Received-SPF: pass (google.com: domain of linux-kernel+bounces-207500-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Sun, 09 Jun 2024 16:19:08 -0400
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: Chengen Du <chengen.du@canonical.com>, 
 willemdebruijn.kernel@gmail.com
Cc: davem@davemloft.net, 
 edumazet@google.com, 
 kuba@kernel.org, 
 pabeni@redhat.com, 
 kaber@trash.net, 
 netdev@vger.kernel.org, 
 linux-kernel@vger.kernel.org, 
 Chengen Du <chengen.du@canonical.com>, 
 stable@vger.kernel.org
Message-ID: <66660e3cd5636_8dbbb294c@willemb.c.googlers.com.notmuch>
In-Reply-To: <20240608025347.90680-1-chengen.du@canonical.com>
References: <20240608025347.90680-1-chengen.du@canonical.com>
Subject: Re: [PATCH v6] af_packet: Handle outgoing VLAN packets without
 hardware offloading
Precedence: bulk
Mime-Version: 1.0
Content-Type: text/plain;
 charset=utf-8
Content-Transfer-Encoding: 7bit

Chengen Du wrote:
> The issue initially stems from libpcap. The ethertype will be overwritten
> as the VLAN TPID if the network interface lacks hardware VLAN offloading.
> In the outbound packet path, if hardware VLAN offloading is unavailable,
> the VLAN tag is inserted into the payload but then cleared from the sk_buff
> struct. Consequently, this can lead to a false negative when checking for
> the presence of a VLAN tag, causing the packet sniffing outcome to lack
> VLAN tag information (i.e., TCI-TPID). As a result, the packet capturing
> tool may be unable to parse packets as expected.
> 
> The TCI-TPID is missing because the prb_fill_vlan_info() function does not
> modify the tp_vlan_tci/tp_vlan_tpid values, as the information is in the
> payload and not in the sk_buff struct. The skb_vlan_tag_present() function
> only checks vlan_all in the sk_buff struct. In cooked mode, the L2 header
> is stripped, preventing the packet capturing tool from determining the
> correct TCI-TPID value. Additionally, the protocol in SLL is incorrect,
> which means the packet capturing tool cannot parse the L3 header correctly.
> 
> Link: https://github.com/the-tcpdump-group/libpcap/issues/1105
> Link: https://lore.kernel.org/netdev/20240520070348.26725-1-chengen.du@canonical.com/T/#u
> Fixes: 393e52e33c6c ("packet: deliver VLAN TCI to userspace")
> Cc: stable@vger.kernel.org
> Signed-off-by: Chengen Du <chengen.du@canonical.com>

Overall, solid.

> ---
>  net/packet/af_packet.c | 57 ++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 55 insertions(+), 2 deletions(-)
> 
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index ea3ebc160e25..8cffbe1f912d 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -538,6 +538,43 @@ static void *packet_current_frame(struct packet_sock *po,
>  	return packet_lookup_frame(po, rb, rb->head, status);
>  }
>  
> +static u16 vlan_get_tci(struct sk_buff *skb)
> +{
> +	struct vlan_hdr vhdr, *vh;
> +	u8 *skb_orig_data = skb->data;
> +	int skb_orig_len = skb->len;
> +
> +	skb_push(skb, skb->data - skb_mac_header(skb));
> +	vh = skb_header_pointer(skb, ETH_HLEN, sizeof(vhdr), &vhdr);

Don't harcode Ethernet.

According to documentation VLANs are used with other link layers.

More importantly, in practice PF_PACKET allows inserting this
skb->protocol on any device.

We don't use link layer specific constants anywhere in the packet
socket code for this reason. But instead dev->hard_header_len.

One caveat there is variable length link layer headers, where
dev->min_header_len != dev->hard_header_len. Will just have to fail
on those.

> +	if (skb_orig_data != skb->data) {
> +		skb->data = skb_orig_data;
> +		skb->len = skb_orig_len;
> +	}
> +	if (unlikely(!vh))
> +		return 0;
> +
> +	return ntohs(vh->h_vlan_TCI);
> +}
> +

Only since I had to respond above: this is non-obvious enough to
deserve a function comment. Something like the following?

/* For SOCK_DGRAM, data starts at the network protocol, after any VLAN
 * headers. sll_protocol must point to the network protocol. The
 * (outer) VLAN TCI is still accessible as auxdata.
 */

> +static __be16 vlan_get_protocol_dgram(struct sk_buff *skb)
> +{
> +	__be16 proto = skb->protocol;
> +
> +	if (unlikely(eth_type_vlan(proto))) {
> +		u8 *skb_orig_data = skb->data;
> +		int skb_orig_len = skb->len;
> +
> +		skb_push(skb, skb->data - skb_mac_header(skb));
> +		proto = __vlan_get_protocol(skb, proto, NULL);
> +		if (skb_orig_data != skb->data) {
> +			skb->data = skb_orig_data;
> +			skb->len = skb_orig_len;
> +		}
> +	}
> +
> +	return proto;
> +}
> +
>  static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
>  {
>  	del_timer_sync(&pkc->retire_blk_timer);
> @@ -1007,10 +1044,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
>  static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
>  			struct tpacket3_hdr *ppd)
>  {
> +	struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc);
> +
>  	if (skb_vlan_tag_present(pkc->skb)) {
>  		ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
>  		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
>  		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
> +	} else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) {
> +		ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb);
> +		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol);
> +		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
>  	} else {
>  		ppd->hv1.tp_vlan_tci = 0;
>  		ppd->hv1.tp_vlan_tpid = 0;
> @@ -2428,6 +2471,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
>  			h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
>  			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
>  			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
> +		} else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
> +			h.h2->tp_vlan_tci = vlan_get_tci(skb);
> +			h.h2->tp_vlan_tpid = ntohs(skb->protocol);
> +			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
>  		} else {
>  			h.h2->tp_vlan_tci = 0;
>  			h.h2->tp_vlan_tpid = 0;
> @@ -2457,7 +2504,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
>  	sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
>  	sll->sll_family = AF_PACKET;
>  	sll->sll_hatype = dev->type;
> -	sll->sll_protocol = skb->protocol;
> +	sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ?
> +		vlan_get_protocol_dgram(skb) : skb->protocol;
>  	sll->sll_pkttype = skb->pkt_type;
>  	if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
>  		sll->sll_ifindex = orig_dev->ifindex;
> @@ -3482,7 +3530,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
>  		/* Original length was stored in sockaddr_ll fields */
>  		origlen = PACKET_SKB_CB(skb)->sa.origlen;
>  		sll->sll_family = AF_PACKET;
> -		sll->sll_protocol = skb->protocol;
> +		sll->sll_protocol = (sock->type == SOCK_DGRAM) ?
> +			vlan_get_protocol_dgram(skb) : skb->protocol;
>  	}
>  
>  	sock_recv_cmsgs(msg, sk, skb);
> @@ -3539,6 +3588,10 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
>  			aux.tp_vlan_tci = skb_vlan_tag_get(skb);
>  			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
>  			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
> +		} else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
> +			aux.tp_vlan_tci = vlan_get_tci(skb);
> +			aux.tp_vlan_tpid = ntohs(skb->protocol);
> +			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
>  		} else {
>  			aux.tp_vlan_tci = 0;
>  			aux.tp_vlan_tpid = 0;
> -- 
> 2.43.0
>