lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <4B042A53.9010301@gmail.com>
Date:	Wed, 18 Nov 2009 18:09:39 +0100
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	"David S. Miller" <davem@...emloft.net>
CC:	Linux Netdev List <netdev@...r.kernel.org>
Subject: [PATCH] veth: Fix veth_get_stats()

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@...il.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)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ