From: Andi Kleen <andi@firstfloor.org>
To: "Zhu, Yijun (NSN - CN/Beijing)" <yijun.zhu@nsn.com>
Cc: <linux-kernel@vger.kernel.org>, <linux-arch@vger.kernel.org>
Subject: Re: Questions about SMP bootup control
Date: Mon, 22 Mar 2010 04:29:05 +0100 [thread overview]
Message-ID: <87tys9dofy.fsf@basil.nowhere.org> (raw)
In-Reply-To: <2234BBB33B4B2048B28E3B3ACFC9795C01B53251@CNBEEXC007.nsn-intra.net> (Yijun Zhu's message of "Mon, 22 Mar 2010 10:46:32 +0800")
"Zhu, Yijun (NSN - CN/Beijing)" <yijun.zhu@nsn.com> writes:
> Hi All:
>
> I want to do some modification on the SMP architecture.
>
> Purpose:
> Only the first CPU is running the linux OS, while others do some private
> services processing.
>
> My solution:
> In the end of the start_secondary() function, I try to schedu the slave
> cpu to call my private endless loop instead of cpu_idle();
>
> Result:
> The system can NOT up, there is no interactive cli.
>
> Question:
> Is there some wrong with my modification or I go to the wrong way?
Presumably you're doing this to own that CPU exclusively.
Hooking at cpu_idle is not very useful then because interrupts will be
already enabled and the system participate in IPIs etc, so you can't
simply disable them, the others will miss them.
You would rather need to prevent them from being started in the
first place, e.g. by exluding them with maxcpus=..
A better alternative might be to use isolcpus=... and schedule
a standard program.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2010-03-22 3:29 UTC|newest]
Thread overview: 77+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-03-21 7:13 [PATCH 00/20] x86: early_res and irq_desc Yinghai Lu
2010-03-21 7:13 ` [PATCH 01/20] x86: add find_e820_area_node Yinghai Lu
2010-03-21 7:13 ` [PATCH 02/20] x86: add get_centaur_ram_top Yinghai Lu
2010-03-21 7:13 ` [PATCH 03/20] x86: make e820 to be static Yinghai Lu
2010-03-21 7:13 ` [PATCH 04/20] x86: use wake_system_ram_range instead of e820_any_mapped in agp path Yinghai Lu
2010-03-21 7:13 ` [PATCH 05/20] x86: make e820 to be initdata Yinghai Lu
2010-03-21 7:13 ` [PATCH 06/20] early_res: seperate common memmap func from e820.c to fw_memmap.c Yinghai Lu
2010-03-22 2:37 ` Benjamin Herrenschmidt
2010-03-22 2:46 ` Questions about SMP bootup control Zhu, Yijun (NSN - CN/Beijing)
2010-03-22 3:29 ` Andi Kleen [this message]
2010-03-22 7:45 ` Zhu, Yijun (NSN - CN/Beijing)
2010-03-22 3:56 ` [PATCH 06/20] early_res: seperate common memmap func from e820.c to fw_memmap.c Yinghai Lu
2010-03-22 4:00 ` David Miller
2010-03-22 4:28 ` Yinghai Lu
2010-03-22 4:33 ` David Miller
2010-03-22 9:28 ` Ingo Molnar
2010-03-22 11:30 ` Paul Mackerras
2010-03-22 13:05 ` Ingo Molnar
2010-03-22 21:04 ` Benjamin Herrenschmidt
2010-03-22 21:20 ` Ingo Molnar
2010-03-22 21:52 ` Benjamin Herrenschmidt
2010-03-22 22:14 ` Yinghai Lu
2010-03-22 18:18 ` [PATCH 06/20] early_res: seperate common memmap func from e820.c to fw_memmap.cy Thomas Gleixner
2010-03-22 19:37 ` Ingo Molnar
2010-03-22 20:07 ` Yinghai Lu
2010-03-22 21:08 ` Benjamin Herrenschmidt
2010-03-22 22:09 ` Thomas Gleixner
2010-03-22 22:25 ` Yinghai Lu
2010-03-22 22:53 ` Thomas Gleixner
2010-03-22 23:41 ` Yinghai Lu
2010-03-23 0:45 ` Thomas Gleixner
2010-03-23 1:04 ` Yinghai Lu
2010-03-23 1:36 ` Thomas Gleixner
2010-03-23 6:01 ` Yinghai Lu
2010-03-23 8:02 ` Ingo Molnar
2010-03-23 9:02 ` Yinghai Lu
2010-03-23 9:48 ` Ingo Molnar
2010-03-24 4:29 ` Benjamin Herrenschmidt
2010-03-24 4:44 ` Benjamin Herrenschmidt
2010-03-24 5:54 ` Yinghai Lu
2010-03-24 7:43 ` Benjamin Herrenschmidt
2010-03-24 18:37 ` Yinghai Lu
2010-03-24 9:00 ` Ingo Molnar
2010-03-24 9:32 ` Benjamin Herrenschmidt
2010-03-24 4:24 ` Benjamin Herrenschmidt
2010-03-24 6:05 ` Yinghai Lu
2010-03-22 20:47 ` [PATCH 06/20] early_res: seperate common memmap func from e820.c to fw_memmap.c Benjamin Herrenschmidt
2010-03-22 20:57 ` Ingo Molnar
2010-03-22 21:54 ` Benjamin Herrenschmidt
2010-03-23 8:53 ` Geert Uytterhoeven
2010-03-23 11:16 ` Ingo Molnar
2010-03-24 4:50 ` Benjamin Herrenschmidt
2010-03-24 5:47 ` Kyle Moffett
2010-03-22 21:57 ` Paul Mackerras
2010-03-22 21:07 ` Benjamin Herrenschmidt
2010-03-22 21:01 ` Benjamin Herrenschmidt
2010-03-22 5:12 ` Benjamin Herrenschmidt
2010-03-22 6:09 ` Yinghai Lu
2010-03-22 7:05 ` Eric W. Biederman
2010-03-21 7:13 ` [PATCH 07/20] irq: move some interrupt arch_* functions into struct irq_chip Yinghai Lu
2010-03-21 7:13 ` [PATCH 08/20] x86: fix out of order of gsi - full Yinghai Lu
2010-03-21 7:13 ` [PATCH 09/20] x86: set nr_irqs_gsi only in probe_nr_irqs_gsi Yinghai Lu
2010-03-21 7:13 ` [PATCH 10/20] x86: kill smpboot_hooks.h Yinghai Lu
2010-03-21 7:13 ` [PATCH 11/20] x86: use vector_desc instead of vector_irq Yinghai Lu
2010-03-21 7:13 ` [PATCH 12/20] genericirq: change ack/mask in irq_chip to take irq_desc instead of irq -- x86 and core Yinghai Lu
2010-03-21 7:13 ` [PATCH 13/20] genericirq: change ack/mask in irq_chip to take irq_desc instead of irq -- other arch Yinghai Lu
2010-03-21 7:13 ` [PATCH 14/20] genericirq: add set_irq_desc_chip/data Yinghai Lu
2010-03-21 7:13 ` [PATCH 15/20] x86/iommu/dmar: update iommu/inter_remapping to use desc Yinghai Lu
2010-03-21 7:13 ` [PATCH 16/20] x86: use num_processors for possible cpus Yinghai Lu
2010-03-21 7:13 ` [PATCH 17/20] x86: make 32bit apic flat to physflat switch like 64bit Yinghai Lu
2010-03-21 7:13 ` [PATCH 18/20] x86: remove arch_probe_nr_irqs Yinghai Lu
2010-03-21 7:13 ` [PATCH 19/20] x86/pci: ioh new version read all at same time Yinghai Lu
2010-03-22 16:16 ` Jesse Barnes
2010-03-22 19:32 ` Yinghai Lu
2010-03-21 7:13 ` [PATCH 20/20] x86/pci: add mmconf range into e820 for when it is from MSR with amd faml0h Yinghai Lu
2010-03-22 2:35 ` [PATCH 00/20] x86: early_res and irq_desc Benjamin Herrenschmidt
2010-03-22 3:26 ` Yinghai Lu
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=87tys9dofy.fsf@basil.nowhere.org \
--to=andi@firstfloor.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=yijun.zhu@nsn.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