netdev - Re: [PATCH bpf-next 1/2] bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <Y7h8yrOEkPuHkNpJ@google.com>
Date:   Fri, 6 Jan 2023 11:55:54 -0800
From:   sdf@...gle.com
To:     Ziyang Xuan <william.xuanziyang@...wei.com>
Cc:     ast@...nel.org, daniel@...earbox.net, andrii@...nel.org,
        davem@...emloft.net, edumazet@...gle.com, kuba@...nel.org,
        pabeni@...hat.com, bpf@...r.kernel.org, netdev@...r.kernel.org,
        martin.lau@...ux.dev, song@...nel.org, yhs@...com,
        john.fastabend@...il.com, kpsingh@...nel.org, haoluo@...gle.com,
        jolsa@...nel.org, willemb@...gle.com
Subject: Re: [PATCH bpf-next 1/2] bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust_room()

On 01/06, Ziyang Xuan wrote:
> Add ipip6 and ip6ip decap support for bpf_skb_adjust_room().
> Main use case is for using cls_bpf on ingress hook to decapsulate
> IPv4 over IPv6 and IPv6 over IPv4 tunnel packets.

CC'd Willem since he has done bpf_skb_adjust_room changes in the past.
There might be a lot of GRO/GSO context I'm missing.

> Signed-off-by: Ziyang Xuan <william.xuanziyang@...wei.com>
> ---
>   net/core/filter.c | 34 ++++++++++++++++++++++++++++++++--
>   1 file changed, 32 insertions(+), 2 deletions(-)

> diff --git a/net/core/filter.c b/net/core/filter.c
> index 929358677183..73982fb4fe2e 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3495,6 +3495,12 @@ static int bpf_skb_net_grow(struct sk_buff *skb,  
> u32 off, u32 len_diff,
>   static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
>   			      u64 flags)
>   {
> +	union {
> +		struct iphdr *v4;
> +		struct ipv6hdr *v6;
> +		unsigned char *hdr;
> +	} ip;
> +	__be16 proto;
>   	int ret;

>   	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
> @@ -3512,10 +3518,19 @@ static int bpf_skb_net_shrink(struct sk_buff  
> *skb, u32 off, u32 len_diff,
>   	if (unlikely(ret < 0))
>   		return ret;

> +	ip.hdr = skb_inner_network_header(skb);
> +	if (ip.v4->version == 4)
> +		proto = htons(ETH_P_IP);
> +	else
> +		proto = htons(ETH_P_IPV6);
> +
>   	ret = bpf_skb_net_hdr_pop(skb, off, len_diff);
>   	if (unlikely(ret < 0))
>   		return ret;

> +	/* Match skb->protocol to new outer l3 protocol */
> +	skb->protocol = proto;
> +
>   	if (skb_is_gso(skb)) {
>   		struct skb_shared_info *shinfo = skb_shinfo(skb);

> @@ -3578,10 +3593,14 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *,  
> skb, s32, len_diff,
>   	   u32, mode, u64, flags)
>   {
>   	u32 len_cur, len_diff_abs = abs(len_diff);
> -	u32 len_min = bpf_skb_net_base_len(skb);
> -	u32 len_max = BPF_SKB_MAX_LEN;
> +	u32 len_min, len_max = BPF_SKB_MAX_LEN;
>   	__be16 proto = skb->protocol;
>   	bool shrink = len_diff < 0;
> +	union {
> +		struct iphdr *v4;
> +		struct ipv6hdr *v6;
> +		unsigned char *hdr;
> +	} ip;
>   	u32 off;
>   	int ret;

> @@ -3594,6 +3613,9 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *,  
> skb, s32, len_diff,
>   		     proto != htons(ETH_P_IPV6)))
>   		return -ENOTSUPP;

> +	if (unlikely(shrink && !skb->encapsulation))
> +		return -ENOTSUPP;
> +
>   	off = skb_mac_header_len(skb);
>   	switch (mode) {
>   	case BPF_ADJ_ROOM_NET:
> @@ -3605,6 +3627,14 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *,  
> skb, s32, len_diff,
>   		return -ENOTSUPP;
>   	}

> +	if (shrink) {
> +		ip.hdr = skb_inner_network_header(skb);
> +		if (ip.v4->version == 4)
> +			len_min = sizeof(struct iphdr);
> +		else
> +			len_min = sizeof(struct ipv6hdr);
> +	}
> +
>   	len_cur = skb->len - skb_network_offset(skb);
>   	if ((shrink && (len_diff_abs >= len_cur ||
>   			len_cur - len_diff_abs < len_min)) ||
> --
> 2.25.1