Re: [PATCH v2 1/4] net: tun: fix tun_xdp_one() for IFF_TUN mode

[Jason Wang <jasowang@redhat.com>]

在 2021/6/23 下午9:52, David Woodhouse 写道:
> On Wed, 2021-06-23 at 11:45 +0800, Jason Wang wrote:
>> As replied in previous version, it would be better if we can unify
>> similar logic in tun_get_user().
> So that ends up looking something like this (incremental).
>
> Note the '/* XXX: frags && */' part in tun_skb_set_protocol(), because
> the 'frags &&' was there in tun_get_user() and it wasn't obvious to me
> whether I should be lifting that out as a separate argument to
> tun_skb_set_protocol() or if there's a better way.
>
> Either way, in my judgement this is less suitable for a stable fix and
> more appropriate for a follow-on cleanup. But I don't feel that
> strongly; I'm more than happy for you to overrule me on that.
> Especially if you fix the above XXX part while you're at it :)


By simply adding a boolean "pull" in tun_skb_set_protocol()?

Thanks


>
> I tested this with vhost-net and !IFF_NO_PI, and TX works. RX is still
> hosed on the vhost-net side, for the same reason that a bunch of test
> cases were already listed in #if 0, but I'll address that in a separate
> email. It's not part of *this* patch.
>
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -1641,6 +1641,40 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
>   	return NULL;
>   }
>   
> +static int tun_skb_set_protocol(struct tun_struct *tun, struct sk_buff *skb,
> +				__be16 pi_proto)
> +{
> +	switch (tun->flags & TUN_TYPE_MASK) {
> +	case IFF_TUN:
> +		if (tun->flags & IFF_NO_PI) {
> +			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
> +
> +			switch (ip_version) {
> +			case 4:
> +				pi_proto = htons(ETH_P_IP);
> +				break;
> +			case 6:
> +				pi_proto = htons(ETH_P_IPV6);
> +				break;
> +			default:
> +				return -EINVAL;
> +			}
> +		}
> +
> +		skb_reset_mac_header(skb);
> +		skb->protocol = pi_proto;
> +		skb->dev = tun->dev;
> +		break;
> +	case IFF_TAP:
> +		if (/* XXX frags && */!pskb_may_pull(skb, ETH_HLEN))
> +			return -ENOMEM;
> +
> +		skb->protocol = eth_type_trans(skb, tun->dev);
> +		break;
> +	}
> +	return 0;
> +}
> +
>   /* Get packet from user space buffer */
>   static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
>   			    void *msg_control, struct iov_iter *from,
> @@ -1784,37 +1818,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
>   		return -EINVAL;
>   	}
>   
> -	switch (tun->flags & TUN_TYPE_MASK) {
> -	case IFF_TUN:
> -		if (tun->flags & IFF_NO_PI) {
> -			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
> -
> -			switch (ip_version) {
> -			case 4:
> -				pi.proto = htons(ETH_P_IP);
> -				break;
> -			case 6:
> -				pi.proto = htons(ETH_P_IPV6);
> -				break;
> -			default:
> -				atomic_long_inc(&tun->dev->rx_dropped);
> -				kfree_skb(skb);
> -				return -EINVAL;
> -			}
> -		}
> -
> -		skb_reset_mac_header(skb);
> -		skb->protocol = pi.proto;
> -		skb->dev = tun->dev;
> -		break;
> -	case IFF_TAP:
> -		if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
> -			err = -ENOMEM;
> -			goto drop;
> -		}
> -		skb->protocol = eth_type_trans(skb, tun->dev);
> -		break;
> -	}
> +	err = tun_skb_set_protocol(tun, skb, pi.proto);
> +	if (err)
> +		goto drop;
>   
>   	/* copy skb_ubuf_info for callback when skb has no error */
>   	if (zerocopy) {
> @@ -2334,8 +2340,10 @@ static int tun_xdp_one(struct tun_struct *tun,
>   	struct virtio_net_hdr *gso = NULL;
>   	struct bpf_prog *xdp_prog;
>   	struct sk_buff *skb = NULL;
> +	__be16 proto = 0;
>   	u32 rxhash = 0, act;
>   	int buflen = hdr->buflen;
> +	int reservelen = xdp->data - xdp->data_hard_start;
>   	int err = 0;
>   	bool skb_xdp = false;
>   	struct page *page;
> @@ -2343,6 +2351,17 @@ static int tun_xdp_one(struct tun_struct *tun,
>   	if (tun->flags & IFF_VNET_HDR)
>   		gso = &hdr->gso;
>   
> +	if (!(tun->flags & IFF_NO_PI)) {
> +		struct tun_pi *pi = xdp->data;
> +		if (datasize < sizeof(*pi)) {
> +			atomic_long_inc(&tun->rx_frame_errors);
> +			return  -EINVAL;
> +		}
> +		proto = pi->proto;
> +		reservelen += sizeof(*pi);
> +		datasize -= sizeof(*pi);
> +	}
> +
>   	xdp_prog = rcu_dereference(tun->xdp_prog);
>   	if (xdp_prog) {
>   		if (gso && gso->gso_type) {
> @@ -2388,8 +2407,8 @@ static int tun_xdp_one(struct tun_struct *tun,
>   		goto out;
>   	}
>   
> -	skb_reserve(skb, xdp->data - xdp->data_hard_start);
> -	skb_put(skb, xdp->data_end - xdp->data);
> +	skb_reserve(skb, reservelen);
> +	skb_put(skb, datasize);
>   
>   	if (gso && virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) {
>   		atomic_long_inc(&tun->rx_frame_errors);
> @@ -2397,48 +2416,12 @@ static int tun_xdp_one(struct tun_struct *tun,
>   		err = -EINVAL;
>   		goto out;
>   	}
> -	switch (tun->flags & TUN_TYPE_MASK) {
> -	case IFF_TUN:
> -		if (tun->flags & IFF_NO_PI) {
> -			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
>   
> -			switch (ip_version) {
> -			case 4:
> -				skb->protocol = htons(ETH_P_IP);
> -				break;
> -			case 6:
> -				skb->protocol = htons(ETH_P_IPV6);
> -				break;
> -			default:
> -				atomic_long_inc(&tun->dev->rx_dropped);
> -				kfree_skb(skb);
> -				err = -EINVAL;
> -				goto out;
> -			}
> -		} else {
> -			struct tun_pi *pi = (struct tun_pi *)skb->data;
> -			if (!pskb_may_pull(skb, sizeof(*pi))) {
> -				atomic_long_inc(&tun->dev->rx_dropped);
> -				kfree_skb(skb);
> -				err = -ENOMEM;
> -				goto out;
> -			}
> -			skb_pull_inline(skb, sizeof(*pi));
> -			skb->protocol = pi->proto;
> -		}
> -
> -		skb_reset_mac_header(skb);
> -		skb->dev = tun->dev;
> -		break;
> -	case IFF_TAP:
> -		if (!pskb_may_pull(skb, ETH_HLEN)) {
> -			atomic_long_inc(&tun->dev->rx_dropped);
> -			kfree_skb(skb);
> -			err = -ENOMEM;
> -			goto out;
> -		}
> -		skb->protocol = eth_type_trans(skb, tun->dev);
> -		break;
> +	err = tun_skb_set_protocol(tun, skb, proto);
> +	if (err) {
> +		atomic_long_inc(&tun->dev->rx_dropped);
> +		kfree_skb(skb);
> +		goto out;
>   	}
>   
>   	skb_reset_network_header(skb);
>