From patchwork Tue Apr 26 15:47:56 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tomasz Kulasek X-Patchwork-Id: 12258 X-Patchwork-Delegate: thomas@monjalon.net Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id 709A43208; Tue, 26 Apr 2016 17:48:14 +0200 (CEST) Received: from mga04.intel.com (mga04.intel.com [192.55.52.120]) by dpdk.org (Postfix) with ESMTP id 9036C2B96 for ; Tue, 26 Apr 2016 17:48:12 +0200 (CEST) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga104.fm.intel.com with ESMTP; 26 Apr 2016 08:48:11 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.24,537,1455004800"; d="scan'208";a="966904067" Received: from unknown (HELO Sent) ([10.217.248.44]) by fmsmga002.fm.intel.com with SMTP; 26 Apr 2016 08:48:07 -0700 Received: by Sent (sSMTP sendmail emulation); Tue, 26 Apr 2016 17:48:06 +0200 From: Tomasz Kulasek To: ian.betts@intel.com Cc: dev@dpdk.org Date: Tue, 26 Apr 2016 17:47:56 +0200 Message-Id: <1461685676-7084-1-git-send-email-tomaszx.kulasek@intel.com> X-Mailer: git-send-email 2.1.4 Subject: [dpdk-dev] [PATCH] examples/performance-thread: fix segfault with in gcc 5.x X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" It seems that with gcc >5.x and -O2/-O3 optimization breaks packet grouping algorithm in l3fwd-thread application causing segfault. When last packet pointer "lp" and "pnum->u64" buffer points the same memory buffer, high optimization can cause unpredictable results. It seems that assignment of precalculated group sizes may interfere with initialization of new group size when lp points value inside current group and didn't should be changed. With gcc >5.x and optimization we cannot be sure which assignment will be done first, so the group size can be counted incorrectly causing segfault. This patch eliminates intersection of assignment of initial group size (lp[0] = 1) and precalculated group sizes when gptbl[v].idx < 4. Fixes: d48415e1fee3 ("examples/performance-thread: add l3fwd-thread app") Signed-off-by: Tomasz Kulasek --- examples/performance-thread/l3fwd-thread/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/performance-thread/l3fwd-thread/main.c b/examples/performance-thread/l3fwd-thread/main.c index 15c0a4d..3417fd5 100644 --- a/examples/performance-thread/l3fwd-thread/main.c +++ b/examples/performance-thread/l3fwd-thread/main.c @@ -1658,9 +1658,9 @@ port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, __m128i dp1, __m128i dp2) /* if dest port value has changed. */ if (v != GRPMSK) { - lp = pnum->u16 + gptbl[v].idx; - lp[0] = 1; pnum->u64 = gptbl[v].pnum; + pnum->u16[FWDSTEP] = 1; + lp = pnum->u16 + gptbl[v].idx; } return lp;