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, 467 insertions, 0 deletions

diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c
new file mode 100644
index 000000000..7aafc221b
--- /dev/null
+++ b/drivers/net/mdio/mdio-xgene.c
@@ -0,0 +1,467 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Applied Micro X-Gene SoC MDIO Driver
+ *
+ * Copyright (c) 2016, Applied Micro Circuits Corporation
+ * Author: Iyappan Subramanian <isubramanian@apm.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/efi.h>
+#include <linux/if_vlan.h>
+#include <linux/io.h>
+#include <linux/mdio/mdio-xgene.h>
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/prefetch.h>
+#include <net/ip.h>
+
+static bool xgene_mdio_status;
+
+u32 xgene_mdio_rd_mac(struct xgene_mdio_pdata *pdata, u32 rd_addr)
+{
+	void __iomem *addr, *rd, *cmd, *cmd_done;
+	u32 done, rd_data = BUSY_MASK;
+	u8 wait = 10;
+
+	addr = pdata->mac_csr_addr + MAC_ADDR_REG_OFFSET;
+	rd = pdata->mac_csr_addr + MAC_READ_REG_OFFSET;
+	cmd = pdata->mac_csr_addr + MAC_COMMAND_REG_OFFSET;
+	cmd_done = pdata->mac_csr_addr + MAC_COMMAND_DONE_REG_OFFSET;
+
+	spin_lock(&pdata->mac_lock);
+	iowrite32(rd_addr, addr);
+	iowrite32(XGENE_ENET_RD_CMD, cmd);
+
+	while (!(done = ioread32(cmd_done)) && wait--)
+		udelay(1);
+
+	if (done)
+		rd_data = ioread32(rd);
+
+	iowrite32(0, cmd);
+	spin_unlock(&pdata->mac_lock);
+
+	return rd_data;
+}
+EXPORT_SYMBOL(xgene_mdio_rd_mac);
+
+void xgene_mdio_wr_mac(struct xgene_mdio_pdata *pdata, u32 wr_addr, u32 data)
+{
+	void __iomem *addr, *wr, *cmd, *cmd_done;
+	u8 wait = 10;
+	u32 done;
+
+	addr = pdata->mac_csr_addr + MAC_ADDR_REG_OFFSET;
+	wr = pdata->mac_csr_addr + MAC_WRITE_REG_OFFSET;
+	cmd = pdata->mac_csr_addr + MAC_COMMAND_REG_OFFSET;
+	cmd_done = pdata->mac_csr_addr + MAC_COMMAND_DONE_REG_OFFSET;
+
+	spin_lock(&pdata->mac_lock);
+	iowrite32(wr_addr, addr);
+	iowrite32(data, wr);
+	iowrite32(XGENE_ENET_WR_CMD, cmd);
+
+	while (!(done = ioread32(cmd_done)) && wait--)
+		udelay(1);
+
+	if (!done)
+		pr_err("MCX mac write failed, addr: 0x%04x\n", wr_addr);
+
+	iowrite32(0, cmd);
+	spin_unlock(&pdata->mac_lock);
+}
+EXPORT_SYMBOL(xgene_mdio_wr_mac);
+
+int xgene_mdio_rgmii_read(struct mii_bus *bus, int phy_id, int reg)
+{
+	struct xgene_mdio_pdata *pdata = (struct xgene_mdio_pdata *)bus->priv;
+	u32 data, done;
+	u8 wait = 10;
+
+	data = SET_VAL(PHY_ADDR, phy_id) | SET_VAL(REG_ADDR, reg);
+	xgene_mdio_wr_mac(pdata, MII_MGMT_ADDRESS_ADDR, data);
+	xgene_mdio_wr_mac(pdata, MII_MGMT_COMMAND_ADDR, READ_CYCLE_MASK);
+	do {
+		usleep_range(5, 10);
+		done = xgene_mdio_rd_mac(pdata, MII_MGMT_INDICATORS_ADDR);
+	} while ((done & BUSY_MASK) && wait--);
+
+	if (done & BUSY_MASK) {
+		dev_err(&bus->dev, "MII_MGMT read failed\n");
+		return -EBUSY;
+	}
+
+	data = xgene_mdio_rd_mac(pdata, MII_MGMT_STATUS_ADDR);
+	xgene_mdio_wr_mac(pdata, MII_MGMT_COMMAND_ADDR, 0);
+
+	return data;
+}
+EXPORT_SYMBOL(xgene_mdio_rgmii_read);
+
+int xgene_mdio_rgmii_write(struct mii_bus *bus, int phy_id, int reg, u16 data)
+{
+	struct xgene_mdio_pdata *pdata = (struct xgene_mdio_pdata *)bus->priv;
+	u32 val, done;
+	u8 wait = 10;
+
+	val = SET_VAL(PHY_ADDR, phy_id) | SET_VAL(REG_ADDR, reg);
+	xgene_mdio_wr_mac(pdata, MII_MGMT_ADDRESS_ADDR, val);
+
+	xgene_mdio_wr_mac(pdata, MII_MGMT_CONTROL_ADDR, data);
+	do {
+		usleep_range(5, 10);
+		done = xgene_mdio_rd_mac(pdata, MII_MGMT_INDICATORS_ADDR);
+	} while ((done & BUSY_MASK) && wait--);
+
+	if (done & BUSY_MASK) {
+		dev_err(&bus->dev, "MII_MGMT write failed\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(xgene_mdio_rgmii_write);
+
+static u32 xgene_menet_rd_diag_csr(struct xgene_mdio_pdata *pdata, u32 offset)
+{
+	return ioread32(pdata->diag_csr_addr + offset);
+}
+
+static void xgene_menet_wr_diag_csr(struct xgene_mdio_pdata *pdata,
+				    u32 offset, u32 val)
+{
+	iowrite32(val, pdata->diag_csr_addr + offset);
+}
+
+static int xgene_enet_ecc_init(struct xgene_mdio_pdata *pdata)
+{
+	u32 data;
+	u8 wait = 10;
+
+	xgene_menet_wr_diag_csr(pdata, MENET_CFG_MEM_RAM_SHUTDOWN_ADDR, 0x0);
+	do {
+		usleep_range(100, 110);
+		data = xgene_menet_rd_diag_csr(pdata, MENET_BLOCK_MEM_RDY_ADDR);
+	} while ((data != 0xffffffff) && wait--);
+
+	if (data != 0xffffffff) {
+		dev_err(pdata->dev, "Failed to release memory from shutdown\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void xgene_gmac_reset(struct xgene_mdio_pdata *pdata)
+{
+	xgene_mdio_wr_mac(pdata, MAC_CONFIG_1_ADDR, SOFT_RESET);
+	xgene_mdio_wr_mac(pdata, MAC_CONFIG_1_ADDR, 0);
+}
+
+static int xgene_mdio_reset(struct xgene_mdio_pdata *pdata)
+{
+	int ret;
+
+	if (pdata->dev->of_node) {
+		clk_prepare_enable(pdata->clk);
+		udelay(5);
+		clk_disable_unprepare(pdata->clk);
+		udelay(5);
+		clk_prepare_enable(pdata->clk);
+		udelay(5);
+	} else {
+#ifdef CONFIG_ACPI
+		acpi_evaluate_object(ACPI_HANDLE(pdata->dev),
+				     "_RST", NULL, NULL);
+#endif
+	}
+
+	ret = xgene_enet_ecc_init(pdata);
+	if (ret) {
+		if (pdata->dev->of_node)
+			clk_disable_unprepare(pdata->clk);
+		return ret;
+	}
+	xgene_gmac_reset(pdata);
+
+	return 0;
+}
+
+static void xgene_enet_rd_mdio_csr(void __iomem *base_addr,
+				   u32 offset, u32 *val)
+{
+	void __iomem *addr = base_addr  + offset;
+
+	*val = ioread32(addr);
+}
+
+static void xgene_enet_wr_mdio_csr(void __iomem *base_addr,
+				   u32 offset, u32 val)
+{
+	void __iomem *addr = base_addr  + offset;
+
+	iowrite32(val, addr);
+}
+
+static int xgene_xfi_mdio_write(struct mii_bus *bus, int phy_id,
+				int reg, u16 data)
+{
+	void __iomem *addr = (void __iomem *)bus->priv;
+	int timeout = 100;
+	u32 status, val;
+
+	val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg) |
+	      SET_VAL(HSTMIIMWRDAT, data);
+	xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val);
+
+	val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_WRITE);
+	xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val);
+
+	do {
+		usleep_range(5, 10);
+		xgene_enet_rd_mdio_csr(addr, MIIM_INDICATOR_ADDR, &status);
+	} while ((status & BUSY_MASK) && timeout--);
+
+	xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, 0);
+
+	return 0;
+}
+
+static int xgene_xfi_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+{
+	void __iomem *addr = (void __iomem *)bus->priv;
+	u32 data, status, val;
+	int timeout = 100;
+
+	val = SET_VAL(HSTPHYADX, phy_id) | SET_VAL(HSTREGADX, reg);
+	xgene_enet_wr_mdio_csr(addr, MIIM_FIELD_ADDR, val);
+
+	val = HSTLDCMD | SET_VAL(HSTMIIMCMD, MIIM_CMD_LEGACY_READ);
+	xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, val);
+
+	do {
+		usleep_range(5, 10);
+		xgene_enet_rd_mdio_csr(addr, MIIM_INDICATOR_ADDR, &status);
+	} while ((status & BUSY_MASK) && timeout--);
+
+	if (status & BUSY_MASK) {
+		pr_err("XGENET_MII_MGMT write failed\n");
+		return -EBUSY;
+	}
+
+	xgene_enet_rd_mdio_csr(addr, MIIMRD_FIELD_ADDR, &data);
+	xgene_enet_wr_mdio_csr(addr, MIIM_COMMAND_ADDR, 0);
+
+	return data;
+}
+
+struct phy_device *xgene_enet_phy_register(struct mii_bus *bus, int phy_addr)
+{
+	struct phy_device *phy_dev;
+
+	phy_dev = get_phy_device(bus, phy_addr, false);
+	if (!phy_dev || IS_ERR(phy_dev))
+		return NULL;
+
+	if (phy_device_register(phy_dev))
+		phy_device_free(phy_dev);
+
+	return phy_dev;
+}
+EXPORT_SYMBOL(xgene_enet_phy_register);
+
+#ifdef CONFIG_ACPI
+static acpi_status acpi_register_phy(acpi_handle handle, u32 lvl,
+				     void *context, void **ret)
+{
+	struct mii_bus *mdio = context;
+	struct acpi_device *adev;
+	struct phy_device *phy_dev;
+	const union acpi_object *obj;
+	u32 phy_addr;
+
+	adev = acpi_fetch_acpi_dev(handle);
+	if (!adev)
+		return AE_OK;
+
+	if (acpi_dev_get_property(adev, "phy-channel", ACPI_TYPE_INTEGER, &obj))
+		return AE_OK;
+	phy_addr = obj->integer.value;
+
+	phy_dev = xgene_enet_phy_register(mdio, phy_addr);
+	adev->driver_data = phy_dev;
+
+	return AE_OK;
+}
+#endif
+
+static const struct of_device_id xgene_mdio_of_match[] = {
+	{
+		.compatible = "apm,xgene-mdio-rgmii",
+		.data = (void *)XGENE_MDIO_RGMII
+	},
+	{
+		.compatible = "apm,xgene-mdio-xfi",
+		.data = (void *)XGENE_MDIO_XFI
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, xgene_mdio_of_match);
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xgene_mdio_acpi_match[] = {
+	{ "APMC0D65", XGENE_MDIO_RGMII },
+	{ "APMC0D66", XGENE_MDIO_XFI },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(acpi, xgene_mdio_acpi_match);
+#endif
+
+
+static int xgene_mdio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mii_bus *mdio_bus;
+	const struct of_device_id *of_id;
+	struct xgene_mdio_pdata *pdata;
+	void __iomem *csr_base;
+	int mdio_id = 0, ret = 0;
+
+	of_id = of_match_device(xgene_mdio_of_match, &pdev->dev);
+	if (of_id) {
+		mdio_id = (enum xgene_mdio_id)of_id->data;
+	} else {
+#ifdef CONFIG_ACPI
+		const struct acpi_device_id *acpi_id;
+
+		acpi_id = acpi_match_device(xgene_mdio_acpi_match, &pdev->dev);
+		if (acpi_id)
+			mdio_id = (enum xgene_mdio_id)acpi_id->driver_data;
+#endif
+	}
+
+	if (!mdio_id)
+		return -ENODEV;
+
+	pdata = devm_kzalloc(dev, sizeof(struct xgene_mdio_pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+	pdata->mdio_id = mdio_id;
+	pdata->dev = dev;
+
+	csr_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(csr_base))
+		return PTR_ERR(csr_base);
+	pdata->mac_csr_addr = csr_base;
+	pdata->mdio_csr_addr = csr_base + BLOCK_XG_MDIO_CSR_OFFSET;
+	pdata->diag_csr_addr = csr_base + BLOCK_DIAG_CSR_OFFSET;
+
+	if (mdio_id == XGENE_MDIO_RGMII)
+		spin_lock_init(&pdata->mac_lock);
+
+	if (dev->of_node) {
+		pdata->clk = devm_clk_get(dev, NULL);
+		if (IS_ERR(pdata->clk)) {
+			dev_err(dev, "Unable to retrieve clk\n");
+			return PTR_ERR(pdata->clk);
+		}
+	}
+
+	ret = xgene_mdio_reset(pdata);
+	if (ret)
+		return ret;
+
+	mdio_bus = mdiobus_alloc();
+	if (!mdio_bus) {
+		ret = -ENOMEM;
+		goto out_clk;
+	}
+
+	mdio_bus->name = "APM X-Gene MDIO bus";
+
+	if (mdio_id == XGENE_MDIO_RGMII) {
+		mdio_bus->read = xgene_mdio_rgmii_read;
+		mdio_bus->write = xgene_mdio_rgmii_write;
+		mdio_bus->priv = (void __force *)pdata;
+		snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s",
+			 "xgene-mii-rgmii");
+	} else {
+		mdio_bus->read = xgene_xfi_mdio_read;
+		mdio_bus->write = xgene_xfi_mdio_write;
+		mdio_bus->priv = (void __force *)pdata->mdio_csr_addr;
+		snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s",
+			 "xgene-mii-xfi");
+	}
+
+	mdio_bus->parent = dev;
+	platform_set_drvdata(pdev, pdata);
+
+	if (dev->of_node) {
+		ret = of_mdiobus_register(mdio_bus, dev->of_node);
+	} else {
+#ifdef CONFIG_ACPI
+		/* Mask out all PHYs from auto probing. */
+		mdio_bus->phy_mask = ~0;
+		ret = mdiobus_register(mdio_bus);
+		if (ret)
+			goto out_mdiobus;
+
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_HANDLE(dev), 1,
+				    acpi_register_phy, NULL, mdio_bus, NULL);
+#endif
+	}
+
+	if (ret)
+		goto out_mdiobus;
+
+	pdata->mdio_bus = mdio_bus;
+	xgene_mdio_status = true;
+
+	return 0;
+
+out_mdiobus:
+	mdiobus_free(mdio_bus);
+
+out_clk:
+	if (dev->of_node)
+		clk_disable_unprepare(pdata->clk);
+
+	return ret;
+}
+
+static int xgene_mdio_remove(struct platform_device *pdev)
+{
+	struct xgene_mdio_pdata *pdata = platform_get_drvdata(pdev);
+	struct mii_bus *mdio_bus = pdata->mdio_bus;
+	struct device *dev = &pdev->dev;
+
+	mdiobus_unregister(mdio_bus);
+	mdiobus_free(mdio_bus);
+
+	if (dev->of_node)
+		clk_disable_unprepare(pdata->clk);
+
+	return 0;
+}
+
+static struct platform_driver xgene_mdio_driver = {
+	.driver = {
+		.name = "xgene-mdio",
+		.of_match_table = of_match_ptr(xgene_mdio_of_match),
+		.acpi_match_table = ACPI_PTR(xgene_mdio_acpi_match),
+	},
+	.probe = xgene_mdio_probe,
+	.remove = xgene_mdio_remove,
+};
+
+module_platform_driver(xgene_mdio_driver);
+
+MODULE_DESCRIPTION("APM X-Gene SoC MDIO driver");
+MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>");
+MODULE_LICENSE("GPL");