Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 26 insertions, 17 deletions

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 83a933e563fe..e1a2610a0e06 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -49,10 +49,12 @@ struct phylink_link_state;
 #define DSA_TAG_PROTO_XRS700X_VALUE		19
 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE	20
 #define DSA_TAG_PROTO_SEVILLE_VALUE		21
+#define DSA_TAG_PROTO_BRCM_LEGACY_VALUE		22
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
 	DSA_TAG_PROTO_BRCM		= DSA_TAG_PROTO_BRCM_VALUE,
+	DSA_TAG_PROTO_BRCM_LEGACY	= DSA_TAG_PROTO_BRCM_LEGACY_VALUE,
 	DSA_TAG_PROTO_BRCM_PREPEND	= DSA_TAG_PROTO_BRCM_PREPEND_VALUE,
 	DSA_TAG_PROTO_DSA		= DSA_TAG_PROTO_DSA_VALUE,
 	DSA_TAG_PROTO_EDSA		= DSA_TAG_PROTO_EDSA_VALUE,
@@ -115,20 +117,6 @@ struct dsa_netdevice_ops {
 #define MODULE_ALIAS_DSA_TAG_DRIVER(__proto)				\
 	MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE))
 
-struct dsa_skb_cb {
-	struct sk_buff *clone;
-};
-
-struct __dsa_skb_cb {
-	struct dsa_skb_cb cb;
-	u8 priv[48 - sizeof(struct dsa_skb_cb)];
-};
-
-#define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb))
-
-#define DSA_SKB_CB_PRIV(skb)			\
-	((void *)(skb)->cb + offsetof(struct __dsa_skb_cb, priv))
-
 struct dsa_switch_tree {
 	struct list_head	list;
 
@@ -147,6 +135,11 @@ struct dsa_switch_tree {
 	/* Tagging protocol operations */
 	const struct dsa_device_ops *tag_ops;
 
+	/* Default tagging protocol preferred by the switches in this
+	 * tree.
+	 */
+	enum dsa_tag_protocol default_proto;
+
 	/*
 	 * Configuration data for the platform device that owns
 	 * this dsa switch tree instance.
@@ -258,7 +251,7 @@ struct dsa_port {
 	unsigned int		index;
 	const char		*name;
 	struct dsa_port		*cpu_dp;
-	const char		*mac;
+	u8			mac[ETH_ALEN];
 	struct device_node	*dn;
 	unsigned int		ageing_time;
 	bool			vlan_filtering;
@@ -491,6 +484,20 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
 		return dp->vlan_filtering;
 }
 
+static inline
+struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp)
+{
+	if (!dp->bridge_dev)
+		return NULL;
+
+	if (dp->lag_dev)
+		return dp->lag_dev;
+	else if (dp->hsr_dev)
+		return dp->hsr_dev;
+
+	return dp->slave;
+}
+
 typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
 			      bool is_static, void *data);
 struct dsa_switch_ops {
@@ -561,6 +568,8 @@ struct dsa_switch_ops {
 					 int port, uint64_t *data);
 	void	(*get_stats64)(struct dsa_switch *ds, int port,
 				   struct rtnl_link_stats64 *s);
+	void	(*self_test)(struct dsa_switch *ds, int port,
+			     struct ethtool_test *etest, u64 *data);
 
 	/*
 	 * ethtool Wake-on-LAN
@@ -717,8 +726,8 @@ struct dsa_switch_ops {
 				     struct ifreq *ifr);
 	int	(*port_hwtstamp_set)(struct dsa_switch *ds, int port,
 				     struct ifreq *ifr);
-	bool	(*port_txtstamp)(struct dsa_switch *ds, int port,
-				 struct sk_buff *clone, unsigned int type);
+	void	(*port_txtstamp)(struct dsa_switch *ds, int port,
+				 struct sk_buff *skb);
 	bool	(*port_rxtstamp)(struct dsa_switch *ds, int port,
 				 struct sk_buff *skb, unsigned int type);