Meta Platforms Technologies, LLC

Facebook Technologies, LLC

Neeraj Upasani

Wojciech Stefan Powiertowski

Sudhir K Satpathy

Dinesh D Patil

Nagendra Gupta Modadugu

Shrirang Madhav Yardi

Marco Brambilla

Drew Eric Wingard

Jun Wang

Gregory Ehmann

Miguel Angel Guerrero

Nagendra Modadugu

Jay Shih Tsao

Minli Lin

This disclosure describes systems on a chip (SOCs) that prevent trim attempts. The SOCs include one-time programmable (OTP) memory and an engine configured to determine if the one-time programmable (OTP) memory has been trimmed; and if the one-time programmable (OTP) memory has been trimmed, to prevent trimming of the OTP memory.

Tamper detection and prevention in computer systems having one-time programmable memory

Systems, methods, and devices authenticate processor instructions stored by a read-only memory (ROM). In one example, a ROM stores a block of register words. The block of register words includes a first register word specifying an authentication tag and one or more register words that each specify an instruction. A security controller identifies the first register word as specifying the authentication tag and performs authentication of the authentication tag. Upon successfully authenticating the authentication tag, the security controller forwards the register words that each specify instructions to a processor for execution. Upon unsuccessfully authenticating the authentication tag, the security controller blocks the register words that each specify instructions from execution by the processor.

ROM instruction authentication and integrity verification for artificial reality security controller

A system on a chip includes a first subsystem comprising a first memory; a second subsystem comprising a second memory; and an always-on subsystem. The always-on subsystem can comprise processing circuitry configured to: in response to a first activation event, signal the first subsystem to initiate repair operations on the first memory, and in response to a second activation event occurring after the first event, signal the second subsystem to initiate repair operations on the second memory.

Distributed phased SRAM repair for systems on a chip

An example method for execution on a system on a chip (SoC) having a plurality of subsystems includes receiving, by a storage controller from a subsystem of the plurality of subsystems, a command to fetch, from a local memory, task descriptor data comprising access parameters for accessing a storage device, the access parameters including a storage device address; obtaining, by an encryption engine of the SoC, the command to fetch the task descriptor data; determining, by the encryption engine based on an access rule, whether the subsystem has sufficient privilege to access the storage device address; in response to determining that the subsystem has sufficient privilege to access the storage device, encrypting, source data in the local memory according to an encryption key associated with the subsystem; and providing the encrypted source data to the storage controller for writing to the storage device at the storage device address.

Isolation of secrets from an operating system

This disclosure describes system on a chip (SOC) communications that prevent direct memory access (DMA) attacks. An example SoC includes an encryption engine and a security processor. The encryption engine is configured to encrypt raw input data using a cipher key to form an encrypted payload. The security processor is configured to select the cipher key from a key store holding a plurality of cipher keys based on a channel ID describing a {source subsystem, destination subsystem} tuple for the encrypted payload, to form an encryption header that includes the channel ID, to encapsulate the encrypted payload with the encryption header that includes the channel ID to form a crypto packet, and to transmit the crypto packet to a destination SoC that is external to the SoC.

System on a chip (SOC) communications to prevent direct memory access (DMA) attacks

An example system on a chip (SoC) includes a security processor configured to store a plurality of key-pairs associated with subsystems of the SoC to a key vault; and an encryption engine configured to: determine a first tweak value based on a first sector address of a storage device; encrypt the first tweak value according to the second key of the key-pair associated with a subsystem; encrypt a first portion of the source data according to a first key of the key-pair and the encrypted first tweak value; determine a second tweak value based on a second sector address of the storage device and encrypt the second tweak value according to the second key prior to completing the encryption of the first portion of the source data; and encrypt a second portion of the source data according to the first key and the encrypted second tweak value.

High throughput storage encryption

Techniques are described for improving security of a boot sequence of a system, such as an artificial reality system. In some examples, a method includes configuring, by a boot sequencing system, attack detection circuitry based on configuration information accessed from a first storage device; after configuring the attack detection circuitry, starting, by the boot sequencing system, a root of trust processor to initiate a boot sequence; enabling access, by the root of trust processor during the boot sequence, to secret information stored in a second storage device.

Artificial reality system with multi-stage boot process

The disclosure describes wireless communication systems. The wireless communication system includes first memory, second memory, a direct memory access (DMA) controller, an encryption engine in-line between the DMA controller and the second memory, a first microprocessor, and a second microprocessor. The first microprocessor communicates with other systems that generate application data to be wirelessly transmitted. The application data to be wirelessly transmitted is stored in the second memory and programs the DMA controller to transfer packets of the application data to the first memory from the second memory. The encryption engine receives the packets of the application data from the DMA controller, encrypts the packets to generate encrypted application data packets, and outputs the encrypted application data packets for storage to the first memory.

Inline encryption of packet data in a wireless communication system

In an example of the described techniques, a wireless communication system includes first memory, second memory, a first microcontroller, and a second microcontroller. The first microcontroller manages drivers for a wireless transceiver and direct data movement between the wireless transceiver and the first memory. The second microcontroller communicates with other systems that generate application data to be wirelessly transmitted. The application data to be wirelessly transmitted is stored in the second memory. Additionally, the second microcontroller direct data movement between the second memory and the first memory.

Wireless communication with code separation

System on a chip (SoC) communications to prevent direct memory access (DMA) attacks

The disclosure describes techniques for interrupt and inter-processor communication (IPC) mechanisms that are shared among computer processors. For example, an artificial reality system includes a plurality of processors; an inter-processor communication (IPC) unit comprising a register, wherein the IPC unit is configured to: receive a memory access request from a first processor of the processors, wherein the memory access request includes information indicative of a hardware identifier (HWID) associated with the first processor; determine whether the HWID associated with the first processor matches an HWID for the register of the IPC unit; and permit, based on determining that the HWID associated with the first processor matches the HWID for the register of the IPC unit, the memory access request to indicate a communication from the first processor to at least one other processor.

Artificial reality system with inter-processor communication (IPC)

This disclosure describes systems on a chip (SOCs) that prevent side channel attacks on encryption and decryption engines of an electronic device. The SoCs of this disclosure concurrently operate key-diverse encryption and decryption datapaths to obfuscate the power trace signature exhibited by the device that includes the SoC. An example SoC includes an encryption engine configured to encrypt transmission (Tx) channel data using an encryption key and a decryption engine configured to decrypt encrypted received (Rx) channel data using a decryption key that is different from the encryption key. The SoC also includes a scheduler configured to establish concurrent data availability between the encryption and decryption engines and activate the encryption engine and the decryption engine to cause the encryption engine to encrypt the Tx channel data concurrently with the decryption engine decrypting the encrypted Rx channel data using the decryption key that is different from the encryption key.

Parallel scheduling of encryption engines and decryption engines to prevent side channel attacks

Systems on a chip (SoCs) include security logic configured to increase resistance to fault injection attacks (FIAs). The security logic includes a monitoring circuit and a cascaded series of substitution-boxes (S-Boxes) having a circuit delay that is designed to match (or most closely match) the computing device critical path length. The monitoring circuit monitors the number of iterations required for the cascaded series of S-Boxes to return to an initial value and generates an error signal if the monitored loop length is different from the expected loop length. In some examples, the error signal is received by a mitigation processor that executes one or more processes aimed at mitigating the attack.

Monitoring circuit including cascaded s-boxes for fault injection attack protection

In general, this disclosure describes techniques for using a random number generator to affect the lengths of clock cycles in a clock waveform that drives the timing of operations performed by processing circuitry. In one example, the processing circuitry includes a central processing unit and a clock generator. The clock generator is configured, upon receiving an indication of a boot command for the processing circuitry, generate a random number using a true random number generator and generate, based at least in part on the random number, an output clock waveform indicating at least a length of a clock cycle for the central processing unit. The central processing unit is configured to execute a boot sequence for at least the processing circuitry using the output clock waveform.

Randomized clock cycle lengths for boot sequences

This disclosure describes systems on a chip (SOCs) that prevent side channel attacks (SCAs). The SoCs of this disclosure concurrently operate multi-round encryption and decryption datapaths according to a combined sequence of encryption rounds and decryption rounds. An example SoC of this disclosure includes an engine configured to encrypt transmission (Tx) channel data using a multi-round encryption datapath, and to decrypt encrypted received (Rx) channel data using a multi-round decryption datapath. The SoC further includes a security processor configured to multiplex the multi-round encryption datapath against the multi-round decryption datapath on a round-by-round basis to generate a mixed sequence of encryption rounds and decryption rounds, and to control the engine to encrypt the Tx channel data and decrypt the encrypted Rx channel data according to the mixed sequence of encryption rounds and decryption rounds.

Growing community of inventors

Redmond, WA, United States of America

Neeraj Upasani