From patchwork Tue Mar 8 16:36:49 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Eli Cohen X-Patchwork-Id: 594271 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 4BDA01402DE for ; Wed, 9 Mar 2016 03:37:45 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754351AbcCHQhh (ORCPT ); Tue, 8 Mar 2016 11:37:37 -0500 Received: from [193.47.165.129] ([193.47.165.129]:52279 "EHLO mellanox.co.il" rhost-flags-FAIL-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1754255AbcCHQhf (ORCPT ); Tue, 8 Mar 2016 11:37:35 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from eli@mellanox.com) with ESMTPS (AES256-SHA encrypted); 8 Mar 2016 18:37:04 +0200 Received: from sw-mtx-012.mtx.labs.mlnx (sw-mtx-012.mtx.labs.mlnx [10.12.150.39]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id u28Gb3pG031864; Tue, 8 Mar 2016 18:37:04 +0200 Received: from sw-mtx-012.mtx.labs.mlnx (localhost [127.0.0.1]) by sw-mtx-012.mtx.labs.mlnx (8.14.7/8.14.7) with ESMTP id u28Gb3c6017681; Tue, 8 Mar 2016 18:37:03 +0200 Received: (from eli@localhost) by sw-mtx-012.mtx.labs.mlnx (8.14.7/8.14.7/Submit) id u28Gb3UC017680; Tue, 8 Mar 2016 18:37:03 +0200 From: Eli Cohen To: dledford@redhat.com Cc: linux-rdma@vger.kernel.org, liranl@mellanox.com, eitan@mellanox.com, Eli Cohen , netdev@vger.kernel.org Subject: [PATCH rdma-next V2 01/10] net/core: Add support for configuring VF GUIDs Date: Tue, 8 Mar 2016 18:36:49 +0200 Message-Id: <1457455018-17638-2-git-send-email-eli@mellanox.com> X-Mailer: git-send-email 2.7.2 In-Reply-To: <1457455018-17638-1-git-send-email-eli@mellanox.com> References: <1457455018-17638-1-git-send-email-eli@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Add two new NLAs to support configuration of Infiniband node or port GUIDs. New applications can choose to use this interface to configure GUIDs with iproute2 with commands such as: ip link set dev ib0 vf 0 node_guid 00:02:c9:03:00:21:6e:70 ip link set dev ib0 vf 0 port_guid 00:02:c9:03:00:21:6e:78 A new ndo, ndo_sef_vf_guid is introduced to notify the net device of the request to change the GUID. Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz --- include/linux/netdevice.h | 3 +++ include/uapi/linux/if_link.h | 7 +++++++ net/core/rtnetlink.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 46 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5440b7b705eb..7b4ae218b90b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1147,6 +1147,9 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_set_vf_guid)(struct net_device *dev, + int vf, u64 guid, + int guid_type); int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a30b78090594..1d01e8a4e5dd 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -556,6 +556,8 @@ enum { */ IFLA_VF_STATS, /* network device statistics */ IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ __IFLA_VF_MAX, }; @@ -588,6 +590,11 @@ struct ifla_vf_spoofchk { __u32 setting; }; +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + enum { IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ IFLA_VF_LINK_STATE_ENABLE, /* link always up */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d735e854f916..4b6f3db9f8af 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1387,6 +1387,8 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) }, [IFLA_VF_STATS] = { .type = NLA_NESTED }, [IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) }, + [IFLA_VF_IB_NODE_GUID] = { .len = sizeof(struct ifla_vf_guid) }, + [IFLA_VF_IB_PORT_GUID] = { .len = sizeof(struct ifla_vf_guid) }, }; static const struct nla_policy ifla_vf_stats_policy[IFLA_VF_STATS_MAX + 1] = { @@ -1534,6 +1536,22 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return 0; } +static int handle_infiniband_guid(struct net_device *dev, struct ifla_vf_guid *ivt, + int guid_type) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + return ops->ndo_set_vf_guid(dev, ivt->vf, ivt->guid, guid_type); +} + +static int handle_vf_guid(struct net_device *dev, struct ifla_vf_guid *ivt, int guid_type) +{ + if (dev->type != ARPHRD_INFINIBAND) + return -EOPNOTSUPP; + + return handle_infiniband_guid(dev, ivt, guid_type); +} + static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1636,6 +1654,24 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) return err; } + if (tb[IFLA_VF_IB_NODE_GUID]) { + struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + + if (!ops->ndo_set_vf_guid) + return -EOPNOTSUPP; + + return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); + } + + if (tb[IFLA_VF_IB_PORT_GUID]) { + struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + + if (!ops->ndo_set_vf_guid) + return -EOPNOTSUPP; + + return handle_vf_guid(dev, ivt, IFLA_VF_IB_PORT_GUID); + } + return err; }