System and method for monitoring the operation of a computer
Patent Information
- Application Number
- EP2022840225
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2021-12-30
- Filing Date
- 2022-12-30
- Publication Date
- 2024-11-06
AI Technical Summary
Current monitoring systems for critical on-board computers are inadequate in detecting attacks exploiting hardware vulnerabilities, such as the Specter, Meltdown, and Rowhammer attacks, and fail to ensure operational safety and cybersecurity.
A monitoring system that utilizes a collection unit to count requests and form associations between tasks and hardware block usage, storing this information in a dedicated memory accessible only by hardware elements, allowing for real-time detection of abnormal behavior and attacks.
Enhances security by preventing malicious exploitation of monitoring information and detecting attacks that target hardware vulnerabilities, ensuring better safety and compatibility with real-time implementations.
Smart Images

Figure 1.1
Abstract
Description
[0001] System and method for monitoring the operation of a computer
[0002] The present invention relates to a system for monitoring the operation of a computer. The present invention also relates to a method for monitoring the operation of a computer.
[0003] The field of reliable critical embedded computers is faced with issues of protection of systems using embedded computers (and possibly the users of these systems) in the event of failure or breakdown of the computers (issue of operational safety) but also of resistance to malicious attacks (cybersecurity).
[0004] To address these issues, it is desirable that embedded computers meet constraints expressed in the form of properties to be guaranteed, such as confidentiality, integrity, or availability in the field of security, or reliability, real-time behavior, or traceability in the field of operational safety.
[0005] A large part of the certification of these critical computers therefore consists of guaranteeing, demonstrating and testing these properties, which is made possible by a set of monitoring systems (often referred to by the corresponding English term "monitoring") which make it possible both to design secure systems upstream, and to observe the deviations generated by cyber-attacks.
[0006] Such monitoring systems include, in particular, intrusion detection systems (more often referred to as IDS, an abbreviation which refers to the corresponding English term for "Intrusion Detection System") which already use information from monitoring the operation of software to detect cyber attacks.
[0007] In particular, so-called HIDS systems are also known. In the previous name, the H refers to the corresponding English term for "Host", i.e. "host" and IDS to the aforementioned abbreviation. HIDS systems focus on a computer, at the level of its operating system. HIDS systems seek to detect abnormal behavior, by monitoring running processes, memory allocations, connected users and others. An alert is generated when one of the quantities monitored by the HIDS system in question deviates from a predefined standard.
[0008] Furthermore, in the field of operational safety and in the context of the use of multi-core hardware architectures, it is also known to use systems to guarantee a sufficient level of segregation between software having shared hardware resources.
[0009] On the one hand, control systems are used, generally exploiting a system of time windows and preventing the hardware use of resources by applications outside the windows assigned to this application, thus guaranteeing strict partitioning and predictable temporal behavior at the cost of reduced performance.
[0010] On the other hand, regulation systems are used, more flexible but offering fewer strict guarantees which monitor in real time the use of material resources, and are reactive only in the event of congestion on the path of these resources.
[0011] However, these systems cannot detect attacks that exploit hardware vulnerabilities at the processor level, such as the Spectre attack, the Meltdown attack, or the Rowhammer attack.
[0012] There is therefore a need for a computer operation monitoring system ensuring better computer security.
[0013] To this end, the description describes a system for monitoring the operation of a computer, the computer comprising hardware blocks, the hardware blocks comprising several cores, the computer also comprising a set of task scheduling units, the set being capable of scheduling the execution of a task by assigning it an identifier and storing the identifier on a first storage unit. The monitoring system comprises a collection unit capable of counting the number of requests of each hardware block during the performance of a task, the collection unit also being capable of reading the identifier of the task performed in the first storage unit, the collection unit also being capable of forming an association between a request with the corresponding identifier and storing each association formed on a second storage unit.The monitoring system also includes a monitoring unit capable of determining the operating status of the computer using stored associations.
[0014] The monitoring system uses dedicated memory for collecting monitoring information to ensure a higher level of security. Indeed, the dedicated memory is only addressable from hardware elements and not at the software level. This prevents the collected information from being accessible by applications and thus prevents its exploitation for malicious purposes.
[0015] It can also be noted that each task here is a software task and the collection unit is a hardware block (physical component). This implies that the collection unit has no a priori information about the tasks, which are scheduled by the operating system.
[0016] According to particular embodiments, the monitoring system has one or more of the following characteristics, taken in isolation or in all technically possible combinations:
[0017] - a hardware block is a main memory shared by the cores, the storage unit being part of the main memory.
[0018] - a hardware block is a debugging support unit shared by the cores, the storage unit being part of the debugging support unit.
[0019] - the storage unit is a core-specific memory.
[0020] - each core has tightly coupled memory, with core-specific memory being tightly coupled memory.
[0021] - each core has a memory management unit, with core-specific memory located in the memory management unit.
[0022] - each core has a performance measurement unit, with core-specific memory contained within the performance measurement unit.
[0023] - each core has a performance measurement unit, the collection unit being formed by all the performance measurement units.
[0024] - the first storage unit is distinct from the second storage unit.
[0025] The description also describes a method for monitoring the operation of a computer, the computer comprising hardware blocks, the hardware blocks comprising several cores, the computer also comprising a set of task scheduling units, the set being capable of scheduling the execution of a task by assigning it an identifier and storing the identifier on a first storage unit, the method being implemented by a monitoring system comprising a collection unit and a monitoring unit, the method comprising a step of counting the number of requests of each hardware block during the performance of a task, a step of reading the identifier of the task performed in the first storage unit, a step of forming an association between a request with the corresponding identifier and storing each association formed on a second storage unit,and a step of determining the operating state of the calculator using the stored associations.,
[0026] Characteristics and advantages of the invention will appear on reading the description which follows, given solely by way of non-limiting example, and made with reference to the appended drawings, in which: - figure 1 is a schematic representation of an example of a calculator,
[0027] - Figure 2 is a schematic representation of the processes implemented by the calculator, and
[0028] - Figure 3 is a schematic representation of another example of a calculator.
[0029] A calculator 10 is shown schematically in Figure 1.
[0030] The computer 10 is, for example, an on-board computer, in particular a critical computer.
[0031] Such a computer 10 is usable in an aircraft, in a payload or satellite platform or implanted medical systems.
[0032] According to the example described, the computer 10 is a multi-core computer.
[0033] The computer 10 comprises cores 12, an interconnect 14, a main memory 16 and a debug support unit 18.
[0034] A core 12 is a set of circuits capable of executing programs autonomously.
[0035] Only two 12 cores are shown in Figure 1 for simplicity, knowing that the number of 12 cores is possibly much larger.
[0036] Each core 12 comprises a computing unit 20 comprising a scheduling unit 22, cache memories 26, a tightly coupled memory 28, a memory management unit 30 and a performance measurement unit 34.
[0037] Computing unit 20 is the unit that performs the various tasks.
[0038] An example of operation of the computing unit 20 on the software level is illustrated in FIG. 2.
[0039] In this figure, a hypervisor HYP implements two operating systems OS1 and OS2. They all have a scheduling unit 22.
[0040] Each of these operating systems OS1 and OS2 in turn implement two respective processes. The first operating system OS1 implements a first process P1 and a second process P2 while the second operating system OS2 implements a third process P3 and a fourth process P4.
[0041] Each process P1, P2, P3 or P4 corresponds to a set of several tasks.
[0042] The implementation of these tasks is managed by the scheduling unit 22.
[0043] The set of scheduling units 22 forms a set 38 which is suitable for scheduling the execution of a task by assigning it an identifier and for storing the identifier on a storage unit. By definition, a cache memory is a memory which temporarily records copies of data coming from a source, in order to reduce the time of subsequent access (reading) of computer hardware (in general, a processor) to this data.
[0044] In the proposed example, the core comprises several cache memories 26 represented in the form of a single block in figure 1.
[0045] For example, it is common to distinguish between a cache memory storing code and a cache memory storing data.
[0046] A tightly coupled memory 28 is a memory suitable for explicitly storing instructions or private data of a core 12, with access times comparable to the cache memory 26 but without generating implicit transactions on the interconnect 14.
[0047] Such memory is more often referred to by the abbreviation TCM, referring to the corresponding English term for “Tightly Coupled Memory”.
[0048] The memory management unit 30 is used to control memory accesses.
[0049] The memory management unit 30 is more often referred to by the abbreviation MMU referring to the corresponding English name of “Memory Management Unit”.
[0050] The performance measurement unit 34 is capable of counting the number of requests made to each element of the core 12 during the performance of a task by the calculation unit 20.
[0051] Such a performance measurement unit 34 is often referred to by the acronym PMU, which refers to the English term “Performance Monitoring Unit”.
[0052] According to the embodiments, the core 12 which has just been described has other elements and / or does not include all of the preceding blocks.
[0053] For example, core 12 may include an interrupt controller (sometimes referred to as an IC block, the abbreviation IC referring to the English term for "Interrupt Controller"). As its name suggests, the interrupt controller manages interrupts.
[0054] The interconnection 14 serves to ensure the interconnection between the different elements of the cores 12 and the shared elements such as the main memory 16.
[0055] According to the described example, the interconnect is a NoC interconnect because it is assumed that all 12 cores are part of the same chip.
[0056] The acronym NoC refers to the English term “Network on Chip” which literally means “network on a chip”.
[0057] The main memory 16 is suitable for storing data shared between the cores 12. Being of greater capacity than the tightly coupled memories 28, the main memory 16 can store large data. It also allows the exchange of data between cores 12.
[0058] The debugging support unit 18 is a unit suitable for observing the correct execution of the software on the various elements of the computer 10 in order to develop this software.
[0059] The Debug Support Unit 18 is more often referred to as the English term "Debug Support Unit".
[0060] The computer 10 thus comprises a set of hardware blocks 36, the set 38, a monitoring system 40 and a storage unit 42.
[0061] A hardware block 36 is a physical component capable of performing more or less complex tasks.
[0062] Some hardware blocks 36 have already been described previously.
[0063] For example, the elements of the core 12 or the main memory 16 are hardware blocks 36.
[0064] Further, in Figure 1, it appears that the storage unit 42 is contained in the main memory 16.
[0065] Other possible implementations are conceivable such as allocating a small portion of memory 16 for storing task identifiers or storing task identifiers in performance measurement unit 34 or in tightly coupled memory 28.
[0066] The monitoring system 40 is suitable for monitoring the operation of the computer 10.
[0067] The monitoring system 40 is thus adapted to implement a method for monitoring the operation of the computer 10.
[0068] The monitoring system 40 comprises a collection unit 44 and a monitoring unit 46.
[0069] The collection unit 44 is capable of counting the number of requests for each hardware block 36 during the performance of a task.
[0070] It should be noted that the term "task" is used here generically; it can be any or all of the following levels: a thread, a process, a partition, a virtual machine, a user co-routine, or an interrupt request.
[0071] The collection unit 44 is also capable of reading the identifier of the task carried out in the storage unit 42.
[0072] The collection unit 44 is also capable of forming an association between a request with the corresponding task identifier. The collection unit 44 is also capable of storing each association formed.
[0073] In the case of Figure 1, the collection unit 44 is also formed by the performance measurement units 34.
[0074] This interaction is shown by a dotted line in Figure 1.
[0075] The monitoring unit 46 is capable of determining the operating status using the stored associations.
[0076] The operation of the monitoring system 46 is now described with reference to an example of implementation of a method for monitoring the operation of the computer 10, the monitoring method comprising several steps which are explained below.
[0077] The scheduling unit 22 orders the execution of a first task by assigning it an identifier.
[0078] The identifier is therefore a task identifier in the sense that it is specific to the task it identifies.
[0079] In the remainder of this description, the identifier of the first task is called the first identifier.
[0080] The scheduling unit 22 then stores the first identifier in the storage unit 42, in this case in the main memory 16.
[0081] The first task is then implemented.
[0082] Such an implementation involves the solicitation of 36 hardware blocks.
[0083] The performance measurement units 34 count each of these requests for each core 12.
[0084] For clarity, the demands of the first task are called "first material demands" in what follows.
[0085] The collection unit 44 simultaneously reads the first identifier in the area 42 and each of the first hardware requests in the performance measurement unit 34.
[0086] The collection unit 44 stores the association of the first identifier and the first hardware requests in the main memory 16 for example.
[0087] Each of the previous steps is repeated for a second task.
[0088] Using the same formalism for naming the identifier and the requests, this reiteration of the steps can be described as follows.
[0089] The scheduling unit 22 orders the execution of a second task by assigning it a second identifier which is stored in the storage unit 42.
[0090] Then, the performance measurement units 34 count the second hardware requests and the collection unit 44 associates them with the second identifier. The collection unit 44 stores this association in the main memory 16. These steps may be repeated for each task implementation.
[0091] A database is thus created associating the material requests counted with a specific task.
[0092] Using this database, the monitoring unit 46 determines the operating state of the computer 10.
[0093] For example, when the load on a hardware block 36 is too high for a given task, this may be a sign of impaired operation of the computer 10.
[0094] The monitoring system 40 having context information linked to a higher demand on a hardware block 36, this makes it possible to ensure additional monitoring since an attack changing the number of accesses to a hardware block 36 is now detectable.
[0095] The monitoring system 40 is therefore capable of detecting attacks exploiting hardware vulnerabilities at the processor level and generating requests, such as the Spectre attack, the Meltdown attack or the Rowhammer attack.
[0096] As a result, the monitoring system 40 provides better security to the computer 10.
[0097] Furthermore, the monitoring system 40 is compatible with real-time implementation.
[0098] It should be noted that the storage unit 42 may be different from the main memory 16 which poses the problem of being relatively far from the cores 12 and therefore requiring relatively long accesses.
[0099] In particular, the storage unit 42 may be located in the memory management unit 30.
[0100] Such implementation does not impact transactions in calculator 10.
[0101] It is also possible to use the debug support unit 18, the performance measurement units 34 or the tightly coupled memories 28.
[0102] Finally, it may be noted that it is not necessary for the identifier to be stored on the same storage unit 42.
[0103] For example, it may be advantageous to store the identifiers in a local memory of a core 12 while the association would be stored in a shared memory.
[0104] Another embodiment of the calculator 10 is shown in Figure 3.
[0105] The same remarks as for the calculator 10 of Figure 1 also apply to that of Figure 3. Also, only the differences are highlighted in what follows. In this case, the collection unit 44 is suitable for collecting the information from the performance measurement units 34.
[0106] Unlike the embodiment of Figure 1, the collection unit 44 is here a centralized unit.
Claims
DEMANDS 1. Monitoring system (40) for the operation of a computer (10), the computer (10) comprising: - hardware blocks (36), the hardware blocks (36) comprising several cores (12), - a set (38) of task scheduling units (22), the set (38) being suitable for scheduling the execution of a task by assigning it an identifier and for storing the identifier on a first storage unit (42), the monitoring system (40) comprising: - a collection unit (44) designed to count the number of times each material block (36) is activated during the execution of a task, the collection unit (44) also being designed to read the identifier of the task performed in the first storage unit (42), the collection unit (44) also being designed to form an association between an activation and the corresponding identifier and to store each association formed on a second storage unit, and - a monitoring unit (46) capable of determining the operating status of the computer (10) using the stored associations.
2. Monitoring system according to claim 1, wherein each task is a software task and the collection unit (44) is a physical component.
3. Monitoring system according to claim 1 or 2, wherein a hardware block (36) is a main memory (16) shared by the cores (12), the memory unit (42) being part of the main memory.
4. Monitoring system according to any one of claims 1 to 3, wherein a hardware block (36) is a core-shared debugging support unit (18), the memory unit (42) being part of the debugging support unit (18).
5. Monitoring system according to any one of claims 1 to 4, wherein the memory unit (42) is a single-core memory (12).
6. Monitoring system according to claim 5, wherein each core (12) has a tightly coupled memory (28), the memory specific to a core (12) being the tightly coupled memory (28).
7. Monitoring system according to claim 5 or 6, wherein each core (12) comprises a memory management unit (30), the memory specific to a core (12) being located in the memory management unit (30).
8. Monitoring system according to any one of claims 5 to 7, wherein each core (12) comprises a performance measurement unit (34), the memory specific to a core (12) being contained in the performance measurement unit (34).
9. Monitoring system according to any one of claims 5 to 8, wherein each core (12) comprises a performance measurement unit (34), the collection unit (44) being formed by the set of performance measurement units (34).
10. Monitoring system according to any one of claims 1 to 9, wherein the first storage unit (42) is distinct from the second storage unit.
11. Method for monitoring the operation of a computer (10), the computer (10) comprising: - hardware blocks (36), the hardware blocks (36) comprising several cores (12), - a set (38) of task scheduling units (22), the set (38) being suitable for scheduling the execution of a task by assigning it an identifier and for storing the identifier on a first storage unit (42), the process being implemented by a monitoring system (40) comprising a collection unit (44) and a monitoring unit, the process comprising the steps of: - counts the number of times each hardware block (36) is activated during the execution of a task, - reading the identifier of the task performed in the first memorization unit (42), - formation of an association between a request and the corresponding identifier, and storage of each association formed on a second storage unit, and - determination of the operating state of the computer (10) using the stored associations.
