WO2013059991A1 - Data message processing method and system, message forwarding device - Google Patents

Abstract

The present invention provides a data message processing method and system, and a message forwarding device. In an embodiment of the present invention, an IPv6 flow table supporting an IPv6 message is defined in advance in a controller of OpenFlow system architecture, and the IPv6 flow table is delivered to a message forwarding device of OpenFlow system architecture. The message forwarding device, after receiving the data message, determines whether the data message is an IPv6 message according to a link layer data type field comprised in the data message, and if the data message is the IPv6 message, the message forwarding device matches field content comprised in the IPv6 message with field content in the stored IPv6 flow table, and performs a processing on the IPv6 message according to a matching result. Therefore, the embodiment of the present invention enables the message forwarding device of OpenFlow system architecture to support the IPv6 message, thereby extending the OpenFlow system architecture.

Description

 The present invention relates to the field of communications technologies, and in particular, to a data packet processing method and system, and a packet forwarding device. Background technique

 Traditional Transmission Control Protocol/Internet Protocol (TCP/IP) The architecture of the Internet is based on a distributed routing protocol. The network completes the inter-host communication through IP. communication.

 However, with the development of the Internet, the architecture of the distributed network cannot better meet the network scalability and management requirements. Therefore, the centralized programmable network architecture emerges. The OpenFlow (hereinafter referred to as: OpenFlow) system architecture is a centralized programmable network architecture. The OpenFlow Switch converts the packet forwarding process that was originally controlled by the switch/router into an OpenFlow switch and control server (Controller). ) to complete together, thus achieving the separation of data forwarding and routing control. The control server can control the flow table in the OpenFlow switch through pre-defined interface operations to control data forwarding. The switch can obtain the flow table entry that matches the data packet by querying the flow table, and the operation that needs to be performed on the data packet can be determined according to the flow table entry, and the operation can be, for example, forwarding. Go to the destination port, drop, report to the control server, and so on.

The inventor found in the research process that the existing OpenFlow system architecture only supports Internet Protocol version 4 (hereinafter referred to as IPv4), but does not support Internet Protocol version 6 (hereinafter referred to as Internet Protocol version 6; IPv6) is a slogan, which limits the development of the OpenFlow system architecture to a certain extent. SUMMARY OF THE INVENTION Embodiments of the present invention provide a data packet processing method and system, and a packet forwarding device. The embodiment of the invention provides a data packet processing method, including: Determining, according to the link layer data type field included in the data packet, whether the data packet is an IPv6 packet;

 If the data packet is an IPv6 packet, the content of the field in the IPv6 packet is matched with the content of the field that is required to be matched in the IPv6 flow table that is sent by the control server, and the IPv6 flow table includes the following. Said at least one field:

 Message entry field, metadata field, link layer source address field, link layer destination address field, link layer data type field, virtual local area network identification field, virtual local area network priority field, MPLS label field, MPLS traffic type field, IPv6 source address field, IPv6 destination address field, IPv6 traffic type field, IPv6 next header field, IPv6 flow label field, transport layer source port or ICMP type field, transport layer destination port or ICMP code field;

 The IPv6 text is processed correspondingly according to the matching result.

 The embodiment of the invention provides a packet forwarding device, which includes:

 a determining module, configured to determine, according to a link layer data type field included in the data packet, whether the data packet is an IPv6 packet;

 a matching module, configured to: if the data packet is an IPv6 packet, match the field content in the IPv6 packet with a field content that needs to be matched in an IPv6 flow table that is sent by the control server in advance, the IPv6 The flow table contains at least one of the following fields:

 Message entry field, metadata field, link layer source address field, link layer destination address field, link layer data type field, virtual local area network identification field, virtual local area network priority field, MPLS label field, MPLS traffic type field, IPv6 source address field, IPv6 destination address field, IPv6 traffic type field, IPv6 next header field, IPv6 flow label field, transport layer source port or ICMP type field, transport layer destination port or ICMP code field;

 The processing module is configured to perform corresponding processing on the IPv6 packet according to the matching result. The embodiment of the present invention further provides a data packet processing system, including a control server and at least one packet forwarding device, wherein the packet forwarding device uses the packet forwarding device.

In the embodiment of the present invention, the IPv6 flow table structure supporting the IPv6 packet is pre-defined in the control server of the OpenFlow system architecture, and the IPv6 flow table is delivered to the packet forwarding device of the OpenFlow system architecture. After receiving the data packet, the packet forwarding device may determine, according to the link layer data type field included in the data packet, whether the data packet is an IPv6 packet, and if it is an IPv6 packet, the packet forwarding device Can be in the field contained in the IPv6 message The content matches the content of the field in the stored IPv6 flow table, and the IPv6 packet is processed according to the matching result. Therefore, the embodiment of the present invention can enable the packet forwarding device of the OpenFlow system architecture to support IPv6 packets, and expand the OpenFlow system architecture. DRAWINGS

The drawings used in the embodiments or the description of the prior art are briefly described. It is obvious that the drawings in the following description are some embodiments of the present invention, and are not creative to those skilled in the art. Other drawings can also be obtained from these drawings on the premise of labor.

 1 is a flowchart of Embodiment 1 of a data packet processing method according to the present invention;

 2 is a flowchart of Embodiment 2 of a data packet processing method according to the present invention;

 3 is a flowchart of Embodiment 3 of a data packet processing method according to the present invention;

 4 is a schematic structural diagram of Embodiment 1 of a packet forwarding device according to the present invention;

 FIG. 5 is a schematic structural diagram of Embodiment 2 of a packet forwarding device according to the present invention;

 FIG. 6 is a schematic structural diagram of an embodiment of a data packet processing system according to the present invention. detailed description

 The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is a partial embodiment of the invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

 In the prior art, the flow table in the OpenFlow system architecture only supports IPv4 packets, but does not support IPv6 packets, and cannot identify and match related fields in the header of IPv6 packets. Therefore, the OpenFlow system architecture cannot be completed. Network programming control based on IPv64 transmission.

 In the embodiment of the present invention, in order to solve the defect that the existing OpenFlow system architecture cannot support the IPv6 packet, the flow table is extended in the OpenFlow system architecture, and an IPv6 flow table supporting the IPv6 packet is added to support the identification and matching of the IPv6 packet.

Compared with the IPv4 flow table in the prior art, the IPv6 flow table in the embodiment of the present invention is removed. IPv4 related fields in the existing OpenFlow flow table, namely IPv4 source address, IPv4 destination address, IPv4 protocol type (IPv4 Protocol Type) and IPv4 monthly service type field (IPv4 ToS), newly added IPv6 source address The field, the IPv6 destination address field, the IPv6 traffic type field, the IPv6 next header field, and the IPv6 flow label field are five fields, thereby forming an IPv6 flow table containing 16 fields. Further, in order to support the IPv6 extension header, the embodiment of the present invention may further add a Hop-by-Hop Header Options field and a routing header of the Routing Header in the IPv6 flow table. The (Routing Type) field, the Segment Left field, the Type Specific Data field, and the Options Options field of the Destination Options Header form an IPv6 stream containing 21 fields. table.

 In the embodiment of the present invention, the complete IPv6 flow table may include the following 21 fields: an Ingress Port field, a Metadata field, a link layer source address (Ether Src) field, and a link layer destination. Address (Ether Dst) field, link layer data type (Ether Type) field, virtual local area network (VLAN) identifier (Vlan ID) field, virtual local area network priority (Vlan Priority) field, multi-protocol Multi-Protocol Label Switching (hereinafter referred to as MPLS) label (MPLS Label) field, MPLS Traffic Class field, IPv6 source address (IPv6 Src) field, IPv6 destination address (IPv6 Dst) field, IPv6 The IPv6 Traffic Class field, the IPv6 Next Header field, the IPv6 Flow Label field, the transport layer source port, or the Internet Protocol Message Protocol (ICMP). Type (TCP/UDP/SCTP Src Port/ICMP Type) field, Transport destination port or ICMP code (TCP/UDP/SCTP Dst Port/ICMP Code) field, Hop-by-Hop Header option (Options) field, Routing header (Routing Header) route type The (Routing Type) field, the Segment Left field, the Type Specific Data field, and the Options Options field of the Destination Options Header.

The field length of the IPv6 source address field may be 256 bits, which may include a 128-bit IPv6 source address mask field and a 128-bit source address field. When the IPv6 source address field matches, the IPv6 source address mask field may be selectively matched. . IPv6 destination address field The field length can be 256 bits, which can contain a 128-bit IPv6 destination address mask field. When the IPv6 destination address field matches, the IPv6 destination address mask field can be selectively matched. Both the IPv6 Traffic Class field and the IPv6 Next Header field can be 8 bits. The length of the IPv6 Flow Label field can be 32 bits. Only the lower 20 bits are used as valid storage bits, and the upper 12 bits are all zero.

 It should be noted that, for the transport layer source port or the ICMP field TCP/UDP/SCTP Src Port/ICMP Type, the TCP/UDP/SCTP Src Port represents the transport layer source port, and the ICMP Type represents the ICMP type, and the field is either Indicates the source port of the transport layer, which indicates the ICMP type. If the field indicates the transport layer source port or ICMP type, it is characterized by the specific content of the field. It is similar to the port of the transport layer or the ICMP code TCP/UDP/SCTP Dst Port/ICMP Code field, and will not be described here.

 It can be understood by those skilled in the art that, in the architecture of the OpenFlow system, the control server (Controller) does not need a packet forwarding device, such as a switch or a router, to receive all the fields in the received IPv6 packet. Matches with the above 16 fields or 21 fields.

 Therefore, the control server can send the following two forms of IPv6 flow table to the packet forwarding device:

 Form 1. The control server delivers a complete IPv6 flow table.

 The complete IPv6 flow table includes the above 16 fields or 21 fields. In these fields, the content of one or a few fields may be matched by the corresponding field in the IPv6 packet received by the packet forwarding device, and the remaining fields are matched. You can indicate that no matching is required by setting it to "empty" or "any".

 Form 2: The control server delivers an incomplete IPv6 flow table.

 To simplify the IPv6 flow table sent by the control server, the control server only needs to send the fields that need to match the IPv6 data, that is, only the entries in the IPv6 flow table are sent, and the other fields that do not need to be matched need not be sent. .

 In the embodiment of the present invention, the fields in the IPv6 flow table entries to be delivered may be in the form of a type-length-value. Said.

It can be understood that the IPv6 flow table delivered by the above two methods is included in the required The matching field is matched to the corresponding operation (Instruction). Moreover, if the matching of the required matching field is unsuccessful, the packet forwarding device may perform a preset operation, for example, discarding the IPv6 packet, or sending the IPv6 packet to the controller server to request the control server to the IPv6. The text is processed.

 The embodiment of the present invention may further optimize as follows:

 If a packet cannot be both an IPv4 packet and an IPv6 packet, if the IPv4 flow table and the IPv6 flow table are placed in a unified OpenFlow flow table, there must be free storage space in the unified OpenFlow flow table. The utilization of the OpenFlow flow table is low. Therefore, in the embodiment of the present invention, the IPv6 flow table may be used as an independent flow table, and the IPv6 flow table does not include the IPv4 flow table.

 It can be understood that if the packet forwarding device in the OpenFlow system architecture only needs to support the IPv6 packet, the control server can only send the IPv6 flow table to the packet forwarding device, and if the packet forwarding device needs to support the IPv6 packet, And the IPv4 dual-stack operation, the control server needs to send the IPv4 flow table to the packet forwarding device, and the IPv6 flow table is sent to the packet forwarding device. At this time, the IPv6 flow table stored in the packet forwarding device and The IPv4 flow table needs to be distinguished by the respective flow table type values of the IPv6 flow table and the IPv4 flow table.

 The technical solutions of the invention will be described in detail below using several embodiments.

 1 is a flowchart of Embodiment 1 of a data packet processing method according to the present invention. As shown in FIG. 1, the method in this embodiment includes:

 Step 101: Determine, according to the link layer data type field included in the data packet, whether the data packet is an IPv6 packet.

 A packet forwarding device in the OpenFlow system architecture, such as an OpenFlow switch, can receive data packets, which can be either IPv4 packets or IPv6 packets. The two packets can pass data packets. The link layer data type field contained in the Ether Type representation.

 For example, if the Ether Type is 0x0800, the data packet is an IPv4 packet. If the Ether Type is 0x86DD, the data packet is an IPv6 packet.

Step 102: If the data packet is an IPv6 packet, match the content of the field in the IPv6 packet with the content of the field that needs to be matched in the IPv6 flow table that is sent by the control server in advance. In this embodiment, the IPv6 flow table may include at least one of the following fields:

 Ingress Port, Metadata, Ether Src, Ether Dst, Ether Type, Vlan ID, Vlan Priority, MPLS Label, MPLS Traffic Class, IPv6 Src, IPv6 Dst, IPv6 Traffic Class, IPv6 Next Header, IPv6 Flow Label, TCP/UDP/SCTP Src Port/ICMP Type, TCP/UDP/SCTP Dst Port/ICMP Code, Hop-by-Hop Header Options, Routing Type, Segment Left, Type Specific Data, and Destination Options Header Options.

 Specifically, the Controller in the OpenFlow system architecture may send the IPv6 flow table to the switch controlled by the IPv6 flow table in advance. Specifically, the switch may send the two forms of the IPv6 flow table to the switch. It can be understood by those skilled in the art that the Controller can issue different IPv6 flow tables for different switches controlled by the controller.

 After determining that the data packet is an IPv6 packet, the switch in the OpenFlow system architecture may extract the content of the field from the IPv6 packet, and then extract the content of the field with the field content that needs to be matched in the pre-stored IPv6 flow table. Make a match.

 It should be noted that the switch can extract all the contents of the field included in the IPv6 packet, and only match the content of the field to be matched with the entry in the IPv6 flow table, or extract only the required matching. The content of the field matches the entry in the IPv6 flow table.

 In a specific implementation, the switch may extract the packet entry field, the link layer source address field, the link layer destination address field, and the link in the data packet before determining whether the received data packet is an IPv6 packet. The content of the layer data type field is similar to the process of IPv4 in the OpenFlow system architecture, and is not described here. After determining that the data is an IPv6 packet, the switch can extract the IPv6 source address field, the IPv6 destination address field, the IPv6 traffic type field, the IPv6 next header field, the IPv6 flow label field, and the transport layer source in the IPv6 packet. The port or ICMP type field, the transport layer destination port, or the ICMP code field. If the IPv6 packet has an extension header, the option field of the hop-by-hop extension header and the route type field of the route extension header may also be extracted in the IPv6 extension header. , the remaining slice field, the type specification data field, and the option field of the destination option header. Through the above process, the switch can complete the extraction of the field contents in the IPv6 message.

First, before matching the contents of the required matching field with the entries in the IPv6 flow table, the switch may first apply the extracted field content to generate a flow table matching structure, and then generate the data. The formed flow table matching structure matches the content of the field that needs to be matched in the IPv6 flow table.

 Step 103: Perform corresponding processing on the IPv6 packet according to the matching result.

 After the switch obtains the matching result, the IPv6 4 message can be processed according to the matching result.

 For example, if the matching result is successful, the switch can perform an IPv6 flow table corresponding to the processing operation of the IPv6 packet. The Instruction can include:

 If the IPv6 flow table is cascaded, the operation of the next-level IPv6 flow table is associated with the IPv6 packet forwarding operation.

 Change the set field action of the IPv6 packet, for example, add the IPv6 source address, IPv6 destination address, IPv6 Traffic Class, and IPv6 Flow Table settings.

 If the matching result is unsuccessful, the switch can perform the preset operation to process the IPv6 packet, for example, discarding the IPv6 text or sending the IPv6^ message to the Controller.

 In this embodiment, the IPv6 flow table structure supporting the IPv6 packet is pre-defined in the control server of the OpenFlow system architecture, and the IPv6 flow table is delivered to the packet forwarding device of the OpenFlow system architecture. After receiving the data packet, the packet forwarding device may determine, according to the link layer data type field included in the data packet, whether the data packet is an IPv6 packet, and if it is an IPv6 packet, the packet forwarding device The content of the field included in the IPv6 packet may be matched with the content of the field in the stored IPv6 flow table, and the IPv6 packet is processed according to the matching result. Therefore, this embodiment can enable the packet forwarding device of the OpenFlow system architecture to support IPv6 packets, and expand the OpenFlow system architecture.

 The IPv4 packet is already supported in the existing OpenFlow system architecture. On the basis of the technical solution described in the foregoing embodiment of the present invention, the OpenFlow system architecture can support IPv6 packets. Therefore, for the Swtich in the OpenFlow system architecture. It is said that if it needs to support IPv6 packets and IPv4 packets, it needs to perform double-stack operation on IPv6 packets and IPv4 packets. The IPv4 flow table and the IPv6 flow table can be delivered to the switch by the controller in advance. . The dual stack operation will be described in detail below using an embodiment.

 2 is a flowchart of Embodiment 2 of a data packet processing method according to the present invention. As shown in FIG. 2, the method in this embodiment may include:

Step 201: Receive a data packet. Step 202: Initialize content of a message entry field, a link layer source address field, a link layer destination address field, and a link layer data type field in the flow table matching structure.

 Specifically, the initialization operation may be an Ingress Port field, a link layer source address (Ether Src) field, a link layer destination address (Ether Dst) field, and a link layer in the flow table matching structure. The Ether Type field is initialized to the corresponding value in the data, and the initial value of the remaining fields in the flow table matching structure can be set to zero.

 It should be noted that, in this embodiment, only a specific implementation manner in which all field contents are extracted and a flow table matching structure is adopted is taken as an example. Those skilled in the art can understand that only the flow table matching structure is used, and only the field content is used. This technical solution can also be implemented by extracting and performing subsequent matching operations.

 Step 203: Whether the next header is Vlan, if yes, execute step 204, otherwise step 206 is performed. Whether it is Vlan. For example, if the content of the Ether Type is 0x8100 or 0x88a8, the next header is Vlan.

 Step 204: Extract the Vlan ID and Vlan Priority fields, and continue processing using the Ether Type after the last Vlan header.

 After the switch determines that the next header is Vlan, it can extract the Vlan ID and Vlan Priority fields from the data packet. Subsequent Steps 207 When using Ether Type for processing, use the Ether Type after the last Vlan header.

 Step 205: Skip the remaining Vlan headers and perform step 206.

 Step 206: Whether the switch supports MPLS. If yes, go to step 207. Otherwise, go to step 210.

 It should be noted that this step is an optional step. If the switch supports MPLS by default, the next step can be omitted.

 Step 207: Whether the next header is an MPLS shim header, if yes, go to step 208; otherwise, go to step 210.

The switch can determine whether the next 4-head is MPLS by determining the content of the Ether Type. For example, if the content of the Ether Type is 0x8848 or 0x8847, the next one is MPLS. Step 208: Extract the Mpls label and the Mpls Traffic Class.

 Step 209: Skip the remaining MPLS headers and perform step 214.

 For MPLS, the default processing mode of the switch is to ignore the first MPLS label and then skip all the remaining MPLS labels and process the MPLS payload packet header.

 Step 210: Whether the next header is an IPv6 header, if yes, go to step 211, otherwise go to step 212.

 The switch can determine whether the next header is an IPv6 header by determining the content of the Ether Type. For example, if the content of the Ether Type is 0x86DD, the next header is the IPv6 header.

 Step 211: Perform IPv6 packet processing, and perform step 214.

 In the step 211, the IPv6 packet can be processed by using the method described in the foregoing Embodiment 1, and details are not described herein.

 Step 212: Whether the next header is an IPv4 header, if yes, step 213 is performed, otherwise it ends.

 If the switch determines that the next header is not an IPv6 header, it can further determine whether the header is an IPv4 header. Specifically, the switch can also determine whether the next header is an IPv4 header by determining the content of the Ether Type. For example, if the content of the Ether Type is 0x0800, the header is an IPv4 header.

 Step 213: Perform: ^¥4 "3⁄4" processing, and perform step 214.

 It should be noted that the sequence between the foregoing steps 210 to 211 and the steps 212 to 213 may be reversed, that is, whether the IPv4 packet is determined first, and then it is determined whether the packet is an IPv6 packet, or the foregoing step 210 and step 212 may be performed in combination. That is, the switch can determine whether the data packet is an IPv4 packet or an IPv6 packet by using the value of the Ether Type.

 Step 214: Determine a flow table to be used according to the flow table type value identification, and use the extracted related field to perform a flow table query.

Specifically, the related fields that are extracted may be filled in the corresponding fields of the flow table matching structure, and then the switch may identify the flow table to be used according to the value of the flow table type. If the data packet is an IPv6 packet, The switch can match the flow table matching structure with the IPv6 flow table for flow table query. If the data packet is an IPv4 packet, the switch can match the flow table matching structure with IPv4. The flow table performs flow table query matching.

 In the technical solution of the embodiment, the flow table type value is defined in the IPv6 flow table, and the flow table type value is different from the flow table type value of the IPv4 flow table, so that the IPv6 flow table and the IPv4 flow table can be distinguished by the flow table type value. Flow table.

 Based on the embodiment shown in FIG. 1, the present embodiment further describes the dual-stack operation of IPv4 4 and IPv6 messages in a detailed manner, and is compatible with the existing OpenFlow system architecture.

 The process of performing IPv6 packet processing in step 211 in the embodiment shown in FIG. 2 is described in detail below by using a more specific embodiment.

 FIG. 3 is a flowchart of Embodiment 3 of a data packet processing method according to the present invention. As shown in FIG. 3, the method in this embodiment may include:

 Step 301: Extract an IPv6 source address, a destination address, a Traffic Class, a Next header, and a Flow label.

 Step 302: Whether the next header is an IPv6 extension header, if yes, step 303 is performed, otherwise step 309 is performed.

 Step 303: Whether the next header is a Hop-by-Hop header, if yes, step 304 is performed; otherwise, step 305 is performed.

 The Switch can determine whether the next header is a Hop-by-Hop header by determining whether the IP v6 Next Header is equal to zero.

 Step 304: Extract the Options field of the Hop-by-Hop Header, and perform step 302. Step 305: Whether the next header is a Routing Header extension header, if yes, executing step 306, otherwise performing step 307.

 The switch can determine whether the next header is a Routing Header extension header by determining whether the IPv6 Next Header is equal to 43.

 Step 306: Extract the Routing Type, Segment Left, and Type Specific Data fields of the IPv6 routing extension header, and perform step 302.

 Step 307: Whether the next header is a Destination Options Header extension header, if yes, go to step 308; otherwise, go to step 302.

 The switch can determine if the next header is a Destination Options Header extension by determining if the IPv6 Next Header is equal to 60.

Step 308, extract the options field of the Destination Options Header, and execute the step Step 302.

 Step 309: Whether the IPv6 Next Header is equal to 6, 17 or 132, if yes, go to step 310, otherwise go to step 311.

 Step 310: Extract the TCP/UDP/SCTP Src Port/Dst Port, and go to step 313. If the IPv6 Next Header is equal to 6, extract the TCP Src Port/Dst Port if IPv6 Next

If Header is equal to 17, the UDP Src Port/Dst Port is extracted. If the IPv6 Next Header is equal to 132, the SCTP Src Port/Dst Port is extracted.

 Step 311: Whether the IP Next Header is equal to 58, if yes, execute step 312, otherwise step 313 is performed.

 Step 312: Extract the ICMP Type and Code, and perform step 313.

 Step 313: Perform an flow table query by using the extracted field.

 The foregoing embodiment of the present invention can enable the packet forwarding device of the OpenFlow system architecture to support the IPv6 packet. Moreover, the technical solution of the embodiment of the present invention can support the dual stack operation and expand the OpenFlow system architecture.

 4 is a schematic structural diagram of Embodiment 1 of a packet forwarding device according to the present invention. As shown in FIG. 4, the device in this embodiment may include: a determining module 11, a matching module 12, and a processing module 13, where the determining module 11 is configured to Determining, according to the link layer data type field included in the data packet, whether the data packet is an IPv6 packet, and the matching module 12, configured to: if the data packet is an IPv6 packet, the IPv6 packet The content of the field matches the content of the field that needs to be matched in the IPv6 flow table that is sent by the control server. The IPv6 flow table includes at least one of the following fields: a message entry field, a metadata field, and a link layer source. Address field, link layer destination address field, link layer data type field, virtual local area network identification field, virtual local area network priority field, MPLS label field, MPLS traffic type field, IPv6 source address field, IPv6 destination address field, IPv6 traffic type Field, IPv6 Next Header Field, IPv6 Flow Label Field, Transport Layer Source Port or ICMP Type Field, Transport Layer The destination port or the ICMP code field; the processing module 13 is configured to perform corresponding processing on the IPv6 packet according to the matching result.

 In this embodiment, the processing module 13 may be specifically configured to: if the matching is successful, perform the processing operation corresponding to the IPv6 flow table on the IPv6 packet; if the matching is unsuccessful, discard the IPv6 packet. Or sending the IPv6 packet to the control server.

The packet forwarding device in this embodiment may be a switch in an OpenFlow system architecture or Router. The packet forwarding device of this embodiment may be used to implement the technical solution of the method embodiment shown in FIG. 1. The implementation principle and technical effects are similar, and details are not described herein again.

 5 is a schematic structural diagram of Embodiment 2 of a packet forwarding device according to the present invention. As shown in FIG. 5, the device in this embodiment may further include: an extraction module 14 for determining a module, based on the device shown in FIG. Determining, before determining whether the data packet is an IPv6 packet, extracting, in the data packet, a content of a message entry field, a link layer source address field, a link layer destination address field, and a link layer data type field; After the determining module determines that the data packet is an IPv6 packet, extracting an IPv6 source address field, an IPv6 destination address field, an IPv6 traffic type field, an IPv6 next header field, and an IPv6 flow label field in the IPv6 packet. , transport layer source port or ICMP type field, transport layer destination port or ICMP code field, option field for hop-by-hop extension header, route type field for route extension header, remaining slice field, type specification data field, option for destination option header a matching module 12, specifically configured to: use the content of the field extracted by the extraction module and the IPv6 flow table Field contents need to match to match.

 Further, the matching module 12 may include: a generating unit 121 and a matching unit 122, where the generating unit 121 is configured to generate the flow table matching structure by using the field content extracted by the extracting module 14; the matching unit 122 is configured to use the matching table The matching structure matches the content of the field that needs to match in the IPv6 flow table.

 In order to support the dual-stack operation of the IPv6 packet and the IPv4 packet, the device in this embodiment may further include: a flow table identification module 15 configured to use the flow table included in the IPv6 flow table before the matching module performs matching The type value identifies the IPv6 flow table from the IPv6 flow table and the IPv4 flow table.

 The device of this embodiment may further include: a flow table storage module 16, configured to receive an IPv6 flow table sent by the control server, where each field in the IPv6 flow table includes a type, a length, and a value of the field.

 The device in this embodiment can be used to implement the technical solution of the method embodiment shown in FIG. 2 or FIG. 3, and the implementation principle is similar, and details are not described herein again.

FIG. 6 is a schematic structural diagram of an embodiment of a data packet processing system according to the present invention. As shown in FIG. 6, the system in this embodiment may be an OpenFlow system architecture. In this embodiment, the system includes: a control server 1 and at least one packet. The text forwarding device 2, in the present embodiment, two message forwarding devices are shown. The packet forwarding device 2 in this embodiment may adopt the structure shown in FIG. 4 or FIG. The technical solution described in any one of FIG. 1 to FIG. 3 is specifically implemented, and the implementation principle is similar, and details are not described herein again.

 A person skilled in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by using hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed. The foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

 It should be noted that the above embodiments are only for explaining the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: The technical solutions described in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; and the modifications or substitutions do not deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

Claim  A data packet processing method, comprising:  Determining, according to the link layer data type field included in the data packet, whether the data packet is an IPv6 packet;  If the data packet is an IPv6 packet, the content of the field in the IPv6 packet is matched with the content of the field that is required to be matched in the IPv6 flow table that is sent by the control server, and the IPv6 flow table includes the following. Said at least one field:  Message entry field, metadata field, link layer source address field, link layer destination address field, link layer data type field, virtual local area network identification field, virtual local area network priority field, MPLS label field, MPLS traffic type field, IPv6 source address field, IPv6 destination address field, IPv6 traffic type field, IPv6 next header field, IPv6 flow label field, transport layer source port or ICMP type field, transport layer destination port or ICMP code field;  The IPv6 text is processed correspondingly according to the matching result.  2. The method according to claim 1, wherein the IPv6 flow table further comprises at least one of the following fields:  The option field of the hop-by-hop extension header, the route type field of the route extension header, the remaining slice field, the type specification data field, and the option field of the destination option header.  The method according to claim 2, wherein, before determining whether the data packet is an IPv6 packet, according to the link layer data type field included in the data packet, the method further includes:  Extracting content of a message entry field, a link layer source address field, a link layer address field, and a link layer data type field in the data packet;  After determining whether the data packet is an IPv6 packet, the method further includes:  Extracting an IPv6 source address field in the IPv6 packet, an IPv6 destination address field, an IPv6 traffic type field, an IPv6 next header field, an IPv6 flow label field, a transport layer source port or an ICMP type field, and a transmission The destination port or ICMP code field, the option field of the hop-by-hop extension header, the route type field of the route extension header, the remaining slice field, the type specification data field, and the option field of the destination option header; The matching the content of the field in the IPv6 packet with the content of the field that needs to be matched in the IPv6 flow table that is sent by the control server in advance includes: The extracted content of the above field is matched with the content of the field that needs to match in the IPv6 flow table.  The method according to claim 3, wherein the matching the content of the field to be matched with the content of the field in the IPv6 flow table, including:  Applying the extracted field content to generate a flow table matching structure, and matching the flow table matching structure with the required matching field content in the IPv6 flow table.  The method according to claim 4, wherein the content of the field extracted by the application generates a flow table matching structure, including:  Initializing, in the data packet, a message entry field, a link layer source address field, a link layer destination address field, and a link layer data type field into a corresponding field of the flow table matching structure;  Filling in the flow table matching structure, the IPv6 source address field, the IPv6 destination address field, the IPv6 traffic type field, the IPv6 next header field, the content of the IPv6 flow label field, the option field of the hop-by-hop extension header, and the route extension header. Route type field, remaining slice field, type specified data field;  Filling in the transport layer source port and the destination port in the flow table matching structure according to the content of the IPv6 next header field, or filling in the ICMP type field and the code field in the flow table matching structure.  The method according to claim 1, wherein, before the matching, in the field of the field in the IPv6 flow table, the content of the field in the IPv6 flow table that is previously delivered by the control server is matched, :  And determining, according to the flow table type value included in the IPv6 flow table, the IPv6 flow table from the IPv6 flow table and the IPv4 flow table.  The method according to claim 1, wherein before the determining whether the data packet is an IPv6 packet, the method further includes:  And receiving an IPv6 flow table sent by the control server, where each field in the IPv6 flow table includes a type, a length, and a value of the field.  The method according to any one of claims 1 to 7, wherein the processing the IPv6 ^ 艮 based on the matching result comprises: If the matching is successful, performing processing corresponding to the IPv6 flow table on the IPv6 packet Operation  If the match is unsuccessful, the IPv6 packet is discarded or the IPv6 packet is sent to the control server.  9. The method according to claim 8, wherein the corresponding processing operation comprises:  Associate the operations of the next-level IPv6 flow table, port forwarding operations, and set domain operations.  10. A packet forwarding device, comprising:  a determining module, configured to determine, according to a link layer data type field included in the data packet, whether the data packet is an IPv6 packet;  a matching module, configured to: if the data packet is an IPv6 packet, match the field content in the IPv6 packet with a field content that needs to be matched in an IPv6 flow table that is sent by the control server in advance, the IPv6 The flow table contains at least one of the following fields:  Message entry field, metadata field, link layer source address field, link layer destination address field, link layer data type field, virtual local area network identification field, virtual local area network priority field, MPLS label field, MPLS traffic type field, IPv6 source address field, IPv6 destination address field, IPv6 traffic type field, IPv6 next header field, IPv6 flow label field, transport layer source port or ICMP type field, transport layer destination port or ICMP code field;  The processing module is configured to perform corresponding processing on the IPv6 packet according to the matching result. The device according to claim 10, further comprising:  And an extracting module, configured to: before the determining module determines whether the data packet is an IPv6 packet, extract a packet entry field, a link layer source address field, a link layer destination address field, and a link layer source address field in the data packet The content of the link layer data type field; after the determining module determines that the data packet is an IPv6 packet, extracts the following fields in the IPv6 packet: an IPv6 source address field, an IPv6 destination address field, and an IPv6 traffic. Type field; IPv6 next header field; IPv6 flow label field; transport layer source port or ICMP type field; transport layer destination port or ICMP code field; option field of hop-by-hop extension header; route type field of route extension header; Field; type specifies the data field; the option field of the destination option header;  The matching module is specifically configured to match the content of the field extracted by the extraction module with the content of the field that needs to be matched in the IPv6 flow table. The device according to claim 11, wherein the matching module comprises: a generating unit, configured to generate a flow table matching structure by using the foregoing field content extracted by the extracting module;  And a matching unit, configured to match the flow table matching structure with a field content that needs to match in the IPv6 flow table.  13. The device according to claim 10, further comprising:  The flow table identification module is configured to identify, by the matching module, the IPv6 flow table from the IPv6 flow table and the IPv4 flow table according to the flow table type value included in the IPv6 flow table.  The device according to claim 10, further comprising:  The flow table storage module is configured to receive an IPv6 flow table sent by the control server, where each field in the IPv6 flow table includes a type, a length, and a value of the field.  The device according to any one of claims 10 to 14, wherein the processing module is configured to perform processing corresponding to the IPv6 flow table on the IPv6 packet if the matching is successful. If the match is unsuccessful, the IPv6 file is discarded or the IPv6 message is sent to the control server.  A data message processing system, comprising: a control server and at least one message forwarding device, wherein the message forwarding device uses the message forwarding device according to any one of claims 10 to 15.