A multiprocessor computing device and a method for constructing the root of trust therein
By using a first root of trust chip in a multiprocessor computing device for serial chip select signal communication, the processor's initial code is verified step by step, solving the problem of processor expansion and improving system security and the establishment of a trust chain.
Patent Information
- Application Number
- CN202211645769.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-20
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2042-12-20
AI Technical Summary
How to build a trusted chain in a multiprocessor computing device so that the number of processors can be freely expanded and the system security can be improved.
The first root of trust chip is used to select different processors through serial chip select signals, verify and start their first code step by step, and establish a trust chain.
It enables unlimited expansion of the number of processors in multiprocessor computing devices, improves the system's security level, and hides the processor correspondence by encrypting the chip select signal, thereby enhancing the system's security.
Smart Images

Figure CN115879118B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of information security technology, and in particular to a multiprocessor computing device and a method for constructing a root of trust therein. Background Technology
[0002] The trusted computing system constructs a trusted immune architecture of "host-trusted dual nodes". Specifically, a logically independent trusted system is built outside the computing device (or host device)'s own system. When powered on, this trusted system creates a trusted chain for the host device from the underlying hardware and software of the computing device to the application, thereby providing comprehensive bottom-up protection for the host device.
[0003] As people's demands for computing performance continue to increase, a computing device often has two or even more processors. Therefore, how to build a trusted chain for multi-processor computing devices so that the number of processors can be freely expanded is an urgent technical problem to be solved. Summary of the Invention
[0004] One embodiment of this specification provides a multiprocessor computing device, which includes a first root of trust chip and two or more processors. The first root of trust chip is used to select different processors for communication via a serial chip select signal to verify the first code of the corresponding processor and start the first code of the processor after successful verification. Each of the two or more processors is used to: verify the next level code through the first code and start the next level code after successful verification; the next level code of the first code verifies the next level code after that and starts the next level code after successful verification; in this way, the code of the next level is verified and started layer by layer, thereby completing the establishment of the trusted chain of the processor.
[0005] One embodiment of this specification provides a method for constructing a root of trust in a multiprocessor computing device, the computing device including two or more processors. The method includes: activating a first root of trust chip; using the first root of trust chip to select different processors for communication based on a serial chip select signal, to verify the start code of the corresponding processor, and activating the start code of the processor after successful verification; for each of the two or more processors: verifying the next level code through the start code, and activating the next level code after successful verification; the next level code of the start code verifies the next level code below it, and activating the next level code below it after successful verification; thereby verifying and activating the next level code layer by layer, and thus completing the establishment of the trust chain for the processor. Attached Figure Description
[0006] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:
[0007] Figure 1 This is a schematic diagram of the structure of a trust tree in a multiprocessor computing device according to some embodiments of this specification;
[0008] Figure 2 These are schematic diagrams of the structure of a computing device according to some embodiments of this specification;
[0009] Figure 3 These are schematic diagrams of the structure of a computing device according to some embodiments of this specification;
[0010] Figure 4 This is an exemplary flowchart of a trusted root construction method according to some embodiments of this specification. Detailed Implementation
[0011] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.
[0012] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.
[0013] As indicated in this specification, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.
[0014] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.
[0015] To effectively address current computer information security needs, a novel trusted computing framework has been proposed. It constructs a trusted immune architecture of "host-trusted dual nodes" within the computing device. Specifically, a logically independent trusted system is built outside the computing device's (or host device's) own system, providing bottom-up trusted support for the host device.
[0016] A trusted system (also known as a trusted computing platform) can further include a root of trust (ROT) and a trusted software base. The ROT is the fundamental functional module of the trusted system; it is the minimum computing system that must be trusted because improper behavior cannot be detected. It can be implemented based on a security chip and further includes a root of trust for measurement (RTM), a root of trust for storage (RTM), and a root of trust for reporting (RTR). The RTM is the basis for trusted system measurements. It is the initial code in the computing device's own system, such as the BIOS, and is used to perform trusted measurements on the device's critical underlying computing resources. Specifically, the RTM measures the important resource data of the computing device according to a preset measurement method, which may include, but is not limited to, calculating digital digests, hash values, encryption, and decryption. For example, when the computing device leaves the factory, a hash value is calculated for its initial resource data and securely stored as a trusted measurement value. When the computing device starts up or runs, the RTM recalculates the hash value of the important resource data and compares it with the stored initial hash value to achieve integrity measurement. For example, digital signatures of code within computing devices can be obtained from manufacturers, such as BIOS digital signatures and OS loader digital signatures. During computing device startup or runtime, the RTM recalculates digital digests of critical resource data and obtains a digital digest of the digital signature based on the digital signature of the relevant code and the code vendor's public key. The integrity of the relevant code is verified by comparing the currently calculated digital digest with the digital digest in the digital signature. The root of trust for storage (RTS) is the base point for securely storing trusted metrics, such as trusted hash values or digital signatures (or collectively referred to as baseline values) of critical resource data of the computing device. In addition, the RTS can store other information from the measurement process, such as the recalculated hash value and the comparison result between the recalculated hash value and the baseline value. The root of trust for report (RTR) can respond to a request for proof by sending a digitally signed audit report to the requesting party to demonstrate the trusted system's measurement of computing resources in the computing device. A Trusted Software Base (TSB) is a collection of software elements that support the trustworthiness of a computing device. During the operation of the computing device after startup, it proactively intercepts and measures data requests or accesses within its system, achieving dynamic immune defense security capabilities. In some embodiments, access control information within the computing device can be stored in the RTS as a log.
[0017] Multiprocessor computing devices contain two or more processors, such as CPUs (Central Processing Units), DPUs (Data Processing Units), GPUs (Graphics Processing Units), and DSAs (Domain Specific Architectures). These processors can exchange data to enable parallel execution of jobs, tasks, and programs. In some embodiments, a computing device may include a main processor and one or more coprocessors (or simply XPUs). A coprocessor may have its own operating system (OS), memory, and hard disk resources, essentially functioning as a small (relative to the computing device) computer system. The coprocessor can communicate with the motherboard of the computing device (e.g., via PCIe interface, SPI, etc.). In practical applications, coprocessors primarily assist the main processor in performing tasks that it cannot execute or that are inefficient or ineffective. For example, in a computing device used for image processing, the CPU acts as the main processor, and the GPU acts as the coprocessor. The GPU assists the main processor in performing image processing and related calculations, thus freeing up the main processor from image processing tasks and allowing it to focus its resources on other internal operations. For example, in computing devices used for secure computing, the DPU acts as a coprocessor, primarily responsible for data encryption and decryption. The main processor can call the coprocessor to complete data encryption and decryption within the computing device. With the development of information security technology, various processors can have built-in roots of trust, independent trusted subsystems, or TEEs (Trusted Execution Environments) to serve as trusted starting points within the processor and establish a chain of trust within the processor.
[0018] In multiprocessor computing devices, to improve the overall system security, a trusted tree can be established, starting from a unified root of trust and extending to each processor. For example... Figure 1As shown, after the computing device powers on, a first root of trust is initiated. This first root of trust verifies the header code of each processor within the computing device, and initiates the corresponding processor's header code upon successful verification. After the processor's header code is initiated, its next-level code is verified, and so on, with trust being passed step-by-step along the respective boot chain within each processor. In some embodiments, the first root of trust can be implemented based on a security chip, or a first root of trust chip. The root of trust for the first root of trust may include the security chip's own processor and related firmware code, while the root of trust for storage can be implemented based on the storage area on the security chip. Furthermore, the security chip can provide relevant access instructions to read data from the storage area and provide remote authentication to third parties. The program processes and stored data in the security chip are difficult for external parties to probe or interfere with, ensuring the security of the root of trust itself.
[0019] In some embodiments, the first root of trust chip can communicate with different processors in the computing device to obtain part or all of their header code for verification or measurement. Specifically, the first root of trust chip can select different processors via chip select signals, and the selected processors can interact with the first root of trust chip for data exchange. In some embodiments, the first root of trust chip can have multiple chip select ports or pins, each port outputting a chip select signal to the corresponding processor. In the idle / non-transfer state, the chip select signal can be kept high; when the chip select signal is low, it is considered valid. As an example, the computing device has three processors. When data interaction with the first processor is required, the chip select port of the first root of trust connected to the first processor outputs a valid low level, while the other two chip select ports output a high level. This can be seen as the chip select ports outputting chip select signals in parallel data form, with the chip select signals of each processor output simultaneously. It can be seen that, with chip selection in this way, the number of processors that the first root of trust can measure is limited by the number of chip select ports. If the first root of trust chip provides a maximum of two chip select ports, then only two processors can be measured.
[0020] In view of this, some embodiments of this specification provide a multiprocessor computing device and a method for constructing a root of trust therewith. The first root of trust chip selects different processors in the computing device through serial chip select signals, so that the number of measurable processors in the multiprocessor computing device is unlimited.
[0021] In some embodiments, the multiprocessor computing device includes a first root of trust chip and two or more processors; the first root of trust chip is used to select different processors for communication via a serial chip select signal to verify the start code of the corresponding processor, and to start the start code of the processor after successful verification.
[0022] Serial communication, also known as serial data transmission, refers to a communication method that transmits one bit of data at a time on a computer bus or other data channel, continuously performing this single process. Parallel communication is the opposite of serial communication. In some embodiments, serial communication of chip select signals can be achieved through one or more ports, and the number of processors that can be measured is theoretically unlimited, at least exceeding the number of chip select ports on the first root of trust chip. In some embodiments, different serially encoded chip select signals can be configured for different processors. For example, "001" is the valid chip select signal corresponding to the main processor (CPU), "010" is the valid chip select signal corresponding to the coprocessor (GPU), and "011" is the valid chip select signal corresponding to the coprocessor (DPU). The first root of trust chip serially outputs the corresponding chip select signal on its chip select port, thereby activating the corresponding processor and reading the corresponding header code for measurement or verification. For ease of description, the following mainly describes the serial communication method using two ports; it should be understood that this does not mean that the scheme described in this specification is only applicable to the two-port case.
[0023] The processor's start code is a segment of code verified by the first root of trust chip for each processor, and can be viewed as the starting point of the trusted chain within each processor. In some embodiments, for the main processor, the start code can be the BIOS. For the coprocessor, the start code is the lowest-level control firmware of the coprocessor, which can implement the coprocessor's power-on self-test and processor initialization. The coprocessor's start code can be a segment of boot code embedded in its ROM (such as XPU-1ROM, XPU-2ROM, ..., XPU-NROM, etc.), or it can be called ROM boot code.
[0024] In some embodiments, the first root of trust chip can measure the start code in each processor of the computing device using a trusted metric. For example, the trusted metric can obtain one or more pieces of data (such as instructions, parameters, etc.) from the start code of the processor and calculate its hash value. The calculated hash value is then compared with a pre-stored benchmark value in the trusted storage root. When the comparison result matches, the start code is determined to have passed verification, and the first root of trust chip can then start the start code of the corresponding processor. For example, the first root of trust chip controls the main processor to load the BIOS into the computing device's memory, allowing the start code to be executed. As another example, after the coprocessor's ROM code has passed verification, the first root of trust chip controls the coprocessor to load the ROM code into its memory so that the ROM code can be executed.
[0025] In some embodiments, when the comparison results are inconsistent, it can be determined that the initial code verification fails, and the first root of trust chip does not start the initial code of the corresponding processor, or restricts the start of the initial code. For example, the first root of trust chip can control the processor to load a portion of the initial code into memory (the memory of the computing device or the memory of the coprocessor) for execution. In other embodiments, when verification fails, the first root of trust chip can still start the initial code of the processor, but at the same time store the verification data, which may include the metrics calculated on the initial code and / or the comparison results, such as storing them in the trusted root of storage in the form of an audit report or log.
[0026] In some embodiments, each of two or more processors in a multiprocessor computing device is configured to: verify its next-level code through the start code, and start the next-level code after successful verification; verify the next-level code of the start code, and start the next-level code after successful verification; thereby verifying and starting the next-level code layer by layer, thus completing the establishment of the trusted chain for that processor. Specifically, for the main processor CPU, the various levels of code below its start code may sequentially include: master boot record code, OS (Operating System) loader, OS kernel, application programs, etc.; for the coprocessor, the various levels of code below its start code may sequentially include: XPU firmware, coprocessor subsystem OS (Operating System), etc.
[0027] After the initial code in the processor starts, each processor begins to establish its own trusted chain internally. Within the processor, the trusted chain is established layer by layer following the processor's startup path. In some embodiments, relevant information for each verification during the establishment of the trusted chain by the main processor and coprocessors is recorded in the trusted storage root. This relevant information includes, but is not limited to, calculated metrics and comparison results between the calculated metrics and pre-stored benchmark values in the trusted storage root.
[0028] In some embodiments, a processor within a computing device (such as a main processor or a coprocessor) can act as the requester, initiating a request for local verification from the computing device. For example, the main processor can request a trusted verification of a first coprocessor from a first root of trust chip in the computing device. The trusted reporting root in the first root of trust chip can generate an audit report based on verification data related to the first coprocessor in the trusted storage root and send it to the main processor. Similarly, the trusted reporting root can digitally sign the audit report. More specifically, the processor can initiate a request for local verification from the computing device by executing a relevant computer program. As an example, if the main processor executes an application and needs to send relevant sensitive data to a coprocessor for privacy computing, the application can contain instructions to request local verification from the first root of trust chip and set program execution conditions so that the coprocessor is called to process the sensitive data only after the local verification indicates that the coprocessor is trusted. Within a computing device, when processors call each other (such as the main processor calling a coprocessor to perform image processing or privacy data computation), a trusted tree node is created. The trusted tree node is interactively verified through local proof requests within the computing device, thereby effectively expanding the trusted boundary of the processor and providing a sound trusted foundation for various applications on the computing device.
[0029] The following describes the implementation of some embodiments of this specification at the hardware architecture level.
[0030] In some embodiments, the first root of trust chip includes a data group port and a chip select port, wherein the number of data group ports can be one or more. The data group port may include a data port for receiving / transmitting data and a clock port. The data port and clock port of the first root of trust chip can be connected to the data port and clock port of each processor, respectively. Under the control of a clock signal, the first root of trust chip can read data from or output data to the processor. In some embodiments, the data ports for receiving data and transmitting data (both from the perspective of the first root of trust chip) can be configured separately. As an example, one data port can be used to receive data, and another data port can be used to transmit data. In still other embodiments, the same data port can operate in a time-sharing manner, either receiving data or transmitting data, according to configuration instructions.
[0031] In some embodiments, the chip select port of the first root of trust chip can be connected to multiple processors simultaneously. The first root of trust chip outputs the chip select serial code of the processor currently to be verified, such as "010", on the chip select port. Each processor can compare the received chip select signal with its own valid chip select signal. When they match, the processor is in the selected state.
[0032] In some embodiments, different processors can be selected by a computing-capable allocation unit via a serial chip select signal. In some embodiments, the allocation unit may include one or more of the following: microcontroller unit (MCU), complex programmable logic device (CPLD), and programmable gate array (FPGA).
[0033] In some embodiments, the data group port of the first root of trust chip can also be connected to the data group ports of each processor via an allocation component.
[0034] Figure 2 This is a schematic diagram of the structure of a computing device according to some embodiments of this specification.
[0035] For example, such as Figure 2 In the computing device 200 shown, the allocation component includes a CPLD. The data group port of the first root of trust chip has a communication connection with the data group ports of each processor through the allocation component. Specifically, the data group port of the first root of trust chip can be connected to a group of ports of the CPLD (hereinafter referred to as the first group of ports), and several other groups of ports of the CPLD (hereinafter referred to as the second, third, ... groups of ports) can be connected to the data group ports of multiple processors respectively.
[0036] In some embodiments, the data group ports of the first root of trust chip, the data group ports of the allocation unit, and the data group ports of each processor interact with each other using the SPI protocol. SPI is an abbreviation for Serial Peripheral Interface, a high-speed synchronous communication bus that enables communication between a master device and one or more slave devices. The conventional SPI protocol includes four lines: MISO (Master Data Input), MOSI (Master Data Output), SCLK (Clock), and CS (Chip Select). MISO is used for master data input and slave data output; MOSI is used for master data output and slave data input; SCLK is used to transmit the clock signal; and CS is used to transmit the chip select signal. MISO, MOSI, and SCLK can be considered as data group ports. In some embodiments, configuration instructions can be used to configure MISO and MOSI in the SPI protocol to simultaneously receive or transmit data (IO1, IO2), thus extending the original SPI protocol to a Dual SPI (Two-Wire Serial Peripheral Interface) protocol. In this case, the first root of trust chip and the processor can write or read data at twice the speed, improving data transmission efficiency. In some other embodiments, the number of data ports can be increased, such as 4-wire or 8-wire, following the Quad SPI and Oct SPI protocols respectively, to further improve data transmission efficiency.
[0037] In some embodiments, the chip select port of the first root of trust chip can be connected to the allocation component. Specifically, the chip select port CS of the first root of trust chip can be connected to a port of the CPLD. In some embodiments, the chip select signal can be encoded using 8B / 10B encoding, variable-length encoding, or user-defined encoding. The first root of trust chip and the allocation component can be pre-configured with the serial chip select encoding corresponding to each processor, for example, the main processor corresponds to "001", the coprocessor GPU corresponds to "010", the coprocessor DPU corresponds to "011", and so on. When there is more processor data, the number of bits in the serial encoding can be increased. Since some embodiments of this specification represent the chip select signals of each processor through serial data, only one data line is needed to transmit the chip select signals of different processors.
[0038] In some embodiments, the chip select port of the first root of trust chip may include two (such as CS1 and CS2). In this case, the chip select ports CS1 and CS2 can be connected to the two ports of the CPLD respectively, and communication can be achieved through the I2C protocol. I2C (also known as I2C) 2 I2C (or I2C) is a two-wire synchronous serial bus that includes SDA (serial data line) and SCL (serial clock line). In this embodiment, one port of the first root of trust chip, such as CS1, is used as the SDA port to transmit the serially encoded chip select signal, and the other port, such as CS2, is used as the SCL port to transmit the clock signal upon which I2C communication depends. Under the control of the SCL clock, the first root of trust chip can transmit the serial chip select signal of the corresponding processor to the allocation unit through the SDA port.
[0039] In some embodiments, the allocation component is used to decode the serial chip select signal output by the first root of trust chip and connect the data group port of the first root of trust chip to the data group port of the corresponding processor based on the decoded signal. A CPLD is a digital integrated circuit whose logic functions are constructed by the user according to their own needs. Using methods such as schematic diagrams and hardware description languages, corresponding object files are generated, and the code is transferred to the CPLD via a download cable to configure its internal pathways. As an example, the CPLD can decode the serial chip select signal to determine the selected processor. If the serial chip select signal transmitted by the first root of trust chip is "001", the CPLD decodes it and determines that the first root of trust chip currently needs to interact with the main processor CPU. The CPLD can then change its internal signal path, connecting the first group of ports to the second group of ports (the group of ports connected to the main processor CPU). Thus, the first root of trust chip can communicate with the main processor CPU through its data group port to complete the measurement or verification of the main processor CPU.
[0040] It should be noted that most computing devices have a CPLD on their motherboard, and current security chips support the SPI protocol. Therefore, this embodiment can be implemented with almost no hardware modification to existing computing devices, thus achieving the establishment of a trust tree in a multiprocessor computing device at a relatively low cost. Furthermore, the CPLD's internal pathways can be configured via software, and no additional chip select ports need to be set between the allocation component and each processor.
[0041] by Figure 2 For example, when the computing device 200 constructs a root of trust, it first activates the first root of trust chip. The first root of trust chip encodes the chip select information used to select the target processor (such as the coprocessor XPU-1) to obtain a chip select signal, and transmits the chip select signal to the CPLD via chip select ports CS1 and CS2 based on the I2C protocol. Then, the CPLD decodes the chip select signal received by SDA and SCL, determines the target processor to be selected, and connects the data group port of the first root of trust chip to the data group port of the target processor, so that the first root of trust chip can verify the start code of the corresponding processor, and activate the start code of that processor after successful verification. Subsequently, the target processor internally measures or verifies the lower-level code level by level, establishing a trust chain.
[0042] In addition, Figure 2 Based on the illustrated embodiment, the chip select port of the first root of trust chip can be connected to the chip select ports of each processor through the allocation component. That is, the allocation component has a set of chip select ports respectively connected to the chip select ports of each processor. Further, the allocation component decodes the serial chip select signal output by the first root of trust chip and outputs a decoded signal to the chip select port of each processor to select the corresponding processor. After selecting the corresponding processor, the data group port of the first root of trust chip can be connected to the data group port of the corresponding processor through the allocation component to realize data transmission. As another variation of this embodiment, the CPLD can pre-connect the data port of the first root of trust chip to the data group ports of each processor. This embodiment may increase the occupancy of the allocation component interface, but it can reduce the steps requiring software control.
[0043] Figure 3 This is a schematic diagram of the structure of a computing device according to some embodiments of this specification.
[0044] refer to Figure 3 In some embodiments, the data group port of the first root of trust chip can be connected to the data group ports of each processor, and the chip select port of the first root of trust chip can be connected to the chip select ports of each processor through an allocation unit. That is, the allocation unit only processes the chip select signal of the first root of trust and connects to multiple processors through ports CS-1, CS-2, ..., CS-n respectively.
[0045] In some embodiments, the allocation unit decodes the serial chip select signal output by the first root trust chip and outputs a decoded signal to the chip select port of each processor to select the corresponding processor. After the corresponding processor is selected, the data group port of the first root trust chip can transmit data with the data group port of the corresponding processor. As an example, the chip select signal transmitted by the first root trust chip to the allocation unit is "010". After decoding it, the allocation unit determines that the processor that needs to interact with the data is the coprocessor GPU. Then, the allocation unit can output the chip select signal (or the decoded chip select signal) in parallel through its CS-1, CS-2, ..., CS-n ports. The port connected to the coprocessor GPU outputs a low level, i.e., "0", and the port connected to other processors outputs a high level, i.e., "1".
[0046] by Figure 3 For example, when constructing a root of trust in computing device 300, the difference from computing device 200 is that: the allocation component decodes the chip select signal received to obtain a decoded signal, and then outputs the decoded signal to the chip select port of each processor. After receiving a valid chip select signal, the target processor communicates through its data group port, which is directly connected to the data group port of the first root of trust chip.
[0047] In this embodiment, the allocation component can be any chip capable of performing data processing, such as an MCU or FPGA, or it can be a CPLD.
[0048] Figure 4 This is an exemplary flowchart of a trusted root construction method according to some embodiments of this specification.
[0049] In some embodiments of this specification, a method for constructing a root of trust for a multiprocessor computing device is provided. This computing device includes two or more processors, which can be... Figure 2 The computing device 200 or Figure 3 The computing device 300 in the middle. For example... Figure 4 As shown, the process 400 of this method may include the following steps:
[0050] Step 410: Start the first trusted root chip.
[0051] Step 420: The first root of trust chip selects different processors for communication based on a serial chip select signal to verify the start code of the corresponding processor, and starts the start code of the processor after the verification is successful.
[0052] Step 430: For each of the two or more processors: the next level of code is verified by the first code, and the next level of code is started after the verification is passed; the next level of code of the first code verifies the next level of code after that, and the next level of code after that is started after the verification is passed; in this way, the next level of code is verified and started layer by layer, thereby completing the establishment of the trusted chain of the processor.
[0053] Since the method for constructing a root of trust using computing device 200 or computing device 300 has already been described in the preceding text, please refer to [link to relevant documentation]. Figure 2 and Figure 3 The corresponding locations will not be elaborated upon here.
[0054] In some embodiments, information related to each of the verifications is stored in the first trusted root chip.
[0055] In some embodiments, step 410 includes: decoding the serial chip select signal output by the first root trust chip through the allocation component, and selecting a corresponding processor based on the decoded signal so that the first root trust chip can communicate with the processor.
[0056] By executing process 400, a multiprocessor computing device can establish a trust tree that extends the startup link of each processor, starting from the first root trust chip.
[0057] The beneficial effects that the embodiments of this specification may bring include, but are not limited to: (1) using the first root of trust chip to select different processors based on serial chip select signals, so that the number of processors in the computing device can be expanded infinitely; (2) constructing a trust tree starting from the first root of trust chip in a multi-processor computing device, thereby improving the security level of the entire system; (3) the serial chip select signal can be encoded in any way, which to some extent hides the correspondence between the chip select signal and the processor, thus playing the role of encrypting the chip select signal.
[0058] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation on the embodiments of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to the embodiments of this specification. Such modifications, improvements, and corrections are suggested in the embodiments of this specification, and therefore, such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.
[0059] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.
[0060] Furthermore, those skilled in the art will understand that various aspects of the embodiments of this specification can be described and illustrated through several patentable types or situations, including any new and useful combinations of processes, machines, products, or substances, or any new and useful improvements thereto. Accordingly, various aspects of the embodiments of this specification can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." Furthermore, various aspects of the embodiments of this specification may be embodied as a computer product located on one or more computer-readable media, the product including computer-readable program code.
[0061] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.
[0062] The computer program code required for the operation of each part of the embodiments in this specification can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).
[0063] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in the embodiments of this specification are not intended to limit the order of the processes and methods of the embodiments of this specification. Although some inventive embodiments that are currently considered useful have been discussed by way of various examples in the foregoing disclosure, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. Rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented solely by software solutions, such as installing the described system on existing processing devices or mobile devices.
[0064] Similarly, it should be noted that, in order to simplify the description of the embodiments disclosed in this specification and thereby aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the objects of the embodiments in this specification require more features than those mentioned in the claims. In fact, the embodiments have fewer features than all the features of the single embodiments disclosed above.
[0065] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with this specification, as well as documents that limit the broadest scope of the claims of this application (currently or subsequently appended to this application). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.
[0066] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of the embodiments described herein. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.
Claims
1. A multiprocessor computing device, comprising a first root of trust chip, an allocation unit, and two or more processors; The first root of trust chip is used to select different processors for communication via a serial chip select signal, obtain one or more data entries of the start code in the corresponding processor to verify the start code of the corresponding processor, and start the start code of the processor after successful verification; wherein, The data group port of the first root of trust chip is connected to the data group port of each processor. The chip select port of the first root of trust chip is connected to the chip select port of each processor through the allocation component. The allocation component is used to decode the chip select signal output by the first root of trust chip and output a decoding signal to the chip select port of each processor to select the corresponding processor. Each of the two or more processors is configured to: verify the next level of code through the first code, and start the next level of code after the verification is successful; the next level of code of the first code verifies the next level of code after that, and starts the next level of code after the verification is successful; in this way, the next level of code is verified and started layer by layer, thereby completing the establishment of the trusted chain of the processor. The information related to each of the verifications is stored in the first root of trust chip; the first root of trust chip is also used to send an audit report to the requester in response to a local proof request, the audit report being generated based on the verification data related to the requested party in the first root of trust chip; the requester and the requested party are both processors in the multiprocessor computing device, and the local proof request is initiated when the processors in the multiprocessor computing device call each other.
2. The computing device as claimed in claim 1, wherein, The chip select port of the first trusted root chip is connected to the allocation component via the I2C protocol.
3. The computing device as claimed in claim 1, wherein, The dispensing component includes one or more of the following: Microcontroller units, complex programmable logic devices, and programmable logic gate arrays.
4. The computing device as claimed in claim 1, wherein, The data group port follows the SPI protocol.
5. A method for constructing a root of trust in a multiprocessor computing device, the computing device comprising two or more processors, the method comprising: Start the first trusted root chip; The first root of trust chip uses a serial chip select signal to select different processors for communication, obtain one or more data entries of the start code in the corresponding processor to verify the start code of the corresponding processor, and start the start code of the processor after successful verification; wherein, the data group port of the first root of trust chip is connected to the data group port of each processor respectively, and the chip select port of the first root of trust chip is connected to the chip select port of each processor respectively through an allocation component. The allocation component is used to decode the chip select signal output by the first root of trust chip and output a decoded signal to the chip select port of each processor to select the corresponding processor; For each of the two or more processors: the first code verifies the next level of code, and starts the next level of code after the verification is successful; the next level of code of the first code verifies the next level of code after that, and starts the next level of code after the verification is successful; in this way, the code of the next level is verified and started layer by layer, thereby completing the establishment of the trusted chain of the processor; the information related to each of the verifications is stored in the first trusted root chip; The first trusted root chip responds to the local proof request by sending an audit report to the requester; the audit report is generated based on the verification data related to the requested party in the first trusted root chip, and both the requester and the requested party are processors in the multiprocessor computing device, and the local proof request is initiated when the processors in the multiprocessor computing device call each other.
Citation Information
Patent Citations
Trusted verification method and system, equipment and storage medium
CN111901285A
Authentication certificate transmission method, chip and equipment
CN113032786A
Trusted measurement method, trusted chip, logic controller and trusted measurement system
CN113468615A
