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, 462 insertions, 0 deletions

diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
new file mode 100644
index 000000000..a62b96237
--- /dev/null
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Broadcom BCM7038 style Level 1 interrupt controller driver
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ * Author: Kevin Cernekee
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME	": " fmt
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/types.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/syscore_ops.h>
+
+#define IRQS_PER_WORD		32
+#define REG_BYTES_PER_IRQ_WORD	(sizeof(u32) * 4)
+#define MAX_WORDS		8
+
+struct bcm7038_l1_cpu;
+
+struct bcm7038_l1_chip {
+	raw_spinlock_t		lock;
+	unsigned int		n_words;
+	struct irq_domain	*domain;
+	struct bcm7038_l1_cpu	*cpus[NR_CPUS];
+#ifdef CONFIG_PM_SLEEP
+	struct list_head	list;
+	u32			wake_mask[MAX_WORDS];
+#endif
+	u32			irq_fwd_mask[MAX_WORDS];
+	u8			affinity[MAX_WORDS * IRQS_PER_WORD];
+};
+
+struct bcm7038_l1_cpu {
+	void __iomem		*map_base;
+	u32			mask_cache[];
+};
+
+/*
+ * STATUS/MASK_STATUS/MASK_SET/MASK_CLEAR are packed one right after another:
+ *
+ * 7038:
+ *   0x1000_1400: W0_STATUS
+ *   0x1000_1404: W1_STATUS
+ *   0x1000_1408: W0_MASK_STATUS
+ *   0x1000_140c: W1_MASK_STATUS
+ *   0x1000_1410: W0_MASK_SET
+ *   0x1000_1414: W1_MASK_SET
+ *   0x1000_1418: W0_MASK_CLEAR
+ *   0x1000_141c: W1_MASK_CLEAR
+ *
+ * 7445:
+ *   0xf03e_1500: W0_STATUS
+ *   0xf03e_1504: W1_STATUS
+ *   0xf03e_1508: W2_STATUS
+ *   0xf03e_150c: W3_STATUS
+ *   0xf03e_1510: W4_STATUS
+ *   0xf03e_1514: W0_MASK_STATUS
+ *   0xf03e_1518: W1_MASK_STATUS
+ *   [...]
+ */
+
+static inline unsigned int reg_status(struct bcm7038_l1_chip *intc,
+				      unsigned int word)
+{
+	return (0 * intc->n_words + word) * sizeof(u32);
+}
+
+static inline unsigned int reg_mask_status(struct bcm7038_l1_chip *intc,
+					   unsigned int word)
+{
+	return (1 * intc->n_words + word) * sizeof(u32);
+}
+
+static inline unsigned int reg_mask_set(struct bcm7038_l1_chip *intc,
+					unsigned int word)
+{
+	return (2 * intc->n_words + word) * sizeof(u32);
+}
+
+static inline unsigned int reg_mask_clr(struct bcm7038_l1_chip *intc,
+					unsigned int word)
+{
+	return (3 * intc->n_words + word) * sizeof(u32);
+}
+
+static inline u32 l1_readl(void __iomem *reg)
+{
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		return ioread32be(reg);
+	else
+		return readl(reg);
+}
+
+static inline void l1_writel(u32 val, void __iomem *reg)
+{
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		iowrite32be(val, reg);
+	else
+		writel(val, reg);
+}
+
+static void bcm7038_l1_irq_handle(struct irq_desc *desc)
+{
+	struct bcm7038_l1_chip *intc = irq_desc_get_handler_data(desc);
+	struct bcm7038_l1_cpu *cpu;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int idx;
+
+#if defined(CONFIG_SMP) && defined(CONFIG_MIPS)
+	cpu = intc->cpus[cpu_logical_map(smp_processor_id())];
+#else
+	cpu = intc->cpus[0];
+#endif
+
+	chained_irq_enter(chip, desc);
+
+	for (idx = 0; idx < intc->n_words; idx++) {
+		int base = idx * IRQS_PER_WORD;
+		unsigned long pending, flags;
+		int hwirq;
+
+		raw_spin_lock_irqsave(&intc->lock, flags);
+		pending = l1_readl(cpu->map_base + reg_status(intc, idx)) &
+			  ~cpu->mask_cache[idx];
+		raw_spin_unlock_irqrestore(&intc->lock, flags);
+
+		for_each_set_bit(hwirq, &pending, IRQS_PER_WORD)
+			generic_handle_domain_irq(intc->domain, base + hwirq);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void __bcm7038_l1_unmask(struct irq_data *d, unsigned int cpu_idx)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+
+	intc->cpus[cpu_idx]->mask_cache[word] &= ~mask;
+	l1_writel(mask, intc->cpus[cpu_idx]->map_base +
+			reg_mask_clr(intc, word));
+}
+
+static void __bcm7038_l1_mask(struct irq_data *d, unsigned int cpu_idx)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+
+	intc->cpus[cpu_idx]->mask_cache[word] |= mask;
+	l1_writel(mask, intc->cpus[cpu_idx]->map_base +
+			reg_mask_set(intc, word));
+}
+
+static void bcm7038_l1_unmask(struct irq_data *d)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	__bcm7038_l1_unmask(d, intc->affinity[d->hwirq]);
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+}
+
+static void bcm7038_l1_mask(struct irq_data *d)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	__bcm7038_l1_mask(d, intc->affinity[d->hwirq]);
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+}
+
+#if defined(CONFIG_MIPS) && defined(CONFIG_SMP)
+static int bcm7038_l1_set_affinity(struct irq_data *d,
+				   const struct cpumask *dest,
+				   bool force)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+	irq_hw_number_t hw = d->hwirq;
+	u32 word = hw / IRQS_PER_WORD;
+	u32 mask = BIT(hw % IRQS_PER_WORD);
+	unsigned int first_cpu = cpumask_any_and(dest, cpu_online_mask);
+	bool was_disabled;
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+
+	was_disabled = !!(intc->cpus[intc->affinity[hw]]->mask_cache[word] &
+			  mask);
+	__bcm7038_l1_mask(d, intc->affinity[hw]);
+	intc->affinity[hw] = first_cpu;
+	if (!was_disabled)
+		__bcm7038_l1_unmask(d, first_cpu);
+
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+	irq_data_update_effective_affinity(d, cpumask_of(first_cpu));
+
+	return 0;
+}
+#endif
+
+static int __init bcm7038_l1_init_one(struct device_node *dn,
+				      unsigned int idx,
+				      struct bcm7038_l1_chip *intc)
+{
+	struct resource res;
+	resource_size_t sz;
+	struct bcm7038_l1_cpu *cpu;
+	unsigned int i, n_words, parent_irq;
+	int ret;
+
+	if (of_address_to_resource(dn, idx, &res))
+		return -EINVAL;
+	sz = resource_size(&res);
+	n_words = sz / REG_BYTES_PER_IRQ_WORD;
+
+	if (n_words > MAX_WORDS)
+		return -EINVAL;
+	else if (!intc->n_words)
+		intc->n_words = n_words;
+	else if (intc->n_words != n_words)
+		return -EINVAL;
+
+	ret = of_property_read_u32_array(dn , "brcm,int-fwd-mask",
+					 intc->irq_fwd_mask, n_words);
+	if (ret != 0 && ret != -EINVAL) {
+		/* property exists but has the wrong number of words */
+		pr_err("invalid brcm,int-fwd-mask property\n");
+		return -EINVAL;
+	}
+
+	cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32),
+					GFP_KERNEL);
+	if (!cpu)
+		return -ENOMEM;
+
+	cpu->map_base = ioremap(res.start, sz);
+	if (!cpu->map_base)
+		return -ENOMEM;
+
+	for (i = 0; i < n_words; i++) {
+		l1_writel(~intc->irq_fwd_mask[i],
+			  cpu->map_base + reg_mask_set(intc, i));
+		l1_writel(intc->irq_fwd_mask[i],
+			  cpu->map_base + reg_mask_clr(intc, i));
+		cpu->mask_cache[i] = ~intc->irq_fwd_mask[i];
+	}
+
+	parent_irq = irq_of_parse_and_map(dn, idx);
+	if (!parent_irq) {
+		pr_err("failed to map parent interrupt %d\n", parent_irq);
+		return -EINVAL;
+	}
+
+	if (of_property_read_bool(dn, "brcm,irq-can-wake"))
+		enable_irq_wake(parent_irq);
+
+	irq_set_chained_handler_and_data(parent_irq, bcm7038_l1_irq_handle,
+					 intc);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+/*
+ * We keep a list of bcm7038_l1_chip used for suspend/resume. This hack is
+ * used because the struct chip_type suspend/resume hooks are not called
+ * unless chip_type is hooked onto a generic_chip. Since this driver does
+ * not use generic_chip, we need to manually hook our resume/suspend to
+ * syscore_ops.
+ */
+static LIST_HEAD(bcm7038_l1_intcs_list);
+static DEFINE_RAW_SPINLOCK(bcm7038_l1_intcs_lock);
+
+static int bcm7038_l1_suspend(void)
+{
+	struct bcm7038_l1_chip *intc;
+	int boot_cpu, word;
+	u32 val;
+
+	/* Wakeup interrupt should only come from the boot cpu */
+#if defined(CONFIG_SMP) && defined(CONFIG_MIPS)
+	boot_cpu = cpu_logical_map(0);
+#else
+	boot_cpu = 0;
+#endif
+
+	list_for_each_entry(intc, &bcm7038_l1_intcs_list, list) {
+		for (word = 0; word < intc->n_words; word++) {
+			val = intc->wake_mask[word] | intc->irq_fwd_mask[word];
+			l1_writel(~val,
+				intc->cpus[boot_cpu]->map_base + reg_mask_set(intc, word));
+			l1_writel(val,
+				intc->cpus[boot_cpu]->map_base + reg_mask_clr(intc, word));
+		}
+	}
+
+	return 0;
+}
+
+static void bcm7038_l1_resume(void)
+{
+	struct bcm7038_l1_chip *intc;
+	int boot_cpu, word;
+
+#if defined(CONFIG_SMP) && defined(CONFIG_MIPS)
+	boot_cpu = cpu_logical_map(0);
+#else
+	boot_cpu = 0;
+#endif
+
+	list_for_each_entry(intc, &bcm7038_l1_intcs_list, list) {
+		for (word = 0; word < intc->n_words; word++) {
+			l1_writel(intc->cpus[boot_cpu]->mask_cache[word],
+				intc->cpus[boot_cpu]->map_base + reg_mask_set(intc, word));
+			l1_writel(~intc->cpus[boot_cpu]->mask_cache[word],
+				intc->cpus[boot_cpu]->map_base + reg_mask_clr(intc, word));
+		}
+	}
+}
+
+static struct syscore_ops bcm7038_l1_syscore_ops = {
+	.suspend	= bcm7038_l1_suspend,
+	.resume		= bcm7038_l1_resume,
+};
+
+static int bcm7038_l1_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	if (on)
+		intc->wake_mask[word] |= mask;
+	else
+		intc->wake_mask[word] &= ~mask;
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+
+	return 0;
+}
+#endif
+
+static struct irq_chip bcm7038_l1_irq_chip = {
+	.name			= "bcm7038-l1",
+	.irq_mask		= bcm7038_l1_mask,
+	.irq_unmask		= bcm7038_l1_unmask,
+#if defined(CONFIG_SMP) && defined(CONFIG_MIPS)
+	.irq_set_affinity	= bcm7038_l1_set_affinity,
+#endif
+#ifdef CONFIG_PM_SLEEP
+	.irq_set_wake		= bcm7038_l1_set_wake,
+#endif
+};
+
+static int bcm7038_l1_map(struct irq_domain *d, unsigned int virq,
+			  irq_hw_number_t hw_irq)
+{
+	struct bcm7038_l1_chip *intc = d->host_data;
+	u32 mask = BIT(hw_irq % IRQS_PER_WORD);
+	u32 word = hw_irq / IRQS_PER_WORD;
+
+	if (intc->irq_fwd_mask[word] & mask)
+		return -EPERM;
+
+	irq_set_chip_and_handler(virq, &bcm7038_l1_irq_chip, handle_level_irq);
+	irq_set_chip_data(virq, d->host_data);
+	irqd_set_single_target(irq_get_irq_data(virq));
+	return 0;
+}
+
+static const struct irq_domain_ops bcm7038_l1_domain_ops = {
+	.xlate			= irq_domain_xlate_onecell,
+	.map			= bcm7038_l1_map,
+};
+
+static int __init bcm7038_l1_of_init(struct device_node *dn,
+			      struct device_node *parent)
+{
+	struct bcm7038_l1_chip *intc;
+	int idx, ret;
+
+	intc = kzalloc(sizeof(*intc), GFP_KERNEL);
+	if (!intc)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&intc->lock);
+	for_each_possible_cpu(idx) {
+		ret = bcm7038_l1_init_one(dn, idx, intc);
+		if (ret < 0) {
+			if (idx)
+				break;
+			pr_err("failed to remap intc L1 registers\n");
+			goto out_free;
+		}
+	}
+
+	intc->domain = irq_domain_add_linear(dn, IRQS_PER_WORD * intc->n_words,
+					     &bcm7038_l1_domain_ops,
+					     intc);
+	if (!intc->domain) {
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+#ifdef CONFIG_PM_SLEEP
+	/* Add bcm7038_l1_chip into a list */
+	raw_spin_lock(&bcm7038_l1_intcs_lock);
+	list_add_tail(&intc->list, &bcm7038_l1_intcs_list);
+	raw_spin_unlock(&bcm7038_l1_intcs_lock);
+
+	if (list_is_singular(&bcm7038_l1_intcs_list))
+		register_syscore_ops(&bcm7038_l1_syscore_ops);
+#endif
+
+	pr_info("registered BCM7038 L1 intc (%pOF, IRQs: %d)\n",
+		dn, IRQS_PER_WORD * intc->n_words);
+
+	return 0;
+
+out_unmap:
+	for_each_possible_cpu(idx) {
+		struct bcm7038_l1_cpu *cpu = intc->cpus[idx];
+
+		if (cpu) {
+			if (cpu->map_base)
+				iounmap(cpu->map_base);
+			kfree(cpu);
+		}
+	}
+out_free:
+	kfree(intc);
+	return ret;
+}
+
+IRQCHIP_PLATFORM_DRIVER_BEGIN(bcm7038_l1)
+IRQCHIP_MATCH("brcm,bcm7038-l1-intc", bcm7038_l1_of_init)
+IRQCHIP_PLATFORM_DRIVER_END(bcm7038_l1)
+MODULE_DESCRIPTION("Broadcom STB 7038-style L1/L2 interrupt controller");
+MODULE_LICENSE("GPL v2");