net: Set skb->mono_delivery_time and clear it after sch_handle_ingress()

The previous patches handled the delivery_time before sch_handle_ingress().

This patch can now set the skb->mono_delivery_time to flag the skb->tstamp
is used as the mono delivery_time (EDT) instead of the (rcv) timestamp
and also clear it with skb_clear_delivery_time() after
sch_handle_ingress().  This will make the bpf_redirect_*()
to keep the mono delivery_time and used by a qdisc (fq) of
the egress-ing interface.

A latter patch will postpone the skb_clear_delivery_time() until the
stack learns that the skb is being delivered locally and that will
make other kernel forwarding paths (ip[6]_forward) able to keep
the delivery_time also.  Thus, like the previous patches on using
the skb->mono_delivery_time bit, calling skb_clear_delivery_time()
is not limited within the CONFIG_NET_INGRESS to avoid too many code
churns among this set.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8e8a4af..0f5fd53 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3993,8 +3993,7 @@ 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 = 0;
+       skb->mono_delivery_time = kt && mono;
 }
 
 DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);

diff --git a/net/core/dev.c b/net/core/dev.c
index 5db2443..4b572bb 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5220,8 +5220,10 @@ another_round:
                        goto out;
        }
 
-       if (skb_skip_tc_classify(skb))
+       if (skb_skip_tc_classify(skb)) {
+               skb_clear_delivery_time(skb);
                goto skip_classify;
+       }
 
        if (pfmemalloc)
                goto skip_taps;
@@ -5250,12 +5252,14 @@ skip_taps:
                        goto another_round;
                if (!skb)
                        goto out;
+               skb_clear_delivery_time(skb);
 
                nf_skip_egress(skb, false);
                if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
                        goto out;
-       }
+       } else
 #endif
+               skb_clear_delivery_time(skb);
        skb_reset_redirect(skb);
 skip_classify:
        if (pfmemalloc && !skb_pfmemalloc_protocol(skb))

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a9588e0..00b4bf2 100644 (file)
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1728,8 +1728,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
                          arg->csumoffset) = csum_fold(csum_add(nskb->csum,
                                                                arg->csum));
                nskb->ip_summed = CHECKSUM_NONE;
-               /* Setting mono_delivery_time will be enabled later */
-               nskb->mono_delivery_time = 0;
+               nskb->mono_delivery_time = !!transmit_time;
                ip_push_pending_frames(sk, &fl4);
        }
 out: