netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Eric Dumazet <eric.dumazet@gmail.com>,
	"David S. Miller" <davem@davemloft.net>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>,
	netdev@vger.kernel.org, Florian Westphal <fw@strlen.de>,
	Daniel Borkmann <dborkman@redhat.com>,
	Hannes Frederic Sowa <hannes@stressinduktion.org>
Subject: [net-next PATCH 1/3] net: frag, avoid several CPUs grabbing same frag queue during LRU evictor loop
Date: Wed, 27 Mar 2013 16:55:25 +0100	[thread overview]
Message-ID: <20130327155457.15203.69656.stgit@dragon> (raw)
In-Reply-To: <20130327155238.15203.6688.stgit@dragon>

The LRU list is protected by its own lock, since commit 3ef0eb0db4
(net: frag, move LRU list maintenance outside of rwlock), and
no-longer by a read_lock.

This makes it possible, to remove the inet_frag_queue, which is about
to be "evicted", from the LRU list head.  This avoids the problem, of
several CPUs grabbing the same frag queue.

Note, cannot remove the inet_frag_lru_del() call in fq_unlink()
called by inet_frag_kill(), because inet_frag_kill() is also used in
other situations.  Thus, we use list_del_init() to allow this
double list_del to work.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---

 net/ipv4/inet_fragment.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 2bff045..8ba548a 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -204,6 +204,9 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
 		q = list_first_entry(&nf->lru_list,
 				struct inet_frag_queue, lru_list);
 		atomic_inc(&q->refcnt);
+		/* Remove q from list to avoid several CPUs grabbing it */
+		list_del_init(&q->lru_list);
+
 		spin_unlock(&nf->lru_lock);
 
 		spin_lock(&q->lock);

  reply	other threads:[~2013-03-27 15:55 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-27 15:54 [net-next PATCH 0/3] net: frag performance followup Jesper Dangaard Brouer
2013-03-27 15:55 ` Jesper Dangaard Brouer [this message]
2013-03-27 16:14   ` [net-next PATCH 1/3] net: frag, avoid several CPUs grabbing same frag queue during LRU evictor loop Eric Dumazet
2013-03-27 17:10     ` David Miller
2013-03-27 15:55 ` [net-next PATCH 2/3] net: use the frag lru_lock to protect netns_frags.nqueues update Jesper Dangaard Brouer
2013-03-27 16:21   ` Eric Dumazet
2013-03-27 17:10     ` David Miller
2013-03-27 15:56 ` [net-next PATCH 3/3] net: frag queue per hash bucket locking Jesper Dangaard Brouer
2013-03-27 17:25   ` Eric Dumazet
2013-03-28 18:57     ` Hannes Frederic Sowa
2013-03-28 19:03       ` David Miller
2013-03-28 19:10         ` Hannes Frederic Sowa
2013-03-28 19:19           ` David Miller
2013-03-28 20:22       ` Eric Dumazet
2013-03-28 23:30         ` Hannes Frederic Sowa
2013-03-28 23:39           ` Eric Dumazet
2013-03-29  0:33             ` Hannes Frederic Sowa
2013-03-29 19:01               ` Jesper Dangaard Brouer
2013-03-29 19:05                 ` Eric Dumazet
2013-03-29 19:22                 ` David Miller
2013-04-02 15:23                 ` Jesper Dangaard Brouer
2013-04-03 22:11                 ` Jesper Dangaard Brouer
2013-04-04  7:52                   ` [net-next PATCH V2] " Jesper Dangaard Brouer
2013-04-04  9:03                     ` Hannes Frederic Sowa
2013-04-04  9:27                       ` Jesper Dangaard Brouer
2013-04-04  9:38                         ` [net-next PATCH V3] " Jesper Dangaard Brouer
2013-04-04  9:58                           ` Hannes Frederic Sowa
2013-04-04 16:24                           ` Eric Dumazet
2013-04-04 21:38                             ` 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=20130327155457.15203.69656.stgit@dragon \
    --to=brouer@redhat.com \
    --cc=davem@davemloft.net \
    --cc=dborkman@redhat.com \
    --cc=eric.dumazet@gmail.com \
    --cc=fw@strlen.de \
    --cc=hannes@stressinduktion.org \
    --cc=netdev@vger.kernel.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).