On Fri, Jun 26, 2020 at 10:55 AM Martin KaFai Lau <kafai@xxxxxx> wrote:
>
> This patch adds logic to parse experimental kind 254 with 16 bit magic
> 0xeB9F. The latter patch will allow bpf prog to write and parse data
> under this experimental kind and magic.
>
> A one byte bpf_hdr_opt_off is added to tcp_skb_cb by using an existing
> 4 byte hole. It is only used in rx. It stores the offset to the
> bpf experimental option and will be made available to BPF prog
> in a latter patch. This offset is also stored in the saved_syn.
>
> Signed-off-by: Martin KaFai Lau <kafai@xxxxxx>
> ---
> include/net/request_sock.h | 1 +
> include/net/tcp.h | 3 +++
> net/ipv4/tcp_input.c | 6 ++++++
> net/ipv4/tcp_ipv4.c | 1 +
> net/ipv6/tcp_ipv6.c | 1 +
> 5 files changed, 12 insertions(+)
>
> diff --git a/include/net/request_sock.h b/include/net/request_sock.h
> index d77237ec9fb4..55297286c066 100644
> --- a/include/net/request_sock.h
> +++ b/include/net/request_sock.h
> @@ -43,6 +43,7 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
>
> struct saved_syn {
> u32 network_hdrlen;
> + u32 bpf_hdr_opt_off;
> u8 data[];
> };
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index eab1c7d0facb..07a9dfe35242 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -191,6 +191,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
> */
> #define TCPOPT_FASTOPEN_MAGIC 0xF989
> #define TCPOPT_SMC_MAGIC 0xE2D4C3D9
> +#define TCPOPT_BPF_MAGIC 0xEB9F
>
> /*
> * TCP option lengths
> @@ -204,6 +205,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
> #define TCPOLEN_FASTOPEN_BASE 2
> #define TCPOLEN_EXP_FASTOPEN_BASE 4
> #define TCPOLEN_EXP_SMC_BASE 6
> +#define TCPOLEN_EXP_BPF_BASE 4
>
> /* But this is what stacks really send out. */
> #define TCPOLEN_TSTAMP_ALIGNED 12
> @@ -857,6 +859,7 @@ struct tcp_skb_cb {
> has_rxtstamp:1, /* SKB has a RX timestamp */
> unused:5;
> __u32 ack_seq; /* Sequence number ACK'd */
> + __u8 bpf_hdr_opt_off;/* offset to bpf hdr option. rx only. */
> union {
> struct {
> /* There is space for up to 24 bytes */
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index eb0e32b2def9..640408a80b3d 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -3924,6 +3924,10 @@ void tcp_parse_options(const struct net *net,
> tcp_parse_fastopen_option(opsize -
> TCPOLEN_EXP_FASTOPEN_BASE,
> ptr + 2, th->syn, foc, true);
> + else if (opsize >= TCPOLEN_EXP_BPF_BASE &&
> + get_unaligned_be16(ptr) ==
> + TCPOPT_BPF_MAGIC)
> + TCP_SKB_CB(skb)->bpf_hdr_opt_off = (ptr - 2) - (unsigned char *)th;
> else
> smc_parse_options(th, opt_rx, ptr,
> opsize);
> @@ -6562,6 +6566,8 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
> saved_syn = kmalloc(len + sizeof(*saved_syn), GFP_ATOMIC);
> if (saved_syn) {
> saved_syn->network_hdrlen = skb_network_header_len(skb);
> + saved_syn->bpf_hdr_opt_off =
> + TCP_SKB_CB(skb)->bpf_hdr_opt_off;
> memcpy(saved_syn->data, skb_network_header(skb), len);
> req->saved_syn = saved_syn;
> }
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index ea0df9fd7618..a3535b7fe002 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1864,6 +1864,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
> TCP_SKB_CB(skb)->sacked = 0;
> TCP_SKB_CB(skb)->has_rxtstamp =
> skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
> + TCP_SKB_CB(skb)->bpf_hdr_opt_off = 0;
> }
>
> /*
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index f67d45ff00b4..8356d0562279 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1545,6 +1545,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
> TCP_SKB_CB(skb)->sacked = 0;
> TCP_SKB_CB(skb)->has_rxtstamp =
> skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
> + TCP_SKB_CB(skb)->bpf_hdr_opt_off = 0;
> }
>
> INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
> --
> 2.24.1
>
