From patchwork Sun Apr 26 08:39:08 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Gavin Hu X-Patchwork-Id: 69336 X-Patchwork-Delegate: david.marchand@redhat.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id CF08EA00C5; Sun, 26 Apr 2020 10:39:29 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id B1B0A1C06A; Sun, 26 Apr 2020 10:39:25 +0200 (CEST) Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by dpdk.org (Postfix) with ESMTP id B22371C037 for ; Sun, 26 Apr 2020 10:39:23 +0200 (CEST) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 1EC4131B; Sun, 26 Apr 2020 01:39:23 -0700 (PDT) Received: from net-arm-thunderx2-01.shanghai.arm.com (net-arm-thunderx2-01.shanghai.arm.com [10.169.41.214]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id A54AE3F6CF; Sun, 26 Apr 2020 01:39:20 -0700 (PDT) From: Gavin Hu To: dev@dpdk.org Cc: nd@arm.com, david.marchand@redhat.com, thomas@monjalon.net, jerinj@marvell.com, Honnappa.Nagarahalli@arm.com, Ruifeng.Wang@arm.com, Phil.Yang@arm.com, Joyce.Kong@arm.com Date: Sun, 26 Apr 2020 16:39:08 +0800 Message-Id: <20200426083909.897-2-gavin.hu@arm.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200426083909.897-1-gavin.hu@arm.com> References: <20200426083909.897-1-gavin.hu@arm.com> In-Reply-To: <20200424070741.16619-1-gavin.hu@arm.com> References: <20200424070741.16619-1-gavin.hu@arm.com> Subject: [dpdk-dev] [PATCH v2 1/2] spinlock: use wfe to reduce contention on aarch64 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" In acquiring a spinlock, cores repeatedly poll the lock variable. This is replaced by rte_wait_until_equal API. Running the micro benchmarking and the testpmd and l3fwd traffic tests on ThunderX2, Ampere eMAG80 and Arm N1SDP, everything went well and no notable performance gain nor degradation was measured. Signed-off-by: Gavin Hu Reviewed-by: Ruifeng Wang Reviewed-by: Phil Yang Reviewed-by: Steve Capper Reviewed-by: Ola Liljedahl Reviewed-by: Honnappa Nagarahalli Tested-by: Pavan Nikhilesh Acked-by: Jerin Jacob --- lib/librte_eal/include/generic/rte_spinlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/librte_eal/include/generic/rte_spinlock.h b/lib/librte_eal/include/generic/rte_spinlock.h index 87ae7a4f1..40fe49d5a 100644 --- a/lib/librte_eal/include/generic/rte_spinlock.h +++ b/lib/librte_eal/include/generic/rte_spinlock.h @@ -65,8 +65,8 @@ rte_spinlock_lock(rte_spinlock_t *sl) while (!__atomic_compare_exchange_n(&sl->locked, &exp, 1, 0, __ATOMIC_ACQUIRE, __ATOMIC_RELAXED)) { - while (__atomic_load_n(&sl->locked, __ATOMIC_RELAXED)) - rte_pause(); + rte_wait_until_equal_32((volatile uint32_t *)&sl->locked, + 0, __ATOMIC_RELAXED); exp = 0; } }