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

Pull networking fixes from David Miller:

 1) Limit xt_hashlimit hash table size to avoid OOM or hung tasks, from
    Cong Wang.

 2) Fix deadlock in xsk by publishing global consumer pointers when NAPI
    is finished, from Magnus Karlsson.

 3) Set table field properly to RT_TABLE_COMPAT when necessary, from
    Jethro Beekman.

 4) NLA_STRING attributes are not necessary NULL terminated, deal wiht
    that in IFLA_ALT_IFNAME. From Eric Dumazet.

 5) Fix checksum handling in atlantic driver, from Dmitry Bezrukov.

 6) Handle mtu==0 devices properly in wireguard, from Jason A.
    Donenfeld.

 7) Fix several lockdep warnings in bonding, from Taehee Yoo.

 8) Fix cls_flower port blocking, from Jason Baron.

 9) Sanitize internal map names in libbpf, from Toke Høiland-Jørgensen.

10) Fix RDMA race in qede driver, from Michal Kalderon.

11) Fix several false lockdep warnings by adding conditions to
    list_for_each_entry_rcu(), from Madhuparna Bhowmik.

12) Fix sleep in atomic in mlx5 driver, from Huy Nguyen.

13) Fix potential deadlock in bpf_map_do_batch(), from Yonghong Song.

14) Hey, variables declared in switch statement before any case
    statements are not initialized. I learn something every day. Get
    rids of this stuff in several parts of the networking, from Kees
    Cook.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (99 commits)
  bnxt_en: Issue PCIe FLR in kdump kernel to cleanup pending DMAs.
  bnxt_en: Improve device shutdown method.
  net: netlink: cap max groups which will be considered in netlink_bind()
  net: thunderx: workaround BGX TX Underflow issue
  ionic: fix fw_status read
  net: disable BRIDGE_NETFILTER by default
  net: macb: Properly handle phylink on at91rm9200
  s390/qeth: fix off-by-one in RX copybreak check
  s390/qeth: don't warn for napi with 0 budget
  s390/qeth: vnicc Fix EOPNOTSUPP precedence
  openvswitch: Distribute switch variables for initialization
  net: ip6_gre: Distribute switch variables for initialization
  net: core: Distribute switch variables for initialization
  udp: rehash on disconnect
  net/tls: Fix to avoid gettig invalid tls record
  bpf: Fix a potential deadlock with bpf_map_do_batch
  bpf: Do not grab the bucket spinlock by default on htab batch ops
  ice: Wait for VF to be reset/ready before configuration
  ice: Don't tell the OS that link is going down
  ice: Don't reject odd values of usecs set by user
  ...

2 files changed, 42 insertions, 5 deletions

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index e9391e877f9a..628383915827 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <linux/siphash.h>
+#include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
 struct sk_buff;
@@ -348,4 +349,12 @@ struct bpf_flow_dissector {
 	void			*data_end;
 };
 
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+			 struct flow_dissector_key_basic *key_basic)
+{
+	memset(key_control, 0, sizeof(*key_control));
+	memset(key_basic, 0, sizeof(*key_basic));
+}
+
 #endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 02162b0378f7..328564525526 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -117,19 +117,26 @@ typedef __u64 __bitwise __addrpair;
  *	struct sock_common - minimal network layer representation of sockets
  *	@skc_daddr: Foreign IPv4 addr
  *	@skc_rcv_saddr: Bound local IPv4 addr
+ *	@skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr
  *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_u16hashes: two u16 hash values used by UDP lookup tables
  *	@skc_dport: placeholder for inet_dport/tw_dport
  *	@skc_num: placeholder for inet_num/tw_num
+ *	@skc_portpair: __u32 union of @skc_dport & @skc_num
  *	@skc_family: network address family
  *	@skc_state: Connection state
  *	@skc_reuse: %SO_REUSEADDR setting
  *	@skc_reuseport: %SO_REUSEPORT setting
+ *	@skc_ipv6only: socket is IPV6 only
+ *	@skc_net_refcnt: socket is using net ref counting
  *	@skc_bound_dev_if: bound device index if != 0
  *	@skc_bind_node: bind hash linkage for various protocol lookup tables
  *	@skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol
  *	@skc_prot: protocol handlers inside a network family
  *	@skc_net: reference to the network namespace of this socket
+ *	@skc_v6_daddr: IPV6 destination address
+ *	@skc_v6_rcv_saddr: IPV6 source address
+ *	@skc_cookie: socket's cookie value
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
  *	@skc_tx_queue_mapping: tx queue number for this connection
@@ -137,7 +144,15 @@ typedef __u64 __bitwise __addrpair;
  *	@skc_flags: place holder for sk_flags
  *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ *	@skc_listener: connection request listener socket (aka rsk_listener)
+ *		[union with @skc_flags]
+ *	@skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row
+ *		[union with @skc_flags]
  *	@skc_incoming_cpu: record/match cpu processing incoming packets
+ *	@skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled)
+ *		[union with @skc_incoming_cpu]
+ *	@skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number
+ *		[union with @skc_incoming_cpu]
  *	@skc_refcnt: reference count
  *
  *	This is the minimal network layer representation of sockets, the header
@@ -245,6 +260,7 @@ struct bpf_sk_storage;
   *	@sk_dst_cache: destination cache
   *	@sk_dst_pending_confirm: need to confirm neighbour
   *	@sk_policy: flow policy
+  *	@sk_rx_skb_cache: cache copy of recently accessed RX skb
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
   *	@sk_tsq_flags: TCP Small Queues flags
@@ -265,6 +281,8 @@ struct bpf_sk_storage;
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
+  *	@sk_route_forced_caps: static, forced route capabilities
+  *		(set in tcp_init_sock())
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
   *	@sk_gso_max_size: Maximum GSO segment size to build
   *	@sk_gso_max_segs: Maximum number of GSO segments
@@ -303,6 +321,8 @@ struct bpf_sk_storage;
   *	@sk_frag: cached page frag
   *	@sk_peek_off: current peek_offset value
   *	@sk_send_head: front of stuff to transmit
+  *	@tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head]
+  *	@sk_tx_skb_cache: cache copy of recently accessed TX skb
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
   *	@sk_cgrp_data: cgroup data for this cgroup
@@ -313,11 +333,14 @@ struct bpf_sk_storage;
   *	@sk_write_space: callback to indicate there is bf sending space available
   *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
   *	@sk_backlog_rcv: callback to process the backlog
+  *	@sk_validate_xmit_skb: ptr to an optional validate function
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
+  *	@sk_bpf_storage: ptr to cache and control for bpf_sk_storage
   *	@sk_rcu: used during RCU grace period
   *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
   *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+  *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   */
 struct sock {
@@ -393,7 +416,9 @@ struct sock {
 	struct sk_filter __rcu	*sk_filter;
 	union {
 		struct socket_wq __rcu	*sk_wq;
+		/* private: */
 		struct socket_wq	*sk_wq_raw;
+		/* public: */
 	};
 #ifdef CONFIG_XFRM
 	struct xfrm_policy __rcu *sk_policy[2];
@@ -2017,7 +2042,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro
  * sk_wmem_alloc_get - returns write allocations
  * @sk: socket
  *
- * Returns sk_wmem_alloc minus initial offset of one
+ * Return: sk_wmem_alloc minus initial offset of one
  */
 static inline int sk_wmem_alloc_get(const struct sock *sk)
 {
@@ -2028,7 +2053,7 @@ static inline int sk_wmem_alloc_get(const struct sock *sk)
  * sk_rmem_alloc_get - returns read allocations
  * @sk: socket
  *
- * Returns sk_rmem_alloc
+ * Return: sk_rmem_alloc
  */
 static inline int sk_rmem_alloc_get(const struct sock *sk)
 {
@@ -2039,7 +2064,7 @@ static inline int sk_rmem_alloc_get(const struct sock *sk)
  * sk_has_allocations - check if allocations are outstanding
  * @sk: socket
  *
- * Returns true if socket has write or read allocations
+ * Return: true if socket has write or read allocations
  */
 static inline bool sk_has_allocations(const struct sock *sk)
 {
@@ -2050,7 +2075,7 @@ static inline bool sk_has_allocations(const struct sock *sk)
  * skwq_has_sleeper - check if there are any waiting processes
  * @wq: struct socket_wq
  *
- * Returns true if socket_wq has waiting processes
+ * Return: true if socket_wq has waiting processes
  *
  * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
  * barrier call. They were added due to the race found within the tcp code.
@@ -2238,6 +2263,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
  * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
  * inside other socket operations and end up recursing into sk_page_frag()
  * while it's already in use.
+ *
+ * Return: a per task page_frag if context allows that,
+ * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
@@ -2432,6 +2460,7 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
 			   &skb_shinfo(skb)->tskey);
 }
 
+DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
@@ -2440,7 +2469,6 @@ 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);