On Tue, Oct 15, 2024 at 9:44 AM Willem de Bruijn
<willemdebruijn.kernel@xxxxxxxxx> wrote:
>
> Jason Xing wrote:
> > From: Jason Xing <kernelxing@xxxxxxxxxxx>
> >
> > Prepare for later changes in this series. Here I use u32 for
> > bpf_sock_ops_cb_flags for better extension and introduce a new
> > rx bpf flag to control separately.
> >
> > Main change is let userside set through bpf_setsockopt() for
> > SO_TIMESTAMPING feature.
> >
> > Signed-off-by: Jason Xing <kernelxing@xxxxxxxxxxx>
> > ---
> > include/linux/tcp.h | 2 +-
> > include/net/tcp.h | 2 +-
> > include/uapi/linux/bpf.h | 5 ++++-
> > net/core/filter.c | 6 +++++-
> > net/ipv4/tcp.c | 13 ++++++++++++-
> > tools/include/uapi/linux/bpf.h | 5 ++++-
> > 6 files changed, 27 insertions(+), 6 deletions(-)
> >
> > diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> > index 6a5e08b937b3..e21fd3035962 100644
> > --- a/include/linux/tcp.h
> > +++ b/include/linux/tcp.h
> > @@ -446,7 +446,7 @@ struct tcp_sock {
> >
> > /* Sock_ops bpf program related variables */
> > #ifdef CONFIG_BPF
> > - u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs
> > + u32 bpf_sock_ops_cb_flags; /* Control calling BPF programs
> > * values defined in uapi/linux/tcp.h
> > */
> > u8 bpf_chg_cc_inprogress:1; /* In the middle of
> > diff --git a/include/net/tcp.h b/include/net/tcp.h
> > index 739a9fb83d0c..728db7107074 100644
> > --- a/include/net/tcp.h
> > +++ b/include/net/tcp.h
> > @@ -423,7 +423,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val);
> > int tcp_set_window_clamp(struct sock *sk, int val);
> > void tcp_update_recv_tstamps(struct sk_buff *skb,
> > struct scm_timestamping_internal *tss);
> > -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
> > +void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
> > struct scm_timestamping_internal *tss);
> > void tcp_data_ready(struct sock *sk);
> > #ifdef CONFIG_MMU
> > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> > index 1b478ec18ac2..d2754f155cf7 100644
> > --- a/include/uapi/linux/bpf.h
> > +++ b/include/uapi/linux/bpf.h
> > @@ -6903,8 +6903,11 @@ enum {
> > /* Call bpf when the kernel is generating tx timestamps.
> > */
> > BPF_SOCK_OPS_TX_TIMESTAMPING_OPT_CB_FLAG = (1<<7),
> > + /* Call bpf when the kernel is generating rx timestamps.
> > + */
> > + BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG = (1<<8),
> > /* Mask of all currently supported cb flags */
> > - BPF_SOCK_OPS_ALL_CB_FLAGS = 0xFF,
> > + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x1FF,
> > };
> >
> > /* List of known BPF sock_ops operators.
> > diff --git a/net/core/filter.c b/net/core/filter.c
> > index 3b4afaa273d9..36b357b76f4a 100644
> > --- a/net/core/filter.c
> > +++ b/net/core/filter.c
> > @@ -5216,14 +5216,18 @@ static int bpf_sock_set_timestamping(struct sock *sk,
> > return -EINVAL;
> >
> > if (!(flags & (SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE |
> > - SOF_TIMESTAMPING_TX_ACK)))
> > + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_RX_SOFTWARE)))
> > return -EINVAL;
> >
> > ret = sock_set_tskey(sk, flags, BPFPROG_TS_REQUESTOR);
> > if (ret)
> > return ret;
> >
> > + if (flags & SOF_TIMESTAMPING_RX_SOFTWARE)
> > + sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
> > +
> > WRITE_ONCE(sk->sk_tsflags[BPFPROG_TS_REQUESTOR], flags);
> > +
> > static_branch_enable(&bpf_tstamp_control);
> >
> > return 0;
> > diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> > index d37e231b2737..0891b41bc745 100644
> > --- a/net/ipv4/tcp.c
> > +++ b/net/ipv4/tcp.c
> > @@ -2260,14 +2260,25 @@ static int tcp_zerocopy_receive(struct sock *sk,
> > }
> > #endif
> >
> > +static void tcp_bpf_recv_timestamp(struct sock *sk, struct scm_timestamping_internal *tss)
> > +{
> > + struct tcp_sock *tp = tcp_sk(sk);
> > +
> > + if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RX_TIMESTAMPING_OPT_CB_FLAG))
> > + return;
> > +}
> > +
> > /* Similar to __sock_recv_timestamp, but does not require an skb */
> > -void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
> > +void tcp_recv_timestamp(struct msghdr *msg, struct sock *sk,
> > struct scm_timestamping_internal *tss)
> > {
> > int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
> > u32 tsflags = READ_ONCE(sk->sk_tsflags[SOCKETOPT_TS_REQUESTOR]);
> > bool has_timestamping = false;
> >
> > + if (static_branch_unlikely(&bpf_tstamp_control))
> > + tcp_bpf_recv_timestamp(sk, tss);
> > +
> > if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
> > if (sock_flag(sk, SOCK_RCVTSTAMP)) {
> > if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
>
> tcp_recv_timestamp is called from tcp_recvmsg only conditionally:
>
> if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
> if (cmsg_flags & TCP_CMSG_TS)
> tcp_recv_timestamp(msg, sk, &tss);
>
> How do you get this triggered for your BPF program?
When users use BPF SO_TIMESTAMPING to print rx timestamp, it will use
bpf_setsockopt() to call sock_enable_timestamp() (see this patch), so
the skb will carry a timestamp. In tcp_recvmsg_locked(), cmsg_flags
will be initialized, so tcp_recv_timestamp() will get called.
>
> And also check the other caller, tcp_zc_finalize_rx_tstamp.
Got it, thanks for pointing it out.
