Jason Xing wrote:
> Users can write the following code to enable the bpf extension:
> int flags = SK_BPF_CB_TX_TIMESTAMPING;
> int opts = SK_BPF_CB_FLAGS;
> bpf_setsockopt(skops, SOL_SOCKET, opts, &flags, sizeof(flags));
>
> Signed-off-by: Jason Xing <kerneljasonxing@xxxxxxxxx>
> ---
> include/net/sock.h | 3 +++
> include/uapi/linux/bpf.h | 8 ++++++++
> net/core/filter.c | 23 +++++++++++++++++++++++
> tools/include/uapi/linux/bpf.h | 1 +
> 4 files changed, 35 insertions(+)
>
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 8036b3b79cd8..7916982343c6 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -303,6 +303,7 @@ struct sk_filter;
> * @sk_stamp: time stamp of last packet received
> * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
> * @sk_tsflags: SO_TIMESTAMPING flags
> + * @sk_bpf_cb_flags: used in bpf_setsockopt()
> * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag.
> * Sockets that can be used under memory reclaim should
> * set this to false.
> @@ -445,6 +446,8 @@ struct sock {
> u32 sk_reserved_mem;
> int sk_forward_alloc;
> u32 sk_tsflags;
> +#define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG))
> + u32 sk_bpf_cb_flags;
> __cacheline_group_end(sock_write_rxtx);
>
> __cacheline_group_begin(sock_write_tx);
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 2acf9b336371..6116eb3d1515 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -6913,6 +6913,13 @@ enum {
> BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F,
> };
>
> +/* Definitions for bpf_sk_cb_flags */
> +enum {
> + SK_BPF_CB_TX_TIMESTAMPING = 1<<0,
> + SK_BPF_CB_MASK = (SK_BPF_CB_TX_TIMESTAMPING - 1) |
> + SK_BPF_CB_TX_TIMESTAMPING
> +};
> +
> /* List of known BPF sock_ops operators.
> * New entries can only be added at the end
> */
> @@ -7091,6 +7098,7 @@ enum {
> TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */
> TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */
> TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
> + SK_BPF_CB_FLAGS = 1009, /* Used to set socket bpf flags */
> };
>
> enum {
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 2ec162dd83c4..1c6c07507a78 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5222,6 +5222,25 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
> .arg1_type = ARG_PTR_TO_CTX,
> };
>
> +static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt)
> +{
> + u32 sk_bpf_cb_flags;
> +
> + if (getopt) {
> + *(u32 *)optval = sk->sk_bpf_cb_flags;
> + return 0;
> + }
> +
> + sk_bpf_cb_flags = *(u32 *)optval;
> +
> + if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK)
> + return -EINVAL;
> +
> + sk->sk_bpf_cb_flags = sk_bpf_cb_flags;
I don't know BPF internals that well:
Is there mutual exclusion between these sol_socket_sockopt calls?
Or do these sk field accesses need WRITE_ONCE/READ_ONCE.
> +
> + return 0;
> +}
> +
> static int sol_socket_sockopt(struct sock *sk, int optname,
> char *optval, int *optlen,
> bool getopt)
> @@ -5238,6 +5257,7 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
> case SO_MAX_PACING_RATE:
> case SO_BINDTOIFINDEX:
> case SO_TXREHASH:
> + case SK_BPF_CB_FLAGS:
> if (*optlen != sizeof(int))
> return -EINVAL;
> break;
> @@ -5247,6 +5267,9 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
> return -EINVAL;
> }
>
> + if (optname == SK_BPF_CB_FLAGS)
> + return sk_bpf_set_get_cb_flags(sk, optval, getopt);
> +
> if (getopt) {
> if (optname == SO_BINDTODEVICE)
> return -EINVAL;
> diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
> index 2acf9b336371..70366f74ef4e 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
> @@ -7091,6 +7091,7 @@ enum {
> TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */
> TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */
> TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
> + SK_BPF_CB_FLAGS = 1009, /* Used to set socket bpf flags */
> };
>
> enum {
> --
> 2.43.5
>
