WO2023115852A1 - Pcie-based communication method and apparatus, and computer device and readable storage medium - Google Patents

Abstract

The present application relates to a PCIE-based communication method and apparatus, and a computer device and a readable storage medium. The method comprises: when a host side identifies a PCIE endpoint device, a PCIE driver establishing a first mapping relationship between queue numbers of hardware queues and channel numbers of virtual channels, wherein each hardware queue is a hardware access channel of the PCIE endpoint device (S202); the PCIE driver mounting each upper-layer function driver, and allocating a corresponding virtual channel to each upper-layer function driver, such that the upper-layer function driver issues first service data by means of the corresponding virtual channel (S204); and after receiving the first service data, the PCIE driver determining from the first mapping relationship a first target queue number which corresponds to a first target channel number, and sending the first service data to a hardware queue which corresponds to the first target queue number, wherein the first target channel number is a channel number of a virtual channel corresponding to the upper-layer function driver which issues the first service data (S206).

Description

PCIE-based communication method, device, computer equipment and readable storage medium

Cross References to Related Applications

This application claims the priority of the Chinese patent application submitted to the China Patent Office on December 24, 2021, with the application number 2021116033043, and the title of the invention is "PCIE-based communication method, device, computer equipment, and readable storage medium", all of which The contents are incorporated by reference in this application.

technical field

The present application relates to the technical field of communication, in particular to a PCIE-based communication method, device, computer equipment and readable storage medium.

Background technique

Currently, in WWAN (Wireless Wide Area Network, wireless wide area network) products, there are multiple function drivers configured on the host side. In order to realize the communication between each function driver and the PCIE (Peripheral Component Interconnect Express, high-speed serial computer expansion bus standard) endpoint device, the prior art will configure a UDE (USB Device Emulation, USB device simulation) driver on the host side to The PCIE device is simulated as a USB (Universal Serial Bus, Universal Serial Bus) device, and then provides ports to mount Microsoft's MBIM (Mobile Broadband Interface Model, Mobile Broadband Interface Model), ACM and other drivers, as well as GNSS (Global Navigation Satellite System, global satellite navigation system) to support various services required by WWAN products.

However, under the requirements of the new generation of 5G communication, the traditional driving method has been difficult to meet the high-speed requirements of high-performance products.

Contents of the invention

According to various embodiments of the present application, a PCIE-based communication method, device, computer equipment, and readable storage medium are provided, which can complete the data communication between the host side and the PCIE endpoint device through PCIE, so that 5G products can be used in The effect of high speed, large bandwidth, and low latency can be achieved on computer equipment.

In a first aspect, the present application provides a communication method based on PCIE. The method is applied to the host side, and the host side is configured with an upper layer function driver and a kernel driver, and the kernel driver includes a PCIE driver. The methods include:

When the host side recognizes the PCIE endpoint device, the PCIE drives the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel; wherein, the hardware queue is the hardware of the PCIE endpoint device access channel;

The PCIE driver mounts each of the upper-layer function drivers, and assigns a corresponding virtual channel for each of the upper-layer function drivers, so that the upper-layer function drivers deliver first business data through the corresponding virtual channels;

When the PCIE driver receives the first business data, it determines the first target queue number corresponding to the first target channel number from the first mapping relationship, and sends the first business data to the In the hardware queue corresponding to the first target queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver that delivers the first service data.

In one of the embodiments, the kernel driver also includes a network adapter driver. The method also includes:

The PCIE driver mounts the network adapter driver, and allocates a corresponding virtual channel for the network adapter driver, so that the network adapter driver sends the second service data through the corresponding virtual channel;

When the PCIE driver receives the second business data, it determines the second target queue number corresponding to the second target channel number from the first mapping relationship, and sends the second business data to the In the hardware queue corresponding to the second target queue number; wherein, the second target channel number is the channel number of the virtual channel corresponding to the network adapter driver.

In one of the embodiments, the method further includes: the network adapter driver calls a preset function interface to deliver the second service data to the PCIE driver;

Wherein, the preset function interface is a function interface generated according to the universal unique identification code driven by the PCIE and the universal unique identification code driven by the network adapter.

In one of the embodiments, the second service data includes sending IP data and sending MBIM protocol data. The network adapter drives the call of the preset function interface to drive the step of sending the second service data to the PCIE, including:

The network adapter driver calls the preset function interface to send the issued IP data to the PCIE driver;

The network adapter driver generates a data write request according to the second target channel number and the issued MBIM protocol data, and sends the data write request to the PCIE driver, so as to send the data write request to the PCIE driver. Send MBIM protocol data.

In one of the embodiments, the method further includes: when the PCIE driver obtains the first return data sent by the PCIE endpoint device, calling a preset function interface to send the data to the network adapter driver The first return data; wherein, the preset function interface is a function interface generated according to the UUID code driven by the PCIE and the UUID code driven by the network adapter.

In one of the embodiments, the first returned data is returned IP data or returned MBIM protocol data. The PCIE driver calls the preset function interface to drive the step of sending the second service data to the network adapter, including:

When the first return data is the return IP data, the PCIE driver calls the preset function interface to send the return IP data to the network adapter driver;

When the first returned data is the returned MBIM data, the PCIE driver writes the returned MBIM data into a corresponding memory queue;

The PCIE driver sends the returned MBIM data to the network adapter driver when receiving the data read request sent by the network adapter driver.

In one of the embodiments, the PCIE driver mounts each of the upper-layer function drivers, and the step of assigning a corresponding virtual channel for each of the upper-layer function drivers includes:

Described PCIE drives generation child node; The quantity of described child node is determined according to the quantity that upper layer function drives;

The PCIE driver mounts each of the upper-layer function drivers through the sub-node; wherein, different upper-layer function drivers correspond to different sub-nodes;

Described PCIE drives and assigns corresponding virtual channel for each described upper layer function driver, and establishes the second mapping relation between the channel number of child node and virtual channel;

Before the step of determining the first target queue number corresponding to the first target channel number from the first mapping relationship, it also includes:

The PCIE driver determines the first target channel number from the second mapping relationship according to the child node corresponding to the upper layer function driver that delivers the first service data.

In one of the embodiments, the method further includes: the PCIE driver acquires the working mode of the host side, and derives a corresponding sub-node according to the working mode.

In one of the embodiments, the step of sending the first business data into the hardware queue corresponding to the first target queue number includes: the PCIE driver according to the first target channel number and the first The service data generates a data packet, and sends the data packet into the hardware queue corresponding to the first target queue number.

In one embodiment, the method also includes:

The PCIE driver determines the target upper layer function driver corresponding to the second return data when the second return data sent by the PCIE endpoint device is obtained;

The PCIE driver writes the second return data into the memory queue corresponding to the target upper layer function driver, and when receiving the data read request sent by the target upper layer function driver, sends the data to the target The upper layer function driver sends the second return data.

In a second aspect, the present application also provides a PCIE-based communication device. The device includes a kernel driver configured on the host side, the kernel driver includes a PCIE driver, and the host side is also configured with an upper layer function driver. The PCIE driver includes:

The first mapping relationship establishment module is used to establish the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel when the host side recognizes the PCIE endpoint device; wherein the hardware queue is The hardware access channel of the PCIE endpoint device;

An allocation module, configured to mount each of the upper-layer function drivers, and assign a corresponding virtual channel to each of the upper-layer function drivers, so that the upper-layer function drivers deliver the first service data through the corresponding virtual channels;

A business data writing module, configured to determine the first target queue number corresponding to the first target channel number from the first mapping relationship when the first business data is received, and write the first business data The data is sent to the hardware queue corresponding to the first target queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver that delivers the first service data.

In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

When the host side recognizes the PCIE endpoint device, the PCIE drives the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel; wherein, the hardware queue is the hardware of the PCIE endpoint device access channel;

The PCIE driver mounts each of the upper-layer function drivers, and assigns a corresponding virtual channel for each of the upper-layer function drivers, so that the upper-layer function drivers deliver first business data through the corresponding virtual channels;

When the PCIE driver receives the first business data, it determines the first target queue number corresponding to the first target channel number from the first mapping relationship, and sends the first business data to the In the hardware queue corresponding to the first target queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver that delivers the first service data.

In one of the embodiments, the computer device further includes a PCIE endpoint device, and the PCIE endpoint device is connected to the processor through a PCIE bus.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

When the host side recognizes the PCIE endpoint device, the PCIE drives the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel; wherein, the hardware queue is the hardware of the PCIE endpoint device access channel;

The PCIE driver mounts each of the upper-layer function drivers, and assigns a corresponding virtual channel for each of the upper-layer function drivers, so that the upper-layer function drivers deliver first business data through the corresponding virtual channels;

When the PCIE driver receives the first business data, it determines the first target queue number corresponding to the first target channel number from the first mapping relationship, and sends the first business data to the In the hardware queue corresponding to the first target queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver that delivers the first service data.

The details of one or more embodiments of the invention are set forth in the accompanying drawings and the description below. Other features, objects and advantages of the invention will be apparent from the description, drawings and claims.

Description of drawings

In order to better describe and illustrate embodiments and or examples of the inventions disclosed herein, reference may be made to one or more of the accompanying drawings. The accompanying specification or examples used to describe the drawings should not be considered limiting of the scope of any of the disclosed inventions, the presently described embodiments and or examples, and the best mode of these inventions currently understood.

FIG. 1 is an architecture diagram of a host side of a WWAN product in the prior art;

Fig. 2 is the application environment figure of the communication method based on PCIE in an embodiment;

Fig. 3 is one of schematic flow charts of the communication method based on PCIE in an embodiment;

Fig. 4 is the second schematic flow chart of the communication method based on PCIE in an embodiment;

Fig. 5 is a schematic flowchart of the step of sending the second service data driven by the network adapter in one embodiment;

Fig. 6 is a schematic flow chart of the step of sending the first return data by the PCIE driver in one embodiment;

Fig. 7 is a schematic flow chart of the steps of the PCIE driver mounting the upper layer function driver in one embodiment;

FIG. 8 is a software architecture diagram of the host side of the present application in an embodiment;

Fig. 9 is a structural block diagram of a communication device based on PCIE in an embodiment;

Figure 10 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

Fig. 1 shows a structure diagram of a host side of a WWAN product in the prior art. As shown in Figure 1, in the Windows driver of the existing WWAN product, although it is a PCIE device, the host side will emulate the PCIE device as a USB device through the UDE driver, and perform data communication through the virtual USB device. Utilize the mature technology of USB to complete the work of MBIM communication, data transmission and equipment power management of WWAN products. However, under the requirements of the new generation of 5G communication, it is already difficult for USB-based communication to meet the high-speed, low-latency and large-bandwidth requirements of high-performance products. Therefore, other methods are required to achieve it.

At the same time, in the Windows driver of existing products (such as the Windows driver of 4G WWAN products), the built-in MBIM driver of Microsoft system is mostly used to realize the transmission of MBIM data, without independent development. However, in the latest 5G architecture of Windows, Microsoft designed the NetAdapterCx architecture, which only provides interface methods and interface adaptation, but does not provide a mature MBIM driver that can be used directly. For IHV (Independent Hardware Vendor, Independent Hardware Vendor), it must develop corresponding drivers in accordance with Microsoft's driver architecture requirements.

In order to solve the aforementioned problems, the present application provides a PCIE-based communication method, device, computer equipment and readable storage medium. Wherein, the PCIE driver mounts each upper-layer function driver respectively, and maps multiple hardware channels of the PCIE endpoint device into multiple virtual channels for use by each upper-layer function driver. Each upper-layer function driver can directly realize data communication with the PCIE endpoint device through the PCIE driver, without simulating the PCIE device as a USB device. In this way, the data communication between the host side and the PCIE endpoint device can be completed through PCIE, and the transmission rate can be increased, so that 5G products can achieve high speed, large bandwidth, and low delay on computer equipment, meeting the requirements of 5G products. rate requirements.

In some embodiments, the present application is also adapted to the NetAdapterCx framework of Microsoft 5G, and the network adapter driver (that is, the NetAdapter driver) is set separately from the PCIE driver, so that the hardware processing logic and business logic are layered. The main hardware logic is realized through the PCIE driver, which can reduce the workload of driving Microsoft certification.

The PCIE-based communication method provided by this application can be applied to the computer equipment shown in FIG. 2 . The computer equipment can be, but not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, and the like.

Among them, the computer device can be divided into a host side 102 and a PCIE endpoint device 104 . The host side 102 is a part for configuring and running the upper layer function driver and the kernel driver. In the architecture of a computer system, it can be divided into user layer, kernel layer and hardware layer. Wherein, the upper layer function driver refers to the function driver set in the user layer, and the kernel driver refers to the function driver set in the kernel layer, and the kernel driver may include a PCIE driver.

The host side 102 can be connected to the PCIE endpoint device 104 through a PCIE interface and/or a PCIE bus. It can be understood that the device type of the PCIE endpoint device 104 can be determined according to the actual situation, and the present application does not make specific limitations on this, as long as it is connected to the host side 102 through a PCIE interface and/or a PCIE bus. In some of the following embodiments, the present application takes the PCIE endpoint device 104 as a 5G communication module as an example for illustration.

In one embodiment, as shown in FIG. 3 , a PCIE-based communication method is provided, and the method is applied to the host side in FIG. 2 as an example for illustration. Include the following steps:

S202. When the host side recognizes the PCIE endpoint device, the PCIE driver establishes a first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel; wherein, the hardware queue is a hardware access channel of the PCIE endpoint device.

Wherein, the PCIE endpoint device will set a certain number of hardware access channels, and the hardware access channels are the "hardware queues" involved in each embodiment. It can be understood that the specific device type of the hardware queue can be determined according to the specific hardware structure of the PCIE endpoint device, which is not specifically limited in the present application. In one example, a hardware queue can be a memory device. Each hardware queue is identified by a unique queue number, so that each hardware queue can be distinguished by the queue number.

Specifically, when the host side is connected to the PCIE endpoint device, the host side can recognize the access of the PCIE endpoint device. The PCIE driver maps each hardware queue to a different virtual channel, and establishes a first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel. Further, the specific set number of virtual channels may be determined according to the amount of service data, which is not specifically limited in this application. In one embodiment, the queue number of the same hardware queue may correspond to the channel number of a virtual channel, that is, there is a one-to-one correspondence between the hardware queue and the virtual channel. In another embodiment, the queue number of the same hardware queue can correspond to the channel numbers of multiple different virtual channels, that is, there is a one-to-many correspondence between the hardware queue and the virtual channel, so when the amount of business data When the number of queues exceeds the number of hardware queues, multiple types of business data can be sent to the same hardware queue to further achieve high efficiency, large bandwidth and low latency.

In one of the embodiments, the PCIE driver can map the hardware queues into two types of virtual channels to construct data paths and control paths. Wherein, the data path is a path for transmitting communication data, and the control path is a path for transmitting control messages. The data path and the control path respectively include their own sending and receiving hardware queues to realize the sending and receiving of communication data and control messages.

S204. The PCIE driver mounts each upper-layer function driver, and assigns a corresponding virtual channel to each upper-layer function driver, so that the upper-layer function driver delivers the first service data through the corresponding virtual channel.

Among them, the upper layer function drivers include but are not limited to GNSS drivers, burning drivers, COM port drivers (which can realize functions such as AT commands, FLASH, log capture, and Coredump export), etc. The first service data refers to the service data delivered by the upper-layer function driver, which may be but not limited to IP (Internet Protocol, Internet Protocol) data and control messages.

Specifically, the PCIE driver can mount each upper-layer function driver separately, and assign a corresponding virtual channel to each upper-layer function driver, so that the upper-layer function driver can be mapped to the underlying virtual channel, and through the assigned virtual channel. data transmission. When a certain upper-layer function driver needs to send corresponding business data to the PCIE endpoint device, the upper-layer function driver can send the first business data to the PCIE driver through its corresponding virtual channel, and the PCIE driver will send the first business data to the PCIE driver after subsequent processing. A service data is sent to the PCIE endpoint device.

In one embodiment, each upper layer function driver may correspond to a different virtual channel. In another embodiment, each upper-layer function driver can correspond to multiple virtual channels, for example, the same upper-layer function driver can correspond to two virtual channels, any virtual channel is used to transmit communication data, and the other virtual channel is used for Transmit control messages.

S206, when the PCIE driver receives the first business data, determine the first target queue number corresponding to the first target channel number from the first mapping relationship, and send the first business data into the first target queue number corresponding to In the hardware queue; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver delivering the first service data.

Specifically, when the PCIE driver receives the first service data delivered by a certain upper-layer function driver, its PCIE driver can determine the channel number corresponding to the virtual channel from the first mapping relationship according to the channel number of the upper-layer function driver. The channel number corresponds to the first target queue number, and the first service data is sent to the hardware queue corresponding to the first target queue number. In this way, the first service data delivered by the upper-layer function driver can be sent to the designated hardware queue to realize data transmission between the host side and the PCIE endpoint device. In one of the embodiments, the upper-layer function driver can send the first service data to a specified hardware queue by sending a data read request or a data write request to the PCIE driver.

In the above-mentioned PCIE-based communication method, when the host side is connected to the PCIE endpoint device, the PCIE driver on the host side maps multiple hardware queues of the PCIE endpoint device to multiple virtual channels, and establishes the queue number and A first mapping relationship between channel numbers of virtual channels. The PCIE driver can mount various upper-layer function drivers, and assign corresponding virtual channels to the mounted upper-layer function drivers for use by the upper-layer function drivers. The upper-layer function drivers can send the first business data to the PCIE driver through the corresponding virtual channels . In the case of receiving the first service data, the PCIE driver determines the hardware queue number corresponding to the upper-layer driver that issues the first service data from the first mapping relationship, that is, the first target queue number, and transfers the first service data to Send it to the hardware queue corresponding to the first target queue number. In this application, each upper-layer function driver can directly implement data communication with the PCIE endpoint device through the PCIE driver, without simulating the PCIE device as a USB device. In this way, the data communication between the host side and the PCIE endpoint device can be completed through PCIE, and the transmission rate can be increased, so that 5G products can achieve high speed, large bandwidth, and low delay on computer equipment, meeting the requirements of 5G products. rate requirements.

In one embodiment, the kernel driver also includes a network adapter driver, that is, a NetAdapter driver. As shown in Figure 4, the PCIE-based communication method also includes:

S208, the PCIE driver mounts the network adapter driver, and assigns a corresponding virtual channel to the network adapter driver, so that the network adapter driver sends the second service data through the corresponding virtual channel;

S210, when the PCIE driver receives the second business data, determine the second target queue number corresponding to the second target channel number from the first mapping relationship, and send the second business data to the second target queue number corresponding to In the hardware queue; wherein, the second target channel number is the channel number of the virtual channel corresponding to the network adapter driver.

Wherein, the second service data refers to the service data sent by the network adapter driver, which may be but not limited to sending IP data and sending control messages.

As a bus driver, the PCIE driver is used to realize the logic processing of the hardware link. As a kind of function driver, the network adapter driver is used to implement business logic just like the upper layer function driver. This application separates the function driver from the PCIE driver, so that the business logic and hardware processing logic are layered, so that the business processing can be clearer, and it is convenient for developers to understand, locate and solve problems.

Specifically, the PCIE driver can mount the network adapter driver, and can allocate a corresponding virtual channel to the network adapter driver. Further, the PCIE driver can allocate virtual channels to the upper-layer function drivers and network adapters in the same manner, which can be specifically as described in any of the above embodiments, and will not be repeated here. After the PCIE driver allocates a virtual channel to the network adapter driver, the network adapter driver can map to the underlying virtual channel and implement data transmission through the allocated virtual channel. When the PCIE driver receives the second service data sent by the network adapter driver through the corresponding virtual channel, the corresponding second target queue number can be determined from the first mapping relationship according to the channel number of the virtual channel corresponding to the network adapter, And send the second service data into the hardware queue corresponding to the second target queue number. In this way, the second service data delivered by the network adapter driver can be sent to the designated hardware queue, so as to realize the data transmission between the host side and the PCIE endpoint device.

In one of the embodiments, the network adapter driver is a driver implemented based on the NetAdapterCx architecture and adapts to the Windows framework interface.

In this application, there is a parent-child relationship between the PCIE driver and each function driver (including the network adapter driver and each upper-layer function driver), and each function driver serves as a child driver and only provides a service processing interface. After the sub-driver is stable, only the PCIE driver needs to be modified to realize the adaptation between the host side and the PCIE endpoint device. However, Microsoft's driver HLK (test automation tool group) certification has fewer certification items for PCIE drivers, and more certification items for function drivers. This application puts the main hardware logic in the PCIE driver, thereby greatly reducing the workload of the driver in Microsoft HLK certification.

In this embodiment, by separating the function driver from the PCIE driver, the business logic and the hardware processing logic are layered, so that the business processing can be clearer, and it is convenient for developers to understand, locate and solve problems. At the same time, by placing the main hardware logic in the PCIE driver, the workload of the driver in Microsoft HLK certification can be greatly reduced.

In one embodiment, the PCIE-based communication method further includes: the network adapter driver calls a preset function interface to deliver the second service data to the PCIE driver. Wherein, the preset function interface is a function interface generated according to a UUID (Universally Unique Identifier) driven by PCIE and a UUID of a network adapter.

Specifically, since both the PCIE driver and the network adapter driver are located at the kernel layer, the preset function can be generated according to the UUID of the PCIE driver and the UUID of the network adapter through the technology provided by the Microsoft WDF (Windows Driver Framework, Windows Driver Framework) framework. interface. The network adapter driver invokes the preset function interface to transmit data to the PCIE driver to complete the data transmission without any request encapsulation and conversion, thereby speeding up the transmission rate.

In one of the embodiments, the application can generate a preset function interface through UUID in the PCIE driver, and define an API (Application Programming Interface, Application Programming Interface) for data transmission in the interface. In this way, the network adapter driver only needs to export the preset function interface, and the API defined by the interface can be used to deliver the second service data to the PCIE driver.

In this embodiment, the network adapter driver invokes a preset function interface to deliver the second service data to the PCIE driver without any request encapsulation and conversion, thereby speeding up the transmission rate.

In one embodiment, the second service data includes sending IP data and sending MBIM protocol data. As shown in Figure 5, the network adapter driver calls the preset function interface to send the second service data to the PCIE driver, including:

S302. The network adapter driver calls a preset function interface to send the issued IP data to the PCIE driver;

S304. The network adapter driver generates a data write request according to the second target channel number and the delivered MBIM protocol data, and sends the data write request to the PCIE driver, so as to send the delivered MBIM protocol data to the PCIE driver.

Specifically, the data transmission driven by the network adapter includes sending MBIM protocol data transmission and IP data transmission, wherein the sending MBIM protocol data is a control message. Considering that the amount of IP data delivered is relatively large, and the transmission rate of delivered IP data affects the communication rate, in order to improve data transmission efficiency, 5G products can achieve high speed, large bandwidth, and low delay on computer equipment. As a result, to meet the rate requirements of 5G products, the IP data delivered by the network adapter driver can be directly sent to the PCIE driver through the preset function interface to reduce data encapsulation and conversion, thereby increasing the transmission rate.

Since sending the MBIM protocol data does not require a high rate, the network adapter driver can complete the sending of the MBIM protocol data by sending a data write request. Since the data writing request is a standard method, the interface provided by the system can be directly invoked to complete it, without having to define a preset function interface separately, thereby simplifying program implementation. Specifically, in the process of sending the MBIM protocol data, the network adapter driver can generate a data write request according to the channel number of the virtual channel corresponding to the network adapter driver and send the MBIM protocol data, and send the data write request to the PCIE driver. The data writing request enables the PCIE driver to receive the issued MBIM protocol data, and send the issued MBIM protocol data to the corresponding hardware queue, so as to realize the transmission of the issued MBIM protocol data.

In this embodiment, the network adapter driver sends IP data to the PCIE driver by calling a preset function interface, and sends MBIM protocol data to the PCIE driver through a data write request. In this way, the transmission rate can be improved and program implementation can be simplified.

In one embodiment, the PCIE-based communication method further includes: when the PCIE driver obtains the first return data sent by the PCIE endpoint device, calling a preset function interface to send the first return data to the network adapter driver . Wherein, the preset function interface is a function interface generated according to the UUID driven by the PCIE and the UUID driven by the network adapter.

Wherein, the preset function interface can be as described in the above embodiment, and the present application will not repeat it here. The first returned data refers to the returned data that needs to be sent to the network adapter driver. In one embodiment, the first returned data may be returned IP data or returned MBIM protocol data.

Specifically, in the process of returning data from the PCIE endpoint device to the network adapter driver, since the relationship between the PCIE driver and the network adapter driver is a parent-child relationship, the PCIE endpoint device needs to send the first return data to the network adapter driver through the PCIE driver . When the PCIE driver acquires the first return data, it can call the preset function interface to send the first return data to the network adapter driver through the preset function interface. In this way, there is no need to do any request encapsulation and conversion, which can speed up the return rate.

In one embodiment, the first returned data is returned IP data or returned MBIM protocol data. As shown in Figure 6, when the PCIE driver obtains the first return data sent by the PCIE endpoint device, it calls the preset function interface to send the first return data to the network adapter driver, including:

S402, when the first returned data is returned IP data, the PCIE driver invokes a preset function interface to send the returned IP data to the network adapter driver;

S404, when the first returned data is the returned MBIM data, the PCIE driver writes the returned MBIM data into the corresponding memory queue;

S406, when the PCIE driver receives the data reading request sent by the network adapter driver, send the returned MBIM data to the network adapter driver.

In this embodiment, the corresponding memory queue refers to the memory queue corresponding to the network adapter driver, and the memory queue refers to the memory mapped in the system for storing the data of the PCIE endpoint device.

Specifically, the PCIE driver can transmit backhaul IP data and backhaul MBIM data in different ways. Considering that the data volume of backhauled IP data may be relatively large, and the transmission rate of backhauled IP data affects the communication rate, therefore, in order to improve data transmission efficiency, 5G products can achieve high speed, large bandwidth, and low cost on computer equipment. Due to the effect of delay, the PCIE driver can directly send back IP data to the network adapter driver by calling the preset function interface to reduce data encapsulation and conversion, thereby increasing the transmission rate.

Since the rate requirement for returning the MBIM protocol data is not high, the network adapter driver can complete the sending of the returning MBIM protocol data by sending a data read request. Since the data reading request is a standard method, the interface provided by the system can be directly called to complete it, without having to define a preset function interface separately, thereby simplifying program implementation. Specifically, the PCIE driver can write the returned MBIM data into the memory queue corresponding to the network adapter driver. The network adapter driver can read the data in the corresponding memory queue by sending a data read request to the PCIE driver, so as to read the returned MBIM data.

In this embodiment, the PCIE driver returns the IP data to the network adapter driver by calling the preset function interface, and sends the MBIM protocol data back to the network adapter driver through the data read request, so that the transmission rate can be improved and the program can be simplified accomplish.

In one embodiment, the communication method based on PCIE also includes:

When the PCIE driver obtains the second return data sent by the PCIE endpoint device, determine the target upper layer function driver corresponding to the second return data;

The PCIE driver writes the second return data into the memory queue corresponding to the target upper layer function, and sends the second return data to the target upper layer function driver when receiving the data read request sent by the target upper layer function driver.

Wherein, the second return data refers to the return data sent by the PCIE endpoint device to the upper layer function driver.

Specifically, according to the driver architecture of Microsoft, the upper-layer function driver can perform data transmission with the lower-layer driver (ie, PCIE driver) by sending a data read request. Specifically, when the PCIE driver obtains the second returned data, it determines the upper-layer function driver that needs to receive the second returned data, and the upper-layer function driver is the target upper-layer function driver. The PCIE driver writes the second return data into the memory queue corresponding to the target upper layer function driver. The target upper layer function driver can read the data in the corresponding memory queue by sending a data read request to the PCIE driver, so as to read the second returned data.

In one of the embodiments, the application can obtain the first return data and the second return data in the following manner: the PCIE endpoint device can write the return data into DMA (Direct Memory Access, direct memory access) memory, And the host side is notified through an interrupt, so that the host side is notified that there is returned data for processing. After receiving the interrupt, the host side obtains the returned data from the DMA memory, and analyzes the returned data. Determine the function driver that needs to receive the returned data according to the parsed returned data. When the returned data is sent to the network adapter driver, the parsed returned data is used as the first returned data; when the returned data is sent to the upper layer function driver, the parsed returned data is used The return data of is used as the second return data.

Data reading request is a standard method, which can directly call the interface provided by the system to realize data reading. In this embodiment, the reading of the second returned data is completed by invoking the interface provided by the system, and the data returned between the PCIE endpoint device and the upper-layer function driver is realized, thereby simplifying program implementation.

In one embodiment, as shown in Figure 7, the PCIE driver mounts each upper-layer function driver, and the step of assigning a corresponding virtual channel for each upper-layer function driver includes:

S502, the PCIE driver generates child nodes, wherein the number of child nodes is determined according to the number of upper layer function drivers;

S504, the PCIE driver mounts each upper-layer function driver through the sub-node; wherein, different upper-layer function drivers correspond to different sub-nodes;

S506. The PCIE driver allocates a corresponding virtual channel to each upper-layer function driver, and establishes a second mapping relationship between the child node and the channel number of the virtual channel.

Before the step of determining the first target queue number corresponding to the first target channel number from the first mapping relationship, it also includes: the PCIE driver drives the corresponding child node according to the upper layer function that sends the first business data, from the second mapping relationship Determine the first target channel number in .

Wherein, the child node may be a unique identifier, which is used to distinguish the mounted function drivers.

Specifically, the PCIE driver can generate different sub-nodes, and each upper-layer function driver can be mounted through each sub-node. Wherein, one sub-node mounts one upper-layer function driver, and one upper-layer function driver is mounted through one sub-node. When the PCIE driver mounts each upper-layer function driver, it can assign corresponding virtual channels to each upper-layer function driver. The method of allocating virtual channels can be as described in the above embodiment, and this application will not repeat it. After the virtual channel is allocated, the PCIE driver can establish a second mapping relationship, so as to reflect the mapping relationship between the child node of each upper layer function driver and the channel number of the corresponding virtual channel through the second mapping relationship.

In one of the embodiments, the network adapter driver and each upper-layer function driver serve as the function driver, and the PCIE driver can also mount the network adapter driver through the sub-node, and different function drivers are mounted on different sub-nodes. The second mapping relationship may also reflect the mapping relationship between the sub-nodes of the network adapter driver and the channel number of the virtual channel corresponding to the network adapter driver.

When the PCIE driver receives the service data issued by the function driver, the PCIE driver can determine the channel number of the virtual channel corresponding to the function driver from the second mapping relationship according to the child node of the function driver that delivered the service data, and then from The queue number of the corresponding hardware queue is determined in the first mapping relationship, so as to deliver service data to the PCIE endpoint device.

In this embodiment, since the child node is a unique number, even if the channel number changes or the first mapping relationship and the second mapping relationship change, the first target channel number can be accurately determined according to the child node, thereby improving the reliability of communication .

In one embodiment, the PCIE-based communication method further includes: the PCIE driver obtains the working mode of the host side, and derives a corresponding sub-node according to the working mode.

Wherein, the working mode may be the mode that the host side is in when starting up, and may be but not limited to normal mode, debug mode, burning mode and dump mode, etc.

Specifically, the present application can derive corresponding sub-nodes according to the working mode of the host side, so as to complete functions in different states. In one of the embodiments, the application exports NetAdapter ports and GNSS ports in normal mode; exports all ports in debug mode, such as log export ports, etc.; exports burning ports in burning mode for burning of firmware Function; only coredump ports are exported in dump mode.

In one embodiment, the step of sending the first business data into the hardware queue corresponding to the first target queue number includes: the PCIE driver generates a data packet according to the first target channel number and the first business data, and sends the data packet to into the hardware queue corresponding to the first target queue number.

Specifically, when the PCIE driver receives the first service data sent by the upper-layer function driver, it can group the first service data with the first target channel number so that the header of the data packet includes the first target channel number , so that the PCIE endpoint device determines the service type of the first service data through the first target channel number, and performs subsequent processing. Further, the packet header of the data packet may also include the first target queue number. The PCIE driver can send the data packet into the corresponding hardware queue.

In one of the embodiments, similarly, the PCIE driver can also generate a data packet according to the second target channel number and the second service data, and send the data packet into the hardware queue corresponding to the second target queue number. For the specific implementation process of this step, please refer to the process of generating data packets by the PCIE driver according to the first target channel number and the first service data, which will not be described in detail in this application.

In another embodiment, the PCIE endpoint device may also obtain a third mapping relationship between the channel number of the virtual channel and the service type, and determine the service type of the service data according to the third mapping relationship.

In order to facilitate the understanding of the solution of the present application, a specific example is used below to illustrate. The PCIE-based driver architecture can be as shown in Figure 8, so that the host side (i.e. the host side in Figure 8) and the PCIE endpoint device (i.e. the PCIE EP in Figure 8) can communicate in a PCIE manner.

A PCIE driver is configured on the host side (the PCIE driver is the WWAN host interface in Figure 8). The PCIE driver includes a data path and a control path, and the data path and the control path respectively include their own hardware sending and receiving queues for implementing data sending and receiving. The hardware transceiver queue in the data path and the hardware transceiver queue in the control path are mapped to different virtual channels for data transmission from the function driver.

The PCIE driver generates different sub-nodes for mounting functional drivers such as network adapters, GNSS, AT, FLASH, log, and Coredump. These function drivers are mapped to different virtual channels at the bottom layer through a certain mapping relationship, and other function drivers (that is, each upper-layer function driver) except the network adapter driver can send data read requests and/or data write requests. Send to the specified hardware queue of the PCIE endpoint device.

Both the PCIE driver and the network adapter driver are configured in the kernel layer, and the other function drivers except the network adapter driver are configured in the user layer, so data transmission can be performed between the PCIE driver and the network adapter driver through a preset function interface. There are two kinds of data in the network adapter driver, namely MBIM protocol data and IP data. The MBIM protocol data can be transmitted through the control channel. Since the MBIM protocol data does not require a high rate, the transmission of the MBIM protocol data can be completed by sending a data read and write request. IP data needs to be transmitted through the data channel. In order to speed up the transmission rate, the technology provided by the Microsoft WDF framework can be used to generate a preset function interface through UUID in the PCIE driver, and define the API interface for data transmission in the preset function interface , in order to realize the sending and receiving of IP data. During data transmission, the network adapter driver can directly use the API interface defined by the preset function interface by exporting the preset function interface to transfer the IP data to the PCIE driver to complete the delivery of the IP data without doing Any request encapsulation and transformation.

In the driver architecture of this application, port export can be divided into multiple modes. This application can export the port corresponding to the network adapter driver and the port corresponding to the GNSS driver in the normal mode; in the debug mode, export all ports, including log export, etc.; in the burning mode, export the burning port for the burning function of the firmware. Export the Coredump port in dump mode. In this way, the functions of different states can be completed.

This application relies on Microsoft's NetAdapterCx framework, through PCIE driver development, to achieve the application of computer equipment on the host side, and to achieve the effect of 5G products on computer equipment that can meet high speed and large bandwidth.

It should be understood that although the steps in the flow charts involved in the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flow charts involved in the above-mentioned embodiments may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be performed at different times For execution, the execution order of these steps or stages is not necessarily performed sequentially, but may be executed in turn or alternately with other steps or at least a part of steps or stages in other steps.

Based on the same inventive concept, an embodiment of the present application further provides a PCIE-based communication device for implementing the above-mentioned PCIE-based communication method. The solution to the problem provided by the device is similar to the implementation described in the above method, so the specific limitations in one or more PCIE-based communication device embodiments provided below can be referred to above for PCIE-based communication The limitation of the method will not be repeated here.

In one embodiment, as shown in Figure 9, a PCIE-based communication device is provided, the device includes a kernel driver configured on the host side, the kernel driver includes a PCIE driver, and the host side is also configured with an upper layer function driver. PCIE drivers include:

The first mapping relationship establishment module is used to establish the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel when the host side recognizes the PCIE endpoint device; wherein, the hardware queue is of the PCIE endpoint device hardware access channel;

An allocation module, configured to mount each upper-layer function driver, and assign a corresponding virtual channel to each upper-layer function driver, so that the upper-layer function driver sends the first business data through the corresponding virtual channel;

The business data writing module is used to determine the first target queue number corresponding to the first target channel number from the first mapping relationship when the first business data is received, and send the first business data to the first target In the hardware queue corresponding to the queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver delivering the first service data.

In one embodiment, the kernel driver also includes a network adapter driver. The allocation module is also used to mount the network adapter driver, and allocate a corresponding virtual channel to the network adapter driver, so that the network adapter driver delivers the second service data through the corresponding virtual channel. The business data writing module is also used to determine the second target queue number corresponding to the second target channel number from the first mapping relationship when receiving the second business data, and send the second business data to the second target In the hardware queue corresponding to the queue number; wherein, the second target channel number is the channel number of the virtual channel corresponding to the network adapter driver.

In one embodiment, the network adapter driver includes a first interface calling module, configured to call a preset function interface to send the second service data to the PCIE driver. Wherein, the preset function interface is a function interface generated according to the UUID code driven by the PCIE and the UUID code driven by the network adapter.

In one embodiment, the second service data includes sending IP data and sending MBIM protocol data. The first interface calling module includes an IP data delivery unit and an MBIM protocol data delivery unit. Wherein, the IP data delivery unit calls a preset function interface to send the IP data to the PCIE driver. The MBIM protocol data sending unit is used to generate a data write request according to the second target channel number and the sent MBIM protocol data, and send a data write request to the PCIE driver to send the sent MBIM protocol data to the PCIE driver.

In one embodiment, the PCIE driver further includes a second interface calling module. The second interface calling module is used to call a preset function interface to send the first return data to the network adapter driver when the first return data sent by the PCIE endpoint device is obtained. Wherein, the preset function interface is a function interface generated according to the UUID code driven by the PCIE and the UUID code driven by the network adapter.

In one embodiment, the first returned data is returned IP data or returned MBIM protocol data. The second interface calling module includes an IP data return unit and an MBIM protocol data return unit. Wherein, the IP data return unit is configured to call a preset function interface to send the return IP data to the network adapter driver when the first return data is return IP data. The MBIM protocol data return unit is used to write the returned MBIM data into the corresponding memory queue when the first returned data is the returned MBIM data; it is also used to read the data sent by the network adapter driver If requested, send back MBIM data to the network adapter driver.

In one embodiment, the allocation module includes a child node generating unit, a mounting unit and a second mapping relationship establishing unit. The PCIE driver also includes a first target channel number determination module. Wherein, the sub-node generation unit is used to generate sub-nodes; the number of sub-nodes is determined according to the number of upper layer function drivers. The mounting unit is used to mount each upper-layer function driver through sub-nodes; wherein, different upper-layer function drivers correspond to different sub-nodes. The second mapping relation establishing unit is used for assigning a corresponding virtual channel to each upper layer function driver, and establishing a second mapping relation between the sub-node and the channel number of the virtual channel. The module for determining the first target channel number is configured to determine the first target channel number from the second mapping relationship according to the sub-node corresponding to the upper-layer function driver that delivers the first service data.

In one embodiment, the PCIE driver further includes an export module, which is used to obtain the working mode of the host, and derive corresponding sub-nodes according to the working mode.

In one embodiment, the business data writing module includes a data packet generation unit, which is used to generate a data packet according to the first target channel number and the first business data, and send the data packet to the first target queue number in the corresponding hardware queue.

In one embodiment, the PCIE driver further includes a target upper layer function driver module and a return module. Wherein, the target upper-layer function driver module is configured to determine the target upper-layer function driver corresponding to the second return data when the second return data sent by the PCIE endpoint device is obtained. The return module is used to write the second return data into the memory queue corresponding to the target upper-layer function driver, and send the second return to the target upper-layer function driver when receiving the data read request sent by the target upper-layer function driver data.

Each module in the above-mentioned PCIE communication device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

As used in this application, the terms "component," "module," and "system" and the like are intended to mean a computer-related entity, which may be hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and or a computer. As an illustration, both an application running on a server and a server can be a component. One or more components can reside within a process and or thread of execution, and a component can be localized on one computer and or distributed between two or more computers.

In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure may be as shown in FIG. 10 . The computer device includes a processor, memory and a communication interface connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. When the computer program is executed by the processor, a PCIE communication method is realized.

Those skilled in the art can understand that the structure shown in Figure 10 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, there is also provided a computer device, including a memory and a processor, where a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

In an embodiment, the computer device may further include a PCIE endpoint device, and the PCIE endpoint device is connected to the processor through a PCIE bus. In one of the embodiments, the PCIE endpoint device is a 5G communication module. In one example, the PCIE endpoint device can be a 5G modem.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be completed by instructing related hardware through computer programs, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the application should be based on the appended claims.

Claims (14)

A communication method based on PCIE is applied to the host side, and the host side is configured with an upper layer function driver and a kernel driver, and the kernel driver includes a PCIE driver; the method includes: When the host side recognizes the PCIE endpoint device, the PCIE drives the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel; wherein, the hardware queue is the hardware of the PCIE endpoint device access channel; The PCIE driver mounts each of the upper-layer function drivers, and assigns a corresponding virtual channel for each of the upper-layer function drivers, so that the upper-layer function drivers deliver first business data through the corresponding virtual channels; When the PCIE driver receives the first business data, it determines the first target queue number corresponding to the first target channel number from the first mapping relationship, and sends the first business data to the In the hardware queue corresponding to the first target queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver that delivers the first service data. The communication method according to claim 1, wherein the kernel driver also includes a network adapter driver; the method also includes: The PCIE driver mounts the network adapter driver, and allocates a corresponding virtual channel for the network adapter driver, so that the network adapter driver sends the second service data through the corresponding virtual channel; When the PCIE driver receives the second business data, it determines the second target queue number corresponding to the second target channel number from the first mapping relationship, and sends the second business data to the In the hardware queue corresponding to the second target queue number; wherein, the second target channel number is the channel number of the virtual channel corresponding to the network adapter driver. The communication method according to claim 2, wherein the method further comprises: The network adapter driver calls a preset function interface to deliver the second service data to the PCIE driver; Wherein, the preset function interface is a function interface generated according to the universal unique identification code driven by the PCIE and the universal unique identification code driven by the network adapter. The communication method according to claim 3, wherein the second service data includes sending IP data and sending MBIM protocol data; The network adapter driver calls the preset function interface to send the second service data to the PCIE driver, including: The network adapter driver calls the preset function interface to send the issued IP data to the PCIE driver; The network adapter driver generates a data write request according to the second target channel number and the issued MBIM protocol data, and sends the data write request to the PCIE driver, so as to send the data write request to the PCIE driver. Send MBIM protocol data. The communication method according to claim 2, wherein the method further comprises: When the PCIE driver obtains the first return data sent by the PCIE endpoint device, it calls a preset function interface to send the first return data to the network adapter driver; Wherein, the preset function interface is a function interface generated according to the universal unique identification code driven by the PCIE and the universal unique identification code driven by the network adapter. The communication method according to claim 5, wherein the first returned data is returned IP data or returned MBIM protocol data; The PCIE driver calls the preset function interface to drive the step of sending the second service data to the network adapter, including: When the first return data is the return IP data, the PCIE driver calls the preset function interface to send the return IP data to the network adapter driver; When the first returned data is the returned MBIM data, the PCIE driver writes the returned MBIM data into a corresponding memory queue; The PCIE driver sends the returned MBIM data to the network adapter driver when receiving the data read request sent by the network adapter driver. The communication method according to claim 1, wherein the PCIE driver mounts each of the upper-layer function drivers, and the step of assigning a corresponding virtual channel for each of the upper-layer function drivers includes: Described PCIE drives generation child node; The quantity of described child node is determined according to the quantity that upper layer function drives; The PCIE driver mounts each of the upper-layer function drivers through the sub-node; wherein, different upper-layer function drivers correspond to different sub-nodes; Described PCIE drives and assigns corresponding virtual channel for each described upper layer function driver, and establishes the second mapping relation between the channel number of child node and virtual channel; Before the step of determining the first target queue number corresponding to the first target channel number from the first mapping relationship, it also includes: The PCIE driver determines the first target channel number from the second mapping relationship according to the child node corresponding to the upper layer function driver that delivers the first service data. The communication method according to claim 7, wherein the method further comprises: The PCIE driver obtains the working mode of the host side, and derives the corresponding sub-node according to the working mode. The communication method according to claim 1, wherein the step of sending the first business data into the hardware queue corresponding to the first target queue number comprises: The PCIE driver generates a data packet according to the first target channel number and the first service data, and sends the data packet into a hardware queue corresponding to the first target queue number. The communication method according to any one of claims 1 to 9, wherein the method further comprises: The PCIE driver determines the target upper layer function driver corresponding to the second return data when the second return data sent by the PCIE endpoint device is obtained; The PCIE driver writes the second return data into the memory queue corresponding to the target upper layer function driver, and when receiving the data read request sent by the target upper layer function driver, sends the data to the target The upper layer function driver sends the second return data. A communication device based on PCIE, the device includes a kernel driver configured on the host side, the kernel driver includes a PCIE driver, and the host side is also configured with an upper layer function driver; the PCIE driver includes: The first mapping relationship establishment module is used to establish the first mapping relationship between the queue number of the hardware queue and the channel number of the virtual channel when the host side recognizes the PCIE endpoint device; wherein the hardware queue is The hardware access channel of the PCIE endpoint device; An allocation module, configured to mount each of the upper-layer function drivers, and assign a corresponding virtual channel to each of the upper-layer function drivers, so that the upper-layer function drivers deliver the first service data through the corresponding virtual channels; A business data writing module, configured to determine the first target queue number corresponding to the first target channel number from the first mapping relationship when the first business data is received, and write the first business data The data is sent to the hardware queue corresponding to the first target queue number; wherein, the first target channel number is the channel number of the virtual channel corresponding to the upper layer function driver that delivers the first service data. A computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 10 when executing the computer program. The computer device according to claim 12, wherein the computer device further comprises a PCIE endpoint device, and the PCIE endpoint device is connected to the processor through a PCIE bus. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images