From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 643CEC05027 for ; Thu, 9 Feb 2023 12:43:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229971AbjBIMn1 (ORCPT ); Thu, 9 Feb 2023 07:43:27 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:51592 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229939AbjBIMnZ (ORCPT ); Thu, 9 Feb 2023 07:43:25 -0500 Received: from out0-216.mail.aliyun.com (out0-216.mail.aliyun.com [140.205.0.216]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4AF325C89A for ; Thu, 9 Feb 2023 04:43:21 -0800 (PST) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R121e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018047187;MF=amy.saq@antgroup.com;NM=1;PH=DS;RN=7;SR=0;TI=SMTPD_---.RGtG-14_1675946598; Received: from localhost(mailfrom:amy.saq@antgroup.com fp:SMTPD_---.RGtG-14_1675946598) by smtp.aliyun-inc.com; Thu, 09 Feb 2023 20:43:19 +0800 From: "=?UTF-8?B?5rKI5a6J55CqKOWHm+eOpSk=?=" To: netdev@vger.kernel.org Cc: , , , , "=?UTF-8?B?6LCI6Ym06ZSL?=" , "=?UTF-8?B?5rKI5a6J55CqKOWHm+eOpSk=?=" Subject: [PATCH 2/2] net/packet: send and receive pkt with given vnet_hdr_sz Date: Thu, 09 Feb 2023 20:43:15 +0800 Message-Id: <1675946595-103034-3-git-send-email-amy.saq@antgroup.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1675946595-103034-1-git-send-email-amy.saq@antgroup.com> References: <1675946595-103034-1-git-send-email-amy.saq@antgroup.com> Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: "Jianfeng Tan" When raw socket is used as the backend for kernel vhost, currently it will regard the virtio net header as 10-byte, which is not always the case since some virtio features need virtio net header other than 10-byte, such as mrg_rxbuf and VERSION_1 that both need 12-byte virtio net header. Instead of hardcoding virtio net header length to 10 bytes, tpacket_snd, tpacket_rcv, packet_snd and packet_recvmsg now get the virtio net header size that is recorded in packet_sock to indicate the exact virtio net header size that virtio user actually prepares in the packets. By doing so, it can fix the issue of incorrect mac header parsing when these virtio features that need virtio net header other than 10-byte are enable. Signed-off-by: Jianfeng Tan Co-developed-by: Anqi Shen Signed-off-by: Anqi Shen --- net/packet/af_packet.c | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ab37baf..4f49939 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2092,18 +2092,25 @@ static unsigned int run_filter(struct sk_buff *skb, } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, - size_t *len) + size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr vnet_hdr; + int ret; - if (*len < sizeof(vnet_hdr)) + if (*len < vnet_hdr_sz) return -EINVAL; - *len -= sizeof(vnet_hdr); + *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true, 0)) return -EINVAL; - return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr)); + ret = memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr)); + + /* reserve space for extra info in vnet_hdr if needed */ + if (ret == 0) + iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(vnet_hdr)); + + return ret; } /* @@ -2311,7 +2318,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, (maclen < 16 ? 16 : maclen)) + po->tp_reserve; if (po->has_vnet_hdr) { - netoff += sizeof(struct virtio_net_hdr); + netoff += po->vnet_hdr_sz; do_vnet = true; } macoff = netoff - maclen; @@ -2552,16 +2559,23 @@ static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, - struct virtio_net_hdr *vnet_hdr) + struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { - if (*len < sizeof(*vnet_hdr)) + int ret; + + if (*len < vnet_hdr_sz) return -EINVAL; - *len -= sizeof(*vnet_hdr); + *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; - return __packet_snd_vnet_parse(vnet_hdr, *len); + ret = __packet_snd_vnet_parse(vnet_hdr, *len); + + /* move iter to point to the start of mac header */ + if (ret == 0) + iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); + return ret; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, @@ -2730,6 +2744,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo = 0; + int vnet_hdr_sz; mutex_lock(&po->pg_vec_lock); @@ -2811,8 +2826,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) tlen = dev->needed_tailroom; if (po->has_vnet_hdr) { vnet_hdr = data; - data += sizeof(*vnet_hdr); - tp_len -= sizeof(*vnet_hdr); + vnet_hdr_sz = po->vnet_hdr_sz; + data += vnet_hdr_sz; + tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; @@ -2947,6 +2963,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int offset = 0; struct packet_sock *po = pkt_sk(sk); bool has_vnet_hdr = false; + int vnet_hdr_sz; int hlen, tlen, linear; int extra_len = 0; @@ -2991,7 +3008,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (po->has_vnet_hdr) { - err = packet_snd_vnet_parse(msg, &len, &vnet_hdr); + vnet_hdr_sz = po->vnet_hdr_sz; + err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; has_vnet_hdr = true; @@ -3068,7 +3086,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; - len += sizeof(vnet_hdr); + len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } @@ -3452,10 +3470,10 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, packet_rcv_try_clear_pressure(pkt_sk(sk)); if (pkt_sk(sk)->has_vnet_hdr) { - err = packet_rcv_vnet(msg, skb, &len); + vnet_hdr_len = pkt_sk(sk)->vnet_hdr_sz; + err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; - vnet_hdr_len = sizeof(struct virtio_net_hdr); } /* You lose any data beyond the buffer you gave. If it worries -- 1.8.3.1