Protocol processing stack for use with intelligent network interface device

• US 6,697,868 B2
• Filed: 07/29/2002
• Issued: 02/24/2004
• Est. Priority Date: 02/28/2000
• Status: Expired due to Term

• Current Assignee: Alacritech, Inc.
• Original Assignee: Alacritech, Inc.
• Inventors: Higgen, David A., Philbrick, Clive M., Boucher, Laurence B., Craft, Peter K.
• Primary Examiner(s): Maung, Zarni
• Application Number:
  US10/208,093
• Publication Number:
  US 20030079033A1
• Time in Patent Office: 575 Days
• Field of Search: 709/230, 709/250, 709/236, 709/243, 709/228, 709/238
• US Class Current: 709/230
• CPC Class Codes: G02B 7/36 using image sharpness techniques , e.g. image processing techniques for generating autofocus signals image data processing per se G06T; in cameras having a solid state image sensor H04N23/67
• CPC Class Codes: H04L 49/90 Buffering arrangements
• CPC Class Codes: H04L 49/9042 Separate storage for different parts of the packet, e.g. header and payload
• CPC Class Codes: H04L 49/9063 Intermediate storage in different physical parts of a node or terminal
• CPC Class Codes: H04L 61/00 Network arrangements, protocols or services for addressing or naming
• CPC Class Codes: H04L 61/10 of different types
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/34 involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416
• CPC Class Codes: H04L 67/62 Establishing a time schedule for servicing the requests
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context
• CPC Class Codes: H04L 69/08 Protocols for interworking; Protocol conversion
• CPC Class Codes: H04L 69/12 Protocol engines
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
• CPC Class Codes: H04L 69/161 Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
• CPC Class Codes: H04L 69/163 In-band adaptation of TCP data exchange; In-band control procedures
• CPC Class Codes: H04L 69/166 IP fragmentation; TCP segmentation
• CPC Class Codes: H04L 69/22 Parsing or analysis of headers
• CPC Class Codes: H04L 69/32 Architecture of open systems interconnection [OSI] 7-layer type protocol stacks, e.g. the interfaces between the data link level and the physical level
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A host CPU runs a network protocol processing stack that provides instructions not only to process network messages but also to allocate processing of certain network messages to a specialized network communication device, offloading some of the most time consuming protocol processing from the host CPU to the network communication device. By allocating common and time consuming network processes to the device, while retaining the ability to handle less time intensive and more varied processing on the host stack, the network communication device can be relatively simple and cost effective. The host CPU, operating according to instructions from the stack, and the network communication device together determine whether and to what extent a given message is processed by the host CPU or by the network communication device.

Claims

1. A set of instructions executable on a processor, the set of instructions being for performing steps comprising:

establishing a TCP connection, the TCP connection being at least in part identified by a TCP source port, TCP destination port, IP source address, and IP destination address; and

offloading the TCP connection from the processor to an intelligent TCP offload mechanism.

2. The set of instructions of claim 1, wherein the TCP offload mechanism is a network interface card (NIC), and wherein the set of executable instructions are part of an operating system program executing on a host computer, the processor being a central processing unit (CPU) of the host computer.

3. The set of instructions of claim 1, wherein the set of instructions includes a protocol processing stack.

4. The set of instructions of claim 1, wherein the offloading includes transferring control of the TCP connection from the processor to the TCP offload mechanism.

5. The set of instructions of claim 1, wherein the offloading includes communicating a status of the TCP connection from the processor to the TCP offload mechanism.

6. The set of instructions of claim 1, wherein the offloading includes fast-path processing of the TCP connection.

7. The set of instructions of claim 1, wherein the offloading includes data path processing of the TCP connection.

8. The set of instructions of claim 1, wherein a message is communicated via the TCP connection, and wherein the offloading involves protocol processing of the message.

9. The set of instructions of claim 1, wherein a message is communicated via the TCP connection, and wherein the offloading involves fast-path processing of the message.

10. The set of instructions of claim 1, wherein a message is communicated via the TCP connection, and wherein the offloading involves data path processing of the message.

11. The set of instructions of claim 1, wherein the processor is a processor of a host, and wherein the TCP offload mechanism is a communication processing device (CPD), the CPD being integrated into the host.

12. The set of instructions of claim 1, wherein the offloading involves a first phase and a second phase, wherein the first phase involves causing the TCP offload mechanism to queue subsequent incoming frames for the TCP connection while the processor is in control of the TCP connection, the subsequent incoming frames not being passed to the processor during the first phase, and wherein the second phase involves passing control of the TCP connection from the processor to the TCP offload mechanism.

13. A set of instructions executable on a host computer, the set of instructions being for performing steps comprising:

sending a first communication from the host computer to a TCP offload device, the first communication causing the TCP offload device to store subsequently received frames for a TCP connection, the subsequently received frames being received onto the TCP offload device from a network;

receiving a second communication from the TCP offload device by the host computer; and

in response to the receiving of the second communication sending a third communication from the host computer to the TCP offload device, the third communication causing control of the TCP connection to be passed from the host computer to the TCP offload device.

14. The set of instructions of claim 13, wherein the set of instructions comprises a driver and a stack of protocol processing layers, and wherein the TCP offload device is a network interface card (NIC).

15. The set of instructions of claim 13, wherein the sending of the third communication includes sending a memory descriptor list (MDL) from the host computer to the TCP offload device, the MDL identifying a destination in a memory on the host computer.

16. A set of instructions executable on a host computer for performing steps comprising:

determining whether a TCP offload device coupled to the host computer has fast-path capabilities;

obtaining from an application program an indication of a destination on the host computer, the destination being a place in a memory on the host computer where data of a TCP connection is to be placed;

passing control of the TCP connection to the TCP offload device; and

receiving statistics information from the TCP offload device, the statistics information being statistics information on the TCP connection.

17. The set of instructions of claim 16, wherein the statistics information includes a number of segments received by the TCP offload device.

18. The set of instructions of claim 16, wherein the set of instructions is also for performing the further steps of:

receiving control of the TCP connection back from the TCP offload device; and

receiving a communication from the TCP offload device, the communication containing a residual field, the residual field indicating an amount of the data of the TCP connection that remains to be placed in the destination on the host computer.

19. The set of instructions of claim 16, wherein the control of the TCP connection is passed to the TCP offload device in a plural-phase handout process, a first phase of the handout process including causing the TCP offload device to queue subsequent message packets received onto the TCP offload device for the TCP connection such that the subsequent message packets do not pass to the host computer during the first phase, a second phase of the handout process including passing the indication of the destination to the TCP offload device.

20. The set of instructions of claim 16, wherein the indication of the destination is a memory descriptor list (MDL).

21. An operating system that passes control of a TCP connection from a host computer to a TCP offload device coupled to the host computer, wherein after said control of the TCP connection is passed to the TCP offload device the TCP offload device performs all or substantially all TCP protocol processing on network frames received onto the TCP offload device for the TCP connection such that the operating system and the host computer perform no or substantially no TCP protocol processing on the network frames after said control is passed.

22. The operating system of claim 21, wherein the operating system performed some TCP protocol processing on the TCP connection prior to said control being passed to the TCP offload device.

23. The operating system of claim 21, wherein the operating system established the TCP connection prior to said control being passed to the TCP offload device.