Multi Channel DMA Intel® FPGA IP for PCI Express* User Guide

Download PDF
ID 683821
Date 7/30/2024
Public
Document Table of Contents
Document Table of Contents x
1. Before You Begin 2. Introduction 3. Functional Description 4. Interface Overview 5. Parameters (H-Tile) 6. Parameters (P-Tile) (F-Tile) (R-Tile) 7. Designing with the IP Core 8. Software Programming Model 9. Registers 10. Troubleshooting/Debugging 11. Multi Channel DMA Intel FPGA IP for PCI Express User Guide Archives 12. Revision History for the Multi Channel DMA Intel FPGA IP for PCI Express User Guide
1. Before You Begin x
1.1. Terms and Acronyms 1.2. Known Issues
2. Introduction x
2.1. Multi Channel DMA IP for PCI Express Features 2.2. Device Family Support 2.3. Recommended Speed Grades 2.4. Resource Utilization 2.5. Release Information
2.1. Multi Channel DMA IP for PCI Express Features x
2.1.1. Endpoint Mode 2.1.2. Root Port Mode
3. Functional Description x
3.1. Multi Channel DMA 3.2. Bursting Avalon-MM Master (BAM) 3.3. Bursting Avalon-MM Slave (BAS) 3.4. MSI Interrupt 3.5. Config Slave (CS) 3.6. Root Port Address Translation Table Enablement 3.7. Hard IP Reconfiguration Interface 3.8. Config TL Interface 3.9. Configuration Intercept Interface (EP Only) 3.10. Data Mover Only
3.1. Multi Channel DMA x
3.1.1. H2D Data Mover 3.1.2. D2H Data Mover 3.1.3. Descriptors 3.1.4. Avalon-MM PIO Master 3.1.5. Avalon-MM Write (H2D) and Read (D2H) Master 3.1.6. Avalon-ST Source (H2D) and Sink (D2H) 3.1.7. User MSI-X 3.1.8. User Functional Level Reset (FLR) 3.1.9. Control Registers
3.1.2. D2H Data Mover x
3.1.2.1. D2H Descriptor Fetch
3.1.3. Descriptors x
3.1.3.1. Support for Unaligned (or byte-aligned) Data Transfer 3.1.3.2. Metadata Support 3.1.3.3. MSI-X/Writeback
3.1.6. Avalon-ST Source (H2D) and Sink (D2H) x
3.1.6.1. Avalon-ST 1-Port Mode 3.1.6.2. Packet (File) Boundary 3.1.6.3. Metadata
3.4. MSI Interrupt x
3.4.1. Endpoint MSI Support through BAS 3.4.2. MSI Interrupt Controller
3.5. Config Slave (CS) x
3.5.1. 29 bit AVMM address format 3.5.2. 14 bit AVMM address format 3.5.3. Configuration Access Mechanism
3.10. Data Mover Only x
3.10.1. H2D Data Mover 3.10.2. D2H Data Mover 3.10.3. Application Specific Bits
3.10.1. H2D Data Mover x
3.10.1.1. H2D Descriptor Format (h2ddm_desc) 3.10.1.2. H2D Descriptor Completion Packet Format (h2ddm_desc_cmpl) 3.10.1.3. H2D Descriptor Status (h2ddm_desc_status)
3.10.2. D2H Data Mover x
3.10.2.1. D2H Descriptor Format (d2hdm_desc) 3.10.2.2. D2H Descriptor Status (d2hdm_desc_status)
4. Interface Overview x
4.1. Port List 4.2. Clocks 4.3. Resets 4.4. Multi Channel DMA 4.5. Bursting Avalon-MM Master (BAM) Interface 4.6. Bursting Avalon-MM Slave (BAS) Interface 4.7. Legacy Interrupt Interface 4.8. MSI Interface 4.9. Config Slave Interface (RP only) 4.10. Hard IP Reconfiguration Interface 4.11. Config TL Interface 4.12. Configuration Intercept Interface (EP Only) 4.13. Data Mover Interface 4.14. Hard IP Status Interface 4.15. Precision Time Management (PTM) Interface
4.1. Port List x
4.1.1. Port List (H-Tile) 4.1.2. Port List (P-Tile) (F-Tile) (R-Tile)
4.2. Clocks x
4.2.1. F-Tile System PLL Reference Clock Requirements
4.4. Multi Channel DMA x
4.4.1. Avalon-MM PIO Master 4.4.2. Avalon-MM Write Master (H2D) 4.4.3. Avalon-MM Read Master (D2H) 4.4.4. Avalon-ST Source (H2D) 4.4.5. Avalon-ST Sink (D2H) 4.4.6. User Event MSI-X Interface 4.4.7. User Functional Level Reset (FLR) Interface
4.13. Data Mover Interface x
4.13.1. H2D Data Mover Interface 4.13.2. D2H Data Mover Interface
5. Parameters (H-Tile) x
5.1. IP Settings 5.2. Example Designs
5.1. IP Settings x
5.1.1. System Settings 5.1.2. MCDMA Settings 5.1.3. Device Identification Registers 5.1.4. Multifunction and SR-IOV System Settings Parameters [Endpoint Mode] 5.1.5. Configuration, Debug and Extension Options 5.1.6. PHY Characteristics 5.1.7. PCI Express / PCI Capabilities Parameters
5.1.7. PCI Express / PCI Capabilities Parameters x
5.1.7.1. Device 5.1.7.2. Link 5.1.7.3. MSI-X 5.1.7.4. Power Management 5.1.7.5. Vendor Specific Extended Capability (VSEC)
6. Parameters (P-Tile) (F-Tile) (R-Tile) x
6.1. Top-Level Settings 6.2. PCIe0 Settings 6.3. Example Designs 6.4. Analog Parameters (F-Tile MCDMA IP Only) 6.5. PCIe1 Settings
6.2. PCIe0 Settings x
6.2.1. Base Address Register 6.2.2. PCIe0 Configuration, Debug and Extension Options 6.2.3. PCIe0 Device Identification Registers 6.2.4. PCIe0 PCI Express / PCI Capabilities 6.2.5. MCDMA Settings
6.2.3. PCIe0 Device Identification Registers x
6.2.3.1. PCIe0 PF0 IDs 6.2.3.2. PCIe0 PF0 VF IDs
6.2.4. PCIe0 PCI Express / PCI Capabilities x
6.2.4.1. PCIe0 Device 6.2.4.2. PCIe0 Link 6.2.4.3. PCIe0 MSI-X 6.2.4.4. PCIe0 DEV SER 6.2.4.5. PCIe0 PRS 6.2.4.6. PCIe0 PTM 6.2.4.7. PCIe0 ACS Capabilities 6.2.4.8. PCIe0 ATS 6.2.4.9. PCIe0 TPH 6.2.4.10. Receiver Detection (F-Tile MCDMA IP Only)
6.2.4.7. PCIe0 ACS Capabilities x
6.2.4.7.1. PCIe0 ACS for Physical Functions 6.2.4.7.2. PCIe0 ACS for Virtual Functions
6.2.4.8. PCIe0 ATS x
6.2.4.8.1. PCIe0 ATS for Physical Functions 6.2.4.8.2. PCIe0 ATS for Virtual Functions
6.2.4.9. PCIe0 TPH x
6.2.4.9.1. PCIe0 TPH for Physical Functions 6.2.4.9.2. PCIe0 TPH for Virtual Functions
6.5. PCIe1 Settings x
6.5.1. PCIe1 Configuration, Debug and Extension Options
7. Designing with the IP Core x
7.1. Generating the IP Core 7.2. Simulating the IP Core 7.3. IP Core Generation Output - Quartus® Prime Pro Edition 7.4. Systems Integration and Implementation
7.4. Systems Integration and Implementation x
7.4.1. Required Supporting IP
8. Software Programming Model x
8.1. Multi Channel DMA IP Custom Driver 8.2. Multi Channel DMA IP DPDK Poll-Mode based Driver 8.3. Multi Channel DMA IP Kernel Mode Network Device Driver
8.1. Multi Channel DMA IP Custom Driver x
8.1.1. Architecture 8.1.2. libmqdma library details 8.1.3. Application Multi-threading with Multiple Channels Scheduling Threads 8.1.4. Software Flow 8.1.5. API Flow 8.1.6. libmqdma Library API List 8.1.7. Request Structures
8.1.2. libmqdma library details x
8.1.2.1. Channel Initialization 8.1.2.2. Descriptor Memory Management 8.1.2.3. Descriptor Completion Status Update
8.1.5. API Flow x
8.1.5.1. Single Descriptor Load and Submit 8.1.5.2. Multiple Descriptor Load and Submit
8.1.6. libmqdma Library API List x
8.1.6.1. ifc_api_start 8.1.6.2. ifc_mcdma_port_by_name 8.1.6.3. ifc_qdma_device_get 8.1.6.4. ifc_num_channels_get 8.1.6.5. ifc_qdma_channel_get 8.1.6.6. ifc_qdma_acquire_channels 8.1.6.7. ifc_qdma_release_all_channels 8.1.6.8. ifc_qdma_device_put 8.1.6.9. ifc_qdma_channel_put 8.1.6.10. ifc_qdma_completion_poll 8.1.6.11. ifc_qdma_request_start 8.1.6.12. ifc_qdma_request_prepare 8.1.6.13. ifc_qdma_descq_queue_batch_load 8.1.6.14. ifc_qdma_request_submit 8.1.6.15. ifc_qdma_pio_read32 8.1.6.16. ifc_qdma_pio_write32 8.1.6.17. ifc_qdma_pio_read64 8.1.6.18. ifc_qdma_pio_write64 8.1.6.19. ifc_qdma_pio_read128 8.1.6.20. ifc_qdma_pio_write128 8.1.6.21. ifc_qdma_pio_read256 8.1.6.22. ifc_qdma_pio_write256 8.1.6.23. ifc_request_malloc 8.1.6.24. ifc_request_free 8.1.6.25. ifc_app_stop 8.1.6.26. ifc_qdma_poll_init 8.1.6.27. ifc_qdma_poll_add 8.1.6.28. ifc_qdma_poll_wait 8.1.6.29. ifc_mcdma_port_by_name
8.2. Multi Channel DMA IP DPDK Poll-Mode based Driver x
8.2.1. Architecture 8.2.2. MCDMA Poll Mode Driver 8.2.3. DPDK based application 8.2.4. Request Structures 8.2.5. Software Flow 8.2.6. API Flow 8.2.7. API List
8.2.2. MCDMA Poll Mode Driver x
8.2.2.1. Completion Status Update 8.2.2.2. Metadata Support 8.2.2.3. User MSI-X
8.3. Multi Channel DMA IP Kernel Mode Network Device Driver x
8.3.1. Architecture 8.3.2. Driver Information 8.3.3. Software Flow
8.3.2. Driver Information x
8.3.2.1. Device Management 8.3.2.2. Channel Management 8.3.2.3. Descriptor Memory Management 8.3.2.4. Completions Management 8.3.2.5. ethtool support 8.3.2.6. debugfs support 8.3.2.7. SRIOV Support
8.3.3. Software Flow x
8.3.3.1. Host to Device Flow 8.3.3.2. Device to Host Flow
9. Registers x
9.1. Queue Control (QCSR) 9.2. MSI-X Memory Space 9.3. Control Register (GCSR)
10. Troubleshooting/Debugging x
10.1. Debug Toolkit
10.1. Debug Toolkit x
10.1.1. Overview 10.1.2. Enabling the Debug Toolkit 10.1.3. Launching the Debug Toolkit 10.1.4. Using the Debug Toolkit
10.1.4. Using the Debug Toolkit x
10.1.4.1. Main View 10.1.4.2. Toolkit Parameters 10.1.4.3. Channel Parameters 10.1.4.4. Eye Viewer 10.1.4.5. Link Inspector
10.1.4.4. Eye Viewer x
10.1.4.4.1. Running Eye Viewer in the P-Tile Debug Toolkit 10.1.4.4.2. Running Eye Viewer in the F-Tile Debug Toolkit
1. Before You Begin
2. Introduction
3. Functional Description
4. Interface Overview
5. Parameters (H-Tile)
6. Parameters (P-Tile) (F-Tile) (R-Tile)
7. Designing with the IP Core
8. Software Programming Model
9. Registers
10. Troubleshooting/Debugging
11. Multi Channel DMA Intel FPGA IP for PCI Express User Guide Archives
12. Revision History for the Multi Channel DMA Intel FPGA IP for PCI Express User Guide

8.1.3. Application

At the time of starting the application, by using the APIs provided by driver, it reads the MCDMA capabilities, creates application context, open BAR registers, initializes the PCI Express functions. At the time of termination, it clears the application context and stops all the channels.

Multi-threading with Multiple Channels

Based on the input parameters, the application starts multiple threads with posix thread APIs, associate the queue to the thread and submit DMA transactions one at a time independently. As part of this, driver updates the tail register of that channel. Update tid ID update, hardware picks up the channel and start DMA operation.

Each thread performs the following tasks.
  1. Get the device context based on BDF (Bus Device Function)
  2. Acquire the available channel
  3. Get DMA capable memory
  4. Start DMA operation
  5. Release the channel

As multiple threads can try to grab and release the channel at a time, userspace driver (libmqdma) handles synchronization problems while performing channel management.

Scheduling Threads

As POSIX libraries are being used for thread management, Linux scheduler takes care of scheduling the threads, there is no custom scheduler which takes care of scheduling the threads.

perfq_app schedules multiple queues on single threads for DMA operations.
  1. Reads number of channels from user (-c <num>)
  2. Reads number of threads from user (-a <num>)
  3. Calculate number of queues DMA need to perform from one thread
  4. After every TID update, perfq_app swaps out a queue and swaps in other queue to perform DMA operation.
Level Two Title