Re: [RFC PATCH v3 net-next 1/4] net: Add skb->mono_delivery_time to distinguish mono delivery_time from (rcv) timestamp

[Martin KaFai Lau <kafai@fb.com>]

On Sat, Jan 22, 2022 at 10:32:16AM -0500, Willem de Bruijn wrote:
> On Fri, Jan 21, 2022 at 2:30 AM Martin KaFai Lau <kafai@fb.com> 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.  For example, when forwarding from egress to
> > ingress and then finally back to egress:
> >
> >             tcp-sender => veth@netns => veth@hostns => fq@eth0@hostns
> >                                      ^              ^
> >                                      reset          rest
> >
> > [0] (slide 22): https://linuxplumbersconf.org/event/11/contributions/953/attachments/867/1658/LPC_2021_BPF_Datapath_Extensions.pdf 
> >
> > This patch adds one bit skb->mono_delivery_time to flag the skb->tstamp
> > is storing the mono delivery_time instead of the (rcv) timestamp.
> >
> > The current use case is to keep the TCP mono delivery_time (EDT) and
> > to be used with sch_fq.  The later patch will also allow tc-bpf to read
> > and change the mono delivery_time.
> >
> > In the future, another bit (e.g. skb->user_delivery_time) can be added
> > for the SCM_TXTIME where the clock base is tracked by sk->sk_clockid.
> >
> > [ This patch is a prep work.  The following patch will
> >   get the other parts of the stack ready first.  Then another patch
> >   after that will finally set the skb->mono_delivery_time. ]
> >
> > skb_set_delivery_time() function is added.  It is used by the tcp_output.c
> > and during ip[6] fragmentation to assign the delivery_time to
> > the skb->tstamp and also set the skb->mono_delivery_time.
> >
> > Signed-off-by: Martin KaFai Lau <kafai@fb.com>
> > ---
> >  include/linux/skbuff.h                     | 13 +++++++++++++
> >  net/bridge/netfilter/nf_conntrack_bridge.c |  5 +++--
> >  net/ipv4/ip_output.c                       |  5 +++--
> >  net/ipv4/tcp_output.c                      | 16 +++++++++-------
> >  net/ipv6/ip6_output.c                      |  5 +++--
> >  net/ipv6/netfilter.c                       |  5 +++--
> >  6 files changed, 34 insertions(+), 15 deletions(-)
> >
> > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> > index bf11e1fbd69b..b9e20187242a 100644
> > --- a/include/linux/skbuff.h
> > +++ b/include/linux/skbuff.h
> > @@ -720,6 +720,10 @@ typedef unsigned char *sk_buff_data_t;
> >   *     @dst_pending_confirm: need to confirm neighbour
> >   *     @decrypted: Decrypted SKB
> >   *     @slow_gro: state present at GRO time, slower prepare step required
> > + *     @mono_delivery_time: When set, skb->tstamap has the
> 
> tstamp
> 
> > + *             delivery_time in mono clock base (i.e. EDT).  Otherwise, the
> > + *             skb->tstamp has the (rcv) timestamp at ingress and
> > + *             delivery_time at egress.
> >   *     @napi_id: id of the NAPI struct this skb came from
> >   *     @sender_cpu: (aka @napi_id) source CPU in XPS
> >   *     @secmark: security marking
> > @@ -890,6 +894,7 @@ struct sk_buff {
> >         __u8                    decrypted:1;
> >  #endif
> >         __u8                    slow_gro:1;
> > +       __u8                    mono_delivery_time:1;
> 
> This bit fills a hole, does not change sk_buff size, right?
> 
> >
> >  #ifdef CONFIG_NET_SCHED
> >         __u16                   tc_index;       /* traffic control index */
> > @@ -3903,6 +3908,14 @@ static inline ktime_t net_invalid_timestamp(void)
> >         return 0;
> >  }
> >
> > +static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
> > +                                        bool mono)
> > +{
> > +       skb->tstamp = kt;
> > +       /* Setting mono_delivery_time will be enabled later */
> > +       /* skb->mono_delivery_time = kt && mono; */
> > +}
> > +
> >  static inline u8 skb_metadata_len(const struct sk_buff *skb)
> >  {
> >         return skb_shinfo(skb)->meta_len;
> > diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
> > index fdbed3158555..ebfb2a5c59e4 100644
> > --- a/net/bridge/netfilter/nf_conntrack_bridge.c
> > +++ b/net/bridge/netfilter/nf_conntrack_bridge.c
> > @@ -32,6 +32,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
> >                                            struct sk_buff *))
> >  {
> >         int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
> > +       bool mono_delivery_time = skb->mono_delivery_time;
> 
> This use of a local variable is just a style choice, not needed for
> correctness, correct?
It is needed.  The current code also saves the very first
skb->tstamp (two lines below):

> >         unsigned int hlen, ll_rs, mtu;
> >         ktime_t tstamp = skb->tstamp;

My understanding is all frags reuse the first (/original) skb tstamp info.
The frags output() is one-by-one, meaning when sending the later frags,
the first skb has already been output()-ed, so the first skb tstamp info
needs to be saved in local variables.