From patchwork Tue Nov 17 00:12:07 2009 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Hefty, Sean" X-Patchwork-Id: 60553 Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by demeter.kernel.org (8.14.2/8.14.2) with ESMTP id nAH0C9mg016960 for ; Tue, 17 Nov 2009 00:12:09 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754532AbZKQAMC (ORCPT ); Mon, 16 Nov 2009 19:12:02 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754730AbZKQAMC (ORCPT ); Mon, 16 Nov 2009 19:12:02 -0500 Received: from mga02.intel.com ([134.134.136.20]:11238 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754532AbZKQAMB (ORCPT ); Mon, 16 Nov 2009 19:12:01 -0500 Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga101.jf.intel.com with ESMTP; 16 Nov 2009 15:57:46 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.44,754,1249282800"; d="scan'208";a="467876069" Received: from mshefty-mobl2.amr.corp.intel.com (HELO msheftyMOBL2) ([10.24.90.109]) by orsmga002.jf.intel.com with ESMTP; 16 Nov 2009 16:29:14 -0800 From: "Sean Hefty" To: Subject: [PATCH 9/9] ib/addr: fix ipv6 routing lookup Date: Mon, 16 Nov 2009 16:12:07 -0800 Message-ID: <2449CF17D7E94FCBA643A743473246A5@amr.corp.intel.com> MIME-Version: 1.0 X-Mailer: Microsoft Office Outlook 11 Thread-Index: AcpnGpj3RC+1H00iSVKfra9dGy/oAA== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.5579 Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 07c2944..b152ca2 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -176,34 +176,6 @@ static void queue_req(struct addr_req *req) mutex_unlock(&lock); } -static void addr_send_arp(struct sockaddr *dst_in) -{ - struct rtable *rt; - struct flowi fl; - - memset(&fl, 0, sizeof fl); - - switch (dst_in->sa_family) { -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - case AF_INET6: - { - struct dst_entry *dst; - - fl.nl_u.ip6_u.daddr = - ((struct sockaddr_in6 *) dst_in)->sin6_addr; - - dst = ip6_route_output(&init_net, NULL, &fl); - if (!dst) - return; - - neigh_event_send(dst->neighbour, NULL); - dst_release(dst); - break; - } -#endif - } -} - static int addr4_resolve(struct sockaddr_in *src_in, struct sockaddr_in *dst_in, struct rdma_dev_addr *addr) @@ -259,39 +231,63 @@ out: } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static int addr6_resolve_remote(struct sockaddr_in6 *src_in, - struct sockaddr_in6 *dst_in, - struct rdma_dev_addr *addr) +static int addr6_resolve(struct sockaddr_in6 *src_in, + struct sockaddr_in6 *dst_in, + struct rdma_dev_addr *addr) { struct flowi fl; struct neighbour *neigh; struct dst_entry *dst; - int ret = -ENODATA; + int ret; memset(&fl, 0, sizeof fl); - fl.nl_u.ip6_u.daddr = dst_in->sin6_addr; - fl.nl_u.ip6_u.saddr = src_in->sin6_addr; + ipv6_addr_copy(&fl.fl6_dst, &dst_in->sin6_addr); + ipv6_addr_copy(&fl.fl6_src, &src_in->sin6_addr); fl.oif = addr->bound_dev_if; dst = ip6_route_output(&init_net, NULL, &fl); - if (!dst) - return ret; + if ((ret = dst->error)) + goto put; + if (ipv6_addr_any(&fl.fl6_src)) { + ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev, + &fl.fl6_dst, 0, &fl.fl6_src); + if (ret) + goto put; + + src_in->sin6_family = AF_INET6; + ipv6_addr_copy(&src_in->sin6_addr, &fl.fl6_src); + } + + if (dst->dev->flags & IFF_LOOPBACK) { + ret = rdma_translate_ip((struct sockaddr *) dst_in, addr); + if (!ret) + memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN); + goto put; + } + + /* If the device does ARP internally, return 'done' */ if (dst->dev->flags & IFF_NOARP) { ret = rdma_copy_addr(addr, dst->dev, NULL); - } else { - neigh = dst->neighbour; - if (neigh && (neigh->nud_state & NUD_VALID)) - ret = rdma_copy_addr(addr, neigh->dev, neigh->ha); + goto put; + } + + neigh = dst->neighbour; + if (!neigh || !(neigh->nud_state & NUD_VALID)) { + neigh_event_send(dst->neighbour, NULL); + ret = -ENODATA; + goto put; } + ret = rdma_copy_addr(addr, dst->dev, neigh->ha); +put: dst_release(dst); return ret; } #else -static int addr6_resolve_remote(struct sockaddr_in6 *src_in, - struct sockaddr_in6 *dst_in, - struct rdma_dev_addr *addr) +static int addr6_resolve(struct sockaddr_in6 *src_in, + struct sockaddr_in6 *dst_in, + struct rdma_dev_addr *addr) { return -EADDRNOTAVAIL; } @@ -305,7 +301,7 @@ static int addr_resolve(struct sockaddr *src_in, return addr4_resolve((struct sockaddr_in *) src_in, (struct sockaddr_in *) dst_in, addr); } else - return addr6_resolve_remote((struct sockaddr_in6 *) src_in, + return addr6_resolve((struct sockaddr_in6 *) src_in, (struct sockaddr_in6 *) dst_in, addr); } @@ -346,60 +342,6 @@ static void process_req(struct work_struct *work) } } -static int addr_resolve_local(struct sockaddr *src_in, - struct sockaddr *dst_in, - struct rdma_dev_addr *addr) -{ - struct net_device *dev; - int ret; - - switch (dst_in->sa_family) { -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) - case AF_INET6: - { - struct in6_addr *a; - - read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) - if (ipv6_chk_addr(&init_net, - &((struct sockaddr_in6 *) addr)->sin6_addr, - dev, 1)) - break; - - if (!dev) { - read_unlock(&dev_base_lock); - return -EADDRNOTAVAIL; - } - - a = &((struct sockaddr_in6 *) src_in)->sin6_addr; - - if (ipv6_addr_any(a)) { - src_in->sa_family = dst_in->sa_family; - ((struct sockaddr_in6 *) src_in)->sin6_addr = - ((struct sockaddr_in6 *) dst_in)->sin6_addr; - ret = rdma_copy_addr(addr, dev, dev->dev_addr); - } else if (ipv6_addr_loopback(a)) { - ret = rdma_translate_ip(dst_in, addr); - if (!ret) - memcpy(addr->dst_dev_addr, dev->dev_addr, MAX_ADDR_LEN); - } else { - ret = rdma_translate_ip(src_in, addr); - if (!ret) - memcpy(addr->dst_dev_addr, dev->dev_addr, MAX_ADDR_LEN); - } - read_unlock(&dev_base_lock); - break; - } -#endif - - default: - ret = -EADDRNOTAVAIL; - break; - } - - return ret; -} - int rdma_resolve_ip(struct rdma_addr_client *client, struct sockaddr *src_addr, struct sockaddr *dst_addr, struct rdma_dev_addr *addr, int timeout_ms, @@ -429,10 +371,7 @@ int rdma_resolve_ip(struct rdma_addr_client *client, src_in = (struct sockaddr *) &req->src_addr; dst_in = (struct sockaddr *) &req->dst_addr; - req->status = addr_resolve_local(src_in, dst_in, addr); - if (req->status == -EADDRNOTAVAIL) - req->status = addr_resolve(src_in, dst_in, addr); - + req->status = addr_resolve(src_in, dst_in, addr); switch (req->status) { case 0: req->timeout = jiffies; @@ -441,7 +380,6 @@ int rdma_resolve_ip(struct rdma_addr_client *client, case -ENODATA: req->timeout = msecs_to_jiffies(timeout_ms) + jiffies; queue_req(req); - addr_send_arp(dst_in); break; default: ret = req->status; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 38867a4..71e616a 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1472,15 +1472,6 @@ static void cma_listen_on_all(struct rdma_id_private *id_priv) mutex_unlock(&lock); } -static int cma_bind_any(struct rdma_cm_id *id, sa_family_t af) -{ - struct sockaddr_storage addr_in; - - memset(&addr_in, 0, sizeof addr_in); - addr_in.ss_family = af; - return rdma_bind_addr(id, (struct sockaddr *) &addr_in); -} - int rdma_listen(struct rdma_cm_id *id, int backlog) { struct rdma_id_private *id_priv; @@ -1488,7 +1479,8 @@ int rdma_listen(struct rdma_cm_id *id, int backlog) id_priv = container_of(id, struct rdma_id_private, id); if (id_priv->state == CMA_IDLE) { - ret = cma_bind_any(id, AF_INET); + ((struct sockaddr *) &id->route.addr.src_addr)->sa_family = AF_INET; + ret = rdma_bind_addr(id, (struct sockaddr *) &id->route.addr.src_addr); if (ret) return ret; } @@ -1885,10 +1877,14 @@ err: static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, struct sockaddr *dst_addr) { - if (src_addr && src_addr->sa_family) - return rdma_bind_addr(id, src_addr); - else - return cma_bind_any(id, dst_addr->sa_family); + if (!src_addr || !src_addr->sa_family) { + src_addr = (struct sockaddr *) &id->route.addr.src_addr; + if ((src_addr->sa_family = dst_addr->sa_family) == AF_INET6) { + ((struct sockaddr_in6 *) src_addr)->sin6_scope_id = + ((struct sockaddr_in6 *) dst_addr)->sin6_scope_id; + } + } + return rdma_bind_addr(id, src_addr); } int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, @@ -2084,6 +2080,23 @@ static int cma_get_port(struct rdma_id_private *id_priv) return ret; } +static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, + struct sockaddr *addr) +{ + struct sockaddr_in6 *sin6; + + if (addr->sa_family != AF_INET6) + return 0; + + sin6 = (struct sockaddr_in6 *) addr; + if ((ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !sin6->sin6_scope_id) + return -EINVAL; + + dev_addr->bound_dev_if = sin6->sin6_scope_id; + return 0; +} + int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; @@ -2096,6 +2109,10 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) if (!cma_comp_exch(id_priv, CMA_IDLE, CMA_ADDR_BOUND)) return -EINVAL; + ret = cma_check_linklocal(&id->route.addr.dev_addr, addr); + if (ret) + goto err1; + if (cma_loopback_addr(addr)) { ret = cma_bind_loopback(id_priv); } else if (!cma_zero_addr(addr)) {