二 DATAPATH--网桥的创建

一 datapath内核态进程加载后，调用ovs_internal_dev_rtnl_link_register初始化网桥操作

int ovs_internal_dev_rtnl_link_register(void)
{
    int err;

    err = rtnl_link_register(&internal_dev_link_ops);
    if (err < 0)
        return err;

    err = ovs_vport_ops_register(&ovs_internal_vport_ops); // ovs_internal_vport_ops就是对网桥的操作
    if (err < 0)
        rtnl_link_unregister(&internal_dev_link_ops);

    return err;
}

 

static struct vport_ops ovs_internal_vport_ops = {
    .type       = OVS_VPORT_TYPE_INTERNAL,
    .create     = internal_dev_create,
    .destroy    = internal_dev_destroy,
    .send       = internal_dev_recv,
};

 

static struct vport *internal_dev_create(const struct vport_parms *parms)
{
    struct vport *vport;
    struct internal_dev *internal_dev;
    int err;

    vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
    if (IS_ERR(vport)) {
        err = PTR_ERR(vport);
        goto error;
    }

    printk("vport-internel_dev:parms->name[%s]\n", parms->name);

    vport->dev = alloc_netdev(sizeof(struct internal_dev),
                  parms->name, NET_NAME_USER, do_setup); 
// 网桥是个网络设备，对于linux kernel来说，是一个net_device，对net_device的初始化，通过钩子，这里的钩子就是do_setup。在do_setup中初始了网桥的操作.
    if (!vport->dev) {
        err = -ENOMEM;
        goto error_free_vport;
    }
    vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
    if (!vport->dev->tstats) {
        err = -ENOMEM;
        goto error_free_netdev;
    }

#ifdef HAVE_IFF_PHONY_HEADROOM
    vport->dev->needed_headroom = vport->dp->max_headroom;
#endif
    dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));

    // 调用netdev_priv取出私有数据块的地址，也就是207行分配的vport的地址，赋给internal_dev
    // 然后将私有数据块地址指向vport地址

    internal_dev = internal_dev_priv(vport->dev);
    internal_dev->vport = vport;

    /* Restrict bridge port to current netns. */
    if (vport->port_no == OVSP_LOCAL)
        vport->dev->features |= NETIF_F_NETNS_LOCAL;

    rtnl_lock();

    printk("vport-internal_dev.c:internal_dev_create->register device\n");

    err = register_netdevice(vport->dev);
    if (err)
        goto error_unlock;

    dev_set_promiscuity(vport->dev, 1);
    rtnl_unlock();
    netif_start_queue(vport->dev);

    return vport;

error_unlock:
    rtnl_unlock();
    free_percpu(vport->dev->tstats);
error_free_netdev:
    free_netdev(vport->dev);
error_free_vport:
    ovs_vport_free(vport);
error:
    return ERR_PTR(err);
}

 

static void do_setup(struct net_device *netdev)
{
    ether_setup(netdev);

    netdev->netdev_ops = &internal_dev_netdev_ops; // 网桥的操作

    netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
    netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
                  IFF_PHONY_HEADROOM | IFF_NO_QUEUE;
    netdev->destructor = internal_dev_destructor;
    netdev->ethtool_ops = &internal_dev_ethtool_ops;
    netdev->rtnl_link_ops = &internal_dev_link_ops;

#ifndef HAVE_IFF_NO_QUEUE
    netdev->tx_queue_len = 0;
#endif

    netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
               NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
               NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL;

    netdev->vlan_features = netdev->features;
    netdev->hw_enc_features = netdev->features;
    netdev->features |= NETIF_F_HW_VLAN_CTAG_TX;
    netdev->hw_features = netdev->features & ~NETIF_F_LLTX;

    eth_hw_addr_random(netdev);
}

 

static const struct net_device_ops internal_dev_netdev_ops = {
    .ndo_open = internal_dev_open,
    .ndo_stop = internal_dev_stop,
    .ndo_start_xmit = internal_dev_xmit, // 接收数据
    .ndo_set_mac_address = eth_mac_addr,
    .ndo_change_mtu = internal_dev_change_mtu,
    .ndo_get_stats64 = internal_get_stats,
#ifdef HAVE_IFF_PHONY_HEADROOM
    .ndo_set_rx_headroom = internal_set_rx_headroom,
#endif
};

 

static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
{
    int len, err;

    len = skb->len;
    rcu_read_lock();
    err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
    rcu_read_unlock();

    if (likely(!err)) {
        struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats);

        u64_stats_update_begin(&tstats->syncp);
        tstats->tx_bytes += len;
        tstats->tx_packets++;
        u64_stats_update_end(&tstats->syncp);
    } else {
        netdev->stats.tx_errors++;
    }
    return 0;
}

 

int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
              const struct ip_tunnel_info *tun_info)
{
    struct sw_flow_key key;
    int error;

    OVS_CB(skb)->input_vport = vport;
    OVS_CB(skb)->mru = 0;
    OVS_CB(skb)->cutlen = 0;
    if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
        u32 mark;

        mark = skb->mark;
        skb_scrub_packet(skb, true);
        skb->mark = mark;
        tun_info = NULL;
    }
    
    ovs_skb_init_inner_protocol(skb);
    skb_clear_ovs_gso_cb(skb);
    /* Extract flow from 'skb' into 'key'. */
    error = ovs_flow_key_extract(tun_info, skb, &key); // skb-->流表
    if (unlikely(error)) {
        kfree_skb(skb);
        return error;
    }
    ovs_dp_process_packet(skb, &key); // 流表匹配
    return 0;
}

 

void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
{
    const struct vport *p = OVS_CB(skb)->input_vport;
    struct datapath *dp = p->dp;
    struct sw_flow *flow;
    struct sw_flow_actions *sf_acts;
    struct dp_stats_percpu *stats;
    u64 *stats_counter;
    u32 n_mask_hit;

    stats = this_cpu_ptr(dp->stats_percpu);

    /* Look up flow. */
    flow = ovs_flow_tbl_lookup_stats(&dp->table, key, skb_get_hash(skb),
                     &n_mask_hit); // 流表匹配
    if (unlikely(!flow)) { // 匹配不成功
        struct dp_upcall_info upcall;
        int error;

        memset(&upcall, 0, sizeof(upcall));
        upcall.cmd = OVS_PACKET_CMD_MISS;
        upcall.portid = ovs_vport_find_upcall_portid(p, skb);
        upcall.mru = OVS_CB(skb)->mru;
        error = ovs_dp_upcall(dp, skb, key, &upcall, 0); // 上行给用户态处理，走慢速通道
        if (unlikely(error))
            kfree_skb(skb);
        else 
            consume_skb(skb);
        stats_counter = &stats->n_missed;
        goto out; 
    }    

    ovs_flow_stats_update(flow, key->tp.flags, skb); 
    sf_acts = rcu_dereference(flow->sf_acts);
    ovs_execute_actions(dp, skb, sf_acts, key); // 匹配成功，执行datapath Action

    stats_counter = &stats->n_hit;

out:
    /* Update datapath statistics. */
    u64_stats_update_begin(&stats->syncp);
    (*stats_counter)++;
    stats->n_mask_hit += n_mask_hit;
    u64_stats_update_end(&stats->syncp);
}

 对于上行的用户态和执行datapath Action，留在后面章节！！！