DEVICE VIRTUALIZATION IN A CONFIDENTIAL COMPUTING ENVIRONMENT

The implementation of attested and encrypted emulated devices with unique identifiers addresses MITM attacks in confidential computing environments, enhancing data security and compliance.

DE102023128805A1Pending Publication Date: 2024-11-28INTEL CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
DE102023128805
Authority / Receiving Office
DE · DE
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-22
Filing Date
2023-10-19
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Existing devices in confidential computing environments are vulnerable to man-in-the-middle (MITM) attacks due to spoofing of PCIe devices, leading to potential data theft and identity loss, as they lack proper endpoint authentication and encryption.

Method used

Implementing a trusted SEP or emulated device with attestation and encryption mechanisms, including unique identifiers signed with keys, to ensure secure access and communication within a confidential computing cluster, using technologies like TCG Device Identifier Composition Engine (DICE) and Total Memory Encryption (TME) to protect data at rest and in transit.

Benefits of technology

Reduces the likelihood of MITM attacks by ensuring secure and trusted access to emulated devices, protecting data integrity and confidentiality, and meeting regulatory requirements for customer data protection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

The examples described herein concern a trusted and secure emulated device. The emulated device can be assigned to a service based on attesting to the emulated device's hardware platform, assigning the emulated device to a trusted domain, and attesting to a device configuration associated with the emulated device.
Need to check novelty before this filing date? Find Prior Art

Description

STATE OF THE ART

[0001] The Peripheral Component Interconnect Special Interest Group (PCI-SIG) Integrity and Data Encryption (IDE) specification (December 2, 2020) requires devices connected to a central processing unit (CPU), system on a chip (SoC), network interface device, or other device to provide: (1) a trusted identity (e.g., in the form of a private key), (2) endpoint authentication (e.g., to ensure that the devices and their firmware originate from a trusted source), (3) the establishment of keys for the Peripheral Component Interconnect Express (PCIe) interconnect communication session (e.g., to establish new sets of keys), and (4) encryption and integrity (e.g., to protect data shared between the device and the SoC, CPU, or network interface device). BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 shows an example system. Fig. 2A and Fig. 2B show example systems. Fig. 3 shows an example of a register lock. Fig. Figure 4 shows an example of end-to-end tenant attestation of an emulated SEP device in a trust domain (TD). Fig. 5 shows an example process for assigning an emulated device. Fig. 6 shows an example process. Fig. Figure 7 shows an example system. Fig. Figure 8 shows an example system. DETAILED DESCRIPTION

[0002] In some platforms, a network interface device may include an intelligent endpoint (SEP), which may provide an intermediary between a server and circuitry in the network interface device. Applications running on the server may communicate with the SEP as if they were communicating with the network interface device, and the SEP may provide applications with access to circuitry of the network interface device. An SEP may provide applications with access to emulated PCIe devices through one or more emulated SEPs.

[0003] In some cases, the SEP or an emulated SEP can be used for a man-in-the-middle (MITM) attack by spoofing a PCIe device and accessing data or commands intended for that spoofed PCIe device, or the spoofed PCIe device delivers malicious data or commands to a tenant's virtual machine (VM) or container. A SEP can act as a MITM if a tenant is unaware of the SEP's use as an intermediary or delivers data to the SEP without encryption. A masquerading attack can occur if a virtual machine (VM) or container delivers data to or retrieves data from the emulated device that is not an authorized emulated device. For example, identity theft can occur, which can lead to the loss of data and identity credentials, including user and subscriber data.

[0004] To at least attempt to reduce the likelihood of successful MITM attacks, a trusted SEP or other circuitry or firmware may be attested prior to assigning an emulated device to a trust domain. The trusted SEP or other circuitry or firmware may constitute an emulated device and may provide an entity with access to the emulated device via a device interface. The SEP or other circuitry or firmware may include technology to communicate with a particular emulated device using a unique identifier attested using signed keys, so that the unique identifier can be validated and attested prior to communication with the emulated device and prior to communications to and from the emulated device.The SEP or other circuitry or firmware can provide trusted and secure access to the emulated device to a virtual execution environment.

[0005] In some examples, the emulated device has an associated cryptographic domain to preclude access by unauthorized access operations to the emulated device and associated data. The entity and the emulated device may operate as part of a confidential computing cluster, and data may be encrypted and decrypted using keys available for use in a particular confidential computing cluster. Examples may extend confidential computing technologies to cover server systems, SEPs, and backend devices. An entity may include a virtual machine, container, application, process, service, microservice, or others. An emulated device may represent an allocation of shared or non-shared software and hardware resources.Based on a successful attestation of the emulated SEP device, a tenant can be assigned the use of the SEP emulated device and can access the emulated SEP device.

[0006] Accordingly, prior to assigning the emulated device to a virtualized execution environment, various examples provide a trusted emulated device (e.g., a trusted emulated SEP device) based on one or more of: attesting hardware underlying the emulated device, assigning the emulated device to a trust domain, attesting a device configuration associated with the emulated device, and attesting and authenticating an emulated device identifier.

[0007] Accordingly, an entity can avoid communicating with an emulated device if an identifier of the emulated device does not match an approved emulated device identifier. Furthermore, even if the entity communicates with a spoofed emulated device, shared or received data can be protected so that the spoofed device is unable to access it from the entity. Additionally, by using a SEP or emulated devices, a tenant can meet regulatory requirements to protect customer data at rest, in motion between storage devices, or during processing.

[0008] Fig. 1 shows an example system. Intelligent endpoint (SEP) or endpoint circuitry 100 may provide an intermediary between a host system (e.g., a server) 110 and a protocol engine 160. SEP 100 may utilize a work scheduler 104 to schedule the transmission of commands and communications received from host 110 via host interface 120 to protocol engine 160 or via fabric 170 to cores 108-0 through 108-X, where X≥1. In some examples, SEP 100 may utilize a microcontroller 106 to perform SEP 100 operations, such as a security agent or security controller, as described herein. SEP 100 may utilize a DMA engine 102 to copy data to or from host 110.

[0009] Protocol engine 160 may provide commands and communications between an application and operating system (OS) executed by processors on host 110 and device 190 according to one or more applicable application program interfaces (APIs) or protocols (e.g., Non-Volatile Memory Express (NVMe) or others). In some examples, protocol engine 160 may be associated with device 190 (e.g., a network interface device, a storage controller, a storage device (e.g., an NVMe drive), a storage pool controller, a graphics processing unit, a cryptographic processor, or other device).

[0010] The SEP 100 can emulate a specific Peripheral Component Interconnect Express (PCIe) device or other input / output (I / O) virtualization interface. For example, the SEP 100 can emulate a PCIe device frontend, performing one or more of the following backend operations: a local area network (LAN) protocol engine (PE) 160, the device 190, or the cores 108-0 through 108-X. For example, the SEP 100 can provide access to one or more virtual or emulated instances of a SEP and its backend per customer parameter and system configuration.For example, according to a customer's parameters and system configurations, an emulated instance of the SEP based on shared or exclusively dedicated software and / or hardware may include an instance of one or more of the following: storage devices, specific software and / or hardware accelerators, network interfaces, or other devices. The processing engine 160 and / or firmware executing in the SEP 100 may expose registers of an emulated SEP device for access by applications executing from the host 110. Emulated device instances may use shared infrastructure, circuitry, and / or hardware resources (e.g.,Memory 162, storage, buffers, other direct memory access (DMA) engines 102, the work scheduling unit 104, the microcontroller 106, the fabric 170, cryptographic circuitry, compression circuitry and DMA circuitry 180, accelerators (e.g., field-programmable gate arrays (FPGAs)), storage controllers, and others). The SEP 100 can be used in edge and cloud-to-edge use cases where communication service providers (CoSPs) and cloud service providers (CSPs) can create emulated devices to perform multi-tenant workloads (WLS).

[0011] Additionally, instances of emulated devices can coexist, can be stopped and restarted as new devices, can be paused and resumed as the same device or platform, or a different device or platform. For example, code, data, and context state for an emulated device can be stored in a TD associated with a tenant, and the code, data, and context state can continue to be stored based on the TD associated with the tenant going offline, and can resume access to the emulated device's state after the TD is rescheduled for use by an operating system (OS) or hypervisor. A customer can access one or more of the emulated devices concurrently or in staggered usage patterns.

[0012] Fig. 2A shows an example system. A host 200 may include one or more processors, one or more memory devices, one or more device interfaces, and other circuitry and software that may be configured at least with respect to Fig. 7 and / or 8. Processors of host 100 may execute software, such as applications 202 (e.g., services, microservices, virtual machines (VMs), micro VMs, containers, processes, threads, or other virtualized execution environments), an operating system (OS), and one or more device drivers 204. For example, applications 202 executing on host 200 may communicate with a device 250 using device driver 204 to receive or send packet traffic using device 250 and / or send commands to or receive commands from device 250. A virtual machine manager (VMM) 206 and a trusted VMM 208 may provide virtualized access to emulated devices, as described herein.

[0013] The host 200 may communicate with the device 250 using a system interface 220. The system interface 220 may include communication circuitry, such as a bus or other conductive circuitry.

[0014] Device 250 may include at least one or more security controllers 258, endpoint circuitry 252, such as a SEP, and hardware resources 254. Endpoint circuitry 252 may provide access to one or more emulated instances of a SEP as emulated devices 256-0 through 256-X. For example, via system interface 220, emulated devices 256-0 through 256-X may be accessible via a PCIe, Compute Express Link (CXL), Universal Chiplet Interconnect Express (UCIe), Single Root I / O Virtualization (SR-IOV), or Scalable Input / Output (I / O) Virtualization (S-IOV) virtual device.

[0015] Trusted firmware executing on device 250 or controller 258 may create instances of the emulated endpoint devices by providing special register accesses and a hardware composition to emulated device instances. For example, emulated devices 256-0 through 256-X may represent a composition of emulated endpoint circuitry 252 and / or other hardware resources 254.The hardware resources 254 may include one or more of the following: firmware, software, circuitry, cache, memory, storage, a microprocessor, a processor, an accelerator, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a network interface device, a storage controller, a memory pool controller, a graphics processing unit, a cryptographic processor, or other software or devices operative with respect to at least one or more of. Fig. 7 or Fig. 8 are described.

[0016] For example, an emulated device may implement a virtual storage device in virtio mode to enable virtual storage devices, the emulated device may handle virtio queues, and a Storage Performance Development Kit (SPDK)-based backend service running on a compute complex (e.g., cores 108-0 through 108-X) may perform storage operations. Reference to virtio devices could include either virtio-net or virtio-blk.

[0017] A security controller 258 may provide platform or end-to-end (E2E) security for a multi-tenant data center. The security controller 252 may provide trusted software, firmware, and hardware that are signed and verified at boot time and prior to the creation of an emulated device. Trusted Computing Group (TCG) Device Identifier Composition Engine (DICE) standards (e.g., DICE Attestation Architecture Version 1.00 (2020) and earlier versions, revisions, and variations thereof) may be used to sign and verify software, firmware, and hardware. Additionally, the security controller 252 may provide a root trust for the emulated devices 256-0 through 256-X, where X > 1, as well as the device 250, the endpoint circuitry 252, and / or the hardware resources 254.The security controller 252 can provide keys for emulated devices and attestation and signing of emulated device identifiers. Keys can be used by applications and devices assigned to a particular tenant.

[0018] The security controller 258 may assign a unique identifier to an emulated endpoint device (e.g., SEP device) with a specific configuration. In some examples, trusted firmware executed by the security controller 258 may generate an emulated device identifier for each emulated SEP based on public and private pairs. If multiple emulated devices are created, each of the multiple emulated devices may be assigned its own unique identifier despite being used by one or more tenants. The security controller 258 may track an emulated device instance and its identifier and store the encrypted emulated device instance and identifier in encrypted storage. For example, an emulated device identifier may be based on a unique hash composed of a public and private key pair (e.g.,Rivest-Shamir-Adleman (RSA), Elliptic Curve Cryptography (ECC) or others) or blockchain-based identities.

[0019] For example, keys for one or more of the following may be signed by authorized parties or devices (e.g., the security controller 252 or an attestation server): firmware (e.g., security version number (SVN)), the endpoint circuitry 252, software, and hardware resources 254 (e.g., circuitry, accelerators, memory devices, storage devices, or others). An attestation root key may be used to sign a hash value obtained by concatenating the initial boot firmware or software and subsequent firmware or software images located in the Trusted Compute Base (TCB) of the SEP-emulated devices.

[0020] In some examples, keys per emulated device may be generated by secure and trusted firmware executed by the trusted network interface device 250. In some examples, the security controller 258 may generate keys with handles to the firmware to assign unique keys to generated emulated devices. Emulated devices may be assigned a unique key and thus a unique identity. For example, an emulated device identity may be a hash of a concatenation of the public key portion, configuration, and initial emulated device firmware identifiers, and signed by the security controller 258 or the trusted firmware of the device 250.

[0021] The security controller 258 and / or the trusted firmware executed by the network interface device 250 can dynamically generate keys and assign them to a physical function (PF) or the endpoint circuitry 252. For physical devices connected to Trusted Domain Extensions (TDX), the keys can be securely provided to the security controller 258 and / or the device 250 during a manufacturing process.

[0022] Attestation and authentication of device 250 may be performed as part of a PCIe Link security key protocol (e.g., PCI-SIG IDE standard), which may authenticate device 250 and generate shared pairwise unique keys for encryption for communications between host 200 and device 250. A tenant may authenticate device 250 through its trust domain (TD), and device 250 may be packaged as part of an attestation notation that receives the TD from an emulated device signed by an attestation root key of device 250.

[0023] In some examples, emulated devices may operate independently in cryptographically isolated trust domains. A cryptographic domain may be associated with an attested identifier and keys assigned for use in a particular domain. The security controller 252 may provide cryptographic isolation of at least one of the emulated devices 256-0 through 256-X. For example, shared resources (e.g., buffers, memory 259, state machine circuitry, accelerators, etc.) may have access control and data access separation, with shared queues, state machines either dedicated to an emulated device for exclusive use and / or identified and accessed using an emulated device identifier (ID), and data access protection schemes utilized (e.g.,Data encryption and decryption of data at rest or in transit). An attested platform (e.g., device 250, firmware, or controller 258) can provide trusted assignment of an emulated device to a trust domain.

[0024] A trust domain, confidential computing environment, or security enclave can be created using one or more of the following: Total Memory Encryption (TME), Multi-Key Total Memory Encryption (MKTME), Trusted Domain Extensions (TDX), Double Data Rate Encryption (DDR), Function-as-a-Service (FaaS) container encryption or an enclave / TD (trust domain), Intel® SGX, Intel® TDX, AMD Memory Encryption Technology, AMD Secure Memory Encryption (SME) and Secure Encrypted Virtualization (SEV), AMD Secure Encrypted Virtualization-Secure Nested Paging (AMD SEV-SNP), ARM® TrustZone®, ARM® Realms and Confidential Compute, Apple Secure Enclave Processor, Qualcomm® Trusted Execution Environment, RISC-V Trusted Execution Environment (TEE), security protocol and Distributed Management Task Force (DMTF) data model (SPDM) specification, virtualization-based isolation such as Intel VTd and AMD-V, or others.

[0025] A trusted authority can attest whether an identifier is valid. An attestation quote can be sent to the trusted CSP / CoSP attestation server to verify the signed quote. Alternatively, the signed quote could be sent to the tenant's trusted virtual machine (VM) (e.g., Trust Domain Extensions (TDX) VM), which can authenticate the quote.

[0026] Device 250 may create multiple emulated endpoint devices 256-0 through 256-X. However, emulated endpoint devices 256-0 through 256-X are not disclosed to applications 202 until emulated endpoint devices are assigned to a TD by a trusted host module (e.g., as a TDX connection module), successful attestation of the emulated device occurs, and the endpoint device configuration is locked (e.g., Fig. 3). Based on the assignment of the emulated device to a trust domain and successful attestation of the emulated device, the tenant may permit use of the SEP-emulated devices by one or more of the applications 202. For example, trusted firmware may expose the emulated device instance as a device to the host 200. A Virtual Machine Manager (VMM) (e.g., the VMM 206 or 208) executing on the host 200 may virtualize emulated device instances to provide access to an emulated device.

[0027] Data access protection schemes for protecting data at rest or in transit may apply to data stored in local memory or external storage based on a unique key for an emulated device. The security controller 258 may generate emulated device keys, and access to the keys may be restricted to the security controller 258. For example, emulated device keys may be constructed and managed in a manner similar to those of Intel® Multi-Key Total Memory Encryption (MK-TME).

[0028] The security controller 258 may access a virtualization card to map transactions from and to specific host applications 202 to an intended emulated device using a mapping table (e.g., card) to manage security access control policies (e.g., allowing or denying inbound and outbound transactions (e.g., memory-mapped I / O (MMIO), register reads or writes, DMA, etc.) through the mapping table).

[0029] Encryption or decryption of data accessible to emulated devices may, for example, use whole memory encryption (TME) and multi-key whole memory encryption (MKTME) commercially available from Intel Corporation (as described in the Intel Architecture Memory Encryption Technologies Specification version 1.1, dated December 17, 2017, and previous versions, revisions, and variations thereof), the components that make up TME and MKTME, the manner in which TME and MKTME operate, and so on. TME provides a scheme for encrypting data through memory interfaces, where a memory controller encrypts the data flowing to memory or decrypts data flowing from memory and provides plaintext for internal consumption by the processor.

[0030] In some examples, TME is a technology that encrypts all or a portion of a device's memory with a key. When enabled through a BIOS (or UEFI (Universal Extensible Firmware Interface) or bootloader configuration) configuration, TME can cause memory accessed by a processor on an external memory bus to be encrypted, including customer credentials, encryption keys, and other intellectual property (IP) or personal information. TME supports a variety of encryption algorithms and, in one embodiment, can use a National Institute of Standards and Technology (NIST) encryption standard for storage, such as the Advanced Encryption System (AES)-XTS algorithm with 128-bit keys, 256-bit keys, or other key lengths.The encryption key used for memory encryption is generated using a hardened random number generator in the processor and is never disclosed to software. Data in memory and on external memory buses can be encrypted and resides in plaintext within the processor circuitry. This allows existing software to run unchanged while protecting memory using TME. There may be scenarios where it would be advantageous to leave a portion of memory unencrypted; therefore, TME allows the BIOS (or UEFI, or bootloader) to specify a physical address range of memory that remains unencrypted. Software running on a TME-enabled system can access memory sections not encrypted by TME.

[0031] In some embodiments, the TME can support multiple encryption keys (Multi-Key TME (MKTME)) and provides the ability to specify the use of a specific key for a memory page. This architecture enables either processor-generated keys or tenant-provided keys, providing customers with complete flexibility. Processes can be cryptographically isolated from each other in memory with separate encryption keys, which can be used in multi-tenant cloud environments. Processes can also be pooled so that they share an individual key, further enhancing scalability and flexibility.

[0032] Trusted VMs / containers can rely on devices in multi-hosted virtualization models (e.g., VMware, Microsoft® Azure Cloud®, or others) where VMs can be paused and restarted, and restarted VMs can resume using the paused SEP instances. If a previously instantiated emulated SEP device is restarted, the emulated SEP device resumes operation with the same identity. Therefore, SEP instances resume operation with their original identities.

[0033] In some examples, security controller 252 may perform operations of one or more of: Intel® Converged Security and Management Engine, Microsoft or Open Compute Project Cerberus, Amazon Nitro, or others.

[0034] Fig. 2B shows an example system. For example, emulated device 266-0 and emulated device 266-1 may be assigned shared use of circuitry 270, buffers 274, registers 276, and memory 278. For example, emulated device 266-2 may be assigned exclusive use of circuitry 272 and shared use, along with emulated devices 266-0 and 266-1, of buffers 274, registers 276, and memory 278. In some examples, safety controller 262 may attest to and verify hardware and software resources associated with emulated devices 266-0, 266-1, and 266-2.Based on attesting and verifying identifiers associated with the emulated devices 266-0, 266-1, and 266-2, assigning the emulated devices 266-0, 266-1, and 266-2 to one or more trust domains, and locking registers, the security controller 262 may share the unique identifiers with applications 260 to access the emulated devices 266-0, 266-1, and 266-2.

[0035] For example, security controller 262 may utilize mapping table 264 to manage security policies for inbound and outbound transactions (e.g., MMIO, registers, DMA, etc.) to restrict communications. To access a particular emulated device, an application 260 may provide an emulated device with the associated unique identifier in communications. Communications received from an emulated device may be associated with the unique identifier. If the unique identifier is not used or differs from the assigned one, communications will not be permitted to be forwarded to an emulated device or to emulated applications 260.

[0036] Fig. Figure 3 shows an example of a register lock. After authenticating and attesting an emulated SEP device, access to registers and MMIO associated with the emulated SEP device can be locked based on the security policy of an assignable interface and a security policy according to the PCIe-SIG Trusted Execution Environments (TEE) Device Interface Security Protocol (TDISP) (2022) standard. In some examples, instructions or data stored in the registers or accessed via MMIO can be encrypted using keys available to the requestor (e.g., the application) and an emulated SEP device.

[0037] A device interface can be associated with configuration registers. Some configuration registers can be customized or managed by a TD or a VM running in a TD. Some configuration registers can be customized or managed by a VMM or a TD module. MMIO read / write operations can be used as a doorbell between the VM and the device to indicate readiness for data processing. For external devices, data copied between the TD and the interface can be encrypted and integrity protected. Data encryption can optionally be performed for communication between circuits within a system-on-chip (SoC).

[0038] Fig. Figure 4 shows an example of end-to-end tenant attestation of an emulated SEP device in a trust domain (TD). Device 400 may be deployed in one or more of CSP, CoSP, Edge, Edge Artificial Intelligence (Edge AI), 5G, Secure Access Service Edge (SASE), or Mobile Edge Computing (MEC) deployments. For example, an orchestrator (e.g., Kubernetes, Docker, OpenStack, Apache Mesos, and so on) for a tenant (e.g., Tenant A or Tenant B) may manage the creation of emulated SEP devices, attestation, and assignment to trusted applications (e.g., TDX, AMD-SEV, or others), as well as the verification of the platform root trust (PRoT). In some examples, the orchestrator may cause certain emulated SEP devices to be assigned to tenant A and cause other certain emulated SEP devices to be assigned to tenant B.

[0039] An infrastructure orchestrator may provide the security controller of device 500 with attestation keys and perform attestation of the endpoint circuitry. A tenant-specific orchestrator may perform attestation of identifiers and compositions of software, firmware, and hardware of emulated SEP devices. In some examples, a tenant-specific orchestrator may assign attestation keys to a security controller so that the security controller performs attestation of compositions of software, firmware, and hardware of emulated SEP devices. The attestation may provide a trust-establishment mechanism that allows a tenant to determine the characteristics of the target system so that the system can provide the various security assurances required by the tenant to run its trusted workloads.In some examples, trusted firmware executed by an SEP or by trusted hardware can generate unique identifiers for an emulated SEP device. An attestation key (e.g., attestation root key) can be used by a security controller to sign a hash value obtained by concatenating an initial boot firmware and subsequent firmware and / or software images located in a trusted compute base (TCB) of the emulated SEP devices. The security controller can send an attestation notation to the trusted CSP or CoSP attestation server to verify the signed notation to authenticate or attest an emulated SEP device, or to indicate that the signed notation is not verified and therefore indicate that the emulated SEP device is not authenticated or attested.The emulated devices can be assigned to a TD for tenant A or a TD for tenant B.

[0040] Fig. 5 shows an example process for allocating an emulated device. The process may be performed by a safety controller or other trusted software, firmware, or circuitry. At 502, a SEP agent may be loaded for execution by a safety controller. At 504, a determination may be made whether an access request to an emulated SEP device instance has been received from a requestor, such as an application. If an access request to an emulated SEP device instance has been received, the process may proceed to 506. If no access request to an emulated SEP device instance has been received, the process may return to 504.

[0041] At 506, an emulated SEP device instance may be created. For example, an emulated SEP device instance may correspond to a virtio device instance. In some examples, the SEP agent may determine at 506 whether an emulated SEP device instance is available. For example, an emulated SEP device instance may be available if a unique identifier is assigned to the emulated SEP device, composite software and / or hardware resources associated with the emulated SEP device have been authenticated and attested, and the emulated SEP device instances are assigned to a trust domain. In some examples, the emulated device may be reassigned for use based on a reboot or migration of an emulated device. Based on an available emulated SEP device, the process may proceed to 522 (not shown).

[0042] At 508, a device fingerprinting process may be performed to create an emulated SEP device with a specific configuration. The SEP agent may perform secure onboarding of an emulated device (e.g., Virtio, Data Plane Development Kit (DPDK), Vector Packet Processing (VPP), etc.). The device fingerprinting process may include authentication and attestation of composite software and / or hardware resources assigned to the emulated SEP device and assignment of a unique identifier to the emulated SEP device. At 510, it may be determined whether the emulated SEP device fingerprinting was successful. Based on a successful attestation of the emulated SEP device, the process may proceed to 520. Based on an unsuccessful attestation of the emulated SEP device, the process may proceed to 512.If the SEP device fingerprinting process fails, the SEP creation of a new virtio device instance fails, and no new SEP virtio device instance is disclosed to the host, and an error is logged. At 512, the request for an emulated SEP device is rejected, and the process returns to 504. An emulated SEP device is not disclosed to the host until the device fingerprinting process has succeeded.

[0043] At 520, if the SEP device fingerprinting process for an emulated SEP device passes, the emulated device may be successfully assigned to a trust domain (TD). For example, the emulated device may be successfully assigned to a tenant's TD. At 522, the emulated device may be exposed to the host, which an application (e.g., VM or container) may access.

[0044] Fig. 6 shows an example process. The process may, in some examples, be performed by a security controller of endpoint circuitry (e.g., an accelerator or SEP) connected inline between a host system and a device. At 602, a composition of software, firmware, and / or hardware may be assigned to an emulated endpoint device. At 604, authentication and attestation of the composition of software, firmware, and / or hardware assigned to the emulated endpoint device may occur. At 606, the emulated endpoint device may be made available for access to a trust domain based on authentication and attestation of the composition of software, firmware, and / or hardware assigned to the emulated endpoint device.A trust domain can use a trusted VM, a trusted container, and / or a trusted process.

[0045] Fig. 7 shows an example computing system. Components of system 700 may be configured to provide emulated endpoint devices that are attested and execute trusted computing environments as described herein. System 700 includes a processor 710 that provides processing, operations management, and instruction execution for system 700. Processor 710 may include any type of microprocessor, central processing unit (CPU), graphics processing unit (GPU), processing core, or other processing hardware to provide processing for system 700, or a combination of processors.The processor 710 controls the overall operation of the system 700 and may be or include one or more programmable general-purpose or special-purpose microprocessors, digital signal processors (DSPs), programmable controllers, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or the like, or a combination of such devices.

[0046] In one example, system 700 includes an interface 712 coupled to processor 710, which represents a higher-speed or high-throughput interface for system components requiring higher-bandwidth connections, such as a memory subsystem 720 or graphics interface components 740 or accelerators 742. Interface 712 represents interface circuitry that may be a standalone component or integrated on a processor die. In some examples, graphics interface 740 generates a display based on data stored in memory 730, or based on operations performed by processor 710, or both.In some examples, graphics interface 740 generates a display based on data stored in memory 730, or based on operations performed by processor 710, or both.

[0047] Accelerators 742 may be a fixed-function swap engine or a programmable swap engine that may be accessed or used by a processor 710. For example, an accelerator among accelerators 742 may provide compression capability (DC capability), cryptographic services such as public key encryption (PKE), a cipher, hashing / authentication capabilities, decryption, or other capabilities or services. In some cases, accelerators 742 may be integrated into a CPU socket (e.g., a connector on a motherboard or circuit board that contains a CPU and provides an electrical interface with the CPU).For example, accelerators 742 may include a single- or multi-core processor, a graphics processing unit, a logical execution unit, single- or multi-level caches, functional units usable to independently execute programs or threads, application-specific integrated circuits (ASICs), neural network processors (NNps), programmable control logic, and programmable processing elements such as field-programmable gate arrays (FPGAs) or programmable logic devices (PLDs). Accelerators 742 may provide multiple neural networks, CPUs, processor cores, general-purpose graphics processing units, or graphics processing units may be made available for use by artificial intelligence (AI) or machine learning (ML) models.For example, the AI ​​model may include one or more of the following: a reinforcement learning scheme, Q-learning scheme, deep Q-learning, or Asynchronous Advantage Actor-Critic (A3C) scheme, a combinatorial neural network, a recurrent combinatorial neural network, or another AI or ML model. Multiple neural networks, processor cores, or graphics processing units may be made available for use by AI or ML models.

[0048] A memory subsystem 720 represents the main memory of system 700 and provides storage for code to be executed by processor 710 or for data values ​​to be used in executing a routine. Memory subsystem 720 may include one or more memory devices 730, such as read-only memory (ROM), flash memory, one or more variants of random access memory (RAM) such as DRAM, or other memory devices, or a combination of such devices. Memory 730 stores and hosts, among other things, an operating system (OS) 732 to provide a software platform for executing instructions in system 700. Additionally, applications 734 may be executed on the software platform of OS 732 from memory 730. Applications 734 represent programs that have their own operating logic to perform one or more functions.Processes 736 represent agents or routines that provide additional functionality to the OS 732 or one or more applications 734, or a combination. The OS 732, the applications 734, and processes 736 provide software logic to provide functionality to the system 700. In one example, the memory subsystem 720 includes cryptographic circuitry 721, a memory controller 722, which is a memory controller for generating and issuing commands to the memory 730. It is understood that the memory controller 722 could be a physical part of the processor 710 or a physical part of the interface 712. The memory controller 722 may, for example, be an integrated memory controller integrated on circuitry with the processor 710.Cryptographic circuitry 721 may encrypt data before storing it in memory 730 or decrypt data after accessing it from memory 730, as described herein.

[0049] While not specifically illustrated, it should be understood that system 700 may include one or more buses or bus systems between devices, such as a memory bus, a graphics bus, interface buses, or others. Buses or other signal lines may communicatively or electrically couple components to one another, or may couple the components both communicatively and electrically. Buses may include physical communication lines, point-to-point connections, bridges, adapters, controllers, or other circuitry, or a combination. For example, buses may include one or more of a system bus, a Peripheral Component Interconnect (PCI) bus, a HyperTransport or Industry Standard Architecture (ISA) bus, a Small Computer System Interface (SCSI) bus, a Universal Serial Bus (USB), or an Institute of Electrical and Electronics Engineers (IEEE) 1394 (Firewire) bus.

[0050] In one example, system 700 includes an interface 714 that may be coupled to interface 712. In one example, interface 714 represents interface circuitry that may include discrete components and integrated circuitry. In one example, multiple user interface components or peripheral components, or both, couple to interface 714. Network interface 750 provides system 700 with the ability to communicate with remote devices (e.g., servers or other computing devices) over one or more networks. Network interface 750 may include an Ethernet adapter, wireless interconnect components, cellular network interconnect components, Universal Serial Bus (USB), or other wired or wireless, standards-based, or proprietary interfaces.The network interface 750 may send data to a device located in the same data center or rack or to the same remote device, which may include sending data stored in memory.

[0051] The network interface 750 (e.g., a NIC) may include one or more of the following: a network interface controller (NIC), a remote direct memory access (RDMA)-capable NIC, a SmartNIC, a router, a switch, or a network-attached device. Some examples of a network interface 750 are part of, or utilized by, an infrastructure processing unit (IPU) or a data processing unit (DPU). An xPU may refer to at least one of an IPU, DPU, GPU, GPGPU, or other processing units (e.g., accelerator devices). An IPU or DPU may include a network interface with one or more programmable pipelines or fixed-function processors to perform offloading of operations that may have been performed by a CPU.For example, one or more programmable pipelines or fixed-function processors or other circuitry may be configured to perform event processing using an accelerator or other circuitry inline with the network interface device 750, wherein the network interface device 750 is accessed at least using device virtualization, as described herein.

[0052] For example, network interface 750 may include media access control (MAC) circuitry, alignment sublayer circuitry, and physical layer interface (PHY) circuitry. PHY circuitry may include physical medium attachment (PMA) sublayer circuitry, physical medium dependent (PMD) circuitry, forward error correction (FEC) circuitry, and physical coding sublayer (PCS) circuitry. In some examples, the PHY may provide an interface that includes or utilizes a serializer-deserializer (SerDes). In some examples, at least when network interface 750 is a router or switch, the router or switch may include interface circuitry that includes a SerDes.

[0053] In some examples, system 700 includes a storage subsystem 780 for storing data in a non-volatile manner. In some examples, in certain system implementations, at least certain components of storage 780 may overlap with components of memory subsystem 720. Memory subsystem 780 includes one or more memory devices 784, which may be or include any conventional medium for storing large amounts of data in a non-volatile manner, such as one or more magnetic, solid-state, or optical disks, or a combination thereof. Volatile memory is memory whose state (and therefore the data stored thereon) is indeterminate if power to the device is interrupted. A non-volatile memory (NVM) device is memory whose state is determined even if power to the device is interrupted.Storage 784 maintains code or instructions and data 786 in a persistent state (e.g., the value is retained despite interruption of power to system 700). Storage 784 may generally be considered "memory," although memory 730 is typically the execution or operational memory for providing instructions to processor 710. While storage 784 is non-volatile, memory 730 may include volatile memory (e.g., the value or state of the data is indeterminate if power to system 700 is interrupted). In some examples, storage subsystem 780 includes a controller 782 to couple to storage 784. In some examples, controller 782 is a physical part of interface 714 or processor 710, or may include circuitry or logic in both processor 710 and interface 714.

[0054] In one example, system 700 may be implemented using interconnected computing systems with processors, memories, storage, network interfaces, and other components. High-speed interconnections may be used, such as Ethernet (IEEE 802.3), Remote Direct Memory Access (RDMA), InfiniBand, Internet Wide Area RDMA Protocol (iWARP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), quick UDP Internet Connections (QUIC), RDMA over Converged Ethernet (RoCE), Peripheral Component Interconnect express (PCIe), Intel QuickPath Interconnect (QPI), Intel Ultra Path Interconnect (UPI), Intel On-Chip System Fabric (IOSF), Omni-Path, Compute Express Link (CXL), Universal Chiplet Interconnect Express (UCIe), HyperTransport, High Speed ​​Fabric, NVLink, an Advanced Microcontroller Bus Architecture (AMBA) interconnect, OpenCAPI, Gen-Z, Infinity Fabric (IF), Cache Coherent Interconnect for Accelerators (CCIX), 3GPP Long Term Evolution (LTE) (4G), 3GPP 5G, and variations thereof. Data can be copied or stored in virtualized storage nodes or accessed using a protocol such as Non-Volatile Memory Express over Fabrics (NVMe-of) (e.g.NVMe Specification, Version 1.0 (2016) and variations, extensions, and derivatives thereof) or NVMe (e.g., Non-Volatile Memory Express (NVMe) Specification, Revision 1.3c, published May 24, 2018 (“NVMe Specification”) and variations, extensions, and derivatives thereof).

[0055] Next, various examples of device virtualization techniques are described. The Single Root I / O Virtualization (SR-IOV) and Sharing specification, version 1.1, published on January 20, 2010, by the Peripheral Component Interconnect (PCI) Special Interest Group (PCI-SIG), provides a hardware-assisted high-performance I / O virtualization technique that enables scalable sharing across virtualized execution environments of I / O devices, such as network interface devices, storage controllers, a packet processor, a packet processing pipeline, a cryptographic accelerator (e.g., decryption or encryption), memory pool controllers, graphics processing units, and other hardware accelerators, across a large number of virtualized execution environments. PCI Express (PCIe) is defined in the PCI Express Base Specification, Revision 4.0, version 1.0, published on October 5, 2017.In contrast to SR-IOV's coarse-grained device partitioning approach for creating multiple VFs on a PF, S-IOV enables flexible composite virtual devices at finer granularity by leveraging hardware support for device sharing. Some operations on the composite virtual device are performed by the underlying device hardware, while some operations can be emulated by device-specific composite software executed by the host. A technical specification for Scalable Input / Output (I / O) Virtualization (S-IOV) is the Intel® Scalable I / O Virtualization Technical Specification (June 2018) and its revisions and variations.

[0056] Communications between devices may occur using a network that provides die-to-die communications; chip-to-chip communications; board-to-board communications; and / or package-to-package communications. One or more components of system 700 may be implemented as part of a system-on-chip (SoC).

[0057] Embodiments herein may be implemented in various types of computing devices, smartphones, tablets, personal computers, and network equipment, such as switches, routers, racks, and blade servers, such as those deployed in a data center and / or server farm environment. The servers used in data centers and server farms include server configurations in arrangements such as rack-based servers or blade servers. These servers are communicatively interconnected via various network assignments, such as partitioning groups of servers into local area networks (LANs) with appropriate switching and routing between the LANs to form a private intranet. Cloud hosting facilities, for example, may typically employ large data centers with many servers. A blade comprises a separate computing platform designed to perform server-type functions—that is, a "server on a card."Accordingly, each blade contains components common to traditional servers, including a printed circuit board (Motherboard) that provides internal wiring (e.g., buses) for coupling appropriate integrated circuits (ICs) and other board-mounted components.

[0058] In some examples, a network interface and other embodiments described herein may be used in connection with a base station (e.g., 3G, 4G, 5G, and so on), a macro base station (e.g., 5G networks), a pico station (e.g., an IEEE 802.11 compliant access point), a nano station (e.g., for Point-to-MultiPoint (PtMP) applications), a micro data center, on-premises data centers, off-premises data centers, edge network elements, fog network elements, and / or hybrid data centers (e.g., data centers that use virtualization, cloud, and software-defined networking to deliver application workloads across physical data centers and distributed multi-cloud environments).

[0059] Fig.8 shows an example network interface device. A network interface device 800 may manage performance of one or more processes using one or more of processors 806, processors 810, accelerators 820, storage pool 830, or servers 840-0 through 840-N, where N is an integer of 1 or more. The network interface device 800 may provide emulated endpoint devices from endpoint circuitry 808 that are attested and execute trusted computing environments as described herein. In some examples, the processors 806 of the network interface device 800 may execute one or more processes, applications, VMs, containers, microservices, and so forth that request execution of workloads by one or more of: processors 810, accelerators 820, storage pool 830, and / or servers 840-0 through 840-N.The network interface device 800 may utilize a network interface 802 or one or more device interfaces to communicate with the processors 810, the accelerators 820, the memory pool 830, and / or the servers 840-0 through 840-N. The network interface device 800 may utilize a programmable pipeline 804 to process packets to be transmitted by the network interface 802 or received by the network interface 802.

[0060] The programmable pipeline 804 and / or the processors 806 may be configured or programmed using languages ​​based on one or more of: P4, Software for Open Networking in the Cloud (SONiC), C, Python, Broadcom Network Programming Language (NPL), NVIDIA® CUDA®, NVIDIA® DOCA™, Infrastructure Programmer Development Kit (IPDK), or x86-compatible executable binaries or other executable binaries.

[0061] Various examples may be implemented using hardware elements, software elements, or a combination of both. In some examples, hardware elements may include devices, components, processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, and so on), integrated circuits, ASICs, PLDs, DSPs, FPGAs, memory units, logic gates, registers, semiconductor devices, chips, microchips, chipsets, and so on. In some examples, software elements may include software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, APIs, instruction sets, computational code, computer code, code segments, computer code segments, words, values, symbols, or any combination thereof.Determining whether an example is implemented using hardware elements and / or software elements may vary according to any number of factors, such as a desired computation rate, power levels, thermal tolerances, processing cycle budget, input data rates, output data rates, memory resources, data bus speeds, and other design or performance constraints as desired for a given implementation. A processor may be one or more combinations of a hardware state machine, digital control logic, a central processing unit, or any of the hardware, firmware, and / or software elements.

[0062] Some examples may be implemented using or as a fabricated article or at least one computer-readable medium. A computer-readable medium may include a non-transitory storage medium to store logic. In some examples, the non-transitory storage medium may include one or more types of computer-readable storage media capable of storing electronic data, including volatile memory or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or rewritable memory, and so on.In some examples, the logic may include various software elements, such as software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, API, instruction sets, computational code, computer code, code segments, computer code segments, words, values, symbols, or any combination thereof.

[0063] According to some examples, a computer-readable medium may include a non-transitory storage medium for storing or preserving instructions that, when executed by a machine, computing device, or system, cause the machine, computing device, or system to perform methods and / or operations consistent with the described examples. The instructions may include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. The instructions may be implemented in accordance with a predefined computer language, style, or syntax for instructing a machine, computing device, or system to perform a particular function.The instructions can be implemented using any high-level, low-level, object-oriented, visual, compiled and / or interpreted programming language.

[0064] One or more aspects of at least one example may be implemented by representative instructions stored on at least one machine-readable medium representing various logic within the processor that, when read by a machine, computing device, or system, causes the machine, computing device, or system to generate logic to perform the techniques described herein. These representations, known as "IP cores," may be stored on tangible machine-readable medium and provided to various customers or manufacturing facilities for loading into the manufacturing machines that actually manufacture the logic or processor.

[0065] The appearance of the phrase "a single example" or "an example" does not necessarily always refer to the same example or embodiment. Any aspect described herein may be combined with any other aspect described herein or a similar aspect, regardless of whether the aspects are described with respect to the same figure or element. The partitioning, omission, or inclusion of block functions illustrated in the accompanying figures does not imply that the hardware components, circuitry, software, and / or elements for implementing those functions would necessarily be partitioned, omitted, or included in embodiments.

[0066] Some examples can be described using the terms "coupled" and "connected," along with their derivatives. These terms are not necessarily intended to be synonymous. For example, descriptions using the terms "connected" and / or "coupled" may indicate that two or more elements are in direct physical or electrical contact with each other. However, the term "coupled" can also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0067] The terms "first," "second," and the like, as used herein, do not denote order, quantity, or importance, but rather are used to distinguish one element from another. The terms "a," "an," and "an" do not denote a limitation of quantity, but rather denote the presence of at least one of the recited elements. The term "detected," as used herein with respect to a signal, denotes a state of the signal in which the signal is active, which can be achieved by applying any logic level, either logic 0 or logic 1, to the signal. The terms "follow" or "after" can denote immediately following or following another event or events. Other sequences of operations may also be performed according to alternative embodiments.Furthermore, additional operations may be added or removed depending on the particular application. Any combination of modifications may be used, and those of ordinary skill in the art, having the benefit of this disclosure, would appreciate the many variations, modifications, and alternative embodiments thereof.

[0068] Disjunctive language such as the phrase "at least one of X, Y, or Z," unless explicitly stated otherwise, is understood in context to mean something other than what is generally used to represent that an element, term, etc., can be either X, Y, or Z, or any combination thereof (e.g., X, Y, and / or Z). Therefore, such disjunctive language is not intended to, and should not, generally imply that particular embodiments require at least one of X, at least one of Y, or at least one of Z to be present. Furthermore, subjunctive language such as the phrase "at least one of X, Y, and Z," unless explicitly stated otherwise, should also be understood to mean X, Y, Z, or any combination thereof, including "X, Y, and / or Z."

[0069] Illustrative examples of the devices, systems, and methods disclosed herein are provided below. An embodiment of the devices, systems, and methods may include one or more, and any combination, of the examples described below.

[0070] Example 1 includes one or more examples and includes a device including a system interface and a device including: circuitry configured to provide trusted and secure access to the emulated device to a virtual execution environment based on an attestation of the device, an assignment of an emulated device to a trust domain (TD), and an attestation of a device configuration associated with the emulated device, wherein: the device configuration is associated with one or more circuitry and software associated with the device, the emulated device is accessible via a device interface to the virtual execution environment, and the device configuration comprises one or more of: register access, a network interface device,a storage controller, an accelerator, a processor, or a storage device.

[0071] Example 2 includes one or more examples where the circuitry is to perform attestation and signing of a key for the emulated device and to provide data based on the key to the emulated device for communications between the virtual execution environment and the emulated device.

[0072] Example 3 includes one or more examples, wherein the circuitry is to provide a secure and trusted environment to perform: generating a key for the emulated device, providing and / or generating an attestation key, and signing the key for the emulated device and the attestation key.

[0073] Example 4 includes one or more examples where the circuitry is to execute trusted device firmware to: generate an attested notation based on one or more of: identifiers of the one or more circuitry and software associated with the device, first bootable device firmware, executable device firmware, a device configuration, endpoint emulated device firmware, or an endpoint emulated device configuration and assignments; and verify the attested notation before providing trusted access to the emulated device to a virtual execution environment.

[0074] Example 5 includes one or more examples comprising a memory device, wherein the circuitry is to cause the memory device to: store code, data, and context state for the emulated device in the TD associated with a tenant such that the code, data, and context state continue to be stored based on the TD associated with the tenant going offline and resuming the state of the emulated device based on an attestation of the emulated device and scheduling the TD and the attested emulated device for use.

[0075] Example 6 includes one or more examples where the device interface is consistent with one or more of: Peripheral Component Interconnect Express (PCIe), Compute Express Link (CXL), Universal Chiplet Interconnect Express (UCIe), Single Root I / O Virtualization (SR-IOV), or Scalable Input / Output (I / O) Virtualization (S-IOV).

[0076] Example 7 includes one or more examples, where the device comprises one or more of: the network interface device, the storage controller, the accelerator, the processor, or the memory device.

[0077] Example 8 includes one or more examples where the emulated device comprises endpoint circuitry.

[0078] Example 9 includes one or more examples, where the virtual execution environment comprises one or more of: a virtual machine, a container, an application, a process, a service, or a microservice.

[0079] Example 10 includes one or more examples and includes a server, wherein the server is communicatively coupled to the system interface, and wherein the server is to execute the virtual execution environment to access the emulated device.

[0080] Example 11 includes one or more examples and includes a method comprising: based on attestation of a platform, assignment of an emulated device to a trust domain (TD), and attestation of a device configuration associated with the emulated device and disabling register access, providing trusted and secure access to the emulated device for a virtual execution environment by a controller, wherein: the device configuration comprises one or more of: register access, a network interface device, a storage controller, an accelerator, a processor, or a memory device.

[0081] Example 12 includes one or more examples and includes, by the controller, performing attestation and signing of a key for the emulated device and providing data based on the key to the emulated device for communications between the virtual execution environment and the emulated device.

[0082] Example 13 includes one or more examples and includes, by the controller: generating an attested notation based on one or more of: identifiers of one or more circuitry and software associated with the device, first bootable device firmware, executable device firmware, a device configuration, endpoint emulated device firmware, or an endpoint emulated device configuration and assignments; and verifying the attested notation before providing a virtual execution environment with trusted access to the emulated device.

[0083] Example 14 includes one or more examples and includes, by the controller: storing a state of the emulated device for the emulated device in the TD, wherein the state of the emulated device is further stored based on the TD associated with the tenant going offline and the state of the emulated device being accessible to the emulated device after the TD and the emulated device are rescheduled for use.

[0084] Example 15 includes one or more examples where the emulated device comprises endpoint circuitry.

[0085] Example 16 includes one or more examples where the control is attested during manufacture.

[0086] Example 17 includes one or more examples and includes at least one non-transitory computer-readable medium comprising instructions stored thereon that, when executed by one or more circuitry, cause the one or more circuitry to: based on an attestation of a platform, an assignment of an emulated device to a trust domain (TD), and an attestation of a device configuration associated with the emulated device, and a lock on register access, provide trusted and secure access to the emulated device to a virtual execution environment by a controller, wherein the emulated device comprises endpoint circuitry.

[0087] Example 18 includes one or more examples where the device configuration includes one or more of: register access, a network interface device, a storage controller, an accelerator, a processor, or a memory device.

[0088] Example 19 includes one or more examples and includes instructions stored thereon that, if executed by one or more circuitry, cause the one or more circuitry to: perform attestation and signing of a key for the emulated device; and provide the key to the emulated device for communications between the virtual execution environment and the emulated device.

[0089] Example 20 includes one or more examples and includes instructions stored thereon that, when executed by one or more circuitry, cause the one or more circuitry to: generate an attested notation based on one or more of: identifiers of the one or more circuitry and software associated with the device, first bootable device firmware, executable device firmware, a device configuration, endpoint emulated device firmware, or an endpoint emulated device configuration and assignments; and verify the attested notation before providing trusted access to the emulated device to a virtual execution environment.

Claims

[1] Facility comprising: a system interface and a device comprising: a circuit arrangement designed: to provide a virtual execution environment with trusted and secure access to the emulated device based on an attestation of the device, an assignment of an emulated device to a trust domain (TD), and an attestation of a device configuration associated with the emulated device, wherein: the device configuration is associated with one or more circuit arrangements and software associated with the device, the emulated device can be accessed via a device interface to the virtual execution environment and the device configuration includes one or more of: register access, a network interface device, a storage controller, an accelerator, a processor, or a memory device. [2] The device of claim 1, wherein the circuitry is to perform attestation and signing of a key for the emulated device and to provide data based on the key for the emulated device for communications between the virtual execution environment and the emulated device. [3] The device of claim 1, wherein the circuitry is to provide a secure and trusted environment to perform the following: generating a key for the emulated device, providing and / or generating an attestation key, and signing the key for the emulated device and the attestation key. [4] A device according to claim 1, comprising a memory device, wherein the circuit arrangement is to cause the memory device to: Storing code, data, and context state for the emulated device in the TD associated with a tenant such that the code, data, and context state continue to be stored based on the TD associated with the tenant going offline and resuming the state of the emulated device based on an attestation of the emulated device and scheduling the TD and the attested emulated device for use. [5] The device of claim 1, wherein the device interface is consistent with one or more of: Peripheral Component Interconnect Express (PCIe), Compute Express Link (CXL), Universal Chiplet Interconnect Express (UCIe), Single Root I / O Virtualization (SR-IOV), or Scalable Input / Output (I / O) Virtualization (S-IOV). [6] The apparatus of claim 1, wherein the device comprises one or more of: the network interface device, the storage controller, the accelerator, the processor, or the memory device. [7] The device of claim 1, wherein the emulated device comprises endpoint circuitry. [8] The device of claim 1, wherein the virtual execution environment comprises one or more of: a virtual machine, a container, an application, a process, a service, or a microservice. [9] The device of claim 1, comprising a server, wherein the server is communicatively coupled to the system interface, and wherein the server is to execute the virtual execution environment to access the emulated device. [10] Device according to one or more of claims 1-9, wherein the circuit arrangement is to execute trusted device firmware to: generate an attested notation based on one or more of the following: identifiers of the one or more circuitry and software associated with the device, first bootable device firmware, executable device firmware, a device configuration, endpoint emulated device firmware, or an endpoint emulated device configuration and assignments, and to verify the attested notation before providing a virtual execution environment with trusted access to the emulated device. [11] A method comprising: based on an attestation of a platform, an assignment of an emulated device to a trust domain (TD), and an attestation of a device configuration associated with the emulated device, and a lock on register access, providing trusted and secure access to the emulated device for a virtual execution environment by a controller, wherein: the device configuration includes one or more of: register access, a network interface device, a storage controller, an accelerator, a processor, or a memory device. [12] A method according to claim 11, comprising: by the controller, performing attestation and signing a key for the emulated device and providing data based on the key to the emulated device for communications between the virtual execution environment and the emulated device by the controller. [13] A method according to claim 11, comprising, by the controller: Generating an attested notation based on one or more of the following: identifiers of one or more circuitry and software associated with the device, first bootable device firmware, executable device firmware, a device configuration, endpoint emulated device firmware, or an endpoint emulated device configuration and assignments, and Verify the attested notation before providing a virtual execution environment with trusted access to the emulated device. [14] The method of claim 11, wherein the emulated device comprises endpoint circuitry. [15] The method of claim 11, wherein the control is certified during manufacture. [16] Method according to one or more of claims 11-15, comprising, by the controller: Storing a state of the emulated device for the emulated device in the TD, wherein the state of the emulated device is further stored based on the TD associated with the tenant going offline and the state of the emulated device being accessible to the emulated device after the TD and the emulated device are rescheduled for use. [17] At least one non-transitory computer-readable medium comprising instructions stored thereon which, if executed by one or more circuit arrangements, cause the one or more circuit arrangements to: based on attestation of a platform, assignment of an emulated device to a trust domain (TD), and attestation of a device configuration associated with the emulated device, and lock of register access, providing a virtual execution environment with trusted and secure access to the emulated device, wherein the emulated device comprises endpoint circuitry. [18] The computer-readable medium of claim 17, wherein the device configuration comprises one or more of: register access, a network interface device, a storage controller, an accelerator, a processor, or a memory device. [19] The computer-readable medium of claim 17, comprising instructions stored thereon that, if executed by one or more circuitry, cause the one or more circuitry to: Performing attestation and signing of a key for the emulated device and providing the key to the emulated device for communications between the virtual execution environment and the emulated device. [20] A computer-readable medium according to one or more of claims 17-19, comprising instructions stored thereon which, if executed by one or more circuit arrangements, cause the one or more circuit arrangements to: generate an attested notation based on one or more of the following: identifiers of the one or more circuitry and software associated with the device, first bootable device firmware, executable device firmware, a device configuration, endpoint emulated device firmware, or an endpoint emulated device configuration and assignments, and to verify the attested notation before providing a virtual execution environment with trusted access to the emulated device.