Messages in this thread | | | Date | Fri, 8 Aug 1997 01:24:41 +0100 (BST) | From | Mark Hemment <> | Subject | Re: Kernel virtual memory? |
| |
On Thu, 7 Aug 1997, Jochen Karrer wrote: > > DMA memory could be allocated by moving allocated blocks away from the > > lower 16MB, and other parts of kernel could be made happy by changing the > > page tables accordingly. > > > > So, is this possible/feasible/too ugly to implement? > Not possible.
Both Benjamin LaHaise and I are working on [different] schemes which allow this. Infact, it is possible to do (to a limited extent) with the current Memory Managment scheme. Although, it would be very ugly.
Once there was the idea of supporting a re-locatable kernel; when memory is greater than 16MB loading the kernel into high memory would make more DMA pages available (for Intel with the ISA restrictions). There was a problem with some (SCSI?) drivers which assumed the data/BSS section has DMAable (which wouldn't be true for a high loaded kernel), but I'm not aware of any other reason why this wasn't implemented....someone care to comment?
Regards,
markhe
------------------------------------------------------------------ Mark Hemment, Unix/C Software Engineer (Contractor) markhe@nextd.demon.co.uk http://www.nextd.demon.co.uk/ "Success has many fathers, failure is a B**TARD!" - anon ------------------------------------------------------------------
| |