On 06.03.2009, at 23:47, Christoffer Dall wrote:
Hi. We are a small group trying to port KVM to ARM and taking inspiration in the work done for PowerPC.
Wow, awesome. Do you have any idea how to come around the limitations of the platform? As far as I know ARM is not virtualizable. One reason I remember is that the status register for context switches (supervisor/privileged) is not trappable.
Alex
We are just beginning to understand KVM, so bear with us for noob questions. We are willing to put a lot of work into this though. When going through the code in booke_interrupts.S, I can see that the execution of code is performed by the rfi instruction, which jumps to the location stored in the vcpu struct, but I cannot see how the actual code to run is ever loaded in that place. I have tried going through the userspace code as well, but I am unsure if loading the code for execution happens through mmap, a page fault signal or ...? Any help would be GREATLY appreciated! Thank you! Best regards, Christoffer Dall -- To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
-- To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
