Secure computing platform
Through the separation design of master-core and slave-core, the isolation and high reliability of the security application of train control systems is achieved, and the problems of high hardware cost, complex maintenance and poor scalability in the existing technology are solved. The EN50129 standard is met and multiple implementations are achieved. The independent operation of individual security applications.
Patent Information
- Application Number
- CN202410289029.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-14
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-03-14
AI Technical Summary
The existing train control system security computing platform requires an independent hardware platform for each subsystem, resulting in high hardware cost, large deployment area, complex maintenance, poor scalability, and difficult to meet the EN50129 functional safety certification standard.
The design of separation between the master and slave cores is adopted, and the master core runs the management program and non-secure applications. The slave core runs the secure applications independently. Through shared memory communication, the isolation and high reliability of the secure applications are achieved, meeting the EN50129 standard.
It reduces hardware costs and deployment area, simplifies the maintenance process, improves the scalability and security of the system, and realizes the independent operation of multiple security applications on one platform.
Smart Images

Figure CN117892365B_ABST
Abstract
Description
Technical Field
[0001] This article relates to the field of transportation technology, and more particularly to a secure computing platform. Background Art
[0002] With the in-depth study of cloud technology in the next generation of train control systems, the train control safety computing platform has gradually developed from an independent structure to an integrated and modular one. The use of cloud technology in the next generation of rail transit train control systems will surely become a major technological advancement in the future. The core idea of cloud technology is to use software and hardware technology to abstract physical resources, thereby virtualizing multiple independent resources from the underlying physical resources, or dividing them into multiple independent and isolated operating environments to meet the application operation requirements of various attributes. At present, in the train control system in the field of rail transit, the safety computing platform refers to a computing platform that can prevent the occurrence of endangerment to personal safety and major equipment losses in the event of a fault, and is the core control unit of the rail transit train control system. The ground safety products built on the safety platform in the current rail transit signal field include the computer interlocking system CBI, the station train control center system TCC, the radio block center RBC of the CTCS-3 level train control system, and the temporary speed limit server TSRS. These systems are all safety-critical subsystems that constitute the national railway train control system. The functional safety integrity of the system needs to meet the requirements of the EN50129 standard to reach the SIL4 level, and the safety computing platform is the core equipment to ensure this requirement.
[0003] The safety computing platform structure of the train control system in the field of rail transit is mainly its safety hardware structure design, such as the two-by-two-out-of-two structure and the three-by-two structure, as well as the software strategies related to the safety hardware structure, such as the two-by-two logic and the master-slave switching logic. Among them, the two-by-two-out-of-two structure means that the safety computing platform is composed of two systems, A and B. A and B have the same hardware structure. When working normally, A and B are in a one-master-one-slave redundant relationship. When the main system has an abnormal downtime, the standby system is upgraded to the main system to achieve dual-system redundant switching. The entire system function still operates normally, thus forming the hardware "two-by-two" architecture and software master-slave switching logic. Each system consists of two central processors, which run independently and run the same logic and process the same data. The two central processors will compare and vote on the results of data calculation. Only when the vote is consistent can the data be output to the outside, thus forming the hardware "two-out" structure and software "two-out-of-two" logic. The three-out-of-two structure is similar to the two-by-two-out-of-two structure, so it will not be repeated here.
[0004] At present, no matter the train control safety computing platform adopts the above-mentioned two-by-two-out-of-two structure or three-out-of-two structure, a set of safety computing platform only supports one subsystem of the train control system or one safety function application. This form makes each subsystem use an independent hardware platform, which has the following problems: First, each subsystem requires a safety computing platform, and each subsystem needs to include racks, cabinets, power supplies, industrial computer terminals, switches, lightning protection and other hardware facilities that are compatible with the safety computing platform, resulting in high hardware costs and a large deployment area for the entire train control system; secondly, for the operation and maintenance of the train control system, it is necessary to maintain the software and hardware of the safety computing platform of each subsystem, which increases the complexity and labor costs of maintenance. For example, if the safety computing platform of one of the subsystems has undergone a software or hardware upgrade, if other subsystems need to be upgraded in the same way according to the safety computing platform, the subsystem must be shut down. If it is upgraded, the safety computing platforms between systems will be different. As the number of subsystems increases, , making the version management of the safety computing platform more complicated; secondly, with the increasing demand for train control systems, the increase of subsystems and the expansion of functions are inevitable development trends. When expanding new subsystems or increasing system functions, it is necessary to re-evaluate the performance of the current safety computing platform's central processor to see if it can meet the needs of new subsystems or functional expansions. If not, it is necessary to develop new and higher-performance safety computing platform software and hardware, which not only increases the workload of system transplantation, but also requires re-security certification, resulting in poor system scalability; finally, when one system of the current safety computing platform fails, it automatically switches to another system for operation. The faulty system requires manual maintenance to handle the fault. Before the faulty system is handled, the system will run as a single system. At this time, if the other system also fails, the entire system will enter a faulty state, affecting train operations. The core technology of cloud technology is virtualization technology, which specifically refers to a resource management technology in computers. It provides an easy-to-implement platform for scalable and high-availability services, abstracts and virtualizes the physical resources in the computer to improve work performance. The current virtualization technology architecture mainly includes two implementation architectures, namely host architecture and bare metal architecture. Host architecture such as Figure 1 As shown in the figure, the architecture consists of a host operating system running on a hardware platform, and the virtualization function is implemented by embedding the virtual manager in the operating system. The virtual manager manages device drivers and services, virtual machines 1, 2, and n. Each of virtual machines 1 to n includes an application and an operating system. The bare metal structure is shown in the figure. Figure 1As shown in the figure, this architecture does not require host operation. The virtual monitor works on the hardware platform and provides a virtualized environment to the virtual machine. The bare metal structure also includes device drivers, virtual machine 1, virtual machine 2, and virtual machine n. Each of virtual machines 1 to n includes applications and operating systems. However, both architectures are difficult to meet the EN50129 functional safety certification standard. The reason is that whether using the host operating system or the virtual monitor, firstly, the complexity of the operating system and the virtual monitor makes it difficult to perform fault-safety analysis. Secondly, the host operating system or the virtual monitor needs to schedule all hardware resources, such as the central processing unit and memory, so that the security applications on each virtual machine cannot be effectively isolated. Summary of the invention
[0005] The embodiments of the present application provide a secure computer module and a secure computing platform, which enable each slave core to run an independent execution program of a security application, so that the security applications have no impact on each other and meet the EN50129 functional safety certification standard. The number of execution programs of the running security applications is the same as the number of slave cores, and a secure computing platform can run the execution programs of two or more security applications.
[0006] The present application provides a secure computer module, comprising at least two secure computers, each of which comprises a central processing unit, a first memory and an external device, each of which comprises a central processing unit, the at least two secure computers are configured to run the same logic, process the same data, compare and vote on calculation results, and output data after a consistent vote, the central processing unit comprises a master core and at least one slave core;
[0007] The main core is configured to run a first operating system and to run a hypervisor and an executive program of a non-secure application on the first operating system;
[0008] Each slave core is configured to start under the control of the master core, and to run a second operating system, and to run an independent security application execution program on the second operating system.
[0009] In an exemplary embodiment, the first memory includes a non-secure computing address block, secure computing address blocks and shared memory address blocks having the same number as the slave cores; the secure computing address blocks and the shared memory address blocks correspond to the slave cores one by one respectively;
[0010] The master core is also configured to have only the authority to access and read and write the non-secure computing address block and the shared memory address block; the slave core is also configured to have only the authority to access and read and write the secure computing address block and the shared memory address block corresponding to itself; the master core and each slave core communicate through the shared memory address block corresponding to the slave core.
[0011] In an exemplary embodiment, the external device includes a second memory;
[0012] The second memory is connected to the main core and is configured to store a startup script, a startup program, an image of the first operating system, a device tree file, an executive program of a hypervisor or a non-secure application, and an image of the second operating system.
[0013] In an exemplary embodiment, the master core is further configured to establish a heartbeat mechanism with each slave core, and monitor the status of the slave core according to the heartbeat mechanism.
[0014] In an exemplary embodiment, the management program is used to drive an external device, access the external device, and start a slave core.
[0015] In an exemplary embodiment, the slave core is further configured to perform a hardware self-test that meets preset standard requirements upon startup.
[0016] The present application provides a secure computing platform, including multiple main control subsystems and management modules;
[0017] Each main control subsystem includes at least two safety computer modules; the safety computer module is the safety computer module described in any of the above embodiments;
[0018] The management module is configured to store the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information; configure each main control subsystem according to the security computing platform configuration information; after establishing a secure connection with the two security computer modules of any main control subsystem, send the execution program of the security application to the two security computer modules of the main control subsystem, and manage each security application.
[0019] In an exemplary embodiment, at least one backup safety computer module is also included;
[0020] The management module is further configured to replace the failed safety computer module with the backup safety computer module when a safety computer module in any main control subsystem fails, so that the backup safety computer module becomes the backup system of the main control subsystem.
[0021] In an exemplary embodiment, it also includes a switch and a maintenance management terminal;
[0022] All the safety computer modules are respectively connected to the switch to achieve interconnection between the safety computer modules;
[0023] The maintenance and management terminals are connected to the switches respectively, and are configured to send the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information to the management module, and provide manual query, modification and update of the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information stored in the management module.
[0024] In an exemplary embodiment, the management module includes a main management module and a backup management module to form a "two by two take two" architecture;
[0025] A redundant switch is also included to form a "two by two take two" architecture with the switch.
[0026] The security computer module of the embodiment of the present application is provided with a master core and a slave core, the master core and the slave core run under different operating systems, the master core runs a hypervisor and an executive program of a non-security application, the slave core runs an executive program of a security application, and each slave core runs an independent executive program of a security application, so that the security applications have no influence on each other. The number of executive programs of the running security applications is the same as the number of slave cores.
[0027] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by implementing the present application. Other advantages of the present application can be realized and obtained by the schemes described in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings are used to provide an understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.
[0029] Figure 1 is a schematic diagram of a virtualization technology architecture in some embodiments;
[0030] Figure 2 A schematic diagram of a secure computer module according to at least one embodiment of the present application;
[0031] Figure 3 A schematic diagram of a secure computer module according to at least one embodiment of the present application;
[0032] Figure 4 A schematic diagram of a secure computer module according to at least one embodiment of the present application;
[0033] Figure 5 A schematic diagram of a secure computing platform according to at least one embodiment of the present application;
[0034] Figure 6 A schematic diagram of a secure computing platform according to at least one embodiment of the present application;
[0035] Figure 7 A schematic diagram of a secure computing platform according to at least one embodiment of the present application;
[0036] Figure 8 A schematic diagram of a secure computing platform according to at least one embodiment of the present application;
[0037] Fig. 9 A schematic diagram of a secure computing platform according to at least one embodiment of the present application. DETAILED DESCRIPTION
[0038] Figure 2 A schematic diagram of a secure computer module according to at least one embodiment of the present application, such as Figure 2 As shown, the security computer module includes a first security computer to an nth security computer, wherein n is a positive integer greater than 1, each security computer includes a central processing unit, a first memory and an external device, each security computer includes a central processing unit, and the at least two security computers are configured to run the same logic, process the same data, compare and vote on the calculation results, and output data after a consistent vote.
[0039] The main core is configured to run a first operating system and to run a hypervisor and an executive program of a non-secure application on the first operating system;
[0040] Each slave core is configured to start under the control of the master core, and to run a second operating system, and to run an independent security application execution program on the second operating system.
[0041] The security computer module of the embodiment of the present application is provided with a master core and a slave core, and the master core and the slave core run under different operating systems, and the supervisor and the non-security application execution program are run on the master core, and the security application execution program is run on the slave core, and each slave core runs an independent security application execution program, so that each security application has no effect on each other. The number of security application execution programs running is the same as the number of slave cores. A security computing module can run the execution program of one security application, or it can run the execution programs of two or more security applications.
[0042] Exemplarily, the first operating system may be a LINUX system, or may be other real-time operating systems, such as VxWorks, RT-Thread, or a real-time operating system RTOS (Real Time operating System, RTOS for short). VxWorks is a real-time operating system launched by Wind River Corporation of the United States. RT-Thread is an open source real-time operating system mainly developed by the Chinese open source community.
[0043] For example, the second operating system may be an operating system that complies with the EN50129 functional safety certification standard or meets the software requirements of the IEC61508-3 standard, and has a safety level of SIL3. For example, the second operating system may be a secure microkernel system or a secure VxWorks.
[0044] For example, each central processing unit may include four identical processor cores of the Advanced RISC Machine (ARM) Cortex-A53 architecture. The ARM Cortex-A53 is a processor core for mobile devices and embedded systems. It uses the ARMv8-A architecture and is the first ARM Cortex-A series processor core launched by ARM that supports a 64-bit instruction set. The operating mechanism of the four cores is the Asymmetric Multi-Processing (AMP) architecture, that is, each core runs its own proprietary independent kernel.
[0045] Exemplarily, the master core is responsible for external device drivers, the boot function of the slave core, and running the hypervisor and the execution program of the non-safety application.
[0046] The main external devices of each central processing unit include field programmable gate array FPGA, Ethernet interface ETH, serial port UART, flash memory FLASH, etc. Only the master core has the authority to access these external devices and interfaces, and the slave core cannot access them.
[0047] Exemplarily, there may be two or more slave cores.
[0048] In an exemplary embodiment, the master core is further configured to establish a heartbeat mechanism with each slave core, and monitor the status of the slave core according to the heartbeat mechanism, so that slave core failures can be discovered in a timely manner.
[0049] In an exemplary embodiment, the slave core is further configured to perform a hardware self-test that meets preset standard requirements upon startup.
[0050] The preset standard may be the EN50129 standard. The hardware self-test may include a memory self-test, a memory management unit self-test, an instruction decoding self-test, a register self-test, an instruction execution self-test, a program counter self-test, a stack pointer self-test, and a clock self-test.
[0051] In an exemplary embodiment, the management program can be used to drive external devices, access the external devices, and start the slave core.
[0052] Among them, a non-safety application may refer to an application that does not participate in calculations involving safety functions.
[0053] The first memory may be a program running memory, which is a volatile memory, that is, data is lost after power failure.
[0054] Figure 3 A schematic diagram of a secure computer module according to at least one embodiment of the present application, such as Figure 3 As shown, the security computer module includes: the security computer module includes a first security computer to an nth security computer, wherein n is a positive integer greater than 1, each security computer includes a central processing unit, a first memory and an external device, each security computer includes a central processing unit, and the at least two security computers are configured to run the same logic, process the same data, compare and vote on the calculation results, and output data after the vote is consistent. The first memory includes a non-secure computing address block, a secure computing address block with the same number of slave cores, and a shared memory address block; the secure computing address block and the shared memory address block correspond to the slave cores one by one;
[0055] The main core is configured to run a first operating system and to run a hypervisor and an executive program of a non-secure application on the first operating system;
[0056] Each slave core is configured to start under the control of the master core; and to run a second operating system, and to run an independent execution program of a security application on the second operating system;
[0057] The master core is also configured to have only the authority to access and read and write the non-secure computing address block and the shared memory address block; the slave core is also configured to have only the authority to access and read and write the secure computing address block and the shared memory address block corresponding to itself; the master core and each slave core communicate through the shared memory address block corresponding to the slave core.
[0058] The security computer module of the embodiment of the present application is provided with a main core and a slave core. The main core and the slave core run under different operating systems. The supervisor and the executive program of the non-security application are run on the main core, and the executive program of the security application is run on the slave core, and each slave core runs an independent executive program of the security application, so that each security application has no influence on each other. The number of executive programs of the running security applications is the same as the number of slave cores. A security computing module can run the executive program of one security application, or it can run the executive programs of two or more security applications. The main core and the slave core communicate through a shared memory address block to achieve high-speed communication. The executive programs of the security applications running on each slave core only use their own physical memory blocks for security computing, and the security computing areas of the security applications are isolated from each other, with high reliability and security, and meet the requirements of the EN50129 standard.
[0059] For example, each central processing unit may include four identical processor cores of the Advanced RISC Machine (ARM) Cortex-A53 architecture. The ARM Cortex-A53 is a processor core for mobile devices and embedded systems. It uses the ARMv8-A architecture and is the first ARM Cortex-A series processor core launched by ARM that supports a 64-bit instruction set. The operating mechanism of the four cores is the Asymmetric Multi-Processing (AMP) architecture, that is, each core runs its own proprietary independent kernel.
[0060] Exemplarily, the first operating system may be a LINUX system, or may be other real-time operating systems, such as VxWorks, RT-Thread, or a real-time operating system RTOS (Real Time operating System, RTOS for short). VxWorks is a real-time operating system launched by Wind River Corporation of the United States. RT-Thread is an open source real-time operating system mainly developed by the Chinese open source community.
[0061] For example, the second operating system may be an operating system that complies with the EN50129 functional safety certification standard or meets the software requirements of the IEC61508-3 standard, and has a safety level of SIL3. For example, the second operating system may be a secure microkernel system or a secure VxWorks.
[0062] Exemplarily, the master core is responsible for allocating the first memory, for driving the external devices of the secure computer module, for the boot function of the slave core, and for running the management program and the execution program of the non-secure application.
[0063] The first memory can be allocated as follows: Assuming that the address space of the first memory is 4GB, the first memory can be divided into 4 address blocks. Assuming that the main core can be allocated a 1GB address block, which is a non-secure computing address block, used to run the Linux system, hypervisor and executive programs of non-secure applications. The remaining address space is evenly distributed to the slave cores. Assuming there are 3 slave cores, each slave core will be allocated a 1GB address block. This 1GB memory address block is divided into two parts: a shared memory communication address block and a secure computing address block; the shared memory communication address block is used for shared memory communication with the main core, and its size can be 250MB; the secure computing address block is used to run the secure microkernel and the executive programs of secure applications, and its size can be the remaining 750MB.
[0064] The master core has access and read and write permissions to the shared memory communication address blocks assigned to other slave cores, but cannot access the secure computing address blocks assigned to other slave cores. Slave cores cannot access each other's address block memory, and slave cores cannot access the master core's address blocks.
[0065] The main external devices of each central processing unit include field programmable gate array FPGA, Ethernet interface ETH, serial port UART, flash memory FLASH, etc. Only the master core has the authority to access these external devices and interfaces, and the slave core cannot access them.
[0066] Exemplarily, there may be two or more slave cores.
[0067] In an exemplary embodiment, the master core is further configured to establish a heartbeat mechanism with each slave core, and monitor the status of the slave core according to the heartbeat mechanism, so that slave core failures can be discovered in a timely manner.
[0068] In an exemplary embodiment, the slave core is further configured to perform a self-test that meets a preset standard upon startup.
[0069] The preset standard may be the EN50129 standard. The hardware self-test may include a memory self-test, a memory management unit self-test, an instruction decoding self-test, a register self-test, an instruction execution self-test, a program counter self-test, a stack pointer self-test, and a clock self-test.
[0070] In an exemplary embodiment, the management program can be used to allocate the first memory, drive external devices, access the external devices, and start the slave core.
[0071] Among them, a non-safety application may refer to an application that does not participate in calculations involving safety functions.
[0072] The first memory may be a program running memory, which is a volatile memory, that is, data is lost after power failure. Exemplarily, the first memory may be a double data rate memory (DDR memory), for example, a double data rate synchronous dynamic random access memory.
[0073] Figure 4 A schematic diagram of a secure computer module according to at least one embodiment of the present application, such as Figure 4 As shown, the secure computer module includes: the secure computer module includes a first secure computer to an nth secure computer, wherein n is a positive integer greater than 1, each secure computer includes a central processing unit, a first memory and an external device, each secure computer includes a central processing unit, and the at least two secure computers are configured to run the same logic, process the same data, compare and vote on the calculation results, and output data after the vote is consistent. The first memory includes a non-secure computing address block, a secure computing address block with the same number as the slave cores, and a shared memory address block; the secure computing address block and the shared memory address block correspond to the slave cores one by one. The external device includes a second memory, which is connected to the master core and is configured to store a startup script, a startup program, an image of the first operating system, a device tree file, an executive program of a hypervisor or a non-secure application, and an image of the second operating system.
[0074] The main core is configured to run a first operating system and to run a hypervisor and an executive program of a non-secure application on the first operating system;
[0075] Each slave core is configured to start under the control of the master core; and to run a second operating system, and to run an independent execution program of a security application on the second operating system;
[0076] The master core is also configured to have only the authority to access and read and write the non-secure computing address block and the shared memory address block; the slave core is also configured to have only the authority to access and read and write the secure computing address block and the shared memory address block corresponding to itself; the master core and each slave core communicate through the shared memory address block corresponding to the slave core.
[0077] The security computer module of the embodiment of the present application is provided with a main core and a slave core. The main core and the slave core run under different operating systems. The supervisor and the executive program of the non-security application are run on the main core, and the executive program of the security application is run on the slave core, and each slave core runs an independent executive program of the security application, so that each security application has no influence on each other. The number of executive programs of the running security applications is the same as the number of slave cores. A security computing module can run the executive program of one security application, or it can run the executive programs of two or more security applications. The main core and the slave core communicate through a shared memory address block to achieve high-speed communication. The executive programs of the security applications running on each slave core only use their own physical memory blocks for security computing, and the security computing areas of the security applications are isolated from each other, with high reliability and security, and meet the requirements of the EN50129 standard.
[0078] For example, each central processing unit may include four identical processor cores of the Advanced RISC Machine (ARM) Cortex-A53 architecture. The ARM Cortex-A53 is a processor core for mobile devices and embedded systems. It uses the ARMv8-A architecture and is the first ARM Cortex-A series processor core launched by ARM that supports a 64-bit instruction set. The operating mechanism of the four cores is the Asymmetric Multi-Processing (AMP) architecture, that is, each core runs its own proprietary independent kernel.
[0079] Exemplarily, the first operating system may be a LINUX system, or may be other real-time operating systems, such as VxWorks, RT-Thread, or a real-time operating system RTOS (Real Time operating System, RTOS for short). VxWorks is a real-time operating system launched by Wind River Corporation of the United States. RT-Thread is an open source real-time operating system mainly developed by the Chinese open source community.
[0080] For example, the second operating system may be an operating system that complies with the EN50129 functional safety certification standard or meets the software requirements of the IEC61508-3 standard, and has a safety level of SIL3. For example, the second operating system may be a secure microkernel system or a secure VxWorks.
[0081] Exemplarily, the master core is responsible for allocating the first memory, for driving the external devices of the secure computer module, for the boot function of the slave core, and for running the management program and the execution program of the non-secure application.
[0082] The first memory can be allocated as follows: Assuming that the address space of the first memory is 4GB, the first memory can be divided into 4 address blocks. Assuming that the main core can be allocated a 1GB address block, which is a non-secure computing address block, used to run the Linux system, hypervisor and executive programs of non-secure applications. The remaining address space is evenly distributed to the slave cores. Assuming there are 3 slave cores, each slave core will be allocated a 1GB address block. This 1GB memory address block is divided into two parts: a shared memory communication address block and a secure computing address block; the shared memory communication address block is used for shared memory communication with the main core, and its size can be 250MB; the secure computing address block is used to run the secure microkernel and the executive programs of secure applications, and its size can be the remaining 750MB.
[0083] The master core has access and read and write permissions to the shared memory communication address blocks assigned to other slave cores, but cannot access the secure computing address blocks assigned to other slave cores. Slave cores cannot access each other's address block memory, and slave cores cannot access the master core's address blocks.
[0084] The main external devices of each central processing unit include field programmable gate array FPGA, Ethernet interface ETH, serial port UART, flash memory FLASH, etc. Only the master core has the authority to access these external devices and interfaces, and the slave core cannot access them.
[0085] Exemplarily, there may be two or more slave cores.
[0086] In an exemplary embodiment, the master core is further configured to establish a heartbeat mechanism with each slave core, and monitor the status of the slave core according to the heartbeat mechanism, so that slave core failures can be discovered in a timely manner.
[0087] In an exemplary embodiment, the slave core is further configured to perform a hardware self-test that meets preset standards upon startup.
[0088] The preset standard may be the EN50129 standard. The hardware self-test may include a memory self-test, a memory management unit self-test, an instruction decoding self-test, a register self-test, an instruction execution self-test, a program counter self-test, a stack pointer self-test, and a clock self-test.
[0089] In an exemplary embodiment, the management program can be used to allocate the first memory, drive external devices, access the external devices, and start the slave core.
[0090] Among them, a non-safety application may refer to an application that does not participate in calculations involving safety functions.
[0091] The first memory may be a program running memory, which is a volatile memory, that is, data is lost after power failure. Exemplarily, the first memory may be a double data rate memory (DDR memory), for example, a double data rate synchronous dynamic random access memory.
[0092] The second memory may be a non-volatile memory, that is, data will not be lost after power failure.
[0093] Exemplarily, the second memory may be a flash memory card (MicroSD).
[0094] Figure 5 A schematic diagram of a secure computer module according to at least one embodiment of the present application, such as Figure 5 As shown, the safety computer module includes two safety computers, a first safety computer 501, a second safety computer 502 and a safety watchdog 503. The first safety computer 501 includes a first central processor 51 and a first memory 515.
[0095] Among them, the first central processor 51 includes a main core 511, a first slave core 512, a second slave core 513, a third slave core 514, a first memory 515, a first field programmable array logic (FPGA) 5111 connected to the main core 511, a first Ethernet interface 5112 connected to the main core 511, a first serial port (UART) 5113 connected to the main core 511, a first flash memory (FLASH) 5114 connected to the main core 511, and a second memory (which can be MicroSD) 5115 connected to the main core 511.
[0096] The main core 511 runs a Linux system; a hypervisor and an executive program of a non-secure application run on the Linux system; the first slave core 512, the second slave core 513, and the third slave core 514 each run a secure microkernel system; and an executive program of a secure application runs on each of the secure microkernel systems of the slave cores.
[0097] The first secure computer 501 further includes a first memory 515 , which includes a non-secure computing address block 5151 , three secure computing address blocks 5152 , and three shared memory address blocks 5153 .
[0098] The second security computer 502 includes a second central processor 52. The second central processor 52 includes a master core 521, a first slave core 522, a second slave core 523, a third slave core 524, a first memory 525, a first field programmable array logic (FPGA) 5211 connected to the master core 521, a second Ethernet interface 5212 connected to the master core 521, a second serial port (UART) 5213 connected to the master core 521, a second flash memory (FLASH) 5214 connected to the master core 521, and a second memory (which may be MicroSD) 5215 connected to the master core 521.
[0099] The second secure computer 502 includes a first memory 525 , and the first memory 525 includes a non-secure computing address block 5251 , three secure computing address blocks 5252 , and three shared memory address blocks 5253 .
[0100] The main core 521 runs a Linux system; a hypervisor and an executive program of a non-secure application run on the Linux system; the first slave core 522, the second slave core 523, and the third slave core 524 each run a secure microkernel system; and an executive program of a secure application runs on the secure microkernel system of each slave core.
[0101] The at least two secure computers are configured to run the same logic, process the same data, compare and vote on the calculation results, and output the data after a consensus is reached;
[0102] The safety watchdog 503 is configured to receive a "feed the dog" signal periodically. If the "feed the dog" signal is not received within a specified time, the connection between the safety computer module and the first Ethernet interface 5112 and the second Ethernet interface 5212 is cut off to ensure that no erroneous data is output.
[0103] Among them, the "feed the dog" signal is sent by the management program when no abnormal failure occurs in the security computer module.
[0104] The master core is also configured to have only the authority to access and read and write the non-secure computing address block and the shared memory address block; the slave core is also configured to have only the authority to access and read and write the secure computing address block and the shared memory address block corresponding to itself; the master core has access and read and write authority to the shared memory communication address block assigned to other slave cores, but cannot access the secure computing address block assigned to other slave cores. The slave cores cannot access each other's address block memory, and the slave cores cannot access the address block of the master core.
[0105] The master core and each slave core communicate via a shared memory address block corresponding to the slave core.
[0106] The security computer module of the embodiment of the present application is provided with a main core and a slave core. The main core and the slave core run under different operating systems. The supervisor and the executive program of the non-security application are run on the main core, and the executive program of the security application is run on the slave core, and each slave core runs an independent executive program of the security application, so that each security application has no influence on each other. The number of executive programs of the running security applications is the same as the number of slave cores. A security computing module can run the executive program of one security application, or it can run the executive programs of two or more security applications. The main core and the slave core communicate through a shared memory address block to achieve high-speed communication. The executive programs of the security applications running on each slave core only use their own physical memory blocks for security computing, and the security computing areas of the security applications are isolated from each other, with high reliability and security, and meet the requirements of the EN50129 standard.
[0107] Figure 6 A schematic diagram of a secure computing platform of at least one embodiment of the present application, as shown in FIG6 , the secure computing platform includes a plurality of main control subsystems and management modules;
[0108] Each main control subsystem includes at least two security computer modules; the security computer module is a security computer module as described in any of the above embodiments;
[0109] The management module is configured to store the execution programs of all security applications that need to be run on the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information; configure each main control subsystem according to the security computing platform configuration information; after establishing a secure connection with the two security computer modules of any main control subsystem, send the execution programs of the security applications, security application configuration information and security computer module configuration information to the two security computer modules of the main control subsystem, and manage the security applications.
[0110] The secure computing platform in the embodiment of the present application includes multiple main control subsystems, each main control subsystem includes at least two secure computer modules, each secure computer module is capable of running one or more execution programs of secure applications, so that one or more execution programs of secure applications can be run on a secure computing platform, and the execution program of each secure application runs independently in a slave core, so the secure applications have no impact on each other.
[0111] The management module manages the distribution and configuration of the execution programs of the safety applications of all the main control subsystems, so the number of safety applications can be increased by expanding the main control subsystem. In theory, the safety computing platform of the present invention can realize the simultaneous operation of all limited safety applications, thereby reducing the hardware cost and required deployment area of the entire train control system. In addition, the safety application can be expanded and configured online without affecting the operation of the already online safety application, which has good scalability.
[0112] In some exemplary embodiments, the master core and the slave core communicate through a shared memory address block to achieve high-speed communication. The execution program of the safety application running on each slave core only uses its own physical memory block for safety calculation, and the safety calculation areas of the safety application are isolated from each other, with high reliability and safety, in compliance with the EN50129 standard requirements.
[0113] In some exemplary embodiments, the main control subsystems communicate with each other via a local area network within the platform.
[0114] In some exemplary embodiments, the management module stores the execution program of the security application, the security application configuration information, the security computer module configuration information and the security computing platform configuration information in the second memory of the security computer module. After the management programs of the two security computer modules establish a secure connection with each slave core, the execution program of the security application run by the master control subsystem and the security application configuration information and the security computer module configuration information are sent to each slave core of the master control subsystem according to the security computing platform configuration information to start running and manage each security application.
[0115] In some exemplary embodiments, the safety application configuration information may be configuration data of the safety application, such as line data of the train control system, supported train IDs, etc. These configurations are equivalent to attachments to the safety application program and are used during the operation of the application. Different safety applications have different types of configuration information.
[0116] In some exemplary embodiments, the security computer module configuration information may be the name of the security application, the number of the slave core corresponding to the security application, the IP address of the slave core through which data is output, etc. This configuration is used for the security computer module to correctly start the security application.
[0117] In some exemplary embodiments, the secure computing platform configuration information may be configured through human-computer interaction of the maintenance management terminal, and the default configuration information generated includes a list of secure computing modules in the platform, a correspondence between secure computer modules and secure applications, number information of secure computing modules, address information, etc. This configuration is used by the management module to maintain and manage all secure computer modules.
[0118] In some exemplary embodiments, the management module includes a main management module and a backup management module to form a "two by two take two" architecture.
[0119] Figure 7 A schematic diagram of a secure computing platform of at least one embodiment of the present application, such as Figure 7 As shown, the secure computing platform includes a plurality of main control subsystems, a management module and at least one backup secure computer module;
[0120] Each main control subsystem includes at least two security computer modules; the security computer module is a security computer module as described in any of the above embodiments;
[0121] The management module is configured to store the execution programs of all security applications that need to be run on the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information; configure each main control subsystem according to the security computing platform configuration information; after establishing a secure connection with the two security computer modules of any main control subsystem, send the execution programs of the security applications, security application configuration information and security computer module configuration information to the two security computer modules of the main control subsystem, and manage the security applications.
[0122] Also included is at least one backup safety computer module;
[0123] The management module is further configured to replace the failed safety computer module with the backup safety computer module when a safety computer module in any main control subsystem fails, so that the backup safety computer module becomes the backup system of the main control subsystem.
[0124] The secure computing platform in the embodiment of the present application includes multiple main control subsystems, each main control subsystem includes at least two secure computer modules, each secure computer module is capable of running one or more execution programs of secure applications, so that one or more execution programs of secure applications can be run on a secure computing platform, and the execution program of each secure application runs independently in a slave core, so the secure applications have no impact on each other.
[0125] The management module manages the distribution and configuration of safety applications of all main control subsystems, so the number of safety applications can be increased by expanding the main control subsystem. In theory, the safety computing platform of the present invention can realize the simultaneous operation of all limited safety applications, thereby reducing the hardware cost and required deployment area of the entire train control system. It can also expand and configure safety applications online without affecting the operation of safety applications that are already online, and has good scalability.
[0126] Based on the fault switching mechanism of the safety computing platform, a main control subsystem has only one main system at the same time. When a safety computer module (whether it is the main system or the backup system) fails, the backup safety computer module will start and be able to synchronize data and status with the safety computer module of the main control subsystem that is not faulty, and quickly become the backup system of the main control subsystem.
[0127] In some exemplary embodiments, the master core and the slave core communicate through a shared memory address block to achieve high-speed communication. The execution program of the safety application running on each slave core only uses its own physical memory block for safety calculation, and the safety calculation areas of the safety application are isolated from each other, with high reliability and safety, in compliance with the EN50129 standard requirements.
[0128] In some exemplary embodiments, the main control subsystems communicate with each other via a local area network within the platform.
[0129] In some exemplary embodiments, the management module stores the execution program of the security application, the security application configuration information, the security computer module configuration information and the security computing platform configuration information in the second memory of the security computer module. After the management programs of the two security computer modules establish a secure connection with each slave core, the execution program of the security application run by the master control subsystem and the security application configuration information and the security computer module configuration information are sent to each slave core of the master control subsystem according to the security computing platform configuration information to start running and manage each security application.
[0130] In some exemplary embodiments, the safety application configuration information may be configuration data of the safety application, such as line data of the train control system, supported train IDs, etc. These configurations are equivalent to attachments to the safety application program and are used during the operation of the application. Different safety applications have different types of configuration information.
[0131] In some exemplary embodiments, the security computer module configuration information may be the name of the security application, the number of the slave core corresponding to the security application, the IP address of the slave core through which data is output, etc. This configuration is used for the security computer module to correctly start the security application.
[0132] In some exemplary embodiments, the secure computing platform configuration information may be configured through human-computer interaction of the maintenance management terminal, and the default configuration information generated includes a list of secure computing modules in the platform, a correspondence between secure computer modules and secure applications, number information of secure computing modules, address information, etc. This configuration is used by the management module to maintain and manage all secure computer modules.
[0133] In some exemplary embodiments, the management module includes a main management module and a backup management module to form a "two by two take two" architecture.
[0134] Figure 8 A schematic diagram of a secure computing platform of at least one embodiment of the present application, such as Figure 8 As shown, the secure computing platform includes multiple main control subsystems, a management module, at least one backup secure computer module, a switch and a maintenance management terminal;
[0135] Each main control subsystem includes at least two security computer modules; the security computer module is a security computer module as described in any of the above embodiments;
[0136] The management module is configured to store the execution programs of all security applications that need to be run on the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information; configure each main control subsystem according to the security computing platform configuration information; after establishing a secure connection with the two security computer modules of any main control subsystem, send the execution programs of the security applications, security application configuration information and security computer module configuration information to the two security computer modules of the main control subsystem, and manage the security applications.
[0137] Also included is at least one backup safety computer module;
[0138] The management module is further configured to replace the failed safety computer module with the backup safety computer module when a safety computer module in any main control subsystem fails, so that the backup safety computer module becomes the backup system of the main control subsystem.
[0139] The safety computer module, management module and backup safety computer module in the safety computing platform are respectively connected to the switch to realize the interconnection between the modules;
[0140] The maintenance and management terminals are connected to the switches respectively, and are configured to send the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information to the management module, and provide manual query, modification and update of the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information stored in the management module.
[0141] The secure computing platform in the embodiment of the present application includes multiple main control subsystems, each main control subsystem includes at least two secure computer modules, each secure computer module is capable of running one or more execution programs of secure applications, so that one or more execution programs of secure applications can be run on a secure computing platform, and the execution program of each secure application runs independently in a slave core, so the secure applications have no impact on each other.
[0142] The management module manages the distribution and configuration of safety applications of all main control subsystems, so the number of safety applications can be increased by expanding the main control subsystem. In theory, the safety computing platform of the present invention can realize the simultaneous operation of all limited safety applications, thereby reducing the hardware cost and required deployment area of the entire train control system. It can also expand and configure safety applications online without affecting the operation of safety applications that are already online, and has good scalability.
[0143] Based on the fault switching mechanism of the secure computing platform, a main control subsystem has only one main system at the same time. When a security computer module (whether it is the main system or the backup system) fails, the backup security computer module will start, and can synchronize data and status through the security computer module of the main control subsystem that is not faulty, and quickly become the backup system of the main control subsystem. Through the setting of the backup security computer module and the safety mechanism of fault switching, any security application can currently meet the two-by-two-out-of-two architecture.
[0144] In some exemplary embodiments, the master core and the slave core communicate through a shared memory address block to achieve high-speed communication. The execution program of the safety application running on each slave core only uses its own physical memory block for safety calculation, and the safety calculation areas of the safety application are isolated from each other, with high reliability and safety, in compliance with the EN50129 standard requirements.
[0145] In some exemplary embodiments, all main control subsystems are connected to the management module; when the security applications running on different security computer modules need to communicate, they can be connected to each other; the security computing platform supports flexible configuration of any module as a backup module, so when a backup module is converted to a backup module of a certain main control subsystem during a failover, it is necessary to request status information from the main module of the subsystem. In this case, the connection between modules is random, so it is necessary to realize that all security computing modules are interconnected through a local area network.
[0146] In some exemplary embodiments, the management module stores the execution program of the security application, the security application configuration information, the security computer module configuration information and the security computing platform configuration information in the second memory of the security computer module. After the management programs of the two security computer modules establish a secure connection with each slave core, the execution program of the security application run by the master control subsystem and the security application configuration information and the security computer module configuration information are sent to each slave core of the master control subsystem according to the security computing platform configuration information to start running and manage each security application.
[0147] In some exemplary embodiments, the secure computing platform configuration information is information manually configured through a maintenance management terminal, including configuration information of each secure computer module. When the secure computer platform configuration information is sent to the management module, the management module sends the configuration information of each secure computer module in the secure computing platform configuration information to the corresponding secure computer module.
[0148] In some exemplary embodiments, the secure computing platform further includes a redundant switch to form a "two by two take two" architecture with the switch, and when the switch fails, the switch is replaced.
[0149] In some exemplary embodiments, the management module includes a main management module and a backup management module to form a "two by two take two" architecture.
[0150] Fig. 9 A schematic diagram of a secure computing platform of at least one embodiment of the present application, such as Fig. 9 As shown, the security computing platform includes a main control subsystem 31, a backup security computer module 32, a management module 33, a switch 34, a redundant switch 35 and a maintenance management terminal 36. The main control subsystem 31 includes a main control 1A 311, a main control 1B 312, a main control 2A and a main control 2B; the main control 1A module and the main control 1B module are redundant with each other, forming a "two times two take two" architecture that can run multiple applications, and the main control 2A module and the main control 2B module are redundant with each other, forming a "two times two take two" architecture that can run multiple applications. The management module 33 includes a management module A 331 and a management module B 332, which also form a "two times two take two" architecture, which is used to configure and manage the security applications of each main control subsystem. The backup security computer module 32 includes at least a backup security computer module 321. The secure computing platform can reserve several secure computer modules as backup secure computer modules. When one of the two main control modules of any main control subsystem fails, the system automatically enables the backup secure computer module, thereby still forming a "two by two take two" architecture.
[0151] All safety computer modules are connected to switches and redundant switches respectively to achieve interconnection between safety computer modules. All safety computer modules establish an internal LAN through switches, and all safety computer modules are used to establish another redundant internal LAN through redundant switches. When a switch fails, the safety computer modules communicate data through another redundant switch without affecting the normal operation of the platform.
[0152] The maintenance management terminal is also connected to the switch and redundant switch for human-computer interaction configuration management module and log recording.
[0153] The present application provides a method for starting a secure computing platform, including:
[0154] Step 1: When the secure computing platform is started for the first time, the execution programs of all the secure applications that need to be run on the secure computing platform, the secure application configuration information, the secure computer module configuration information and the secure computing platform configuration information are sent to the management module through the maintenance management terminal. The management module configures the main control subsystem, secure applications, etc. according to the secure computing platform configuration information.
[0155] For example, configure the security computer modules 1 and 2 as the master control 1A and the master control 1B, run the security applications 1, 2, 3, and the corresponding configuration parameters; similarly configure the security computer modules 3 and 4 as the master control 2A and the master control 2B, run the security applications 4, 5, 6, and the corresponding configuration parameters. The corresponding configuration parameters may include the corresponding relationship between the security applications 1, 2, 3 and the slave core numbers 1, 2, 3, the IP address information and port number information of the security application for external communication through the master core, and the protocol information of the slave core security application communicating with the master core management program.
[0156] Step 2: All the security computer modules enter the startup standby mode according to the startup process, and the management module establishes a secure connection with the management program in the main core of all the security computer modules.
[0157] Among them, the secure connection adopts a security protocol that complies with "TB-T 3528.2-2018 Railway Signal Safety Communication Protocol Part 2: Type II Protocol".
[0158] Step 3. After the two security computer modules of any main control subsystem establish a secure connection with the management module, the management module will send the binary execution program and configuration file of the security application run by the main control subsystem to the management program of the main control subsystem. The management program will store the binary execution program and configuration file of the security application run by the main control subsystem in the MicroSD card of the security computer module (corresponding to the second memory mentioned above). At the same time, the management program will send each application to each slave core for startup and operation according to the security application configuration file.
[0159] Step 4: Both safety applications of the main control subsystem have a heartbeat mechanism.
[0160] The present application provides a method for starting a secure computer module, comprising the following steps S11-S15:
[0161] S11, when the first central processing unit and the second central processing unit are powered on, the startup script and the startup program in the MicroSD card are automatically obtained and executed.
[0162] Among them, the startup script and startup program are responsible for reading the Linux system image, device tree file, and the secure microkernel image of the slave core from the MicroSD card and moving them to the corresponding running address space. That is, the Linux system image and device tree file are moved to the memory address block of the main core (that is, the non-secure computing address block), and the secure microkernel image of the slave core is moved to the memory address block of each slave core respectively, and then the Linux system of the main core is started. Among them, the MicroSD card stores the CPU startup script, startup program, Linux system image, device tree file, management / non-secure application execution program, and secure microkernel image of the slave core. The device tree file is a file that the operating system supports hardware driver standards. The system learns which hardware drivers the system needs to support and start, as well as the hardware parameters (such as hardware type, number, rate, address, etc.) by reading the device file.
[0163] S12, the Linux system starts to initialize the master core; after the master core is initialized, each slave core is configured to start, and the program of each slave core is set to jump to the beginning of the memory address block of the respective secure microkernel for execution. At this time, the slave cores will start to run their respective secure microkernel programs. The master core continues to start the Linux operating system.
[0164] S13, after the Linux system of the master core is started, the management program and the execution program of the non-safe application are automatically executed. The management program first monitors the shared memory channel of each slave core, responds after receiving the communication connection request, and establishes a secure connection with each slave core.
[0165] S14. After the secure microkernel program is started, it starts to initialize its own core and completes the startup and operation of the secure microkernel. Then, the default startup self-test program and the waiting application execution program are executed on the secure microkernel. The startup self-test program is a hardware self-test of its own core and memory in accordance with EN50129, including but not limited to memory self-test, register self-test, timer self-test, and kernel software version verification. Only after the verification passes can the waiting application execution program continue to run, otherwise the secure computer module will crash and be directed to the security side.
[0166] S15. After the secure microkernel completes the startup self-check program, it will execute the waiting application execution program, which first initiates a communication connection request to the hypervisor running on the main core through a shared memory communication cycle and waits for the hypervisor to respond. When the hypervisor responds, a secure connection is established with the hypervisor, and the security protocol of the connection adopts "TB-T 3528.2-2018 Railway Signal Safety Communication Protocol Part 2: Type II Protocol".
[0167] After waiting for the application execution program to establish a secure connection with the main core, the hypervisor establishes a "heartbeat" mechanism with each slave core, that is, it periodically sends an active status request to the slave core, and the slave core will immediately reply with an active status response. In this way, the hypervisor can monitor the operating status of the slave core in real time. When any slave core breaks the "heartbeat" mechanism and the hypervisor does not receive the active status of the slave core for three consecutive cycles, it is judged that the slave core is faulty, and the hypervisor executes the failure mode, the current security computer module crashes, and is directed to the safety side.
[0168] Since then, the startup of the security computer module has been completed, and each slave core is waiting for the application execution program to enter the startup standby mode, waiting for the execution program of the security application to be issued and run.
[0169] The startup process of the main core is as follows: start the Linux system of the main core through the startup script and the startup program, initialize the main core, start each slave core, complete the startup of the Linux system of the main core, automatically execute the execution program of the management program and the execution program of the non-security application, the management program responds to the communication connection request to establish a secure connection to each slave core, and the main core and the slave core establish a "heartbeat" mechanism.
[0170] The startup process of the slave core is as follows: after each slave core is started, it runs its own secure microkernel program, starts the self-test program, executes the waiting application execution program (waiting for the application execution program to initiate a communication connection request to the management program), establishes a secure connection with the master core, and the master core and the slave core establish a "heartbeat" mechanism.
[0171] The present application describes multiple embodiments, but the description is exemplary rather than restrictive, and it is obvious to those skilled in the art that there may be more embodiments and implementations within the scope of the embodiments described in the present application. Although many possible feature combinations are shown in the drawings and discussed in the specific embodiments, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with any other feature or element in any other embodiment, or may replace any other feature or element in any other embodiment.
[0172] The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in the present application may also be combined with any conventional features or elements to form a unique invention scheme. Any features or elements of any embodiment may also be combined with features or elements from other invention schemes to form another unique invention scheme. Therefore, it should be understood that any feature shown and / or discussed in the present application may be implemented individually or in any appropriate combination. Therefore, except for the limitations made according to the attached claims and their equivalents, the embodiments are not subject to other restrictions. In addition, various modifications and changes may be made within the scope of protection of the attached claims.
[0173] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a specific sequence of steps. However, to the extent that the method or process does not rely on the specific order of the steps described herein, the method or process should not be limited to the steps of the specific order described. As will be understood by those of ordinary skill in the art, other sequences of steps are also possible. Therefore, the specific sequence of the steps set forth in the specification should not be interpreted as a limitation to the claims. In addition, the claims for the method and / or process should not be limited to the steps of performing them in the order written, and those skilled in the art can easily understand that these sequences can be changed and still remain within the spirit and scope of the embodiments of the present application.
[0174] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all components may be implemented as software executed by a central processor, such as a digital signal central processor or a micro-central processor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term "computer storage medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.
[0175] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include at least one of the features.
[0176] In the description of the present application, “plurality” means at least two, for example, two, three, etc., unless otherwise clearly and specifically defined.
[0177] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0178] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A secure computing platform, characterized in that: It includes a plurality of main control subsystems, a management module and at least one backup safety computer module; Each main control subsystem includes at least two security computer modules; the management module is configured to store the execution programs of all security applications to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information; configure each main control subsystem according to the security computing platform configuration information; after establishing a secure connection with the two security computer modules of any main control subsystem, send the execution program of the security application to the two security computer modules of the main control subsystem, and manage each security application; The management module is further configured to replace the failed safety computer module with the backup safety computer module when a safety computer module in any main control subsystem fails, so that the backup safety computer module becomes a backup system of the main control subsystem; Wherein, the security computer module includes at least two security computers, each security computer includes a central processing unit, a first memory and an external device, each security computer includes a central processing unit, and the at least two security computers are configured to run the same logic, process the same data, compare and vote on the calculation results, and output data after the vote is consistent, and the central processing unit includes a master core and at least one slave core; The main core is configured to run a first operating system and to run a hypervisor and an executive program of a non-secure application on the first operating system; Each slave core is configured to start under the control of the master core, and to run a second operating system, and to run an independent security application execution program on the second operating system.
2. The secure computing platform according to claim 1, characterized in that: It also includes switches and maintenance management terminals; All the safety computer modules are respectively connected to the switch to achieve interconnection between the safety computer modules; The maintenance and management terminals are connected to the switches respectively, and are configured to send the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information to the management module, and provide manual query, modification and update of the execution programs of all security applications that need to be run by the security computing platform, security application configuration information, security computer module configuration information and security computing platform configuration information stored in the management module.
3. The secure computing platform according to claim 2, characterized in that: The management module includes a main management module and a backup management module to form a "two by two take two" architecture; A redundant switch is also included to form a "two by two take two" architecture with the switch.
4. The secure computing platform according to claim 1, characterized in that: The first memory includes a non-secure computing address block, secure computing address blocks and shared memory address blocks having the same number as the slave cores; the secure computing address blocks and the shared memory address blocks correspond to the slave cores one by one respectively; The master core is also configured to have only the authority to access and read and write the non-secure computing address block and the shared memory address block; the slave core is also configured to have only the authority to access and read and write the secure computing address block and the shared memory address block corresponding to itself; the master core and each slave core communicate through the shared memory address block corresponding to the slave core.
5. The secure computing platform according to claim 1, characterized in that: The external device includes a second memory; The second memory is connected to the main core and is configured to store a startup script, a startup program, an image of the first operating system, a device tree file, an executive program of a hypervisor or a non-secure application, and an image of the second operating system.
6. The secure computing platform according to claim 1, characterized in that: The master core is further configured to establish a heartbeat mechanism with each slave core, and monitor the status of the slave core according to the heartbeat mechanism.
7. The secure computing platform according to claim 1, characterized in that: The management program is used to drive external devices, access the external devices, and start the slave core.
8. The secure computing platform according to claim 1, characterized in that: The slave core is also configured to perform a hardware self-test that meets preset standard requirements when starting up.
