Bypass Virtualization

• US 20080168479A1
• Filed: 01/07/2008
• Published: 07/10/2008
• Est. Priority Date: 01/05/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: MOKA5, INC.
• Inventors: Chun, Won, Carbin, Michael, Purtell, Thomas Joseph
• Granted Patent: US 8,065,687 B2
• Time in Patent Office: Days
• US Class Current: 719/328
• CPC Class Codes: G06F 2009/45583 Memory management, e.g. access or allocation
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

Embodiments of the present invention comprise methods and systems for augmenting machine virtualization by entirely bypassing resource emulation for performance-critical features, such as 3D graphics acceleration, through the use of high-performance interfaces between the guest OS and the host OS. Embodiments of the present invention also comprise methods and systems for ameliorating the performance penalties and functionality restrictions of conventional resource emulation.

Claims

1. A system, comprising:

an intercept module that intercepts a function call from an application on a guest operating system, the guest operating system in a virtual machine monitor on a host operating system; and

a forwarding module that forwards the intercepted function call to the host operating system.

2. The system of claim 1, further comprising:

a remapping module which translates the address space of the guest to the address space of the host such that the host operating system may interpret the function calls from the application on the guest operating system.

3. The system of claim 2, further comprising:

a guest response module for monitoring the forwarded guest function call and returning at least one response from the host operating system to the application.

4. The system of claim 3, wherein the remapping module is used to translate the address space of the host to the address space of the guest for responses to forwarded guest function calls.

5. The system of claim 3, further comprising:

an interpretation module that translates the intercepted function call into at least one system call, wherein the at least one system call is processed within the host operating system.

6. The system of claim 5, wherein the interpretation module further translates at least one system call response from the host operating system into at least one function call response readable by the application.

7. The system of claim 2, wherein remapping module creates a continuous block of host virtual memory for forwarding the function calls to the host operating system.

8. The system of claim 6, wherein the forwarded function call includes a specially formed I/O request corresponding to the interpreted function call.

9. The system of claim 6, wherein the intercept module operates in user mode of the guest operating system.

10. The system of claim 6, wherein the remapping module operates in user mode on the host operating system.

11. The system of claim 2, wherein the intercept module is a low-level API within the guest operating system.

12. The system of claim 11, wherein the low-level API within the guest operating system is a thunk library.

13. The system of claim 12, wherein the thunk library corresponds to a sub system of the kernel of the guest operating system, and wherein the kernel sub system controls at least one graphics device driver for rendering 3-D graphics.