The current generation of virtualization extensions only supports one VM layer. While we can't change that, it is pretty easy to emulate the CPU's behavior and implement the virtualization opcodes ourselves.
This patchset does exactly this for SVM. Using it, KVM can run within a VM. Since we're emulating the real CPU's behavior, this should also enable other VMMs to run within KVM. So far I've only tested to run KVM inside the VM though. Currently running an SMP level2 guest is broken. I have yet to find out why. As always, comments and suggestions are highly welcome. v2 takes most comments from Avi into account. Two things are missing: - save/restore of hflags - #VMEXIT on save/restore I'd rather have them submitted as later patches though, so we don't clutter this already big patchset (I'm slowly getting crazy using git to manage it) v3 addresses Joergs comments, including - V_INTR_MASKING support - a generic permission checking helper To be usable, this patchset requires the two simple changes in the userspace part, that I sent to the list with the first version. Thanks for reviewing! Alex Alexander Graf (9): Add CPUID feature flag for SVM v3 Clean up VINTR setting v3 Add helper functions for nested SVM v3 Implement GIF, clgi and stgi v3 Implement hsave v3 Add VMLOAD and VMSAVE handlers v3 Add VMRUN handler v3 Add VMEXIT handler and intercepts v3 Allow setting the SVME bit v3 arch/x86/kvm/kvm_svm.h | 11 + arch/x86/kvm/svm.c | 743 +++++++++++++++++++++++++++++++++++++++++- include/asm-x86/cpufeature.h | 1 + include/asm-x86/kvm_host.h | 5 + 4 files changed, 748 insertions(+), 12 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
