From patchwork Tue Dec 22 16:20:34 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jesper Dangaard Brouer X-Patchwork-Id: 346898 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=-20.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, MENTIONS_GIT_HOSTING, SPF_HELO_NONE, SPF_PASS 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 257DDC433E6 for ; Tue, 22 Dec 2020 16:22:15 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id DAF64229C6 for ; Tue, 22 Dec 2020 16:22:14 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727985AbgLVQWO (ORCPT ); Tue, 22 Dec 2020 11:22:14 -0500 Received: from us-smtp-delivery-124.mimecast.com ([63.128.21.124]:40120 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727785AbgLVQWN (ORCPT ); Tue, 22 Dec 2020 11:22:13 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1608654047; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Z+tbcl4L04NWTojo+MJYMqV/uyN9LUn9rWpBUllzfzo=; b=fVJn3dEgBJ+E70Cq8hgSD7Qb+nIjShdwUjKssipbgdxjVIyGPGMQCNt9yc1yNi5TFE34WO OdBJixk7BDoYCMbYklOon2c0+Q2g3P1h+7qx6DE4gteOzHMqDmGTKHGPrMCdh5Bwybjjeo GBnSk8HqnHObn+iQpdrdtHj5cXzfVWg= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-550-CCpAyrEOM4K7Xva1bcOhUg-1; Tue, 22 Dec 2020 11:20:43 -0500 X-MC-Unique: CCpAyrEOM4K7Xva1bcOhUg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 1853A107ACE3; Tue, 22 Dec 2020 16:20:41 +0000 (UTC) Received: from firesoul.localdomain (unknown [10.40.208.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id C9BD05E1A4; Tue, 22 Dec 2020 16:20:35 +0000 (UTC) Received: from [192.168.42.3] (localhost [IPv6:::1]) by firesoul.localdomain (Postfix) with ESMTP id A015332138455; Tue, 22 Dec 2020 17:20:34 +0100 (CET) Subject: [PATCH bpf-next V10 1/7] bpf: Remove MTU check in __bpf_skb_max_len From: Jesper Dangaard Brouer To: bpf@vger.kernel.org Cc: Jesper Dangaard Brouer , netdev@vger.kernel.org, Daniel Borkmann , Alexei Starovoitov , maze@google.com, lmb@cloudflare.com, shaun@tigera.io, Lorenzo Bianconi , marek@cloudflare.com, John Fastabend , Jakub Kicinski , eyal.birger@gmail.com, colrack@gmail.com Date: Tue, 22 Dec 2020 17:20:34 +0100 Message-ID: <160865403459.3593456.4223063693967710846.stgit@firesoul> In-Reply-To: <160865400291.3593456.17026136957003358677.stgit@firesoul> References: <160865400291.3593456.17026136957003358677.stgit@firesoul> User-Agent: StGit/0.19 MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Multiple BPF-helpers that can manipulate/increase the size of the SKB uses __bpf_skb_max_len() as the max-length. This function limit size against the current net_device MTU (skb->dev->mtu). When a BPF-prog grow the packet size, then it should not be limited to the MTU. The MTU is a transmit limitation, and software receiving this packet should be allowed to increase the size. Further more, current MTU check in __bpf_skb_max_len uses the MTU from ingress/current net_device, which in case of redirects uses the wrong net_device. This patch keeps a sanity max limit of SKB_MAX_ALLOC (16KiB). The real limit is elsewhere in the system. Jesper's testing[1] showed it was not possible to exceed 8KiB when expanding the SKB size via BPF-helper. The limiting factor is the define KMALLOC_MAX_CACHE_SIZE which is 8192 for SLUB-allocator (CONFIG_SLUB) in-case PAGE_SIZE is 4096. This define is in-effect due to this being called from softirq context see code __gfp_pfmemalloc_flags() and __do_kmalloc_node(). Jakub's testing showed that frames above 16KiB can cause NICs to reset (but not crash). Keep this sanity limit at this level as memory layer can differ based on kernel config. [1] https://github.com/xdp-project/bpf-examples/tree/master/MTU-tests V3: replace __bpf_skb_max_len() with define and use IPv6 max MTU size. Signed-off-by: Jesper Dangaard Brouer --- net/core/filter.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 255aeee72402..f8f198252ff2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3552,11 +3552,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, return 0; } -static u32 __bpf_skb_max_len(const struct sk_buff *skb) -{ - return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : - SKB_MAX_ALLOC; -} +#define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) @@ -3605,7 +3601,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); - u32 len_max = __bpf_skb_max_len(skb); + u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; @@ -3688,7 +3684,7 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; @@ -3764,7 +3760,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = { static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; From patchwork Tue Dec 22 16:20:44 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jesper Dangaard Brouer X-Patchwork-Id: 346897 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=-15.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED 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 C1BAFC433E6 for ; Tue, 22 Dec 2020 16:22:24 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 94E4A229C6 for ; Tue, 22 Dec 2020 16:22:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728007AbgLVQWY (ORCPT ); Tue, 22 Dec 2020 11:22:24 -0500 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:31425 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727971AbgLVQWX (ORCPT ); Tue, 22 Dec 2020 11:22:23 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1608654056; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=z8eZuV4Imsfk3Jy4IdoIcXPttP3NfxyIc0y3hORRqsQ=; b=RGUs1XTpmEt4Yuezz9uQDnZSRABd38cOztc5BscW777Mh6N67vmlMfC+79ODcdzI/dumZO bLFSDBAW3G9yTup5MvqZ0A9NYRKgGKP71ouwh22DXI9rxBaTEhlz4tX6mMLuXXG1rzpUvN n9mJ/l5GLJjoOBYNgdUg8qD+ZI3+rao= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-379-QDuIU2VAOxupNb7_gMpscw-1; Tue, 22 Dec 2020 11:20:51 -0500 X-MC-Unique: QDuIU2VAOxupNb7_gMpscw-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 82647180E469; Tue, 22 Dec 2020 16:20:49 +0000 (UTC) Received: from firesoul.localdomain (unknown [10.40.208.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id C8E1910013C1; Tue, 22 Dec 2020 16:20:45 +0000 (UTC) Received: from [192.168.42.3] (localhost [IPv6:::1]) by firesoul.localdomain (Postfix) with ESMTP id C62F132138455; Tue, 22 Dec 2020 17:20:44 +0100 (CET) Subject: [PATCH bpf-next V10 3/7] bpf: bpf_fib_lookup return MTU value as output when looked up From: Jesper Dangaard Brouer To: bpf@vger.kernel.org Cc: Jesper Dangaard Brouer , netdev@vger.kernel.org, Daniel Borkmann , Alexei Starovoitov , maze@google.com, lmb@cloudflare.com, shaun@tigera.io, Lorenzo Bianconi , marek@cloudflare.com, John Fastabend , Jakub Kicinski , eyal.birger@gmail.com, colrack@gmail.com Date: Tue, 22 Dec 2020 17:20:44 +0100 Message-ID: <160865404473.3593456.12027262817547996261.stgit@firesoul> In-Reply-To: <160865400291.3593456.17026136957003358677.stgit@firesoul> References: <160865400291.3593456.17026136957003358677.stgit@firesoul> User-Agent: StGit/0.19 MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup) can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog don't know the MTU value that caused this rejection. If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it need to know this MTU value for the ICMP packet. Patch change lookup and result struct bpf_fib_lookup, to contain this MTU value as output via a union with 'tot_len' as this is the value used for the MTU lookup. V5: - Fixed uninit value spotted by Dan Carpenter. - Name struct output member mtu_result Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Jesper Dangaard Brouer --- include/uapi/linux/bpf.h | 11 +++++++++-- net/core/filter.c | 22 +++++++++++++++------- tools/include/uapi/linux/bpf.h | 11 +++++++++-- 3 files changed, 33 insertions(+), 11 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 77d7c1bb2923..649586d656b6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2225,6 +2225,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4975,9 +4978,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ diff --git a/net/core/filter.c b/net/core/filter.c index c1e460193bae..db59ab55572c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5268,12 +5268,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, const struct neighbour *neigh, - const struct net_device *dev) + const struct net_device *dev, u32 mtu) { memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + if (mtu) + params->mtu_result = mtu; /* union with tot_len */ return 0; } @@ -5289,8 +5291,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct net_device *dev; struct fib_result res; struct flowi4 fl4; + u32 mtu = 0; int err; - u32 mtu; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -5357,8 +5359,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } nhc = res.nhc; @@ -5392,7 +5396,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5409,7 +5413,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct flowi6 fl6; int strict = 0; int oif, err; - u32 mtu; + u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) @@ -5484,8 +5488,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } if (res.nh->fib_nh_lws) @@ -5505,7 +5511,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5581,6 +5587,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; + + params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 77d7c1bb2923..649586d656b6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2225,6 +2225,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4975,9 +4978,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ From patchwork Tue Dec 22 16:20:54 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jesper Dangaard Brouer X-Patchwork-Id: 346896 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=-15.8 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS 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 6E62AC433E6 for ; Tue, 22 Dec 2020 16:22:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 4096223124 for ; Tue, 22 Dec 2020 16:22:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728038AbgLVQWa (ORCPT ); Tue, 22 Dec 2020 11:22:30 -0500 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:39914 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727764AbgLVQWa (ORCPT ); Tue, 22 Dec 2020 11:22:30 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1608654063; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=mEjCQsN6h65UaNIHKyPdAxgFvABSUmSKRgsC4iWP3iI=; b=ZbVokM1j+MqDx9MwbO2vEhPzRU4iNzFwUi6TegSyCIcxbeqMGUdqq5t/INe+bBatSfcVAC TtXGtvDLwLqiJVOJuob+BAqSysJsGc57cv3ZQwsAes9cyAJgZYQVnOo1d0xHUtuGjzRyQX Ev+Lgi7OTiyxEVeG02hpyqQCPsm/JY0= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-521-IDDNt4fnN2mK8-L_OLSe5Q-1; Tue, 22 Dec 2020 11:20:59 -0500 X-MC-Unique: IDDNt4fnN2mK8-L_OLSe5Q-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id B54B8180E461; Tue, 22 Dec 2020 16:20:56 +0000 (UTC) Received: from firesoul.localdomain (unknown [10.40.208.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id 0C7336062F; Tue, 22 Dec 2020 16:20:56 +0000 (UTC) Received: from [192.168.42.3] (localhost [IPv6:::1]) by firesoul.localdomain (Postfix) with ESMTP id EFDB832138458; Tue, 22 Dec 2020 17:20:54 +0100 (CET) Subject: [PATCH bpf-next V10 5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress From: Jesper Dangaard Brouer To: bpf@vger.kernel.org Cc: Jesper Dangaard Brouer , netdev@vger.kernel.org, Daniel Borkmann , Alexei Starovoitov , maze@google.com, lmb@cloudflare.com, shaun@tigera.io, Lorenzo Bianconi , marek@cloudflare.com, John Fastabend , Jakub Kicinski , eyal.birger@gmail.com, colrack@gmail.com Date: Tue, 22 Dec 2020 17:20:54 +0100 Message-ID: <160865405490.3593456.308516388598061580.stgit@firesoul> In-Reply-To: <160865400291.3593456.17026136957003358677.stgit@firesoul> References: <160865400291.3593456.17026136957003358677.stgit@firesoul> User-Agent: StGit/0.19 MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.11 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org The use-case for dropping the MTU check when TC-BPF does redirect to ingress, is described by Eyal Birger in email[0]. The summary is the ability to increase packet size (e.g. with IPv6 headers for NAT64) and ingress redirect packet and let normal netstack fragment packet as needed. [0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/ V9: - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect V4: - Keep net_device "up" (IFF_UP) check. - Adjustment to handle bpf_redirect_peer() helper Signed-off-by: Jesper Dangaard Brouer --- include/linux/netdevice.h | 31 +++++++++++++++++++++++++++++-- net/core/dev.c | 19 ++----------------- net/core/filter.c | 14 +++++++++++--- 3 files changed, 42 insertions(+), 22 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7bf167993c05..4c78f73db1ec 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3947,11 +3947,38 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); +static __always_inline bool __is_skb_forwardable(const struct net_device *dev, + const struct sk_buff *skb, + const bool check_mtu) +{ + const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + if (!check_mtu) + return true; + + len = dev->mtu + dev->hard_header_len + vlan_hdr_len; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} + static __always_inline int ____dev_forward_skb(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { + unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; diff --git a/net/core/dev.c b/net/core/dev.c index a46334906c94..ffead13c158f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2176,28 +2176,13 @@ static inline void net_timestamp_set(struct sk_buff *skb) bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { - unsigned int len; - - if (!(dev->flags & IFF_UP)) - return false; - - len = dev->mtu + dev->hard_header_len + VLAN_HLEN; - if (skb->len <= len) - return true; - - /* if TSO is enabled, we don't care about the length as the packet - * could be forwarded without being segmented before - */ - if (skb_is_gso(skb)) - return true; - - return false; + return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - int ret = ____dev_forward_skb(dev, skb); + int ret = ____dev_forward_skb(dev, skb, true); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); diff --git a/net/core/filter.c b/net/core/filter.c index 3f2e593244ca..1908800b671c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2083,13 +2083,21 @@ static const struct bpf_func_proto bpf_csum_level_proto = { static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { - return dev_forward_skb(dev, skb); + int ret = ____dev_forward_skb(dev, skb, false); + + if (likely(!ret)) { + skb->protocol = eth_type_trans(skb, dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + ret = netif_rx(skb); + } + + return ret; } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { - int ret = ____dev_forward_skb(dev, skb); + int ret = ____dev_forward_skb(dev, skb, false); if (likely(!ret)) { skb->dev = dev; @@ -2480,7 +2488,7 @@ int skb_do_redirect(struct sk_buff *skb) goto out_drop; dev = ops->ndo_get_peer_dev(dev); if (unlikely(!dev || - !is_skb_forwardable(dev, skb) || + !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; From patchwork Tue Dec 22 16:21:05 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jesper Dangaard Brouer X-Patchwork-Id: 346895 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=-13.0 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER, INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, UNWANTED_LANGUAGE_BODY 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 6337EC433E0 for ; Tue, 22 Dec 2020 16:22:42 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 31D6523103 for ; Tue, 22 Dec 2020 16:22:42 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728059AbgLVQWl (ORCPT ); Tue, 22 Dec 2020 11:22:41 -0500 Received: from us-smtp-delivery-124.mimecast.com ([63.128.21.124]:42083 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727795AbgLVQWl (ORCPT ); Tue, 22 Dec 2020 11:22:41 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1608654073; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=yR/LlUOCBQ9jzBVvgoleDX6ifWEJpGJ3XGa9uTr+O9c=; b=C9KjYlhMoD2uxeUvB9tCnYRRUW/LuYkkr7akTCnCcrkBWNDwRYBQS4FezcxHJTIYvZVu3e 2BF4gYPTEm2U4+mv5QzAnbjh9rEKgNCbBt7DSAYPQr5uC1vGJ6DSUVsn4IBYYTU9AsoXhN KYScbuKVX69Yzy6lNCUetgGtwPcFKyA= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-274-d5wovaT4M5iIbGYcUW5Nzg-1; Tue, 22 Dec 2020 11:21:09 -0500 X-MC-Unique: d5wovaT4M5iIbGYcUW5Nzg-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 0134EC7403; Tue, 22 Dec 2020 16:21:07 +0000 (UTC) Received: from firesoul.localdomain (unknown [10.40.208.19]) by smtp.corp.redhat.com (Postfix) with ESMTP id 4362E6F447; Tue, 22 Dec 2020 16:21:06 +0000 (UTC) Received: from [192.168.42.3] (localhost [IPv6:::1]) by firesoul.localdomain (Postfix) with ESMTP id 1D92B32138458; Tue, 22 Dec 2020 17:21:05 +0100 (CET) Subject: [PATCH bpf-next V10 7/7] bpf/selftests: tests using bpf_check_mtu BPF-helper From: Jesper Dangaard Brouer To: bpf@vger.kernel.org Cc: Jesper Dangaard Brouer , netdev@vger.kernel.org, Daniel Borkmann , Alexei Starovoitov , maze@google.com, lmb@cloudflare.com, shaun@tigera.io, Lorenzo Bianconi , marek@cloudflare.com, John Fastabend , Jakub Kicinski , eyal.birger@gmail.com, colrack@gmail.com Date: Tue, 22 Dec 2020 17:21:05 +0100 Message-ID: <160865406506.3593456.8475116968286355613.stgit@firesoul> In-Reply-To: <160865400291.3593456.17026136957003358677.stgit@firesoul> References: <160865400291.3593456.17026136957003358677.stgit@firesoul> User-Agent: StGit/0.19 MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.11 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Adding selftest for BPF-helper bpf_check_mtu(). Making sure it can be used from both XDP and TC. V10: - Remove errno non-zero test in CHECK_ATTR() - Addresse comments from Andrii Nakryiko Signed-off-by: Jesper Dangaard Brouer --- tools/testing/selftests/bpf/prog_tests/check_mtu.c | 218 ++++++++++++++++++++ tools/testing/selftests/bpf/progs/test_check_mtu.c | 199 ++++++++++++++++++ 2 files changed, 417 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/check_mtu.c create mode 100644 tools/testing/selftests/bpf/progs/test_check_mtu.c diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c new file mode 100644 index 000000000000..63f01c9e08d8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Jesper Dangaard Brouer */ + +#include /* before test_progs.h, avoid bpf_util.h redefines */ + +#include +#include "test_check_mtu.skel.h" +#include + +#include +#include + +#define IFINDEX_LO 1 + +static __u32 duration; /* Hint: needed for CHECK macro */ + +static int read_mtu_device_lo(void) +{ + const char *filename = "/sys/class/net/lo/mtu"; + char buf[11] = {}; + int value; + int fd; + + fd = open(filename, 0, O_RDONLY); + if (fd == -1) + return -1; + + if (read(fd, buf, sizeof(buf)) == -1) { + close(fd); + return -2; + } + close(fd); + + value = strtoimax(buf, NULL, 10); + if (errno == ERANGE) + return -3; + + return value; +} + +static void test_check_mtu_xdp_attach() +{ + struct bpf_link_info link_info; + __u32 link_info_len = sizeof(link_info); + struct test_check_mtu *skel; + struct bpf_program *prog; + struct bpf_link *link; + int err = 0; + int fd; + + skel = test_check_mtu__open_and_load(); + if (CHECK(!skel, "open and load skel", "failed")) + return; /* Exit if e.g. helper unknown to kernel */ + + prog = skel->progs.xdp_use_helper_basic; + + link = bpf_program__attach_xdp(prog, IFINDEX_LO); + if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + goto out; + skel->links.xdp_use_helper_basic = link; + + memset(&link_info, 0, sizeof(link_info)); + fd = bpf_link__fd(link); + err = bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); + if (CHECK(err, "link_info", "failed: %d\n", err)) + goto out; + + CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type", + "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP); + CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex", + "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO); + + err = bpf_link__detach(link); + CHECK(err, "link_detach", "failed %d\n", err); + +out: + test_check_mtu__destroy(skel); +} + +static void test_check_mtu_run_xdp(struct test_check_mtu *skel, + struct bpf_program *prog, + __u32 mtu_expect) +{ + const char *prog_name = bpf_program__name(prog); + int retval_expect = XDP_PASS; + __u32 mtu_result = 0; + char buf[256] = {}; + int err; + struct bpf_prog_test_run_attr tattr = { + .repeat = 1, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .prog_fd = bpf_program__fd(prog), + }; + + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err != 0, "bpf_prog_test_run", + "prog_name:%s (err %d errno %d retval %d)\n", + prog_name, err, errno, tattr.retval); + + CHECK(tattr.retval != retval_expect, "retval", + "progname:%s unexpected retval=%d expected=%d\n", + prog_name, tattr.retval, retval_expect); + + /* Extract MTU that BPF-prog got */ + mtu_result = skel->bss->global_bpf_mtu_xdp; + ASSERT_EQ(mtu_result, mtu_expect, "MTU-compare-user"); +} + + +static void test_check_mtu_xdp(__u32 mtu, __u32 ifindex) +{ + struct test_check_mtu *skel; + int err; + + skel = test_check_mtu__open(); + if (CHECK(!skel, "skel_open", "failed")) + return; + + /* Update "constants" in BPF-prog *BEFORE* libbpf load */ + skel->rodata->GLOBAL_USER_MTU = mtu; + skel->rodata->GLOBAL_USER_IFINDEX = ifindex; + + err = test_check_mtu__load(skel); + if (CHECK(err, "skel_load", "failed: %d\n", err)) + goto cleanup; + + test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu); + test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu); + test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu); + +cleanup: + test_check_mtu__destroy(skel); +} + +static void test_check_mtu_run_tc(struct test_check_mtu *skel, + struct bpf_program *prog, + __u32 mtu_expect) +{ + const char *prog_name = bpf_program__name(prog); + int retval_expect = BPF_OK; + __u32 mtu_result = 0; + char buf[256] = {}; + int err; + struct bpf_prog_test_run_attr tattr = { + .repeat = 1, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .prog_fd = bpf_program__fd(prog), + }; + + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(err != 0, "bpf_prog_test_run", + "prog_name:%s (err %d errno %d retval %d)\n", + prog_name, err, errno, tattr.retval); + + CHECK(tattr.retval != retval_expect, "retval", + "progname:%s unexpected retval=%d expected=%d\n", + prog_name, tattr.retval, retval_expect); + + /* Extract MTU that BPF-prog got */ + mtu_result = skel->bss->global_bpf_mtu_tc; + ASSERT_EQ(mtu_result, mtu_expect, "MTU-compare-user"); +} + + +static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) +{ + struct test_check_mtu *skel; + int err; + + skel = test_check_mtu__open(); + if (CHECK(!skel, "skel_open", "failed")) + return; + + /* Update "constants" in BPF-prog *BEFORE* libbpf load */ + skel->rodata->GLOBAL_USER_MTU = mtu; + skel->rodata->GLOBAL_USER_IFINDEX = ifindex; + + err = test_check_mtu__load(skel); + if (CHECK(err, "skel_load", "failed: %d\n", err)) + goto cleanup; + + test_check_mtu_run_tc(skel, skel->progs.tc_use_helper, mtu); + test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu); + test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu); + test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu); +cleanup: + test_check_mtu__destroy(skel); +} + +void test_check_mtu(void) +{ + __u32 mtu_lo; + + if (test__start_subtest("bpf_check_mtu XDP-attach")) + test_check_mtu_xdp_attach(); + + mtu_lo = read_mtu_device_lo(); + if (CHECK(mtu_lo < 0, "reading MTU value", "failed (err:%d)", mtu_lo)) + return; + + if (test__start_subtest("bpf_check_mtu XDP-run")) + test_check_mtu_xdp(mtu_lo, 0); + + if (test__start_subtest("bpf_check_mtu XDP-run ifindex-lookup")) + test_check_mtu_xdp(mtu_lo, IFINDEX_LO); + + if (test__start_subtest("bpf_check_mtu TC-run")) + test_check_mtu_tc(mtu_lo, 0); + + if (test__start_subtest("bpf_check_mtu TC-run ifindex-lookup")) + test_check_mtu_tc(mtu_lo, IFINDEX_LO); +} diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c new file mode 100644 index 000000000000..d31cbf403683 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Jesper Dangaard Brouer */ + +#include +#include +#include + +#include +#include + +char _license[] SEC("license") = "GPL"; + +/* Userspace will update with MTU it can see on device */ +static volatile const int GLOBAL_USER_MTU; +static volatile const __u32 GLOBAL_USER_IFINDEX; + +/* BPF-prog will update these with MTU values it can see */ +__u32 global_bpf_mtu_xdp = 0; +__u32 global_bpf_mtu_tc = 0; + +SEC("xdp") +int xdp_use_helper_basic(struct xdp_md *ctx) +{ + __u32 mtu_len = 0; + + if (bpf_check_mtu(ctx, 0, &mtu_len, 0, 0)) + return XDP_ABORTED; + + return XDP_PASS; +} + +SEC("xdp") +int xdp_use_helper(struct xdp_md *ctx) +{ + int retval = XDP_PASS; /* Expected retval on successful test */ + __u32 mtu_len = 0; + __u32 ifindex = 0; + int delta = 0; + + /* When ifindex is zero, save net_device lookup and use ctx netdev */ + if (GLOBAL_USER_IFINDEX > 0) + ifindex = GLOBAL_USER_IFINDEX; + + if (bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0)) { + /* mtu_len is also valid when check fail */ + retval = XDP_ABORTED; + goto out; + } + + if (mtu_len != GLOBAL_USER_MTU) + retval = XDP_DROP; + +out: + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_exceed_mtu(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + int retval = XDP_ABORTED; /* Fail */ + __u32 mtu_len = 0; + + int delta; + int err; + + /* Exceed MTU with 1 via delta adjust */ + delta = GLOBAL_USER_MTU - (data_len - ETH_HLEN) + 1; + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0); + if (err) { + retval = XDP_PASS; /* Success in exceeding MTU check */ + if (err != BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = XDP_DROP; + } + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_minus_delta(struct xdp_md *ctx) +{ + int retval = XDP_PASS; /* Expected retval on successful test */ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + __u32 mtu_len = 0; + int delta; + + /* Boarderline test case: Minus delta exceeding packet length allowed */ + delta = -((data_len - ETH_HLEN) + 1); + + /* Minus length (adjusted via delta) still pass MTU check, other helpers + * are responsible for catching this, when doing actual size adjust + */ + if (bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0)) + retval = XDP_ABORTED; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("classifier") +int tc_use_helper(struct __sk_buff *ctx) +{ + int retval = BPF_OK; /* Expected retval on successful test */ + __u32 mtu_len = 0; + int delta = 0; + + if (bpf_check_mtu(ctx, 0, &mtu_len, delta, 0)) { + retval = BPF_DROP; + goto out; + } + + if (mtu_len != GLOBAL_USER_MTU) + retval = BPF_REDIRECT; +out: + global_bpf_mtu_tc = mtu_len; + return retval; +} + +SEC("classifier") +int tc_exceed_mtu(struct __sk_buff *ctx) +{ + __u32 ifindex = GLOBAL_USER_IFINDEX; + int retval = BPF_DROP; /* Fail */ + __u32 skb_len = ctx->len; + __u32 mtu_len = 0; + int delta; + int err; + + /* Exceed MTU with 1 via delta adjust */ + delta = GLOBAL_USER_MTU - (skb_len - ETH_HLEN) + 1; + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0); + if (err) { + retval = BPF_OK; /* Success in exceeding MTU check */ + if (err != BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = BPF_DROP; + } + + global_bpf_mtu_tc = mtu_len; + return retval; +} + +SEC("classifier") +int tc_exceed_mtu_da(struct __sk_buff *ctx) +{ + /* SKB Direct-Access variant */ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + int retval = BPF_DROP; /* Fail */ + __u32 mtu_len = 0; + int delta; + int err; + + /* Exceed MTU with 1 via delta adjust */ + delta = GLOBAL_USER_MTU - (data_len - ETH_HLEN) + 1; + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0); + if (err) { + retval = BPF_OK; /* Success in exceeding MTU check */ + if (err != BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = BPF_DROP; + } + + global_bpf_mtu_tc = mtu_len; + return retval; +} + +SEC("classifier") +int tc_minus_delta(struct __sk_buff *ctx) +{ + int retval = BPF_OK; /* Expected retval on successful test */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 skb_len = ctx->len; + __u32 mtu_len = 0; + int delta; + + /* Boarderline test case: Minus delta exceeding packet length allowed */ + delta = -((skb_len - ETH_HLEN) + 1); + + /* Minus length (adjusted via delta) still pass MTU check, other helpers + * are responsible for catching this, when doing actual size adjust + */ + if (bpf_check_mtu(ctx, ifindex, &mtu_len, delta, 0)) + retval = BPF_DROP; + + global_bpf_mtu_xdp = mtu_len; + return retval; +}