Attached is a patch to fix the high FPU corruption (thanks to Andreas
and Chris). This patch also unifies the FPU save/restore for SMP and UP
and also fixes another problem with FPH save/restore path due to an
unaligned fault. Sorry for the delay.

This patch based on 2.4.21-rc2 (latest bktree).

Thanks,
Asit



> From: Mallick, Asit K
> Sent: Thursday, May 08, 2003 10:14 AM
> To: davidm@hpl.hp.com; Andreas Schwab
> Cc: linux-ia64@linuxia64.org; Chris Mason
> Subject: RE: [Linux-ia64] High fpu register corruption
> 
> David,
> 
> The save part in the context switch also needs to be fixed and we will
> take a look at this.
> Thanks,
> Asit
> 
> 
> > -----Original Message-----
> > From: David Mosberger [mailto:davidm@napali.hpl.hp.com]
> > Sent: Thursday, May 08, 2003 10:03 AM
> > To: Andreas Schwab
> > Cc: linux-ia64@linuxia64.org; Chris Mason
> > Subject: Re: [Linux-ia64] High fpu register corruption
> >
> > >>>>> On Thu, 08 May 2003 16:16:13 +0200, Andreas Schwab
> <schwab@suse.de>
> > said:
> >
> >   Andreas> When a process clears the psr.mfh bit after using the
high
> >   Andreas> fpu registers and then starts using them again it can
> >   Andreas> corrupt the fpu state of another process.  In order for
> >   Andreas> this to happen there must be some context switches
> >   Andreas> inbetween (thanks to Chris Mason for tracking this down):
> >
> > Ah, _now_ it makes sense.  I got a similar bug report yesterday, but
> > it claimed the _old_ (2.4.19) context switch was breaking and the
> > new one (2.4.20) was fine.  When I looked at the old code, I
couldn't
> > find anythign wrong with it.
> >
> >   Andreas> +	} else if (ia64_get_fpu_owner() != next)
> \
> >   Andreas> +		ia64_psr(ia64_task_regs(next))->dfh = 1;
> \
> >
> > I suspect what we really want to do here is something along the
lines
> > of:
> >
> >   Andreas> +	ia64_psr(ia64_task_regs(next))->dfh =
> > (ia64_get_fpu_owner() != next);		\
> >
> > This expresses the invariant we're after: the next thread has DFH
set
> > unless it owns the FPH partition.  IIRC, this is what the UP code
does
> > already.
> >
> > 	--david
> >
> > _______________________________________________
> > Linux-IA64 mailing list
> > Linux-IA64@linuxia64.org
> > http://lists.linuxia64.org/lists/listinfo/linux-ia64
> 
> _______________________________________________
> Linux-IA64 mailing list
> Linux-IA64@linuxia64.org
> http://lists.linuxia64.org/lists/listinfo/linux-ia64