Received: from mail.netfilter.org (mail.netfilter.org [217.70.190.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 558282E401 for ; Thu, 30 Apr 2026 05:58:41 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.70.190.124 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777528724; cv=none; b=Lb1V249/w9wxxp+cFdi6GU3pR9f1gsxF3kD5v/8WpZWqB8MP16R8FuuuqFoPPakBFb6rZV2Xei/eBDLDQ0+kZQT5yP9Cx3h2Qd3Ls9u7ht1dtSa6D0bKY+tZXGkSjLVJF9rr67KEfzTXGP4bIguUT2PywXurFGUXnDow86BhgTQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777528724; c=relaxed/simple; bh=iJqKuCz90K3Cle7yMvZ/e5UYXSCmDvQMtxoOWBcIjSo=; h=From:To:Subject:Date:Message-ID:MIME-Version; b=lC1dfG+KtoWBk+XIbZhL1h2HXkYRL76j/+Dip9We5h+Q53OTxVDWE2osJ0e6MKisIFYG2YgmZq2z0aAToX2RRRlHik/deGun5hHoB1W8HWGcSKYNu+HmO/B0WlPu7OGmW0ePSpHgibpdvaF713XjyVFxS3sLoEWKiPgzYJfQKq0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=netfilter.org; spf=pass smtp.mailfrom=netfilter.org; dkim=pass (2048-bit key) header.d=netfilter.org header.i=@netfilter.org header.b=F9euZMVE; arc=none smtp.client-ip=217.70.190.124 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=netfilter.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=netfilter.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=netfilter.org header.i=@netfilter.org header.b="F9euZMVE" Received: from localhost.localdomain (mail-agni [217.70.190.124]) by mail.netfilter.org (Postfix) with ESMTPSA id 8E18A602CB for ; Thu, 30 Apr 2026 07:58:39 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=netfilter.org; s=2025; t=1777528719; bh=VJC0c+A2ZfA5zjovv0mZFmdDnFCi61FUB+825VzYzeQ=; h=From:To:Subject:Date:From; b=F9euZMVEt64gG7exyfiPmTWEQqD/tu/Ur7yUMCtb1zLO07W8mkbjpH5KaQcc6xLfB Ii51gpo8Rz/pW3LLqX4dzFl3kZIV0kxNotPPpjHW9b+8EswSiAZO1mOdr1Hb4hGwjD oWRuhg/XzNyoX+WvSHmz27rUy357nT4gx7CLFBFePnkQX0VI6VMQwhyXacQz0zigEh jpMi7vYe4U1E4fHGiuOiV5VlCcyxbBOBi1/tgZL3vqhB4SZgDOtfmXqIQj9FQ7dvIR 208r4ZIWeum4XAIM9pgMfm5ZP/RSK9PxhED0RWpgqEerQ+avPxIoYbNRtRe6//Ce1T bptnCCOJcHPgQ== From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Subject: [PATCH nf,v4 1/2] netfilter: flowtable: fix inline vlan encapsulation in xmit path Date: Thu, 30 Apr 2026 07:58:35 +0200 Message-ID: <20260430055836.223494-1-pablo@netfilter.org> X-Mailer: git-send-email 2.47.3 Precedence: bulk X-Mailing-List: netfilter-devel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Several issues in the inline vlan support: - The layer 2 encapsulation representation in the tuple takes encap[0] as the outer header and encap[1] as the inner header as seen from the ingress path. Reverse the encap loop to push first the inner then the outer vlan header. - Postpone pushing the layer 2 header once destination device is known. This allows to calculate the needed hearoom via LL_RESERVED_SPACE to accommodate the layer 2 headers. - Add and use nf_flow_vlan_push() as suggested by Eric Woudstra, this is a simplified version of skb_vlan_push() for egress path only. Fixes: c653d5a78f34 ("netfilter: flowtable: inline vlan encapsulation in xmit path") Signed-off-by: Pablo Neira Ayuso --- v4: no changes net/netfilter/nf_flow_table_ip.c | 91 ++++++++++++++++++++++---------- 1 file changed, 63 insertions(+), 28 deletions(-) diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index dbd7644fdbeb..6da0bc3965df 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -462,23 +462,6 @@ static void nf_flow_encap_pop(struct nf_flowtable_ctx *ctx, nf_flow_ip_tunnel_pop(ctx, skb); } -struct nf_flow_xmit { - const void *dest; - const void *source; - struct net_device *outdev; -}; - -static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, - struct nf_flow_xmit *xmit) -{ - skb->dev = xmit->outdev; - dev_hard_header(skb, skb->dev, ntohs(skb->protocol), - xmit->dest, xmit->source, skb->len); - dev_queue_xmit(skb); - - return NF_STOLEN; -} - static struct flow_offload_tuple_rhash * nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx, struct nf_flowtable *flow_table, struct sk_buff *skb) @@ -544,6 +527,31 @@ static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx, return 1; } +/* Similar to skb_vlan_push. */ +static int nf_flow_vlan_push(struct sk_buff *skb, __be16 proto, u16 id, + u32 needed_headroom) +{ + if (skb_vlan_tag_present(skb)) { + struct vlan_hdr *vhdr; + + if (skb_cow_head(skb, needed_headroom + VLAN_HLEN)) + return -1; + + __skb_push(skb, VLAN_HLEN); + if (skb_mac_header_was_set(skb)) + skb->mac_header -= VLAN_HLEN; + + vhdr = (struct vlan_hdr *)skb->data; + skb->network_header -= VLAN_HLEN; + vhdr->h_vlan_TCI = htons(skb_vlan_tag_get(skb)); + vhdr->h_vlan_encapsulated_proto = skb->protocol; + skb->protocol = skb->vlan_proto; + } + __vlan_hwaccel_put_tag(skb, proto, id); + + return 0; +} + static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id) { int data_len = skb->len + sizeof(__be16); @@ -730,17 +738,19 @@ static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb, } static int nf_flow_encap_push(struct sk_buff *skb, - struct flow_offload_tuple *tuple) + struct flow_offload_tuple *tuple, + struct net_device *outdev) { + u32 needed_headroom = LL_RESERVED_SPACE(outdev); int i; - for (i = 0; i < tuple->encap_num; i++) { + for (i = tuple->encap_num - 1; i >= 0; i--) { switch (tuple->encap[i].proto) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): - skb_reset_mac_header(skb); - if (skb_vlan_push(skb, tuple->encap[i].proto, - tuple->encap[i].id) < 0) + if (nf_flow_vlan_push(skb, tuple->encap[i].proto, + tuple->encap[i].id, + needed_headroom) < 0) return -1; break; case htons(ETH_P_PPP_SES): @@ -753,6 +763,35 @@ static int nf_flow_encap_push(struct sk_buff *skb, return 0; } +struct nf_flow_xmit { + const void *dest; + const void *source; + struct net_device *outdev; + struct flow_offload_tuple *tuple; +}; + +static void __nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, + struct nf_flow_xmit *xmit) +{ + skb->dev = xmit->outdev; + dev_hard_header(skb, skb->dev, ntohs(skb->protocol), + xmit->dest, xmit->source, skb->len); + dev_queue_xmit(skb); +} + +static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, + struct nf_flow_xmit *xmit) +{ + if (xmit->tuple->encap_num) { + if (nf_flow_encap_push(skb, xmit->tuple, xmit->outdev) < 0) + return NF_DROP; + } + + __nf_flow_queue_xmit(net, skb, xmit); + + return NF_STOLEN; +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -797,9 +836,6 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, &ip_daddr) < 0) return NF_DROP; - if (nf_flow_encap_push(skb, other_tuple) < 0) - return NF_DROP; - switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: rt = dst_rtable(tuplehash->tuple.dst_cache); @@ -829,6 +865,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, WARN_ON_ONCE(1); return NF_DROP; } + xmit.tuple = other_tuple; return nf_flow_queue_xmit(state->net, skb, &xmit); } @@ -1119,9 +1156,6 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, &ip6_daddr, encap_limit) < 0) return NF_DROP; - if (nf_flow_encap_push(skb, other_tuple) < 0) - return NF_DROP; - switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: rt = dst_rt6_info(tuplehash->tuple.dst_cache); @@ -1151,6 +1185,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, WARN_ON_ONCE(1); return NF_DROP; } + xmit.tuple = other_tuple; return nf_flow_queue_xmit(state->net, skb, &xmit); } -- 2.47.3