1 files changed, 76 insertions, 61 deletions

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 5d7e23f4cc0e..852e603c1755 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -24,9 +24,11 @@
 #include <linux/if_vlan.h>
 #include <linux/skb_array.h>
 #include <linux/if_macvlan.h>
+#include <linux/bpf.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
+#include <net/hotdata.h>
 #include <trace/events/qdisc.h>
 #include <trace/events/net.h>
 #include <net/xfrm.h>
@@ -178,9 +180,10 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 static void try_bulk_dequeue_skb(struct Qdisc *q,
 				 struct sk_buff *skb,
 				 const struct netdev_queue *txq,
-				 int *packets)
+				 int *packets, int budget)
 {
 	int bytelimit = qdisc_avail_bulklimit(txq) - skb->len;
+	int cnt = 0;
 
 	while (bytelimit > 0) {
 		struct sk_buff *nskb = q->dequeue(q);
@@ -191,8 +194,10 @@ static void try_bulk_dequeue_skb(struct Qdisc *q,
 		bytelimit -= nskb->len; /* covers GSO len */
 		skb->next = nskb;
 		skb = nskb;
-		(*packets)++; /* GSO counts as one pkt */
+		if (++cnt >= budget)
+			break;
 	}
+	(*packets) += cnt;
 	skb_mark_not_on_list(skb);
 }
 
@@ -226,7 +231,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q,
  * A requeued skb (via q->gso_skb) can also be a SKB list.
  */
 static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
-				   int *packets)
+				   int *packets, int budget)
 {
 	const struct netdev_queue *txq = q->dev_queue;
 	struct sk_buff *skb = NULL;
@@ -293,7 +298,7 @@ validate:
 	if (skb) {
 bulk:
 		if (qdisc_may_bulk(q))
-			try_bulk_dequeue_skb(q, skb, txq, packets);
+			try_bulk_dequeue_skb(q, skb, txq, packets, budget);
 		else
 			try_bulk_dequeue_skb_slow(q, skb, packets);
 	}
@@ -385,7 +390,7 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
  *				>0 - queue is not empty.
  *
  */
-static inline bool qdisc_restart(struct Qdisc *q, int *packets)
+static inline bool qdisc_restart(struct Qdisc *q, int *packets, int budget)
 {
 	spinlock_t *root_lock = NULL;
 	struct netdev_queue *txq;
@@ -394,7 +399,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 	bool validate;
 
 	/* Dequeue packet */
-	skb = dequeue_skb(q, &validate, packets);
+	skb = dequeue_skb(q, &validate, packets, budget);
 	if (unlikely(!skb))
 		return false;
 
@@ -409,10 +414,10 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 
 void __qdisc_run(struct Qdisc *q)
 {
-	int quota = READ_ONCE(dev_tx_weight);
+	int quota = READ_ONCE(net_hotdata.dev_tx_weight);
 	int packets;
 
-	while (qdisc_restart(q, &packets)) {
+	while (qdisc_restart(q, &packets, quota)) {
 		quota -= packets;
 		if (quota <= 0) {
 			if (q->flags & TCQ_F_NOLOCK)
@@ -494,7 +499,7 @@ EXPORT_SYMBOL(netif_tx_unlock);
 
 static void dev_watchdog(struct timer_list *t)
 {
-	struct net_device *dev = from_timer(dev, t, watchdog_timer);
+	struct net_device *dev = timer_container_of(dev, t, watchdog_timer);
 	bool release = true;
 
 	spin_lock(&dev->tx_global_lock);
@@ -505,31 +510,41 @@ static void dev_watchdog(struct timer_list *t)
 			unsigned int timedout_ms = 0;
 			unsigned int i;
 			unsigned long trans_start;
+			unsigned long oldest_start = jiffies;
 
 			for (i = 0; i < dev->num_tx_queues; i++) {
 				struct netdev_queue *txq;
 
 				txq = netdev_get_tx_queue(dev, i);
+				if (!netif_xmit_stopped(txq))
+					continue;
+
+				/* Paired with WRITE_ONCE() + smp_mb...() in
+				 * netdev_tx_sent_queue() and netif_tx_stop_queue().
+				 */
+				smp_mb();
 				trans_start = READ_ONCE(txq->trans_start);
-				if (netif_xmit_stopped(txq) &&
-				    time_after(jiffies, (trans_start +
-							 dev->watchdog_timeo))) {
+
+				if (time_after(jiffies, trans_start + dev->watchdog_timeo)) {
 					timedout_ms = jiffies_to_msecs(jiffies - trans_start);
 					atomic_long_inc(&txq->trans_timeout);
 					break;
 				}
+				if (time_after(oldest_start, trans_start))
+					oldest_start = trans_start;
 			}
 
 			if (unlikely(timedout_ms)) {
 				trace_net_dev_xmit_timeout(dev, i);
-				WARN_ONCE(1, "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out %u ms\n",
-					  dev->name, netdev_drivername(dev), i, timedout_ms);
+				netdev_crit(dev, "NETDEV WATCHDOG: CPU: %d: transmit queue %u timed out %u ms\n",
+					    raw_smp_processor_id(),
+					    i, timedout_ms);
 				netif_freeze_queues(dev);
 				dev->netdev_ops->ndo_tx_timeout(dev, i);
 				netif_unfreeze_queues(dev);
 			}
 			if (!mod_timer(&dev->watchdog_timer,
-				       round_jiffies(jiffies +
+				       round_jiffies(oldest_start +
 						     dev->watchdog_timeo)))
 				release = false;
 		}
@@ -540,28 +555,23 @@ static void dev_watchdog(struct timer_list *t)
 		netdev_put(dev, &dev->watchdog_dev_tracker);
 }
 
-void __netdev_watchdog_up(struct net_device *dev)
-{
-	if (dev->netdev_ops->ndo_tx_timeout) {
-		if (dev->watchdog_timeo <= 0)
-			dev->watchdog_timeo = 5*HZ;
-		if (!mod_timer(&dev->watchdog_timer,
-			       round_jiffies(jiffies + dev->watchdog_timeo)))
-			netdev_hold(dev, &dev->watchdog_dev_tracker,
-				    GFP_ATOMIC);
-	}
-}
-EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
-
-static void dev_watchdog_up(struct net_device *dev)
+void netdev_watchdog_up(struct net_device *dev)
 {
-	__netdev_watchdog_up(dev);
+	if (!dev->netdev_ops->ndo_tx_timeout)
+		return;
+	if (dev->watchdog_timeo <= 0)
+		dev->watchdog_timeo = 5*HZ;
+	if (!mod_timer(&dev->watchdog_timer,
+		       round_jiffies(jiffies + dev->watchdog_timeo)))
+		netdev_hold(dev, &dev->watchdog_dev_tracker,
+			    GFP_ATOMIC);
 }
+EXPORT_SYMBOL_GPL(netdev_watchdog_up);
 
-static void dev_watchdog_down(struct net_device *dev)
+static void netdev_watchdog_down(struct net_device *dev)
 {
 	netif_tx_lock_bh(dev);
-	if (del_timer(&dev->watchdog_timer))
+	if (timer_delete(&dev->watchdog_timer))
 		netdev_put(dev, &dev->watchdog_dev_tracker);
 	netif_tx_unlock_bh(dev);
 }
@@ -580,7 +590,7 @@ void netif_carrier_on(struct net_device *dev)
 		atomic_inc(&dev->carrier_up_count);
 		linkwatch_fire_event(dev);
 		if (netif_running(dev))
-			__netdev_watchdog_up(dev);
+			netdev_watchdog_up(dev);
 	}
 }
 EXPORT_SYMBOL(netif_carrier_on);
@@ -628,6 +638,7 @@ EXPORT_SYMBOL_GPL(netif_carrier_event);
 static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 			struct sk_buff **to_free)
 {
+	dev_core_stats_tx_dropped_inc(skb->dev);
 	__qdisc_drop(skb, to_free);
 	return NET_XMIT_CN;
 }
@@ -658,7 +669,6 @@ struct Qdisc noop_qdisc = {
 	.ops		=	&noop_qdisc_ops,
 	.q.lock		=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
 	.dev_queue	=	&noop_netdev_queue,
-	.busylock	=	__SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
 	.gso_skb = {
 		.next = (struct sk_buff *)&noop_qdisc.gso_skb,
 		.prev = (struct sk_buff *)&noop_qdisc.gso_skb,
@@ -694,9 +704,10 @@ struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
 	.owner		=	THIS_MODULE,
 };
 
-static const u8 prio2band[TC_PRIO_MAX + 1] = {
-	1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
+const u8 sch_default_prio2band[TC_PRIO_MAX + 1] = {
+	1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1
 };
+EXPORT_SYMBOL(sch_default_prio2band);
 
 /* 3-band FIFO queue: old style, but should be a bit faster than
    generic prio+fifo combination.
@@ -721,7 +732,7 @@ static inline struct skb_array *band2list(struct pfifo_fast_priv *priv,
 static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 			      struct sk_buff **to_free)
 {
-	int band = prio2band[skb->priority & TC_PRIO_MAX];
+	int band = sch_default_prio2band[skb->priority & TC_PRIO_MAX];
 	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 	struct skb_array *q = band2list(priv, band);
 	unsigned int pkt_len = qdisc_pkt_len(skb);
@@ -730,6 +741,8 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 	err = skb_array_produce(q, skb);
 
 	if (unlikely(err)) {
+		tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_OVERLIMIT);
+
 		if (qdisc_is_percpu_stats(qdisc))
 			return qdisc_drop_cpu(skb, qdisc, to_free);
 		else
@@ -830,7 +843,7 @@ static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb)
 {
 	struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
 
-	memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
+	memcpy(&opt.priomap, sch_default_prio2band, TC_PRIO_MAX + 1);
 	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
 		goto nla_put_failure;
 	return skb->len;
@@ -897,8 +910,8 @@ static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch,
 		bands[prio] = q;
 	}
 
-	return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len,
-					 GFP_KERNEL);
+	return skb_array_resize_multiple_bh(bands, PFIFO_FAST_BANDS, new_len,
+					    GFP_KERNEL);
 }
 
 struct Qdisc_ops pfifo_fast_ops __read_mostly = {
@@ -942,7 +955,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	__skb_queue_head_init(&sch->gso_skb);
 	__skb_queue_head_init(&sch->skb_bad_txq);
 	gnet_stats_basic_sync_init(&sch->bstats);
+	lockdep_register_key(&sch->root_lock_key);
 	spin_lock_init(&sch->q.lock);
+	lockdep_set_class(&sch->q.lock, &sch->root_lock_key);
 
 	if (ops->static_flags & TCQ_F_CPUSTATS) {
 		sch->cpu_bstats =
@@ -957,10 +972,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 		}
 	}
 
-	spin_lock_init(&sch->busylock);
-	lockdep_set_class(&sch->busylock,
-			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
-
 	/* seqlock has the same scope of busylock, for NOLOCK qdisc */
 	spin_lock_init(&sch->seqlock);
 	lockdep_set_class(&sch->seqlock,
@@ -976,6 +987,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 
 	return sch;
 errout1:
+	lockdep_unregister_key(&sch->root_lock_key);
 	kfree(sch);
 errout:
 	return ERR_PTR(err);
@@ -988,14 +1000,14 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
 {
 	struct Qdisc *sch;
 
-	if (!try_module_get(ops->owner)) {
+	if (!bpf_try_module_get(ops, ops->owner)) {
 		NL_SET_ERR_MSG(extack, "Failed to increase module reference counter");
 		return NULL;
 	}
 
 	sch = qdisc_alloc(dev_queue, ops, extack);
 	if (IS_ERR(sch)) {
-		module_put(ops->owner);
+		bpf_module_put(ops, ops->owner);
 		return NULL;
 	}
 	sch->parent = parentid;
@@ -1049,6 +1061,7 @@ static void qdisc_free_cb(struct rcu_head *head)
 static void __qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
+	struct net_device *dev = qdisc_dev(qdisc);
 
 #ifdef CONFIG_NET_SCHED
 	qdisc_hash_del(qdisc);
@@ -1059,11 +1072,13 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 
 	qdisc_reset(qdisc);
 
+
 	if (ops->destroy)
 		ops->destroy(qdisc);
 
-	module_put(ops->owner);
-	netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker);
+	lockdep_unregister_key(&qdisc->root_lock_key);
+	bpf_module_put(ops, ops->owner);
+	netdev_put(dev, &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);
 
@@ -1246,7 +1261,7 @@ void dev_activate(struct net_device *dev)
 
 	if (need_watchdog) {
 		netif_trans_update(dev);
-		dev_watchdog_up(dev);
+		netdev_watchdog_up(dev);
 	}
 }
 EXPORT_SYMBOL(dev_activate);
@@ -1261,15 +1276,17 @@ static void qdisc_deactivate(struct Qdisc *qdisc)
 
 static void dev_deactivate_queue(struct net_device *dev,
 				 struct netdev_queue *dev_queue,
-				 void *_qdisc_default)
+				 void *_sync_needed)
 {
-	struct Qdisc *qdisc_default = _qdisc_default;
+	bool *sync_needed = _sync_needed;
 	struct Qdisc *qdisc;
 
 	qdisc = rtnl_dereference(dev_queue->qdisc);
 	if (qdisc) {
+		if (qdisc->enqueue)
+			*sync_needed = true;
 		qdisc_deactivate(qdisc);
-		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
+		rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc);
 	}
 }
 
@@ -1336,24 +1353,22 @@ static bool some_qdisc_is_busy(struct net_device *dev)
  */
 void dev_deactivate_many(struct list_head *head)
 {
+	bool sync_needed = false;
 	struct net_device *dev;
 
 	list_for_each_entry(dev, head, close_list) {
 		netdev_for_each_tx_queue(dev, dev_deactivate_queue,
-					 &noop_qdisc);
+					 &sync_needed);
 		if (dev_ingress_queue(dev))
 			dev_deactivate_queue(dev, dev_ingress_queue(dev),
-					     &noop_qdisc);
+					     &sync_needed);
 
-		dev_watchdog_down(dev);
+		netdev_watchdog_down(dev);
 	}
 
-	/* Wait for outstanding qdisc-less dev_queue_xmit calls or
-	 * outstanding qdisc enqueuing calls.
-	 * This is avoided if all devices are in dismantle phase :
-	 * Caller will call synchronize_net() for us
-	 */
-	synchronize_net();
+	/* Wait for outstanding qdisc enqueuing calls. */
+	if (sync_needed)
+		synchronize_net();
 
 	list_for_each_entry(dev, head, close_list) {
 		netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);