From: Andrew Morton <akpm@osdl.org>
To: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Pavel Machek <pavel@suse.cz>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Greg Kroah-Hartman <gregkh@suse.de>,
Christoph Hellwig <hch@infradead.org>,
ltt-dev@shafik.org, systemtap@sources.redhat.com,
Douglas Niehaus <niehaus@eecs.ku.edu>,
"Martin J. Bligh" <mbligh@mbligh.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH] local_t : Documentation
Date: Tue, 09 Jan 2007 22:12:00 -0000 [thread overview]
Message-ID: <20070109141112.1bfb6ef5.akpm@osdl.org> (raw)
In-Reply-To: <20070109220616.GA30535@Krystal>
On Tue, 9 Jan 2007 17:06:16 -0500
Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote:
> * Andrew Morton (akpm@osdl.org) wrote:
> > On Mon, 8 Jan 2007 22:14:46 -0500
> > Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote:
> >
> > > +* How to use local atomic operations
> > > +
> > > +#include <linux/percpu.h>
> > > +#include <asm/local.h>
> > > +
> > > +static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0);
> > > +
> > > +
> > > +* Counting
> > > +
> > > +In preemptible context, use get_cpu_var() and put_cpu_var() around local atomic
> > > +operations : it makes sure that preemption is disabled around write access to
> > > +the per cpu variable. For instance :
> > > +
> > > + local_inc(&get_cpu_var(counters));
> > > + put_cpu_var(counters);
> >
> > Confused. The whole point behind local_t is that we can do
> > atomic-wrt-interrupts inc and dec on them.
> >
> > Consequently, as atomic-wrt-interrupts means atomic-wrt-preemption, there
> > is no need to do a preempt_disable() around local_inc() and local_dec().
> >
>
> Hi Andrew,
>
> Not exactly : the increment operation is atomic, but not the selection of the
> local variable. local_inc(&__get_cpu_var()) implies the following sequence
> of operations :
>
> 1 - Get the variable copy corresponding to the currently running CPU.
> 2 - atomically increment the variable.
>
> It would be wrong to be scheduled on another CPU between 1 and 2, because the
> atomic increment should only be done by the CPU "owner" of the local variable,
> as the local atomic increment is not atomic wrt other CPUs.
>
doh. I knew that.
next prev parent reply other threads:[~2007-01-09 22:12 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-12-21 0:22 [PATCH 0/10] local_t : adding and standardising atomic primitives Mathieu Desnoyers
2006-12-21 0:22 ` [PATCH 1/10] local_t : architecture agnostic Mathieu Desnoyers
2006-12-21 0:24 ` [PATCH 2/10] local_t : alpha Mathieu Desnoyers
2006-12-21 0:25 ` [PATCH 3/10] local_t : i386 Mathieu Desnoyers
2006-12-21 19:47 ` [Ltt-dev] [PATCH 3/10] local_t : i386, local_add_return fix Mathieu Desnoyers
2006-12-21 0:26 ` [PATCH 4/10] local_t : ia64 Mathieu Desnoyers
2006-12-21 0:27 ` [PATCH 5/10] " Mathieu Desnoyers
2006-12-21 18:56 ` [Ltt-dev] [PATCH 5/10] local_t : MIPS Mathieu Desnoyers
2006-12-21 0:27 ` [PATCH 6/10] local_t : parisc Mathieu Desnoyers
2006-12-21 0:28 ` [PATCH 7/10] local_t : powerpc Mathieu Desnoyers
2006-12-21 14:04 ` [Ltt-dev] " Mathieu Desnoyers
2007-01-24 10:00 ` Paul Mackerras
2007-01-24 10:43 ` Gabriel Paubert
2007-01-24 17:05 ` Mathieu Desnoyers
2006-12-21 0:29 ` [PATCH 8/10] local_t : s390 Mathieu Desnoyers
2006-12-21 0:41 ` [PATCH 9/10] local_t : sparc64 Mathieu Desnoyers
2006-12-21 3:01 ` [PATCH 10/10] local_t : x86_64 Mathieu Desnoyers
2006-12-21 19:55 ` [Ltt-dev] [PATCH 10/10] local_t : x86_64 : local_add_return Mathieu Desnoyers
2006-12-26 19:48 ` [PATCH 0/10] local_t : adding and standardising atomic primitives Pavel Machek
2007-01-09 3:20 ` [PATCH] local_t : Documentation Mathieu Desnoyers
2007-01-09 21:02 ` Andrew Morton
2007-01-09 22:11 ` Mathieu Desnoyers
2007-01-09 22:12 ` Andrew Morton [this message]
2007-01-09 22:38 ` Pavel Machek
2007-01-09 22:41 ` Pavel Machek
2007-01-09 23:27 ` [PATCH] local_t : Documentation - update Mathieu Desnoyers
2007-01-09 23:45 ` Pavel Machek
2007-01-10 0:39 ` Mathieu Desnoyers
2007-01-10 1:06 ` [Ltt-dev] " Mathieu Desnoyers
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=20070109141112.1bfb6ef5.akpm@osdl.org \
--to=akpm@osdl.org \
--cc=gregkh@suse.de \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=ltt-dev@shafik.org \
--cc=mathieu.desnoyers@polymtl.ca \
--cc=mbligh@mbligh.org \
--cc=mingo@redhat.com \
--cc=niehaus@eecs.ku.edu \
--cc=pavel@suse.cz \
--cc=systemtap@sources.redhat.com \
--cc=tglx@linutronix.de \
/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 read-only IMAP folder(s) and NNTP newsgroup(s).