netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: Linux Netdev List <netdev@vger.kernel.org>
Subject: [PATCH] veth: Fix veth_get_stats()
Date: Wed, 18 Nov 2009 18:09:39 +0100	[thread overview]
Message-ID: <4B042A53.9010301@gmail.com> (raw)

veth_get_stats() can be called in parallel on several cpus.

It's better to not reset dev->stats as it could give wrong result on
one cpu. Use temporary variables, then store the final results.

Also, we should loop on every possible cpus, not only online cpus,
or cpu hotplug can suddenly give wrong veth stats.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
 drivers/net/veth.c |   35 ++++++++++++++++-------------------
 1 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ade5b34..52af501 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -210,32 +210,29 @@ rx_drop:
 static struct net_device_stats *veth_get_stats(struct net_device *dev)
 {
 	struct veth_priv *priv;
-	struct net_device_stats *dev_stats;
 	int cpu;
-	struct veth_net_stats *stats;
+	struct veth_net_stats *stats, total = {0};
 
 	priv = netdev_priv(dev);
-	dev_stats = &dev->stats;
-
-	dev_stats->rx_packets = 0;
-	dev_stats->tx_packets = 0;
-	dev_stats->rx_bytes = 0;
-	dev_stats->tx_bytes = 0;
-	dev_stats->tx_dropped = 0;
-	dev_stats->rx_dropped = 0;
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		stats = per_cpu_ptr(priv->stats, cpu);
 
-		dev_stats->rx_packets += stats->rx_packets;
-		dev_stats->tx_packets += stats->tx_packets;
-		dev_stats->rx_bytes += stats->rx_bytes;
-		dev_stats->tx_bytes += stats->tx_bytes;
-		dev_stats->tx_dropped += stats->tx_dropped;
-		dev_stats->rx_dropped += stats->rx_dropped;
+		total.rx_packets += stats->rx_packets;
+		total.tx_packets += stats->tx_packets;
+		total.rx_bytes   += stats->rx_bytes;
+		total.tx_bytes   += stats->tx_bytes;
+		total.tx_dropped += stats->tx_dropped;
+		total.rx_dropped += stats->rx_dropped;
 	}
-
-	return dev_stats;
+	dev->stats.rx_packets = total.rx_packets;
+	dev->stats.tx_packets = total.tx_packets;
+	dev->stats.rx_bytes   = total.rx_bytes;
+	dev->stats.tx_bytes   = total.tx_bytes;
+	dev->stats.tx_dropped = total.tx_dropped;
+	dev->stats.rx_dropped = total.rx_dropped;
+
+	return &dev->stats;
 }
 
 static int veth_open(struct net_device *dev)

             reply	other threads:[~2009-11-18 17:09 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-18 17:09 Eric Dumazet [this message]
2009-11-19 20:27 ` [PATCH] veth: Fix veth_get_stats() 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=4B042A53.9010301@gmail.com \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --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).