bpf: Support selective sampling for bpf timestamping

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@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-12-kerneljasonxing@gmail.com

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 9de6acddd479b4f5e32a5e6ba43cf369de4cee29..551eedb87d58064b253e931bb31d235829621fb2 100644 (file)
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -8524,6 +8524,7 @@ 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 90a8fbc2e09677bb45e208179cd751e010ebc166..a0867c5b32b37064824860451d6ce44d7943e86d 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -12103,6 +12103,25 @@ __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;
+
+       if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB)
+               return -EOPNOTSUPP;
+
+       if (flags)
+               return -EINVAL;
+
+       skb = skops->skb;
+       skb_shinfo(skb)->tx_flags |= SKBTX_BPF;
+       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,
@@ -12136,6 +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,
@@ -12156,6 +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;
@@ -12174,7 +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);