Re: Virtual address space exhaustion (was Discontigmem virt_to_page() )

[Pavel Machek <pavel@suse.cz>]

Hi!

> > > One of the Unix characteristics is that the kernel
> > > address space is shared with each of the process
> > > address space.
> > 
> > This hasn't been an absolute requirement. There have
> > been 32-bit Unix implementations that gave separate
> > 4G address spaces to the kernel and to each user
> > process.  The only real downside to this is that
> > copyin()/copyout() are more complex. Some processors
> > provided special instructions to access user-mode
> > addresses from kernel to mitigate this complexity.
> > 
> Really? The only 32-bit Unix's I've seen the details of
> are SCO Unix, Interactive Unix, Linux, and BSD Unix.
> The other Unix's I've become familiar are Sun-OS, the
> original AT&T(Unix System Labs)/SYS-V and DEC Ultrix.
> All these Unix's share user address-space with kernel
> address-space. This is supposed to be the very thing

Remember userspace being accessed through fs: in linux-2.0 days?

That counts as separate address space to me...
								Pavel
-- 
Philips Velo 1: 1"x4"x8", 300gram, 60, 12MB, 40bogomips, linux, mutt,
details at http://atrey.karlin.mff.cuni.cz/~pavel/velo/index.html.