Hi Julien, On Fri, May 08, 2015 at 05:38:47PM +0100, Julien Grall wrote: > Hi Chen, > > On 07/04/15 08:33, Chen Baozi wrote: > > From: Chen Baozi <baoz...@gmail.com> > > > > On arm64, either firmware or xen's smp_up_cpu gate uses WFE on secondary > > cpus to stand-by when booting. Thus, using SEV is enough for the boot > > cpu to kick other secondaries. Further more, the current implementation > > of cpu_up_send_sgi would pass a NULL cpumask pointer to send_SGI, which > > then lead a data fault on GICv3 send_SGI implementation. > > I've sent a patch to fix send_SGI on GICv3 [1]. You should not see the > segfault anymore.
Yes, I have. And sorry for not being able to test&reply it in time. I was busy for other stuffs last few weeks. I'll try the patch as soon as possible. > > Although, you were saying that the SGI is not necessary for the spin > table. Right? Yes. I have checked the firmware, linux and xen. They all use WFE on secondary CPUs to stand-by when booting. Cheers, Baozi. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel
