03 29 PCI Express Basics

PCI Express Basics
Ravi Budruk Senior Staff Engineer and Partner MindShare, Inc.
Copyright 2007, PCI-SIG, All Rights Reserved
PCI Express Introduction

PCI Express architecture is a high performance, IO interconnect for peripherals in computing/communication platforms Evolved from PCI and PCI-X architectures
Yet PCI Express architecture is significantly different from its predecessors PCI and PCI-X
PCI Express is a serial point-to-point interconnect between two devices Implements packet based protocol for information transfer Scalable performance based on number of signal Lanes implemented on the PCI Express interconnect
PCI-SIG Developers Conference
PCI Express Terminology

PCI Express Device A
Signal Wire
Link Lane
PCI Express Device B

PCI-SIG Developers Conference Copyright 2007, PCI-SIG, All Rights Reserved 3
PCI Express Throughput

Link Width Aggregate BW (GBytes/s) x1 0.5 x2 1 x4 2 x8 4 x12 6 x16 8 x32 16
Assumes 2.5 GT/s signaling in each direction 80% BW utilized due to 8b/10b encoding overhead Aggregate bandwidth implies simultaneous traffic in both directions Peak bandwidth is higher than any bus available PCIe 2.0 PHYs may optionally support 5 GT/s signaling, thus doubling above bandwidth numbers
PCI Express Features

Point-to-point connection Serial bus means fewer pins Scaleable: x1, x2, x4, x8, x12, x16, x32 Dual Simplex connection 2.5VGT/s transfer/direction/s Packet based transaction protocol
PCIe Device A
Packet
Link (x1, x2, x4, x8, x12, x16 or x32)

Packet
PCIe Device B
5
Differential Signaling
Electrical characteristics of PCI Express signal
Differential signaling
Transmitter Differential Peak voltage = 0.4 - 0.6 V Transmitter Common mode voltage = 0 - 3.6 V
DVcm D+ V Diffp
Two devices at opposite ends of a Link may support different DC common mode voltages
Example PCI Express Topology

CPU
Root Complex
PCIe PCIe PCIe Switch Endpoint PCIe PCIe PCIe
Memory
PCIe Endpoint
PCIe
PCIe Bridge To
PCI/PCI-X
PCIe Endpoint
Legacy Endpoint
PCI/PCI-X
Legend PCI Express Device Downstream Port PCI Express Device Upstream Port
Example PCI Express Topology Root & Switch

CPU Bus
CPU Root
RCRB
Bus 0
Root Complex
PCIe PCIe PCIe Switch Endpoint PCIe PCIe PCIe
Memory
Virtual PCI Bridge
Virtual PCI Bridge
Virtual PCI Bridge
PCIe Endpoint
PCIe
PCIe Bridge To
PCI/PCI-X
PCI Express Links
PCIe Endpoint
Legacy Endpoint
Switch
PCI/PCI-X
Virtual PCI Bridge
Virtual PCI Bridge
Legend PCI Express Device Downstream Port PCI Express Device Upstream Port
PCI-SIG Developers Conference Copyright 2007, PCI-SIG, All Rights Reserved
Virtual PCI Bridge
Virtual PCI Bridge
Example Low Cost PCI Express System

Processor FSB PCI Express GFX GFX
Root Complex
DDR SDRAM
Slots
HDD
Serial ATA USB 2.0 LPC
PCI Express PCI IO Controller Hub (ICH) IEEE 1394

Slot
S IO
COM1 COM2
GB Ethernet
Add-In Add-In Add-In PCI Express
PCI Express Link

Example PCI Express Server System

Processor FSB PCI Express GFX GFX Endpoint InfiniBand Switch Out-of-Box 10Gb Ethernet Endpoint Processor
Root Complex
DDR SDRAM
InfiniBand Endpoint
Switch
Switch
Fiber Channel RAID Disk array
Add-In
Switch
10Gb Ethernet Endpoint
PCI Express to-PCI Endpoint
SCSI Endpoint PCI
PCI Express Link
Add-In
Gb Ethernet Endpoint
COM1 COM2
S IO
IEEE 1394
Slots
10
Transaction Types, Address Spaces

Request are translated to one of four transaction types by the Transaction Layer:
1. Memory Read or Memory Write. Used to transfer data from or to a memory mapped location The protocol also supports a locked memory read transaction variant. I/O Read or I/O Write. Used to transfer data from or to an I/O location These transactions are restricted to supporting legacy endpoint devices. Configuration Read or Configuration Write. Used to discover device capabilities, program features, and check status in the 4KB PCI Express configuration space. Messages. Handled like posted writes. Used for event signaling and general purpose messaging.
2.
3.
4.
11
PCI Express TLP Types

Description
Memory Read Request Memory Read Request Locked Access Memory Write Request IO Read Request IO Write Request Configuration Read Request Type 0 and Type 1 Configuration Write Request Type 0 and Type 1 Message Request without Data Payload Message Request with Data Payload Completion without Data (used for IO, configuration write completions and read completion with error completion status) Completion with Data (used for memory, IO and configuration read completions) Completion for Locked Memory Read without Data (used for error status) Completion for Locked Memory Read with Data
Abbreviated Name
MRd MRdLk MWr IORd IOWr CfgRd0, CfgRd1 CfgWr0, CfgWr1 Msg MsgD Cpl CplD CplLk CplDLk
12
Three Methods For Packet Routing

Each request or completion header is tagged as to its type, and each of the packet types is routed based on one of three schemes:
Address Routing ID Routing Implicit Routing
Memory and IO requests use address routing. Completions and Configuration cycles use ID routing. Message requests have selectable routing based on a 3-bit code in the message routing sub-field of the header type field.
13
Programmed I/O Transaction

Processor MRd Requester: -Step 1: Root Complex (requester) initiates Memory Read Request (MRd) -Step 4: Root Complex receives CplD MRd Switch A MRd CplD Switch B MRd Endpoint Endpoint Endpoint CplD Completer: -Step 2: Endpoint (completer) receives MRd -Step 3: Endpoint returns Completion with data (CplD) Endpoint Endpoint FSB Processor
Root Complex CplD Switch C
DDR SDRAM
14
DMA Transaction
Processor FSB Completer: -Step 2: Root Complex (completer) receives MRd -Step 3: Root Complex returns Completion with data (CplD) CplD Switch A CplD MRd Switch B Endpoint Endpoint Endpoint Processor
Root Complex MRd Switch C
DDR SDRAM
CplD Endpoint Endpoint
MRd Requester: -Step 1: Endpoint (requester) initiates Memory Read Request (MRd) -Step 4: Endpoint receives CplD
15
Peer-to-Peer Transaction
Processor FSB Processor
Root Complex CplD Switch A CplD MRd Switch B Endpoint MRd Endpoint CplD Endpoint MRd MRd Switch C CplD
DDR SDRAM
CplD Endpoint Endpoint
MRd
Requester: -Step 1: Endpoint (requester) initiates Memory Read Request (MRd) -Step 4: Endpoint receives CplD
Completer: -Step 2: Endpoint (completer) receives MRd -Step 3: Endpoint returns Completion with data (CplD)
16
PCI Express Device Layers

PCI Express Device A Device Core PCI Express Core Logic Interface
TX RX TX
PCI Express Device B Device Core PCI Express Core Logic Interface
RX
Transaction Layer Data Link Layer Physical Layer

Link
17
TLP Origin and Destination

TX TLP Transmitted RX TX
RX TLP Received

Link
18
TLP Structure
Information in core section of TLP comes from Software Layer / Device Core Bit transmit direction
Start Sequence Header

1B 2B 3-4 DW
Data Payload
0-1024 DW
ECRC LCRC End

1DW 1DW 1B
Created by Transaction Layer
Appended by Data Link Layer
Appended by Physical Layer

DLLP Origin and Destination

TX RX TX
RX
Transaction Layer
DLLP Transmitted

Link DLLP Received
Data Link Layer Physical Layer
20
DLLP Structure
Bit transmit direction
Start
1B
DLLP
4B
CRC
2B
End
1B
Data Link Layer
Appended by Physical Layer
ACK / NAK Packets Flow Control Packets Power Management Packets Vendor Defined Packets
21
Ordered-Set Origin and Destination

TX RX TX
RX
Transaction Layer Data Link Layer

Ordered-Set Transmitted

Link Ordered-Set Received
Physical Layer
22
Ordered-Set Structure
COM Identifier Identifier Identifier
Training Sequence One (TS1)

16 character set: 1 COM, 15 TS1 data characters
Training Sequence Two (TS2)

16 character set: 1 COM, 15 TS2 data characters
SKIP
4 character set: 1 COM followed by 3 SKP identifiers
Electrical Idle (IDLE)

4 characters: 1 COM followed by 3 IDL identifiers
Fast Training Sequence (FTS)

4 characters: 1 COM followed by 3 FTS identifiers
Quality of Service
Processor PCI Express GFX GFX Endpoint InfiniBand Switch Out-of-Box 10Gb Ethernet Endpoint Processor
Root Complex
DDR SDRAM
InfiniBand Endpoint
Switch
Switch
Fiber Channel RAID Disk array
Add-In
Slot
Switch
10Gb Ethernet Endpoint
PCI Express to-PCI Endpoint
SCSI Endpoint PCI
PCI Express Link

Video Camera
SCSI Endpoint
COM1 COM2
S IO
IEEE 1394
Slots
24
Traffic Classes and Virtual Channels

Quality of Service (QoS) policy through Virtual Channel and Traffic Class tags
Transmitter Device A
TC[2:0] maps to VC0 VC0
Receiver Device B Link VC0 TC/VC Mapping VC0 Arbitration
TC[7:0]
TC/VC Mapping
Buffers
TC[7:3] maps to VC1 VC1
Buffers TC[7:0] VC1
VC1
One physical Link, multiple virtual paths
25
Port Arbitration and VC Arbitration

Link
TC[2:0] to VC0 TC[7:3] to VC1
VC0 VC1
ng pi rt 0 ap o M sP VC es C/ Egr T r fo
Link
VC0 Port Arb VC1 Port Arb VC0 VC Arb VC1
VC0 0 VC1
TC[2:0] to VC0 TC[7:3] to VC1
VC0 VC1
T f C or /V Eg C re Ma ss pp P i or ng t0
Link
26
PCI Express Flow Control

Credit-based flow control is point-to-point based, not end-to-end
Buffer space available TLP VC Buffer
Transmitter
Receiver
Flow Control DLLP (FCx) Receiver sends Flow Control Packets (FCP) which are a type of DLLP (Data Link Layer Packet) to provide the transmitter with credits so that it can transmit packets to the receiver
27
ACK/NAK Protocol Overview

Transmit Device A
From Transaction Layer Tx
Receiver Device B
To Transaction Layer Rx
Data Link Layer

TLP Sequence TLP Replay Buffer Mux DLLP LCRC
ACK / NAK
Data Link Layer

DLLP
ACK / NAK
TLP Sequence TLP De-mux
LCRC
De-mux Mux Error Check
Tx
Rx
DLLP
ACK / NAK
Tx
Rx
Link
TLP Sequence TLP PCI-SIG Developers Conference LCRC 28
ACK/NAK Protocol: Point-to-Point

1a. Request 4b. ACK Requester 1b. ACK 4a. Completion Switch 2b. ACK 3a. Completion 2a. Request 3b. ACK Completer
ACK returned for good reception of Request or Completion NAK returned for error reception of Request or Completion
29
Interrupt Model: Three Methods

PCI Express supports three interrupt reporting mechanisms:
1. Message Signaled Interrupts (MSI)
Legacy endpoints are required to support MSI (or MSI-X) with 32- or 64-bit MSI capability register implementation
Native PCI Express endpoints are required to support MSI with 64-bit MSI capability register implementation
2. 3.
Message Signaled Interrupts - X (MSI-X)

Legacy and native endpoints are required to support MSI-X (or MSI) and implement the associated MSI-X capability register Native and Legacy endpoints are required to support Legacy INTx Emulation PCI Express defines in-band messages which emulate the four physical interrupt signals (INTA-INTD) routed between PCI devices and the system interrupt controller Forwarding support required by switches
Copyright 2007, PCI-SIG, All Rights Reserved 30
INTx Emulation.

Native and Legacy Interrupts
PCIe -
PCIe
PCIe
31
PCI Express Error Handling

All PCI Express devices are required to support some combination of:
Existing software written for generic PCI error handling, and which takes advantage of the fact that PCI Express has mapped many of its error conditions to existing PCI error handling mechanisms. Additional PCI Express-specific reporting mechanisms
Errors are classified as correctable and uncorrectable. Uncorrectable errors are further divided into:
Fatal uncorrectable errors Non-fatal uncorrectable errors.
32
Correctable Errors
Errors classified as correctable, degrade system performance, but recovery can occur with no loss of information
Hardware is responsible for recovery from a correctable error and no software intervention is required.
Even though hardware handles the correction, logging the frequency of correctable errors may be useful if software is monitoring link operations. An example of a correctable error is the detection of a link CRC (LCRC) error when a TLP is sent, resulting in a Data Link Layer retry event.
33
Uncorrectable Errors
Errors classified as uncorrectable impair the functionality of the interface and there is no specification mechanism to correct these errors The two subgroups are fatal and non-fatal
1. Fatal Uncorrectable Errors: Errors which render the link unreliable
First-level strategy for recovery may involve a link reset by the system Handling of fatal errors is platform-specific
2.
Non-Fatal Uncorrectable Errors: Uncorrectable errors associated with a particular transaction, while the link itself is reliable
Software may limit recovery strategy to the device(s) involved Transactions between other devices are not affected
34
Baseline Error Reporting

Enabling/disabling error reporting Providing error status Providing error status for Link Training Initiating Link Re-training Registers provide control and status for
Correctable errors Non-fatal uncorrectable errors Fatal uncorrectable errors Unsupported request errors
Advanced Error Reporting

Finer granularity in defining error type Ability to define severity of uncorrectable errors
Either send ERR_FATAL or ERR_NONFATAL message for a given error
Support for error logging of error type and TLP header related to error Ability to mask reporting of errors Enable/disable root reporting of errors Identify source of errors
36
PCI Express Configuration Space
37
Summary of Changes for 2.0

Higher speed (5.0 GT/s), supported by:
Selectable de-emphasis levels Selectable transmitter voltage range
Dynamic speed and link width changes

Power savings, higher bandwidth, reliability
Virtualization support
Access Control Services
Other New Features

Completion timeout control Function Level Reset Modified Compliance Pattern for testing
38
Thank you for attending the PCI-SIG Developers Conference 2007.
For more information please go to www.pcisig.com

PCI Express Basics

Ravi Budruk Senior Staff Engineer and Partner MindShare, Inc.
40

03 29 PCI Express Basics

Uploaded by

Copyright:

Available Formats

03 29 PCI Express Basics

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

03 29 PCI Express Basics

Uploaded by

Copyright:

Available Formats

PCI Express Basics

Ravi Budruk Senior Staff Engineer and Partner MindShare, Inc.

Copyright 2007, PCI-SIG, All Rights Reserved

PCI Express Introduction

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

PCI Express Terminology

PCI Express Device B

PCI Express Throughput

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

PCI Express Features

Link (x1, x2, x4, x8, x12, x16 or x32)

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

Example PCI Express Topology

Example PCI Express Topology Root & Switch

Virtual PCI Bridge

Virtual PCI Bridge

Virtual PCI Bridge

PCI Express Links

Virtual PCI Bridge

Virtual PCI Bridge

Virtual PCI Bridge

Example Low Cost PCI Express System

Serial ATA USB 2.0 LPC

PCI Express PCI IO Controller Hub (ICH) IEEE 1394

Add-In Add-In Add-In PCI Express

PCI Express Link

Copyright 2007, PCI-SIG, All Rights Reserved

Example PCI Express Server System

Fiber Channel RAID Disk array

10Gb Ethernet Endpoint

PCI Express to-PCI Endpoint

SCSI Endpoint PCI

PCI Express Link

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

Transaction Types, Address Spaces

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

PCI Express TLP Types

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

Three Methods For Packet Routing

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

Programmed I/O Transaction

Root Complex CplD Switch C

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

Root Complex MRd Switch C

CplD Endpoint Endpoint

PCI-SIG Developers Conference

Copyright 2007, PCI-SIG, All Rights Reserved

CplD Endpoint Endpoint

PCI-SIG Developers Conference

PCI Express Device Layers

Transaction Layer Data Link Layer Physical Layer

Transaction Layer Data Link Layer Physical Layer