1 files changed, 131 insertions, 24 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index b91658e8aedb..3f525278a871 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -159,6 +159,7 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/types.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/rps.h>
 #include <linux/phy_link_topology.h>
 
@@ -1007,7 +1008,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id)
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	if (napi_id < MIN_NAPI_ID)
+	if (!napi_id_valid(napi_id))
 		return NULL;
 
 	napi = napi_by_id(napi_id);
@@ -1121,6 +1122,12 @@ out:
 	return ret;
 }
 
+static bool dev_addr_cmp(struct net_device *dev, unsigned short type,
+			 const char *ha)
+{
+	return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len);
+}
+
 /**
  *	dev_getbyhwaddr_rcu - find a device by its hardware address
  *	@net: the applicable net namespace
@@ -1129,7 +1136,7 @@ out:
  *
  *	Search for an interface by MAC address. Returns NULL if the device
  *	is not found or a pointer to the device.
- *	The caller must hold RCU or RTNL.
+ *	The caller must hold RCU.
  *	The returned device has not had its ref count increased
  *	and the caller must therefore be careful about locking
  *
@@ -1141,14 +1148,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 	struct net_device *dev;
 
 	for_each_netdev_rcu(net, dev)
-		if (dev->type == type &&
-		    !memcmp(dev->dev_addr, ha, dev->addr_len))
+		if (dev_addr_cmp(dev, type, ha))
 			return dev;
 
 	return NULL;
 }
 EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
 
+/**
+ * dev_getbyhwaddr() - find a device by its hardware address
+ * @net: the applicable net namespace
+ * @type: media type of device
+ * @ha: hardware address
+ *
+ * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold
+ * rtnl_lock.
+ *
+ * Context: rtnl_lock() must be held.
+ * Return: pointer to the net_device, or NULL if not found
+ */
+struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
+				   const char *ha)
+{
+	struct net_device *dev;
+
+	ASSERT_RTNL();
+	for_each_netdev(net, dev)
+		if (dev_addr_cmp(dev, type, ha))
+			return dev;
+
+	return NULL;
+}
+EXPORT_SYMBOL(dev_getbyhwaddr);
+
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 {
 	struct net_device *dev, *ret = NULL;
@@ -2070,6 +2102,42 @@ static void __move_netdevice_notifier_net(struct net *src_net,
 	__register_netdevice_notifier_net(dst_net, nb, true);
 }
 
+static void rtnl_net_dev_lock(struct net_device *dev)
+{
+	bool again;
+
+	do {
+		struct net *net;
+
+		again = false;
+
+		/* netns might be being dismantled. */
+		rcu_read_lock();
+		net = dev_net_rcu(dev);
+		net_passive_inc(net);
+		rcu_read_unlock();
+
+		rtnl_net_lock(net);
+
+#ifdef CONFIG_NET_NS
+		/* dev might have been moved to another netns. */
+		if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) {
+			rtnl_net_unlock(net);
+			net_passive_dec(net);
+			again = true;
+		}
+#endif
+	} while (again);
+}
+
+static void rtnl_net_dev_unlock(struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+
+	rtnl_net_unlock(net);
+	net_passive_dec(net);
+}
+
 int register_netdevice_notifier_dev_net(struct net_device *dev,
 					struct notifier_block *nb,
 					struct netdev_net_notifier *nn)
@@ -2077,6 +2145,11 @@ int register_netdevice_notifier_dev_net(struct net_device *dev,
 	struct net *net = dev_net(dev);
 	int err;
 
+	/* rtnl_net_lock() assumes dev is not yet published by
+	 * register_netdevice().
+	 */
+	DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list));
+
 	rtnl_net_lock(net);
 	err = __register_netdevice_notifier_net(net, nb, false);
 	if (!err) {
@@ -2093,13 +2166,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev,
 					  struct notifier_block *nb,
 					  struct netdev_net_notifier *nn)
 {
-	struct net *net = dev_net(dev);
 	int err;
 
-	rtnl_net_lock(net);
+	rtnl_net_dev_lock(dev);
 	list_del(&nn->list);
-	err = __unregister_netdevice_notifier_net(net, nb);
-	rtnl_net_unlock(net);
+	err = __unregister_netdevice_notifier_net(dev_net(dev), nb);
+	rtnl_net_dev_unlock(dev);
 
 	return err;
 }
@@ -4500,7 +4572,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	skb_reset_mac_header(skb);
 	skb_assert_len(skb);
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
+	if (unlikely(skb_shinfo(skb)->tx_flags &
+		     (SKBTX_SCHED_TSTAMP | SKBTX_BPF)))
 		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
 
 	/* Disable soft irqs for various locks below. Also
@@ -6119,16 +6192,18 @@ EXPORT_SYMBOL(netif_receive_skb_list);
 static void flush_backlog(struct work_struct *work)
 {
 	struct sk_buff *skb, *tmp;
+	struct sk_buff_head list;
 	struct softnet_data *sd;
 
+	__skb_queue_head_init(&list);
 	local_bh_disable();
 	sd = this_cpu_ptr(&softnet_data);
 
 	backlog_lock_irq_disable(sd);
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
-		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+		if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			dev_kfree_skb_irq(skb);
+			__skb_queue_tail(&list, skb);
 			rps_input_queue_head_incr(sd);
 		}
 	}
@@ -6136,14 +6211,16 @@ static void flush_backlog(struct work_struct *work)
 
 	local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
-		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+		if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&list, skb);
 			rps_input_queue_head_incr(sd);
 		}
 	}
 	local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 	local_bh_enable();
+
+	__skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY);
 }
 
 static bool flush_required(int cpu)
@@ -6735,7 +6812,7 @@ static void napi_hash_add(struct napi_struct *napi)
 
 	/* 0..NR_CPUS range is reserved for sender_cpu use */
 	do {
-		if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+		if (unlikely(!napi_id_valid(++napi_gen_id)))
 			napi_gen_id = MIN_NAPI_ID;
 	} while (napi_by_id(napi_gen_id));
 
@@ -6906,7 +6983,7 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi)
 
 	higher = &dev->napi_list;
 	list_for_each_entry(pos, &dev->napi_list, dev_list) {
-		if (pos->napi_id >= MIN_NAPI_ID)
+		if (napi_id_valid(pos->napi_id))
 			pos_id = pos->napi_id;
 		else if (pos->config)
 			pos_id = pos->config->napi_id;
@@ -6920,6 +6997,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi)
 	list_add_rcu(&napi->dev_list, higher); /* adds after higher */
 }
 
+/* Double check that napi_get_frags() allocates skbs with
+ * skb->head being backed by slab, not a page fragment.
+ * This is to make sure bug fixed in 3226b158e67c
+ * ("net: avoid 32 x truesize under-estimation for tiny skbs")
+ * does not accidentally come back.
+ */
+static void napi_get_frags_check(struct napi_struct *napi)
+{
+	struct sk_buff *skb;
+
+	local_bh_disable();
+	skb = napi_get_frags(napi);
+	WARN_ON_ONCE(skb && skb->head_frag);
+	napi_free_frags(napi);
+	local_bh_enable();
+}
+
 void netif_napi_add_weight_locked(struct net_device *dev,
 				  struct napi_struct *napi,
 				  int (*poll)(struct napi_struct *, int),
@@ -7071,6 +7165,9 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
 		return;
 
+	/* Make sure NAPI is disabled (or was never enabled). */
+	WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
+
 	if (napi->config) {
 		napi->index = -1;
 		napi->config = NULL;
@@ -9174,7 +9271,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags,
 
 	if ((flags ^ dev->gflags) & IFF_PROMISC) {
 		int inc = (flags & IFF_PROMISC) ? 1 : -1;
-		unsigned int old_flags = dev->flags;
+		old_flags = dev->flags;
 
 		dev->gflags ^= IFF_PROMISC;
 
@@ -11112,9 +11209,8 @@ void netdev_run_todo(void)
 	list_replace_init(&net_unlink_list, &unlink_list);
 
 	while (!list_empty(&unlink_list)) {
-		struct net_device *dev = list_first_entry(&unlink_list,
-							  struct net_device,
-							  unlink_list);
+		dev = list_first_entry(&unlink_list, struct net_device,
+				       unlink_list);
 		list_del_init(&dev->unlink_list);
 		dev->nested_level = dev->lower_level - 1;
 	}
@@ -11738,6 +11834,19 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
 }
 EXPORT_SYMBOL(unregister_netdevice_queue);
 
+static void dev_memory_provider_uninstall(struct net_device *dev)
+{
+	unsigned int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct netdev_rx_queue *rxq = &dev->_rx[i];
+		struct pp_memory_provider_params *p = &rxq->mp_params;
+
+		if (p->mp_ops && p->mp_ops->uninstall)
+			p->mp_ops->uninstall(rxq->mp_params.mp_priv, rxq);
+	}
+}
+
 void unregister_netdevice_many_notify(struct list_head *head,
 				      u32 portid, const struct nlmsghdr *nlh)
 {
@@ -11792,7 +11901,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		dev_tcx_uninstall(dev);
 		dev_xdp_uninstall(dev);
 		bpf_dev_bound_netdev_unregister(dev);
-		dev_dmabuf_uninstall(dev);
+		dev_memory_provider_uninstall(dev);
 
 		netdev_offload_xstats_disable_all(dev);
 
@@ -11880,11 +11989,9 @@ EXPORT_SYMBOL(unregister_netdevice_many);
  */
 void unregister_netdev(struct net_device *dev)
 {
-	struct net *net = dev_net(dev);
-
-	rtnl_net_lock(net);
+	rtnl_net_dev_lock(dev);
 	unregister_netdevice(dev);
-	rtnl_net_unlock(net);
+	rtnl_net_dev_unlock(dev);
 }
 EXPORT_SYMBOL(unregister_netdev);