Re: [PATCH net-next v3 04/14] net-timestamp: introduce TS_SCHED_OPT_CB to generate dev xmit timestamp

[Willem de Bruijn <willemdebruijn.kernel@gmail.com>]

Jason Xing wrote:
> From: Jason Xing <kernelxing@tencent.com>
> 
> Introduce BPF_SOCK_OPS_TS_SCHED_OPT_CB flag so that we can decide to
> print timestamps when the skb just passes the dev layer.
> 
> Signed-off-by: Jason Xing <kernelxing@tencent.com>
> ---
>  include/uapi/linux/bpf.h       |  5 +++++
>  net/core/skbuff.c              | 31 ++++++++++++++++++++++++++++++-
>  tools/include/uapi/linux/bpf.h |  5 +++++
>  3 files changed, 40 insertions(+), 1 deletion(-)
> 
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index e8241b320c6d..324e9e40969c 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -7013,6 +7013,11 @@ enum {
>  					 * by the kernel or the
>  					 * earlier bpf-progs.
>  					 */
> +	BPF_SOCK_OPS_TS_SCHED_OPT_CB,	/* Called when skb is passing through
> +					 * dev layer when SO_TIMESTAMPING
> +					 * feature is on. It indicates the
> +					 * recorded timestamp.
> +					 */
>  };
>  
>  /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 39309f75e105..e6a5c883bdc6 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -64,6 +64,7 @@
>  #include <linux/mpls.h>
>  #include <linux/kcov.h>
>  #include <linux/iov_iter.h>
> +#include <linux/bpf-cgroup.h>
>  
>  #include <net/protocol.h>
>  #include <net/dst.h>
> @@ -5621,13 +5622,41 @@ static void skb_tstamp_tx_output(struct sk_buff *orig_skb,
>  	__skb_complete_tx_timestamp(skb, sk, tstype, opt_stats);
>  }
>  
> +static void timestamp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
> +{
> +	struct bpf_sock_ops_kern sock_ops;
> +
> +	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
> +	if (sk_fullsock(sk)) {
> +		sock_ops.is_fullsock = 1;
> +		sock_owned_by_me(sk);

Why this check?

This will usually be false, as timestamps are taken outside the
protocol layers.

> +	}
> +
> +	sock_ops.sk = sk;
> +	sock_ops.op = op;
> +	if (nargs > 0)
> +		memcpy(sock_ops.args, args, nargs * sizeof(*args));
> +
> +	BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
> +}
> +