Re: [PATCH 2/6] 2.6.16-rc1 perfmon2 patch for review

From: Keith Owens
Date: Wed Jan 25 2006 - 06:09:20 EST


Stephane Eranian (on Tue, 24 Jan 2006 07:13:25 -0800) wrote:
>Well, I am not sure why the smp_call_function_single() is not already
>implemented for i386. I can see that the underlying function send_IPI_mask()
>is there. It also looks like flush_tlb_others() is also selecting CPUs a subset
>of CPUs. I am not a big enough expert on x86 to understand if there are gotchas
>to watch for. Yet it would surprise me if this is radically different than on
>x86_64 (em64t) which already has the call. Maybe someone can clarify this?

There is no hardware reason why smp_call_function_single() cannot be
implemented on i386. The only reason it has not been implemented on
i386 is that nobody has had a need for it yet.

-
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/