On Fri, Jan 21, 2022 at 2:30 AM Martin KaFai Lau <kafai@xxxxxx> wrote: > > skb->tstamp was first used as the (rcv) timestamp in real time clock base. > The major usage is to report it to the user (e.g. SO_TIMESTAMP). > > Later, skb->tstamp is also set as the (future) delivery_time (e.g. EDT in TCP) > during egress and used by the qdisc (e.g. sch_fq) to make decision on when > the skb can be passed to the dev. > > Currently, there is no way to tell skb->tstamp having the (rcv) timestamp > or the delivery_time, so it is always reset to 0 whenever forwarded > between egress and ingress. > > While it makes sense to always clear the (rcv) timestamp in skb->tstamp > to avoid confusing sch_fq that expects the delivery_time, it is a > performance issue [0] to clear the delivery_time if the skb finally > egress to a fq@phy-dev. > > v3: > - Feedback from v2 is using shinfo(skb)->tx_flags could be racy. > - Considered to reuse a few bits in skb->tstamp to represent > different semantics, other than more code churns, it will break > the bpf usecase which currently can write and then read back > the skb->tstamp. > - Went back to v1 idea on adding a bit to skb and address the > feedbacks on v1: > - Added one bit skb->mono_delivery_time to flag that > the skb->tstamp has the mono delivery_time (EDT), instead > of adding a bit to flag if the skb->tstamp has been forwarded or not. > - Instead of resetting the delivery_time back to the (rcv) timestamp > during recvmsg syscall which may be too late and not useful, > the delivery_time reset in v3 happens earlier once the stack > knows that the skb will be delivered locally. > - Handled the tapping@ingress case by af_packet > - No need to change the (rcv) timestamp to mono clock base as in v1. > The added one bit to flag skb->mono_delivery_time is enough > to keep the EDT delivery_time during forward. > - Added logic to the bpf side to make the existing bpf > running at ingress can still get the (rcv) timestamp > when reading the __sk_buff->tstamp. New __sk_buff->mono_delivery_time > is also added. Test is still needed to test this piece. > > Martin KaFai Lau (4): > net: Add skb->mono_delivery_time to distinguish mono delivery_time > from (rcv) timestamp > net: Add skb_clear_tstamp() to keep the mono delivery_time > net: Set skb->mono_delivery_time and clear it when delivering locally > bpf: Add __sk_buff->mono_delivery_time and handle __sk_buff->tstamp > based on tc_at_ingress > > drivers/net/loopback.c | 2 +- > include/linux/filter.h | 31 ++++- > include/linux/skbuff.h | 64 ++++++++-- > include/uapi/linux/bpf.h | 1 + > net/bridge/br_forward.c | 2 +- > net/bridge/netfilter/nf_conntrack_bridge.c | 5 +- > net/core/dev.c | 4 +- > net/core/filter.c | 140 +++++++++++++++++++-- > net/core/skbuff.c | 8 +- > net/ipv4/ip_forward.c | 2 +- > net/ipv4/ip_input.c | 1 + > net/ipv4/ip_output.c | 5 +- > net/ipv4/tcp_output.c | 16 +-- > net/ipv6/ip6_input.c | 1 + > net/ipv6/ip6_output.c | 7 +- > net/ipv6/netfilter.c | 5 +- > net/netfilter/ipvs/ip_vs_xmit.c | 6 +- > net/netfilter/nf_dup_netdev.c | 2 +- > net/netfilter/nf_flow_table_ip.c | 4 +- > net/netfilter/nft_fwd_netdev.c | 2 +- > net/openvswitch/vport.c | 2 +- > net/packet/af_packet.c | 4 +- > net/sched/act_bpf.c | 5 +- > net/sched/cls_bpf.c | 6 +- > net/xfrm/xfrm_interface.c | 2 +- > tools/include/uapi/linux/bpf.h | 1 + > 26 files changed, 265 insertions(+), 63 deletions(-) > > -- This overall looks great to me. The only effect on timestamping is slightly delayed receive timestamp for packets arriving over a virtual loop (loopback, veth, ..) interface, as the timestamp is now captured at the network protocol input. Actually, while writing that: timestamping is a socket level option, not specific to IP. Might this break receive timestamping over such interfaces for other protocols?
