linux-wireless.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <hawk@comx.dk>
To: "David S. Miller" <davem@davemloft.net>
Cc: Jesper Dangaard Brouer <hawk@comx.dk>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	dougthompson@xmission.com, bluesmoke-devel@lists.sourceforge.net,
	axboe@kernel.dk, "Patrick McHardy" <kaber@trash.net>,
	christine.caulfield@googlemail.com, Trond.Myklebust@netapp.com,
	linux-wireless@vger.kernel.org, johannes@sipsolutions.net,
	yoshfuji@linux-ipv6.org, shemminger@linux-foundation.org,
	linux-nfs@vger.kernel.org, bfields@fieldses.org, neilb@suse.de,
	linux-ext4@vger.kernel.org, tytso@mit.edu, adilger@sun.com,
	netfilter-devel@vger.kernel.org
Subject: [PATCH 09/10] cfq-iosched: Uses its own open-coded rcu_barrier.
Date: Tue, 23 Jun 2009 17:04:39 +0200	[thread overview]
Message-ID: <20090623150439.22490.14657.stgit@localhost> (raw)
In-Reply-To: <20090623150330.22490.87327.stgit@localhost>

This module cfq-iosched, has discovered the value of waiting for
call_rcu() completion, but its has its own open-coded implementation
of rcu_barrier(), which I don't think is 'strong' enough.

This patch only leaves a comment for the maintainers to consider.

Signed-off-by: Jesper Dangaard Brouer <hawk@comx.dk>
---

 block/cfq-iosched.c |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 833ec18..c15555b 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2657,6 +2657,12 @@ static void __exit cfq_exit(void)
 	/*
 	 * this also protects us from entering cfq_slab_kill() with
 	 * pending RCU callbacks
+	 *
+	 * hawk@comx.dk 2009-06-18: Maintainer please consider using
+	 *  rcu_barrier() instead of this open-coded wait for
+	 *  completion implementation.  I think it provides a better
+	 *  guarantee that all CPUs are finished, although
+	 *  elv_ioc_count_read() do consider all CPUs.
 	 */
 	if (elv_ioc_count_read(ioc_count))
 		wait_for_completion(&all_gone);


  parent reply	other threads:[~2009-06-23 15:29 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-06-23 15:03 [PATCH 00/10] We must use rcu_barrier() on module unload Jesper Dangaard Brouer
2009-06-23 15:03 ` [PATCH 01/10] ext4: Use " Jesper Dangaard Brouer
2009-07-06  2:31   ` Theodore Tso
2009-06-23 15:04 ` [PATCH 02/10] bridge: Use rcu_barrier() instead of syncronize_net() on unload Jesper Dangaard Brouer
2009-06-23 15:04 ` [PATCH 03/10] mac80211: Use rcu_barrier() " Jesper Dangaard Brouer
2009-06-23 15:15   ` Johannes Berg
2009-06-24 10:06     ` Jesper Dangaard Brouer
2009-06-24 10:21       ` Johannes Berg
2009-06-24 11:32         ` Jesper Dangaard Brouer
2009-06-24 11:39           ` Johannes Berg
2009-06-23 15:04 ` [PATCH 04/10] sunrpc: " Jesper Dangaard Brouer
2009-06-23 16:59   ` Trond Myklebust
2009-06-23 15:04 ` [PATCH 05/10] nfs: Use rcu_barrier() on module unload Jesper Dangaard Brouer
2009-06-23 15:04 ` [PATCH 06/10] ipv6: " Jesper Dangaard Brouer
2009-06-23 15:04 ` [PATCH 07/10] decnet: " Jesper Dangaard Brouer
2009-06-24  6:23   ` Chrissie Caulfield
2009-06-24 11:44     ` Jesper Dangaard Brouer
2009-06-24 12:09       ` Jesper Dangaard Brouer
2009-06-23 15:04 ` [PATCH 08/10] edac_core: Uses call_rcu() and its own wait_for_completion scheme Jesper Dangaard Brouer
2009-06-23 15:04 ` Jesper Dangaard Brouer [this message]
2009-06-24  6:42   ` [PATCH 09/10] cfq-iosched: Uses its own open-coded rcu_barrier Jens Axboe
2009-06-24 14:05     ` Paul E. McKenney
2009-06-23 15:04 ` [PATCH 10/10] nf_conntrack: Use rcu_barrier() Jesper Dangaard Brouer
2009-06-23 16:23   ` Patrick McHardy
2009-06-24  9:02     ` Jesper Dangaard Brouer
2009-06-24  9:40       ` [PATCH v2 10/10] nf_conntrack: Use rcu_barrier() and fix kmem_cache_create flags Jesper Dangaard Brouer
2009-06-24 13:58         ` Patrick McHardy
2009-06-25  9:29           ` Jesper Dangaard Brouer
2009-06-25 10:02             ` [PATCH v3 10/10] nf_conntrack: Use rcu_barrier() Jesper Dangaard Brouer
2009-06-25 14:33               ` Patrick McHardy
2009-06-25 13:59             ` [PATCH v2 10/10] nf_conntrack: Use rcu_barrier() and fix kmem_cache_create flags Patrick McHardy
2009-06-25 19:32             ` Paul E. McKenney
2009-06-24  1:44 ` [PATCH 00/10] We must use rcu_barrier() on module unload Paul E. McKenney
2009-06-24  7:02 ` David Miller

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=20090623150439.22490.14657.stgit@localhost \
    --to=hawk@comx.dk \
    --cc=Trond.Myklebust@netapp.com \
    --cc=adilger@sun.com \
    --cc=axboe@kernel.dk \
    --cc=bfields@fieldses.org \
    --cc=bluesmoke-devel@lists.sourceforge.net \
    --cc=christine.caulfield@googlemail.com \
    --cc=davem@davemloft.net \
    --cc=dougthompson@xmission.com \
    --cc=johannes@sipsolutions.net \
    --cc=kaber@trash.net \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-wireless@vger.kernel.org \
    --cc=neilb@suse.de \
    --cc=netdev@vger.kernel.org \
    --cc=netfilter-devel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=shemminger@linux-foundation.org \
    --cc=tytso@mit.edu \
    --cc=yoshfuji@linux-ipv6.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).