Re: [PATCH V18 12/14] drm/xe: Expose bad VRAM pages via debugfs

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

On Wed, Aug 26, 2026 at 07:21:47PM +0530, Tejas Upadhyay wrote:
> Add a debugfs file "vram_bad_pages" that shows offlined and queued
> VRAM pages across all tiles. Each entry displays the page frame number,
> GPU page size, and status flag (R=reserved, P=pending, F=failed).
> 
> example,
> cat /sys/kernel/debug/dri/0/vram_bad_pages
> 
> max_pages: 10000
> 0x0000000000000000 : 0x0000000000001000 : R
> 0x0000000000001234 : 0x0000000000001000 : P
> 0x0000000000080000 : 0x0000000000001000 : R   ← tile 1 addr (includes tile offset)
> 
> Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

> ---
>  drivers/gpu/drm/xe/xe_debugfs.c            |  4 ++
>  drivers/gpu/drm/xe/xe_ttm_vram_mgr.c       | 66 ++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_ttm_vram_mgr.h       |  2 +
>  drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h |  2 +
>  4 files changed, 74 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
> index 28135f84e286..e19eafffbb08 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"
>  
> @@ -773,6 +774,9 @@ void xe_debugfs_register(struct xe_device *xe)
>  	if (man)
>  		ttm_resource_manager_create_debugfs(man, root, "stolen_mm");
>  
> +	if (xe->info.platform == XE_CRESCENTISLAND)
> +		xe_ttm_vram_debugfs_init(xe, root);
> +
>  	for_each_tile(tile, xe, tile_id)
>  		xe_tile_debugfs_register(tile);
>  
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> index 24d134754265..af9e1fa868d7 100644
> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
> @@ -5,6 +5,7 @@
>   */
>  
>  #include <linux/cgroup_dmem.h>
> +#include <linux/debugfs.h>
>  
>  #include <drm/drm_managed.h>
>  #include <drm/drm_drv.h>
> @@ -874,3 +875,68 @@ int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr)
>  	return xe_ttm_vram_reserve_page_at_addr(xe, addr - vr->dpa_base, vram_mgr, mm);
>  }
>  EXPORT_SYMBOL(xe_ttm_vram_handle_addr_fault);
> +
> +static int vram_bad_pages_show(struct seq_file *m, void *unused)
> +{
> +	struct xe_device *xe = m->private;
> +	struct xe_ttm_vram_offline_resource *pos;
> +	struct ttm_resource_manager *man;
> +	struct gpu_buddy_block *block;
> +	struct xe_ttm_vram_mgr *mgr;
> +	struct xe_tile *tile;
> +	u8 id;
> +
> +	man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0);
> +	if (man)
> +		seq_printf(m, "max_pages: %d\n",
> +			   to_xe_ttm_vram_mgr(man)->max_pages);
> +
> +	for_each_tile(tile, xe, id) {
> +		struct xe_vram_region *vr = tile->mem.vram;
> +
> +		man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0 + id);
> +		if (!man || !vr)
> +			continue;
> +		mgr = to_xe_ttm_vram_mgr(man);
> +
> +		rcu_read_lock();
> +
> +		list_for_each_entry_rcu(pos, &mgr->offlined_pages, offlined_link) {
> +			block = list_first_entry_or_null(&pos->blocks,
> +							 struct gpu_buddy_block, link);
> +			if (!block)
> +				continue;
> +
> +			seq_printf(m, "0x%016llx : 0x%016llx : R\n",
> +				   (gpu_buddy_block_offset(block) + vr->dpa_base) >> PAGE_SHIFT,
> +				   gpu_buddy_block_size(&mgr->mm, block));
> +		}
> +
> +		list_for_each_entry_rcu(pos, &mgr->queued_pages, queued_link) {
> +			u64 pfn, blk_size;
> +
> +			block = list_first_entry_or_null(&pos->blocks,
> +							 struct gpu_buddy_block, link);
> +			if (block) {
> +				pfn = (gpu_buddy_block_offset(block) + vr->dpa_base) >> PAGE_SHIFT;
> +				blk_size = gpu_buddy_block_size(&mgr->mm, block);
> +			} else {
> +				pfn = (pos->addr + vr->dpa_base) >> PAGE_SHIFT;
> +				blk_size = PAGE_SIZE;
> +			}
> +
> +			seq_printf(m, "0x%016llx : 0x%016llx : %c\n",
> +				   pfn, blk_size, pos->status ? 'F' : 'P');
> +		}
> +
> +		rcu_read_unlock();
> +	}
> +
> +	return 0;
> +}
> +DEFINE_SHOW_ATTRIBUTE(vram_bad_pages);
> +
> +void xe_ttm_vram_debugfs_init(struct xe_device *xe, struct dentry *root)
> +{
> +	debugfs_create_file("vram_bad_pages", 0444, root, xe, &vram_bad_pages_fops);
> +}
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> index d5392beff30c..f354c26c4257 100644
> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
> @@ -9,6 +9,7 @@
>  #include "xe_ttm_vram_mgr_types.h"
>  
>  enum dma_data_direction;
> +struct dentry;
>  struct xe_device;
>  struct xe_tile;
>  struct xe_vram_region;
> @@ -32,6 +33,7 @@ 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);
> +void xe_ttm_vram_debugfs_init(struct xe_device *xe, struct dentry *root);
>  static inline struct xe_ttm_vram_mgr_resource *
>  to_xe_ttm_vram_mgr_resource(struct ttm_resource *res)
>  {
> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
> index dc97b0ad0e51..efcf3e1d4e80 100644
> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
> @@ -37,6 +37,8 @@ struct xe_ttm_vram_mgr {
>  	struct mutex lock;
>  	/** @mem_type: The TTM memory type */
>  	u32 mem_type;
> +	/** @max_pages: max pages that can be in offline queue retrieved from FW */
> +	u16 max_pages;
>  };
>  
>  /**
> -- 
> 2.52.0
>