sparc64 kernel code question..

[Julian Elischer]

On Sun, 9 May 2004, Brian Fundakowski Feldman wrote:

> Julian Elischer <julian at elischer.org> wrote:
> > 
> > in vm_machdep.c the sparc64  code has
> > void
> > cpu_sched_exit(struct thread *td)
> > {

[..]

> > This is the only architecture that has this..
> > What does it do? And what does it have to do with the scheduler?
> 
> It would appear to detach the vmspace in question from other executing CPUs. 
> This makes no sense -- how would other CPUs be executing on that vmspace if 
> it's already single-threaded at that point (also, single-threaded in the 
> rfork(2) sense because of the vm_refcnt check)?

I'm glad I'm not the only person scratching his head :-)

I'm assuming that one needs to know something abuot the Sparc64
architecture for this to make sense...

maybe one mmu for > 1 CPU or something?
Virtual IO for devices?