Adding upstream version 6.1.76.upstream/6.1.76upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 1303 insertions, 0 deletions

diff --git a/drivers/hwmon/peci/Kconfig b/drivers/hwmon/peci/Kconfig
new file mode 100644
index 000000000..9d32a57ba
--- /dev/null
+++ b/drivers/hwmon/peci/Kconfig
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config SENSORS_PECI_CPUTEMP
+	tristate "PECI CPU temperature monitoring client"
+	depends on PECI
+	select SENSORS_PECI
+	select PECI_CPU
+	help
+	  If you say yes here you get support for the generic Intel PECI
+	  cputemp driver which provides Digital Thermal Sensor (DTS) thermal
+	  readings of the CPU package and CPU cores that are accessible via
+	  the processor PECI interface.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called peci-cputemp.
+
+config SENSORS_PECI_DIMMTEMP
+	tristate "PECI DIMM temperature monitoring client"
+	depends on PECI
+	select SENSORS_PECI
+	select PECI_CPU
+	help
+	  If you say yes here you get support for the generic Intel PECI hwmon
+	  driver which provides Temperature Sensor on DIMM readings that are
+	  accessible via the processor PECI interface.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called peci-dimmtemp.
+
+config SENSORS_PECI
+	tristate
diff --git a/drivers/hwmon/peci/Makefile b/drivers/hwmon/peci/Makefile
new file mode 100644
index 000000000..191cfa022
--- /dev/null
+++ b/drivers/hwmon/peci/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+peci-cputemp-y := cputemp.o
+peci-dimmtemp-y := dimmtemp.o
+
+obj-$(CONFIG_SENSORS_PECI_CPUTEMP)	+= peci-cputemp.o
+obj-$(CONFIG_SENSORS_PECI_DIMMTEMP)	+= peci-dimmtemp.o
diff --git a/drivers/hwmon/peci/common.h b/drivers/hwmon/peci/common.h
new file mode 100644
index 000000000..734506b0e
--- /dev/null
+++ b/drivers/hwmon/peci/common.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2021 Intel Corporation */
+
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+#ifndef __PECI_HWMON_COMMON_H
+#define __PECI_HWMON_COMMON_H
+
+#define PECI_HWMON_UPDATE_INTERVAL	HZ
+
+/**
+ * struct peci_sensor_state - PECI state information
+ * @valid: flag to indicate the sensor value is valid
+ * @last_updated: time of the last update in jiffies
+ * @lock: mutex to protect sensor access
+ */
+struct peci_sensor_state {
+	bool valid;
+	unsigned long last_updated;
+	struct mutex lock; /* protect sensor access */
+};
+
+/**
+ * struct peci_sensor_data - PECI sensor information
+ * @value: sensor value in milli units
+ * @state: sensor update state
+ */
+
+struct peci_sensor_data {
+	s32 value;
+	struct peci_sensor_state state;
+};
+
+/**
+ * peci_sensor_need_update() - check whether sensor update is needed or not
+ * @sensor: pointer to sensor data struct
+ *
+ * Return: true if update is needed, false if not.
+ */
+
+static inline bool peci_sensor_need_update(struct peci_sensor_state *state)
+{
+	return !state->valid ||
+	       time_after(jiffies, state->last_updated + PECI_HWMON_UPDATE_INTERVAL);
+}
+
+/**
+ * peci_sensor_mark_updated() - mark the sensor is updated
+ * @sensor: pointer to sensor data struct
+ */
+static inline void peci_sensor_mark_updated(struct peci_sensor_state *state)
+{
+	state->valid = true;
+	state->last_updated = jiffies;
+}
+
+#endif /* __PECI_HWMON_COMMON_H */
diff --git a/drivers/hwmon/peci/cputemp.c b/drivers/hwmon/peci/cputemp.c
new file mode 100644
index 000000000..87d56f0fc
--- /dev/null
+++ b/drivers/hwmon/peci/cputemp.c
@@ -0,0 +1,592 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2018-2021 Intel Corporation
+
+#include <linux/auxiliary_bus.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/hwmon.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/peci.h>
+#include <linux/peci-cpu.h>
+#include <linux/units.h>
+
+#include "common.h"
+
+#define CORE_NUMS_MAX		64
+
+#define BASE_CHANNEL_NUMS	5
+#define CPUTEMP_CHANNEL_NUMS	(BASE_CHANNEL_NUMS + CORE_NUMS_MAX)
+
+#define TEMP_TARGET_FAN_TEMP_MASK	GENMASK(15, 8)
+#define TEMP_TARGET_REF_TEMP_MASK	GENMASK(23, 16)
+#define TEMP_TARGET_TJ_OFFSET_MASK	GENMASK(29, 24)
+
+#define DTS_MARGIN_MASK		GENMASK(15, 0)
+#define PCS_MODULE_TEMP_MASK	GENMASK(15, 0)
+
+struct resolved_cores_reg {
+	u8 bus;
+	u8 dev;
+	u8 func;
+	u8 offset;
+};
+
+struct cpu_info {
+	struct resolved_cores_reg *reg;
+	u8 min_peci_revision;
+	s32 (*thermal_margin_to_millidegree)(u16 val);
+};
+
+struct peci_temp_target {
+	s32 tcontrol;
+	s32 tthrottle;
+	s32 tjmax;
+	struct peci_sensor_state state;
+};
+
+enum peci_temp_target_type {
+	tcontrol_type,
+	tthrottle_type,
+	tjmax_type,
+	crit_hyst_type,
+};
+
+struct peci_cputemp {
+	struct peci_device *peci_dev;
+	struct device *dev;
+	const char *name;
+	const struct cpu_info *gen_info;
+	struct {
+		struct peci_temp_target target;
+		struct peci_sensor_data die;
+		struct peci_sensor_data dts;
+		struct peci_sensor_data core[CORE_NUMS_MAX];
+	} temp;
+	const char **coretemp_label;
+	DECLARE_BITMAP(core_mask, CORE_NUMS_MAX);
+};
+
+enum cputemp_channels {
+	channel_die,
+	channel_dts,
+	channel_tcontrol,
+	channel_tthrottle,
+	channel_tjmax,
+	channel_core,
+};
+
+static const char * const cputemp_label[BASE_CHANNEL_NUMS] = {
+	"Die",
+	"DTS",
+	"Tcontrol",
+	"Tthrottle",
+	"Tjmax",
+};
+
+static int update_temp_target(struct peci_cputemp *priv)
+{
+	s32 tthrottle_offset, tcontrol_margin;
+	u32 pcs;
+	int ret;
+
+	if (!peci_sensor_need_update(&priv->temp.target.state))
+		return 0;
+
+	ret = peci_pcs_read(priv->peci_dev, PECI_PCS_TEMP_TARGET, 0, &pcs);
+	if (ret)
+		return ret;
+
+	priv->temp.target.tjmax =
+		FIELD_GET(TEMP_TARGET_REF_TEMP_MASK, pcs) * MILLIDEGREE_PER_DEGREE;
+
+	tcontrol_margin = FIELD_GET(TEMP_TARGET_FAN_TEMP_MASK, pcs);
+	tcontrol_margin = sign_extend32(tcontrol_margin, 7) * MILLIDEGREE_PER_DEGREE;
+	priv->temp.target.tcontrol = priv->temp.target.tjmax - tcontrol_margin;
+
+	tthrottle_offset = FIELD_GET(TEMP_TARGET_TJ_OFFSET_MASK, pcs) * MILLIDEGREE_PER_DEGREE;
+	priv->temp.target.tthrottle = priv->temp.target.tjmax - tthrottle_offset;
+
+	peci_sensor_mark_updated(&priv->temp.target.state);
+
+	return 0;
+}
+
+static int get_temp_target(struct peci_cputemp *priv, enum peci_temp_target_type type, long *val)
+{
+	int ret;
+
+	mutex_lock(&priv->temp.target.state.lock);
+
+	ret = update_temp_target(priv);
+	if (ret)
+		goto unlock;
+
+	switch (type) {
+	case tcontrol_type:
+		*val = priv->temp.target.tcontrol;
+		break;
+	case tthrottle_type:
+		*val = priv->temp.target.tthrottle;
+		break;
+	case tjmax_type:
+		*val = priv->temp.target.tjmax;
+		break;
+	case crit_hyst_type:
+		*val = priv->temp.target.tjmax - priv->temp.target.tcontrol;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+unlock:
+	mutex_unlock(&priv->temp.target.state.lock);
+
+	return ret;
+}
+
+/*
+ * Error codes:
+ *   0x8000: General sensor error
+ *   0x8001: Reserved
+ *   0x8002: Underflow on reading value
+ *   0x8003-0x81ff: Reserved
+ */
+static bool dts_valid(u16 val)
+{
+	return val < 0x8000 || val > 0x81ff;
+}
+
+/*
+ * Processors return a value of DTS reading in S10.6 fixed point format
+ * (16 bits: 10-bit signed magnitude, 6-bit fraction).
+ */
+static s32 dts_ten_dot_six_to_millidegree(u16 val)
+{
+	return sign_extend32(val, 15) * MILLIDEGREE_PER_DEGREE / 64;
+}
+
+/*
+ * For older processors, thermal margin reading is returned in S8.8 fixed
+ * point format (16 bits: 8-bit signed magnitude, 8-bit fraction).
+ */
+static s32 dts_eight_dot_eight_to_millidegree(u16 val)
+{
+	return sign_extend32(val, 15) * MILLIDEGREE_PER_DEGREE / 256;
+}
+
+static int get_die_temp(struct peci_cputemp *priv, long *val)
+{
+	int ret = 0;
+	long tjmax;
+	u16 temp;
+
+	mutex_lock(&priv->temp.die.state.lock);
+	if (!peci_sensor_need_update(&priv->temp.die.state))
+		goto skip_update;
+
+	ret = peci_temp_read(priv->peci_dev, &temp);
+	if (ret)
+		goto err_unlock;
+
+	if (!dts_valid(temp)) {
+		ret = -EIO;
+		goto err_unlock;
+	}
+
+	ret = get_temp_target(priv, tjmax_type, &tjmax);
+	if (ret)
+		goto err_unlock;
+
+	priv->temp.die.value = (s32)tjmax + dts_ten_dot_six_to_millidegree(temp);
+
+	peci_sensor_mark_updated(&priv->temp.die.state);
+
+skip_update:
+	*val = priv->temp.die.value;
+err_unlock:
+	mutex_unlock(&priv->temp.die.state.lock);
+	return ret;
+}
+
+static int get_dts(struct peci_cputemp *priv, long *val)
+{
+	int ret = 0;
+	u16 thermal_margin;
+	long tcontrol;
+	u32 pcs;
+
+	mutex_lock(&priv->temp.dts.state.lock);
+	if (!peci_sensor_need_update(&priv->temp.dts.state))
+		goto skip_update;
+
+	ret = peci_pcs_read(priv->peci_dev, PECI_PCS_THERMAL_MARGIN, 0, &pcs);
+	if (ret)
+		goto err_unlock;
+
+	thermal_margin = FIELD_GET(DTS_MARGIN_MASK, pcs);
+	if (!dts_valid(thermal_margin)) {
+		ret = -EIO;
+		goto err_unlock;
+	}
+
+	ret = get_temp_target(priv, tcontrol_type, &tcontrol);
+	if (ret)
+		goto err_unlock;
+
+	/* Note that the tcontrol should be available before calling it */
+	priv->temp.dts.value =
+		(s32)tcontrol - priv->gen_info->thermal_margin_to_millidegree(thermal_margin);
+
+	peci_sensor_mark_updated(&priv->temp.dts.state);
+
+skip_update:
+	*val = priv->temp.dts.value;
+err_unlock:
+	mutex_unlock(&priv->temp.dts.state.lock);
+	return ret;
+}
+
+static int get_core_temp(struct peci_cputemp *priv, int core_index, long *val)
+{
+	int ret = 0;
+	u16 core_dts_margin;
+	long tjmax;
+	u32 pcs;
+
+	mutex_lock(&priv->temp.core[core_index].state.lock);
+	if (!peci_sensor_need_update(&priv->temp.core[core_index].state))
+		goto skip_update;
+
+	ret = peci_pcs_read(priv->peci_dev, PECI_PCS_MODULE_TEMP, core_index, &pcs);
+	if (ret)
+		goto err_unlock;
+
+	core_dts_margin = FIELD_GET(PCS_MODULE_TEMP_MASK, pcs);
+	if (!dts_valid(core_dts_margin)) {
+		ret = -EIO;
+		goto err_unlock;
+	}
+
+	ret = get_temp_target(priv, tjmax_type, &tjmax);
+	if (ret)
+		goto err_unlock;
+
+	/* Note that the tjmax should be available before calling it */
+	priv->temp.core[core_index].value =
+		(s32)tjmax + dts_ten_dot_six_to_millidegree(core_dts_margin);
+
+	peci_sensor_mark_updated(&priv->temp.core[core_index].state);
+
+skip_update:
+	*val = priv->temp.core[core_index].value;
+err_unlock:
+	mutex_unlock(&priv->temp.core[core_index].state.lock);
+	return ret;
+}
+
+static int cputemp_read_string(struct device *dev, enum hwmon_sensor_types type,
+			       u32 attr, int channel, const char **str)
+{
+	struct peci_cputemp *priv = dev_get_drvdata(dev);
+
+	if (attr != hwmon_temp_label)
+		return -EOPNOTSUPP;
+
+	*str = channel < channel_core ?
+		cputemp_label[channel] : priv->coretemp_label[channel - channel_core];
+
+	return 0;
+}
+
+static int cputemp_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	struct peci_cputemp *priv = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_temp_input:
+		switch (channel) {
+		case channel_die:
+			return get_die_temp(priv, val);
+		case channel_dts:
+			return get_dts(priv, val);
+		case channel_tcontrol:
+			return get_temp_target(priv, tcontrol_type, val);
+		case channel_tthrottle:
+			return get_temp_target(priv, tthrottle_type, val);
+		case channel_tjmax:
+			return get_temp_target(priv, tjmax_type, val);
+		default:
+			return get_core_temp(priv, channel - channel_core, val);
+		}
+		break;
+	case hwmon_temp_max:
+		return get_temp_target(priv, tcontrol_type, val);
+	case hwmon_temp_crit:
+		return get_temp_target(priv, tjmax_type, val);
+	case hwmon_temp_crit_hyst:
+		return get_temp_target(priv, crit_hyst_type, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static umode_t cputemp_is_visible(const void *data, enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	const struct peci_cputemp *priv = data;
+
+	if (channel > CPUTEMP_CHANNEL_NUMS)
+		return 0;
+
+	if (channel < channel_core)
+		return 0444;
+
+	if (test_bit(channel - channel_core, priv->core_mask))
+		return 0444;
+
+	return 0;
+}
+
+static int init_core_mask(struct peci_cputemp *priv)
+{
+	struct peci_device *peci_dev = priv->peci_dev;
+	struct resolved_cores_reg *reg = priv->gen_info->reg;
+	u64 core_mask;
+	u32 data;
+	int ret;
+
+	/* Get the RESOLVED_CORES register value */
+	switch (peci_dev->info.model) {
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_D:
+		ret = peci_ep_pci_local_read(peci_dev, 0, reg->bus, reg->dev,
+					     reg->func, reg->offset + 4, &data);
+		if (ret)
+			return ret;
+
+		core_mask = (u64)data << 32;
+
+		ret = peci_ep_pci_local_read(peci_dev, 0, reg->bus, reg->dev,
+					     reg->func, reg->offset, &data);
+		if (ret)
+			return ret;
+
+		core_mask |= data;
+
+		break;
+	default:
+		ret = peci_pci_local_read(peci_dev, reg->bus, reg->dev,
+					  reg->func, reg->offset, &data);
+		if (ret)
+			return ret;
+
+		core_mask = data;
+
+		break;
+	}
+
+	if (!core_mask)
+		return -EIO;
+
+	bitmap_from_u64(priv->core_mask, core_mask);
+
+	return 0;
+}
+
+static int create_temp_label(struct peci_cputemp *priv)
+{
+	unsigned long core_max = find_last_bit(priv->core_mask, CORE_NUMS_MAX);
+	int i;
+
+	priv->coretemp_label = devm_kzalloc(priv->dev, (core_max + 1) * sizeof(char *), GFP_KERNEL);
+	if (!priv->coretemp_label)
+		return -ENOMEM;
+
+	for_each_set_bit(i, priv->core_mask, CORE_NUMS_MAX) {
+		priv->coretemp_label[i] = devm_kasprintf(priv->dev, GFP_KERNEL, "Core %d", i);
+		if (!priv->coretemp_label[i])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void check_resolved_cores(struct peci_cputemp *priv)
+{
+	/*
+	 * Failure to resolve cores is non-critical, we're still able to
+	 * provide other sensor data.
+	 */
+
+	if (init_core_mask(priv))
+		return;
+
+	if (create_temp_label(priv))
+		bitmap_zero(priv->core_mask, CORE_NUMS_MAX);
+}
+
+static void sensor_init(struct peci_cputemp *priv)
+{
+	int i;
+
+	mutex_init(&priv->temp.target.state.lock);
+	mutex_init(&priv->temp.die.state.lock);
+	mutex_init(&priv->temp.dts.state.lock);
+
+	for_each_set_bit(i, priv->core_mask, CORE_NUMS_MAX)
+		mutex_init(&priv->temp.core[i].state.lock);
+}
+
+static const struct hwmon_ops peci_cputemp_ops = {
+	.is_visible = cputemp_is_visible,
+	.read_string = cputemp_read_string,
+	.read = cputemp_read,
+};
+
+static const struct hwmon_channel_info *peci_cputemp_info[] = {
+	HWMON_CHANNEL_INFO(temp,
+			   /* Die temperature */
+			   HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX |
+			   HWMON_T_CRIT | HWMON_T_CRIT_HYST,
+			   /* DTS margin */
+			   HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_MAX |
+			   HWMON_T_CRIT | HWMON_T_CRIT_HYST,
+			   /* Tcontrol temperature */
+			   HWMON_T_LABEL | HWMON_T_INPUT | HWMON_T_CRIT,
+			   /* Tthrottle temperature */
+			   HWMON_T_LABEL | HWMON_T_INPUT,
+			   /* Tjmax temperature */
+			   HWMON_T_LABEL | HWMON_T_INPUT,
+			   /* Core temperature - for all core channels */
+			   [channel_core ... CPUTEMP_CHANNEL_NUMS - 1] =
+						HWMON_T_LABEL | HWMON_T_INPUT),
+	NULL
+};
+
+static const struct hwmon_chip_info peci_cputemp_chip_info = {
+	.ops = &peci_cputemp_ops,
+	.info = peci_cputemp_info,
+};
+
+static int peci_cputemp_probe(struct auxiliary_device *adev,
+			      const struct auxiliary_device_id *id)
+{
+	struct device *dev = &adev->dev;
+	struct peci_device *peci_dev = to_peci_device(dev->parent);
+	struct peci_cputemp *priv;
+	struct device *hwmon_dev;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->name = devm_kasprintf(dev, GFP_KERNEL, "peci_cputemp.cpu%d",
+				    peci_dev->info.socket_id);
+	if (!priv->name)
+		return -ENOMEM;
+
+	priv->dev = dev;
+	priv->peci_dev = peci_dev;
+	priv->gen_info = (const struct cpu_info *)id->driver_data;
+
+	/*
+	 * This is just a sanity check. Since we're using commands that are
+	 * guaranteed to be supported on a given platform, we should never see
+	 * revision lower than expected.
+	 */
+	if (peci_dev->info.peci_revision < priv->gen_info->min_peci_revision)
+		dev_warn(priv->dev,
+			 "Unexpected PECI revision %#x, some features may be unavailable\n",
+			 peci_dev->info.peci_revision);
+
+	check_resolved_cores(priv);
+
+	sensor_init(priv);
+
+	hwmon_dev = devm_hwmon_device_register_with_info(priv->dev, priv->name,
+							 priv, &peci_cputemp_chip_info, NULL);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+/*
+ * RESOLVED_CORES PCI configuration register may have different location on
+ * different platforms.
+ */
+static struct resolved_cores_reg resolved_cores_reg_hsx = {
+	.bus = 1,
+	.dev = 30,
+	.func = 3,
+	.offset = 0xb4,
+};
+
+static struct resolved_cores_reg resolved_cores_reg_icx = {
+	.bus = 14,
+	.dev = 30,
+	.func = 3,
+	.offset = 0xd0,
+};
+
+static const struct cpu_info cpu_hsx = {
+	.reg		= &resolved_cores_reg_hsx,
+	.min_peci_revision = 0x33,
+	.thermal_margin_to_millidegree = &dts_eight_dot_eight_to_millidegree,
+};
+
+static const struct cpu_info cpu_skx = {
+	.reg		= &resolved_cores_reg_hsx,
+	.min_peci_revision = 0x33,
+	.thermal_margin_to_millidegree = &dts_ten_dot_six_to_millidegree,
+};
+
+static const struct cpu_info cpu_icx = {
+	.reg		= &resolved_cores_reg_icx,
+	.min_peci_revision = 0x40,
+	.thermal_margin_to_millidegree = &dts_ten_dot_six_to_millidegree,
+};
+
+static const struct auxiliary_device_id peci_cputemp_ids[] = {
+	{
+		.name = "peci_cpu.cputemp.hsx",
+		.driver_data = (kernel_ulong_t)&cpu_hsx,
+	},
+	{
+		.name = "peci_cpu.cputemp.bdx",
+		.driver_data = (kernel_ulong_t)&cpu_hsx,
+	},
+	{
+		.name = "peci_cpu.cputemp.bdxd",
+		.driver_data = (kernel_ulong_t)&cpu_hsx,
+	},
+	{
+		.name = "peci_cpu.cputemp.skx",
+		.driver_data = (kernel_ulong_t)&cpu_skx,
+	},
+	{
+		.name = "peci_cpu.cputemp.icx",
+		.driver_data = (kernel_ulong_t)&cpu_icx,
+	},
+	{
+		.name = "peci_cpu.cputemp.icxd",
+		.driver_data = (kernel_ulong_t)&cpu_icx,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(auxiliary, peci_cputemp_ids);
+
+static struct auxiliary_driver peci_cputemp_driver = {
+	.probe		= peci_cputemp_probe,
+	.id_table	= peci_cputemp_ids,
+};
+
+module_auxiliary_driver(peci_cputemp_driver);
+
+MODULE_AUTHOR("Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>");
+MODULE_AUTHOR("Iwona Winiarska <iwona.winiarska@intel.com>");
+MODULE_DESCRIPTION("PECI cputemp driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(PECI_CPU);
diff --git a/drivers/hwmon/peci/dimmtemp.c b/drivers/hwmon/peci/dimmtemp.c
new file mode 100644
index 000000000..0a633bda3
--- /dev/null
+++ b/drivers/hwmon/peci/dimmtemp.c
@@ -0,0 +1,615 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2018-2021 Intel Corporation
+
+#include <linux/auxiliary_bus.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/devm-helpers.h>
+#include <linux/hwmon.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/peci.h>
+#include <linux/peci-cpu.h>
+#include <linux/units.h>
+#include <linux/workqueue.h>
+
+#include "common.h"
+
+#define DIMM_MASK_CHECK_DELAY_JIFFIES	msecs_to_jiffies(5000)
+
+/* Max number of channel ranks and DIMM index per channel */
+#define CHAN_RANK_MAX_ON_HSX	8
+#define DIMM_IDX_MAX_ON_HSX	3
+#define CHAN_RANK_MAX_ON_BDX	4
+#define DIMM_IDX_MAX_ON_BDX	3
+#define CHAN_RANK_MAX_ON_BDXD	2
+#define DIMM_IDX_MAX_ON_BDXD	2
+#define CHAN_RANK_MAX_ON_SKX	6
+#define DIMM_IDX_MAX_ON_SKX	2
+#define CHAN_RANK_MAX_ON_ICX	8
+#define DIMM_IDX_MAX_ON_ICX	2
+#define CHAN_RANK_MAX_ON_ICXD	4
+#define DIMM_IDX_MAX_ON_ICXD	2
+
+#define CHAN_RANK_MAX		CHAN_RANK_MAX_ON_HSX
+#define DIMM_IDX_MAX		DIMM_IDX_MAX_ON_HSX
+#define DIMM_NUMS_MAX		(CHAN_RANK_MAX * DIMM_IDX_MAX)
+
+#define CPU_SEG_MASK		GENMASK(23, 16)
+#define GET_CPU_SEG(x)		(((x) & CPU_SEG_MASK) >> 16)
+#define CPU_BUS_MASK		GENMASK(7, 0)
+#define GET_CPU_BUS(x)		((x) & CPU_BUS_MASK)
+
+#define DIMM_TEMP_MAX		GENMASK(15, 8)
+#define DIMM_TEMP_CRIT		GENMASK(23, 16)
+#define GET_TEMP_MAX(x)		(((x) & DIMM_TEMP_MAX) >> 8)
+#define GET_TEMP_CRIT(x)	(((x) & DIMM_TEMP_CRIT) >> 16)
+
+#define NO_DIMM_RETRY_COUNT_MAX	5
+
+struct peci_dimmtemp;
+
+struct dimm_info {
+	int chan_rank_max;
+	int dimm_idx_max;
+	u8 min_peci_revision;
+	int (*read_thresholds)(struct peci_dimmtemp *priv, int dimm_order,
+			       int chan_rank, u32 *data);
+};
+
+struct peci_dimm_thresholds {
+	long temp_max;
+	long temp_crit;
+	struct peci_sensor_state state;
+};
+
+enum peci_dimm_threshold_type {
+	temp_max_type,
+	temp_crit_type,
+};
+
+struct peci_dimmtemp {
+	struct peci_device *peci_dev;
+	struct device *dev;
+	const char *name;
+	const struct dimm_info *gen_info;
+	struct delayed_work detect_work;
+	struct {
+		struct peci_sensor_data temp;
+		struct peci_dimm_thresholds thresholds;
+	} dimm[DIMM_NUMS_MAX];
+	char **dimmtemp_label;
+	DECLARE_BITMAP(dimm_mask, DIMM_NUMS_MAX);
+	u8 no_dimm_retry_count;
+};
+
+static u8 __dimm_temp(u32 reg, int dimm_order)
+{
+	return (reg >> (dimm_order * 8)) & 0xff;
+}
+
+static int get_dimm_temp(struct peci_dimmtemp *priv, int dimm_no, long *val)
+{
+	int dimm_order = dimm_no % priv->gen_info->dimm_idx_max;
+	int chan_rank = dimm_no / priv->gen_info->dimm_idx_max;
+	int ret = 0;
+	u32 data;
+
+	mutex_lock(&priv->dimm[dimm_no].temp.state.lock);
+	if (!peci_sensor_need_update(&priv->dimm[dimm_no].temp.state))
+		goto skip_update;
+
+	ret = peci_pcs_read(priv->peci_dev, PECI_PCS_DDR_DIMM_TEMP, chan_rank, &data);
+	if (ret)
+		goto unlock;
+
+	priv->dimm[dimm_no].temp.value = __dimm_temp(data, dimm_order) * MILLIDEGREE_PER_DEGREE;
+
+	peci_sensor_mark_updated(&priv->dimm[dimm_no].temp.state);
+
+skip_update:
+	*val = priv->dimm[dimm_no].temp.value;
+unlock:
+	mutex_unlock(&priv->dimm[dimm_no].temp.state.lock);
+	return ret;
+}
+
+static int update_thresholds(struct peci_dimmtemp *priv, int dimm_no)
+{
+	int dimm_order = dimm_no % priv->gen_info->dimm_idx_max;
+	int chan_rank = dimm_no / priv->gen_info->dimm_idx_max;
+	u32 data;
+	int ret;
+
+	if (!peci_sensor_need_update(&priv->dimm[dimm_no].thresholds.state))
+		return 0;
+
+	ret = priv->gen_info->read_thresholds(priv, dimm_order, chan_rank, &data);
+	if (ret == -ENODATA) /* Use default or previous value */
+		return 0;
+	if (ret)
+		return ret;
+
+	priv->dimm[dimm_no].thresholds.temp_max = GET_TEMP_MAX(data) * MILLIDEGREE_PER_DEGREE;
+	priv->dimm[dimm_no].thresholds.temp_crit = GET_TEMP_CRIT(data) * MILLIDEGREE_PER_DEGREE;
+
+	peci_sensor_mark_updated(&priv->dimm[dimm_no].thresholds.state);
+
+	return 0;
+}
+
+static int get_dimm_thresholds(struct peci_dimmtemp *priv, enum peci_dimm_threshold_type type,
+			       int dimm_no, long *val)
+{
+	int ret;
+
+	mutex_lock(&priv->dimm[dimm_no].thresholds.state.lock);
+	ret = update_thresholds(priv, dimm_no);
+	if (ret)
+		goto unlock;
+
+	switch (type) {
+	case temp_max_type:
+		*val = priv->dimm[dimm_no].thresholds.temp_max;
+		break;
+	case temp_crit_type:
+		*val = priv->dimm[dimm_no].thresholds.temp_crit;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+unlock:
+	mutex_unlock(&priv->dimm[dimm_no].thresholds.state.lock);
+
+	return ret;
+}
+
+static int dimmtemp_read_string(struct device *dev,
+				enum hwmon_sensor_types type,
+				u32 attr, int channel, const char **str)
+{
+	struct peci_dimmtemp *priv = dev_get_drvdata(dev);
+
+	if (attr != hwmon_temp_label)
+		return -EOPNOTSUPP;
+
+	*str = (const char *)priv->dimmtemp_label[channel];
+
+	return 0;
+}
+
+static int dimmtemp_read(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long *val)
+{
+	struct peci_dimmtemp *priv = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_temp_input:
+		return get_dimm_temp(priv, channel, val);
+	case hwmon_temp_max:
+		return get_dimm_thresholds(priv, temp_max_type, channel, val);
+	case hwmon_temp_crit:
+		return get_dimm_thresholds(priv, temp_crit_type, channel, val);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t dimmtemp_is_visible(const void *data, enum hwmon_sensor_types type,
+				   u32 attr, int channel)
+{
+	const struct peci_dimmtemp *priv = data;
+
+	if (test_bit(channel, priv->dimm_mask))
+		return 0444;
+
+	return 0;
+}
+
+static const struct hwmon_ops peci_dimmtemp_ops = {
+	.is_visible = dimmtemp_is_visible,
+	.read_string = dimmtemp_read_string,
+	.read = dimmtemp_read,
+};
+
+static int check_populated_dimms(struct peci_dimmtemp *priv)
+{
+	int chan_rank_max = priv->gen_info->chan_rank_max;
+	int dimm_idx_max = priv->gen_info->dimm_idx_max;
+	u32 chan_rank_empty = 0;
+	u32 dimm_mask = 0;
+	int chan_rank, dimm_idx, ret;
+	u32 pcs;
+
+	BUILD_BUG_ON(BITS_PER_TYPE(chan_rank_empty) < CHAN_RANK_MAX);
+	BUILD_BUG_ON(BITS_PER_TYPE(dimm_mask) < DIMM_NUMS_MAX);
+	if (chan_rank_max * dimm_idx_max > DIMM_NUMS_MAX) {
+		WARN_ONCE(1, "Unsupported number of DIMMs - chan_rank_max: %d, dimm_idx_max: %d",
+			  chan_rank_max, dimm_idx_max);
+		return -EINVAL;
+	}
+
+	for (chan_rank = 0; chan_rank < chan_rank_max; chan_rank++) {
+		ret = peci_pcs_read(priv->peci_dev, PECI_PCS_DDR_DIMM_TEMP, chan_rank, &pcs);
+		if (ret) {
+			/*
+			 * Overall, we expect either success or -EINVAL in
+			 * order to determine whether DIMM is populated or not.
+			 * For anything else we fall back to deferring the
+			 * detection to be performed at a later point in time.
+			 */
+			if (ret == -EINVAL) {
+				chan_rank_empty |= BIT(chan_rank);
+				continue;
+			}
+
+			return -EAGAIN;
+		}
+
+		for (dimm_idx = 0; dimm_idx < dimm_idx_max; dimm_idx++)
+			if (__dimm_temp(pcs, dimm_idx))
+				dimm_mask |= BIT(chan_rank * dimm_idx_max + dimm_idx);
+	}
+
+	/*
+	 * If we got all -EINVALs, it means that the CPU doesn't have any
+	 * DIMMs. Unfortunately, it may also happen at the very start of
+	 * host platform boot. Retrying a couple of times lets us make sure
+	 * that the state is persistent.
+	 */
+	if (chan_rank_empty == GENMASK(chan_rank_max - 1, 0)) {
+		if (priv->no_dimm_retry_count < NO_DIMM_RETRY_COUNT_MAX) {
+			priv->no_dimm_retry_count++;
+
+			return -EAGAIN;
+		}
+
+		return -ENODEV;
+	}
+
+	/*
+	 * It's possible that memory training is not done yet. In this case we
+	 * defer the detection to be performed at a later point in time.
+	 */
+	if (!dimm_mask) {
+		priv->no_dimm_retry_count = 0;
+		return -EAGAIN;
+	}
+
+	dev_dbg(priv->dev, "Scanned populated DIMMs: %#x\n", dimm_mask);
+
+	bitmap_from_arr32(priv->dimm_mask, &dimm_mask, DIMM_NUMS_MAX);
+
+	return 0;
+}
+
+static int create_dimm_temp_label(struct peci_dimmtemp *priv, int chan)
+{
+	int rank = chan / priv->gen_info->dimm_idx_max;
+	int idx = chan % priv->gen_info->dimm_idx_max;
+
+	priv->dimmtemp_label[chan] = devm_kasprintf(priv->dev, GFP_KERNEL,
+						    "DIMM %c%d", 'A' + rank,
+						    idx + 1);
+	if (!priv->dimmtemp_label[chan])
+		return -ENOMEM;
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *peci_dimmtemp_temp_info[] = {
+	HWMON_CHANNEL_INFO(temp,
+			   [0 ... DIMM_NUMS_MAX - 1] = HWMON_T_LABEL |
+				HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT),
+	NULL
+};
+
+static const struct hwmon_chip_info peci_dimmtemp_chip_info = {
+	.ops = &peci_dimmtemp_ops,
+	.info = peci_dimmtemp_temp_info,
+};
+
+static int create_dimm_temp_info(struct peci_dimmtemp *priv)
+{
+	int ret, i, channels;
+	struct device *dev;
+
+	/*
+	 * We expect to either find populated DIMMs and carry on with creating
+	 * sensors, or find out that there are no DIMMs populated.
+	 * All other states mean that the platform never reached the state that
+	 * allows to check DIMM state - causing us to retry later on.
+	 */
+	ret = check_populated_dimms(priv);
+	if (ret == -ENODEV) {
+		dev_dbg(priv->dev, "No DIMMs found\n");
+		return 0;
+	} else if (ret) {
+		schedule_delayed_work(&priv->detect_work, DIMM_MASK_CHECK_DELAY_JIFFIES);
+		dev_dbg(priv->dev, "Deferred populating DIMM temp info\n");
+		return ret;
+	}
+
+	channels = priv->gen_info->chan_rank_max * priv->gen_info->dimm_idx_max;
+
+	priv->dimmtemp_label = devm_kzalloc(priv->dev, channels * sizeof(char *), GFP_KERNEL);
+	if (!priv->dimmtemp_label)
+		return -ENOMEM;
+
+	for_each_set_bit(i, priv->dimm_mask, DIMM_NUMS_MAX) {
+		ret = create_dimm_temp_label(priv, i);
+		if (ret)
+			return ret;
+		mutex_init(&priv->dimm[i].thresholds.state.lock);
+		mutex_init(&priv->dimm[i].temp.state.lock);
+	}
+
+	dev = devm_hwmon_device_register_with_info(priv->dev, priv->name, priv,
+						   &peci_dimmtemp_chip_info, NULL);
+	if (IS_ERR(dev)) {
+		dev_err(priv->dev, "Failed to register hwmon device\n");
+		return PTR_ERR(dev);
+	}
+
+	dev_dbg(priv->dev, "%s: sensor '%s'\n", dev_name(dev), priv->name);
+
+	return 0;
+}
+
+static void create_dimm_temp_info_delayed(struct work_struct *work)
+{
+	struct peci_dimmtemp *priv = container_of(to_delayed_work(work),
+						  struct peci_dimmtemp,
+						  detect_work);
+	int ret;
+
+	ret = create_dimm_temp_info(priv);
+	if (ret && ret != -EAGAIN)
+		dev_err(priv->dev, "Failed to populate DIMM temp info\n");
+}
+
+static int peci_dimmtemp_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id)
+{
+	struct device *dev = &adev->dev;
+	struct peci_device *peci_dev = to_peci_device(dev->parent);
+	struct peci_dimmtemp *priv;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->name = devm_kasprintf(dev, GFP_KERNEL, "peci_dimmtemp.cpu%d",
+				    peci_dev->info.socket_id);
+	if (!priv->name)
+		return -ENOMEM;
+
+	priv->dev = dev;
+	priv->peci_dev = peci_dev;
+	priv->gen_info = (const struct dimm_info *)id->driver_data;
+
+	/*
+	 * This is just a sanity check. Since we're using commands that are
+	 * guaranteed to be supported on a given platform, we should never see
+	 * revision lower than expected.
+	 */
+	if (peci_dev->info.peci_revision < priv->gen_info->min_peci_revision)
+		dev_warn(priv->dev,
+			 "Unexpected PECI revision %#x, some features may be unavailable\n",
+			 peci_dev->info.peci_revision);
+
+	ret = devm_delayed_work_autocancel(priv->dev, &priv->detect_work,
+					   create_dimm_temp_info_delayed);
+	if (ret)
+		return ret;
+
+	ret = create_dimm_temp_info(priv);
+	if (ret && ret != -EAGAIN) {
+		dev_err(dev, "Failed to populate DIMM temp info\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+read_thresholds_hsx(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u32 *data)
+{
+	u8 dev, func;
+	u16 reg;
+	int ret;
+
+	/*
+	 * Device 20, Function 0: IMC 0 channel 0 -> rank 0
+	 * Device 20, Function 1: IMC 0 channel 1 -> rank 1
+	 * Device 21, Function 0: IMC 0 channel 2 -> rank 2
+	 * Device 21, Function 1: IMC 0 channel 3 -> rank 3
+	 * Device 23, Function 0: IMC 1 channel 0 -> rank 4
+	 * Device 23, Function 1: IMC 1 channel 1 -> rank 5
+	 * Device 24, Function 0: IMC 1 channel 2 -> rank 6
+	 * Device 24, Function 1: IMC 1 channel 3 -> rank 7
+	 */
+	dev = 20 + chan_rank / 2 + chan_rank / 4;
+	func = chan_rank % 2;
+	reg = 0x120 + dimm_order * 4;
+
+	ret = peci_pci_local_read(priv->peci_dev, 1, dev, func, reg, data);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int
+read_thresholds_bdxd(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u32 *data)
+{
+	u8 dev, func;
+	u16 reg;
+	int ret;
+
+	/*
+	 * Device 10, Function 2: IMC 0 channel 0 -> rank 0
+	 * Device 10, Function 6: IMC 0 channel 1 -> rank 1
+	 * Device 12, Function 2: IMC 1 channel 0 -> rank 2
+	 * Device 12, Function 6: IMC 1 channel 1 -> rank 3
+	 */
+	dev = 10 + chan_rank / 2 * 2;
+	func = (chan_rank % 2) ? 6 : 2;
+	reg = 0x120 + dimm_order * 4;
+
+	ret = peci_pci_local_read(priv->peci_dev, 2, dev, func, reg, data);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int
+read_thresholds_skx(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u32 *data)
+{
+	u8 dev, func;
+	u16 reg;
+	int ret;
+
+	/*
+	 * Device 10, Function 2: IMC 0 channel 0 -> rank 0
+	 * Device 10, Function 6: IMC 0 channel 1 -> rank 1
+	 * Device 11, Function 2: IMC 0 channel 2 -> rank 2
+	 * Device 12, Function 2: IMC 1 channel 0 -> rank 3
+	 * Device 12, Function 6: IMC 1 channel 1 -> rank 4
+	 * Device 13, Function 2: IMC 1 channel 2 -> rank 5
+	 */
+	dev = 10 + chan_rank / 3 * 2 + (chan_rank % 3 == 2 ? 1 : 0);
+	func = chan_rank % 3 == 1 ? 6 : 2;
+	reg = 0x120 + dimm_order * 4;
+
+	ret = peci_pci_local_read(priv->peci_dev, 2, dev, func, reg, data);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int
+read_thresholds_icx(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u32 *data)
+{
+	u32 reg_val;
+	u64 offset;
+	int ret;
+	u8 dev;
+
+	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd4, &reg_val);
+	if (ret || !(reg_val & BIT(31)))
+		return -ENODATA; /* Use default or previous value */
+
+	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd0, &reg_val);
+	if (ret)
+		return -ENODATA; /* Use default or previous value */
+
+	/*
+	 * Device 26, Offset 224e0: IMC 0 channel 0 -> rank 0
+	 * Device 26, Offset 264e0: IMC 0 channel 1 -> rank 1
+	 * Device 27, Offset 224e0: IMC 1 channel 0 -> rank 2
+	 * Device 27, Offset 264e0: IMC 1 channel 1 -> rank 3
+	 * Device 28, Offset 224e0: IMC 2 channel 0 -> rank 4
+	 * Device 28, Offset 264e0: IMC 2 channel 1 -> rank 5
+	 * Device 29, Offset 224e0: IMC 3 channel 0 -> rank 6
+	 * Device 29, Offset 264e0: IMC 3 channel 1 -> rank 7
+	 */
+	dev = 26 + chan_rank / 2;
+	offset = 0x224e0 + dimm_order * 4 + (chan_rank % 2) * 0x4000;
+
+	ret = peci_mmio_read(priv->peci_dev, 0, GET_CPU_SEG(reg_val), GET_CPU_BUS(reg_val),
+			     dev, 0, offset, data);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct dimm_info dimm_hsx = {
+	.chan_rank_max	= CHAN_RANK_MAX_ON_HSX,
+	.dimm_idx_max	= DIMM_IDX_MAX_ON_HSX,
+	.min_peci_revision = 0x33,
+	.read_thresholds = &read_thresholds_hsx,
+};
+
+static const struct dimm_info dimm_bdx = {
+	.chan_rank_max	= CHAN_RANK_MAX_ON_BDX,
+	.dimm_idx_max	= DIMM_IDX_MAX_ON_BDX,
+	.min_peci_revision = 0x33,
+	.read_thresholds = &read_thresholds_hsx,
+};
+
+static const struct dimm_info dimm_bdxd = {
+	.chan_rank_max	= CHAN_RANK_MAX_ON_BDXD,
+	.dimm_idx_max	= DIMM_IDX_MAX_ON_BDXD,
+	.min_peci_revision = 0x33,
+	.read_thresholds = &read_thresholds_bdxd,
+};
+
+static const struct dimm_info dimm_skx = {
+	.chan_rank_max	= CHAN_RANK_MAX_ON_SKX,
+	.dimm_idx_max	= DIMM_IDX_MAX_ON_SKX,
+	.min_peci_revision = 0x33,
+	.read_thresholds = &read_thresholds_skx,
+};
+
+static const struct dimm_info dimm_icx = {
+	.chan_rank_max	= CHAN_RANK_MAX_ON_ICX,
+	.dimm_idx_max	= DIMM_IDX_MAX_ON_ICX,
+	.min_peci_revision = 0x40,
+	.read_thresholds = &read_thresholds_icx,
+};
+
+static const struct dimm_info dimm_icxd = {
+	.chan_rank_max	= CHAN_RANK_MAX_ON_ICXD,
+	.dimm_idx_max	= DIMM_IDX_MAX_ON_ICXD,
+	.min_peci_revision = 0x40,
+	.read_thresholds = &read_thresholds_icx,
+};
+
+static const struct auxiliary_device_id peci_dimmtemp_ids[] = {
+	{
+		.name = "peci_cpu.dimmtemp.hsx",
+		.driver_data = (kernel_ulong_t)&dimm_hsx,
+	},
+	{
+		.name = "peci_cpu.dimmtemp.bdx",
+		.driver_data = (kernel_ulong_t)&dimm_bdx,
+	},
+	{
+		.name = "peci_cpu.dimmtemp.bdxd",
+		.driver_data = (kernel_ulong_t)&dimm_bdxd,
+	},
+	{
+		.name = "peci_cpu.dimmtemp.skx",
+		.driver_data = (kernel_ulong_t)&dimm_skx,
+	},
+	{
+		.name = "peci_cpu.dimmtemp.icx",
+		.driver_data = (kernel_ulong_t)&dimm_icx,
+	},
+	{
+		.name = "peci_cpu.dimmtemp.icxd",
+		.driver_data = (kernel_ulong_t)&dimm_icxd,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(auxiliary, peci_dimmtemp_ids);
+
+static struct auxiliary_driver peci_dimmtemp_driver = {
+	.probe		= peci_dimmtemp_probe,
+	.id_table	= peci_dimmtemp_ids,
+};
+
+module_auxiliary_driver(peci_dimmtemp_driver);
+
+MODULE_AUTHOR("Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>");
+MODULE_AUTHOR("Iwona Winiarska <iwona.winiarska@intel.com>");
+MODULE_DESCRIPTION("PECI dimmtemp driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(PECI_CPU);