Re: [PATCH 1/2] drm/xe/sysfs: Simplify and fix sysfs registration

[Raag Jadav <raag.jadav@intel.com>]

On Mon, Sep 15, 2025 at 04:06:13PM +0200, Michal Wajdeczko wrote:
> Instead of manually maintaining each sysfs attribute define and use
> attribute groups and register them using device managed function.
> Then use is_visible() to filter-out unsupported attributes.
> 
> This will result not only in less code and smaller footprint:
> 
>   Function                                     old     new   delta
>   late_bind_attr_is_visible                      -     183    +183
>   ____versions                               80832   80896     +64
>   vram_attr_group                                -      48     +48
>   late_bind_attr_group                           -      48     +48
>   auto_link_downgrade_attr_group                 -      48     +48
>   late_bind_attrs                                -      24     +24
>   vram_attrs                                     -      16     +16
>   __pfx_late_bind_attr_is_visible                -      16     +16
>   xe_device_sysfs_init.cold                     20      21      +1
>   __pfx_xe_device_sysfs_fini                    16       -     -16
>   xe_device_sysfs_fini.cold                     21       -     -21
>   xe_device_sysfs_fini                         271       -    -271
>   xe_device_sysfs_init                         421     135    -286
>   Total: Before=2848898, After=2848752, chg -0.01%

I find the summary to be sufficient but upto you.

> but will also fix some bad error handling that we had here.
> 
> Fixes: 0e414bf7ad01 ("drm/xe: Expose PCIe link downgrade attributes")
> Fixes: cdc36b66cd41 ("drm/xe: Expose fan control and voltage regulator version")
> Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Lucas De Marchi <lucas.demarchi@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: Raag Jadav <raag.jadav@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_device_sysfs.c | 96 +++++++++++-----------------
>  1 file changed, 39 insertions(+), 57 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
> index 6ee422594b56..5b0b98ac9b17 100644
> --- a/drivers/gpu/drm/xe/xe_device_sysfs.c
> +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
> @@ -71,6 +71,15 @@ vram_d3cold_threshold_store(struct device *dev, struct device_attribute *attr,
>  
>  static DEVICE_ATTR_RW(vram_d3cold_threshold);
>  
> +static struct attribute *vram_attrs[] = {
> +	&dev_attr_vram_d3cold_threshold.attr,
> +	NULL
> +};
> +
> +static const struct attribute_group vram_attr_group = {
> +	.attrs = vram_attrs,
> +};
> +
>  static ssize_t
>  lb_fan_control_version_show(struct device *dev, struct device_attribute *attr, char *buf)
>  {
> @@ -149,8 +158,16 @@ lb_voltage_regulator_version_show(struct device *dev, struct device_attribute *a
>  }
>  static DEVICE_ATTR_ADMIN_RO(lb_voltage_regulator_version);
>  
> -static int late_bind_create_files(struct device *dev)
> +static struct attribute *late_bind_attrs[] = {
> +	&dev_attr_lb_fan_control_version.attr,
> +	&dev_attr_lb_voltage_regulator_version.attr,
> +	NULL
> +};
> +
> +static umode_t late_bind_attr_is_visible(struct kobject *kobj,
> +					 struct attribute *attr, int n)
>  {
> +	struct device *dev = kobj_to_dev(kobj);
>  	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
>  	struct xe_tile *root = xe_device_get_root_tile(xe);
>  	u32 cap = 0;
> @@ -160,51 +177,25 @@ static int late_bind_create_files(struct device *dev)
>  
>  	ret = xe_pcode_read(root, PCODE_MBOX(PCODE_LATE_BINDING, GET_CAPABILITY_STATUS, 0),
>  			    &cap, NULL);
> -	if (ret) {
> -		if (ret == -ENXIO) {
> -			drm_dbg(&xe->drm, "Late binding not supported by firmware\n");
> -			ret = 0;
> -		}
> -		goto out;
> -	}
> -
> -	if (REG_FIELD_GET(V1_FAN_SUPPORTED, cap)) {
> -		ret = sysfs_create_file(&dev->kobj, &dev_attr_lb_fan_control_version.attr);
> -		if (ret)
> -			goto out;
> -	}
> -
> -	if (REG_FIELD_GET(VR_PARAMS_SUPPORTED, cap))
> -		ret = sysfs_create_file(&dev->kobj, &dev_attr_lb_voltage_regulator_version.attr);
> -out:
>  	xe_pm_runtime_put(xe);
> -
> -	return ret;
> -}
> -
> -static void late_bind_remove_files(struct device *dev)
> -{
> -	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
> -	struct xe_tile *root = xe_device_get_root_tile(xe);
> -	u32 cap = 0;
> -	int ret;
> -
> -	xe_pm_runtime_get(xe);
> -
> -	ret = xe_pcode_read(root, PCODE_MBOX(PCODE_LATE_BINDING, GET_CAPABILITY_STATUS, 0),
> -			    &cap, NULL);
>  	if (ret)
> -		goto out;
> +		return 0;

Should we keep the original log so we don't have to guesswork our way around
random pcode errors?

PS: I've found patience algo to generate much readable diffs but ofcourse
it's a personal preference :)

Raag