net: Enable 64-bit net device statistics on 32-bit architectures

Use struct rtnl_link_stats64 as the statistics structure.

On 32-bit architectures, insert 32 bits of padding after/before each
field of struct net_device_stats to make its layout compatible with
struct rtnl_link_stats64.  Add an anonymous union in net_device; move
stats into the union and add struct rtnl_link_stats64 stats64.

Add net_device_ops::ndo_get_stats64, implementations of which will
return a pointer to struct rtnl_link_stats64.  Drivers that implement
this operation must not update the structure asynchronously.

Change dev_get_stats() to call ndo_get_stats64 if available, and to
return a pointer to struct rtnl_link_stats64.  Change callers of
dev_get_stats() accordingly.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_main.c

@@ -3804,20 +3804,21 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
-static struct net_device_stats *bond_get_stats(struct net_device *bond_dev)
+static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct net_device_stats *stats = &bond_dev->stats;
-	struct net_device_stats local_stats;
+	struct rtnl_link_stats64 *stats = &bond_dev->stats64;
+	struct rtnl_link_stats64 local_stats;
 	struct slave *slave;
 	int i;
 
-	memset(&local_stats, 0, sizeof(struct net_device_stats));
+	memset(&local_stats, 0, sizeof(local_stats));
 
 	read_lock_bh(&bond->lock);
 
 	bond_for_each_slave(bond, slave, i) {
-		const struct net_device_stats *sstats = dev_get_stats(slave->dev);
+		const struct rtnl_link_stats64 *sstats =
+			dev_get_stats(slave->dev);
 
 		local_stats.rx_packets += sstats->rx_packets;
 		local_stats.rx_bytes += sstats->rx_bytes;
@@ -4569,7 +4570,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_stop		= bond_close,
 	.ndo_start_xmit		= bond_start_xmit,
 	.ndo_select_queue	= bond_select_queue,
-	.ndo_get_stats		= bond_get_stats,
+	.ndo_get_stats64	= bond_get_stats,
 	.ndo_do_ioctl		= bond_do_ioctl,
 	.ndo_set_multicast_list	= bond_set_multicast_list,
 	.ndo_change_mtu		= bond_change_mtu,

include/linux/if_link.h

@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <linux/netlink.h>
 
-/* The struct should be in sync with struct net_device_stats */
+/* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
 	__u32	rx_packets;		/* total packets received	*/
 	__u32	tx_packets;		/* total packets transmitted	*/
@@ -37,6 +37,7 @@ struct rtnl_link_stats {
 	__u32	tx_compressed;
 };
 
+/* The main device statistics structure */
 struct rtnl_link_stats64 {
 	__u64	rx_packets;		/* total packets received	*/
 	__u64	tx_packets;		/* total packets transmitted	*/

include/linux/netdevice.h

@@ -159,45 +159,49 @@ static inline bool dev_xmit_complete(int rc)
 #define MAX_HEADER (LL_MAX_HEADER + 48)
 #endif
 
-#endif  /*  __KERNEL__  */
-
 /*
- *	Network device statistics. Akin to the 2.0 ether stats but
- *	with byte counters.
+ *	Old network device statistics. Fields are native words
+ *	(unsigned long) so they can be read and written atomically.
+ *	Each field is padded to 64 bits for compatibility with
+ *	rtnl_link_stats64.
  */
 
+#if BITS_PER_LONG == 64
+#define NET_DEVICE_STATS_DEFINE(name)	unsigned long name
+#elif defined(__LITTLE_ENDIAN)
+#define NET_DEVICE_STATS_DEFINE(name)	unsigned long name, pad_ ## name
+#else
+#define NET_DEVICE_STATS_DEFINE(name)	unsigned long pad_ ## name, name
+#endif
+
 struct net_device_stats {
-	unsigned long	rx_packets;		/* total packets received	*/
-	unsigned long	tx_packets;		/* total packets transmitted	*/
-	unsigned long	rx_bytes;		/* total bytes received 	*/
-	unsigned long	tx_bytes;		/* total bytes transmitted	*/
-	unsigned long	rx_errors;		/* bad packets received		*/
-	unsigned long	tx_errors;		/* packet transmit problems	*/
-	unsigned long	rx_dropped;		/* no space in linux buffers	*/
-	unsigned long	tx_dropped;		/* no space available in linux	*/
-	unsigned long	multicast;		/* multicast packets received	*/
-	unsigned long	collisions;
-
-	/* detailed rx_errors: */
-	unsigned long	rx_length_errors;
-	unsigned long	rx_over_errors;		/* receiver ring buff overflow	*/
-	unsigned long	rx_crc_errors;		/* recved pkt with crc error	*/
-	unsigned long	rx_frame_errors;	/* recv'd frame alignment error */
-	unsigned long	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	unsigned long	rx_missed_errors;	/* receiver missed packet	*/
-
-	/* detailed tx_errors */
-	unsigned long	tx_aborted_errors;
-	unsigned long	tx_carrier_errors;
-	unsigned long	tx_fifo_errors;
-	unsigned long	tx_heartbeat_errors;
-	unsigned long	tx_window_errors;
-	
-	/* for cslip etc */
-	unsigned long	rx_compressed;
-	unsigned long	tx_compressed;
+	NET_DEVICE_STATS_DEFINE(rx_packets);
+	NET_DEVICE_STATS_DEFINE(tx_packets);
+	NET_DEVICE_STATS_DEFINE(rx_bytes);
+	NET_DEVICE_STATS_DEFINE(tx_bytes);
+	NET_DEVICE_STATS_DEFINE(rx_errors);
+	NET_DEVICE_STATS_DEFINE(tx_errors);
+	NET_DEVICE_STATS_DEFINE(rx_dropped);
+	NET_DEVICE_STATS_DEFINE(tx_dropped);
+	NET_DEVICE_STATS_DEFINE(multicast);
+	NET_DEVICE_STATS_DEFINE(collisions);
+	NET_DEVICE_STATS_DEFINE(rx_length_errors);
+	NET_DEVICE_STATS_DEFINE(rx_over_errors);
+	NET_DEVICE_STATS_DEFINE(rx_crc_errors);
+	NET_DEVICE_STATS_DEFINE(rx_frame_errors);
+	NET_DEVICE_STATS_DEFINE(rx_fifo_errors);
+	NET_DEVICE_STATS_DEFINE(rx_missed_errors);
+	NET_DEVICE_STATS_DEFINE(tx_aborted_errors);
+	NET_DEVICE_STATS_DEFINE(tx_carrier_errors);
+	NET_DEVICE_STATS_DEFINE(tx_fifo_errors);
+	NET_DEVICE_STATS_DEFINE(tx_heartbeat_errors);
+	NET_DEVICE_STATS_DEFINE(tx_window_errors);
+	NET_DEVICE_STATS_DEFINE(rx_compressed);
+	NET_DEVICE_STATS_DEFINE(tx_compressed);
 };
 
+#endif  /*  __KERNEL__  */
+
 
 /* Media selection options. */
 enum {
@@ -662,10 +666,19 @@ struct netdev_rx_queue {
  *	Callback uses when the transmitter has not made any progress
  *	for dev->watchdog ticks.
  *
+ * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev);
  * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
  *	Called when a user wants to get the network device usage
- *	statistics. If not defined, the counters in dev->stats will
- *	be used.
+ *	statistics. Drivers must do one of the following:
+ *	1. Define @ndo_get_stats64 to update a rtnl_link_stats64 structure
+ *	   (which should normally be dev->stats64) and return a ponter to
+ *	   it. The structure must not be changed asynchronously.
+ *	2. Define @ndo_get_stats to update a net_device_stats64 structure
+ *	   (which should normally be dev->stats) and return a pointer to
+ *	   it. The structure may be changed asynchronously only if each
+ *	   field is written atomically.
+ *	3. Update dev->stats asynchronously and atomically, and define
+ *	   neither operation.
  *
  * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp);
  *	If device support VLAN receive accleration
@@ -720,6 +733,7 @@ struct net_device_ops {
 						   struct neigh_parms *);
 	void			(*ndo_tx_timeout) (struct net_device *dev);
 
+	struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev);
 	struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
 
 	void			(*ndo_vlan_rx_register)(struct net_device *dev,
@@ -869,7 +883,10 @@ struct net_device {
 	int			ifindex;
 	int			iflink;
 
-	struct net_device_stats	stats;
+	union {
+		struct rtnl_link_stats64 stats64;
+		struct net_device_stats stats;
+	};
 
 #ifdef CONFIG_WIRELESS_EXT
 	/* List of functions to handle Wireless Extensions (instead of ioctl).
@@ -2121,7 +2138,7 @@ extern void		netdev_features_change(struct net_device *dev);
 /* Load a device via the kmod */
 extern void		dev_load(struct net *net, const char *name);
 extern void		dev_mcast_init(void);
-extern const struct net_device_stats *dev_get_stats(struct net_device *dev);
+extern const struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev);
 extern void		dev_txq_stats_fold(const struct net_device *dev, struct net_device_stats *stats);
 
 extern int		netdev_max_backlog;

net/8021q/vlanproc.c

@@ -278,8 +278,9 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
 {
 	struct net_device *vlandev = (struct net_device *) seq->private;
 	const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
-	const struct net_device_stats *stats;
+	const struct rtnl_link_stats64 *stats;
 	static const char fmt[] = "%30s %12lu\n";
+	static const char fmt64[] = "%30s %12llu\n";
 	int i;
 
 	if (!is_vlan_dev(vlandev))
@@ -291,12 +292,12 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
 		   vlandev->name, dev_info->vlan_id,
 		   (int)(dev_info->flags & 1), vlandev->priv_flags);
 
-	seq_printf(seq, fmt, "total frames received", stats->rx_packets);
-	seq_printf(seq, fmt, "total bytes received", stats->rx_bytes);
-	seq_printf(seq, fmt, "Broadcast/Multicast Rcvd", stats->multicast);
+	seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
+	seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
+	seq_printf(seq, fmt64, "Broadcast/Multicast Rcvd", stats->multicast);
 	seq_puts(seq, "\n");
-	seq_printf(seq, fmt, "total frames transmitted", stats->tx_packets);
-	seq_printf(seq, fmt, "total bytes transmitted", stats->tx_bytes);
+	seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
+	seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
 	seq_printf(seq, fmt, "total headroom inc",
 		   dev_info->cnt_inc_headroom_on_tx);
 	seq_printf(seq, fmt, "total encap on xmit",

net/core/dev.c

@@ -3701,10 +3701,10 @@ void dev_seq_stop(struct seq_file *seq, void *v)
 
 static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
 {
-	const struct net_device_stats *stats = dev_get_stats(dev);
+	const struct rtnl_link_stats64 *stats = dev_get_stats(dev);
 
-	seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
-		   "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+	seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
+		   "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
 		   dev->name, stats->rx_bytes, stats->rx_packets,
 		   stats->rx_errors,
 		   stats->rx_dropped + stats->rx_missed_errors,
@@ -5281,18 +5281,21 @@ EXPORT_SYMBOL(dev_txq_stats_fold);
  *	@dev: device to get statistics from
  *
  *	Get network statistics from device. The device driver may provide
- *	its own method by setting dev->netdev_ops->get_stats; otherwise
- *	the internal statistics structure is used.
+ *	its own method by setting dev->netdev_ops->get_stats64 or
+ *	dev->netdev_ops->get_stats; otherwise the internal statistics
+ *	structure is used.
  */
-const struct net_device_stats *dev_get_stats(struct net_device *dev)
+const struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
+	if (ops->ndo_get_stats64)
+		return ops->ndo_get_stats64(dev);
 	if (ops->ndo_get_stats)
-		return ops->ndo_get_stats(dev);
+		return (struct rtnl_link_stats64 *)ops->ndo_get_stats(dev);
 
 	dev_txq_stats_fold(dev, &dev->stats);
-	return &dev->stats;
+	return &dev->stats64;
 }
 EXPORT_SYMBOL(dev_get_stats);
 

net/core/net-sysfs.c

@@ -29,6 +29,7 @@ static const char fmt_hex[] = "%#x\n";
 static const char fmt_long_hex[] = "%#lx\n";
 static const char fmt_dec[] = "%d\n";
 static const char fmt_ulong[] = "%lu\n";
+static const char fmt_u64[] = "%llu\n";
 
 static inline int dev_isalive(const struct net_device *dev)
 {
@@ -324,14 +325,13 @@ static ssize_t netstat_show(const struct device *d,
 	struct net_device *dev = to_net_dev(d);
 	ssize_t ret = -EINVAL;
 
-	WARN_ON(offset > sizeof(struct net_device_stats) ||
-			offset % sizeof(unsigned long) != 0);
+	WARN_ON(offset > sizeof(struct rtnl_link_stats64) ||
+			offset % sizeof(u64) != 0);
 
 	read_lock(&dev_base_lock);
 	if (dev_isalive(dev)) {
-		const struct net_device_stats *stats = dev_get_stats(dev);
-		ret = sprintf(buf, fmt_ulong,
-			      *(unsigned long *)(((u8 *) stats) + offset));
+		const struct rtnl_link_stats64 *stats = dev_get_stats(dev);
+		ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset));
 	}
 	read_unlock(&dev_base_lock);
 	return ret;
@@ -343,7 +343,7 @@ static ssize_t show_##name(struct device *d,				\
 			   struct device_attribute *attr, char *buf) 	\
 {									\
 	return netstat_show(d, attr, buf,				\
-			    offsetof(struct net_device_stats, name));	\
+			    offsetof(struct rtnl_link_stats64, name));	\
 }									\
 static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
 

net/core/rtnetlink.c

@@ -579,7 +579,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
 }
 
 static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
-				 const struct net_device_stats *b)
+				 const struct rtnl_link_stats64 *b)
 {
 	a->rx_packets = b->rx_packets;
 	a->tx_packets = b->tx_packets;
@@ -610,7 +610,7 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
 	a->tx_compressed = b->tx_compressed;
 }
 
-static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b)
+static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b)
 {
 	struct rtnl_link_stats64 a;
 
@@ -791,7 +791,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
-	const struct net_device_stats *stats;
+	const struct rtnl_link_stats64 *stats;
 	struct nlattr *attr;
 
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);