MESSAGE SIGNALED INTERRUPT

Hope you might have read my previous article "Interrupt journey  from hardware to software"

Due to increasing pressure on chipset and processor packages to reduce pin count, the need for interrupt pins is expected to diminish over time.Devices, due to pin constraints, may implement messages to increase performance. 

PCI Express endpoints uses INTx emulation (in-band messages) instead of IRQ pin assertion. Using INTx emulation requires interruptsharing among devices connected to the same node (PCI bridge) while MSI is unique (non-shared) and does not require BIOS configuration support. As a result, the PCI Express technology requires MSI support for better interrupt performance.

INTERRUPT DELIVERY MECHANISM

Legacy PCI Interrupt Delivery

   

This mechanism supports devices that must use PCI-Compatible interrupt signaling (i.e., INTA#, INTB#, INTC#, and INTD#) defined for the PCI bus. Legacy functions use one of the interrupt lines to signal an interrupt. An INTx# signal is asserted to request interrupt service and deasserted when the interrupt service accesses a device-specific register, thereby indicating the interrupt is being serviced.

Native PCI Express Interrupt Delivery 

Native PCI Express device use message signaled interrupt. A Message Signaled Interrupt is not a PCI express message instead it is a simple memory write transaction. This write is distinguished from normal write by target address which is reserved for MSI interrupt delivery.

           PCI Express and Legacy Interrupt Delivery

Message Signaled Interrupts (MSIs) are delivered to the Root Complex via memory write transactions. The MSI Capability register provides all the information that the device requires to signal MSIs. This register is set up by configuration software (PCI bus driver) and includes the following information:

• Target memory address
• Data Value to be written to the specified address location
• The number of messages that can be encoded into the data

         MSI Capability Register

MSI Configuration Process

The following list specifies the steps taken by software (PCI bus driver) to configure MSI interrupts for a PCI Express device.

1. At startup time, the configuration software scans the PCI bus(es) (referred to as bus enumeration) and discovers devices (i.e., it performs configuration reads for valid Vendor IDs). On discovering a PCI express function, the configuration software reads the Capabilities List Pointer to obtain the location of the first Capability register within the chain of registers.

2. The software then searches the capability register sets until it discovers the MSI Capability register set (Capability ID of 05h).

3. Software assigns a dword-aligned memory address to the device's Message Address register. This is the destination address of the memory write used when delivering an interrupt request.

4. Software checks the Multiple Message Capable field in the device's Message Control register to determine how many event-specific messages the device would like assigned to it.

5. The software then allocates a number of messages equal to or less than what the device requested. At a minimum, one message will be allocated to the device.

6. The software writes the base message data pattern into the device's Message Data register.

7. Finally, the software sets the MSI Enable bit in the device's Message Control register, thereby enabling it to generate interrupts using MSI memory writes.

Memory Write Transaction (MSI):

When the device must generate an interrupt request, it writes the Message Data register contents to the memory address specified in its Message Address register. Header fields need to filled.

MSI-x is a extension to MSI which supports additional vectors per function.

Reference: PCI Express System Architecture

INTERRUPT JOURNEY FROM HARDWARE TO SOFTWARE - 1

Interrupt is a very vast topic. This post is about How Interrupt is generated from Peripheral and routed to the processor. Exactly till we get an IRQ number.

INTERRUPT: 

    An event external to the currently executing process that causes a change in the normal flow of instruction execution, usually generated by hardware devices external to the CPU sometimes by software.

We will deal software interrupts and exceptions in a separate post.

Hardware interrupts are asynchronous in nature.

How it is asynchronous ? 

Interrupt will not wait for nay other CPU routine to complete. It can be raised even in the middle of CPU execution.

Interrupt Vs Polling

Polling is a technique used by CPU to check for events in the peripheral device in a periodic manner.

Pros:

Efficient if interrupts arrive frequently.

Cons:

Takes precious CPU time even when there is no request from external device.

Each hardware interrupt has an interrupt level, trigger, and interrupt priority.

The following sections describe various interrupt components:

Interrupt Level

The interrupt level defines the source of the interrupt and is often referred to as the interrupt source. There are basically two types of interrupt levels: system and bus. The bus interrupts are generated by the devices on the buses (such as PCI, ISA, VDEVICE, and PCI-E). Examples of system interrupts are the timer and Environmental and Power Off Warning (EPOW).

Interrupt Trigger

There are two types of trigger mechanisms, level-triggered interrupts and edge-triggered interrupts.

Level-Triggered: A level-triggered interrupt module always generates an interrupt whenever the level of the interrupt source is asserted.

A device sends a signal (Setting this line to active), and keeps it at that state until the interrupt is serviced.
Typically, the processor samples the interrupt input at predefined times during each bus cycle
Pro:Level-triggered interrupt is favored by some because it is easy to share the interrupt Request line without losing the interrupts, when multiple shared devices interrupt at the same time. Upon detecting assertion of the interrupt line, the CPU must search through the devices sharing the interrupt Request line until one who triggered the interrupt is detected.
Con: As long as any device on the line has an outstanding request for service the line remains asserted, so it is not possible to detect a change in the status of any other device.

• 
  

An edge-triggered interrupt is an interrupt signalled by a level transition on the interrupt line, either a falling edge (high to low) or a rising edge (low to high). A device, wishing to signal an interrupt, drives a pulse onto the line and then releases the line to its inactive state.
Hybrid.

Some systems use a hybrid of level-triggered and edge-triggered signalling. The hardware not only looks for an edge, but it also verifies that the interrupt signal stays active for a certain period of time.

A common use of a hybrid interrupt is for the NMI (non-maskable interrupt) input.

A message-signaled interrupt does not use a physical interrupt line. Instead, a device signals its request for service by sending a short message over some communications medium, typically a computer bus. The message might be of a type reserved for interrupts, or it might be of some pre-existing type such as a memory write. This is been used by PCI Express devices.

To generate an interrupt request PCI Express device initiates a memory write transaction targeting north bridge (APIC Interrupt controller). The data written is a unique interrupt vector associated with device generating the interrupt.

Interrupt controller interrupts the CPU through North bridge and the vector is delivered to the CPU.

We will have a separate post on MSI.

doorbell interrupt is often used to describe a mechanism whereby a software system can signal or notify a computer hardware device that there is some work to be done. Typically, the software system will place data in some well known and mutually agreed upon memory location(s), and "ring the doorbell" by writing to a different memory location.

Interrupt Priorities

The interrupt priority defines which of a set of pending interrupts is serviced first.

INTERRUPT STATES

Inactive An interrupt that is not active or pending.
Pending An interrupt from a source to the PIC that is recognized as asserted in hardware or generated by software and is waiting to be serviced by a target processor.
Active An interrupt from a source to the PIC that has been acknowledged by a processor, and is being serviced but has not completed.
Active and pending A processor is servicing the interrupt and the PIC has a pending interrupt from the 
same source.

 

 programmable interrupt controller (PIC) is a device that is used to combine several sources of interrupt onto one or more CPU lines, while allowing priority levels to be assigned to its interrupt outputs. 

INTERRUPT CONTROLLER INTERNALS

Delivering the interrupt from Interrupt controller to processor completes with Interrupt acknowledgement sequence. As a result Processor will be getting the IRQ number.

1. Eight interrupt lines IR0-IR7 are connected to the interrupt request register (IRR). The IRR is eight bits wide, where every bit corresponds to one of the lines IR0-IR7. The device requiring service signals the PIC via one of the eight pins IR0-IR7 setting it to a high level. The 8259A then sets the corresponding bit in the IRR.
2. At the same time, the PIC activates its output INT line to inform the processor about the interrupt request. The INT line is directly connected to the INTR input of the processor. This starts an interrupt acknowledge sequence.
3. The CPU receives the INT signal, finishes the currently executing instruction and outputs a first interrupt acknowledge (INTA) pulse if the IE flag is set (that is, if the interrupts are not masked at the CPU).
4. Upon receival of the first INTA pulse from the CPU the highest priority in the IRR register is cleared and the corresponding bit in the in-service register (ISR) register is set.There is no PIC activity on the data bus in this cycle.
5. The processor initiates a second INTA pulse and thus causes the 8259A to put an 8-bit number onto the data bus. This 8 bit number is the IRQ number. The CPU reads this number as the number of the interrupt handler to call, through IDT-Interrupt Descriptor Table, which is then fetched and executed.
6. In the Automatic End Of Interrupt (AEOI) Mode the ISR bit is reset at the end of the second INTA pulse. Otherwise, the CPU must issue an End of Interrupt (EOI) to the 8259A PIC when executing the interrupt handler to clear the ISR bit manually.

The above procedure will give you a clear picture on how Interrupt is routed from Peripheral device to the Processor.

***More to be posted on Interrupt descriptor Table and how OS handles it.

Memory Mapping

Many of us have heard "Memory mapping" numerous time.

Hardware registers, data buffers are mapped ? Where it is mapped? 

We might have worked on lot of PCI devices with register set used for control, status, data access.

OS with the help of device drivers used to map the register space in device into main memory that is RAM.

Device drivers, kernel code does not have direct access over hardware, they will write or read from the mapped space in RAM. OS has special memory management functions to do this 
(eg: ioremap in linux). OS needs physical Base address to perform this operation which can be obtained from PCI configuration space (BAR- Base Address Register).


   Memory space


Devices are mapped into kernel space. Application are mapped to user space which have their own privilege

But, how data written into RAM (mapped space) is copied to Register space and values updated in hardware register is visible in RAM memory space?

load/store architecture only allows memory to be accessed by load and store operations, and all values for an operation need to be loaded from memory and be present in registers. Following the operation, the result needs to be stored back to memory

• load To load a value from memory, you copy the data from memory into a register.
• store To store a value to memory, you copy the data from a register to memory.