L-Tile and H-Tile Avalon® Memory-mapped Intel® FPGA IP for PCI Express* User Guide

Download PDF
ID 683667
Date 4/03/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents
Document Table of Contents x
1. Introduction 2. Quick Start Guide 3. Interface Overview 4. Parameters 5. Designing with the IP Core 6. Block Descriptions 7. Registers 8. Programming Model for the DMA Descriptor Controller 9. Programming Model for the Avalon® -MM Root Port 10. Avalon-MM Testbench and Design Example 11. Troubleshooting and Observing the Link A. PCI Express Core Architecture B. Root Port Enumeration C. Document Revision History
1. Introduction x
1.1. Avalon-MM Interface for PCIe 1.2. Features 1.3. Release Information 1.4. Device Family Support 1.5. Recommended Fabric Speed Grades 1.6. Performance and Resource Utilization 1.7. Transceiver Tiles 1.8. PCI Express IP Core Package Layout 1.9. Channel Availability
2. Quick Start Guide x
2.1. Design Components 2.2. Hardware and Software Requirements 2.3. Directory Structure 2.4. Generating the Design Example 2.5. Simulating the Design Example 2.6. Compiling the Design Example and Programming the Device 2.7. Installing the Linux Kernel Driver 2.8. Running the Design Example Application
3. Interface Overview x
3.1. Avalon-MM DMA Interfaces when Descriptor Controller Is Internally Instantiated 3.2. Avalon-MM DMA Interfaces when Descriptor Controller is Externally Instantiated 3.3. Other Avalon-MM Interfaces 3.4. Clocks and Reset 3.5. System Interfaces
3.3. Other Avalon-MM Interfaces x
3.3.1. Avalon-MM Master Interfaces 3.3.2. Avalon-MM Slave Interfaces 3.3.3. Control Register Access (CRA) Avalon-MM Slave
4. Parameters x
4.1. Avalon-MM Settings 4.2. Base Address Registers 4.3. Device Identification Registers 4.4. PCI Express and PCI Capabilities Parameters 4.5. Configuration, Debug and Extension Options 4.6. PHY Characteristics 4.7. Example Designs
4.4. PCI Express and PCI Capabilities Parameters x
4.4.1. Device Capabilities 4.4.2. Link Capabilities 4.4.3. MSI and MSI-X Capabilities 4.4.4. Slot Capabilities 4.4.5. Power Management 4.4.6. Vendor Specific Extended Capability (VSEC)
5. Designing with the IP Core x
5.1. Generation 5.2. Simulation 5.3. IP Core Generation Output ( Intel® Quartus® Prime Pro Edition) 5.4. Channel Layout and PLL Usage
6. Block Descriptions x
6.1. Interfaces
6.1. Interfaces x
6.1.1. Intel® Stratix® 10 DMA Avalon-MM DMA Interface to the Application Layer 6.1.2. Avalon-MM Interface to the Application Layer 6.1.3. Clocks and Reset 6.1.4. Interrupts 6.1.5. Flush Requests 6.1.6. Serial Data, PIPE, Status, Reconfiguration, and Test Interfaces
6.1.1. Intel® Stratix® 10 DMA Avalon-MM DMA Interface to the Application Layer x
6.1.1.1. Descriptor Controller Interfaces when Instantiated Internally 6.1.1.2. Write DMA Avalon-MM Master Port 6.1.1.3. Descriptor Controller Interfaces when Instantiated Externally
6.1.1.1. Descriptor Controller Interfaces when Instantiated Internally x
6.1.1.1.1. Read Data Mover 6.1.1.1.2. Read Descriptor Controller Avalon-MM Master interface 6.1.1.1.3. Write Descriptor Controller Avalon-MM Master Interface 6.1.1.1.4. Read Descriptor Table Avalon-MM Slave Interface 6.1.1.1.5. Write Descriptor Table Avalon-MM Slave Interface
6.1.1.3. Descriptor Controller Interfaces when Instantiated Externally x
6.1.1.3.1. Avalon® -ST Descriptor Source
6.1.2. Avalon-MM Interface to the Application Layer x
6.1.2.1. Bursting and Non-Bursting Avalon® -MM Module Signals 6.1.2.2. Non-Bursing Slave Module 6.1.2.3. 32-Bit Control Register Access (CRA) Slave Signals 6.1.2.4. Bursting Slave Module
6.1.3. Clocks and Reset x
6.1.3.1. Clocks 6.1.3.2. Resets
6.1.4. Interrupts x
6.1.4.1. MSI Interrupts for Endpoints 6.1.4.2. Legacy Interrupts
6.1.6. Serial Data, PIPE, Status, Reconfiguration, and Test Interfaces x
6.1.6.1. Serial Data Interface 6.1.6.2. PIPE Interface 6.1.6.3. Hard IP Status Interface 6.1.6.4. Hard IP Reconfiguration 6.1.6.5. Test Interface
7. Registers x
7.1. Configuration Space Registers 7.2. Avalon-MM DMA Bridge Registers
7.1. Configuration Space Registers x
7.1.1. Register Access Definitions 7.1.2. PCI Configuration Header Registers 7.1.3. PCI Express Capability Structures 7.1.4. Intel Defined VSEC Capability Header 7.1.5. Uncorrectable Internal Error Status Register 7.1.6. Uncorrectable Internal Error Mask Register 7.1.7. Correctable Internal Error Status Register 7.1.8. Correctable Internal Error Mask Register
7.1.4. Intel Defined VSEC Capability Header x
7.1.4.1. Intel Defined Vendor Specific Header 7.1.4.2. Intel Marker 7.1.4.3. JTAG Silicon ID 7.1.4.4. User Configurable Device and Board ID
7.2. Avalon-MM DMA Bridge Registers x
7.2.1. PCI Express Avalon-MM Bridge Register Address Map 7.2.2. DMA Descriptor Controller Registers
7.2.1. PCI Express Avalon-MM Bridge Register Address Map x
7.2.1.1. Avalon-MM to PCI Express Interrupt Status Registers 7.2.1.2. Avalon-MM to PCI Express Interrupt Enable Registers 7.2.1.3. Address Mapping for High-Performance Avalon-MM 32-Bit Slave Modules 7.2.1.4. PCI Express to Avalon-MM Interrupt Status and Enable Registers for Endpoints 7.2.1.5. PCI Express Configuration Information Registers
7.2.2. DMA Descriptor Controller Registers x
7.2.2.1. Read DMA Internal Descriptor Controller Registers 7.2.2.2. Write DMA Internal Descriptor Controller Registers
8. Programming Model for the DMA Descriptor Controller x
8.1. Read DMA Example 8.2. Write DMA Example 8.3. Software Program for Simultaneous Read and Write DMA 8.4. Read DMA and Write DMA Descriptor Format
9. Programming Model for the Avalon® -MM Root Port x
9.1. Root Port TLP Data Control and Status Registers 9.2. Sending a TLP 9.3. Receiving a Non-Posted Completion TLP 9.4. Example of Reading and Writing BAR0 Using the CRA Interface
10. Avalon-MM Testbench and Design Example x
10.1. Avalon-MM Endpoint Testbench 10.2. Endpoint Design Example 10.3. Avalon® -MM Test Driver Module 10.4. Root Port BFM 10.5. BFM Procedures and Functions
10.2. Endpoint Design Example x
10.2.1. BAR Setup
10.4. Root Port BFM x
10.4.1. Overview 10.4.2. Issuing Read and Write Transactions to the Application Layer 10.4.3. Configuration of Root Port and Endpoint 10.4.4. Configuration Space Bus and Device Numbering 10.4.5. BFM Memory Map
10.5. BFM Procedures and Functions x
10.5.1. ebfm_barwr Procedure 10.5.2. ebfm_barwr_imm Procedure 10.5.3. ebfm_barrd_wait Procedure 10.5.4. ebfm_barrd_nowt Procedure 10.5.5. ebfm_cfgwr_imm_wait Procedure 10.5.6. ebfm_cfgwr_imm_nowt Procedure 10.5.7. ebfm_cfgrd_wait Procedure 10.5.8. ebfm_cfgrd_nowt Procedure 10.5.9. BFM Configuration Procedures 10.5.10. BFM Shared Memory Access Procedures 10.5.11. BFM Log and Message Procedures 10.5.12. Verilog HDL Formatting Functions
10.5.9. BFM Configuration Procedures x
10.5.9.1. ebfm_cfg_rp_ep Procedure 10.5.9.2. ebfm_cfg_decode_bar Procedure
10.5.10. BFM Shared Memory Access Procedures x
10.5.10.1. Shared Memory Constants 10.5.10.2. shmem_write Task 10.5.10.3. shmem_read Function 10.5.10.4. shmem_display Verilog HDL Function 10.5.10.5. shmem_fill Procedure 10.5.10.6. shmem_chk_ok Function
10.5.11. BFM Log and Message Procedures x
10.5.11.1. ebfm_display Verilog HDL Function 10.5.11.2. ebfm_log_stop_sim Verilog HDL Function 10.5.11.3. ebfm_log_set_suppressed_msg_mask Task 10.5.11.4. ebfm_log_set_stop_on_msg_mask Verilog HDL Task 10.5.11.5. ebfm_log_open Verilog HDL Function 10.5.11.6. ebfm_log_close Verilog HDL Function
10.5.12. Verilog HDL Formatting Functions x
10.5.12.1. himage1 10.5.12.2. himage2 10.5.12.3. himage4 10.5.12.4. himage8 10.5.12.5. himage16 10.5.12.6. dimage1 10.5.12.7. dimage2 10.5.12.8. dimage3 10.5.12.9. dimage4 10.5.12.10. dimage5 10.5.12.11. dimage6 10.5.12.12. dimage7
11. Troubleshooting and Observing the Link x
11.1. Troubleshooting 11.2. PCIe Link Inspector Overview
11.1. Troubleshooting x
11.1.1. Simulation Fails To Progress Beyond Polling.Active State 11.1.2. Hardware Bring-Up Issues 11.1.3. Link Training 11.1.4. Use Third-Party PCIe Analyzer
11.2. PCIe Link Inspector Overview x
11.2.1. PCIe* Link Inspector Hardware
11.2.1. PCIe* Link Inspector Hardware x
11.2.1.1. Enabling the PCIe* Link Inspector 11.2.1.2. Launching the PCIe* Link Inspector 11.2.1.3. The PCIe* Link Inspector LTSSM Monitor 11.2.1.4. Accessing the Configuration Space and Transceiver Registers 11.2.1.5. Additional Status Commands
11.2.1.3. The PCIe* Link Inspector LTSSM Monitor x
11.2.1.3.1. LTSSM Monitor Registers 11.2.1.3.2. ltssm_save2file <file_name> 11.2.1.3.3. ltssm_file2console 11.2.1.3.4. ltssm_debug_check 11.2.1.3.5. ltssm_display <num_states> 11.2.1.3.6. ltssm_save_oldstates
11.2.1.4. Accessing the Configuration Space and Transceiver Registers x
11.2.1.4.1. PCIe* Link Inspector Commands 11.2.1.4.2. NPDME PLL and Channel Commands 11.2.1.4.3. Register Address Map
11.2.1.5. Additional Status Commands x
11.2.1.5.1. Displaying PLL Lock and Calibration Status Registers
A. PCI Express Core Architecture x
A.1. Transaction Layer A.2. Data Link Layer A.3. Physical Layer
C. Document Revision History x
C.1. Document Revision History for the L-Tile and H-Tile Avalon® Memory-mapped Intel® FPGA IP for PCI Express* User Guide
1. Introduction
2. Quick Start Guide
3. Interface Overview
4. Parameters
5. Designing with the IP Core
6. Block Descriptions
7. Registers
8. Programming Model for the DMA Descriptor Controller
9. Programming Model for the Avalon® -MM Root Port
10. Avalon-MM Testbench and Design Example
11. Troubleshooting and Observing the Link
A. PCI Express Core Architecture
B. Root Port Enumeration
C. Document Revision History

10.4.3. Configuration of Root Port and Endpoint

Before you issue transactions to the Endpoint, you must configure the Root Port and Endpoint Configuration Space registers.

The ebfm_cfg_rp_ep procedure executes the following steps to initialize the Configuration Space:

  1. Sets the Root Port Configuration Space to enable the Root Port to send transactions on the PCI Express link.
  2. Sets the Root Port and Endpoint PCI Express Capability Device Control registers as follows:
    1. Disables Error Reporting in both the Root Port and Endpoint. The BFM does not have error handling capability.
    2. Enables Relaxed Ordering in both Root Port and Endpoint.
    3. Enables Extended Tags for the Endpoint if the Endpoint has that capability.
    4. Disables Phantom Functions, Aux Power PM, and No Snoop in both the Root Port and Endpoint.
    5. Sets the Max Payload Size to the value that the Endpoint supports because the Root Port supports the maximum payload size.
    6. Sets the Root Port Max Read Request Size to 4 KB because the example Endpoint design supports breaking the read into as many completions as necessary.
    7. Sets the Endpoint Max Read Request Size equal to the Max Payload Size because the Root Port does not support breaking the read request into multiple completions.
  3. Assigns values to all the Endpoint BAR registers. The BAR addresses are assigned by the algorithm outlined below.
    1. I/O BARs are assigned smallest to largest starting just above the ending address of BFM shared memory in I/O space and continuing as needed throughout a full 32-bit I/O space.
    2. The 32-bit non-prefetchable memory BARs are assigned smallest to largest, starting just above the ending address of BFM shared memory in memory space and continuing as needed throughout a full 32-bit memory space.
    3. The value of the addr_map_4GB_limit input to the ebfm_cfg_rp_ep procedure controls the assignment of the 32-bit prefetchable and 64-bit prefetchable memory BARS. The default value of the addr_map_4GB_limit is 0.

      If the addr_map_4GB_limit input to the ebfm_cfg_rp_ep procedure is set to 0, then the ebfm_cfg_rp_ep procedure assigns the 32‑bit prefetchable memory BARs largest to smallest, starting at the top of 32-bit memory space and continuing as needed down to the ending address of the last 32-bit non-prefetchable BAR.

      However, if the addr_map_4GB_limit input is set to 1, the address map is limited to 4 GB. The ebfm_cfg_rp_ep procedure assigns 32-bit and 64-bit prefetchable memory BARs largest to smallest, starting at the top of the 32-bit memory space and continuing as needed down to the ending address of the last 32-bit non-prefetchable BAR.

    4. If the addr_map_4GB_limit input to the ebfm_cfg_rp_ep procedure is set to 0, then the ebfm_cfg_rp_ep procedure assigns the 64-bit prefetchable memory BARs smallest to largest starting at the 4 GB address assigning memory ascending above the 4 GB limit throughout the full 64-bit memory space.

      If the addr_map_4 GB_limit input to the ebfm_cfg_rp_ep procedure is set to 1, the ebfm_cfg_rp_ep procedure assigns the 32-bit and the 64-bit prefetchable memory BARs largest to smallest starting at the 4 GB address and assigning memory by descending below the 4 GB address to memory addresses as needed down to the ending address of the last 32-bit non-prefetchable BAR.

      The above algorithm cannot always assign values to all BARs when there are a few very large (1 GB or greater) 32-bit BARs. Although assigning addresses to all BARs may be possible, a more complex algorithm would be required to effectively assign these addresses. However, such a configuration is unlikely to be useful in real systems. If the procedure is unable to assign the BARs, it displays an error message and stops the simulation.

  4. Based on the above BAR assignments, the ebfm_cfg_rp_ep procedure assigns the Root Port Configuration Space address windows to encompass the valid BAR address ranges.
  5. The ebfm_cfg_rp_ep procedure enables master transactions, memory address decoding, and I/O address decoding in the Endpoint PCIe* control register.

The ebfm_cfg_rp_ep procedure also sets up a bar_table data structure in BFM shared memory that lists the sizes and assigned addresses of all Endpoint BARs. This area of BFM shared memory is write-protected. Consequently, any application logic write accesses to this area cause a fatal simulation error.

BFM procedure calls to generate full PCIe* addresses for read and write requests to particular offsets from a BAR use this data structure. This procedure allows the testbench code that accesses the Endpoint application logic to use offsets from a BAR and avoid tracking specific addresses assigned to the BAR. The following table shows how to use those offsets.

Table 75.  BAR Table Structure

Offset (Bytes)

Description

+0

PCI Express address in BAR0

+4

PCI Express address in BAR1

+8

PCI Express address in BAR2

+12

PCI Express address in BAR3

+16

PCI Express address in BAR4

+20

PCI Express address in BAR5

+24

PCI Express address in Expansion ROM BAR

+28

Reserved

+32

BAR0 read back value after being written with all 1’s (used to compute size)

+36

BAR1 read back value after being written with all 1’s

+40

BAR2 read back value after being written with all 1’s

+44

BAR3 read back value after being written with all 1’s

+48

BAR4 read back value after being written with all 1’s

+52

BAR5 read back value after being written with all 1’s

+56

Expansion ROM BAR read back value after being written with all 1’s

+60

Reserved

The configuration routine does not configure any advanced PCI Express capabilities such as the AER capability.

Besides the ebfm_cfg_rp_ep procedure in altpcietb_bfm_rp_gen3_x8.sv, routines to read and write Endpoint Configuration Space registers directly are available in the Verilog HDL include file. After the ebfm_cfg_rp_ep procedure runs the PCI Express I/O and Memory Spaces have the layout shown in the following three figures. The memory space layout depends on the value of the addr_map_4GB_limit input parameter. The following figure shows the resulting memory space map when the addr_map_4GB_limit is 1.

Figure 71. Memory Space Layout—4 GB Limit

The following figure shows the resulting memory space map when the addr_map_4GB_limit is 0.

Figure 72. Memory Space Layout—No Limit

The following figure shows the I/O address space.

Figure 73. I/O Address Space
Level Two Title