> FWIW, slab.c has a "struct array_cache *new[NR_CPUS]" on the
> stack.

I don't think so.  That line is part of the "struct ccupdate_struct"
definition.  We only declare a pointer to one of those on the stack.

> Also, net/core/utils.c has "unsigned long seed[NR_CPUS]".

I don't see this one either (in Linus 2.6.21-rc5). Looking at
the history Suresh Siddha zapped it last August specifically
because of worries about stack overflow on 1024 cpu systems.

I do see:
kernel/sched.c:         int ints[NR_CPUS], i;

> I'm only adding 1/4 as much space. Can I get away with it or
> should I allocate a node-local chunk of memory & keep a pointer to
> it in per-cpu data?

Debugging kernel stack overflow is no fun at all, so you might
want to take the better-safe-than-sorry approach here.

-Tony
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to