From patchwork Wed Apr 4 22:16:27 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jiri Pirko X-Patchwork-Id: 150816 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 17C14B6FF7 for ; Thu, 5 Apr 2012 08:17:38 +1000 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757266Ab2DDWRg (ORCPT ); Wed, 4 Apr 2012 18:17:36 -0400 Received: from mx1.redhat.com ([209.132.183.28]:12188 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753556Ab2DDWRf (ORCPT ); Wed, 4 Apr 2012 18:17:35 -0400 Received: from int-mx02.intmail.prod.int.phx2.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id q34MHTUN024496 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Wed, 4 Apr 2012 18:17:30 -0400 Received: from localhost (ovpn-116-50.ams2.redhat.com [10.36.116.50]) by int-mx02.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id q34MGVH9005896; Wed, 4 Apr 2012 18:16:31 -0400 From: Jiri Pirko To: netdev@vger.kernel.org Cc: davem@davemloft.net, eric.dumazet@gmail.com, bhutchings@solarflare.com, shemminger@vyatta.com, raise.sail@gmail.com, nuno.martins@caixamagica.pt, matt@ozlabs.org Subject: [patch net-next 2/2] team: add loadbalance mode Date: Thu, 5 Apr 2012 00:16:27 +0200 Message-Id: <1333577787-878-2-git-send-email-jpirko@redhat.com> In-Reply-To: <1333577787-878-1-git-send-email-jpirko@redhat.com> References: <1333577787-878-1-git-send-email-jpirko@redhat.com> X-Scanned-By: MIMEDefang 2.67 on 10.5.11.12 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org This patch introduces new team mode. It's TX port is selected by user-set BPF hash function. Signed-off-by: Jiri Pirko --- drivers/net/team/Kconfig | 11 ++ drivers/net/team/Makefile | 1 + drivers/net/team/team_mode_loadbalance.c | 188 ++++++++++++++++++++++++++++++ 3 files changed, 200 insertions(+), 0 deletions(-) create mode 100644 drivers/net/team/team_mode_loadbalance.c diff --git a/drivers/net/team/Kconfig b/drivers/net/team/Kconfig index 248a144..89024d5 100644 --- a/drivers/net/team/Kconfig +++ b/drivers/net/team/Kconfig @@ -40,4 +40,15 @@ config NET_TEAM_MODE_ACTIVEBACKUP To compile this team mode as a module, choose M here: the module will be called team_mode_activebackup. +config NET_TEAM_MODE_LOADBALANCE + tristate "Load-balance mode support" + depends on NET_TEAM + ---help--- + This mode provides load balancing functionality. Tx port selection + is done using BPF function set up from userspace (bpf_hash_func + option) + + To compile this team mode as a module, choose M here: the module + will be called team_mode_loadbalance. + endif # NET_TEAM diff --git a/drivers/net/team/Makefile b/drivers/net/team/Makefile index 85f2028..fb9f4c1 100644 --- a/drivers/net/team/Makefile +++ b/drivers/net/team/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_NET_TEAM) += team.o obj-$(CONFIG_NET_TEAM_MODE_ROUNDROBIN) += team_mode_roundrobin.o obj-$(CONFIG_NET_TEAM_MODE_ACTIVEBACKUP) += team_mode_activebackup.o +obj-$(CONFIG_NET_TEAM_MODE_LOADBALANCE) += team_mode_loadbalance.o diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c new file mode 100644 index 0000000..ed20f39 --- /dev/null +++ b/drivers/net/team/team_mode_loadbalance.c @@ -0,0 +1,188 @@ +/* + * drivers/net/team/team_mode_loadbalance.c - Load-balancing mode for team + * Copyright (c) 2012 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +struct lb_priv { + struct sk_filter __rcu *fp; + struct sock_fprog *orig_fprog; +}; + +static struct lb_priv *lb_priv(struct team *team) +{ + return (struct lb_priv *) &team->mode_priv; +} + +static bool lb_transmit(struct team *team, struct sk_buff *skb) +{ + struct sk_filter *fp; + struct team_port *port; + unsigned int hash; + int port_index; + + fp = rcu_dereference(lb_priv(team)->fp); + if (unlikely(!fp)) + goto drop; + hash = SK_RUN_FILTER(fp, skb); + port_index = hash % team->port_count; + port = team_get_port_by_index_rcu(team, port_index); + if (unlikely(!port)) + goto drop; + skb->dev = port->dev; + if (dev_queue_xmit(skb)) + return false; + return true; + +drop: + dev_kfree_skb_any(skb); + return false; +} + +static int lb_bpf_func_get(struct team *team, void *arg) +{ + struct team_option_binary *tbinary = team_optarg_tbinary(arg); + + memset(tbinary, 0, sizeof(*tbinary)); + if (!lb_priv(team)->orig_fprog) + return 0; + + tbinary->data_len = lb_priv(team)->orig_fprog->len * + sizeof(struct sock_filter); + tbinary->data = lb_priv(team)->orig_fprog->filter; + return 0; +} + +static int __fprog_create(struct sock_fprog **pfprog, u32 data_len, + void *data) +{ + struct sock_fprog *fprog; + struct sock_filter *filter = (struct sock_filter *) data; + + if (data_len % sizeof(struct sock_filter)) + return -EINVAL; + fprog = kmalloc(sizeof(struct sock_fprog), GFP_KERNEL); + if (!fprog) + return -ENOMEM; + fprog->filter = kmemdup(filter, data_len, GFP_KERNEL); + if (!fprog->filter) { + kfree(fprog); + return -ENOMEM; + } + fprog->len = data_len / sizeof(struct sock_filter); + *pfprog = fprog; + return 0; +} + +static void __fprog_destroy(struct sock_fprog *fprog) +{ + kfree(fprog->filter); + kfree(fprog); +} + +static int lb_bpf_func_set(struct team *team, void *arg) +{ + struct team_option_binary *tbinary = team_optarg_tbinary(arg); + struct sk_filter *fp = NULL; + struct sock_fprog *fprog = NULL; + int err; + + if (tbinary->data_len) { + err = __fprog_create(&fprog, tbinary->data_len, + tbinary->data); + if (err) + return err; + err = sk_unattached_filter_create(&fp, fprog); + if (err) { + __fprog_destroy(fprog); + return err; + } + } + + if (lb_priv(team)->orig_fprog) { + /* Clear old filter data */ + __fprog_destroy(lb_priv(team)->orig_fprog); + sk_unattached_filter_destroy(lb_priv(team)->fp); + } + + rcu_assign_pointer(lb_priv(team)->fp, fp); + lb_priv(team)->orig_fprog = fprog; + return 0; +} + +static const struct team_option lb_options[] = { + { + .name = "bpf_hash_func", + .type = TEAM_OPTION_TYPE_BINARY, + .getter = lb_bpf_func_get, + .setter = lb_bpf_func_set, + }, +}; + +int lb_init(struct team *team) +{ + return team_options_register(team, lb_options, + ARRAY_SIZE(lb_options)); +} + +void lb_exit(struct team *team) +{ + team_options_unregister(team, lb_options, + ARRAY_SIZE(lb_options)); +} + +static int lb_port_enter(struct team *team, struct team_port *port) +{ + return team_port_set_team_mac(port); +} + +static void lb_port_change_mac(struct team *team, struct team_port *port) +{ + team_port_set_team_mac(port); +} + +static const struct team_mode_ops lb_mode_ops = { + .init = lb_init, + .exit = lb_exit, + .transmit = lb_transmit, + .port_enter = lb_port_enter, + .port_change_mac = lb_port_change_mac, +}; + +static struct team_mode lb_mode = { + .kind = "loadbalance", + .owner = THIS_MODULE, + .priv_size = sizeof(struct lb_priv), + .ops = &lb_mode_ops, +}; + +static int __init lb_init_module(void) +{ + return team_mode_register(&lb_mode); +} + +static void __exit lb_cleanup_module(void) +{ + team_mode_unregister(&lb_mode); +} + +module_init(lb_init_module); +module_exit(lb_cleanup_module); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jiri Pirko "); +MODULE_DESCRIPTION("Load-balancing mode for team"); +MODULE_ALIAS("team-mode-loadbalance");