�ݺ�ߣ

© 2004 IBM Corporation
IBM Systems and Technology Group
1 z/VM CP Storage Management Education Series
Storage Prefixing on z/Architecture
A Brief Primer
Dan FitzGerald
Monday, October 19, 2009 (Revision 2)

04/27/15
z/VM CP Storage Management Education Series2
Outline
Review: Terminology
Background
Introduction to Prefixing
How Prefixing Works
Special Operations
Low-Address Protection
Suppression on Protection

04/27/15
Review: Terminology
In this portion of the presentation, we will introduce concepts
that will come up in our discussion on prefixing
Most of this information is available from the z/Architecture
Principles of Operation, Chapter 3.
We will present this information as a series of definitions.
This is intended to be a fast reference/review only, so please
consult the Principles of Operation or your Connections
Coach if you have any questions.

04/27/15
Review: Terminology
 There are four different types of addresses that we will encounter
in z/Architecture. They are known as “absolute”, “real”, “virtual” and
“logical.” Additionally, we will hear about “effective” addresses.
Absolute Address – The address assigned to a main storage
location
These are the unmodified, “actual” addresses of bytes in storage.
The “ultimate” address of any unit of storage; all addresses are
eventually translated into absolute addresses.
Real Address – Identifies a location in real storage
This is an address that we will use for an access to storage
As we will see, real addresses are converted by prefixing into absolute
addresses.
The “penultimate” address of any unit of storage; all addresses are
translated first into real addresses, then into absolute addresses.

04/27/15
Review: Terminology
Virtual Address – Identifies a location in virtual storage
When a virtual address is used for an access to main storage, it is
translated by means of dynamic address translation (DAT) to a real
address, which is then prefixed to an absolute address.
Logical Address – Your addresses are translated within
whatever mode the architecture is set to
In z/Architecture, a specific address mode can be set.
For example, your machine may be set to “real address mode”. In this
case, your logical addresses will be treated as real addresses.
Unless otherwise specified, the storage-operand addresses for most
instructions are logical addresses.
 Virtual and Logical are the addresses that a program will typically use

04/27/15
Review: Terminology
Effective Address – The address which exists before any
transformation by dynamic address translation or any
prefixing is performed
Instruction Address – Addresses used to fetch instructions
from storage

04/27/15
Background
Architecturally, low-order real memory (0 to 8191 bytes) is
very special
Lots of important stuff is kept there; things such as program interrupts
and things being passed back and forth between the hardware and the
software.
More specifically, old Program Status Words (PSWs) are stored there,
as are spaces for various machine check states.
Low-order memory is mapped and described in detail on pages 3-55
thru 3-64 of the Principles of Operation (SA22-7832-04).
This gives us a problem on multiprocessor systems
Each CPU has its own interrupts, PSWs, etc.
Each CPU wants to store these things in low-order memory.
Obviously, everybody cannot get their way.

04/27/15
Introduction to Prefixing
Prefixing is the solution to the aforementioned problem!
The concept is simple: every CPU needs low-order memory
for its own use, so why don't we just map “low-order”
memory somewhere else?
Prefixing is a one-to-one mapping between absolute storage
and what we will refer to as “real storage” (see the “Review”
section).

Each CPU's low-order real memory is transformed into
absolute addresses different from that of every other CPU
Absolute addresses that lie between 0 - 8191 must be
mapped to a space elsewhere in memory; for demonstration
purposes, say it's 10000 – 18191
Similarly, the address range 10000 – 18191 is mapped to 0 –
8191. This is a reverse prefix.

04/27/15
How Prefixing Works
The prefix is a 51-bit quantity contained in bit positions 0-50
of the prefix register
Bits 0-32 of this quantity are always all zeroes
When prefixing is applied, the software-generated real
address is converted to an absolute address using these
three rules:
1. If bits 0-50 of the address are all zeroes, replace them with bits 0-50 of the
prefix
2. If bits 0-50 of the address are equal to the prefix value, replace them with
all zeroes
3. If bits 0-50 of the address are neither all zeroes nor equal to the prefix,
leave the address unchanged. In this case, the “real” and “absolute”
addresses are identical.

04/27/15
How Prefixing Works
Only the address presented to storage is translated by
prefixing
The contents of the source of the address remain unchanged
A diagram of this process can be found on page 3-16 of the
Principles of Operation

04/27/15
Special Operations
While bits 0-32 of the prefix register are always zeroes, it is
possible to set bits 33-50
This is done through the use of the privileged instructions
SET PREFIX and STORE PREFIX
SET PREFIX sets bits 33-50 of the prefix register with the
value in bit positions 1-18 of a word in storage

04/27/15
Special Operations
Inversely, STORE PREFIX stores the value in bits 33-50 of
the prefix register into bit positions 1-18 of a word in storage

�ݺ�ߣ

Prefixing Education

More Related Content

Prefixing Education