[PATCH v3 3/4] thermal: qoriq: workaround unexpected temperature readings from tmu

[Frank Li]

On Mon, Aug 18, 2025 at 05:33:13PM +0800, Jacky Bai wrote:
> Invalid temperature measurements may be observed across the temperature
> range specified in the device data sheet. The invalid temperature can be
> read from any remote site and from any capture or report registers. The
> invalid change in temperature can be positive or negative and the resulting
> temperature can be outside the calibrated range, in which case the TSR[ORL]
> or TSR[ORH] bit will be set.
>
> Workaround:
> Use the raising/falling edge threshold to filter out the invalid temp.
> Check the TIDR register to make sure no jump happens When reading the temp.
>
> i.MX93 ERR052243:
> (https://www.nxp.com/webapp/Download?colCode=IMX93_2P87F&appType=license)
>
> Signed-off-by: Jacky Bai <ping.bai at nxp.com>
> ---
>  - v3 changes:
>   - refine the code with FIELD_PREP macro
>   - add errata doc url link and refine the commit log
>
>  - v2 changes:
>   - no
> ---
>  drivers/thermal/qoriq_thermal.c | 42 +++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 40 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c
> index b2e634547271dcf512c714907baa162921d2d527..134a63abb482d44b5cc78e672e6312fbdce5ba31 100644
> --- a/drivers/thermal/qoriq_thermal.c
> +++ b/drivers/thermal/qoriq_thermal.c
> @@ -30,6 +30,9 @@
>  #define TMU_VER1		0x1
>  #define TMU_VER2		0x2
>
> +/* errata ID info define */
> +#define TMU_ERR052243	BIT(0)
> +
>  #define REGS_TMR	0x000	/* Mode Register */
>  #define TMR_DISABLE	0x0
>  #define TMR_ME		0x80000000
> @@ -45,6 +48,13 @@
>  #define REGS_TIER	0x020	/* Interrupt Enable Register */
>  #define TIER_DISABLE	0x0
>
> +#define REGS_TIDR	0x24
> +#define TMRTRCTR	0x70
> +#define TMRTRCTR_EN	BIT(31)
> +#define TMRTRCTR_TEMP_MASK	GENMASK(7, 0)
> +#define TMFTRCTR	0x74
> +#define TMFTRCTR_EN	BIT(31)
> +#define TMFTRCTR_TEMP_MASK	GENMASK(7, 0)
>
>  #define REGS_TTCFGR	0x080	/* Temperature Configuration Register */
>  #define REGS_TSCFGR	0x084	/* Sensor Configuration Register */
> @@ -69,6 +79,7 @@
>  #define REGS_V2_TEUMR(n)	(0xf00 + 4 * (n))
>
>  #define GET_TEUMR0(drvdata)	(drvdata && drvdata->teumr0 ? drvdata->teumr0 : TEUMR0_V2)
> +#define CHECK_ERRATA_FLAG(drvdata, flag) (drvdata ? drvdata->tmu_errata & (flag) : 0)
>
>  /*
>   * Thermal zone data
> @@ -79,6 +90,7 @@ struct qoriq_sensor {
>
>  struct tmu_drvdata {
>  	u32 teumr0;
> +	u32 tmu_errata;
>  };
>
>  struct qoriq_tmu_data {
> @@ -99,7 +111,7 @@ static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
>  {
>  	struct qoriq_sensor *qsensor = thermal_zone_device_priv(tz);
>  	struct qoriq_tmu_data *qdata = qoriq_sensor_to_data(qsensor);
> -	u32 val;
> +	u32 val, tidr;
>  	/*
>  	 * REGS_TRITSR(id) has the following layout:
>  	 *
> @@ -124,6 +136,15 @@ static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
>  	if (!(val & TMR_ME))
>  		return -EAGAIN;
>
> +	/* ERR052243: If a raising or falling edge happens, try later */
> +	if (CHECK_ERRATA_FLAG(qdata->drvdata, TMU_ERR052243)) {
> +		regmap_read(qdata->regmap, REGS_TIDR, &tidr);
> +		if (tidr & GENMASK(25, 24)) {
> +			regmap_write(qdata->regmap, REGS_TIDR, GENMASK(25, 24));
> +			return -EAGAIN;
> +		}
> +	}
> +
>  	if (regmap_read_poll_timeout(qdata->regmap,
>  				     REGS_TRITSR(qsensor->id),
>  				     val,
> @@ -132,6 +153,15 @@ static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
>  				     10 * USEC_PER_MSEC))
>  		return -ENODATA;
>
> +	/*ERR052243: If a raising or falling edge happens, try later */
> +	if (CHECK_ERRATA_FLAG(qdata->drvdata, TMU_ERR052243)) {
> +		regmap_read(qdata->regmap, REGS_TIDR, &tidr);
> +		if (tidr & GENMASK(25, 24)) {

you use GENMASK(25, 24) twice, define it as macro.

> +			regmap_write(qdata->regmap, REGS_TIDR, GENMASK(25, 24));
> +			return -EAGAIN;
> +		}
> +	}
> +
>  	if (qdata->ver == TMU_VER1) {
>  		*temp = (val & GENMASK(7, 0)) * MILLIDEGREE_PER_DEGREE;
>  	} else {
> @@ -238,7 +268,6 @@ static void qoriq_tmu_init_device(struct qoriq_tmu_data *data)
>  	regmap_write(data->regmap, REGS_TIER, TIER_DISABLE);
>
>  	/* Set update_interval */
> -

uncessary change.

>  	if (data->ver == TMU_VER1) {
>  		regmap_write(data->regmap, REGS_TMTMIR, TMTMIR_DEFAULT);
>  	} else {
> @@ -246,6 +275,14 @@ static void qoriq_tmu_init_device(struct qoriq_tmu_data *data)
>  		regmap_write(data->regmap, REGS_V2_TEUMR(0), GET_TEUMR0(data->drvdata));
>  	}
>
> +	/* ERR052243: Set the raising & falling edge monitor */
> +	if (CHECK_ERRATA_FLAG(data->drvdata, TMU_ERR052243)) {
> +		regmap_write(data->regmap, TMRTRCTR, TMRTRCTR_EN |
> +			     FIELD_PREP(TMRTRCTR_TEMP_MASK, 0x7));
> +		regmap_write(data->regmap, TMFTRCTR, TMFTRCTR_EN |
> +			     FIELD_PREP(TMFTRCTR_TEMP_MASK, 0x7));

the same here for 0x7

Frank
> +
> +	}
>  	/* Disable monitoring */
>  	regmap_write(data->regmap, REGS_TMR, TMR_DISABLE);
>  }
> @@ -389,6 +426,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(qoriq_tmu_pm_ops,
>
>  static const struct tmu_drvdata imx93_data = {
>  	.teumr0 = TEUMR0_V21,
> +	.tmu_errata = TMU_ERR052243,
>  };
>
>  static const struct of_device_id qoriq_tmu_match[] = {
>
> --
> 2.34.1
>