From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-0.8 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_HELO_NONE, SPF_PASS,URIBL_BLOCKED autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3D17AECE59D for ; Tue, 15 Oct 2019 22:30:25 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 0A5FD2064B for ; Tue, 15 Oct 2019 22:30:25 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=lists.infradead.org header.i=@lists.infradead.org header.b="hfMNLDaS" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 0A5FD2064B Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=breakpoint.cc Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-arm-kernel-bounces+infradead-linux-arm-kernel=archiver.kernel.org@lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20170209; h=Sender: Content-Transfer-Encoding:Content-Type:Cc:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:In-Reply-To:MIME-Version:References: Message-ID:Subject:To:From:Date:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=OV56QpoKERZ++jGNeatoaguviWx52f00Tw+Y4rqvioc=; b=hfMNLDaSDOX5yc SZSdnBjn9uL+N2u2EkqWOZzl3raU75QbrHmggy0v0KIu5tpoQA/AZUSXQe7Kxh635q3/DBRwiunhk BVbv2b0HGecHuNdvwTvvnZhYYKCPgqcOJjwFesiHEhVYwQaCGSd3EnWblU7xMhL2IZLqTEt89ytgl KZJFt/wzrLAA0wsyVk19jvZgjPF6cbdpNRBPh5EPmdT3wchXahyWD2z7/VcauEkaqtU4mLzXFrY0R sc8OUOfYs7JeCfA9sErODLYp5e0lXKLDgKiE+fU6mCijVH2iBHEMGVgmGhkyXfoFiUS8C7CUkS2Up O5W20A/vHnN0P09Vg0MA==; Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.92.3 #3 (Red Hat Linux)) id 1iKVKd-0005H4-SJ; Tue, 15 Oct 2019 22:30:19 +0000 Received: from chamillionaire.breakpoint.cc ([2a0a:51c0:0:12e:520::1]) by bombadil.infradead.org with esmtps (Exim 4.92.3 #3 (Red Hat Linux)) id 1iKVKa-0005G9-LJ for linux-arm-kernel@lists.infradead.org; Tue, 15 Oct 2019 22:30:18 +0000 Received: from bigeasy by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1iKVKY-0007J4-1r; Wed, 16 Oct 2019 00:30:14 +0200 Date: Wed, 16 Oct 2019 00:30:14 +0200 From: Sebastian Andrzej Siewior To: Arnd Bergmann Subject: Re: [PATCH 6/6] ARM: Inline locking functions for !PREEMPTION Message-ID: <20191015223011.nyjbtylco6isjvb6@flow> References: <20191013221310.30748-1-sebastian@breakpoint.cc> <20191013221310.30748-7-sebastian@breakpoint.cc> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20191015_153016_702334_D5305DB1 X-CRM114-Status: GOOD ( 14.51 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Peter Zijlstra , Russell King , Ingo Molnar , Waiman Long , Will Deacon , Linux ARM Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+infradead-linux-arm-kernel=archiver.kernel.org@lists.infradead.org On 2019-10-14 12:01:02 [+0200], Arnd Bergmann wrote: > On Mon, Oct 14, 2019 at 9:43 AM Arnd Bergmann wrote: > > On Mon, Oct 14, 2019 at 12:14 AM Sebastian Andrzej Siewior wrote > > > > Also, the output of 'size vmlinux' before and after the patch for > > multi_v7_defconfig would be useful to have in the changelog, as there > > are a couple of platforms that are particularly sensitive to object code > > size changes. > > To follow up, here are the numbers I get, building the linux-5.4-rc2 > multi_v7_defconfig with clang-9, comparing the original spinlock > and the qspinlock, combined with inlining all locks or leaving them > out of line: > > text data bss dec hex filename > 15294816 6958636 404480 22657932 159bb8c vmlinux-orig > 16004898 6962060 404480 23371438 1649eae vmlinux-orig-inline > 15198619 6958812 404560 22561991 15844c7 vmlinux-qlock-noinline > 15622897 6962116 404560 22989573 15ecb05 vmlinux-qlock-inline > > This gives us a 1.5% size increase over the original code with > inlining, or a 0.5% decrease without inlining, or about 1.9% size > difference for the Kconfig change itself, which does sound > significant. I had 2% increase (vmlinux-orig -> vmlinux-qlock-inline) but my vmlinux was only half the size. Performance wise the inlining improved the hackbench numbers in my test. How do we account that? > Maybe it should be configurable? Any comment from the locking department? I would prefer to avoid an extra knob for it. The v7 config is PREEMPT_NONE and HZ_100. Based on the perf numbers I posted last time: with inlining I get more or less to the performance of the ticket implementation on imx6 and it makes no difference on AM572x. Let me run the hackbench test with the multi_v7_defconfig on my two boards with ORIG/qlock/qlock-inline and come with some numbers here. > Arnd Sebastian _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel