[RFC,v9,23/23] vdpa: Add x-svq to NetdevVhostVDPAOptions

diff --git a/qapi/net.json b/qapi/net.json
index 9af11e9a3b..75ba2cb989 100644
--- a/qapi/net.json
+++ b/qapi/net.json
@@ -445,12 +445,19 @@ 
 # @queues: number of queues to be created for multiqueue vhost-vdpa
 #          (default: 1)
 #
+# @x-svq: Start device with (experimental) shadow virtqueue. (Since 7.1)
+#         (default: false)
+#
+# Features:
+# @unstable: Member @x-svq is experimental.
+#
 # Since: 5.1
 ##
 { 'struct': 'NetdevVhostVDPAOptions',
   'data': {
     '*vhostdev':     'str',
-    '*queues':       'int' } }
+    '*queues':       'int',
+    '*x-svq':        {'type': 'bool', 'features' : [ 'unstable'] } } }
 
 ##
 # @NetdevVmnetHostOptions:
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index bb6ac7d96c..3f10636e05 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -93,6 +93,30 @@  const int vdpa_feature_bits[] = {
     VHOST_INVALID_FEATURE_BIT
 };
 
+/** Supported device specific feature bits with SVQ */
+static const uint64_t vdpa_svq_device_features =
+    BIT_ULL(VIRTIO_NET_F_CSUM) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_CSUM) |
+    BIT_ULL(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) |
+    BIT_ULL(VIRTIO_NET_F_MTU) |
+    BIT_ULL(VIRTIO_NET_F_MAC) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_TSO4) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_TSO6) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_ECN) |
+    BIT_ULL(VIRTIO_NET_F_GUEST_UFO) |
+    BIT_ULL(VIRTIO_NET_F_HOST_TSO4) |
+    BIT_ULL(VIRTIO_NET_F_HOST_TSO6) |
+    BIT_ULL(VIRTIO_NET_F_HOST_ECN) |
+    BIT_ULL(VIRTIO_NET_F_HOST_UFO) |
+    BIT_ULL(VIRTIO_NET_F_MRG_RXBUF) |
+    BIT_ULL(VIRTIO_NET_F_STATUS) |
+    BIT_ULL(VIRTIO_NET_F_CTRL_VQ) |
+    BIT_ULL(VIRTIO_NET_F_MQ) |
+    BIT_ULL(VIRTIO_F_ANY_LAYOUT) |
+    BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR) |
+    BIT_ULL(VIRTIO_NET_F_RSC_EXT) |
+    BIT_ULL(VIRTIO_NET_F_STANDBY);
+
 VHostNetState *vhost_vdpa_get_vhost_net(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
@@ -151,7 +175,11 @@  err_init:
 static void vhost_vdpa_cleanup(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    struct vhost_dev *dev = &s->vhost_net->dev;
 
+    if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
+        g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
+    }
     if (s->vhost_net) {
         vhost_net_cleanup(s->vhost_net);
         g_free(s->vhost_net);
@@ -454,6 +482,14 @@  static uint64_t vhost_vdpa_net_iov_len(const struct iovec *iov,
     return len;
 }
 
+static int vhost_vdpa_get_iova_range(int fd,
+                                     struct vhost_vdpa_iova_range *iova_range)
+{
+    int ret = ioctl(fd, VHOST_VDPA_GET_IOVA_RANGE, iova_range);
+
+    return ret < 0 ? -errno : 0;
+}
+
 static CVQElement *vhost_vdpa_net_cvq_copy_elem(VhostVDPAState *s,
                                                 VirtQueueElement *elem)
 {
@@ -628,7 +664,9 @@  static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
                                            int vdpa_device_fd,
                                            int queue_pair_index,
                                            int nvqs,
-                                           bool is_datapath)
+                                           bool is_datapath,
+                                           bool svq,
+                                           VhostIOVATree *iova_tree)
 {
     NetClientState *nc = NULL;
     VhostVDPAState *s;
@@ -646,6 +684,8 @@  static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
 
     s->vhost_vdpa.device_fd = vdpa_device_fd;
     s->vhost_vdpa.index = queue_pair_index;
+    s->vhost_vdpa.shadow_vqs_enabled = svq;
+    s->vhost_vdpa.iova_tree = iova_tree;
     if (!is_datapath) {
         s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops;
         s->vhost_vdpa.shadow_vq_ops_opaque = s;
@@ -708,6 +748,7 @@  int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
     uint64_t features;
     int vdpa_device_fd;
     g_autofree NetClientState **ncs = NULL;
+    g_autoptr(VhostIOVATree) iova_tree = NULL;
     NetClientState *nc;
     int queue_pairs, r, i, has_cvq = 0;
 
@@ -735,22 +776,45 @@  int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
         return queue_pairs;
     }
 
+    if (opts->x_svq) {
+        struct vhost_vdpa_iova_range iova_range;
+
+        uint64_t invalid_dev_features =
+            features & ~vdpa_svq_device_features &
+            /* Transport are all accepted at this point */
+            ~MAKE_64BIT_MASK(VIRTIO_TRANSPORT_F_START,
+                             VIRTIO_TRANSPORT_F_END - VIRTIO_TRANSPORT_F_START);
+
+        if (invalid_dev_features) {
+            error_setg(errp, "vdpa svq does not work with features 0x%" PRIx64,
+                       invalid_dev_features);
+            goto err_svq;
+        }
+
+        vhost_vdpa_get_iova_range(vdpa_device_fd, &iova_range);
+        iova_tree = vhost_iova_tree_new(iova_range.first, iova_range.last);
+    }
+
     ncs = g_malloc0(sizeof(*ncs) * queue_pairs);
 
     for (i = 0; i < queue_pairs; i++) {
         ncs[i] = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
-                                     vdpa_device_fd, i, 2, true);
+                                     vdpa_device_fd, i, 2, true, opts->x_svq,
+                                     iova_tree);
         if (!ncs[i])
             goto err;
     }
 
     if (has_cvq) {
         nc = net_vhost_vdpa_init(peer, TYPE_VHOST_VDPA, name,
-                                 vdpa_device_fd, i, 1, false);
+                                 vdpa_device_fd, i, 1, false,
+                                 opts->x_svq, iova_tree);
         if (!nc)
             goto err;
     }
 
+    /* iova_tree ownership belongs to last NetClientState */
+    g_steal_pointer(&iova_tree);
     return 0;
 
 err:
@@ -759,6 +823,8 @@  err:
             qemu_del_net_client(ncs[i]);
         }
     }
+
+err_svq:
     qemu_close(vdpa_device_fd);
 
     return -1;