Re: [discuss] Re: [patch 0/4] CPU hot-plug support for x86_64

[Andi Kleen]

On Tue, May 24, 2005 at 02:23:30PM +0530, Srivatsa Vaddagiri wrote:
> On Mon, May 23, 2005 at 11:01:06PM -0700, Ashok Raj wrote:
> > We do this today in x86_64 case when we setup this upcomming cpu in 
> > cpu_online_map. But the issue is when we use ipi broadcast, its an ugly
> 
> I don't know of x86-64, but atleast on x86 ipi broadcast will send 
> to _all_ CPUs present, right? I mean the h/w does not know of the offline
> CPUs and will send to them also. This could lead to a problem for the offline 
> CPUs when they come online and can take a spurious IPI (unless
> there is support in h/w to clear pending IPI before doing STI).

x86-64 works the same here. 

The hardware does not clear pending IPIs AFAIK, but software could
do that manually during cpu bootup. Races can be avoided by taking
call_lock and the tlb flush lock while doing that.

-Andi
-
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/