[Linux-ia64] Re: ia64_spinlock_contention and NEW_LOCK

From: Keith Owens <kaos_at_sgi.com>
Date: 2003-03-14 09:20:12
On Thu, 13 Mar 2003 14:14:44 -0800, 
David Mosberger <davidm@napali.hpl.hp.com> wrote:
>>>>>> On Fri, 14 Mar 2003 08:59:54 +1100, Keith Owens <kaos@sgi.com> said:
>  Keith> All is not lost, there is one spare slot in spin_lock which
>  Keith> can clear r29 (dummy ar.pfs) before entering
>  Keith> ia64_spinlock_contention.
>But that won't work for leaf routines as that would permanently
>clobber pfs.

I am not touching the real ar.pfs, precisely to avoid changing leaf
routines.  Setting r29 to 0 and .save ar.pfs, r29 in ia64_unwind_contention
will fool the unwind code into doing the unwind correctly but without
changing the state of the routine using spin_lock().
Received on Thu Mar 13 14:20:25 2003

This archive was generated by hypermail 2.1.8 : 2005-08-02 09:20:12 EST