Received-SPF: pass (google.com: domain of linux-kernel+bounces-187675-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Thu, 23 May 2024 10:56:56 -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, 
 netdev@vger.kernel.org, 
 linux-kernel@vger.kernel.org, 
 Chengen Du <chengen.du@canonical.com>
Message-ID: <664f5938d2bef_1b5d2429467@willemb.c.googlers.com.notmuch>
In-Reply-To: <20240520070348.26725-1-chengen.du@canonical.com>
References: <20240520070348.26725-1-chengen.du@canonical.com>
Subject: Re: [PATCH] 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:
> In the outbound packet path, if hardware VLAN offloading is unavailable,
> the VLAN tag is inserted into the payload but then cleared from the
> metadata. Consequently, this could lead to a false negative result when
> checking for the presence of a VLAN tag using skb_vlan_tag_present(),
> causing the packet sniffing outcome to lack VLAN tag information. As a
> result, the packet capturing tool may be unable to parse packets as
> expected.
> 
> Signed-off-by: Chengen Du <chengen.du@canonical.com>

Fixes tag and Cc: stable.

As discussed please add more detail to the commit message that
explains the bug. And/or add a Link: for instance to the github
issue.

> ---
>  net/packet/af_packet.c | 25 +++++++++++++++++++------
>  1 file changed, 19 insertions(+), 6 deletions(-)
> 
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index ea3ebc160e25..73e9acb1875b 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -1010,12 +1010,15 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
>  	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 (eth_type_vlan(pkc->skb->protocol)) {
> +		ppd->hv1.tp_vlan_tci = ntohs(vlan_eth_hdr(pkc->skb)->h_vlan_TCI);
> +		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol);
>  	} else {
>  		ppd->hv1.tp_vlan_tci = 0;
>  		ppd->hv1.tp_vlan_tpid = 0;
> -		ppd->tp_status = TP_STATUS_AVAILABLE;
>  	}
> +	ppd->tp_status = (ppd->hv1.tp_vlan_tci || ppd->hv1.tp_vlan_tpid) ?
> +		TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID : TP_STATUS_AVAILABLE;

Don't move this out of the original branch and don't make the valid
conditional on the value of tp_vlan_tci. Just duplicating the line
to both branches is fine. Here and below.

>  }
>  
>  static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
> @@ -2427,11 +2430,15 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
>  		if (skb_vlan_tag_present(skb)) {
>  			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 (eth_type_vlan(skb->protocol)) {
> +			h.h2->tp_vlan_tci = ntohs(vlan_eth_hdr(skb)->h_vlan_TCI);
> +			h.h2->tp_vlan_tpid = ntohs(skb->protocol);
>  		} else {
>  			h.h2->tp_vlan_tci = 0;
>  			h.h2->tp_vlan_tpid = 0;
>  		}
> +		if (h.h2->tp_vlan_tci || h.h2->tp_vlan_tpid)
> +			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
>  		memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding));
>  		hdrlen = sizeof(*h.h2);
>  		break;
> @@ -2457,7 +2464,8 @@ 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 = eth_type_vlan(skb->protocol) ?
> +		vlan_eth_hdr(skb)->h_vlan_encapsulated_proto : skb->protocol;

For QinQ you probably want the true network protocol, not the inner
VLAN tag.
>  	sll->sll_pkttype = skb->pkt_type;
>  	if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
>  		sll->sll_ifindex = orig_dev->ifindex;
> @@ -3482,7 +3490,8 @@ 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 = eth_type_vlan(skb->protocol) ?
> +			vlan_eth_hdr(skb)->h_vlan_encapsulated_proto : skb->protocol;
>  	}
>  
>  	sock_recv_cmsgs(msg, sk, skb);
> @@ -3538,11 +3547,15 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
>  		if (skb_vlan_tag_present(skb)) {
>  			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 (eth_type_vlan(skb->protocol)) {
> +			aux.tp_vlan_tci = ntohs(vlan_eth_hdr(skb)->h_vlan_TCI);
> +			aux.tp_vlan_tpid = ntohs(skb->protocol);
>  		} else {
>  			aux.tp_vlan_tci = 0;
>  			aux.tp_vlan_tpid = 0;
>  		}
> +		if (aux.tp_vlan_tci || aux.tp_vlan_tpid)
> +			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
>  		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
>  	}
>  
> -- 
> 2.40.1
>