Abstract: In one embodiment, a predefined behavior of a virtual machine monitor (VMM) with respect to one or more virtual machines (VMs) is identified, and processor-managed resources associated with the one or more VMs are utilized based on the predefined behavior of the VMM.

Abstract: In one embodiment, the present invention includes a method of transitioning control to guest software in a virtual machine from a virtual machine monitor, receiving control following a transition from the virtual machine to the virtual machine monitor upon an event, and determining whether to modify a state of the guest code, a state of the virtual machine monitor or a state of controls. If such a determination is made, the state may be modified and control is transitioned back to the guest software.

Abstract: In one embodiment, a method includes receiving control transitioned from a virtual machine (VM) due to a privileged event pertaining to a translation-lookaside buffer (TLB), and determining which entries in a guest translation data structure were modified by the VM. The determination is made based on metadata extracted from a shadow translation data structure maintained by a virtual machine monitor (VMM) and attributes associated with entries in the shadow translation data structure. The method further includes synchronizing entries in the shadow translation data structure that correspond to the modified entries in the guest translation data structure with the modified entries in the guest translation data structure.

Abstract: In some embodiments, the invention involves a system to deprivilege components of a virtual machine monitor and enable deprivileged service virtual machines (SVMs) to handle selected trapped events. An embodiment of the invention is a hybrid VMM operating on a platform with hardware virtualization support. The hybrid VMM utilizes features from both hypervisor-based and host-based VMM architectures. In at least one embodiment, the functionality of a traditional VMM is partitioned into a small platform-dependent part called a micro-hypervisor (MH) and one or more platform-independent parts called service virtual machines (SVMs). The micro-hypervisor operates at a higher virtual machine (VM) privilege level than any SVM, while the SVM and other VMs may still have access to any instruction set architecture (ISA) privilege level. Other embodiments are described and claimed.

Abstract: In one embodiment, a method for handling privileged events in a virtual machine environment includes detecting an occurrence of a privileged event, determining which one of multiple virtual machine monitors (VMMs) is to handle the privileged event, and transitioning control to this VMM.

Abstract: In one embodiment, a method includes receiving control transitioned from a virtual machine (VM) due to a privileged event pertaining to a translation-lookaside buffer (TLB), and determining which entries in a guest translation data structure were modified by the VM. The determination is made based on metadata extracted from a shadow translation data structure maintained by a virtual machine monitor (VMM) and attributes associated with entries in the shadow translation data structure. The method further includes synchronizing entries in the shadow translation data structure that correspond to the modified entries in the guest translation data structure with the modified entries in the guest translation data structure.

Abstract: Methods and systems to provide support for single stepping a virtual machine in a virtual machine environment are disclosed. An exemplary method may include receiving a request to transition control to a virtual machine (VM) from a virtual machine monitor (VMM), determining that a single-stepping indicator is set to a single stepping value, and transitioning control to the VM. Further, if an execution of a first instruction in the VM completes successfully, control is transitioned to the VMM following the successful completion of the execution of the first instruction.

Abstract: A processing system may include a service operating system (OS) and a guest virtual machine (VM). The service OS may be a host OS or an OS in a service VM, for instance. The guest VM may have a physical address space. In one embodiment, a pseudo-device driver in the service OS causes an address within the physical address space of the guest VM to be mapped to an address within a virtual address space of a user level monitor (ULM) running on top of the service OS. When an operation that involves the physical address space of the guest VM (e.g., a direct memory access (DMA) operation requested by the guest VM, an interrupt triggered by the guest VM, etc.) is detected, the ULM may use its virtual address space to access the physical address space of the guest VM. Other embodiments are described and claimed.

Abstract: In one embodiment, information pertaining to a first fault occurring during operation of a virtual machine (VM) is stored in a first field. A second fault is detected while delivering the first fault to the VM, and a determination is made as to whether the second fault is associated with a transition of control to a virtual machine monitor (VMM). If this determination is positive, information pertaining to the second fault is stored in a second field, and control is transitioned to the VMM.