-----BEGIN PGP SIGNATURE-----

Version: GnuPG v1
 
 iQEcBAABAgAGBQJjEaMLAAoJEO8Ells5jWIRoRwIAJpwefLgH/+lkd1mtWqxBhuS
 KLa0bkcS6nIGnjQzNX/XWipu/5tMbBLzbaKw0myodvoK6Yx0MFog1cWf6gLHuvWH
 Jy3ONUrF9umHYuOa9sJJtXv/aP7neNJSB3RW67BaiLCLkaetDj9lLciA/KKMvb/I
 JNFtuLVTPibZ5iVTjvifFWmJD/Yk0P8mlrH5yfrA3B2EaaWf1es0GWobGIwwLu9s
 ZSqjhMDAhfOW2E1sBh7jFRh4lJX1t1jRhyIGx2bOXevPx2hFHq6FSq+yuJ9OsZvO
 wC8mC4DD+fovypDWbv3WLslIejM0+THD8KuBQnZtKX5Mbhc+0cELpIFLUdH95TM=
 =eMUT
 -----END PGP SIGNATURE-----

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

# -----BEGIN PGP SIGNATURE-----
# Version: GnuPG v1
#
# iQEcBAABAgAGBQJjEaMLAAoJEO8Ells5jWIRoRwIAJpwefLgH/+lkd1mtWqxBhuS
# KLa0bkcS6nIGnjQzNX/XWipu/5tMbBLzbaKw0myodvoK6Yx0MFog1cWf6gLHuvWH
# Jy3ONUrF9umHYuOa9sJJtXv/aP7neNJSB3RW67BaiLCLkaetDj9lLciA/KKMvb/I
# JNFtuLVTPibZ5iVTjvifFWmJD/Yk0P8mlrH5yfrA3B2EaaWf1es0GWobGIwwLu9s
# ZSqjhMDAhfOW2E1sBh7jFRh4lJX1t1jRhyIGx2bOXevPx2hFHq6FSq+yuJ9OsZvO
# wC8mC4DD+fovypDWbv3WLslIejM0+THD8KuBQnZtKX5Mbhc+0cELpIFLUdH95TM=
# =eMUT
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 02 Sep 2022 02:30:35 EDT
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [full]
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* tag 'net-pull-request' of https://github.com/jasowang/qemu: (21 commits)
  net: tulip: Restrict DMA engine to memories
  net/colo.c: Fix the pointer issue reported by Coverity.
  vdpa: Delete CVQ migration blocker
  vdpa: Add virtio-net mac address via CVQ at start
  vhost_net: add NetClientState->load() callback
  vdpa: extract vhost_vdpa_net_cvq_add from vhost_vdpa_net_handle_ctrl_avail
  vdpa: Move command buffers map to start of net device
  vdpa: add net_vhost_vdpa_cvq_info NetClientInfo
  vhost_net: Add NetClientInfo stop callback
  vhost_net: Add NetClientInfo start callback
  vhost: Do not depend on !NULL VirtQueueElement on vhost_svq_flush
  vhost: Delete useless read memory barrier
  vhost: use SVQ element ndescs instead of opaque data for desc validation
  vhost: stop transfer elem ownership in vhost_handle_guest_kick
  vdpa: Use ring hwaddr at vhost_vdpa_svq_unmap_ring
  vhost: Always store new kick fd on vhost_svq_set_svq_kick_fd
  vdpa: Make SVQ vring unmapping return void
  vdpa: Remove SVQ vring from iova_tree at shutdown
  util: accept iova_tree_remove_parameter by value
  vdpa: do not save failed dma maps in SVQ iova tree
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

hw/i386/intel_iommu.c

@@ -1187,7 +1187,7 @@ static int vtd_page_walk_one(IOMMUTLBEvent *event, vtd_page_walk_info *info)
                     return ret;
                 }
                 /* Drop any existing mapping */
-                iova_tree_remove(as->iova_tree, &target);
+                iova_tree_remove(as->iova_tree, target);
                 /* Recover the correct type */
                 event->type = IOMMU_NOTIFIER_MAP;
                 entry->perm = cache_perm;
@@ -1200,7 +1200,7 @@ static int vtd_page_walk_one(IOMMUTLBEvent *event, vtd_page_walk_info *info)
             trace_vtd_page_walk_one_skip_unmap(entry->iova, entry->addr_mask);
             return 0;
         }
-        iova_tree_remove(as->iova_tree, &target);
+        iova_tree_remove(as->iova_tree, target);
     }
 
     trace_vtd_page_walk_one(info->domain_id, entry->iova,
@@ -3563,7 +3563,7 @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
 
     map.iova = n->start;
     map.size = size;
-    iova_tree_remove(as->iova_tree, &map);
+    iova_tree_remove(as->iova_tree, map);
 }
 
 static void vtd_address_space_unmap_all(IntelIOMMUState *s)

hw/net/tulip.c

@@ -70,7 +70,7 @@ static const VMStateDescription vmstate_pci_tulip = {
 static void tulip_desc_read(TULIPState *s, hwaddr p,
         struct tulip_descriptor *desc)
 {
-    const MemTxAttrs attrs = MEMTXATTRS_UNSPECIFIED;
+    const MemTxAttrs attrs = { .memory = true };
 
     if (s->csr[0] & CSR0_DBO) {
         ldl_be_pci_dma(&s->dev, p, &desc->status, attrs);
@@ -88,7 +88,7 @@ static void tulip_desc_read(TULIPState *s, hwaddr p,
 static void tulip_desc_write(TULIPState *s, hwaddr p,
         struct tulip_descriptor *desc)
 {
-    const MemTxAttrs attrs = MEMTXATTRS_UNSPECIFIED;
+    const MemTxAttrs attrs = { .memory = true };
 
     if (s->csr[0] & CSR0_DBO) {
         stl_be_pci_dma(&s->dev, p, desc->status, attrs);

hw/net/vhost_net.c

@@ -244,6 +244,13 @@ static int vhost_net_start_one(struct vhost_net *net,
     struct vhost_vring_file file = { };
     int r;
 
+    if (net->nc->info->start) {
+        r = net->nc->info->start(net->nc);
+        if (r < 0) {
+            return r;
+        }
+    }
+
     r = vhost_dev_enable_notifiers(&net->dev, dev);
     if (r < 0) {
         goto fail_notifiers;
@@ -274,6 +281,13 @@ static int vhost_net_start_one(struct vhost_net *net,
             }
         }
     }
+
+    if (net->nc->info->load) {
+        r = net->nc->info->load(net->nc);
+        if (r < 0) {
+            goto fail;
+        }
+    }
     return 0;
 fail:
     file.fd = -1;
@@ -313,6 +327,9 @@ static void vhost_net_stop_one(struct vhost_net *net,
         net->nc->info->poll(net->nc, true);
     }
     vhost_dev_stop(&net->dev, dev);
+    if (net->nc->info->stop) {
+        net->nc->info->stop(net->nc);
+    }
     vhost_dev_disable_notifiers(&net->dev, dev);
 }
 

hw/virtio/vhost-iova-tree.c

@@ -104,7 +104,7 @@ int vhost_iova_tree_map_alloc(VhostIOVATree *tree, DMAMap *map)
  * @iova_tree: The vhost iova tree
  * @map: The map to remove
  */
-void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map)
+void vhost_iova_tree_remove(VhostIOVATree *iova_tree, DMAMap map)
 {
     iova_tree_remove(iova_tree->iova_taddr_map, map);
 }

hw/virtio/vhost-iova-tree.h

@@ -22,6 +22,6 @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostIOVATree, vhost_iova_tree_delete);
 const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *iova_tree,
                                         const DMAMap *map);
 int vhost_iova_tree_map_alloc(VhostIOVATree *iova_tree, DMAMap *map);
-void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map);
+void vhost_iova_tree_remove(VhostIOVATree *iova_tree, DMAMap map);
 
 #endif

hw/virtio/vhost-shadow-virtqueue.c

@@ -233,9 +233,6 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq)
 /**
  * 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 not ENOSPC, it is free.
- *
  * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full
  */
 int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
@@ -252,7 +249,6 @@ int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
 
     ok = vhost_svq_add_split(svq, out_sg, out_num, in_sg, in_num, &qemu_head);
     if (unlikely(!ok)) {
-        g_free(elem);
         return -EINVAL;
     }
 
@@ -293,7 +289,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)
         virtio_queue_set_notification(svq->vq, false);
 
         while (true) {
-            VirtQueueElement *elem;
+            g_autofree VirtQueueElement *elem;
             int r;
 
             if (svq->next_guest_avail_elem) {
@@ -324,12 +320,14 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)
                      * queue the current guest descriptor and ignore kicks
                      * until some elements are used.
                      */
-                    svq->next_guest_avail_elem = elem;
+                    svq->next_guest_avail_elem = g_steal_pointer(&elem);
                 }
 
                 /* VQ is full or broken, just return and ignore kicks */
                 return;
             }
+            /* elem belongs to SVQ or external caller now */
+            elem = NULL;
         }
 
         virtio_queue_set_notification(svq->vq, true);
@@ -416,7 +414,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,
         return NULL;
     }
 
-    if (unlikely(!svq->desc_state[used_elem.id].elem)) {
+    if (unlikely(!svq->desc_state[used_elem.id].ndescs)) {
         qemu_log_mask(LOG_GUEST_ERROR,
             "Device %s says index %u is used, but it was not available",
             svq->vdev->name, used_elem.id);
@@ -424,6 +422,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,
     }
 
     num = svq->desc_state[used_elem.id].ndescs;
+    svq->desc_state[used_elem.id].ndescs = 0;
     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;
@@ -500,20 +499,20 @@ static void vhost_svq_flush(VhostShadowVirtqueue *svq,
 size_t vhost_svq_poll(VhostShadowVirtqueue *svq)
 {
     int64_t start_us = g_get_monotonic_time();
+    uint32_t len;
+
     do {
-        uint32_t len;
+        if (vhost_svq_more_used(svq)) {
-        VirtQueueElement *elem = vhost_svq_get_buf(svq, &len);
+            break;
-        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);
+
+    vhost_svq_get_buf(svq, &len);
+    return len;
 }
 
 /**
@@ -602,13 +601,13 @@ void vhost_svq_set_svq_kick_fd(VhostShadowVirtqueue *svq, int svq_kick_fd)
         event_notifier_set_handler(svq_kick, NULL);
     }
 
+    event_notifier_init_fd(svq_kick, svq_kick_fd);
     /*
      * event_notifier_set_handler already checks for guest's notifications if
      * they arrive at the new file descriptor in the switch, so there is no
      * need to explicitly check for them.
      */
     if (poll_start) {
-        event_notifier_init_fd(svq_kick, svq_kick_fd);
         event_notifier_set(svq_kick);
         event_notifier_set_handler(svq_kick, vhost_handle_guest_kick_notifier);
     }
@@ -655,7 +654,7 @@ void vhost_svq_start(VhostShadowVirtqueue *svq, VirtIODevice *vdev,
  */
 void vhost_svq_stop(VhostShadowVirtqueue *svq)
 {
-    event_notifier_set_handler(&svq->svq_kick, NULL);
+    vhost_svq_set_svq_kick_fd(svq, VHOST_FILE_UNBIND);
     g_autofree VirtQueueElement *next_avail_elem = NULL;
 
     if (!svq->vq) {

hw/virtio/vhost-vdpa.c

@@ -176,6 +176,7 @@ static void vhost_vdpa_listener_commit(MemoryListener *listener)
 static void vhost_vdpa_listener_region_add(MemoryListener *listener,
                                            MemoryRegionSection *section)
 {
+    DMAMap mem_region = {};
     struct vhost_vdpa *v = container_of(listener, struct vhost_vdpa, listener);
     hwaddr iova;
     Int128 llend, llsize;
@@ -212,13 +213,13 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
 
     llsize = int128_sub(llend, int128_make64(iova));
     if (v->shadow_vqs_enabled) {
-        DMAMap mem_region = {
+        int r;
-            .translated_addr = (hwaddr)(uintptr_t)vaddr,
-            .size = int128_get64(llsize) - 1,
-            .perm = IOMMU_ACCESS_FLAG(true, section->readonly),
-        };
 
-        int r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region);
+        mem_region.translated_addr = (hwaddr)(uintptr_t)vaddr,
+        mem_region.size = int128_get64(llsize) - 1,
+        mem_region.perm = IOMMU_ACCESS_FLAG(true, section->readonly),
+
+        r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region);
         if (unlikely(r != IOVA_OK)) {
             error_report("Can't allocate a mapping (%d)", r);
             goto fail;
@@ -232,11 +233,16 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
                              vaddr, section->readonly);
     if (ret) {
         error_report("vhost vdpa map fail!");
-        goto fail;
+        goto fail_map;
     }
 
     return;
 
+fail_map:
+    if (v->shadow_vqs_enabled) {
+        vhost_iova_tree_remove(v->iova_tree, mem_region);
+    }
+
 fail:
     /*
      * On the initfn path, store the first error in the container so we
@@ -289,8 +295,12 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
         };
 
         result = vhost_iova_tree_find_iova(v->iova_tree, &mem_region);
+        if (!result) {
+            /* The memory listener map wasn't mapped */
+            return;
+        }
         iova = result->iova;
-        vhost_iova_tree_remove(v->iova_tree, result);
+        vhost_iova_tree_remove(v->iova_tree, *result);
     }
     vhost_vdpa_iotlb_batch_begin_once(v);
     ret = vhost_vdpa_dma_unmap(v, iova, int128_get64(llsize));
@@ -874,41 +884,41 @@ static int vhost_vdpa_svq_set_fds(struct vhost_dev *dev,
 /**
  * Unmap a SVQ area in the device
  */
-static bool vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v,
+static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr addr)
-                                      const DMAMap *needle)
 {
-    const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, needle);
+    const DMAMap needle = {
+        .translated_addr = addr,
+    };
+    const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, &needle);
     hwaddr size;
     int r;
 
     if (unlikely(!result)) {
         error_report("Unable to find SVQ address to unmap");
-        return false;
+        return;
     }
 
     size = ROUND_UP(result->size, qemu_real_host_page_size());
     r = vhost_vdpa_dma_unmap(v, result->iova, size);
-    return r == 0;
+    if (unlikely(r < 0)) {
+        error_report("Unable to unmap SVQ vring: %s (%d)", g_strerror(-r), -r);
+        return;
+    }
+
+    vhost_iova_tree_remove(v->iova_tree, *result);
 }
 
-static bool vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
+static void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
                                        const VhostShadowVirtqueue *svq)
 {
-    DMAMap needle = {};
     struct vhost_vdpa *v = dev->opaque;
     struct vhost_vring_addr svq_addr;
-    bool ok;
 
     vhost_svq_get_vring_addr(svq, &svq_addr);
 
-    needle.translated_addr = svq_addr.desc_user_addr;
+    vhost_vdpa_svq_unmap_ring(v, svq_addr.desc_user_addr);
-    ok = vhost_vdpa_svq_unmap_ring(v, &needle);
-    if (unlikely(!ok)) {
-        return false;
-    }
 
-    needle.translated_addr = svq_addr.used_user_addr;
+    vhost_vdpa_svq_unmap_ring(v, svq_addr.used_user_addr);
-    return vhost_vdpa_svq_unmap_ring(v, &needle);
 }
 
 /**
@@ -934,7 +944,7 @@ static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle,
                            needle->perm == IOMMU_RO);
     if (unlikely(r != 0)) {
         error_setg_errno(errp, -r, "Cannot map region to device");
-        vhost_iova_tree_remove(v->iova_tree, needle);
+        vhost_iova_tree_remove(v->iova_tree, *needle);
     }
 
     return r == 0;
@@ -986,7 +996,7 @@ static bool vhost_vdpa_svq_map_rings(struct vhost_dev *dev,
     ok = vhost_vdpa_svq_map_ring(v, &device_region, errp);
     if (unlikely(!ok)) {
         error_prepend(errp, "Cannot create vq device region: ");
-        vhost_vdpa_svq_unmap_ring(v, &driver_region);
+        vhost_vdpa_svq_unmap_ring(v, driver_region.translated_addr);
     }
     addr->used_user_addr = device_region.iova;
 
@@ -1023,13 +1033,6 @@ 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);
@@ -1072,33 +1075,21 @@ err:
         vhost_svq_stop(svq);
     }
 
-    if (v->migration_blocker) {
-        migrate_del_blocker(v->migration_blocker);
-    }
-
     return false;
 }
 
-static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev)
+static void vhost_vdpa_svqs_stop(struct vhost_dev *dev)
 {
     struct vhost_vdpa *v = dev->opaque;
 
     if (!v->shadow_vqs) {
-        return true;
+        return;
     }
 
     for (unsigned i = 0; i < v->shadow_vqs->len; ++i) {
         VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i);
-        bool ok = vhost_vdpa_svq_unmap_rings(dev, svq);
+        vhost_vdpa_svq_unmap_rings(dev, svq);
-        if (unlikely(!ok)) {
-            return false;
-        }
     }
-
-    if (v->migration_blocker) {
-        migrate_del_blocker(v->migration_blocker);
-    }
-    return true;
 }
 
 static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
@@ -1115,10 +1106,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
         }
         vhost_vdpa_set_vring_ready(dev);
     } else {
-        ok = vhost_vdpa_svqs_stop(dev);
+        vhost_vdpa_svqs_stop(dev);
-        if (unlikely(!ok)) {
-            return -1;
-        }
         vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs);
     }
 

include/hw/virtio/vhost-vdpa.h

@@ -35,7 +35,6 @@ 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;

include/net/net.h

@@ -44,6 +44,9 @@ typedef struct NICConf {
 
 typedef void (NetPoll)(NetClientState *, bool enable);
 typedef bool (NetCanReceive)(NetClientState *);
+typedef int (NetStart)(NetClientState *);
+typedef int (NetLoad)(NetClientState *);
+typedef void (NetStop)(NetClientState *);
 typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t);
 typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int);
 typedef void (NetCleanup) (NetClientState *);
@@ -71,6 +74,9 @@ typedef struct NetClientInfo {
     NetReceive *receive_raw;
     NetReceiveIOV *receive_iov;
     NetCanReceive *can_receive;
+    NetStart *start;
+    NetLoad *load;
+    NetStop *stop;
     NetCleanup *cleanup;
     LinkStatusChanged *link_status_changed;
     QueryRxFilter *query_rx_filter;

include/qemu/iova-tree.h

@@ -73,7 +73,7 @@ int iova_tree_insert(IOVATree *tree, const DMAMap *map);
  * all the mappings that are included in the provided range will be
  * removed from the tree.  Here map->translated_addr is meaningless.
  */
-void iova_tree_remove(IOVATree *tree, const DMAMap *map);
+void iova_tree_remove(IOVATree *tree, DMAMap map);
 
 /**
  * iova_tree_find:

net/colo.c

@@ -44,21 +44,28 @@ int parse_packet_early(Packet *pkt)
 {
     int network_length;
     static const uint8_t vlan[] = {0x81, 0x00};
-    uint8_t *data = pkt->data + pkt->vnet_hdr_len;
+    uint8_t *data = pkt->data;
     uint16_t l3_proto;
     ssize_t l2hdr_len;
 
-    if (data == NULL) {
+    assert(data);
-        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) {
+    /* Check the received vnet_hdr_len then add the offset */
-        trace_colo_proxy_main("pkt->size < ETH_HLEN");
+    if ((pkt->vnet_hdr_len > sizeof(struct virtio_net_hdr_v1_hash)) ||
+        (pkt->size < sizeof(struct eth_header) + sizeof(struct vlan_header) +
+        pkt->vnet_hdr_len)) {
+        /*
+         * The received remote packet maybe misconfiguration here,
+         * Please enable/disable filter module's the vnet_hdr flag at
+         * the same time.
+         */
+        trace_colo_proxy_main_vnet_info("This received packet load wrong ",
+                                        pkt->vnet_hdr_len, pkt->size);
         return 1;
     }
+    data += pkt->vnet_hdr_len;
+
+    l2hdr_len = eth_get_l2_hdr_length(data);
 
     /*
      * TODO: support vlan.

net/colo.h

@@ -18,6 +18,7 @@
 #include "qemu/jhash.h"
 #include "qemu/timer.h"
 #include "net/eth.h"
+#include "standard-headers/linux/virtio_net.h"
 
 #define HASHTABLE_MAX_SIZE 16384
 

net/trace-events

@@ -9,7 +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_proxy_main_vnet_info(const char *sta, uint32_t vnet_hdr, int size) ": %s pkt->vnet_hdr_len = %u, pkt->size = %d"
 
 # colo-compare.c
 colo_compare_main(const char *chr) ": %s"

net/vhost-vdpa.c

@@ -244,7 +244,7 @@ static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
         error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
     }
 
-    vhost_iova_tree_remove(tree, map);
+    vhost_iova_tree_remove(tree, *map);
 }
 
 static size_t vhost_vdpa_net_cvq_cmd_len(void)
@@ -263,29 +263,20 @@ 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. */
+/** Map CVQ buffer. */
-static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
+static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size,
-                                   const struct iovec *out_data,
+                                  bool write)
-                                   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.size = size - 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;
+        return r;
     }
 
     r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf,
@@ -294,63 +285,151 @@ static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
         goto dma_map_err;
     }
 
-    return true;
+    return 0;
 
 dma_map_err:
-    vhost_iova_tree_remove(v->iova_tree, &map);
+    vhost_iova_tree_remove(v->iova_tree, map);
-    return false;
+    return r;
 }
 
-/**
+static int vhost_vdpa_net_cvq_start(NetClientState *nc)
- * 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;
+    VhostVDPAState *s;
-    bool ok;
+    int r;
 
-    iov[0].iov_base = s->cvq_cmd_out_buffer;
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
-    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,
+    s = DO_UPCAST(VhostVDPAState, nc, nc);
-                                &iov[0].iov_len, false);
+    if (!s->vhost_vdpa.shadow_vqs_enabled) {
-    if (unlikely(!ok)) {
+        return 0;
-        return false;
     }
 
-    iov[1].iov_base = s->cvq_cmd_in_buffer;
+    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer,
-    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0,
+                               vhost_vdpa_net_cvq_cmd_page_len(), false);
-                                sizeof(virtio_net_ctrl_ack), iov[1].iov_base,
+    if (unlikely(r < 0)) {
-                                &in_copied, true);
+        return r;
-    if (unlikely(!ok)) {
+    }
+
+    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer,
+                               vhost_vdpa_net_cvq_cmd_page_len(), true);
+    if (unlikely(r < 0)) {
         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 r;
-    return true;
 }
 
+static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    if (s->vhost_vdpa.shadow_vqs_enabled) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer);
+    }
+}
+
+static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
+                                      size_t in_len)
+{
+    /* Buffers for the device */
+    const struct iovec out = {
+        .iov_base = s->cvq_cmd_out_buffer,
+        .iov_len = out_len,
+    };
+    const struct iovec in = {
+        .iov_base = s->cvq_cmd_in_buffer,
+        .iov_len = sizeof(virtio_net_ctrl_ack),
+    };
+    VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0);
+    int r;
+
+    r = vhost_svq_add(svq, &out, 1, &in, 1, NULL);
+    if (unlikely(r != 0)) {
+        if (unlikely(r == -ENOSPC)) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
+                          __func__);
+        }
+        return r;
+    }
+
+    /*
+     * 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
+     */
+    return vhost_svq_poll(svq);
+}
+
+static int vhost_vdpa_net_load(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    const struct vhost_vdpa *v = &s->vhost_vdpa;
+    const VirtIONet *n;
+    uint64_t features;
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    if (!v->shadow_vqs_enabled) {
+        return 0;
+    }
+
+    n = VIRTIO_NET(v->dev->vdev);
+    features = n->parent_obj.guest_features;
+    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
+        const struct virtio_net_ctrl_hdr ctrl = {
+            .class = VIRTIO_NET_CTRL_MAC,
+            .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET,
+        };
+        char *cursor = s->cvq_cmd_out_buffer;
+        ssize_t dev_written;
+
+        memcpy(cursor, &ctrl, sizeof(ctrl));
+        cursor += sizeof(ctrl);
+        memcpy(cursor, n->mac, sizeof(n->mac));
+
+        dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac),
+                                             sizeof(virtio_net_ctrl_ack));
+        if (unlikely(dev_written < 0)) {
+            return dev_written;
+        }
+
+        return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK;
+    }
+
+    return 0;
+}
+
+static NetClientInfo net_vhost_vdpa_cvq_info = {
+    .type = NET_CLIENT_DRIVER_VHOST_VDPA,
+    .size = sizeof(VhostVDPAState),
+    .receive = vhost_vdpa_receive,
+    .start = vhost_vdpa_net_cvq_start,
+    .load = vhost_vdpa_net_load,
+    .stop = vhost_vdpa_net_cvq_stop,
+    .cleanup = vhost_vdpa_cleanup,
+    .has_vnet_hdr = vhost_vdpa_has_vnet_hdr,
+    .has_ufo = vhost_vdpa_has_ufo,
+    .check_peer_type = vhost_vdpa_check_peer_type,
+};
+
 /**
  * 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,
+static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len)
-                                            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(len < sizeof(ctrl))) {
-    if (unlikely(n < sizeof(ctrl))) {
         qemu_log_mask(LOG_GUEST_ERROR,
-                      "%s: invalid legnth of out buffer %zu\n", __func__, n);
+                      "%s: invalid legnth of out buffer %zu\n", __func__, len);
         return false;
     }
 
+    memcpy(&ctrl, out_buf, sizeof(ctrl));
     switch (ctrl.class) {
     case VIRTIO_NET_CTRL_MAC:
         switch (ctrl.cmd) {
@@ -380,58 +459,45 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
                                             void *opaque)
 {
     VhostVDPAState *s = opaque;
-    size_t in_len, dev_written;
+    size_t in_len;
     virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
-    /* out and in buffers sent to the device */
+    /* Out buffer sent to both the vdpa device and the device model */
-    struct iovec dev_buffers[2] = {
+    struct iovec out = {
-        { .iov_base = s->cvq_cmd_out_buffer },
+        .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;
+    ssize_t dev_written = -EINVAL;
     bool ok;
 
-    ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers);
+    out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0,
+                             s->cvq_cmd_out_buffer,
+                             vhost_vdpa_net_cvq_cmd_len());
+    ok = vhost_vdpa_net_cvq_validate_cmd(s->cvq_cmd_out_buffer, out.iov_len);
     if (unlikely(!ok)) {
         goto out;
     }
 
-    ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1);
+    dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status));
-    if (unlikely(!ok)) {
+    if (unlikely(dev_written < 0)) {
         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));
+    memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status));
     if (status != VIRTIO_NET_OK) {
-        goto out;
+        return VIRTIO_NET_ERR;
     }
 
     status = VIRTIO_NET_ERR;
-    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1);
+    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, &out, 1);
     if (status != VIRTIO_NET_OK) {
         error_report("Bad CVQ processing in model");
     }
@@ -444,13 +510,7 @@ out:
     }
     vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status)));
     g_free(elem);
-    if (dev_buffers[0].iov_base) {
+    return dev_written < 0 ? dev_written : 0;
-        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 = {
@@ -475,7 +535,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
         nc = qemu_new_net_client(&net_vhost_vdpa_info, peer, device,
                                  name);
     } else {
-        nc = qemu_new_net_control_client(&net_vhost_vdpa_info, peer,
+        nc = qemu_new_net_control_client(&net_vhost_vdpa_cvq_info, peer,
                                          device, name);
     }
     snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA);
@@ -495,8 +555,6 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
 
         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) {

util/iova-tree.c

@@ -164,11 +164,11 @@ void iova_tree_foreach(IOVATree *tree, iova_tree_iterator iterator)
     g_tree_foreach(tree->tree, iova_tree_traverse, iterator);
 }
 
-void iova_tree_remove(IOVATree *tree, const DMAMap *map)
+void iova_tree_remove(IOVATree *tree, DMAMap map)
 {
     const DMAMap *overlap;
 
-    while ((overlap = iova_tree_find(tree, map))) {
+    while ((overlap = iova_tree_find(tree, &map))) {
         g_tree_remove(tree->tree, overlap);
     }
 }