Re: [PATCH V15 10/14] drm/xe/configfs: Add vram bad page reservation policy

On 11-08-2026 18:10, Tejas Upadhyay wrote:
> The interface enables setting the policy for how bad pages are
> handled in VRAM. This is crucial for maintaining system
> stability in scenarios where VRAM degradation occurs.
> 
> By default policy will be "reserve", which can be changed to
> "logging" only.
> 
> v3:
> - All FW communication moved under RAS
> v2:
> - Add CRI check and rebase
> 
> Signed-off-by: Tejas Upadhyay <[email protected]>
> ---
>   drivers/gpu/drm/xe/xe_configfs.c     | 64 +++++++++++++++++++++++++++-
>   drivers/gpu/drm/xe/xe_configfs.h     |  2 +
>   drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 10 +++++
>   3 files changed, 75 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
> index 052cce962161..c4f386d4bf09 100644
> --- a/drivers/gpu/drm/xe/xe_configfs.c
> +++ b/drivers/gpu/drm/xe/xe_configfs.c
> @@ -61,7 +61,8 @@
>    *	    ├── survivability_mode
>    *	    ├── gt_types_allowed
>    *	    ├── engines_allowed
> - *	    └── enable_psmi
> + *          ├── enable_psmi
> + *          └── bad_page_reservation
>    *
>    * After configuring the attributes as per next section, the device can be
>    * probed with::
> @@ -159,6 +160,16 @@
>    *
>    * This attribute can only be set before binding to the device.
>    *
> + * Bad pages reservation:
> + * ---------------------
> + *
> + * Disable vram bad pages reservation, instead just report it in dmesg.
> + *  Example to disable it::
> + *
> + *      # echo 0 > /sys/kernel/config/xe/0000:03:00.0/bad_page_reservation
> + *
> + * This attribute can only be set before binding to the device.
> + *
>    * Context restore BB
>    * ------------------
>    *
> @@ -275,6 +286,7 @@ struct xe_config_group_device {
>   		bool survivability_mode;
>   		bool enable_psmi;
>   		bool enable_multi_queue;
> +		bool bad_page_reservation;
>   		struct {
>   			unsigned int max_vfs;
>   			bool admin_only_pf;
> @@ -295,6 +307,7 @@ static const struct xe_config_device device_defaults = {
>   	.survivability_mode = false,
>   	.enable_psmi = false,
>   	.enable_multi_queue = true,
> +	.bad_page_reservation = true,
>   	.sriov = {
>   		.max_vfs = XE_DEFAULT_MAX_VFS,
>   		.admin_only_pf = XE_DEFAULT_ADMIN_ONLY_PF,
> @@ -616,6 +629,32 @@ static ssize_t enable_multi_queue_store(struct config_item *item, const char *pa
>   	return len;
>   }
>   
> +static ssize_t bad_page_reservation_show(struct config_item *item, char *page)
> +{
> +	struct xe_config_device *dev = to_xe_config_device(item);
> +
> +	return sprintf(page, "%d\n", dev->bad_page_reservation);
> +}
> +
> +static ssize_t bad_page_reservation_store(struct config_item *item, const char *page, size_t len)
> +{
> +	struct xe_config_group_device *dev = to_xe_config_group_device(item);
> +	bool val;
> +	int ret;
> +
> +	ret = kstrtobool(page, &val);
> +	if (ret)
> +		return ret;
> +
> +	guard(mutex)(&dev->lock);
> +	if (is_bound(dev))
> +		return -EBUSY;
> +
> +	dev->config.bad_page_reservation = val;
> +
> +	return len;
> +}
> +
>   static bool wa_bb_read_advance(bool dereference, char **p,
>   			       const char *append, size_t len,
>   			       size_t *max_size)
> @@ -855,6 +894,7 @@ CONFIGFS_ATTR(, ctx_restore_mid_bb);
>   CONFIGFS_ATTR(, ctx_restore_post_bb);
>   CONFIGFS_ATTR(, enable_multi_queue);
>   CONFIGFS_ATTR(, enable_psmi);
> +CONFIGFS_ATTR(, bad_page_reservation);
>   CONFIGFS_ATTR(, engines_allowed);
>   CONFIGFS_ATTR(, gt_types_allowed);
>   CONFIGFS_ATTR(, survivability_mode);
> @@ -864,6 +904,7 @@ static struct configfs_attribute *xe_config_device_attrs[] = {
>   	&attr_ctx_restore_post_bb,
>   	&attr_enable_multi_queue,
>   	&attr_enable_psmi,
> +	&attr_bad_page_reservation,
>   	&attr_engines_allowed,
>   	&attr_gt_types_allowed,
>   	&attr_survivability_mode,
> @@ -1142,6 +1183,7 @@ static void dump_custom_dev_config(struct pci_dev *pdev,
>   	PRI_CUSTOM_ATTR("%llx", engines_allowed);
>   	PRI_CUSTOM_ATTR("%d", enable_multi_queue);
>   	PRI_CUSTOM_ATTR("%d", enable_psmi);
> +	PRI_CUSTOM_ATTR("%d", bad_page_reservation);
>   	PRI_CUSTOM_ATTR("%d", survivability_mode);
>   	PRI_CUSTOM_ATTR("%u", sriov.admin_only_pf);
>   
> @@ -1290,6 +1332,26 @@ bool xe_configfs_get_enable_multi_queue(struct pci_dev *pdev)
>   	return ret;
>   }
>   
> +/**
> + * xe_configfs_get_bad_page_reservation - get configfs bad_page_reservation setting
> + * @pdev: pci device
> + *
> + * Return: bad_page_reservation setting in configfs

Nit: Better to document configfs val 0 means Logging only
                                      1 means logging and offlining

With that

Reviewed-by: Himal Prasad Ghimiray <[email protected]>

> + */
> +bool xe_configfs_get_bad_page_reservation(struct pci_dev *pdev)
> +{
> +	struct xe_config_group_device *dev = find_xe_config_group_device(pdev);
> +	bool ret;
> +
> +	if (!dev)
> +		return device_defaults.bad_page_reservation;
> +
> +	ret = dev->config.bad_page_reservation;
> +	config_group_put(&dev->group);
> +
> +	return ret;
> +}
> +
>   /**
>    * xe_configfs_get_ctx_restore_mid_bb - get configfs ctx_restore_mid_bb setting
>    * @pdev: pci device
> diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h
> index 4fbbeafba473..7405cc5f3207 100644
> --- a/drivers/gpu/drm/xe/xe_configfs.h
> +++ b/drivers/gpu/drm/xe/xe_configfs.h
> @@ -24,6 +24,7 @@ bool xe_configfs_media_gt_allowed(struct pci_dev *pdev);
>   u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev);
>   bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev);
>   bool xe_configfs_get_enable_multi_queue(struct pci_dev *pdev);
> +bool xe_configfs_get_bad_page_reservation(struct pci_dev *pdev);
>   u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev,
>   				       enum xe_engine_class class,
>   				       const u32 **cs);
> @@ -44,6 +45,7 @@ static inline bool xe_configfs_media_gt_allowed(struct pci_dev *pdev) { return t
>   static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; }
>   static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; }
>   static inline bool xe_configfs_get_enable_multi_queue(struct pci_dev *pdev) { return true; }
> +static inline bool xe_configfs_get_bad_page_reservation(struct pci_dev *pdev) { return true; }
>   static inline u32 xe_configfs_get_ctx_restore_mid_bb(struct pci_dev *pdev,
>   						     enum xe_engine_class class,
>   						     const u32 **cs) { return 0; }
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> index 370bcf50c7f7..6280886e2ebb 100644
> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> @@ -13,6 +13,7 @@
>   
>   #include "regs/xe_regs.h"
>   #include "xe_bo.h"
> +#include "xe_configfs.h"
>   #include "xe_device.h"
>   #include "xe_exec_queue.h"
>   #include "xe_lrc.h"
> @@ -792,6 +793,7 @@ int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr)
>   	struct xe_ttm_vram_mgr *vram_mgr;
>   	struct xe_vram_region *vr;
>   	struct gpu_buddy *mm;
> +	bool policy;
>   
>   	vr = xe_ttm_vram_addr_to_region(xe, addr);
>   	if (IS_ERR(vr)) {
> @@ -811,6 +813,14 @@ int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr)
>   	vram_mgr = &vr->ttm;
>   	mm = &vram_mgr->mm;
>   
> +	policy = xe_configfs_get_bad_page_reservation(to_pci_dev(xe->drm.dev));
> +	if (!policy) {
> +		drm_err(&xe->drm, "0x%llx is reported as corrupted address by HW\n",
> +			addr);
> +		/* Let RAS report to FW to drop addr from SRAM queue */
> +		return -EOPNOTSUPP;
> +	}
> +
>   	/* Reserve page at address */
>   	return xe_ttm_vram_reserve_page_at_addr(xe, addr, vram_mgr, mm);
>   }