Jason Thorpe wrote:
> 
> On Jun 13, 2005, at 6:07 PM, James K. Lowden wrote:
> 
> > Do we support, anywhere, the idea of changing a word (4 bytes) of  
> > memory
> > atomically, meaning that no other thread can intervene?
> 
> It is a highly platform (well, CPU, mostly)-specific question.

I know, but I'm a userland program, so I need a kernel service.  

David Laight said "Code will assume that a write of a 32bit (aligned)
quantity is atomic", but that the functions I quoted refer to 64-bit
values.  

For the time being, unless someone corrects me, I think I need
pthread_mutex_lock(3).  I'm not sure how I'll set that up -- I don't know
the codebase well enough -- and it'll probably perform terribly.  But from
what I've gleaned here I think that it's in the right neighborhood.  

Thank you, both.  

--jkl