bridge: per-cpu packet statistics (v3)
The shared packet statistics are a potential source of slow down
on bridged traffic. Convert to per-cpu array, but only keep those
statistics which change per-packet.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 90a9024e..5b8a6e7 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -26,12 +26,13 @@
const unsigned char *dest = skb->data;
struct net_bridge_fdb_entry *dst;
struct net_bridge_mdb_entry *mdst;
+ struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+
+ brstats->tx_packets++;
+ brstats->tx_bytes += skb->len;
BR_INPUT_SKB_CB(skb)->brdev = dev;
- dev->stats.tx_packets++;
- dev->stats.tx_bytes += skb->len;
-
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
@@ -81,6 +82,31 @@
return 0;
}
+static struct net_device_stats *br_get_stats(struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+ struct net_device_stats *stats = &dev->stats;
+ struct br_cpu_netstats sum = { 0 };
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ const struct br_cpu_netstats *bstats
+ = per_cpu_ptr(br->stats, cpu);
+
+ sum.tx_bytes += bstats->tx_bytes;
+ sum.tx_packets += bstats->tx_packets;
+ sum.rx_bytes += bstats->rx_bytes;
+ sum.rx_packets += bstats->rx_packets;
+ }
+
+ stats->tx_bytes = sum.tx_bytes;
+ stats->tx_packets = sum.tx_packets;
+ stats->rx_bytes = sum.rx_bytes;
+ stats->rx_packets = sum.rx_packets;
+
+ return stats;
+}
+
static int br_change_mtu(struct net_device *dev, int new_mtu)
{
struct net_bridge *br = netdev_priv(dev);
@@ -180,19 +206,28 @@
.ndo_open = br_dev_open,
.ndo_stop = br_dev_stop,
.ndo_start_xmit = br_dev_xmit,
+ .ndo_get_stats = br_get_stats,
.ndo_set_mac_address = br_set_mac_address,
.ndo_set_multicast_list = br_dev_set_multicast_list,
.ndo_change_mtu = br_change_mtu,
.ndo_do_ioctl = br_dev_ioctl,
};
+static void br_dev_free(struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ free_percpu(br->stats);
+ free_netdev(dev);
+}
+
void br_dev_setup(struct net_device *dev)
{
random_ether_addr(dev->dev_addr);
ether_setup(dev);
dev->netdev_ops = &br_netdev_ops;
- dev->destructor = free_netdev;
+ dev->destructor = br_dev_free;
SET_ETHTOOL_OPS(dev, &br_ethtool_ops);
dev->tx_queue_len = 0;
dev->priv_flags = IFF_EBRIDGE;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index b6a3872..b7cdd2e 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -185,6 +185,12 @@
br = netdev_priv(dev);
br->dev = dev;
+ br->stats = alloc_percpu(struct br_cpu_netstats);
+ if (!br->stats) {
+ free_netdev(dev);
+ return NULL;
+ }
+
spin_lock_init(&br->lock);
INIT_LIST_HEAD(&br->port_list);
spin_lock_init(&br->hash_lock);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index d74d570..333dfb7 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -23,9 +23,11 @@
static int br_pass_frame_up(struct sk_buff *skb)
{
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
+ struct net_bridge *br = netdev_priv(brdev);
+ struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
- brdev->stats.rx_packets++;
- brdev->stats.rx_bytes += skb->len;
+ brstats->rx_packets++;
+ brstats->rx_bytes += skb->len;
indev = skb->dev;
skb->dev = brdev;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 846d7d1..791d4ab 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -135,6 +135,14 @@
spinlock_t lock;
struct list_head port_list;
struct net_device *dev;
+
+ struct br_cpu_netstats __percpu {
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long tx_packets;
+ unsigned long tx_bytes;
+ } *stats;
+
spinlock_t hash_lock;
struct hlist_head hash[BR_HASH_SIZE];
unsigned long feature_mask;
