Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

1 files changed, 152 insertions, 34 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 904ff431d570..2a9c39f8824e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -94,6 +94,7 @@
 #include <linux/ethtool.h>
 #include <linux/notifier.h>
 #include <linux/skbuff.h>
+#include <linux/bpf.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/busy_poll.h>
@@ -139,6 +140,7 @@
 #include <linux/hrtimer.h>
 #include <linux/netfilter_ingress.h>
 #include <linux/sctp.h>
+#include <linux/crash_dump.h>
 
 #include "net-sysfs.h"
 
@@ -2249,11 +2251,12 @@ EXPORT_SYMBOL(netif_set_real_num_rx_queues);
  */
 int netif_get_num_default_rss_queues(void)
 {
-	return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+	return is_kdump_kernel() ?
+		1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
 }
 EXPORT_SYMBOL(netif_get_num_default_rss_queues);
 
-static inline void __netif_reschedule(struct Qdisc *q)
+static void __netif_reschedule(struct Qdisc *q)
 {
 	struct softnet_data *sd;
 	unsigned long flags;
@@ -2420,7 +2423,7 @@ EXPORT_SYMBOL(__skb_tx_hash);
 
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
-	static const netdev_features_t null_features = 0;
+	static const netdev_features_t null_features;
 	struct net_device *dev = skb->dev;
 	const char *name = "";
 
@@ -3068,6 +3071,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				 struct netdev_queue *txq)
 {
 	spinlock_t *root_lock = qdisc_lock(q);
+	struct sk_buff *to_free = NULL;
 	bool contended;
 	int rc;
 
@@ -3075,7 +3079,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	/*
 	 * Heuristic to force contended enqueues to serialize on a
 	 * separate lock before trying to get qdisc main lock.
-	 * This permits __QDISC___STATE_RUNNING owner to get the lock more
+	 * This permits qdisc->running owner to get the lock more
 	 * often and dequeue packets faster.
 	 */
 	contended = qdisc_is_running(q);
@@ -3084,7 +3088,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	spin_lock(root_lock);
 	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
-		kfree_skb(skb);
+		__qdisc_drop(skb, &to_free);
 		rc = NET_XMIT_DROP;
 	} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
 		   qdisc_run_begin(q)) {
@@ -3107,7 +3111,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
-		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
@@ -3117,6 +3121,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		}
 	}
 	spin_unlock(root_lock);
+	if (unlikely(to_free))
+		kfree_skb_list(to_free);
 	if (unlikely(contended))
 		spin_unlock(&q->busylock);
 	return rc;
@@ -3142,8 +3148,6 @@ static void skb_update_prio(struct sk_buff *skb)
 DEFINE_PER_CPU(int, xmit_recursion);
 EXPORT_SYMBOL(xmit_recursion);
 
-#define RECURSION_LIMIT 10
-
 /**
  *	dev_loopback_xmit - loop back @skb
  *	@net: network namespace this loopback is happening in
@@ -3386,8 +3390,8 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
 		if (txq->xmit_lock_owner != cpu) {
-
-			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+			if (unlikely(__this_cpu_read(xmit_recursion) >
+				     XMIT_RECURSION_LIMIT))
 				goto recursion_alert;
 
 			skb = validate_xmit_skb(skb, dev);
@@ -3898,22 +3902,14 @@ static void net_tx_action(struct softirq_action *h)
 			head = head->next_sched;
 
 			root_lock = qdisc_lock(q);
-			if (spin_trylock(root_lock)) {
-				smp_mb__before_atomic();
-				clear_bit(__QDISC_STATE_SCHED,
-					  &q->state);
-				qdisc_run(q);
-				spin_unlock(root_lock);
-			} else {
-				if (!test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state)) {
-					__netif_reschedule(q);
-				} else {
-					smp_mb__before_atomic();
-					clear_bit(__QDISC_STATE_SCHED,
-						  &q->state);
-				}
-			}
+			spin_lock(root_lock);
+			/* We need to make sure head->next_sched is read
+			 * before clearing __QDISC_STATE_SCHED
+			 */
+			smp_mb__before_atomic();
+			clear_bit(__QDISC_STATE_SCHED, &q->state);
+			qdisc_run(q);
+			spin_unlock(root_lock);
 		}
 	}
 }
@@ -4977,7 +4973,7 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
 
 			if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
 				rc = napi->poll(napi, BUSY_POLL_BUDGET);
-				trace_napi_poll(napi);
+				trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
 				if (rc == BUSY_POLL_BUDGET) {
 					napi_complete_done(napi, rc);
 					napi_schedule(napi);
@@ -5133,7 +5129,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 	work = 0;
 	if (test_bit(NAPI_STATE_SCHED, &n->state)) {
 		work = n->poll(n, weight);
-		trace_napi_poll(n);
+		trace_napi_poll(n, work, weight);
 	}
 
 	WARN_ON_ONCE(work > weight);
@@ -5450,6 +5446,52 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
 EXPORT_SYMBOL(netdev_lower_get_next);
 
 /**
+ * netdev_all_lower_get_next - Get the next device from all lower neighbour list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's all lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour all lower
+ * list will remain unchanged.
+ */
+struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry(*iter, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->all_adj_list.lower)
+		return NULL;
+
+	*iter = lower->list.next;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_all_lower_get_next);
+
+/**
+ * netdev_all_lower_get_next_rcu - Get the next device from all
+ *				   lower neighbour list, RCU variant
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's all lower neighbour
+ * list, starting from iter position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
+				       struct netdev_adjacent, list);
+
+	return lower ? lower->dev : NULL;
+}
+EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
+
+/**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *				       lower neighbour list, RCU
  *				       variant
@@ -5919,7 +5961,7 @@ static void netdev_adjacent_add_links(struct net_device *dev)
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_add(iter->dev, dev,
 					  &iter->dev->adj_list.lower);
@@ -5928,7 +5970,7 @@ static void netdev_adjacent_add_links(struct net_device *dev)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_add(iter->dev, dev,
 					  &iter->dev->adj_list.upper);
@@ -5944,7 +5986,7 @@ static void netdev_adjacent_del_links(struct net_device *dev)
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, dev->name,
 					  &iter->dev->adj_list.lower);
@@ -5953,7 +5995,7 @@ static void netdev_adjacent_del_links(struct net_device *dev)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, dev->name,
 					  &iter->dev->adj_list.upper);
@@ -5969,7 +6011,7 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.lower);
@@ -5978,7 +6020,7 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.upper);
@@ -6046,6 +6088,50 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
 }
 EXPORT_SYMBOL(netdev_lower_state_changed);
 
+int netdev_default_l2upper_neigh_construct(struct net_device *dev,
+					   struct neighbour *n)
+{
+	struct net_device *lower_dev, *stop_dev;
+	struct list_head *iter;
+	int err;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (!lower_dev->netdev_ops->ndo_neigh_construct)
+			continue;
+		err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n);
+		if (err) {
+			stop_dev = lower_dev;
+			goto rollback;
+		}
+	}
+	return 0;
+
+rollback:
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (lower_dev == stop_dev)
+			break;
+		if (!lower_dev->netdev_ops->ndo_neigh_destroy)
+			continue;
+		lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct);
+
+void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
+					  struct neighbour *n)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		if (!lower_dev->netdev_ops->ndo_neigh_destroy)
+			continue;
+		lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
+	}
+}
+EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -6530,6 +6616,38 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
 EXPORT_SYMBOL(dev_change_proto_down);
 
 /**
+ *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
+ *	@dev: device
+ *	@fd: new program fd or negative value to clear
+ *
+ *	Set or clear a bpf program for a device
+ */
+int dev_change_xdp_fd(struct net_device *dev, int fd)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct bpf_prog *prog = NULL;
+	struct netdev_xdp xdp = {};
+	int err;
+
+	if (!ops->ndo_xdp)
+		return -EOPNOTSUPP;
+	if (fd >= 0) {
+		prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+		if (IS_ERR(prog))
+			return PTR_ERR(prog);
+	}
+
+	xdp.command = XDP_SETUP_PROG;
+	xdp.prog = prog;
+	err = ops->ndo_xdp(dev, &xdp);
+	if (err < 0 && prog)
+		bpf_prog_put(prog);
+
+	return err;
+}
+EXPORT_SYMBOL(dev_change_xdp_fd);
+
+/**
  *	dev_new_index	-	allocate an ifindex
  *	@net: the applicable net namespace
  *