Intel Corporation

Mcafee, Inc.

Ravi L Sahita

David M Durham

Vedvyas Shanbhogue

Barry E Huntley

Gilbert A Neiger

Uday R Savagaonkar

Baiju V Patel

Jason W Brandt

Michael Lemay

Hormuzd M Khosravi

Xiaoning Li

Deepak K Gupta

Siddhartha Chhabra

Karanvir S Grewal

Gideon Gerzon

Travis T Schluessler

Andrew V Anderson

Ido Ouziel

David A Koufaty

Abhishek Basak

Rajesh M Sankaran

Carlos V Rozas

Prashant Dewan

Manohar Ruben Castelino

Ned M Smith

Jr-Shian Tsai

Ioannis T Schoinas

Vincent R Scarlata

Utkarsh Y Kakaiya

Mingqiu Sun

Francis X Mckeen

Andrew J Herdrich

Scott Dion Rodgers

Asit K Mallick

Rupin H Vakharwala

Mesut A Ergin

Kshitij Arun Doshi

Kapil Sood

Michael E Kounavis

Pradeep M Pappachan

Nitin V Sarangdhar

Vadim Sukhomlinov

Robert S Chappell

Scott H Robinson

Jacob Doweck

Tsung-Yuan Charles Tai

Sanjeev N Trika

Tobias Max Kohlenberg

Koichi Yamada

Igor Tatourian

Men Long

Joseph Nuzman

Krystof C Zmudzinski

Stanislav Shwartsman

Wei Wang

Mona Vij

Beeman C Strong

Ofer Levy

Edwin Verplanke

Alpa T Narendra Trivedi

Nikhil M Deshpande

Francesc Guim Bernat

Balaji Vembu

Mohan J Kumar

Manoj R Sastry

Karthik Kumar

Reshma Lal

Ren Wang

Jesse R Walker

Hong C Li

Ravishankar Iyer

Geoffrey S Strongin

Raanan Sade

Arvind A Kumar

James P Kardach

Santosh Ghosh

Sara S Baghsorkhi

Debra Bernstein

Alexander W Min

Raj K Ramanujan

Scott R Janus

Raghunandan Makaram

Yong Jiang

Selvakumar Panneer

Bin Xing

Parthasarathy Sarangam

Ravi Rajwar

Michael A Goldsmith

Sergej Deutsch

Jason Martin

Alexander Bachmutsky

Robert L Vaughn

Ian M Steiner

David J Cowperthwaite

Marcos Emanuel Carranza

Rameshkumar G Illikkal

Erik J Johnson

Anjali Singhai Jain

Cedric Cochin

Methods and apparatus to set guest physical address mapping attributes for a trusted domain In one embodiment, the method includes executing a first one or more of instructions to establish a trusted domain and executing a second one or more of the instructions to add a first memory page to the trusted domain, where the first memory page is private to the trusted domain and a first set of page attributes is set for the first memory page based on the second one or more of the instructions, where the first set of page attributes indicates how the first memory page is mapped in a secure extended page table. The method further includes storing the first set of page attributes for the first memory page in the secure extended page table at a storage location responsive to executing the second one or more of the instructions.

Method and apparatus to set guest physical address mapping attributes for trusted domain

In one embodiment, an apparatus comprises a processor to execute instruction(s), wherein the instructions comprise a memory access operation associated with a memory location of a memory. The apparatus further comprises a memory encryption controller to: identify the memory access operation; determine that the memory location is associated with a protected domain, wherein the protected domain is associated with a protected memory region of the memory, and wherein the protected domain is identified from a plurality of protected domains associated with a plurality of protected memory regions of the memory; identify an encryption key associated with the protected domain; perform a cryptography operation on data associated with the memory access operation, wherein the cryptography operation is performed based on the encryption key associated with the protected domain; and return a result of the cryptography operation, wherein the result is to be used for the memory access operation.

Multi-key cryptographic memory protection

Technologies for untrusted code execution include a computing device having a processor with sandbox support. The computing device executes code included in a native domain in a non-privileged, native processor mode. The computing device may invoke a sandbox jump processor instruction during execution of the code in the native domain to enter a sandbox domain. The computing device executes code in the sandbox domain in a non-privileged, sandbox processor mode in response to invoking the sandbox jump instruction. While executing in the sandbox processor mode, the processor denies access to memory outside of the sandbox domain and may deny execution of one or more prohibited instructions. From the sandbox domain, the computing device may execute a sandbox exit instruction to exit the sandbox domain and resume execution in the native domain. The computing device may execute processor instructions to configure the sandbox domain. Other embodiments are described and claimed.

Technologies for untrusted code execution with processor sandbox support

Examples described herein relate to an Infrastructure Processing Unit (IPU) that comprises: interface circuitry to provide a communicative coupling with a platform; network interface circuitry to provide a communicative coupling with a network medium; and circuitry to expose infrastructure services to be accessed by microservices for function composition and to selectively provide a barrier to halt operation of at least one microservice based on event data from a composite node that performs the at least one microservice.

Infrastructure processing unit

A processor of an aspect includes a decode unit to decode an aperture access instruction, and an execution unit coupled with the decode unit. The execution unit, in response to the aperture access instruction, is to read a host physical memory address, which is to be associated with an aperture that is to be in system memory, from an access protected structure, and access data within the aperture at a host physical memory address that is not to be obtained through address translation. Other processors are also disclosed, as are methods, systems, and machine-readable medium storing aperture access instructions.

Aperture access processors, methods, systems, and instructions

Various embodiments are generally directed to techniques for training deep neural networks, such as with an iterative approach, for instance. Some embodiments are particularly directed to a deep neural network (DNN) training system that generates a hardened DNN by iteratively training DNNs with images that were misclassified by previous iterations of the DNN. One or more embodiments, for example, may include logic to generate an adversarial image that is misclassified by a first DNN that was previously trained with a set of sample images. In some embodiments, the logic may determine a second training set that includes the adversarial image that was misclassified by the first DNN and the first training set of one or more sample images. The second training set may be used to train a second DNN. In various embodiments, the above process may be repeated for a predetermined number of iterations to produce a hardened DNN.

Hardened deep neural networks through training from adversarial misclassified data

Implementations describe a computing system that implements a plurality of virtual machines inside a trust domain (TD), enabled via a secure arbitration mode (SEAM) of the processor. A processor includes one or more registers to store a SEAM range of memory, a TD key identifier of a TD private encryption key. The processor is capable of initializing a trust domain resource manager (TDRM) to manage the TD, and a virtual machine monitor within the TD to manage the plurality of virtual machines therein. The processor is further capable of exclusively associating a plurality of memory pages with the TD, wherein the plurality of memory pages associated with the TD is encrypted with a TD private encryption key inaccessible to the TDRM. The processor is further capable of using the SEAM range of memory, inaccessible to the TDRM, to provide isolation between the TDRM and the plurality of virtual machines.

Scalable virtual machine operation inside trust domains within the trust domain architecture

This disclosure is directed to a system for address mapping and translation protection. In one embodiment, processing circuitry may include a virtual machine manager (VMM) to control specific guest linear address (GLA) translations. Control may be implemented in a performance sensitive and secure manner, and may be capable of improving performance for critical linear address page walks over legacy operation by removing some or all of the cost of page walking extended page tables (EPTs) for critical mappings. Alone or in combination with the above, certain portions of a page table structure may be selectively made immutable by a VMM or early boot process using a sub-page policy (SPP). For example, SPP may enable non-volatile kernel and/or user space code and data virtual-to-physical memory mappings to be made immutable (e.g., non-writable) while allowing for modifications to non-protected portions of the OS paging structures and particularly the user space.

System for address mapping and translation protection

Techniques for expanded trusted domains are disclosed. In the illustrative embodiment, a trusted domain can be established that includes hardware components from a processor as well as an off-load device. The off-load device may provide compute resources for the trusted domain. The trusted domain can be expanded and contracted on-demand, allowing for a flexible approach to creating and using trusted domains.

Technologies for expanded trusted domains

Apparatus and method for role-based register protection. For example, one embodiment of an apparatus comprises: one or more processor cores to execute instructions and process data, the one or more processor cores to execute one or more security instructions to protect a virtual machine or trusted application from a virtual machine monitor (VMM) or operating system (OS); an interconnect fabric to couple the one or more processor cores to a device; and security hardware logic to determine whether to allow a read or write transaction directed to a protected register to proceed over the interconnect fabric, the security hardware logic to evaluate one or more security attributes associated with an initiator of the transaction to make the determination.

Apparatus and method for role-based register protection for TDX-IO

Techniques for migration of a source protected virtual machine from a source platform to a destination platform are descried. A method of an aspect includes enforcing that bundles of state, of a first protected virtual machine (VM), received at a second platform over a stream, during an in-order phase of a migration of the first protected VM from a first platform to the second platform, are imported to a second protected VM of the second platform, in a same order that they were exported from the first protected VM. Receiving a marker over the stream marking an end of the in-order phase. Determining that all bundles of state exported from the first protected VM prior to export of the marker have been imported to the second protected VM. Starting an out-of-order phase of the migration based on the determination that said all bundles of the state exported have been imported.

Methods, apparatus, systems, and instructions to migrate protected virtual machines

A processor of an aspect includes a decode unit to decode an instruction. The processor also includes an execution unit coupled with the decode unit. The execution unit, in response to the instruction, is to determine that an attempted change due to the instruction, to a shadow stack pointer of a shadow stack, would cause the shadow stack pointer to exceed an allowed range. The execution unit is also to take an exception in response to determining that the attempted change to the shadow stack pointer would cause the shadow stack pointer to exceed the allowed range. Other processors, methods, systems, and instructions are disclosed.

Processors, methods, systems, and instructions to protect shadow stacks

On-demand paging support for confidential computing is described. An example of an apparatus includes circuitry including one or more processors including a first processor, the first processor including a TEE and registers, wherein the one or more processors are to: receive a memory access request associated with a trust domain (TD), wherein one or more direct memory access payloads associated with the request being generated by a protocol engine (PE) of a peripheral device and written to a host interface (HIF), the HIF including an address translation engine (ATE); and, in response to a page fault being identified for a payload, divert the payload and forward a payload fault to one or more TD fault buffers in a set of registers, and resolve the page fault by an ATE driver and a virtual machine manager using the TEE.

On-demand paging support for confidential computing

A processor implementing techniques for processor extensions to protect stacks during ring transitions is provided. In one embodiment, the processor includes a plurality of registers and a processor core, operatively coupled to the plurality of registers. The plurality of registers is used to store data used in privilege level transitions. Each register of the plurality of registers is associated with a privilege level. An indicator to change a first privilege level of a currently active application to a second privilege level is received. In view of the second privilege level, a shadow stack pointer (SSP) stored in a register of the plurality of registers is selected. The register is associated with the second privilege level. By using the SSP, a shadow stack for use by the processor at the second privilege level is identified.

Processor extensions to protect stacks during ring transitions

In function-as-a-service (FaaS) environments, a client makes use of a function executing within a trusted execution environment (TEE) on a FaaS server. Multiple tenants of the FaaS platform may provide functions to be executed by the FaaS platform via a gateway. Each tenant may provide code and data for any number of functions to be executed within any number of TEEs on the FaaS platform and accessed via the gateway. Additionally, each tenant may provide code and data for a single surrogate attester TEE. The client devices of the tenant use the surrogate attester TEE to attest each of the other TEEs of the tenant and establish trust with the functions in those TEEs. Once the functions have been attested, the client devices have confidence that the other TEEs of the tenant are running on the same platform as the gateway.

Scalable attestation for trusted execution environments

Growing community of inventors

Beaverton, OR, United States of America

Ravi L Sahita