On Tue, Oct 26, 2010 at 03:19:38PM -0700, Sridhar Samudrala wrote:
> With the current default macvtap mode, a KVM guest using virtio with
> macvtap backend has the following limitations.
> - cannot change/add a mac address on the guest virtio-net
> - cannot create a vlan device on the guest virtio-net
> - cannot enable promiscuous mode on guest virtio-net
>
> This patch introduces a new mode called 'passthru' when creating a
> macvlan device which allows takeover of the underlying device and
> passing it to a guest using virtio with macvtap backend.
>
> Only one macvlan device is allowed in passthru mode and it inherits
> the mac address from the underlying device and sets it in promiscuous
> mode to receive and forward all the packets.
>
> Thanks
> Sridhar
One concern with promisc mode is that for the common case,
which is a single mac and no vlans, we will be getting
extra packets that will get dropped in userspace/guest
as compared to the case where same mac is programmed
in hardware and by guest.
We could let userspace supply a list of mac/vlan addresses through
an ioctl on macvtap, and then
1. for a single mac, program it in hardware
2. for other configurations, set promisc mode
tun already has TUNSETTXFILTER which might come in handy here.
We don't pass in vlans with the filter now but maybe we should.
How does this sound?
> diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
> index 0ef0eb0..bca3cb7 100644
> --- a/drivers/net/macvlan.c
> +++ b/drivers/net/macvlan.c
> @@ -38,6 +38,7 @@ struct macvlan_port {
> struct hlist_head vlan_hash[MACVLAN_HASH_SIZE];
> struct list_head vlans;
> struct rcu_head rcu;
> + bool passthru;
> };
>
> #define macvlan_port_get_rcu(dev) \
> @@ -169,6 +170,7 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
> macvlan_broadcast(skb, port, NULL,
> MACVLAN_MODE_PRIVATE |
> MACVLAN_MODE_VEPA |
> + MACVLAN_MODE_PASSTHRU|
> MACVLAN_MODE_BRIDGE);
> else if (src->mode == MACVLAN_MODE_VEPA)
> /* flood to everyone except source */
> @@ -185,7 +187,10 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
> return skb;
> }
>
> - vlan = macvlan_hash_lookup(port, eth->h_dest);
> + if (port->passthru)
> + vlan = list_first_entry(&port->vlans, struct macvlan_dev, list);
> + else
> + vlan = macvlan_hash_lookup(port, eth->h_dest);
> if (vlan == NULL)
> return skb;
>
> @@ -284,6 +289,11 @@ static int macvlan_open(struct net_device *dev)
> struct net_device *lowerdev = vlan->lowerdev;
> int err;
>
> + if (vlan->port->passthru) {
> + dev_set_promiscuity(lowerdev, 1);
> + goto hash_add;
> + }
> +
> err = -EBUSY;
> if (macvlan_addr_busy(vlan->port, dev->dev_addr))
> goto out;
> @@ -296,6 +306,8 @@ static int macvlan_open(struct net_device *dev)
> if (err < 0)
> goto del_unicast;
> }
> +
> +hash_add:
> macvlan_hash_add(vlan);
> return 0;
>
> @@ -310,12 +322,18 @@ static int macvlan_stop(struct net_device *dev)
> struct macvlan_dev *vlan = netdev_priv(dev);
> struct net_device *lowerdev = vlan->lowerdev;
>
> + if (vlan->port->passthru) {
> + dev_set_promiscuity(lowerdev, -1);
> + goto hash_del;
> + }
> +
> dev_mc_unsync(lowerdev, dev);
> if (dev->flags & IFF_ALLMULTI)
> dev_set_allmulti(lowerdev, -1);
>
> dev_uc_del(lowerdev, dev->dev_addr);
>
> +hash_del:
> macvlan_hash_del(vlan);
> return 0;
> }
> @@ -549,6 +567,7 @@ static int macvlan_port_create(struct net_device *dev)
> if (port == NULL)
> return -ENOMEM;
>
> + port->passthru = false;
> port->dev = dev;
> INIT_LIST_HEAD(&port->vlans);
> for (i = 0; i < MACVLAN_HASH_SIZE; i++)
> @@ -593,6 +612,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])
> case MACVLAN_MODE_PRIVATE:
> case MACVLAN_MODE_VEPA:
> case MACVLAN_MODE_BRIDGE:
> + case MACVLAN_MODE_PASSTHRU:
> break;
> default:
> return -EINVAL;
> @@ -661,6 +681,10 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
> }
> port = macvlan_port_get(lowerdev);
>
> + /* Only 1 macvlan device can be created in passthru mode */
> + if (port->passthru)
> + return -EINVAL;
> +
> vlan->lowerdev = lowerdev;
> vlan->dev = dev;
> vlan->port = port;
> @@ -671,6 +695,13 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
> if (data && data[IFLA_MACVLAN_MODE])
> vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
>
> + if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
> + if (!list_empty(&port->vlans))
> + return -EINVAL;
> + port->passthru = true;
> + memcpy(dev->dev_addr, lowerdev->dev_addr, ETH_ALEN);
> + }
> +
> err = register_netdevice(dev);
> if (err < 0)
> goto destroy_port;
> diff --git a/include/linux/if_link.h b/include/linux/if_link.h
> index 2fc66dd..8454805 100644
> --- a/include/linux/if_link.h
> +++ b/include/linux/if_link.h
> @@ -232,6 +232,7 @@ enum macvlan_mode {
> MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */
> MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */
> MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */
> + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */
> };
>
> /* SR-IOV virtual function management section */
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
