P-Tile Avalon® Streaming Intel® FPGA IP for PCI Express* User Guide

ID 683059
Date 3/28/2022
Public

A newer version of this document is available.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

Document Table of Contents

4.7.1. Completion Timeout Interface

The P-Tile IP for PCIe features a Completion timeout mechanism to keep track of Non-Posted requests sent by the user application and the corresponding Completions received. When the P-Tile IP detects a Completion timeout, it notifies the user application by asserting the cpl_timeout_o signal.

When a Completion timeout happens, the user application can use the Avalon® -MM Completion Timeout Interface (for each port) to access the Completion timeout FIFO in the Hard IP to get more detailed information about the event and update the AER capability registers if required. After the completion timeout FIFO becomes empty, the IP core deasserts the cpl_timeout_o signal.

The cpl_timeout_avmm interface is synchronized to the cpl_timeout_avmm_clk_i clock.

Example:

When cpl_timeout_o is asserted, the user application can issue an Avalon® -MM Read to retrieve information from the Completion FIFO. Then, it can issue an Avalon® -MM Write to write 1 to bit[0] of the CONTROL register to get access to the next data.

Note: User application logic should not use this interface during TLP Bypass mode as the information on this interface is not valid in that mode.
Table 67.  Completion Timeout Interface
Signal Name Direction Description Clock domain EP/RP/BP
cpl_timeout_o O

Indicates the event that the completion TLP for a request has not been received within the expected time window.

The IP core asserts this signal as long as the completion timeout FIFO in the Hard IP is not empty.

You can obtain more details about the completion timeout event by looking at the signals on the completion timeout Avalon® -MM interface (listed below).

coreclkout_hip EP/RP/BP
cpl_timeout_avmm_read_i I Avalon® -MM read enable. cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_readdata_o[7:0] O Avalon® -MM read data outputs. cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_readdata_valid_o O This signal qualifies the cpl_timeout_avmm_readdata_o signals into the Application Layer. cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_write_i I Avalon® -MM write enable. cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_writedata_i[7:0] I Avalon® -MM write data inputs. cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_addr_i[20:0] I

Avalon® -MM address inputs.

[20:3] : Reserved. Tie them to 0.

[2:0] : Address for the FIFO register. Refer to the address map table below for more details.

cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_waitrequest_o O When asserted, this signal indicates the IP core is not ready to take any request. cpl_timeout_avmm_clk_i EP/RP/BP
cpl_timeout_avmm_clk_i I

Avalon® -MM clock.

50 MHz - 125 MHz (Range)

100 MHz (Recommended)

  EP/RP/BP
Note: The Completion Timeout Interface has a separate address map that is isolated from other address maps.
Table 68.  Address Map for the Completion Timeout Interface
Address Name Access Type Description
0x0 STATUS RO

[7:2] : Reserved

[1] : Completion timeout FIFO full

[0] : Completion timeout FIFO empty

0x1 CONTROL WO

[7:1] : Reserved

[0] : Read (popping data from the FIFO). You need to read all the information regarding the timed out request before writing 1 to bit 0 of the CONTROL register. Writing to bit 0 of the CONTROL register makes the next data appear.

0x2 VF RO

[7:0] : vfunc_num[7:0]

Virtual Function number for the VF that initiates the non-posted transaction for which the completion timeout is observed.

0x3 PF RO

[7] : vfunc_active

[6] : Reserved

[5:3] : func_num[2:0]

Physical function number (least significant 8 bits) for the PF that initiates the non-posted transaction for which the completion timeout is observed.

[2:0] : vfunc_num[10:8]

Virtual Function number (most significant 3 bits) for the VF that initiates the memory read request for which the completion timeout is observed.

0x4 LEN1 RO

[7:0] : cpl_lenn[7:0]

Transfer length in bytes (least significant 8 bits), of the expected completion that timed out for the non-posted transaction. For a split completion, it indicates the number of bytes remaining to be delivered when the completion timed out (Max length is Max Read request size. Ex: 4K Bytes = 2^12 bytes)

0x5 LEN2 RO

[7:4] : Reserved

[3:0] : cpl_lenn[11:8]

Transfer length in bytes (most significant 4 bits), of the expected completion that timed out for the non-posted transaction. For a split completion, it indicates the number of bytes remaining to be delivered when the completion timed out (Max length is Max Read request size. Ex: 4K Bytes = 2^12 bytes)

0x6 TAG1 RO

[7:0] : cpl_tag[7:0]

Tag ID (least significant 8 bits) of the expected completion that timed out for the non-posted transaction.

0x7 TAG2 RO

[7:5] : cpl_tc[2:0]

Traffic class of the expected completion that timed out for the non-posted transaction.

[4:3] : cpl_attr[1:0]

Attribute of the expected completion that timed out for the non-posted transaction. ID based ordering is not supported. [4] -> Relaxed ordering, [3] -> No Snoop

[2] : Reserved

[1:0]: cpl_tag[9:8]

Tag ID (most significant 2 bits) of the expected completion that timed out for the non-posted transaction.