From patchwork Thu Oct 28 23:10:50 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sridhar Samudrala X-Patchwork-Id: 69514 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 89E48B70DF for ; Fri, 29 Oct 2010 10:11:21 +1100 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758837Ab0J1XKz (ORCPT ); Thu, 28 Oct 2010 19:10:55 -0400 Received: from e8.ny.us.ibm.com ([32.97.182.138]:52747 "EHLO e8.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758427Ab0J1XKx (ORCPT ); Thu, 28 Oct 2010 19:10:53 -0400 Received: from d01relay05.pok.ibm.com (d01relay05.pok.ibm.com [9.56.227.237]) by e8.ny.us.ibm.com (8.14.4/8.13.1) with ESMTP id o9SMsRGX001570; Thu, 28 Oct 2010 18:54:27 -0400 Received: from d01av02.pok.ibm.com (d01av02.pok.ibm.com [9.56.224.216]) by d01relay05.pok.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id o9SNAqJa154160; Thu, 28 Oct 2010 19:10:52 -0400 Received: from d01av02.pok.ibm.com (loopback [127.0.0.1]) by d01av02.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id o9SNApwY002120; Thu, 28 Oct 2010 21:10:52 -0200 Received: from [9.47.24.19] (sridhar.beaverton.ibm.com [9.47.24.19]) by d01av02.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVin) with ESMTP id o9SNAome002076; Thu, 28 Oct 2010 21:10:51 -0200 Subject: [PATCH] macvlan: Introduce 'passthru' mode to takeover the underlying device From: Sridhar Samudrala To: Arnd Bergmann , Patrick McHardy , Stephen Hemminger , "Michael S. Tsirkin" Cc: netdev , "kvm@vger.kernel.org" Date: Thu, 28 Oct 2010 16:10:50 -0700 Message-Id: <1288307450.30131.82.camel@sridhar.beaverton.ibm.com> Mime-Version: 1.0 X-Mailer: Evolution 2.26.3 (2.26.3-1.fc11) Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org With the current default 'vepa' 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 To address these limitations, 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. Signed-off-by: Sridhar Samudrala ------------------------------------------------------------------------- --- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html 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 */