Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933955AbcJQJzV (ORCPT ); Mon, 17 Oct 2016 05:55:21 -0400 Received: from mga04.intel.com ([192.55.52.120]:46808 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933830AbcJQJzM (ORCPT ); Mon, 17 Oct 2016 05:55:12 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.31,357,1473145200"; d="scan'208";a="20408864" From: "Luc, Piotr" To: "hpa@zytor.com" , "bp@alien8.de" CC: "mingo@kernel.org" , "peterz@infradead.org" , "linux-kernel@vger.kernel.org" , "torvalds@linux-foundation.org" , "tglx@linutronix.de" , "linux-tip-commits@vger.kernel.org" , "jpoimboe@redhat.com" , "brgerst@gmail.com" , "luto@kernel.org" , "Hansen, Dave" , "dvlasenk@redhat.com" Subject: Re: [tip:x86/urgent] x86/cpufeature: Add AVX512_4VNNIW and AVX512_4FMAPS features Thread-Topic: [tip:x86/urgent] x86/cpufeature: Add AVX512_4VNNIW and AVX512_4FMAPS features Thread-Index: AQHSJ5+kfr6iWnnrREOfxvkynktjEKCrEXWAgAAcBoCAAAk/gIAAI1cAgABDNACAALqlgA== Date: Mon, 17 Oct 2016 09:55:07 +0000 Message-ID: <1476697859.27884.21.camel@intel.com> References: <20161012175731.29619-1-piotr.luc@intel.com> <20161016142233.xuqrahty6gcwq7en@pd.tnic> <20161016163557.weyfwd4obnk3rh5v@pd.tnic> <20161016224258.e2jen3qkoo3m6qd7@pd.tnic> In-Reply-To: <20161016224258.e2jen3qkoo3m6qd7@pd.tnic> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.237.138.164] Content-Type: text/plain; charset="utf-8" Content-ID: MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from base64 to 8bit by mail.home.local id u9H9v16M001312 Content-Length: 1002 Lines: 32 On Mon, 2016-10-17 at 00:42 +0200, Borislav Petkov wrote: > On Sun, Oct 16, 2016 at 11:42:26AM -0700, hpa@zytor.com wrote: > > > > It's needlessly adding complexity for no reason, at least for the > > What complexity? The init_scattered_cpuid_features() version is a > trivial patch in comparison to the current version. > > > > > leaves that are going to add bits over time. > > Sure, except they don't get added or we don't need them or whatever, > and > we end up with only a small number of bits actually being used. > > I don't mind moving them to x86_capability later, when a high > percentage > of the respective leaf is actually being used but not for a couple of > bits. That's just waste. > > > > > The x86_capability array is not an expensive resource. > > 0.1% here, 0.1% there, the creeping bloat thing. > > And again, the init_scattered_cpuid_features() hunk is much smaller. > I agree, the scattered solution reduces data segment footprint in case many cores. Regards, Piotr