Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751568AbdGZT5s (ORCPT ); Wed, 26 Jul 2017 15:57:48 -0400 Received: from aserp1040.oracle.com ([141.146.126.69]:29007 "EHLO aserp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750942AbdGZT5r (ORCPT ); Wed, 26 Jul 2017 15:57:47 -0400 Date: Wed, 26 Jul 2017 22:57:28 +0300 From: Yuval Shaia To: Marcel Apfelbaum Cc: linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org, monis@mellanox.com, dledford@redhat.com, sean.hefty@intel.com, hal.rosenstock@gmail.com Subject: Re: [PATCH] drivers/rxe: improve rxe loopback Message-ID: <20170726195727.GB2339@yuvallap> References: <20170726145248.21677-1-marcel@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170726145248.21677-1-marcel@redhat.com> User-Agent: Mutt/1.8.3 (2017-05-23) X-Source-IP: aserv0022.oracle.com [141.146.126.234] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3046 Lines: 101 On Wed, Jul 26, 2017 at 05:52:48PM +0300, Marcel Apfelbaum wrote: > Currently a packet is marked for loopback only if the source and > destination address match. This is not enough when multiple > gids are present in rxe's gid table and the traffic is > from one gid to another. > > Fix it by marking the packet for loopback if the destination > address appears in rxe's gid table. > > Signed-off-by: Marcel Apfelbaum Reviewed-by: Yuval Shaia Tested-by: Yuval Shaia > --- > drivers/infiniband/sw/rxe/rxe_net.c | 47 +++++++++++++++++++++++++++++++++++-- > 1 file changed, 45 insertions(+), 2 deletions(-) > > diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c > index c3a140e..b76a9a3 100644 > --- a/drivers/infiniband/sw/rxe/rxe_net.c > +++ b/drivers/infiniband/sw/rxe/rxe_net.c > @@ -351,6 +351,27 @@ static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, > ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); > } > > +static inline bool addr4_same_rxe(struct rxe_dev *rxe, struct in_addr *daddr) > +{ > + struct in_device *in_dev; > + bool same_rxe = false; > + > + rcu_read_lock(); > + in_dev = __in_dev_get_rcu(rxe->ndev); > + if (!in_dev) > + goto out; > + > + for_ifa(in_dev) > + if (!memcmp(&ifa->ifa_address, daddr, sizeof(*daddr))) { > + same_rxe = true; > + goto out; > + } > + endfor_ifa(in_dev); > +out: > + rcu_read_unlock(); > + return same_rxe; > +} > + > static int prepare4(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, > struct sk_buff *skb, struct rxe_av *av) > { > @@ -367,7 +388,7 @@ static int prepare4(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, > return -EHOSTUNREACH; > } > > - if (!memcmp(saddr, daddr, sizeof(*daddr))) > + if (addr4_same_rxe(rxe, daddr)) > pkt->mask |= RXE_LOOPBACK_MASK; > > prepare_udp_hdr(skb, htons(RXE_ROCE_V2_SPORT), > @@ -384,6 +405,28 @@ static int prepare4(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, > return 0; > } > > +static inline bool addr6_same_rxe(struct rxe_dev *rxe, struct in6_addr *daddr) > +{ > + struct inet6_dev *in6_dev; > + struct inet6_ifaddr *ifp; > + bool same_rxe = false; > + > + in6_dev = in6_dev_get(rxe->ndev); > + if (!in6_dev) > + return false; > + > + read_lock_bh(&in6_dev->lock); > + list_for_each_entry(ifp, &in6_dev->addr_list, if_list) > + if (!memcmp(&ifp->addr, daddr, sizeof(*daddr))) { > + same_rxe = true; > + goto out; > + } > +out: > + read_unlock_bh(&in6_dev->lock); > + in6_dev_put(in6_dev); > + return same_rxe; > +} > + > static int prepare6(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, > struct sk_buff *skb, struct rxe_av *av) > { > @@ -398,7 +441,7 @@ static int prepare6(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, > return -EHOSTUNREACH; > } > > - if (!memcmp(saddr, daddr, sizeof(*daddr))) > + if (addr6_same_rxe(rxe, daddr)) > pkt->mask |= RXE_LOOPBACK_MASK; > > prepare_udp_hdr(skb, htons(RXE_ROCE_V2_SPORT), > -- > 2.9.4 >