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, 719 insertions, 0 deletions

diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c
new file mode 100644
index 000000000..8e3724728
--- /dev/null
+++ b/drivers/hwmon/ibmpowernv.c
@@ -0,0 +1,719 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * IBM PowerNV platform sensors for temperature/fan/voltage/power
+ * Copyright (C) 2014 IBM
+ */
+
+#define DRVNAME		"ibmpowernv"
+#define pr_fmt(fmt)	DRVNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include <linux/platform_device.h>
+#include <asm/opal.h>
+#include <linux/err.h>
+#include <asm/cputhreads.h>
+#include <asm/smp.h>
+
+#define MAX_ATTR_LEN	32
+#define MAX_LABEL_LEN	64
+
+/* Sensor suffix name from DT */
+#define DT_FAULT_ATTR_SUFFIX		"faulted"
+#define DT_DATA_ATTR_SUFFIX		"data"
+#define DT_THRESHOLD_ATTR_SUFFIX	"thrs"
+
+/*
+ * Enumerates all the types of sensors in the POWERNV platform and does index
+ * into 'struct sensor_group'
+ */
+enum sensors {
+	FAN,
+	TEMP,
+	POWER_SUPPLY,
+	POWER_INPUT,
+	CURRENT,
+	ENERGY,
+	MAX_SENSOR_TYPE,
+};
+
+#define INVALID_INDEX (-1U)
+
+/*
+ * 'compatible' string properties for sensor types as defined in old
+ * PowerNV firmware (skiboot). These are ordered as 'enum sensors'.
+ */
+static const char * const legacy_compatibles[] = {
+	"ibm,opal-sensor-cooling-fan",
+	"ibm,opal-sensor-amb-temp",
+	"ibm,opal-sensor-power-supply",
+	"ibm,opal-sensor-power"
+};
+
+static struct sensor_group {
+	const char *name; /* matches property 'sensor-type' */
+	struct attribute_group group;
+	u32 attr_count;
+	u32 hwmon_index;
+} sensor_groups[] = {
+	{ "fan"   },
+	{ "temp"  },
+	{ "in"    },
+	{ "power" },
+	{ "curr"  },
+	{ "energy" },
+};
+
+struct sensor_data {
+	u32 id; /* An opaque id of the firmware for each sensor */
+	u32 hwmon_index;
+	u32 opal_index;
+	enum sensors type;
+	char label[MAX_LABEL_LEN];
+	char name[MAX_ATTR_LEN];
+	struct device_attribute dev_attr;
+	struct sensor_group_data *sgrp_data;
+};
+
+struct sensor_group_data {
+	struct mutex mutex;
+	u32 gid;
+	bool enable;
+};
+
+struct platform_data {
+	const struct attribute_group *attr_groups[MAX_SENSOR_TYPE + 1];
+	struct sensor_group_data *sgrp_data;
+	u32 sensors_count; /* Total count of sensors from each group */
+	u32 nr_sensor_groups; /* Total number of sensor groups */
+};
+
+static ssize_t show_sensor(struct device *dev, struct device_attribute *devattr,
+			   char *buf)
+{
+	struct sensor_data *sdata = container_of(devattr, struct sensor_data,
+						 dev_attr);
+	ssize_t ret;
+	u64 x;
+
+	if (sdata->sgrp_data && !sdata->sgrp_data->enable)
+		return -ENODATA;
+
+	ret =  opal_get_sensor_data_u64(sdata->id, &x);
+
+	if (ret)
+		return ret;
+
+	/* Convert temperature to milli-degrees */
+	if (sdata->type == TEMP)
+		x *= 1000;
+	/* Convert power to micro-watts */
+	else if (sdata->type == POWER_INPUT)
+		x *= 1000000;
+
+	return sprintf(buf, "%llu\n", x);
+}
+
+static ssize_t show_enable(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
+{
+	struct sensor_data *sdata = container_of(devattr, struct sensor_data,
+						 dev_attr);
+
+	return sprintf(buf, "%u\n", sdata->sgrp_data->enable);
+}
+
+static ssize_t store_enable(struct device *dev,
+			    struct device_attribute *devattr,
+			    const char *buf, size_t count)
+{
+	struct sensor_data *sdata = container_of(devattr, struct sensor_data,
+						 dev_attr);
+	struct sensor_group_data *sgrp_data = sdata->sgrp_data;
+	int ret;
+	bool data;
+
+	ret = kstrtobool(buf, &data);
+	if (ret)
+		return ret;
+
+	ret = mutex_lock_interruptible(&sgrp_data->mutex);
+	if (ret)
+		return ret;
+
+	if (data != sgrp_data->enable) {
+		ret =  sensor_group_enable(sgrp_data->gid, data);
+		if (!ret)
+			sgrp_data->enable = data;
+	}
+
+	if (!ret)
+		ret = count;
+
+	mutex_unlock(&sgrp_data->mutex);
+	return ret;
+}
+
+static ssize_t show_label(struct device *dev, struct device_attribute *devattr,
+			  char *buf)
+{
+	struct sensor_data *sdata = container_of(devattr, struct sensor_data,
+						 dev_attr);
+
+	return sprintf(buf, "%s\n", sdata->label);
+}
+
+static int get_logical_cpu(int hwcpu)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		if (get_hard_smp_processor_id(cpu) == hwcpu)
+			return cpu;
+
+	return -ENOENT;
+}
+
+static void make_sensor_label(struct device_node *np,
+			      struct sensor_data *sdata, const char *label)
+{
+	u32 id;
+	size_t n;
+
+	n = scnprintf(sdata->label, sizeof(sdata->label), "%s", label);
+
+	/*
+	 * Core temp pretty print
+	 */
+	if (!of_property_read_u32(np, "ibm,pir", &id)) {
+		int cpuid = get_logical_cpu(id);
+
+		if (cpuid >= 0)
+			/*
+			 * The digital thermal sensors are associated
+			 * with a core.
+			 */
+			n += scnprintf(sdata->label + n,
+				      sizeof(sdata->label) - n, " %d",
+				      cpuid);
+		else
+			n += scnprintf(sdata->label + n,
+				      sizeof(sdata->label) - n, " phy%d", id);
+	}
+
+	/*
+	 * Membuffer pretty print
+	 */
+	if (!of_property_read_u32(np, "ibm,chip-id", &id))
+		n += scnprintf(sdata->label + n, sizeof(sdata->label) - n,
+			      " %d", id & 0xffff);
+}
+
+static int get_sensor_index_attr(const char *name, u32 *index, char *attr)
+{
+	char *hash_pos = strchr(name, '#');
+	char buf[8] = { 0 };
+	char *dash_pos;
+	u32 copy_len;
+	int err;
+
+	if (!hash_pos)
+		return -EINVAL;
+
+	dash_pos = strchr(hash_pos, '-');
+	if (!dash_pos)
+		return -EINVAL;
+
+	copy_len = dash_pos - hash_pos - 1;
+	if (copy_len >= sizeof(buf))
+		return -EINVAL;
+
+	strncpy(buf, hash_pos + 1, copy_len);
+
+	err = kstrtou32(buf, 10, index);
+	if (err)
+		return err;
+
+	strscpy(attr, dash_pos + 1, MAX_ATTR_LEN);
+
+	return 0;
+}
+
+static const char *convert_opal_attr_name(enum sensors type,
+					  const char *opal_attr)
+{
+	const char *attr_name = NULL;
+
+	if (!strcmp(opal_attr, DT_FAULT_ATTR_SUFFIX)) {
+		attr_name = "fault";
+	} else if (!strcmp(opal_attr, DT_DATA_ATTR_SUFFIX)) {
+		attr_name = "input";
+	} else if (!strcmp(opal_attr, DT_THRESHOLD_ATTR_SUFFIX)) {
+		if (type == TEMP)
+			attr_name = "max";
+		else if (type == FAN)
+			attr_name = "min";
+	}
+
+	return attr_name;
+}
+
+/*
+ * This function translates the DT node name into the 'hwmon' attribute name.
+ * IBMPOWERNV device node appear like cooling-fan#2-data, amb-temp#1-thrs etc.
+ * which need to be mapped as fan2_input, temp1_max respectively before
+ * populating them inside hwmon device class.
+ */
+static const char *parse_opal_node_name(const char *node_name,
+					enum sensors type, u32 *index)
+{
+	char attr_suffix[MAX_ATTR_LEN];
+	const char *attr_name;
+	int err;
+
+	err = get_sensor_index_attr(node_name, index, attr_suffix);
+	if (err)
+		return ERR_PTR(err);
+
+	attr_name = convert_opal_attr_name(type, attr_suffix);
+	if (!attr_name)
+		return ERR_PTR(-ENOENT);
+
+	return attr_name;
+}
+
+static int get_sensor_type(struct device_node *np)
+{
+	enum sensors type;
+	const char *str;
+
+	for (type = 0; type < ARRAY_SIZE(legacy_compatibles); type++) {
+		if (of_device_is_compatible(np, legacy_compatibles[type]))
+			return type;
+	}
+
+	/*
+	 * Let's check if we have a newer device tree
+	 */
+	if (!of_device_is_compatible(np, "ibm,opal-sensor"))
+		return MAX_SENSOR_TYPE;
+
+	if (of_property_read_string(np, "sensor-type", &str))
+		return MAX_SENSOR_TYPE;
+
+	for (type = 0; type < MAX_SENSOR_TYPE; type++)
+		if (!strcmp(str, sensor_groups[type].name))
+			return type;
+
+	return MAX_SENSOR_TYPE;
+}
+
+static u32 get_sensor_hwmon_index(struct sensor_data *sdata,
+				  struct sensor_data *sdata_table, int count)
+{
+	int i;
+
+	/*
+	 * We don't use the OPAL index on newer device trees
+	 */
+	if (sdata->opal_index != INVALID_INDEX) {
+		for (i = 0; i < count; i++)
+			if (sdata_table[i].opal_index == sdata->opal_index &&
+			    sdata_table[i].type == sdata->type)
+				return sdata_table[i].hwmon_index;
+	}
+	return ++sensor_groups[sdata->type].hwmon_index;
+}
+
+static int init_sensor_group_data(struct platform_device *pdev,
+				  struct platform_data *pdata)
+{
+	struct sensor_group_data *sgrp_data;
+	struct device_node *groups, *sgrp;
+	int count = 0, ret = 0;
+	enum sensors type;
+
+	groups = of_find_compatible_node(NULL, NULL, "ibm,opal-sensor-group");
+	if (!groups)
+		return ret;
+
+	for_each_child_of_node(groups, sgrp) {
+		type = get_sensor_type(sgrp);
+		if (type != MAX_SENSOR_TYPE)
+			pdata->nr_sensor_groups++;
+	}
+
+	if (!pdata->nr_sensor_groups)
+		goto out;
+
+	sgrp_data = devm_kcalloc(&pdev->dev, pdata->nr_sensor_groups,
+				 sizeof(*sgrp_data), GFP_KERNEL);
+	if (!sgrp_data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for_each_child_of_node(groups, sgrp) {
+		u32 gid;
+
+		type = get_sensor_type(sgrp);
+		if (type == MAX_SENSOR_TYPE)
+			continue;
+
+		if (of_property_read_u32(sgrp, "sensor-group-id", &gid))
+			continue;
+
+		if (of_count_phandle_with_args(sgrp, "sensors", NULL) <= 0)
+			continue;
+
+		sensor_groups[type].attr_count++;
+		sgrp_data[count].gid = gid;
+		mutex_init(&sgrp_data[count].mutex);
+		sgrp_data[count++].enable = false;
+	}
+
+	pdata->sgrp_data = sgrp_data;
+out:
+	of_node_put(groups);
+	return ret;
+}
+
+static struct sensor_group_data *get_sensor_group(struct platform_data *pdata,
+						  struct device_node *node,
+						  enum sensors gtype)
+{
+	struct sensor_group_data *sgrp_data = pdata->sgrp_data;
+	struct device_node *groups, *sgrp;
+
+	groups = of_find_compatible_node(NULL, NULL, "ibm,opal-sensor-group");
+	if (!groups)
+		return NULL;
+
+	for_each_child_of_node(groups, sgrp) {
+		struct of_phandle_iterator it;
+		u32 gid;
+		int rc, i;
+		enum sensors type;
+
+		type = get_sensor_type(sgrp);
+		if (type != gtype)
+			continue;
+
+		if (of_property_read_u32(sgrp, "sensor-group-id", &gid))
+			continue;
+
+		of_for_each_phandle(&it, rc, sgrp, "sensors", NULL, 0)
+			if (it.phandle == node->phandle) {
+				of_node_put(it.node);
+				break;
+			}
+
+		if (rc)
+			continue;
+
+		for (i = 0; i < pdata->nr_sensor_groups; i++)
+			if (gid == sgrp_data[i].gid) {
+				of_node_put(sgrp);
+				of_node_put(groups);
+				return &sgrp_data[i];
+			}
+	}
+
+	of_node_put(groups);
+	return NULL;
+}
+
+static int populate_attr_groups(struct platform_device *pdev)
+{
+	struct platform_data *pdata = platform_get_drvdata(pdev);
+	const struct attribute_group **pgroups = pdata->attr_groups;
+	struct device_node *opal, *np;
+	enum sensors type;
+	int ret;
+
+	ret = init_sensor_group_data(pdev, pdata);
+	if (ret)
+		return ret;
+
+	opal = of_find_node_by_path("/ibm,opal/sensors");
+	for_each_child_of_node(opal, np) {
+		const char *label;
+
+		type = get_sensor_type(np);
+		if (type == MAX_SENSOR_TYPE)
+			continue;
+
+		sensor_groups[type].attr_count++;
+
+		/*
+		 * add attributes for labels, min and max
+		 */
+		if (!of_property_read_string(np, "label", &label))
+			sensor_groups[type].attr_count++;
+		if (of_find_property(np, "sensor-data-min", NULL))
+			sensor_groups[type].attr_count++;
+		if (of_find_property(np, "sensor-data-max", NULL))
+			sensor_groups[type].attr_count++;
+	}
+
+	of_node_put(opal);
+
+	for (type = 0; type < MAX_SENSOR_TYPE; type++) {
+		sensor_groups[type].group.attrs = devm_kcalloc(&pdev->dev,
+					sensor_groups[type].attr_count + 1,
+					sizeof(struct attribute *),
+					GFP_KERNEL);
+		if (!sensor_groups[type].group.attrs)
+			return -ENOMEM;
+
+		pgroups[type] = &sensor_groups[type].group;
+		pdata->sensors_count += sensor_groups[type].attr_count;
+		sensor_groups[type].attr_count = 0;
+	}
+
+	return 0;
+}
+
+static void create_hwmon_attr(struct sensor_data *sdata, const char *attr_name,
+			      ssize_t (*show)(struct device *dev,
+					      struct device_attribute *attr,
+					      char *buf),
+			    ssize_t (*store)(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t count))
+{
+	snprintf(sdata->name, MAX_ATTR_LEN, "%s%d_%s",
+		 sensor_groups[sdata->type].name, sdata->hwmon_index,
+		 attr_name);
+
+	sysfs_attr_init(&sdata->dev_attr.attr);
+	sdata->dev_attr.attr.name = sdata->name;
+	sdata->dev_attr.show = show;
+	if (store) {
+		sdata->dev_attr.store = store;
+		sdata->dev_attr.attr.mode = 0664;
+	} else {
+		sdata->dev_attr.attr.mode = 0444;
+	}
+}
+
+static void populate_sensor(struct sensor_data *sdata, int od, int hd, int sid,
+			    const char *attr_name, enum sensors type,
+			    const struct attribute_group *pgroup,
+			    struct sensor_group_data *sgrp_data,
+			    ssize_t (*show)(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf),
+			    ssize_t (*store)(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t count))
+{
+	sdata->id = sid;
+	sdata->type = type;
+	sdata->opal_index = od;
+	sdata->hwmon_index = hd;
+	create_hwmon_attr(sdata, attr_name, show, store);
+	pgroup->attrs[sensor_groups[type].attr_count++] = &sdata->dev_attr.attr;
+	sdata->sgrp_data = sgrp_data;
+}
+
+static char *get_max_attr(enum sensors type)
+{
+	switch (type) {
+	case POWER_INPUT:
+		return "input_highest";
+	default:
+		return "highest";
+	}
+}
+
+static char *get_min_attr(enum sensors type)
+{
+	switch (type) {
+	case POWER_INPUT:
+		return "input_lowest";
+	default:
+		return "lowest";
+	}
+}
+
+/*
+ * Iterate through the device tree for each child of 'sensors' node, create
+ * a sysfs attribute file, the file is named by translating the DT node name
+ * to the name required by the higher 'hwmon' driver like fan1_input, temp1_max
+ * etc..
+ */
+static int create_device_attrs(struct platform_device *pdev)
+{
+	struct platform_data *pdata = platform_get_drvdata(pdev);
+	const struct attribute_group **pgroups = pdata->attr_groups;
+	struct device_node *opal, *np;
+	struct sensor_data *sdata;
+	u32 count = 0;
+	u32 group_attr_id[MAX_SENSOR_TYPE] = {0};
+
+	sdata = devm_kcalloc(&pdev->dev,
+			     pdata->sensors_count, sizeof(*sdata),
+			     GFP_KERNEL);
+	if (!sdata)
+		return -ENOMEM;
+
+	opal = of_find_node_by_path("/ibm,opal/sensors");
+	for_each_child_of_node(opal, np) {
+		struct sensor_group_data *sgrp_data;
+		const char *attr_name;
+		u32 opal_index, hw_id;
+		u32 sensor_id;
+		const char *label;
+		enum sensors type;
+
+		type = get_sensor_type(np);
+		if (type == MAX_SENSOR_TYPE)
+			continue;
+
+		/*
+		 * Newer device trees use a "sensor-data" property
+		 * name for input.
+		 */
+		if (of_property_read_u32(np, "sensor-id", &sensor_id) &&
+		    of_property_read_u32(np, "sensor-data", &sensor_id)) {
+			dev_info(&pdev->dev,
+				 "'sensor-id' missing in the node '%pOFn'\n",
+				 np);
+			continue;
+		}
+
+		sdata[count].id = sensor_id;
+		sdata[count].type = type;
+
+		/*
+		 * If we can not parse the node name, it means we are
+		 * running on a newer device tree. We can just forget
+		 * about the OPAL index and use a defaut value for the
+		 * hwmon attribute name
+		 */
+		attr_name = parse_opal_node_name(np->name, type, &opal_index);
+		if (IS_ERR(attr_name)) {
+			attr_name = "input";
+			opal_index = INVALID_INDEX;
+		}
+
+		hw_id = get_sensor_hwmon_index(&sdata[count], sdata, count);
+		sgrp_data = get_sensor_group(pdata, np, type);
+		populate_sensor(&sdata[count], opal_index, hw_id, sensor_id,
+				attr_name, type, pgroups[type], sgrp_data,
+				show_sensor, NULL);
+		count++;
+
+		if (!of_property_read_string(np, "label", &label)) {
+			/*
+			 * For the label attribute, we can reuse the
+			 * "properties" of the previous "input"
+			 * attribute. They are related to the same
+			 * sensor.
+			 */
+
+			make_sensor_label(np, &sdata[count], label);
+			populate_sensor(&sdata[count], opal_index, hw_id,
+					sensor_id, "label", type, pgroups[type],
+					NULL, show_label, NULL);
+			count++;
+		}
+
+		if (!of_property_read_u32(np, "sensor-data-max", &sensor_id)) {
+			attr_name = get_max_attr(type);
+			populate_sensor(&sdata[count], opal_index, hw_id,
+					sensor_id, attr_name, type,
+					pgroups[type], sgrp_data, show_sensor,
+					NULL);
+			count++;
+		}
+
+		if (!of_property_read_u32(np, "sensor-data-min", &sensor_id)) {
+			attr_name = get_min_attr(type);
+			populate_sensor(&sdata[count], opal_index, hw_id,
+					sensor_id, attr_name, type,
+					pgroups[type], sgrp_data, show_sensor,
+					NULL);
+			count++;
+		}
+
+		if (sgrp_data && !sgrp_data->enable) {
+			sgrp_data->enable = true;
+			hw_id = ++group_attr_id[type];
+			populate_sensor(&sdata[count], opal_index, hw_id,
+					sgrp_data->gid, "enable", type,
+					pgroups[type], sgrp_data, show_enable,
+					store_enable);
+			count++;
+		}
+	}
+
+	of_node_put(opal);
+	return 0;
+}
+
+static int ibmpowernv_probe(struct platform_device *pdev)
+{
+	struct platform_data *pdata;
+	struct device *hwmon_dev;
+	int err;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, pdata);
+	pdata->sensors_count = 0;
+	pdata->nr_sensor_groups = 0;
+	err = populate_attr_groups(pdev);
+	if (err)
+		return err;
+
+	/* Create sysfs attribute data for each sensor found in the DT */
+	err = create_device_attrs(pdev);
+	if (err)
+		return err;
+
+	/* Finally, register with hwmon */
+	hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev, DRVNAME,
+							   pdata,
+							   pdata->attr_groups);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct platform_device_id opal_sensor_driver_ids[] = {
+	{
+		.name = "opal-sensor",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, opal_sensor_driver_ids);
+
+static const struct of_device_id opal_sensor_match[] = {
+	{ .compatible	= "ibm,opal-sensor" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, opal_sensor_match);
+
+static struct platform_driver ibmpowernv_driver = {
+	.probe		= ibmpowernv_probe,
+	.id_table	= opal_sensor_driver_ids,
+	.driver		= {
+		.name	= DRVNAME,
+		.of_match_table	= opal_sensor_match,
+	},
+};
+
+module_platform_driver(ibmpowernv_driver);
+
+MODULE_AUTHOR("Neelesh Gupta <neelegup@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("IBM POWERNV platform sensors");
+MODULE_LICENSE("GPL");