From patchwork Thu Apr 30 19:21:31 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220148 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id DA131C47253 for ; Thu, 30 Apr 2020 19:21:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C51852072A for ; Thu, 30 Apr 2020 19:21:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726974AbgD3TV4 (ORCPT ); Thu, 30 Apr 2020 15:21:56 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:44305 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726366AbgD3TVz (ORCPT ); Thu, 30 Apr 2020 15:21:55 -0400 Received: from Internal Mail-Server by MTLPINE1 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAJ004128; Thu, 30 Apr 2020 22:21:52 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 mlx5-next 01/16] net/core: Introduce netdev_get_xmit_slave Date: Thu, 30 Apr 2020 22:21:31 +0300 Message-Id: <20200430192146.12863-2-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Add new ndo to get the xmit slave of master device. The reference counters are not incremented so the caller must be careful with locks. User can ask to get the xmit slave assume all the slaves can transmit by set all_slaves arg to true. Signed-off-by: Maor Gottlieb Reviewed-by: Jiri Pirko Reviewed-by: David Ahern --- include/linux/netdevice.h | 12 ++++++++++++ net/core/dev.c | 22 ++++++++++++++++++++++ 2 files changed, 34 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..26bc0f11b7ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1146,6 +1146,12 @@ struct netdev_net_notifier { * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * + * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev, + * struct sk_buff *skb, + * bool all_slaves); + * Get the xmit slave of master device. If all_slaves is true, function + * assume all the slaves can transmit. + * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); @@ -1389,6 +1395,9 @@ struct net_device_ops { struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); + struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, @@ -2731,6 +2740,9 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +struct net_device *netdev_get_xmit_slave(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); diff --git a/net/core/dev.c b/net/core/dev.c index 522288177bbd..294e59e20080 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7786,6 +7786,28 @@ void netdev_bonding_info_change(struct net_device *dev, } EXPORT_SYMBOL(netdev_bonding_info_change); +/** + * netdev_get_xmit_slave - Get the xmit slave of master device + * @skb: The packet + * @all_slaves: assume all the slaves are active + * + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. + * %NULL is returned if no slave is found. + */ + +struct net_device *netdev_get_xmit_slave(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_get_xmit_slave) + return NULL; + return ops->ndo_get_xmit_slave(dev, skb, all_slaves); +} +EXPORT_SYMBOL(netdev_get_xmit_slave); + static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; From patchwork Thu Apr 30 19:21:34 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220142 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id C0F13C47247 for ; Thu, 30 Apr 2020 19:22:28 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id AAC922072A for ; Thu, 30 Apr 2020 19:22:28 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727023AbgD3TW1 (ORCPT ); Thu, 30 Apr 2020 15:22:27 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:56872 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726478AbgD3TV7 (ORCPT ); Thu, 30 Apr 2020 15:21:59 -0400 Received: from Internal Mail-Server by MTLPINE2 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAM004128; Thu, 30 Apr 2020 22:21:53 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 mlx5-next 04/16] bonding/alb: Add helper functions to get the xmit slave Date: Thu, 30 Apr 2020 22:21:34 +0300 Message-Id: <20200430192146.12863-5-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Add two helper functions to get the xmit slave of bond in alb or tlb mode. Extract the logic of find the xmit slave from the xmit flow to function. Xmit flow will xmit through this slave and in the following patches the new .ndo will call to the helper function to return the xmit slave. Signed-off-by: Maor Gottlieb Reviewed-by: Jiri Pirko Reviewed-by: Jay Vosburgh --- drivers/net/bonding/bond_alb.c | 35 +++++++++++++++++++++++++--------- include/net/bond_alb.h | 4 ++++ 2 files changed, 30 insertions(+), 9 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 7bb49b049dcc..e863c694c309 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1334,11 +1334,11 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, return NETDEV_TX_OK; } -netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, + struct sk_buff *skb) { - struct bonding *bond = netdev_priv(bond_dev); - struct ethhdr *eth_data; struct slave *tx_slave = NULL; + struct ethhdr *eth_data; u32 hash_index; skb_reset_mac_header(skb); @@ -1369,20 +1369,29 @@ netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) break; } } - return bond_do_alb_xmit(skb, bond, tx_slave); + return tx_slave; } -netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct ethhdr *eth_data; + struct slave *tx_slave; + + tx_slave = bond_xmit_tlb_slave_get(bond, skb); + return bond_do_alb_xmit(skb, bond, tx_slave); +} + +struct slave *bond_xmit_alb_slave_get(struct bonding *bond, + struct sk_buff *skb) +{ struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct slave *tx_slave = NULL; static const __be32 ip_bcast = htonl(0xffffffff); - int hash_size = 0; + struct slave *tx_slave = NULL; + const u8 *hash_start = NULL; bool do_tx_balance = true; + struct ethhdr *eth_data; u32 hash_index = 0; - const u8 *hash_start = NULL; + int hash_size = 0; skb_reset_mac_header(skb); eth_data = eth_hdr(skb); @@ -1501,7 +1510,15 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) count]; } } + return tx_slave; +} + +netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *tx_slave = NULL; + tx_slave = bond_xmit_alb_slave_get(bond, skb); return bond_do_alb_xmit(skb, bond, tx_slave); } diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index b3504fcd773d..f6af76c87a6c 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -158,6 +158,10 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave); int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +struct slave *bond_xmit_alb_slave_get(struct bonding *bond, + struct sk_buff *skb); +struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, + struct sk_buff *skb); void bond_alb_monitor(struct work_struct *); int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr); void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id); From patchwork Thu Apr 30 19:21:37 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220147 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7C6DDC47253 for ; Thu, 30 Apr 2020 19:22:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 672D22072A for ; Thu, 30 Apr 2020 19:22:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727093AbgD3TWB (ORCPT ); Thu, 30 Apr 2020 15:22:01 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:44355 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1727057AbgD3TWA (ORCPT ); Thu, 30 Apr 2020 15:22:00 -0400 Received: from Internal Mail-Server by MTLPINE1 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAP004128; Thu, 30 Apr 2020 22:21:53 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 mlx5-next 07/16] bonding: Add function to get the xmit slave in active-backup mode Date: Thu, 30 Apr 2020 22:21:37 +0300 Message-Id: <20200430192146.12863-8-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Add helper function to get the xmit slave in active-backup mode. It's only one line function that return the curr_active_slave, but it will used both in the xmit flow and by the new .ndo to get the xmit slave. Signed-off-by: Maor Gottlieb Reviewed-by: Jiri Pirko Reviewed-by: Jay Vosburgh --- drivers/net/bonding/bond_main.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 09c8485e965d..1b0ae750d732 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4042,6 +4042,12 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, return NETDEV_TX_OK; } +static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond, + struct sk_buff *skb) +{ + return rcu_dereference(bond->curr_active_slave); +} + /* In active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. */ @@ -4051,7 +4057,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - slave = rcu_dereference(bond->curr_active_slave); + slave = bond_xmit_activebackup_slave_get(bond, skb); if (slave) bond_dev_queue_xmit(bond, skb, slave->dev); else From patchwork Thu Apr 30 19:21:38 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220146 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id D3FF5C47254 for ; Thu, 30 Apr 2020 19:22:07 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C2D232073E for ; Thu, 30 Apr 2020 19:22:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727112AbgD3TWG (ORCPT ); Thu, 30 Apr 2020 15:22:06 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:56902 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1727030AbgD3TWE (ORCPT ); Thu, 30 Apr 2020 15:22:04 -0400 Received: from Internal Mail-Server by MTLPINE2 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAQ004128; Thu, 30 Apr 2020 22:21:53 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 mlx5-next 08/16] bonding: Add array of all slaves Date: Thu, 30 Apr 2020 22:21:38 +0300 Message-Id: <20200430192146.12863-9-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Keep all slaves in array so it could be used to get the xmit slave assume all the slaves are active. The logic to add slave to the array is like the usable slaves, except that we also add slaves that currently can't transmit - not up or active. Signed-off-by: Maor Gottlieb Reviewed-by: Jiri Pirko Reviewed-by: Jay Vosburgh --- drivers/net/bonding/bond_main.c | 78 +++++++++++++++++++++++++-------- include/net/bonding.h | 3 +- 2 files changed, 61 insertions(+), 20 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1b0ae750d732..2de693f0262e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4120,6 +4120,38 @@ static void bond_skip_slave(struct bond_up_slave *slaves, } } +static void bond_set_slave_arr(struct bonding *bond, + struct bond_up_slave *usable_slaves, + struct bond_up_slave *all_slaves) +{ + struct bond_up_slave *usable, *all; + + usable = rtnl_dereference(bond->usable_slaves); + rcu_assign_pointer(bond->usable_slaves, usable_slaves); + kfree_rcu(usable, rcu); + + all = rtnl_dereference(bond->all_slaves); + rcu_assign_pointer(bond->all_slaves, all_slaves); + kfree_rcu(all, rcu); +} + +static void bond_reset_slave_arr(struct bonding *bond) +{ + struct bond_up_slave *usable, *all; + + usable = rtnl_dereference(bond->usable_slaves); + if (usable) { + RCU_INIT_POINTER(bond->usable_slaves, NULL); + kfree_rcu(usable, rcu); + } + + all = rtnl_dereference(bond->all_slaves); + if (all) { + RCU_INIT_POINTER(bond->all_slaves, NULL); + kfree_rcu(all, rcu); + } +} + /* Build the usable slaves array in control path for modes that use xmit-hash * to determine the slave interface - * (a) BOND_MODE_8023AD @@ -4130,7 +4162,7 @@ static void bond_skip_slave(struct bond_up_slave *slaves, */ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) { - struct bond_up_slave *usable_slaves, *old_usable_slaves; + struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL; struct slave *slave; struct list_head *iter; int agg_id = 0; @@ -4142,7 +4174,9 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) usable_slaves = kzalloc(struct_size(usable_slaves, arr, bond->slave_cnt), GFP_KERNEL); - if (!usable_slaves) { + all_slaves = kzalloc(struct_size(all_slaves, arr, + bond->slave_cnt), GFP_KERNEL); + if (!usable_slaves || !all_slaves) { ret = -ENOMEM; goto out; } @@ -4151,20 +4185,19 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) if (bond_3ad_get_active_agg_info(bond, &ad_info)) { pr_debug("bond_3ad_get_active_agg_info failed\n"); - kfree_rcu(usable_slaves, rcu); /* No active aggragator means it's not safe to use * the previous array. */ - old_usable_slaves = rtnl_dereference(bond->usable_slaves); - if (old_usable_slaves) { - RCU_INIT_POINTER(bond->usable_slaves, NULL); - kfree_rcu(old_usable_slaves, rcu); - } + bond_reset_slave_arr(bond); goto out; } agg_id = ad_info.aggregator_id; } bond_for_each_slave(bond, slave, iter) { + if (skipslave == slave) + continue; + + all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg; @@ -4174,8 +4207,6 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) } if (!bond_slave_can_tx(slave)) continue; - if (skipslave == slave) - continue; slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n", usable_slaves->count); @@ -4183,14 +4214,17 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) usable_slaves->arr[usable_slaves->count++] = slave; } - old_usable_slaves = rtnl_dereference(bond->usable_slaves); - rcu_assign_pointer(bond->usable_slaves, usable_slaves); - if (old_usable_slaves) - kfree_rcu(old_usable_slaves, rcu); + bond_set_slave_arr(bond, usable_slaves, all_slaves); + return ret; out: - if (ret != 0 && skipslave) + if (ret != 0 && skipslave) { + bond_skip_slave(rtnl_dereference(bond->all_slaves), + skipslave); bond_skip_slave(rtnl_dereference(bond->usable_slaves), skipslave); + } + kfree_rcu(all_slaves, rcu); + kfree_rcu(usable_slaves, rcu); return ret; } @@ -4501,9 +4535,9 @@ void bond_setup(struct net_device *bond_dev) static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct bond_up_slave *usable, *all; struct list_head *iter; struct slave *slave; - struct bond_up_slave *arr; bond_netpoll_cleanup(bond_dev); @@ -4512,10 +4546,16 @@ static void bond_uninit(struct net_device *bond_dev) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); - arr = rtnl_dereference(bond->usable_slaves); - if (arr) { + usable = rtnl_dereference(bond->usable_slaves); + if (usable) { RCU_INIT_POINTER(bond->usable_slaves, NULL); - kfree_rcu(arr, rcu); + kfree_rcu(usable, rcu); + } + + all = rtnl_dereference(bond->all_slaves); + if (all) { + RCU_INIT_POINTER(bond->all_slaves, NULL); + kfree_rcu(all, rcu); } list_del(&bond->bond_list); diff --git a/include/net/bonding.h b/include/net/bonding.h index 33bdb6d5182d..b5e49bedbc9f 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -200,7 +200,8 @@ struct bonding { struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; - struct bond_up_slave __rcu *usable_slaves; /* Array of usable slaves */ + struct bond_up_slave __rcu *usable_slaves; + struct bond_up_slave __rcu *all_slaves; bool force_primary; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, From patchwork Thu Apr 30 19:21:41 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220143 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 77999C4724C for ; Thu, 30 Apr 2020 19:22:23 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 5AA0C2072A for ; Thu, 30 Apr 2020 19:22:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727802AbgD3TWW (ORCPT ); Thu, 30 Apr 2020 15:22:22 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:44388 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1727068AbgD3TWA (ORCPT ); Thu, 30 Apr 2020 15:22:00 -0400 Received: from Internal Mail-Server by MTLPINE1 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAT004128; Thu, 30 Apr 2020 22:21:53 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 mlx5-next 11/16] net/mlx5: Add support to get lag physical port Date: Thu, 30 Apr 2020 22:21:41 +0300 Message-Id: <20200430192146.12863-12-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Add function to get the device physical port of the lag slave. Signed-off-by: Maor Gottlieb Reviewed-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 24 +++++++++++++++++++ include/linux/mlx5/driver.h | 2 ++ 2 files changed, 26 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 496a3408d771..5461fbe47c0d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -710,6 +710,30 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_get_roce_netdev); +u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, + struct net_device *slave) +{ + struct mlx5_lag *ldev; + u8 port = 0; + + spin_lock(&lag_lock); + ldev = mlx5_lag_dev_get(dev); + if (!(ldev && __mlx5_lag_is_roce(ldev))) + goto unlock; + + if (ldev->pf[MLX5_LAG_P1].netdev == slave) + port = MLX5_LAG_P1; + else + port = MLX5_LAG_P2; + + port = ldev->v2p_map[port]; + +unlock: + spin_unlock(&lag_lock); + return port; +} +EXPORT_SYMBOL(mlx5_lag_get_slave_port); + bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6f8f79ef829b..7b81b512d116 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1062,6 +1062,8 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); +u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, + struct net_device *slave); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, From patchwork Thu Apr 30 19:21:42 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220144 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 61FB0C47253 for ; Thu, 30 Apr 2020 19:22:19 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 40FDE2072A for ; Thu, 30 Apr 2020 19:22:19 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727773AbgD3TWS (ORCPT ); Thu, 30 Apr 2020 15:22:18 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:56932 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1727044AbgD3TWR (ORCPT ); Thu, 30 Apr 2020 15:22:17 -0400 Received: from Internal Mail-Server by MTLPINE2 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAU004128; Thu, 30 Apr 2020 22:21:53 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 rdma-next 12/16] RDMA: Group create AH arguments in struct Date: Thu, 30 Apr 2020 22:21:42 +0300 Message-Id: <20200430192146.12863-13-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Following patch adds additional argument to the create AH function, so it make sense to group ah_attr and flags arguments in struct. Signed-off-by: Maor Gottlieb Acked-by: Devesh Sharma Acked-by: Gal Pressman Acked-by: Weihang Li Reviewed-by: Jason Gunthorpe --- drivers/infiniband/core/verbs.c | 5 ++++- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 8 +++++--- drivers/infiniband/hw/bnxt_re/ib_verbs.h | 2 +- drivers/infiniband/hw/efa/efa.h | 3 +-- drivers/infiniband/hw/efa/efa_verbs.c | 6 +++--- drivers/infiniband/hw/hns/hns_roce_ah.c | 5 +++-- drivers/infiniband/hw/hns/hns_roce_device.h | 4 ++-- drivers/infiniband/hw/mlx4/ah.c | 11 +++++++---- drivers/infiniband/hw/mlx4/mlx4_ib.h | 2 +- drivers/infiniband/hw/mlx5/ah.c | 5 +++-- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +- drivers/infiniband/hw/mthca/mthca_provider.c | 9 +++++---- drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 3 ++- drivers/infiniband/hw/ocrdma/ocrdma_ah.h | 2 +- drivers/infiniband/hw/qedr/verbs.c | 4 ++-- drivers/infiniband/hw/qedr/verbs.h | 2 +- drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c | 5 +++-- drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 2 +- drivers/infiniband/sw/rdmavt/ah.c | 11 ++++++----- drivers/infiniband/sw/rdmavt/ah.h | 4 ++-- drivers/infiniband/sw/rxe/rxe_verbs.c | 9 +++++---- include/rdma/ib_verbs.h | 9 +++++++-- 22 files changed, 66 insertions(+), 47 deletions(-) diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3bfadd8effcc..86be8a54a2d6 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -502,6 +502,7 @@ static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, u32 flags, struct ib_udata *udata) { + struct rdma_ah_init_attr init_attr = {}; struct ib_device *device = pd->device; struct ib_ah *ah; int ret; @@ -521,8 +522,10 @@ static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, ah->pd = pd; ah->type = ah_attr->type; ah->sgid_attr = rdma_update_sgid_attr(ah_attr, NULL); + init_attr.ah_attr = ah_attr; + init_attr.flags = flags; - ret = device->ops.create_ah(ah, ah_attr, flags, udata); + ret = device->ops.create_ah(ah, &init_attr, udata); if (ret) { kfree(ah); return ERR_PTR(ret); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index d98348e82422..5a7c090204c5 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -631,11 +631,12 @@ static u8 bnxt_re_stack_to_dev_nw_type(enum rdma_network_type ntype) return nw_type; } -int bnxt_re_create_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) +int bnxt_re_create_ah(struct ib_ah *ib_ah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { struct ib_pd *ib_pd = ib_ah->pd; struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd); + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr); struct bnxt_re_dev *rdev = pd->rdev; const struct ib_gid_attr *sgid_attr; @@ -673,7 +674,8 @@ int bnxt_re_create_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr, memcpy(ah->qplib_ah.dmac, ah_attr->roce.dmac, ETH_ALEN); rc = bnxt_qplib_create_ah(&rdev->qplib_res, &ah->qplib_ah, - !(flags & RDMA_CREATE_AH_SLEEPABLE)); + !(init_attr->flags & + RDMA_CREATE_AH_SLEEPABLE)); if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate HW AH"); return rc; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index 18dd46f46cf4..204c0849ba28 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -170,7 +170,7 @@ enum rdma_link_layer bnxt_re_get_link_layer(struct ib_device *ibdev, u8 port_num); int bnxt_re_alloc_pd(struct ib_pd *pd, struct ib_udata *udata); void bnxt_re_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata); -int bnxt_re_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags, +int bnxt_re_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); int bnxt_re_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int bnxt_re_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h index aa7396a1588a..45d519edb4c3 100644 --- a/drivers/infiniband/hw/efa/efa.h +++ b/drivers/infiniband/hw/efa/efa.h @@ -153,8 +153,7 @@ int efa_mmap(struct ib_ucontext *ibucontext, struct vm_area_struct *vma); void efa_mmap_free(struct rdma_user_mmap_entry *rdma_entry); int efa_create_ah(struct ib_ah *ibah, - struct rdma_ah_attr *ah_attr, - u32 flags, + struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); void efa_destroy_ah(struct ib_ah *ibah, u32 flags); int efa_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 5c57098a4aee..454b01b21e6a 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1639,10 +1639,10 @@ static int efa_ah_destroy(struct efa_dev *dev, struct efa_ah *ah) } int efa_create_ah(struct ib_ah *ibah, - struct rdma_ah_attr *ah_attr, - u32 flags, + struct rdma_ah_init_attr *init_attr, struct ib_udata *udata) { + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; struct efa_dev *dev = to_edev(ibah->device); struct efa_com_create_ah_params params = {}; struct efa_ibv_create_ah_resp resp = {}; @@ -1650,7 +1650,7 @@ int efa_create_ah(struct ib_ah *ibah, struct efa_ah *ah = to_eah(ibah); int err; - if (!(flags & RDMA_CREATE_AH_SLEEPABLE)) { + if (!(init_attr->flags & RDMA_CREATE_AH_SLEEPABLE)) { ibdev_dbg(&dev->ibdev, "Create address handle is not supported in atomic context\n"); err = -EOPNOTSUPP; diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c index 8a522e14ef62..5b2f9314edd3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_ah.c +++ b/drivers/infiniband/hw/hns/hns_roce_ah.c @@ -39,13 +39,14 @@ #define HNS_ROCE_VLAN_SL_BIT_MASK 7 #define HNS_ROCE_VLAN_SL_SHIFT 13 -int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) +int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(ibah->device); const struct ib_gid_attr *gid_attr; struct device *dev = hr_dev->dev; struct hns_roce_ah *ah = to_hr_ah(ibah); + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr); u16 vlan_id = 0xffff; bool vlan_en = false; diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index ecbfeb6dbdd4..e1032cec2b12 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -1208,8 +1208,8 @@ void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap, unsigned long obj, int cnt, int rr); -int hns_roce_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata); +int hns_roce_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata); int hns_roce_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); void hns_roce_destroy_ah(struct ib_ah *ah, u32 flags); diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 02a169f8027b..5f8f8d5c0ce0 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -141,10 +141,11 @@ static int create_iboe_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr) return 0; } -int mlx4_ib_create_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) - +int mlx4_ib_create_ah(struct ib_ah *ib_ah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; + if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) { if (!(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH)) return -EINVAL; @@ -167,12 +168,14 @@ int mlx4_ib_create_ah_slave(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, int slave_sgid_index, u8 *s_mac, u16 vlan_tag) { struct rdma_ah_attr slave_attr = *ah_attr; + struct rdma_ah_init_attr init_attr = {}; struct mlx4_ib_ah *mah = to_mah(ah); int ret; slave_attr.grh.sgid_attr = NULL; slave_attr.grh.sgid_index = slave_sgid_index; - ret = mlx4_ib_create_ah(ah, &slave_attr, 0, NULL); + init_attr.ah_attr = &slave_attr; + ret = mlx4_ib_create_ah(ah, &init_attr, NULL); if (ret) return ret; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index d188573187fa..182a237b87f7 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -752,7 +752,7 @@ int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags); void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq); void mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq); -int mlx4_ib_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags, +int mlx4_ib_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); int mlx4_ib_create_ah_slave(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, int slave_sgid_index, u8 *s_mac, u16 vlan_tag); diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c index 80642dd359bc..9b59348d51b5 100644 --- a/drivers/infiniband/hw/mlx5/ah.c +++ b/drivers/infiniband/hw/mlx5/ah.c @@ -68,10 +68,11 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah, } } -int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) +int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; struct mlx5_ib_ah *ah = to_mah(ibah); struct mlx5_ib_dev *dev = to_mdev(ibah->device); enum rdma_ah_attr_type ah_type = ah_attr->type; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 9b2baf119823..3a1977ab899b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1163,7 +1163,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index); -int mlx5_ib_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags, +int mlx5_ib_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); void mlx5_ib_destroy_ah(struct ib_ah *ah, u32 flags); diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 69a3e4f62fb1..bc3e3d741ca3 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -388,14 +388,15 @@ static void mthca_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata) mthca_pd_free(to_mdev(pd->device), to_mpd(pd)); } -static int mthca_ah_create(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) +static int mthca_ah_create(struct ib_ah *ibah, + struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { struct mthca_ah *ah = to_mah(ibah); - return mthca_create_ah(to_mdev(ibah->device), to_mpd(ibah->pd), ah_attr, - ah); + return mthca_create_ah(to_mdev(ibah->device), to_mpd(ibah->pd), + init_attr->ah_attr, ah); } static void mthca_ah_destroy(struct ib_ah *ah, u32 flags) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c index 2b7f00ac41b0..6eea02b18968 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -155,7 +155,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah, return status; } -int ocrdma_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr, u32 flags, +int ocrdma_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata) { u32 *ahid_addr; @@ -165,6 +165,7 @@ int ocrdma_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr, u32 flags, u16 vlan_tag = 0xffff; const struct ib_gid_attr *sgid_attr; struct ocrdma_pd *pd = get_ocrdma_pd(ibah->pd); + struct rdma_ah_attr *attr = init_attr->ah_attr; struct ocrdma_dev *dev = get_ocrdma_dev(ibah->device); if ((attr->type != RDMA_AH_ATTR_TYPE_ROCE) || diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h index 9780afcde780..8b73b3489f3a 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h @@ -51,7 +51,7 @@ enum { OCRDMA_AH_L3_TYPE_SHIFT = 0x1D /* 29 bits */ }; -int ocrdma_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags, +int ocrdma_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); void ocrdma_destroy_ah(struct ib_ah *ah, u32 flags); int ocrdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index a5bd3adaf90a..d6b94a713573 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -2750,12 +2750,12 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) return 0; } -int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr, u32 flags, +int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata) { struct qedr_ah *ah = get_qedr_ah(ibah); - rdma_copy_ah_attr(&ah->attr, attr); + rdma_copy_ah_attr(&ah->attr, init_attr->ah_attr); return 0; } diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h index 18027844eb87..5e02387e068d 100644 --- a/drivers/infiniband/hw/qedr/verbs.h +++ b/drivers/infiniband/hw/qedr/verbs.h @@ -70,7 +70,7 @@ int qedr_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr); void qedr_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata); int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_recv_wr); -int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr, u32 flags, +int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); void qedr_destroy_ah(struct ib_ah *ibah, u32 flags); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c index faf7ecd7b3fa..ccbded2d26ce 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c @@ -509,9 +509,10 @@ void pvrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata) * * @return: 0 on success, otherwise errno. */ -int pvrdma_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) +int pvrdma_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; struct pvrdma_dev *dev = to_vdev(ibah->device); struct pvrdma_ah *ah = to_vah(ibah); const struct ib_global_route *grh; diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h index e4a48f5c0c85..267702226f10 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h @@ -414,7 +414,7 @@ int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int pvrdma_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags); -int pvrdma_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags, +int pvrdma_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); void pvrdma_destroy_ah(struct ib_ah *ah, u32 flags); diff --git a/drivers/infiniband/sw/rdmavt/ah.c b/drivers/infiniband/sw/rdmavt/ah.c index ee02c6176007..40480add7dd3 100644 --- a/drivers/infiniband/sw/rdmavt/ah.c +++ b/drivers/infiniband/sw/rdmavt/ah.c @@ -98,14 +98,14 @@ EXPORT_SYMBOL(rvt_check_ah); * * Return: 0 on success */ -int rvt_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, - u32 create_flags, struct ib_udata *udata) +int rvt_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { struct rvt_ah *ah = ibah_to_rvtah(ibah); struct rvt_dev_info *dev = ib_to_rvt(ibah->device); unsigned long flags; - if (rvt_check_ah(ibah->device, ah_attr)) + if (rvt_check_ah(ibah->device, init_attr->ah_attr)) return -EINVAL; spin_lock_irqsave(&dev->n_ahs_lock, flags); @@ -117,10 +117,11 @@ int rvt_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr, dev->n_ahs_allocated++; spin_unlock_irqrestore(&dev->n_ahs_lock, flags); - rdma_copy_ah_attr(&ah->attr, ah_attr); + rdma_copy_ah_attr(&ah->attr, init_attr->ah_attr); if (dev->driver_f.notify_new_ah) - dev->driver_f.notify_new_ah(ibah->device, ah_attr, ah); + dev->driver_f.notify_new_ah(ibah->device, + init_attr->ah_attr, ah); return 0; } diff --git a/drivers/infiniband/sw/rdmavt/ah.h b/drivers/infiniband/sw/rdmavt/ah.h index bbb4d3bdec4e..40b7123fec76 100644 --- a/drivers/infiniband/sw/rdmavt/ah.h +++ b/drivers/infiniband/sw/rdmavt/ah.h @@ -50,8 +50,8 @@ #include -int rvt_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, - u32 create_flags, struct ib_udata *udata); +int rvt_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata); void rvt_destroy_ah(struct ib_ah *ibah, u32 destroy_flags); int rvt_modify_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); int rvt_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 9dd4bd7aea92..b8a22af724e8 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -195,15 +195,16 @@ static void rxe_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata) rxe_drop_ref(pd); } -static int rxe_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr, - u32 flags, struct ib_udata *udata) +static int rxe_create_ah(struct ib_ah *ibah, + struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { int err; struct rxe_dev *rxe = to_rdev(ibah->device); struct rxe_ah *ah = to_rah(ibah); - err = rxe_av_chk_attr(rxe, attr); + err = rxe_av_chk_attr(rxe, init_attr->ah_attr); if (err) return err; @@ -211,7 +212,7 @@ static int rxe_create_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr, if (err) return err; - rxe_init_av(attr, &ah->av); + rxe_init_av(init_attr->ah_attr, &ah->av); return 0; } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bbc5cfb57cd2..20ea26810349 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -880,6 +880,11 @@ struct ib_mr_status { */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); +struct rdma_ah_init_attr { + struct rdma_ah_attr *ah_attr; + u32 flags; +}; + enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, @@ -2403,8 +2408,8 @@ struct ib_device_ops { void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); void (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); - int (*create_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata); + int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, + struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); void (*destroy_ah)(struct ib_ah *ah, u32 flags); From patchwork Thu Apr 30 19:21:43 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maor Gottlieb X-Patchwork-Id: 220145 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.7 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, SIGNED_OFF_BY, SPF_HELO_NONE, SPF_PASS, UNPARSEABLE_RELAY, URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3461FC47247 for ; Thu, 30 Apr 2020 19:22:16 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 1EB412073E for ; Thu, 30 Apr 2020 19:22:16 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726451AbgD3TWP (ORCPT ); Thu, 30 Apr 2020 15:22:15 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:44437 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726486AbgD3TWG (ORCPT ); Thu, 30 Apr 2020 15:22:06 -0400 Received: from Internal Mail-Server by MTLPINE1 (envelope-from maorg@mellanox.com) with ESMTPS (AES256-SHA encrypted); 30 Apr 2020 22:21:53 +0300 Received: from dev-l-vrt-201.mtl.labs.mlnx (dev-l-vrt-201.mtl.labs.mlnx [10.134.201.1]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 03UJLqAV004128; Thu, 30 Apr 2020 22:21:53 +0300 From: Maor Gottlieb To: davem@davemloft.net, jgg@mellanox.com, dledford@redhat.com, j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net, kuba@kernel.org, jiri@mellanox.com, dsahern@kernel.org Cc: leonro@mellanox.com, saeedm@mellanox.com, linux-rdma@vger.kernel.org, netdev@vger.kernel.org, alexr@mellanox.com, Maor Gottlieb Subject: [PATCH V8 rdma-next 13/16] RDMA/core: Add LAG functionality Date: Thu, 30 Apr 2020 22:21:43 +0300 Message-Id: <20200430192146.12863-14-maorg@mellanox.com> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20200430192146.12863-1-maorg@mellanox.com> References: <20200430192146.12863-1-maorg@mellanox.com> Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Add support to get the RoCE LAG xmit slave by building skb of the RoCE packet and call to master_get_xmit_slave. If driver wants to get the slave assume all slaves are available, then need to set RDMA_LAG_FLAGS_HASH_ALL_SLAVES in flags. Signed-off-by: Maor Gottlieb Reviewed-by: Leon Romanovsky --- drivers/infiniband/core/Makefile | 2 +- drivers/infiniband/core/lag.c | 136 +++++++++++++++++++++++++++++++ include/rdma/ib_verbs.h | 1 + include/rdma/lag.h | 23 ++++++ 4 files changed, 161 insertions(+), 1 deletion(-) create mode 100644 drivers/infiniband/core/lag.c create mode 100644 include/rdma/lag.h diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile index d1b14887960e..870f0fcd54d5 100644 --- a/drivers/infiniband/core/Makefile +++ b/drivers/infiniband/core/Makefile @@ -12,7 +12,7 @@ ib_core-y := packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \ roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \ multicast.o mad.o smi.o agent.o mad_rmpp.o \ nldev.o restrack.o counters.o ib_core_uverbs.o \ - trace.o + trace.o lag.o ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o diff --git a/drivers/infiniband/core/lag.c b/drivers/infiniband/core/lag.c new file mode 100644 index 000000000000..a29533626a7c --- /dev/null +++ b/drivers/infiniband/core/lag.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* + * Copyright (c) 2020 Mellanox Technologies. All rights reserved. + */ + +#include +#include +#include + +static struct sk_buff *rdma_build_skb(struct ib_device *device, + struct net_device *netdev, + struct rdma_ah_attr *ah_attr, + gfp_t flags) +{ + struct ipv6hdr *ip6h; + struct sk_buff *skb; + struct ethhdr *eth; + struct iphdr *iph; + struct udphdr *uh; + u8 smac[ETH_ALEN]; + bool is_ipv4; + int hdr_len; + + is_ipv4 = ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw); + hdr_len = ETH_HLEN + sizeof(struct udphdr) + LL_RESERVED_SPACE(netdev); + hdr_len += is_ipv4 ? sizeof(struct iphdr) : sizeof(struct ipv6hdr); + + skb = alloc_skb(hdr_len, flags); + if (!skb) + return NULL; + + skb->dev = netdev; + skb_reserve(skb, hdr_len); + skb_push(skb, sizeof(struct udphdr)); + skb_reset_transport_header(skb); + uh = udp_hdr(skb); + uh->source = htons(0xC000); + uh->dest = htons(ROCE_V2_UDP_DPORT); + uh->len = htons(sizeof(struct udphdr)); + + if (is_ipv4) { + skb_push(skb, sizeof(struct iphdr)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + iph->frag_off = 0; + iph->version = 4; + iph->protocol = IPPROTO_UDP; + iph->ihl = 0x5; + iph->tot_len = htons(sizeof(struct udphdr) + sizeof(struct + iphdr)); + memcpy(&iph->saddr, ah_attr->grh.sgid_attr->gid.raw + 12, + sizeof(struct in_addr)); + memcpy(&iph->daddr, ah_attr->grh.dgid.raw + 12, + sizeof(struct in_addr)); + } else { + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + ip6h->version = 6; + ip6h->nexthdr = IPPROTO_UDP; + memcpy(&ip6h->flow_lbl, &ah_attr->grh.flow_label, + sizeof(*ip6h->flow_lbl)); + memcpy(&ip6h->saddr, ah_attr->grh.sgid_attr->gid.raw, + sizeof(struct in6_addr)); + memcpy(&ip6h->daddr, ah_attr->grh.dgid.raw, + sizeof(struct in6_addr)); + } + + skb_push(skb, sizeof(struct ethhdr)); + skb_reset_mac_header(skb); + eth = eth_hdr(skb); + skb->protocol = eth->h_proto = htons(is_ipv4 ? ETH_P_IP : ETH_P_IPV6); + rdma_read_gid_l2_fields(ah_attr->grh.sgid_attr, NULL, smac); + memcpy(eth->h_source, smac, ETH_ALEN); + memcpy(eth->h_dest, ah_attr->roce.dmac, ETH_ALEN); + + return skb; +} + +static struct net_device *rdma_get_xmit_slave_udp(struct ib_device *device, + struct net_device *master, + struct rdma_ah_attr *ah_attr, + gfp_t flags) +{ + struct net_device *slave; + struct sk_buff *skb; + + skb = rdma_build_skb(device, master, ah_attr, flags); + if (!skb) + return ERR_PTR(-ENOMEM); + + rcu_read_lock(); + slave = netdev_get_xmit_slave(master, skb, + !!(device->lag_flags & + RDMA_LAG_FLAGS_HASH_ALL_SLAVES)); + if (slave) + dev_hold(slave); + rcu_read_unlock(); + kfree_skb(skb); + return slave; +} + +void rdma_lag_put_ah_roce_slave(struct net_device *xmit_slave) +{ + if (xmit_slave) + dev_put(xmit_slave); +} + +struct net_device *rdma_lag_get_ah_roce_slave(struct ib_device *device, + struct rdma_ah_attr *ah_attr, + gfp_t flags) +{ + struct net_device *slave = NULL; + struct net_device *master; + + if (!(ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE && + ah_attr->grh.sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)) + return NULL; + + rcu_read_lock(); + master = rdma_read_gid_attr_ndev_rcu(ah_attr->grh.sgid_attr); + if (IS_ERR(master)) { + rcu_read_unlock(); + return master; + } + dev_hold(master); + rcu_read_unlock(); + + if (!netif_is_bond_master(master)) + goto put; + + slave = rdma_get_xmit_slave_udp(device, master, ah_attr, flags); +put: + dev_put(master); + return slave; +} diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 20ea26810349..e6c18ec0365a 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2714,6 +2714,7 @@ struct ib_device { /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; + u32 lag_flags; }; struct ib_client_nl_info; diff --git a/include/rdma/lag.h b/include/rdma/lag.h new file mode 100644 index 000000000000..7c06ec9b2eef --- /dev/null +++ b/include/rdma/lag.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* + * Copyright (c) 2020 Mellanox Technologies. All rights reserved. + */ + +#ifndef _RDMA_LAG_H_ +#define _RDMA_LAG_H_ + +#include + +struct ib_device; +struct rdma_ah_attr; + +enum rdma_lag_flags { + RDMA_LAG_FLAGS_HASH_ALL_SLAVES = 1 << 0 +}; + +void rdma_lag_put_ah_roce_slave(struct net_device *xmit_slave); +struct net_device *rdma_lag_get_ah_roce_slave(struct ib_device *device, + struct rdma_ah_attr *ah_attr, + gfp_t flags); + +#endif /* _RDMA_LAG_H_ */