Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 442 insertions, 0 deletions

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
new file mode 100644
index 000000000..8662543ca
--- /dev/null
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -0,0 +1,442 @@
+/*
+ * Driver for the MDIO interface of Marvell network interfaces.
+ *
+ * Since the MDIO interface of Marvell network interfaces is shared
+ * between all network interfaces, having a single driver allows to
+ * handle concurrent accesses properly (you may have four Ethernet
+ * ports, but they in fact share the same SMI interface to access
+ * the MDIO bus). This driver is currently used by the mvneta and
+ * mv643xx_eth drivers.
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_mdio.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define MVMDIO_SMI_DATA_SHIFT		0
+#define MVMDIO_SMI_PHY_ADDR_SHIFT	16
+#define MVMDIO_SMI_PHY_REG_SHIFT	21
+#define MVMDIO_SMI_READ_OPERATION	BIT(26)
+#define MVMDIO_SMI_WRITE_OPERATION	0
+#define MVMDIO_SMI_READ_VALID		BIT(27)
+#define MVMDIO_SMI_BUSY			BIT(28)
+#define MVMDIO_ERR_INT_CAUSE		0x007C
+#define  MVMDIO_ERR_INT_SMI_DONE	0x00000010
+#define MVMDIO_ERR_INT_MASK		0x0080
+
+#define MVMDIO_XSMI_MGNT_REG		0x0
+#define  MVMDIO_XSMI_PHYADDR_SHIFT	16
+#define  MVMDIO_XSMI_DEVADDR_SHIFT	21
+#define  MVMDIO_XSMI_WRITE_OPERATION	(0x5 << 26)
+#define  MVMDIO_XSMI_READ_OPERATION	(0x7 << 26)
+#define  MVMDIO_XSMI_READ_VALID		BIT(29)
+#define  MVMDIO_XSMI_BUSY		BIT(30)
+#define MVMDIO_XSMI_ADDR_REG		0x8
+
+/*
+ * SMI Timeout measurements:
+ * - Kirkwood 88F6281 (Globalscale Dreamplug): 45us to 95us (Interrupt)
+ * - Armada 370       (Globalscale Mirabox):   41us to 43us (Polled)
+ */
+#define MVMDIO_SMI_TIMEOUT		1000 /* 1000us = 1ms */
+#define MVMDIO_SMI_POLL_INTERVAL_MIN	45
+#define MVMDIO_SMI_POLL_INTERVAL_MAX	55
+
+#define MVMDIO_XSMI_POLL_INTERVAL_MIN	150
+#define MVMDIO_XSMI_POLL_INTERVAL_MAX	160
+
+struct orion_mdio_dev {
+	void __iomem *regs;
+	struct clk *clk[4];
+	/*
+	 * If we have access to the error interrupt pin (which is
+	 * somewhat misnamed as it not only reflects internal errors
+	 * but also reflects SMI completion), use that to wait for
+	 * SMI access completion instead of polling the SMI busy bit.
+	 */
+	int err_interrupt;
+	wait_queue_head_t smi_busy_wait;
+};
+
+enum orion_mdio_bus_type {
+	BUS_TYPE_SMI,
+	BUS_TYPE_XSMI
+};
+
+struct orion_mdio_ops {
+	int (*is_done)(struct orion_mdio_dev *);
+	unsigned int poll_interval_min;
+	unsigned int poll_interval_max;
+};
+
+/* Wait for the SMI unit to be ready for another operation
+ */
+static int orion_mdio_wait_ready(const struct orion_mdio_ops *ops,
+				 struct mii_bus *bus)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	unsigned long timeout = usecs_to_jiffies(MVMDIO_SMI_TIMEOUT);
+	unsigned long end = jiffies + timeout;
+	int timedout = 0;
+
+	while (1) {
+	        if (ops->is_done(dev))
+			return 0;
+	        else if (timedout)
+			break;
+
+	        if (dev->err_interrupt <= 0) {
+			usleep_range(ops->poll_interval_min,
+				     ops->poll_interval_max);
+
+			if (time_is_before_jiffies(end))
+				++timedout;
+	        } else {
+			/* wait_event_timeout does not guarantee a delay of at
+			 * least one whole jiffie, so timeout must be no less
+			 * than two.
+			 */
+			if (timeout < 2)
+				timeout = 2;
+			wait_event_timeout(dev->smi_busy_wait,
+				           ops->is_done(dev), timeout);
+
+			++timedout;
+	        }
+	}
+
+	dev_err(bus->parent, "Timeout: SMI busy for too long\n");
+	return  -ETIMEDOUT;
+}
+
+static int orion_mdio_smi_is_done(struct orion_mdio_dev *dev)
+{
+	return !(readl(dev->regs) & MVMDIO_SMI_BUSY);
+}
+
+static const struct orion_mdio_ops orion_mdio_smi_ops = {
+	.is_done = orion_mdio_smi_is_done,
+	.poll_interval_min = MVMDIO_SMI_POLL_INTERVAL_MIN,
+	.poll_interval_max = MVMDIO_SMI_POLL_INTERVAL_MAX,
+};
+
+static int orion_mdio_smi_read(struct mii_bus *bus, int mii_id,
+			       int regnum)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	u32 val;
+	int ret;
+
+	ret = orion_mdio_wait_ready(&orion_mdio_smi_ops, bus);
+	if (ret < 0)
+		return ret;
+
+	writel(((mii_id << MVMDIO_SMI_PHY_ADDR_SHIFT) |
+		(regnum << MVMDIO_SMI_PHY_REG_SHIFT)  |
+		MVMDIO_SMI_READ_OPERATION),
+	       dev->regs);
+
+	ret = orion_mdio_wait_ready(&orion_mdio_smi_ops, bus);
+	if (ret < 0)
+		return ret;
+
+	val = readl(dev->regs);
+	if (!(val & MVMDIO_SMI_READ_VALID)) {
+		dev_err(bus->parent, "SMI bus read not valid\n");
+		return -ENODEV;
+	}
+
+	return val & GENMASK(15, 0);
+}
+
+static int orion_mdio_smi_write(struct mii_bus *bus, int mii_id,
+				int regnum, u16 value)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	int ret;
+
+	ret = orion_mdio_wait_ready(&orion_mdio_smi_ops, bus);
+	if (ret < 0)
+		return ret;
+
+	writel(((mii_id << MVMDIO_SMI_PHY_ADDR_SHIFT) |
+		(regnum << MVMDIO_SMI_PHY_REG_SHIFT)  |
+		MVMDIO_SMI_WRITE_OPERATION            |
+		(value << MVMDIO_SMI_DATA_SHIFT)),
+	       dev->regs);
+
+	return 0;
+}
+
+static int orion_mdio_xsmi_is_done(struct orion_mdio_dev *dev)
+{
+	return !(readl(dev->regs + MVMDIO_XSMI_MGNT_REG) & MVMDIO_XSMI_BUSY);
+}
+
+static const struct orion_mdio_ops orion_mdio_xsmi_ops = {
+	.is_done = orion_mdio_xsmi_is_done,
+	.poll_interval_min = MVMDIO_XSMI_POLL_INTERVAL_MIN,
+	.poll_interval_max = MVMDIO_XSMI_POLL_INTERVAL_MAX,
+};
+
+static int orion_mdio_xsmi_read_c45(struct mii_bus *bus, int mii_id,
+				    int dev_addr, int regnum)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	int ret;
+
+	ret = orion_mdio_wait_ready(&orion_mdio_xsmi_ops, bus);
+	if (ret < 0)
+		return ret;
+
+	writel(regnum, dev->regs + MVMDIO_XSMI_ADDR_REG);
+	writel((mii_id << MVMDIO_XSMI_PHYADDR_SHIFT) |
+	       (dev_addr << MVMDIO_XSMI_DEVADDR_SHIFT) |
+	       MVMDIO_XSMI_READ_OPERATION,
+	       dev->regs + MVMDIO_XSMI_MGNT_REG);
+
+	ret = orion_mdio_wait_ready(&orion_mdio_xsmi_ops, bus);
+	if (ret < 0)
+		return ret;
+
+	if (!(readl(dev->regs + MVMDIO_XSMI_MGNT_REG) &
+	      MVMDIO_XSMI_READ_VALID)) {
+		dev_err(bus->parent, "XSMI bus read not valid\n");
+		return -ENODEV;
+	}
+
+	return readl(dev->regs + MVMDIO_XSMI_MGNT_REG) & GENMASK(15, 0);
+}
+
+static int orion_mdio_xsmi_write_c45(struct mii_bus *bus, int mii_id,
+				     int dev_addr, int regnum, u16 value)
+{
+	struct orion_mdio_dev *dev = bus->priv;
+	int ret;
+
+	ret = orion_mdio_wait_ready(&orion_mdio_xsmi_ops, bus);
+	if (ret < 0)
+		return ret;
+
+	writel(regnum, dev->regs + MVMDIO_XSMI_ADDR_REG);
+	writel((mii_id << MVMDIO_XSMI_PHYADDR_SHIFT) |
+	       (dev_addr << MVMDIO_XSMI_DEVADDR_SHIFT) |
+	       MVMDIO_XSMI_WRITE_OPERATION | value,
+	       dev->regs + MVMDIO_XSMI_MGNT_REG);
+
+	return 0;
+}
+
+static irqreturn_t orion_mdio_err_irq(int irq, void *dev_id)
+{
+	struct orion_mdio_dev *dev = dev_id;
+
+	if (readl(dev->regs + MVMDIO_ERR_INT_CAUSE) &
+			MVMDIO_ERR_INT_SMI_DONE) {
+		writel(~MVMDIO_ERR_INT_SMI_DONE,
+				dev->regs + MVMDIO_ERR_INT_CAUSE);
+		wake_up(&dev->smi_busy_wait);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int orion_mdio_probe(struct platform_device *pdev)
+{
+	enum orion_mdio_bus_type type;
+	struct resource *r;
+	struct mii_bus *bus;
+	struct orion_mdio_dev *dev;
+	int i, ret;
+
+	type = (enum orion_mdio_bus_type)device_get_match_data(&pdev->dev);
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "No SMI register address given\n");
+		return -ENODEV;
+	}
+
+	bus = devm_mdiobus_alloc_size(&pdev->dev,
+				      sizeof(struct orion_mdio_dev));
+	if (!bus)
+		return -ENOMEM;
+
+	switch (type) {
+	case BUS_TYPE_SMI:
+		bus->read = orion_mdio_smi_read;
+		bus->write = orion_mdio_smi_write;
+		break;
+	case BUS_TYPE_XSMI:
+		bus->read_c45 = orion_mdio_xsmi_read_c45;
+		bus->write_c45 = orion_mdio_xsmi_write_c45;
+		break;
+	}
+
+	bus->name = "orion_mdio_bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii",
+		 dev_name(&pdev->dev));
+	bus->parent = &pdev->dev;
+
+	dev = bus->priv;
+	dev->regs = devm_ioremap(&pdev->dev, r->start, resource_size(r));
+	if (!dev->regs) {
+		dev_err(&pdev->dev, "Unable to remap SMI register\n");
+		return -ENODEV;
+	}
+
+	init_waitqueue_head(&dev->smi_busy_wait);
+
+	if (pdev->dev.of_node) {
+		for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+			dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+			if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+				ret = -EPROBE_DEFER;
+				goto out_clk;
+			}
+			if (IS_ERR(dev->clk[i]))
+				break;
+			clk_prepare_enable(dev->clk[i]);
+		}
+
+		if (!IS_ERR(of_clk_get(pdev->dev.of_node,
+				       ARRAY_SIZE(dev->clk))))
+			dev_warn(&pdev->dev,
+				 "unsupported number of clocks, limiting to the first "
+				 __stringify(ARRAY_SIZE(dev->clk)) "\n");
+	} else {
+		dev->clk[0] = clk_get(&pdev->dev, NULL);
+		if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto out_clk;
+		}
+		if (!IS_ERR(dev->clk[0]))
+			clk_prepare_enable(dev->clk[0]);
+	}
+
+
+	dev->err_interrupt = platform_get_irq_optional(pdev, 0);
+	if (dev->err_interrupt > 0 &&
+	    resource_size(r) < MVMDIO_ERR_INT_MASK + 4) {
+		dev_err(&pdev->dev,
+			"disabling interrupt, resource size is too small\n");
+		dev->err_interrupt = 0;
+	}
+	if (dev->err_interrupt > 0) {
+		ret = devm_request_irq(&pdev->dev, dev->err_interrupt,
+					orion_mdio_err_irq,
+					IRQF_SHARED, pdev->name, dev);
+		if (ret)
+			goto out_mdio;
+
+		writel(MVMDIO_ERR_INT_SMI_DONE,
+			dev->regs + MVMDIO_ERR_INT_MASK);
+
+	} else if (dev->err_interrupt == -EPROBE_DEFER) {
+		ret = -EPROBE_DEFER;
+		goto out_mdio;
+	}
+
+	/* For the platforms not supporting DT/ACPI fall-back
+	 * to mdiobus_register via of_mdiobus_register.
+	 */
+	if (is_acpi_node(pdev->dev.fwnode))
+		ret = acpi_mdiobus_register(bus, pdev->dev.fwnode);
+	else
+		ret = of_mdiobus_register(bus, pdev->dev.of_node);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret);
+		goto out_mdio;
+	}
+
+	platform_set_drvdata(pdev, bus);
+
+	return 0;
+
+out_mdio:
+	if (dev->err_interrupt > 0)
+		writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
+
+out_clk:
+	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+		if (IS_ERR(dev->clk[i]))
+			break;
+		clk_disable_unprepare(dev->clk[i]);
+		clk_put(dev->clk[i]);
+	}
+
+	return ret;
+}
+
+static int orion_mdio_remove(struct platform_device *pdev)
+{
+	struct mii_bus *bus = platform_get_drvdata(pdev);
+	struct orion_mdio_dev *dev = bus->priv;
+	int i;
+
+	if (dev->err_interrupt > 0)
+		writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
+	mdiobus_unregister(bus);
+
+	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+		if (IS_ERR(dev->clk[i]))
+			break;
+		clk_disable_unprepare(dev->clk[i]);
+		clk_put(dev->clk[i]);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id orion_mdio_match[] = {
+	{ .compatible = "marvell,orion-mdio", .data = (void *)BUS_TYPE_SMI },
+	{ .compatible = "marvell,xmdio", .data = (void *)BUS_TYPE_XSMI },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, orion_mdio_match);
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id orion_mdio_acpi_match[] = {
+	{ "MRVL0100", BUS_TYPE_SMI },
+	{ "MRVL0101", BUS_TYPE_XSMI },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, orion_mdio_acpi_match);
+#endif
+
+static struct platform_driver orion_mdio_driver = {
+	.probe = orion_mdio_probe,
+	.remove = orion_mdio_remove,
+	.driver = {
+		.name = "orion-mdio",
+		.of_match_table = orion_mdio_match,
+		.acpi_match_table = ACPI_PTR(orion_mdio_acpi_match),
+	},
+};
+
+module_platform_driver(orion_mdio_driver);
+
+MODULE_DESCRIPTION("Marvell MDIO interface driver");
+MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@free-electrons.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:orion-mdio");