When I first integrated the Algorithmics emulator with the Linux kernel
several years back, I tried doing something like this but ran into some
problem that I cannot recall exactly - there may have been some case
where the system expected threads to "inherit" FCSR changes. I agree
that this is an obviously cleaner approach, but be careful.
----- Original Message -----
From: "Ralf Baechle" <firstname.lastname@example.org>
To: "Atsushi Nemoto" <email@example.com>
Sent: Thursday, April 28, 2005 6:41 AM
Subject: Re: preempt safe fpu-emulator
> On Wed, Apr 27, 2005 at 02:36:22PM +0900, Atsushi Nemoto wrote:
> > Hi. Here is a patch to make the fpu-emulator preempt-safe. It would
> > be SMP-safe also.
> > The 'ieee754_csr' global variable is removed. Now the 'ieee754_csr'
> > is an alias of current->thread.fpu.soft.fcr31. While the fpu-emulator
> > uses different mapping for RM bits (FPU_CSR_Rm vs. IEEE754_Rm), RM
> > bits are converted before (and after) calling of cop1Emulate(). If we
> > adjusted IEEE754_Rm to match with FPU_CSR_Rm, we can remove ieee_rm
> > and mips_rm. Should we do it?
> > With this patch, whole fpu-emulator can be run without disabling
> > preempt. I will post a patch to fix preemption issue soon.
> I applied both your patches with some slight cleanup for the endianess
> stuff in arch/mips/math-emu/ieee754.h and non-Linux stuff.