[Devel] [PATCH v2 rh7] vznetstat: fix statistics output when getting stats for same device in parallel

[Konstantin Khorenko]

Before this patch .get_stats() for venetdev was not defended from
racing, Documentation/networking/netdevices.txt states ndo_get_stats()
is to be syncronized by dev_base_lock rwlock, but we do READ stats, so
can go in parallel.

At the same time the algorithm of gathering per-cpu stats into a single
value used per-device structure, so in case .get_stats() is called in
parallel, stats could be corrupted.

Example, 2 cpu node:

	cpu A					cpu B
.get_stats()
memset(dev->...->stats, 0)
stats.rx_bytes += cpuA.rx_bytes
					.get_stats()
					memset(dev->...->stats, 0)
stats.rx_bytes += cpuB.rx_bytes
return stats
					stats.rx_bytes += cpuA.rx_bytes
					stats.rx_bytes += cpuB.rx_bytes
					return stats

=> process running on cpu A will print rx_bytes only taken from cpu B
(so lower than expected), and the process running on cpu B will print
too high numbers because cpu B values will be added twice.

Let's make venetdev provide ndo_get_stats64() callback which gets a
storage as an argument, thus does not suffer from a race of filling
a per-netdevice struct in parallel.

https://jira.vzint.dev/browse/PSBM-150027

Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
---
v2:
  * get rid of extra function venet_stats_one()
  * get rid of extra struct venet_device_stats and filling it

 drivers/net/venetdev.c | 20 ++++++++------------
 include/linux/venet.h  |  1 -
 2 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/net/venetdev.c b/drivers/net/venetdev.c
index 3ca4f8a49a5c..9785b9ba7247 100644
--- a/drivers/net/venetdev.c
+++ b/drivers/net/venetdev.c
@@ -568,25 +568,21 @@ static int venet_xmit(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static struct net_device_stats *get_stats(struct net_device *dev)
+static void venet_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *total)
 {
 	int i;
-	struct venet_stats *stats;
 
-	stats = (struct venet_stats *)dev->ml_priv;
-	memset(&stats->stats, 0, sizeof(struct net_device_stats));
 	for_each_possible_cpu(i) {
 		struct net_device_stats *dev_stats;
 
 		dev_stats = venet_stats(dev, i);
-		stats->stats.rx_bytes   += dev_stats->rx_bytes;
-		stats->stats.tx_bytes   += dev_stats->tx_bytes;
-		stats->stats.rx_packets += dev_stats->rx_packets;
-		stats->stats.tx_packets += dev_stats->tx_packets;
-		stats->stats.tx_dropped += dev_stats->tx_dropped;
+		total->rx_bytes += dev_stats->rx_bytes;
+		total->tx_bytes += dev_stats->tx_bytes;
+		total->rx_packets += dev_stats->rx_packets;
+		total->tx_packets += dev_stats->tx_packets;
+		total->tx_dropped += dev_stats->tx_dropped;
 	}
-
-	return &stats->stats;
 }
 
 /* Initialize the rest of the LOOPBACK device. */
@@ -712,7 +708,7 @@ static const struct ethtool_ops venet_ethtool_ops = {
 
 static const struct net_device_ops venet_netdev_ops = {
 	.ndo_start_xmit = venet_xmit,
-	.ndo_get_stats = get_stats,
+	.ndo_get_stats64 = venet_get_stats64,
 	.ndo_open = venet_open,
 	.ndo_stop = venet_close,
 	.ndo_init = venet_init_dev,
diff --git a/include/linux/venet.h b/include/linux/venet.h
index 51e0abeb03d7..f0a00832f6de 100644
--- a/include/linux/venet.h
+++ b/include/linux/venet.h
@@ -21,7 +21,6 @@
 struct ve_struct;
 struct venet_stat;
 struct venet_stats {
-	struct net_device_stats	stats;
 	struct net_device_stats	*real_stats;
 };
 
-- 
2.24.3