Merge tag 'net-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter.

  Current release - regressions:

   - four fixes for the netdev per-instance locking

  Current release - new code bugs:

   - consolidate more code between existing Rx zero-copy and uring so
     that the latter doesn't miss / have to duplicate the safety checks

  Previous releases - regressions:

   - ipv6: fix omitted Netlink attributes when using SKIP_STATS

  Previous releases - always broken:

   - net: fix geneve_opt length integer overflow

   - udp: fix multiple wrap arounds of sk->sk_rmem_alloc when it
     approaches INT_MAX

   - dsa: mvpp2: add a lock to avoid corruption of the shared TCAM

   - dsa: airoha: fix issues with traffic QoS configuration / offload,
     and flow table offload

  Misc:

   - touch up the Netlink YAML specs of old families to make them usable
     for user space C codegen"

* tag 'net-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (56 commits)
  selftests: net: amt: indicate progress in the stress test
  netlink: specs: rt_route: pull the ifa- prefix out of the names
  netlink: specs: rt_addr: pull the ifa- prefix out of the names
  netlink: specs: rt_addr: fix get multi command name
  netlink: specs: rt_addr: fix the spec format / schema failures
  net: avoid false positive warnings in __net_mp_close_rxq()
  net: move mp dev config validation to __net_mp_open_rxq()
  net: ibmveth: make veth_pool_store stop hanging
  arcnet: Add NULL check in com20020pci_probe()
  ipv6: Do not consider link down nexthops in path selection
  ipv6: Start path selection from the first nexthop
  usbnet:fix NPE during rx_complete
  net: octeontx2: Handle XDP_ABORTED and XDP invalid as XDP_DROP
  net: fix geneve_opt length integer overflow
  io_uring/zcrx: fix selftests w/ updated netdev Python helpers
  selftests: net: use netdevsim in netns test
  docs: net: document netdev notifier expectations
  net: dummy: request ops lock
  netdevsim: add dummy device notifiers
  net: rename rtnl_net_debug to lock_debug
  ...

24 files changed, 231 insertions, 146 deletions

diff --git a/net/core/Makefile b/net/core/Makefile
index a10c3bd96798..b2a76ce33932 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -45,5 +45,5 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
 obj-$(CONFIG_OF)	+= of_net.o
 obj-$(CONFIG_NET_TEST) += net_test.o
 obj-$(CONFIG_NET_DEVMEM) += devmem.o
-obj-$(CONFIG_DEBUG_NET_SMALL_RTNL) += rtnl_net_debug.o
+obj-$(CONFIG_DEBUG_NET) += lock_debug.o
 obj-$(CONFIG_FAIL_SKB_REALLOC) += skb_fault_injection.o
diff --git a/net/core/dev.c b/net/core/dev.c
index be17e0660144..0608605cfc24 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1771,6 +1771,7 @@ void netif_disable_lro(struct net_device *dev)
 		netdev_unlock_ops(lower_dev);
 	}
 }
+EXPORT_IPV6_MOD(netif_disable_lro);
 
 /**
  *	dev_disable_gro_hw - disable HW Generic Receive Offload on a device
@@ -1858,7 +1859,9 @@ static int call_netdevice_register_net_notifiers(struct notifier_block *nb,
 	int err;
 
 	for_each_netdev(net, dev) {
+		netdev_lock_ops(dev);
 		err = call_netdevice_register_notifiers(nb, dev);
+		netdev_unlock_ops(dev);
 		if (err)
 			goto rollback;
 	}
@@ -10284,7 +10287,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		goto unlock;
 	}
 
+	netdev_lock_ops(dev);
 	err = dev_xdp_attach_link(dev, &extack, link);
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 
 	if (err) {
@@ -11045,7 +11050,9 @@ int register_netdevice(struct net_device *dev)
 		memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
 
 	/* Notify protocols, that a new device appeared. */
+	netdev_lock_ops(dev);
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
+	netdev_unlock_ops(dev);
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		/* Expect explicit free_netdev() on failure */
@@ -12057,7 +12064,7 @@ void unregister_netdev(struct net_device *dev)
 }
 EXPORT_SYMBOL(unregister_netdev);
 
-int netif_change_net_namespace(struct net_device *dev, struct net *net,
+int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 			       const char *pat, int new_ifindex,
 			       struct netlink_ext_ack *extack)
 {
@@ -12142,11 +12149,12 @@ int netif_change_net_namespace(struct net_device *dev, struct net *net,
 	 * And now a mini version of register_netdevice unregister_netdevice.
 	 */
 
+	netdev_lock_ops(dev);
 	/* If device is running close it first. */
 	netif_close(dev);
-
 	/* And unlink it from device chain */
 	unlist_netdevice(dev);
+	netdev_unlock_ops(dev);
 
 	synchronize_net();
 
@@ -12208,11 +12216,12 @@ int netif_change_net_namespace(struct net_device *dev, struct net *net,
 	err = netdev_change_owner(dev, net_old, net);
 	WARN_ON(err);
 
+	netdev_lock_ops(dev);
 	/* Add the device back in the hashes */
 	list_netdevice(dev);
-
 	/* Notify protocols, that a new device appeared. */
 	call_netdevice_notifiers(NETDEV_REGISTER, dev);
+	netdev_unlock_ops(dev);
 
 	/*
 	 *	Prevent userspace races by waiting until the network
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 8dbc60612100..90bafb0b1b8c 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -117,13 +117,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user);
 int dev_change_net_namespace(struct net_device *dev, struct net *net,
 			     const char *pat)
 {
-	int ret;
-
-	netdev_lock_ops(dev);
-	ret = netif_change_net_namespace(dev, net, pat, 0, NULL);
-	netdev_unlock_ops(dev);
-
-	return ret;
+	return __dev_change_net_namespace(dev, net, pat, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(dev_change_net_namespace);
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
index ee145a2aa41c..6e27a47d0493 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/dma-buf.h>
-#include <linux/ethtool_netlink.h>
 #include <linux/genalloc.h>
 #include <linux/mm.h>
 #include <linux/netdevice.h>
@@ -117,21 +116,19 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 	struct netdev_rx_queue *rxq;
 	unsigned long xa_idx;
 	unsigned int rxq_idx;
-	int err;
 
 	if (binding->list.next)
 		list_del(&binding->list);
 
 	xa_for_each(&binding->bound_rxqs, xa_idx, rxq) {
-		WARN_ON(rxq->mp_params.mp_priv != binding);
-
-		rxq->mp_params.mp_priv = NULL;
-		rxq->mp_params.mp_ops = NULL;
+		const struct pp_memory_provider_params mp_params = {
+			.mp_priv	= binding,
+			.mp_ops		= &dmabuf_devmem_ops,
+		};
 
 		rxq_idx = get_netdev_rx_queue_index(rxq);
 
-		err = netdev_rx_queue_restart(binding->dev, rxq_idx);
-		WARN_ON(err && err != -ENETDOWN);
+		__net_mp_close_rxq(binding->dev, rxq_idx, &mp_params);
 	}
 
 	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
@@ -143,57 +140,28 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 				    struct net_devmem_dmabuf_binding *binding,
 				    struct netlink_ext_ack *extack)
 {
+	struct pp_memory_provider_params mp_params = {
+		.mp_priv	= binding,
+		.mp_ops		= &dmabuf_devmem_ops,
+	};
 	struct netdev_rx_queue *rxq;
 	u32 xa_idx;
 	int err;
 
-	if (rxq_idx >= dev->real_num_rx_queues) {
-		NL_SET_ERR_MSG(extack, "rx queue index out of range");
-		return -ERANGE;
-	}
-
-	if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) {
-		NL_SET_ERR_MSG(extack, "tcp-data-split is disabled");
-		return -EINVAL;
-	}
-
-	if (dev->cfg->hds_thresh) {
-		NL_SET_ERR_MSG(extack, "hds-thresh is not zero");
-		return -EINVAL;
-	}
+	err = __net_mp_open_rxq(dev, rxq_idx, &mp_params, extack);
+	if (err)
+		return err;
 
 	rxq = __netif_get_rx_queue(dev, rxq_idx);
-	if (rxq->mp_params.mp_ops) {
-		NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
-		return -EEXIST;
-	}
-
-#ifdef CONFIG_XDP_SOCKETS
-	if (rxq->pool) {
-		NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP");
-		return -EBUSY;
-	}
-#endif
-
 	err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b,
 		       GFP_KERNEL);
 	if (err)
-		return err;
-
-	rxq->mp_params.mp_priv = binding;
-	rxq->mp_params.mp_ops = &dmabuf_devmem_ops;
-
-	err = netdev_rx_queue_restart(dev, rxq_idx);
-	if (err)
-		goto err_xa_erase;
+		goto err_close_rxq;
 
 	return 0;
 
-err_xa_erase:
-	rxq->mp_params.mp_priv = NULL;
-	rxq->mp_params.mp_ops = NULL;
-	xa_erase(&binding->bound_rxqs, xa_idx);
-
+err_close_rxq:
+	__net_mp_close_rxq(dev, rxq_idx, &mp_params);
 	return err;
 }
 
diff --git a/net/core/dst.c b/net/core/dst.c
index c99b95cf9cbb..795ca07e28a4 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -165,6 +165,14 @@ static void dst_count_dec(struct dst_entry *dst)
 void dst_release(struct dst_entry *dst)
 {
 	if (dst && rcuref_put(&dst->__rcuref)) {
+#ifdef CONFIG_DST_CACHE
+		if (dst->flags & DST_METADATA) {
+			struct metadata_dst *md_dst = (struct metadata_dst *)dst;
+
+			if (md_dst->type == METADATA_IP_TUNNEL)
+				dst_cache_reset_now(&md_dst->u.tun_info.dst_cache);
+		}
+#endif
 		dst_count_dec(dst);
 		call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu);
 	}
diff --git a/net/core/rtnl_net_debug.c b/net/core/lock_debug.c
index 7ecd28cc1c22..b7f22dc92a6f 100644
--- a/net/core/rtnl_net_debug.c
+++ b/net/core/lock_debug.c
@@ -6,10 +6,11 @@
 #include <linux/notifier.h>
 #include <linux/rtnetlink.h>
 #include <net/net_namespace.h>
+#include <net/netdev_lock.h>
 #include <net/netns/generic.h>
 
-static int rtnl_net_debug_event(struct notifier_block *nb,
-				unsigned long event, void *ptr)
+int netdev_debug_event(struct notifier_block *nb, unsigned long event,
+		       void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
@@ -17,11 +18,13 @@ static int rtnl_net_debug_event(struct notifier_block *nb,
 
 	/* Keep enum and don't add default to trigger -Werror=switch */
 	switch (cmd) {
+	case NETDEV_REGISTER:
 	case NETDEV_UP:
+		netdev_ops_assert_locked(dev);
+		fallthrough;
 	case NETDEV_DOWN:
 	case NETDEV_REBOOT:
 	case NETDEV_CHANGE:
-	case NETDEV_REGISTER:
 	case NETDEV_UNREGISTER:
 	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGEADDR:
@@ -66,6 +69,7 @@ static int rtnl_net_debug_event(struct notifier_block *nb,
 
 	return NOTIFY_DONE;
 }
+EXPORT_SYMBOL_NS_GPL(netdev_debug_event, "NETDEV_INTERNAL");
 
 static int rtnl_net_debug_net_id;
 
@@ -74,7 +78,7 @@ static int __net_init rtnl_net_debug_net_init(struct net *net)
 	struct notifier_block *nb;
 
 	nb = net_generic(net, rtnl_net_debug_net_id);
-	nb->notifier_call = rtnl_net_debug_event;
+	nb->notifier_call = netdev_debug_event;
 
 	return register_netdevice_notifier_net(net, nb);
 }
@@ -95,14 +99,14 @@ static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = {
 };
 
 static struct notifier_block rtnl_net_debug_block = {
-	.notifier_call = rtnl_net_debug_event,
+	.notifier_call = netdev_debug_event,
 };
 
 static int __init rtnl_net_debug_init(void)
 {
 	int ret;
 
-	ret = register_pernet_device(&rtnl_net_debug_net_ops);
+	ret = register_pernet_subsys(&rtnl_net_debug_net_ops);
 	if (ret)
 		return ret;
 
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 3afeaa8c5dc5..5d7af50fe702 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -874,12 +874,6 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock;
 	}
 
-	if (dev_xdp_prog_count(netdev)) {
-		NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached");
-		err = -EEXIST;
-		goto err_unlock;
-	}
-
 	binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack);
 	if (IS_ERR(binding)) {
 		err = PTR_ERR(binding);
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 3af716f77a13..d126f10197bf 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/ethtool_netlink.h>
 #include <linux/netdevice.h>
 #include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
@@ -86,8 +87,9 @@ err_free_new_mem:
 }
 EXPORT_SYMBOL_NS_GPL(netdev_rx_queue_restart, "NETDEV_INTERNAL");
 
-static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
-			     struct pp_memory_provider_params *p)
+int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
+		      const struct pp_memory_provider_params *p,
+		      struct netlink_ext_ack *extack)
 {
 	struct netdev_rx_queue *rxq;
 	int ret;
@@ -95,16 +97,41 @@ static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
 	if (!netdev_need_ops_lock(dev))
 		return -EOPNOTSUPP;
 
-	if (ifq_idx >= dev->real_num_rx_queues)
+	if (rxq_idx >= dev->real_num_rx_queues)
 		return -EINVAL;
-	ifq_idx = array_index_nospec(ifq_idx, dev->real_num_rx_queues);
+	rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues);
 
-	rxq = __netif_get_rx_queue(dev, ifq_idx);
-	if (rxq->mp_params.mp_ops)
+	if (rxq_idx >= dev->real_num_rx_queues) {
+		NL_SET_ERR_MSG(extack, "rx queue index out of range");
+		return -ERANGE;
+	}
+	if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) {
+		NL_SET_ERR_MSG(extack, "tcp-data-split is disabled");
+		return -EINVAL;
+	}
+	if (dev->cfg->hds_thresh) {
+		NL_SET_ERR_MSG(extack, "hds-thresh is not zero");
+		return -EINVAL;
+	}
+	if (dev_xdp_prog_count(dev)) {
+		NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached");
 		return -EEXIST;
+	}
+
+	rxq = __netif_get_rx_queue(dev, rxq_idx);
+	if (rxq->mp_params.mp_ops) {
+		NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
+		return -EEXIST;
+	}
+#ifdef CONFIG_XDP_SOCKETS
+	if (rxq->pool) {
+		NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP");
+		return -EBUSY;
+	}
+#endif
 
 	rxq->mp_params = *p;
-	ret = netdev_rx_queue_restart(dev, ifq_idx);
+	ret = netdev_rx_queue_restart(dev, rxq_idx);
 	if (ret) {
 		rxq->mp_params.mp_ops = NULL;
 		rxq->mp_params.mp_priv = NULL;
@@ -112,21 +139,22 @@ static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
 	return ret;
 }
 
-int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 		    struct pp_memory_provider_params *p)
 {
 	int ret;
 
 	netdev_lock(dev);
-	ret = __net_mp_open_rxq(dev, ifq_idx, p);
+	ret = __net_mp_open_rxq(dev, rxq_idx, p, NULL);
 	netdev_unlock(dev);
 	return ret;
 }
 
-static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
-			      struct pp_memory_provider_params *old_p)
+void __net_mp_close_rxq(struct net_device *dev, unsigned int ifq_idx,
+			const struct pp_memory_provider_params *old_p)
 {
 	struct netdev_rx_queue *rxq;
+	int err;
 
 	if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues))
 		return;
@@ -146,7 +174,8 @@ static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
 
 	rxq->mp_params.mp_ops = NULL;
 	rxq->mp_params.mp_priv = NULL;
-	WARN_ON(netdev_rx_queue_restart(dev, ifq_idx));
+	err = netdev_rx_queue_restart(dev, ifq_idx);
+	WARN_ON(err && err != -ENETDOWN);
 }
 
 void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 334db17be37d..c23852835050 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3025,8 +3025,6 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	char ifname[IFNAMSIZ];
 	int err;
 
-	netdev_lock_ops(dev);
-
 	err = validate_linkmsg(dev, tb, extack);
 	if (err < 0)
 		goto errout;
@@ -3042,14 +3040,16 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 		new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0);
 
-		err = netif_change_net_namespace(dev, tgt_net, pat,
+		err = __dev_change_net_namespace(dev, tgt_net, pat,
 						 new_ifindex, extack);
 		if (err)
-			goto errout;
+			return err;
 
 		status |= DO_SETLINK_MODIFIED;
 	}
 
+	netdev_lock_ops(dev);
+
 	if (tb[IFLA_MAP]) {
 		struct rtnl_link_ifmap *u_map;
 		struct ifmap k_map;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 754f60fb6e25..77e5705ac799 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -281,7 +281,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	if (!in_dev->arp_parms)
 		goto out_kfree;
 	if (IPV4_DEVCONF(in_dev->cnf, FORWARDING))
-		dev_disable_lro(dev);
+		netif_disable_lro(dev);
 	/* Reference in_dev->dev */
 	netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL);
 	/* Account for reference dev->ip_ptr (below) */
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index a3676155be78..f65d2f727381 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -416,7 +416,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 
 	skb_dst_update_pmtu_no_confirm(skb, mtu);
 
-	if (!reply || skb->pkt_type == PACKET_HOST)
+	if (!reply)
 		return 0;
 
 	if (skb->protocol == htons(ETH_P_IP))
@@ -451,7 +451,7 @@ static const struct nla_policy
 geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
 	[LWTUNNEL_IP_OPT_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[LWTUNNEL_IP_OPT_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static const struct nla_policy
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d0bffcfa56d8..2742cc7602bb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1625,12 +1625,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb)
 }
 
 /* fully reclaim rmem/fwd memory allocated for skb */
-static void udp_rmem_release(struct sock *sk, int size, int partial,
-			     bool rx_queue_lock_held)
+static void udp_rmem_release(struct sock *sk, unsigned int size,
+			     int partial, bool rx_queue_lock_held)
 {
 	struct udp_sock *up = udp_sk(sk);
 	struct sk_buff_head *sk_queue;
-	int amt;
+	unsigned int amt;
 
 	if (likely(partial)) {
 		up->forward_deficit += size;
@@ -1650,10 +1650,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (!rx_queue_lock_held)
 		spin_lock(&sk_queue->lock);
 
-
-	sk_forward_alloc_add(sk, size);
-	amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
-	sk_forward_alloc_add(sk, -amt);
+	amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
+	sk_forward_alloc_add(sk, size - amt);
 
 	if (amt)
 		__sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT);
@@ -1725,17 +1723,25 @@ static int udp_rmem_schedule(struct sock *sk, int size)
 int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct sk_buff_head *list = &sk->sk_receive_queue;
-	int rmem, err = -ENOMEM;
+	unsigned int rmem, rcvbuf;
 	spinlock_t *busy = NULL;
-	int size, rcvbuf;
+	int size, err = -ENOMEM;
 
-	/* Immediately drop when the receive queue is full.
-	 * Always allow at least one packet.
-	 */
 	rmem = atomic_read(&sk->sk_rmem_alloc);
 	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
-	if (rmem > rcvbuf)
-		goto drop;
+	size = skb->truesize;
+
+	/* Immediately drop when the receive queue is full.
+	 * Cast to unsigned int performs the boundary check for INT_MAX.
+	 */
+	if (rmem + size > rcvbuf) {
+		if (rcvbuf > INT_MAX >> 1)
+			goto drop;
+
+		/* Always allow at least one packet for small buffer. */
+		if (rmem > rcvbuf)
+			goto drop;
+	}
 
 	/* Under mem pressure, it might be helpful to help udp_recvmsg()
 	 * having linear skbs :
@@ -1745,10 +1751,10 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (rmem > (rcvbuf >> 1)) {
 		skb_condense(skb);
-
+		size = skb->truesize;
 		busy = busylock_acquire(sk);
 	}
-	size = skb->truesize;
+
 	udp_set_dev_scratch(skb);
 
 	atomic_add(size, &sk->sk_rmem_alloc);
@@ -1835,7 +1841,7 @@ EXPORT_IPV6_MOD_GPL(skb_consume_udp);
 
 static struct sk_buff *__first_packet_length(struct sock *sk,
 					     struct sk_buff_head *rcvq,
-					     int *total)
+					     unsigned int *total)
 {
 	struct sk_buff *skb;
 
@@ -1868,8 +1874,8 @@ static int first_packet_length(struct sock *sk)
 {
 	struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue;
 	struct sk_buff_head *sk_queue = &sk->sk_receive_queue;
+	unsigned int total = 0;
 	struct sk_buff *skb;
-	int total = 0;
 	int res;
 
 	spin_lock_bh(&rcvq->lock);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ac8cc1076536..c3b908fccbc1 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -80,6 +80,7 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/l3mdev.h>
+#include <net/netdev_lock.h>
 #include <linux/if_tunnel.h>
 #include <linux/rtnetlink.h>
 #include <linux/netconf.h>
@@ -377,6 +378,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	int err = -ENOMEM;
 
 	ASSERT_RTNL();
+	netdev_ops_assert_locked(dev);
 
 	if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev)
 		return ERR_PTR(-EINVAL);
@@ -402,7 +404,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 		return ERR_PTR(err);
 	}
 	if (ndev->cnf.forwarding)
-		dev_disable_lro(dev);
+		netif_disable_lro(dev);
 	/* We refer to the device */
 	netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL);
 
@@ -3152,10 +3154,12 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
 
 	rtnl_net_lock(net);
 	dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
+	netdev_lock_ops(dev);
 	if (dev)
 		err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL);
 	else
 		err = -ENODEV;
+	netdev_unlock_ops(dev);
 	rtnl_net_unlock(net);
 	return err;
 }
@@ -5026,9 +5030,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!dev) {
 		NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface");
 		err = -ENODEV;
-		goto unlock;
+		goto unlock_rtnl;
 	}
 
+	netdev_lock_ops(dev);
 	idev = ipv6_find_idev(dev);
 	if (IS_ERR(idev)) {
 		err = PTR_ERR(idev);
@@ -5065,6 +5070,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	in6_ifa_put(ifa);
 unlock:
+	netdev_unlock_ops(dev);
+unlock_rtnl:
 	rtnl_net_unlock(net);
 
 	return err;
@@ -5784,6 +5791,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 	}
 }
 
+static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb,
+					struct inet6_dev *idev)
+{
+	struct nlattr *nla;
+
+	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
+	if (!nla)
+		goto nla_put_failure;
+	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
+
+	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
+	if (!nla)
+		goto nla_put_failure;
+	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
 				  u32 ext_filter_mask)
 {
@@ -5806,18 +5834,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
 
 	/* XXX - MC not implemented */
 
-	if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
-		return 0;
-
-	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
-	if (!nla)
-		goto nla_put_failure;
-	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
-
-	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
-	if (!nla)
-		goto nla_put_failure;
-	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+	if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) {
+		if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0)
+			goto nla_put_failure;
+	}
 
 	nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
 	if (!nla)
@@ -6503,7 +6523,9 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write,
 
 			if (idev->cnf.addr_gen_mode != new_val) {
 				WRITE_ONCE(idev->cnf.addr_gen_mode, new_val);
+				netdev_lock_ops(idev->dev);
 				addrconf_init_auto_addrs(idev->dev);
+				netdev_unlock_ops(idev->dev);
 			}
 		} else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) {
 			struct net_device *dev;
@@ -6515,7 +6537,9 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write,
 				    idev->cnf.addr_gen_mode != new_val) {
 					WRITE_ONCE(idev->cnf.addr_gen_mode,
 						  new_val);
+					netdev_lock_ops(idev->dev);
 					addrconf_init_auto_addrs(idev->dev);
+					netdev_unlock_ops(idev->dev);
 				}
 			}
 		}
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index dbcea9fee626..62618a058b8f 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1072,8 +1072,13 @@ static int calipso_sock_getattr(struct sock *sk,
 	struct ipv6_opt_hdr *hop;
 	int opt_len, len, ret_val = -ENOMSG, offset;
 	unsigned char *opt;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return -EAFNOSUPPORT;
 
+	txopts = txopt_get(pinfo);
 	if (!txopts || !txopts->hopopt)
 		goto done;
 
@@ -1125,8 +1130,13 @@ static int calipso_sock_setattr(struct sock *sk,
 {
 	int ret_val;
 	struct ipv6_opt_hdr *old, *new;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return -EAFNOSUPPORT;
 
+	txopts = txopt_get(pinfo);
 	old = NULL;
 	if (txopts)
 		old = txopts->hopopt;
@@ -1153,8 +1163,13 @@ static int calipso_sock_setattr(struct sock *sk,
 static void calipso_sock_delattr(struct sock *sk)
 {
 	struct ipv6_opt_hdr *new_hop;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return;
 
+	txopts = txopt_get(pinfo);
 	if (!txopts || !txopts->hopopt)
 		goto done;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c3406a0d45bd..ab12b816ab94 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -412,12 +412,37 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
+static struct fib6_info *
+rt6_multipath_first_sibling_rcu(const struct fib6_info *rt)
+{
+	struct fib6_info *iter;
+	struct fib6_node *fn;
+
+	fn = rcu_dereference(rt->fib6_node);
+	if (!fn)
+		goto out;
+	iter = rcu_dereference(fn->leaf);
+	if (!iter)
+		goto out;
+
+	while (iter) {
+		if (iter->fib6_metric == rt->fib6_metric &&
+		    rt6_qualify_for_ecmp(iter))
+			return iter;
+		iter = rcu_dereference(iter->fib6_next);
+	}
+
+out:
+	return NULL;
+}
+
 void fib6_select_path(const struct net *net, struct fib6_result *res,
 		      struct flowi6 *fl6, int oif, bool have_oif_match,
 		      const struct sk_buff *skb, int strict)
 {
-	struct fib6_info *match = res->f6i;
+	struct fib6_info *first, *match = res->f6i;
 	struct fib6_info *sibling;
+	int hash;
 
 	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;
@@ -440,16 +465,25 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		return;
 	}
 
-	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
+	first = rt6_multipath_first_sibling_rcu(match);
+	if (!first)
 		goto out;
 
-	list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+	hash = fl6->mp_hash;
+	if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) &&
+	    rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+			    strict) >= 0) {
+		match = first;
+		goto out;
+	}
+
+	list_for_each_entry_rcu(sibling, &first->fib6_siblings,
 				fib6_siblings) {
 		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;
 
 		nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
-		if (fl6->mp_hash > nh_upper_bound)
+		if (hash > nh_upper_bound)
 			continue;
 		if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
 			break;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c2df81b7e950..a133e1c175ce 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2839,11 +2839,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			err = nft_netdev_register_hooks(ctx->net, &hook.list);
 			if (err < 0)
 				goto err_hooks;
+
+			unregister = true;
 		}
 	}
 
-	unregister = true;
-
 	if (nla[NFTA_CHAIN_COUNTERS]) {
 		if (!nft_is_base_chain(chain)) {
 			err = -EOPNOTSUPP;
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 8bfac4185ac7..abb0c8ec6371 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -309,7 +309,8 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set,
 
 	nft_setelem_expr_foreach(expr, elem_expr, size) {
 		if (expr->ops->gc &&
-		    expr->ops->gc(read_pnet(&set->net), expr))
+		    expr->ops->gc(read_pnet(&set->net), expr) &&
+		    set->flags & NFT_SET_EVAL)
 			return true;
 	}
 
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 681301b46aa4..0c63d1367cf7 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -335,13 +335,13 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
 static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = {
 	[NFTA_TUNNEL_KEY_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[NFTA_TUNNEL_KEY_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[NFTA_TUNNEL_KEY_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[NFTA_TUNNEL_KEY_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static int nft_tunnel_obj_geneve_init(const struct nlattr *attr,
 				      struct nft_tunnel_opts *opts)
 {
-	struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len;
+	struct geneve_opt *opt = (struct geneve_opt *)(opts->u.data + opts->len);
 	struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1];
 	int err, data_len;
 
@@ -625,7 +625,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb,
 		if (!inner)
 			goto failure;
 		while (opts->len > offset) {
-			opt = (struct geneve_opt *)opts->u.data + offset;
+			opt = (struct geneve_opt *)(opts->u.data + offset);
 			if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS,
 					 opt->opt_class) ||
 			    nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE,
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 704c858cf209..61fea7baae5d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -947,12 +947,6 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 				pskb_trim(skb, ovs_mac_header_len(key));
 		}
 
-		/* Need to set the pkt_type to involve the routing layer.  The
-		 * packet movement through the OVS datapath doesn't generally
-		 * use routing, but this is needed for tunnel cases.
-		 */
-		skb->pkt_type = PACKET_OUTGOING;
-
 		if (likely(!mru ||
 		           (skb->len <= mru + vport->dev->hard_header_len))) {
 			ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index ae5dea7c48a8..2cef4b08befb 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -68,7 +68,7 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]	   = { .type = NLA_U16 },
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]	   = { .type = NLA_U8 },
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]	   = { .type = NLA_BINARY,
-						       .len = 128 },
+						       .len = 127 },
 };
 
 static const struct nla_policy
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 03505673d523..099ff6a3e1f5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -766,7 +766,7 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]      = { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]       = { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]       = { .type = NLA_BINARY,
-						       .len = 128 },
+						       .len = 127 },
 };
 
 static const struct nla_policy
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 20ff7386b74b..f485f62ab721 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -123,8 +123,6 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	/* Check to update highest and lowest priorities. */
 	if (skb_queue_empty(lp_qdisc)) {
 		if (q->lowest_prio == q->highest_prio) {
-			/* The incoming packet is the only packet in queue. */
-			BUG_ON(sch->q.qlen != 1);
 			q->lowest_prio = prio;
 			q->highest_prio = prio;
 		} else {
@@ -156,7 +154,6 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch)
 	/* Update highest priority field. */
 	if (skb_queue_empty(hpq)) {
 		if (q->lowest_prio == q->highest_prio) {
-			BUG_ON(sch->q.qlen);
 			q->highest_prio = 0;
 			q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1;
 		} else {
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 8e1e97be4df7..ee3eac338a9d 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -525,6 +525,8 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static DEFINE_MUTEX(sctp_sysctl_mutex);
+
 static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -549,6 +551,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 		if (new_value > max || new_value < min)
 			return -EINVAL;
 
+		mutex_lock(&sctp_sysctl_mutex);
 		net->sctp.udp_port = new_value;
 		sctp_udp_sock_stop(net);
 		if (new_value) {
@@ -561,6 +564,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 		lock_sock(sk);
 		sctp_sk(sk)->udp_port = htons(net->sctp.udp_port);
 		release_sock(sk);
+		mutex_unlock(&sctp_sysctl_mutex);
 	}
 
 	return ret;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7e3db87ae433..fc6afbc8d680 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1551,7 +1551,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 	timeout = vsk->connect_timeout;
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-	while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
+	/* If the socket is already closing or it is in an error state, there
+	 * is no point in waiting.
+	 */
+	while (sk->sk_state != TCP_ESTABLISHED &&
+	       sk->sk_state != TCP_CLOSING && sk->sk_err == 0) {
 		if (flags & O_NONBLOCK) {
 			/* If we're not going to block, we schedule a timeout
 			 * function to generate a timeout on the connection