Messages in this thread | | | Date | Mon, 18 Aug 2008 18:39:43 +0400 | From | Cyrill Gorcunov <> | Subject | Re: [PATCH 2/6] x86: apic - unify lapic_resume |
| |
[Maciej W. Rozycki - Mon, Aug 18, 2008 at 03:19:05PM +0100] | On Sun, 17 Aug 2008, Cyrill Gorcunov wrote: | | > it seems this limit is not APIC related since iirc 82489DX allows | > to address 2^14 bits, x2APIC - more then 128 entities too. So I suspect | > it somehow cpu bitmap related. Am I wrong (I didn't _check_ the code)? | | For the record: the 82489DX supports an 8-bit physical unit ID so 256 | distinct values are supported. Of these I gather 255 is taken for the | broadcast ID in the physical destination mode, but that is nowhere | explicitly confirmed in the 82489DX docs (it can be implied from protocol | description though). While the ID is indeed 8-bit in the 82489DX, for | systems where future compatibility was a concern Intel recommended the use | of IDs from 0 through to 14 only in anticipation of the future integrated | APIC with the physical mode addressing capability limited to 4 bits only | (and 15 taken for the broadcast ID). | | Full 32 bits are available with the 82489DX for the logical destination | mode and only the flat (no cluster) mode is supported. | | Maciej |
Thanks, Maciej! The doc says to use 0-14 so I misinterpreted it as bits :(. I've to be more carefull next time. Thanks!
- Cyrill -
| |