[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3426.1248464836@death.nxdomain.ibm.com>
Date: Fri, 24 Jul 2009 12:47:16 -0700
From: Jay Vosburgh <fubar@...ibm.com>
To: Patrick McHardy <kaber@...sh.net>
cc: Or Gerlitz <ogerlitz@...taire.com>, eilong@...adcom.com,
David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
Eric Dumazet <eric.dumazet@...il.com>
Subject: Re: [net-next 6/10] bnx2x: Update vlan_features
Patrick McHardy <kaber@...sh.net> wrote:
>In case of bonding, its necessary to update vlan_features so it
>contains the intersection of all underlying devices. But a
>change will only take effect for existing VLANs (f.i. when
>enslaving a new device) if you call netdev_features_change().
Patrick, can you clarify one bit about your above statment? You
say the bonding features should be an "intersection"; is that a strict
intersection (i.e., slave1->vlan_features | slave2->vlan_features), or
does the NETIF_F_ONE_FOR_ALL logic apply for vlan_features as it does
for regular dev->features (using netdev_incrmenet_features() to combine
the feature sets)?
In other words, if a bond has two slaves, one with, e.g.,
NETIF_F_SG in its vlan_features, and the other slave has 0 in
vlan_features, should the bond's vlan_features be NETIF_F_SG, or 0?
-J
---
-Jay Vosburgh, IBM Linux Technology Center, fubar@...ibm.com
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists