From: Michael Neuling <mikey@neuling.org>
To: Darren Hart <dvhltc@us.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>,
Gautham R Shenoy <ego@in.ibm.com>,
Josh Triplett <josh@joshtriplett.org>,
Steven Rostedt <rostedt@goodmis.org>,
linuxppc-dev@ozlabs.org, Will Schmidt <willschm@us.ibm.com>,
Paul Mackerras <paulus@samba.org>,
Ankita Garg <ankita@in.ibm.com>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH][RFC] preempt_count corruption across H_CEDE call with CONFIG_PREEMPT on pseries
Date: Thu, 02 Sep 2010 13:46:29 +1000 [thread overview]
Message-ID: <20565.1283399189@neuling.org> (raw)
In-Reply-To: <4C7E9FC1.60004@us.ibm.com>
> + /* Check to see if the CPU out of FW already for kexec */
Wow, that comment is shit. The checkin comment in
aef40e87d866355ffd279ab21021de733242d0d5 is much better.
> This comment is really confusing to me. I _think_ it is saying that this test
> determines if the CPU is done executing firmware code and has begun executing
> OS code.... Is that right?
Yeah.
It means for a normal boot, the CPU will not have started yet (still in
firmware (FW)) so we have to call FW to bring it out. In the kexec case
though, the CPU will have started already (it's spinning in the kernel)
so we don't have to call FW to bring it back out again. To distinguish
between these two cases, we ask FW if the CPU has started or not (via
smp_query_cpu_stopped()) and if it's already start, don't restart it.
Originally, we could call FW to start a cpu that was already started,
but FW changed recently and stopped allowing us to do this. Hence this
patch.
Mikey
prev parent reply other threads:[~2010-09-02 3:46 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-22 18:24 [PATCH][RFC] preempt_count corruption across H_CEDE call with CONFIG_PREEMPT on pseries Darren Hart
2010-07-22 18:36 ` Darren Hart
2010-07-22 18:38 ` Thomas Gleixner
2010-08-10 22:36 ` Darren Hart
2010-07-22 22:25 ` Benjamin Herrenschmidt
2010-07-22 23:57 ` Darren Hart
2010-07-23 4:44 ` Darren Hart
2010-07-23 5:08 ` Vaidyanathan Srinivasan
2010-07-23 5:11 ` Benjamin Herrenschmidt
2010-07-23 7:07 ` Vaidyanathan Srinivasan
2010-08-05 4:45 ` Darren Hart
2010-08-05 11:06 ` Vaidyanathan Srinivasan
2010-08-05 12:26 ` Thomas Gleixner
2010-07-23 5:09 ` Benjamin Herrenschmidt
2010-08-06 2:19 ` Darren Hart
2010-08-06 5:09 ` Vaidyanathan Srinivasan
2010-08-06 7:13 ` Darren Hart
2010-07-23 14:39 ` Will Schmidt
2010-08-04 13:44 ` Darren Hart
2010-08-19 15:58 ` Ankita Garg
2010-08-19 18:58 ` Will Schmidt
2010-08-23 22:20 ` Darren Hart
2010-08-31 7:12 ` Darren Hart
2010-09-01 5:54 ` Michael Ellerman
2010-09-01 15:10 ` Darren Hart
2010-09-01 18:47 ` Darren Hart
2010-09-01 19:59 ` Steven Rostedt
2010-09-01 20:42 ` Darren Hart
2010-09-02 1:02 ` Michael Neuling
2010-09-02 4:06 ` Steven Rostedt
2010-09-02 6:04 ` Darren Hart
2010-09-03 20:10 ` Will Schmidt
2010-09-02 23:04 ` Michael Neuling
2010-09-03 0:08 ` Darren Hart
2010-09-02 3:46 ` Michael Neuling [this message]
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=20565.1283399189@neuling.org \
--to=mikey@neuling.org \
--cc=ankita@in.ibm.com \
--cc=dvhltc@us.ibm.com \
--cc=ego@in.ibm.com \
--cc=josh@joshtriplett.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=paulus@samba.org \
--cc=rostedt@goodmis.org \
--cc=sfr@canb.auug.org.au \
--cc=tglx@linutronix.de \
--cc=willschm@us.ibm.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).