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, 728 insertions, 0 deletions

diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c
new file mode 100644
index 000000000..5a9f86b1d
--- /dev/null
+++ b/arch/sparc/kernel/of_device_64.c
@@ -0,0 +1,728 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/irq.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <asm/spitfire.h>
+
+#include "of_device_common.h"
+
+void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name)
+{
+	unsigned long ret = res->start + offset;
+	struct resource *r;
+
+	if (res->flags & IORESOURCE_MEM)
+		r = request_mem_region(ret, size, name);
+	else
+		r = request_region(ret, size, name);
+	if (!r)
+		ret = 0;
+
+	return (void __iomem *) ret;
+}
+EXPORT_SYMBOL(of_ioremap);
+
+void of_iounmap(struct resource *res, void __iomem *base, unsigned long size)
+{
+	if (res->flags & IORESOURCE_MEM)
+		release_mem_region((unsigned long) base, size);
+	else
+		release_region((unsigned long) base, size);
+}
+EXPORT_SYMBOL(of_iounmap);
+
+/*
+ * PCI bus specific translator
+ */
+
+static int of_bus_pci_match(struct device_node *np)
+{
+	if (of_node_name_eq(np, "pci")) {
+		const char *model = of_get_property(np, "model", NULL);
+
+		if (model && !strcmp(model, "SUNW,simba"))
+			return 0;
+
+		/* Do not do PCI specific frobbing if the
+		 * PCI bridge lacks a ranges property.  We
+		 * want to pass it through up to the next
+		 * parent as-is, not with the PCI translate
+		 * method which chops off the top address cell.
+		 */
+		if (!of_find_property(np, "ranges", NULL))
+			return 0;
+
+		return 1;
+	}
+
+	return 0;
+}
+
+static int of_bus_simba_match(struct device_node *np)
+{
+	const char *model = of_get_property(np, "model", NULL);
+
+	if (model && !strcmp(model, "SUNW,simba"))
+		return 1;
+
+	/* Treat PCI busses lacking ranges property just like
+	 * simba.
+	 */
+	if (of_node_name_eq(np, "pci")) {
+		if (!of_find_property(np, "ranges", NULL))
+			return 1;
+	}
+
+	return 0;
+}
+
+static int of_bus_simba_map(u32 *addr, const u32 *range,
+			    int na, int ns, int pna)
+{
+	return 0;
+}
+
+static void of_bus_pci_count_cells(struct device_node *np,
+				   int *addrc, int *sizec)
+{
+	if (addrc)
+		*addrc = 3;
+	if (sizec)
+		*sizec = 2;
+}
+
+static int of_bus_pci_map(u32 *addr, const u32 *range,
+			  int na, int ns, int pna)
+{
+	u32 result[OF_MAX_ADDR_CELLS];
+	int i;
+
+	/* Check address type match */
+	if (!((addr[0] ^ range[0]) & 0x03000000))
+		goto type_match;
+
+	/* Special exception, we can map a 64-bit address into
+	 * a 32-bit range.
+	 */
+	if ((addr[0] & 0x03000000) == 0x03000000 &&
+	    (range[0] & 0x03000000) == 0x02000000)
+		goto type_match;
+
+	return -EINVAL;
+
+type_match:
+	if (of_out_of_range(addr + 1, range + 1, range + na + pna,
+			    na - 1, ns))
+		return -EINVAL;
+
+	/* Start with the parent range base.  */
+	memcpy(result, range + na, pna * 4);
+
+	/* Add in the child address offset, skipping high cell.  */
+	for (i = 0; i < na - 1; i++)
+		result[pna - 1 - i] +=
+			(addr[na - 1 - i] -
+			 range[na - 1 - i]);
+
+	memcpy(addr, result, pna * 4);
+
+	return 0;
+}
+
+static unsigned long of_bus_pci_get_flags(const u32 *addr, unsigned long flags)
+{
+	u32 w = addr[0];
+
+	/* For PCI, we override whatever child busses may have used.  */
+	flags = 0;
+	switch((w >> 24) & 0x03) {
+	case 0x01:
+		flags |= IORESOURCE_IO;
+		break;
+
+	case 0x02: /* 32 bits */
+	case 0x03: /* 64 bits */
+		flags |= IORESOURCE_MEM;
+		break;
+	}
+	if (w & 0x40000000)
+		flags |= IORESOURCE_PREFETCH;
+	return flags;
+}
+
+/*
+ * FHC/Central bus specific translator.
+ *
+ * This is just needed to hard-code the address and size cell
+ * counts.  'fhc' and 'central' nodes lack the #address-cells and
+ * #size-cells properties, and if you walk to the root on such
+ * Enterprise boxes all you'll get is a #size-cells of 2 which is
+ * not what we want to use.
+ */
+static int of_bus_fhc_match(struct device_node *np)
+{
+	return of_node_name_eq(np, "fhc") ||
+		of_node_name_eq(np, "central");
+}
+
+#define of_bus_fhc_count_cells of_bus_sbus_count_cells
+
+/*
+ * Array of bus specific translators
+ */
+
+static struct of_bus of_busses[] = {
+	/* PCI */
+	{
+		.name = "pci",
+		.addr_prop_name = "assigned-addresses",
+		.match = of_bus_pci_match,
+		.count_cells = of_bus_pci_count_cells,
+		.map = of_bus_pci_map,
+		.get_flags = of_bus_pci_get_flags,
+	},
+	/* SIMBA */
+	{
+		.name = "simba",
+		.addr_prop_name = "assigned-addresses",
+		.match = of_bus_simba_match,
+		.count_cells = of_bus_pci_count_cells,
+		.map = of_bus_simba_map,
+		.get_flags = of_bus_pci_get_flags,
+	},
+	/* SBUS */
+	{
+		.name = "sbus",
+		.addr_prop_name = "reg",
+		.match = of_bus_sbus_match,
+		.count_cells = of_bus_sbus_count_cells,
+		.map = of_bus_default_map,
+		.get_flags = of_bus_default_get_flags,
+	},
+	/* FHC */
+	{
+		.name = "fhc",
+		.addr_prop_name = "reg",
+		.match = of_bus_fhc_match,
+		.count_cells = of_bus_fhc_count_cells,
+		.map = of_bus_default_map,
+		.get_flags = of_bus_default_get_flags,
+	},
+	/* Default */
+	{
+		.name = "default",
+		.addr_prop_name = "reg",
+		.match = NULL,
+		.count_cells = of_bus_default_count_cells,
+		.map = of_bus_default_map,
+		.get_flags = of_bus_default_get_flags,
+	},
+};
+
+static struct of_bus *of_match_bus(struct device_node *np)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(of_busses); i ++)
+		if (!of_busses[i].match || of_busses[i].match(np))
+			return &of_busses[i];
+	BUG();
+	return NULL;
+}
+
+static int __init build_one_resource(struct device_node *parent,
+				     struct of_bus *bus,
+				     struct of_bus *pbus,
+				     u32 *addr,
+				     int na, int ns, int pna)
+{
+	const u32 *ranges;
+	int rone, rlen;
+
+	ranges = of_get_property(parent, "ranges", &rlen);
+	if (ranges == NULL || rlen == 0) {
+		u32 result[OF_MAX_ADDR_CELLS];
+		int i;
+
+		memset(result, 0, pna * 4);
+		for (i = 0; i < na; i++)
+			result[pna - 1 - i] =
+				addr[na - 1 - i];
+
+		memcpy(addr, result, pna * 4);
+		return 0;
+	}
+
+	/* Now walk through the ranges */
+	rlen /= 4;
+	rone = na + pna + ns;
+	for (; rlen >= rone; rlen -= rone, ranges += rone) {
+		if (!bus->map(addr, ranges, na, ns, pna))
+			return 0;
+	}
+
+	/* When we miss an I/O space match on PCI, just pass it up
+	 * to the next PCI bridge and/or controller.
+	 */
+	if (!strcmp(bus->name, "pci") &&
+	    (addr[0] & 0x03000000) == 0x01000000)
+		return 0;
+
+	return 1;
+}
+
+static int __init use_1to1_mapping(struct device_node *pp)
+{
+	/* If we have a ranges property in the parent, use it.  */
+	if (of_find_property(pp, "ranges", NULL) != NULL)
+		return 0;
+
+	/* If the parent is the dma node of an ISA bus, pass
+	 * the translation up to the root.
+	 *
+	 * Some SBUS devices use intermediate nodes to express
+	 * hierarchy within the device itself.  These aren't
+	 * real bus nodes, and don't have a 'ranges' property.
+	 * But, we should still pass the translation work up
+	 * to the SBUS itself.
+	 */
+	if (of_node_name_eq(pp, "dma") ||
+	    of_node_name_eq(pp, "espdma") ||
+	    of_node_name_eq(pp, "ledma") ||
+	    of_node_name_eq(pp, "lebuffer"))
+		return 0;
+
+	/* Similarly for all PCI bridges, if we get this far
+	 * it lacks a ranges property, and this will include
+	 * cases like Simba.
+	 */
+	if (of_node_name_eq(pp, "pci"))
+		return 0;
+
+	return 1;
+}
+
+static int of_resource_verbose;
+
+static void __init build_device_resources(struct platform_device *op,
+					  struct device *parent)
+{
+	struct platform_device *p_op;
+	struct of_bus *bus;
+	int na, ns;
+	int index, num_reg;
+	const void *preg;
+
+	if (!parent)
+		return;
+
+	p_op = to_platform_device(parent);
+	bus = of_match_bus(p_op->dev.of_node);
+	bus->count_cells(op->dev.of_node, &na, &ns);
+
+	preg = of_get_property(op->dev.of_node, bus->addr_prop_name, &num_reg);
+	if (!preg || num_reg == 0)
+		return;
+
+	/* Convert to num-cells.  */
+	num_reg /= 4;
+
+	/* Convert to num-entries.  */
+	num_reg /= na + ns;
+
+	/* Prevent overrunning the op->resources[] array.  */
+	if (num_reg > PROMREG_MAX) {
+		printk(KERN_WARNING "%pOF: Too many regs (%d), "
+		       "limiting to %d.\n",
+		       op->dev.of_node, num_reg, PROMREG_MAX);
+		num_reg = PROMREG_MAX;
+	}
+
+	op->resource = op->archdata.resource;
+	op->num_resources = num_reg;
+	for (index = 0; index < num_reg; index++) {
+		struct resource *r = &op->resource[index];
+		u32 addr[OF_MAX_ADDR_CELLS];
+		const u32 *reg = (preg + (index * ((na + ns) * 4)));
+		struct device_node *dp = op->dev.of_node;
+		struct device_node *pp = p_op->dev.of_node;
+		struct of_bus *pbus, *dbus;
+		u64 size, result = OF_BAD_ADDR;
+		unsigned long flags;
+		int dna, dns;
+		int pna, pns;
+
+		size = of_read_addr(reg + na, ns);
+		memcpy(addr, reg, na * 4);
+
+		flags = bus->get_flags(addr, 0);
+
+		if (use_1to1_mapping(pp)) {
+			result = of_read_addr(addr, na);
+			goto build_res;
+		}
+
+		dna = na;
+		dns = ns;
+		dbus = bus;
+
+		while (1) {
+			dp = pp;
+			pp = dp->parent;
+			if (!pp) {
+				result = of_read_addr(addr, dna);
+				break;
+			}
+
+			pbus = of_match_bus(pp);
+			pbus->count_cells(dp, &pna, &pns);
+
+			if (build_one_resource(dp, dbus, pbus, addr,
+					       dna, dns, pna))
+				break;
+
+			flags = pbus->get_flags(addr, flags);
+
+			dna = pna;
+			dns = pns;
+			dbus = pbus;
+		}
+
+	build_res:
+		memset(r, 0, sizeof(*r));
+
+		if (of_resource_verbose)
+			printk("%pOF reg[%d] -> %llx\n",
+			       op->dev.of_node, index,
+			       result);
+
+		if (result != OF_BAD_ADDR) {
+			if (tlb_type == hypervisor)
+				result &= 0x0fffffffffffffffUL;
+
+			r->start = result;
+			r->end = result + size - 1;
+			r->flags = flags;
+		}
+		r->name = op->dev.of_node->full_name;
+	}
+}
+
+static struct device_node * __init
+apply_interrupt_map(struct device_node *dp, struct device_node *pp,
+		    const u32 *imap, int imlen, const u32 *imask,
+		    unsigned int *irq_p)
+{
+	struct device_node *cp;
+	unsigned int irq = *irq_p;
+	struct of_bus *bus;
+	phandle handle;
+	const u32 *reg;
+	int na, num_reg, i;
+
+	bus = of_match_bus(pp);
+	bus->count_cells(dp, &na, NULL);
+
+	reg = of_get_property(dp, "reg", &num_reg);
+	if (!reg || !num_reg)
+		return NULL;
+
+	imlen /= ((na + 3) * 4);
+	handle = 0;
+	for (i = 0; i < imlen; i++) {
+		int j;
+
+		for (j = 0; j < na; j++) {
+			if ((reg[j] & imask[j]) != imap[j])
+				goto next;
+		}
+		if (imap[na] == irq) {
+			handle = imap[na + 1];
+			irq = imap[na + 2];
+			break;
+		}
+
+	next:
+		imap += (na + 3);
+	}
+	if (i == imlen) {
+		/* Psycho and Sabre PCI controllers can have 'interrupt-map'
+		 * properties that do not include the on-board device
+		 * interrupts.  Instead, the device's 'interrupts' property
+		 * is already a fully specified INO value.
+		 *
+		 * Handle this by deciding that, if we didn't get a
+		 * match in the parent's 'interrupt-map', and the
+		 * parent is an IRQ translator, then use the parent as
+		 * our IRQ controller.
+		 */
+		if (pp->irq_trans)
+			return pp;
+
+		return NULL;
+	}
+
+	*irq_p = irq;
+	cp = of_find_node_by_phandle(handle);
+
+	return cp;
+}
+
+static unsigned int __init pci_irq_swizzle(struct device_node *dp,
+					   struct device_node *pp,
+					   unsigned int irq)
+{
+	const struct linux_prom_pci_registers *regs;
+	unsigned int bus, devfn, slot, ret;
+
+	if (irq < 1 || irq > 4)
+		return irq;
+
+	regs = of_get_property(dp, "reg", NULL);
+	if (!regs)
+		return irq;
+
+	bus = (regs->phys_hi >> 16) & 0xff;
+	devfn = (regs->phys_hi >> 8) & 0xff;
+	slot = (devfn >> 3) & 0x1f;
+
+	if (pp->irq_trans) {
+		/* Derived from Table 8-3, U2P User's Manual.  This branch
+		 * is handling a PCI controller that lacks a proper set of
+		 * interrupt-map and interrupt-map-mask properties.  The
+		 * Ultra-E450 is one example.
+		 *
+		 * The bit layout is BSSLL, where:
+		 * B: 0 on bus A, 1 on bus B
+		 * D: 2-bit slot number, derived from PCI device number as
+		 *    (dev - 1) for bus A, or (dev - 2) for bus B
+		 * L: 2-bit line number
+		 */
+		if (bus & 0x80) {
+			/* PBM-A */
+			bus  = 0x00;
+			slot = (slot - 1) << 2;
+		} else {
+			/* PBM-B */
+			bus  = 0x10;
+			slot = (slot - 2) << 2;
+		}
+		irq -= 1;
+
+		ret = (bus | slot | irq);
+	} else {
+		/* Going through a PCI-PCI bridge that lacks a set of
+		 * interrupt-map and interrupt-map-mask properties.
+		 */
+		ret = ((irq - 1 + (slot & 3)) & 3) + 1;
+	}
+
+	return ret;
+}
+
+static int of_irq_verbose;
+
+static unsigned int __init build_one_device_irq(struct platform_device *op,
+						struct device *parent,
+						unsigned int irq)
+{
+	struct device_node *dp = op->dev.of_node;
+	struct device_node *pp, *ip;
+	unsigned int orig_irq = irq;
+	int nid;
+
+	if (irq == 0xffffffff)
+		return irq;
+
+	if (dp->irq_trans) {
+		irq = dp->irq_trans->irq_build(dp, irq,
+					       dp->irq_trans->data);
+
+		if (of_irq_verbose)
+			printk("%pOF: direct translate %x --> %x\n",
+			       dp, orig_irq, irq);
+
+		goto out;
+	}
+
+	/* Something more complicated.  Walk up to the root, applying
+	 * interrupt-map or bus specific translations, until we hit
+	 * an IRQ translator.
+	 *
+	 * If we hit a bus type or situation we cannot handle, we
+	 * stop and assume that the original IRQ number was in a
+	 * format which has special meaning to it's immediate parent.
+	 */
+	pp = dp->parent;
+	ip = NULL;
+	while (pp) {
+		const void *imap, *imsk;
+		int imlen;
+
+		imap = of_get_property(pp, "interrupt-map", &imlen);
+		imsk = of_get_property(pp, "interrupt-map-mask", NULL);
+		if (imap && imsk) {
+			struct device_node *iret;
+			int this_orig_irq = irq;
+
+			iret = apply_interrupt_map(dp, pp,
+						   imap, imlen, imsk,
+						   &irq);
+
+			if (of_irq_verbose)
+				printk("%pOF: Apply [%pOF:%x] imap --> [%pOF:%x]\n",
+				       op->dev.of_node,
+				       pp, this_orig_irq, iret, irq);
+
+			if (!iret)
+				break;
+
+			if (iret->irq_trans) {
+				ip = iret;
+				break;
+			}
+		} else {
+			if (of_node_name_eq(pp, "pci")) {
+				unsigned int this_orig_irq = irq;
+
+				irq = pci_irq_swizzle(dp, pp, irq);
+				if (of_irq_verbose)
+					printk("%pOF: PCI swizzle [%pOF] "
+					       "%x --> %x\n",
+					       op->dev.of_node,
+					       pp, this_orig_irq,
+					       irq);
+
+			}
+
+			if (pp->irq_trans) {
+				ip = pp;
+				break;
+			}
+		}
+		dp = pp;
+		pp = pp->parent;
+	}
+	if (!ip)
+		return orig_irq;
+
+	irq = ip->irq_trans->irq_build(op->dev.of_node, irq,
+				       ip->irq_trans->data);
+	if (of_irq_verbose)
+		printk("%pOF: Apply IRQ trans [%pOF] %x --> %x\n",
+		      op->dev.of_node, ip, orig_irq, irq);
+
+out:
+	nid = of_node_to_nid(dp);
+	if (nid != -1) {
+		cpumask_t numa_mask;
+
+		cpumask_copy(&numa_mask, cpumask_of_node(nid));
+		irq_set_affinity(irq, &numa_mask);
+	}
+
+	return irq;
+}
+
+static struct platform_device * __init scan_one_device(struct device_node *dp,
+						 struct device *parent)
+{
+	struct platform_device *op = kzalloc(sizeof(*op), GFP_KERNEL);
+	const unsigned int *irq;
+	struct dev_archdata *sd;
+	int len, i;
+
+	if (!op)
+		return NULL;
+
+	sd = &op->dev.archdata;
+	sd->op = op;
+
+	op->dev.of_node = dp;
+
+	irq = of_get_property(dp, "interrupts", &len);
+	if (irq) {
+		op->archdata.num_irqs = len / 4;
+
+		/* Prevent overrunning the op->irqs[] array.  */
+		if (op->archdata.num_irqs > PROMINTR_MAX) {
+			printk(KERN_WARNING "%pOF: Too many irqs (%d), "
+			       "limiting to %d.\n",
+			       dp, op->archdata.num_irqs, PROMINTR_MAX);
+			op->archdata.num_irqs = PROMINTR_MAX;
+		}
+		memcpy(op->archdata.irqs, irq, op->archdata.num_irqs * 4);
+	} else {
+		op->archdata.num_irqs = 0;
+	}
+
+	build_device_resources(op, parent);
+	for (i = 0; i < op->archdata.num_irqs; i++)
+		op->archdata.irqs[i] = build_one_device_irq(op, parent, op->archdata.irqs[i]);
+
+	op->dev.parent = parent;
+	op->dev.bus = &platform_bus_type;
+	if (!parent)
+		dev_set_name(&op->dev, "root");
+	else
+		dev_set_name(&op->dev, "%08x", dp->phandle);
+	op->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	op->dev.dma_mask = &op->dev.coherent_dma_mask;
+
+	if (of_device_register(op)) {
+		printk("%pOF: Could not register of device.\n", dp);
+		kfree(op);
+		op = NULL;
+	}
+
+	return op;
+}
+
+static void __init scan_tree(struct device_node *dp, struct device *parent)
+{
+	while (dp) {
+		struct platform_device *op = scan_one_device(dp, parent);
+
+		if (op)
+			scan_tree(dp->child, &op->dev);
+
+		dp = dp->sibling;
+	}
+}
+
+static int __init scan_of_devices(void)
+{
+	struct device_node *root = of_find_node_by_path("/");
+	struct platform_device *parent;
+
+	parent = scan_one_device(root, NULL);
+	if (!parent)
+		return 0;
+
+	scan_tree(root->child, &parent->dev);
+	return 0;
+}
+postcore_initcall(scan_of_devices);
+
+static int __init of_debug(char *str)
+{
+	int val = 0;
+
+	get_option(&str, &val);
+	if (val & 1)
+		of_resource_verbose = 1;
+	if (val & 2)
+		of_irq_verbose = 1;
+	return 1;
+}
+
+__setup("of_debug=", of_debug);