Thread (43 messages) flat view 43 messages, 8 authors, 2018-02-13

Re: [RFC v2 net-next 02/10] net: ipv4: raw: Hook into time based transmission.

From: Eric Dumazet <hidden>
Date: 2018-01-18 00:28:20
Also in: intel-wired-lan

On Wed, 2018-01-17 at 15:06 -0800, Jesus Sanchez-Palencia wrote:
quoted hunk ↗ jump to hunk
From: Richard Cochran <redacted>

For raw packets, copy the desired future transmit time from the CMSG
cookie into the skb.

Signed-off-by: Richard Cochran <redacted>
Signed-off-by: Jesus Sanchez-Palencia <redacted>
---
 net/ipv4/raw.c | 2 ++
 1 file changed, 2 insertions(+)
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 136544b36a46..e37ea8ab6a78 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -381,6 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
@@ -562,6 +563,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	ipc.sockc.tsflags = sk->sk_tsflags;
+	ipc.sockc.transmit_time = 0;
 	ipc.addr = inet->inet_saddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;

It seems that skb_scrub_packet() will clear skb->tstamp, meaning  that
going through a tunnel will break your feature.

Maybe we need to remove skb->tstamp clear from skb_scrub_packet() and
do the cleaning only in forwarding path.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help