[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Pine.LNX.4.55.0808181506230.29123@cliff.in.clinika.pl>
Date: Mon, 18 Aug 2008 15:19:05 +0100 (BST)
From: "Maciej W. Rozycki" <macro@...ux-mips.org>
To: Cyrill Gorcunov <gorcunov@...il.com>
cc: Arjan van de Ven <arjan@...radead.org>, mingo@...e.hu,
hpa@...or.com, tglx@...utronix.de, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 2/6] x86: apic - unify lapic_resume
On Sun, 17 Aug 2008, Cyrill Gorcunov wrote:
> it seems this limit is not APIC related since iirc 82489DX allows
> to address 2^14 bits, x2APIC - more then 128 entities too. So I suspect
> it somehow cpu bitmap related. Am I wrong (I didn't _check_ the code)?
For the record: the 82489DX supports an 8-bit physical unit ID so 256
distinct values are supported. Of these I gather 255 is taken for the
broadcast ID in the physical destination mode, but that is nowhere
explicitly confirmed in the 82489DX docs (it can be implied from protocol
description though). While the ID is indeed 8-bit in the 82489DX, for
systems where future compatibility was a concern Intel recommended the use
of IDs from 0 through to 14 only in anticipation of the future integrated
APIC with the physical mode addressing capability limited to 4 bits only
(and 15 taken for the broadcast ID).
Full 32 bits are available with the 82489DX for the logical destination
mode and only the flat (no cluster) mode is supported.
Maciej
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists