Qualcomm Incorporated

Assaf Shacham

David Teb

Amit Gil

Maya Haim

Shaul Yohai Yifrach

Dolev Raviv

Lee Susman

Tom Yahalom

Jung Pill Kim

Lior Amarilio

Yanru Li

Azzedine Touzni

Hyunsuk Shin

Ron Keidar

Thomas Zeng

Nir Gerber

Osman Koyuncu

Erez Tsidon

Yossi Amon

Tatyana Brokhman

Konstantin Dorfman

Eyal Skulsky

Aviad Zacks-Shtrauss

Itai Lanel

Aspects disclosed in the detailed description include hardware accelerated storage compression. In one aspect, prior to writing an uncompressed data block to the storage device, a hardware compression accelerator provided in a storage controller compresses the uncompressed data blocks individually into a compressed data block and allocates the compressed data block to a storage data block in the storage device. The hardware compression accelerator then generates a modified logical block address (LBA) to link the uncompressed data block to the compressed data blocks. In another aspect, the hardware compression accelerator locates a compressed data block based on a corresponding modified LBA and decompresses the compressed data block into an uncompressed data block. By performing hardware accelerated storage compression in the storage controller, it is possible to reduce processing overhead associated with traditional software-based compression systems and improve compression control over traditional storage device driven compression systems.

Hardware-accelerated storage compression

Aspects disclosed in the detailed description include inline cryptographic engine (ICE) for peripheral component interconnect express (PCIe). In this regard, in one aspect, an ICE is provided in a PCIe root complex (RC) in a host system. The PCIe RC is configured to receive at least one transport layer packet (TLP), which includes a TLP prefix, from a storage device. In a non-limiting example, the TLP prefix includes transaction-specific information that may be used by the ICE to provide data encryption and decryption. By providing the ICE in the PCIe RC and receiving the transaction-specific information in the TLP prefix, it is possible to encrypt and decrypt data in the PCIe RC in compliance with established standards, thus ensuring adequate protection during data exchange between the PCIe RC and the storage device.

Inline cryptographic engine (ICE) for peripheral component interconnect express (PCIe) systems

Device identification generation in electronic devices to allow external control, such as selection or reprogramming, of device identification for bus communications identification, is disclosed. In this manner, device identifications of electronic devices coupled to a common communications bus in a system can be selected or reprogrammed to ensure they are unique to avoid bus communications collisions. In certain aspects, to select or reprogram a device identification in an electronic device, an external source can be electrically coupled to the electronic device. The external source closes a circuit with a device identification generation circuit in the electronic device. The closed circuit provides a desired electrical characteristic detectable by the device identification generation circuit. The device identification generation circuit is configured to generate a device identification as a function of the detected electrical characteristics of the closed circuit from the external source.

Device identification generation in electronic devices to allow external control of device identification for bus communications identification, and related systems and methods

Aspects disclosed in the detailed description include storage resource management in virtualized environments. In this regard, in one aspect, a virtualization layer is provided in a storage controller as an interface between one or more clients and a storage device. The storage controller is configured to trap storage resource requests from a client. A virtualized resource manager creates a virtual resource allocation that corresponds to a physical resource allocation in the storage device. The client receives the virtual resource allocation from the virtualization layer and subsequently accesses the virtual resource allocation through the storage controller as if the client were the sole user of the storage device. By trapping the storage resource requests at the storage controller and providing the virtual resource allocations to the one or more clients, it is possible to share compatibly the storage device among the one or more clients in a virtualized environment.

Storage resource management in virtualized environments

Hardware-based translation lookaside buffer (TLB) invalidation techniques are disclosed. A host system is configured to exchange data with a peripheral component interconnect express PCIE) endpoint (EP). A memory management unit (MMU), which is a hardware element, is included in the host system to provide address translation according to at least one TLB. In one aspect, the MMU is configured to invalidate the at least one TLB in response to receiving at least one TLB invalidation command from the PCIE EP. In another aspect, the PCIE EP is configured to determine that the at least one TLB needs to be invalidated and provide the TLB invalidation command to invalidate the at least one TLB. By implementing hardware-based TLB invalidation in the host system, it is possible to reduce TLB invalidation delay, thus leading to increased data throughput, reduced power consumption, and improved user experience.

Hardware-based translation lookaside buffer (TLB) invalidation

Storage resource management in virtualized environments is provided. In this regard, when receiving a request for accessing a target general purpose partition (GPP) in a storage device, partition switching circuitry is configured to determine whether the target GPP equals a current GPP that is accessed by a list of existing requests. The partition switching circuitry adds the request into the list of existing requests if the target GPP equals the current GPP. Otherwise, the partition switching circuitry waits for the list of existing requests to be executed on the current GPP before switching to the target GPP to execute the request received from a client. By switching to the target GPP after executing the list of existing commands on the current GPP, it is possible to share a plurality of GPPs among multiple clients in a virtualized environment while maintaining data integrity and security in the storage device.

Bifurcated memory management for memory elements techniques are disclosed. In one aspect, a memory element includes a self-managed portion and a portion that is managed by a remote host. Software that needs low latency access may be stored in the portion of the memory element that is managed by the remote host and other software may be stored in the portion of the memory element that is managed by the memory element. By providing such bifurcated memory management of the memory element, a relatively inexpensive memory element may be used to store software while at the same time allowing low latency (albeit at low throughputs) access to sensitive software elements with minimal bus logic.

Bifurcated memory management for memory elements

A multi-host power controller (MHPC) of a flash-memory-based storage device is disclosed. In one aspect, the MHPC receives power mode change requests from each of multiple input/output (I/O) clients. The MHPC extracts and stores a 'vote,' or a requested power mode, from the power mode change requests, and then applies a voting logic to the stored votes to determine whether to transition the flash-memory-based storage device between power modes. If the flash-memory-based storage device is not currently operating in the power mode determined by the MHPC, the MHPC is configured to issue a power mode change command to the flash-memory-based storage device to transition to the determined power mode. In this manner, the MHPC is able to control the power mode of the flash-memory-based storage device while receiving direct power mode change requests from multiple I/O clients.

Multi-host power controller (MHPC) of a flash-memory-based storage device

Disclosed is a method and apparatus to decrypt file segments in parallel. In one embodiment, an integrated circuit may be used with a storage device of a computing device that comprises: a hardware interface to communicate with the storage device; a crypto-engine to encrypt file segments to be stored on the storage device and to decrypt file segments read from the storage device; and a processor. The processor may be configured to: read a plurality of decrypted file segments from the storage device through the crypto-engine in parallel; and to store the plurality of decrypted file segments.

Apparatus and method to decrypt file segments in parallel

Command trapping in an input/output virtualization (IOV) host controller (HC) (IOV-HC) of a flash-memory-based storage device is disclosed. In one aspect, an IOV-HC is configured to receive a request from a client register interface (CRI) of one of multiple input/output (I/O) clients. The IOV-HC inspects a content of the request prior to the request being passed to a transport protocol engine. Based on the content, the IOV-HC determines whether the request should be further processed or should be trapped. If the IOV-HC determines that the request should be trapped, the IOV-HC traps the request using a request trap. In some aspects, the IOV-HC generates an interrupt to a virtual machine manager (VMM) to notify the VMM that the request was trapped. In some aspects, the IOV-HC provides a response generation circuit to receive instructions from the VMM to generate a response to the CRI from which the trapped request originated.

Providing command trapping using a request filter circuit in an input/output virtualization (IOV) host controller (HC) (IOV-HC) of a flash-memory-based storage device

An input/output virtualization (IOY) host controller (HC) (IOV-HC) of a flash-memory-based storage device is disclosed. In one aspect, an IOV-HC is coupled to input/output (I/O) clients via corresponding client register interfaces (CRIs), and is also coupled to a flash-memory-based storage device. The IOV-HC comprises transfer request list (TRL) slot offset registers indicating slots of a shared TRL that are assigned as base slots to each of the CRIs. The IOV-HC further comprises TRL slot count registers indicating how many slots of the shared TRL are assigned to each of the CRIs. When a transfer request (TR) directed to the flash-memory-based storage device is received from a CRI, the IOV-HC is configured to map the TR to a slot of the shared TRL based on a TRL slot offset register and a TRL slot count register of the plurality of TRL slot count registers corresponding to the CRI.

Providing input/output virtualization (IOV) by mapping transfer requests to shared transfer requests lists by IOV host controllers

Providing command queuing in embedded memories is provided. In particular, aspects disclosed herein relate to a process through which a status of the queue is communicated to a host from a device. Aspects of the present disclosure use the command structure of the embedded Multi-Media Card (eMMC) standard, such that the host may determine a state of the queue in the device proximate a known end of an in-progress data transfer. In this manner, the host can select a task to commence after completion of a current data transfer while the current data transfer is still ongoing.

Providing command queuing in embedded memories

A method for error detection and recovery is provided in which a host controller and host software collaborate together. The host controller may: detect an error condition, set an error interrupt or register, and/or halt task execution or processing at the host controller. The host software may: detect an error condition as a result of the host controller having set the error interrupt or register; performs error handling, and clears the error condition. The host controller then resumes execution or processing of tasks upon detecting that error condition has been cleared by the host software.

Robust hardware/software error recovery system

Efficient techniques using a multi-port shared non-volatile memory are described that reduce latency in memory accesses from dedicated function specific processors, such as a modem control processor. The modem processor preempts a host processor that is accessing data from a multi-port shared non-volatile memory flash device allowing the modem processor to quickly access data in the flash device. The preemption process uses a doorbell interrupt initiated by a processor that seeks access and interrupts the processor being preempted. After preemption, the host processor may resume or restart the data access. Access control by the processors utilizes a hardware semaphore atomic control mechanism. Power control of the shared non-volatile memory modules includes at least one inactivity timer to indicate when a supply voltage to the shared non-volatile memory modules can be safely reduced or turned off. Power may be restarted by any of the processors sharing the memory, allowing fast access to the data.

Dual host embedded shared device controller

Removable memory card discrimination systems and methods are disclosed. In particular, exemplary embodiments discriminate between secure digital (SD) cards and other removable memory cards that comply with the SD form factor, but support the Universal Flash Storage (UFS) protocol. That is, a host may have a receptacle that supports the SD card form factor and is configured to receive a device. In use, a removable memory card is inserted into the receptacle and, using an SD compliant interrogation signal, the host interrogates a common area on the card so inserted. The common area includes information related to capability descriptors of the card. An SD compliant card will respond with information such as capability descriptors about the SD protocol capabilities, while a UFS compliant card will respond with an indication that the card is UFS compliant. The host may then restart the communication with the card using the UFS protocol.

Growing community of inventors

Zichron Yaakov, Israel

Assaf Shacham