[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]
Re: new mremap(2): relax alignment restrictions?
> On Wed, Jul 25, 2007 at 04:51:46PM -0400, der Mouse wrote:
Digging out old mail, are we? :)
>> (I'd actually *prefer* getting SEGV/BUS/etc for accesses to space
>> after EOF [in an mmapped file], but that would be quite run-time
>> expensive to do, and likely somewhat difficult besides.)
> To make that efficient, we'd need flexible *segmentation* on top of
> paging in the hardware - that is, a MMU length field per page with
> byte granularity.
Right. "Quite run-time expensive" because hardware without that -
which AIUI is most of the machines we run on - would have to protect
the page and simulate all accesses in the kernel.
Actually, on reflection, "quite expensive" doesn't half cover it.
"Execrably slow" might be more like it.
/~\ The ASCII der Mouse
\ / Ribbon Campaign
X Against HTML mouse%rodents-montreal.org@localhost
/ \ Email! 7D C8 61 52 5D E7 2D 39 4E F1 31 3E E8 B3 27 4B
Main Index |
Thread Index |