From: Segher Boessenkool <segher@kernel.crashing.org>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org,
Johannes Berg <johannes@sipsolutions.net>,
Paul Mackerras <paulus@samba.org>
Subject: Re: [PATCH] powermac: support G5 CPU hotplug
Date: Thu, 3 May 2007 03:01:16 +0200 [thread overview]
Message-ID: <15a6025d58d0f62ee10efab20dc98278@kernel.crashing.org> (raw)
In-Reply-To: <1178151690.17299.46.camel@localhost.localdomain>
>> The difference between doze and nap is that in nap mode
>> the bus interface unit is switched off; on the 970 and
>> 970FX this means that the L2 cache has to be flushed
>> before entering nap mode (or otherwise snoops will go
>> missing in action);
>
> BZZZT... incorrect... the 970FX and MP behave the same here.
Yeah I goofed here -- cache flush is only required if
you take a CPU offline.
> There is
> only one state you can "manually" enter and it's NAP.
BZZZT... incorrect... you can "manually" switch to
all of doze, nap, and deep nap.
> Transitions
> between DOZE and NAP are automatic to handle snooping in both cases.
> Cache flushing is never needed ... unless in our case the CPU gets
> actually powered down for suspend-to-ram.
Yeah. Or to hot-unplug it ;-)
>> the 970MP automatically transitions
>> from nap to doze mode if snoops are requested (and back
>> to nap again), so no L2 flush is required. The 970MP
>> also has a "deep nap" mode which saves more power by
>> automatically clocking the CPU down.
>
> Also deep nap only really works on 970MP DD3 and later I think
Yes, we put that knowledge into the kernel already.
>> One more thing -- perhaps keeping the CPU in reset
>> state saves even more power?
>
> Dunno... Somebody can try... but I don't think we have access to the
> reset line on 970's..
Isn't it just a GPIO, like on older Macs? Of course, we
cannot bring a CPU back online after doing that so it's
pretty useless I suppose.
Segher
next prev parent reply other threads:[~2007-05-03 1:01 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-27 11:25 patches for 2.6.22 Paul Mackerras
2007-04-27 12:00 ` Johannes Berg
2007-04-27 21:41 ` [PATCH] powerpc: fix suspend states again Johannes Berg
2007-04-27 21:53 ` Olof Johansson
2007-04-27 21:54 ` Johannes Berg
2007-04-27 21:57 ` Olof Johansson
2007-04-27 22:00 ` [PATCH] powerpc: put enable_kernel_spe into a header Johannes Berg
2007-04-27 22:02 ` [PATCH v2] powerpc: fix suspend states again Johannes Berg
2007-04-27 23:13 ` Olof Johansson
2007-04-30 0:14 ` Paul Mackerras
2007-04-30 11:35 ` Johannes Berg
2007-04-30 11:37 ` [PATCH v3] " Johannes Berg
2007-05-01 14:16 ` Johannes Berg
2007-04-27 23:42 ` patches for 2.6.22 Arnd Bergmann
2007-04-28 2:49 ` [PATCH] cell: cbe_cpufreq cleanup and crash fix Arnd Bergmann
2007-04-28 7:49 ` [PATCH] powermac: proper sleep management Johannes Berg
2007-04-28 8:08 ` Paul Mackerras
2007-04-28 12:52 ` Johannes Berg
2007-04-28 8:38 ` Benjamin Herrenschmidt
2007-04-28 12:51 ` Johannes Berg
2007-04-28 12:01 ` Paul Mackerras
2007-04-28 13:46 ` Johannes Berg
2007-04-30 5:31 ` Paul Mackerras
2007-04-30 12:08 ` Johannes Berg
2007-05-01 12:14 ` Paul Mackerras
2007-05-01 12:24 ` Johannes Berg
2007-04-30 11:44 ` [PATCH v3] " Johannes Berg
2007-05-01 8:55 ` Johannes Berg
2007-04-30 19:51 ` patches for 2.6.22 Kim Phillips
2007-05-01 3:38 ` Paul Mackerras
2007-05-02 14:12 ` Kumar Gala
2007-05-02 14:19 ` Kim Phillips
2007-05-01 9:06 ` Johannes Berg
2007-05-02 5:33 ` [PATCH] adb: replace sleep notifier with platform driver suspend/resume hooks Johannes Berg
2007-05-02 5:34 ` [PATCH] apm_emu: use generic apm-emulation Johannes Berg
2007-05-02 5:36 ` [PATCH] via-pmu: remove LED sleep notifier Johannes Berg
2007-05-02 10:57 ` Stephen Rothwell
2007-05-02 14:32 ` [PATCH v2] " Johannes Berg
2007-05-07 8:47 ` Paul Mackerras
2007-05-07 8:58 ` Johannes Berg
2007-05-07 15:08 ` [PATCH v3] " Johannes Berg
2007-05-02 5:39 ` [PATCH] remove awacs dmasound Johannes Berg
2007-05-02 6:18 ` [PATCH] via-pmu: kill sleep notifiers completely Johannes Berg
2007-05-02 6:21 ` [PATCH] powermac: support G5 CPU hotplug Johannes Berg
2007-05-02 10:55 ` Paul Mackerras
2007-05-02 14:33 ` Johannes Berg
2007-05-02 17:57 ` Segher Boessenkool
2007-05-02 22:03 ` Benjamin Herrenschmidt
2007-05-02 23:47 ` Segher Boessenkool
2007-05-02 23:59 ` Benjamin Herrenschmidt
2007-05-03 0:05 ` Segher Boessenkool
2007-05-03 0:18 ` Benjamin Herrenschmidt
2007-05-03 0:01 ` Paul Mackerras
2007-05-03 0:08 ` Benjamin Herrenschmidt
2007-05-03 0:10 ` Benjamin Herrenschmidt
2007-05-03 0:19 ` Segher Boessenkool
2007-05-03 0:17 ` Segher Boessenkool
2007-05-03 0:21 ` Benjamin Herrenschmidt
2007-05-03 0:24 ` Benjamin Herrenschmidt
2007-05-03 1:01 ` Segher Boessenkool [this message]
2007-05-03 2:11 ` Benjamin Herrenschmidt
2007-05-03 16:49 ` Segher Boessenkool
2007-05-02 20:33 ` [PATCH v2] " Johannes Berg
2007-05-02 6:33 ` [PATCH] powerpc: MPIC sys_device & suspend/resume Johannes Berg
2007-05-02 6:35 ` [PATCH] powermac: fix G5-cpufreq for cpu on/offline Johannes Berg
2007-05-03 12:25 ` patches for 2.6.22 Johannes Berg
2007-05-03 12:28 ` [PATCH] powerpc: dart iommu suspend Johannes Berg
2007-05-03 12:30 ` Benjamin Herrenschmidt
2007-05-03 12:34 ` Johannes Berg
2007-05-03 12:34 ` Benjamin Herrenschmidt
2007-05-03 12:48 ` Johannes Berg
2007-05-03 14:24 ` Olof Johansson
2007-05-04 10:51 ` Johannes Berg
2007-05-03 12:29 ` [PATCH] powerpc: mark pages that don't exist as nosave Johannes Berg
2007-05-03 12:31 ` [PATCH] powermac: suspend to disk on G5 Johannes Berg
2007-07-17 13:28 ` [PATCH] remove awacs dmasound Johannes Berg
2007-07-17 13:37 ` Adrian Bunk
2007-07-17 13:43 ` Johannes Berg
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=15a6025d58d0f62ee10efab20dc98278@kernel.crashing.org \
--to=segher@kernel.crashing.org \
--cc=benh@kernel.crashing.org \
--cc=johannes@sipsolutions.net \
--cc=linuxppc-dev@ozlabs.org \
--cc=paulus@samba.org \
/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).