Advanced Micro Devices Corporation

Globalfoundries Inc.

Other

Intel Corporation

Michael Haertel

Geoffrey S Strongin

Mark Douglas Hummel

Mitchell K Alsup

Andrew William Lueck

Benjamin Charles Serebrin

David J Sager

Michael G Frank

Maurice B Steinman

William Alexander Hughes

Eric A Sprangle

R Stephen Polzin

I Claude Denton

Ole Bentz

Andrej Kocev

David Leibs

A data processing device includes one or more state registers to store state information associated with an execution core of the device. Each state register includes an associated 'dirty' bit. When a guest program is executed at the execution core, a dirty bit is set in response to a change in the state information at the associated state register. In response to a world switch from the guest program to a VMM, the state information at each state register is stored to memory only if the associated dirty bit is set. In addition, if the VMM changes any stored state information, it clears a 'clean' bit associated with the changed information. In response to a world switch from the VMM to a guest, the state information associated with cleared clean bits is retrieved from memory.

World switch between virtual machines with selective storage of state information

In one embodiment, a processor comprises one or more registers coupled to an execution core. The registers are configured to store an intercept configuration that identifies which of a plurality of intercept events are enabled for intercept during guest execution. Additionally, the intercept configuration identifies, for each enabled intercept event, which of at least two exit mechanisms are to be used in response to detection of the enabled intercept event. The execution core is configured to detect one of the enabled intercept events during execution of a guest and to exit the guest using the exit mechanism identified in the intercept configuration for that detected, enabled intercept event.

Processor and method configured to determine an exit mechanism using an intercept configuration for a virtual machine

A method and apparatus for implementation of error correction code (ECC) checking in non-ECC-compliant components. The method includes receiving a logical address, wherein the logical address maps to first and second physical addresses of a memory. The first and second physical addresses of the memory correspond to memory locations that store data and a corresponding ECC, respectively. The method further comprises translating the logical address into the first and second physical addresses, accessing the data over a data path, separately accessing the ECC over the same data path, and checking the integrity of the data using the ECC.

ECC implementation in non-ECC components

In one embodiment, a processor supports an alternate address space during execution of non-guest code (such as a minivisor or a virtual machine monitor (VMM)). The alternate address space may be the guest address space. An instruction in the minivisor/VMM may specify the alternate address space for a data access, permitting the minivisor/VMM to read guest memory state via the alternate address space. In another embodiment, a processor may implement a page table base address register dedicated for the minivisor's use. In still another embodiment, the minivisor may be implemented as a specified entry point in the VMM address space.

Separate page table base address for minivisor

In one embodiment, a processor comprises an execution core, a level 1 (L1) data cache coupled to the execution core and configured to store data, and a transient/transactional cache (TTC) coupled to the execution core. The execution core is configured to generate memory read and write operations responsive to instruction execution, and to generate transactional read and write operations responsive to executing transactional instructions. The L1 data cache is configured to cache memory data accessed responsive to memory read and write operations to identify potentially transient data and to prevent the identified transient data from being stored in the L1 data cache. The TTC is also configured to cache transaction data accessed responsive to transactional read and write operations to track transactions. Each entry in the TTC is usable for transaction data and for transient data.

Transient transactional cache

In one embodiment, a system comprises one or more input/output (I/O) devices; an I/O memory management unit (IOMMU) coupled to receive memory requests sourced by the I/O devices and configured to provide address translation for the memory requests; and a virtual machine monitor (VMM) configured to manage one or more virtual machines on the system, wherein the VMM is configured to virtualize the IOMMU, providing one or more virtual IOMMUs for use by one or more virtual machines.

Virtualizing an IOMMU

In an embodiment, an input/output (I/O) memory management unit (IOMMU) comprises at least one memory configured to store translation data; and control logic coupled to the memory and configured to translate an I/O device-generated memory request using the translation data. The translation data corresponds to one or more device table entries in a device table stored in a memory system of a computer system that includes the IOMMU, wherein the device table entry for a given request is selected by an identifier corresponding to the I/O device that generates the request. The translation data further corresponds to one or more I/O page tables, wherein the selected device table entry for the given request includes a pointer to a set of I/O page tables to be used to translate the given request.

Direct memory access (DMA) address translation in an input/output memory management unit (IOMMU)

Address translation for input/output (I/O) devices and interrupt remapping for I/O devices in an I/O memory management unit (IOMMU)

In one embodiment, an input/output (I/O) node comprises an I/O memory management unit (IOMMU) configured to translate memory requests. The I/O node is configured to couple to an interconnect and to operate as a tunnel on the interconnect, and wherein the IOMMU is configured translate memory requests passing through the tunnel in the upstream direction. In another embodiment, a system comprises another I/O node configured to bridge another interconnect to the interconnect, wherein the I/O node is the tunnel for the other I/O node.

Chained hybrid input/output memory management unit

In an embodiment, a computer system comprises a processor; a memory management module comprising a plurality of instructions executable on the processor; a memory coupled to the processor; and an input/output memory management unit (IOMMU) coupled to the memory. The IOMMU is configured to implement address translation and memory protection for memory operations sourced by one or more input/output (I/O) devices. The memory stores a command queue during use. The memory management module is configured to write one or more control commands to the command queue, and the IOMMU is configured to read the control commands from the command queue and execute the control commands.

Controlling an I/O MMU

In an embodiment, an input/output memory management unit (IOMMU) is configured to receive a completion wait command defined to ensure that one or more preceding invalidation commands are completed by the IOMMU prior to a completion of the completion wait command. The IOMMU is configured to respond to the completion wait command by delaying completion of the completion wait command until: (1) a read response corresponding to each outstanding memory read operation that depends on a translation entry that is invalidated by the preceding invalidation commands is received; and (2) the control unit transmits one or more operations upstream to ensure that each memory write operation that depends on the translation table entry that is invalidated by the preceding invalidation commands has at least reached a bridge to a coherent fabric in the computer system and has become visible to the system.

Avoiding silent data corruption and data leakage in a virtual environment with multiple guests

In one embodiment, an input/output memory management unit (IOMMU) comprises a cache to cache translation data from memory; and a control unit coupled to the cache. The control unit is configured to implement address translation and memory protection for memory requests sourced by one or more input/output (I/O) devices. The memory requests sourced by the I/O devices travel in one or more first virtual channels, and the control unit is configured to transmit memory requests sourced by the control unit in at least a second virtual channel separate from the first virtual channels.

Ensuring deadlock free operation for peer to peer traffic in an input/output memory management unit (IOMMU)

A flexible architecture is presented that allows either Synchronous Optical Network (SONET) framing, Optical Transport Network (OTN) framing, or SONET framing followed by OTN framing. The architecture consists of SONET frame processors, OTN frame processors, and a configurable selection network.

Flexible architecture for SONET and OTN frame processing

A method and apparatus to execute data speculative instructions in a processor comprising at least one source register, each source register comprising a bit to indicate validity of data in the at least one source register. A data validity circuit coupled to the one or more source registers to determine the validity of the data in the source registers, and to indicate the validity of the data in a destination register based upon the validity bit in the at least one source register. The processor optionally comprising a checker unit to retire those instructions from the execution unit which write valid data to the destination register, and to re-schedules those instructions for execution which write invalid data to the destination register.

Growing community of inventors

Sunnyvale, CA, United States of America

Michael Haertel