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, 433 insertions, 0 deletions

diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c
new file mode 100644
index 000000000..527c90e09
--- /dev/null
+++ b/drivers/irqchip/irq-ls-scfg-msi.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Freescale SCFG MSI(-X) support
+ *
+ * Copyright (C) 2016 Freescale Semiconductor.
+ *
+ * Author: Minghuan Lian <Minghuan.Lian@nxp.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+
+#define MSI_IRQS_PER_MSIR	32
+#define MSI_MSIR_OFFSET		4
+
+#define MSI_LS1043V1_1_IRQS_PER_MSIR	8
+#define MSI_LS1043V1_1_MSIR_OFFSET	0x10
+
+struct ls_scfg_msi_cfg {
+	u32 ibs_shift; /* Shift of interrupt bit select */
+	u32 msir_irqs; /* The irq number per MSIR */
+	u32 msir_base; /* The base address of MSIR */
+};
+
+struct ls_scfg_msir {
+	struct ls_scfg_msi *msi_data;
+	unsigned int index;
+	unsigned int gic_irq;
+	unsigned int bit_start;
+	unsigned int bit_end;
+	unsigned int srs; /* Shared interrupt register select */
+	void __iomem *reg;
+};
+
+struct ls_scfg_msi {
+	spinlock_t		lock;
+	struct platform_device	*pdev;
+	struct irq_domain	*parent;
+	struct irq_domain	*msi_domain;
+	void __iomem		*regs;
+	phys_addr_t		msiir_addr;
+	struct ls_scfg_msi_cfg	*cfg;
+	u32			msir_num;
+	struct ls_scfg_msir	*msir;
+	u32			irqs_num;
+	unsigned long		*used;
+};
+
+static struct irq_chip ls_scfg_msi_irq_chip = {
+	.name = "MSI",
+	.irq_mask	= pci_msi_mask_irq,
+	.irq_unmask	= pci_msi_unmask_irq,
+};
+
+static struct msi_domain_info ls_scfg_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS |
+		   MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_PCI_MSIX),
+	.chip	= &ls_scfg_msi_irq_chip,
+};
+
+static int msi_affinity_flag = 1;
+
+static int __init early_parse_ls_scfg_msi(char *p)
+{
+	if (p && strncmp(p, "no-affinity", 11) == 0)
+		msi_affinity_flag = 0;
+	else
+		msi_affinity_flag = 1;
+
+	return 0;
+}
+early_param("lsmsi", early_parse_ls_scfg_msi);
+
+static void ls_scfg_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct ls_scfg_msi *msi_data = irq_data_get_irq_chip_data(data);
+
+	msg->address_hi = upper_32_bits(msi_data->msiir_addr);
+	msg->address_lo = lower_32_bits(msi_data->msiir_addr);
+	msg->data = data->hwirq;
+
+	if (msi_affinity_flag) {
+		const struct cpumask *mask;
+
+		mask = irq_data_get_effective_affinity_mask(data);
+		msg->data |= cpumask_first(mask);
+	}
+
+	iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), msg);
+}
+
+static int ls_scfg_msi_set_affinity(struct irq_data *irq_data,
+				    const struct cpumask *mask, bool force)
+{
+	struct ls_scfg_msi *msi_data = irq_data_get_irq_chip_data(irq_data);
+	u32 cpu;
+
+	if (!msi_affinity_flag)
+		return -EINVAL;
+
+	if (!force)
+		cpu = cpumask_any_and(mask, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask);
+
+	if (cpu >= msi_data->msir_num)
+		return -EINVAL;
+
+	if (msi_data->msir[cpu].gic_irq <= 0) {
+		pr_warn("cannot bind the irq to cpu%d\n", cpu);
+		return -EINVAL;
+	}
+
+	irq_data_update_effective_affinity(irq_data, cpumask_of(cpu));
+
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip ls_scfg_msi_parent_chip = {
+	.name			= "SCFG",
+	.irq_compose_msi_msg	= ls_scfg_msi_compose_msg,
+	.irq_set_affinity	= ls_scfg_msi_set_affinity,
+};
+
+static int ls_scfg_msi_domain_irq_alloc(struct irq_domain *domain,
+					unsigned int virq,
+					unsigned int nr_irqs,
+					void *args)
+{
+	msi_alloc_info_t *info = args;
+	struct ls_scfg_msi *msi_data = domain->host_data;
+	int pos, err = 0;
+
+	WARN_ON(nr_irqs != 1);
+
+	spin_lock(&msi_data->lock);
+	pos = find_first_zero_bit(msi_data->used, msi_data->irqs_num);
+	if (pos < msi_data->irqs_num)
+		__set_bit(pos, msi_data->used);
+	else
+		err = -ENOSPC;
+	spin_unlock(&msi_data->lock);
+
+	if (err)
+		return err;
+
+	err = iommu_dma_prepare_msi(info->desc, msi_data->msiir_addr);
+	if (err)
+		return err;
+
+	irq_domain_set_info(domain, virq, pos,
+			    &ls_scfg_msi_parent_chip, msi_data,
+			    handle_simple_irq, NULL, NULL);
+
+	return 0;
+}
+
+static void ls_scfg_msi_domain_irq_free(struct irq_domain *domain,
+				   unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct ls_scfg_msi *msi_data = irq_data_get_irq_chip_data(d);
+	int pos;
+
+	pos = d->hwirq;
+	if (pos < 0 || pos >= msi_data->irqs_num) {
+		pr_err("failed to teardown msi. Invalid hwirq %d\n", pos);
+		return;
+	}
+
+	spin_lock(&msi_data->lock);
+	__clear_bit(pos, msi_data->used);
+	spin_unlock(&msi_data->lock);
+}
+
+static const struct irq_domain_ops ls_scfg_msi_domain_ops = {
+	.alloc	= ls_scfg_msi_domain_irq_alloc,
+	.free	= ls_scfg_msi_domain_irq_free,
+};
+
+static void ls_scfg_msi_irq_handler(struct irq_desc *desc)
+{
+	struct ls_scfg_msir *msir = irq_desc_get_handler_data(desc);
+	struct ls_scfg_msi *msi_data = msir->msi_data;
+	unsigned long val;
+	int pos, size, hwirq;
+
+	chained_irq_enter(irq_desc_get_chip(desc), desc);
+
+	val = ioread32be(msir->reg);
+
+	pos = msir->bit_start;
+	size = msir->bit_end + 1;
+
+	for_each_set_bit_from(pos, &val, size) {
+		hwirq = ((msir->bit_end - pos) << msi_data->cfg->ibs_shift) |
+			msir->srs;
+		generic_handle_domain_irq(msi_data->parent, hwirq);
+	}
+
+	chained_irq_exit(irq_desc_get_chip(desc), desc);
+}
+
+static int ls_scfg_msi_domains_init(struct ls_scfg_msi *msi_data)
+{
+	/* Initialize MSI domain parent */
+	msi_data->parent = irq_domain_add_linear(NULL,
+						 msi_data->irqs_num,
+						 &ls_scfg_msi_domain_ops,
+						 msi_data);
+	if (!msi_data->parent) {
+		dev_err(&msi_data->pdev->dev, "failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	msi_data->msi_domain = pci_msi_create_irq_domain(
+				of_node_to_fwnode(msi_data->pdev->dev.of_node),
+				&ls_scfg_msi_domain_info,
+				msi_data->parent);
+	if (!msi_data->msi_domain) {
+		dev_err(&msi_data->pdev->dev, "failed to create MSI domain\n");
+		irq_domain_remove(msi_data->parent);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int ls_scfg_msi_setup_hwirq(struct ls_scfg_msi *msi_data, int index)
+{
+	struct ls_scfg_msir *msir;
+	int virq, i, hwirq;
+
+	virq = platform_get_irq(msi_data->pdev, index);
+	if (virq <= 0)
+		return -ENODEV;
+
+	msir = &msi_data->msir[index];
+	msir->index = index;
+	msir->msi_data = msi_data;
+	msir->gic_irq = virq;
+	msir->reg = msi_data->regs + msi_data->cfg->msir_base + 4 * index;
+
+	if (msi_data->cfg->msir_irqs == MSI_LS1043V1_1_IRQS_PER_MSIR) {
+		msir->bit_start = 32 - ((msir->index + 1) *
+				  MSI_LS1043V1_1_IRQS_PER_MSIR);
+		msir->bit_end = msir->bit_start +
+				MSI_LS1043V1_1_IRQS_PER_MSIR - 1;
+	} else {
+		msir->bit_start = 0;
+		msir->bit_end = msi_data->cfg->msir_irqs - 1;
+	}
+
+	irq_set_chained_handler_and_data(msir->gic_irq,
+					 ls_scfg_msi_irq_handler,
+					 msir);
+
+	if (msi_affinity_flag) {
+		/* Associate MSIR interrupt to the cpu */
+		irq_set_affinity(msir->gic_irq, get_cpu_mask(index));
+		msir->srs = 0; /* This value is determined by the CPU */
+	} else
+		msir->srs = index;
+
+	/* Release the hwirqs corresponding to this MSIR */
+	if (!msi_affinity_flag || msir->index == 0) {
+		for (i = 0; i < msi_data->cfg->msir_irqs; i++) {
+			hwirq = i << msi_data->cfg->ibs_shift | msir->index;
+			bitmap_clear(msi_data->used, hwirq, 1);
+		}
+	}
+
+	return 0;
+}
+
+static int ls_scfg_msi_teardown_hwirq(struct ls_scfg_msir *msir)
+{
+	struct ls_scfg_msi *msi_data = msir->msi_data;
+	int i, hwirq;
+
+	if (msir->gic_irq > 0)
+		irq_set_chained_handler_and_data(msir->gic_irq, NULL, NULL);
+
+	for (i = 0; i < msi_data->cfg->msir_irqs; i++) {
+		hwirq = i << msi_data->cfg->ibs_shift | msir->index;
+		bitmap_set(msi_data->used, hwirq, 1);
+	}
+
+	return 0;
+}
+
+static struct ls_scfg_msi_cfg ls1021_msi_cfg = {
+	.ibs_shift = 3,
+	.msir_irqs = MSI_IRQS_PER_MSIR,
+	.msir_base = MSI_MSIR_OFFSET,
+};
+
+static struct ls_scfg_msi_cfg ls1046_msi_cfg = {
+	.ibs_shift = 2,
+	.msir_irqs = MSI_IRQS_PER_MSIR,
+	.msir_base = MSI_MSIR_OFFSET,
+};
+
+static struct ls_scfg_msi_cfg ls1043_v1_1_msi_cfg = {
+	.ibs_shift = 2,
+	.msir_irqs = MSI_LS1043V1_1_IRQS_PER_MSIR,
+	.msir_base = MSI_LS1043V1_1_MSIR_OFFSET,
+};
+
+static const struct of_device_id ls_scfg_msi_id[] = {
+	/* The following two misspelled compatibles are obsolete */
+	{ .compatible = "fsl,1s1021a-msi", .data = &ls1021_msi_cfg},
+	{ .compatible = "fsl,1s1043a-msi", .data = &ls1021_msi_cfg},
+
+	{ .compatible = "fsl,ls1012a-msi", .data = &ls1021_msi_cfg },
+	{ .compatible = "fsl,ls1021a-msi", .data = &ls1021_msi_cfg },
+	{ .compatible = "fsl,ls1043a-msi", .data = &ls1021_msi_cfg },
+	{ .compatible = "fsl,ls1043a-v1.1-msi", .data = &ls1043_v1_1_msi_cfg },
+	{ .compatible = "fsl,ls1046a-msi", .data = &ls1046_msi_cfg },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ls_scfg_msi_id);
+
+static int ls_scfg_msi_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	struct ls_scfg_msi *msi_data;
+	struct resource *res;
+	int i, ret;
+
+	match = of_match_device(ls_scfg_msi_id, &pdev->dev);
+	if (!match)
+		return -ENODEV;
+
+	msi_data = devm_kzalloc(&pdev->dev, sizeof(*msi_data), GFP_KERNEL);
+	if (!msi_data)
+		return -ENOMEM;
+
+	msi_data->cfg = (struct ls_scfg_msi_cfg *) match->data;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	msi_data->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(msi_data->regs)) {
+		dev_err(&pdev->dev, "failed to initialize 'regs'\n");
+		return PTR_ERR(msi_data->regs);
+	}
+	msi_data->msiir_addr = res->start;
+
+	msi_data->pdev = pdev;
+	spin_lock_init(&msi_data->lock);
+
+	msi_data->irqs_num = MSI_IRQS_PER_MSIR *
+			     (1 << msi_data->cfg->ibs_shift);
+	msi_data->used = devm_bitmap_zalloc(&pdev->dev, msi_data->irqs_num, GFP_KERNEL);
+	if (!msi_data->used)
+		return -ENOMEM;
+	/*
+	 * Reserve all the hwirqs
+	 * The available hwirqs will be released in ls1_msi_setup_hwirq()
+	 */
+	bitmap_set(msi_data->used, 0, msi_data->irqs_num);
+
+	msi_data->msir_num = of_irq_count(pdev->dev.of_node);
+
+	if (msi_affinity_flag) {
+		u32 cpu_num;
+
+		cpu_num = num_possible_cpus();
+		if (msi_data->msir_num >= cpu_num)
+			msi_data->msir_num = cpu_num;
+		else
+			msi_affinity_flag = 0;
+	}
+
+	msi_data->msir = devm_kcalloc(&pdev->dev, msi_data->msir_num,
+				      sizeof(*msi_data->msir),
+				      GFP_KERNEL);
+	if (!msi_data->msir)
+		return -ENOMEM;
+
+	for (i = 0; i < msi_data->msir_num; i++)
+		ls_scfg_msi_setup_hwirq(msi_data, i);
+
+	ret = ls_scfg_msi_domains_init(msi_data);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, msi_data);
+
+	return 0;
+}
+
+static int ls_scfg_msi_remove(struct platform_device *pdev)
+{
+	struct ls_scfg_msi *msi_data = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < msi_data->msir_num; i++)
+		ls_scfg_msi_teardown_hwirq(&msi_data->msir[i]);
+
+	irq_domain_remove(msi_data->msi_domain);
+	irq_domain_remove(msi_data->parent);
+
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver ls_scfg_msi_driver = {
+	.driver = {
+		.name = "ls-scfg-msi",
+		.of_match_table = ls_scfg_msi_id,
+	},
+	.probe = ls_scfg_msi_probe,
+	.remove = ls_scfg_msi_remove,
+};
+
+module_platform_driver(ls_scfg_msi_driver);
+
+MODULE_AUTHOR("Minghuan Lian <Minghuan.Lian@nxp.com>");
+MODULE_DESCRIPTION("Freescale Layerscape SCFG MSI controller driver");
+MODULE_LICENSE("GPL v2");