f2098f2..8d03e7c 100644
--- a/hw/vfio/user.h
+++ b/hw/vfio/user.h
@@ -85,5 +85,6 @@ void vfio_user_set_handler(VFIODevice *vbasedev,
 int vfio_user_validate_version(VFIODevice *vbasedev, Error **errp);
 
 extern VFIODevIO vfio_dev_io_sock;
+extern VFIOContIO vfio_cont_io_sock;
 
 #endif /* VFIO_USER_H */
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index b498964..c0e7632 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -94,6 +94,7 @@ typedef struct VFIOContainer {
     uint64_t max_dirty_bitmap_size;
     unsigned long pgsizes;
     unsigned int dma_max_mappings;
+    VFIOProxy *proxy;
     QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
     QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
     QLIST_HEAD(, VFIOGroup) group_list;
@@ -300,6 +301,8 @@ 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);
+void vfio_connect_proxy(VFIOProxy *proxy, VFIOGroup *group, AddressSpace *as);
+void vfio_disconnect_proxy(VFIOGroup *group);
 
 extern const MemoryRegionOps vfio_region_ops;
 typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index e19f321..fdd2702 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include CONFIG_DEVICES
 #include <sys/ioctl.h>
 #ifdef CONFIG_KVM
 #include <linux/kvm.h>
@@ -2204,6 +2205,62 @@ put_space_exit:
     return ret;
 }
 
+
+#ifdef CONFIG_VFIO_USER
+
+void vfio_connect_proxy(VFIOProxy *proxy, VFIOGroup *group, AddressSpace *as)
+{
+    VFIOAddressSpace *space;
+    VFIOContainer *container;
+
+    if (QLIST_EMPTY(&vfio_group_list)) {
+        qemu_register_reset(vfio_reset_handler, NULL);
+    }
+
+    QLIST_INSERT_HEAD(&vfio_group_list, group, next);
+
+    /*
+     * try to mirror vfio_connect_container()
+     * as much as possible
+     */
+
+    space = vfio_get_address_space(as);
+
+    container = g_malloc0(sizeof(*container));
+    container->space = space;
+    container->fd = -1;
+    container->io_ops = &vfio_cont_io_sock;
+    QLIST_INIT(&container->giommu_list);
+    QLIST_INIT(&container->hostwin_list);
+    container->proxy = proxy;
+
+    /*
+     * The proxy uses a SW IOMMU in lieu of the HW one
+     * used in the ioctl() version.  Use TYPE1 with the
+     * target's page size for maximum capatibility
+     */
+    container->iommu_type = VFIO_TYPE1_IOMMU;
+    vfio_host_win_add(container, 0, (hwaddr)-1, TARGET_PAGE_SIZE);
+    container->pgsizes = TARGET_PAGE_SIZE;
+
+    container->dirty_pages_supported = true;
+    container->max_dirty_bitmap_size = VFIO_USER_DEF_MAX_XFER;
+    container->dirty_pgsizes = TARGET_PAGE_SIZE;
+
+    QLIST_INIT(&container->group_list);
+    QLIST_INSERT_HEAD(&space->containers, container, next);
+
+    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);
+    container->initialized = true;
+}
+
+#endif /* CONFIG_VFIO_USER */
+
+
 static void vfio_disconnect_container(VFIOGroup *group)
 {
     VFIOContainer *container = group->container;
@@ -2246,6 +2303,47 @@ static void vfio_disconnect_container(VFIOGroup *group)
     }
 }
 
+
+#ifdef CONFIG_VFIO_USER
+
+void vfio_disconnect_proxy(VFIOGroup *group)
+{
+    VFIOContainer *container = group->container;
+    VFIOAddressSpace *space = container->space;
+    VFIOGuestIOMMU *giommu, *tmp;
+
+    /*
+     * try to mirror vfio_disconnect_container()
+     * as much as possible, knowing each device
+     * is in one group and one container
+     */
+
+    QLIST_REMOVE(group, container_next);
+    group->container = NULL;
+
+    /*
+     * Explicitly release the listener first before unset container,
+     * since unset may destroy the backend container if it's the last
+     * group.
+     */
+    memory_listener_unregister(&container->listener);
+
+    QLIST_REMOVE(container, next);
+
+    QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
+        memory_region_unregister_iommu_notifier(
+            MEMORY_REGION(giommu->iommu), &giommu->n);
+        QLIST_REMOVE(giommu, giommu_next);
+        g_free(giommu);
+    }
+
+    g_free(container);
+    vfio_put_address_space(space);
+}
+
+#endif /* CONFIG_VFIO_USER */
+
+
 VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp)
 {
     VFIOGroup *group;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 6f2d2fd..d657b01 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3489,6 +3489,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     VFIODevice *vbasedev = &vdev->vbasedev;
     SocketAddress addr;
     VFIOProxy *proxy;
+    VFIOGroup *group = NULL;
     struct vfio_device_info info;
     int ret;
     Error *err = NULL;
@@ -3537,6 +3538,19 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     vbasedev->io_ops = &vfio_dev_io_sock;
     vbasedev->valid_ops = &vfio_pci_valid_ops;
 
+    /*
+     * each device gets its own group and container
+     * make them unrelated to any host IOMMU groupings
+     */
+    group = g_malloc0(sizeof(*group));
+    group->fd = -1;
+    group->groupid = -1;
+    QLIST_INIT(&group->device_list);
+    QLIST_INSERT_HEAD(&group->device_list, vbasedev, next);
+    vbasedev->group = group;
+
+    vfio_connect_proxy(proxy, group, pci_device_iommu_address_space(pdev));
+
     ret = VDEV_GET_INFO(vbasedev, &info);
     if (ret) {
         error_setg_errno(errp, -ret, "get info failure");
@@ -3644,6 +3658,9 @@ out_teardown:
     vfio_teardown_msi(vdev);
     vfio_bars_exit(vdev);
 error:
+    if (group != NULL) {
+        vfio_disconnect_proxy(group);
+    }
     vfio_user_disconnect(proxy);
     error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name);
 }
@@ -3652,6 +3669,13 @@ static void vfio_user_instance_finalize(Object *obj)
 {
     VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
     VFIODevice *vbasedev = &vdev->vbasedev;
+    VFIOGroup *group = vbasedev->group;
+
+    if (group != NULL) {
+        vfio_disconnect_proxy(group);
+        g_free(group);
+        vbasedev->group = NULL;
+    }
 
     vfio_put_device(vdev);
 
diff --git a/hw/vfio/user.c b/hw/vfio/user.c
index 1e220b9..70fe7a6 100644
--- a/hw/vfio/user.c
+++ b/hw/vfio/user.c
@@ -1224,3 +1224,6 @@ VFIODevIO vfio_dev_io_sock = {
     .region_write = vfio_user_io_region_write,
 };
 
+
+VFIOContIO vfio_cont_io_sock = {
+};
-- 
1.8.3.1