<div class="gmail_quote">2012/6/18 Michal Simek <span dir="ltr"><<a href="mailto:monstr@monstr.eu" target="_blank">monstr@monstr.eu</a>></span><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="HOEnZb"><div class="h5">On 06/18/2012 01:33 PM, Russell King - ARM Linux wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
On Mon, Jun 18, 2012 at 01:30:04PM +0200, Michal Simek wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
gic_set_affinity doesn't support force option. Force option<br>
should work with all possible cpus in the system not only with<br>
online cpus.<br>
</blockquote>
<br>
Neither does x86. Why do you want this? Offline CPUs are unable to<br>
receive the interrupt in any case (and must not receive interrupts in<br>
the bringup path until they are online.)<br>
</blockquote>
<br></div></div>
The whole reason for all these changes in AMP on dual core Cortex A9 where<br>
on one cpu runs Linux and on the second RTOS/standlone.<br>
<br>
It means that the second cpu is from Linux point of view offline all the time.<br>
But GIC has to be (and can be) setup to forward IRQ directly to the second cpu.<br>
GIC should be controlled by Linux.<br>
<br></blockquote></div><br>Russel: Any other reaction?<br>Can you see a way how to get this feature to the mainline Linux kernel?<br>Some patches needs to be refactored a little bit but the point is if you are willing to <br>
support this type of configuration.<br><br>Not sure if Ohad has any information that someone else would like to use it remoteproc(AMP) among ARM cores.<br><br>Thanks,<br>Michal<br><br><br><br>