Messages in this thread | | | Date | Wed, 1 Jul 2009 10:44:30 +0200 | From | Jiri Olsa <> | Subject | Re: [PATCH] net: fix race in the receive/select |
| |
On Wed, Jul 01, 2009 at 04:31:44PM +0800, Herbert Xu wrote: > On Wed, Jul 01, 2009 at 09:22:26AM +0200, Andi Kleen wrote: > > > > Agreed. > > > > I suspect the reordering of the wake queue tests might makes a difference, but > > in this case to ensure they are always tested in the proper order by > > the compiler would need more smp_rmb()s > > I just looked up the original bug report and it's against RHEL4 > which is a 2.6.9 kernel. Jiri, have we reproduced this on a more > recent kernel?
no, only RHEL 4..
it is very hard to reproduce. I was succesfull once on RHEL4 after 8 days, never on upstream though.
jirka
> > Thanks, > -- > 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
| |