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

Pull networking fixes from David Miller:

 1) Several nf_flow_table_offload fixes from Pablo Neira Ayuso,
    including adding a missing ipv6 match description.

 2) Several heap overflow fixes in mwifiex from qize wang and Ganapathi
    Bhat.

 3) Fix uninit value in bond_neigh_init(), from Eric Dumazet.

 4) Fix non-ACPI probing of nxp-nci, from Stephan Gerhold.

 5) Fix use after free in tipc_disc_rcv(), from Tuong Lien.

 6) Enforce limit of 33 tail calls in mips and riscv JIT, from Paul
    Chaignon.

 7) Multicast MAC limit test is off by one in qede, from Manish Chopra.

 8) Fix established socket lookup race when socket goes from
    TCP_ESTABLISHED to TCP_LISTEN, because there lacks an intervening
    RCU grace period. From Eric Dumazet.

 9) Don't send empty SKBs from tcp_write_xmit(), also from Eric Dumazet.

10) Fix active backup transition after link failure in bonding, from
    Mahesh Bandewar.

11) Avoid zero sized hash table in gtp driver, from Taehee Yoo.

12) Fix wrong interface passed to ->mac_link_up(), from Russell King.

13) Fix DSA egress flooding settings in b53, from Florian Fainelli.

14) Memory leak in gmac_setup_txqs(), from Navid Emamdoost.

15) Fix double free in dpaa2-ptp code, from Ioana Ciornei.

16) Reject invalid MTU values in stmmac, from Jose Abreu.

17) Fix refcount leak in error path of u32 classifier, from Davide
    Caratti.

18) Fix regression causing iwlwifi firmware crashes on boot, from Anders
    Kaseorg.

19) Fix inverted return value logic in llc2 code, from Chan Shu Tak.

20) Disable hardware GRO when XDP is attached to qede, frm Manish
    Chopra.

21) Since we encode state in the low pointer bits, dst metrics must be
    at least 4 byte aligned, which is not necessarily true on m68k. Add
    annotations to fix this, from Geert Uytterhoeven.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (160 commits)
  sfc: Include XDP packet headroom in buffer step size.
  sfc: fix channel allocation with brute force
  net: dst: Force 4-byte alignment of dst_metrics
  selftests: pmtu: fix init mtu value in description
  hv_netvsc: Fix unwanted rx_table reset
  net: phy: ensure that phy IDs are correctly typed
  mod_devicetable: fix PHY module format
  qede: Disable hardware gro when xdp prog is installed
  net: ena: fix issues in setting interrupt moderation params in ethtool
  net: ena: fix default tx interrupt moderation interval
  net/smc: unregister ib devices in reboot_event
  net: stmmac: platform: Fix MDIO init for platforms without PHY
  llc2: Fix return statement of llc_stat_ev_rx_null_dsap_xid_c (and _test_c)
  net: hisilicon: Fix a BUG trigered by wrong bytes_compl
  net: dsa: ksz: use common define for tag len
  s390/qeth: don't return -ENOTSUPP to userspace
  s390/qeth: fix promiscuous mode after reset
  s390/qeth: handle error due to unsupported transport mode
  cxgb4: fix refcount init for TC-MQPRIO offload
  tc-testing: initial tdc selftests for cls_u32
  ...

15 files changed, 91 insertions, 20 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 169fd25f6bc2..9be71c195d74 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -157,8 +157,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
 			     struct cgroup *cgroup,
 			     enum bpf_attach_type type);
 void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
-int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map);
-void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map);
+int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map);
+void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map);
 
 int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
@@ -360,9 +360,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 
 static inline void bpf_cgroup_storage_set(
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {}
-static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog,
+static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux,
 					    struct bpf_map *map) { return 0; }
-static inline void bpf_cgroup_storage_release(struct bpf_prog *prog,
+static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux,
 					      struct bpf_map *map) {}
 static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
 	struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 35903f148be5..085a59afba85 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -461,6 +461,7 @@ struct bpf_trampoline {
 	struct {
 		struct btf_func_model model;
 		void *addr;
+		bool ftrace_managed;
 	} func;
 	/* list of BPF programs using this trampoline */
 	struct hlist_head progs_hlist[BPF_TRAMP_MAX];
@@ -817,6 +818,8 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 int __bpf_prog_charge(struct user_struct *user, u32 pages);
 void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
+void __bpf_free_used_maps(struct bpf_prog_aux *aux,
+			  struct bpf_map **used_maps, u32 len);
 
 void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 5714fd35a83c..e3596db077dc 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -587,9 +587,9 @@ struct platform_device_id {
 #define MDIO_NAME_SIZE		32
 #define MDIO_MODULE_PREFIX	"mdio:"
 
-#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d"
+#define MDIO_ID_FMT "%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u"
 #define MDIO_ID_ARGS(_id) \
-	(_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1,	\
+	((_id)>>31) & 1, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \
 	((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \
 	((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \
 	((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9ef20389622d..ae5e260911e2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1775,7 +1775,7 @@ enum netdev_priv_flags {
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
  *	@qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock
-				spinlock
+ *				spinlock
  *	@qdisc_running_key:	lockdep class annotating Qdisc->running seqcount
  *	@qdisc_xmit_lock_key:	lockdep class annotating
  *				netdev_queue->_xmit_lock spinlock
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 99cefe6f5edb..79bc82e30c02 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 
 #if IS_ENABLED(CONFIG_OF_MDIO)
+extern bool of_mdiobus_child_is_phy(struct device_node *child);
 extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
 extern struct phy_device *of_phy_find_device(struct device_node *phy_np);
 extern struct phy_device *of_phy_connect(struct net_device *dev,
@@ -54,6 +55,11 @@ static inline int of_mdio_parse_addr(struct device *dev,
 }
 
 #else /* CONFIG_OF_MDIO */
+static bool of_mdiobus_child_is_phy(struct device_node *child)
+{
+	return false;
+}
+
 static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 {
 	/*
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 5032d453ac66..dd4a91f1feaa 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1000,7 +1000,7 @@ int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum,
 int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum,
 		     u16 mask, u16 set);
 
-struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
+struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
 #if IS_ENABLED(CONFIG_PHYLIB)
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index bc8206a8f30e..61974c4c566b 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -101,6 +101,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 }
 
 /**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist_nulls,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					    struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	/* Note: write side code, so rcu accessors are not needed. */
+	for (i = h->first; !is_a_nulls(i); i = i->next)
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
+/**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct hlist_nulls_node to use as a loop cursor.
diff --git a/include/net/dst.h b/include/net/dst.h
index fe62fe2eb781..8224dad2ae94 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -82,7 +82,7 @@ struct dst_entry {
 struct dst_metrics {
 	u32		metrics[RTAX_MAX];
 	refcount_t	refcnt;
-};
+} __aligned(4);		/* Low pointer bits contain DST_METRICS_FLAGS */
 extern const struct dst_metrics dst_default_metrics;
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index af2b4c065a04..d0019d3395cf 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -103,13 +103,19 @@ struct inet_bind_hashbucket {
 	struct hlist_head	chain;
 };
 
-/*
- * Sockets can be hashed in established or listening table
+/* Sockets can be hashed in established or listening table.
+ * We must use different 'nulls' end-of-chain value for all hash buckets :
+ * A socket might transition from ESTABLISH to LISTEN state without
+ * RCU grace period. A lookup in ehash table needs to handle this case.
  */
+#define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
 	unsigned int		count;
-	struct hlist_head	head;
+	union {
+		struct hlist_head	head;
+		struct hlist_nulls_head	nulls_head;
+	};
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 6ad9ad47a9c5..8ec77bfdc1a4 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -72,7 +72,6 @@ struct neigh_parms {
 	struct net_device *dev;
 	struct list_head list;
 	int	(*neigh_setup)(struct neighbour *);
-	void	(*neigh_cleanup)(struct neighbour *);
 	struct neigh_table *tbl;
 
 	void	*sysctl_table;
diff --git a/include/net/sock.h b/include/net/sock.h
index 80f996406bba..8dff68b4c316 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -722,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
+static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+}
+
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	sock_hold(sk);
@@ -2583,9 +2588,9 @@ static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
  */
 static inline void sk_pacing_shift_update(struct sock *sk, int val)
 {
-	if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val)
+	if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val)
 		return;
-	sk->sk_pacing_shift = val;
+	WRITE_ONCE(sk->sk_pacing_shift, val);
 }
 
 /* if a socket is bound to a device, check that the given device
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 86b9a8766648..e460ea7f767b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1766,9 +1766,18 @@ static inline bool tcp_skb_is_last(const struct sock *sk,
 	return skb_queue_is_last(&sk->sk_write_queue, skb);
 }
 
+/**
+ * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue
+ * @sk: socket
+ *
+ * Since the write queue can have a temporary empty skb in it,
+ * we must not use "return skb_queue_empty(&sk->sk_write_queue)"
+ */
 static inline bool tcp_write_queue_empty(const struct sock *sk)
 {
-	return skb_queue_empty(&sk->sk_write_queue);
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	return tp->write_seq == tp->snd_nxt;
 }
 
 static inline bool tcp_rtx_queue_empty(const struct sock *sk)
diff --git a/include/net/x25.h b/include/net/x25.h
index ed1acc3044ac..d7d6c2b4ffa7 100644
--- a/include/net/x25.h
+++ b/include/net/x25.h
@@ -62,7 +62,8 @@ enum {
 	X25_STATE_1,		/* Awaiting Call Accepted */
 	X25_STATE_2,		/* Awaiting Clear Confirmation */
 	X25_STATE_3,		/* Data Transfer */
-	X25_STATE_4		/* Awaiting Reset Confirmation */
+	X25_STATE_4,		/* Awaiting Reset Confirmation */
+	X25_STATE_5		/* Call Accepted / Call Connected pending */
 };
 
 enum {
diff --git a/include/uapi/linux/netfilter/xt_sctp.h b/include/uapi/linux/netfilter/xt_sctp.h
index 4bc6d1a08781..b4d804a9fccb 100644
--- a/include/uapi/linux/netfilter/xt_sctp.h
+++ b/include/uapi/linux/netfilter/xt_sctp.h
@@ -41,19 +41,19 @@ struct xt_sctp_info {
 #define SCTP_CHUNKMAP_SET(chunkmap, type) 		\
 	do { 						\
 		(chunkmap)[type / bytes(__u32)] |= 	\
-			1 << (type % bytes(__u32));	\
+			1u << (type % bytes(__u32));	\
 	} while (0)
 
 #define SCTP_CHUNKMAP_CLEAR(chunkmap, type)		 	\
 	do {							\
 		(chunkmap)[type / bytes(__u32)] &= 		\
-			~(1 << (type % bytes(__u32)));	\
+			~(1u << (type % bytes(__u32)));	\
 	} while (0)
 
 #define SCTP_CHUNKMAP_IS_SET(chunkmap, type) 			\
 ({								\
 	((chunkmap)[type / bytes (__u32)] & 		\
-		(1 << (type % bytes (__u32)))) ? 1: 0;	\
+		(1u << (type % bytes (__u32)))) ? 1: 0;	\
 })
 
 #define SCTP_CHUNKMAP_RESET(chunkmap) \
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 341e0e8cae46..5eab191607f8 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -5517,6 +5517,10 @@ enum nl80211_feature_flags {
  *	with VLAN tagged frames and separate VLAN-specific netdevs added using
  *	vconfig similarly to the Ethernet case.
  *
+ * @NL80211_EXT_FEATURE_AQL: The driver supports the Airtime Queue Limit (AQL)
+ *	feature, which prevents bufferbloat by using the expected transmission
+ *	time to limit the amount of data buffered in the hardware.
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -5563,6 +5567,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_STA_TX_PWR,
 	NL80211_EXT_FEATURE_SAE_OFFLOAD,
 	NL80211_EXT_FEATURE_VLAN_OFFLOAD,
+	NL80211_EXT_FEATURE_AQL,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,