diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h
index 24a6cb1aec86..77a19dfe3990 100644
--- a/include/uapi/linux/mpls.h
+++ b/include/uapi/linux/mpls.h
@@ -43,4 +43,34 @@ struct mpls_label {
#define MPLS_LABEL_FIRST_UNRESERVED 16 /* RFC3032 */
+/* These are embedded into IFLA_STATS_AF_SPEC:
+ * [IFLA_STATS_AF_SPEC]
+ * -> [AF_MPLS]
+ * -> [MPLS_STATS_xxx]
+ *
+ * Attributes:
+ * [MPLS_STATS_LINK] = {
+ * struct mpls_link_stats
+ * }
+ */
+enum {
+ MPLS_STATS_UNSPEC, /* also used as 64bit pad attribute */
+ MPLS_STATS_LINK,
+ __MPLS_STATS_MAX,
+};
+
+#define MPLS_STATS_MAX (__MPLS_STATS_MAX - 1)
+
+struct mpls_link_stats {
+ __u64 rx_packets; /* total packets received */
+ __u64 tx_packets; /* total packets transmitted */
+ __u64 rx_bytes; /* total bytes received */
+ __u64 tx_bytes; /* total bytes transmitted */
+ __u64 rx_errors; /* bad packets received */
+ __u64 tx_errors; /* packet transmit problems */
+ __u64 rx_dropped; /* packet dropped on receive */
+ __u64 tx_dropped; /* packet dropped on transmit */
+ __u64 rx_noroute; /* no route for packet dest */
+};
+
#endif /* _UAPI_MPLS_H */
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 15fe97644ffe..4dc81963af8f 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -8,6 +8,7 @@
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/vmalloc.h>
+#include <linux/percpu.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
@@ -17,8 +18,8 @@
#include <net/netns/generic.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
-#include <net/addrconf.h>
#endif
+#include <net/addrconf.h>
#include <net/nexthop.h>
#include "internal.h"
@@ -48,11 +49,6 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
return rt;
}
-static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
-{
- return rcu_dereference_rtnl(dev->mpls_ptr);
-}
-
bool mpls_output_possible(const struct net_device *dev)
{
return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
@@ -98,6 +94,31 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
}
EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
+void mpls_stats_inc_outucastpkts(struct net_device *dev,
+ const struct sk_buff *skb)
+{
+ struct mpls_dev *mdev;
+
+ if (skb->protocol == htons(ETH_P_MPLS_UC)) {
+ mdev = mpls_dev_get(dev);
+ if (mdev)
+ MPLS_INC_STATS_LEN(mdev, skb->len,
+ tx_packets,
+ tx_bytes);
+ } else if (skb->protocol == htons(ETH_P_IP)) {
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct inet6_dev *in6dev = __in6_dev_get(dev);
+
+ if (in6dev)
+ IP6_UPD_PO_STATS(dev_net(dev), in6dev,
+ IPSTATS_MIB_OUT, skb->len);
+#endif
+ }
+}
+EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts);
+
static u32 mpls_multipath_hash(struct mpls_route *rt,
struct sk_buff *skb, bool bos)
{
@@ -253,6 +274,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
struct mpls_nh *nh;
struct mpls_entry_decoded dec;
struct net_device *out_dev;
+ struct mpls_dev *out_mdev;
struct mpls_dev *mdev;
unsigned int hh_len;
unsigned int new_header_size;
@@ -262,17 +284,25 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
/* Careful this entire function runs inside of an rcu critical section */
mdev = mpls_dev_get(dev);
- if (!mdev || !mdev->input_enabled)
+ if (!mdev)
goto drop;
+ MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets,
+ rx_bytes);
+
+ if (!mdev->input_enabled) {
+ MPLS_INC_STATS(mdev, rx_dropped);
+ goto drop;
+ }
+
if (skb->pkt_type != PACKET_HOST)
- goto drop;
+ goto err;
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
- goto drop;
+ goto err;
if (!pskb_may_pull(skb, sizeof(*hdr)))
- goto drop;
+ goto err;
/* Read and decode the label */
hdr = mpls_hdr(skb);
@@ -285,33 +315,35 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
skb_orphan(skb);
rt = mpls_route_input_rcu(net, dec.label);
- if (!rt)
+ if (!rt) {
+ MPLS_INC_STATS(mdev, rx_noroute);
goto drop;
+ }
nh = mpls_select_multipath(rt, skb, dec.bos);
if (!nh)
- goto drop;
-
- /* Find the output device */
- out_dev = rcu_dereference(nh->nh_dev);
- if (!mpls_output_possible(out_dev))
- goto drop;
+ goto err;
if (skb_warn_if_lro(skb))
- goto drop;
+ goto err;
skb_forward_csum(skb);
/* Verify ttl is valid */
if (dec.ttl <= 1)
- goto drop;
+ goto err;
dec.ttl -= 1;
+ /* Find the output device */
+ out_dev = rcu_dereference(nh->nh_dev);
+ if (!mpls_output_possible(out_dev))
+ goto tx_err;
+
/* Verify the destination can hold the packet */
new_header_size = mpls_nh_header_size(nh);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
- goto drop;
+ goto tx_err;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
@@ -319,7 +351,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
- goto drop;
+ goto tx_err;
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
@@ -327,7 +359,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
if (unlikely(!new_header_size && dec.bos)) {
/* Penultimate hop popping */
if (!mpls_egress(rt, skb, dec))
- goto drop;
+ goto err;
} else {
bool bos;
int i;
@@ -343,6 +375,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
}
}
+ mpls_stats_inc_outucastpkts(out_dev, skb);
+
/* If via wasn't specified then send out using device address */
if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC)
err = neigh_xmit(NEIGH_LINK_TABLE, out_dev,
@@ -355,6 +389,13 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
__func__, err);
return 0;
+tx_err:
+ out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL;
+ if (out_mdev)
+ MPLS_INC_STATS(out_mdev, tx_errors);
+ goto drop;
+err:
+ MPLS_INC_STATS(mdev, rx_errors);
drop:
kfree_skb(skb);
return NET_RX_DROP;
@@ -853,6 +894,70 @@ errout:
return err;
}
+static void mpls_get_stats(struct mpls_dev *mdev,
+ struct mpls_link_stats *stats)
+{
+ struct mpls_pcpu_stats *p;
+ int i;
+
+ memset(stats, 0, sizeof(*stats));
+
+ for_each_possible_cpu(i) {
+ struct mpls_link_stats local;
+ unsigned int start;
+
+ p = per_cpu_ptr(mdev->stats, i);
+ do {
+ start = u64_stats_fetch_begin(&p->syncp);
+ local = p->stats;
+ } while (u64_stats_fetch_retry(&p->syncp, start));
+
+ stats->rx_packets += local.rx_packets;
+ stats->rx_bytes += local.rx_bytes;
+ stats->tx_packets += local.tx_packets;
+ stats->tx_bytes += local.tx_bytes;
+ stats->rx_errors += local.rx_errors;
+ stats->tx_errors += local.tx_errors;
+ stats->rx_dropped += local.rx_dropped;
+ stats->tx_dropped += local.tx_dropped;
+ stats->rx_noroute += local.rx_noroute;
+ }
+}
+
+static int mpls_fill_stats_af(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct mpls_link_stats *stats;
+ struct mpls_dev *mdev;
+ struct nlattr *nla;
+
+ mdev = mpls_dev_get(dev);
+ if (!mdev)
+ return -ENODATA;
+
+ nla = nla_reserve_64bit(skb, MPLS_STATS_LINK,
+ sizeof(struct mpls_link_stats),
+ MPLS_STATS_UNSPEC);
+ if (!nla)
+ return -EMSGSIZE;
+
+ stats = nla_data(nla);
+ mpls_get_stats(mdev, stats);
+
+ return 0;
+}
+
+static size_t mpls_get_stats_af_size(const struct net_device *dev)
+{
+ struct mpls_dev *mdev;
+
+ mdev = mpls_dev_get(dev);
+ if (!mdev)
+ return 0;
+
+ return nla_total_size_64bit(sizeof(struct mpls_link_stats));
+}
+
#define MPLS_PERDEV_SYSCTL_OFFSET(field) \
(&((struct mpls_dev *)0)->field)
@@ -911,6 +1016,7 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
{
struct mpls_dev *mdev;
int err = -ENOMEM;
+ int i;
ASSERT_RTNL();
@@ -918,6 +1024,17 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
if (!mdev)
return ERR_PTR(err);
+ mdev->stats = alloc_percpu(struct mpls_pcpu_stats);
+ if (!mdev->stats)
+ goto free;
+
+ for_each_possible_cpu(i) {
+ struct mpls_pcpu_stats *mpls_stats;
+
+ mpls_stats = per_cpu_ptr(mdev->stats, i);
+ u64_stats_init(&mpls_stats->syncp);
+ }
+
err = mpls_dev_sysctl_register(dev, mdev);
if (err)
goto free;
@@ -927,10 +1044,19 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
return mdev;
free:
+ free_percpu(mdev->stats);
kfree(mdev);
return ERR_PTR(err);
}
+static void mpls_dev_destroy_rcu(struct rcu_head *head)
+{
+ struct mpls_dev *mdev = container_of(head, struct mpls_dev, rcu);
+
+ free_percpu(mdev->stats);
+ kfree(mdev);
+}
+
static void mpls_ifdown(struct net_device *dev, int event)
{
struct mpls_route __rcu **platform_label;
@@ -1045,7 +1171,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
if (mdev) {
mpls_dev_sysctl_unregister(mdev);
RCU_INIT_POINTER(dev->mpls_ptr, NULL);
- kfree_rcu(mdev, rcu);
+ call_rcu(&mdev->rcu, mpls_dev_destroy_rcu);
}
break;
case NETDEV_CHANGENAME:
@@ -1706,6 +1832,12 @@ static struct pernet_operations mpls_net_ops = {
.exit = mpls_net_exit,
};
+static struct rtnl_af_ops mpls_af_ops __read_mostly = {
+ .family = AF_MPLS,
+ .fill_stats_af = mpls_fill_stats_af,
+ .get_stats_af_size = mpls_get_stats_af_size,
+};
+
static int __init mpls_init(void)
{
int err;
@@ -1722,6 +1854,8 @@ static int __init mpls_init(void)
dev_add_pack(&mpls_packet_type);
+ rtnl_af_register(&mpls_af_ops);
+
rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL);
rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL);
rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL);
@@ -1738,6 +1872,7 @@ module_init(mpls_init);
static void __exit mpls_exit(void)
{
rtnl_unregister_all(PF_MPLS);
+ rtnl_af_unregister(&mpls_af_ops);
dev_remove_pack(&mpls_packet_type);
unregister_netdevice_notifier(&mpls_dev_notifier);
unregister_pernet_subsys(&mpls_net_ops);
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index bdfef6c3271a..d97243034605 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -9,13 +9,58 @@ struct mpls_entry_decoded {
u8 bos;
};
-struct mpls_dev {
- int input_enabled;
-
- struct ctl_table_header *sysctl;
- struct rcu_head rcu;
+struct mpls_pcpu_stats {
+ struct mpls_link_stats stats;
+ struct u64_stats_sync syncp;
};
+struct mpls_dev {
+ int input_enabled;
+
+ struct mpls_pcpu_stats __percpu *stats;
+
+ struct ctl_table_header *sysctl;
+ struct rcu_head rcu;
+};
+
+#if BITS_PER_LONG == 32
+
+#define MPLS_INC_STATS_LEN(mdev, len, pkts_field, bytes_field) \
+ do { \
+ __typeof__(*(mdev)->stats) *ptr = \
+ raw_cpu_ptr((mdev)->stats); \
+ local_bh_disable(); \
+ u64_stats_update_begin(&ptr->syncp); \
+ ptr->stats.pkts_field++; \
+ ptr->stats.bytes_field += (len); \
+ u64_stats_update_end(&ptr->syncp); \
+ local_bh_enable(); \
+ } while (0)
+
+#define MPLS_INC_STATS(mdev, field) \
+ do { \
+ __typeof__(*(mdev)->stats) *ptr = \
+ raw_cpu_ptr((mdev)->stats); \
+ local_bh_disable(); \
+ u64_stats_update_begin(&ptr->syncp); \
+ ptr->stats.field++; \
+ u64_stats_update_end(&ptr->syncp); \
+ local_bh_enable(); \
+ } while (0)
+
+#else
+
+#define MPLS_INC_STATS_LEN(mdev, len, pkts_field, bytes_field) \
+ do { \
+ this_cpu_inc((mdev)->stats->stats.pkts_field); \
+ this_cpu_add((mdev)->stats->stats.bytes_field, (len)); \
+ } while (0)
+
+#define MPLS_INC_STATS(mdev, field) \
+ this_cpu_inc((mdev)->stats->stats.field)
+
+#endif
+
struct sk_buff;
#define LABEL_NOT_SPECIFIED (1 << 20)
@@ -114,6 +159,11 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *
return result;
}
+static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
+{
+ return rcu_dereference_rtnl(dev->mpls_ptr);
+}
+
int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels,
const u32 label[]);
int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels,
@@ -123,5 +173,7 @@ int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
bool mpls_output_possible(const struct net_device *dev);
unsigned int mpls_dev_mtu(const struct net_device *dev);
bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu);
+void mpls_stats_inc_outucastpkts(struct net_device *dev,
+ const struct sk_buff *skb);
#endif /* MPLS_INTERNAL_H */
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2f7ccd934416..02531284bc49 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -48,11 +48,15 @@ static int mpls_xmit(struct sk_buff *skb)
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = NULL;
struct rt6_info *rt6 = NULL;
+ struct mpls_dev *out_mdev;
int err = 0;
bool bos;
int i;
unsigned int ttl;
+ /* Find the output device */
+ out_dev = dst->dev;
+
/* Obtain the ttl */
if (dst->ops->family == AF_INET) {
ttl = ip_hdr(skb)->ttl;
@@ -66,8 +70,6 @@ static int mpls_xmit(struct sk_buff *skb)
skb_orphan(skb);
- /* Find the output device */
- out_dev = dst->dev;
if (!mpls_output_possible(out_dev) ||
!dst->lwtstate || skb_warn_if_lro(skb))
goto drop;
@@ -109,6 +111,8 @@ static int mpls_xmit(struct sk_buff *skb)
bos = false;
}
+ mpls_stats_inc_outucastpkts(out_dev, skb);
+
if (rt)
err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway,
skb);
@@ -122,6 +126,9 @@ static int mpls_xmit(struct sk_buff *skb)
return LWTUNNEL_XMIT_DONE;
drop:
+ out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL;
+ if (out_mdev)
+ MPLS_INC_STATS(out_mdev, tx_errors);
kfree_skb(skb);
return -EINVAL;
}