netdev - Re: [PATCH bpf-next v10 11/12] bpf: support selective sampling for bpf timestamping

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <eb579932-e85e-4241-bfe7-6e0d780ee9d6@linux.dev>
Date: Wed, 12 Feb 2025 15:49:45 -0800
From: Martin KaFai Lau <martin.lau@...ux.dev>
To: Jason Xing <kerneljasonxing@...il.com>
Cc: davem@...emloft.net, edumazet@...gle.com, kuba@...nel.org,
 pabeni@...hat.com, dsahern@...nel.org, willemdebruijn.kernel@...il.com,
 willemb@...gle.com, ast@...nel.org, daniel@...earbox.net, andrii@...nel.org,
 eddyz87@...il.com, song@...nel.org, yonghong.song@...ux.dev,
 john.fastabend@...il.com, kpsingh@...nel.org, sdf@...ichev.me,
 haoluo@...gle.com, jolsa@...nel.org, shuah@...nel.org, ykolal@...com,
 bpf@...r.kernel.org, netdev@...r.kernel.org
Subject: Re: [PATCH bpf-next v10 11/12] bpf: support selective sampling for
 bpf timestamping

On 2/11/25 10:18 PM, Jason Xing wrote:
> Add the bpf_sock_ops_enable_tx_tstamp kfunc to allow BPF programs to
> selectively enable TX timestamping on a skb during tcp_sendmsg().
> 
> For example, BPF program will limit tracking X numbers of packets
> and then will stop there instead of tracing all the sendmsgs of
> matched flow all along. It would be helpful for users who cannot
> afford to calculate latencies from every sendmsg call probably
> due to the performance or storage space consideration.
> 
> Signed-off-by: Jason Xing <kerneljasonxing@...il.com>
> ---
>   kernel/bpf/btf.c  |  1 +
>   net/core/filter.c | 32 +++++++++++++++++++++++++++++++-
>   2 files changed, 32 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
> index 9433b6467bbe..740210f883dc 100644
> --- a/kernel/bpf/btf.c
> +++ b/kernel/bpf/btf.c
> @@ -8522,6 +8522,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
>   	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
>   	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
>   	case BPF_PROG_TYPE_CGROUP_SYSCTL:
> +	case BPF_PROG_TYPE_SOCK_OPS:
>   		return BTF_KFUNC_HOOK_CGROUP;
>   	case BPF_PROG_TYPE_SCHED_ACT:
>   		return BTF_KFUNC_HOOK_SCHED_ACT;
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 7f56d0bbeb00..36793c68b125 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -12102,6 +12102,26 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,
>   #endif
>   }
>   
> +__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
> +					      u64 flags)
> +{
> +	struct sk_buff *skb;
> +	struct sock *sk;
> +
> +	if (skops->op != BPF_SOCK_OPS_TS_SND_CB)
> +		return -EOPNOTSUPP;

It still needs to test the "flags" such that it can be used in the future....

	if (flags)
		return -EINVAL;

> +
> +	skb = skops->skb;
> +	sk = skops->sk;
> +	skb_shinfo(skb)->tx_flags |= SKBTX_BPF;
> +	if (sk_is_tcp(sk)) {

Unnecessary check like this will only confuse reader. Remove it and revisit when 
UDP will be supported.

> +		TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF;
> +		skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
> +	}
> +
> +	return 0;
> +}
> +
>   __bpf_kfunc_end_defs();
>   
>   int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
> @@ -12135,6 +12155,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk)
>   BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)
>   BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk)
>   
> +BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops)
> +BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS)
> +BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops)
> +
>   static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
>   	.owner = THIS_MODULE,
>   	.set = &bpf_kfunc_check_set_skb,
> @@ -12155,6 +12179,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = {
>   	.set = &bpf_kfunc_check_set_tcp_reqsk,
>   };
>   
> +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = {
> +	.owner = THIS_MODULE,
> +	.set = &bpf_kfunc_check_set_sock_ops,
> +};
> +
>   static int __init bpf_kfunc_init(void)
>   {
>   	int ret;
> @@ -12173,7 +12202,8 @@ static int __init bpf_kfunc_init(void)
>   	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
>   	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
>   					       &bpf_kfunc_set_sock_addr);
> -	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
> +	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
> +	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops);
>   }
>   late_initcall(bpf_kfunc_init);
>