Subject: Re: mmap() of device
To: Chuck Cranor <chuck@dworkin.wustl.edu>
From: Jonathan Stone <jonathan@DSG.Stanford.EDU>
List: tech-kern
Date: 08/07/1997 16:53:58
Chuck Cranor <chuck@dworkin.wustl.edu> writes:

>Jonathan Stone writes:
>>The right answer really is to write a pager that can revoke the mmap()
>>bindings created by user processes, and re-create them on demand as
>>the user processes (or a network peer) faults on the pages.

>how do you propose a pager do this revoke operation?

For my application, doing a `pageout' would suffice.  

I didn't mean actually removing the VM bindings from processes that
had them, just removing the physical pages _and_ any DMA bindings
associated with them, so the DMAable pages could be reused by another
process.  (This predated bus-dma.)

I don't know about an NVRAM or FLASH-ram system.