From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH v12 06/17] Use callback to deal with skb_release_data() specially. Date: Mon, 11 Oct 2010 17:42:11 +0200 Message-ID: <1286811731.2737.28.camel@edumazet-laptop> References: <20101001.001439.85411154.davem@davemloft.net> <20101011.082728.193709462.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: xiaohui.xin@intel.com, netdev@vger.kernel.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, mst@redhat.com, mingo@elte.hu, herbert@gondor.apana.org.au, jdike@linux.intel.com To: David Miller Return-path: In-Reply-To: <20101011.082728.193709462.davem@davemloft.net> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Le lundi 11 octobre 2010 =C3=A0 08:27 -0700, David Miller a =C3=A9crit = : > From: "Xin, Xiaohui" > Date: Mon, 11 Oct 2010 15:06:05 +0800 >=20 > > That's to avoid the new cache miss caused by using destructor_arg i= n data path > > like skb_release_data(). > > That's based on the comment from Eric Dumazet on v7 patches. >=20 > Thanks for the explanation. Anyway, frags[] must be the last field of "struct skb_shared_info" since commit fed66381 (net: pskb_expand_head() optimization) It seems Xin worked on a quite old tree.