From patchwork Thu Oct 15 01:16:22 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838353 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 40A9BC433E7 for ; Thu, 15 Oct 2020 01:16:47 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E8F6B22254 for ; Thu, 15 Oct 2020 01:16:46 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731533AbgJOBQp (ORCPT ); Wed, 14 Oct 2020 21:16:45 -0400 Received: from correo.us.es ([193.147.175.20]:38738 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1730279AbgJOBQo (ORCPT ); Wed, 14 Oct 2020 21:16:44 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id 6E89DDA7E3 for ; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 584CADA722 for ; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id 4DED8DA789; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 26DB4DA722; Thu, 15 Oct 2020 03:16:40 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:40 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id E91D041FF201; Thu, 15 Oct 2020 03:16:39 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 1/9] netfilter: flowtable: add xmit path types Date: Thu, 15 Oct 2020 03:16:22 +0200 Message-Id: <20201015011630.2399-2-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Add the xmit_type field that defines the two supported xmit paths in the flowtable data plane, which are the neighbour and the xfrm xmit paths. This patch prepares for new flowtable xmit path types to come. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 6 ++++ net/netfilter/nf_flow_table_core.c | 4 +++ net/netfilter/nf_flow_table_ip.c | 50 ++++++++++++++++++--------- 3 files changed, 44 insertions(+), 16 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 16e8b2f8d006..08e779f149ee 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -89,6 +89,11 @@ enum flow_offload_tuple_dir { FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX }; +enum flow_offload_xmit_type { + FLOW_OFFLOAD_XMIT_NEIGH = 0, + FLOW_OFFLOAD_XMIT_XFRM, +}; + struct flow_offload_tuple { union { struct in_addr src_v4; @@ -108,6 +113,7 @@ struct flow_offload_tuple { u8 l3proto; u8 l4proto; u8 dir; + enum flow_offload_xmit_type xmit_type:8; u16 mtu; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 513f78db3cb2..97f04f244961 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -95,6 +95,10 @@ static int flow_offload_fill_route(struct flow_offload *flow, } flow_tuple->iifidx = other_dst->dev->ifindex; + + if (dst_xfrm(dst)) + flow_tuple->xmit_type = FLOW_OFFLOAD_XMIT_XFRM; + flow_tuple->dst_cache = dst; return 0; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index a698dbe28ef5..e215c79e6777 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -252,6 +252,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, unsigned int thoff; struct iphdr *iph; __be32 nexthop; + int ret; if (skb->protocol != htons(ETH_P_IP)) return NF_ACCEPT; @@ -295,19 +296,27 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); - if (unlikely(dst_xfrm(&rt->dst))) { + switch (tuplehash->tuple.xmit_type) { + case FLOW_OFFLOAD_XMIT_NEIGH: + skb->dev = outdev; + nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + ret = NF_STOLEN; + break; + case FLOW_OFFLOAD_XMIT_XFRM: memset(skb->cb, 0, sizeof(struct inet_skb_parm)); IPCB(skb)->iif = skb->dev->ifindex; IPCB(skb)->flags = IPSKB_FORWARDED; - return nf_flow_xmit_xfrm(skb, state, &rt->dst); + ret = nf_flow_xmit_xfrm(skb, state, &rt->dst); + break; + default: + WARN_ON_ONCE(1); + ret = NF_DROP; + break; } - skb->dev = outdev; - nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); - skb_dst_set_noref(skb, &rt->dst); - neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); - - return NF_STOLEN; + return ret; } EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); @@ -493,6 +502,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, struct net_device *outdev; struct ipv6hdr *ip6h; struct rt6_info *rt; + int ret; if (skb->protocol != htons(ETH_P_IPV6)) return NF_ACCEPT; @@ -536,18 +546,26 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); - if (unlikely(dst_xfrm(&rt->dst))) { + switch (tuplehash->tuple.xmit_type) { + case FLOW_OFFLOAD_XMIT_NEIGH: + skb->dev = outdev; + nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + ret = NF_STOLEN; + break; + case FLOW_OFFLOAD_XMIT_XFRM: memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->iif = skb->dev->ifindex; IP6CB(skb)->flags = IP6SKB_FORWARDED; - return nf_flow_xmit_xfrm(skb, state, &rt->dst); + ret = nf_flow_xmit_xfrm(skb, state, &rt->dst); + break; + default: + WARN_ON_ONCE(1); + ret = NF_DROP; + break; } - skb->dev = outdev; - nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); - skb_dst_set_noref(skb, &rt->dst); - neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); - - return NF_STOLEN; + return ret; } EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); From patchwork Thu Oct 15 01:16:23 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838365 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 F071FC433DF for ; Thu, 15 Oct 2020 01:16:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id AD6E222254 for ; Thu, 15 Oct 2020 01:16:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387673AbgJOBQ4 (ORCPT ); Wed, 14 Oct 2020 21:16:56 -0400 Received: from correo.us.es ([193.147.175.20]:38760 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1730878AbgJOBQr (ORCPT ); Wed, 14 Oct 2020 21:16:47 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id F2976DA7F0 for ; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id DAF9ADA78E for ; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id CF25DDA78B; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id BD930DA73F; Thu, 15 Oct 2020 03:16:40 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:40 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id 9563541FF201; Thu, 15 Oct 2020 03:16:40 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 2/9] net: resolve forwarding path from virtual netdevice and HW destination address Date: Thu, 15 Oct 2020 03:16:23 +0200 Message-Id: <20201015011630.2399-3-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org This patch adds dev_fill_forward_path() which resolves the path to reach the real netdevice from the IP forwarding step. This function takes as input the netdevice and the destination hardware address and it walks down over the devices calling .ndo_fill_forward_path() for each device until the real device is found. For instance, assuming the following topology: IP forwarding / \ br0 eth0 / \ eth1 eth2 . . . ethX ab:cd:ef:ab:cd:ef where eth1 and eth2 are bridge ports and eth0 provides WAN connectivity. ethX is the interface in another box which is connected to the eth1 bridge port. For packets in the IP forwarding step going to br0 whose destination MAC address is ab:cd:ef:ab:cd:ef, dev_fill_forward_path() provides the following path: br0 -> eth1 .ndo_fill_forward_path for br0 looks up at the FDB for the bridge port from the destination MAC address to get the bridge port eth1. This information allows to create a fast path to bypass the classic bridge and the IP forwarding path, so packets go directly from the bridge port eth1 to eth0 (wan interface) and vice versa. fast path .------------------------. / \ | IP forwarding | | / \ . | br0 eth0 . / \ -> eth1 eth2 . . . ethX ab:cd:ef:ab:cd:ef Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 27 +++++++++++++++++++++++++++ net/core/dev.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 964b494b0e8d..b77960621c27 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -833,6 +833,27 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); +enum net_device_path_type { + DEV_PATH_ETHERNET = 0, +}; + +struct net_device_path { + enum net_device_path_type type; + const struct net_device *dev; +}; + +#define NET_DEVICE_PATH_STACK_MAX 5 + +struct net_device_path_stack { + int num_paths; + struct net_device_path path[NET_DEVICE_PATH_STACK_MAX]; +}; + +struct net_device_path_ctx { + const struct net_device *dev; + const u8 *daddr; +}; + enum tc_setup_type { TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, @@ -1279,6 +1300,8 @@ struct netdev_net_notifier { * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); * If a device is paired with a peer device, return the peer instance. * The caller must be under RCU read context. + * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); + * Get the forwarding path to reach the real device from the HW destination address */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1487,6 +1510,8 @@ struct net_device_ops { int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); + int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, + struct net_device_path *path); }; /** @@ -2798,6 +2823,8 @@ void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); +int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, + struct net_device_path_stack *stack); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); diff --git a/net/core/dev.c b/net/core/dev.c index 751e5264fd49..51d820bb89d4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -845,6 +845,37 @@ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); +int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, + struct net_device_path_stack *stack) +{ + const struct net_device *last_dev; + struct net_device_path_ctx ctx; + struct net_device_path *path; + int ret = 0; + + memset(&ctx, 0, sizeof(ctx)); + ctx.dev = dev; + ctx.daddr = daddr; + + while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { + last_dev = ctx.dev; + + path = &stack->path[stack->num_paths++]; + ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); + if (ret < 0) + return -1; + + if (WARN_ON_ONCE(last_dev == ctx.dev)) + return -1; + } + path = &stack->path[stack->num_paths++]; + path->type = DEV_PATH_ETHERNET; + path->dev = ctx.dev; + + return ret; +} +EXPORT_SYMBOL_GPL(dev_fill_forward_path); + /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace From patchwork Thu Oct 15 01:16:24 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838359 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 0C8F9C433E7 for ; Thu, 15 Oct 2020 01:17:10 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C990B22257 for ; Thu, 15 Oct 2020 01:17:09 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1732050AbgJOBRJ (ORCPT ); Wed, 14 Oct 2020 21:17:09 -0400 Received: from correo.us.es ([193.147.175.20]:38756 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731379AbgJOBQq (ORCPT ); Wed, 14 Oct 2020 21:16:46 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id 7655FDA7F6 for ; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 5FDDBDA78C for ; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id 54F52DA73D; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 483C1DA72F; Thu, 15 Oct 2020 03:16:41 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:41 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id 1FEFE41FF201; Thu, 15 Oct 2020 03:16:41 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 3/9] net: 8021q: resolve forwarding path for vlan devices Date: Thu, 15 Oct 2020 03:16:24 +0200 Message-Id: <20201015011630.2399-4-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Add .ndo_fill_forward_path for vlan devices. For instance, assuming the following topology: IP forwarding / \ eth0.100 eth0 | eth0 . . . ethX ab:cd:ef:ab:cd:ef For packets in the IP forwarding going to eth0.100 whose destination MAC address is ab:cd:ef:ab:cd:ef, dev_fill_forward_path() provides the following path: eth0.100 -> eth0 Signed-off-by: Pablo Neira Ayuso Reported-by: kernel test robot --- include/linux/netdevice.h | 7 +++++++ net/8021q/vlan_dev.c | 15 +++++++++++++++ 2 files changed, 22 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b77960621c27..6a3370fafe4b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -835,11 +835,18 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, enum net_device_path_type { DEV_PATH_ETHERNET = 0, + DEV_PATH_VLAN, }; struct net_device_path { enum net_device_path_type type; const struct net_device *dev; + union { + struct { + __be16 id; + __be16 proto; + } vlan; + }; }; #define NET_DEVICE_PATH_STACK_MAX 5 diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ec8408d1638f..f06a507557f9 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -767,6 +767,20 @@ static int vlan_dev_get_iflink(const struct net_device *dev) return real_dev->ifindex; } +static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(ctx->dev); + + path->type = DEV_PATH_VLAN; + path->vlan.id = vlan->vlan_id; + path->vlan.proto = vlan->vlan_proto; + path->dev = ctx->dev; + ctx->dev = vlan->real_dev; + + return 0; +} + static const struct ethtool_ops vlan_ethtool_ops = { .get_link_ksettings = vlan_ethtool_get_link_ksettings, .get_drvinfo = vlan_ethtool_get_drvinfo, @@ -805,6 +819,7 @@ static const struct net_device_ops vlan_netdev_ops = { #endif .ndo_fix_features = vlan_dev_fix_features, .ndo_get_iflink = vlan_dev_get_iflink, + .ndo_fill_forward_path = vlan_dev_fill_forward_path, }; static void vlan_dev_free(struct net_device *dev) From patchwork Thu Oct 15 01:16:25 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838357 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 1B23DC43457 for ; Thu, 15 Oct 2020 01:17:12 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id CB78A22254 for ; Thu, 15 Oct 2020 01:17:11 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387603AbgJOBRK (ORCPT ); Wed, 14 Oct 2020 21:17:10 -0400 Received: from correo.us.es ([193.147.175.20]:38752 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731231AbgJOBQr (ORCPT ); Wed, 14 Oct 2020 21:16:47 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id E6421DA7F9 for ; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id D1A75DA78D for ; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id C72A1DA73F; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id CB5B0DA704; Thu, 15 Oct 2020 03:16:41 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:41 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id A294C41FF201; Thu, 15 Oct 2020 03:16:41 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 4/9] bridge: resolve forwarding path for bridge devices Date: Thu, 15 Oct 2020 03:16:25 +0200 Message-Id: <20201015011630.2399-5-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Add .ndo_fill_forward_path for bridge devices. Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 1 + net/bridge/br_device.c | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a3370fafe4b..e72fc9d23cd9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -836,6 +836,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, enum net_device_path_type { DEV_PATH_ETHERNET = 0, DEV_PATH_VLAN, + DEV_PATH_BRIDGE, }; struct net_device_path { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6f742fee874a..06046a35868d 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -391,6 +391,27 @@ static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) return br_del_if(br, slave_dev); } +static int br_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct net_bridge_fdb_entry *f; + struct net_bridge *br; + + if (netif_is_bridge_port(ctx->dev)) + return -1; + + br = netdev_priv(ctx->dev); + f = br_fdb_find_rcu(br, ctx->daddr, 0); + if (!f || !f->dst) + return -1; + + path->type = DEV_PATH_BRIDGE; + path->dev = f->dst->br->dev; + ctx->dev = f->dst->dev; + + return 0; +} + static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, @@ -425,6 +446,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_bridge_setlink = br_setlink, .ndo_bridge_dellink = br_dellink, .ndo_features_check = passthru_features_check, + .ndo_fill_forward_path = br_fill_forward_path, }; static struct device_type br_type = { From patchwork Thu Oct 15 01:16:26 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838367 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 158AAC43467 for ; Thu, 15 Oct 2020 01:17:14 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C66A522254 for ; Thu, 15 Oct 2020 01:17:13 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387719AbgJOBRM (ORCPT ); Wed, 14 Oct 2020 21:17:12 -0400 Received: from correo.us.es ([193.147.175.20]:38754 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731368AbgJOBQq (ORCPT ); Wed, 14 Oct 2020 21:16:46 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id 8E410DA7E5 for ; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 76D62DA78B for ; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id 69B26DA72F; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 5A6E4DA78A; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:42 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id 31AFE41FF201; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 5/9] netfilter: flowtable: use dev_fill_forward_path() to obtain ingress device Date: Thu, 15 Oct 2020 03:16:26 +0200 Message-Id: <20201015011630.2399-6-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org The ingress device in the tuple is obtained from route in the reply direction. Use dev_fill_forward_path() instead to provide the real ingress device for this flow. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 6 ++- net/netfilter/nf_flow_table_core.c | 3 +- net/netfilter/nft_flow_offload.c | 75 ++++++++++++++++++++++++++- 3 files changed, 80 insertions(+), 4 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 08e779f149ee..ecb84d4358cc 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -112,9 +112,10 @@ struct flow_offload_tuple { u8 l3proto; u8 l4proto; + + /* All members above are keys for lookups, see flow_offload_hash(). */ u8 dir; enum flow_offload_xmit_type xmit_type:8; - u16 mtu; struct dst_entry *dst_cache; @@ -160,6 +161,9 @@ static inline __s32 nf_flow_timeout_delta(unsigned int timeout) struct nf_flow_route { struct { + struct { + u32 ifindex; + } in; struct dst_entry *dst; } tuple[FLOW_OFFLOAD_DIR_MAX]; }; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 97f04f244961..66abc7f287a3 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -79,7 +79,6 @@ static int flow_offload_fill_route(struct flow_offload *flow, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *other_dst = route->tuple[!dir].dst; struct dst_entry *dst = route->tuple[dir].dst; if (!dst_hold_safe(route->tuple[dir].dst)) @@ -94,7 +93,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, break; } - flow_tuple->iifidx = other_dst->dev->ifindex; + flow_tuple->iifidx = route->tuple[dir].in.ifindex; if (dst_xfrm(dst)) flow_tuple->xmit_type = FLOW_OFFLOAD_XMIT_XFRM; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3a6c84fb2c90..4b476b0a3c88 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -19,6 +19,75 @@ struct nft_flow_offload { struct nft_flowtable *flowtable; }; +static int nft_dev_fill_forward_path(const struct nf_flow_route *route, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + struct net_device_path_stack *stack) +{ + const struct dst_entry *dst_cache = route->tuple[dir].dst; + const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; + unsigned char ha[ETH_ALEN]; + struct net_device *dev; + struct neighbour *n; + struct rtable *rt; + u8 nud_state; + + rt = (struct rtable *)dst_cache; + dev = rt->dst.dev; + + n = dst_neigh_lookup(dst_cache, daddr); + if (!n) + return -1; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(ha, n->ha); + read_unlock_bh(&n->lock); + neigh_release(n); + + if (!(nud_state & NUD_VALID)) + return -1; + + return dev_fill_forward_path(dev, ha, stack); +} + +struct nft_forward_info { + u32 iifindex; +}; + +static int nft_dev_forward_path(struct nf_flow_route *route, + const struct nf_conn *ct, + enum ip_conntrack_dir dir) +{ + struct net_device_path_stack stack = {}; + struct nft_forward_info info = {}; + struct net_device_path *path; + int i, ret; + + memset(&stack, 0, sizeof(stack)); + + ret = nft_dev_fill_forward_path(route, ct, dir, &stack); + if (ret < 0) + return -1; + + for (i = stack.num_paths - 1; i >= 0; i--) { + path = &stack.path[i]; + switch (path->type) { + case DEV_PATH_ETHERNET: + info.iifindex = path->dev->ifindex; + break; + case DEV_PATH_VLAN: + return -1; + case DEV_PATH_BRIDGE: + return -1; + } + } + + route->tuple[!dir].in.ifindex = info.iifindex; + + return 0; +} + static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, @@ -47,6 +116,10 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, route->tuple[dir].dst = this_dst; route->tuple[!dir].dst = other_dst; + if (nft_dev_forward_path(route, ct, IP_CT_DIR_ORIGINAL) < 0 || + nft_dev_forward_path(route, ct, IP_CT_DIR_REPLY) < 0) + return -ENOENT; + return 0; } @@ -74,8 +147,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; + struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; - struct nf_flow_route route; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; From patchwork Thu Oct 15 01:16:27 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838355 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 42799C433E7 for ; Thu, 15 Oct 2020 01:16:56 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 02F0122257 for ; Thu, 15 Oct 2020 01:16:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387626AbgJOBQx (ORCPT ); Wed, 14 Oct 2020 21:16:53 -0400 Received: from correo.us.es ([193.147.175.20]:38766 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1731355AbgJOBQq (ORCPT ); Wed, 14 Oct 2020 21:16:46 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id 0F6EADA800 for ; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id E98E3DA730 for ; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id DC9D5DA73D; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id D047CDA730; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:42 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id A71ED41FF201; Thu, 15 Oct 2020 03:16:42 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 6/9] netfilter: flowtable: use dev_fill_forward_path() to obtain egress device Date: Thu, 15 Oct 2020 03:16:27 +0200 Message-Id: <20201015011630.2399-7-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org The egress device in the tuple is obtained from route. Use dev_fill_forward_path() instead to provide the real ingress device for this flow whenever this is available. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 4 ++++ net/netfilter/nf_flow_table_core.c | 1 + net/netfilter/nf_flow_table_ip.c | 25 +++++++++++++++++++++++-- net/netfilter/nft_flow_offload.c | 1 + 4 files changed, 29 insertions(+), 2 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ecb84d4358cc..fe225e881cc7 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -117,6 +117,7 @@ struct flow_offload_tuple { u8 dir; enum flow_offload_xmit_type xmit_type:8; u16 mtu; + u32 oifidx; struct dst_entry *dst_cache; }; @@ -164,6 +165,9 @@ struct nf_flow_route { struct { u32 ifindex; } in; + struct { + u32 ifindex; + } out; struct dst_entry *dst; } tuple[FLOW_OFFLOAD_DIR_MAX]; }; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 66abc7f287a3..99f01f08c550 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -94,6 +94,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, } flow_tuple->iifidx = route->tuple[dir].in.ifindex; + flow_tuple->oifidx = route->tuple[dir].out.ifindex; if (dst_xfrm(dst)) flow_tuple->xmit_type = FLOW_OFFLOAD_XMIT_XFRM; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index e215c79e6777..92f444db8d9f 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -228,6 +228,15 @@ static int nf_flow_offload_dst_check(struct dst_entry *dst) return 0; } +static struct net_device *nf_flow_outdev_lookup(struct net *net, int oifidx, + struct net_device *dev) +{ + if (oifidx == dev->ifindex) + return dev; + + return dev_get_by_index_rcu(net, oifidx); +} + static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -267,7 +276,6 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; - outdev = rt->dst.dev; if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) return NF_ACCEPT; @@ -286,6 +294,13 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return NF_ACCEPT; } + outdev = nf_flow_outdev_lookup(state->net, tuplehash->tuple.oifidx, + rt->dst.dev); + if (!outdev) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) return NF_DROP; @@ -517,7 +532,6 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; - outdev = rt->dst.dev; if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) return NF_ACCEPT; @@ -533,6 +547,13 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return NF_ACCEPT; } + outdev = nf_flow_outdev_lookup(state->net, tuplehash->tuple.oifidx, + rt->dst.dev); + if (!outdev) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, sizeof(*ip6h))) return NF_DROP; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 4b476b0a3c88..6a6633e2ceeb 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -84,6 +84,7 @@ static int nft_dev_forward_path(struct nf_flow_route *route, } route->tuple[!dir].in.ifindex = info.iifindex; + route->tuple[dir].out.ifindex = info.iifindex; return 0; } From patchwork Thu Oct 15 01:16:28 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838361 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 DE32DC43457 for ; Thu, 15 Oct 2020 01:16:59 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 98AB522254 for ; Thu, 15 Oct 2020 01:16:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731854AbgJOBQ6 (ORCPT ); Wed, 14 Oct 2020 21:16:58 -0400 Received: from correo.us.es ([193.147.175.20]:38752 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387422AbgJOBQy (ORCPT ); Wed, 14 Oct 2020 21:16:54 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id 90074DA805 for ; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 7C30CDA78C for ; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id 7111FDA73F; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 54D14DA722; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:43 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id 2BD0741FF201; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 7/9] netfilter: flowtable: add direct xmit path Date: Thu, 15 Oct 2020 03:16:28 +0200 Message-Id: <20201015011630.2399-8-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Add FLOW_OFFLOAD_XMIT_DIRECT to turn on the direct dev_queue_xmit() path to transmit ethernet frames. Cache the source and destination hardware address for flow to use dev_queue_xmit() to transfer packets. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 5 +++++ net/netfilter/nf_flow_table_core.c | 2 ++ net/netfilter/nf_flow_table_ip.c | 24 ++++++++++++++++++++++++ net/netfilter/nft_flow_offload.c | 16 +++++++++++----- 4 files changed, 42 insertions(+), 5 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index fe225e881cc7..1b57d1d1270d 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -92,6 +92,7 @@ enum flow_offload_tuple_dir { enum flow_offload_xmit_type { FLOW_OFFLOAD_XMIT_NEIGH = 0, FLOW_OFFLOAD_XMIT_XFRM, + FLOW_OFFLOAD_XMIT_DIRECT, }; struct flow_offload_tuple { @@ -119,6 +120,8 @@ struct flow_offload_tuple { u16 mtu; u32 oifidx; + u8 h_source[ETH_ALEN]; + u8 h_dest[ETH_ALEN]; struct dst_entry *dst_cache; }; @@ -167,6 +170,8 @@ struct nf_flow_route { } in; struct { u32 ifindex; + u8 h_source[ETH_ALEN]; + u8 h_dest[ETH_ALEN]; } out; struct dst_entry *dst; } tuple[FLOW_OFFLOAD_DIR_MAX]; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 99f01f08c550..725366339b85 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -94,6 +94,8 @@ static int flow_offload_fill_route(struct flow_offload *flow, } flow_tuple->iifidx = route->tuple[dir].in.ifindex; + memcpy(flow_tuple->h_dest, route->tuple[dir].out.h_dest, ETH_ALEN); + memcpy(flow_tuple->h_source, route->tuple[dir].out.h_source, ETH_ALEN); flow_tuple->oifidx = route->tuple[dir].out.ifindex; if (dst_xfrm(dst)) diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 92f444db8d9f..1fa5c67cd914 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -247,6 +247,24 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } +static unsigned int nf_flow_queue_xmit(struct sk_buff *skb, + struct net_device *outdev, + const struct flow_offload_tuple *tuple) +{ + struct ethhdr *eth; + + skb->dev = outdev; + skb_push(skb, skb->mac_len); + skb_reset_mac_header(skb); + + eth = eth_hdr(skb); + memcpy(eth->h_source, tuple->h_source, ETH_ALEN); + memcpy(eth->h_dest, tuple->h_dest, ETH_ALEN); + dev_queue_xmit(skb); + + return NF_STOLEN; +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -325,6 +343,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, IPCB(skb)->flags = IPSKB_FORWARDED; ret = nf_flow_xmit_xfrm(skb, state, &rt->dst); break; + case FLOW_OFFLOAD_XMIT_DIRECT: + ret = nf_flow_queue_xmit(skb, outdev, &tuplehash->tuple); + break; default: WARN_ON_ONCE(1); ret = NF_DROP; @@ -581,6 +602,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, IP6CB(skb)->flags = IP6SKB_FORWARDED; ret = nf_flow_xmit_xfrm(skb, state, &rt->dst); break; + case FLOW_OFFLOAD_XMIT_DIRECT: + ret = nf_flow_queue_xmit(skb, outdev, &tuplehash->tuple); + break; default: WARN_ON_ONCE(1); ret = NF_DROP; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 6a6633e2ceeb..d440e436cb16 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -21,12 +21,11 @@ struct nft_flow_offload { static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct nf_conn *ct, - enum ip_conntrack_dir dir, + enum ip_conntrack_dir dir, u8 *dst, struct net_device_path_stack *stack) { const struct dst_entry *dst_cache = route->tuple[dir].dst; const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; - unsigned char ha[ETH_ALEN]; struct net_device *dev; struct neighbour *n; struct rtable *rt; @@ -41,18 +40,20 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, read_lock_bh(&n->lock); nud_state = n->nud_state; - ether_addr_copy(ha, n->ha); + ether_addr_copy(dst, n->ha); read_unlock_bh(&n->lock); neigh_release(n); if (!(nud_state & NUD_VALID)) return -1; - return dev_fill_forward_path(dev, ha, stack); + return dev_fill_forward_path(dev, dst, stack); } struct nft_forward_info { u32 iifindex; + u8 h_source[ETH_ALEN]; + u8 h_dest[ETH_ALEN]; }; static int nft_dev_forward_path(struct nf_flow_route *route, @@ -62,11 +63,12 @@ static int nft_dev_forward_path(struct nf_flow_route *route, struct net_device_path_stack stack = {}; struct nft_forward_info info = {}; struct net_device_path *path; + unsigned char dst[ETH_ALEN]; int i, ret; memset(&stack, 0, sizeof(stack)); - ret = nft_dev_fill_forward_path(route, ct, dir, &stack); + ret = nft_dev_fill_forward_path(route, ct, dir, dst, &stack); if (ret < 0) return -1; @@ -74,6 +76,8 @@ static int nft_dev_forward_path(struct nf_flow_route *route, path = &stack.path[i]; switch (path->type) { case DEV_PATH_ETHERNET: + memcpy(info.h_dest, path->dev->dev_addr, ETH_ALEN); + memcpy(info.h_source, dst, ETH_ALEN); info.iifindex = path->dev->ifindex; break; case DEV_PATH_VLAN: @@ -84,6 +88,8 @@ static int nft_dev_forward_path(struct nf_flow_route *route, } route->tuple[!dir].in.ifindex = info.iifindex; + memcpy(route->tuple[dir].out.h_dest, info.h_source, ETH_ALEN); + memcpy(route->tuple[dir].out.h_source, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.iifindex; return 0; From patchwork Thu Oct 15 01:16:29 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838369 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 D99ECC43457 for ; Thu, 15 Oct 2020 01:17:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 89ABC22254 for ; Thu, 15 Oct 2020 01:17:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1731940AbgJOBRC (ORCPT ); Wed, 14 Oct 2020 21:17:02 -0400 Received: from correo.us.es ([193.147.175.20]:38766 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387588AbgJOBQz (ORCPT ); Wed, 14 Oct 2020 21:16:55 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id E7A56DA7EA for ; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id D2D94DA78A for ; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id C8A29DA730; Thu, 15 Oct 2020 03:16:45 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id C7FF1DA789; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:43 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id 9F66F41FF201; Thu, 15 Oct 2020 03:16:43 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 8/9] netfilter: flowtable: bridge port support Date: Thu, 15 Oct 2020 03:16:29 +0200 Message-Id: <20201015011630.2399-9-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Update hardware destination address to the master bridge device to emulate the forwarding behaviour. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 1 + net/netfilter/nf_flow_table_core.c | 4 ++++ net/netfilter/nft_flow_offload.c | 6 +++++- 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 1b57d1d1270d..4ec3f9bb2f32 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -172,6 +172,7 @@ struct nf_flow_route { u32 ifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; + enum flow_offload_xmit_type xmit_type; } out; struct dst_entry *dst; } tuple[FLOW_OFFLOAD_DIR_MAX]; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 725366339b85..e80dcabe3668 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -100,6 +100,10 @@ static int flow_offload_fill_route(struct flow_offload *flow, if (dst_xfrm(dst)) flow_tuple->xmit_type = FLOW_OFFLOAD_XMIT_XFRM; + else + flow_tuple->xmit_type = route->tuple[dir].out.xmit_type; + + flow_tuple->dst_cache = dst; flow_tuple->dst_cache = dst; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index d440e436cb16..9efb5d584290 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -54,6 +54,7 @@ struct nft_forward_info { u32 iifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; + enum flow_offload_xmit_type xmit_type; }; static int nft_dev_forward_path(struct nf_flow_route *route, @@ -83,7 +84,9 @@ static int nft_dev_forward_path(struct nf_flow_route *route, case DEV_PATH_VLAN: return -1; case DEV_PATH_BRIDGE: - return -1; + memcpy(info.h_dest, path->dev->dev_addr, ETH_ALEN); + info.xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; + break; } } @@ -91,6 +94,7 @@ static int nft_dev_forward_path(struct nf_flow_route *route, memcpy(route->tuple[dir].out.h_dest, info.h_source, ETH_ALEN); memcpy(route->tuple[dir].out.h_source, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.iifindex; + route->tuple[dir].out.xmit_type = info.xmit_type; return 0; } From patchwork Thu Oct 15 01:16:30 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Pablo Neira Ayuso X-Patchwork-Id: 11838371 X-Patchwork-Delegate: kuba@kernel.org 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=-12.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,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 B3C22C433E7 for ; Thu, 15 Oct 2020 01:17:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 704C322257 for ; Thu, 15 Oct 2020 01:17:27 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387747AbgJOBR0 (ORCPT ); Wed, 14 Oct 2020 21:17:26 -0400 Received: from correo.us.es ([193.147.175.20]:38754 "EHLO mail.us.es" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387621AbgJOBQ4 (ORCPT ); Wed, 14 Oct 2020 21:16:56 -0400 Received: from antivirus1-rhel7.int (unknown [192.168.2.11]) by mail.us.es (Postfix) with ESMTP id CB507DA7F2 for ; Thu, 15 Oct 2020 03:16:46 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id B1655DA78A for ; Thu, 15 Oct 2020 03:16:46 +0200 (CEST) Received: by antivirus1-rhel7.int (Postfix, from userid 99) id A6BF0DA73D; Thu, 15 Oct 2020 03:16:46 +0200 (CEST) Received: from antivirus1-rhel7.int (localhost [127.0.0.1]) by antivirus1-rhel7.int (Postfix) with ESMTP id 5032CDA704; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) Received: from 192.168.1.97 (192.168.1.97) by antivirus1-rhel7.int (F-Secure/fsigk_smtp/550/antivirus1-rhel7.int); Thu, 15 Oct 2020 03:16:44 +0200 (CEST) X-Virus-Status: clean(F-Secure/fsigk_smtp/550/antivirus1-rhel7.int) Received: from localhost.localdomain (unknown [90.77.255.23]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: pneira@us.es) by entrada.int (Postfix) with ESMTPSA id 2651441FF201; Thu, 15 Oct 2020 03:16:44 +0200 (CEST) X-SMTPAUTHUS: auth mail.us.es From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH net-next 9/9] netfilter: flowtable: add vlan support Date: Thu, 15 Oct 2020 03:16:30 +0200 Message-Id: <20201015011630.2399-10-pablo@netfilter.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20201015011630.2399-1-pablo@netfilter.org> References: <20201015011630.2399-1-pablo@netfilter.org> MIME-Version: 1.0 X-Virus-Scanned: ClamAV using ClamSMTP Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org Add the vlan id and proto to the flow tuple to uniquely identify flows from the receive path. Store the vlan id and proto to set it accordingly from the transmit path. This patch includes support for two VLAN headers (Q-in-Q). Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 21 +++- net/netfilter/nf_flow_table_core.c | 13 +++ net/netfilter/nf_flow_table_ip.c | 148 ++++++++++++++++++++++---- net/netfilter/nft_flow_offload.c | 23 +++- 4 files changed, 184 insertions(+), 21 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 4ec3f9bb2f32..ed7a610d10bc 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -95,6 +95,8 @@ enum flow_offload_xmit_type { FLOW_OFFLOAD_XMIT_DIRECT, }; +#define NF_FLOW_TABLE_VLAN_MAX 2 + struct flow_offload_tuple { union { struct in_addr src_v4; @@ -113,13 +115,24 @@ struct flow_offload_tuple { u8 l3proto; u8 l4proto; + struct { + u16 id; + __be16 proto; + } in_vlan[NF_FLOW_TABLE_VLAN_MAX]; /* All members above are keys for lookups, see flow_offload_hash(). */ u8 dir; - enum flow_offload_xmit_type xmit_type:8; + enum flow_offload_xmit_type xmit_type:6, + in_vlan_num:2; u16 mtu; u32 oifidx; + struct { + u16 id; + __be16 proto; + } out_vlan[NF_FLOW_TABLE_VLAN_MAX]; + u8 out_vlan_num; + u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; struct dst_entry *dst_cache; @@ -167,11 +180,17 @@ struct nf_flow_route { struct { struct { u32 ifindex; + u16 vid[NF_FLOW_TABLE_VLAN_MAX]; + __be16 vproto[NF_FLOW_TABLE_VLAN_MAX]; + u8 num_vlans; } in; struct { u32 ifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; + u16 vid[NF_FLOW_TABLE_VLAN_MAX]; + __be16 vproto[NF_FLOW_TABLE_VLAN_MAX]; + u8 num_vlans; enum flow_offload_xmit_type xmit_type; } out; struct dst_entry *dst; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index e80dcabe3668..c486c9b489e0 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -80,6 +80,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; struct dst_entry *dst = route->tuple[dir].dst; + int i; if (!dst_hold_safe(route->tuple[dir].dst)) return -1; @@ -98,6 +99,18 @@ static int flow_offload_fill_route(struct flow_offload *flow, memcpy(flow_tuple->h_source, route->tuple[dir].out.h_source, ETH_ALEN); flow_tuple->oifidx = route->tuple[dir].out.ifindex; + for (i = 0; i < route->tuple[dir].in.num_vlans; i++) { + flow_tuple->in_vlan[i].id = route->tuple[dir].in.vid[i]; + flow_tuple->in_vlan[i].proto = route->tuple[dir].in.vproto[i]; + } + flow_tuple->in_vlan_num = route->tuple[dir].in.num_vlans; + + for (i = 0; i < route->tuple[dir].out.num_vlans; i++) { + flow_tuple->out_vlan[i].id = route->tuple[dir].out.vid[i]; + flow_tuple->out_vlan[i].proto = route->tuple[dir].out.vproto[i]; + } + flow_tuple->out_vlan_num = route->tuple[dir].out.num_vlans; + if (dst_xfrm(dst)) flow_tuple->xmit_type = FLOW_OFFLOAD_XMIT_XFRM; else diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 1fa5c67cd914..f2d7ba6aad3c 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -159,17 +159,35 @@ static bool ip_has_options(unsigned int thoff) return thoff != sizeof(struct iphdr); } +static void nf_flow_tuple_vlan(struct sk_buff *skb, + struct flow_offload_tuple *tuple) +{ + if (skb_vlan_tag_present(skb)) { + tuple->in_vlan[0].id = skb_vlan_tag_get(skb); + tuple->in_vlan[0].proto = skb->vlan_proto; + } + if (skb->protocol == ntohs(ETH_P_8021Q)) { + struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb_mac_header(skb); + + tuple->in_vlan[1].id = ntohs(veth->h_vlan_TCI); + tuple->in_vlan[1].proto = skb->protocol; + } +} + static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, struct flow_offload_tuple *tuple) { - unsigned int thoff, hdrsize; + unsigned int thoff, hdrsize, offset = 0; struct flow_ports *ports; struct iphdr *iph; - if (!pskb_may_pull(skb, sizeof(*iph))) + if (skb->protocol == ntohs(ETH_P_8021Q)) + offset += VLAN_HLEN; + + if (!pskb_may_pull(skb, sizeof(*iph) + offset)) return -1; - iph = ip_hdr(skb); + iph = (struct iphdr *)(skb_network_header(skb) + offset); thoff = iph->ihl * 4; if (ip_is_fragment(iph) || @@ -191,11 +209,11 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, return -1; thoff = iph->ihl * 4; - if (!pskb_may_pull(skb, thoff + hdrsize)) + if (!pskb_may_pull(skb, thoff + hdrsize + offset)) return -1; - iph = ip_hdr(skb); - ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + iph = (struct iphdr *)(skb_network_header(skb) + offset); + ports = (struct flow_ports *)(skb_network_header(skb) + thoff + offset); tuple->src_v4.s_addr = iph->saddr; tuple->dst_v4.s_addr = iph->daddr; @@ -204,6 +222,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, tuple->l3proto = AF_INET; tuple->l4proto = iph->protocol; tuple->iifidx = dev->ifindex; + nf_flow_tuple_vlan(skb, tuple); return 0; } @@ -247,6 +266,67 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } +static bool nf_flow_skb_vlan_protocol(const struct sk_buff *skb, __be16 proto) +{ + if (skb->protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veth; + + veth = (struct vlan_ethhdr *)skb_mac_header(skb); + if (veth->h_vlan_encapsulated_proto == proto) + return true; + } + + return false; +} + +static void nf_flow_vlan_pop(struct sk_buff *skb, + struct flow_offload_tuple_rhash *tuplehash) +{ + struct vlan_hdr *vlan_hdr; + int i; + + for (i = 0; i < tuplehash->tuple.in_vlan_num; i++) { + if (skb_vlan_tag_present(skb)) { + __vlan_hwaccel_clear_tag(skb); + continue; + } + vlan_hdr = (struct vlan_hdr *)skb->data; + __skb_pull(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vlan_hdr); + skb_reset_network_header(skb); + } +} + +static int __nf_flow_vlan_push(struct sk_buff *skb, + const struct flow_offload_tuple *tuple) +{ + int i; + + for (i = tuple->out_vlan_num - 1; i >= 0; i--) { + if (skb_vlan_push(skb, tuple->out_vlan[i].proto, + tuple->out_vlan[i].id) < 0) + return -1; + } + + return 0; +} + +static int nf_flow_vlan_push(struct sk_buff *skb, + const struct flow_offload_tuple *tuple) +{ + if (tuple->out_vlan_num > 1) + skb_push(skb, skb->mac_len); + + __nf_flow_vlan_push(skb, tuple); + + if (tuple->out_vlan_num > 1) { + __skb_pull(skb, skb->mac_len - VLAN_HLEN); + skb_reset_network_header(skb); + } + + return 0; +} + static unsigned int nf_flow_queue_xmit(struct sk_buff *skb, struct net_device *outdev, const struct flow_offload_tuple *tuple) @@ -257,6 +337,10 @@ static unsigned int nf_flow_queue_xmit(struct sk_buff *skb, skb_push(skb, skb->mac_len); skb_reset_mac_header(skb); + if (tuple->out_vlan_num > 0 && + __nf_flow_vlan_push(skb, tuple) < 0) + return NF_DROP; + eth = eth_hdr(skb); memcpy(eth->h_source, tuple->h_source, ETH_ALEN); memcpy(eth->h_dest, tuple->h_dest, ETH_ALEN); @@ -279,9 +363,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, unsigned int thoff; struct iphdr *iph; __be32 nexthop; + u32 offset = 0; int ret; - if (skb->protocol != htons(ETH_P_IP)) + if (skb->protocol != htons(ETH_P_IP) && + !nf_flow_skb_vlan_protocol(skb, htons(ETH_P_IP))) return NF_ACCEPT; if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) @@ -298,11 +384,15 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) return NF_ACCEPT; - if (skb_try_make_writable(skb, sizeof(*iph))) + if (skb->protocol == ntohs(ETH_P_8021Q)) + offset += VLAN_HLEN; + + if (skb_try_make_writable(skb, sizeof(*iph) + offset)) return NF_DROP; - thoff = ip_hdr(skb)->ihl * 4; - if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) + iph = (struct iphdr *)(skb_network_header(skb) + offset); + thoff = (iph->ihl * 4) + offset; + if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; flow_offload_refresh(flow_table, flow); @@ -319,6 +409,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return NF_ACCEPT; } + nf_flow_vlan_pop(skb, tuplehash); + thoff -= offset; + if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) return NF_DROP; @@ -331,6 +424,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: + if (nf_flow_vlan_push(skb, &tuplehash->tuple) < 0) + return NF_DROP; + skb->dev = outdev; nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); skb_dst_set_noref(skb, &rt->dst); @@ -484,14 +580,17 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow, static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, struct flow_offload_tuple *tuple) { - unsigned int thoff, hdrsize; + unsigned int thoff, hdrsize, offset = 0; struct flow_ports *ports; struct ipv6hdr *ip6h; - if (!pskb_may_pull(skb, sizeof(*ip6h))) + if (skb->protocol == ntohs(ETH_P_8021Q)) + offset += VLAN_HLEN; + + if (!pskb_may_pull(skb, sizeof(*ip6h) + offset)) return -1; - ip6h = ipv6_hdr(skb); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); switch (ip6h->nexthdr) { case IPPROTO_TCP: @@ -508,11 +607,11 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, return -1; thoff = sizeof(*ip6h); - if (!pskb_may_pull(skb, thoff + hdrsize)) + if (!pskb_may_pull(skb, thoff + hdrsize + offset)) return -1; - ip6h = ipv6_hdr(skb); - ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); + ports = (struct flow_ports *)(skb_network_header(skb) + thoff + offset); tuple->src_v6 = ip6h->saddr; tuple->dst_v6 = ip6h->daddr; @@ -521,6 +620,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, tuple->l3proto = AF_INET6; tuple->l4proto = ip6h->nexthdr; tuple->iifidx = dev->ifindex; + nf_flow_tuple_vlan(skb, tuple); return 0; } @@ -538,9 +638,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, struct net_device *outdev; struct ipv6hdr *ip6h; struct rt6_info *rt; + u32 offset = 0; int ret; - if (skb->protocol != htons(ETH_P_IPV6)) + if (skb->protocol != htons(ETH_P_IPV6) && + !nf_flow_skb_vlan_protocol(skb, htons(ETH_P_IPV6))) return NF_ACCEPT; if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) @@ -557,8 +659,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) return NF_ACCEPT; - if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb, - sizeof(*ip6h))) + if (skb->protocol == ntohs(ETH_P_8021Q)) + offset += VLAN_HLEN; + + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); + if (nf_flow_state_check(flow, ip6h->nexthdr, skb, sizeof(*ip6h))) return NF_ACCEPT; flow_offload_refresh(flow_table, flow); @@ -575,6 +680,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return NF_ACCEPT; } + nf_flow_vlan_pop(skb, tuplehash); + if (skb_try_make_writable(skb, sizeof(*ip6h))) return NF_DROP; @@ -590,6 +697,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: + if (nf_flow_vlan_push(skb, &tuplehash->tuple) < 0) + return NF_DROP; + skb->dev = outdev; nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); skb_dst_set_noref(skb, &rt->dst); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 9efb5d584290..17117893cb8c 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -51,6 +51,9 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, } struct nft_forward_info { + __be16 vid[NF_FLOW_TABLE_VLAN_MAX]; + __be16 vproto[NF_FLOW_TABLE_VLAN_MAX]; + u8 num_vlans; u32 iifindex; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; @@ -82,7 +85,13 @@ static int nft_dev_forward_path(struct nf_flow_route *route, info.iifindex = path->dev->ifindex; break; case DEV_PATH_VLAN: - return -1; + if (info.num_vlans >= NF_FLOW_TABLE_VLAN_MAX) + return -1; + + info.vid[info.num_vlans] = path->vlan.id; + info.vproto[info.num_vlans] = path->vlan.proto; + info.num_vlans++; + break; case DEV_PATH_BRIDGE: memcpy(info.h_dest, path->dev->dev_addr, ETH_ALEN); info.xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; @@ -96,6 +105,18 @@ static int nft_dev_forward_path(struct nf_flow_route *route, route->tuple[dir].out.ifindex = info.iifindex; route->tuple[dir].out.xmit_type = info.xmit_type; + for (i = 0; i < info.num_vlans; i++) { + route->tuple[!dir].in.vid[i] = info.vid[i]; + route->tuple[!dir].in.vproto[i] = info.vproto[i]; + } + route->tuple[!dir].in.num_vlans = info.num_vlans; + + for (i = 0; i < info.num_vlans; i++) { + route->tuple[dir].out.vid[i] = info.vid[i]; + route->tuple[dir].out.vproto[i] = info.vproto[i]; + } + route->tuple[dir].out.num_vlans = info.num_vlans; + return 0; }