[PATCH v2 3/3] thermal: qcom: add PM8901 PMIC temperature-alarm driver

[Herman van Hazendonk]

Add a thermal-of sensor driver for the temperature-alarm block inside
the Qualcomm PM8901 PMIC. PM8901 is a secondary PMIC paired with
PM8058 on the MSM8x60 family (MSM8260/MSM8660/APQ8060). It exposes
an over-temperature alarm at SSBI offset 0x23/0x24 with three
escalating stages (105/125/145 C); the driver decodes the stage +
threshold pair into a millicelsius reading and registers two PMIC-
internal interrupts (TEMP_ALARM at block 6 bit 4, TEMP_HI_ALARM at
block 6 bit 5).

Used by board thermal-zones for the orderly_poweroff path on the HP
TouchPad.

Signed-off-by: Herman van Hazendonk <github.com@xxxxxxxxxx>
---
 drivers/thermal/qcom/Kconfig          |  12 +
 drivers/thermal/qcom/Makefile         |   1 +
 drivers/thermal/qcom/qcom-pm8901-tm.c | 408 ++++++++++++++++++++++++++
 3 files changed, 421 insertions(+)
 create mode 100644 drivers/thermal/qcom/qcom-pm8901-tm.c

diff --git a/drivers/thermal/qcom/Kconfig b/drivers/thermal/qcom/Kconfig
index a6bb01082ec6..af099032f1e6 100644
--- a/drivers/thermal/qcom/Kconfig
+++ b/drivers/thermal/qcom/Kconfig
@@ -32,6 +32,18 @@ config QCOM_SPMI_TEMP_ALARM
 	  real time die temperature if an ADC is present or an estimate of the
 	  temperature based upon the over temperature stage value.
 
+config QCOM_PM8901_TEMP_ALARM
+	tristate "Qualcomm PM8901 PMIC Temperature Alarm"
+	depends on MFD_PM8XXX || COMPILE_TEST
+	depends on THERMAL_OF
+	help
+	  This enables the thermal driver for the PM8901 PMIC over-temperature
+	  alarm block. PM8901 exposes a stage-based alarm (no raw ADC) with
+	  four selectable thresholds and three escalating stages. The driver
+	  registers a thermal-of sensor so a board device tree can declare
+	  trip points and a critical-trip action (orderly_poweroff). Used on
+	  HP TouchPad (APQ8060) where PM8901 supplies the secondary PMIC die.
+
 config QCOM_LMH
 	tristate "Qualcomm Limits Management Hardware"
 	depends on ARCH_QCOM || COMPILE_TEST
diff --git a/drivers/thermal/qcom/Makefile b/drivers/thermal/qcom/Makefile
index 0fa2512042e7..90dc05151e33 100644
--- a/drivers/thermal/qcom/Makefile
+++ b/drivers/thermal/qcom/Makefile
@@ -5,4 +5,5 @@ qcom_tsens-y			+= tsens.o tsens-v2.o tsens-v1.o tsens-v0_1.o \
 				   tsens-8960.o
 obj-$(CONFIG_QCOM_SPMI_ADC_TM5)	+= qcom-spmi-adc-tm5.o
 obj-$(CONFIG_QCOM_SPMI_TEMP_ALARM)	+= qcom-spmi-temp-alarm.o
+obj-$(CONFIG_QCOM_PM8901_TEMP_ALARM)	+= qcom-pm8901-tm.o
 obj-$(CONFIG_QCOM_LMH)		+= lmh.o
diff --git a/drivers/thermal/qcom/qcom-pm8901-tm.c b/drivers/thermal/qcom/qcom-pm8901-tm.c
new file mode 100644
index 000000000000..b159e9917c2c
--- /dev/null
+++ b/drivers/thermal/qcom/qcom-pm8901-tm.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Qualcomm PM8901 PMIC Thermal-Alarm Driver
+ *
+ * Mainline port of the legacy 2.6.35-palm drivers/thermal/pmic8901-tm.c.
+ * PM8901 exposes a stage-based over-temperature alarm (no raw ADC) with
+ * four selectable thresholds and three escalating stages. This driver
+ * mirrors the legacy programming exactly (threshold-set 0, software
+ * override enabled, PWM gating at 8 Hz) and registers a thermal-of
+ * sensor so a board DT can declare trip points and a critical action.
+ *
+ * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
+ * Copyright (c) 2026 Herman van Hazendonk <github.com@xxxxxxxxxx>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+/* SSBI registers (offsets from the per-instance reg base) */
+#define PM8901_TM_REG_CTRL		0x00	/* CTRL/STATUS  (base + 0) */
+#define PM8901_TM_REG_PWM		0x01	/* PWM gating  (base + 1) */
+
+/* CTRL register fields */
+#define CTRL_ST3_SD			BIT(7)
+#define CTRL_ST2_SD			BIT(6)
+#define CTRL_STATUS_MASK		GENMASK(5, 4)
+#define CTRL_THRESH_MASK		GENMASK(3, 2)
+#define CTRL_OVRD_ST3			BIT(1)
+#define CTRL_OVRD_ST2			BIT(0)
+#define CTRL_OVRD_MASK			GENMASK(1, 0)
+
+/* PWM register fields */
+#define PWM_EN				BIT(7)
+#define PWM_PER_PRE_MASK		GENMASK(5, 3)
+#define PWM_PER_DIV_MASK		GENMASK(2, 0)
+
+/* Temperature math (from legacy pmic8901-tm.c) */
+#define PM8901_TEMP_STAGE_STEP		20000	/* 20 deg C between stages */
+#define PM8901_TEMP_STAGE_HYSTERESIS	2000	/*  2 deg C transition guard */
+#define PM8901_TEMP_THRESH_MIN		105000	/* threshold 0 base = 105 C */
+#define PM8901_TEMP_THRESH_STEP		5000	/*  5 deg C per threshold step */
+
+/*
+ * PM8901 has no real die ADC; when stage == 0 ("below threshold") we
+ * report a plausible idle estimate matching the legacy DEFAULT_NO_ADC_TEMP.
+ */
+#define PM8901_TEMP_NO_ALARM		37000
+
+struct pm8901_tm_chip {
+	struct device			*dev;
+	struct regmap			*map;
+	struct thermal_zone_device	*tz_dev;
+	struct mutex			lock;
+	unsigned int			base;	/* SSBI offset, from DT reg */
+	unsigned int			stage;
+	unsigned int			thresh;
+	int				temp;
+	bool				initialised;
+};
+
+static int pm8901_tm_read_ctrl(struct pm8901_tm_chip *chip, u8 *val)
+{
+	unsigned int v;
+	int ret;
+
+	ret = regmap_read(chip->map, chip->base + PM8901_TM_REG_CTRL, &v);
+	if (!ret)
+		*val = v;
+	return ret;
+}
+
+static int pm8901_tm_write_ctrl(struct pm8901_tm_chip *chip, u8 val)
+{
+	return regmap_write(chip->map, chip->base + PM8901_TM_REG_CTRL, val);
+}
+
+static int pm8901_tm_write_pwm(struct pm8901_tm_chip *chip, u8 val)
+{
+	return regmap_write(chip->map, chip->base + PM8901_TM_REG_PWM, val);
+}
+
+/*
+ * Decode the (stage, threshold) pair into a single millicelsius value.
+ * Logic matches the legacy pmic8901-tm.c hysteresis selection:
+ *  - on a rising stage transition, use the lower bound of the new stage
+ *    plus +HYSTERESIS so we don't bounce
+ *  - on a falling stage transition, use the upper bound of the new stage
+ *    minus -HYSTERESIS
+ *  - on the first read after probe (initialised == false), report the
+ *    lower bound of the current stage (the most conservative estimate
+ *    given that the hardware only tells us "we crossed this stage's
+ *    threshold"), or PM8901_TEMP_NO_ALARM when stage == 0.
+ */
+static int pm8901_tm_update_temp_locked(struct pm8901_tm_chip *chip)
+{
+	unsigned int new_stage;
+	u8 reg;
+	int ret;
+
+	ret = pm8901_tm_read_ctrl(chip, &reg);
+	if (ret)
+		return ret;
+
+	new_stage = FIELD_GET(CTRL_STATUS_MASK, reg);
+	chip->thresh = FIELD_GET(CTRL_THRESH_MASK, reg);
+
+	if (!chip->initialised) {
+		if (new_stage)
+			chip->temp = PM8901_TEMP_THRESH_MIN +
+				     chip->thresh * PM8901_TEMP_THRESH_STEP +
+				     (new_stage - 1) * PM8901_TEMP_STAGE_STEP;
+		else
+			chip->temp = PM8901_TEMP_NO_ALARM;
+		chip->initialised = true;
+	} else if (new_stage > chip->stage) {
+		chip->temp = PM8901_TEMP_THRESH_MIN +
+			     chip->thresh * PM8901_TEMP_THRESH_STEP +
+			     (new_stage - 1) * PM8901_TEMP_STAGE_STEP +
+			     PM8901_TEMP_STAGE_HYSTERESIS;
+	} else if (new_stage < chip->stage) {
+		chip->temp = PM8901_TEMP_THRESH_MIN +
+			     chip->thresh * PM8901_TEMP_THRESH_STEP +
+			     new_stage * PM8901_TEMP_STAGE_STEP -
+			     PM8901_TEMP_STAGE_HYSTERESIS;
+	}
+
+	chip->stage = new_stage;
+	return 0;
+}
+
+static int pm8901_tm_get_temp(struct thermal_zone_device *tz, int *temp)
+{
+	struct pm8901_tm_chip *chip = thermal_zone_device_priv(tz);
+	int ret;
+
+	if (!temp)
+		return -EINVAL;
+
+	mutex_lock(&chip->lock);
+	ret = pm8901_tm_update_temp_locked(chip);
+	if (!ret)
+		*temp = chip->temp;
+	mutex_unlock(&chip->lock);
+
+	return ret;
+}
+
+static const struct thermal_zone_device_ops pm8901_tm_zone_ops = {
+	.get_temp = pm8901_tm_get_temp,
+};
+
+/*
+ * Shared ISR for both TEMP_ALARM (stage-transition) and TEMP_HI_ALARM
+ * (hi-temp) interrupts. Updates the cached temperature, clears any
+ * latched ST2_SD / ST3_SD shutdown bits so the next stage transition
+ * can be observed, and pokes the thermal core which then re-reads
+ * temp and walks trips (a critical-trip cross triggers orderly_poweroff
+ * via the kernel's standard machinery).
+ */
+static irqreturn_t pm8901_tm_isr(int irq, void *data)
+{
+	struct pm8901_tm_chip *chip = data;
+	u8 reg;
+	int ret;
+
+	mutex_lock(&chip->lock);
+
+	ret = pm8901_tm_update_temp_locked(chip);
+	if (ret) {
+		mutex_unlock(&chip->lock);
+		return IRQ_HANDLED;
+	}
+
+	ret = pm8901_tm_read_ctrl(chip, &reg);
+	if (!ret && (reg & (CTRL_ST2_SD | CTRL_ST3_SD))) {
+		reg &= ~(CTRL_ST2_SD | CTRL_ST3_SD | CTRL_STATUS_MASK);
+		pm8901_tm_write_ctrl(chip, reg);
+	}
+
+	dev_dbg(chip->dev, "alarm irq=%d stage=%u thresh=%u temp=%d\n",
+		irq, chip->stage, chip->thresh, chip->temp);
+
+	mutex_unlock(&chip->lock);
+
+	thermal_zone_device_update(chip->tz_dev, THERMAL_EVENT_UNSPECIFIED);
+	return IRQ_HANDLED;
+}
+
+/*
+ * Program PM8901 to the legacy default: threshold-set 0 (105 / 125 / 145 C),
+ * PWM at 8 Hz (legacy "cut down on unnecessary interrupts" rate), and
+ * prime the cached temperature. This intentionally does NOT yet flip the
+ * software-override bits; HW auto-shutdown is left enabled here so the
+ * PMIC keeps protecting the part if any later probe step fails. The
+ * SW-override switch happens in pm8901_tm_enable_sw_override() and is
+ * paired with a devm action that reverts the bits if the driver unbinds.
+ */
+static int pm8901_tm_init_hw(struct pm8901_tm_chip *chip)
+{
+	int ret;
+	u8 reg;
+
+	mutex_lock(&chip->lock);
+
+	ret = pm8901_tm_read_ctrl(chip, &reg);
+	if (ret)
+		goto out;
+
+	/* Clear status + threshold bits, leave OVRD bits as the HW found them. */
+	reg = reg & ~(CTRL_STATUS_MASK | CTRL_THRESH_MASK);
+	ret = pm8901_tm_write_ctrl(chip, reg);
+	if (ret)
+		goto out;
+
+	chip->thresh = 0;
+
+	/* PWM @ 8 Hz: PWM_EN | PRE=3 | DIV=3 — verbatim from legacy. */
+	reg = PWM_EN | FIELD_PREP(PWM_PER_PRE_MASK, 3) |
+	      FIELD_PREP(PWM_PER_DIV_MASK, 3);
+	ret = pm8901_tm_write_pwm(chip, reg);
+	if (ret)
+		goto out;
+
+	/* Prime the cached temperature from current hardware state. */
+	chip->initialised = false;
+	ret = pm8901_tm_update_temp_locked(chip);
+
+out:
+	mutex_unlock(&chip->lock);
+	return ret;
+}
+
+/*
+ * Re-enable PM8901's hardware auto-cut on the way out, so the PMIC takes
+ * over thermal protection again once the kernel is no longer the
+ * shutdown agent. Best-effort: log on failure, do not propagate the
+ * error (there is nothing the unbind path can do about it).
+ */
+static void pm8901_tm_restore_hw_shutdown(void *data)
+{
+	struct pm8901_tm_chip *chip = data;
+	int ret;
+	u8 reg;
+
+	mutex_lock(&chip->lock);
+	ret = pm8901_tm_read_ctrl(chip, &reg);
+	if (!ret) {
+		reg &= ~CTRL_OVRD_MASK;
+		ret = pm8901_tm_write_ctrl(chip, reg);
+	}
+	mutex_unlock(&chip->lock);
+
+	if (ret)
+		dev_warn(chip->dev,
+			 "failed to restore PMIC HW auto-shutdown: %d\n", ret);
+}
+
+/*
+ * Hand thermal protection responsibility from the PMIC's hardware
+ * auto-cut to the kernel thermal core. This is the LAST step of probe
+ * so that, if any earlier step fails, the PMIC keeps protecting the
+ * part on its own. Once it succeeds we install a devm action that
+ * re-enables HW auto-cut if/when the driver is unbound.
+ */
+static int pm8901_tm_enable_sw_override(struct pm8901_tm_chip *chip)
+{
+	int ret;
+	u8 reg;
+
+	mutex_lock(&chip->lock);
+	ret = pm8901_tm_read_ctrl(chip, &reg);
+	if (!ret) {
+		reg = (reg & ~CTRL_OVRD_MASK) | CTRL_OVRD_ST3 | CTRL_OVRD_ST2;
+		ret = pm8901_tm_write_ctrl(chip, reg);
+	}
+	mutex_unlock(&chip->lock);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(chip->dev,
+					pm8901_tm_restore_hw_shutdown, chip);
+}
+
+static int pm8901_tm_probe(struct platform_device *pdev)
+{
+	struct pm8901_tm_chip *chip;
+	int ret, irq_alarm, irq_hi_alarm;
+	u32 res;
+
+	chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->dev = &pdev->dev;
+	mutex_init(&chip->lock);
+
+	chip->map = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!chip->map)
+		return dev_err_probe(&pdev->dev, -ENXIO,
+				     "no regmap on PM8901 parent\n");
+
+	ret = of_property_read_u32(pdev->dev.of_node, "reg", &res);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "missing reg property\n");
+	chip->base = res;
+
+	irq_alarm = platform_get_irq_byname(pdev, "alarm");
+	if (irq_alarm < 0)
+		return irq_alarm;
+	irq_hi_alarm = platform_get_irq_byname(pdev, "hi-alarm");
+	if (irq_hi_alarm < 0)
+		return irq_hi_alarm;
+
+	ret = pm8901_tm_init_hw(chip);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "hw init failed\n");
+
+	chip->tz_dev = devm_thermal_of_zone_register(&pdev->dev, 0, chip,
+						     &pm8901_tm_zone_ops);
+	if (IS_ERR(chip->tz_dev))
+		return dev_err_probe(&pdev->dev, PTR_ERR(chip->tz_dev),
+				     "thermal zone register failed\n");
+
+	ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
+					pm8901_tm_isr, IRQF_ONESHOT,
+					"pm8901-tm-alarm", chip);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "alarm IRQ request failed\n");
+
+	ret = devm_request_threaded_irq(&pdev->dev, irq_hi_alarm, NULL,
+					pm8901_tm_isr, IRQF_ONESHOT,
+					"pm8901-tm-hi-alarm", chip);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "hi-alarm IRQ request failed\n");
+
+	platform_set_drvdata(pdev, chip);
+
+	/*
+	 * All resources that we need on the thermal hot path are now in
+	 * place; hand thermal-shutdown responsibility from the PMIC's
+	 * hardware auto-cut to the kernel thermal core. If this fails the
+	 * PMIC is left with its original (post-reset) HW auto-cut intact,
+	 * so we never leave the part unprotected.
+	 */
+	ret = pm8901_tm_enable_sw_override(chip);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "failed to enable SW thermal override\n");
+
+	thermal_zone_device_update(chip->tz_dev, THERMAL_EVENT_UNSPECIFIED);
+
+	{
+		unsigned int stage, thresh;
+		int temp;
+
+		/*
+		 * IRQs and thermal-core polling are live by now, so the
+		 * cached state can be updated under chip->lock at any time.
+		 * Snapshot under the lock so the boot banner is consistent.
+		 */
+		mutex_lock(&chip->lock);
+		stage = chip->stage;
+		thresh = chip->thresh;
+		temp = chip->temp;
+		mutex_unlock(&chip->lock);
+
+		dev_info(&pdev->dev,
+			 "PM8901 thermal alarm: base=0x%x stage=%u thresh=%u temp=%d\n",
+			 chip->base, stage, thresh, temp);
+	}
+
+	return 0;
+}
+
+/*
+ * No explicit ->remove() needed: pm8901_tm_restore_hw_shutdown() is
+ * registered as a devm action in probe and re-enables the PMIC's HW
+ * auto-cut automatically on unbind.
+ */
+
+static const struct of_device_id pm8901_tm_match_table[] = {
+	{ .compatible = "qcom,pm8901-temp-alarm" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pm8901_tm_match_table);
+
+static struct platform_driver pm8901_tm_driver = {
+	.driver = {
+		.name		= "pm8901-temp-alarm",
+		.of_match_table	= pm8901_tm_match_table,
+	},
+	.probe	= pm8901_tm_probe,
+};
+module_platform_driver(pm8901_tm_driver);
+
+MODULE_ALIAS("platform:pm8901-temp-alarm");
+MODULE_DESCRIPTION("Qualcomm PM8901 PMIC Thermal Alarm driver");
+MODULE_LICENSE("GPL v2");
-- 
2.43.0