Merge remote branch 'mst/for_anthony' into staging

8 files changed, 168 insertions, 88 deletions

diff --git a/hw/eepro100.c b/hw/eepro100.c
index 2b75c8f495..5f6dcb6e6e 100644
--- a/hw/eepro100.c
+++ b/hw/eepro100.c
@@ -219,7 +219,8 @@ typedef enum {
 
 typedef struct {
     PCIDevice dev;
-    uint8_t mult[8];            /* multicast mask array */
+    /* Hash register (multicast mask array, multiple individual addresses). */
+    uint8_t mult[8];
     int mmio_index;
     NICState *nic;
     NICConf conf;
@@ -599,7 +600,7 @@ static void nic_reset(void *opaque)
 {
     EEPRO100State *s = opaque;
     TRACE(OTHER, logout("%p\n", s));
-    /* TODO: Clearing of multicast table for selective reset, too? */
+    /* TODO: Clearing of hash register for selective reset, too? */
     memset(&s->mult[0], 0, sizeof(s->mult));
     nic_selective_reset(s);
 }
@@ -851,7 +852,14 @@ static void action_command(EEPRO100State *s)
         case CmdConfigure:
             cpu_physical_memory_read(s->cb_address + 8, &s->configuration[0],
                                      sizeof(s->configuration));
-            TRACE(OTHER, logout("configuration: %s\n", nic_dump(&s->configuration[0], 16)));
+            TRACE(OTHER, logout("configuration: %s\n",
+                                nic_dump(&s->configuration[0], 16)));
+            TRACE(OTHER, logout("configuration: %s\n",
+                                nic_dump(&s->configuration[16],
+                                ARRAY_SIZE(s->configuration) - 16)));
+            if (s->configuration[20] & BIT(6)) {
+                TRACE(OTHER, logout("Multiple IA bit\n"));
+            }
             break;
         case CmdMulticastList:
             set_multicast_list(s);
@@ -1647,12 +1655,6 @@ static ssize_t nic_receive(VLANClientState *nc, const uint8_t * buf, size_t size
     static const uint8_t broadcast_macaddr[6] =
         { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 
-    /* TODO: check multiple IA bit. */
-    if (s->configuration[20] & BIT(6)) {
-        missing("Multiple IA bit");
-        return -1;
-    }
-
     if (s->configuration[8] & 0x80) {
         /* CSMA is disabled. */
         logout("%p received while CSMA is disabled\n", s);
@@ -1702,6 +1704,16 @@ static ssize_t nic_receive(VLANClientState *nc, const uint8_t * buf, size_t size
         /* Promiscuous: receive all. */
         TRACE(RXTX, logout("%p received frame in promiscuous mode, len=%zu\n", s, size));
         rfd_status |= 0x0004;
+    } else if (s->configuration[20] & BIT(6)) {
+        /* Multiple IA bit set. */
+        unsigned mcast_idx = compute_mcast_idx(buf);
+        assert(mcast_idx < 64);
+        if (s->mult[mcast_idx >> 3] & (1 << (mcast_idx & 7))) {
+            TRACE(RXTX, logout("%p accepted, multiple IA bit set\n", s));
+        } else {
+            TRACE(RXTX, logout("%p frame ignored, multiple IA bit set\n", s));
+            return -1;
+        }
     } else {
         TRACE(RXTX, logout("%p received frame, ignored, len=%zu,%s\n", s, size,
               nic_dump(buf, size)));
diff --git a/hw/vhost.c b/hw/vhost.c
index 1b8624d981..8586f66bac 100644
--- a/hw/vhost.c
+++ b/hw/vhost.c
@@ -454,11 +454,6 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
     };
     struct VirtQueue *vvq = virtio_get_queue(vdev, idx);
 
-    if (!vdev->binding->set_guest_notifier) {
-        fprintf(stderr, "binding does not support guest notifiers\n");
-        return -ENOSYS;
-    }
-
     if (!vdev->binding->set_host_notifier) {
         fprintf(stderr, "binding does not support host notifiers\n");
         return -ENOSYS;
@@ -511,12 +506,6 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
         r = -errno;
         goto fail_alloc;
     }
-    r = vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, true);
-    if (r < 0) {
-        fprintf(stderr, "Error binding guest notifier: %d\n", -r);
-        goto fail_guest_notifier;
-    }
-
     r = vdev->binding->set_host_notifier(vdev->binding_opaque, idx, true);
     if (r < 0) {
         fprintf(stderr, "Error binding host notifier: %d\n", -r);
@@ -526,12 +515,14 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
     file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq));
     r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file);
     if (r) {
+        r = -errno;
         goto fail_kick;
     }
 
     file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq));
     r = ioctl(dev->control, VHOST_SET_VRING_CALL, &file);
     if (r) {
+        r = -errno;
         goto fail_call;
     }
 
@@ -541,8 +532,6 @@ fail_call:
 fail_kick:
     vdev->binding->set_host_notifier(vdev->binding_opaque, idx, false);
 fail_host_notifier:
-    vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, false);
-fail_guest_notifier:
 fail_alloc:
     cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx),
                               0, 0);
@@ -568,13 +557,6 @@ static void vhost_virtqueue_cleanup(struct vhost_dev *dev,
         .index = idx,
     };
     int r;
-    r = vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, false);
-    if (r < 0) {
-        fprintf(stderr, "vhost VQ %d guest cleanup failed: %d\n", idx, r);
-        fflush(stderr);
-    }
-    assert (r >= 0);
-
     r = vdev->binding->set_host_notifier(vdev->binding_opaque, idx, false);
     if (r < 0) {
         fprintf(stderr, "vhost VQ %d host cleanup failed: %d\n", idx, r);
@@ -647,15 +629,26 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
 int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
 {
     int i, r;
+    if (!vdev->binding->set_guest_notifiers) {
+        fprintf(stderr, "binding does not support guest notifiers\n");
+        r = -ENOSYS;
+        goto fail;
+    }
+
+    r = vdev->binding->set_guest_notifiers(vdev->binding_opaque, true);
+    if (r < 0) {
+        fprintf(stderr, "Error binding guest notifier: %d\n", -r);
+        goto fail_notifiers;
+    }
 
     r = vhost_dev_set_features(hdev, hdev->log_enabled);
     if (r < 0) {
-        goto fail;
+        goto fail_features;
     }
     r = ioctl(hdev->control, VHOST_SET_MEM_TABLE, hdev->mem);
     if (r < 0) {
         r = -errno;
-        goto fail;
+        goto fail_mem;
     }
     for (i = 0; i < hdev->nvqs; ++i) {
         r = vhost_virtqueue_init(hdev,
@@ -675,13 +668,14 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
                   (uint64_t)(unsigned long)hdev->log);
         if (r < 0) {
             r = -errno;
-            goto fail_vq;
+            goto fail_log;
         }
     }
 
     hdev->started = true;
 
     return 0;
+fail_log:
 fail_vq:
     while (--i >= 0) {
         vhost_virtqueue_cleanup(hdev,
@@ -689,13 +683,18 @@ fail_vq:
                                 hdev->vqs + i,
                                 i);
     }
+fail_mem:
+fail_features:
+    vdev->binding->set_guest_notifiers(vdev->binding_opaque, false);
+fail_notifiers:
 fail:
     return r;
 }
 
 void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
 {
-    int i;
+    int i, r;
+
     for (i = 0; i < hdev->nvqs; ++i) {
         vhost_virtqueue_cleanup(hdev,
                                 vdev,
@@ -704,6 +703,13 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
     }
     vhost_client_sync_dirty_bitmap(&hdev->client, 0,
                                    (target_phys_addr_t)~0x0ull);
+    r = vdev->binding->set_guest_notifiers(vdev->binding_opaque, false);
+    if (r < 0) {
+        fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r);
+        fflush(stderr);
+    }
+    assert (r >= 0);
+
     hdev->started = false;
     qemu_free(hdev->log);
     hdev->log_size = 0;
diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index 0a9cae22c4..7e1688cf69 100644
--- a/hw/virtio-net.c
+++ b/hw/virtio-net.c
@@ -54,6 +54,7 @@ typedef struct VirtIONet
     uint8_t nouni;
     uint8_t nobcast;
     uint8_t vhost_started;
+    bool vm_running;
     VMChangeStateEntry *vmstate;
     struct {
         int in_use;
@@ -98,6 +99,38 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)
     }
 }
 
+static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
+{
+    VirtIONet *n = to_virtio_net(vdev);
+    if (!n->nic->nc.peer) {
+        return;
+    }
+    if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
+        return;
+    }
+
+    if (!tap_get_vhost_net(n->nic->nc.peer)) {
+        return;
+    }
+    if (!!n->vhost_started == ((status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+                               (n->status & VIRTIO_NET_S_LINK_UP) &&
+                               n->vm_running)) {
+        return;
+    }
+    if (!n->vhost_started) {
+        int r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+        if (r < 0) {
+            fprintf(stderr, "unable to start vhost net: %d: "
+                    "falling back on userspace virtio\n", -r);
+        } else {
+            n->vhost_started = 1;
+        }
+    } else {
+        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+        n->vhost_started = 0;
+    }
+}
+
 static void virtio_net_set_link_status(VLANClientState *nc)
 {
     VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
@@ -110,6 +143,8 @@ static void virtio_net_set_link_status(VLANClientState *nc)
 
     if (n->status != old_status)
         virtio_notify_config(&n->vdev);
+
+    virtio_net_set_status(&n->vdev, n->vdev.status);
 }
 
 static void virtio_net_reset(VirtIODevice *vdev)
@@ -123,10 +158,6 @@ static void virtio_net_reset(VirtIODevice *vdev)
     n->nomulti = 0;
     n->nouni = 0;
     n->nobcast = 0;
-    if (n->vhost_started) {
-        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev);
-        n->vhost_started = 0;
-    }
 
     /* Flush any MAC and VLAN filter table state */
     n->mac_table.in_use = 0;
@@ -783,12 +814,9 @@ static void virtio_net_save(QEMUFile *f, void *opaque)
 {
     VirtIONet *n = opaque;
 
-    if (n->vhost_started) {
-        /* TODO: should we really stop the backend?
-         * If we don't, it might keep writing to memory. */
-        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
-        n->vhost_started = 0;
-    }
+    /* At this point, backend must be stopped, otherwise
+     * it might keep writing to memory. */
+    assert(!n->vhost_started);
     virtio_save(&n->vdev, f);
 
     qemu_put_buffer(f, n->mac, ETH_ALEN);
@@ -924,44 +952,14 @@ static NetClientInfo net_virtio_info = {
     .link_status_changed = virtio_net_set_link_status,
 };
 
-static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
-{
-    VirtIONet *n = to_virtio_net(vdev);
-    if (!n->nic->nc.peer) {
-        return;
-    }
-    if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
-        return;
-    }
-
-    if (!tap_get_vhost_net(n->nic->nc.peer)) {
-        return;
-    }
-    if (!!n->vhost_started == !!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
-        return;
-    }
-    if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
-        int r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), vdev);
-        if (r < 0) {
-            fprintf(stderr, "unable to start vhost net: %d: "
-                    "falling back on userspace virtio\n", -r);
-        } else {
-            n->vhost_started = 1;
-        }
-    } else {
-        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev);
-        n->vhost_started = 0;
-    }
-}
-
 static void virtio_net_vmstate_change(void *opaque, int running, int reason)
 {
     VirtIONet *n = opaque;
-    uint8_t status = running ? VIRTIO_CONFIG_S_DRIVER_OK : 0;
+    n->vm_running = running;
     /* This is called when vm is started/stopped,
-     * it will start/stop vhost backend if * appropriate
+     * it will start/stop vhost backend if appropriate
      * e.g. after migration. */
-    virtio_net_set_status(&n->vdev, n->vdev.status & status);
+    virtio_net_set_status(&n->vdev, n->vdev.status);
 }
 
 VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf,
@@ -1028,9 +1026,8 @@ void virtio_net_exit(VirtIODevice *vdev)
     VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev);
     qemu_del_vm_change_state_handler(n->vmstate);
 
-    if (n->vhost_started) {
-        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev);
-    }
+    /* This will stop vhost backend if appropriate. */
+    virtio_net_set_status(vdev, 0);
 
     qemu_purge_queued_packets(&n->nic->nc);
 
diff --git a/hw/virtio-pci.c b/hw/virtio-pci.c
index 86e6b0a561..729917d891 100644
--- a/hw/virtio-pci.c
+++ b/hw/virtio-pci.c
@@ -451,6 +451,33 @@ static int virtio_pci_set_guest_notifier(void *opaque, int n, bool assign)
     return 0;
 }
 
+static int virtio_pci_set_guest_notifiers(void *opaque, bool assign)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = proxy->vdev;
+    int r, n;
+
+    for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
+        if (!virtio_queue_get_num(vdev, n)) {
+            break;
+        }
+
+        r = virtio_pci_set_guest_notifier(opaque, n, assign);
+        if (r < 0) {
+            goto assign_error;
+        }
+    }
+
+    return 0;
+
+assign_error:
+    /* We get here on assignment failure. Recover by undoing for VQs 0 .. n. */
+    while (--n >= 0) {
+        virtio_pci_set_guest_notifier(opaque, n, !assign);
+    }
+    return r;
+}
+
 static int virtio_pci_set_host_notifier(void *opaque, int n, bool assign)
 {
     VirtIOPCIProxy *proxy = opaque;
@@ -488,7 +515,7 @@ static const VirtIOBindings virtio_pci_bindings = {
     .load_queue = virtio_pci_load_queue,
     .get_features = virtio_pci_get_features,
     .set_host_notifier = virtio_pci_set_host_notifier,
-    .set_guest_notifier = virtio_pci_set_guest_notifier,
+    .set_guest_notifiers = virtio_pci_set_guest_notifiers,
 };
 
 static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev,
diff --git a/hw/virtio.c b/hw/virtio.c
index fbef788854..c8a0fc6ff0 100644
--- a/hw/virtio.c
+++ b/hw/virtio.c
@@ -458,6 +458,8 @@ void virtio_reset(void *opaque)
     VirtIODevice *vdev = opaque;
     int i;
 
+    virtio_set_status(vdev, 0);
+
     if (vdev->reset)
         vdev->reset(vdev);
 
diff --git a/hw/virtio.h b/hw/virtio.h
index 96514e6c8b..02fa312d3e 100644
--- a/hw/virtio.h
+++ b/hw/virtio.h
@@ -93,7 +93,7 @@ typedef struct {
     int (*load_config)(void * opaque, QEMUFile *f);
     int (*load_queue)(void * opaque, int n, QEMUFile *f);
     unsigned (*get_features)(void * opaque);
-    int (*set_guest_notifier)(void * opaque, int n, bool assigned);
+    int (*set_guest_notifiers)(void * opaque, bool assigned);
     int (*set_host_notifier)(void * opaque, int n, bool assigned);
 } VirtIOBindings;
 
diff --git a/net.c b/net.c
index 3d0fde77b2..ed74c7f103 100644
--- a/net.c
+++ b/net.c
@@ -281,29 +281,64 @@ NICState *qemu_new_nic(NetClientInfo *info,
     return nic;
 }
 
-void qemu_del_vlan_client(VLANClientState *vc)
+static void qemu_cleanup_vlan_client(VLANClientState *vc)
 {
     if (vc->vlan) {
         QTAILQ_REMOVE(&vc->vlan->clients, vc, next);
     } else {
-        if (vc->send_queue) {
-            qemu_del_net_queue(vc->send_queue);
-        }
         QTAILQ_REMOVE(&non_vlan_clients, vc, next);
-        if (vc->peer) {
-            vc->peer->peer = NULL;
-        }
     }
 
     if (vc->info->cleanup) {
         vc->info->cleanup(vc);
     }
+}
 
+static void qemu_free_vlan_client(VLANClientState *vc)
+{
+    if (!vc->vlan) {
+        if (vc->send_queue) {
+            qemu_del_net_queue(vc->send_queue);
+        }
+        if (vc->peer) {
+            vc->peer->peer = NULL;
+        }
+    }
     qemu_free(vc->name);
     qemu_free(vc->model);
     qemu_free(vc);
 }
 
+void qemu_del_vlan_client(VLANClientState *vc)
+{
+    /* If there is a peer NIC, delete and cleanup client, but do not free. */
+    if (!vc->vlan && vc->peer && vc->peer->info->type == NET_CLIENT_TYPE_NIC) {
+        NICState *nic = DO_UPCAST(NICState, nc, vc->peer);
+        if (nic->peer_deleted) {
+            return;
+        }
+        nic->peer_deleted = true;
+        /* Let NIC know peer is gone. */
+        vc->peer->link_down = true;
+        if (vc->peer->info->link_status_changed) {
+            vc->peer->info->link_status_changed(vc->peer);
+        }
+        qemu_cleanup_vlan_client(vc);
+        return;
+    }
+
+    /* If this is a peer NIC and peer has already been deleted, free it now. */
+    if (!vc->vlan && vc->peer && vc->info->type == NET_CLIENT_TYPE_NIC) {
+        NICState *nic = DO_UPCAST(NICState, nc, vc);
+        if (nic->peer_deleted) {
+            qemu_free_vlan_client(vc->peer);
+        }
+    }
+
+    qemu_cleanup_vlan_client(vc);
+    qemu_free_vlan_client(vc);
+}
+
 VLANClientState *
 qemu_find_vlan_client_by_name(Monitor *mon, int vlan_id,
                               const char *client_str)
diff --git a/net.h b/net.h
index 518cf9c1f7..44c31a9b32 100644
--- a/net.h
+++ b/net.h
@@ -72,6 +72,7 @@ typedef struct NICState {
     VLANClientState nc;
     NICConf *conf;
     void *opaque;
+    bool peer_deleted;
 } NICState;
 
 struct VLANState {