User manual
Table Of Contents
- Intel® IXP2800 Network Processor
- Copyright
- Contents
- Introduction 1
- Technical Description 2
- 2.1 Overview
- 2.2 Intel XScale® Core Microarchitecture
- 2.3 Microengines
- 2.4 DRAM
- 2.5 SRAM
- 2.6 Scratchpad Memory
- 2.7 Media and Switch Fabric Interface
- 2.8 Hash Unit
- 2.9 PCI Controller
- 2.10 Control and Status Register Access Proxy
- 2.11 Intel XScale® Core Peripherals
- 2.12 I/O Latency
- 2.13 Performance Monitor
- Intel XScale® Core 3
- 3.1 Introduction
- 3.2 Features
- 3.3 Memory Management
- 3.4 Instruction Cache
- 3.5 Branch Target Buffer (BTB)
- 3.6 Data Cache
- 3.6.1 Overviews
- 3.6.2 Data Cache and Mini-Data Cache Operation
- 3.6.3 Data Cache and Mini-Data Cache Control
- 3.6.4 Reconfiguring the Data Cache as Data RAM
- 3.6.5 Write Buffer/Fill Buffer Operation and Control
- 3.7 Configuration
- 3.8 Performance Monitoring
- 3.9 Performance Considerations
- 3.9.1 Interrupt Latency
- 3.9.2 Branch Prediction
- 3.9.3 Addressing Modes
- 3.9.4 Instruction Latencies
- 3.9.4.1 Performance Terms
- 3.9.4.2 Branch Instruction Timings
- 3.9.4.3 Data Processing Instruction Timings
- 3.9.4.4 Multiply Instruction Timings
- 3.9.4.5 Saturated Arithmetic Instructions
- 3.9.4.6 Status Register Access Instructions
- 3.9.4.7 Load/Store Instructions
- 3.9.4.8 Semaphore Instructions
- 3.9.4.9 Coprocessor Instructions
- 3.9.4.10 Miscellaneous Instruction Timing
- 3.9.4.11 Thumb Instructions
- 3.10 Test Features
- 3.11 Intel XScale® Core Gasket Unit
- 3.12 Intel XScale® Core Peripheral Interface
- 3.12.1 XPI Overview
- 3.12.2 UART Overview
- 3.12.3 UART Operation
- 3.12.4 Baud Rate Generator
- 3.12.5 General Purpose I/O (GPIO)
- 3.12.6 Timers
- 3.12.7 Slowport Unit
- Microengines 4
- DRAM 5
- SRAM Interface 6
- SHaC - Unit Expansion 7
- Media and Switch Fabric Interface 8
- 8.1 Overview
- 8.2 Receive
- 8.3 Transmit
- 8.4 RBUF and TBUF Summary
- 8.5 CSIX Flow Control Interface
- 8.6 Deskew and Training
- 8.7 CSIX Startup Sequence
- 8.8 Interface to Command and Push and Pull Buses
- 8.9 Receiver and Transmitter Interoperation with Framers and Switch Fabrics
- 8.9.1 Receiver and Transmitter Configurations
- 8.9.2 System Configurations
- 8.9.2.1 Framer, Single Network Processor Ingress and Egress, and Fabric Interface Chip
- 8.9.2.2 Framer, Dual Network Processor Ingress, Single Network Processor Egress, and Fabric Interface Chip
- 8.9.2.3 Framer, Single Network Processor Ingress and Egress, and CSIX-L1 Chips for Translation and Fabric Interface
- 8.9.2.4 CPU Complex, Network Processor, and Fabric Interface Chip
- 8.9.2.5 Framer, Single Network Processor, Co-Processor, and Fabric Interface Chip
- 8.9.3 SPI-4.2 Support
- 8.9.4 CSIX-L1 Protocol Support
- 8.9.5 Dual Protocol (SPI and CSIX-L1) Support
- 8.9.6 Transmit State Machine
- 8.9.7 Dynamic De-Skew
- 8.9.8 Summary of Receiver and Transmitter Signals
- PCI Unit 9
- 9.1 Overview
- 9.2 PCI Pin Protocol Interface Block
- 9.2.1 PCI Commands
- 9.2.2 IXP2800 Network Processor Initialization
- 9.2.3 PCI Type 0 Configuration Cycles
- 9.2.4 PCI 64-Bit Bus Extension
- 9.2.5 PCI Target Cycles
- 9.2.6 PCI Initiator Transactions
- 9.2.7 PCI Fast Back-to-Back Cycles
- 9.2.8 PCI Retry
- 9.2.9 PCI Disconnect
- 9.2.10 PCI Built-In System Test
- 9.2.11 PCI Central Functions
- 9.3 Slave Interface Block
- 9.4 Master Interface Block
- 9.5 PCI Unit Error Behavior
- 9.5.1 PCI Target Error Behavior
- 9.5.1.1 Target Access Has an Address Parity Error
- 9.5.1.2 Initiator Asserts PCI_PERR_L in Response to One of Our Data Phases
- 9.5.1.3 Discard Timer Expires on a Target Read
- 9.5.1.4 Target Access to the PCI_CSR_BAR Space Has Illegal Byte Enables
- 9.5.1.5 Target Write Access Receives Bad Parity PCI_PAR with the Data
- 9.5.1.6 SRAM Responds with a Memory Error on One or More Data Phases on a Target Read
- 9.5.1.7 DRAM Responds with a Memory Error on One or More Data Phases on a Target Read
- 9.5.2 As a PCI Initiator During a DMA Transfer
- 9.5.2.1 DMA Read from DRAM (Memory-to-PCI Transaction) Gets a Memory Error
- 9.5.2.2 DMA Read from SRAM (Descriptor Read) Gets a Memory Error
- 9.5.2.3 DMA from DRAM Transfer (Write to PCI) Receives PCI_PERR_L on PCI Bus
- 9.5.2.4 DMA To DRAM (Read from PCI) Has Bad Data Parity
- 9.5.2.5 DMA Transfer Experiences a Master Abort (Time-Out) on PCI
- 9.5.2.6 DMA Transfer Receives a Target Abort Response During a Data Phase
- 9.5.2.7 DMA Descriptor Has a 0x0 Word Count (Not an Error)
- 9.5.3 As a PCI Initiator During a Direct Access from the Intel XScale® Core or Microengine
- 9.5.3.1 Master Transfer Experiences a Master Abort (Time-Out) on PCI
- 9.5.3.2 Master Transfer Receives a Target Abort Response During a Data Phase
- 9.5.3.3 Master from the Intel XScale® Core or Microengine Transfer (Write to PCI) Receives PCI_PERR_L on PCI Bus
- 9.5.3.4 Master Read from PCI (Read from PCI) Has Bad Data Parity
- 9.5.3.5 Master Transfer Receives PCI_SERR_L from the PCI Bus
- 9.5.3.6 Intel XScale® Core Microengine Requests Direct Transfer when the PCI Bus is in Reset
- 9.5.1 PCI Target Error Behavior
- 9.6 PCI Data Byte Lane Alignment
- Clocks and Reset 10
- 10.1 Clocks
- 10.2 Synchronization Between Frequency Domains
- 10.3 Reset
- 10.4 Boot Mode
- 10.5 Initialization
- Performance Monitor Unit 11
- 11.1 Introduction
- 11.2 Interface and CSR Description
- 11.3 Performance Measurements
- 11.4 Events Monitored in Hardware
- 11.4.1 Queue Statistics Events
- 11.4.2 Count Events
- 11.4.3 Design Block Select Definitions
- 11.4.4 Null Event
- 11.4.5 Threshold Events
- 11.4.6 External Input Events
- 11.4.6.1 XPI Events Target ID(000001) / Design Block #(0100)
- 11.4.6.2 SHaC Events Target ID(000010) / Design Block #(0101)
- 11.4.6.3 IXP2800 Network Processor MSF Events Target ID(000011) / Design Block #(0110)
- 11.4.6.4 Intel XScale® Core Events Target ID(000100) / Design Block #(0111)
- 11.4.6.5 PCI Events Target ID(000101) / Design Block #(1000)
- 11.4.6.6 ME00 Events Target ID(100000) / Design Block #(1001)
- 11.4.6.7 ME01 Events Target ID(100001) / Design Block #(1001)
- 11.4.6.8 ME02 Events Target ID(100010) / Design Block #(1001)
- 11.4.6.9 ME03 Events Target ID(100011) / Design Block #(1001)
- 11.4.6.10 ME04 Events Target ID(100100) / Design Block #(1001)
- 11.4.6.11 ME05 Events Target ID(100101) / Design Block #(1001)
- 11.4.6.12 ME06 Events Target ID(100110) / Design Block #(1001)
- 11.4.6.13 ME07 Events Target ID(100111) / Design Block #(1001)
- 11.4.6.14 ME10 Events Target ID(110000) / Design Block #(1010)
- 11.4.6.15 ME11 Events Target ID(110001) / Design Block #(1010)
- 11.4.6.16 ME12 Events Target ID(110010) / Design Block #(1010)
- 11.4.6.17 ME13 Events Target ID(110011) / Design Block #(1010)
- 11.4.6.18 ME14 Events Target ID(110100) / Design Block #(1010)
- 11.4.6.19 ME15 Events Target ID(110101) / Design Block #(1010)
- 11.4.6.20 ME16 Events Target ID(100110) / Design Block #(1010)
- 11.4.6.21 ME17 Events Target ID(110111) / Design Block #(1010)
- 11.4.6.22 SRAM DP1 Events Target ID(001001) / Design Block #(0010)
- 11.4.6.23 SRAM DP0 Events Target ID(001010) / Design Block #(0010)
- 11.4.6.24 SRAM CH3 Events Target ID(001011) / Design Block #(0010)
- 11.4.6.25 SRAM CH2 Events Target ID(001100) / Design Block #(0010)
- 11.4.6.26 SRAM CH1 Events Target ID(001101) / Design Block #(0010)
- 11.4.6.27 SRAM CH0 Events Target ID(001110) / Design Block #(0010)
- 11.4.6.28 DRAM DPLA Events Target ID(010010) / Design Block #(0011)
- 11.4.6.29 DRAM DPSA Events Target ID(010011) / Design Block #(0011)
- 11.4.6.30 IXP2800 Network Processor DRAM CH2 Events Target ID(010100) / Design Block #(0011)
- 11.4.6.31 IXP2800 Network Processor DRAM CH1 Events Target ID(010101) / Design Block #(0011)
- 11.4.6.32 IXP2800 Network Processor DRAM CH0 Events Target ID(010110) / Design Block #(0011)

Hardware Reference Manual 265
Intel
®
IXP2800 Network Processor
Media and Switch Fabric Interface
Payload Offset — Number of bytes to skip from the last 64-bit word of the Prepend to the start of
Payload. The absolute byte number of the first byte of Payload in the element is:
((Prepend Offset + Prepend Length + 0x7) && 0xF8) + Payload Offset.
Payload Length — Number of bytes of Payload.
The sum of Prepend Length, Payload length, and any gaps in between them (((prepend_offset +
prepend_length + 7) & 0xF8) + payload_offset + payload_length) must be no greater than the
number of bytes in the element. Typically, the Prepend is computed by a Microengine and written
into the TBUF by
msf[write] and the Payload will be written by dram[tbuf_wr]. These two
operations can be done in either order; the microcode is responsible for making sure the element is
not marked valid to transmit until all data is in the element (see Section 8.3.3).
Example 36 illustrates the usage of the parameters. The element in Example 36 is shown as 8 bytes
wide because the smallest unit that can be moved into the element is 8 bytes. In Example 36, bytes
to be transmitted are shown in black (the offsets are byte numbers); bytes in gray are written into
TBUF (because the writes always write 8 bytes), but are not transmitted.
Prepend Offset = 6 (bytes 0x0 — 0x5 are not transmitted).
Prepend Length = 16 (bytes 0x6 — 0x15 are transmitted).
Payload Offset = 7 (bytes 0x16 — 0x1E are not transmitted). The Payload starts in the next 8-byte
row (i.e., the next “empty” row above where the Prepend stops), even if there is room in the last
row containing Prepend information. This is done because the TBUF does not have byte write
capability, and therefore would not merge the
msf[write] and dram[tbuf_wr]. The software
computing the Payload Offset only needs to know how many bytes of the payload that were put
into DRAM need to be removed.
Payload Length = 33 (bytes 0x1F through 0x3F are transmitted).
The transmit logic will send the valid bytes onto TDAT correctly aligned and with no gaps. The
protocol transmitted, SPI-4 or CSIX (and the value of the TPROT output) are based on which
partition of TBUF the data was placed (see Table 95).
Example 36. TBUF Prepend and Payload
0 1 2 3 4 5 67
89ABCDEF
10 11 12 13 14 15 16 17
18 19 1A 1B 1C 1D 1E 1F
20 21 22 23 24 25 26 27
28 29 2A 2B 2C 2D 2E 2F
30 31 32 33 34 35 36 37
38 39 3A 3B 3C 3D 3E 3F