From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754172AbYDWW3G (ORCPT ); Wed, 23 Apr 2008 18:29:06 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751937AbYDWW2y (ORCPT ); Wed, 23 Apr 2008 18:28:54 -0400 Received: from Chamillionaire.breakpoint.cc ([85.10.199.196]:41600 "EHLO Chamillionaire.breakpoint.cc" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751926AbYDWW2x (ORCPT ); Wed, 23 Apr 2008 18:28:53 -0400 Date: Thu, 24 Apr 2008 00:28:43 +0200 From: Sebastian Siewior To: Herbert Xu Cc: "Huang, Ying" , "Adam J. Richter" , akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-crypto@vger.kernel.org, mingo@elte.hu, tglx@linutronix.de Subject: Re: [PATCH -mm crypto] AES: x86_64 asm implementation optimization Message-ID: <20080423222843.GA16683@Chamillionaire.breakpoint.cc> References: <1207723262.18313.37.camel@caritas-dev.intel.com> <20080416073108.GA13494@Chamillionaire.breakpoint.cc> <1208333949.4322.5.camel@caritas-dev.intel.com> <20080416184016.GA21365@Chamillionaire.breakpoint.cc> <1208397123.4322.21.camel@caritas-dev.intel.com> <20080417033402.GB3394@gondor.apana.org.au> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <20080417033402.GB3394@gondor.apana.org.au> X-Key-Id: FE3F4706 X-Key-Fingerprint: FFDA BBBB 3563 1B27 75C9 925B 98D5 5C1C FE3F 4706 User-Agent: Mutt/1.5.16 (2007-06-09) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Herbert Xu | 2008-04-17 11:34:02 [+0800]: >On Thu, Apr 17, 2008 at 09:52:03AM +0800, Huang, Ying wrote: >> >> As far as I know, the CRYPTO_MINALIGN is defined in >> include/linux/crypto.h as __alignof__(unsigned long long), and the >> __crt_ctx in crypto_tfm is aligned in CRYPTO_MINALIGN. So I think adding >> a pad is sufficient for x86_64 implementation. > >It should be sufficient but it would be better to use an align Doesn't this imply that kmalloc() returns memory that is always pointer aligned what isn't the case AFAIK? >Thanks, Sebastian