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, 487 insertions, 0 deletions

diff --git a/drivers/soc/fsl/qe/qe_ic.c b/drivers/soc/fsl/qe/qe_ic.c
new file mode 100644
index 000000000..bbae3d39c
--- /dev/null
+++ b/drivers/soc/fsl/qe/qe_ic.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * arch/powerpc/sysdev/qe_lib/qe_ic.c
+ *
+ * Copyright (C) 2006 Freescale Semiconductor, Inc.  All rights reserved.
+ *
+ * Author: Li Yang <leoli@freescale.com>
+ * Based on code from Shlomi Gridish <gridish@freescale.com>
+ *
+ * QUICC ENGINE Interrupt Controller
+ */
+
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/irq.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/stddef.h>
+#include <linux/sched.h>
+#include <linux/signal.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/platform_device.h>
+#include <asm/irq.h>
+#include <asm/io.h>
+#include <soc/fsl/qe/qe.h>
+
+#define NR_QE_IC_INTS		64
+
+/* QE IC registers offset */
+#define QEIC_CICR		0x00
+#define QEIC_CIVEC		0x04
+#define QEIC_CIPXCC		0x10
+#define QEIC_CIPYCC		0x14
+#define QEIC_CIPWCC		0x18
+#define QEIC_CIPZCC		0x1c
+#define QEIC_CIMR		0x20
+#define QEIC_CRIMR		0x24
+#define QEIC_CIPRTA		0x30
+#define QEIC_CIPRTB		0x34
+#define QEIC_CHIVEC		0x60
+
+struct qe_ic {
+	/* Control registers offset */
+	__be32 __iomem *regs;
+
+	/* The remapper for this QEIC */
+	struct irq_domain *irqhost;
+
+	/* The "linux" controller struct */
+	struct irq_chip hc_irq;
+
+	/* VIRQ numbers of QE high/low irqs */
+	int virq_high;
+	int virq_low;
+};
+
+/*
+ * QE interrupt controller internal structure
+ */
+struct qe_ic_info {
+	/* Location of this source at the QIMR register */
+	u32	mask;
+
+	/* Mask register offset */
+	u32	mask_reg;
+
+	/*
+	 * For grouped interrupts sources - the interrupt code as
+	 * appears at the group priority register
+	 */
+	u8	pri_code;
+
+	/* Group priority register offset */
+	u32	pri_reg;
+};
+
+static DEFINE_RAW_SPINLOCK(qe_ic_lock);
+
+static struct qe_ic_info qe_ic_info[] = {
+	[1] = {
+	       .mask = 0x00008000,
+	       .mask_reg = QEIC_CIMR,
+	       .pri_code = 0,
+	       .pri_reg = QEIC_CIPWCC,
+	       },
+	[2] = {
+	       .mask = 0x00004000,
+	       .mask_reg = QEIC_CIMR,
+	       .pri_code = 1,
+	       .pri_reg = QEIC_CIPWCC,
+	       },
+	[3] = {
+	       .mask = 0x00002000,
+	       .mask_reg = QEIC_CIMR,
+	       .pri_code = 2,
+	       .pri_reg = QEIC_CIPWCC,
+	       },
+	[10] = {
+		.mask = 0x00000040,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 1,
+		.pri_reg = QEIC_CIPZCC,
+		},
+	[11] = {
+		.mask = 0x00000020,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 2,
+		.pri_reg = QEIC_CIPZCC,
+		},
+	[12] = {
+		.mask = 0x00000010,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 3,
+		.pri_reg = QEIC_CIPZCC,
+		},
+	[13] = {
+		.mask = 0x00000008,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 4,
+		.pri_reg = QEIC_CIPZCC,
+		},
+	[14] = {
+		.mask = 0x00000004,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 5,
+		.pri_reg = QEIC_CIPZCC,
+		},
+	[15] = {
+		.mask = 0x00000002,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 6,
+		.pri_reg = QEIC_CIPZCC,
+		},
+	[20] = {
+		.mask = 0x10000000,
+		.mask_reg = QEIC_CRIMR,
+		.pri_code = 3,
+		.pri_reg = QEIC_CIPRTA,
+		},
+	[25] = {
+		.mask = 0x00800000,
+		.mask_reg = QEIC_CRIMR,
+		.pri_code = 0,
+		.pri_reg = QEIC_CIPRTB,
+		},
+	[26] = {
+		.mask = 0x00400000,
+		.mask_reg = QEIC_CRIMR,
+		.pri_code = 1,
+		.pri_reg = QEIC_CIPRTB,
+		},
+	[27] = {
+		.mask = 0x00200000,
+		.mask_reg = QEIC_CRIMR,
+		.pri_code = 2,
+		.pri_reg = QEIC_CIPRTB,
+		},
+	[28] = {
+		.mask = 0x00100000,
+		.mask_reg = QEIC_CRIMR,
+		.pri_code = 3,
+		.pri_reg = QEIC_CIPRTB,
+		},
+	[32] = {
+		.mask = 0x80000000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 0,
+		.pri_reg = QEIC_CIPXCC,
+		},
+	[33] = {
+		.mask = 0x40000000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 1,
+		.pri_reg = QEIC_CIPXCC,
+		},
+	[34] = {
+		.mask = 0x20000000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 2,
+		.pri_reg = QEIC_CIPXCC,
+		},
+	[35] = {
+		.mask = 0x10000000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 3,
+		.pri_reg = QEIC_CIPXCC,
+		},
+	[36] = {
+		.mask = 0x08000000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 4,
+		.pri_reg = QEIC_CIPXCC,
+		},
+	[40] = {
+		.mask = 0x00800000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 0,
+		.pri_reg = QEIC_CIPYCC,
+		},
+	[41] = {
+		.mask = 0x00400000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 1,
+		.pri_reg = QEIC_CIPYCC,
+		},
+	[42] = {
+		.mask = 0x00200000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 2,
+		.pri_reg = QEIC_CIPYCC,
+		},
+	[43] = {
+		.mask = 0x00100000,
+		.mask_reg = QEIC_CIMR,
+		.pri_code = 3,
+		.pri_reg = QEIC_CIPYCC,
+		},
+};
+
+static inline u32 qe_ic_read(__be32  __iomem *base, unsigned int reg)
+{
+	return ioread32be(base + (reg >> 2));
+}
+
+static inline void qe_ic_write(__be32  __iomem *base, unsigned int reg,
+			       u32 value)
+{
+	iowrite32be(value, base + (reg >> 2));
+}
+
+static inline struct qe_ic *qe_ic_from_irq(unsigned int virq)
+{
+	return irq_get_chip_data(virq);
+}
+
+static inline struct qe_ic *qe_ic_from_irq_data(struct irq_data *d)
+{
+	return irq_data_get_irq_chip_data(d);
+}
+
+static void qe_ic_unmask_irq(struct irq_data *d)
+{
+	struct qe_ic *qe_ic = qe_ic_from_irq_data(d);
+	unsigned int src = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 temp;
+
+	raw_spin_lock_irqsave(&qe_ic_lock, flags);
+
+	temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg);
+	qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg,
+		    temp | qe_ic_info[src].mask);
+
+	raw_spin_unlock_irqrestore(&qe_ic_lock, flags);
+}
+
+static void qe_ic_mask_irq(struct irq_data *d)
+{
+	struct qe_ic *qe_ic = qe_ic_from_irq_data(d);
+	unsigned int src = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 temp;
+
+	raw_spin_lock_irqsave(&qe_ic_lock, flags);
+
+	temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg);
+	qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg,
+		    temp & ~qe_ic_info[src].mask);
+
+	/* Flush the above write before enabling interrupts; otherwise,
+	 * spurious interrupts will sometimes happen.  To be 100% sure
+	 * that the write has reached the device before interrupts are
+	 * enabled, the mask register would have to be read back; however,
+	 * this is not required for correctness, only to avoid wasting
+	 * time on a large number of spurious interrupts.  In testing,
+	 * a sync reduced the observed spurious interrupts to zero.
+	 */
+	mb();
+
+	raw_spin_unlock_irqrestore(&qe_ic_lock, flags);
+}
+
+static struct irq_chip qe_ic_irq_chip = {
+	.name = "QEIC",
+	.irq_unmask = qe_ic_unmask_irq,
+	.irq_mask = qe_ic_mask_irq,
+	.irq_mask_ack = qe_ic_mask_irq,
+};
+
+static int qe_ic_host_match(struct irq_domain *h, struct device_node *node,
+			    enum irq_domain_bus_token bus_token)
+{
+	/* Exact match, unless qe_ic node is NULL */
+	struct device_node *of_node = irq_domain_get_of_node(h);
+	return of_node == NULL || of_node == node;
+}
+
+static int qe_ic_host_map(struct irq_domain *h, unsigned int virq,
+			  irq_hw_number_t hw)
+{
+	struct qe_ic *qe_ic = h->host_data;
+	struct irq_chip *chip;
+
+	if (hw >= ARRAY_SIZE(qe_ic_info)) {
+		pr_err("%s: Invalid hw irq number for QEIC\n", __func__);
+		return -EINVAL;
+	}
+
+	if (qe_ic_info[hw].mask == 0) {
+		printk(KERN_ERR "Can't map reserved IRQ\n");
+		return -EINVAL;
+	}
+	/* Default chip */
+	chip = &qe_ic->hc_irq;
+
+	irq_set_chip_data(virq, qe_ic);
+	irq_set_status_flags(virq, IRQ_LEVEL);
+
+	irq_set_chip_and_handler(virq, chip, handle_level_irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops qe_ic_host_ops = {
+	.match = qe_ic_host_match,
+	.map = qe_ic_host_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+/* Return an interrupt vector or 0 if no interrupt is pending. */
+static unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic)
+{
+	int irq;
+
+	BUG_ON(qe_ic == NULL);
+
+	/* get the interrupt source vector. */
+	irq = qe_ic_read(qe_ic->regs, QEIC_CIVEC) >> 26;
+
+	if (irq == 0)
+		return 0;
+
+	return irq_linear_revmap(qe_ic->irqhost, irq);
+}
+
+/* Return an interrupt vector or 0 if no interrupt is pending. */
+static unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic)
+{
+	int irq;
+
+	BUG_ON(qe_ic == NULL);
+
+	/* get the interrupt source vector. */
+	irq = qe_ic_read(qe_ic->regs, QEIC_CHIVEC) >> 26;
+
+	if (irq == 0)
+		return 0;
+
+	return irq_linear_revmap(qe_ic->irqhost, irq);
+}
+
+static void qe_ic_cascade_low(struct irq_desc *desc)
+{
+	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
+	unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	if (cascade_irq != 0)
+		generic_handle_irq(cascade_irq);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+
+static void qe_ic_cascade_high(struct irq_desc *desc)
+{
+	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
+	unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	if (cascade_irq != 0)
+		generic_handle_irq(cascade_irq);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+
+static void qe_ic_cascade_muxed_mpic(struct irq_desc *desc)
+{
+	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
+	unsigned int cascade_irq;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	cascade_irq = qe_ic_get_high_irq(qe_ic);
+	if (cascade_irq == 0)
+		cascade_irq = qe_ic_get_low_irq(qe_ic);
+
+	if (cascade_irq != 0)
+		generic_handle_irq(cascade_irq);
+
+	chip->irq_eoi(&desc->irq_data);
+}
+
+static int qe_ic_init(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	void (*low_handler)(struct irq_desc *desc);
+	void (*high_handler)(struct irq_desc *desc);
+	struct qe_ic *qe_ic;
+	struct resource *res;
+	struct device_node *node = pdev->dev.of_node;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res == NULL) {
+		dev_err(dev, "no memory resource defined\n");
+		return -ENODEV;
+	}
+
+	qe_ic = devm_kzalloc(dev, sizeof(*qe_ic), GFP_KERNEL);
+	if (qe_ic == NULL)
+		return -ENOMEM;
+
+	qe_ic->regs = devm_ioremap(dev, res->start, resource_size(res));
+	if (qe_ic->regs == NULL) {
+		dev_err(dev, "failed to ioremap() registers\n");
+		return -ENODEV;
+	}
+
+	qe_ic->hc_irq = qe_ic_irq_chip;
+
+	qe_ic->virq_high = platform_get_irq(pdev, 0);
+	qe_ic->virq_low = platform_get_irq(pdev, 1);
+
+	if (qe_ic->virq_low <= 0)
+		return -ENODEV;
+
+	if (qe_ic->virq_high > 0 && qe_ic->virq_high != qe_ic->virq_low) {
+		low_handler = qe_ic_cascade_low;
+		high_handler = qe_ic_cascade_high;
+	} else {
+		low_handler = qe_ic_cascade_muxed_mpic;
+		high_handler = NULL;
+	}
+
+	qe_ic->irqhost = irq_domain_add_linear(node, NR_QE_IC_INTS,
+					       &qe_ic_host_ops, qe_ic);
+	if (qe_ic->irqhost == NULL) {
+		dev_err(dev, "failed to add irq domain\n");
+		return -ENODEV;
+	}
+
+	qe_ic_write(qe_ic->regs, QEIC_CICR, 0);
+
+	irq_set_handler_data(qe_ic->virq_low, qe_ic);
+	irq_set_chained_handler(qe_ic->virq_low, low_handler);
+
+	if (high_handler) {
+		irq_set_handler_data(qe_ic->virq_high, qe_ic);
+		irq_set_chained_handler(qe_ic->virq_high, high_handler);
+	}
+	return 0;
+}
+static const struct of_device_id qe_ic_ids[] = {
+	{ .compatible = "fsl,qe-ic"},
+	{ .type = "qeic"},
+	{},
+};
+
+static struct platform_driver qe_ic_driver =
+{
+	.driver	= {
+		.name		= "qe-ic",
+		.of_match_table	= qe_ic_ids,
+	},
+	.probe	= qe_ic_init,
+};
+
+static int __init qe_ic_of_init(void)
+{
+	platform_driver_register(&qe_ic_driver);
+	return 0;
+}
+subsys_initcall(qe_ic_of_init);