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, 682 insertions, 0 deletions

diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
new file mode 100644
index 000000000..83a347ca3
--- /dev/null
+++ b/drivers/hwmon/pwm-fan.c
@@ -0,0 +1,682 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * pwm-fan.c - Hwmon driver for fans connected to PWM lines.
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ *
+ * Author: Kamil Debski <k.debski@samsung.com>
+ */
+
+#include <linux/hwmon.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pwm.h>
+#include <linux/regulator/consumer.h>
+#include <linux/sysfs.h>
+#include <linux/thermal.h>
+#include <linux/timer.h>
+
+#define MAX_PWM 255
+
+struct pwm_fan_tach {
+	int irq;
+	atomic_t pulses;
+	unsigned int rpm;
+	u8 pulses_per_revolution;
+};
+
+enum pwm_fan_enable_mode {
+	pwm_off_reg_off,
+	pwm_disable_reg_enable,
+	pwm_enable_reg_enable,
+	pwm_disable_reg_disable,
+};
+
+struct pwm_fan_ctx {
+	struct device *dev;
+
+	struct mutex lock;
+	struct pwm_device *pwm;
+	struct pwm_state pwm_state;
+	struct regulator *reg_en;
+	enum pwm_fan_enable_mode enable_mode;
+	bool regulator_enabled;
+	bool enabled;
+
+	int tach_count;
+	struct pwm_fan_tach *tachs;
+	ktime_t sample_start;
+	struct timer_list rpm_timer;
+
+	unsigned int pwm_value;
+	unsigned int pwm_fan_state;
+	unsigned int pwm_fan_max_state;
+	unsigned int *pwm_fan_cooling_levels;
+	struct thermal_cooling_device *cdev;
+
+	struct hwmon_chip_info info;
+	struct hwmon_channel_info fan_channel;
+};
+
+/* This handler assumes self resetting edge triggered interrupt. */
+static irqreturn_t pulse_handler(int irq, void *dev_id)
+{
+	struct pwm_fan_tach *tach = dev_id;
+
+	atomic_inc(&tach->pulses);
+
+	return IRQ_HANDLED;
+}
+
+static void sample_timer(struct timer_list *t)
+{
+	struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer);
+	unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start);
+	int i;
+
+	if (delta) {
+		for (i = 0; i < ctx->tach_count; i++) {
+			struct pwm_fan_tach *tach = &ctx->tachs[i];
+			int pulses;
+
+			pulses = atomic_read(&tach->pulses);
+			atomic_sub(pulses, &tach->pulses);
+			tach->rpm = (unsigned int)(pulses * 1000 * 60) /
+				(tach->pulses_per_revolution * delta);
+		}
+
+		ctx->sample_start = ktime_get();
+	}
+
+	mod_timer(&ctx->rpm_timer, jiffies + HZ);
+}
+
+static void pwm_fan_enable_mode_2_state(int enable_mode,
+					struct pwm_state *state,
+					bool *enable_regulator)
+{
+	switch (enable_mode) {
+	case pwm_disable_reg_enable:
+		/* disable pwm, keep regulator enabled */
+		state->enabled = false;
+		*enable_regulator = true;
+		break;
+	case pwm_enable_reg_enable:
+		/* keep pwm and regulator enabled */
+		state->enabled = true;
+		*enable_regulator = true;
+		break;
+	case pwm_off_reg_off:
+	case pwm_disable_reg_disable:
+		/* disable pwm and regulator */
+		state->enabled = false;
+		*enable_regulator = false;
+	}
+}
+
+static int pwm_fan_switch_power(struct pwm_fan_ctx *ctx, bool on)
+{
+	int ret = 0;
+
+	if (!ctx->reg_en)
+		return ret;
+
+	if (!ctx->regulator_enabled && on) {
+		ret = regulator_enable(ctx->reg_en);
+		if (ret == 0)
+			ctx->regulator_enabled = true;
+	} else if (ctx->regulator_enabled && !on) {
+		ret = regulator_disable(ctx->reg_en);
+		if (ret == 0)
+			ctx->regulator_enabled = false;
+	}
+	return ret;
+}
+
+static int pwm_fan_power_on(struct pwm_fan_ctx *ctx)
+{
+	struct pwm_state *state = &ctx->pwm_state;
+	int ret;
+
+	if (ctx->enabled)
+		return 0;
+
+	ret = pwm_fan_switch_power(ctx, true);
+	if (ret < 0) {
+		dev_err(ctx->dev, "failed to enable power supply\n");
+		return ret;
+	}
+
+	state->enabled = true;
+	ret = pwm_apply_state(ctx->pwm, state);
+	if (ret) {
+		dev_err(ctx->dev, "failed to enable PWM\n");
+		goto disable_regulator;
+	}
+
+	ctx->enabled = true;
+
+	return 0;
+
+disable_regulator:
+	pwm_fan_switch_power(ctx, false);
+	return ret;
+}
+
+static int pwm_fan_power_off(struct pwm_fan_ctx *ctx)
+{
+	struct pwm_state *state = &ctx->pwm_state;
+	bool enable_regulator = false;
+	int ret;
+
+	if (!ctx->enabled)
+		return 0;
+
+	pwm_fan_enable_mode_2_state(ctx->enable_mode,
+				    state,
+				    &enable_regulator);
+
+	state->enabled = false;
+	state->duty_cycle = 0;
+	ret = pwm_apply_state(ctx->pwm, state);
+	if (ret) {
+		dev_err(ctx->dev, "failed to disable PWM\n");
+		return ret;
+	}
+
+	pwm_fan_switch_power(ctx, enable_regulator);
+
+	ctx->enabled = false;
+
+	return 0;
+}
+
+static int  __set_pwm(struct pwm_fan_ctx *ctx, unsigned long pwm)
+{
+	struct pwm_state *state = &ctx->pwm_state;
+	unsigned long period;
+	int ret = 0;
+
+	if (pwm > 0) {
+		if (ctx->enable_mode == pwm_off_reg_off)
+			/* pwm-fan hard disabled */
+			return 0;
+
+		period = state->period;
+		state->duty_cycle = DIV_ROUND_UP(pwm * (period - 1), MAX_PWM);
+		ret = pwm_apply_state(ctx->pwm, state);
+		if (ret)
+			return ret;
+		ret = pwm_fan_power_on(ctx);
+	} else {
+		ret = pwm_fan_power_off(ctx);
+	}
+	if (!ret)
+		ctx->pwm_value = pwm;
+
+	return ret;
+}
+
+static int set_pwm(struct pwm_fan_ctx *ctx, unsigned long pwm)
+{
+	int ret;
+
+	mutex_lock(&ctx->lock);
+	ret = __set_pwm(ctx, pwm);
+	mutex_unlock(&ctx->lock);
+
+	return ret;
+}
+
+static void pwm_fan_update_state(struct pwm_fan_ctx *ctx, unsigned long pwm)
+{
+	int i;
+
+	for (i = 0; i < ctx->pwm_fan_max_state; ++i)
+		if (pwm < ctx->pwm_fan_cooling_levels[i + 1])
+			break;
+
+	ctx->pwm_fan_state = i;
+}
+
+static int pwm_fan_update_enable(struct pwm_fan_ctx *ctx, long val)
+{
+	int ret = 0;
+	int old_val;
+
+	mutex_lock(&ctx->lock);
+
+	if (ctx->enable_mode == val)
+		goto out;
+
+	old_val = ctx->enable_mode;
+	ctx->enable_mode = val;
+
+	if (val == 0) {
+		/* Disable pwm-fan unconditionally */
+		if (ctx->enabled)
+			ret = __set_pwm(ctx, 0);
+		else
+			ret = pwm_fan_switch_power(ctx, false);
+		if (ret)
+			ctx->enable_mode = old_val;
+		pwm_fan_update_state(ctx, 0);
+	} else {
+		/*
+		 * Change PWM and/or regulator state if currently disabled
+		 * Nothing to do if currently enabled
+		 */
+		if (!ctx->enabled) {
+			struct pwm_state *state = &ctx->pwm_state;
+			bool enable_regulator = false;
+
+			state->duty_cycle = 0;
+			pwm_fan_enable_mode_2_state(val,
+						    state,
+						    &enable_regulator);
+
+			pwm_apply_state(ctx->pwm, state);
+			pwm_fan_switch_power(ctx, enable_regulator);
+			pwm_fan_update_state(ctx, 0);
+		}
+	}
+out:
+	mutex_unlock(&ctx->lock);
+
+	return ret;
+}
+
+static int pwm_fan_write(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long val)
+{
+	struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+	int ret;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		if (val < 0 || val > MAX_PWM)
+			return -EINVAL;
+		ret = set_pwm(ctx, val);
+		if (ret)
+			return ret;
+		pwm_fan_update_state(ctx, val);
+		break;
+	case hwmon_pwm_enable:
+		if (val < 0 || val > 3)
+			ret = -EINVAL;
+		else
+			ret = pwm_fan_update_enable(ctx, val);
+
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int pwm_fan_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			*val = ctx->pwm_value;
+			return 0;
+		case hwmon_pwm_enable:
+			*val = ctx->enable_mode;
+			return 0;
+		}
+		return -EOPNOTSUPP;
+	case hwmon_fan:
+		*val = ctx->tachs[channel].rpm;
+		return 0;
+
+	default:
+		return -ENOTSUPP;
+	}
+}
+
+static umode_t pwm_fan_is_visible(const void *data,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return 0644;
+
+	case hwmon_fan:
+		return 0444;
+
+	default:
+		return 0;
+	}
+}
+
+static const struct hwmon_ops pwm_fan_hwmon_ops = {
+	.is_visible = pwm_fan_is_visible,
+	.read = pwm_fan_read,
+	.write = pwm_fan_write,
+};
+
+/* thermal cooling device callbacks */
+static int pwm_fan_get_max_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	struct pwm_fan_ctx *ctx = cdev->devdata;
+
+	if (!ctx)
+		return -EINVAL;
+
+	*state = ctx->pwm_fan_max_state;
+
+	return 0;
+}
+
+static int pwm_fan_get_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	struct pwm_fan_ctx *ctx = cdev->devdata;
+
+	if (!ctx)
+		return -EINVAL;
+
+	*state = ctx->pwm_fan_state;
+
+	return 0;
+}
+
+static int
+pwm_fan_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state)
+{
+	struct pwm_fan_ctx *ctx = cdev->devdata;
+	int ret;
+
+	if (!ctx || (state > ctx->pwm_fan_max_state))
+		return -EINVAL;
+
+	if (state == ctx->pwm_fan_state)
+		return 0;
+
+	ret = set_pwm(ctx, ctx->pwm_fan_cooling_levels[state]);
+	if (ret) {
+		dev_err(&cdev->device, "Cannot set pwm!\n");
+		return ret;
+	}
+
+	ctx->pwm_fan_state = state;
+
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops pwm_fan_cooling_ops = {
+	.get_max_state = pwm_fan_get_max_state,
+	.get_cur_state = pwm_fan_get_cur_state,
+	.set_cur_state = pwm_fan_set_cur_state,
+};
+
+static int pwm_fan_of_get_cooling_data(struct device *dev,
+				       struct pwm_fan_ctx *ctx)
+{
+	struct device_node *np = dev->of_node;
+	int num, i, ret;
+
+	if (!of_find_property(np, "cooling-levels", NULL))
+		return 0;
+
+	ret = of_property_count_u32_elems(np, "cooling-levels");
+	if (ret <= 0) {
+		dev_err(dev, "Wrong data!\n");
+		return ret ? : -EINVAL;
+	}
+
+	num = ret;
+	ctx->pwm_fan_cooling_levels = devm_kcalloc(dev, num, sizeof(u32),
+						   GFP_KERNEL);
+	if (!ctx->pwm_fan_cooling_levels)
+		return -ENOMEM;
+
+	ret = of_property_read_u32_array(np, "cooling-levels",
+					 ctx->pwm_fan_cooling_levels, num);
+	if (ret) {
+		dev_err(dev, "Property 'cooling-levels' cannot be read!\n");
+		return ret;
+	}
+
+	for (i = 0; i < num; i++) {
+		if (ctx->pwm_fan_cooling_levels[i] > MAX_PWM) {
+			dev_err(dev, "PWM fan state[%d]:%d > %d\n", i,
+				ctx->pwm_fan_cooling_levels[i], MAX_PWM);
+			return -EINVAL;
+		}
+	}
+
+	ctx->pwm_fan_max_state = num - 1;
+
+	return 0;
+}
+
+static void pwm_fan_cleanup(void *__ctx)
+{
+	struct pwm_fan_ctx *ctx = __ctx;
+
+	del_timer_sync(&ctx->rpm_timer);
+	/* Switch off everything */
+	ctx->enable_mode = pwm_disable_reg_disable;
+	pwm_fan_power_off(ctx);
+}
+
+static int pwm_fan_probe(struct platform_device *pdev)
+{
+	struct thermal_cooling_device *cdev;
+	struct device *dev = &pdev->dev;
+	struct pwm_fan_ctx *ctx;
+	struct device *hwmon;
+	int ret;
+	const struct hwmon_channel_info **channels;
+	u32 *fan_channel_config;
+	int channel_count = 1;	/* We always have a PWM channel. */
+	int i;
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	mutex_init(&ctx->lock);
+
+	ctx->dev = &pdev->dev;
+	ctx->pwm = devm_pwm_get(dev, NULL);
+	if (IS_ERR(ctx->pwm))
+		return dev_err_probe(dev, PTR_ERR(ctx->pwm), "Could not get PWM\n");
+
+	platform_set_drvdata(pdev, ctx);
+
+	ctx->reg_en = devm_regulator_get_optional(dev, "fan");
+	if (IS_ERR(ctx->reg_en)) {
+		if (PTR_ERR(ctx->reg_en) != -ENODEV)
+			return PTR_ERR(ctx->reg_en);
+
+		ctx->reg_en = NULL;
+	}
+
+	pwm_init_state(ctx->pwm, &ctx->pwm_state);
+
+	/*
+	 * set_pwm assumes that MAX_PWM * (period - 1) fits into an unsigned
+	 * long. Check this here to prevent the fan running at a too low
+	 * frequency.
+	 */
+	if (ctx->pwm_state.period > ULONG_MAX / MAX_PWM + 1) {
+		dev_err(dev, "Configured period too big\n");
+		return -EINVAL;
+	}
+
+	ctx->enable_mode = pwm_disable_reg_enable;
+
+	/*
+	 * Set duty cycle to maximum allowed and enable PWM output as well as
+	 * the regulator. In case of error nothing is changed
+	 */
+	ret = set_pwm(ctx, MAX_PWM);
+	if (ret) {
+		dev_err(dev, "Failed to configure PWM: %d\n", ret);
+		return ret;
+	}
+	timer_setup(&ctx->rpm_timer, sample_timer, 0);
+	ret = devm_add_action_or_reset(dev, pwm_fan_cleanup, ctx);
+	if (ret)
+		return ret;
+
+	ctx->tach_count = platform_irq_count(pdev);
+	if (ctx->tach_count < 0)
+		return dev_err_probe(dev, ctx->tach_count,
+				     "Could not get number of fan tachometer inputs\n");
+	dev_dbg(dev, "%d fan tachometer inputs\n", ctx->tach_count);
+
+	if (ctx->tach_count) {
+		channel_count++;	/* We also have a FAN channel. */
+
+		ctx->tachs = devm_kcalloc(dev, ctx->tach_count,
+					  sizeof(struct pwm_fan_tach),
+					  GFP_KERNEL);
+		if (!ctx->tachs)
+			return -ENOMEM;
+
+		ctx->fan_channel.type = hwmon_fan;
+		fan_channel_config = devm_kcalloc(dev, ctx->tach_count + 1,
+						  sizeof(u32), GFP_KERNEL);
+		if (!fan_channel_config)
+			return -ENOMEM;
+		ctx->fan_channel.config = fan_channel_config;
+	}
+
+	channels = devm_kcalloc(dev, channel_count + 1,
+				sizeof(struct hwmon_channel_info *), GFP_KERNEL);
+	if (!channels)
+		return -ENOMEM;
+
+	channels[0] = HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT | HWMON_PWM_ENABLE);
+
+	for (i = 0; i < ctx->tach_count; i++) {
+		struct pwm_fan_tach *tach = &ctx->tachs[i];
+		u32 ppr = 2;
+
+		tach->irq = platform_get_irq(pdev, i);
+		if (tach->irq == -EPROBE_DEFER)
+			return tach->irq;
+		if (tach->irq > 0) {
+			ret = devm_request_irq(dev, tach->irq, pulse_handler, 0,
+					       pdev->name, tach);
+			if (ret) {
+				dev_err(dev,
+					"Failed to request interrupt: %d\n",
+					ret);
+				return ret;
+			}
+		}
+
+		of_property_read_u32_index(dev->of_node,
+					   "pulses-per-revolution",
+					   i,
+					   &ppr);
+		tach->pulses_per_revolution = ppr;
+		if (!tach->pulses_per_revolution) {
+			dev_err(dev, "pulses-per-revolution can't be zero.\n");
+			return -EINVAL;
+		}
+
+		fan_channel_config[i] = HWMON_F_INPUT;
+
+		dev_dbg(dev, "tach%d: irq=%d, pulses_per_revolution=%d\n",
+			i, tach->irq, tach->pulses_per_revolution);
+	}
+
+	if (ctx->tach_count > 0) {
+		ctx->sample_start = ktime_get();
+		mod_timer(&ctx->rpm_timer, jiffies + HZ);
+
+		channels[1] = &ctx->fan_channel;
+	}
+
+	ctx->info.ops = &pwm_fan_hwmon_ops;
+	ctx->info.info = channels;
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "pwmfan",
+						     ctx, &ctx->info, NULL);
+	if (IS_ERR(hwmon)) {
+		dev_err(dev, "Failed to register hwmon device\n");
+		return PTR_ERR(hwmon);
+	}
+
+	ret = pwm_fan_of_get_cooling_data(dev, ctx);
+	if (ret)
+		return ret;
+
+	ctx->pwm_fan_state = ctx->pwm_fan_max_state;
+	if (IS_ENABLED(CONFIG_THERMAL)) {
+		cdev = devm_thermal_of_cooling_device_register(dev,
+			dev->of_node, "pwm-fan", ctx, &pwm_fan_cooling_ops);
+		if (IS_ERR(cdev)) {
+			ret = PTR_ERR(cdev);
+			dev_err(dev,
+				"Failed to register pwm-fan as cooling device: %d\n",
+				ret);
+			return ret;
+		}
+		ctx->cdev = cdev;
+	}
+
+	return 0;
+}
+
+static void pwm_fan_shutdown(struct platform_device *pdev)
+{
+	struct pwm_fan_ctx *ctx = platform_get_drvdata(pdev);
+
+	pwm_fan_cleanup(ctx);
+}
+
+static int pwm_fan_suspend(struct device *dev)
+{
+	struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+
+	return pwm_fan_power_off(ctx);
+}
+
+static int pwm_fan_resume(struct device *dev)
+{
+	struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+
+	return set_pwm(ctx, ctx->pwm_value);
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(pwm_fan_pm, pwm_fan_suspend, pwm_fan_resume);
+
+static const struct of_device_id of_pwm_fan_match[] = {
+	{ .compatible = "pwm-fan", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match);
+
+static struct platform_driver pwm_fan_driver = {
+	.probe		= pwm_fan_probe,
+	.shutdown	= pwm_fan_shutdown,
+	.driver	= {
+		.name		= "pwm-fan",
+		.pm		= pm_sleep_ptr(&pwm_fan_pm),
+		.of_match_table	= of_pwm_fan_match,
+	},
+};
+
+module_platform_driver(pwm_fan_driver);
+
+MODULE_AUTHOR("Kamil Debski <k.debski@samsung.com>");
+MODULE_ALIAS("platform:pwm-fan");
+MODULE_DESCRIPTION("PWM FAN driver");
+MODULE_LICENSE("GPL");