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, 409 insertions, 0 deletions

diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
new file mode 100644
index 000000000..3c77acc7e
--- /dev/null
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -0,0 +1,409 @@
+/*
+ * Copyright (C) 2017 Marvell
+ *
+ * Hanna Hawa <hannah@marvell.com>
+ * 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/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+
+#include <dt-bindings/interrupt-controller/mvebu-icu.h>
+
+/* ICU registers */
+#define ICU_SETSPI_NSR_AL	0x10
+#define ICU_SETSPI_NSR_AH	0x14
+#define ICU_CLRSPI_NSR_AL	0x18
+#define ICU_CLRSPI_NSR_AH	0x1c
+#define ICU_SET_SEI_AL		0x50
+#define ICU_SET_SEI_AH		0x54
+#define ICU_CLR_SEI_AL		0x58
+#define ICU_CLR_SEI_AH		0x5C
+#define ICU_INT_CFG(x)          (0x100 + 4 * (x))
+#define   ICU_INT_ENABLE	BIT(24)
+#define   ICU_IS_EDGE		BIT(28)
+#define   ICU_GROUP_SHIFT	29
+
+/* ICU definitions */
+#define ICU_MAX_IRQS		207
+#define ICU_SATA0_ICU_ID	109
+#define ICU_SATA1_ICU_ID	107
+
+struct mvebu_icu_subset_data {
+	unsigned int icu_group;
+	unsigned int offset_set_ah;
+	unsigned int offset_set_al;
+	unsigned int offset_clr_ah;
+	unsigned int offset_clr_al;
+};
+
+struct mvebu_icu {
+	void __iomem *base;
+	struct device *dev;
+};
+
+struct mvebu_icu_msi_data {
+	struct mvebu_icu *icu;
+	atomic_t initialized;
+	const struct mvebu_icu_subset_data *subset_data;
+};
+
+struct mvebu_icu_irq_data {
+	struct mvebu_icu *icu;
+	unsigned int icu_group;
+	unsigned int type;
+};
+
+static DEFINE_STATIC_KEY_FALSE(legacy_bindings);
+
+static void mvebu_icu_init(struct mvebu_icu *icu,
+			   struct mvebu_icu_msi_data *msi_data,
+			   struct msi_msg *msg)
+{
+	const struct mvebu_icu_subset_data *subset = msi_data->subset_data;
+
+	if (atomic_cmpxchg(&msi_data->initialized, false, true))
+		return;
+
+	/* Set 'SET' ICU SPI message address in AP */
+	writel_relaxed(msg[0].address_hi, icu->base + subset->offset_set_ah);
+	writel_relaxed(msg[0].address_lo, icu->base + subset->offset_set_al);
+
+	if (subset->icu_group != ICU_GRP_NSR)
+		return;
+
+	/* Set 'CLEAR' ICU SPI message address in AP (level-MSI only) */
+	writel_relaxed(msg[1].address_hi, icu->base + subset->offset_clr_ah);
+	writel_relaxed(msg[1].address_lo, icu->base + subset->offset_clr_al);
+}
+
+static void mvebu_icu_write_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	struct irq_data *d = irq_get_irq_data(desc->irq);
+	struct mvebu_icu_msi_data *msi_data = platform_msi_get_host_data(d->domain);
+	struct mvebu_icu_irq_data *icu_irqd = d->chip_data;
+	struct mvebu_icu *icu = icu_irqd->icu;
+	unsigned int icu_int;
+
+	if (msg->address_lo || msg->address_hi) {
+		/* One off initialization per domain */
+		mvebu_icu_init(icu, msi_data, msg);
+		/* Configure the ICU with irq number & type */
+		icu_int = msg->data | ICU_INT_ENABLE;
+		if (icu_irqd->type & IRQ_TYPE_EDGE_RISING)
+			icu_int |= ICU_IS_EDGE;
+		icu_int |= icu_irqd->icu_group << ICU_GROUP_SHIFT;
+	} else {
+		/* De-configure the ICU */
+		icu_int = 0;
+	}
+
+	writel_relaxed(icu_int, icu->base + ICU_INT_CFG(d->hwirq));
+
+	/*
+	 * The SATA unit has 2 ports, and a dedicated ICU entry per
+	 * port. The ahci sata driver supports only one irq interrupt
+	 * per SATA unit. To solve this conflict, we configure the 2
+	 * SATA wired interrupts in the south bridge into 1 GIC
+	 * interrupt in the north bridge. Even if only a single port
+	 * is enabled, if sata node is enabled, both interrupts are
+	 * configured (regardless of which port is actually in use).
+	 */
+	if (d->hwirq == ICU_SATA0_ICU_ID || d->hwirq == ICU_SATA1_ICU_ID) {
+		writel_relaxed(icu_int,
+			       icu->base + ICU_INT_CFG(ICU_SATA0_ICU_ID));
+		writel_relaxed(icu_int,
+			       icu->base + ICU_INT_CFG(ICU_SATA1_ICU_ID));
+	}
+}
+
+static struct irq_chip mvebu_icu_nsr_chip = {
+	.name			= "ICU-NSR",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_type		= irq_chip_set_type_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+};
+
+static struct irq_chip mvebu_icu_sei_chip = {
+	.name			= "ICU-SEI",
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_set_type		= irq_chip_set_type_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+};
+
+static int
+mvebu_icu_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec,
+			       unsigned long *hwirq, unsigned int *type)
+{
+	unsigned int param_count = static_branch_unlikely(&legacy_bindings) ? 3 : 2;
+	struct mvebu_icu_msi_data *msi_data = platform_msi_get_host_data(d);
+	struct mvebu_icu *icu = msi_data->icu;
+
+	/* Check the count of the parameters in dt */
+	if (WARN_ON(fwspec->param_count != param_count)) {
+		dev_err(icu->dev, "wrong ICU parameter count %d\n",
+			fwspec->param_count);
+		return -EINVAL;
+	}
+
+	if (static_branch_unlikely(&legacy_bindings)) {
+		*hwirq = fwspec->param[1];
+		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+		if (fwspec->param[0] != ICU_GRP_NSR) {
+			dev_err(icu->dev, "wrong ICU group type %x\n",
+				fwspec->param[0]);
+			return -EINVAL;
+		}
+	} else {
+		*hwirq = fwspec->param[0];
+		*type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK;
+
+		/*
+		 * The ICU receives level interrupts. While the NSR are also
+		 * level interrupts, SEI are edge interrupts. Force the type
+		 * here in this case. Please note that this makes the interrupt
+		 * handling unreliable.
+		 */
+		if (msi_data->subset_data->icu_group == ICU_GRP_SEI)
+			*type = IRQ_TYPE_EDGE_RISING;
+	}
+
+	if (*hwirq >= ICU_MAX_IRQS) {
+		dev_err(icu->dev, "invalid interrupt number %ld\n", *hwirq);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+mvebu_icu_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			   unsigned int nr_irqs, void *args)
+{
+	int err;
+	unsigned long hwirq;
+	struct irq_fwspec *fwspec = args;
+	struct mvebu_icu_msi_data *msi_data = platform_msi_get_host_data(domain);
+	struct mvebu_icu *icu = msi_data->icu;
+	struct mvebu_icu_irq_data *icu_irqd;
+	struct irq_chip *chip = &mvebu_icu_nsr_chip;
+
+	icu_irqd = kmalloc(sizeof(*icu_irqd), GFP_KERNEL);
+	if (!icu_irqd)
+		return -ENOMEM;
+
+	err = mvebu_icu_irq_domain_translate(domain, fwspec, &hwirq,
+					     &icu_irqd->type);
+	if (err) {
+		dev_err(icu->dev, "failed to translate ICU parameters\n");
+		goto free_irqd;
+	}
+
+	if (static_branch_unlikely(&legacy_bindings))
+		icu_irqd->icu_group = fwspec->param[0];
+	else
+		icu_irqd->icu_group = msi_data->subset_data->icu_group;
+	icu_irqd->icu = icu;
+
+	err = platform_msi_device_domain_alloc(domain, virq, nr_irqs);
+	if (err) {
+		dev_err(icu->dev, "failed to allocate ICU interrupt in parent domain\n");
+		goto free_irqd;
+	}
+
+	/* Make sure there is no interrupt left pending by the firmware */
+	err = irq_set_irqchip_state(virq, IRQCHIP_STATE_PENDING, false);
+	if (err)
+		goto free_msi;
+
+	if (icu_irqd->icu_group == ICU_GRP_SEI)
+		chip = &mvebu_icu_sei_chip;
+
+	err = irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+					    chip, icu_irqd);
+	if (err) {
+		dev_err(icu->dev, "failed to set the data to IRQ domain\n");
+		goto free_msi;
+	}
+
+	return 0;
+
+free_msi:
+	platform_msi_device_domain_free(domain, virq, nr_irqs);
+free_irqd:
+	kfree(icu_irqd);
+	return err;
+}
+
+static void
+mvebu_icu_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+			  unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_get_irq_data(virq);
+	struct mvebu_icu_irq_data *icu_irqd = d->chip_data;
+
+	kfree(icu_irqd);
+
+	platform_msi_device_domain_free(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops mvebu_icu_domain_ops = {
+	.translate = mvebu_icu_irq_domain_translate,
+	.alloc     = mvebu_icu_irq_domain_alloc,
+	.free      = mvebu_icu_irq_domain_free,
+};
+
+static const struct mvebu_icu_subset_data mvebu_icu_nsr_subset_data = {
+	.icu_group = ICU_GRP_NSR,
+	.offset_set_ah = ICU_SETSPI_NSR_AH,
+	.offset_set_al = ICU_SETSPI_NSR_AL,
+	.offset_clr_ah = ICU_CLRSPI_NSR_AH,
+	.offset_clr_al = ICU_CLRSPI_NSR_AL,
+};
+
+static const struct mvebu_icu_subset_data mvebu_icu_sei_subset_data = {
+	.icu_group = ICU_GRP_SEI,
+	.offset_set_ah = ICU_SET_SEI_AH,
+	.offset_set_al = ICU_SET_SEI_AL,
+};
+
+static const struct of_device_id mvebu_icu_subset_of_match[] = {
+	{
+		.compatible = "marvell,cp110-icu-nsr",
+		.data = &mvebu_icu_nsr_subset_data,
+	},
+	{
+		.compatible = "marvell,cp110-icu-sei",
+		.data = &mvebu_icu_sei_subset_data,
+	},
+	{},
+};
+
+static int mvebu_icu_subset_probe(struct platform_device *pdev)
+{
+	struct mvebu_icu_msi_data *msi_data;
+	struct device_node *msi_parent_dn;
+	struct device *dev = &pdev->dev;
+	struct irq_domain *irq_domain;
+
+	msi_data = devm_kzalloc(dev, sizeof(*msi_data), GFP_KERNEL);
+	if (!msi_data)
+		return -ENOMEM;
+
+	if (static_branch_unlikely(&legacy_bindings)) {
+		msi_data->icu = dev_get_drvdata(dev);
+		msi_data->subset_data = &mvebu_icu_nsr_subset_data;
+	} else {
+		msi_data->icu = dev_get_drvdata(dev->parent);
+		msi_data->subset_data = of_device_get_match_data(dev);
+	}
+
+	dev->msi.domain = of_msi_get_domain(dev, dev->of_node,
+					    DOMAIN_BUS_PLATFORM_MSI);
+	if (!dev->msi.domain)
+		return -EPROBE_DEFER;
+
+	msi_parent_dn = irq_domain_get_of_node(dev->msi.domain);
+	if (!msi_parent_dn)
+		return -ENODEV;
+
+	irq_domain = platform_msi_create_device_tree_domain(dev, ICU_MAX_IRQS,
+							    mvebu_icu_write_msg,
+							    &mvebu_icu_domain_ops,
+							    msi_data);
+	if (!irq_domain) {
+		dev_err(dev, "Failed to create ICU MSI domain\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct platform_driver mvebu_icu_subset_driver = {
+	.probe  = mvebu_icu_subset_probe,
+	.driver = {
+		.name = "mvebu-icu-subset",
+		.of_match_table = mvebu_icu_subset_of_match,
+	},
+};
+builtin_platform_driver(mvebu_icu_subset_driver);
+
+static int mvebu_icu_probe(struct platform_device *pdev)
+{
+	struct mvebu_icu *icu;
+	int i;
+
+	icu = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_icu),
+			   GFP_KERNEL);
+	if (!icu)
+		return -ENOMEM;
+
+	icu->dev = &pdev->dev;
+
+	icu->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(icu->base))
+		return PTR_ERR(icu->base);
+
+	/*
+	 * Legacy bindings: ICU is one node with one MSI parent: force manually
+	 *                  the probe of the NSR interrupts side.
+	 * New bindings: ICU node has children, one per interrupt controller
+	 *               having its own MSI parent: call platform_populate().
+	 * All ICU instances should use the same bindings.
+	 */
+	if (!of_get_child_count(pdev->dev.of_node))
+		static_branch_enable(&legacy_bindings);
+
+	/*
+	 * Clean all ICU interrupts of type NSR and SEI, required to
+	 * avoid unpredictable SPI assignments done by firmware.
+	 */
+	for (i = 0 ; i < ICU_MAX_IRQS ; i++) {
+		u32 icu_int, icu_grp;
+
+		icu_int = readl_relaxed(icu->base + ICU_INT_CFG(i));
+		icu_grp = icu_int >> ICU_GROUP_SHIFT;
+
+		if (icu_grp == ICU_GRP_NSR ||
+		    (icu_grp == ICU_GRP_SEI &&
+		     !static_branch_unlikely(&legacy_bindings)))
+			writel_relaxed(0x0, icu->base + ICU_INT_CFG(i));
+	}
+
+	platform_set_drvdata(pdev, icu);
+
+	if (static_branch_unlikely(&legacy_bindings))
+		return mvebu_icu_subset_probe(pdev);
+	else
+		return devm_of_platform_populate(&pdev->dev);
+}
+
+static const struct of_device_id mvebu_icu_of_match[] = {
+	{ .compatible = "marvell,cp110-icu", },
+	{},
+};
+
+static struct platform_driver mvebu_icu_driver = {
+	.probe  = mvebu_icu_probe,
+	.driver = {
+		.name = "mvebu-icu",
+		.of_match_table = mvebu_icu_of_match,
+	},
+};
+builtin_platform_driver(mvebu_icu_driver);