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, 69 insertions, 26 deletions

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 992fcab4b552..8c0f3c6ab365 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -15,11 +15,11 @@
 #include <linux/mdio.h>
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
+#include <net/selftests.h>
 #include <net/tc_act/tc_mirred.h>
 #include <linux/if_bridge.h>
 #include <linux/if_hsr.h>
 #include <linux/netpoll.h>
-#include <linux/ptp_classify.h>
 
 #include "dsa_priv.h"
 
@@ -555,26 +555,14 @@ static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p,
 				 struct sk_buff *skb)
 {
 	struct dsa_switch *ds = p->dp->ds;
-	struct sk_buff *clone;
-	unsigned int type;
 
-	type = ptp_classify_raw(skb);
-	if (type == PTP_CLASS_NONE)
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		return;
 
 	if (!ds->ops->port_txtstamp)
 		return;
 
-	clone = skb_clone_sk(skb);
-	if (!clone)
-		return;
-
-	if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) {
-		DSA_SKB_CB(skb)->clone = clone;
-		return;
-	}
-
-	kfree_skb(clone);
+	ds->ops->port_txtstamp(ds, p->dp->index, skb);
 }
 
 netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev)
@@ -626,11 +614,9 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	dev_sw_netstats_tx_add(dev, 1, skb->len);
 
-	DSA_SKB_CB(skb)->clone = NULL;
+	memset(skb->cb, 0, sizeof(skb->cb));
 
-	/* Identify PTP protocol packets, clone them, and pass them to the
-	 * switch driver
-	 */
+	/* Handle tx timestamp if any */
 	dsa_skb_tx_timestamp(p, skb);
 
 	if (dsa_realloc_skb(skb, dev)) {
@@ -748,7 +734,10 @@ static void dsa_slave_get_strings(struct net_device *dev,
 		if (ds->ops->get_strings)
 			ds->ops->get_strings(ds, dp->index, stringset,
 					     data + 4 * len);
+	} else if (stringset ==  ETH_SS_TEST) {
+		net_selftest_get_strings(data);
 	}
+
 }
 
 static void dsa_slave_get_ethtool_stats(struct net_device *dev,
@@ -794,11 +783,27 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
 			count += ds->ops->get_sset_count(ds, dp->index, sset);
 
 		return count;
+	} else if (sset ==  ETH_SS_TEST) {
+		return net_selftest_get_count();
 	}
 
 	return -EOPNOTSUPP;
 }
 
+static void dsa_slave_net_selftest(struct net_device *ndev,
+				   struct ethtool_test *etest, u64 *buf)
+{
+	struct dsa_port *dp = dsa_slave_to_port(ndev);
+	struct dsa_switch *ds = dp->ds;
+
+	if (ds->ops->self_test) {
+		ds->ops->self_test(ds, dp->index, etest, buf);
+		return;
+	}
+
+	net_selftest(ndev, etest, buf);
+}
+
 static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
@@ -1278,14 +1283,32 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 	}
 }
 
+static int dsa_slave_setup_ft_block(struct dsa_switch *ds, int port,
+				    void *type_data)
+{
+	struct dsa_port *cpu_dp = dsa_to_port(ds, port)->cpu_dp;
+	struct net_device *master = cpu_dp->master;
+
+	if (!master->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	return master->netdev_ops->ndo_setup_tc(master, TC_SETUP_FT, type_data);
+}
+
 static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct dsa_switch *ds = dp->ds;
 
-	if (type == TC_SETUP_BLOCK)
+	switch (type) {
+	case TC_SETUP_BLOCK:
 		return dsa_slave_setup_tc_block(dev, type_data);
+	case TC_SETUP_FT:
+		return dsa_slave_setup_ft_block(ds, dp->index, type_data);
+	default:
+		break;
+	}
 
 	if (!ds->ops->port_setup_tc)
 		return -EOPNOTSUPP;
@@ -1612,6 +1635,7 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_rxnfc		= dsa_slave_get_rxnfc,
 	.set_rxnfc		= dsa_slave_set_rxnfc,
 	.get_ts_info		= dsa_slave_get_ts_info,
+	.self_test		= dsa_slave_net_selftest,
 };
 
 /* legacy way, bypassing the bridge *****************************************/
@@ -1654,6 +1678,21 @@ static void dsa_slave_get_stats64(struct net_device *dev,
 		dev_get_tstats64(dev, s);
 }
 
+static int dsa_slave_fill_forward_path(struct net_device_path_ctx *ctx,
+				       struct net_device_path *path)
+{
+	struct dsa_port *dp = dsa_slave_to_port(ctx->dev);
+	struct dsa_port *cpu_dp = dp->cpu_dp;
+
+	path->dev = ctx->dev;
+	path->type = DEV_PATH_DSA;
+	path->dsa.proto = cpu_dp->tag_ops->proto;
+	path->dsa.port = dp->index;
+	ctx->dev = cpu_dp->master;
+
+	return 0;
+}
+
 static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
@@ -1679,6 +1718,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= dsa_slave_vlan_rx_kill_vid,
 	.ndo_get_devlink_port	= dsa_slave_get_devlink_port,
 	.ndo_change_mtu		= dsa_slave_change_mtu,
+	.ndo_fill_forward_path	= dsa_slave_fill_forward_path,
 };
 
 static struct device_type dsa_type = {
@@ -1862,7 +1902,7 @@ int dsa_slave_create(struct dsa_port *port)
 	slave_dev->hw_features |= NETIF_F_HW_TC;
 	slave_dev->features |= NETIF_F_LLTX;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
-	if (!IS_ERR_OR_NULL(port->mac))
+	if (!is_zero_ether_addr(port->mac))
 		ether_addr_copy(slave_dev->dev_addr, port->mac);
 	else
 		eth_hw_addr_inherit(slave_dev, master);
@@ -1976,11 +2016,14 @@ static int dsa_slave_changeupper(struct net_device *dev,
 				 struct netdev_notifier_changeupper_info *info)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct netlink_ext_ack *extack;
 	int err = NOTIFY_DONE;
 
+	extack = netdev_notifier_info_to_extack(&info->info);
+
 	if (netif_is_bridge_master(info->upper_dev)) {
 		if (info->linking) {
-			err = dsa_port_bridge_join(dp, info->upper_dev);
+			err = dsa_port_bridge_join(dp, info->upper_dev, extack);
 			if (!err)
 				dsa_bridge_mtu_normalization(dp);
 			err = notifier_from_errno(err);
@@ -1991,7 +2034,7 @@ static int dsa_slave_changeupper(struct net_device *dev,
 	} else if (netif_is_lag_master(info->upper_dev)) {
 		if (info->linking) {
 			err = dsa_port_lag_join(dp, info->upper_dev,
-						info->upper_info);
+						info->upper_info, extack);
 			if (err == -EOPNOTSUPP) {
 				NL_SET_ERR_MSG_MOD(info->info.extack,
 						   "Offloading not supported");
@@ -2292,7 +2335,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused,
 		fdb_info = ptr;
 
 		if (dsa_slave_dev_check(dev)) {
-			if (!fdb_info->added_by_user)
+			if (!fdb_info->added_by_user || fdb_info->is_local)
 				return NOTIFY_OK;
 
 			dp = dsa_slave_to_port(dev);
@@ -2389,11 +2432,11 @@ static struct notifier_block dsa_slave_nb __read_mostly = {
 	.notifier_call  = dsa_slave_netdevice_event,
 };
 
-static struct notifier_block dsa_slave_switchdev_notifier = {
+struct notifier_block dsa_slave_switchdev_notifier = {
 	.notifier_call = dsa_slave_switchdev_event,
 };
 
-static struct notifier_block dsa_slave_switchdev_blocking_notifier = {
+struct notifier_block dsa_slave_switchdev_blocking_notifier = {
 	.notifier_call = dsa_slave_switchdev_blocking_event,
 };