Abstract: An apparatus of an aspect includes a context storage to store context of a logical processor, and an execution unit coupled with the context storage. The execution unit to perform operations corresponding to a control primitive or an exceptional condition. The operations including to selectively save a first subset of the context, from a first subset of the context storage written to after entrance into a protected execution environment, to system memory, and cause the logical processor to exit the protected execution environment. Other apparatus, methods, systems, and instructions are disclosed.

Abstract: Techniques and mechanisms for a processor core to execute an instruction for a hardware (HW) thread to have access to a trusted execution environment (TEE). In an embodiment, execution of the instruction includes determining whether any sibling HW thread, which is currently active, is also currently approved to access the TEE. TEE access by the HW thread is conditioned upon a requirement that any sibling HW thread is either currently inactive, is currently in the same TEE, or is currently approved to enter the TEE. In another embodiment, execution of another instruction, for the HW thread to exit the TEE, includes or otherwise results in system software being conditionally notified of an opportunity to wake up one or more sibling HW threads.

Abstract: Example methods and systems are directed to reducing latency in providing trusted execution environments (TEEs). Initializing a TEE includes multiple steps before the TEE starts executing. Besides workload-specific initialization, workload-independent initialization is performed, such as adding memory to the TEE. In function-as-a-service (FaaS) environments, a large portion of the TEE is workload-independent, and thus can be performed prior to receiving the workload. Certain steps performed during TEE initialization are identical for certain classes of workloads. Thus, the common parts of the TEE initialization sequence may be performed before the TEE is requested. When a TEE is requested for a workload in the class and the parts to specialize the TEE for its particular purpose are known, the final steps to initialize the TEE are performed.

Abstract: Example methods and systems are directed to reducing latency in providing trusted execution environments (TEES). Initializing a TEE includes multiple steps before the TEE starts executing. Besides workload-specific initialization, workload-independent initialization is performed, such as adding memory to the TEE. In function-as-a-service (FaaS) environments, a large portion of the TEE is workload-independent, and thus can be performed prior to receiving the workload. Certain steps performed during TEE initialization are identical for certain classes of workloads. Thus, the common parts of the TEE initialization sequence may be performed before the TEE is requested. When a TEE is requested for a workload in the class and the parts to specialize the TEE for its particular purpose are known, the final steps to initialize the TEE are performed.