Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F9/00—Arrangements for program control, e.g. control units
  • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
  • G06F9/44—Arrangements for executing specific programs
  • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
  • G06F9/45533—Hypervisors; Virtual machine monitors
  • G06F9/45545—Guest-host, i.e. hypervisor is an application program itself, e.g. VirtualBox
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
  • G06F12/02—Addressing or allocation; Relocation
  • G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
  • G06F12/023—Free address space management
  • G06F12/0253—Garbage collection, i.e. reclamation of unreferenced memory
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F9/00—Arrangements for program control, e.g. control units
  • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
  • G06F9/44—Arrangements for executing specific programs
  • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
  • G06F9/45533—Hypervisors; Virtual machine monitors
  • G06F9/45558—Hypervisor-specific management and integration aspects
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F9/00—Arrangements for program control, e.g. control units
  • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
  • G06F9/44—Arrangements for executing specific programs
  • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
  • G06F9/45533—Hypervisors; Virtual machine monitors
  • G06F9/45558—Hypervisor-specific management and integration aspects
  • G06F2009/45575—Starting, stopping, suspending or resuming virtual machine instances

Definitions

• One of the primary functions of an operating system is to interface with physical resources on a computing system.
• a typical operating system might guard against accessing the physical resources in an inappropriate manner. For example, when one application is using a particular segment of memory, the operating system may protect that segment of memory from being altered by another application managed by that same operating system. Otherwise, the applications might not function as expected. Such access guards are often based on the assumption that the operating system is the only operating system running on the computing system.
• a hypervisor is a software layer that is configured to be interposed between one or more running operating systems and protected physical resources (such as processors, I/O ports, memory, interrupts, etc.).
• the hypervisor functionally multiplexes the protected physical resources for the operating systems, and manifests the resources to each operating system in a virtualized manner. For instance, as a simple example, suppose that there are two operating systems running on a computing system that has one processor and 1 Gigabyte (GB) of Random Access Memory (RAM).
• the hypervisor may allocate half of the processor cycles to each operating system, and half of the memory (512 Megabytes (MB) of RAM) to each operating system.
• the hypervisor may provide a virtualized range of RAM addressed to each operating system such that it appears to both operating systems that there is only 512 MB of RAM available.
• the hypervisor When the operating system attempts to communicate with a physical resource and vice versa, the hypervisor performs appropriate buffering and transformations to allow each operating system, to experience its environment as though it was the only operating system running on the computing system. Furthermore, the hypervisor does this is a manner that the physical resources on the computing system may be shared by multiple operating system instances while still being protected.
• hypervisors are launched prior to running an operating system. This allows the hypervisor to start the operating system in a virtual machine by presenting a virtualized view of the physical resources.
• the hypervisor includes extensive code for discovering the physical resources and their essential characteristics. Since physical resource discovery is done before there are any running operating systems, the operating system cannot be relied upon in this discovery process. Accordingly, the code for discovering physical resources in a hypervisor may be quite complex.
• some embodiments described herein relate to the launching of a hypervisor after there is already a running operating system.
• the running operating system may be used instead of the hypervisor to discover the physical resources running on the computing system.
• the hypervisor may rely on the operating system to discover the resources, rather than having to have code that performs the same functionality.
• Figure 1 illustrates a computing environment in which embodiments of the present invention may be employed
• Figure 2 illustrates a flowchart of a method for launching a hypervisor using a running operating system
• Figure 3 illustrates a flowchart of a method for launching additional operating system instances
• Figure 4A illustrates a configuration in which a root operating system, in the absence of a hypervisor, is in direct communication with physical resources of the computing system;
• Figure 4B illustrates a configuration in which the operating system has launched a hypervisor to act as an intermediary between the operating system and the physical resources;
• Figure 4C illustrates a configuration in which additional operating systems have been launched and supported by the hypervisor.
• Figure 5 illustrates a flowchart of a method for transporting the operating system to the environment of the hypervisor.
• a hypervisor may be launched after there is already a running operating system.
• the running operating system may be used instead of the hypervisor to discover the physical resources running on the computing system.
• Other operating system instances may be launched after the hypervisor is operational.
• Computing systems are now increasingly taking a wide variety of forms.
• Computing systems may, for example, be handheld devices, appliances, laptop computers, desktop computers, mainframes, distributed computing systems, or even devices that have not conventionally considered a computing system.
• the term "computing system” is defined broadly as including any device or system (or combination thereof) that includes at least one processor, and a memory capable of having thereon computer-executable instructions that may be executed by the processor.
• the memory may take any form and may depend on the nature and form of the computing system.
• a computing system may be distributed over a network environment and may include multiple constituent computing systems.
• a computing system 100 typically includes at least one processing unit 102 and memory 104.
• the memory 104 may be physical system memory, which may be volatile, non-volatile, or some combination of the two.
• An example of volatile memory includes Random Access Memory (RAM).
• Examples of non- volatile memory include Read Only Memory (ROM), flash memory, or the like.
• RAM Random Access Memory
• Examples of non- volatile memory include Read Only Memory (ROM), flash memory, or the like.
• ROM Read Only Memory
• flash memory or the like.
• the term "memory” may also be used herein to refer to non-volatile mass storage such as physical storage media. Such storage may be removable or non-removable, and may include (but is not limited to) PCMCIA cards, magnetic and optical disks, magnetic tape, and the like.
• module can refer to software objects or routines that execute on the computing system.
• the different components, modules, engines, and services described herein may be implemented as objects or processes that execute on the computing system (e.g., as separate threads). While the system and methods described herein may be implemented in software, implementations in hardware, and in combinations of software and hardware are also possible and contemplated.
• FIG. 1 In the description that follows, embodiments of the invention are described with reference to acts that are performed by one or more computing systems. If such acts are implemented in software, one or more processors of the associated computing system that performs the act direct the operation of the computing system in response to having executed computer-executable instructions. An example of such an operation involves the manipulation of data.
• the computer-executable instructions (and the manipulated data) may be stored in the memory 104 of the computing system 100.
• Computing system 100 may also contain communication channels 108 that allow the computing system 100 to communicate with other computing systems over, for example, network 110. Communication channels 108 are examples of communications media.
• Communications media typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism and include any information-delivery media.
• communications media include wired media, such as wired networks and direct- wired connections, and wireless media such as acoustic, radio, infrared, and other wireless media.
• the term computer-readable media as used herein includes both storage media and communications media.
• Embodiments within the scope of the present invention also include computer- readable media for carrying or having computer-executable instructions or data structures stored thereon.
• Such computer-readable media can be any available media that can be accessed by a general purpose or special purpose computer.
• Such computer-readable media can comprise physical storage and/or memory media such as RAM, ROM, EEPROM 5 CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general purpose or special purpose computer.
• Computer-executable instructions comprise, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions.
• FIG. 2 illustrates a flowchart of a method 200 for a running operating system to launch a hypervisor.
• a "hypervisor" is a software layer that is configured to be disposed between one or more running operating systems and protected physical resources.
• the hypervisor functionally multiplexes the protected physical resources for the operating systems, and manifests the resources to each operating system in a virtualized manner.
• the hypervisor acts as a special kind of abstraction layer between the operating system and the physical resources of the computing system.
• GB Gigabyte
• RAM Random Access Memory
• the hypervisor may allocate half of the processor cycles to each operating system, and half of the memory (512 Megabytes (MB) of RAM) to each operating system. Furthermore, the hypervisor may provide a virtualized range of RAM addressed to each operating system such that it appears to both operating systems that there is only 512 MB of RAM available. When the operating system attempts to communicate with a physical resource and vice versa, the hypervisor performs appropriate buffering and transformations to allow each operating system to experience its environment as though it was the only operating system running on the computing system. [026] Unlike conventional hypervisor configurations, embodiments of the present invention permit the hypervisor to be launched after the operating system has been launched, even if the operating system has already discovered the physical resources of the computing system. The operating system that starts the hypervisor passes information representing the state of the discovered physical resources to the hypervisor. Thus, the hypervisor need not have separate code to discover the physical resources of the computing system.
• the operating system may pause execution and pass control to the hypervisor.
• the hypervisor could then set up a virtual machine instance to handle future access requests to any protected resources of the computing system's physical resources.
• the virtual machine instance is initialized with state that is consistent with the operating system's concept of the protected physical resources.
• the operating system resumes in the virtual machine environment.
• the operating system interfaces with the physical resources indirectly through the hypervisor, rather than directly with the physical resources. The change is transparent to the operating system since the virtual machine that is dedicated to communication with the operating system honors the information the operating system had previously discovered about the physical resources.
• the operating system may not be possible for the operating system to discover a protected physical resource without the use of the hypervisor, and then interface later indirectly with that same protected physical resource through the hypervisor in a transparent manner.
• the operating system may be configured to understand that it might later be operating through a hypervisor, and to thus ignore any of the physical resources that cannot later be virtualized in a transparent manner.
• the operating system loader may be configured to inform other operating system components not to use particular protected physical v resources.
• the method 200 begins when the root operating system is launched (act 201).
• a "root” operating system is the operating system that launches the hypervisor, as contrasted with operating systems that may be launched after the hypervisor is operational.
• Figure 4A illustrates a configuration 400A at this stage of operation in which the operating system 401 communicates directly 404 with the physical resources 402 of the computing system in the absence of a hypervisor.
• the root operating system then performs several acts that are illustrated in the left column of Figure 2 under the column header "ROOT OPERATING SYSTEM". For instance, the root operating system discovers at least one physical resource (act 211A). Operating systems typically have instructions that discover the physical resources of the computing system that are executed soon after launching the operating system.
• the operating system 401 discovers physical resource state 403. Discovering physical resources of a computing system can be a complex task. [031] In order to resume the operating system in the state before the launch of the hypervisor, the operating system captures the state of the physical machine prior to the launching the hypervisor. In one embodiment, the captured state includes the state of all the physical processors and the physical APICs. The physical processor state includes:
• Ds Debug registers
• RIP Instruction Pointer
• RSP Stack Pointer
• RFLAGS Flags Register
• Segment state for CS, DS, SS, ES, FS, GS and TR segments including the segment bases, limits and access rights.
• GDTR Global Descriptor Table Register
• IDTR Interrupt Descriptor Table Register
• LDTR Local Descriptor Table Register
• the physical Local APIC state may includes:
• ISR In-Service-Register
• TPR Task Priority Register
• Physical nodes including those that have no associated resources at boot time but may be populated at runtime
• the operating system also launches the hypervisor (act 211B) that is to be interposed between the operating system and the physical resources.
• the hypervisor 405 is interposed between the root operating system 401 and the physical resources 402.
• the operating system provides state information for at least the physical resources to be protected to the hypervisor (act 212).
• This state information includes all the information that a hypervisor would need to discover the relevant state of the protected physical resources that are to be guarded by the hypervisor.
• the state information might include the capture state described above. At the very least, the state information includes at least an identification of the corresponding physical resources.
• the operating system passes control to the hypervisor.
• the hypervisor then performs acts as illustrated in the right column of Figure 2 under the heading "HYPERVISOR".
• the hypervisor then performs tasks necessary to virtualize the protected physical resources of the computing system to the root operating system (act 221).
• the hypervisor may create a virtual machine instance for the root operating system (act 231).
• block 421 represents a virtual machine instance for the operating system 401.
• the virtual machine instance 421 will serve as a proxy for the physical resources 402 for the operating system 401.
• the virtual machine instance 421 will receive service requests from the operating system 401 for the physical resources, and will perform appropriate transformations and buffering of the requests depending on the state information accessible to the virtual machine instance 421.
• the virtual machine instance 421 will then cause the hypervisor 405 to request the appropriate service from the physical resources 402.
• the virtual machine instance 421 will potentially also report back the results of the request to the operating system 401 with appropriate transformations and buffering as needed.
• the virtual machine instance 421 will behave differently depending on the state information accessible to the virtual machine instance.
• the hypervisor honors the state information that the operating system 401 has already discovered regarding the physical resources 402.
• the hypervisor 405 initializes the virtual machine instance 421 with at least some of the state information provided by the operating system (act 232).
• the hypervisor 405 may initialize the virtual machine with the capture state provided by the operating system.
• the virtual machine instance 421 is initialized with state consistent with the information representing the physical resources detected by the operating system.
• the operating system is then resumed in the virtual machine environment (act 233 and act 214).
• the physical resources 402 are virtualized for the operating system 401 through the use of the virtual machine instance 421 and the hypervisor 405. Since the state information used by the virtual machine 421 is consistent with the state information discovered by the operating system 401, the change is transparent to the operating system 401 is some embodiments.
• the virtualization is provided via a virtual processor abstraction which emulates the behavior of the physical processor. Similarly it provides a virtual APIC which emulates the behavior of the physical APIC. This is achieved as follows:
• the state of the virtual processor is initialized to the captured state of the physical processor.
• the state of the virtual APIC is initialized to the captured state of the physical Local APIC.
• the hypervisor installs intercepts to prevent the operating system from accessing privileged physical hardware resources. For example, the guest physical address ' where the local APIC was previously located prior to launching the hypervisor is marked as not present so that all accesses to the local APIC are trapped into the hypervisor.
• the hypervisor may launch additional operating systems, either instances of the same operating system, or instances of different operating systems. For example, referring to Figure 4C, operating systems 412 and 413 amongst potentially others as represented by the ellipses 414 may additionally be launched.
• Figure 3 illustrates a flowchart of a method 300 for virtualizing physical resources to the additional operating systems as well.
• the hypervisor first launches a corresponding virtual machine instance (act 301), through which the operating system is then launched (act 302).
• the hypervisor uses the corresponding virtual machine instance to virtualize the physical resource(s) to the corresponding additional operating system (act 303).
• the operating system that launches the hypervisor may be in a different environment type. For instance, perhaps the operating system is operating in 32- bit mode, whereas the hypervisor to be launched is to operate in 64-bit mode, or vice versa. Similarly, the operating system and the hypervisor may be operating in different paging modes. Some embodiments of the present invention allow the operating system to launch the hypervisor even if the operating system and hypervisor are operating in different environments.
• Figure 5 illustrates a flowchart of a method 500 for the operating system to enter the environment of the hypervisor in preparation for launching the hypervisor. From act 201 of Figure 5 in which the operating system is launched, the operating system first renders inactionable any non-maskable interrupts (act 501), and masks any maskable interrupts. Non-maskable interrupts may be rendered inactionable in a number of different ways. After all, when the operating system is in transition to the hypervisor operating environment, care should be taken to ensure that no interrupts or exceptions occur before the initial state of the hypervisor is loaded.
• NMIs Non-maskable interrupts
• the temporary page tables can map the temporary EDT, the NMI handler and stack at their original virtual addresses and their respective physical addresses. This ensures that if an NMI arrives when the processor is running with the temporary page tables it will be correctly delivered to the handler.
• a temporary virtual machine instance is created (act 502).
• the operating system then initializes the temporary virtual machine instance with an instruction that causes an intercept (act 503).
• An intercept is a transfer of control from the operating system to the hypervisor.
• the virtual machine instance executes the instructions that causes the intercept, and the intercept is thus generated (act 505).
• the temporary virtual machine instance starts executing using the hypervisor state (act 506), thereby causing the operating system to continue operation in hypervisor mode (act 507).
• the operating system may then launch the hypervisor.
• the temporary virtual machine instance may be destroyed (act 508), since it was only needed to put the operating system into the hypervisor mode necessary to launch the hypervisor.
• embodiments of the present invention permit a hypervisor to be launched even after there is already a running operating system present on the computing system.
• the operating system may launch the hypervisor even if the operating system and hypervisor are in different environments.

Landscapes

• Engineering & Computer Science (AREA)
• Software Systems (AREA)
• Theoretical Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Stored Programmes (AREA)
• Debugging And Monitoring (AREA)
• Hardware Redundancy (AREA)

Priority Applications (9)

Applications Claiming Priority (2)

Publications (1)

Family

ID=38686563

Family Applications (1)

Country Status (14)

Cited By (1)

Families Citing this family (36)

Citations (5)

Family Cites Families (11)

• 2006
  • 2006-05-15 US US11/383,455 patent/US8176485B2/en not_active Expired - Fee Related
• 2007
  • 2007-05-03 TW TW096115773A patent/TW200813833A/zh unknown
  • 2007-05-14 WO PCT/US2007/011545 patent/WO2007133741A1/en not_active Ceased
  • 2007-05-14 JP JP2009511012A patent/JP2009537897A/ja not_active Withdrawn
  • 2007-05-14 MX MX2008014548A patent/MX2008014548A/es not_active Application Discontinuation
  • 2007-05-14 CA CA002648874A patent/CA2648874A1/en not_active Abandoned
  • 2007-05-14 CN CN2007800177917A patent/CN101449240B/zh not_active Expired - Fee Related
  • 2007-05-14 BR BRPI0711369A patent/BRPI0711369A8/pt not_active Application Discontinuation
  • 2007-05-14 ES ES07777032T patent/ES2744379T3/es active Active
  • 2007-05-14 RU RU2008145040/08A patent/RU2446447C2/ru active
  • 2007-05-14 AU AU2007249730A patent/AU2007249730A1/en not_active Abandoned
  • 2007-05-14 KR KR1020087027870A patent/KR20090009866A/ko not_active Withdrawn
  • 2007-05-14 EP EP07777032.9A patent/EP2024826B1/en active Active
• 2008
  • 2008-10-21 NO NO20084432A patent/NO20084432L/no not_active Application Discontinuation

Patent Citations (5)

Non-Patent Citations (2)

Also Published As

Similar Documents

Legal Events