Merge branch 'next' into for-linus

Prepare first round of input updates for 3.20.

1 files changed, 469 insertions, 319 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index cf8a95f48cf..683d493aa1b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -118,6 +118,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/mpls.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
 #include <linux/jhash.h>
@@ -133,6 +134,7 @@
 #include <linux/vmalloc.h>
 #include <linux/if_macvlan.h>
 #include <linux/errqueue.h>
+#include <linux/hrtimer.h>
 
 #include "net-sysfs.h"
 
@@ -897,23 +899,25 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
- *	dev_get_by_flags_rcu - find any device with given flags
+ *	__dev_get_by_flags - find any device with given flags
  *	@net: the applicable net namespace
  *	@if_flags: IFF_* values
  *	@mask: bitmask of bits in if_flags to check
  *
  *	Search for any interface with the given flags. Returns NULL if a device
  *	is not found or a pointer to the device. Must be called inside
- *	rcu_read_lock(), and result refcount is unchanged.
+ *	rtnl_lock(), and result refcount is unchanged.
  */
 
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
-				    unsigned short mask)
+struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
+				      unsigned short mask)
 {
 	struct net_device *dev, *ret;
 
+	ASSERT_RTNL();
+
 	ret = NULL;
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		if (((dev->flags ^ if_flags) & mask) == 0) {
 			ret = dev;
 			break;
@@ -921,7 +925,7 @@ struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags
 	}
 	return ret;
 }
-EXPORT_SYMBOL(dev_get_by_flags_rcu);
+EXPORT_SYMBOL(__dev_get_by_flags);
 
 /**
  *	dev_valid_name - check if name is okay for network device
@@ -1284,7 +1288,6 @@ static int __dev_open(struct net_device *dev)
 		clear_bit(__LINK_STATE_START, &dev->state);
 	else {
 		dev->flags |= IFF_UP;
-		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
 		add_device_randomness(dev->dev_addr, dev->addr_len);
@@ -1363,7 +1366,6 @@ static int __dev_close_many(struct list_head *head)
 			ops->ndo_stop(dev);
 
 		dev->flags &= ~IFF_UP;
-		net_dmaengine_put();
 		netpoll_poll_enable(dev);
 	}
 
@@ -1435,22 +1437,17 @@ EXPORT_SYMBOL(dev_close);
  */
 void dev_disable_lro(struct net_device *dev)
 {
-	/*
-	 * If we're trying to disable lro on a vlan device
-	 * use the underlying physical device instead
-	 */
-	if (is_vlan_dev(dev))
-		dev = vlan_dev_real_dev(dev);
-
-	/* the same for macvlan devices */
-	if (netif_is_macvlan(dev))
-		dev = macvlan_dev_real_dev(dev);
+	struct net_device *lower_dev;
+	struct list_head *iter;
 
 	dev->wanted_features &= ~NETIF_F_LRO;
 	netdev_update_features(dev);
 
 	if (unlikely(dev->features & NETIF_F_LRO))
 		netdev_WARN(dev, "failed to disable LRO!\n");
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter)
+		dev_disable_lro(lower_dev);
 }
 EXPORT_SYMBOL(dev_disable_lro);
 
@@ -1697,6 +1694,7 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	skb_scrub_packet(skb, true);
 	skb->protocol = eth_type_trans(skb, dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	return 0;
 }
@@ -2153,7 +2151,7 @@ static inline void __netif_reschedule(struct Qdisc *q)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	sd = &__get_cpu_var(softnet_data);
+	sd = this_cpu_ptr(&softnet_data);
 	q->next_sched = NULL;
 	*sd->output_queue_tailp = q;
 	sd->output_queue_tailp = &q->next_sched;
@@ -2177,6 +2175,53 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
 	return (struct dev_kfree_skb_cb *)skb->cb;
 }
 
+void netif_schedule_queue(struct netdev_queue *txq)
+{
+	rcu_read_lock();
+	if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
+		struct Qdisc *q = rcu_dereference(txq->qdisc);
+
+		__netif_schedule(q);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(netif_schedule_queue);
+
+/**
+ *	netif_wake_subqueue - allow sending packets on subqueue
+ *	@dev: network device
+ *	@queue_index: sub queue index
+ *
+ * Resume individual transmit queue of a device with multiple transmit queues.
+ */
+void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
+{
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
+
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) {
+		struct Qdisc *q;
+
+		rcu_read_lock();
+		q = rcu_dereference(txq->qdisc);
+		__netif_schedule(q);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(netif_wake_subqueue);
+
+void netif_tx_wake_queue(struct netdev_queue *dev_queue)
+{
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) {
+		struct Qdisc *q;
+
+		rcu_read_lock();
+		q = rcu_dereference(dev_queue->qdisc);
+		__netif_schedule(q);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(netif_tx_wake_queue);
+
 void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 {
 	unsigned long flags;
@@ -2373,16 +2418,6 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
 		if (ptype->type == type && ptype->callbacks.gso_segment) {
-			if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
-				int err;
-
-				err = ptype->callbacks.gso_send_check(skb);
-				segs = ERR_PTR(err);
-				if (err || skb_gso_ok(skb, features))
-					break;
-				__skb_push(skb, (skb->data -
-						 skb_network_header(skb)));
-			}
 			segs = ptype->callbacks.gso_segment(skb, features);
 			break;
 		}
@@ -2485,61 +2520,15 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 	return 0;
 }
 
-struct dev_gso_cb {
-	void (*destructor)(struct sk_buff *skb);
-};
-
-#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
-
-static void dev_gso_skb_destructor(struct sk_buff *skb)
-{
-	struct dev_gso_cb *cb;
-
-	kfree_skb_list(skb->next);
-	skb->next = NULL;
-
-	cb = DEV_GSO_CB(skb);
-	if (cb->destructor)
-		cb->destructor(skb);
-}
-
-/**
- *	dev_gso_segment - Perform emulated hardware segmentation on skb.
- *	@skb: buffer to segment
- *	@features: device features as applicable to this skb
- *
- *	This function segments the given skb and stores the list of segments
- *	in skb->next.
- */
-static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
-{
-	struct sk_buff *segs;
-
-	segs = skb_gso_segment(skb, features);
-
-	/* Verifying header integrity only. */
-	if (!segs)
-		return 0;
-
-	if (IS_ERR(segs))
-		return PTR_ERR(segs);
-
-	skb->next = segs;
-	DEV_GSO_CB(skb)->destructor = skb->destructor;
-	skb->destructor = dev_gso_skb_destructor;
-
-	return 0;
-}
-
 /* If MPLS offload request, verify we are testing hardware MPLS features
  * instead of standard features for the netdev.
  */
-#ifdef CONFIG_NET_MPLS_GSO
+#if IS_ENABLED(CONFIG_NET_MPLS_GSO)
 static netdev_features_t net_mpls_features(struct sk_buff *skb,
 					   netdev_features_t features,
 					   __be16 type)
 {
-	if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+	if (eth_p_mpls(type))
 		features &= skb->dev->mpls_features;
 
 	return features;
@@ -2574,21 +2563,33 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
+	struct net_device *dev = skb->dev;
+	netdev_features_t features = dev->features;
+	u16 gso_segs = skb_shinfo(skb)->gso_segs;
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = skb->dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
-	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
-		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
-		protocol = veh->h_vlan_encapsulated_proto;
-	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, features);
+	/* If encapsulation offload request, verify we are testing
+	 * hardware encapsulation features instead of standard
+	 * features for the netdev
+	 */
+	if (skb->encapsulation)
+		features &= dev->hw_enc_features;
+
+	if (!vlan_tx_tag_present(skb)) {
+		if (unlikely(protocol == htons(ETH_P_8021Q) ||
+			     protocol == htons(ETH_P_8021AD))) {
+			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+			protocol = veh->h_vlan_encapsulated_proto;
+		} else {
+			goto finalize;
+		}
 	}
 
 	features = netdev_intersect_features(features,
-					     skb->dev->vlan_features |
+					     dev->vlan_features |
 					     NETIF_F_HW_VLAN_CTAG_TX |
 					     NETIF_F_HW_VLAN_STAG_TX);
 
@@ -2601,123 +2602,147 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 						     NETIF_F_HW_VLAN_CTAG_TX |
 						     NETIF_F_HW_VLAN_STAG_TX);
 
+finalize:
+	if (dev->netdev_ops->ndo_features_check)
+		features &= dev->netdev_ops->ndo_features_check(skb, dev,
+								features);
+
 	return harmonize_features(skb, features);
 }
 EXPORT_SYMBOL(netif_skb_features);
 
-int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq)
+static int xmit_one(struct sk_buff *skb, struct net_device *dev,
+		    struct netdev_queue *txq, bool more)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
-	int rc = NETDEV_TX_OK;
-	unsigned int skb_len;
+	unsigned int len;
+	int rc;
 
-	if (likely(!skb->next)) {
-		netdev_features_t features;
+	if (!list_empty(&ptype_all))
+		dev_queue_xmit_nit(skb, dev);
 
-		/*
-		 * If device doesn't need skb->dst, release it right now while
-		 * its hot in this cpu cache
-		 */
-		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
-			skb_dst_drop(skb);
+	len = skb->len;
+	trace_net_dev_start_xmit(skb, dev);
+	rc = netdev_start_xmit(skb, dev, txq, more);
+	trace_net_dev_xmit(skb, rc, dev, len);
 
-		features = netif_skb_features(skb);
+	return rc;
+}
+
+struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev,
+				    struct netdev_queue *txq, int *ret)
+{
+	struct sk_buff *skb = first;
+	int rc = NETDEV_TX_OK;
 
-		if (vlan_tx_tag_present(skb) &&
-		    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
-			skb = __vlan_put_tag(skb, skb->vlan_proto,
-					     vlan_tx_tag_get(skb));
-			if (unlikely(!skb))
-				goto out;
+	while (skb) {
+		struct sk_buff *next = skb->next;
 
-			skb->vlan_tci = 0;
+		skb->next = NULL;
+		rc = xmit_one(skb, dev, txq, next != NULL);
+		if (unlikely(!dev_xmit_complete(rc))) {
+			skb->next = next;
+			goto out;
 		}
 
-		/* If encapsulation offload request, verify we are testing
-		 * hardware encapsulation features instead of standard
-		 * features for the netdev
-		 */
-		if (skb->encapsulation)
-			features &= dev->hw_enc_features;
+		skb = next;
+		if (netif_xmit_stopped(txq) && skb) {
+			rc = NETDEV_TX_BUSY;
+			break;
+		}
+	}
 
-		if (netif_needs_gso(skb, features)) {
-			if (unlikely(dev_gso_segment(skb, features)))
-				goto out_kfree_skb;
-			if (skb->next)
-				goto gso;
-		} else {
-			if (skb_needs_linearize(skb, features) &&
-			    __skb_linearize(skb))
-				goto out_kfree_skb;
+out:
+	*ret = rc;
+	return skb;
+}
 
-			/* If packet is not checksummed and device does not
-			 * support checksumming for this protocol, complete
-			 * checksumming here.
-			 */
-			if (skb->ip_summed == CHECKSUM_PARTIAL) {
-				if (skb->encapsulation)
-					skb_set_inner_transport_header(skb,
-						skb_checksum_start_offset(skb));
-				else
-					skb_set_transport_header(skb,
-						skb_checksum_start_offset(skb));
-				if (!(features & NETIF_F_ALL_CSUM) &&
-				     skb_checksum_help(skb))
-					goto out_kfree_skb;
-			}
-		}
+static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
+					  netdev_features_t features)
+{
+	if (vlan_tx_tag_present(skb) &&
+	    !vlan_hw_offload_capable(features, skb->vlan_proto))
+		skb = __vlan_hwaccel_push_inside(skb);
+	return skb;
+}
 
-		if (!list_empty(&ptype_all))
-			dev_queue_xmit_nit(skb, dev);
+static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
+{
+	netdev_features_t features;
 
-		skb_len = skb->len;
-		trace_net_dev_start_xmit(skb, dev);
-		rc = ops->ndo_start_xmit(skb, dev);
-		trace_net_dev_xmit(skb, rc, dev, skb_len);
-		if (rc == NETDEV_TX_OK)
-			txq_trans_update(txq);
-		return rc;
-	}
+	if (skb->next)
+		return skb;
 
-gso:
-	do {
-		struct sk_buff *nskb = skb->next;
+	features = netif_skb_features(skb);
+	skb = validate_xmit_vlan(skb, features);
+	if (unlikely(!skb))
+		goto out_null;
 
-		skb->next = nskb->next;
-		nskb->next = NULL;
+	if (netif_needs_gso(dev, skb, features)) {
+		struct sk_buff *segs;
 
-		if (!list_empty(&ptype_all))
-			dev_queue_xmit_nit(nskb, dev);
-
-		skb_len = nskb->len;
-		trace_net_dev_start_xmit(nskb, dev);
-		rc = ops->ndo_start_xmit(nskb, dev);
-		trace_net_dev_xmit(nskb, rc, dev, skb_len);
-		if (unlikely(rc != NETDEV_TX_OK)) {
-			if (rc & ~NETDEV_TX_MASK)
-				goto out_kfree_gso_skb;
-			nskb->next = skb->next;
-			skb->next = nskb;
-			return rc;
+		segs = skb_gso_segment(skb, features);
+		if (IS_ERR(segs)) {
+			goto out_kfree_skb;
+		} else if (segs) {
+			consume_skb(skb);
+			skb = segs;
+		}
+	} else {
+		if (skb_needs_linearize(skb, features) &&
+		    __skb_linearize(skb))
+			goto out_kfree_skb;
+
+		/* If packet is not checksummed and device does not
+		 * support checksumming for this protocol, complete
+		 * checksumming here.
+		 */
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			if (skb->encapsulation)
+				skb_set_inner_transport_header(skb,
+							       skb_checksum_start_offset(skb));
+			else
+				skb_set_transport_header(skb,
+							 skb_checksum_start_offset(skb));
+			if (!(features & NETIF_F_ALL_CSUM) &&
+			    skb_checksum_help(skb))
+				goto out_kfree_skb;
 		}
-		txq_trans_update(txq);
-		if (unlikely(netif_xmit_stopped(txq) && skb->next))
-			return NETDEV_TX_BUSY;
-	} while (skb->next);
-
-out_kfree_gso_skb:
-	if (likely(skb->next == NULL)) {
-		skb->destructor = DEV_GSO_CB(skb)->destructor;
-		consume_skb(skb);
-		return rc;
 	}
+
+	return skb;
+
 out_kfree_skb:
 	kfree_skb(skb);
-out:
-	return rc;
+out_null:
+	return NULL;
+}
+
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev)
+{
+	struct sk_buff *next, *head = NULL, *tail;
+
+	for (; skb != NULL; skb = next) {
+		next = skb->next;
+		skb->next = NULL;
+
+		/* in case skb wont be segmented, point to itself */
+		skb->prev = skb;
+
+		skb = validate_xmit_skb(skb, dev);
+		if (!skb)
+			continue;
+
+		if (!head)
+			head = skb;
+		else
+			tail->next = skb;
+		/* If skb was segmented, skb->prev points to
+		 * the last segment. If not, it still contains skb.
+		 */
+		tail = skb->prev;
+	}
+	return head;
 }
-EXPORT_SYMBOL_GPL(dev_hard_start_xmit);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
@@ -2780,12 +2805,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		 * waiting to be sent out; and the qdisc is not running -
 		 * xmit the skb directly.
 		 */
-		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
-			skb_dst_force(skb);
 
 		qdisc_bstats_update(q, skb);
 
-		if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
+		if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
 				contended = false;
@@ -2796,7 +2819,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
-		skb_dst_force(skb);
 		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
@@ -2893,6 +2915,14 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 
 	skb_update_prio(skb);
 
+	/* If device/qdisc don't need skb->dst, release it right now while
+	 * its hot in this cpu cache.
+	 */
+	if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+		skb_dst_drop(skb);
+	else
+		skb_dst_force(skb);
+
 	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);
 
@@ -2925,11 +2955,15 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
 				goto recursion_alert;
 
+			skb = validate_xmit_skb(skb, dev);
+			if (!skb)
+				goto drop;
+
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
-				rc = dev_hard_start_xmit(skb, dev, txq);
+				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
 				__this_cpu_dec(xmit_recursion);
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
@@ -2950,10 +2984,11 @@ recursion_alert:
 	}
 
 	rc = -ENETDOWN;
+drop:
 	rcu_read_unlock_bh();
 
 	atomic_long_inc(&dev->tx_dropped);
-	kfree_skb(skb);
+	kfree_skb_list(skb);
 	return rc;
 out:
 	rcu_read_unlock_bh();
@@ -3130,8 +3165,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	if (map) {
-		tcpu = map->cpus[((u64) hash * map->len) >> 32];
-
+		tcpu = map->cpus[reciprocal_scale(hash, map->len)];
 		if (cpu_online(tcpu)) {
 			cpu = tcpu;
 			goto done;
@@ -3201,7 +3235,7 @@ static void rps_trigger_softirq(void *data)
 static int rps_ipi_queued(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	struct softnet_data *mysd = &__get_cpu_var(softnet_data);
+	struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
 	if (sd != mysd) {
 		sd->rps_ipi_next = mysd->rps_ipi_list;
@@ -3228,7 +3262,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	if (qlen < (netdev_max_backlog >> 1))
 		return false;
 
-	sd = &__get_cpu_var(softnet_data);
+	sd = this_cpu_ptr(&softnet_data);
 
 	rcu_read_lock();
 	fl = rcu_dereference(sd->flow_limit);
@@ -3272,7 +3306,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	rps_lock(sd);
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
-		if (skb_queue_len(&sd->input_pkt_queue)) {
+		if (qlen) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
 			input_queue_tail_incr_save(sd, qtail);
@@ -3375,7 +3409,7 @@ EXPORT_SYMBOL(netif_rx_ni);
 
 static void net_tx_action(struct softirq_action *h)
 {
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 
 	if (sd->completion_queue) {
 		struct sk_buff *clist;
@@ -3467,7 +3501,7 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
 	skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
 	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
 
-	q = rxq->qdisc;
+	q = rcu_dereference(rxq->qdisc);
 	if (q != &noop_qdisc) {
 		spin_lock(qdisc_lock(q));
 		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
@@ -3484,7 +3518,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 {
 	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
 
-	if (!rxq || rxq->qdisc == &noop_qdisc)
+	if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
 		goto out;
 
 	if (*pt_prev) {
@@ -3800,7 +3834,7 @@ EXPORT_SYMBOL(netif_receive_skb);
 static void flush_backlog(void *arg)
 {
 	struct net_device *dev = arg;
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	struct sk_buff *skb, *tmp;
 
 	rps_lock(sd);
@@ -3965,11 +3999,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
 
-	if (skb_is_gso(skb) || skb_has_frag_list(skb))
+	if (skb_is_gso(skb) || skb_has_frag_list(skb) || skb->csum_bad)
 		goto normal;
 
 	gro_list_prepare(napi, skb);
-	NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
@@ -3983,6 +4016,22 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->udp_mark = 0;
 
+		/* Setup for GRO checksum validation */
+		switch (skb->ip_summed) {
+		case CHECKSUM_COMPLETE:
+			NAPI_GRO_CB(skb)->csum = skb->csum;
+			NAPI_GRO_CB(skb)->csum_valid = 1;
+			NAPI_GRO_CB(skb)->csum_cnt = 0;
+			break;
+		case CHECKSUM_UNNECESSARY:
+			NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1;
+			NAPI_GRO_CB(skb)->csum_valid = 0;
+			break;
+		default:
+			NAPI_GRO_CB(skb)->csum_cnt = 0;
+			NAPI_GRO_CB(skb)->csum_valid = 0;
+		}
+
 		pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
 		break;
 	}
@@ -4110,6 +4159,10 @@ EXPORT_SYMBOL(napi_gro_receive);
 
 static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 {
+	if (unlikely(skb->pfmemalloc)) {
+		consume_skb(skb);
+		return;
+	}
 	__skb_pull(skb, skb_headlen(skb));
 	/* restore the reserve we had after netdev_alloc_skb_ip_align() */
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
@@ -4128,7 +4181,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 	struct sk_buff *skb = napi->skb;
 
 	if (!skb) {
-		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
+		skb = napi_alloc_skb(napi, GRO_MAX_HEAD);
 		napi->skb = skb;
 	}
 	return skb;
@@ -4212,6 +4265,31 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_gro_frags);
 
+/* Compute the checksum from gro_offset and return the folded value
+ * after adding in any pseudo checksum.
+ */
+__sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
+{
+	__wsum wsum;
+	__sum16 sum;
+
+	wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0);
+
+	/* NAPI_GRO_CB(skb)->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	NAPI_GRO_CB(skb)->csum = wsum;
+	NAPI_GRO_CB(skb)->csum_valid = 1;
+
+	return sum;
+}
+EXPORT_SYMBOL(__skb_gro_checksum_complete);
+
 /*
  * net_rps_action_and_irq_enable sends any pending IPI's for rps.
  * Note: called with local irq disabled, but exits with local irq enabled.
@@ -4240,20 +4318,28 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
 		local_irq_enable();
 }
 
+static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+	return sd->rps_ipi_list != NULL;
+#else
+	return false;
+#endif
+}
+
 static int process_backlog(struct napi_struct *napi, int quota)
 {
 	int work = 0;
 	struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
 
-#ifdef CONFIG_RPS
 	/* Check if we have pending ipi, its better to send them now,
 	 * not waiting net_rx_action() end.
 	 */
-	if (sd->rps_ipi_list) {
+	if (sd_has_rps_ipi_waiting(sd)) {
 		local_irq_disable();
 		net_rps_action_and_irq_enable(sd);
 	}
-#endif
+
 	napi->weight = weight_p;
 	local_irq_disable();
 	while (1) {
@@ -4280,7 +4366,6 @@ static int process_backlog(struct napi_struct *napi, int quota)
 			 * We can use a plain write instead of clear_bit(),
 			 * and we dont need an smp_mb() memory barrier.
 			 */
-			list_del(&napi->poll_list);
 			napi->state = 0;
 			rps_unlock(sd);
 
@@ -4300,30 +4385,42 @@ static int process_backlog(struct napi_struct *napi, int quota)
  * __napi_schedule - schedule for receive
  * @n: entry to schedule
  *
- * The entry's receive function will be scheduled to run
+ * The entry's receive function will be scheduled to run.
+ * Consider using __napi_schedule_irqoff() if hard irqs are masked.
  */
 void __napi_schedule(struct napi_struct *n)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	____napi_schedule(&__get_cpu_var(softnet_data), n);
+	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__napi_schedule);
 
+/**
+ * __napi_schedule_irqoff - schedule for receive
+ * @n: entry to schedule
+ *
+ * Variant of __napi_schedule() assuming hard irqs are masked
+ */
+void __napi_schedule_irqoff(struct napi_struct *n)
+{
+	____napi_schedule(this_cpu_ptr(&softnet_data), n);
+}
+EXPORT_SYMBOL(__napi_schedule_irqoff);
+
 void __napi_complete(struct napi_struct *n)
 {
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
-	BUG_ON(n->gro_list);
 
-	list_del(&n->poll_list);
+	list_del_init(&n->poll_list);
 	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
 }
 EXPORT_SYMBOL(__napi_complete);
 
-void napi_complete(struct napi_struct *n)
+void napi_complete_done(struct napi_struct *n, int work_done)
 {
 	unsigned long flags;
 
@@ -4334,12 +4431,28 @@ void napi_complete(struct napi_struct *n)
 	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
 		return;
 
-	napi_gro_flush(n, false);
-	local_irq_save(flags);
-	__napi_complete(n);
-	local_irq_restore(flags);
+	if (n->gro_list) {
+		unsigned long timeout = 0;
+
+		if (work_done)
+			timeout = n->dev->gro_flush_timeout;
+
+		if (timeout)
+			hrtimer_start(&n->timer, ns_to_ktime(timeout),
+				      HRTIMER_MODE_REL_PINNED);
+		else
+			napi_gro_flush(n, false);
+	}
+	if (likely(list_empty(&n->poll_list))) {
+		WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
+	} else {
+		/* If n->poll_list is not empty, we need to mask irqs */
+		local_irq_save(flags);
+		__napi_complete(n);
+		local_irq_restore(flags);
+	}
 }
-EXPORT_SYMBOL(napi_complete);
+EXPORT_SYMBOL(napi_complete_done);
 
 /* must be called under rcu_read_lock(), as we dont take a reference */
 struct napi_struct *napi_by_id(unsigned int napi_id)
@@ -4393,10 +4506,23 @@ void napi_hash_del(struct napi_struct *napi)
 }
 EXPORT_SYMBOL_GPL(napi_hash_del);
 
+static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
+{
+	struct napi_struct *napi;
+
+	napi = container_of(timer, struct napi_struct, timer);
+	if (napi->gro_list)
+		napi_schedule(napi);
+
+	return HRTIMER_NORESTART;
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
 	INIT_LIST_HEAD(&napi->poll_list);
+	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
 	napi->gro_list = NULL;
 	napi->skb = NULL;
@@ -4415,6 +4541,20 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 }
 EXPORT_SYMBOL(netif_napi_add);
 
+void napi_disable(struct napi_struct *n)
+{
+	might_sleep();
+	set_bit(NAPI_STATE_DISABLE, &n->state);
+
+	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
+		msleep(1);
+
+	hrtimer_cancel(&n->timer);
+
+	clear_bit(NAPI_STATE_DISABLE, &n->state);
+}
+EXPORT_SYMBOL(napi_disable);
+
 void netif_napi_del(struct napi_struct *napi)
 {
 	list_del_init(&napi->dev_list);
@@ -4426,99 +4566,112 @@ void netif_napi_del(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(netif_napi_del);
 
-static void net_rx_action(struct softirq_action *h)
+static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 {
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
-	unsigned long time_limit = jiffies + 2;
-	int budget = netdev_budget;
 	void *have;
+	int work, weight;
 
-	local_irq_disable();
+	list_del_init(&n->poll_list);
 
-	while (!list_empty(&sd->poll_list)) {
-		struct napi_struct *n;
-		int work, weight;
+	have = netpoll_poll_lock(n);
 
-		/* If softirq window is exhuasted then punt.
-		 * Allow this to run for 2 jiffies since which will allow
-		 * an average latency of 1.5/HZ.
-		 */
-		if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit)))
-			goto softnet_break;
+	weight = n->weight;
 
-		local_irq_enable();
+	/* This NAPI_STATE_SCHED test is for avoiding a race
+	 * with netpoll's poll_napi().  Only the entity which
+	 * obtains the lock and sees NAPI_STATE_SCHED set will
+	 * actually make the ->poll() call.  Therefore we avoid
+	 * accidentally calling ->poll() when NAPI is not scheduled.
+	 */
+	work = 0;
+	if (test_bit(NAPI_STATE_SCHED, &n->state)) {
+		work = n->poll(n, weight);
+		trace_napi_poll(n);
+	}
 
-		/* Even though interrupts have been re-enabled, this
-		 * access is safe because interrupts can only add new
-		 * entries to the tail of this list, and only ->poll()
-		 * calls can remove this head entry from the list.
-		 */
-		n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
+	WARN_ON_ONCE(work > weight);
 
-		have = netpoll_poll_lock(n);
+	if (likely(work < weight))
+		goto out_unlock;
 
-		weight = n->weight;
+	/* Drivers must not modify the NAPI state if they
+	 * consume the entire weight.  In such cases this code
+	 * still "owns" the NAPI instance and therefore can
+	 * move the instance around on the list at-will.
+	 */
+	if (unlikely(napi_disable_pending(n))) {
+		napi_complete(n);
+		goto out_unlock;
+	}
 
-		/* This NAPI_STATE_SCHED test is for avoiding a race
-		 * with netpoll's poll_napi().  Only the entity which
-		 * obtains the lock and sees NAPI_STATE_SCHED set will
-		 * actually make the ->poll() call.  Therefore we avoid
-		 * accidentally calling ->poll() when NAPI is not scheduled.
+	if (n->gro_list) {
+		/* flush too old packets
+		 * If HZ < 1000, flush all packets.
 		 */
-		work = 0;
-		if (test_bit(NAPI_STATE_SCHED, &n->state)) {
-			work = n->poll(n, weight);
-			trace_napi_poll(n);
-		}
+		napi_gro_flush(n, HZ >= 1000);
+	}
 
-		WARN_ON_ONCE(work > weight);
+	/* Some drivers may have called napi_schedule
+	 * prior to exhausting their budget.
+	 */
+	if (unlikely(!list_empty(&n->poll_list))) {
+		pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
+			     n->dev ? n->dev->name : "backlog");
+		goto out_unlock;
+	}
 
-		budget -= work;
+	list_add_tail(&n->poll_list, repoll);
 
-		local_irq_disable();
+out_unlock:
+	netpoll_poll_unlock(have);
 
-		/* Drivers must not modify the NAPI state if they
-		 * consume the entire weight.  In such cases this code
-		 * still "owns" the NAPI instance and therefore can
-		 * move the instance around on the list at-will.
-		 */
-		if (unlikely(work == weight)) {
-			if (unlikely(napi_disable_pending(n))) {
-				local_irq_enable();
-				napi_complete(n);
-				local_irq_disable();
-			} else {
-				if (n->gro_list) {
-					/* flush too old packets
-					 * If HZ < 1000, flush all packets.
-					 */
-					local_irq_enable();
-					napi_gro_flush(n, HZ >= 1000);
-					local_irq_disable();
-				}
-				list_move_tail(&n->poll_list, &sd->poll_list);
-			}
+	return work;
+}
+
+static void net_rx_action(struct softirq_action *h)
+{
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
+	unsigned long time_limit = jiffies + 2;
+	int budget = netdev_budget;
+	LIST_HEAD(list);
+	LIST_HEAD(repoll);
+
+	local_irq_disable();
+	list_splice_init(&sd->poll_list, &list);
+	local_irq_enable();
+
+	for (;;) {
+		struct napi_struct *n;
+
+		if (list_empty(&list)) {
+			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
+				return;
+			break;
 		}
 
-		netpoll_poll_unlock(have);
+		n = list_first_entry(&list, struct napi_struct, poll_list);
+		budget -= napi_poll(n, &repoll);
+
+		/* If softirq window is exhausted then punt.
+		 * Allow this to run for 2 jiffies since which will allow
+		 * an average latency of 1.5/HZ.
+		 */
+		if (unlikely(budget <= 0 ||
+			     time_after_eq(jiffies, time_limit))) {
+			sd->time_squeeze++;
+			break;
+		}
 	}
-out:
-	net_rps_action_and_irq_enable(sd);
 
-#ifdef CONFIG_NET_DMA
-	/*
-	 * There may not be any more sk_buffs coming right now, so push
-	 * any pending DMA copies to hardware
-	 */
-	dma_issue_pending_all();
-#endif
+	local_irq_disable();
 
-	return;
+	list_splice_tail_init(&sd->poll_list, &list);
+	list_splice_tail(&repoll, &list);
+	list_splice(&list, &sd->poll_list);
+	if (!list_empty(&sd->poll_list))
+		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
 
-softnet_break:
-	sd->time_squeeze++;
-	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
-	goto out;
+	net_rps_action_and_irq_enable(sd);
 }
 
 struct netdev_adjacent {
@@ -5718,7 +5871,7 @@ EXPORT_SYMBOL(dev_change_carrier);
  *	Get device physical port ID
  */
 int dev_get_phys_port_id(struct net_device *dev,
-			 struct netdev_phys_port_id *ppid)
+			 struct netdev_phys_item_id *ppid)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
@@ -5797,6 +5950,8 @@ static void rollback_registered_many(struct list_head *head)
 	synchronize_net();
 
 	list_for_each_entry(dev, head, unreg_list) {
+		struct sk_buff *skb = NULL;
+
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
 
@@ -5806,6 +5961,11 @@ static void rollback_registered_many(struct list_head *head)
 		*/
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
+		if (!dev->rtnl_link_ops ||
+		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+						     GFP_KERNEL);
+
 		/*
 		 *	Flush the unicast and multicast chains
 		 */
@@ -5815,9 +5975,8 @@ static void rollback_registered_many(struct list_head *head)
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+		if (skb)
+			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL);
 
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
@@ -6589,6 +6748,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
+	dev->gso_min_segs = 0;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
@@ -6598,7 +6758,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->adj_list.lower);
 	INIT_LIST_HEAD(&dev->all_adj_list.upper);
 	INIT_LIST_HEAD(&dev->all_adj_list.lower);
-	dev->priv_flags = IFF_XMIT_DST_RELEASE;
+	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
 	dev->num_tx_queues = txqs;
@@ -7020,53 +7180,45 @@ const char *netdev_drivername(const struct net_device *dev)
 	return empty;
 }
 
-static int __netdev_printk(const char *level, const struct net_device *dev,
-			   struct va_format *vaf)
+static void __netdev_printk(const char *level, const struct net_device *dev,
+			    struct va_format *vaf)
 {
-	int r;
-
 	if (dev && dev->dev.parent) {
-		r = dev_printk_emit(level[1] - '0',
-				    dev->dev.parent,
-				    "%s %s %s%s: %pV",
-				    dev_driver_string(dev->dev.parent),
-				    dev_name(dev->dev.parent),
-				    netdev_name(dev), netdev_reg_state(dev),
-				    vaf);
+		dev_printk_emit(level[1] - '0',
+				dev->dev.parent,
+				"%s %s %s%s: %pV",
+				dev_driver_string(dev->dev.parent),
+				dev_name(dev->dev.parent),
+				netdev_name(dev), netdev_reg_state(dev),
+				vaf);
 	} else if (dev) {
-		r = printk("%s%s%s: %pV", level, netdev_name(dev),
-			   netdev_reg_state(dev), vaf);
+		printk("%s%s%s: %pV",
+		       level, netdev_name(dev), netdev_reg_state(dev), vaf);
 	} else {
-		r = printk("%s(NULL net_device): %pV", level, vaf);
+		printk("%s(NULL net_device): %pV", level, vaf);
 	}
-
-	return r;
 }
 
-int netdev_printk(const char *level, const struct net_device *dev,
-		  const char *format, ...)
+void netdev_printk(const char *level, const struct net_device *dev,
+		   const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, format);
 
 	vaf.fmt = format;
 	vaf.va = &args;
 
-	r = __netdev_printk(level, dev, &vaf);
+	__netdev_printk(level, dev, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(netdev_printk);
 
 #define define_netdev_printk_level(func, level)			\
-int func(const struct net_device *dev, const char *fmt, ...)	\
+void func(const struct net_device *dev, const char *fmt, ...)	\
 {								\
-	int r;							\
 	struct va_format vaf;					\
 	va_list args;						\
 								\
@@ -7075,11 +7227,9 @@ int func(const struct net_device *dev, const char *fmt, ...)	\
 	vaf.fmt = fmt;						\
 	vaf.va = &args;						\
 								\
-	r = __netdev_printk(level, dev, &vaf);			\
+	__netdev_printk(level, dev, &vaf);			\
 								\
 	va_end(args);						\
-								\
-	return r;						\
 }								\
 EXPORT_SYMBOL(func);
 
@@ -7141,11 +7291,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
 	 */
 	struct net *net;
 	bool unregistering;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&netdev_unregistering_wq, &wait);
 	for (;;) {
-		prepare_to_wait(&netdev_unregistering_wq, &wait,
-				TASK_UNINTERRUPTIBLE);
 		unregistering = false;
 		rtnl_lock();
 		list_for_each_entry(net, net_list, exit_list) {
@@ -7157,9 +7306,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
 		if (!unregistering)
 			break;
 		__rtnl_unlock();
-		schedule();
+
+		wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	finish_wait(&netdev_unregistering_wq, &wait);
+	remove_wait_queue(&netdev_unregistering_wq, &wait);
 }
 
 static void __net_exit default_device_exit_batch(struct list_head *net_list)