Merge remote-tracking branch 'mst/tags/for_anthony' into staging

pci,net,pc enhancements

This includes some fixes and enhancements that accumulated in my tree:
pci fixes by dkoch, virtio-net enhancements by akong and mst,
and a fix for xen pc by mst.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Wed 17 Jul 2013 04:44:45 AM CDT using RSA key ID D28D5469
# gpg: Can't check signature: public key not found

# By Don Koch (2) and others
# Via Michael S. Tsirkin
* mst/tags/for_anthony:
  pc: don't access fw cfg if NULL
  virtio-net: add feature bit for any header s/g
  net: add support of mac-programming over macvtap in QEMU side
  pci: fix BRDIGE typo
  pci-bridge: update mappings for migration/restore

Message-id: 1374054430-21966-1-git-send-email-mst@redhat.com
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

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
 -----
 

hw/i386/pc.c

@@ -1005,7 +1005,7 @@ typedef struct PcRomPciInfo {
 static void pc_fw_cfg_guest_info(PcGuestInfo *guest_info)
 {
     PcRomPciInfo *info;
-    if (!guest_info->has_pci_info) {
+    if (!guest_info->has_pci_info || !guest_info->fw_cfg) {
         return;
     }
 

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);

hw/pci-bridge/i82801b11.c

@@ -69,7 +69,7 @@ static int i82801b11_bridge_initfn(PCIDevice *d)
     if (rc < 0) {
         goto err_bridge;
     }
-    pci_config_set_prog_interface(d->config, PCI_CLASS_BRDIGE_PCI_INF_SUB);
+    pci_config_set_prog_interface(d->config, PCI_CLASS_BRIDGE_PCI_INF_SUB);
     return 0;
 
 err_bridge:

hw/pci/pci.c

@@ -378,6 +378,7 @@ int pci_bus_num(PCIBus *s)
 static int get_pci_config_device(QEMUFile *f, void *pv, size_t size)
 {
     PCIDevice *s = container_of(pv, PCIDevice, config);
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(s);
     uint8_t *config;
     int i;
 
@@ -395,6 +396,10 @@ static int get_pci_config_device(QEMUFile *f, void *pv, size_t size)
     memcpy(s->config, config, size);
 
     pci_update_mappings(s);
+    if (pc->is_bridge) {
+        PCIBridge *b = container_of(s, PCIBridge, dev);
+        pci_bridge_update_mappings(b);
+    }
 
     memory_region_set_enabled(&s->bus_master_enable_region,
                               pci_get_word(s->config + PCI_COMMAND)

hw/pci/pci_bridge.c

@@ -224,7 +224,7 @@ static void pci_bridge_region_cleanup(PCIBridge *br, PCIBridgeWindows *w)
     g_free(w);
 }
 
-static void pci_bridge_update_mappings(PCIBridge *br)
+void pci_bridge_update_mappings(PCIBridge *br)
 {
     PCIBridgeWindows *w = br->windows;
 

include/hw/i386/pc.h

@@ -231,6 +231,10 @@ int e820_add_entry(uint64_t, uint64_t, uint32_t);
             .driver   = "Nehalem-" TYPE_X86_CPU,\
             .property = "level",\
             .value    = stringify(2),\
+        },{\
+            .driver   = "virtio-net-pci",\
+            .property = "any_layout",\
+            .value    = "off",\
         }
 
 #define PC_COMPAT_1_4 \

include/hw/pci/pci_bridge.h

@@ -37,6 +37,7 @@ PCIBus *pci_bridge_get_sec_bus(PCIBridge *br);
 pcibus_t pci_bridge_get_base(const PCIDevice *bridge, uint8_t type);
 pcibus_t pci_bridge_get_limit(const PCIDevice *bridge, uint8_t type);
 
+void pci_bridge_update_mappings(PCIBridge *br);
 void pci_bridge_write_config(PCIDevice *d,
                              uint32_t address, uint32_t val, int len);
 void pci_bridge_disable_base_limit(PCIDevice *dev);

include/hw/pci/pci_ids.h

@@ -39,7 +39,7 @@
 #define PCI_CLASS_BRIDGE_HOST            0x0600
 #define PCI_CLASS_BRIDGE_ISA             0x0601
 #define PCI_CLASS_BRIDGE_PCI             0x0604
-#define PCI_CLASS_BRDIGE_PCI_INF_SUB     0x01
+#define PCI_CLASS_BRIDGE_PCI_INF_SUB     0x01
 #define PCI_CLASS_BRIDGE_OTHER           0x0680
 
 #define PCI_CLASS_COMMUNICATION_SERIAL   0x0700

include/hw/virtio/virtio-net.h

@@ -243,6 +243,7 @@ struct virtio_net_ctrl_mq {
 
 #define DEFINE_VIRTIO_NET_FEATURES(_state, _field) \
         DEFINE_VIRTIO_COMMON_FEATURES(_state, _field), \
+        DEFINE_PROP_BIT("any_layout", _state, _field, VIRTIO_F_ANY_LAYOUT, true), \
         DEFINE_PROP_BIT("csum", _state, _field, VIRTIO_NET_F_CSUM, true), \
         DEFINE_PROP_BIT("guest_csum", _state, _field, VIRTIO_NET_F_GUEST_CSUM, true), \
         DEFINE_PROP_BIT("gso", _state, _field, VIRTIO_NET_F_GSO, true), \

include/hw/virtio/virtio.h

@@ -43,6 +43,8 @@
 /* We notify when the ring is completely used, even if the guest is suppressing
  * callbacks */
 #define VIRTIO_F_NOTIFY_ON_EMPTY        24
+/* Can the device handle any descriptor layout? */
+#define VIRTIO_F_ANY_LAYOUT             27
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC     28
 /* The Guest publishes the used index for which it expects an interrupt

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,

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 {

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",

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;

qapi-schema.json

@@ -3679,3 +3679,79 @@
             '*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'] }

qmp-commands.hx

@@ -3046,4 +3046,67 @@ Example:
 -> { "execute": "chardev-remove", "arguments": { "id" : "foo" } }
 <- { "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