I'm working on a security measure based on the virtualization instructions. The only requirement is memory isolation. So, to minimize performance impact, a vmexit should only be issued when a (EPT) protected page is accessed. On my processor however, access to control registers always causes an vmexit, resulting in a noticeable impact from the hypervisor. The documentation states that future processors may be more flexible and allow the programmer to disable the vmexits in such situations. Are there processors on the market yet that support this feature?

How to return to executive monitor from SMM monitor after activating dual-monitor treatment?
VMLAUNCH on SMM-transfer VMCS reports "VMLAUNCH with non-clear VMCS", VMRESUME on SMM-transfer VMCS reports "VMRESUME with non-launched VMCS".

I've made a very simple hypervisor. It works at one CPU, at base of Windows7 x64 and has no usefull functionality.
I can not solve two big problem:
1) If I run it at one CPU, I've got a tripple fault after some success VM exits. But if i set "int 3" at begin of non-root code after vmlaunch - host OS works almost very well.
2) If I try to repeat starting VMM at every CPU - I'v got a freezing and then random fatal error.

I suggest, I've done something wrong around interrupt tuning and has corrupt interrupt handling on the host

I was frustrated that it was problematic to run Ubuntu and Vista and XP on my laptop (I am a consultant and need to have the ability to develop in several platforms) when I realized that I could add OracleVirtual Boxinto Linux (or Vista but I usually use Linux) and run XP . Note that only XP Pro SP3 (which I have) allows virtualization not Home.Vista does not for Home or Business, only Enterprise and Ultimate and the same for Windows 7. XP runs so well on my HP 6830s with a P8400 Duo that I can't tell that it's a virtual machine.