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

Pull networking fixes from David Miller:
 "Lots of bug fixes here:

   1) Out of bounds access in __bpf_skc_lookup, from Lorenz Bauer.

   2) Fix rate reporting in cfg80211_calculate_bitrate_he(), from John
      Crispin.

   3) Use after free in psock backlog workqueue, from John Fastabend.

   4) Fix source port matching in fdb peer flow rule of mlx5, from Raed
      Salem.

   5) Use atomic_inc_not_zero() in fl6_sock_lookup(), from Eric Dumazet.

   6) Network header needs to be set for packet redirect in nfp, from
      John Hurley.

   7) Fix udp zerocopy refcnt, from Willem de Bruijn.

   8) Don't assume linear buffers in vxlan and geneve error handlers,
      from Stefano Brivio.

   9) Fix TOS matching in mlxsw, from Jiri Pirko.

  10) More SCTP cookie memory leak fixes, from Neil Horman.

  11) Fix VLAN filtering in rtl8366, from Linus Walluij.

  12) Various TCP SACK payload size and fragmentation memory limit fixes
      from Eric Dumazet.

  13) Use after free in pneigh_get_next(), also from Eric Dumazet.

  14) LAPB control block leak fix from Jeremy Sowden"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (145 commits)
  lapb: fixed leak of control-blocks.
  tipc: purge deferredq list for each grp member in tipc_group_delete
  ax25: fix inconsistent lock state in ax25_destroy_timer
  neigh: fix use-after-free read in pneigh_get_next
  tcp: fix compile error if !CONFIG_SYSCTL
  hv_sock: Suppress bogus "may be used uninitialized" warnings
  be2net: Fix number of Rx queues used for flow hashing
  net: handle 802.1P vlan 0 packets properly
  tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
  tcp: add tcp_min_snd_mss sysctl
  tcp: tcp_fragment() should apply sane memory limits
  tcp: limit payload size of sacked skbs
  Revert "net: phylink: set the autoneg state in phylink_phy_change"
  bpf: fix nested bpf tracepoints with per-cpu data
  bpf: Fix out of bounds memory access in bpf_sk_storage
  vsock/virtio: set SOCK_DONE on peer shutdown
  net: dsa: rtl8366: Fix up VLAN filtering
  net: phylink: set the autoneg state in phylink_phy_change
  net: add high_order_alloc_disable sysctl/static key
  tcp: add tcp_tx_skb_cache sysctl
  ...

14 files changed, 63 insertions, 10 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index cb3c6b3b89c8..a7f7a98ec39d 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -238,6 +238,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx)		       \
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx)
 
+#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr)			\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_RECVMSG, NULL)
+
+#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr)			\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL)
+
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops)				       \
 ({									       \
 	int __ret = 0;							       \
@@ -339,6 +345,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5df8e9e2a393..b92ef9f73e42 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -600,7 +600,6 @@ void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 
 extern int sysctl_unprivileged_bpf_disabled;
-extern int sysctl_bpf_stats_enabled;
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 6411c624f63a..2d2e55dfea94 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -123,11 +123,20 @@ int mac_link_state(struct net_device *ndev,
  * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
  * @state: a pointer to a &struct phylink_link_state.
  *
+ * Note - not all members of @state are valid.  In particular,
+ * @state->lp_advertising, @state->link, @state->an_complete are never
+ * guaranteed to be correct, and so any mac_config() implementation must
+ * never reference these fields.
+ *
  * The action performed depends on the currently selected mode:
  *
  * %MLO_AN_FIXED, %MLO_AN_PHY:
  *   Configure the specified @state->speed, @state->duplex and
- *   @state->pause (%MLO_PAUSE_TX / %MLO_PAUSE_RX) mode.
+ *   @state->pause (%MLO_PAUSE_TX / %MLO_PAUSE_RX) modes over a link
+ *   specified by @state->interface.  @state->advertising may be used,
+ *   but is not required.  Other members of @state must be ignored.
+ *
+ *   Valid state members: interface, speed, duplex, pause, advertising.
  *
  * %MLO_AN_INBAND:
  *   place the link in an inband negotiation mode (such as 802.3z
@@ -150,6 +159,8 @@ int mac_link_state(struct net_device *ndev,
  *   responsible for reading the configuration word and configuring
  *   itself accordingly.
  *
+ *   Valid state members: interface, an_enabled, pause, advertising.
+ *
  * Implementations are expected to update the MAC to reflect the
  * requested settings - i.o.w., if nothing has changed between two
  * calls, no action is expected.  If only flow control settings have
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 178a3933a71b..50ced8aba9db 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -351,6 +351,8 @@ static inline void sk_psock_update_proto(struct sock *sk,
 static inline void sk_psock_restore_proto(struct sock *sk,
 					  struct sk_psock *psock)
 {
+	sk->sk_write_space = psock->saved_write_space;
+
 	if (psock->sk_proto) {
 		sk->sk_prot = psock->sk_proto;
 		psock->sk_proto = NULL;
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index b769ecfcc3bd..aadd310769d0 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -63,6 +63,9 @@ extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
 				      void __user *, size_t *, loff_t *);
 extern int proc_do_large_bitmap(struct ctl_table *, int,
 				void __user *, size_t *, loff_t *);
+extern int proc_do_static_key(struct ctl_table *table, int write,
+			      void __user *buffer, size_t *lenp,
+			      loff_t *ppos);
 
 /*
  * Register a set of sysctl names by calling register_sysctl_table
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 711361af9ce0..9a478a0cd3a2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -484,4 +484,8 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
 
 	return (user_mss && user_mss < mss) ? user_mss : mss;
 }
+
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
+		  int shiftlen);
+
 #endif	/* _LINUX_TCP_H */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 2f67ae854ff0..becdad576859 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -310,6 +310,22 @@ 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/cfg80211.h b/include/net/cfg80211.h
index 87dae868707e..948139690a58 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3839,7 +3839,8 @@ struct cfg80211_ops {
  *	on wiphy_new(), but can be changed by the driver if it has a good
  *	reason to override the default
  * @WIPHY_FLAG_4ADDR_AP: supports 4addr mode even on AP (with a single station
- *	on a VLAN interface)
+ *	on a VLAN interface). This flag also serves an extra purpose of
+ *	supporting 4ADDR AP mode on devices which do not support AP/VLAN iftype.
  * @WIPHY_FLAG_4ADDR_STATION: supports 4addr mode even as a station
  * @WIPHY_FLAG_CONTROL_PORT_PROTOCOL: This device supports setting the
  *	control port protocol ethertype. The device also honours the
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 7c5a8d9a8d2a..dfabc0503446 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -46,6 +46,7 @@ struct flow_dissector_key_tags {
 
 struct flow_dissector_key_vlan {
 	u16	vlan_id:12,
+		vlan_dei:1,
 		vlan_priority:3;
 	__be16	vlan_tpid;
 };
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 7698460a3dd1..623cfbb7b8dc 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -117,6 +117,7 @@ struct netns_ipv4 {
 #endif
 	int sysctl_tcp_mtu_probing;
 	int sysctl_tcp_base_mss;
+	int sysctl_tcp_min_snd_mss;
 	int sysctl_tcp_probe_threshold;
 	u32 sysctl_tcp_probe_interval;
 
diff --git a/include/net/sock.h b/include/net/sock.h
index e9d769c04637..6cbc16136357 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1463,12 +1463,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 		__sk_mem_reclaim(sk, 1 << 20);
 }
 
+DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	sk->sk_wmem_queued -= skb->truesize;
 	sk_mem_uncharge(sk, skb->truesize);
-	if (!sk->sk_tx_skb_cache && !skb_cloned(skb)) {
+	if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
+	    !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
 		skb_zcopy_clear(skb, true);
 		sk->sk_tx_skb_cache = skb;
 		return;
@@ -2433,13 +2435,11 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
  * This routine must be called with interrupts disabled or with the socket
  * locked so that the sk_buff queue operation is ok.
 */
+DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
-	if (
-#ifdef CONFIG_RPS
-	    !static_branch_unlikely(&rps_needed) &&
-#endif
+	if (static_branch_unlikely(&tcp_rx_skb_cache_key) &&
 	    !sk->sk_rx_skb_cache) {
 		sk->sk_rx_skb_cache = skb;
 		skb_orphan(skb);
@@ -2534,6 +2534,8 @@ extern int sysctl_optmem_max;
 extern __u32 sysctl_wmem_default;
 extern __u32 sysctl_rmem_default;
 
+DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
+
 static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
 {
 	/* Does this proto have per netns sysctl_wmem ? */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ac2f53fbfa6b..582c0caa9811 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -51,6 +51,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
+#define TCP_MIN_SND_MSS		48
+#define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
 
 /*
  * Never offer a window over 32767 without using window scaling. Some
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 63e0cf66f01a..a8b823c30b43 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -192,6 +192,8 @@ enum bpf_attach_type {
 	BPF_LIRC_MODE2,
 	BPF_FLOW_DISSECTOR,
 	BPF_CGROUP_SYSCTL,
+	BPF_CGROUP_UDP4_RECVMSG,
+	BPF_CGROUP_UDP6_RECVMSG,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3376,8 +3378,8 @@ struct bpf_raw_tracepoint_args {
 /* DIRECT:  Skip the FIB rules and go to FIB table associated with device
  * OUTPUT:  Do lookup from egress perspective; default is ingress
  */
-#define BPF_FIB_LOOKUP_DIRECT  BIT(0)
-#define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
+#define BPF_FIB_LOOKUP_DIRECT  (1U << 0)
+#define BPF_FIB_LOOKUP_OUTPUT  (1U << 1)
 
 enum {
 	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 86dc24a96c90..fd42c1316d3d 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -283,6 +283,7 @@ enum
 	LINUX_MIB_TCPACKCOMPRESSED,		/* TCPAckCompressed */
 	LINUX_MIB_TCPZEROWINDOWDROP,		/* TCPZeroWindowDrop */
 	LINUX_MIB_TCPRCVQDROP,			/* TCPRcvQDrop */
+	LINUX_MIB_TCPWQUEUETOOBIG,		/* TCPWqueueTooBig */
 	__LINUX_MIB_MAX
 };