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
  ...

4 files changed, 44 insertions, 5 deletions

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ff8c9d527bb4..bfdf41537cf1 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -688,7 +688,10 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 	u8         nic_rx_multi_path_tirs[0x1];
 	u8         nic_rx_multi_path_tirs_fts[0x1];
 	u8         allow_sniffer_and_nic_rx_shared_tir[0x1];
-	u8	   reserved_at_3[0x1d];
+	u8	   reserved_at_3[0x4];
+	u8	   sw_owner_reformat_supported[0x1];
+	u8	   reserved_at_8[0x18];
+
 	u8	   encap_general_header[0x1];
 	u8	   reserved_at_21[0xa];
 	u8	   log_max_packet_reformat_context[0x5];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9f1f633235f6..6c3f7032e8d9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+#define MAX_NEST_DEV 8
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -4389,11 +4391,8 @@ void *netdev_lower_get_next(struct net_device *dev,
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
-						 struct list_head **iter);
-
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
 					void *data),
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index e5b752027a03..9670b54b484a 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -145,6 +145,13 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
 	}
 }
 
+/* after that hlist_nulls_del will work */
+static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
+{
+	n->pprev = &n->next;
+	n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL);
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ca8806b69388..5b50278c4bc8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -611,9 +611,15 @@ typedef unsigned char *sk_buff_data_t;
  *	@next: Next buffer in list
  *	@prev: Previous buffer in list
  *	@tstamp: Time we arrived/left
+ *	@skb_mstamp_ns: (aka @tstamp) earliest departure time; start point
+ *		for retransmit timer
  *	@rbnode: RB tree node, alternative to next/prev for netem/tcp
+ *	@list: queue head
  *	@sk: Socket we are owned by
+ *	@ip_defrag_offset: (aka @sk) alternate use of @sk, used in
+ *		fragmentation management
  *	@dev: Device we arrived on/are leaving by
+ *	@dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
  *	@sp: the security path, used for xfrm
@@ -632,6 +638,9 @@ typedef unsigned char *sk_buff_data_t;
  *	@pkt_type: Packet class
  *	@fclone: skbuff clone status
  *	@ipvs_property: skbuff is owned by ipvs
+ *	@inner_protocol_type: whether the inner protocol is
+ *		ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO
+ *	@remcsum_offload: remote checksum offload is enabled
  *	@offload_fwd_mark: Packet was L2-forwarded in hardware
  *	@offload_l3_fwd_mark: Packet was L3-forwarded in hardware
  *	@tc_skip_classify: do not classify packet. set by IFB device
@@ -650,6 +659,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
+ *	@head_frag: skb was allocated from page fragments,
+ *		not allocated by kmalloc() or vmalloc().
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@active_extensions: active extensions (skb_ext_id types)
  *	@ndisc_nodetype: router type (from link layer)
@@ -660,15 +671,28 @@ typedef unsigned char *sk_buff_data_t;
  *	@wifi_acked_valid: wifi_acked was set
  *	@wifi_acked: whether frame was acked on wifi or not
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
+ *	@encapsulation: indicates the inner headers in the skbuff are valid
+ *	@encap_hdr_csum: software checksum is needed
+ *	@csum_valid: checksum is already valid
  *	@csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
+ *	@csum_complete_sw: checksum was completed by software
+ *	@csum_level: indicates the number of consecutive checksums found in
+ *		the packet minus one that have been verified as
+ *		CHECKSUM_UNNECESSARY (max 3)
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@napi_id: id of the NAPI struct this skb came from
+ *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@secmark: security marking
  *	@mark: Generic packet mark
+ *	@reserved_tailroom: (aka @mark) number of bytes of free space available
+ *		at the tail of an sk_buff
+ *	@vlan_present: VLAN tag is present
  *	@vlan_proto: vlan encapsulation protocol
  *	@vlan_tci: vlan tag control information
  *	@inner_protocol: Protocol (encapsulation)
+ *	@inner_ipproto: (aka @inner_protocol) stores ipproto when
+ *		skb->inner_protocol_type == ENCAP_TYPE_IPPROTO;
  *	@inner_transport_header: Inner transport layer header (encapsulation)
  *	@inner_network_header: Network layer header (encapsulation)
  *	@inner_mac_header: Link layer header (encapsulation)
@@ -750,7 +774,9 @@ struct sk_buff {
 #endif
 #define CLONED_OFFSET()		offsetof(struct sk_buff, __cloned_offset)
 
+	/* private: */
 	__u8			__cloned_offset[0];
+	/* public: */
 	__u8			cloned:1,
 				nohdr:1,
 				fclone:2,
@@ -775,7 +801,9 @@ struct sk_buff {
 #endif
 #define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)
 
+	/* private: */
 	__u8			__pkt_type_offset[0];
+	/* public: */
 	__u8			pkt_type:3;
 	__u8			ignore_df:1;
 	__u8			nf_trace:1;
@@ -798,7 +826,9 @@ struct sk_buff {
 #define PKT_VLAN_PRESENT_BIT	0
 #endif
 #define PKT_VLAN_PRESENT_OFFSET()	offsetof(struct sk_buff, __pkt_vlan_present_offset)
+	/* private: */
 	__u8			__pkt_vlan_present_offset[0];
+	/* public: */
 	__u8			vlan_present:1;
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;