From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [PATCH net-next] skbuff: clear tx zero-copy flag Date: Mon, 25 Jul 2011 11:07:43 +0300 Message-ID: <20110725080743.GC7840@redhat.com> References: <1310195566.25391.6.camel@localhost.localdomain> <20110725004200.GA25794@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Shirley Ma , davem@davemloft.net, netdev@vger.kernel.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org To: Herbert Xu Return-path: Content-Disposition: inline In-Reply-To: <20110725004200.GA25794@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Mon, Jul 25, 2011 at 08:42:00AM +0800, Herbert Xu wrote: > Shirley Ma wrote: > > > > This patch clears tx zero-copy flag as needed. > > > > Sign-off-by: Shirley Ma > > I think we also need to copy and clear this flag on the splice > read path as that takes a direct page reference. > > I hope there isn't any other path that does this. > > Cheers, When there's a way for an skb to get into the host networking stack, (e.g. when tap gains zero copy support) we'll need to handle that. However macvtap passes an skb directly to the lower device, so as long as macvtap is the only user of that interface, we are fine I think - there's no way for an skb to get from macvtap to splice read path I think. Right? > -- > Email: Herbert Xu > Home Page: http://gondor.apana.org.au/~herbert/ > PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt