net: add support of mac-programming over macvtap in QEMU side

Currently macvtap based macvlan device is working in promiscuous
mode, we want to implement mac-programming over macvtap through
Libvirt for better performance.

Design:
 QEMU notifies Libvirt when rx-filter config is changed in guest,
 then Libvirt query the rx-filter information by a monitor command,
 and sync the change to macvtap device. Related rx-filter config
 of the nic contains main mac, rx-mode items and vlan table.

This patch adds a QMP event to notify management of rx-filter change,
and adds a monitor command for management to query rx-filter
information.

Test:
 If we repeatedly add/remove vlan, and change macaddr of vlan
 interfaces in guest by a loop script.

Result:
 The events will flood the QMP client(management), management takes
 too much resource to process the events.

 Event_throttle API (set rate to 1 ms) can avoid the events to flood
 QMP client, but it could cause an unexpected delay (~1ms), guests
 guests normally expect rx-filter updates immediately.

 So we use a flag for each nic to avoid events flooding, the event
 is emitted once until the query command is executed. The flag
 implementation could not introduce unexpected delay.

There maybe exist an uncontrollable delay if we let Libvirt do the
real change, guests normally expect rx-filter updates immediately.
But it's another separate issue, we can investigate it when the
work in Libvirt side is done.

Michael S. Tsirkin: tweaked to enable events on start
Michael S. Tsirkin: fixed not to crash when no id
Michael S. Tsirkin: fold in patch:
   "additional fixes for mac-programming feature"
Amos Kong: always notify QMP client if mactable is changed
Amos Kong: return NULL list if no net client supports rx-filter query

Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Amos Kong <akong@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

8 files changed, 336 insertions, 6 deletions

diff --git a/QMP/qmp-events.txt b/QMP/qmp-events.txt
index 24e804e94..39b601646 100644
--- a/QMP/qmp-events.txt
+++ b/QMP/qmp-events.txt
@@ -172,6 +172,23 @@ Data:
   },
   "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
 
+NIC_RX_FILTER_CHANGED
+-----------------
+
+The event is emitted once until the query command is executed,
+the first event will always be emitted.
+
+Data:
+
+- "name": net client name (json-string)
+- "path": device path (json-string)
+
+{ "event": "NIC_RX_FILTER_CHANGED",
+  "data": { "name": "vnet0",
+            "path": "/machine/peripheral/vnet0/virtio-backend" },
+  "timestamp": { "seconds": 1368697518, "microseconds": 326866 } }
+}
+
 RESET
 -----
 
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 1ea95564a..679f50c33 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -21,6 +21,8 @@
 #include "hw/virtio/virtio-net.h"
 #include "net/vhost_net.h"
 #include "hw/virtio/virtio-bus.h"
+#include "qapi/qmp/qjson.h"
+#include "monitor/monitor.h"
 
 #define VIRTIO_NET_VM_VERSION    11
 
@@ -192,6 +194,105 @@ static void virtio_net_set_link_status(NetClientState *nc)
     virtio_net_set_status(vdev, vdev->status);
 }
 
+static void rxfilter_notify(NetClientState *nc)
+{
+    QObject *event_data;
+    VirtIONet *n = qemu_get_nic_opaque(nc);
+
+    if (nc->rxfilter_notify_enabled) {
+        if (n->netclient_name) {
+            event_data = qobject_from_jsonf("{ 'name': %s, 'path': %s }",
+                                    n->netclient_name,
+                                    object_get_canonical_path(OBJECT(n->qdev)));
+        } else {
+            event_data = qobject_from_jsonf("{ 'path': %s }",
+                                    object_get_canonical_path(OBJECT(n->qdev)));
+        }
+        monitor_protocol_event(QEVENT_NIC_RX_FILTER_CHANGED, event_data);
+        qobject_decref(event_data);
+
+        /* disable event notification to avoid events flooding */
+        nc->rxfilter_notify_enabled = 0;
+    }
+}
+
+static char *mac_strdup_printf(const uint8_t *mac)
+{
+    return g_strdup_printf("%.2x:%.2x:%.2x:%.2x:%.2x:%.2x", mac[0],
+                            mac[1], mac[2], mac[3], mac[4], mac[5]);
+}
+
+static RxFilterInfo *virtio_net_query_rxfilter(NetClientState *nc)
+{
+    VirtIONet *n = qemu_get_nic_opaque(nc);
+    RxFilterInfo *info;
+    strList *str_list, *entry;
+    intList *int_list, *int_entry;
+    int i, j;
+
+    info = g_malloc0(sizeof(*info));
+    info->name = g_strdup(nc->name);
+    info->promiscuous = n->promisc;
+
+    if (n->nouni) {
+        info->unicast = RX_STATE_NONE;
+    } else if (n->alluni) {
+        info->unicast = RX_STATE_ALL;
+    } else {
+        info->unicast = RX_STATE_NORMAL;
+    }
+
+    if (n->nomulti) {
+        info->multicast = RX_STATE_NONE;
+    } else if (n->allmulti) {
+        info->multicast = RX_STATE_ALL;
+    } else {
+        info->multicast = RX_STATE_NORMAL;
+    }
+
+    info->broadcast_allowed = n->nobcast;
+    info->multicast_overflow = n->mac_table.multi_overflow;
+    info->unicast_overflow = n->mac_table.uni_overflow;
+
+    info->main_mac = mac_strdup_printf(n->mac);
+
+    str_list = NULL;
+    for (i = 0; i < n->mac_table.first_multi; i++) {
+        entry = g_malloc0(sizeof(*entry));
+        entry->value = mac_strdup_printf(n->mac_table.macs + i * ETH_ALEN);
+        entry->next = str_list;
+        str_list = entry;
+    }
+    info->unicast_table = str_list;
+
+    str_list = NULL;
+    for (i = n->mac_table.first_multi; i < n->mac_table.in_use; i++) {
+        entry = g_malloc0(sizeof(*entry));
+        entry->value = mac_strdup_printf(n->mac_table.macs + i * ETH_ALEN);
+        entry->next = str_list;
+        str_list = entry;
+    }
+    info->multicast_table = str_list;
+
+    int_list = NULL;
+    for (i = 0; i < MAX_VLAN >> 5; i++) {
+        for (j = 0; n->vlans[i] && j < 0x1f; j++) {
+            if (n->vlans[i] & (1U << j)) {
+                int_entry = g_malloc0(sizeof(*int_entry));
+                int_entry->value = (i << 5) + j;
+                int_entry->next = int_list;
+                int_list = int_entry;
+            }
+        }
+    }
+    info->vlan_table = int_list;
+
+    /* enable event notification after query */
+    nc->rxfilter_notify_enabled = 1;
+
+    return info;
+}
+
 static void virtio_net_reset(VirtIODevice *vdev)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
@@ -420,6 +521,7 @@ static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
 {
     uint8_t on;
     size_t s;
+    NetClientState *nc = qemu_get_queue(n->nic);
 
     s = iov_to_buf(iov, iov_cnt, 0, &on, sizeof(on));
     if (s != sizeof(on)) {
@@ -442,6 +544,8 @@ static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
         return VIRTIO_NET_ERR;
     }
 
+    rxfilter_notify(nc);
+
     return VIRTIO_NET_OK;
 }
 
@@ -487,6 +591,7 @@ static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
 {
     struct virtio_net_ctrl_mac mac_data;
     size_t s;
+    NetClientState *nc = qemu_get_queue(n->nic);
 
     if (cmd == VIRTIO_NET_CTRL_MAC_ADDR_SET) {
         if (iov_size(iov, iov_cnt) != sizeof(n->mac)) {
@@ -495,6 +600,8 @@ static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
         s = iov_to_buf(iov, iov_cnt, 0, &n->mac, sizeof(n->mac));
         assert(s == sizeof(n->mac));
         qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
+        rxfilter_notify(nc);
+
         return VIRTIO_NET_OK;
     }
 
@@ -512,19 +619,19 @@ static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
                    sizeof(mac_data.entries));
     mac_data.entries = ldl_p(&mac_data.entries);
     if (s != sizeof(mac_data.entries)) {
-        return VIRTIO_NET_ERR;
+        goto error;
     }
     iov_discard_front(&iov, &iov_cnt, s);
 
     if (mac_data.entries * ETH_ALEN > iov_size(iov, iov_cnt)) {
-        return VIRTIO_NET_ERR;
+        goto error;
     }
 
     if (mac_data.entries <= MAC_TABLE_ENTRIES) {
         s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,
                        mac_data.entries * ETH_ALEN);
         if (s != mac_data.entries * ETH_ALEN) {
-            return VIRTIO_NET_ERR;
+            goto error;
         }
         n->mac_table.in_use += mac_data.entries;
     } else {
@@ -539,27 +646,33 @@ static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
                    sizeof(mac_data.entries));
     mac_data.entries = ldl_p(&mac_data.entries);
     if (s != sizeof(mac_data.entries)) {
-        return VIRTIO_NET_ERR;
+        goto error;
     }
 
     iov_discard_front(&iov, &iov_cnt, s);
 
     if (mac_data.entries * ETH_ALEN != iov_size(iov, iov_cnt)) {
-        return VIRTIO_NET_ERR;
+        goto error;
     }
 
     if (n->mac_table.in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {
         s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,
                        mac_data.entries * ETH_ALEN);
         if (s != mac_data.entries * ETH_ALEN) {
-            return VIRTIO_NET_ERR;
+            goto error;
         }
         n->mac_table.in_use += mac_data.entries;
     } else {
         n->mac_table.multi_overflow = 1;
     }
 
+    rxfilter_notify(nc);
+
     return VIRTIO_NET_OK;
+
+error:
+    rxfilter_notify(nc);
+    return VIRTIO_NET_ERR;
 }
 
 static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
@@ -567,6 +680,7 @@ static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
 {
     uint16_t vid;
     size_t s;
+    NetClientState *nc = qemu_get_queue(n->nic);
 
     s = iov_to_buf(iov, iov_cnt, 0, &vid, sizeof(vid));
     vid = lduw_p(&vid);
@@ -584,6 +698,8 @@ static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
     else
         return VIRTIO_NET_ERR;
 
+    rxfilter_notify(nc);
+
     return VIRTIO_NET_OK;
 }
 
@@ -1312,6 +1428,7 @@ static NetClientInfo net_virtio_info = {
     .receive = virtio_net_receive,
         .cleanup = virtio_net_cleanup,
     .link_status_changed = virtio_net_set_link_status,
+    .query_rx_filter = virtio_net_query_rxfilter,
 };
 
 static bool virtio_net_guest_notifier_pending(VirtIODevice *vdev, int idx)
@@ -1373,6 +1490,7 @@ static int virtio_net_device_init(VirtIODevice *vdev)
 
     DeviceState *qdev = DEVICE(vdev);
     VirtIONet *n = VIRTIO_NET(vdev);
+    NetClientState *nc;
 
     virtio_init(VIRTIO_DEVICE(n), "virtio-net", VIRTIO_ID_NET,
                                   n->config_size);
@@ -1439,6 +1557,9 @@ static int virtio_net_device_init(VirtIODevice *vdev)
 
     n->vlans = g_malloc0(MAX_VLAN >> 3);
 
+    nc = qemu_get_queue(n->nic);
+    nc->rxfilter_notify_enabled = 1;
+
     n->qdev = qdev;
     register_savevm(qdev, "virtio-net", -1, VIRTIO_NET_VM_VERSION,
                     virtio_net_save, virtio_net_load, n);
diff --git a/include/monitor/monitor.h b/include/monitor/monitor.h
index 1a6cfcf68..1942cc42f 100644
--- a/include/monitor/monitor.h
+++ b/include/monitor/monitor.h
@@ -41,6 +41,7 @@ typedef enum MonitorEvent {
     QEVENT_BLOCK_JOB_READY,
     QEVENT_DEVICE_DELETED,
     QEVENT_DEVICE_TRAY_MOVED,
+    QEVENT_NIC_RX_FILTER_CHANGED,
     QEVENT_SUSPEND,
     QEVENT_SUSPEND_DISK,
     QEVENT_WAKEUP,
diff --git a/include/net/net.h b/include/net/net.h
index 43d85a16e..30e4b0406 100644
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -49,6 +49,7 @@ typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int);
 typedef void (NetCleanup) (NetClientState *);
 typedef void (LinkStatusChanged)(NetClientState *);
 typedef void (NetClientDestructor)(NetClientState *);
+typedef RxFilterInfo *(QueryRxFilter)(NetClientState *);
 
 typedef struct NetClientInfo {
     NetClientOptionsKind type;
@@ -59,6 +60,7 @@ typedef struct NetClientInfo {
     NetCanReceive *can_receive;
     NetCleanup *cleanup;
     LinkStatusChanged *link_status_changed;
+    QueryRxFilter *query_rx_filter;
     NetPoll *poll;
 } NetClientInfo;
 
@@ -74,6 +76,7 @@ struct NetClientState {
     unsigned receive_disabled : 1;
     NetClientDestructor *destructor;
     unsigned int queue_index;
+    unsigned rxfilter_notify_enabled:1;
 };
 
 typedef struct NICState {
diff --git a/monitor.c b/monitor.c
index 9be515c13..4278ea354 100644
--- a/monitor.c
+++ b/monitor.c
@@ -490,6 +490,7 @@ static const char *monitor_event_names[] = {
     [QEVENT_BLOCK_JOB_READY] = "BLOCK_JOB_READY",
     [QEVENT_DEVICE_DELETED] = "DEVICE_DELETED",
     [QEVENT_DEVICE_TRAY_MOVED] = "DEVICE_TRAY_MOVED",
+    [QEVENT_NIC_RX_FILTER_CHANGED] = "NIC_RX_FILTER_CHANGED",
     [QEVENT_SUSPEND] = "SUSPEND",
     [QEVENT_SUSPEND_DISK] = "SUSPEND_DISK",
     [QEVENT_WAKEUP] = "WAKEUP",
diff --git a/net/net.c b/net/net.c
index 43a74e43a..c0d61bf78 100644
--- a/net/net.c
+++ b/net/net.c
@@ -961,6 +961,54 @@ void print_net_client(Monitor *mon, NetClientState *nc)
                    nc->info_str);
 }
 
+RxFilterInfoList *qmp_query_rx_filter(bool has_name, const char *name,
+                                      Error **errp)
+{
+    NetClientState *nc;
+    RxFilterInfoList *filter_list = NULL, *last_entry = NULL;
+
+    QTAILQ_FOREACH(nc, &net_clients, next) {
+        RxFilterInfoList *entry;
+        RxFilterInfo *info;
+
+        if (has_name && strcmp(nc->name, name) != 0) {
+            continue;
+        }
+
+        /* only query rx-filter information of NIC */
+        if (nc->info->type != NET_CLIENT_OPTIONS_KIND_NIC) {
+            if (has_name) {
+                error_setg(errp, "net client(%s) isn't a NIC", name);
+                break;
+            }
+            continue;
+        }
+
+        if (nc->info->query_rx_filter) {
+            info = nc->info->query_rx_filter(nc);
+            entry = g_malloc0(sizeof(*entry));
+            entry->value = info;
+
+            if (!filter_list) {
+                filter_list = entry;
+            } else {
+                last_entry->next = entry;
+            }
+            last_entry = entry;
+        } else if (has_name) {
+            error_setg(errp, "net client(%s) doesn't support"
+                       " rx-filter querying", name);
+            break;
+        }
+    }
+
+    if (filter_list == NULL && !error_is_set(errp) && has_name) {
+        error_setg(errp, "invalid net client name: %s", name);
+    }
+
+    return filter_list;
+}
+
 void do_info_network(Monitor *mon, const QDict *qdict)
 {
     NetClientState *nc, *peer;
diff --git a/qapi-schema.json b/qapi-schema.json
index 5c32528a1..95ba5a6f0 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -3712,3 +3712,79 @@
             '*cpuid-input-ecx': 'int',
             'cpuid-register': 'X86CPURegister32',
             'features': 'int' } }
+
+##
+# @RxState:
+#
+# Packets receiving state
+#
+# @normal: filter assigned packets according to the mac-table
+#
+# @none: don't receive any assigned packet
+#
+# @all: receive all assigned packets
+#
+# Since: 1.6
+##
+{ 'enum': 'RxState', 'data': [ 'normal', 'none', 'all' ] }
+
+##
+# @RxFilterInfo:
+#
+# Rx-filter information for a NIC.
+#
+# @name: net client name
+#
+# @promiscuous: whether promiscuous mode is enabled
+#
+# @multicast: multicast receive state
+#
+# @unicast: unicast receive state
+#
+# @broadcast-allowed: whether to receive broadcast
+#
+# @multicast-overflow: multicast table is overflowed or not
+#
+# @unicast-overflow: unicast table is overflowed or not
+#
+# @main-mac: the main macaddr string
+#
+# @vlan-table: a list of active vlan id
+#
+# @unicast-table: a list of unicast macaddr string
+#
+# @multicast-table: a list of multicast macaddr string
+#
+# Since 1.6
+##
+
+{ 'type': 'RxFilterInfo',
+  'data': {
+    'name':               'str',
+    'promiscuous':        'bool',
+    'multicast':          'RxState',
+    'unicast':            'RxState',
+    'broadcast-allowed':  'bool',
+    'multicast-overflow': 'bool',
+    'unicast-overflow':   'bool',
+    'main-mac':           'str',
+    'vlan-table':         ['int'],
+    'unicast-table':      ['str'],
+    'multicast-table':    ['str'] }}
+
+##
+# @query-rx-filter:
+#
+# Return rx-filter information for all NICs (or for the given NIC).
+#
+# @name: #optional net client name
+#
+# Returns: list of @RxFilterInfo for all NICs (or for the given NIC).
+#          Returns an error if the given @name doesn't exist, or given
+#          NIC doesn't support rx-filter querying, or given net client
+#          isn't a NIC.
+#
+# Since: 1.6
+##
+{ 'command': 'query-rx-filter', 'data': { '*name': 'str' },
+  'returns': ['RxFilterInfo'] }
diff --git a/qmp-commands.hx b/qmp-commands.hx
index 362f0e1ef..aee3f961f 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -3043,3 +3043,66 @@ Example:
 <- { "return": {} }
 
 EQMP
+    {
+        .name       = "query-rx-filter",
+        .args_type  = "name:s?",
+        .mhandler.cmd_new = qmp_marshal_input_query_rx_filter,
+    },
+
+SQMP
+query-rx-filter
+---------------
+
+Show rx-filter information.
+
+Returns a json-array of rx-filter information for all NICs (or for the
+given NIC), returning an error if the given NIC doesn't exist, or
+given NIC doesn't support rx-filter querying, or given net client
+isn't a NIC.
+
+The query will clear the event notification flag of each NIC, then qemu
+will start to emit event to QMP monitor.
+
+Each array entry contains the following:
+
+- "name": net client name (json-string)
+- "promiscuous": promiscuous mode is enabled (json-bool)
+- "multicast": multicast receive state (one of 'normal', 'none', 'all')
+- "unicast": unicast receive state  (one of 'normal', 'none', 'all')
+- "broadcast-allowed": allow to receive broadcast (json-bool)
+- "multicast-overflow": multicast table is overflowed (json-bool)
+- "unicast-overflow": unicast table is overflowed (json-bool)
+- "main-mac": main macaddr string (json-string)
+- "vlan-table": a json-array of active vlan id
+- "unicast-table": a json-array of unicast macaddr string
+- "multicast-table": a json-array of multicast macaddr string
+
+Example:
+
+-> { "execute": "query-rx-filter", "arguments": { "name": "vnet0" } }
+<- { "return": [
+        {
+            "promiscuous": true,
+            "name": "vnet0",
+            "main-mac": "52:54:00:12:34:56",
+            "unicast": "normal",
+            "vlan-table": [
+                4,
+                0
+            ],
+            "unicast-table": [
+            ],
+            "multicast": "normal",
+            "multicast-overflow": false,
+            "unicast-overflow": false,
+            "multicast-table": [
+                "01:00:5e:00:00:01",
+                "33:33:00:00:00:01",
+                "33:33:ff:12:34:56"
+            ],
+            "broadcast-allowed": false
+        }
+      ]
+   }
+
+EQMP