Non-volatile memory access blocking in response to attacks

By quickly blocking access to nonvolatile memory when a potential attack is detected, and triggering erasure and locking after confirming the real attack, the security of sensitive data in nonvolatile memory is solved during attack, ensuring data Fast and permanent protection.

CN119089517APending Publication Date: 2024-12-06HEWLETT PACKARD ENTERPRISE DEV LP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410426442.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-08-28
Filing Date
2024-04-10
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Sensitive data in nonvolatile memory may be slow when a potential attack is detected, causing the attacker to still have some data access during the erasure, and false alarms may cause data recovery difficulties.

Method used

Ensure data security by issuing a command blocking indication when a potential attack is detected, blocking access to nonvolatile memory, and triggering erasing and activation of irreversible locks after confirming the real attack.

Benefits of technology

It quickly blocks data access before confirming the real attack, prevents unauthorized access, and ensures permanent protection of data after confirmation, avoiding the difficulty of data recovery.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089517A_ABST
    Figure CN119089517A_ABST
Patent Text Reader

Abstract

A non-volatile memory access blocking in response to an attack is provided. In some examples, a security processor detects potential attacks in a system. In response to detecting a potential attack in the system, the security processor issues a command blocking indication to block processing of commands to access the non-volatile memory. The security processor determines a likelihood that the potential attack is a real attack based on the monitored information, and triggers an erase of the non-volatile memory in response to the determined likelihood.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0001] When the nonvolatile memory device is powered off or the system including the nonvolatile memory device is powered off, the data in the nonvolatile memory device will be retained (not lost). Examples of nonvolatile memory devices include flash memory devices, such as NOR flash memory devices or NAND flash memory devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0002] Some embodiments of the disclosure are described with respect to the following figures.

[0003] Figure 1 is a block diagram of a computer system including a security processor for detecting attacks in the computer system and taking remedial actions in response to the attacks, according to some examples.

[0004] Figure 2 is a flow diagram of a process according to some examples.

[0005] Figure 3 is a block diagram of a storage medium storing machine-readable instructions according to some examples.

[0006] Figure 4 is a block diagram of a computer system according to some examples.

[0007] Figure 5 is a flow diagram of a process according to some examples.

[0008] Throughout the drawings, the same reference numerals refer to similar, but not necessarily identical, elements. The drawings are not necessarily drawn to scale, and the dimensions of some parts may be exaggerated to more clearly illustrate the examples shown. In addition, the drawings provide examples and / or implementations consistent with the description; however, the description is not limited to the examples and / or implementations provided in the drawings. DETAILED DESCRIPTION

[0009] An attacker (eg, a human, program, or machine) may attempt to access sensitive data stored in the system. Sensitive data stored in non-volatile memory is particularly susceptible to unauthorized access due to the persistence of non-volatile memory.

[0010] In order to protect sensitive data in the non-volatile memory from unauthorized access, a zeroing process can be triggered to erase the sensitive data. The zeroing process erases the data stored in the non-volatile memory by writing an erase pattern to the non-volatile memory (or a portion of the non-volatile memory). The erase pattern can include a random data pattern, or any other type of data pattern that overwrites the stored data in the non-volatile memory and prevents the stored data from being recovered.

[0011] The zeroing process may be triggered in response to detecting an attack on the system. However, the zeroing process may take a significant amount of time to complete because the erase operation of non-volatile memory devices such as flash memory devices may be quite slow, such that during the time interval when the zeroing process is being performed, an attacker may still have access to a portion of the data in the non-volatile memory that has not yet been erased.

[0012] Attack detection mechanisms in the system can monitor certain operational aspects of the system to detect attacks on the system. The monitored operational aspects can include the behavior of programs or hardware components in the system, parameters generated by sensors or other monitoring agents, such as the operating speed of hardware components, voltage, temperature, interference indications, etc.

[0013] In some cases, the attack alert issued by the attack detection mechanism may be a false alarm. If the data in the non-volatile memory is erased in response to such a false alarm, it may take considerable effort and time to recover the erased data. In some cases, it may not be possible to recover the erased data.

[0014] According to some embodiments of the present disclosure, a system is capable of detecting a potential attack in the system by an entity. In response to detecting a potential attack, the system issues a command blocking indication to prevent processing of commands to access non-volatile memory. The command blocking indication can block access to the non-volatile memory relatively quickly (e.g., almost immediately) after detecting a potential attack, so that the attacker will not be able to access data in the non-volatile memory, or alternatively, the attacker can only access a small amount of data in the non-volatile memory. For example, a command blocking indication can be issued by executing a register write, which is a relatively fast procedure that can be completed in about a few nanoseconds or less (e.g., less than 10 nanoseconds, or less than 5 nanoseconds, or less than 2 nanoseconds, etc.).

[0015] The command blocking indication provides the system with time to determine the likelihood that a potential attack is a real attack. In response to determining that the likelihood of a real attack is high, the system can trigger an erase (e.g., zeroing) of the non-volatile memory and activate a lock to prevent further access to the non-volatile memory. The system thus applies a multi-layer attack mitigation technique in which command blocking is first applied to give the system time to confirm the likelihood that the potential attack is a real attack, and if the potential attack is a real attack, a more permanent solution is applied to protect the contents of the non-volatile memory. By using the techniques or mechanisms according to some embodiments of the present disclosure, the system can ensure that remedial actions (e.g., zeroing) that can remove data from the non-volatile memory are taken after a real attack may be occurring, while at the same time implementing a memory access blocking feature that prevents access to the data during the time when the system is confirming the likelihood of a real attack. The memory access blocking feature also prevents access to data in the non-volatile memory while the zeroing process is being performed to erase the data in the non-volatile memory.

[0016] Figure 1 1 is a block diagram of a computer system 100 that includes one or more main processors 102 and a baseboard management controller (BMC) 104 that performs various management tasks. Further details about a "BMC" are provided below. Although reference is made to a BMC in some examples, other types of controllers may be used in other examples. Examples of computer systems may include any one or some combination of the following: a desktop computer, a notebook computer, a server computer, a storage system, a communication node, a vehicle, a home appliance, etc.

[0017] As used herein, a "controller" may refer to one or more hardware processing circuits, which may include any one or some combination of a microprocessor, a core of a multi-core microprocessor, a microcontroller, a programmable integrated circuit, a programmable gate array, or another hardware processing circuit. Alternatively, a "controller" may refer to a combination of one or more hardware processing circuits and machine-readable instructions (software and / or firmware) that may be executed on the one or more hardware processing circuits.

[0018] A processor may include a microprocessor, a core of a multi-core microprocessor, a microcontroller, a programmable integrated circuit, a programmable gate array, or another hardware processing circuit.

[0019] In some examples, the BMC 104 includes a secure enclave 106, which refers to a subsystem of the BMC 104 (or any other type of controller) for which access to and from the subsystem is more strictly controlled than access to other subsystems of the BMC 104. For example, the secure enclave 106 is completely disposed within a cryptographic boundary. The secure enclave may also be referred to as a security boundary, or a security perimeter, or any other similar term. In this case, a "cryptographic boundary" refers to a continuous boundary or perimeter that contains logical and physical components of a cryptographic subsystem, such as BMC components that form the secure enclave 106. According to an example embodiment, the secure enclave 106 of the BMC 104 is isolated from the management plane of the BMC, and other non-secure components of the BMC 104 outside the secure enclave 106. The cryptographic boundary is defined using a secure access mechanism, such as by using encryption or another type of access control to protect components in the secure enclave 106 from unauthorized access by components outside the secure enclave 106.

[0020] Examples of other subsystems of BMC 104 outside of secure enclave 106 (non-secure subsystems) include management processor 108 of BMC 104, which is part of the management plane of the BMC. Machine-readable instructions are executable on management processor 108 to perform management tasks of BMC 104 (examples discussed further below).

[0021] The non-secure subsystem further includes a memory 110 of the BMC 104, a network interface controller (NIC) 112 of the BMC 104, a non-volatile memory access subsystem 114, etc. The NIC 112 allows the BMC 104 to communicate over a network with external entities that may be external to the computer system 100. The external entity may include a remote management server that allows, for example, the computer system 100 to be remotely managed from the remote management server using the BMC 104.

[0022] One or more host processors 102 of the computer system 100 may execute various machine-readable instructions of the computer system 100, such as an operating system (OS) 116, application programs 118, firmware 120 (e.g., including basic input and output system code or unified extensible firmware interface code), etc. The one or more host processors 102 may be coupled to the BMC 104 via an input / output (I / O) bridge 122, which is a device that interconnects various different components.

[0023] In some examples, the secure enclave 106 includes a secure processor 124 that executes attack processing instructions 126 according to some embodiments of the present disclosure. The attack processing instructions 126 may include firmware, software, or other types of machine-readable instructions. The attack processing instructions 126 may be stored in a memory of the secure processor 124 or in a memory external to the secure processor 124 in the secure enclave 106.

[0024] Attack processing instructions 126 , when executed on security processor 124 , are capable of detecting attacks in computer system 100 based on information from one or more sensors. Figure 1 A sensor set 170 is depicted in computer system 100. In other examples, sensor set 170 may further include one or more sensors external to computer system 100. "Sensor" may refer to a hardware sensor, or machine-readable instructions as executed in computer system 100 by main processor 102 or another processor.

[0025] The sensor set 170 may include any one or some combination of the following: temperature sensors, voltage sensors, electrical sensors, clock speed sensors, malware detectors (e.g., virus scanners, ransomware scanners, etc.), physical intrusion detectors, etc.

[0026] although Figure 1 The sensor set 170 is depicted as being in the secure enclave 106, but in other examples, one or more sensors may be external to the secure enclave 106. Such one or more external sensors may be part of the BMC 104, or may be external to the BMC 104 (e.g., coupled to the I / O bridge 122). Yet another example of a sensor in the BMC 104 is a digital canary circuit 172 in the secure enclave 106. A "canary circuit" refers to a circuit that fails due to a security attack caused by an environmental condition, and provides an observable indication when the failure occurs, such that the indication may also be used as an indicator of the attack. In some examples, the digital canary circuit 172 may apply a cryptographic transformation that produces an output based on a known input, and the output may be used as an indicator of the security attack. Examples of cryptographic transformations that may be performed include Advanced Encryption Standard (AES) cryptographic transformations. Deviations in the output of the digital canary circuit 172 from the expected output indicate that a failure has occurred and potentially indicate a security attack caused by an environmental condition. The environmental conditions include the temperature of the computer system 100 , the voltage of the computer system 100 , the current of the computer system 100 , the clock speed in the computer system 100 , and the like.

[0027] Attack handling instructions 126 may detect potential attacks in computer system 100, such as based on monitored information collected by specific sensors of sensor set 170. For example, an out-of-spec temperature condition (based on measured information from a temperature sensor), an out-of-spec voltage condition (based on measured information from a voltage sensor), an out-of-spec current condition (based on measured information from a current sensor), an out-of-spec clock speed condition (based on measured information from a clock speed sensor) may indicate that a potential attack is occurring. An out-of-spec condition may refer to a condition represented by a sensor output that deviates from an expected target behavior (e.g., a measurement may exhibit an unexpected glitch, or a measurement may detect a rapid rise or fall at a rate that exceeds an expected rate, etc.). The expected target behavior may be predefined or dynamically set and represented by information stored in computer system 100.

[0028] In response to detecting a potential attack in computer system 100, attack handling instructions 126 may take remedial actions to ensure that data stored in one or more memories of computer system 100 is protected from unauthorized access by an attacker. In some examples, the data to be protected from unauthorized access may reside in one or more non-volatile memories, such as Figure 1 The non-volatile memories 128 and 130 depicted in FIG. Figure 1 The examples depict the presence of two nonvolatile memories that may contain sensitive data to be protected from unauthorized access, but in other examples, a different number of nonvolatile memories (e.g., a single nonvolatile memory or more than two nonvolatile memories) may store the sensitive data.

[0029] "Non-volatile" memory devices are capable of persistently storing data even when the memory device is powered off. In some examples, each of non-volatile memories 128 and 130 is implemented with a collection of flash read-only memory (ROM) devices, such as NOR flash memory devices or NAND flash memory devices. In other examples, non-volatile memories 128 and 130 can be implemented using other types of memory devices.

[0030] Examples of sensitive data may include any one or some combination of the following: cryptographic keys used to encrypt or sign data, secret information used to derive cryptographic keys, or other information used to protect data for security purposes, such as a password or another credential used to verify that an entity attempting to access the data is an authorized entity, etc. Other types of sensitive information may include proprietary information of an enterprise, personal information of a user, or any other type of information that is designated to be accessed by authorized entities and should not be accessed by unauthorized entities.

[0031] Non-volatile memory 128 is accessible to components within secure enclave 106, including secure processor 124. Non-volatile memory 128 is not accessible to components outside secure enclave 106. Non-volatile memory 130 is accessible to components of BMC 104, such as management processor 108 or components within secure enclave 106.

[0032] Nonvolatile memory 128 is connected to a bus controller 136 in secure enclave 106 via bus 132. Nonvolatile memory 130 is connected to a bus controller 138 in nonvolatile memory access subsystem 114 via bus 134. In some cases, additional devices may be connected to bus 132 and / or bus 134.

[0033] A "bus" may refer to any communication link that includes a collection of signal lines (single signal line or multiple signal lines) through which data may be transferred. In some examples, bus 132 or 134 may be a serial peripheral interface (SPI) bus. In other examples, bus 132 or 134 may be a different type of bus, such as an inter-integrated circuit (I2C) bus, or another type of bus.

[0034] In the example where bus 132 or 134 is an SPI bus, bus controller 136 or 138 is an SPI controller. If bus 132 or 134 is another type of bus, bus controller 136 or 138 may be a different type of bus controller, such as an I2C bus controller or another type of bus controller.

[0035] The bus controller 136 includes a bus control engine 140 that controls communications with the non-volatile memory 128 via the bus 132. The bus control engine 140 may be implemented using a portion of hardware processing circuitry or machine-readable instructions of the bus controller 136. Similarly, the bus controller 138 includes a bus control engine 142 that controls communications with the non-volatile memory 130 via the bus 134.

[0036] The bus controller 136 also includes a command filter 144 that can selectively allow or disallow commands for accessing (reading or writing) the non-volatile memory 128. Examples of commands include a read command to read data, a write command to write data, an erase command to delete data (e.g., an erase command that can erase the entire memory or a specified portion of the memory), and / or other commands.

[0037] In some examples, the bus controller 136 includes a command filter register 146 that stores a command list 150. A command "list" may refer to a single command or a plurality of commands. In some examples, the command list 150 includes a list of approved commands that are allowed to be executed relative to the non-volatile memory 128. In such examples, when the command filter 144 (e.g., from the security processor 124 or another entity) receives a command to access the non-volatile memory 128, the command filter 144 compares the received command to the approved command list, and if the received command is part of the approved command list, the command filter 144 allows the received command to be executed relative to the non-volatile memory 128.

[0038] In various examples, command list 150 may include a list of unapproved commands that are not permitted to be executed relative to non-volatile memory 128. In such an example, command filter 144 compares the received command to the list of unapproved commands and, if the received command is part of the list of approved commands, command filter 144 blocks execution of the received command relative to non-volatile memory 128 (effectively disabling access to non-volatile memory 128 in response to the received command).

[0039] In response to detecting a potential attack in computer system 100, attack handling instructions 126 may program command filter register 146 with command list 150 to block access to non-volatile memory 128. In an example where command list 150 is an approved command list, command list 150 may be a blank list such that command filter 144 will block all commands requesting access to non-volatile memory 128. In a different example, if list command 150 is an unapproved command list, command list 150 may include all commands to be blocked by command filter 144.

[0040] Programming the command filter register 146 with the command list 150 to block access to the non-volatile memory 128 gives the attack handling instructions 126 time to determine the likelihood that the potential attack is a real attack. If the attack handling instructions 126 determine that the potential attack is likely to be a real attack, the attack handling instructions 126 may trigger an erase (zeroing) of the non-volatile memory 128 and activate the lock 152 to prevent further access to the non-volatile memory 128.

[0041] In some examples, lock 152 may be in the form of a one-time programmable (OTP) memory that can only be programmed (written) once in bus controller 136. In other examples, lock 152 may be implemented using a different mechanism.

[0042] The OTP memory may include a field that is initially set to a first value that corresponds to an unlocked state (i.e., access to the non-volatile memory 128 is allowed) so that the bus controller 136 may allow access to the non-volatile memory 128 if the command filter 144 allows the received command. However, if the field in the OTP memory is set to a second value (different from the first value) indicating that access to the non-volatile memory 128 is to be locked, the bus controller 136 will prevent any further access to the non-volatile memory 128. Setting the field of the OTP memory to the second value may be referred to as writing a lock indicator to the OTP memory.

[0043] Once the OTP memory field is written with the second value, the OTP memory field cannot be reversed even if the computer system 100 is to be powered on to power off the bus controller 136. Therefore, the lock 152 is an irreversible lock. An "irreversible" lock is a lock that cannot be modified to an unlocked state by, for example, a user of the computer system 100 after it is set. It should be noted that in some cases, an "irreversible" lock can be reversed by an authorized entity (such as the manufacturer of the computer system 100 or another authorized entity). More generally, once the lock 152 is activated, it will remain activated after the computer system 100 is powered on.

[0044] The activation lock 152 protects the non-volatile memory 128 from unauthorized access even if the zeroing process does not successfully erase the contents of the non-volatile memory 128. In other examples, the lock 152 is omitted or not activated.

[0045] The bus controller 138 in the non-volatile memory access subsystem 114 similarly includes a command filter 154, a command filter register 156 storing a command list 158 ​​(either an approved command list or an unapproved command list), and a lock 160. The programming of the command filter register 156 and the setting of the lock 160 may be controlled by the attack handling instructions 126, which are executed by the security processor 124 in the secure enclave 106. In other examples, the security processor 124 may be implemented using hardware logic, such as a finite state machine for performing the tasks of the attack handling instructions 126 discussed herein.

[0046] The secure enclave 106 further includes a communication interface 162 that allows components in the secure enclave 106 to communicate with components outside the secure enclave 106 (and vice versa). The non-volatile memory access subsystem 114 also includes a communication interface 164. The communication interface 162 or 164 may include a bus interface, a network interface, etc. The communication interface 162 is capable of controlling communications entering or leaving the secure enclave 106, including communications of the security processor 124, and traffic related to access to the non-volatile memory 128. The communication interface 164 handles traffic related to access to the non-volatile memory 130.

[0047] Figure 2 is a flow chart of an attack handling process involving the secure enclave 106 and the non-volatile memory access subsystem 114 according to some examples of the present disclosure. Figure 2 The tasks of the security processor 124 depicted in FIG. 1 may be performed, for example, in Figure 1 Alternatively, the security processor 124 may be implemented using hardware logic such as a finite state machine. Figure 2 A particular order of tasks is shown, but in other examples, the tasks may be performed in a different order and / or in parallel, some tasks may be omitted, and other tasks may be added.

[0048] The security processor 124 in the secure enclave 106 detects (at 202) a potential attack in the computer system 100. The detection may be based on monitored information from a first subset of sensors 170. For example, the detection of a potential attack may be based on a temperature measurement from a temperature sensor, a voltage measurement from a voltage sensor, a current measurement from a current sensor, a tampering indication from a physical intrusion detector, and / or an alert from a malware detector. In some cases, the detection of a potential attack may be based on monitored information from more than one sensor.

[0049] In response to detecting a potential attack in computer system 100, security processor 124 programs (at 204) each of command filter registers 146 in secure enclave 106 and command filter registers 156 in non-volatile memory access subsystem 114 (these registers have corresponding command lists (150 and 158)) to block access to corresponding non-volatile memories 128 and 130. Security processor 124 may program, for example, via Figure 1 The command filter register 156 in the non-volatile memory access subsystem 114 is programmed using the communications interfaces 162 and 164 depicted in FIG.

[0050] Based on the programmed contents of the command filter register 146, the command filter 144 in the secure enclave 106 blocks (at 206) access commands that seek to access the non-volatile memory 128. Based on the programmed contents of the command filter register 156, the command filter 154 blocks (at 208) access commands that seek to access the non-volatile memory 130. The programming of the command filter registers 146 and 156 may be performed relatively quickly (e.g., almost immediately, such as on the order of a few nanoseconds or less) after a potential attack is detected to prevent an attacker from performing unauthorized access to the non-volatile memories 128 and 130. If there are other memories to be protected in the computer system 100, the security processor 124 may similarly program the command filter registers of such other memories to quickly block access to such other memories.

[0051] The security processor 124 then determines (at 210) the likelihood that the potential attack is a real attack. In some cases, the indicated potential attack may be the result of a malfunction in the computer system 100. For example, a sensor that indicates a potential attack may malfunction. As another example, another component of the computer system 100 may malfunction, which may cause the sensor to indicate a potential attack (e.g., a fan malfunctions causing temperature measurements to be out of specification, a power supply malfunctions causing glitches in voltage or current measurements, a clock source malfunctions causing clock speed variations, etc.).

[0052] The determination of the likelihood that a potential attack is a real attack can be based on monitored information from one or more additional sensors in addition to the first subset of sensors used to detect potential attacks. For example, the security processor 124 can detect a potential attack based on a measurement result from a first sensor (e.g., a temperature measurement result from a temperature sensor) exceeding a specification. The security processor 124 can determine the likelihood that a potential attack is a real attack based on examining the monitored information provided by one or more other sensors (e.g., a voltage sensor, a current sensor, a clock speed sensor, a digital canary circuit board 72, etc.). The security processor 124 can generate a value representing the likelihood that a potential attack is a real attack. For example, the security processor 124 can apply a function based on various monitored information from multiple sensors and generate a value representing the likelihood that a potential attack is a real attack.

[0053] The security processor 124 determines (at 212) whether the likelihood exceeds a threshold. If the likelihood exceeds the threshold, the security processor 124 triggers (at 214) an erase (zeroing) of the non-volatile memories 128 and 130, and further the security processor 124 activates (at 216) the lock 152 in the secure enclave 106 and the lock 160 in the non-volatile memory access subsystem 114.

[0054] However, if the security processor 124 determines (at 212) that the likelihood that the potential attack is a real attack does not exceed the threshold, the security processor 124 resets (at 218) the command filter registers 146 and 156 so that the command filters 144 and 154 can once again allow access to the respective non-volatile memories 128 and 130. For example, if the command list 150 in the command filter register 146 and the command list 158 ​​in the command filter register 156 are approved command lists, resetting the command filter registers 146 and 156 includes adding the approved commands to the allowed lists 150 and 158. As another example, if the command list 150 in the command filter register 146 and the command list 158 ​​in the command filter register 156 are unapproved command lists, resetting the command filter registers 146 and 156 includes removing the unapproved commands from the lists 150 and 158.

[0055] Figure 3 is a block diagram of a non-transitory machine-readable or computer-readable storage medium 300 storing machine-readable instructions executable to cause a security processor in a system to perform various tasks. For example, a system may include computer system 100 .

[0056] The machine-readable instructions include potential attack detection instructions 302 for detecting a potential attack in a system. In some examples, the detection of a potential attack can be based on information from, for example, Figure 1 The information monitored by the sensor 170 in the system and / or any one or more of the sensor sets (single sensor or multiple sensors) in the digital canary circuit 172. A potential attack may or may not be a real attack. For example, if a fault in the system generates monitored information indicating a potential attack, the potential attack may not be a real attack.

[0057] The machine-readable instructions include command filtering instructions 304 to issue a command blocking instruction to block processing of commands that access non-volatile memory in response to detecting a potential attack in the system. For example, the command blocking instruction may include writing to a command filter register (e.g., Figure 1146 and / or 156) of the non-volatile memory. If the command list is an approved command list, the command blocking indication may include a blank command list to block processing of any command seeking to access the non-volatile memory.

[0058] The machine-readable instructions include real attack likelihood determination instructions 306 to determine the likelihood that a potential attack is a real attack based on monitored information from at least one additional sensor (in addition to the set of sensors used to indicate a potential attack). For example, real attack likelihood determination instructions 306 can consider input measurement information from multiple sensors to determine the likelihood that a potential attack is a real attack.

[0059] The machine-readable instructions include real attack remediation instructions 308 to trigger erasure of the non-volatile memory in response to the determined likelihood satisfying the criteria. As an example, the determined likelihood satisfying the criteria may include a value indicating that the likelihood exceeds a threshold.

[0060] In some examples, in response to the determined likelihood, the security processor activates a lock to prevent further access to the non-volatile memory. Activation of the lock may include activating an irreversible lock such as by writing a lock indicator to the OTP memory. The lock indicator may be a field in the OTP memory that is set to a specified value.

[0061] In some examples, the secure processor may be a secure enclave (e.g., Figure 1 The controller may be part of the secure enclave or outside the secure enclave. In some examples, the secure enclave may be a BMC (e.g., Figure 1 104) is part of the.

[0062] In some examples, the command blocking directive blocks processing of commands to access the non-volatile memory during a time interval when the system determines the likelihood that a potential attack is a real attack and the system erases the non-volatile memory.

[0063] In some examples, the machine-readable instructions may remove the command blocking indication in response to determining that the potential attack is unlikely to be an actual attack. For example, removing the command blocking indication may include resetting a command filter register.

[0064] Figure 4 4 is a block diagram of a computer system 400 that includes a nonvolatile memory 402, a controller 404 for the nonvolatile memory 402, and a security processor 406. The controller 404 may be a bus controller (e.g., Figure 1 136 or 138 in the table).

[0065] The security processor 406 executes machine readable instructions for performing various tasks. The machine readable instructions executed by the security processor 406 include potential attack detection instructions 408 to detect a potential attack in the computer system 400 based on the first monitored information. The first monitored information may come from a set of sensors.

[0066] The machine-readable instructions executed by the security processor 406 include command filtering activation instructions 410 to activate command filtering to prevent processing of commands that access non-volatile memory in response to detecting a potential attack in the computer system. Activation of command filtering includes setting a command filter register (e.g., Figure 1 146 or 156) for programming.

[0067] Machine readable instructions executed by security processor 406 include real attack likelihood determination instructions 412 to determine the likelihood that a potential attack is a real attack based on the second monitored information. The second monitored information may include monitored information from one or more additional sensors in addition to the set of sensors.

[0068] The machine readable instructions executed by the security processor 406 include real attack remediation instructions 414 to trigger erasure of the non-volatile memory in response to the determined likelihood. During the time when the machine readable instructions are determining the likelihood that the potential attack is a real attack and are erasing the non-volatile memory, command filtering blocks access to the non-volatile memory to prevent unauthorized access to the non-volatile memory.

[0069] In some examples, command filtering is performed by a command filter in a controller, and the lock is included in the controller.

[0070] In some examples, the nonvolatile memory is a first nonvolatile memory and the controller is a first controller. The computer system further includes a second nonvolatile memory and a second controller for the nonvolatile memory. The security processor further executes machine-readable instructions to activate command filtering in the second controller to block processing of commands to access the second nonvolatile memory in response to detecting a potential attack in the computer system, and trigger an erase of the second nonvolatile memory and activate a lock in the second controller to prevent further access to the nonvolatile memory in response to the determined likelihood.

[0071] Figure 5 is a flow chart of a process 500 that may be performed by a security processor (e.g., Figure 1Process 500 includes detecting (at 502) a potential attack in a computer system based on first monitored information from a sensor set by a security processor. The sensor set may include a single sensor or a plurality of sensors.

[0072] In response to detecting a potential attack in the computer system, the security processor triggers (at 504) a multi-layer protection process. The multi-layer protection process includes a first layer (506) that includes command filtering in a controller for non-volatile memory to prevent processing of commands that access the non-volatile memory.

[0073] The multi-layer protection process further includes a second layer (508) that includes determining a likelihood that the potential attack is a real attack based on second monitored information from a sensor other than the sensor set, and in response to the determined likelihood satisfying a criterion, triggering an erase of the non-volatile memory and activating a lock to prevent further access to the non-volatile memory.

[0074] "BMC" may refer to a professional service controller that uses sensors to monitor the physical state of a computer system and communicates with a remote management system (away from the computer system) through an independent "out-of-band" connection. A BMC may perform management tasks that manage components of a computer system. Examples of management tasks that may be performed by a BMC may include any one or some combination of the following: power control that performs power management on a computer system (such as transitioning a computer system between different power consumption states in response to a detected event), thermal monitoring and control of a computer system (such as monitoring the temperature of a computer system and controlling the thermal management state of the computer system), fan control of a fan in a computer system, system health monitoring based on monitoring measurement data from various sensors of a computer system, remote access to a computer system (e.g., accessing a computer system over a network), remote restart of a computer system (using a remote command to trigger a computer system restart), system setup and deployment of a computer system, system security that implements security programs in a computer system, and the like.

[0075] In some examples, the BMC can provide a so-called "unattended" function for the computer system. The unattended function can allow users such as system administrators to perform management operations on the computer system even if the OS is not installed on the computer system or the OS is not functioning on the computer system.

[0076] Furthermore, in some examples, the BMC can operate on auxiliary power provided by an auxiliary power supply (e.g., a battery); thus, the computer system does not have to be powered on to allow the BMC to perform the operations of the BMC. The auxiliary power supply is separate from the main power supply that supplies power to other components of the computer system (e.g., the main processor, memory, input / output (I / O) devices, etc.).

[0077] In some examples, in addition to the BMC in each computer system, an additional management controller (separate from the BMC) may be used to interact with the BMC to perform management of the computer system. In examples where the computer system is a server computer (or other type of computer system) installed in a rack, the additional management controller may be referred to as a rack management controller (RMC). A "rack" refers to a mounting structure with brackets for multiple computer systems.

[0078] Storage media (e.g. Figure 3 300) may include any one or some combination of the following: a semiconductor memory device, such as a dynamic or static random access memory (DRAM or SRAM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), and a flash memory; a magnetic disk, such as a fixed disk, a floppy disk, and a removable disk; another magnetic medium, including a tape; an optical medium, such as a compact disk (CD) or a digital video disk (DVD); or another type of storage device. Note that the instructions discussed above may be provided on one computer-readable or machine-readable storage medium, or alternatively, may be provided on multiple computer-readable or machine-readable storage media distributed in a large system with possibly multiple nodes. Such one or more computer-readable or machine-readable storage media are considered to be part of an article (or product). An article or product may refer to any manufactured single component or multiple components. One or more storage media may be located in a machine running machine-readable instructions, or at a remote site, from which machine-readable instructions may be downloaded over a network for execution.

[0079] In the present disclosure, unless the context clearly indicates otherwise, the use of the terms "a", "an" or "the" is intended to include the plural forms as well. Similarly, when used in the present disclosure, the terms "includes / including / comprises / comprising", "have / having" specify the presence of stated elements, but do not exclude the presence or addition of other elements.

[0080] In the foregoing description, many details are set forth to enable an understanding of the subject matter disclosed herein. However, embodiments may be practiced without some of these details. Other embodiments may include modifications and variations of the details discussed above. The appended claims are intended to cover such modifications and variations.

Claims

1. A non-transitory machine-readable storage medium comprising instructions that, when executed, cause a security processor in a system to perform the following operations: detecting potential attacks on said system; In response to detecting the potential attack in the system, issuing a command blocking indication to block processing of commands that access non-volatile memory; Determining, based on the monitored information, the likelihood that the potential attack is a real attack; as well as In response to the determined likelihood, erasure of the non-volatile memory is triggered.

2. The non-transitory machine-readable storage medium of claim 1, wherein: The instructions, when executed, cause the security processor to activate a lock to prevent further access to the non-volatile memory in response to the determined likelihood.

3. The non-transitory machine-readable storage medium of claim 2, wherein: The activation of the lock includes writing a lock indicator to a one-time programmable (OTP) memory.

4. The non-transitory machine-readable storage medium of claim 2, wherein: The lock is irreversible and remains in place after power is cycled to the system.

5. The non-transitory machine-readable storage medium of claim 1, wherein: The command block indication is provided to a command filter, which blocks one or more commands for accessing the non-volatile memory.

6. The non-transitory machine-readable storage medium of claim 5, wherein: The secure processor is part of a secure enclave and the command filter is outside the secure enclave.

7. The non-transitory machine-readable storage medium of claim 5, wherein: The security processor and the command filter are part of a security enclave.

8. The non-transitory machine-readable storage medium of claim 5, wherein: The command filter is used to block the one or more commands based on a command list stored in a register.

9. The non-transitory machine-readable storage medium of claim 1, wherein: The detecting of the potential attack is based on an output of a first sensor, and determining a likelihood that the potential attack is a real attack is further based on an output of a second sensor different from the first sensor.

10. The non-transitory machine-readable storage medium of claim 1, wherein: The command blocking indication blocks the processing of the command during a time interval when the system determines the possibility that the potential attack is the real attack and the system erases the non-volatile memory.

11. The non-transitory machine-readable storage medium of claim 1, wherein: When executed, the instructions cause the security processor to perform the following operations: The command blocking indication is removed in response to determining that the potential attack is unlikely to be the actual attack.

12. A computer system comprising: Non-volatile memory; A controller, the controller being used for the non-volatile memory; as well as A security processor, the security processor is used to: detecting a potential attack in the computer system based on the first monitored information; activating command filtering to prevent processing of commands that access the non-volatile memory in response to detecting the potential attack in the computer system, determining a likelihood that the potential attack is a real attack based on the second monitored information, and In response to the determined likelihood indicating that the potential attack is the actual attack, erasure of the non-volatile memory is triggered.

13. The computer system of claim 12, wherein: The security processor is to, in response to the determined likelihood indicating that the potential attack is the actual attack, activate a lock to prevent further access to the non-volatile memory, the lock once activated remaining activated when the computer system is power cycled.

14. The computer system of claim 13, wherein: The activating of the lock includes writing a lock indicator to a one-time programmable (OTP) memory in the controller.

15. The computer system of claim 12, wherein: The command filtering is performed by a command filter in the controller, and wherein the security processor is configured to reset the command filtering in response to determining that the potential attack is unlikely to be the actual attack.

16. The computer system of claim 15, wherein: The controller comprises a register including a command list usable by the command filter to determine whether to block received commands accessing the non-volatile memory, and wherein the activation of the command filtering comprises programming the register with the command list.

17. The computer system of claim 12, wherein: The nonvolatile memory is a first nonvolatile memory, and the controller is a first controller, and the computer system further comprises: a second non-volatile memory; a second controller, the second controller being used for the non-volatile memory, Wherein, the security processor is used for: activating command filtering in the second controller to prevent processing of commands that access the second non-volatile memory in response to detecting the potential attack in the computer system, In response to the determined likelihood, an erase of the second non-volatile memory is triggered and a lock in the second controller is activated to prevent further access to the non-volatile memory.

18. The computer system of claim 17, wherein: The security processor and the first controller are part of a secure enclave, and the second controller is outside the secure enclave.

19. A method for protecting a computer system, comprising: detecting, by a security processor, a potential attack in the computer system based on first monitored information from a set of sensors; In response to detecting the potential attack in the computer system, a multi-layer protection process is triggered by the security processor, the multi-layer protection process comprising: a first layer including command filtering in a controller for a non-volatile memory to prevent processing of commands to access the non-volatile memory, and A second layer, the second layer includes determining a likelihood that the potential attack is a real attack based on second monitored information from a sensor other than the sensor set, and in response to the determined likelihood satisfying a criterion, triggering an erase of the non-volatile memory and activating a lock to prevent further access to the non-volatile memory.

20. The method of claim 19, wherein: The command filtering is applied by the controller based on a register programmed with a command list, and the lock includes a one-time programmable (OTP) memory.