Re: [PATCH bpf-next,v2 1/2] bpf: add helper for getting xfrm states

[Alexei Starovoitov <alexei.starovoitov@gmail.com>]

On Thu, Apr 19, 2018 at 12:58:22AM +0300, Eyal Birger wrote:
> This commit introduces a helper which allows fetching xfrm state
> parameters by eBPF programs attached to TC.
> 
> Prototype:
> bpf_skb_get_xfrm_state(skb, index, xfrm_state, size, flags)
> 
> skb: pointer to skb
> index: the index in the skb xfrm_state secpath array
> xfrm_state: pointer to 'struct bpf_xfrm_state'
> size: size of 'struct bpf_xfrm_state'
> flags: reserved for future extensions
> 
> The helper returns 0 on success. Non zero if no xfrm state at the index
> is found - or non exists at all.
> 
> struct bpf_xfrm_state currently includes the SPI, peer IPv4/IPv6
> address and the reqid; it can be further extended by adding elements to
> its end - indicating the populated fields by the 'size' argument -
> keeping backwards compatibility.
> 
> Typical usage:
> 
> struct bpf_xfrm_state x = {};
> bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
> ...
> 
> Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
> ---
>  include/uapi/linux/bpf.h | 25 ++++++++++++++++++++++++-
>  net/core/filter.c        | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 72 insertions(+), 1 deletion(-)
> 
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 9a2d1a0..82b407a 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -762,6 +762,15 @@ union bpf_attr {
>   *     @xdp_md: pointer to xdp_md
>   *     @delta: A negative integer to be added to xdp_md.data_end
>   *     Return: 0 on success or negative on error
> + *
> + * int bpf_skb_get_xfrm_state(skb, index, xfrm_state, size, flags)
> + *     retrieve XFRM state
> + *     @skb: pointer to skb
> + *     @index: index of the xfrm state in the secpath
> + *     @key: pointer to 'struct bpf_xfrm_state'
> + *     @size: size of 'struct bpf_xfrm_state'
> + *     @flags: room for future extensions
> + *     Return: 0 on success or negative error
>   */
>  #define __BPF_FUNC_MAPPER(FN)		\
>  	FN(unspec),			\
> @@ -829,7 +838,8 @@ union bpf_attr {
>  	FN(msg_cork_bytes),		\
>  	FN(msg_pull_data),		\
>  	FN(bind),			\
> -	FN(xdp_adjust_tail),
> +	FN(xdp_adjust_tail),		\
> +	FN(skb_get_xfrm_state),
>  
>  /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>   * function eBPF program intends to call
> @@ -935,6 +945,19 @@ struct bpf_tunnel_key {
>  	__u32 tunnel_label;
>  };
>  
> +/* user accessible mirror of in-kernel xfrm_state.
> + * new fields can only be added to the end of this structure
> + */
> +struct bpf_xfrm_state {
> +	__u32 reqid;
> +	__u32 spi;
> +	__u16 family;
> +	union {
> +		__u32 remote_ipv4;
> +		__u32 remote_ipv6[4];
> +	};
> +};
> +
>  /* Generic BPF return codes which all BPF program types may support.
>   * The values are binary compatible with their TC_ACT_* counter-part to
>   * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 2931859..489d360 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -57,6 +57,7 @@
>  #include <net/sock_reuseport.h>
>  #include <net/busy_poll.h>
>  #include <net/tcp.h>
> +#include <net/xfrm.h>
>  #include <linux/bpf_trace.h>
>  
>  /**
> @@ -3749,6 +3750,49 @@ static const struct bpf_func_proto bpf_bind_proto = {
>  	.arg3_type	= ARG_CONST_SIZE,
>  };
>  
> +#ifdef CONFIG_XFRM
> +BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index,
> +	   struct bpf_xfrm_state *, to, u32, size, u64, flags)
> +{
> +	const struct sec_path *sp = skb_sec_path(skb);
> +	const struct xfrm_state *x;
> +
> +	if (!sp || unlikely(index >= sp->len || flags))
> +		goto err_clear;
> +
> +	x = sp->xvec[index];
> +
> +	if (unlikely(size != sizeof(struct bpf_xfrm_state)))
> +		goto err_clear;
> +
> +	to->reqid = x->props.reqid;
> +	to->spi = be32_to_cpu(x->id.spi);
> +	to->family = x->props.family;
> +	if (to->family == AF_INET6) {
> +		memcpy(to->remote_ipv6, x->props.saddr.a6,
> +		       sizeof(to->remote_ipv6));
> +	} else {
> +		to->remote_ipv4 = be32_to_cpu(x->props.saddr.a4);
> +	}

that looks inconsistent. Why v4 is cpu endian, but v6 not?

Why change endianness of the spi?