Automatic detecting and driving loading method of user mode network card in Linux system

Abstract

The invention provides an automatic detecting and driving loading method of a user mode network card in a Linux system. In the Linux inner core initialization phase, a PCI (peripheral component interconnect) bus registers each drive and scans equipment mounted on the PCI bus; each drive respectively traverses the equipment mounted on the PCI bus, whether the drive is matched with the equipment or not is judged, if the drive is matched with the equipment, whether the category code of the equipment is matched with the category code of network card equipment or not is continuously judged, and if not, the equipment is initialized; and if the category code of the equipment is matched with the category code of the network card equipment, the equipment is distinguished as a network card, the information of the network card is stored, the initialization of the network card is given up, in addition, the user mode obtains the information of the network card, and the corresponding network card driving is loaded according to the information of the network card. The automatic detecting and driving loading method has the advantages that the automatic loading and the driving loading of the network card are respectively placed in the user mode, and high overhead on the system invoking and the data packet copy due to the inner core mode driving is eliminated.

Description

technical field [0001] The invention relates to the field of computer operating systems, in particular to a method for automatic detection and driver loading of a user-mode network card based on a kernel mode under a Linux system. Background technique [0002] With the continuous development of technology, the CPU resources that have been greatly relieved in the early stage of the multi-core era are not enough for network packet processing equipment equipped with 10GE or more network cards. certain CPU resources (especially the X86 architecture); the performance loss of data copying from the kernel mode to the user mode of the Linux operating system will also become a stumbling block for the packet processing equipment to fully utilize the multi-core CPU; therefore, how to eliminate the kernel mode driver belt The high overhead of incoming system calls and data packet copying has become the main research area in the industry. SUMMARY OF THE INVENTION [0003] Aiming at th...

AI Technical Summary

Problems solved by technology

[0002] With the continuous development of technology, the CPU resources that were greatly relieved in the early days of the multi-core era appear to be powerless on network packet processing devices equipped with 10GE or more network cards; the reason is that a large number of interrupts are consumed due to the impact of a large number of packets Certain CPU resources (especially the X86 architecture); the performance loss of the data copy from the kernel mode to the user mode of the Linux operating system will also become a roadblock for the packet processing device to make full use of the multi-core CPU; therefore, how to eliminate the kernel mode driver belt The high overhead of incoming system calls and packet copying has become a major research area in the industry

Images