Re: [PATCH v2 bpf-next 2/9] bpf: Add bpf helper bpf_tcp_enter_cwr

[Stanislav Fomichev <sdf@fomichev.me>]

On 02/22, brakmo wrote:
> From: Martin KaFai Lau <kafai@fb.com>
> 
> This patch adds a new bpf helper BPF_FUNC_tcp_enter_cwr
> "int bpf_tcp_enter_cwr(struct bpf_tcp_sock *tp)".
> It is added to BPF_PROG_TYPE_CGROUP_SKB which can be attached
> to the egress path where the bpf prog is called by
> ip_finish_output() or ip6_finish_output().  The verifier
> ensures that the parameter must be a tcp_sock.
> 
> This helper makes a tcp_sock enter CWR state.  It can be used
> by a bpf_prog to manage egress network bandwidth limit per
> cgroupv2.  A later patch will have a sample program to
> show how it can be used to limit bandwidth usage per cgroupv2.
> 
> To ensure it is only called from BPF_CGROUP_INET_EGRESS, the
> attr->expected_attach_type must be specified as BPF_CGROUP_INET_EGRESS
> during load time if the prog uses this new helper.
> The newly added prog->enforce_expected_attach_type bit will also be set
> if this new helper is used.  This bit is for backward compatibility reason
> because currently prog->expected_attach_type has been ignored in
> BPF_PROG_TYPE_CGROUP_SKB.  During attach time,
> prog->expected_attach_type is only enforced if the
> prog->enforce_expected_attach_type bit is set.
> i.e. prog->expected_attach_type is only enforced if this new helper
> is used by the prog.
> 
> Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
> Signed-off-by: Martin KaFai Lau <kafai@fb.com>
> ---
>  include/linux/bpf.h      |  1 +
>  include/linux/filter.h   |  3 ++-
>  include/uapi/linux/bpf.h |  9 ++++++++-
>  kernel/bpf/syscall.c     | 12 ++++++++++++
>  kernel/bpf/verifier.c    |  4 ++++
>  net/core/filter.c        | 25 +++++++++++++++++++++++++
>  6 files changed, 52 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index d5ba2fc01af3..2d54ba7cf9dd 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -195,6 +195,7 @@ enum bpf_arg_type {
>  	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock */
>  	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
>  	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
> +	ARG_PTR_TO_TCP_SOCK,    /* pointer to tcp_sock */
>  };
>  
>  /* type of values returned from helper functions */
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index f32b3eca5a04..c6e878bdc5a6 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -510,7 +510,8 @@ struct bpf_prog {
>  				blinded:1,	/* Was blinded */
>  				is_func:1,	/* program is a bpf function */
>  				kprobe_override:1, /* Do we override a kprobe? */
> -				has_callchain_buf:1; /* callchain buffer allocated? */
> +				has_callchain_buf:1, /* callchain buffer allocated? */
> +				enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */
>  	enum bpf_prog_type	type;		/* Type of BPF program */
>  	enum bpf_attach_type	expected_attach_type; /* For some prog types */
>  	u32			len;		/* Number of filter blocks */
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index bcdd2474eee7..95b5058fa945 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2359,6 +2359,12 @@ union bpf_attr {
>   *	Return
>   *		A **struct bpf_tcp_sock** pointer on success, or NULL in
>   *		case of failure.
> + *
> + * int bpf_tcp_enter_cwr(struct bpf_tcp_sock *tp)
> + *	Description
> + *		Make a tcp_sock enter CWR state.
> + *	Return
> + *		0 on success, or a negative error in case of failure.
>   */
>  #define __BPF_FUNC_MAPPER(FN)		\
>  	FN(unspec),			\
> @@ -2457,7 +2463,8 @@ union bpf_attr {
>  	FN(spin_lock),			\
>  	FN(spin_unlock),		\
>  	FN(sk_fullsock),		\
> -	FN(tcp_sock),
> +	FN(tcp_sock),			\
> +	FN(tcp_enter_cwr),
>  
>  /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>   * function eBPF program intends to call
> diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
> index ec7c552af76b..9a478f2875cd 100644
> --- a/kernel/bpf/syscall.c
> +++ b/kernel/bpf/syscall.c
> @@ -1482,6 +1482,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
>  		default:
>  			return -EINVAL;
>  		}
> +	case BPF_PROG_TYPE_CGROUP_SKB:
> +		switch (expected_attach_type) {
> +		case BPF_CGROUP_INET_INGRESS:
> +		case BPF_CGROUP_INET_EGRESS:
> +			return 0;
> +		default:
> +			return -EINVAL;
> +		}
>  	default:
>  		return 0;
>  	}
> @@ -1725,6 +1733,10 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
>  	case BPF_PROG_TYPE_CGROUP_SOCK:
>  	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
>  		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
> +	case BPF_PROG_TYPE_CGROUP_SKB:
> +		return prog->enforce_expected_attach_type &&
> +			prog->expected_attach_type != attach_type ?
> +			-EINVAL : 0;
>  	default:
>  		return 0;
>  	}
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 1b9496c41383..95fb385c6f3c 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -2424,6 +2424,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
>  			return -EFAULT;
>  		}
>  		meta->ptr_id = reg->id;
> +	} else if (arg_type == ARG_PTR_TO_TCP_SOCK) {
> +		expected_type = PTR_TO_TCP_SOCK;
> +		if (type != expected_type)
> +			goto err_type;
>  	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
>  		if (meta->func_id == BPF_FUNC_spin_lock) {
>  			if (process_spin_lock(env, regno, true))
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 97916eedfe69..ca57ef25279c 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5426,6 +5426,24 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
>  	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
>  };
>  
> +BPF_CALL_1(bpf_tcp_enter_cwr, struct tcp_sock *, tp)
> +{
> +	struct sock *sk = (struct sock *)tp;
> +
> +	if (sk->sk_state == TCP_ESTABLISHED) {
> +		tcp_enter_cwr(sk);
> +		return 0;
> +	}
> +
> +	return -EINVAL;
> +}
> +
> +static const struct bpf_func_proto bpf_tcp_enter_cwr_proto = {
> +	.func        = bpf_tcp_enter_cwr,
> +	.gpl_only    = false,
> +	.ret_type    = RET_INTEGER,
> +	.arg1_type    = ARG_PTR_TO_TCP_SOCK,
> +};
>  #endif /* CONFIG_INET */
>  
>  bool bpf_helper_changes_pkt_data(void *func)
> @@ -5585,6 +5603,13 @@ cg_skb_func_proto(enum bpf_func_id func_id, struct bpf_prog *prog)
>  #ifdef CONFIG_INET
>  	case BPF_FUNC_tcp_sock:
>  		return &bpf_tcp_sock_proto;

[...]
> +	case BPF_FUNC_tcp_enter_cwr:
> +		if (prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
> +			prog->enforce_expected_attach_type = 1;
> +			return &bpf_tcp_enter_cwr_proto;
Instead of this back and forth with enforce_expected_attach_type, can we
just do here:

if (prog->expected_attach_type == BPF_CGROUP_INET_EGRESS)
	return &bpf_tcp_enter_cwr_proto;
else
	return null;

Wouldn't it have the same effect?

> +		} else {
> +			return NULL;
> +		}
>  #endif
>  	default:
>  		return sk_filter_func_proto(func_id, prog);
> -- 
> 2.17.1
>