JP3557201B2 - Packet processing device, packet processing method, and telephone device that can use the method - Google Patents

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to communication technology, and more particularly to technology for efficiently processing packets.
[0002]
[Prior art]
2. Description of the Related Art With the widespread use of the Internet and the improvement of network infrastructure, Internet telephone devices that packetize data obtained by encoding a call voice signal and transmit / receive the data via a network such as the Internet have attracted attention. By transmitting a video image simultaneously with a call voice, it can be used as a video telephone device, and is expected as a next-generation telephone device to replace a conventional telephone device.
[0003]
At present, TCP / IP (Transmission Control Protocol / Internet Protocol) is widely used as a communication protocol for packet communication. TCP is a communication protocol that emphasizes accuracy, such as transmitting and receiving data after establishing a connection between devices. However, the processing is complicated, and there is a time constraint such that the next packet cannot be sent until the other party confirms that the packet has been received, and the real-time property is lacking.
[0004]
UDP / IP (User Datagram Protocol / Internet Protocol) is a simpler communication protocol than TCP. In UDP, it is not necessary to establish a connection between devices prior to data transmission / reception, and the next packet can be sent without waiting for packet reception confirmation. Therefore, the transmitting side can send packets one after another. it can. Therefore, it is suitable for transmitting and receiving call voice, in which real-time performance is more important than data accuracy.
[0005]
In an apparatus that supports both TCP and UDP communication protocols, packet processing is generally performed by software using a general-purpose processor such as a CPU. That is, when the network interface device receives the packet, the packet addressed to the MAC (Media Access Control) address other than the own device is filtered, and after performing an error check by a CRC (Cyclic Redundancy Check), all the packets that pass through them are checked. The packet is sent to the CPU for processing.
[0006]
[Non-patent document 1]
Estee (ST) Microelectronics, Inc., Voice over IP (VoIP) digital processor datasheet, [online], 2002, [searched September 30, 2002], Internet <URL: http: // www. st. com / stonline / books / pdf / docs / 7818. pdf>
[0007]
[Problems to be solved by the invention]
However, the method of processing all packets by software using the CPU has problems such as low processing efficiency, low speed, and high power consumption. In particular, when talking with a plurality of parties at the same time or sending an image together with voice, the protocol processing is rate-determining, and the real-time property may be impaired. In addition, since the CPU always executes protocol processing during a call, it is difficult to execute other applications in parallel. For example, when communication is performed by a device equipped with a high-performance CPU, such as a personal computer, there is no problem even if the CPU performs all packet processing because it has sufficient capacity to meet the requirement. When developing a dedicated device for an Internet telephone, a relatively low-performance CPU must be mounted in order to realize a reduction in size, cost, and power consumption of the device. The issue is how to reduce the processing load of the system.
[0008]
The present invention has been made in view of such a problem, and an object of the present invention is to provide a technique for efficiently performing packet processing accompanying data communication. Another object of the present invention is to provide a technique for reducing the processing load of a CPU in packet processing and realizing high-speed real-time communication.
[0009]
[Means for Solving the Problems]
One embodiment of the present invention relates to a packet processing device. The packet processing device includes a buffer that temporarily holds a packet acquired via a network, and a write control unit that controls storage of the packet in the buffer. The destination address information in the header information is discarded and stored in the reception buffer.
[0010]
Since the destination MAC address stored in the MAC header of the packet is unnecessary for subsequent packet processing after the packet is received, discarding the destination MAC address can improve the use efficiency of the buffer.
[0011]
The write control unit may store, instead of the destination address information, management information including transmission type information indicating whether the packet was transmitted by unicast, multicast, or broadcast. The management information may further include packet type information indicating a type of the packet, and address information indicating a storage position of a next packet. The write control unit may store the management information in one word, shape subsequent data in word units, and store the data in the buffer.
[0012]
Since the MAC header is 3.5 words of 32 bits and has an odd size, if it is stored in the buffer as it is, all subsequent data will be shifted by half words. Therefore, by discarding the transmission destination MAC address for 1.5 words and storing it in the buffer, subsequent data can be aligned in word units. At this time, management information required for packet processing may be added for one word. This facilitates handling both in hardware and software.
[0017]
Yet another embodiment of the present invention relates to a telephone device. This telephone device has an input unit for inputting voice, a communication unit for transmitting voice input from the input unit to another device and receiving voice from another device, and outputting a voice received from another device. And a communication unit, wherein the communication unit includes: a reception unit that receives a packet transmitted via a network; and a packet processing unit that processes the received packet. Buffer temporarily, and a write control unit that controls the storage of the packet in the buffer, the write control unit, of the header information of the packet, discard the destination address information, The data is stored in the reception buffer.Further, the write control unit stores, in the reception buffer, management information including transmission type information indicating whether the packet was transmitted by unicast, multicast, or broadcast, instead of the discarded destination address information.
[0020]
It is to be noted that any combination of the above-described components and any conversion of the expression of the present invention between a method, an apparatus, a system, and the like are also effective as embodiments of the present invention.
[0021]
BEST MODE FOR CARRYING OUT THE INVENTION
FIG. 1 shows an overall configuration of an Internet telephone device 100 as an example of a communication device according to an embodiment of the present invention. The Internet telephone device 100 is a device for making a call with another Internet telephone device 100 via the Internet 20. The Internet telephone device 100 mainly includes a CPU 110 that is a general-purpose circuit for executing software processing, a memory 120 used as a program area or a work area, a network interface unit 130 that transmits and receives packets via the Internet 20, and a voice signal. 150, a speaker 160 that outputs an audio signal, a codec processing unit 140 that performs a compression encoding process and a decoding process of an audio signal, a security processing unit 172 that performs an encryption process or a decryption process of communication data, and a UDP packet. , A UDP processing unit 174 that is a dedicated circuit for processing the communication, a protocol engine 200 that performs various processes according to a communication protocol, and a bus 102 that electrically connects these components.
[0022]
In the Internet telephone device 100 of the present embodiment, the processing of the received packet is not left to the CPU 110 alone, but before the packet is transferred to the CPU 110, the protocol engine 200 constituted by dedicated hardware performs header analysis, Since processing such as error checking and data alignment is performed, the CPU 110 does not need to perform useless packet processing, and the processing load is greatly reduced.
[0023]
The Internet telephone device 100 of the present embodiment transmits and receives voice signals using UDP. UDP is a communication method that does not require connection establishment and can send out packets one after another, so that protocol processing is easy and high-speed communication is possible, and real-time communication such as sending call voice is performed. Suitable for communication. In the Internet telephone device 100 of the present embodiment, the processing of the UDP packet is performed by the UDP processing unit 174 which is a dedicated circuit, thereby further improving the processing speed and realizing the real-time transmission and reception of the call voice.
[0024]
Of the packets transmitted and received by the Internet telephone device 100, packets transmitted and received by TCP are processed by software using the CPU 110. For TCP packets that do not require real-time processing, software processing is performed by general-purpose circuits without using dedicated circuits, so that increases in circuit scale can be suppressed, and increases in cost, power consumption, and heat generation can be minimized. it can. According to the estimation of the inventor, it has been found that the area and power consumption of the circuit can be reduced to about ３ as compared with the case where both TCP and UDP are processed by the dedicated circuit. As described above, in the present embodiment, cooperative processing is performed by dedicated hardware and general-purpose software, thereby meeting the trade-off demands of speeding up processing and reducing the circuit scale.
[0025]
The packet received by the network interface unit 130 is sent to the protocol engine 200. The protocol engine 200 determines whether or not the packet is addressed to the IP address assigned to the own device, passes only the packet addressed to the own device, and discards other packets. Further, the type of the protocol is detected by referring to the header information attached to the packet. If the packet is a packet transmitted by TCP, the data of the packet is transmitted to the bus 102 and the CPU 110 performs software processing. . If the packet is a UDP packet, the data of the packet is sent to the UDP processing unit 174 and processed by a circuit provided exclusively for processing the UDP packet.
[0026]
The UDP processing unit 174 is a dedicated circuit for processing a UDP packet, receives a UDP packet, analyzes its header, and executes necessary processing. The security processing unit 172 performs processing such as decryption of encryption when data is subjected to security measures such as encryption processing. The decoded data is sent to codec processing section 140. The codec processing unit 140 decodes the communication voice signal that has been compression-encoded and outputs the decoded signal to the speaker 160.
[0027]
As described above, in the Internet telephone device 100 according to the present embodiment, real-time performance is more important than accuracy, and call voice data that needs to be constantly processed during a call is transmitted and received by the UDP. While the processing unit 174 performs hardware processing, data for which accuracy is more important than real-time processing is transmitted and received by TCP, and the CPU 110 performs software processing. This makes it possible to process call voice data at high speed while suppressing an increase in circuit complexity, circuit scale, cost, power consumption, heat generation, and the like. Such an advantage becomes more remarkable when a large amount of data needs to be processed at the same time, such as when talking with a plurality of parties at the same time or transmitting an image together with the call voice. Further, the type of the packet can be detected by the protocol engine 200, and the processing entity of the packet can be selected quickly and appropriately. Further, the processing load on the CPU 110 can be reduced, cost reduction and power consumption can be reduced, and since the CPU 110 has extra power, it is possible to execute other applications during a call and provide a new service. You can also.
[0028]
The operation when the packet is received has been described above. Next, the operation when the audio signal input from the microphone 150 is packetized and transmitted will be described. The audio signal input from the microphone 150 is sent to the codec processing unit 140 and encoded. The encoded signal is, if necessary, encrypted by the security processing unit 172, sent to the UDP processing unit 174, attached with a UDP header, and packetized. This UDP packet is provided with header information such as a checksum value by the protocol engine 200 and transmitted to the Internet 20 via the network interface unit 130.
[0029]
FIG. 2 shows an internal configuration of the protocol engine 200. The ARP control unit 202 automatically sets address (MAC address) information of its own data link layer when the network interface unit 130 receives an ARP (Address Resolution Protocol) packet addressed to its own IP address. Then, a response packet is generated and transmitted to the source of the ARP packet. Conventionally, the ARP packet is also processed by software using the CPU 110. However, in this embodiment, the ARP control unit 202 automatically responds without passing through the CPU 110, thereby greatly reducing the load on the CPU 110 and reducing the task by interrupt. Switches can be reduced.
[0030]
The header analysis unit 210 analyzes the header information of the packet, discards unnecessary packets, and passes only necessary packets. For example, only packets addressed to the own device's IP address are passed, and packets addressed to other IP addresses are discarded. When the protocol engine 200 of the present embodiment is mounted on a device that transmits and receives only IP packets, packets of a communication method other than IP may be discarded. Alternatively, a specific packet may be detected and sent to a dedicated circuit for processing the packet. In the present embodiment, since the UDP packet is processed by the UDP processing unit 174 which is a dedicated circuit, the header analysis unit 210 detects the UDP packet by analyzing the header information, and transmits the UDP packet without passing through the CPU 110. The data is directly transferred to the UDP processing unit 174. At this time, the header information may be discarded and only the data portion may be sent. This allows the CPU 110 to process only packets that require software processing, thereby reducing the processing load on the CPU 110. In addition, by processing the packet by using dedicated hardware as appropriate, the processing can be speeded up.
[0031]
The checksum calculator 212 calculates the checksum of the packet and verifies whether or not the checksum matches the checksum value stored in the header. If they match, the packet is passed. If they do not match, the packet is discarded. Conventionally, the checksum was verified by the CPU 110. However, as in the present embodiment, the checksum is verified by a dedicated circuit at a stage before sending the checksum to the CPU 110, thereby processing unnecessary packets to the CPU 110. Can be prevented, and the processing load on the CPU 110 can be reduced.
[0032]
The write control unit 220 stores the packet that has passed through the header analysis unit 210 in the reception buffer 230. The packet in which the error is detected by the checksum calculation unit 212 is discarded without storing it in the reception buffer 230. However, while the checksum calculation unit 212 calculates the checksum, the packet waits for writing to the reception buffer 230. It is more efficient to write to the reception buffer 230 in parallel than to write. Therefore, the write control unit 220 writes the packet passing through the header analysis unit 210 to the reception buffer 230 without waiting for the result of the verification by the checksum calculation unit 212, and detects an error by the verification by the checksum calculation unit 212. If so, erase the written packet and restore the write pointer. The read control unit 240 controls reading of the received packet stored in the reception buffer 230. Details of the configurations and operations of the write control unit 220, the reception buffer 230, and the read control unit 240 will be described in detail with reference to FIG.
[0033]
The checksum generator 280 calculates a checksum of the transmission packet. Since the packet size of the UDP packet is determined at the time of being put into the transmission queue, the checksum of the data part is calculated and held in advance by the checksum generator 280, and the header is synthesized by the header synthesizer 250 when transmitting the packet. To the checksum value. Since the packet size of a TCP packet is determined at the time of packet transmission, it is not possible to calculate the checksum value of the data portion in advance, but by calculating and storing the checksum accumulated value for each predetermined section. In addition, the checksum calculation process at the time of packet transmission can be simplified. If the packet size of the TCP packet is limited to an integral multiple of the calculated section of the checksum accumulated value, the checksum value of the data section can be obtained by simply subtracting the checksum accumulated values before and after the section of the data section.
[0034]
The first transmission buffer 270 stores transmission packets of which transmission destination MAC address is unresolved among transmission packets. The second transmission buffer 272 stores a transmission packet whose transmission destination MAC address is known among transmission packets. The ARP interface 260 generates an ARP packet and broadcasts it to the network for resolving the MAC address of the packet stored in the first transmission buffer 270 for which the MAC address of the transmission destination is unknown. Since the ARP packet cannot be transmitted until the response is returned, the first transmission buffer 270 is provided separately from the queue of the packets for which the address resolution is not necessary, and the second transmission buffer 272 is kept in the meantime. Sends a transmission packet that does not require address resolution during standby. When the ARP response is returned, the resolved MAC address is set, the packet in the first transmission buffer 270 is transmitted, and then the ARP packet is transmitted for the waiting packet. Then, the packet in the second transmission buffer 272 is transmitted again until a response is returned. As a result, the entire transmission waiting time can be reduced and packets can be transmitted efficiently. Even if the destination MAC address of the packet is unresolved, the packet is sent to the first transmission buffer 270 while automatically resolving the MAC address. It is simple and the processing load can be reduced.
[0035]
The header synthesizing unit 250 generates the header information of the transmission packet waiting for transmission held in the first transmission buffer 270 or the second transmission buffer 272 via the network interface unit 130 so as to be transmitted. The header synthesizing unit 250 automatically generates parameters that are not frequently changed and parameters that can be easily estimated, and generates header information. For example, the header combining unit 250 automatically increments the identifier of the IP header even if the identifier is not specified by the CPU 110, and sets it in the header. The CPU 110 may specify only the transmission destination and the packet size other than the data. As a result, the buffer management of the CPU 110 can be simplified, and the processing load can be reduced.
[0036]
The host table 204 holds a MAC address and an IP address of another device in association with each other. FIG. 3 shows an example of internal data of the host table 204. The host table 204 has a host ID column 205, a MAC address column 206, and an IP address column 207. As for the contents of the host table 204, information of a host device with which the CPU 110 may frequently communicate may be registered in advance, or the CPU 110 or the like may register during communication. Even for a host device whose MAC address is unknown, only the IP address may be stored first, an ARP packet is sent out by the ARP interface 260, and the MAC address may be registered when a response is obtained. Since the host table 204 is provided, the CPU 110 may specify a destination of a packet by using any of a host ID, a MAC address, and an IP address. The header synthesizing unit 250 can refer to the host table 204 and acquire information necessary for generating a header.
[0037]
The host interface unit 290 controls input and output of data and instructions between the components of the protocol engine 200 and the CPU 110.
[0038]
FIG. 4 shows an internal configuration of the write control unit 220 and the read control unit 240. The write control unit 220 includes a management information generation unit 222, a data exchange unit 224, a write address generation unit 226, a delay circuit 228, and a selector 229. The packet that has passed the packet filtering by the header analysis unit 210 is shaped by the management information generation unit 222 and the data exchange unit 224 and stored in the reception buffer 230. The manner in which the packet data is shaped will be described later with reference to FIG. The write address generation unit 226 manages the write pointer of the reception buffer 230. As described above, the packet data is stored in the reception buffer 230 in parallel with the checksum verification by the checksum calculation unit 212. When a checksum error is detected, the write address generation unit 226 Return the light pointer to its original position. When the checksum error is not detected and the storage in the reception buffer 230 ends normally, the write address generation unit 226 notifies the management information generation unit 222 of the address of the next packet. The read control section 240 includes a read address generation section 242 and a selector 244.
[0039]
FIG. 5 shows how the packet data is shaped by the write control unit 220. In a normal IP packet, the leading MAC header occupies 14 bytes. However, since the 32-bit word is 3.5 words, it is 3.5 words, so the subsequent data is shifted by 16 bits. If the data is stored in the reception buffer 230 as it is, it is inconvenient at the time of access. Therefore, in the present embodiment, the data is shaped so that the MAC header has three words, and then stored in the reception buffer 230. That is, the MAC header may be reduced by 16 bits. The destination MAC address in the MAC header is the same as the MAC address of the own device, and is unnecessary because the packet has already been received. Since the MAC address is 48 bits, discarding the MAC address leaves a 32 bit margin. Depending on the application, information indicating whether the packet was transmitted by unicast, multicast, or broadcast may be required. This is stored as a flag instead of the destination MAC address. Since two bits are sufficient for this flag, there is still room for 30 bits. Therefore, a flag indicating the packet type, address information indicating the storage position of the next packet, and the like are stored as management information. As described above, since the MAC header is reduced to three words, the subsequent data can be aligned in word units, and the access is facilitated.
[0040]
Returning to FIG. 4, a procedure for writing and reading a received packet will be described. The management information generation unit 222 generates the above-described management information. As management information, for example, transmission type information indicating whether this packet was transmitted by unicast, multicast, or broadcast, this packet is a TCP packet or a UDP packet, a fragmented IP packet, or an IP packet with options For example, packet type information indicating whether the packet is a special IP packet requiring complicated processing, address information indicating the storage position of the next packet, and the like may be generated. When the address information of the next packet is stored, the address information of the next packet is obtained from the write address generation unit 226 after the storage of the data of the own packet is completed. After the data storage is completed. These pieces of management information are shaped into one word as a whole, and are stored in the reception buffer 230 via the selector 229.
[0041]
The data exchange unit 224 exchanges the upper 16 bits and the lower 16 bits in order to arrange the data of the received packet excluding the MAC address in a 32-bit word. By synthesizing the upper 16 bits of the output of the data exchange unit 224 with a delay of one clock by the delay circuit 228, the data shifted by 16 bits can be aligned. The shaped data is stored in the reception buffer 230 via the selector 229.
[0042]
First, the write address generation unit 226 moves the pointer to the head of the write position, but since the management information of the first word is stored last, the write address generation unit 226 increments the pointer and removes the destination MAC address from the MAC header by removing the destination MAC address. The word, the IP header 5 words, and the IP data are sequentially written while incrementing the pointer. When the writing of the data portion is completed, the next writing start position is notified to the management information generating unit 222, and the pointer is returned to the head of the writing position to write the management information.
[0043]
The header information including the management information is assigned to an independent register so that the CPU 110 can randomly and repeatedly access the register. Since the validity of the packet stored in the reception buffer 230 has been verified by the header analysis unit 210 and the checksum calculation unit 212, the CPU 110 can directly access the header information and determine the application to which the data should be passed. To do. On the other hand, the data portion is read from one access port register. That is, in the first reading to the access port register, the first data of the data portion is read, and thereafter, by successively accessing the same register, data is successively read. Once the transfer destination of the data is determined, there is no need to enable random access since the rest is only to copy the data. Therefore, by adopting the access port method, the processing load can be reduced more easily and more easily than in the memory map method requiring pointer management. Further, it can be used in combination with hardware having no CPU 110.
[0044]
The read address of the reception buffer is composed of an upper address and a lower address. When accessing the header information of the packet stored in the reception buffer 230, the CPU 110 specifies both the upper address and the lower address. For the upper address, if the read address generator 242 specifies which packet of which header is to be accessed, the read address generator 242 automatically generates the upper address and moves the pointer. As for the lower address, the lower address output by the CPU 110 is used as it is as the lower address of the reception buffer so that the CPU 110 can freely read the lower address. When accessing the data portion of the packet, the CPU 110 may specify to the read address generation unit 242 which packet data to access. The read address generation unit 242 automatically generates an upper address and a lower address, moves a pointer, and reads data one after another.
[0045]
The present invention has been described based on the embodiments. This embodiment is an exemplification, and it is understood by those skilled in the art that various modifications can be made to the combination of each component and each processing process, and that such modifications are also within the scope of the present invention. . Hereinafter, such an example will be described.
[0046]
In the embodiments, the telephone device has been described as an example. However, the technology of the present invention can be used for all communication devices that transmit and receive stream data, such as computers and mobile phones.
[0047]
A circuit having the function of the protocol engine 200 may be mounted on one semiconductor substrate. Further, circuits such as the security processing unit 172, the codec processing unit 140, and the CPU 110 may be mounted. This makes it possible to reduce the size, weight, and speed of the communication device.
[0048]
【The invention's effect】
ADVANTAGE OF THE INVENTION According to this invention, the technique which performs the packet processing accompanying data communication efficiently can be provided. Further, according to the present invention, it is possible to provide a technology that reduces the processing load on the CPU in packet processing and realizes high-speed real-time communication.
[Brief description of the drawings]
FIG. 1 is a diagram illustrating an overall configuration of an Internet telephone device as an example of a communication device according to an embodiment.
FIG. 2 is a diagram showing an internal configuration of a protocol engine according to the embodiment.
FIG. 3 is a diagram showing internal data of a host table according to the embodiment.
FIG. 4 is a diagram illustrating an internal configuration of a write control unit and a read control unit according to the embodiment;
FIG. 5 is a diagram illustrating a state in which packet data is shaped by a write control unit;
[Explanation of symbols]
100 Internet telephone device, 130 network interface unit, 140 codec processing unit, 150 microphone, 160 speaker, 174 UDP processing unit, 200 protocol engine, 202 ARP control unit, 204 host table, 210 header analysis unit, 212 checksum calculation unit, 220 write control section, 222 management information generation section, 224 data exchange section, 226 write address generation section, 230 reception buffer, 240 read control section, 242 read address generation section, 250 header synthesis section, 260 ARP interface, 270 first transmission Buffer, 272 second transmission buffer, 280 checksum generator.

Claims (4)

A buffer for temporarily holding packets obtained via the network,
A write control unit that controls storage of the packet in the buffer,
The write control unit,
Of the header information of the packet, the destination address information is discarded and stored in the reception buffer ,
Packet processing, characterized in that the reception buffer stores management information including transmission type information indicating whether the packet was transmitted by unicast, multicast, or broadcast, in place of the discarded destination address information. apparatus. The packet processing device according to claim 1 , wherein the management information further includes packet type information indicating a type of the packet, and address information indicating a storage position of a next packet. The write control unit, met with the management information to one word, and storing, in the buffer shapes the subsequent data word by word, the packet processing apparatus according to claim 1 or 2. An input unit for inputting voice,
A communication unit that transmits voice input by the input unit to another device and receives voice from another device,
An output unit that outputs audio received from another device,
The communication unit,
A receiving unit that receives a packet sent via the network;
A packet processing unit for processing the received packet,
The packet processing unit,
A buffer for temporarily holding the packet,
A write control unit that controls storage of the packet in the buffer,
The write control unit, among the header information of the packet, discards the destination address information and stores it in the reception buffer ,
A telephone device , wherein management information including transmission type information indicating whether a packet is transmitted by unicast, multicast, or broadcast is stored in the reception buffer in place of the discarded destination address information .

Images