Re: [PATCH V15 12/14] drm/xe: Add sysfs interface for bad gpu vram pages

On 11-08-2026 18:10, Tejas Upadhyay wrote:
> Include a sysfs interface designed to expose information about bad
> VRAM pages — those identified as having hardware faults (e.g., ECC
> errors). This interface allows userspace tools and administrators to
> monitor the health of the GPU's local memory and track the status of
> page retirement. Details on bad gpu vram pages can be found under
> /sys/bus/pci/devices/<bdf>/vram_bad_pages.
> 
> The format is: pfn : gpu_page_size : flags
> 
> flags:
>    R: reserved, this gpu page is reserved.
>    P: pending for reserve, this gpu page is marked as bad, will be
>       reserved in next window of page_reserve.
>    F: unable to reserve, this gpu page can't be reserved due to some
>       reasons.
> 
> For example, cat /sys/bus/pci/devices/<bdf>/vram_bad_pages:
>    max_pages : 10000
>    0x0000000000000000 : 0x0000000000001000 : R
>    0x0000000000001234 : 0x0000000000001000 : P
> 
> The sysfs binary attribute is created under the PCI device kobject
> when the platform supports it and the configfs bad_page_reservation
> policy is enabled. Uses RCU-protected list traversal so reads never
> block normal VRAM allocation operations.
> 
> Signed-off-by: Tejas Upadhyay <[email protected]>
> ---
>   drivers/gpu/drm/xe/xe_device_sysfs.c | 7 +++++++
>   drivers/gpu/drm/xe/xe_ttm_vram_mgr.h | 1 +
>   2 files changed, 8 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
> index a73e0e957cb0..47c5be4180fe 100644
> --- a/drivers/gpu/drm/xe/xe_device_sysfs.c
> +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
> @@ -8,12 +8,14 @@
>   #include <linux/pci.h>
>   #include <linux/sysfs.h>
>   
> +#include "xe_configfs.h"
>   #include "xe_device.h"
>   #include "xe_device_sysfs.h"
>   #include "xe_mmio.h"
>   #include "xe_pcode_api.h"
>   #include "xe_pcode.h"
>   #include "xe_pm.h"
> +#include "xe_ttm_vram_mgr.h"
>   
>   /**
>    * DOC: Xe device sysfs
> @@ -267,6 +269,7 @@ static const struct attribute_group auto_link_downgrade_attr_group = {
>   int xe_device_sysfs_init(struct xe_device *xe)
>   {
>   	struct device *dev = xe->drm.dev;
> +	bool policy;
>   	int ret;
>   
>   	if (xe->d3cold.capable) {
> @@ -285,5 +288,9 @@ int xe_device_sysfs_init(struct xe_device *xe)
>   			return ret;
>   	}
>   
> +	policy = xe_configfs_get_bad_page_reservation(to_pci_dev(dev));
> +	if (xe->info.platform == XE_CRESCENTISLAND && policy)
> +		xe_ttm_vram_sysfs_init(xe);
> +
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> index d5392beff30c..eb55b0f74ef3 100644
> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> @@ -32,6 +32,7 @@ void xe_ttm_vram_get_used(struct ttm_resource_manager *man,
>   			  u64 *used, u64 *used_visible);
>   
>   int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr);
> +int xe_ttm_vram_sysfs_init(struct xe_device *xe);

Move implementation to this patch.

>   static inline struct xe_ttm_vram_mgr_resource *
>   to_xe_ttm_vram_mgr_resource(struct ttm_resource *res)
>   {