Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Fix cfg80211 deadlock, from Johannes Berg.

 2) RXRPC fails to send norigications, from David Howells.

 3) MPTCP RM_ADDR parsing has an off by one pointer error, fix from
    Geliang Tang.

 4) Fix crash when using MSG_PEEK with sockmap, from Anny Hu.

 5) The ucc_geth driver needs __netdev_watchdog_up exported, from
    Valentin Longchamp.

 6) Fix hashtable memory leak in dccp, from Wang Hai.

 7) Fix how nexthops are marked as FDB nexthops, from David Ahern.

 8) Fix mptcp races between shutdown and recvmsg, from Paolo Abeni.

 9) Fix crashes in tipc_disc_rcv(), from Tuong Lien.

10) Fix link speed reporting in iavf driver, from Brett Creeley.

11) When a channel is used for XSK and then reused again later for XSK,
    we forget to clear out the relevant data structures in mlx5 which
    causes all kinds of problems. Fix from Maxim Mikityanskiy.

12) Fix memory leak in genetlink, from Cong Wang.

13) Disallow sockmap attachments to UDP sockets, it simply won't work.
    From Lorenz Bauer.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (83 commits)
  net: ethernet: ti: ale: fix allmulti for nu type ale
  net: ethernet: ti: am65-cpsw-nuss: fix ale parameters init
  net: atm: Remove the error message according to the atomic context
  bpf: Undo internal BPF_PROBE_MEM in BPF insns dump
  libbpf: Support pre-initializing .bss global variables
  tools/bpftool: Fix skeleton codegen
  bpf: Fix memlock accounting for sock_hash
  bpf: sockmap: Don't attach programs to UDP sockets
  bpf: tcp: Recv() should return 0 when the peer socket is closed
  ibmvnic: Flush existing work items before device removal
  genetlink: clean up family attributes allocations
  net: ipa: header pad field only valid for AP->modem endpoint
  net: ipa: program upper nibbles of sequencer type
  net: ipa: fix modem LAN RX endpoint id
  net: ipa: program metadata mask differently
  ionic: add pcie_print_link_status
  rxrpc: Fix race between incoming ACK parser and retransmitter
  net/mlx5: E-Switch, Fix some error pointer dereferences
  net/mlx5: Don't fail driver on failure to create debugfs
  net/mlx5e: CT: Fix ipv6 nat header rewrite actions
  ...

5 files changed, 63 insertions, 37 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 061496a1f640..6bc2388141f6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -439,6 +439,7 @@ static const char *const netdev_lock_name[] = {
 	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
 
 static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
+static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
 
 static inline unsigned short netdev_lock_pos(unsigned short dev_type)
 {
@@ -460,11 +461,25 @@ static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
 	lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
 				   netdev_lock_name[i]);
 }
+
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
+{
+	int i;
+
+	i = netdev_lock_pos(dev->type);
+	lockdep_set_class_and_name(&dev->addr_list_lock,
+				   &netdev_addr_lock_key[i],
+				   netdev_lock_name[i]);
+}
 #else
 static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
 						 unsigned short dev_type)
 {
 }
+
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
+{
+}
 #endif
 
 /*******************************************************************************
@@ -9373,15 +9388,6 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
-void netdev_update_lockdep_key(struct net_device *dev)
-{
-	lockdep_unregister_key(&dev->addr_list_lock_key);
-	lockdep_register_key(&dev->addr_list_lock_key);
-
-	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
-}
-EXPORT_SYMBOL(netdev_update_lockdep_key);
-
 /**
  *	register_netdevice	- register a network device
  *	@dev: device to register
@@ -9420,7 +9426,7 @@ int register_netdevice(struct net_device *dev)
 		return ret;
 
 	spin_lock_init(&dev->addr_list_lock);
-	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
+	netdev_set_addr_lockdep_class(dev);
 
 	ret = dev_get_valid_name(net, dev, dev->name);
 	if (ret < 0)
@@ -9939,8 +9945,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
-	lockdep_register_key(&dev->addr_list_lock_key);
-
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
 	dev->upper_level = 1;
@@ -10028,8 +10032,6 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->xdp_bulkq);
 	dev->xdp_bulkq = NULL;
 
-	lockdep_unregister_key(&dev->addr_list_lock_key);
-
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 2f949b5a1eb9..6393ba930097 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
 		return;
 
 	netif_addr_lock_bh(from);
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
 	__dev_set_rx_mode(to);
 	netif_addr_unlock(to);
@@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
 		return;
 
 	netif_addr_lock_bh(from);
-	netif_addr_lock(to);
+	netif_addr_lock_nested(to);
 	__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
 	__dev_set_rx_mode(to);
 	netif_addr_unlock(to);
diff --git a/net/core/filter.c b/net/core/filter.c
index 209482a4eaa2..73395384afe2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1755,25 +1755,27 @@ BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
 	   u32, offset, void *, to, u32, len, u32, start_header)
 {
 	u8 *end = skb_tail_pointer(skb);
-	u8 *net = skb_network_header(skb);
-	u8 *mac = skb_mac_header(skb);
-	u8 *ptr;
+	u8 *start, *ptr;
 
-	if (unlikely(offset > 0xffff || len > (end - mac)))
+	if (unlikely(offset > 0xffff))
 		goto err_clear;
 
 	switch (start_header) {
 	case BPF_HDR_START_MAC:
-		ptr = mac + offset;
+		if (unlikely(!skb_mac_header_was_set(skb)))
+			goto err_clear;
+		start = skb_mac_header(skb);
 		break;
 	case BPF_HDR_START_NET:
-		ptr = net + offset;
+		start = skb_network_header(skb);
 		break;
 	default:
 		goto err_clear;
 	}
 
-	if (likely(ptr >= mac && ptr + len <= end)) {
+	ptr = start + offset;
+
+	if (likely(ptr + len <= end)) {
 		memcpy(to, ptr, len);
 		return 0;
 	}
@@ -4340,8 +4342,6 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			}
 			break;
 		case SO_BINDTODEVICE:
-			ret = -ENOPROTOOPT;
-#ifdef CONFIG_NETDEVICES
 			optlen = min_t(long, optlen, IFNAMSIZ - 1);
 			strncpy(devname, optval, optlen);
 			devname[optlen] = 0;
@@ -4360,7 +4360,6 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				dev_put(dev);
 			}
 			ret = sock_bindtoindex(sk, ifindex, false);
-#endif
 			break;
 		default:
 			ret = -EINVAL;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2269199c5891..9aedc15736ad 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2462,7 +2462,6 @@ static int do_set_master(struct net_device *dev, int ifindex,
 			err = ops->ndo_del_slave(upper_dev, dev);
 			if (err)
 				return err;
-			netdev_update_lockdep_key(dev);
 		} else {
 			return -EOPNOTSUPP;
 		}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 00a26cf2cfe9..4059f94e9bb5 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -424,10 +424,7 @@ static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next)
 	return 0;
 }
 
-static bool sock_map_redirect_allowed(const struct sock *sk)
-{
-	return sk->sk_state != TCP_LISTEN;
-}
+static bool sock_map_redirect_allowed(const struct sock *sk);
 
 static int sock_map_update_common(struct bpf_map *map, u32 idx,
 				  struct sock *sk, u64 flags)
@@ -508,6 +505,11 @@ static bool sk_is_udp(const struct sock *sk)
 	       sk->sk_protocol == IPPROTO_UDP;
 }
 
+static bool sock_map_redirect_allowed(const struct sock *sk)
+{
+	return sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN;
+}
+
 static bool sock_map_sk_is_suitable(const struct sock *sk)
 {
 	return sk_is_tcp(sk) || sk_is_udp(sk);
@@ -989,11 +991,15 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 		err = -EINVAL;
 		goto free_htab;
 	}
+	err = bpf_map_charge_init(&htab->map.memory, cost);
+	if (err)
+		goto free_htab;
 
 	htab->buckets = bpf_map_area_alloc(htab->buckets_num *
 					   sizeof(struct bpf_htab_bucket),
 					   htab->map.numa_node);
 	if (!htab->buckets) {
+		bpf_map_charge_finish(&htab->map.memory);
 		err = -ENOMEM;
 		goto free_htab;
 	}
@@ -1013,6 +1019,7 @@ static void sock_hash_free(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 	struct bpf_htab_bucket *bucket;
+	struct hlist_head unlink_list;
 	struct bpf_htab_elem *elem;
 	struct hlist_node *node;
 	int i;
@@ -1024,13 +1031,32 @@ static void sock_hash_free(struct bpf_map *map)
 	synchronize_rcu();
 	for (i = 0; i < htab->buckets_num; i++) {
 		bucket = sock_hash_select_bucket(htab, i);
-		hlist_for_each_entry_safe(elem, node, &bucket->head, node) {
-			hlist_del_rcu(&elem->node);
+
+		/* We are racing with sock_hash_delete_from_link to
+		 * enter the spin-lock critical section. Every socket on
+		 * the list is still linked to sockhash. Since link
+		 * exists, psock exists and holds a ref to socket. That
+		 * lets us to grab a socket ref too.
+		 */
+		raw_spin_lock_bh(&bucket->lock);
+		hlist_for_each_entry(elem, &bucket->head, node)
+			sock_hold(elem->sk);
+		hlist_move_list(&bucket->head, &unlink_list);
+		raw_spin_unlock_bh(&bucket->lock);
+
+		/* Process removed entries out of atomic context to
+		 * block for socket lock before deleting the psock's
+		 * link to sockhash.
+		 */
+		hlist_for_each_entry_safe(elem, node, &unlink_list, node) {
+			hlist_del(&elem->node);
 			lock_sock(elem->sk);
 			rcu_read_lock();
 			sock_map_unref(elem->sk, elem);
 			rcu_read_unlock();
 			release_sock(elem->sk);
+			sock_put(elem->sk);
+			sock_hash_free_elem(htab, elem);
 		}
 	}