On Sat, Oct 23, 2004 at 07:50:40AM +1000, herbert wrote:
>
> So we don't really know whether it went further or not :)
Actually, I think we've caught your crash now. If that code path
is triggering at all, then it'll trigger with TSO packets too. If
we get a truly partial ack on a TSO packet, then tcp_tso_acked will
not trim it off. So we will fall through to this last-ditch trim
call, which doesn't update packets_out.
There are two solutions to this problem. I've taken the simpler
approach for now. We simply trim off the partial bits in tcp_tso_acked
and live with the fact that the packet counters may differ from
what's on the netwrok by one.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Later on we can "fix" this by remembering where the original TSO
packet started from, perhaps in skb->h or somewhere. Dave, is this
worth it?
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
===== net/ipv4/tcp_input.c 1.81 vs edited =====
--- 1.81/net/ipv4/tcp_input.c 2004-10-04 07:31:39 +10:00
+++ edited/net/ipv4/tcp_input.c 2004-10-23 09:12:42 +10:00
@@ -2369,25 +2369,19 @@
{
struct tcp_opt *tp = tcp_sk(sk);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- __u32 mss = tcp_skb_mss(skb);
- __u32 snd_una = tp->snd_una;
- __u32 orig_seq, seq;
- __u32 packets_acked = 0;
+ __u32 seq = tp->snd_una;
+ __u32 packets_acked;
int acked = 0;
/* If we get here, the whole TSO packet has not been
* acked.
*/
- BUG_ON(!after(scb->end_seq, snd_una));
+ BUG_ON(!after(scb->end_seq, seq));
- seq = orig_seq = scb->seq;
- while (!after(seq + mss, snd_una)) {
- packets_acked++;
- seq += mss;
- }
-
- if (tcp_trim_head(sk, skb, (seq - orig_seq)))
+ packets_acked = tcp_skb_pcount(skb);
+ if (tcp_trim_head(sk, skb, seq - scb->seq))
return 0;
+ packets_acked -= tcp_skb_pcount(skb);
if (packets_acked) {
__u8 sacked = scb->sacked;
--- linux-2.6/net/ipv4/tcp_output.c.orig 2004-10-23 08:44:16.000000000 +1000
+++ linux-2.6/net/ipv4/tcp_output.c 2004-10-23 09:10:13.000000000 +1000
@@ -588,7 +588,7 @@
/* Any change of skb->len requires recalculation of tso
* factor and mss.
*/
- if (tcp_skb_mss(skb))
+ if (tcp_skb_pcount(skb) > 1)
tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb));
return 0;
