In z/OS, it is also protected (most of the time) by low-address protection. When bit 35 of CR0 is '1'b, then a CPU instruction cannot modify this area. Even in key 0. The area, of course, can be updated by various interrupts. This refers to low core in the "real address" sense, not in the "absolute address" sense. Which makes me wonder about something. I know that each CP has its own "prefix register". This maps the first 8K of the "real" address range to some other 8K absolute address. In z/OS, virtual address 0 in an address space is always mapped to real location 0 (correct?). But, since each CP has its own "real" address 0 range of 8K, are the other CP's FLC mapped into virtual storage on this CP? If so, then I guess it would be possible for FLC to become corrupted by an errant key 0 routine. Which would make me hope that the FLC for the "other" CPs are not mapped into the virtual address space at all.
On Thu, Jun 27, 2013 at 9:39 AM, Tom Marchant <m42tom-ibmm...@yahoo.com>wrote: > On Wed, 26 Jun 2013 22:45:50 -0700, Ed Jaffe wrote: > > >AFAIK, there is only one 4K range of virtual addresses guaranteed to > >generate 0C4 now and forever: 7FFFF000 - 7FFFFFFF. > > I didn't know that. Is it documented anywhere? > > The 4K range from 00000000 - 00000FFF is key 0 storage and, as such, > is protected from stores by unauthorized programs. > > -- > Tom Marchant > > ---------------------------------------------------------------------- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > -- This is a test of the Emergency Broadcast System. If this had been an actual emergency, do you really think we'd stick around to tell you? Maranatha! <>< John McKown ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN