Re: mmotm 2009-04-10-02-21 uploaded - forkbombed by work_for_cpu

[Linus Torvalds]

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/