摘要:
An apparatus, method, and system are disclosed. In one embodiment, the apparatus comprises a trusted platform module to store a plurality of contexts, wherein each context includes stored security information for one of a plurality of physical partitions in a computer system.
摘要:
A method of system for hardening a firmware environment. A trusted core framework of firmware components are segregated from initially non-trustworthy extended firmware components such that the trusted core components are executed in a privileged processor mode, while the extended firmware components are executed in a non-privileged processor mode. An authentication of each extended firmware component is made to determine whether it is secure or non-secure. Through a memory code fault mechanism, memory accesses made by the extended firmware components are trapped, and a determination is made to whether the memory accesses should be allowed based on whether the extended firmware component is secure or non-secure and whether the requested memory page was allocated by the trusted core or a secure extended firmware component. This segregation scheme prevents non-trusted firmware from accessing privileged memory, thereby preventing rogue, errant, or malicious firmware from damaging the trusted core framework.
摘要:
Techniques and architectures to provide high assurance image invocation in a pre-boot environment. These techniques may augment implementations of the Unified Extensible Firmware Interface (UEFI) to invoke UEFI images using Trusted Execution Technology (TXT). This can operate to combine pre-boot secure flows, such as UEFI image invocation, with the secure launch instruction set extensions of TXT. This may entail combination of the UEFI StartImage instruction with the SMX leaf SENTER instruction. This may operate to allow original equipment manufacturer (OEM) firmware as a guard and that uses UEFI and TXT access control logic at the same instance to pass control to the operating system (OS).
摘要:
Embodiments of a method and system for saving system context after a power outage are disclosed herein. A power agent operates to reduce the possibility of data corruption due to partially written data during an unexpected power outage. The power agent can determine an amount of time remaining before a power store is depleted. Based on the amount of time, the power agent can store system context information. Correspondingly, the power agent can operate to save complete system context, partial system context, or flush (I/O) buffers. Once power is restored, the power agent can restore the system context based on the nature of the save. Other embodiments are described and claimed.
摘要:
Techniques and architectures to provide high assurance image invocation in a pre-boot environment. These techniques may augment implementations of the Unified Extensible Firmware Interface (UEFI) to invoke UEFI images using Trusted Execution Technology (TXT). This can operate to combine pre-boot secure flows, such as UEFI image invocation, with the secure launch instruction set extensions of TXT. This may entail combination of the UEFI StartImage instruction with the SMX leaf SENTER instruction. This may operate to allow original equipment manufacturer (OEM) firmware as a guard and that uses UEFI and TXT access control logic at the same instance to pass control to the operating system (OS).
摘要:
Provided are a method, system, and machine readable medium for using multiple non-volatile memory devices to store data in a computer system. Access to a first and second memory devices are managed. The first memory device has faster read access and slower write access relative to the second memory device and the second memory device has slower read access and faster write access relative to the first memory device. Write requests to the first memory device are cached in the second memory device.
摘要:
Methods and apparatus for event based console management in a pre-boot environment are disclosed. For example, an event handler is provided for use in a computer having a processor. The example event handler includes a console maintenance agent in communication with the controller to monitor the computer and a driver monitor in communication with the controller to monitor a first driver. The event handler also includes an error monitor in communication with the controller to monitor the computer for a system error and a driver loader in communication with the controller to load a second driver for a console.
摘要:
In one embodiment, the present invention includes a method for receiving an indication of a loss of redundancy with respect to a pair of mirrored memory regions of a partially redundant memory system, determining new mirrored memory regions, and dynamically migrating information stored in the original mirrored memory regions to the new mirrored memory regions. Other embodiments are described and claimed.
摘要:
In one embodiment, the present invention includes a method for receiving an indication of a loss of redundancy with respect to a pair of mirrored memory regions of a partially redundant memory system, determining new mirrored memory regions, and dynamically migrating information stored in the original mirrored memory regions to the new mirrored memory regions. Other embodiments are described and claimed.
摘要:
In one embodiment, the present invention includes a method for receiving an indication of a loss of redundancy with respect to a pair of mirrored memory regions of a partially redundant memory system, determining new mirrored memory regions, and dynamically migrating information stored in the original mirrored memory regions to the new mirrored memory regions. Other embodiments are described and claimed.