net/virtio: add failover support

This patch adds support to handle failover device pairs of a virtio-net
device and a (vfio-)pci device, where the virtio-net acts as the standby
device and the (vfio-)pci device as the primary.

The general idea is that we have a pair of devices, a (vfio-)pci and a
emulated (virtio-net) device. Before migration the vfio device is
unplugged and data flows to the emulated device, on the target side
another (vfio-)pci device is plugged in to take over the data-path. In the
guest the net_failover module will pair net devices with the same MAC
address.

To achieve this we need:

1. Provide a callback function for the should_be_hidden DeviceListener.
   It is called when the primary device is plugged in. Evaluate the QOpt
   passed in to check if it is the matching primary device. It returns
   if the device should be hidden or not.
   When it should be hidden it stores the device options in the VirtioNet
   struct and the device is added once the VIRTIO_NET_F_STANDBY feature is
   negotiated during virtio feature negotiation.

   If the virtio-net devices are not realized at the time the (vfio-)pci
   devices are realized, we need to connect the devices later. This way
   we make sure primary and standby devices can be specified in any
   order.

2. Register a callback for migration status notifier. When called it
   will unplug its primary device before the migration happens.

3. Register a callback for the migration code that checks if a device
   needs to be unplugged from the guest.

Signed-off-by: Jens Freimann <jfreimann@redhat.com>
Message-Id: <20191029114905.6856-11-jfreimann@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 302 insertions, 0 deletions

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index d3d688a5f8..314f365e7c 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -12,6 +12,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/atomic.h"
 #include "qemu/iov.h"
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
@@ -21,6 +22,10 @@
 #include "net/tap.h"
 #include "qemu/error-report.h"
 #include "qemu/timer.h"
+#include "qemu/option.h"
+#include "qemu/option_int.h"
+#include "qemu/config-file.h"
+#include "qapi/qmp/qdict.h"
 #include "hw/virtio/virtio-net.h"
 #include "net/vhost_net.h"
 #include "net/announce.h"
@@ -28,11 +33,15 @@
 #include "qapi/error.h"
 #include "qapi/qapi-events-net.h"
 #include "hw/qdev-properties.h"
+#include "qapi/qapi-types-migration.h"
+#include "qapi/qapi-events-migration.h"
 #include "hw/virtio/virtio-access.h"
 #include "migration/misc.h"
 #include "standard-headers/linux/ethtool.h"
 #include "sysemu/sysemu.h"
 #include "trace.h"
+#include "monitor/qdev.h"
+#include "hw/pci/pci.h"
 
 #define VIRTIO_NET_VM_VERSION    11
 
@@ -746,9 +755,99 @@ static inline uint64_t virtio_net_supported_guest_offloads(VirtIONet *n)
     return virtio_net_guest_offloads_by_features(vdev->guest_features);
 }
 
+static void failover_add_primary(VirtIONet *n, Error **errp)
+{
+    Error *err = NULL;
+
+    n->primary_device_opts = qemu_opts_find(qemu_find_opts("device"),
+            n->primary_device_id);
+    if (n->primary_device_opts) {
+        n->primary_dev = qdev_device_add(n->primary_device_opts, &err);
+        if (err) {
+            qemu_opts_del(n->primary_device_opts);
+        }
+        if (n->primary_dev) {
+            n->primary_bus = n->primary_dev->parent_bus;
+            if (err) {
+                qdev_unplug(n->primary_dev, &err);
+                qdev_set_id(n->primary_dev, "");
+
+            }
+        }
+    } else {
+        error_setg(errp, "Primary device not found");
+        error_append_hint(errp, "Virtio-net failover will not work. Make "
+            "sure primary device has parameter"
+            " failover_pair_id=<virtio-net-id>\n");
+}
+    if (err) {
+        error_propagate(errp, err);
+    }
+}
+
+static int is_my_primary(void *opaque, QemuOpts *opts, Error **errp)
+{
+    VirtIONet *n = opaque;
+    int ret = 0;
+
+    const char *standby_id = qemu_opt_get(opts, "failover_pair_id");
+
+    if (standby_id != NULL && (g_strcmp0(standby_id, n->netclient_name) == 0)) {
+        n->primary_device_id = g_strdup(opts->id);
+        ret = 1;
+    }
+
+    return ret;
+}
+
+static DeviceState *virtio_net_find_primary(VirtIONet *n, Error **errp)
+{
+    DeviceState *dev = NULL;
+    Error *err = NULL;
+
+    if (qemu_opts_foreach(qemu_find_opts("device"),
+                         is_my_primary, n, &err)) {
+        if (err) {
+            error_propagate(errp, err);
+            return NULL;
+        }
+        if (n->primary_device_id) {
+            dev = qdev_find_recursive(sysbus_get_default(),
+                    n->primary_device_id);
+        } else {
+            error_setg(errp, "Primary device id not found");
+            return NULL;
+        }
+    }
+    return dev;
+}
+
+
+
+static DeviceState *virtio_connect_failover_devices(VirtIONet *n,
+                                                    DeviceState *dev,
+                                                    Error **errp)
+{
+    DeviceState *prim_dev = NULL;
+    Error *err = NULL;
+
+    prim_dev = virtio_net_find_primary(n, &err);
+    if (prim_dev) {
+        n->primary_device_id = g_strdup(prim_dev->id);
+        n->primary_device_opts = prim_dev->opts;
+    } else {
+        if (err) {
+            error_propagate(errp, err);
+        }
+    }
+
+    return prim_dev;
+}
+
 static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
+    Error *err = NULL;
     int i;
 
     if (n->mtu_bypass_backend &&
@@ -790,6 +889,28 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
     } else {
         memset(n->vlans, 0xff, MAX_VLAN >> 3);
     }
+
+    if (virtio_has_feature(features, VIRTIO_NET_F_STANDBY)) {
+        qapi_event_send_failover_negotiated(n->netclient_name);
+        atomic_set(&n->primary_should_be_hidden, false);
+        failover_add_primary(n, &err);
+        if (err) {
+            n->primary_dev = virtio_connect_failover_devices(n, n->qdev, &err);
+            if (err) {
+                goto out_err;
+            }
+            failover_add_primary(n, &err);
+            if (err) {
+                goto out_err;
+            }
+        }
+    }
+    return;
+
+out_err:
+    if (err) {
+        warn_report_err(err);
+    }
 }
 
 static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
@@ -2650,6 +2771,150 @@ void virtio_net_set_netclient_name(VirtIONet *n, const char *name,
     n->netclient_type = g_strdup(type);
 }
 
+static bool failover_unplug_primary(VirtIONet *n)
+{
+    HotplugHandler *hotplug_ctrl;
+    PCIDevice *pci_dev;
+    Error *err = NULL;
+
+    hotplug_ctrl = qdev_get_hotplug_handler(n->primary_dev);
+    if (hotplug_ctrl) {
+        pci_dev = PCI_DEVICE(n->primary_dev);
+        pci_dev->partially_hotplugged = true;
+        hotplug_handler_unplug_request(hotplug_ctrl, n->primary_dev, &err);
+        if (err) {
+            error_report_err(err);
+            return false;
+        }
+    } else {
+        return false;
+    }
+    return true;
+}
+
+static bool failover_replug_primary(VirtIONet *n, Error **errp)
+{
+    HotplugHandler *hotplug_ctrl;
+    PCIDevice *pdev = PCI_DEVICE(n->primary_dev);
+
+    if (!pdev->partially_hotplugged) {
+        return true;
+    }
+    if (!n->primary_device_opts) {
+        n->primary_device_opts = qemu_opts_from_qdict(
+                qemu_find_opts("device"),
+                n->primary_device_dict, errp);
+    }
+    if (n->primary_device_opts) {
+        if (n->primary_dev) {
+            n->primary_bus = n->primary_dev->parent_bus;
+        }
+        qdev_set_parent_bus(n->primary_dev, n->primary_bus);
+        n->primary_should_be_hidden = false;
+        qemu_opt_set_bool(n->primary_device_opts,
+                "partially_hotplugged", true, errp);
+        hotplug_ctrl = qdev_get_hotplug_handler(n->primary_dev);
+        if (hotplug_ctrl) {
+            hotplug_handler_pre_plug(hotplug_ctrl, n->primary_dev, errp);
+            hotplug_handler_plug(hotplug_ctrl, n->primary_dev, errp);
+        }
+        if (!n->primary_dev) {
+            error_setg(errp, "virtio_net: couldn't find primary device");
+        }
+    }
+    return *errp != NULL;
+}
+
+static void virtio_net_handle_migration_primary(VirtIONet *n,
+                                                MigrationState *s)
+{
+    bool should_be_hidden;
+    Error *err = NULL;
+
+    should_be_hidden = atomic_read(&n->primary_should_be_hidden);
+
+    if (!n->primary_dev) {
+        n->primary_dev = virtio_connect_failover_devices(n, n->qdev, &err);
+        if (!n->primary_dev) {
+            return;
+        }
+    }
+
+    if (migration_in_setup(s) && !should_be_hidden &&
+        n->primary_dev) {
+        if (failover_unplug_primary(n)) {
+            vmstate_unregister(n->primary_dev, qdev_get_vmsd(n->primary_dev),
+                    n->primary_dev);
+            qapi_event_send_unplug_primary(n->primary_device_id);
+            atomic_set(&n->primary_should_be_hidden, true);
+        } else {
+            warn_report("couldn't unplug primary device");
+        }
+    } else if (migration_has_failed(s)) {
+        /* We already unplugged the device let's plugged it back */
+        if (!failover_replug_primary(n, &err)) {
+            if (err) {
+                error_report_err(err);
+            }
+        }
+    }
+}
+
+static void virtio_net_migration_state_notifier(Notifier *notifier, void *data)
+{
+    MigrationState *s = data;
+    VirtIONet *n = container_of(notifier, VirtIONet, migration_state);
+    virtio_net_handle_migration_primary(n, s);
+}
+
+static int virtio_net_primary_should_be_hidden(DeviceListener *listener,
+            QemuOpts *device_opts)
+{
+    VirtIONet *n = container_of(listener, VirtIONet, primary_listener);
+    bool match_found;
+    bool hide;
+
+    n->primary_device_dict = qemu_opts_to_qdict(device_opts,
+            n->primary_device_dict);
+    if (n->primary_device_dict) {
+        g_free(n->standby_id);
+        n->standby_id = g_strdup(qdict_get_try_str(n->primary_device_dict,
+                    "failover_pair_id"));
+    }
+    if (device_opts && g_strcmp0(n->standby_id, n->netclient_name) == 0) {
+        match_found = true;
+    } else {
+        match_found = false;
+        hide = false;
+        g_free(n->standby_id);
+        n->primary_device_dict = NULL;
+        goto out;
+    }
+
+    n->primary_device_opts = device_opts;
+
+    /* primary_should_be_hidden is set during feature negotiation */
+    hide = atomic_read(&n->primary_should_be_hidden);
+
+    if (n->primary_device_dict) {
+        g_free(n->primary_device_id);
+        n->primary_device_id = g_strdup(qdict_get_try_str(
+                    n->primary_device_dict, "id"));
+        if (!n->primary_device_id) {
+            warn_report("primary_device_id not set");
+        }
+    }
+
+out:
+    if (match_found && hide) {
+        return 1;
+    } else if (match_found && !hide) {
+        return 0;
+    } else {
+        return -1;
+    }
+}
+
 static void virtio_net_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -2680,6 +2945,16 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
         n->host_features |= (1ULL << VIRTIO_NET_F_SPEED_DUPLEX);
     }
 
+    if (n->failover) {
+        n->primary_listener.should_be_hidden =
+            virtio_net_primary_should_be_hidden;
+        atomic_set(&n->primary_should_be_hidden, true);
+        device_listener_register(&n->primary_listener);
+        n->migration_state.notify = virtio_net_migration_state_notifier;
+        add_migration_state_change_notifier(&n->migration_state);
+        n->host_features |= (1ULL << VIRTIO_NET_F_STANDBY);
+    }
+
     virtio_net_set_config_size(n, n->host_features);
     virtio_init(vdev, "virtio-net", VIRTIO_ID_NET, n->config_size);
 
@@ -2802,6 +3077,13 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
     g_free(n->mac_table.macs);
     g_free(n->vlans);
 
+    if (n->failover) {
+        g_free(n->primary_device_id);
+        g_free(n->standby_id);
+        qobject_unref(n->primary_device_dict);
+        n->primary_device_dict = NULL;
+    }
+
     max_queues = n->multiqueue ? n->max_queues : 1;
     for (i = 0; i < max_queues; i++) {
         virtio_net_del_queue(n, i);
@@ -2839,6 +3121,23 @@ static int virtio_net_pre_save(void *opaque)
     return 0;
 }
 
+static bool primary_unplug_pending(void *opaque)
+{
+    DeviceState *dev = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VirtIONet *n = VIRTIO_NET(vdev);
+
+    return n->primary_dev ? n->primary_dev->pending_deleted_event : false;
+}
+
+static bool dev_unplug_pending(void *opaque)
+{
+    DeviceState *dev = opaque;
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(dev);
+
+    return vdc->primary_unplug_pending(dev);
+}
+
 static const VMStateDescription vmstate_virtio_net = {
     .name = "virtio-net",
     .minimum_version_id = VIRTIO_NET_VM_VERSION,
@@ -2848,6 +3147,7 @@ static const VMStateDescription vmstate_virtio_net = {
         VMSTATE_END_OF_LIST()
     },
     .pre_save = virtio_net_pre_save,
+    .dev_unplug_pending = dev_unplug_pending,
 };
 
 static Property virtio_net_properties[] = {
@@ -2909,6 +3209,7 @@ static Property virtio_net_properties[] = {
                      true),
     DEFINE_PROP_INT32("speed", VirtIONet, net_conf.speed, SPEED_UNKNOWN),
     DEFINE_PROP_STRING("duplex", VirtIONet, net_conf.duplex_str),
+    DEFINE_PROP_BOOL("failover", VirtIONet, failover, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -2934,6 +3235,7 @@ static void virtio_net_class_init(ObjectClass *klass, void *data)
     vdc->legacy_features |= (0x1 << VIRTIO_NET_F_GSO);
     vdc->post_load = virtio_net_post_load_virtio;
     vdc->vmsd = &vmstate_virtio_net_device;
+    vdc->primary_unplug_pending = primary_unplug_pending;
 }
 
 static const TypeInfo virtio_net_info = {