From mboxrd@z Thu Jan 1 00:00:00 1970 From: Saeed Mahameed Subject: Re: [net 7/8] net/mlx5e: Fix update of hash function/key via ethtool Date: Sat, 28 Jan 2017 13:06:31 +0200 Message-ID: References: <20170127203843.3206-1-saeedm@mellanox.com> <20170127203843.3206-8-saeedm@mellanox.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Cc: Saeed Mahameed , "David S. Miller" , Linux Kernel Network Developers , Gal Pressman To: Tom Herbert Return-path: Received: from mail-qk0-f170.google.com ([209.85.220.170]:33101 "EHLO mail-qk0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750828AbdA1LGw (ORCPT ); Sat, 28 Jan 2017 06:06:52 -0500 Received: by mail-qk0-f170.google.com with SMTP id s140so87560864qke.0 for ; Sat, 28 Jan 2017 03:06:52 -0800 (PST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Fri, Jan 27, 2017 at 11:50 PM, Tom Herbert wrote: > On Fri, Jan 27, 2017 at 12:38 PM, Saeed Mahameed wrote: >> From: Gal Pressman >> >> Modifying TIR hash should change selected fields bitmask in addition to >> the function and key. >> Formerly, we would not set this field resulting in zeroing of its value, >> which means no packet fields are used for RX RSS hash calculation thus >> causing all traffic to arrive in RQ[0]. >> > This commit log is rather scant in details. Does this mean that RSS is > somehow broken in mlx5? What is exact test that demonstrates bad > behavior? Did you verify that this doesn't break IPv4 or IPv6? > before this fix out of the box RSS worked fine for both IPv4/IPv6, the only broken flow is when the user explicitly uses ethtoo -X to update the RSS indirection table or hash function. We did verify both IPv6 and IPv4 RSS worked fine after the user changes RSS configuration via ethtool -X