From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roland Dreier Subject: Re: [PATCH 14/23 v3] mlx4_core: Determine primary physical function Date: Thu, 04 Feb 2010 14:30:41 -0800 Message-ID: References: <49BFC313.1030901@mellanox.co.il> <4B6AEE1F.5050506@mellanox.co.il> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: general@lists.openfabrics.org, netdev@vger.kernel.org, liranl@mellanox.co.il, tziporet@mellanox.co.il To: Yevgeny Petrilin Return-path: Received: from sj-iport-1.cisco.com ([171.71.176.70]:43904 "EHLO sj-iport-1.cisco.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758373Ab0BDWau (ORCPT ); Thu, 4 Feb 2010 17:30:50 -0500 In-Reply-To: <4B6AEE1F.5050506@mellanox.co.il> (Yevgeny Petrilin's message of "Thu, 04 Feb 2010 17:56:15 +0200") Sender: netdev-owner@vger.kernel.org List-ID: > + MLX4_FLAG_PF = 1 << 5, Am I mistaken, or is this the only place this flag appears anywhere in the patch set? In other words it is never set and never tested -- so probably we don't need it? > + dev_cap->pf_num = field; > + if (dev_cap->pf_num > 1) > + dev->flags |= MLX4_FLAG_MASTER; Is this correct? All PFs > 1 are masters? Or should the test be "== 1" rather than "> 1" instead? -- Roland Dreier Cisco.com - http://www.cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/index.html