Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:

 - Add redirect_neigh() BPF packet redirect helper, allowing to limit
   stack traversal in common container configs and improving TCP
   back-pressure.

   Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain.

 - Expand netlink policy support and improve policy export to user
   space. (Ge)netlink core performs request validation according to
   declared policies. Expand the expressiveness of those policies
   (min/max length and bitmasks). Allow dumping policies for particular
   commands. This is used for feature discovery by user space (instead
   of kernel version parsing or trial and error).

 - Support IGMPv3/MLDv2 multicast listener discovery protocols in
   bridge.

 - Allow more than 255 IPv4 multicast interfaces.

 - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK
   packets of TCPv6.

 - In Multi-patch TCP (MPTCP) support concurrent transmission of data on
   multiple subflows in a load balancing scenario. Enhance advertising
   addresses via the RM_ADDR/ADD_ADDR options.

 - Support SMC-Dv2 version of SMC, which enables multi-subnet
   deployments.

 - Allow more calls to same peer in RxRPC.

 - Support two new Controller Area Network (CAN) protocols - CAN-FD and
   ISO 15765-2:2016.

 - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit
   kernel problem.

 - Add TC actions for implementing MPLS L2 VPNs.

 - Improve nexthop code - e.g. handle various corner cases when nexthop
   objects are removed from groups better, skip unnecessary
   notifications and make it easier to offload nexthops into HW by
   converting to a blocking notifier.

 - Support adding and consuming TCP header options by BPF programs,
   opening the doors for easy experimental and deployment-specific TCP
   option use.

 - Reorganize TCP congestion control (CC) initialization to simplify
   life of TCP CC implemented in BPF.

 - Add support for shipping BPF programs with the kernel and loading
   them early on boot via the User Mode Driver mechanism, hence reusing
   all the user space infra we have.

 - Support sleepable BPF programs, initially targeting LSM and tracing.

 - Add bpf_d_path() helper for returning full path for given 'struct
   path'.

 - Make bpf_tail_call compatible with bpf-to-bpf calls.

 - Allow BPF programs to call map_update_elem on sockmaps.

 - Add BPF Type Format (BTF) support for type and enum discovery, as
   well as support for using BTF within the kernel itself (current use
   is for pretty printing structures).

 - Support listing and getting information about bpf_links via the bpf
   syscall.

 - Enhance kernel interfaces around NIC firmware update. Allow
   specifying overwrite mask to control if settings etc. are reset
   during update; report expected max time operation may take to users;
   support firmware activation without machine reboot incl. limits of
   how much impact reset may have (e.g. dropping link or not).

 - Extend ethtool configuration interface to report IEEE-standard
   counters, to limit the need for per-vendor logic in user space.

 - Adopt or extend devlink use for debug, monitoring, fw update in many
   drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx,
   dpaa2-eth).

 - In mlxsw expose critical and emergency SFP module temperature alarms.
   Refactor port buffer handling to make the defaults more suitable and
   support setting these values explicitly via the DCBNL interface.

 - Add XDP support for Intel's igb driver.

 - Support offloading TC flower classification and filtering rules to
   mscc_ocelot switches.

 - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as
   fixed interval period pulse generator and one-step timestamping in
   dpaa-eth.

 - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3)
   offload.

 - Add Lynx PHY/PCS MDIO module, and convert various drivers which have
   this HW to use it. Convert mvpp2 to split PCS.

 - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as
   7-port Mediatek MT7531 IP.

 - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver,
   and wcn3680 support in wcn36xx.

 - Improve performance for packets which don't require much offloads on
   recent Mellanox NICs by 20% by making multiple packets share a
   descriptor entry.

 - Move chelsio inline crypto drivers (for TLS and IPsec) from the
   crypto subtree to drivers/net. Move MDIO drivers out of the phy
   directory.

 - Clean up a lot of W=1 warnings, reportedly the actively developed
   subsections of networking drivers should now build W=1 warning free.

 - Make sure drivers don't use in_interrupt() to dynamically adapt their
   code. Convert tasklets to use new tasklet_setup API (sadly this
   conversion is not yet complete).

* tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits)
  Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH"
  net, sockmap: Don't call bpf_prog_put() on NULL pointer
  bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo
  bpf, sockmap: Add locking annotations to iterator
  netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements
  net: fix pos incrementment in ipv6_route_seq_next
  net/smc: fix invalid return code in smcd_new_buf_create()
  net/smc: fix valid DMBE buffer sizes
  net/smc: fix use-after-free of delayed events
  bpfilter: Fix build error with CONFIG_BPFILTER_UMH
  cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr
  net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info
  bpf: Fix register equivalence tracking.
  rxrpc: Fix loss of final ack on shutdown
  rxrpc: Fix bundle counting for exclusive connections
  netfilter: restore NF_INET_NUMHOOKS
  ibmveth: Identify ingress large send packets.
  ibmveth: Switch order of ibmveth_helper calls.
  cxgb4: handle 4-tuple PEDIT to NAT mode translation
  selftests: Add VRF route leaking tests
  ...

1 files changed, 210 insertions, 0 deletions

diff --git a/drivers/net/mdio/mdio-mux.c b/drivers/net/mdio/mdio-mux.c
new file mode 100644
index 000000000000..6a1d3540210b
--- /dev/null
+++ b/drivers/net/mdio/mdio-mux.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2011, 2012 Cavium, Inc.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/mdio-mux.h>
+#include <linux/of_mdio.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define DRV_DESCRIPTION "MDIO bus multiplexer driver"
+
+struct mdio_mux_child_bus;
+
+struct mdio_mux_parent_bus {
+	struct mii_bus *mii_bus;
+	int current_child;
+	int parent_id;
+	void *switch_data;
+	int (*switch_fn)(int current_child, int desired_child, void *data);
+
+	/* List of our children linked through their next fields. */
+	struct mdio_mux_child_bus *children;
+};
+
+struct mdio_mux_child_bus {
+	struct mii_bus *mii_bus;
+	struct mdio_mux_parent_bus *parent;
+	struct mdio_mux_child_bus *next;
+	int bus_number;
+};
+
+/*
+ * The parent bus' lock is used to order access to the switch_fn.
+ */
+static int mdio_mux_read(struct mii_bus *bus, int phy_id, int regnum)
+{
+	struct mdio_mux_child_bus *cb = bus->priv;
+	struct mdio_mux_parent_bus *pb = cb->parent;
+	int r;
+
+	mutex_lock_nested(&pb->mii_bus->mdio_lock, MDIO_MUTEX_MUX);
+	r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data);
+	if (r)
+		goto out;
+
+	pb->current_child = cb->bus_number;
+
+	r = pb->mii_bus->read(pb->mii_bus, phy_id, regnum);
+out:
+	mutex_unlock(&pb->mii_bus->mdio_lock);
+
+	return r;
+}
+
+/*
+ * The parent bus' lock is used to order access to the switch_fn.
+ */
+static int mdio_mux_write(struct mii_bus *bus, int phy_id,
+			  int regnum, u16 val)
+{
+	struct mdio_mux_child_bus *cb = bus->priv;
+	struct mdio_mux_parent_bus *pb = cb->parent;
+
+	int r;
+
+	mutex_lock_nested(&pb->mii_bus->mdio_lock, MDIO_MUTEX_MUX);
+	r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data);
+	if (r)
+		goto out;
+
+	pb->current_child = cb->bus_number;
+
+	r = pb->mii_bus->write(pb->mii_bus, phy_id, regnum, val);
+out:
+	mutex_unlock(&pb->mii_bus->mdio_lock);
+
+	return r;
+}
+
+static int parent_count;
+
+int mdio_mux_init(struct device *dev,
+		  struct device_node *mux_node,
+		  int (*switch_fn)(int cur, int desired, void *data),
+		  void **mux_handle,
+		  void *data,
+		  struct mii_bus *mux_bus)
+{
+	struct device_node *parent_bus_node;
+	struct device_node *child_bus_node;
+	int r, ret_val;
+	struct mii_bus *parent_bus;
+	struct mdio_mux_parent_bus *pb;
+	struct mdio_mux_child_bus *cb;
+
+	if (!mux_node)
+		return -ENODEV;
+
+	if (!mux_bus) {
+		parent_bus_node = of_parse_phandle(mux_node,
+						   "mdio-parent-bus", 0);
+
+		if (!parent_bus_node)
+			return -ENODEV;
+
+		parent_bus = of_mdio_find_bus(parent_bus_node);
+		if (!parent_bus) {
+			ret_val = -EPROBE_DEFER;
+			goto err_parent_bus;
+		}
+	} else {
+		parent_bus_node = NULL;
+		parent_bus = mux_bus;
+		get_device(&parent_bus->dev);
+	}
+
+	pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
+	if (!pb) {
+		ret_val = -ENOMEM;
+		goto err_pb_kz;
+	}
+
+	pb->switch_data = data;
+	pb->switch_fn = switch_fn;
+	pb->current_child = -1;
+	pb->parent_id = parent_count++;
+	pb->mii_bus = parent_bus;
+
+	ret_val = -ENODEV;
+	for_each_available_child_of_node(mux_node, child_bus_node) {
+		int v;
+
+		r = of_property_read_u32(child_bus_node, "reg", &v);
+		if (r) {
+			dev_err(dev,
+				"Error: Failed to find reg for child %pOF\n",
+				child_bus_node);
+			continue;
+		}
+
+		cb = devm_kzalloc(dev, sizeof(*cb), GFP_KERNEL);
+		if (!cb) {
+			ret_val = -ENOMEM;
+			continue;
+		}
+		cb->bus_number = v;
+		cb->parent = pb;
+
+		cb->mii_bus = mdiobus_alloc();
+		if (!cb->mii_bus) {
+			ret_val = -ENOMEM;
+			devm_kfree(dev, cb);
+			continue;
+		}
+		cb->mii_bus->priv = cb;
+
+		cb->mii_bus->name = "mdio_mux";
+		snprintf(cb->mii_bus->id, MII_BUS_ID_SIZE, "%x.%x",
+			 pb->parent_id, v);
+		cb->mii_bus->parent = dev;
+		cb->mii_bus->read = mdio_mux_read;
+		cb->mii_bus->write = mdio_mux_write;
+		r = of_mdiobus_register(cb->mii_bus, child_bus_node);
+		if (r) {
+			dev_err(dev,
+				"Error: Failed to register MDIO bus for child %pOF\n",
+				child_bus_node);
+			mdiobus_free(cb->mii_bus);
+			devm_kfree(dev, cb);
+		} else {
+			cb->next = pb->children;
+			pb->children = cb;
+		}
+	}
+	if (pb->children) {
+		*mux_handle = pb;
+		return 0;
+	}
+
+	dev_err(dev, "Error: No acceptable child buses found\n");
+	devm_kfree(dev, pb);
+err_pb_kz:
+	put_device(&parent_bus->dev);
+err_parent_bus:
+	of_node_put(parent_bus_node);
+	return ret_val;
+}
+EXPORT_SYMBOL_GPL(mdio_mux_init);
+
+void mdio_mux_uninit(void *mux_handle)
+{
+	struct mdio_mux_parent_bus *pb = mux_handle;
+	struct mdio_mux_child_bus *cb = pb->children;
+
+	while (cb) {
+		mdiobus_unregister(cb->mii_bus);
+		mdiobus_free(cb->mii_bus);
+		cb = cb->next;
+	}
+
+	put_device(&pb->mii_bus->dev);
+}
+EXPORT_SYMBOL_GPL(mdio_mux_uninit);
+
+MODULE_DESCRIPTION(DRV_DESCRIPTION);
+MODULE_AUTHOR("David Daney");
+MODULE_LICENSE("GPL v2");