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, 673 insertions, 0 deletions

diff --git a/drivers/mfd/ioc3.c b/drivers/mfd/ioc3.c
new file mode 100644
index 000000000..58656837b
--- /dev/null
+++ b/drivers/mfd/ioc3.c
@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SGI IOC3 multifunction device driver
+ *
+ * Copyright (C) 2018, 2019 Thomas Bogendoerfer <tbogendoerfer@suse.de>
+ *
+ * Based on work by:
+ *   Stanislaw Skowronek <skylark@unaligned.org>
+ *   Joshua Kinard <kumba@gentoo.org>
+ *   Brent Casavant <bcasavan@sgi.com> - IOC4 master driver
+ *   Pat Gefre <pfg@sgi.com> - IOC3 serial port IRQ demuxer
+ */
+
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/sgi-w1.h>
+#include <linux/rtc/ds1685.h>
+
+#include <asm/pci/bridge.h>
+#include <asm/sn/ioc3.h>
+
+#define IOC3_IRQ_SERIAL_A	6
+#define IOC3_IRQ_SERIAL_B	15
+#define IOC3_IRQ_KBD		22
+
+/* Bitmask for selecting which IRQs are level triggered */
+#define IOC3_LVL_MASK	(BIT(IOC3_IRQ_SERIAL_A) | BIT(IOC3_IRQ_SERIAL_B))
+
+#define M48T35_REG_SIZE	32768	/* size of m48t35 registers */
+
+/* 1.2 us latency timer (40 cycles at 33 MHz) */
+#define IOC3_LATENCY	40
+
+struct ioc3_priv_data {
+	struct irq_domain *domain;
+	struct ioc3 __iomem *regs;
+	struct pci_dev *pdev;
+	int domain_irq;
+};
+
+static void ioc3_irq_ack(struct irq_data *d)
+{
+	struct ioc3_priv_data *ipd = irq_data_get_irq_chip_data(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+
+	writel(BIT(hwirq), &ipd->regs->sio_ir);
+}
+
+static void ioc3_irq_mask(struct irq_data *d)
+{
+	struct ioc3_priv_data *ipd = irq_data_get_irq_chip_data(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+
+	writel(BIT(hwirq), &ipd->regs->sio_iec);
+}
+
+static void ioc3_irq_unmask(struct irq_data *d)
+{
+	struct ioc3_priv_data *ipd = irq_data_get_irq_chip_data(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+
+	writel(BIT(hwirq), &ipd->regs->sio_ies);
+}
+
+static struct irq_chip ioc3_irq_chip = {
+	.name		= "IOC3",
+	.irq_ack	= ioc3_irq_ack,
+	.irq_mask	= ioc3_irq_mask,
+	.irq_unmask	= ioc3_irq_unmask,
+};
+
+static int ioc3_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hwirq)
+{
+	/* Set level IRQs for every interrupt contained in IOC3_LVL_MASK */
+	if (BIT(hwirq) & IOC3_LVL_MASK)
+		irq_set_chip_and_handler(irq, &ioc3_irq_chip, handle_level_irq);
+	else
+		irq_set_chip_and_handler(irq, &ioc3_irq_chip, handle_edge_irq);
+
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static void ioc3_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops ioc3_irq_domain_ops = {
+	.map = ioc3_irq_domain_map,
+	.unmap = ioc3_irq_domain_unmap,
+};
+
+static void ioc3_irq_handler(struct irq_desc *desc)
+{
+	struct irq_domain *domain = irq_desc_get_handler_data(desc);
+	struct ioc3_priv_data *ipd = domain->host_data;
+	struct ioc3 __iomem *regs = ipd->regs;
+	u32 pending, mask;
+
+	pending = readl(&regs->sio_ir);
+	mask = readl(&regs->sio_ies);
+	pending &= mask; /* Mask off not enabled interrupts */
+
+	if (pending)
+		generic_handle_domain_irq(domain, __ffs(pending));
+	else
+		spurious_interrupt();
+}
+
+/*
+ * System boards/BaseIOs use more interrupt pins of the bridge ASIC
+ * to which the IOC3 is connected. Since the IOC3 MFD driver
+ * knows wiring of these extra pins, we use the map_irq function
+ * to get interrupts activated
+ */
+static int ioc3_map_irq(struct pci_dev *pdev, int slot, int pin)
+{
+	struct pci_host_bridge *hbrg = pci_find_host_bridge(pdev->bus);
+
+	return hbrg->map_irq(pdev, slot, pin);
+}
+
+static int ioc3_irq_domain_setup(struct ioc3_priv_data *ipd, int irq)
+{
+	struct irq_domain *domain;
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_fwnode("IOC3");
+	if (!fn)
+		goto err;
+
+	domain = irq_domain_create_linear(fn, 24, &ioc3_irq_domain_ops, ipd);
+	if (!domain) {
+		irq_domain_free_fwnode(fn);
+		goto err;
+	}
+
+	ipd->domain = domain;
+
+	irq_set_chained_handler_and_data(irq, ioc3_irq_handler, domain);
+	ipd->domain_irq = irq;
+	return 0;
+
+err:
+	dev_err(&ipd->pdev->dev, "irq domain setup failed\n");
+	return -ENOMEM;
+}
+
+static const struct resource ioc3_uarta_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, sregs.uarta),
+		       sizeof_field(struct ioc3, sregs.uarta)),
+	DEFINE_RES_IRQ(IOC3_IRQ_SERIAL_A)
+};
+
+static const struct resource ioc3_uartb_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, sregs.uartb),
+		       sizeof_field(struct ioc3, sregs.uartb)),
+	DEFINE_RES_IRQ(IOC3_IRQ_SERIAL_B)
+};
+
+static struct mfd_cell ioc3_serial_cells[] = {
+	{
+		.name = "ioc3-serial8250",
+		.resources = ioc3_uarta_resources,
+		.num_resources = ARRAY_SIZE(ioc3_uarta_resources),
+	},
+	{
+		.name = "ioc3-serial8250",
+		.resources = ioc3_uartb_resources,
+		.num_resources = ARRAY_SIZE(ioc3_uartb_resources),
+	}
+};
+
+static int ioc3_serial_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	/* Set gpio pins for RS232/RS422 mode selection */
+	writel(GPCR_UARTA_MODESEL | GPCR_UARTB_MODESEL,
+		&ipd->regs->gpcr_s);
+	/* Select RS232 mode for uart a */
+	writel(0, &ipd->regs->gppr[6]);
+	/* Select RS232 mode for uart b */
+	writel(0, &ipd->regs->gppr[7]);
+
+	/* Switch both ports to 16650 mode */
+	writel(readl(&ipd->regs->port_a.sscr) & ~SSCR_DMA_EN,
+	       &ipd->regs->port_a.sscr);
+	writel(readl(&ipd->regs->port_b.sscr) & ~SSCR_DMA_EN,
+	       &ipd->regs->port_b.sscr);
+	udelay(1000); /* Wait until mode switch is done */
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_serial_cells, ARRAY_SIZE(ioc3_serial_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret) {
+		dev_err(&ipd->pdev->dev, "Failed to add 16550 subdevs\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct resource ioc3_kbd_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, serio),
+		       sizeof_field(struct ioc3, serio)),
+	DEFINE_RES_IRQ(IOC3_IRQ_KBD)
+};
+
+static struct mfd_cell ioc3_kbd_cells[] = {
+	{
+		.name = "ioc3-kbd",
+		.resources = ioc3_kbd_resources,
+		.num_resources = ARRAY_SIZE(ioc3_kbd_resources),
+	}
+};
+
+static int ioc3_kbd_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_kbd_cells, ARRAY_SIZE(ioc3_kbd_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret) {
+		dev_err(&ipd->pdev->dev, "Failed to add 16550 subdevs\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct resource ioc3_eth_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, eth),
+		       sizeof_field(struct ioc3, eth)),
+	DEFINE_RES_MEM(offsetof(struct ioc3, ssram),
+		       sizeof_field(struct ioc3, ssram)),
+	DEFINE_RES_IRQ(0)
+};
+
+static const struct resource ioc3_w1_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, mcr),
+		       sizeof_field(struct ioc3, mcr)),
+};
+static struct sgi_w1_platform_data ioc3_w1_platform_data;
+
+static struct mfd_cell ioc3_eth_cells[] = {
+	{
+		.name = "ioc3-eth",
+		.resources = ioc3_eth_resources,
+		.num_resources = ARRAY_SIZE(ioc3_eth_resources),
+	},
+	{
+		.name = "sgi_w1",
+		.resources = ioc3_w1_resources,
+		.num_resources = ARRAY_SIZE(ioc3_w1_resources),
+		.platform_data = &ioc3_w1_platform_data,
+		.pdata_size = sizeof(ioc3_w1_platform_data),
+	}
+};
+
+static int ioc3_eth_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	/* Enable One-Wire bus */
+	writel(GPCR_MLAN_EN, &ipd->regs->gpcr_s);
+
+	/* Generate unique identifier */
+	snprintf(ioc3_w1_platform_data.dev_id,
+		 sizeof(ioc3_w1_platform_data.dev_id), "ioc3-%012llx",
+		 ipd->pdev->resource->start);
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_eth_cells, ARRAY_SIZE(ioc3_eth_cells),
+			      &ipd->pdev->resource[0], ipd->pdev->irq, NULL);
+	if (ret) {
+		dev_err(&ipd->pdev->dev, "Failed to add ETH/W1 subdev\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct resource ioc3_m48t35_resources[] = {
+	DEFINE_RES_MEM(IOC3_BYTEBUS_DEV0, M48T35_REG_SIZE)
+};
+
+static struct mfd_cell ioc3_m48t35_cells[] = {
+	{
+		.name = "rtc-m48t35",
+		.resources = ioc3_m48t35_resources,
+		.num_resources = ARRAY_SIZE(ioc3_m48t35_resources),
+	}
+};
+
+static int ioc3_m48t35_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_m48t35_cells, ARRAY_SIZE(ioc3_m48t35_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret)
+		dev_err(&ipd->pdev->dev, "Failed to add M48T35 subdev\n");
+
+	return ret;
+}
+
+static struct ds1685_rtc_platform_data ip30_rtc_platform_data = {
+	.bcd_mode = false,
+	.no_irq = false,
+	.uie_unsupported = true,
+	.access_type = ds1685_reg_indirect,
+};
+
+static const struct resource ioc3_rtc_ds1685_resources[] = {
+	DEFINE_RES_MEM(IOC3_BYTEBUS_DEV1, 1),
+	DEFINE_RES_MEM(IOC3_BYTEBUS_DEV2, 1),
+	DEFINE_RES_IRQ(0)
+};
+
+static struct mfd_cell ioc3_ds1685_cells[] = {
+	{
+		.name = "rtc-ds1685",
+		.resources = ioc3_rtc_ds1685_resources,
+		.num_resources = ARRAY_SIZE(ioc3_rtc_ds1685_resources),
+		.platform_data = &ip30_rtc_platform_data,
+		.pdata_size = sizeof(ip30_rtc_platform_data),
+		.id = PLATFORM_DEVID_NONE,
+	}
+};
+
+static int ioc3_ds1685_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, irq;
+
+	irq = ioc3_map_irq(ipd->pdev, 6, 0);
+
+	ret = mfd_add_devices(&ipd->pdev->dev, 0, ioc3_ds1685_cells,
+			      ARRAY_SIZE(ioc3_ds1685_cells),
+			      &ipd->pdev->resource[0], irq, NULL);
+	if (ret)
+		dev_err(&ipd->pdev->dev, "Failed to add DS1685 subdev\n");
+
+	return ret;
+};
+
+
+static const struct resource ioc3_leds_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, gppr[0]),
+		       sizeof_field(struct ioc3, gppr[0])),
+	DEFINE_RES_MEM(offsetof(struct ioc3, gppr[1]),
+		       sizeof_field(struct ioc3, gppr[1])),
+};
+
+static struct mfd_cell ioc3_led_cells[] = {
+	{
+		.name = "ip30-leds",
+		.resources = ioc3_leds_resources,
+		.num_resources = ARRAY_SIZE(ioc3_leds_resources),
+		.id = PLATFORM_DEVID_NONE,
+	}
+};
+
+static int ioc3_led_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = mfd_add_devices(&ipd->pdev->dev, 0, ioc3_led_cells,
+			      ARRAY_SIZE(ioc3_led_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret)
+		dev_err(&ipd->pdev->dev, "Failed to add LED subdev\n");
+
+	return ret;
+}
+
+static int ip27_baseio_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_m48t35_setup(ipd);
+}
+
+static int ip27_baseio6g_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_m48t35_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_kbd_setup(ipd);
+}
+
+static int ip27_mio_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = ioc3_irq_domain_setup(ipd, ipd->pdev->irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_kbd_setup(ipd);
+}
+
+static int ip30_sysboard_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_kbd_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_ds1685_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_led_setup(ipd);
+}
+
+static int ioc3_menet_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_serial_setup(ipd);
+}
+
+static int ioc3_menet4_setup(struct ioc3_priv_data *ipd)
+{
+	return ioc3_eth_setup(ipd);
+}
+
+static int ioc3_cad_duo_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_kbd_setup(ipd);
+}
+
+/* Helper macro for filling ioc3_info array */
+#define IOC3_SID(_name, _sid, _setup) \
+	{								   \
+		.name = _name,						   \
+		.sid = PCI_VENDOR_ID_SGI | (IOC3_SUBSYS_ ## _sid << 16),   \
+		.setup = _setup,					   \
+	}
+
+static struct {
+	const char *name;
+	u32 sid;
+	int (*setup)(struct ioc3_priv_data *ipd);
+} ioc3_infos[] = {
+	IOC3_SID("IP27 BaseIO6G", IP27_BASEIO6G, &ip27_baseio6g_setup),
+	IOC3_SID("IP27 MIO", IP27_MIO, &ip27_mio_setup),
+	IOC3_SID("IP27 BaseIO", IP27_BASEIO, &ip27_baseio_setup),
+	IOC3_SID("IP29 System Board", IP29_SYSBOARD, &ip27_baseio6g_setup),
+	IOC3_SID("IP30 System Board", IP30_SYSBOARD, &ip30_sysboard_setup),
+	IOC3_SID("MENET", MENET, &ioc3_menet_setup),
+	IOC3_SID("MENET4", MENET4, &ioc3_menet4_setup)
+};
+#undef IOC3_SID
+
+static int ioc3_setup(struct ioc3_priv_data *ipd)
+{
+	u32 sid;
+	int i;
+
+	/* Clear IRQs */
+	writel(~0, &ipd->regs->sio_iec);
+	writel(~0, &ipd->regs->sio_ir);
+	writel(0, &ipd->regs->eth.eier);
+	writel(~0, &ipd->regs->eth.eisr);
+
+	/* Read subsystem vendor id and subsystem id */
+	pci_read_config_dword(ipd->pdev, PCI_SUBSYSTEM_VENDOR_ID, &sid);
+
+	for (i = 0; i < ARRAY_SIZE(ioc3_infos); i++)
+		if (sid == ioc3_infos[i].sid) {
+			pr_info("ioc3: %s\n", ioc3_infos[i].name);
+			return ioc3_infos[i].setup(ipd);
+		}
+
+	/* Treat everything not identified by PCI subid as CAD DUO */
+	pr_info("ioc3: CAD DUO\n");
+	return ioc3_cad_duo_setup(ipd);
+}
+
+static int ioc3_mfd_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *pci_id)
+{
+	struct ioc3_priv_data *ipd;
+	struct ioc3 __iomem *regs;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	pci_write_config_byte(pdev, PCI_LATENCY_TIMER, IOC3_LATENCY);
+	pci_set_master(pdev);
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		pr_err("%s: No usable DMA configuration, aborting.\n",
+		       pci_name(pdev));
+		goto out_disable_device;
+	}
+
+	/* Set up per-IOC3 data */
+	ipd = devm_kzalloc(&pdev->dev, sizeof(struct ioc3_priv_data),
+			   GFP_KERNEL);
+	if (!ipd) {
+		ret = -ENOMEM;
+		goto out_disable_device;
+	}
+	ipd->pdev = pdev;
+
+	/*
+	 * Map all IOC3 registers.  These are shared between subdevices
+	 * so the main IOC3 module manages them.
+	 */
+	regs = pci_ioremap_bar(pdev, 0);
+	if (!regs) {
+		dev_warn(&pdev->dev, "ioc3: Unable to remap PCI BAR for %s.\n",
+			 pci_name(pdev));
+		ret = -ENOMEM;
+		goto out_disable_device;
+	}
+	ipd->regs = regs;
+
+	/* Track PCI-device specific data */
+	pci_set_drvdata(pdev, ipd);
+
+	ret = ioc3_setup(ipd);
+	if (ret) {
+		/* Remove all already added MFD devices */
+		mfd_remove_devices(&ipd->pdev->dev);
+		if (ipd->domain) {
+			struct fwnode_handle *fn = ipd->domain->fwnode;
+
+			irq_domain_remove(ipd->domain);
+			irq_domain_free_fwnode(fn);
+			free_irq(ipd->domain_irq, (void *)ipd);
+		}
+		pci_iounmap(pdev, regs);
+		goto out_disable_device;
+	}
+
+	return 0;
+
+out_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+}
+
+static void ioc3_mfd_remove(struct pci_dev *pdev)
+{
+	struct ioc3_priv_data *ipd;
+
+	ipd = pci_get_drvdata(pdev);
+
+	/* Clear and disable all IRQs */
+	writel(~0, &ipd->regs->sio_iec);
+	writel(~0, &ipd->regs->sio_ir);
+
+	/* Release resources */
+	mfd_remove_devices(&ipd->pdev->dev);
+	if (ipd->domain) {
+		struct fwnode_handle *fn = ipd->domain->fwnode;
+
+		irq_domain_remove(ipd->domain);
+		irq_domain_free_fwnode(fn);
+		free_irq(ipd->domain_irq, (void *)ipd);
+	}
+	pci_iounmap(pdev, ipd->regs);
+	pci_disable_device(pdev);
+}
+
+static struct pci_device_id ioc3_mfd_id_table[] = {
+	{ PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3, PCI_ANY_ID, PCI_ANY_ID },
+	{ 0, },
+};
+MODULE_DEVICE_TABLE(pci, ioc3_mfd_id_table);
+
+static struct pci_driver ioc3_mfd_driver = {
+	.name = "IOC3",
+	.id_table = ioc3_mfd_id_table,
+	.probe = ioc3_mfd_probe,
+	.remove = ioc3_mfd_remove,
+};
+
+module_pci_driver(ioc3_mfd_driver);
+
+MODULE_AUTHOR("Thomas Bogendoerfer <tbogendoerfer@suse.de>");
+MODULE_DESCRIPTION("SGI IOC3 MFD driver");
+MODULE_LICENSE("GPL v2");