Re: mmotm 2009-04-10-02-21 uploaded - forkbombed by work_for_cpu
From: Linus Torvalds
Date: Wed Apr 15 2009 - 10:52:58 EST
On Wed, 15 Apr 2009, Andrew Morton wrote:
>
> <stares suspiciously at smp_call_function_many()>
>
> * smp_call_function_many(): Run a function on a set of other CPUs.
>
> "other". It refuses to call the function on *this* CPU. Tricky.
.. Argh. And totally different from all the other smp_call_function's. In
smp_call_function_single(), for example, we literally test
if (cpu == this_cpu) {
local_irq_save(flags);
func(info);
local_irq_restore(flags);
} else {
.. do the cross-call ..
so I think this is just smp_call_function_many() breakage.
In fact, right now the PPC flush_tlb_page() does that insane dance just
because of this issue. So yes, there are a few current users, and they
seem to dislike the bad semantics (the kvm code doesn't care).
Duh duh duh.
Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/