Merging upstream version 4.19.304.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

15 files changed, 123 insertions, 60 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index db2a87981..9583d3bba 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -341,6 +341,22 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev)
 }
 
 /**
+ * __in6_dev_stats_get - get inet6_dev pointer for stats
+ * @dev: network device
+ * @skb: skb for original incoming interface if neeeded
+ *
+ * Caller must hold rcu_read_lock or RTNL, because this function
+ * does not take a reference on the inet6_dev.
+ */
+static inline struct inet6_dev *__in6_dev_stats_get(const struct net_device *dev,
+						    const struct sk_buff *skb)
+{
+	if (netif_is_l3_master(dev))
+		dev = dev_get_by_index_rcu(dev_net(dev), inet6_iif(skb));
+	return __in6_dev_get(dev);
+}
+
+/**
  * __in6_dev_get_safely - get inet6_dev pointer from netdevice
  * @dev: network device
  *
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 464a78200..d3503f8c0 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -209,7 +209,7 @@ struct hci_dev {
 	struct list_head list;
 	struct mutex	lock;
 
-	char		name[8];
+	const char	*name;
 	unsigned long	flags;
 	__u16		id;
 	__u8		bus;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index c458f084f..7d317434e 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -675,37 +675,14 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond,
 }
 
 /* Caller must hold rcu_read_lock() for read */
-static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond,
-					       const u8 *mac)
+static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac)
 {
 	struct list_head *iter;
 	struct slave *tmp;
 
 	bond_for_each_slave_rcu(bond, tmp, iter)
 		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
-			return tmp;
-
-	return NULL;
-}
-
-/* Caller must hold rcu_read_lock() for read */
-static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac)
-{
-	struct list_head *iter;
-	struct slave *tmp;
-	struct netdev_hw_addr *ha;
-
-	bond_for_each_slave_rcu(bond, tmp, iter)
-		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
 			return true;
-
-	if (netdev_uc_empty(bond->dev))
-		return false;
-
-	netdev_for_each_uc_addr(ha, bond->dev)
-		if (ether_addr_equal_64bits(mac, ha->addr))
-			return true;
-
 	return false;
 }
 
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b96debd18..157b74fab 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -370,6 +370,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband,
 	if (WARN_ON(iftype >= NL80211_IFTYPE_MAX))
 		return NULL;
 
+	if (iftype == NL80211_IFTYPE_AP_VLAN)
+		iftype = NL80211_IFTYPE_AP;
+
 	for (i = 0; i < sband->n_iftype_data; i++)  {
 		const struct ieee80211_sband_iftype_data *data =
 			&sband->iftype_data[i];
diff --git a/include/net/dst.h b/include/net/dst.h
index 50258a813..972679976 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -362,9 +362,8 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
 static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
 				 struct net *net)
 {
-	/* TODO : stats should be SMP safe */
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += skb->len;
+	DEV_STATS_INC(dev, rx_packets);
+	DEV_STATS_ADD(dev, rx_bytes, skb->len);
 	__skb_tunnel_rx(skb, dev, net);
 }
 
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 3e3a1a388..b8b7edcfc 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -11,9 +11,12 @@
 /**
  * struct genl_multicast_group - generic netlink multicast group
  * @name: name of the multicast group, names are per-family
+ * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding
  */
 struct genl_multicast_group {
 	char			name[GENL_NAMSIZ];
+	u8			flags;
+	u8			cap_sys_admin:1;
 };
 
 struct genl_ops;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0c8832498..3a55a0931 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -602,12 +602,8 @@ static inline u32 ipv6_addr_hash(const struct in6_addr *a)
 /* more secured version of ipv6_addr_hash() */
 static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval)
 {
-	u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1];
-
-	return jhash_3words(v,
-			    (__force u32)a->s6_addr32[2],
-			    (__force u32)a->s6_addr32[3],
-			    initval);
+	return jhash2((__force const u32 *)a->s6_addr32,
+		      ARRAY_SIZE(a->s6_addr32), initval);
 }
 
 static inline bool ipv6_addr_loopback(const struct in6_addr *a)
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 33fd9ba7e..ec75c0a1c 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -16,9 +16,12 @@
 #define LWTUNNEL_STATE_INPUT_REDIRECT	BIT(1)
 #define LWTUNNEL_STATE_XMIT_REDIRECT	BIT(2)
 
+/* LWTUNNEL_XMIT_CONTINUE should be distinguishable from dst_output return
+ * values (NET_XMIT_xxx and NETDEV_TX_xxx in linux/netdevice.h) for safety.
+ */
 enum {
 	LWTUNNEL_XMIT_DONE,
-	LWTUNNEL_XMIT_CONTINUE,
+	LWTUNNEL_XMIT_CONTINUE = 0x100,
 };
 
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1b4f47a87..fd8528648 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -736,6 +736,7 @@ struct nft_expr_type {
 
 enum nft_trans_phase {
 	NFT_TRANS_PREPARE,
+	NFT_TRANS_PREPARE_ERROR,
 	NFT_TRANS_ABORT,
 	NFT_TRANS_COMMIT,
 	NFT_TRANS_RELEASE
@@ -991,6 +992,29 @@ int __nft_release_basechain(struct nft_ctx *ctx);
 
 unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
 
+static inline bool nft_use_inc(u32 *use)
+{
+	if (*use == UINT_MAX)
+		return false;
+
+	(*use)++;
+
+	return true;
+}
+
+static inline void nft_use_dec(u32 *use)
+{
+	WARN_ON_ONCE((*use)-- == 0);
+}
+
+/* For error and abort path: restore use counter to previous state. */
+static inline void nft_use_inc_restore(u32 *use)
+{
+	WARN_ON_ONCE(!nft_use_inc(use));
+}
+
+#define nft_use_dec_restore	nft_use_dec
+
 /**
  *	struct nft_table - nf_tables table
  *
@@ -1049,8 +1073,8 @@ struct nft_object {
 	struct list_head		list;
 	char				*name;
 	struct nft_table		*table;
-	u32				genmask:2,
-					use:30;
+	u32				genmask:2;
+	u32				use;
 	u64				handle;
 	/* runtime data below here */
 	const struct nft_object_ops	*ops ____cacheline_aligned;
@@ -1148,8 +1172,8 @@ struct nft_flowtable {
 	int				hooknum;
 	int				priority;
 	int				ops_len;
-	u32				genmask:2,
-					use:30;
+	u32				genmask:2;
+	u32				use;
 	u64				handle;
 	/* runtime data below here */
 	struct nf_hook_ops		*ops ____cacheline_aligned;
@@ -1160,6 +1184,10 @@ struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
 					   const struct nlattr *nla,
 					   u8 genmask);
 
+void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx,
+				    struct nft_flowtable *flowtable,
+				    enum nft_trans_phase phase);
+
 void nft_register_flowtable_type(struct nf_flowtable_type *type);
 void nft_unregister_flowtable_type(struct nf_flowtable_type *type);
 
@@ -1319,12 +1347,14 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext)
  *	struct nft_trans - nf_tables object update in transaction
  *
  *	@list: used internally
+ *	@binding_list: list of objects with possible bindings
  *	@msg_type: message type
  *	@ctx: transaction context
  *	@data: internal information related to the transaction
  */
 struct nft_trans {
 	struct list_head		list;
+	struct list_head		binding_list;
 	int				msg_type;
 	struct nft_ctx			ctx;
 	char				data[0];
@@ -1409,4 +1439,15 @@ struct nft_trans_flowtable {
 int __init nft_chain_filter_init(void);
 void nft_chain_filter_fini(void);
 
+struct nftables_pernet {
+	struct list_head	tables;
+	struct list_head	commit_list;
+	struct list_head	binding_list;
+	struct list_head	module_list;
+	struct list_head	notify_list;
+	struct mutex		commit_mutex;
+	unsigned int		base_seq;
+	u8			validate_state;
+};
+
 #endif /* _NET_NF_TABLES_H */
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 286fd9608..8c77832d0 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -5,12 +5,7 @@
 #include <linux/list.h>
 
 struct netns_nftables {
-	struct list_head	tables;
-	struct list_head	commit_list;
-	struct mutex		commit_mutex;
-	unsigned int		base_seq;
 	u8			gencursor;
-	u8			validate_state;
 };
 
 #endif
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index fbfa59801..9a5212b46 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -48,6 +48,7 @@ struct netns_xfrm {
 	struct list_head	policy_all;
 	struct hlist_head	*policy_byidx;
 	unsigned int		policy_idx_hmask;
+	unsigned int		idx_generator;
 	struct hlist_head	policy_inexact[XFRM_POLICY_MAX];
 	struct xfrm_policy_hash	policy_bydst[XFRM_POLICY_MAX];
 	unsigned int		policy_count[XFRM_POLICY_MAX * 2];
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index bbdc73a32..8b86560b5 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -278,7 +278,7 @@ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk,
 struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp);
 
 int nfc_set_remote_general_bytes(struct nfc_dev *dev,
-				 u8 *gt, u8 gt_len);
+				 const u8 *gt, u8 gt_len);
 u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len);
 
 int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name,
@@ -292,7 +292,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx,
 		       u8 comm_mode, u8 rf_mode);
 
 int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode,
-		     u8 *gb, size_t gb_len);
+		     const u8 *gb, size_t gb_len);
 int nfc_tm_deactivated(struct nfc_dev *dev);
 int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb);
 
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index e09ea6917..83a16f3bd 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -131,7 +131,7 @@ extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
  */
 static inline unsigned int psched_mtu(const struct net_device *dev)
 {
-	return dev->mtu + dev->hard_header_len;
+	return READ_ONCE(dev->mtu) + dev->hard_header_len;
 }
 
 static inline struct net *qdisc_net(struct Qdisc *q)
diff --git a/include/net/sock.h b/include/net/sock.h
index 616e84d16..81888513b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1152,6 +1152,7 @@ struct proto {
 	/*
 	 * Pressure flag: try to collapse.
 	 * Technical note: it is used by multiple contexts non atomically.
+	 * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes.
 	 * All the __sk_mem_schedule() is of this nature: accounting
 	 * is strict, actions are advisory and have some latency.
 	 */
@@ -1265,6 +1266,12 @@ static inline bool sk_has_memory_pressure(const struct sock *sk)
 	return sk->sk_prot->memory_pressure != NULL;
 }
 
+static inline bool sk_under_global_memory_pressure(const struct sock *sk)
+{
+	return sk->sk_prot->memory_pressure &&
+		!!READ_ONCE(*sk->sk_prot->memory_pressure);
+}
+
 static inline bool sk_under_memory_pressure(const struct sock *sk)
 {
 	if (!sk->sk_prot->memory_pressure)
@@ -1274,7 +1281,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
 	    mem_cgroup_under_socket_pressure(sk->sk_memcg))
 		return true;
 
-	return !!*sk->sk_prot->memory_pressure;
+	return !!READ_ONCE(*sk->sk_prot->memory_pressure);
 }
 
 static inline long
@@ -1328,7 +1335,7 @@ proto_memory_pressure(struct proto *prot)
 {
 	if (!prot->memory_pressure)
 		return false;
-	return !!*prot->memory_pressure;
+	return !!READ_ONCE(*prot->memory_pressure);
 }
 
 
@@ -1752,21 +1759,33 @@ static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
 	/* sk_tx_queue_mapping accept only upto a 16-bit value */
 	if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX))
 		return;
-	sk->sk_tx_queue_mapping = tx_queue;
+	/* Paired with READ_ONCE() in sk_tx_queue_get() and
+	 * other WRITE_ONCE() because socket lock might be not held.
+	 */
+	WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue);
 }
 
 #define NO_QUEUE_MAPPING	USHRT_MAX
 
 static inline void sk_tx_queue_clear(struct sock *sk)
 {
-	sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING;
+	/* Paired with READ_ONCE() in sk_tx_queue_get() and
+	 * other WRITE_ONCE() because socket lock might be not held.
+	 */
+	WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING);
 }
 
 static inline int sk_tx_queue_get(const struct sock *sk)
 {
-	if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING)
-		return sk->sk_tx_queue_mapping;
+	if (sk) {
+		/* Paired with WRITE_ONCE() in sk_tx_queue_clear()
+		 * and sk_tx_queue_set().
+		 */
+		int val = READ_ONCE(sk->sk_tx_queue_mapping);
 
+		if (val != NO_QUEUE_MAPPING)
+			return val;
+	}
 	return -1;
 }
 
@@ -1840,6 +1859,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 }
 
 kuid_t sock_i_uid(struct sock *sk);
+unsigned long __sock_i_ino(struct sock *sk);
 unsigned long sock_i_ino(struct sock *sk);
 
 static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
@@ -1898,7 +1918,7 @@ static inline void dst_negative_advice(struct sock *sk)
 		if (ndst != dst) {
 			rcu_assign_pointer(sk->sk_dst_cache, ndst);
 			sk_tx_queue_clear(sk);
-			sk->sk_dst_pending_confirm = 0;
+			WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
 		}
 	}
 }
@@ -1909,7 +1929,7 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 	struct dst_entry *old_dst;
 
 	sk_tx_queue_clear(sk);
-	sk->sk_dst_pending_confirm = 0;
+	WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
 	old_dst = rcu_dereference_protected(sk->sk_dst_cache,
 					    lockdep_sock_is_held(sk));
 	rcu_assign_pointer(sk->sk_dst_cache, dst);
@@ -1922,7 +1942,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst)
 	struct dst_entry *old_dst;
 
 	sk_tx_queue_clear(sk);
-	sk->sk_dst_pending_confirm = 0;
+	WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
 	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
 	dst_release(old_dst);
 }
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 81300a04b..49da4d4a3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -128,6 +128,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 				  * to combine FIN-WAIT-2 timeout with
 				  * TIME-WAIT timer.
 				  */
+#define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */
 
 #define TCP_DELACK_MAX	((unsigned)(HZ/5))	/* maximal time to delay before sending an ACK */
 #if HZ >= 100
@@ -140,6 +141,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCP_RTO_MAX	((unsigned)(120*HZ))
 #define TCP_RTO_MIN	((unsigned)(HZ/5))
 #define TCP_TIMEOUT_MIN	(2U) /* Min timeout for TCP timers in jiffies */
+
+#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */
+
 #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
 #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ))	/* RFC 1122 initial RTO value, now
 						 * used as a fallback RTO for the
@@ -345,13 +349,14 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
-static inline void tcp_dec_quickack_mode(struct sock *sk,
-					 const unsigned int pkts)
+static inline void tcp_dec_quickack_mode(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (icsk->icsk_ack.quick) {
+		/* How many ACKs S/ACKing new data have we sent? */
+		const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0;
+
 		if (pkts >= icsk->icsk_ack.quick) {
 			icsk->icsk_ack.quick = 0;
 			/* Leaving quickack mode we deflate ATO. */
@@ -1882,7 +1887,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
 static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 {
 	struct net *net = sock_net((struct sock *)tp);
-	return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
+	u32 val;
+
+	val = READ_ONCE(tp->notsent_lowat);
+
+	return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
 }
 
 /* @wake is one when sk_stream_write_space() calls us.