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, 725 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
new file mode 100644
index 000000000..a7db7c310
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -0,0 +1,725 @@
+/*
+ * Copyright 2010 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#ifdef CONFIG_ACPI
+#include <linux/acpi.h>
+#endif
+#include <linux/power_supply.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+
+#include "nouveau_drv.h"
+#include "nouveau_hwmon.h"
+
+#include <nvkm/subdev/iccsense.h>
+#include <nvkm/subdev/volt.h>
+
+#if defined(CONFIG_HWMON) || (defined(MODULE) && defined(CONFIG_HWMON_MODULE))
+
+static ssize_t
+nouveau_hwmon_show_temp1_auto_point1_pwm(struct device *d,
+					 struct device_attribute *a, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", 100);
+}
+static SENSOR_DEVICE_ATTR(temp1_auto_point1_pwm, 0444,
+			  nouveau_hwmon_show_temp1_auto_point1_pwm, NULL, 0);
+
+static ssize_t
+nouveau_hwmon_temp1_auto_point1_temp(struct device *d,
+				     struct device_attribute *a, char *buf)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+	      therm->attr_get(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST) * 1000);
+}
+static ssize_t
+nouveau_hwmon_set_temp1_auto_point1_temp(struct device *d,
+					 struct device_attribute *a,
+					 const char *buf, size_t count)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	long value;
+
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
+
+	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST,
+			value / 1000);
+
+	return count;
+}
+static SENSOR_DEVICE_ATTR(temp1_auto_point1_temp, 0644,
+			  nouveau_hwmon_temp1_auto_point1_temp,
+			  nouveau_hwmon_set_temp1_auto_point1_temp, 0);
+
+static ssize_t
+nouveau_hwmon_temp1_auto_point1_temp_hyst(struct device *d,
+					  struct device_attribute *a, char *buf)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+	 therm->attr_get(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST_HYST) * 1000);
+}
+static ssize_t
+nouveau_hwmon_set_temp1_auto_point1_temp_hyst(struct device *d,
+					      struct device_attribute *a,
+					      const char *buf, size_t count)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	long value;
+
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
+
+	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST_HYST,
+			value / 1000);
+
+	return count;
+}
+static SENSOR_DEVICE_ATTR(temp1_auto_point1_temp_hyst, 0644,
+			  nouveau_hwmon_temp1_auto_point1_temp_hyst,
+			  nouveau_hwmon_set_temp1_auto_point1_temp_hyst, 0);
+
+static ssize_t
+nouveau_hwmon_get_pwm1_max(struct device *d,
+			   struct device_attribute *a, char *buf)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	int ret;
+
+	ret = therm->attr_get(therm, NVKM_THERM_ATTR_FAN_MAX_DUTY);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%i\n", ret);
+}
+
+static ssize_t
+nouveau_hwmon_get_pwm1_min(struct device *d,
+			   struct device_attribute *a, char *buf)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	int ret;
+
+	ret = therm->attr_get(therm, NVKM_THERM_ATTR_FAN_MIN_DUTY);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%i\n", ret);
+}
+
+static ssize_t
+nouveau_hwmon_set_pwm1_min(struct device *d, struct device_attribute *a,
+			   const char *buf, size_t count)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	long value;
+	int ret;
+
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
+
+	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MIN_DUTY, value);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+static SENSOR_DEVICE_ATTR(pwm1_min, 0644,
+			  nouveau_hwmon_get_pwm1_min,
+			  nouveau_hwmon_set_pwm1_min, 0);
+
+static ssize_t
+nouveau_hwmon_set_pwm1_max(struct device *d, struct device_attribute *a,
+			   const char *buf, size_t count)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	long value;
+	int ret;
+
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
+
+	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MAX_DUTY, value);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+static SENSOR_DEVICE_ATTR(pwm1_max, 0644,
+			  nouveau_hwmon_get_pwm1_max,
+			  nouveau_hwmon_set_pwm1_max, 0);
+
+static struct attribute *pwm_fan_sensor_attrs[] = {
+	&sensor_dev_attr_pwm1_min.dev_attr.attr,
+	&sensor_dev_attr_pwm1_max.dev_attr.attr,
+	NULL
+};
+static const struct attribute_group pwm_fan_sensor_group = {
+	.attrs = pwm_fan_sensor_attrs,
+};
+
+static struct attribute *temp1_auto_point_sensor_attrs[] = {
+	&sensor_dev_attr_temp1_auto_point1_pwm.dev_attr.attr,
+	&sensor_dev_attr_temp1_auto_point1_temp.dev_attr.attr,
+	&sensor_dev_attr_temp1_auto_point1_temp_hyst.dev_attr.attr,
+	NULL
+};
+static const struct attribute_group temp1_auto_point_sensor_group = {
+	.attrs = temp1_auto_point_sensor_attrs,
+};
+
+#define N_ATTR_GROUPS   3
+
+static const struct hwmon_channel_info *nouveau_info[] = {
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT |
+			   HWMON_T_MAX | HWMON_T_MAX_HYST |
+			   HWMON_T_CRIT | HWMON_T_CRIT_HYST |
+			   HWMON_T_EMERGENCY | HWMON_T_EMERGENCY_HYST),
+	HWMON_CHANNEL_INFO(fan,
+			   HWMON_F_INPUT),
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT |
+			   HWMON_I_MIN | HWMON_I_MAX |
+			   HWMON_I_LABEL),
+	HWMON_CHANNEL_INFO(pwm,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE),
+	HWMON_CHANNEL_INFO(power,
+			   HWMON_P_INPUT | HWMON_P_CAP_MAX | HWMON_P_CRIT),
+	NULL
+};
+
+static umode_t
+nouveau_chip_is_visible(const void *data, u32 attr, int channel)
+{
+	switch (attr) {
+	case hwmon_chip_update_interval:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static umode_t
+nouveau_power_is_visible(const void *data, u32 attr, int channel)
+{
+	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
+	struct nvkm_iccsense *iccsense = nvxx_iccsense(&drm->client.device);
+
+	if (!iccsense || !iccsense->data_valid || list_empty(&iccsense->rails))
+		return 0;
+
+	switch (attr) {
+	case hwmon_power_input:
+		return 0444;
+	case hwmon_power_max:
+		if (iccsense->power_w_max)
+			return 0444;
+		return 0;
+	case hwmon_power_crit:
+		if (iccsense->power_w_crit)
+			return 0444;
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static umode_t
+nouveau_temp_is_visible(const void *data, u32 attr, int channel)
+{
+	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm || !therm->attr_get || nvkm_therm_temp_get(therm) < 0)
+		return 0;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		return 0444;
+	case hwmon_temp_max:
+	case hwmon_temp_max_hyst:
+	case hwmon_temp_crit:
+	case hwmon_temp_crit_hyst:
+	case hwmon_temp_emergency:
+	case hwmon_temp_emergency_hyst:
+		return 0644;
+	default:
+		return 0;
+	}
+}
+
+static umode_t
+nouveau_pwm_is_visible(const void *data, u32 attr, int channel)
+{
+	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm || !therm->attr_get || !therm->fan_get ||
+	    therm->fan_get(therm) < 0)
+		return 0;
+
+	switch (attr) {
+	case hwmon_pwm_enable:
+	case hwmon_pwm_input:
+		return 0644;
+	default:
+		return 0;
+	}
+}
+
+static umode_t
+nouveau_input_is_visible(const void *data, u32 attr, int channel)
+{
+	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
+	struct nvkm_volt *volt = nvxx_volt(&drm->client.device);
+
+	if (!volt || nvkm_volt_get(volt) < 0)
+		return 0;
+
+	switch (attr) {
+	case hwmon_in_input:
+	case hwmon_in_label:
+	case hwmon_in_min:
+	case hwmon_in_max:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static umode_t
+nouveau_fan_is_visible(const void *data, u32 attr, int channel)
+{
+	struct nouveau_drm *drm = nouveau_drm((struct drm_device *)data);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm || !therm->attr_get || nvkm_therm_fan_sense(therm) < 0)
+		return 0;
+
+	switch (attr) {
+	case hwmon_fan_input:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static int
+nouveau_chip_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	switch (attr) {
+	case hwmon_chip_update_interval:
+		*val = 1000;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nouveau_temp_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	int ret;
+
+	if (!therm || !therm->attr_get)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		if (drm_dev->switch_power_state != DRM_SWITCH_POWER_ON)
+			return -EINVAL;
+		ret = nvkm_therm_temp_get(therm);
+		*val = ret < 0 ? ret : (ret * 1000);
+		break;
+	case hwmon_temp_max:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_THRS_DOWN_CLK)
+					* 1000;
+		break;
+	case hwmon_temp_max_hyst:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_THRS_DOWN_CLK_HYST)
+					* 1000;
+		break;
+	case hwmon_temp_crit:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_THRS_CRITICAL)
+					* 1000;
+		break;
+	case hwmon_temp_crit_hyst:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_THRS_CRITICAL_HYST)
+					* 1000;
+		break;
+	case hwmon_temp_emergency:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_THRS_SHUTDOWN)
+					* 1000;
+		break;
+	case hwmon_temp_emergency_hyst:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_THRS_SHUTDOWN_HYST)
+					* 1000;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nouveau_fan_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_fan_input:
+		if (drm_dev->switch_power_state != DRM_SWITCH_POWER_ON)
+			return -EINVAL;
+		*val = nvkm_therm_fan_sense(therm);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nouveau_in_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_volt *volt = nvxx_volt(&drm->client.device);
+	int ret;
+
+	if (!volt)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_in_input:
+		if (drm_dev->switch_power_state != DRM_SWITCH_POWER_ON)
+			return -EINVAL;
+		ret = nvkm_volt_get(volt);
+		*val = ret < 0 ? ret : (ret / 1000);
+		break;
+	case hwmon_in_min:
+		*val = volt->min_uv > 0 ? (volt->min_uv / 1000) : -ENODEV;
+		break;
+	case hwmon_in_max:
+		*val = volt->max_uv > 0 ? (volt->max_uv / 1000) : -ENODEV;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nouveau_pwm_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm || !therm->attr_get || !therm->fan_get)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_pwm_enable:
+		*val = therm->attr_get(therm, NVKM_THERM_ATTR_FAN_MODE);
+		break;
+	case hwmon_pwm_input:
+		if (drm_dev->switch_power_state != DRM_SWITCH_POWER_ON)
+			return -EINVAL;
+		*val = therm->fan_get(therm);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nouveau_power_read(struct device *dev, u32 attr, int channel, long *val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_iccsense *iccsense = nvxx_iccsense(&drm->client.device);
+
+	if (!iccsense)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_power_input:
+		if (drm_dev->switch_power_state != DRM_SWITCH_POWER_ON)
+			return -EINVAL;
+		*val = nvkm_iccsense_read_all(iccsense);
+		break;
+	case hwmon_power_max:
+		*val = iccsense->power_w_max;
+		break;
+	case hwmon_power_crit:
+		*val = iccsense->power_w_crit;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+nouveau_temp_write(struct device *dev, u32 attr, int channel, long val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm || !therm->attr_set)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_temp_max:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_THRS_DOWN_CLK,
+					val / 1000);
+	case hwmon_temp_max_hyst:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_THRS_DOWN_CLK_HYST,
+					val / 1000);
+	case hwmon_temp_crit:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_THRS_CRITICAL,
+					val / 1000);
+	case hwmon_temp_crit_hyst:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_THRS_CRITICAL_HYST,
+					val / 1000);
+	case hwmon_temp_emergency:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_THRS_SHUTDOWN,
+					val / 1000);
+	case hwmon_temp_emergency_hyst:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_THRS_SHUTDOWN_HYST,
+					val / 1000);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nouveau_pwm_write(struct device *dev, u32 attr, int channel, long val)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+
+	if (!therm || !therm->attr_set)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		return therm->fan_set(therm, val);
+	case hwmon_pwm_enable:
+		return therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MODE, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t
+nouveau_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+			int channel)
+{
+	switch (type) {
+	case hwmon_chip:
+		return nouveau_chip_is_visible(data, attr, channel);
+	case hwmon_temp:
+		return nouveau_temp_is_visible(data, attr, channel);
+	case hwmon_fan:
+		return nouveau_fan_is_visible(data, attr, channel);
+	case hwmon_in:
+		return nouveau_input_is_visible(data, attr, channel);
+	case hwmon_pwm:
+		return nouveau_pwm_is_visible(data, attr, channel);
+	case hwmon_power:
+		return nouveau_power_is_visible(data, attr, channel);
+	default:
+		return 0;
+	}
+}
+
+static const char input_label[] = "GPU core";
+
+static int
+nouveau_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		    int channel, const char **buf)
+{
+	if (type == hwmon_in && attr == hwmon_in_label) {
+		*buf = input_label;
+		return 0;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int
+nouveau_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+							int channel, long *val)
+{
+	switch (type) {
+	case hwmon_chip:
+		return nouveau_chip_read(dev, attr, channel, val);
+	case hwmon_temp:
+		return nouveau_temp_read(dev, attr, channel, val);
+	case hwmon_fan:
+		return nouveau_fan_read(dev, attr, channel, val);
+	case hwmon_in:
+		return nouveau_in_read(dev, attr, channel, val);
+	case hwmon_pwm:
+		return nouveau_pwm_read(dev, attr, channel, val);
+	case hwmon_power:
+		return nouveau_power_read(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nouveau_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+							int channel, long val)
+{
+	switch (type) {
+	case hwmon_temp:
+		return nouveau_temp_write(dev, attr, channel, val);
+	case hwmon_pwm:
+		return nouveau_pwm_write(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops nouveau_hwmon_ops = {
+	.is_visible = nouveau_is_visible,
+	.read = nouveau_read,
+	.read_string = nouveau_read_string,
+	.write = nouveau_write,
+};
+
+static const struct hwmon_chip_info nouveau_chip_info = {
+	.ops = &nouveau_hwmon_ops,
+	.info = nouveau_info,
+};
+#endif
+
+int
+nouveau_hwmon_init(struct drm_device *dev)
+{
+#if defined(CONFIG_HWMON) || (defined(MODULE) && defined(CONFIG_HWMON_MODULE))
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_iccsense *iccsense = nvxx_iccsense(&drm->client.device);
+	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
+	struct nvkm_volt *volt = nvxx_volt(&drm->client.device);
+	const struct attribute_group *special_groups[N_ATTR_GROUPS];
+	struct nouveau_hwmon *hwmon;
+	struct device *hwmon_dev;
+	int ret = 0;
+	int i = 0;
+
+	if (!iccsense && !therm && !volt) {
+		NV_DEBUG(drm, "Skipping hwmon registration\n");
+		return 0;
+	}
+
+	hwmon = drm->hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL);
+	if (!hwmon)
+		return -ENOMEM;
+	hwmon->dev = dev;
+
+	if (therm && therm->attr_get && therm->attr_set) {
+		if (nvkm_therm_temp_get(therm) >= 0)
+			special_groups[i++] = &temp1_auto_point_sensor_group;
+		if (therm->fan_get && therm->fan_get(therm) >= 0)
+			special_groups[i++] = &pwm_fan_sensor_group;
+	}
+
+	special_groups[i] = NULL;
+	hwmon_dev = hwmon_device_register_with_info(dev->dev, "nouveau", dev,
+							&nouveau_chip_info,
+							special_groups);
+	if (IS_ERR(hwmon_dev)) {
+		ret = PTR_ERR(hwmon_dev);
+		NV_ERROR(drm, "Unable to register hwmon device: %d\n", ret);
+		return ret;
+	}
+
+	hwmon->hwmon = hwmon_dev;
+	return 0;
+#else
+	return 0;
+#endif
+}
+
+void
+nouveau_hwmon_fini(struct drm_device *dev)
+{
+#if defined(CONFIG_HWMON) || (defined(MODULE) && defined(CONFIG_HWMON_MODULE))
+	struct nouveau_hwmon *hwmon = nouveau_hwmon(dev);
+
+	if (!hwmon)
+		return;
+
+	if (hwmon->hwmon)
+		hwmon_device_unregister(hwmon->hwmon);
+
+	nouveau_drm(dev)->hwmon = NULL;
+	kfree(hwmon);
+#endif
+}