From: Andi Kleen <ak@muc.de>
To: Zachary Amsden <zach@vmware.com>
Cc: Andrew Morton <akpm@osdl.org>, Chris Wright <chrisw@sous-sol.org>,
Virtualization Mailing List <virtualization@lists.osdl.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/5] Skip timer works.patch
Date: 27 Oct 2006 16:56:50 +0200
Date: Fri, 27 Oct 2006 16:56:50 +0200 [thread overview]
Message-ID: <20061027145650.GA37582@muc.de> (raw)
In-Reply-To: <200610200009.k9K09MrS027558@zach-dev.vmware.com>
On Thu, Oct 19, 2006 at 05:09:22PM -0700, Zachary Amsden wrote:
> Add a way to disable the timer IRQ routing check via a boot option. The
> VMI timer code uses this to avoid triggering the pester Mingo code, which
> probes for some very unusual and broken motherboard routings. It fires
> 100% of the time when using a paravirtual delay mechanism instead of
> using a realtime delay, since there is no elapsed real time, and the 4 timer
> IRQs have not yet been delivered.
You mean paravirtualized udelay will not actually wait?
This implies that you can't ever use any real timer in that kind of guest,
right?
>
> In addition, it is entirely possible, though improbable, that this bug
> could surface on real hardware which picks a particularly bad time to enter
> SMM mode, causing a long latency during one of the timer IRQs.
We already have a no timer check option. But:
>
> While here, make check_timer be __init.
So how is this supposed to work? The hypervisor would always pass that
option? If yes that would seem rather hackish to me. We should probably
instead probe in some way if we have the required timer hardware.
The paravirt kernel should know anyways it is paravirt and that it doesn't
need to probe for flakey hardware.
-Andi
next prev parent reply other threads:[~2006-10-27 14:56 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-10-20 0:09 [PATCH 1/5] Skip timer works.patch Zachary Amsden
2006-10-27 14:56 ` Andi Kleen [this message]
2006-10-27 19:09 ` Zachary Amsden
2006-10-27 21:16 ` Andi Kleen
2006-10-30 20:54 ` Zachary Amsden
2006-10-30 22:50 ` Andi Kleen
2006-10-30 23:09 ` Zachary Amsden
2006-10-30 23:12 ` Andi Kleen
2006-10-30 23:24 ` Zachary Amsden
2006-10-30 23:50 ` Andi Kleen
2006-11-15 8:03 ` Chris Wright
2006-11-15 8:21 ` Zachary Amsden
2006-11-15 22:40 ` Chris Wright
2006-11-15 22:54 ` Chris Wright
2006-11-16 3:27 ` Andi Kleen
2006-11-16 3:37 ` Chris Wright
2006-11-16 3:37 ` Andi Kleen
2006-11-16 5:06 ` Andrew Morton
2006-11-16 6:13 ` Zachary Amsden
2006-11-16 7:23 ` Andi Kleen
2006-11-16 7:02 ` Andi Kleen
2006-11-16 7:16 ` Chris Wright
2006-11-16 8:26 ` Chris Wright
2006-11-16 10:28 ` Chris Wright
2006-11-16 13:16 ` Andi Kleen
2006-11-16 19:03 ` Chris Wright
2006-11-16 19:46 ` Andi Kleen
2006-11-16 20:24 ` Chris Wright
2006-11-17 4:47 ` Andi Kleen
2006-11-17 7:33 ` Chris Wright
2006-11-17 7:38 ` Andi Kleen
2006-11-16 22:53 ` Andrew Morton
2006-11-16 23:08 ` Zachary Amsden
2006-11-16 23:10 ` Chris Wright
2006-11-17 5:05 ` Andi Kleen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20061027145650.GA37582@muc.de \
--to=ak@muc.de \
--cc=akpm@osdl.org \
--cc=chrisw@sous-sol.org \
--cc=linux-kernel@vger.kernel.org \
--cc=virtualization@lists.osdl.org \
--cc=zach@vmware.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).