On Wed, Sep 12, 2007 at 09:40:57PM +0200, Wolfgang Walter wrote:
quoted text
> On Wednesday 12 September 2007, J. Bruce Fields wrote:
> > On Wed, Sep 12, 2007 at 04:14:06PM +0200, Neil Brown wrote:
> > > So it is in 2.6.21 and later and should probably go to .stable for .21
> > > and .22.
> > > 
> > > Bruce:  for you :-)
> > 
> > OK, thanks!  But, (as is alas often the case) I'm still confused:
> > 
> > >  		if (!test_and_set_bit(SK_OLD, &svsk->sk_flags))
> > >  			continue;
> > > -		if (atomic_read(&svsk->sk_inuse) || test_bit(SK_BUSY, &svsk->sk_flags))
> > > +		if (atomic_read(&svsk->sk_inuse) > 1
> > > +		    || test_bit(SK_BUSY, &svsk->sk_flags))
> > >  			continue;
> > >  		atomic_inc(&svsk->sk_inuse);
> > >  		list_move(le, &to_be_aged);
> > 
> > What is it that ensures svsk->sk_inuse isn't incremented or SK_BUSY set
> > after that test?  Not all the code that does either of those is under
> > the same serv->sv_lock lock that this code is.
> > 
> 
> This should not matter - SK_CLOSED may be set at any time.
> 
> svc_age_temp_sockets only detaches the socket, sets SK_CLOSED and then 
> enqueues it. If SK_BUSY is set its already enqueued and svc_sock_enqueue 
> ensures that it is not enqueued twice.

Oh, got it.  And the list manipulation is safe thanks to sv_lock.  Neat,
thanks.  Can you verify that this solves your problem?

--b.
-
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/