Merge tag 'net-pull-request' of https://github.com/jasowang/qemu into staging

# gpg: Signature made Wed 20 Jul 2022 09:58:47 BST
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* tag 'net-pull-request' of https://github.com/jasowang/qemu: (25 commits)
  net/colo.c: fix segmentation fault when packet is not parsed correctly
  net/colo.c: No need to track conn_list for filter-rewriter
  net/colo: Fix a "double free" crash to clear the conn_list
  softmmu/runstate.c: add RunStateTransition support form COLO to PRELAUNCH
  vdpa: Add x-svq to NetdevVhostVDPAOptions
  vdpa: Add device migration blocker
  vdpa: Extract get features part from vhost_vdpa_get_max_queue_pairs
  vdpa: Buffer CVQ support on shadow virtqueue
  vdpa: manual forward CVQ buffers
  vhost-net-vdpa: add stubs for when no virtio-net device is present
  vdpa: Export vhost_vdpa_dma_map and unmap calls
  vhost: Add svq avail_handler callback
  vhost: add vhost_svq_poll
  vhost: Expose vhost_svq_add
  vhost: add vhost_svq_push_elem
  vhost: Track number of descs in SVQDescState
  vhost: Add SVQDescState
  vhost: Decouple vhost_svq_add from VirtQueueElement
  vhost: Check for queue full at vhost_svq_add
  vhost: Move vhost_svq_kick call to vhost_svq_add
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

hw/net/virtio-net.c

@@ -49,7 +49,6 @@
 
 #define VIRTIO_NET_VM_VERSION    11
 
-#define MAC_TABLE_ENTRIES    64
 #define MAX_VLAN    (1 << 12)   /* Per 802.1Q definition */
 
 /* previously fixed value */
@@ -1434,57 +1433,71 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
     return VIRTIO_NET_OK;
 }
 
-static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
+size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
+                                  const struct iovec *in_sg, unsigned in_num,
+                                  const struct iovec *out_sg,
+                                  unsigned out_num)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
     struct virtio_net_ctrl_hdr ctrl;
     virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
-    VirtQueueElement *elem;
     size_t s;
     struct iovec *iov, *iov2;
-    unsigned int iov_cnt;
+
+    if (iov_size(in_sg, in_num) < sizeof(status) ||
+        iov_size(out_sg, out_num) < sizeof(ctrl)) {
+        virtio_error(vdev, "virtio-net ctrl missing headers");
+        return 0;
+    }
+
+    iov2 = iov = g_memdup2(out_sg, sizeof(struct iovec) * out_num);
+    s = iov_to_buf(iov, out_num, 0, &ctrl, sizeof(ctrl));
+    iov_discard_front(&iov, &out_num, sizeof(ctrl));
+    if (s != sizeof(ctrl)) {
+        status = VIRTIO_NET_ERR;
+    } else if (ctrl.class == VIRTIO_NET_CTRL_RX) {
+        status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, out_num);
+    } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) {
+        status = virtio_net_handle_mac(n, ctrl.cmd, iov, out_num);
+    } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) {
+        status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, out_num);
+    } else if (ctrl.class == VIRTIO_NET_CTRL_ANNOUNCE) {
+        status = virtio_net_handle_announce(n, ctrl.cmd, iov, out_num);
+    } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) {
+        status = virtio_net_handle_mq(n, ctrl.cmd, iov, out_num);
+    } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) {
+        status = virtio_net_handle_offloads(n, ctrl.cmd, iov, out_num);
+    }
+
+    s = iov_from_buf(in_sg, in_num, 0, &status, sizeof(status));
+    assert(s == sizeof(status));
+
+    g_free(iov2);
+    return sizeof(status);
+}
+
+static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtQueueElement *elem;
 
     for (;;) {
+        size_t written;
         elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
         if (!elem) {
             break;
         }
-        if (iov_size(elem->in_sg, elem->in_num) < sizeof(status) ||
-            iov_size(elem->out_sg, elem->out_num) < sizeof(ctrl)) {
-            virtio_error(vdev, "virtio-net ctrl missing headers");
+
+        written = virtio_net_handle_ctrl_iov(vdev, elem->in_sg, elem->in_num,
+                                             elem->out_sg, elem->out_num);
+        if (written > 0) {
+            virtqueue_push(vq, elem, written);
+            virtio_notify(vdev, vq);
+            g_free(elem);
+        } else {
             virtqueue_detach_element(vq, elem, 0);
             g_free(elem);
             break;
         }
-
-        iov_cnt = elem->out_num;
-        iov2 = iov = g_memdup2(elem->out_sg,
-                               sizeof(struct iovec) * elem->out_num);
-        s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));
-        iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));
-        if (s != sizeof(ctrl)) {
-            status = VIRTIO_NET_ERR;
-        } else if (ctrl.class == VIRTIO_NET_CTRL_RX) {
-            status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, iov_cnt);
-        } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) {
-            status = virtio_net_handle_mac(n, ctrl.cmd, iov, iov_cnt);
-        } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) {
-            status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, iov_cnt);
-        } else if (ctrl.class == VIRTIO_NET_CTRL_ANNOUNCE) {
-            status = virtio_net_handle_announce(n, ctrl.cmd, iov, iov_cnt);
-        } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) {
-            status = virtio_net_handle_mq(n, ctrl.cmd, iov, iov_cnt);
-        } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) {
-            status = virtio_net_handle_offloads(n, ctrl.cmd, iov, iov_cnt);
-        }
-
-        s = iov_from_buf(elem->in_sg, elem->in_num, 0, &status, sizeof(status));
-        assert(s == sizeof(status));
-
-        virtqueue_push(vq, elem, sizeof(status));
-        virtio_notify(vdev, vq);
-        g_free(iov2);
-        g_free(elem);
     }
 }
 

hw/virtio/vhost-shadow-virtqueue.c

@@ -122,17 +122,35 @@ static bool vhost_svq_translate_addr(const VhostShadowVirtqueue *svq,
     return true;
 }
 
-static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
-                                    const struct iovec *iovec, size_t num,
-                                    bool more_descs, bool write)
+/**
+ * Write descriptors to SVQ vring
+ *
+ * @svq: The shadow virtqueue
+ * @sg: Cache for hwaddr
+ * @iovec: The iovec from the guest
+ * @num: iovec length
+ * @more_descs: True if more descriptors come in the chain
+ * @write: True if they are writeable descriptors
+ *
+ * Return true if success, false otherwise and print error.
+ */
+static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
+                                        const struct iovec *iovec, size_t num,
+                                        bool more_descs, bool write)
 {
     uint16_t i = svq->free_head, last = svq->free_head;
     unsigned n;
     uint16_t flags = write ? cpu_to_le16(VRING_DESC_F_WRITE) : 0;
     vring_desc_t *descs = svq->vring.desc;
+    bool ok;
 
     if (num == 0) {
-        return;
+        return true;
+    }
+
+    ok = vhost_svq_translate_addr(svq, sg, iovec, num);
+    if (unlikely(!ok)) {
+        return false;
     }
 
     for (n = 0; n < num; n++) {
@@ -150,40 +168,39 @@ static void vhost_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
     }
 
     svq->free_head = le16_to_cpu(svq->desc_next[last]);
+    return true;
 }
 
 static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
-                                VirtQueueElement *elem, unsigned *head)
+                                const struct iovec *out_sg, size_t out_num,
+                                const struct iovec *in_sg, size_t in_num,
+                                unsigned *head)
 {
     unsigned avail_idx;
     vring_avail_t *avail = svq->vring.avail;
     bool ok;
-    g_autofree hwaddr *sgs = g_new(hwaddr, MAX(elem->out_num, elem->in_num));
+    g_autofree hwaddr *sgs = g_new(hwaddr, MAX(out_num, in_num));
 
     *head = svq->free_head;
 
     /* We need some descriptors here */
-    if (unlikely(!elem->out_num && !elem->in_num)) {
+    if (unlikely(!out_num && !in_num)) {
         qemu_log_mask(LOG_GUEST_ERROR,
                       "Guest provided element with no descriptors");
         return false;
     }
 
-    ok = vhost_svq_translate_addr(svq, sgs, elem->out_sg, elem->out_num);
+    ok = vhost_svq_vring_write_descs(svq, sgs, out_sg, out_num, in_num > 0,
+                                     false);
     if (unlikely(!ok)) {
         return false;
     }
-    vhost_vring_write_descs(svq, sgs, elem->out_sg, elem->out_num,
-                            elem->in_num > 0, false);
 
-
-    ok = vhost_svq_translate_addr(svq, sgs, elem->in_sg, elem->in_num);
+    ok = vhost_svq_vring_write_descs(svq, sgs, in_sg, in_num, false, true);
     if (unlikely(!ok)) {
         return false;
     }
 
-    vhost_vring_write_descs(svq, sgs, elem->in_sg, elem->in_num, false, true);
-
     /*
      * Put the entry in the available array (but don't update avail->idx until
      * they do sync).
@@ -199,38 +216,58 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
     return true;
 }
 
+static void vhost_svq_kick(VhostShadowVirtqueue *svq)
+{
+    /*
+     * We need to expose the available array entries before checking the used
+     * flags
+     */
+    smp_mb();
+    if (svq->vring.used->flags & VRING_USED_F_NO_NOTIFY) {
+        return;
+    }
+
+    event_notifier_set(&svq->hdev_kick);
+}
+
 /**
  * Add an element to a SVQ.
  *
  * The caller must check that there is enough slots for the new element. It
- * takes ownership of the element: In case of failure, it is free and the SVQ
- * is considered broken.
+ * takes ownership of the element: In case of failure not ENOSPC, it is free.
+ *
+ * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full
  */
-static bool vhost_svq_add(VhostShadowVirtqueue *svq, VirtQueueElement *elem)
+int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
+                  size_t out_num, const struct iovec *in_sg, size_t in_num,
+                  VirtQueueElement *elem)
 {
     unsigned qemu_head;
-    bool ok = vhost_svq_add_split(svq, elem, &qemu_head);
+    unsigned ndescs = in_num + out_num;
+    bool ok;
+
+    if (unlikely(ndescs > vhost_svq_available_slots(svq))) {
+        return -ENOSPC;
+    }
+
+    ok = vhost_svq_add_split(svq, out_sg, out_num, in_sg, in_num, &qemu_head);
     if (unlikely(!ok)) {
         g_free(elem);
-        return false;
+        return -EINVAL;
     }
 
-    svq->ring_id_maps[qemu_head] = elem;
-    return true;
+    svq->desc_state[qemu_head].elem = elem;
+    svq->desc_state[qemu_head].ndescs = ndescs;
+    vhost_svq_kick(svq);
+    return 0;
 }
 
-static void vhost_svq_kick(VhostShadowVirtqueue *svq)
+/* Convenience wrapper to add a guest's element to SVQ */
+static int vhost_svq_add_element(VhostShadowVirtqueue *svq,
+                                 VirtQueueElement *elem)
 {
-    /*
-     * We need to expose the available array entries before checking the used
-     * flags
-     */
-    smp_mb();
-    if (svq->vring.used->flags & VRING_USED_F_NO_NOTIFY) {
-        return;
-    }
-
-    event_notifier_set(&svq->hdev_kick);
+    return vhost_svq_add(svq, elem->out_sg, elem->out_num, elem->in_sg,
+                         elem->in_num, elem);
 }
 
 /**
@@ -257,7 +294,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)
 
         while (true) {
             VirtQueueElement *elem;
-            bool ok;
+            int r;
 
             if (svq->next_guest_avail_elem) {
                 elem = g_steal_pointer(&svq->next_guest_avail_elem);
@@ -269,28 +306,30 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)
                 break;
             }
 
-            if (elem->out_num + elem->in_num > vhost_svq_available_slots(svq)) {
-                /*
-                 * This condition is possible since a contiguous buffer in GPA
-                 * does not imply a contiguous buffer in qemu's VA
-                 * scatter-gather segments. If that happens, the buffer exposed
-                 * to the device needs to be a chain of descriptors at this
-                 * moment.
-                 *
-                 * SVQ cannot hold more available buffers if we are here:
-                 * queue the current guest descriptor and ignore further kicks
-                 * until some elements are used.
-                 */
-                svq->next_guest_avail_elem = elem;
-                return;
+            if (svq->ops) {
+                r = svq->ops->avail_handler(svq, elem, svq->ops_opaque);
+            } else {
+                r = vhost_svq_add_element(svq, elem);
             }
-
-            ok = vhost_svq_add(svq, elem);
-            if (unlikely(!ok)) {
-                /* VQ is broken, just return and ignore any other kicks */
+            if (unlikely(r != 0)) {
+                if (r == -ENOSPC) {
+                    /*
+                     * This condition is possible since a contiguous buffer in
+                     * GPA does not imply a contiguous buffer in qemu's VA
+                     * scatter-gather segments. If that happens, the buffer
+                     * exposed to the device needs to be a chain of descriptors
+                     * at this moment.
+                     *
+                     * SVQ cannot hold more available buffers if we are here:
+                     * queue the current guest descriptor and ignore kicks
+                     * until some elements are used.
+                     */
+                    svq->next_guest_avail_elem = elem;
+                }
+
+                /* VQ is full or broken, just return and ignore kicks */
                 return;
             }
-            vhost_svq_kick(svq);
         }
 
         virtio_queue_set_notification(svq->vq, true);
@@ -311,11 +350,12 @@ static void vhost_handle_guest_kick_notifier(EventNotifier *n)
 
 static bool vhost_svq_more_used(VhostShadowVirtqueue *svq)
 {
+    uint16_t *used_idx = &svq->vring.used->idx;
     if (svq->last_used_idx != svq->shadow_used_idx) {
         return true;
     }
 
-    svq->shadow_used_idx = cpu_to_le16(svq->vring.used->idx);
+    svq->shadow_used_idx = cpu_to_le16(*(volatile uint16_t *)used_idx);
 
     return svq->last_used_idx != svq->shadow_used_idx;
 }
@@ -376,21 +416,36 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,
         return NULL;
     }
 
-    if (unlikely(!svq->ring_id_maps[used_elem.id])) {
+    if (unlikely(!svq->desc_state[used_elem.id].elem)) {
         qemu_log_mask(LOG_GUEST_ERROR,
             "Device %s says index %u is used, but it was not available",
             svq->vdev->name, used_elem.id);
         return NULL;
     }
 
-    num = svq->ring_id_maps[used_elem.id]->in_num +
-          svq->ring_id_maps[used_elem.id]->out_num;
+    num = svq->desc_state[used_elem.id].ndescs;
     last_used_chain = vhost_svq_last_desc_of_chain(svq, num, used_elem.id);
     svq->desc_next[last_used_chain] = svq->free_head;
     svq->free_head = used_elem.id;
 
     *len = used_elem.len;
-    return g_steal_pointer(&svq->ring_id_maps[used_elem.id]);
+    return g_steal_pointer(&svq->desc_state[used_elem.id].elem);
+}
+
+/**
+ * Push an element to SVQ, returning it to the guest.
+ */
+void vhost_svq_push_elem(VhostShadowVirtqueue *svq,
+                         const VirtQueueElement *elem, uint32_t len)
+{
+    virtqueue_push(svq->vq, elem, len);
+    if (svq->next_guest_avail_elem) {
+        /*
+         * Avail ring was full when vhost_svq_flush was called, so it's a
+         * good moment to make more descriptors available if possible.
+         */
+        vhost_handle_guest_kick(svq);
+    }
 }
 
 static void vhost_svq_flush(VhostShadowVirtqueue *svq,
@@ -434,6 +489,33 @@ static void vhost_svq_flush(VhostShadowVirtqueue *svq,
     } while (!vhost_svq_enable_notification(svq));
 }
 
+/**
+ * Poll the SVQ for one device used buffer.
+ *
+ * This function race with main event loop SVQ polling, so extra
+ * synchronization is needed.
+ *
+ * Return the length written by the device.
+ */
+size_t vhost_svq_poll(VhostShadowVirtqueue *svq)
+{
+    int64_t start_us = g_get_monotonic_time();
+    do {
+        uint32_t len;
+        VirtQueueElement *elem = vhost_svq_get_buf(svq, &len);
+        if (elem) {
+            return len;
+        }
+
+        if (unlikely(g_get_monotonic_time() - start_us > 10e6)) {
+            return 0;
+        }
+
+        /* Make sure we read new used_idx */
+        smp_rmb();
+    } while (true);
+}
+
 /**
  * Forward used buffers.
  *
@@ -560,7 +642,7 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev,
     memset(svq->vring.desc, 0, driver_size);
     svq->vring.used = qemu_memalign(qemu_real_host_page_size(), device_size);
     memset(svq->vring.used, 0, device_size);
-    svq->ring_id_maps = g_new0(VirtQueueElement *, svq->vring.num);
+    svq->desc_state = g_new0(SVQDescState, svq->vring.num);
     svq->desc_next = g_new0(uint16_t, svq->vring.num);
     for (unsigned i = 0; i < svq->vring.num - 1; i++) {
         svq->desc_next[i] = cpu_to_le16(i + 1);
@@ -585,7 +667,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq)
 
     for (unsigned i = 0; i < svq->vring.num; ++i) {
         g_autofree VirtQueueElement *elem = NULL;
-        elem = g_steal_pointer(&svq->ring_id_maps[i]);
+        elem = g_steal_pointer(&svq->desc_state[i].elem);
         if (elem) {
             virtqueue_detach_element(svq->vq, elem, 0);
         }
@@ -597,7 +679,7 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq)
     }
     svq->vq = NULL;
     g_free(svq->desc_next);
-    g_free(svq->ring_id_maps);
+    g_free(svq->desc_state);
     qemu_vfree(svq->vring.desc);
     qemu_vfree(svq->vring.used);
 }
@@ -607,12 +689,16 @@ void vhost_svq_stop(VhostShadowVirtqueue *svq)
  * shadow methods and file descriptors.
  *
  * @iova_tree: Tree to perform descriptors translations
+ * @ops: SVQ owner callbacks
+ * @ops_opaque: ops opaque pointer
  *
  * Returns the new virtqueue or NULL.
  *
  * In case of error, reason is reported through error_report.
  */
-VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree)
+VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree,
+                                    const VhostShadowVirtqueueOps *ops,
+                                    void *ops_opaque)
 {
     g_autofree VhostShadowVirtqueue *svq = g_new0(VhostShadowVirtqueue, 1);
     int r;
@@ -634,6 +720,8 @@ VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree)
     event_notifier_init_fd(&svq->svq_kick, VHOST_FILE_UNBIND);
     event_notifier_set_handler(&svq->hdev_call, vhost_svq_handle_call);
     svq->iova_tree = iova_tree;
+    svq->ops = ops;
+    svq->ops_opaque = ops_opaque;
     return g_steal_pointer(&svq);
 
 err_init_hdev_call:

hw/virtio/vhost-shadow-virtqueue.h

@@ -15,6 +15,37 @@
 #include "standard-headers/linux/vhost_types.h"
 #include "hw/virtio/vhost-iova-tree.h"
 
+typedef struct SVQDescState {
+    VirtQueueElement *elem;
+
+    /*
+     * Number of descriptors exposed to the device. May or may not match
+     * guest's
+     */
+    unsigned int ndescs;
+} SVQDescState;
+
+typedef struct VhostShadowVirtqueue VhostShadowVirtqueue;
+
+/**
+ * Callback to handle an avail buffer.
+ *
+ * @svq:  Shadow virtqueue
+ * @elem:  Element placed in the queue by the guest
+ * @vq_callback_opaque:  Opaque
+ *
+ * Returns 0 if the vq is running as expected.
+ *
+ * Note that ownership of elem is transferred to the callback.
+ */
+typedef int (*VirtQueueAvailCallback)(VhostShadowVirtqueue *svq,
+                                      VirtQueueElement *elem,
+                                      void *vq_callback_opaque);
+
+typedef struct VhostShadowVirtqueueOps {
+    VirtQueueAvailCallback avail_handler;
+} VhostShadowVirtqueueOps;
+
 /* Shadow virtqueue to relay notifications */
 typedef struct VhostShadowVirtqueue {
     /* Shadow vring */
@@ -47,8 +78,8 @@ typedef struct VhostShadowVirtqueue {
     /* IOVA mapping */
     VhostIOVATree *iova_tree;
 
-    /* Map for use the guest's descriptors */
-    VirtQueueElement **ring_id_maps;
+    /* SVQ vring descriptors state */
+    SVQDescState *desc_state;
 
     /* Next VirtQueue element that guest made available */
     VirtQueueElement *next_guest_avail_elem;
@@ -59,6 +90,12 @@ typedef struct VhostShadowVirtqueue {
      */
     uint16_t *desc_next;
 
+    /* Caller callbacks */
+    const VhostShadowVirtqueueOps *ops;
+
+    /* Caller callbacks opaque */
+    void *ops_opaque;
+
     /* Next head to expose to the device */
     uint16_t shadow_avail_idx;
 
@@ -74,6 +111,13 @@ typedef struct VhostShadowVirtqueue {
 
 bool vhost_svq_valid_features(uint64_t features, Error **errp);
 
+void vhost_svq_push_elem(VhostShadowVirtqueue *svq,
+                         const VirtQueueElement *elem, uint32_t len);
+int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
+                  size_t out_num, const struct iovec *in_sg, size_t in_num,
+                  VirtQueueElement *elem);
+size_t vhost_svq_poll(VhostShadowVirtqueue *svq);
+
 void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd);
 void vhost_svq_set_svq_call_fd(VhostShadowVirtqueue *svq, int call_fd);
 void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq,
@@ -85,7 +129,9 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev,
                      VirtQueue *vq);
 void vhost_svq_stop(VhostShadowVirtqueue *svq);
 
-VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree);
+VhostShadowVirtqueue *vhost_svq_new(VhostIOVATree *iova_tree,
+                                    const VhostShadowVirtqueueOps *ops,
+                                    void *ops_opaque);
 
 void vhost_svq_free(gpointer vq);
 G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostShadowVirtqueue, vhost_svq_free);

hw/virtio/vhost-vdpa.c

@@ -20,6 +20,7 @@
 #include "hw/virtio/vhost-shadow-virtqueue.h"
 #include "hw/virtio/vhost-vdpa.h"
 #include "exec/address-spaces.h"
+#include "migration/blocker.h"
 #include "qemu/cutils.h"
 #include "qemu/main-loop.h"
 #include "cpu.h"
@@ -71,8 +72,8 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section,
     return false;
 }
 
-static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
-                              void *vaddr, bool readonly)
+int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
+                       void *vaddr, bool readonly)
 {
     struct vhost_msg_v2 msg = {};
     int fd = v->device_fd;
@@ -97,8 +98,7 @@ static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
     return ret;
 }
 
-static int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova,
-                                hwaddr size)
+int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, hwaddr size)
 {
     struct vhost_msg_v2 msg = {};
     int fd = v->device_fd;
@@ -418,8 +418,10 @@ static int vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v,
 
     shadow_vqs = g_ptr_array_new_full(hdev->nvqs, vhost_svq_free);
     for (unsigned n = 0; n < hdev->nvqs; ++n) {
-        g_autoptr(VhostShadowVirtqueue) svq = vhost_svq_new(v->iova_tree);
+        g_autoptr(VhostShadowVirtqueue) svq;
 
+        svq = vhost_svq_new(v->iova_tree, v->shadow_vq_ops,
+                            v->shadow_vq_ops_opaque);
         if (unlikely(!svq)) {
             error_setg(errp, "Cannot create svq %u", n);
             return -1;
@@ -1021,6 +1023,13 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev)
         return true;
     }
 
+    if (v->migration_blocker) {
+        int r = migrate_add_blocker(v->migration_blocker, &err);
+        if (unlikely(r < 0)) {
+            return false;
+        }
+    }
+
     for (i = 0; i < v->shadow_vqs->len; ++i) {
         VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i);
         VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i);
@@ -1063,6 +1072,10 @@ err:
         vhost_svq_stop(svq);
     }
 
+    if (v->migration_blocker) {
+        migrate_del_blocker(v->migration_blocker);
+    }
+
     return false;
 }
 
@@ -1082,6 +1095,9 @@ static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev)
         }
     }
 
+    if (v->migration_blocker) {
+        migrate_del_blocker(v->migration_blocker);
+    }
     return true;
 }
 

include/hw/virtio/vhost-vdpa.h

@@ -15,6 +15,7 @@
 #include <gmodule.h>
 
 #include "hw/virtio/vhost-iova-tree.h"
+#include "hw/virtio/vhost-shadow-virtqueue.h"
 #include "hw/virtio/virtio.h"
 #include "standard-headers/linux/vhost_types.h"
 
@@ -34,9 +35,16 @@ typedef struct vhost_vdpa {
     bool shadow_vqs_enabled;
     /* IOVA mapping used by the Shadow Virtqueue */
     VhostIOVATree *iova_tree;
+    Error *migration_blocker;
     GPtrArray *shadow_vqs;
+    const VhostShadowVirtqueueOps *shadow_vq_ops;
+    void *shadow_vq_ops_opaque;
     struct vhost_dev *dev;
     VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];
 } VhostVDPA;
 
+int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
+                       void *vaddr, bool readonly);
+int vhost_vdpa_dma_unmap(struct vhost_vdpa *v, hwaddr iova, hwaddr size);
+
 #endif

include/hw/virtio/virtio-net.h

@@ -35,6 +35,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(VirtIONet, VIRTIO_NET)
  * and latency. */
 #define TX_BURST 256
 
+/* Maximum VIRTIO_NET_CTRL_MAC_TABLE_SET unicast + multicast entries. */
+#define MAC_TABLE_ENTRIES    64
+
 typedef struct virtio_net_conf
 {
     uint32_t txtimer;
@@ -218,6 +221,10 @@ struct VirtIONet {
     struct EBPFRSSContext ebpf_rss;
 };
 
+size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
+                                  const struct iovec *in_sg, unsigned in_num,
+                                  const struct iovec *out_sg,
+                                  unsigned out_num);
 void virtio_net_set_netclient_name(VirtIONet *n, const char *name,
                                    const char *type);
 

net/colo-compare.c

@@ -1323,7 +1323,7 @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
     s->connection_track_table = g_hash_table_new_full(connection_key_hash,
                                                       connection_key_equal,
                                                       g_free,
-                                                      connection_destroy);
+                                                      NULL);
 
     colo_compare_iothread(s);
 

net/colo.c

@@ -46,7 +46,14 @@ int parse_packet_early(Packet *pkt)
     static const uint8_t vlan[] = {0x81, 0x00};
     uint8_t *data = pkt->data + pkt->vnet_hdr_len;
     uint16_t l3_proto;
-    ssize_t l2hdr_len = eth_get_l2_hdr_length(data);
+    ssize_t l2hdr_len;
+
+    if (data == NULL) {
+        trace_colo_proxy_main_vnet_info("This packet is not parsed correctly, "
+                                        "pkt->vnet_hdr_len", pkt->vnet_hdr_len);
+        return 1;
+    }
+    l2hdr_len = eth_get_l2_hdr_length(data);
 
     if (pkt->size < ETH_HLEN + pkt->vnet_hdr_len) {
         trace_colo_proxy_main("pkt->size < ETH_HLEN");
@@ -218,7 +225,7 @@ Connection *connection_get(GHashTable *connection_track_table,
             /*
              * clear the conn_list
              */
-            while (!g_queue_is_empty(conn_list)) {
+            while (conn_list && !g_queue_is_empty(conn_list)) {
                 connection_destroy(g_queue_pop_head(conn_list));
             }
         }

net/filter-rewriter.c

@@ -383,7 +383,7 @@ static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
     s->connection_track_table = g_hash_table_new_full(connection_key_hash,
                                                       connection_key_equal,
                                                       g_free,
-                                                      connection_destroy);
+                                                      NULL);
     s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
 }
 

net/meson.build

@@ -41,7 +41,8 @@ endif
 softmmu_ss.add(when: 'CONFIG_POSIX', if_true: files(tap_posix))
 softmmu_ss.add(when: 'CONFIG_WIN32', if_true: files('tap-win32.c'))
 if have_vhost_net_vdpa
-  softmmu_ss.add(files('vhost-vdpa.c'))
+  softmmu_ss.add(when: 'CONFIG_VIRTIO_NET', if_true: files('vhost-vdpa.c'), if_false: files('vhost-vdpa-stub.c'))
+  softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-vdpa-stub.c'))
 endif
 
 vmnet_files = files(

net/trace-events

@@ -9,6 +9,7 @@ vhost_user_event(const char *chr, int event) "chr: %s got event: %d"
 
 # colo.c
 colo_proxy_main(const char *chr) ": %s"
+colo_proxy_main_vnet_info(const char *sta, int size) ": %s = %d"
 
 # colo-compare.c
 colo_compare_main(const char *chr) ": %s"

net/vhost-vdpa-stub.c

+/*
+ * vhost-vdpa-stub.c
+ *
+ * Copyright (c) 2022 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "clients.h"
+#include "net/vhost-vdpa.h"
+#include "qapi/error.h"
+
+int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
+                        NetClientState *peer, Error **errp)
+{
+    error_setg(errp, "vhost-vdpa requires frontend driver virtio-net-*");
+    return -1;
+}

net/vhost-vdpa.c

@@ -11,11 +11,14 @@
 
 #include "qemu/osdep.h"
 #include "clients.h"
+#include "hw/virtio/virtio-net.h"
 #include "net/vhost_net.h"
 #include "net/vhost-vdpa.h"
 #include "hw/virtio/vhost-vdpa.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
+#include "qemu/log.h"
+#include "qemu/memalign.h"
 #include "qemu/option.h"
 #include "qapi/error.h"
 #include <linux/vhost.h>
@@ -30,6 +33,9 @@ typedef struct VhostVDPAState {
     NetClientState nc;
     struct vhost_vdpa vhost_vdpa;
     VHostNetState *vhost_net;
+
+    /* Control commands shadow buffers */
+    void *cvq_cmd_out_buffer, *cvq_cmd_in_buffer;
     bool started;
 } VhostVDPAState;
 
@@ -69,6 +75,28 @@ 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_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_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);
@@ -127,7 +155,13 @@ err_init:
 static void vhost_vdpa_cleanup(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    struct vhost_dev *dev = &s->vhost_net->dev;
 
+    qemu_vfree(s->cvq_cmd_out_buffer);
+    qemu_vfree(s->cvq_cmd_in_buffer);
+    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);
@@ -187,13 +221,251 @@ static NetClientInfo net_vhost_vdpa_info = {
         .check_peer_type = vhost_vdpa_check_peer_type,
 };
 
+static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
+{
+    VhostIOVATree *tree = v->iova_tree;
+    DMAMap needle = {
+        /*
+         * No need to specify size or to look for more translations since
+         * this contiguous chunk was allocated by us.
+         */
+        .translated_addr = (hwaddr)(uintptr_t)addr,
+    };
+    const DMAMap *map = vhost_iova_tree_find_iova(tree, &needle);
+    int r;
+
+    if (unlikely(!map)) {
+        error_report("Cannot locate expected map");
+        return;
+    }
+
+    r = vhost_vdpa_dma_unmap(v, map->iova, map->size + 1);
+    if (unlikely(r != 0)) {
+        error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
+    }
+
+    vhost_iova_tree_remove(tree, map);
+}
+
+static size_t vhost_vdpa_net_cvq_cmd_len(void)
+{
+    /*
+     * MAC_TABLE_SET is the ctrl command that produces the longer out buffer.
+     * In buffer is always 1 byte, so it should fit here
+     */
+    return sizeof(struct virtio_net_ctrl_hdr) +
+           2 * sizeof(struct virtio_net_ctrl_mac) +
+           MAC_TABLE_ENTRIES * ETH_ALEN;
+}
+
+static size_t vhost_vdpa_net_cvq_cmd_page_len(void)
+{
+    return ROUND_UP(vhost_vdpa_net_cvq_cmd_len(), qemu_real_host_page_size());
+}
+
+/** Copy and map a guest buffer. */
+static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
+                                   const struct iovec *out_data,
+                                   size_t out_num, size_t data_len, void *buf,
+                                   size_t *written, bool write)
+{
+    DMAMap map = {};
+    int r;
+
+    if (unlikely(!data_len)) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid legnth of %s buffer\n",
+                      __func__, write ? "in" : "out");
+        return false;
+    }
+
+    *written = iov_to_buf(out_data, out_num, 0, buf, data_len);
+    map.translated_addr = (hwaddr)(uintptr_t)buf;
+    map.size = vhost_vdpa_net_cvq_cmd_page_len() - 1;
+    map.perm = write ? IOMMU_RW : IOMMU_RO,
+    r = vhost_iova_tree_map_alloc(v->iova_tree, &map);
+    if (unlikely(r != IOVA_OK)) {
+        error_report("Cannot map injected element");
+        return false;
+    }
+
+    r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf,
+                           !write);
+    if (unlikely(r < 0)) {
+        goto dma_map_err;
+    }
+
+    return true;
+
+dma_map_err:
+    vhost_iova_tree_remove(v->iova_tree, &map);
+    return false;
+}
+
+/**
+ * Copy the guest element into a dedicated buffer suitable to be sent to NIC
+ *
+ * @iov: [0] is the out buffer, [1] is the in one
+ */
+static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s,
+                                        VirtQueueElement *elem,
+                                        struct iovec *iov)
+{
+    size_t in_copied;
+    bool ok;
+
+    iov[0].iov_base = s->cvq_cmd_out_buffer;
+    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, elem->out_sg, elem->out_num,
+                                vhost_vdpa_net_cvq_cmd_len(), iov[0].iov_base,
+                                &iov[0].iov_len, false);
+    if (unlikely(!ok)) {
+        return false;
+    }
+
+    iov[1].iov_base = s->cvq_cmd_in_buffer;
+    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0,
+                                sizeof(virtio_net_ctrl_ack), iov[1].iov_base,
+                                &in_copied, true);
+    if (unlikely(!ok)) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
+        return false;
+    }
+
+    iov[1].iov_len = sizeof(virtio_net_ctrl_ack);
+    return true;
+}
+
+/**
+ * Do not forward commands not supported by SVQ. Otherwise, the device could
+ * accept it and qemu would not know how to update the device model.
+ */
+static bool vhost_vdpa_net_cvq_validate_cmd(const struct iovec *out,
+                                            size_t out_num)
+{
+    struct virtio_net_ctrl_hdr ctrl;
+    size_t n;
+
+    n = iov_to_buf(out, out_num, 0, &ctrl, sizeof(ctrl));
+    if (unlikely(n < sizeof(ctrl))) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: invalid legnth of out buffer %zu\n", __func__, n);
+        return false;
+    }
+
+    switch (ctrl.class) {
+    case VIRTIO_NET_CTRL_MAC:
+        switch (ctrl.cmd) {
+        case VIRTIO_NET_CTRL_MAC_ADDR_SET:
+            return true;
+        default:
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mac cmd %u\n",
+                          __func__, ctrl.cmd);
+        };
+        break;
+    default:
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n",
+                      __func__, ctrl.class);
+    };
+
+    return false;
+}
+
+/**
+ * Validate and copy control virtqueue commands.
+ *
+ * Following QEMU guidelines, we offer a copy of the buffers to the device to
+ * prevent TOCTOU bugs.
+ */
+static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
+                                            VirtQueueElement *elem,
+                                            void *opaque)
+{
+    VhostVDPAState *s = opaque;
+    size_t in_len, dev_written;
+    virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
+    /* out and in buffers sent to the device */
+    struct iovec dev_buffers[2] = {
+        { .iov_base = s->cvq_cmd_out_buffer },
+        { .iov_base = s->cvq_cmd_in_buffer },
+    };
+    /* in buffer used for device model */
+    const struct iovec in = {
+        .iov_base = &status,
+        .iov_len = sizeof(status),
+    };
+    int r = -EINVAL;
+    bool ok;
+
+    ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers);
+    if (unlikely(!ok)) {
+        goto out;
+    }
+
+    ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1);
+    if (unlikely(!ok)) {
+        goto out;
+    }
+
+    r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem);
+    if (unlikely(r != 0)) {
+        if (unlikely(r == -ENOSPC)) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
+                          __func__);
+        }
+        goto out;
+    }
+
+    /*
+     * We can poll here since we've had BQL from the time we sent the
+     * descriptor. Also, we need to take the answer before SVQ pulls by itself,
+     * when BQL is released
+     */
+    dev_written = vhost_svq_poll(svq);
+    if (unlikely(dev_written < sizeof(status))) {
+        error_report("Insufficient written data (%zu)", dev_written);
+        goto out;
+    }
+
+    memcpy(&status, dev_buffers[1].iov_base, sizeof(status));
+    if (status != VIRTIO_NET_OK) {
+        goto out;
+    }
+
+    status = VIRTIO_NET_ERR;
+    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1);
+    if (status != VIRTIO_NET_OK) {
+        error_report("Bad CVQ processing in model");
+    }
+
+out:
+    in_len = iov_from_buf(elem->in_sg, elem->in_num, 0, &status,
+                          sizeof(status));
+    if (unlikely(in_len < sizeof(status))) {
+        error_report("Bad device CVQ written length");
+    }
+    vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status)));
+    g_free(elem);
+    if (dev_buffers[0].iov_base) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[0].iov_base);
+    }
+    if (dev_buffers[1].iov_base) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base);
+    }
+    return r;
+}
+
+static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = {
+    .avail_handler = vhost_vdpa_net_handle_ctrl_avail,
+};
+
 static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
                                            const char *device,
                                            const char *name,
                                            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;
@@ -211,6 +483,21 @@ 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->cvq_cmd_out_buffer = qemu_memalign(qemu_real_host_page_size(),
+                                            vhost_vdpa_net_cvq_cmd_page_len());
+        memset(s->cvq_cmd_out_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
+        s->cvq_cmd_in_buffer = qemu_memalign(qemu_real_host_page_size(),
+                                            vhost_vdpa_net_cvq_cmd_page_len());
+        memset(s->cvq_cmd_in_buffer, 0, vhost_vdpa_net_cvq_cmd_page_len());
+
+        s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops;
+        s->vhost_vdpa.shadow_vq_ops_opaque = s;
+        error_setg(&s->vhost_vdpa.migration_blocker,
+                   "Migration disabled: vhost-vdpa uses CVQ.");
+    }
     ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs);
     if (ret) {
         qemu_del_net_client(nc);
@@ -219,20 +506,32 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
     return nc;
 }
 
-static int vhost_vdpa_get_max_queue_pairs(int fd, int *has_cvq, Error **errp)
+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 int vhost_vdpa_get_features(int fd, uint64_t *features, Error **errp)
+{
+    int ret = ioctl(fd, VHOST_GET_FEATURES, features);
+    if (unlikely(ret < 0)) {
+        error_setg_errno(errp, errno,
+                         "Fail to query features from vhost-vDPA device");
+    }
+    return ret;
+}
+
+static int vhost_vdpa_get_max_queue_pairs(int fd, uint64_t features,
+                                          int *has_cvq, Error **errp)
 {
     unsigned long config_size = offsetof(struct vhost_vdpa_config, buf);
     g_autofree struct vhost_vdpa_config *config = NULL;
     __virtio16 *max_queue_pairs;
-    uint64_t features;
     int ret;
 
-    ret = ioctl(fd, VHOST_GET_FEATURES, &features);
-    if (ret) {
-        error_setg(errp, "Fail to query features from vhost-vDPA device");
-        return ret;
-    }
-
     if (features & (1 << VIRTIO_NET_F_CTRL_VQ)) {
         *has_cvq = 1;
     } else {
@@ -262,10 +561,12 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
                         NetClientState *peer, Error **errp)
 {
     const NetdevVhostVDPAOptions *opts;
+    uint64_t features;
     int vdpa_device_fd;
     g_autofree NetClientState **ncs = NULL;
+    g_autoptr(VhostIOVATree) iova_tree = NULL;
     NetClientState *nc;
-    int queue_pairs, i, has_cvq = 0;
+    int queue_pairs, r, i, has_cvq = 0;
 
     assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA);
     opts = &netdev->u.vhost_vdpa;
@@ -279,29 +580,57 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name,
         return -errno;
     }
 
-    queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd,
+    r = vhost_vdpa_get_features(vdpa_device_fd, &features, errp);
+    if (unlikely(r < 0)) {
+        return r;
+    }
+
+    queue_pairs = vhost_vdpa_get_max_queue_pairs(vdpa_device_fd, features,
                                                  &has_cvq, errp);
     if (queue_pairs < 0) {
         qemu_close(vdpa_device_fd);
         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:
@@ -310,6 +639,8 @@ err:
             qemu_del_net_client(ncs[i]);
         }
     }
+
+err_svq:
     qemu_close(vdpa_device_fd);
 
     return -1;

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:

softmmu/runstate.c

@@ -126,6 +126,7 @@ static const RunStateTransition runstate_transitions_def[] = {
     { RUN_STATE_RESTORE_VM, RUN_STATE_PRELAUNCH },
 
     { RUN_STATE_COLO, RUN_STATE_RUNNING },
+    { RUN_STATE_COLO, RUN_STATE_PRELAUNCH },
     { RUN_STATE_COLO, RUN_STATE_SHUTDOWN},
 
     { RUN_STATE_RUNNING, RUN_STATE_DEBUG },