Re: [PATCH V15 14/14] drm/xe: Add fault-inject based VRAM page offline injection

On 11-08-2026 18:10, Tejas Upadhyay wrote:
> Add a fault-inject based debugfs interface for testing VRAM page
> offlining. This replaces the previous standalone debugfs approach
> with the standard kernel fault-inject infrastructure.
> 
> Two debugfs entries are created under the xe debugfs root for
> CRI platforms:
> - inject_mempage_offline/: Standard fault-inject knobs (probability,
>    times, interval, etc.) — only available with
>    CONFIG_FAULT_INJECTION_DEBUG_FS
> - inject_mempage_offline_trigger: Write a PFN value to inject a
>    specific page, or write "0" to auto-pick the last unallocated
>    VRAM page
> 
> The trigger accepts:
> - "0"      : auto-pick last unallocated page
> - "0xPFN"  : inject fault at a specific PFN address
> 
> On kernels with CONFIG_FAULT_INJECTION_DEBUG_FS, injection is gated
> by should_fail() (probability/times must be configured first).
> On kernels without it, the trigger always injects directly.
> 
> The injection reports the page as faulted via
> xe_ttm_vram_handle_addr_fault(), exercising the full page offlining
> path.
> 
> Usage (with CONFIG_FAULT_INJECTION_DEBUG_FS):
>    echo 100 > inject_mempage_offline/probability
>    echo 1 > inject_mempage_offline/times
>    echo 0 > inject_mempage_offline_trigger
> 
> Usage (without CONFIG_FAULT_INJECTION_DEBUG_FS):
>    echo 0 > inject_mempage_offline_trigger
> 
> v2(sashiko):
> - use cond_resched()
> - validate input first and fix addr < 0 case
> - validate vr, move block, found var as local to scope_guard
> 
> Signed-off-by: Tejas Upadhyay <[email protected]>
> ---
>   drivers/gpu/drm/xe/xe_debugfs.c      | 50 ++++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_debugfs.h      |  2 ++
>   drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 52 ++++++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_ttm_vram_mgr.h |  1 +
>   4 files changed, 105 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
> index eeceab4a9901..2fd1ff806864 100644
> --- a/drivers/gpu/drm/xe/xe_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_debugfs.c
> @@ -32,6 +32,7 @@
>   #include "xe_sriov_vf.h"
>   #include "xe_step.h"
>   #include "xe_tile_debugfs.h"
> +#include "xe_ttm_vram_mgr.h"
>   #include "xe_vsec.h"
>   #include "xe_wa.h"
>   
> @@ -43,12 +44,18 @@
>   
>   DECLARE_FAULT_ATTR(gt_reset_failure);
>   DECLARE_FAULT_ATTR(inject_csc_hw_error);
> +DECLARE_FAULT_ATTR(inject_mempage_offline);
>   
>   static bool csc_hw_error_available(struct xe_device *xe)
>   {
>   	return !IS_SRIOV_VF(xe) && xe->info.platform == XE_BATTLEMAGE;
>   }
>   
> +static bool is_crescent_island(struct xe_device *xe)
> +{
> +	return xe->info.platform == XE_CRESCENTISLAND;
> +}
> +
>   /*
>    * Fault injection table.  Each entry registers a debugfs attribute; add a
>    * matching FAULT_ACTION() below for every entry added here.
> @@ -63,6 +70,9 @@ static struct {
>   	{ .name = "inject_csc_hw_error",
>   	  .attr = &inject_csc_hw_error,
>   	  .is_visible = csc_hw_error_available },
> +	{ .name = "inject_mempage_offline",
> +	  .attr = &inject_mempage_offline,
> +	  .is_visible = is_crescent_island },
>   };
>   
>   /*
> @@ -77,6 +87,41 @@ bool xe_fault_##name(void)				\
>   
>   FAULT_ACTION(gt_reset, gt_reset_failure)
>   FAULT_ACTION(csc_hw_error, inject_csc_hw_error)
> +FAULT_ACTION(mempage_offline, inject_mempage_offline)
> +
> +static ssize_t inject_mempage_offline_trigger(struct file *f,
> +					      const char __user *ubuf,
> +					      size_t size, loff_t *pos)
> +{
> +	struct xe_device *xe = file_inode(f)->i_private;
> +	struct xe_tile *tile = xe_device_get_root_tile(xe);
> +	struct xe_vram_region *vr = tile->mem.vram;
> +	u64 pfn;
> +	int ret;
> +
> +	if (!vr)
> +		return -ENODEV;
> +
> +	ret = kstrtou64_from_user(ubuf, size, 0, &pfn);
> +	if (ret)
> +		return ret;
> +
> +	if (IS_ENABLED(CONFIG_FAULT_INJECTION_DEBUG_FS) &&
> +	    !should_fail(&inject_mempage_offline, 1))
> +		return size;

Use the FAULT_ACTION xe_fault_mempage_offline generated above.

> +
> +	if (pfn == 0)
> +		return xe_ttm_vram_inject_fault(xe) ?: size;
> +
> +	/* User provided PFN — convert to DPA and inject */
> +	return xe_ttm_vram_handle_addr_fault(xe,
> +					     (pfn << PAGE_SHIFT) + vr->dpa_base) ?: size;
> +}
> +
> +static const struct file_operations inject_mempage_offline_fops = {
> +	.owner = THIS_MODULE,
> +	.write = inject_mempage_offline_trigger,
> +};
>   
>   static void xe_fault_inject_debugfs_register(struct xe_device *xe,
>   					     struct dentry *root)
> @@ -91,6 +136,11 @@ static void xe_fault_inject_debugfs_register(struct xe_device *xe,
>   		fault_create_debugfs_attr(xe_fault_inject_entry[i].name, root,
>   					  xe_fault_inject_entry[i].attr);
>   	}
> +
> +	if (is_crescent_island(xe)) {
> +		debugfs_create_file("inject_mempage_offline_trigger", 0200,
> +				    root, xe, &inject_mempage_offline_fops);
> +	}
>   }
>   
>   static void read_residency_counter(struct xe_device *xe, struct xe_mmio *mmio,
> diff --git a/drivers/gpu/drm/xe/xe_debugfs.h b/drivers/gpu/drm/xe/xe_debugfs.h
> index cd56f7442b99..727747f13101 100644
> --- a/drivers/gpu/drm/xe/xe_debugfs.h
> +++ b/drivers/gpu/drm/xe/xe_debugfs.h
> @@ -13,10 +13,12 @@ struct xe_device;
>   #ifdef CONFIG_DEBUG_FS
>   bool xe_fault_gt_reset(void);
>   bool xe_fault_csc_hw_error(void);
> +bool xe_fault_mempage_offline(void);
>   void xe_debugfs_register(struct xe_device *xe);
>   #else
>   static inline bool xe_fault_gt_reset(void) { return false; }
>   static inline bool xe_fault_csc_hw_error(void) { return false; }
> +static inline bool xe_fault_mempage_offline(void) { return false; }
>   static inline void xe_debugfs_register(struct xe_device *xe) { }
>   #endif
>   
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> index 5bb66c7b5505..c985d633c10b 100644
> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> @@ -834,6 +834,58 @@ int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr)
>   }
>   EXPORT_SYMBOL(xe_ttm_vram_handle_addr_fault);
>   
> +/**
> + * xe_ttm_vram_inject_fault - Inject a VRAM page fault for testing
> + * @xe: xe device instance
> + *
> + * Picks the last unallocated VRAM page and reports it as faulted
> + * via xe_ttm_vram_handle_addr_fault(). Used by the fault-inject
> + * debugfs interface for testing page offlining.
> + *
> + * Return: 0 on success, negative error code on failure.
> + */
> +int xe_ttm_vram_inject_fault(struct xe_device *xe)
> +{
> +	struct xe_tile *tile = xe_device_get_root_tile(xe);
> +	struct xe_vram_region *vr = tile->mem.vram;
> +	struct xe_ttm_vram_mgr *vram_mgr = &vr->ttm;
> +	struct gpu_buddy *mm = &vram_mgr->mm;
> +	u64 addr;
> +
> +	if (vr->actual_physical_size < SZ_4K)
> +		return -ENOSPC;
> +
> +	addr = vr->actual_physical_size - SZ_4K;
> +	while (addr < vr->actual_physical_size) {
> +		struct gpu_buddy_block *block;
> +		bool found = false;
> +
> +		scoped_guard(mutex, &vram_mgr->lock) {
> +			block = gpu_buddy_allocated_addr_to_block(mm, addr);
> +			if (!block)
> +				found = true;
> +		}
> +
> +		/*
> +		 * Intentional race window: xe_ttm_vram_handle_addr_fault()
> +		 * re-acquires vram_mgr->lock internally, so we cannot hold
> +		 * it here. A concurrent allocation claiming this page between
> +		 * the two calls is an acceptable false negative for this
> +		 * test-only path.
> +		 */
> +		if (found)
> +			return xe_ttm_vram_handle_addr_fault(xe, addr + vr->dpa_base);
> +
> +		cond_resched();
> +		if (addr == 0)
> +			break;
> +		addr -= SZ_4K;
> +	}
> +
> +	return -ENOSPC;
> +}
> +EXPORT_SYMBOL(xe_ttm_vram_inject_fault);
> +
>   static size_t serialize_bad_pages(struct xe_ttm_vram_mgr *mgr, char *buf, size_t max_len)
>   {
>   	struct xe_ttm_vram_offline_resource *pos;
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> index eb55b0f74ef3..9feb999a1f8d 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_inject_fault(struct xe_device *xe);
>   int xe_ttm_vram_sysfs_init(struct xe_device *xe);
>   static inline struct xe_ttm_vram_mgr_resource *
>   to_xe_ttm_vram_mgr_resource(struct ttm_resource *res)