[PATCH RFC net-next 9/9] tcp: handle the start time of each split skb in the tx path

[Jason Xing <kerneljasonxing@gmail.com>]

Segmentation and collapsing create or reuse skbs with a fresh
shared_info, which would otherwise drop the start time recorded
on the original skb.

Handle every TCP path that manipulates the shared hwtstamps:

  - tcp_gso_segment(): handle the gso case. Propagate the same
    gso_skb's start time to every resulting segment.

  - tcp_fragment/tso_fragment(): handle the tso/recovery.. cases.
    Copy the start time onto the second half of the split so both
    fragments keep it.

  - tcp_skb_collapse_tstamp(): handle collapse case. Copy the eaten
    skb's start time onto the survivor.

  - __tcp_retransmit_skb(): handle retrans case - the retransmit
    path __tcp_retransmit_skb->__pskb_copy.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
---
rx path logic: https://lore.kernel.org/all/20260917132742.87117-1-kerneljasonxing@gmail.com/
---
 include/linux/skbuff.h | 6 ++++++
 net/ipv4/tcp_offload.c | 3 +++
 net/ipv4/tcp_output.c  | 5 +++++
 3 files changed, 14 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c5347be72ff9..5f01239af191 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -5491,6 +5491,12 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb)
 #endif
 }
 
+static inline void skb_copy_start_time(struct sk_buff *dst, struct sk_buff *src)
+{
+	if (static_branch_unlikely(&bpfts_v2_needed_key))
+		skb_hwtstamps(dst)->start_time = skb_hwtstamps(src)->start_time;
+}
+
 ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
 			     ssize_t maxsize);
 
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 3b1fdcd3cb29..3b33e9f4fbc9 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -201,6 +201,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP))
 		tcp_gso_tstamp(segs, gso_skb, seq, mss);
 
+	skb_copy_start_time(segs, gso_skb);
+
 	newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 
 	ecn_cwr_mask = !!(skb_shinfo(gso_skb)->gso_type & SKB_GSO_TCP_ACCECN);
@@ -226,6 +228,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		th->seq = htonl(seq);
 
 		th->cwr &= ecn_cwr_mask;
+		skb_copy_start_time(skb, gso_skb);
 	}
 
 	/* Following permits TCP Small Queues to work well with GSO :
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6f4dca4a4de9..006157321f49 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1900,6 +1900,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	tcp_skb_fragment_eor(skb, buff);
 
 	skb_split(skb, buff, len);
+	skb_copy_start_time(buff, skb);
 
 	skb_set_delivery_time(buff, skb->tstamp, SKB_CLOCK_MONOTONIC);
 	tcp_fragment_tstamp(skb, buff);
@@ -2431,6 +2432,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	tcp_skb_fragment_eor(skb, buff);
 
 	skb_split(skb, buff, len);
+	skb_copy_start_time(buff, skb);
 	tcp_fragment_tstamp(skb, buff);
 
 	/* Fix up tso_factor for both original and new SKB.  */
@@ -3445,6 +3447,8 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 		TCP_SKB_CB(skb)->txstamp_ack |=
 			TCP_SKB_CB(next_skb)->txstamp_ack;
 	}
+	if (!skb_hwtstamps(skb)->start_time)
+		skb_copy_start_time(skb, (struct sk_buff *)next_skb);
 }
 
 /* Collapses two adjacent SKB's during retransmission. */
@@ -3661,6 +3665,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 			nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 			if (nskb) {
 				nskb->dev = NULL;
+				skb_copy_start_time(nskb, skb);
 				err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC);
 			} else {
 				err = -ENOBUFS;
-- 
2.43.7