Merge: net/other: phase-2 backports for rhel-9.8

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7498

JIRA: https://issues.redhat.com/browse/RHEL-115650
Upstream Status: all mainline in net.git
Tested: boot-tested only
Conflicts: None

Signed-off-by: Davide Caratti <dcaratti@redhat.com>

Approved-by: Antoine Tenart <atenart@redhat.com>
Approved-by: Eder Zulian <ezulian@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

drivers/net/loopback.c

@@ -247,8 +247,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static int blackhole_neigh_construct(struct net_device *dev,
+				     struct neighbour *n)
+{
+	n->output = blackhole_neigh_output;
+	return 0;
+}
+
 static const struct net_device_ops blackhole_netdev_ops = {
 	.ndo_start_xmit = blackhole_netdev_xmit,
+	.ndo_neigh_construct = blackhole_neigh_construct,
 };
 
 /* This is a dst-dummy device used specifically for invalidated

net/8021q/vlan.c

@@ -358,6 +358,35 @@ static int __vlan_device_event(struct net_device *dev, unsigned long event)
 	return err;
 }
 
+static void vlan_vid0_add(struct net_device *dev)
+{
+	struct vlan_info *vlan_info;
+	int err;
+
+	if (!(dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		return;
+
+	pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name);
+
+	err = vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
+	if (err)
+		return;
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	vlan_info->auto_vid0 = true;
+}
+
+static void vlan_vid0_del(struct net_device *dev)
+{
+	struct vlan_info *vlan_info = rtnl_dereference(dev->vlan_info);
+
+	if (!vlan_info || !vlan_info->auto_vid0)
+		return;
+
+	vlan_info->auto_vid0 = false;
+	vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
+}
+
 static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			     void *ptr)
 {
@@ -379,15 +408,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			return notifier_from_errno(err);
 	}
 
-	if ((event == NETDEV_UP) &&
-	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) {
-		pr_info("adding VLAN 0 to HW filter on device %s\n",
-			dev->name);
-		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
-	}
-	if (event == NETDEV_DOWN &&
-	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
-		vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
+	if (event == NETDEV_UP)
+		vlan_vid0_add(dev);
+	else if (event == NETDEV_DOWN)
+		vlan_vid0_del(dev);
 
 	vlan_info = rtnl_dereference(dev->vlan_info);
 	if (!vlan_info)

net/8021q/vlan.h

@@ -33,6 +33,7 @@ struct vlan_info {
 	struct vlan_group	grp;
 	struct list_head	vid_list;
 	unsigned int		nr_vids;
+	bool			auto_vid0;
 	struct rcu_head		rcu;
 };
 

net/packet/af_packet.c

@@ -2741,7 +2741,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
 	int hlen, tlen, copylen = 0;
-	long timeo = 0;
+	long timeo;
 
 	mutex_lock(&po->pg_vec_lock);
 
@@ -2796,22 +2796,28 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	    !packet_sock_flag(po, PACKET_SOCK_HAS_VNET_HDR))
 		size_max = dev->mtu + reserve + VLAN_HLEN;
 
+	timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
 	reinit_completion(&po->skb_completion);
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
 					  TP_STATUS_SEND_REQUEST);
 		if (unlikely(ph == NULL)) {
-			if (need_wait && skb) {
-				timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
+			/* Note: packet_read_pending() might be slow if we
+			 * have to call it as it's per_cpu variable, but in
+			 * fast-path we don't have to call it, only when ph
+			 * is NULL, we need to check the pending_refcnt.
+			 */
+			if (need_wait && packet_read_pending(&po->tx_ring)) {
 				timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo);
 				if (timeo <= 0) {
 					err = !timeo ? -ETIMEDOUT : -ERESTARTSYS;
 					goto out_put;
 				}
-			}
-			/* check for additional frames */
-			continue;
+				/* check for additional frames */
+				continue;
+			} else
+				break;
 		}
 
 		skb = NULL;
@@ -2900,14 +2906,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		}
 		packet_increment_head(&po->tx_ring);
 		len_sum += tp_len;
-	} while (likely((ph != NULL) ||
-		/* Note: packet_read_pending() might be slow if we have
-		 * to call it as it's per_cpu variable, but in fast-path
-		 * we already short-circuit the loop with the first
-		 * condition, and luckily don't have to go that path
-		 * anyway.
-		 */
-		 (need_wait && packet_read_pending(&po->tx_ring))));
+	} while (1);
 
 	err = len_sum;
 	goto out_put;
@@ -4501,10 +4500,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	spin_lock(&po->bind_lock);
 	was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING);
 	num = po->num;
-	if (was_running) {
-		WRITE_ONCE(po->num, 0);
+	WRITE_ONCE(po->num, 0);
+	if (was_running)
 		__unregister_prot_hook(sk, false);
-	}
+
 	spin_unlock(&po->bind_lock);
 
 	synchronize_net();
@@ -4536,10 +4535,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	mutex_unlock(&po->pg_vec_lock);
 
 	spin_lock(&po->bind_lock);
-	if (was_running) {
-		WRITE_ONCE(po->num, num);
+	WRITE_ONCE(po->num, num);
+	if (was_running)
 		register_prot_hook(sk);
-	}
+
 	spin_unlock(&po->bind_lock);
 	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */