WO2005006197A2 - An apparatus and method for memory encryption with reduced decryption latency - Google Patents

An apparatus and method for memory encryption with reduced decryption latency Download PDF

Info

Publication number
WO2005006197A2
WO2005006197A2 PCT/US2004/018272 US2004018272W WO2005006197A2 WO 2005006197 A2 WO2005006197 A2 WO 2005006197A2 US 2004018272 W US2004018272 W US 2004018272W WO 2005006197 A2 WO2005006197 A2 WO 2005006197A2
Authority
WO
WIPO (PCT)
Prior art keywords
data block
initialization vector
page
block
keystream
Prior art date
Application number
PCT/US2004/018272
Other languages
French (fr)
Other versions
WO2005006197A3 (en
Inventor
Carlos Rozas
Gary Graunke
Original Assignee
Intel Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intel Corporation filed Critical Intel Corporation
Priority to JP2006509096A priority Critical patent/JP4500306B2/en
Priority to EP19187662.2A priority patent/EP3575971A1/en
Priority to EP04754772.4A priority patent/EP1654661B1/en
Priority to CN2004800177114A priority patent/CN1836220B/en
Publication of WO2005006197A2 publication Critical patent/WO2005006197A2/en
Publication of WO2005006197A3 publication Critical patent/WO2005006197A3/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/14Protection against unauthorised use of memory or access to memory
    • G06F12/1408Protection against unauthorised use of memory or access to memory by using cryptography
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/78Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure storage of data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/82Protecting input, output or interconnection devices
    • G06F21/85Protecting input, output or interconnection devices interconnection devices, e.g. bus-connected or in-line devices
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/06Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols the encryption apparatus using shift registers or memories for block-wise or stream coding, e.g. DES systems or RC4; Hash functions; Pseudorandom sequence generators
    • H04L9/0618Block ciphers, i.e. encrypting groups of characters of a plain text message using fixed encryption transformation
    • H04L9/0637Modes of operation, e.g. cipher block chaining [CBC], electronic codebook [ECB] or Galois/counter mode [GCM]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L2209/00Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
    • H04L2209/12Details relating to cryptographic hardware or logic circuitry

Definitions

  • One or more embodiments of the invention relate generally to the field of cryptography. More particularly, one or more of the embodiments of the invention relates to a method and apparatus for memory encryption with reduced decryption latency.
  • cryptography provides a technique for keeping information secret, for determining that the information has not been tampered with and for determining who authored pieces of information.
  • One form of cryptography involves public or private key systems wherein transmitted information is encrypted prior to transmission and decrypted by the receiver using either a public or private key.
  • transmitted information is encrypted prior to transmission and decrypted by the receiver using either a public or private key.
  • the sensitive information arrives at its designated location, the information is often decrypted and stored. In other words, the sensitive information is not maintained in a secure format at its destination.
  • processor speeds continually increase in response to the growing demands of media and graphics applications, memory performance increases have not kept pace with the reduction in processor clock periods.
  • performing memory encryption by, for example a microprocessor is not feasible because the memory encryption in read operations would introduce additional latency beyond the current bottleneck that exists between processors and memory.
  • FIG. 1 is a block diagram illustrating a computer system including a processor having memory encryption/decryption logic to enable memory encryption with reduced decryption latency, in accordance with one embodiment of the invention.
  • FIG. 2 is a block diagram further illustrating the processor, as depicted in FIG. 1, in accordance with a further embodiment of the invention.
  • FIG. 3 is a block diagram further illustrating the processor, memory encryption/decryption logic, and encryption page structure, as depicted in FIG. 2, in accordance with a further embodiment of the invention.
  • FIG. 4 is a block diagram further illustrating the processor, the memory encryption/deciyption logic, and the encryption page structure, as depicted in FIG. 2, in accordance with a further embodiment of the invention.
  • FIG. 5 is a block diagram illustrating initialization vector recode logic, in accordance with one embodiment of the invention.
  • FIG. 6 is a flowchart illustrating a method for decryption of an encrypted data block read from memory, in accordance with one embodiment of the invention.
  • FIG. 7 is a flowchart illustrating a method for generating a keystream to decrypt an encrypted data block read from memory, in accordance with a further embodiment of the invention.
  • FIG. 8 is a flowchart illustrating a method for generating a keystream to decrypt an encrypted data block read from memory, in accordance with one embodiment of the invention.
  • FIG. 9 is a flowchart illustrating a method for encrypting a data block prior to writing the data block to memory, in accordance with one embodiment of the invention.
  • FIG. 10 is a flowchart illustrating a method for computing an initialization vector to enable formation of a keystream to encrypt a data block prior to writing the data block to memory, in accordance with one embodiment of the invention.
  • FIG. 11 is a flowchart illustrating a method for computing an initialization vector to enable formation of a keystream to encrypt a data block prior to writing the data block to memory, in accordance with a further embodiment of the invention.
  • FIG. 12 is a flowchart illustrating a method for storing components of an initialization vector to enable reformation of the initialization vector to decrypt an encrypted data block, in accordance with one embodiment of the invention.
  • FIG. 13 is a flowchart illustrating a method for receding an initialization vector, in accordance with one embodiment of the invention.
  • FIG. 14 is a block diagram illustrating various design representations or formats for simulation, emulation and fabrication of a design using the disclosed techniques.
  • the method includes reading an encrypted data block from memory. During reading of the encrypted data block, a keystream used to encrypt the data block is regenerated according to one or more stored criteria of the encrypted data block. Once the encrypted data block is read, the encrypted data block is decrypted using the regenerated keystream. Accordingly, in one embodiment, encryption of either random access memory (RAM) or disk memory is performed. A keystream is regenerated during data retrieval such that once the data is received, the data may be decrypted using a single clock operation. As a result, memory encryption is performed without exacerbating memory latency between the processor and memory.
  • RAM random access memory
  • logic is representative of hardware and or software configured to perform one or more functions.
  • examples of “hardware” include, but are not limited or restricted to, an integrated circuit, a finite state machine or even combinatorial logical.
  • the integrated circuit may take the form of a processor such as a microprocessor, application specific integrated circuit, a digital signal processor, a micro-controller, or the like.
  • An example of "software” includes executable code in the form of an application, an applet, a routine or even a series of instructions.
  • the software may be stored in any type of computer or machine readable medium such as a programmable electronic circuit, a semiconductor memory device inclusive of volatile memory (e.g., random access memory, etc.) and/or non- volatile memory (e.g., any type of read-only memory "ROM,” flash memoiy), a floppy diskette, an optical disk (e.g., compact disk or digital video disk “DVD”), a hard drive disk, tape, or the like.
  • FIG. 1 is a block diagram illustrating a computer system 100 including memory encryption/decryption logic 200, in accordance with one embodiment of the invention.
  • Computer system 100 comprises a processor system bus (front side bus (FSB)) 102 for communicating information between a processor (CPU) 110 and a chipset 180, coupled together via FSB 102.
  • FSB front side bus
  • Chipset 180 is coupled to main memory 140 and one or more graphic devices 130.
  • main memory 110 is volatile memory including, but not limited to, random access memory (RAM), synchronous RAM (SRAM), double data rate (DDR), S Data RAM (SDRAM), RAM bus data RAM (RDRAM), or the like.
  • RAM random access memory
  • SRAM synchronous RAM
  • DDR double data rate
  • SDRAM S Data RAM
  • RDRAM RAM bus data RAM
  • HDD hard disk drive devices
  • I/O input/output
  • CPU 110 includes memory encryption/decryption logic 200, which is further described with reference to FIG. 2.
  • FIG. 2 further illustrates CPU 110, to illustrate memory encryption with reduced decryption latency, in accordance with one embodiment of the invention.
  • CPU 110 is comprised of processor core 112, which may include, for example, copyback cache 130, as well as level one (LI) cache 114 for high speed temporary storage of data.
  • processor or CPU 110 may include level two (L2) cache 120.
  • L2 cache 120 is offchip memoiy coupled to backside bus unit 116 via, for example, backside bus 118.
  • CPU 110 includes external unit 104 for interfacing with FSB 102, as depicted in FIG. 1.
  • CPU 110 includes memory encryption/decryption logic 200.
  • logic 200 enables CPU 110 to securely encrypt contents of, for example, volatile memory, such as, for example, main memory 140, as depicted in FIG. 1 using a cipher algorithm.
  • the security provided by a block cipher algorithm consists of two processes that are inverses of each other: encryption and decryption.
  • Encryption is the transformation of a usable message called plaintext into an unreadable form called ciphertext.
  • decryption is the transformation that recovers the plaintext from the ciphertext.
  • memory decryption is provided by performing keystream regeneration during a memory read of an encrypted data block (ciphertext).
  • FIG. 3 illustrates logic 200 in an embodiment for a memory read decryption operation, in accordance with one embodiment of the invention.
  • logic 200 includes cipher logic 230 to generate a keystream 234 according to a secret key 232, as well as an initialization vector (IN) 220. Once the keystream is formed, logic 200 performs a logical exclusive OR operation (XOR) of keystream 234 with ciphertext 202, using XOR block 240. to form plaintext 204.
  • cipher logic 230 is, for example, advanced encryption standard (AES), cipher serpent or other like symmetric block cipher algorithm.
  • Block ciphers operate on blocks of plaintext and ciphertext comprised, for example, of ⁇ -bits.
  • stream ciphers operate on streams of plaintext and ciphertext, one bit or byte at a time.
  • block cipher the same plaintext block always encrypts to the same ciphertext block using the same key.
  • plaintext byte or bit will encrypt to a different bit or byte each time the plaintext is encrypted when using a stream cipher.
  • cipher logic 230 uses a reduced number of rounds to match the memory read latency while still providing adequate security.
  • a block cipher that supports an encryption mode for generating a keystream within the time required to fetch data from memory is used as cipher logic 230.
  • a stream cipher may be used for cipher logic 230.
  • a stream cipher uses a secret key and possibly an initialization vector (IV) or public value that may change and runs some function to produce a keystream. Once the keystream is generated, the keystream is combined with the plaintext to produce the ciphertext within a single clock operation. Conversely, stream cipher decryption consists of the rerunning of the cipher in the same state as encryption to produce the same keystream. The keystream is combined with the ciphertext using an inverse operation to produce the plaintext.
  • IV initialization vector
  • the input the cipher logic 230 is a secret key 232 which may, for example, be generated by CPU 110 during initial boot-up and retained until power off (when memory contents are no longer needed).
  • IN 220 is used in the encryption of plaintext and in the corresponding decryption of ciphertext, although IV 220 need not be kept secret in contrast to key 232, which must be kept in secret.
  • IV 220 need not be kept secret in contrast to key 232, which must be kept in secret.
  • unpredictable initialization vectors are required.
  • cipher logic 230 described herein requires an IV that is a ⁇ O ⁇ CE (i.e., the IV must be unique for each execution of the mode under the given key).
  • cipher logic 230 may function according to a counter mode (CTR) that features the application of forward cipher to a set of input blocks called counters to produce a sequence of output blocks that are logically combined (XOR) with the plaintext to produce the ciphertext and vice versa.
  • CTR counter mode
  • XOR logically combined
  • Generation of the unique IV is required since, if a plaintext block that is encrypted using a known IV value, then the output of the forward cipher function is easily determined from the associated ciphertext. This output allows easy recover of easy recovery of any other plaintext blocks that are encrypted using the same IV from their associated cipher blocks.
  • an encryption page structure 260 is provided.
  • encryption page structure 260 is designed to store one or more counters for each page as well as each data block within a memory system, such as memory 140 as illustrated in FIG. 1, which are stored in, for example, counter logic 290.
  • counter block 290 may include, for example, a page write counter for tracking the number of page writes (PWC) to a given page, as well as a current initialization vector value (INC).
  • PWC page write counter
  • IVC current initialization vector value
  • each page within the memory system may be assigned an array of V initialization vectors, which are formed using, for example, a random number generator (not shown).
  • IVs are stored within a data structure such as, for example, page IV (PIV) block 280 (280-1, . .
  • a page level table is used to store a reduced number of, for example, 64-bit random numbers ("page IVs") for use in the foraiation of initialization vectors for all cache blocks in a page.
  • an encrypted data block is requested from memory via, for example, external bus unit 104 (FIG. 2) according to address 210.
  • encryption page structure 260 is queried to identify a corresponding page within, for example, PIV 280.
  • an index to PIV 280 is provided via a data structure such as a block IV counter (BC) 270 (270-1, . . ., 270-N).
  • BC 270 stores, for example, a two-dimensional data structure including a PWC value, as well as an initialization vector index or IVC value.
  • initialization vector 220 includes a page address 212 and an N - C bit most significant bits (MSB) of block address 214, where N represents a bit length of the address, while C represents a bit length of block counter value 274.
  • P is a log2 (number of bytes in a page)
  • C is log2 (number of bytes in a cache block)
  • N is (P - C)
  • N is log2 (number of cache blocks in a page).
  • counter logic 290 includes, for example, a PWC value and a current IVC value for each page. Accordingly, in response to a write request of plaintext 204, a current IVC value is used to reference PIV 280 to generate a block IN value 282. In addition, a current PWC value is used as a block counter value 274. In one embodiment, the block IN value 282 and block counter value 274 are stored within BC 270 according to a block number of plaintext 204. [0043] In one embodiment, an ⁇ - C most significant bits of block address 214, as well as page address 212, complete formation of IN 220.
  • IN 220 is guaranteed to be unique for each iteration without the need for off-chip storage of INs. Accordingly, utilizing IN 220, the sfream cipher 250 generates keystream 252 using IN 220 as well as secret key 232. Once keystream 252 is generated, keystream 252 is combined with plaintext 204 using, for example, XOR logic 240 to form ciphertext 202. Once formed, ciphertext 202 may be provided to external bus unit 104 which writes the ciphertext to memory according to address 210. [0044] In a further embodiment, as illustrated with reference to FIG.
  • IN recode logic 300 is responsible for detecting whether an IV 220 of a data block is stale. In one embodiment, recode logic 300 is responsible for ensuring that a unique IV is generated for each write operation to prohibit unauthorized decryption of data. As a result, the amount of storage required for the page IVs may be limited to a constant value. In addition, the amount of extra reads and writes that are required for receding of data having a stale IV can be reduced by increasing the number (V) of page IVs.
  • this is performed by identifying a data block having the oldest or least recently used IV 220.
  • recode logic 330 may select a new IV 332 and recode (re-encrypt) the identified d to block using cipher logic 230 and cipher logic 250 to form ciphertext 202.
  • new IV 332 is generated by replacing a page IV portion of the stale IV with a different page IV from PIV 280 according to a current value of IVC 272 for the page containing the identified data block.
  • block cipher 230 (FIG.
  • recoding of data having a stale IV can be performed by a software or microcode interrupt routine by having recode logic 330 raise an exception when recode is required. Accordingly, the recode logic could be simplified to performing the detection of data having a stale IV and the issuance of an interrupt. In one embodiment, data recodes are spread out over time, such that at most one recode is performed per write operation.
  • recoding may be scheduled in an empty slot in the memory pipeline. Accordingly, by using the reduced number of page initialization vectors in conjunction with the recode logic 330, the amount of space required for storage of IV values is very small when compared to the storage requirements of data and therefore enables on-chip storage of IVs such that an additional read operation of off-chip IVs is not required to achieve substantial system security.
  • stale IV 220 is provided to cipher logic 230 to decrypt ciphertext 202 to produce plaintext 204.
  • new IV 332 is provided to cipher logic 250 to produce keystream 254 for re-encrypting plaintext 204.
  • recode logic 330 provides additional security features by preventing prediction of IV 220.
  • BC [PWC] (IVC + 1) mod V (1)
  • FIG. 6 is a flowchart illustrating a method 400 for decryption of an encrypted memory block with reduced decryption latency, in accordance with one embodiment of the invention.
  • method 400 is performed, for example, within encryption decryption logic 200, as shown in FIG. 3.
  • an encrypted data block (ciphertext) is read from memory, for example, in response to a request for the encrypted data block.
  • the memory described is, for example, RAM or non-volatile memory.
  • the memory is referred to as disk memory within, for example, HDD 150 of FIG. 1.
  • computer systems exhibit a significant amount of memory latency between a processor and the memory system. This latency prohibits conventional computer systems from providing processor memory encryption.
  • a keystream is regenerated during reading of the encrypted data block and, as a result, introduces minimal latency into the memory read operation.
  • the regenerated keystream is the keystream that was used to encrypt the data block prior to writing the data block to memory.
  • the keystream is regenerated according to one or more stored criteria of the data block, as described in detail below.
  • the encrypted data block is decrypted according to the generated keystream. In one embodiment, this is performed using a logical XOR operation and may be performed within a single clock cycle, thereby limiting introduced latency to a single clock cycle. As a result, memory latency between processor and memory is not exacerbated by the memory encryption techniques described herein.
  • FIG. 7 is a flowchart illustrating a method 410 for regenerating the keystream of process block 404, as described with reference to FIG. 6 and in accordance with one embodiment of the invention.
  • an initial portion (page IV) of an initialization vector used to encrypt the data block is identified according to a page containing the encrypted data block.
  • the page in conjunction with a block number provides an index to a data structure containing a plurality of initialization vectors (page IVs), such as PIV 280 (FIG. 3).
  • PIV 280 FIG. 3
  • FIG. 8 is a flowchart illustrating a method 420 for recomputing the keystream of process block 416 of FIG. 7, in accordance with a further embodiment of the invention.
  • a stored page initialization vector is selected according to a page containing the encrypted data block.
  • a stored C-bit counter value is selected according to a block number of the encrypted data block. In one embodiment, these values are stored in, for example, encryption page structure 260, as depicted with reference to FIGS. 2-5.
  • the initialization vector used to encrypt the data block is formed according to the page initialization vector value, the C-bit counter value and a (N - C) most significant bits of an address of the encrypted data block.
  • the address is an N-bit value
  • the counter is a C-bit value. Accordingly, as described, for example, with reference to FIG.
  • the initialization vector, or IN 220 is formed according to the indicated values.
  • the formed initialization vector is encrypted using the secret key to form the keystream.
  • a block cipher may be used to form the keystream value during the decryption portion of the embodiments described.
  • the block cipher is a federal information processing (FIPS) symmetric key block cipher algorithm operated according to a counter mode (CTR).
  • FIPS federal information processing
  • CTR counter mode
  • FIG. 9 is a flowchart illustrating a method 500 for encryption of a data block prior to storing the data block within memory, in accordance with one embodiment of the invention.
  • method 500 is illustrated with reference to encryption/decryption logic 200 of FIG. 4.
  • an initialization vector is computed for a data block according to one or more criteria of the data block.
  • the criteria may include an address of the data block, such as a page containing the data block and the block number of the data block.
  • additional criteria may include, for example, one or more counter values according to the data block.
  • the criteria used to for the initialization vector is stored.
  • the criteria is stored within, for example, encryption page structure 260 (FIG. 4) to enable recomput3tion of the initialization vector.
  • a keystream is computed from the initialization vector and a secret key using, for example, stream cipher 250 (FIG. 4).
  • the data block is encrypted according to the keystream using, for example, an XOR operation.
  • the encrypted data block is stored within memory, which includes non-volatile memory, disk memory, or the like as described above.
  • FIG. 10 is a flowchart illustrating a method 510 for computing the initialization vector of process block 502 of FIG. 9, in accordance with one embodiment of the invention.
  • it is determined whether a write request is received.
  • a page containing the requested data block and a block number of the requested data block are identified.
  • a page initialization vector is formed according to the page containing the data block.
  • a block initialization vector is formed according to the block number of the data block.
  • the page initialization vector and the block initialization vector are combined to form the initialization vector used to encrypt the data block.
  • FIG. 11 is a flowchart illustrating a method 530 for combining to form the initialization vector of process block 520 of FIG. 10, in accordance with one embodiment of the invention.
  • a stored page initialization vector value is selected according to a page containing the encrypted data block and optionally a block number of the data block.
  • a stored C-bit counter value is selected according to a block number of the encrypted data block.
  • the initialization vector is formed according to the page initialization vector value, the C-bit counter value and an N - C most significant bit of an address of the encrypted data block.
  • 128-bit encryption is provided for encryption of the data block.
  • the initialization vector is encrypted using the secret key to form the keystream.
  • enciyption of the initialization vector using the keystream is performed, for example, using a stream cipher, such as for example, cipher logic 250 as described with reference to FIG. 4.
  • a block cipher may be used to perform encryption during memory read back whereas a stream cipher may be used to form a keystream during writing and encrypting of a data block in accordance with the embodiments described.
  • FIG. 12 is ⁇ flowchart illustrating a method 550 for storing the criteria used to form initialization vector of process block 540 of FIG. 9, in accordance with one embodiment of the invention.
  • a page counter value used to select a page IV portion of the initialization vector is identified.
  • a block counter value used to form a block IV portion of the initialization vector is identified.
  • the page counter value and the block counter value are stored within an encryption page structure according to a block number of the data block.
  • FIG. 13 is a flowchart illustrating a method 570 for recoding of an initialization vector, for example, as depicted with reference to FIG. 5 in accordance with a further embodiment of the invention.
  • a data block having a least recent initialization vector is identified.
  • the identification of the data block is performed using Equation (1).
  • the identified initialization vector is replaced with a current initialization vector.
  • the current initialization vector is formed by replacing a page IV portion of the stale IV with a current page IV of PIV 280 indexed by a current value of IVC.
  • the identified data block is re-encrypted according to a keystream generated from the current initialization vector and a secret key.
  • FIG. 14 is a block diagram illustrating various representations or formats for simulation, emulation and fabrication of a design using the disclosed techniques.
  • Data representing a design may represent the design in a number of manners.
  • the hardware may be represented using a hardware description language, or another functional description language, which essentially provides a computerized model of how the designed hardware is expected to perform.
  • the hardware model 610 may be stored in a storage medium 600, such as a computer memory, so that the model may be simulated using simulation software 620 that applies a particular test suite 630 to the hardware model to determine if it indeed functions as intended.
  • the simulation software is not recorded, captured or contained in the medium.
  • a circuit level model with logic and/or transistor gates may be produced at some stages of the design process.
  • the model may be similarly simulated some times by dedicated hardware simulators that form the model using programmable logic. This type of simulation taken a degree further may be an emulation technique.
  • reconfigurable hardware is another embodiment that may involve a machine readable medium storing a model employing the disclosed techniques.
  • most designs at some stage reach a level of data representing the physical placements of various devices in the hardware model.
  • the data representing the hardware model may be data specifying the presence or absence of various features on different mask layers or masks used to produce the integrated circuit. Again, this data representing the integrated circuit embodies the techniques disclosed in that the circuitry logic and the data can be simulated or fabricated to perform these techniques.
  • the data may be stored in any form of a machine readable medium.
  • An optical or electrical wave 660 modulated or otherwise generated to transport such information, a memory 650 or a magnetic or optical storage 640, such as a disk, may be the machine readable medium. Any of these mediums may carry the design information.
  • the term "carry” e.g., a machine readable medium carrying information
  • the set of bits describing the design or a particular of the design are (when embodied in a machine readable medium, such as a carrier or storage medium) an article that may be sealed in and out of itself, or used by others for further design or fabrication.
  • Alternate Embodiments It will be appreciated that, for other embodiments, a different system configuration may be used. For example, while the system 100 includes a single CPU
  • a multiprocessor system (where one or more processors may be similar in configuration and operation to the CPU 110 described above) may benefit from the data bus power control approach of various embodiments.
  • Further different type of system or different type of computer system such as, for example, a server, a workstation, a desktop computer system, a gaming system, an embedded computer system, a blade server, etc., may be used for other embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Storage Device Security (AREA)

Abstract

A method and apparatus for memory encryption with reduced decryption latency. In one embodiment, the method includes reading an encrypted data block from memory. During reading of the encrypted data block, a keystream used to encrypt the data block is regenerated according to one or more stored criteria of the encrypted data block. Once the encrypted data block is read, the encrypted data block is decrypted using the regenerated keystream. Accordingly, in one embodiment, encryption of either random access memory (RAM) or disk memory is performed. A keystream is regenerated during data retrieval such that once the data is received, the data may be decrypted using a single clock operation. As a result, memory encryption is performed without exacerbating memory latency between the processor and memory.

Description

AN APPARATUS AND METHOD FOR MEMORY ENCRYPTION WITH REDUCED DECRYPTION LATENCY FIELD OF THE INVENTION [0001] One or more embodiments of the invention relate generally to the field of cryptography. More particularly, one or more of the embodiments of the invention relates to a method and apparatus for memory encryption with reduced decryption latency.
BACKGROUND OF THE INVENTION [0002] The proliferation of the Internet has led to the creation of a new form of commerce, generally referred to as Internet commerce or E-commerce. E-commerce enables the users to sell and purchase items from a worldwide community connected via the Internet. This added simplicity, coupled with the continually reduced costs and increasing processing speed of modern-day computers, has led to the inclusion of a personal computer (PC) in many homes throughout the world. Unfortunately, the proliferation of PCs within the homes throughout the world, as well as the use of such PCs for E-commerce, often results in the storage of sensitive information within a computer. [0003] As a result, computer users become susceptible to rogue agents, which may desire to gain access to secure information loaded within a personal computer. In order to combat the various rogue agents from gaming access to the secure information, many computer systems employ some form of cryptographs in order to prevent access to sensitive information. As known to those skilled in the art, cryptography provides a technique for keeping information secret, for determining that the information has not been tampered with and for determining who authored pieces of information. [0004] One form of cryptography involves public or private key systems wherein transmitted information is encrypted prior to transmission and decrypted by the receiver using either a public or private key. However, once the sensitive information arrives at its designated location, the information is often decrypted and stored. In other words, the sensitive information is not maintained in a secure format at its destination. As a result, during operation of a PC, a rogue agent could possibly gain access to the PC and gain access to the sensitive information. [0005] Furthermore, the proliferation of E-commerce has led to the availability of media applications, such as motion pictures and music, which may be downloaded to a PC for one-time use or for use for a predetermined period of time. Unfortunately, without some mechanism for protecting the contents of such media applications from access by rogue agents, E-commerce with regard to media applications may be prohibitive to the media providers. One technique for possibly protecting the sensitive information of a computer system is memory encryption. Unfortunately, memory encryption is currently not performed within modern computer systems due to the bottleneck that currently exists between processors and memory.
[0006] Although processor speeds continually increase in response to the growing demands of media and graphics applications, memory performance increases have not kept pace with the reduction in processor clock periods. The problems of memory latency, or the time required to access a data unit, in addition with the increasing bandwidth of such media and graphics applications, require innovative memory architectures if processor performance is to continue to increase. As a result, performing memory encryption by, for example a microprocessor, is not feasible because the memory encryption in read operations would introduce additional latency beyond the current bottleneck that exists between processors and memory.
BRIEF DESCRIPTION OF THE DRAWINGS [0007] The various embodiments of the present invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
[0008] FIG. 1 is a block diagram illustrating a computer system including a processor having memory encryption/decryption logic to enable memory encryption with reduced decryption latency, in accordance with one embodiment of the invention. [0009] FIG. 2 is a block diagram further illustrating the processor, as depicted in FIG. 1, in accordance with a further embodiment of the invention.
[0010] FIG. 3 is a block diagram further illustrating the processor, memory encryption/decryption logic, and encryption page structure, as depicted in FIG. 2, in accordance with a further embodiment of the invention. [0011] FIG. 4 is a block diagram further illustrating the processor, the memory encryption/deciyption logic, and the encryption page structure, as depicted in FIG. 2, in accordance with a further embodiment of the invention. [0012] FIG. 5 is a block diagram illustrating initialization vector recode logic, in accordance with one embodiment of the invention.
[0013] FIG. 6 is a flowchart illustrating a method for decryption of an encrypted data block read from memory, in accordance with one embodiment of the invention. [0014] FIG. 7 is a flowchart illustrating a method for generating a keystream to decrypt an encrypted data block read from memory, in accordance with a further embodiment of the invention.
[0015] FIG. 8 is a flowchart illustrating a method for generating a keystream to decrypt an encrypted data block read from memory, in accordance with one embodiment of the invention.
[0016] FIG. 9 is a flowchart illustrating a method for encrypting a data block prior to writing the data block to memory, in accordance with one embodiment of the invention.
[0017] FIG. 10 is a flowchart illustrating a method for computing an initialization vector to enable formation of a keystream to encrypt a data block prior to writing the data block to memory, in accordance with one embodiment of the invention.
[0018] FIG. 11 is a flowchart illustrating a method for computing an initialization vector to enable formation of a keystream to encrypt a data block prior to writing the data block to memory, in accordance with a further embodiment of the invention.
[0019] FIG. 12 is a flowchart illustrating a method for storing components of an initialization vector to enable reformation of the initialization vector to decrypt an encrypted data block, in accordance with one embodiment of the invention.
[0020] FIG. 13 is a flowchart illustrating a method for receding an initialization vector, in accordance with one embodiment of the invention.
[0021] FIG. 14 is a block diagram illustrating various design representations or formats for simulation, emulation and fabrication of a design using the disclosed techniques.
DETAILED DESCRIPTION [0022] A method and apparatus for memory encryption with reduced decryption latency are described. In one embodiment, the method includes reading an encrypted data block from memory. During reading of the encrypted data block, a keystream used to encrypt the data block is regenerated according to one or more stored criteria of the encrypted data block. Once the encrypted data block is read, the encrypted data block is decrypted using the regenerated keystream. Accordingly, in one embodiment, encryption of either random access memory (RAM) or disk memory is performed. A keystream is regenerated during data retrieval such that once the data is received, the data may be decrypted using a single clock operation. As a result, memory encryption is performed without exacerbating memory latency between the processor and memory.
[0023] In the following description, certain terminology is used to describe features of embodiments of the invention. For example, the term "logic" is representative of hardware and or software configured to perform one or more functions. For instance, examples of "hardware" include, but are not limited or restricted to, an integrated circuit, a finite state machine or even combinatorial logical. The integrated circuit may take the form of a processor such as a microprocessor, application specific integrated circuit, a digital signal processor, a micro-controller, or the like.
[0024] An example of "software" includes executable code in the form of an application, an applet, a routine or even a series of instructions. The software may be stored in any type of computer or machine readable medium such as a programmable electronic circuit, a semiconductor memory device inclusive of volatile memory (e.g., random access memory, etc.) and/or non- volatile memory (e.g., any type of read-only memory "ROM," flash memoiy), a floppy diskette, an optical disk (e.g., compact disk or digital video disk "DVD"), a hard drive disk, tape, or the like. In one embodiment, the present invention may be provided as an article of manufacture which may include a machine or computer-readable medium having stored thereon instructions which may be used to program a computer (or other electronic devices) to perform a process according to one embodiment of the present invention. System [0025] FIG. 1 is a block diagram illustrating a computer system 100 including memory encryption/decryption logic 200, in accordance with one embodiment of the invention. Computer system 100 comprises a processor system bus (front side bus (FSB)) 102 for communicating information between a processor (CPU) 110 and a chipset 180, coupled together via FSB 102. As described herein, the term "chipset" is used in a manner well-known to those of ordinary skill in the art to describe, collectively, the various devices coupled to CPU 110 to perform desired system functionality. [0026] Chipset 180 is coupled to main memory 140 and one or more graphic devices 130. In one embodiment, main memory 110 is volatile memory including, but not limited to, random access memory (RAM), synchronous RAM (SRAM), double data rate (DDR), S Data RAM (SDRAM), RAM bus data RAM (RDRAM), or the like. In addition, hard disk drive devices (HDD) 150, as well as one or more input/output (I/O) devices 170 (170-1, , . . ,170-N) are also coupled to chipset 180. As illustrated, CPU 110 includes memory encryption/decryption logic 200, which is further described with reference to FIG. 2.
[0027] FIG. 2 further illustrates CPU 110, to illustrate memory encryption with reduced decryption latency, in accordance with one embodiment of the invention. CPU 110 is comprised of processor core 112, which may include, for example, copyback cache 130, as well as level one (LI) cache 114 for high speed temporary storage of data. In addition, processor or CPU 110 may include level two (L2) cache 120. As illustrated, L2 cache 120 is offchip memoiy coupled to backside bus unit 116 via, for example, backside bus 118. Likewise, CPU 110 includes external unit 104 for interfacing with FSB 102, as depicted in FIG. 1. [0028] However, in contrast to conventional CPUs, CPU 110 includes memory encryption/decryption logic 200. In one embodiment, logic 200 enables CPU 110 to securely encrypt contents of, for example, volatile memory, such as, for example, main memory 140, as depicted in FIG. 1 using a cipher algorithm. The security provided by a block cipher algorithm consists of two processes that are inverses of each other: encryption and decryption. Encryption is the transformation of a usable message called plaintext into an unreadable form called ciphertext. Conversely, decryption is the transformation that recovers the plaintext from the ciphertext. [0029] In one embodiment, memory decryption is provided by performing keystream regeneration during a memory read of an encrypted data block (ciphertext). Once the ciphertext is available, the ciphertext is decrypted using the regenerated keystream, within, for example, a single clock cycle. As a result, inherent memory latency between a processor and main memory is minimally exacerbated while enabling encryption of data contained within, for example, RAM, disk memory or the like. Encryption/decryption logic 200, as well as encryption page structure 250 are further illustrated with reference to FIG. 3, in accordance with one embodiment of the invention. [0030] FIG. 3 illustrates logic 200 in an embodiment for a memory read decryption operation, in accordance with one embodiment of the invention. As illustrated logic 200 includes cipher logic 230 to generate a keystream 234 according to a secret key 232, as well as an initialization vector (IN) 220. Once the keystream is formed, logic 200 performs a logical exclusive OR operation (XOR) of keystream 234 with ciphertext 202, using XOR block 240. to form plaintext 204. In one embodiment, cipher logic 230 is, for example, advanced encryption standard (AES), cipher serpent or other like symmetric block cipher algorithm.
[0031] There are two basic types of symmetric encryption/decryption algorithms: block ciphers and stream ciphers. Block ciphers operate on blocks of plaintext and ciphertext comprised, for example, of Ν-bits. In contrast, stream ciphers operate on streams of plaintext and ciphertext, one bit or byte at a time. With a block cipher, the same plaintext block always encrypts to the same ciphertext block using the same key. In contrast, the same plaintext byte or bit will encrypt to a different bit or byte each time the plaintext is encrypted when using a stream cipher. This discrepancy arises since a block cipher takes a secret key and a plaintext value and runs through many rounds of the cipher to produce the ciphertext directly. [0032] Conversely, block cipher decryption takes the same key and the ciphertext and runs through many rounds of an inverse cipher to produce plaintext. Generally, the many rounds of a cipher performed in both of the cases takes up a substantial amount of time and are thus unsuitable for memory read decryption due to the inherent latency between processor and memory. Accordingly, in the embodiment depicted, cipher logic 230 uses a reduced number of rounds to match the memory read latency while still providing adequate security. In other words, a block cipher that supports an encryption mode for generating a keystream within the time required to fetch data from memory is used as cipher logic 230. In an alternative embodiment, a stream cipher may be used for cipher logic 230. [0033] As known to those skilled in the art, a stream cipher uses a secret key and possibly an initialization vector (IV) or public value that may change and runs some function to produce a keystream. Once the keystream is generated, the keystream is combined with the plaintext to produce the ciphertext within a single clock operation. Conversely, stream cipher decryption consists of the rerunning of the cipher in the same state as encryption to produce the same keystream. The keystream is combined with the ciphertext using an inverse operation to produce the plaintext.
[0034] Referring again to FIG. 3, the input the cipher logic 230 is a secret key 232 which may, for example, be generated by CPU 110 during initial boot-up and retained until power off (when memory contents are no longer needed). IN 220 is used in the encryption of plaintext and in the corresponding decryption of ciphertext, although IV 220 need not be kept secret in contrast to key 232, which must be kept in secret. In order to efficiently use cipher logic 230 to provide optimal security, unpredictable initialization vectors are required. In other words, cipher logic 230 described herein requires an IV that is a ΝOΝCE (i.e., the IV must be unique for each execution of the mode under the given key).
[0035] In one embodiment, cipher logic 230 may function according to a counter mode (CTR) that features the application of forward cipher to a set of input blocks called counters to produce a sequence of output blocks that are logically combined (XOR) with the plaintext to produce the ciphertext and vice versa. Generation of the unique IV is required since, if a plaintext block that is encrypted using a known IV value, then the output of the forward cipher function is easily determined from the associated ciphertext. This output allows easy recover of easy recovery of any other plaintext blocks that are encrypted using the same IV from their associated cipher blocks. As such, in order to generate unique IVs, in one embodiment, an encryption page structure 260 is provided. [0036] As illustrated in FIG. 3, encryption page structure 260 is designed to store one or more counters for each page as well as each data block within a memory system, such as memory 140 as illustrated in FIG. 1, which are stored in, for example, counter logic 290. In the embodiment illustrated, counter block 290 may include, for example, a page write counter for tracking the number of page writes (PWC) to a given page, as well as a current initialization vector value (INC). In embodiments which use a current initialization vector value IVC, each page within the memory system may be assigned an array of V initialization vectors, which are formed using, for example, a random number generator (not shown). In such an embodiment, IVs are stored within a data structure such as, for example, page IV (PIV) block 280 (280-1, . . ., 280-Ν), which includes a predetermined number of unique values for each page to enable generation of unique IVs for each execution. [0037] As indicated above, generation of a unique IV is required to provide optimal security and prevent the prediction of initialization vectors. One technique for generating an IV that is unique for each execution is the generation of a new IV for each memory write. Unfortunately, IVs can take up to 50-100 percent as much space as the original data depending on the relative size of the IVs with reference to the cache block size. As a result, due to the space constraints caused by generating a new IV for each write, the new IVs could not be stored on-chip in temporary memory (cache memory). [0038] Consequently, for each read operation from memory, a separate read would have to be performed to locate the off-chip IV used to encrypt the data. As a result, this separate read operation must be performed before the keystream can be generated to decrypt data read from encrypted memory. Unfortunately, this separate read would further exacerbate the latency that already exists between processor and memory and therefore is not an adequate solution. [0039] As such, in one embodiment, a page level table is used to store a reduced number of, for example, 64-bit random numbers ("page IVs") for use in the foraiation of initialization vectors for all cache blocks in a page. Therefore, by using a reduced number of 64-bit page IVs, the 64-bit page IVs are used to form a unique IV for each write, while providing storage of the page IVs within on-chip memory, and eliminating the additional read as described above. [0040] Accordingly, in response to a memory read operation, an encrypted data block is requested from memory via, for example, external bus unit 104 (FIG. 2) according to address 210. Based on, for example, the page address, encryption page structure 260 is queried to identify a corresponding page within, for example, PIV 280. In addition, an index to PIV 280 is provided via a data structure such as a block IV counter (BC) 270 (270-1, . . ., 270-N). In one embodiment, BC 270 stores, for example, a two-dimensional data structure including a PWC value, as well as an initialization vector index or IVC value.
[0041] Accordingly, based on the page address as well as the block address, BC
270 provides an index to PIV 280 to provide block IV value 282, as well as a block counter value 274, stored during encryption of plaintext 204, to form IV 220. In a further embodiment, initialization vector 220 includes a page address 212 and an N - C bit most significant bits (MSB) of block address 214, where N represents a bit length of the address, while C represents a bit length of block counter value 274. In one embodiment, P is a log2 (number of bytes in a page), C is log2 (number of bytes in a cache block), N is (P - C), or N is log2 (number of cache blocks in a page). Based on this information, a unique IV 220 is formed provided to cipher logic 230 to generate keystream 234. [0042] As illustrated in FIG. 4, counter logic 290 includes, for example, a PWC value and a current IVC value for each page. Accordingly, in response to a write request of plaintext 204, a current IVC value is used to reference PIV 280 to generate a block IN value 282. In addition, a current PWC value is used as a block counter value 274. In one embodiment, the block IN value 282 and block counter value 274 are stored within BC 270 according to a block number of plaintext 204. [0043] In one embodiment, an Ν - C most significant bits of block address 214, as well as page address 212, complete formation of IN 220. As such, using the counter values in conjunction with reuse of a page initialization vector, IN 220 is guaranteed to be unique for each iteration without the need for off-chip storage of INs. Accordingly, utilizing IN 220, the sfream cipher 250 generates keystream 252 using IN 220 as well as secret key 232. Once keystream 252 is generated, keystream 252 is combined with plaintext 204 using, for example, XOR logic 240 to form ciphertext 202. Once formed, ciphertext 202 may be provided to external bus unit 104 which writes the ciphertext to memory according to address 210. [0044] In a further embodiment, as illustrated with reference to FIG. 5, IN recode logic 300 is responsible for detecting whether an IV 220 of a data block is stale. In one embodiment, recode logic 300 is responsible for ensuring that a unique IV is generated for each write operation to prohibit unauthorized decryption of data. As a result, the amount of storage required for the page IVs may be limited to a constant value. In addition, the amount of extra reads and writes that are required for receding of data having a stale IV can be reduced by increasing the number (V) of page IVs.
[0045] In one embodiment, this is performed by identifying a data block having the oldest or least recently used IV 220. When such is detected, using for example stale IV logic 320, recode logic 330 may select a new IV 332 and recode (re-encrypt) the identified d to block using cipher logic 230 and cipher logic 250 to form ciphertext 202. In one embodiment, new IV 332 is generated by replacing a page IV portion of the stale IV with a different page IV from PIV 280 according to a current value of IVC 272 for the page containing the identified data block. In one embodiment, block cipher 230 (FIG. 5) is another instance of stream cipher 250, such that the same stream cipher is to decrypt and re-encrypt). [0046] In one embodiment, recoding of data having a stale IV can be performed by a software or microcode interrupt routine by having recode logic 330 raise an exception when recode is required. Accordingly, the recode logic could be simplified to performing the detection of data having a stale IV and the issuance of an interrupt. In one embodiment, data recodes are spread out over time, such that at most one recode is performed per write operation.
[0047] In an alternative embodiment, recoding may be scheduled in an empty slot in the memory pipeline. Accordingly, by using the reduced number of page initialization vectors in conjunction with the recode logic 330, the amount of space required for storage of IV values is very small when compared to the storage requirements of data and therefore enables on-chip storage of IVs such that an additional read operation of off-chip IVs is not required to achieve substantial system security. [0048] Accordingly, stale IV 220 is provided to cipher logic 230 to decrypt ciphertext 202 to produce plaintext 204. Concurrently, new IV 332 is provided to cipher logic 250 to produce keystream 254 for re-encrypting plaintext 204. Accordingly, recode logic 330 provides additional security features by preventing prediction of IV 220. In one embodiment, this is performed using the following equation within stale IV logic 320: BC [PWC] = (IVC + 1) mod V (1) [0049] As a result, the embodiments described preserve the performance and security properties of the cipher logic by generating new initialization vectors for each write while minimizing additional storage requirements for initialization vectors by recoding old data so old initialization vectors do not need to be retained. Procedural methods for implementing embodiments of the invention are now described. Operation
[0050] FIG. 6 is a flowchart illustrating a method 400 for decryption of an encrypted memory block with reduced decryption latency, in accordance with one embodiment of the invention. In one embodiment, method 400 is performed, for example, within encryption decryption logic 200, as shown in FIG. 3. At process block 402, an encrypted data block (ciphertext) is read from memory, for example, in response to a request for the encrypted data block. In one embodiment, the memory described is, for example, RAM or non-volatile memory. Alternatively, the memory is referred to as disk memory within, for example, HDD 150 of FIG. 1. [0051] As known to those skilled in the art, computer systems exhibit a significant amount of memory latency between a processor and the memory system. This latency prohibits conventional computer systems from providing processor memory encryption.
However, in contrast to conventional systems, at process block 404, a keystream is regenerated during reading of the encrypted data block and, as a result, introduces minimal latency into the memory read operation. The regenerated keystream is the keystream that was used to encrypt the data block prior to writing the data block to memory. [0052] In one embodiment, the keystream is regenerated according to one or more stored criteria of the data block, as described in detail below. Accordingly, at process block 430, once reading of the encrypted data block is complete, at process block 440, the encrypted data block is decrypted according to the generated keystream. In one embodiment, this is performed using a logical XOR operation and may be performed within a single clock cycle, thereby limiting introduced latency to a single clock cycle. As a result, memory latency between processor and memory is not exacerbated by the memory encryption techniques described herein.
[0053] FIG. 7 is a flowchart illustrating a method 410 for regenerating the keystream of process block 404, as described with reference to FIG. 6 and in accordance with one embodiment of the invention. At process block 412, an initial portion (page IV) of an initialization vector used to encrypt the data block is identified according to a page containing the encrypted data block. In one embodiment, the page in conjunction with a block number provides an index to a data structure containing a plurality of initialization vectors (page IVs), such as PIV 280 (FIG. 3). As described, a paging system for accessing data blocks from memory is assumed within the embodiments described. However, the embodiments described may be applied to other forms of memory organization, as known to those skilled in the art.
[0054] At process block 414, a remaining portion of the initialization vector used to encrypt the data block is identified according to a block number of the data block such as, for example, a block counter value. At process block 416, a keystream is computed according to the identified initial portion of the initialization vector and the identified remaining portion of the initialization vector, as well as a secret key. As such, in the embodiments described, the initialization vector is made public or can be made public without jeopardizing the security of the memory encryption decryption described herein. [0055] FIG. 8 is a flowchart illustrating a method 420 for recomputing the keystream of process block 416 of FIG. 7, in accordance with a further embodiment of the invention. At process block 422, a stored page initialization vector is selected according to a page containing the encrypted data block. Once selected, at process block 424, a stored C-bit counter value is selected according to a block number of the encrypted data block. In one embodiment, these values are stored in, for example, encryption page structure 260, as depicted with reference to FIGS. 2-5. At process block 426, the initialization vector used to encrypt the data block is formed according to the page initialization vector value, the C-bit counter value and a (N - C) most significant bits of an address of the encrypted data block. [0056] As described, the address is an N-bit value, whereas the counter is a C-bit value. Accordingly, as described, for example, with reference to FIG. 3, the initialization vector, or IN 220 is formed according to the indicated values. At process block 428, the formed initialization vector is encrypted using the secret key to form the keystream. As such, in the embodiment described, a block cipher may be used to form the keystream value during the decryption portion of the embodiments described. In one embodiment, the block cipher is a federal information processing (FIPS) symmetric key block cipher algorithm operated according to a counter mode (CTR).
[0057] FIG. 9 is a flowchart illustrating a method 500 for encryption of a data block prior to storing the data block within memory, in accordance with one embodiment of the invention. In the embodiment described, method 500 is illustrated with reference to encryption/decryption logic 200 of FIG. 4. At process block 502, an initialization vector is computed for a data block according to one or more criteria of the data block. In the embodiments described, the criteria may include an address of the data block, such as a page containing the data block and the block number of the data block. In addition, additional criteria may include, for example, one or more counter values according to the data block.
[0058] At process block 540, the criteria used to for the initialization vector is stored. In one embodiment, the criteria is stored within, for example, encryption page structure 260 (FIG. 4) to enable recomput3tion of the initialization vector. At process block 560, a keystream is computed from the initialization vector and a secret key using, for example, stream cipher 250 (FIG. 4). At process block 562, the data block is encrypted according to the keystream using, for example, an XOR operation. At process block 564, the encrypted data block is stored within memory, which includes non-volatile memory, disk memory, or the like as described above. [0059] FIG. 10 is a flowchart illustrating a method 510 for computing the initialization vector of process block 502 of FIG. 9, in accordance with one embodiment of the invention. At process block 512, it is determined whether a write request is received.
Once received, at process block 514, a page containing the requested data block and a block number of the requested data block are identified. At process block 516, a page initialization vector is formed according to the page containing the data block. At process block 518, a block initialization vector is formed according to the block number of the data block. At process block 520, the page initialization vector and the block initialization vector are combined to form the initialization vector used to encrypt the data block.
[0060] FIG. 11 is a flowchart illustrating a method 530 for combining to form the initialization vector of process block 520 of FIG. 10, in accordance with one embodiment of the invention. At process block 532, a stored page initialization vector value is selected according to a page containing the encrypted data block and optionally a block number of the data block. At process block 534, a stored C-bit counter value is selected according to a block number of the encrypted data block. At process block 536, the initialization vector is formed according to the page initialization vector value, the C-bit counter value and an N - C most significant bit of an address of the encrypted data block. [0061] As such, in the embodiment described, 128-bit encryption is provided for encryption of the data block. However, various N-bit encryption may be provided such that values may be added or subtracted from the initialization vector as desired. At process block 538, the initialization vector is encrypted using the secret key to form the keystream. In the embodiment described, enciyption of the initialization vector using the keystream is performed, for example, using a stream cipher, such as for example, cipher logic 250 as described with reference to FIG. 4. As such, in the embodiments described, a block cipher may be used to perform encryption during memory read back whereas a stream cipher may be used to form a keystream during writing and encrypting of a data block in accordance with the embodiments described. [0062] FIG. 12 is ø flowchart illustrating a method 550 for storing the criteria used to form initialization vector of process block 540 of FIG. 9, in accordance with one embodiment of the invention. At process block 552, a page counter value used to select a page IV portion of the initialization vector is identified. Once identified, at process block 554, a block counter value used to form a block IV portion of the initialization vector is identified. Once identified, the page counter value and the block counter value are stored within an encryption page structure according to a block number of the data block.
[0063] FIG. 13 is a flowchart illustrating a method 570 for recoding of an initialization vector, for example, as depicted with reference to FIG. 5 in accordance with a further embodiment of the invention. At process block 572, a data block having a least recent initialization vector is identified. In one embodiment, the identification of the data block is performed using Equation (1). Once identified, at process block 574, the identified initialization vector is replaced with a current initialization vector. In one embodiment, the current initialization vector is formed by replacing a page IV portion of the stale IV with a current page IV of PIV 280 indexed by a current value of IVC. Once replaced, the identified data block is re-encrypted according to a keystream generated from the current initialization vector and a secret key.
[0064] FIG. 14 is a block diagram illustrating various representations or formats for simulation, emulation and fabrication of a design using the disclosed techniques. Data representing a design may represent the design in a number of manners. First, as is useful in simulations, the hardware may be represented using a hardware description language, or another functional description language, which essentially provides a computerized model of how the designed hardware is expected to perform. The hardware model 610 may be stored in a storage medium 600, such as a computer memory, so that the model may be simulated using simulation software 620 that applies a particular test suite 630 to the hardware model to determine if it indeed functions as intended. In some embodiments, the simulation software is not recorded, captured or contained in the medium. [0065] Additionally, a circuit level model with logic and/or transistor gates may be produced at some stages of the design process. The model may be similarly simulated some times by dedicated hardware simulators that form the model using programmable logic. This type of simulation taken a degree further may be an emulation technique. In any case, reconfigurable hardware is another embodiment that may involve a machine readable medium storing a model employing the disclosed techniques. [0066] Furthermore, most designs at some stage reach a level of data representing the physical placements of various devices in the hardware model. In the case where conventional semiconductor fabrication techniques are used, the data representing the hardware model may be data specifying the presence or absence of various features on different mask layers or masks used to produce the integrated circuit. Again, this data representing the integrated circuit embodies the techniques disclosed in that the circuitry logic and the data can be simulated or fabricated to perform these techniques.
[0067] In any representation of the design, the data may be stored in any form of a machine readable medium. An optical or electrical wave 660 modulated or otherwise generated to transport such information, a memory 650 or a magnetic or optical storage 640, such as a disk, may be the machine readable medium. Any of these mediums may carry the design information. The term "carry" (e.g., a machine readable medium carrying information) thus covers information stored on a storage device or information encoded or modulated into or onto a carrier wave. The set of bits describing the design or a particular of the design are (when embodied in a machine readable medium, such as a carrier or storage medium) an article that may be sealed in and out of itself, or used by others for further design or fabrication. Alternate Embodiments [0068] It will be appreciated that, for other embodiments, a different system configuration may be used. For example, while the system 100 includes a single CPU
110, for other embodiments, a multiprocessor system (where one or more processors may be similar in configuration and operation to the CPU 110 described above) may benefit from the data bus power control approach of various embodiments. Further different type of system or different type of computer system such as, for example, a server, a workstation, a desktop computer system, a gaming system, an embedded computer system, a blade server, etc., may be used for other embodiments. [0069] Having disclosed exemplary embodiments and the best mode, modifications and variations may be made to the disclosed embodiments while remaining within the scope of the embodiments of the invention as defined by the following claims.

Claims

CLAIMS What is claimed is: 1. A method comprising: reading an encrypted data block from memory; regenerating, during reading of the encrypted data block, a keystream used to encrypt the data block according to one or more stored criteria of the data block; and once reading of the encrypted data block is complete, decrypting the encrypted data block according to the generated keystream.
2. The method of claim 1 , wherein reading the encrypted data block comprises: receiving a request for the encrypted data block; and reading the encrypted data block from a random access memory.
3. The method of claim 1 , wherein re-generating the keystream comprises: identifying an initial portion of an initialization vector used to encrypt the data block according to a page containing the encrypted data block; identifying a remaining portion of the initialization vector used to encrypt the data block according to a block number of the data block; and recomputing the keystream according to the identified initial portion of initialization vector and the identified remaining portion of the initialization vector and a secret key.
4. The method of claim 3, wherein computing the keystream comprises: selecting a stored page initialization vector value according to a page containing the encrypted data block and a block number of the encrypted data block from an on-chip data structure containing one or more unique page initialization vectors; selecting a stored C-bit counter value according to the block number of the encrypted data block; reforming the initialization vector used to encrypt the data block according to the page initialization vector value, the C-bit counter value and (N - C) most significant bits of an address of the encrypted data block, where the address is an N-bit address; and encrypting the formed initialization vector using the secret key to form the keystream.
5. The method of claim 1 , wherein decrypting the encrypted data block is performed within a single clock cycle.
6. An article of manufacture including a machine readable medium having stored thereon instructions which may be used to program a system to perform a method, comprising: reading an encrypted data block from memory; regenerating, during reading of the encrypted data block, a keystream used to encrypt the data block according to one or more stored criteria of the data block; and once reading of the encrypted data block is complete, decrypting the encrypted data block according to the generated keystream.
7. The article of manufacture of claim 6, wherein prior to receiving the request the method comprises: receiving a request for the encrypted data block; and reading the encrypted data block from a random access memory.
8. The article of manufacture of claim 6, wherein prior to receiving the request the method comprises: identifying an initial portion of an initialization vector used to encrypt the data block according to a page containing the encrypted data block; identifying a remaining portion of the initialization vector used to encrypt the data block according to a block number of the data block; and recomputing the keystream according to the identified initial portion of initialization vecloi and ihe identified remaining portion of the initialization vector and a secret key.
9. The article of manufacture of claim 8, wherein prior to receiving the request the method comprises: selecting a stored page initialization vector value according to a page containing the encrypted data block and a block number of the encrypted data block from an on-chip data structure containing one or more unique page initialization vectors; selecting a stored C-bit counter value according to the block number of the encrypted data block; reforming the initialization vector used to encrypt the data block according to the page initialization vector value, the C-bit counter value and (N - C) most significant bits of an address of the encrypted data block, where the address is an N-bit address; and encrypting the formed initialization vector using the secret key to form the keystream.
10. The article of manufacture of claim 6, wherein decrypting the selected data block is performed within a single clock cycle.
11. A method comprising: computing an initialization vector for a data block according to one or more criteria of the data block, storing the criteria of the data block used to compute the initialization vector for the data block; computing a keystream from the initialization vector and a secret key; encrypting the data block according to the keystream; and storing the encrypted data block within memory.
12. The method of claim 11 , wherein computing the initialization vector comprises: receiving a write request for the data block; identifying a page containing the data block; forming a page initialization vector according to the page containing the data block as the initialization vector of the data block.
13 , The method of claim 11 , wherein computing the initialization vector comprises: receiving a write request for the data block; identifying a page containing the data block and a block number of the data block within the page; forming a page initialization vector according to the page containing the data block and the block number of the encrypted data block; forming a block initialization vector according to the block number of the data block; and combining the page initialization vector and the block initialization vector to form the initialization vector.
14. The method of claim 13, wherein forming the page initialization vector comprises: identifying a plurality of page initialization vectors assigned to the page containing the data block from an on-chip data structure containing one or more unique page initialization vectors; and selecting a page initialization vector according to a page counter value for the page containing the data block.
15. The method of claim 13, wherein forming the block initialization vector comprises: selecting a block counter value for page writes to the page containing the data block as the block initialization vector.
16. The method of claim 11 , wherein combining to form the initialization vector comprises: selecting a stored page initialization vector value according to a page containing the unencrypted data block from an on-chip data structure containing one or more unique page initialization vectors; selecting a stored C-bit counter value according to the block number of the encrypted data block; forming the initialization vector used to encrypt the data block according to the page initialization vector value, the C-bit counter value and (N - C) most significant bits of an address of the encrypted data block, where the address is an N-bit address; and encrypting the formed initialization vector using the secret key to form the keystream.
17. The method of claim 11 , wherein computing the keystream comprises: providing the initialization vector and the secret key to one of a stream cipher and a block cipher to generate the keystream.
18. The method of claim 11 , further comprising: identifying a data block having a least recent initialization vector; computing a unique initialization vector for the identified initialization vector; and re-encrypting the identified data block according to a keystream generated from the unique initialization vector and a secret key.
19. The method of claim 18, wherein computing the unique initialization vector comprises: identifying a current page initialization vector value according to a page counter value of a page containing the identified data block; and replacing a page initialization vector portion of the identified initialization vector with the current page initialization vector value to form the unique initialization vector.
20. The method of claim 11 , wherein storing the initialization vector comprises: identifying a page counter value used to select a page vector value of the initialization vector; identifying a block counter value used to form a block vector value of the initialization vector; and storing the page counter value and the block counter value within an encryption page structure according to a block number of the data block.
21. A processor comprising: memory encryption logic to store one or more criteria of a data block used to compute an initialization vector for the data block, encrypt the data block according to a keystream computed from the initialization vector and a secret key, and store the encrypted data block within memory; and memory decryption logic to regenerate, during an encrypted data block read, a keystream used to encrypt the data block according to one or more stored criteria of the data block and decrypt the encrypted data block using the regenerated keystream.
22. The apparatus of claim 21, wherein the encryption logic further comprises: a memory including an encryption page structure having a page data structure containing one or more unique page initialization vector values used in foraiation of initialization vectors, and a block data structure used to store an index value to the page data structure and block data structure used to form an initialization vector for recomputation of a keystream and to encrypt data blocks.
23. The apparatus of claim 21 , wherein the encryption logic further comprises recode logic to identify a data block having a least recent initialization vector, recompute a unique initialization vector for the identified initialization vector, and re- encrypt the identified data block according to a keystream generated from the unique initialization vector and a secret key.
24. The apparatus of claim 21, wherein the decrypt logic decrypts encrypted data blocks within a single clock cycle using an exclusive-OR operation.
25. the apparatus of claim 21, wherein the memory is one of random access memory and disk memory.
26. A system comprising: a random access memory (RAM); a chipset coupled to the memory; and a processor coupled to the chipset, the processor including: memory encryption logic to store one or more criteria of a data block used to compute an initialization vector for the data block, encrypt the data block according to the keystream computed the initialization vector and a secret key, and store the encrypted data block within the memory, and memory decryption logic to regenerate, during an encrypted data block read from the memory, a keystream used to enciypt the data block according to one or more stored criteria of the data block and decrypt the encrypted data block using the regenerated keystream.
27. The system of claim 26, wherein the encryption logic further comprises: a memory including an encryption page structure having a page data structure containing one or more unique page initialization vector values used in formation of initialization vectors, and a block data structure used to store an index value to the page data structure and block data structure used to form an initialization vector for recomputation of a keystream and to encrypt data blocks.
28. The system of claim 26, wherein the encryption logic further comprises recode logic to identify a data block having a least recent initialization vector, replace the identified initialization vector with a current initialization vector, and re- encrypt the identified data block according to a keysfream generated from the current initialization vector and a secret key.
29. The system of claim 26, wherein the decrypt logic decrypts encrypted data blocks within a single clock cycle using an exclusive-OR operation.
30. The system of claim 26, wherein the RAM memory is double data rate (DDR) synchronous data RAM (SDRAM)
31. An article of manufacture including a machine readable medium having stored thereon instructions which may be used to program a system to perform a method, comprising: computing an initialization vector for a data block according to one or more criteria of the data block, storing the criteria of the data block used to compute the initialization vector for the data block; computing a keystream from the initialization vector and a secret key; encrypting the data block according to the keystream; and storing the encrypted data block within memory.
32. The article of manufacture of claim 31 , wherein computing the initialization vector comprises: receiving a write request for the data block; identifying a page containing the data block and a block number of the data block within the page; forming a page initialization vector according to the page containing the data block and the block number of the encrypted data block; forming a block initialization vector according to the block number of the data block; and combining the page initialization vector and the block initialization vector to form the initialization vector.
33. The article of manufacture of claim 31 , wherein combining to form the initialization vector comprises: selecting a stored page initialization vector value according to a page containing the unencrypted data block and the block number of the encrypted data block from an on- chip data structure containing one or more unique page initialization vectors; selecting a stored C-bit counter value according to a block number of the encrypted data block; forming the initialization vector used to encrypt the data block according to the page initialization vector value, the C-bit counter value and (N - C) most significant bits of an address of the encrypted data block, where the address is an N-bit address; and encrypting the formed initialization vector using the secret key to form the keystream.
34. The article of manufacture of claim 31 , wherein the method further comprises: identifying a data block having a least recent initialization vector; computing a unique initialization vector from the identified initialization vector; and re-encrypting the identified data block according to a keystream generated from the unique initialization vector and a secret key.
35. The article of manufacture of claim 34, computing the unique initialization vector comprises: identifying a current page initialization vector value according to a page counter value of a page containing the identified data block; and replacing a page initialization vector portion of the identified initialization vector with the current page initialization vector value to form the unique initialization vector.
PCT/US2004/018272 2003-06-25 2004-06-09 An apparatus and method for memory encryption with reduced decryption latency WO2005006197A2 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2006509096A JP4500306B2 (en) 2003-06-25 2004-06-09 Apparatus and method for memory encryption with reduced decryption latency
EP19187662.2A EP3575971A1 (en) 2003-06-25 2004-06-09 An apparatus and method for memory encryption with reduced decryption latency
EP04754772.4A EP1654661B1 (en) 2003-06-25 2004-06-09 Apparatus and method for memory encryption with reduced decryption latency
CN2004800177114A CN1836220B (en) 2003-06-25 2004-06-09 An apparatus and method for memory encryption with reduced decryption latency

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US10/603,680 2003-06-25
US10/603,680 US7472285B2 (en) 2003-06-25 2003-06-25 Apparatus and method for memory encryption with reduced decryption latency

Publications (2)

Publication Number Publication Date
WO2005006197A2 true WO2005006197A2 (en) 2005-01-20
WO2005006197A3 WO2005006197A3 (en) 2006-02-16

Family

ID=34062229

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2004/018272 WO2005006197A2 (en) 2003-06-25 2004-06-09 An apparatus and method for memory encryption with reduced decryption latency

Country Status (5)

Country Link
US (1) US7472285B2 (en)
EP (2) EP3575971A1 (en)
JP (1) JP4500306B2 (en)
CN (1) CN1836220B (en)
WO (1) WO2005006197A2 (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008110985A1 (en) * 2007-03-13 2008-09-18 Nxp B.V. Encryption and decryption of a dataset in at least two dimensions
WO2008110971A2 (en) * 2007-03-13 2008-09-18 Koninklijke Philips Electronics N.V. Encryption and decryption of auxiliary data
WO2008121614A1 (en) 2007-03-28 2008-10-09 Intel Corporation Flexible architecture and instruction for advanced encryption standard (aes)
WO2011149986A1 (en) * 2010-05-27 2011-12-01 Cisco Technology, Inc. Virtual machine memory compartmentalization in multi-core architectures
WO2012122558A3 (en) * 2011-03-10 2012-12-27 Icform, Inc. Programmable data storage management
EP2958264A1 (en) * 2014-06-20 2015-12-23 Cypress Semiconductor Corporation Encryption method for execute-in-place memories
US20180137294A1 (en) 2014-06-20 2018-05-17 Cypress Semiconductor Corporation Encryption for xip and mmio external memories
US10691838B2 (en) 2014-06-20 2020-06-23 Cypress Semiconductor Corporation Encryption for XIP and MMIO external memories
EP3758276A4 (en) * 2018-12-12 2021-10-13 Shenzhen Goodix Technology Co., Ltd. Data processing method, circuit, terminal device storage medium

Families Citing this family (55)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7734932B2 (en) * 2003-11-10 2010-06-08 Broadcom Corporation System and method for securing executable code
US7162647B2 (en) * 2004-03-11 2007-01-09 Hitachi, Ltd. Method and apparatus for cryptographic conversion in a data storage system
US20060005047A1 (en) * 2004-06-16 2006-01-05 Nec Laboratories America, Inc. Memory encryption architecture
EP1615369A1 (en) * 2004-07-06 2006-01-11 Proton World International N.V. Block encryption of the content of a memory external to a processor
EP1617586B1 (en) * 2004-07-06 2008-09-03 Proton World International N.V. Stream ciphering of the content of a memory which is external to a processor
JP2006023957A (en) * 2004-07-07 2006-01-26 Sony Corp Semiconductor integrated circuit and information processor
US8155306B2 (en) * 2004-12-09 2012-04-10 Intel Corporation Method and apparatus for increasing the speed of cryptographic processing
US8081755B2 (en) * 2005-05-20 2011-12-20 Microsoft Corporation JPEG2000 syntax-compliant encryption with full scalability
US20070067644A1 (en) * 2005-08-26 2007-03-22 International Business Machines Corporation Memory control unit implementing a rotating-key encryption algorithm
US20070050642A1 (en) * 2005-08-26 2007-03-01 International Business Machines Corporation Memory control unit with configurable memory encryption
FR2895608B1 (en) * 2005-12-23 2008-03-21 Trusted Logic Sa METHOD FOR MAKING A SECURED COUNTER ON AN ON-BOARD COMPUTER SYSTEM HAVING A CHIP CARD
US7797751B1 (en) * 2006-03-27 2010-09-14 Oracle America, Inc. Nonce structure for storage devices
KR101369748B1 (en) * 2006-12-04 2014-03-06 삼성전자주식회사 Method for encrypting datas and appatus therefor
US7899978B2 (en) * 2006-12-08 2011-03-01 Pandya Ashish A Dynamic programmable intelligent search memory
WO2008073824A1 (en) * 2006-12-08 2008-06-19 Pandya Ashish A Dynamic programmable intelligent search memory
US7890692B2 (en) * 2007-08-17 2011-02-15 Pandya Ashish A FSA context switch architecture for programmable intelligent search memory
US9141557B2 (en) 2006-12-08 2015-09-22 Ashish A. Pandya Dynamic random access memory (DRAM) that comprises a programmable intelligent search memory (PRISM) and a cryptography processing engine
US7996348B2 (en) * 2006-12-08 2011-08-09 Pandya Ashish A 100GBPS security and search architecture using programmable intelligent search memory (PRISM) that comprises one or more bit interval counters
US20110029549A1 (en) * 2006-12-08 2011-02-03 Pandya Ashish A Signature search architecture for programmable intelligent search memory
DE112006004173T5 (en) * 2006-12-15 2009-11-12 Agere Systems, Inc. Protecting a programmable memory against unauthorized modification
US8509439B2 (en) * 2007-12-31 2013-08-13 Intel Corporation Assigning nonces for security keys
JP5374751B2 (en) * 2008-07-31 2013-12-25 株式会社ハイパーテック Memory management method
JP5272751B2 (en) * 2009-01-26 2013-08-28 富士通セミコンダクター株式会社 Processor
US8719593B2 (en) * 2009-05-20 2014-05-06 Harris Corporation Secure processing device with keystream cache and related methods
US8971530B2 (en) 2009-06-24 2015-03-03 Intel Corporation Cryptographic key generation using a stored input value and a stored count value
DE102010010851A1 (en) * 2010-03-10 2011-09-15 Giesecke & Devrient Gmbh Spying protection when executing an operation sequence in a portable data carrier
US8700892B2 (en) * 2010-03-19 2014-04-15 F5 Networks, Inc. Proxy SSL authentication in split SSL for client-side proxy agent resources with content insertion
JP5167374B2 (en) * 2011-01-21 2013-03-21 シャープ株式会社 Data encryption device and memory card
GB2494625A (en) * 2011-09-06 2013-03-20 St Microelectronics Grenoble 2 Minimizing the latency of a scrambled memory access by sending a memory access operation to the encryption engine and the memory controller in parallel
US8726037B2 (en) 2011-09-27 2014-05-13 Atmel Corporation Encrypted memory access
CN103425935A (en) * 2012-05-16 2013-12-04 侯方勇 Method and device for encrypting data of memory on basis of addresses
KR101458479B1 (en) * 2012-10-12 2014-11-07 한국전자통신연구원 Method of encrypting and decrypting the data of the session state
US9405919B2 (en) 2014-03-11 2016-08-02 Qualcomm Incorporated Dynamic encryption keys for use with XTS encryption systems employing reduced-round ciphers
US9800401B2 (en) * 2014-04-23 2017-10-24 International Business Machines Corporation Initialization vectors generation from encryption/decryption
IL234956A (en) * 2014-10-02 2017-10-31 Kaluzhny Uri Bus protection with improved key entropy
US9942211B1 (en) 2014-12-11 2018-04-10 Amazon Technologies, Inc. Efficient use of keystreams
US9614666B2 (en) 2014-12-23 2017-04-04 Intel Corporation Encryption interface
WO2017048256A1 (en) * 2015-09-17 2017-03-23 Hewlett Packard Enterprise Development Lp Efficiently storing initialization vectors
US9876641B2 (en) * 2015-10-08 2018-01-23 The Boeing Company Data dependent authentication keys for differential power analysis resistant authentication
GB2554096B (en) * 2016-09-20 2019-03-20 Advanced Risc Mach Ltd Handling of inter-element address hazards for vector instructions
CN108073353B (en) 2016-11-15 2020-04-14 华为技术有限公司 Data processing method and device
US10896267B2 (en) 2017-01-31 2021-01-19 Hewlett Packard Enterprise Development Lp Input/output data encryption
IT201800003373A1 (en) 2018-03-08 2019-09-08 St Microelectronics Srl PROCEDURE AND DECRITATION CIRCUIT, CORRESPONDING DEVICE
EP3582134B1 (en) * 2018-06-15 2021-02-24 STMicroelectronics Srl A cryptography method and circuit, corresponding device
US11646870B2 (en) 2019-01-23 2023-05-09 International Business Machines Corporation Securing mobile device by RAM-encryption
EP3697020A1 (en) * 2019-02-15 2020-08-19 Siemens Aktiengesellschaft Method of operating keystream generators in meter mode for secure data transmission, keystream generator with meter mode for secure data transmission and computer program product for keystream generation
US11863670B2 (en) * 2019-04-22 2024-01-02 Cryptography Research, Inc. Efficient side-channel-attack-resistant memory encryptor based on key update
CN110445601B (en) * 2019-07-19 2022-07-26 三未信安科技股份有限公司 Method, system, storage medium and computer device for accelerating encryption algorithm of Zuichong
US11636046B1 (en) * 2019-11-15 2023-04-25 The Charles Stark Draper Laboratory, Inc. Latency free data encryption and decryption between processor and memory
US11782127B2 (en) 2021-02-05 2023-10-10 Nxp Usa, Inc. Stop criterion for greedy target detection algorithms in radar applications using sparse phased arrays
FR3120718B1 (en) * 2021-03-09 2023-02-10 Commissariat Energie Atomique Process for executing a computer program by an electronic device
US11567676B2 (en) 2021-04-30 2023-01-31 Nxp B.V. Inline encryption/decryption for a memory controller
US11874776B2 (en) * 2021-06-25 2024-01-16 Intel Corporation Cryptographic protection of memory attached over interconnects
US11620184B2 (en) 2021-08-16 2023-04-04 Nxp B.V. Runtime integrity checking for a memory system
CN114710287B (en) * 2022-06-06 2022-09-20 中科问天量子科技(天津)有限公司 Encryption method, system, storage medium and encrypted file access method

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5757919A (en) 1996-12-12 1998-05-26 Intel Corporation Cryptographically protected paging subsystem

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4529870A (en) * 1980-03-10 1985-07-16 David Chaum Cryptographic identification, financial transaction, and credential device
US5259025A (en) * 1992-06-12 1993-11-02 Audio Digitalimaging, Inc. Method of verifying fake-proof video identification data
US5345508A (en) * 1993-08-23 1994-09-06 Apple Computer, Inc. Method and apparatus for variable-overhead cached encryption
US5809148A (en) * 1996-05-17 1998-09-15 Motorola, Inc. Decryption of retransmitted data in an encrypted communication system
US6061449A (en) 1997-10-10 2000-05-09 General Instrument Corporation Secure processor with external memory using block chaining and block re-ordering
JP4226760B2 (en) * 2000-05-08 2009-02-18 株式会社東芝 Microprocessor, multitask execution method using the same, and multired execution method
US6937727B2 (en) * 2001-06-08 2005-08-30 Corrent Corporation Circuit and method for implementing the advanced encryption standard block cipher algorithm in a system having a plurality of channels
JP2003023421A (en) * 2001-07-09 2003-01-24 C4 Technology Inc Encryption method, program thereof, recording medium recorded with the program, encryption device, decoding method, and decoder
JP4226816B2 (en) * 2001-09-28 2009-02-18 株式会社東芝 Microprocessor
DE60238853D1 (en) * 2001-10-03 2011-02-17 Nxp Bv Method and system for memory encryption
US7274792B2 (en) * 2002-08-09 2007-09-25 Broadcom Corporation Methods and apparatus for initialization vector processing

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5757919A (en) 1996-12-12 1998-05-26 Intel Corporation Cryptographically protected paging subsystem

Cited By (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008110971A3 (en) * 2007-03-13 2008-11-27 Koninkl Philips Electronics Nv Encryption and decryption of auxiliary data
WO2008110971A2 (en) * 2007-03-13 2008-09-18 Koninklijke Philips Electronics N.V. Encryption and decryption of auxiliary data
WO2008110985A1 (en) * 2007-03-13 2008-09-18 Nxp B.V. Encryption and decryption of a dataset in at least two dimensions
US10581590B2 (en) 2007-03-28 2020-03-03 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
EP2852088A1 (en) * 2007-03-28 2015-03-25 Intel Corporation Flexible Architecture and Instruction for Advanced Encryption Standard (AES)
EP2132899A4 (en) * 2007-03-28 2011-03-16 Intel Corp Flexible architecture and instruction for advanced encryption standard (aes)
US10291394B2 (en) 2007-03-28 2019-05-14 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US9647831B2 (en) 2007-03-28 2017-05-09 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US8538015B2 (en) 2007-03-28 2013-09-17 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10270589B2 (en) 2007-03-28 2019-04-23 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US9654282B2 (en) 2007-03-28 2017-05-16 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
WO2008121614A1 (en) 2007-03-28 2008-10-09 Intel Corporation Flexible architecture and instruction for advanced encryption standard (aes)
US9654281B2 (en) 2007-03-28 2017-05-16 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
EP3145113A1 (en) * 2007-03-28 2017-03-22 INTEL Corporation Flexible architecture and instruction for advanced encryption standard (aes)
US9634830B2 (en) 2007-03-28 2017-04-25 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US9634828B2 (en) 2007-03-28 2017-04-25 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US9634829B2 (en) 2007-03-28 2017-04-25 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US9641319B2 (en) 2007-03-28 2017-05-02 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US9641320B2 (en) 2007-03-28 2017-05-02 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10263769B2 (en) 2007-03-28 2019-04-16 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
EP2132899A1 (en) * 2007-03-28 2009-12-16 Intel Corporation Flexible architecture and instruction for advanced encryption standard (aes)
CN112532376A (en) * 2007-03-28 2021-03-19 英特尔公司 Flexible structure and instructions for Advanced Encryption Standard (AES)
EP3737031A1 (en) * 2007-03-28 2020-11-11 INTEL Corporation Flexible architecture and instruction for advanced encryption standard (aes)
EP3361668A1 (en) * 2007-03-28 2018-08-15 Intel Corporation Flexible architecture and instruction for advanced encryption standard (aes)
US10158478B2 (en) 2007-03-28 2018-12-18 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10164769B2 (en) 2007-03-28 2018-12-25 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10171231B2 (en) 2007-03-28 2019-01-01 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10313107B2 (en) 2007-03-28 2019-06-04 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10171232B2 (en) 2007-03-28 2019-01-01 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10181945B2 (en) 2007-03-28 2019-01-15 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10187201B2 (en) 2007-03-28 2019-01-22 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10554386B2 (en) 2007-03-28 2020-02-04 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10256971B2 (en) 2007-03-28 2019-04-09 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US10256972B2 (en) 2007-03-28 2019-04-09 Intel Corporation Flexible architecture and instruction for advanced encryption standard (AES)
US8990582B2 (en) 2010-05-27 2015-03-24 Cisco Technology, Inc. Virtual machine memory compartmentalization in multi-core architectures
WO2011149986A1 (en) * 2010-05-27 2011-12-01 Cisco Technology, Inc. Virtual machine memory compartmentalization in multi-core architectures
WO2012122558A3 (en) * 2011-03-10 2012-12-27 Icform, Inc. Programmable data storage management
EP2958264A1 (en) * 2014-06-20 2015-12-23 Cypress Semiconductor Corporation Encryption method for execute-in-place memories
US10192062B2 (en) 2014-06-20 2019-01-29 Cypress Semiconductor Corporation Encryption for XIP and MMIO external memories
US10169618B2 (en) 2014-06-20 2019-01-01 Cypress Semiconductor Corporation Encryption method for execute-in-place memories
US10691838B2 (en) 2014-06-20 2020-06-23 Cypress Semiconductor Corporation Encryption for XIP and MMIO external memories
US20180137294A1 (en) 2014-06-20 2018-05-17 Cypress Semiconductor Corporation Encryption for xip and mmio external memories
CN105279439A (en) * 2014-06-20 2016-01-27 赛普拉斯半导体公司 Encryption method for execute-in-place memories
EP3758276A4 (en) * 2018-12-12 2021-10-13 Shenzhen Goodix Technology Co., Ltd. Data processing method, circuit, terminal device storage medium

Also Published As

Publication number Publication date
US7472285B2 (en) 2008-12-30
CN1836220B (en) 2010-11-10
US20050021986A1 (en) 2005-01-27
WO2005006197A3 (en) 2006-02-16
JP2006526173A (en) 2006-11-16
EP1654661B1 (en) 2019-07-24
EP1654661A2 (en) 2006-05-10
CN1836220A (en) 2006-09-20
JP4500306B2 (en) 2010-07-14
EP3575971A1 (en) 2019-12-04

Similar Documents

Publication Publication Date Title
US7472285B2 (en) Apparatus and method for memory encryption with reduced decryption latency
US10142101B2 (en) Hardware enforced one-way cryptography
US9847872B2 (en) Memory integrity
US20170046281A1 (en) Address dependent data encryption
KR100445406B1 (en) Apparatus for encrypting the data and method therefor
JP4551802B2 (en) Processor, memory, computer system, and data transfer method
CN101272238B (en) Performing AES encryption or decryption in multiple modes with a single instruction
WO2017112282A1 (en) Memory integrity with error detection and correction
US20190050347A1 (en) Memory data protection based on authenticated encryption
US20120269340A1 (en) Hierarchical encryption/decryption device and method thereof
JP2020535693A (en) Storage data encryption / decryption device and method
WO2011023708A1 (en) Conversion of cryptographic key protection
TW201346637A (en) A low-overhead cryptographic method and apparatus for providing memory confidentiality, integrity and replay protection
EP4083842B1 (en) Inline encryption/decryption for a memory controller
JP2007336446A (en) Data encryption apparatus
CN103154967A (en) Modifying a length of an element to form an encryption key
JP2011123229A (en) Program code encryption device and program
US7707431B2 (en) Device of applying protection bit codes to encrypt a program for protection
JP2000076144A (en) Logic circuit, microcomputer and communication method between logic circuit and storage device
JP5407585B2 (en) Program code encryption apparatus and program
JP2023130311A (en) Method for protecting electronic computer against side-channel attacks, and electronic computer
JP4887668B2 (en) Encryption / decryption processing circuit and encryption / decryption system
JP2011175464A (en) Apparatus and method for processing information

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
WWE Wipo information: entry into national phase

Ref document number: 2004754772

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2006509096

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 20048177114

Country of ref document: CN

WWP Wipo information: published in national office

Ref document number: 2004754772

Country of ref document: EP