With ESA it was 'absolute' zero. I remember because we had users complain about the unusable portion of a HIPERSPACE which was the PSA.
-teD Original Message From: Robert Hahne Sent: Friday, February 26, 2016 01:36 To: IBM-MAIN@LISTSERV.UA.EDU Reply To: IBM Mainframe Discussion List Subject: Re: Prefix save area - confused In MVS/XA , with prefixing, the processors did not use absolute locations 0-4095. Rather, each processor had its own separate PSA and its own prefix register. When a processor is brought on line, the real starting address of its PSA is stored in its prefix register. Whenever the processor uses an address between 0 and 4095, the hardware adds the the contents of the prefix register to the address and uses the result. With prefixing, the address that normally would be the absolute address of the information in the first page of storage becomes an offset from the start of the real PSA. Because each processor's prefix register contains a different address, each processor can address locations 0 to 4095 and reference its own data. In Z/architecture , it used to fix the first 2 pages unlike MVS/XA and the concept did not change AFAIK ... Robert Hahne > Date: Thu, 25 Feb 2016 09:46:00 -0600 > From: 0000000a2a8c2020-dmarc-requ...@listserv.ua.edu > Subject: Re: Prefix save area - confused > To: IBM-MAIN@LISTSERV.UA.EDU > > On Thu, 25 Feb 2016 07:39:30 +0100, Peter Hunkeler wrote: > > >The 8 KiB area at absolute 0 is the place where the hardware writes > >status information as result of performing the "Store Status" operation. > > Among other things. Those Assigned Storage Locations are defined by > the architecture. Other areas within the PSA are defined by the > operating system. > > >It has existed for longer than PR/SM. I would say, it is owned by the > >hardware. > > >> There is Absolute addressing, real addressing, and virtual addressing. > > > >But wait a minute, isn't there on more level? Absolulte, real, and > >virtual are *within* an LPAR. It is required to support multi-CP > >operating system *instances*. Since PR/SM, each LPAR must have its > >own "absolute address 0", doesn't it? > > Yes. > > >Actually, the requirement has exited since physically partitionable CECs > >had been in place (can't remember exaxtly which were the first such > >machines, 3033, or 308x, or?). > > Probably System/360 model 65MP. For sure model 67. > > >The net would be: Some code is accessing virtual address 0. The DAT > >feature will (with the help of the DAT tables) translate virtual 0 to *a* > >real address (which just happens to always be real frame 0 in z/OS). > >The hardware will recognize an address within the "prefixing area" (8 KiB > >in z/Architcture, 4 KiB in ESA/390 and predecessors, 2 KiB in even earlier > >architectures?), > > System/360 Principles of operation has described prefixing all the way > back to the -0 level of the manual. You can find it at > http://bitsavers.trailing-edge.com/pdf/ibm/360/princOps/A22-6821-0_360PrincOps.pdf > The description is on page 18, under "Multisystem Feature". It is > described there as a 4K area. > > Before the -4 level of the System/370 POO in 1974, the SET PREFIX > instruction was defined. It was not in the -0 edition. > > -- > Tom Marchant > > ---------------------------------------------------------------------- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
