mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Christoph Lameter <cl@gentwo.org>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>, David Howells <dhowells@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Oleg Nesterov <oleg@redhat.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH RFC] percpu: add data dependency barrier in percpu accessors and operations
Date: Fri, 20 Jun 2014 10:29:04 -0500 (CDT)	[thread overview]
Message-ID: <alpine.DEB.2.11.1406201024070.10810@gentwo.org> (raw)
In-Reply-To: <20140619205137.GK4904@linux.vnet.ibm.com>

On Thu, 19 Jun 2014, Paul E. McKenney wrote:

> Or just keep doing what I am doing.  What exactly is the problem with it?
> (Other than probably needing to clean up the cache alignment of some
> of the per-CPU structures?)

Writing to a cacheline of another processor can impact performance of that
other processor since the cacheline (which may contain other performance
critical data) is evicted from that processors cache.

The mechanisms for handling percpu data are not designed with the
consideration of writes into foreign percpu data areas in mind. Surprises
may result from such use.

In particular I see a danger in understanding what "atomic" percpu
operations are. These are not to be confused with regular atomic ops.
Percpu atomics are atomic for accesses that occur in a single specific
hardware thread. Percpu "atomics" are atomic vs. interrupts or preemption
occuring on that specific processor. No serialization is supported for
accesses may it be read or write from foreign processors.



  reply	other threads:[~2014-06-20 15:29 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-12 13:56 Tejun Heo
2014-06-12 15:34 ` Paul E. McKenney
2014-06-12 15:52   ` Tejun Heo
2014-06-17 14:41     ` Paul E. McKenney
2014-06-17 15:27       ` Tejun Heo
2014-06-17 15:56         ` Christoph Lameter
2014-06-17 16:00           ` Tejun Heo
2014-06-17 16:05             ` Tejun Heo
2014-06-17 16:28               ` Christoph Lameter
     [not found]                 ` <CA+55aFxHr8JXwDR-4g4z1mkXvZRtY=OosYcUMPZRD2upfooS1w@mail.gmail.com>
2014-06-17 18:47                   ` Christoph Lameter
2014-06-17 18:55                     ` Paul E. McKenney
2014-06-17 19:39                       ` Christoph Lameter
2014-06-17 19:47                         ` Tejun Heo
2014-06-17 19:56                         ` Paul E. McKenney
2014-06-19 20:39                           ` Christoph Lameter
2014-06-17 16:57         ` Paul E. McKenney
2014-06-17 18:56           ` Tejun Heo
2014-06-17 19:42             ` Christoph Lameter
2014-06-17 20:44               ` Tejun Heo
2014-07-09  0:55         ` Rusty Russell
2014-07-14 11:39           ` Paul E. McKenney
2014-07-14 15:22             ` Christoph Lameter
2014-07-15 10:11               ` Paul E. McKenney
2014-07-15 14:06                 ` Christoph Lameter
2014-07-15 14:32                   ` Paul E. McKenney
2014-07-15 15:06                     ` Christoph Lameter
2014-07-15 15:41                       ` Linus Torvalds
2014-07-15 16:12                         ` Christoph Lameter
     [not found]                           ` <CA+55aFxU166V5-vH4vmK9OBdTZKyede=71RjjbOVSN9Qh+Se+A@mail.gmail.com>
2014-07-15 17:45                             ` Paul E. McKenney
2014-07-15 17:41                       ` Paul E. McKenney
2014-07-16 14:40                         ` Christoph Lameter
2014-07-15 11:50             ` Rusty Russell
2014-06-17 19:27 ` Christoph Lameter
2014-06-17 19:40   ` Paul E. McKenney
2014-06-19 20:42     ` Christoph Lameter
2014-06-19 20:46       ` Tejun Heo
2014-06-19 21:11         ` Christoph Lameter
2014-06-19 21:15           ` Tejun Heo
2014-06-20 15:23             ` Christoph Lameter
2014-06-20 15:52               ` Tejun Heo
2014-06-19 20:51       ` Paul E. McKenney
2014-06-20 15:29         ` Christoph Lameter [this message]
2014-06-20 15:50           ` Paul E. McKenney

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=alpine.DEB.2.11.1406201024070.10810@gentwo.org \
    --to=cl@gentwo.org \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=oleg@redhat.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=tj@kernel.org \
    --cc=torvalds@linux-foundation.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

all inboxes | Powered by JetHome®