Re: [PATCH v6 01/13] drm/xe/hwmon: Handle pcode read failures of xe_hwmon_pcode_rmw_power_limit

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Fri, Sep 25, 2026 at 02:24:17AM +0530, Karthik Poosa wrote:
> Return early when the pcode read operation fails in
> xe_hwmon_pcode_rmw_power_limit() and check the returned error in
> callers to avoid updating power limit settings with invalid data.
> 
> Fixes: 8aa7306631f0 ("drm/xe/hwmon: Fix xe_hwmon_power_max_write")
> Signed-off-by: Karthik Poosa <karthik.poosa@intel.com>
> ---
> v2: Address sashiko-bot@kernel.org review comments. Return -EIO instead of
>     0 on errors in the sysfs store callback to prevent potential userspace
>     infinite loops.
> 
>  drivers/gpu/drm/xe/xe_hwmon.c | 18 ++++++++++++------
>  1 file changed, 12 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
> index 5edeac961ec3..be3fb6733b6f 100644
> --- a/drivers/gpu/drm/xe/xe_hwmon.c
> +++ b/drivers/gpu/drm/xe/xe_hwmon.c
> @@ -232,9 +232,11 @@ static int xe_hwmon_pcode_rmw_power_limit(const struct xe_hwmon *hwmon, u32 attr
>  						  READ_PSYSGPU_POWER_LIMIT :
>  						  READ_PACKAGE_POWER_LIMIT,
>  						  prepare_power_limit_param2(hwmon)), &val0, &val1);
> -	if (ret)
> -		drm_dbg(&hwmon->xe->drm, "read failed ch %d val0 0x%08x, val1 0x%08x, ret %d\n",
> +	if (ret) {
> +		drm_err(&hwmon->xe->drm, "read failed ch %d val0 0x%08x, val1 0x%08x, ret %d\n",
>  			channel, val0, val1, ret);
> +		return ret;
> +	}
>  
>  	if (attr == PL1_HWMON_ATTR)
>  		val0 = (val0 & ~clr) | set;
> @@ -394,7 +396,9 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe
>  		if (hwmon->xe->info.has_mbx_power_limits) {
>  			drm_dbg(&hwmon->xe->drm, "disabling %s on channel %d\n",
>  				PWR_ATTR_TO_STR(attr), channel);
> -			xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM_EN, 0);
> +			ret = xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM_EN, 0);
> +			if (ret)
> +				goto unlock;
>  			xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, &reg_val);
>  		} else {
>  			reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN, 0);
> @@ -679,11 +683,13 @@ xe_hwmon_power_max_interval_store(struct device *dev, struct device_attribute *a
>  
>  	mutex_lock(&hwmon->hwmon_lock);
>  
> -	if (hwmon->xe->info.has_mbx_power_limits)
> -		xe_hwmon_pcode_rmw_power_limit(hwmon, power_attr, channel, PWR_LIM_TIME, rxy);
> -	else
> +	if (hwmon->xe->info.has_mbx_power_limits) {
> +		if (xe_hwmon_pcode_rmw_power_limit(hwmon, power_attr, channel, PWR_LIM_TIME, rxy))
> +			count = -EIO;

please use ret for this, not changing count...
and you may set ret = count earlier, or something like that...

> +	} else {
>  		r = xe_mmio_rmw32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel),
>  				  PWR_LIM_TIME, rxy);
> +	}
>  
>  	mutex_unlock(&hwmon->hwmon_lock);
>  
> -- 
> 2.25.1
>