xfs
[Top] [All Lists]

Re: XFS unhappy with large holey loopback and syncs -- [OT] vmalloc 45-b

To: Andi Kleen <ak@xxxxxxx>
Subject: Re: XFS unhappy with large holey loopback and syncs -- [OT] vmalloc 45-bit/32PiB address limit
From: "Bryan J. Smith" <b.j.smith@xxxxxxxx>
Date: Tue, 29 Nov 2005 07:46:46 -0800 (PST)
Cc: Steve Lord <lord@xxxxxxx>, David Chinner <dgc@xxxxxxx>, linux-xfs@xxxxxxxxxxx
In-reply-to: <20051129154139.GI19515@wotan.suse.de>
Reply-to: b.j.smith@xxxxxxxx
Sender: linux-xfs-bounce@xxxxxxxxxxx
Andi Kleen <ak@xxxxxxx> wrote:
> x86-64 supports 48bits of address space. Half of it is for 
> user space, the other half for the kernel.  Of the kernel
> half half is for physical memory, and half of the other
> half is for kernel text and holes. This leaves 45bits for
> vmalloc.

Ahhh, that makes sense.

I knew x86-64 "Long Mode" is 48-bit (linear segment+offset
register/i486 TLB compatible, hence how it can run 32-bit
applications), but never stopped to think about the mapping
of kernel and user-space memory.

Thanx for explaining it!


-- 
Bryan J. Smith                | Sent from Yahoo Mail
mailto:b.j.smith@xxxxxxxx     |  (please excuse any
http://thebs413.blogspot.com/ |   missing headers)


<Prev in Thread] Current Thread [Next in Thread>