On Thu, Feb 19, 2026 at 12:10:55PM -0800, Matthew Brost wrote:
> All current users of DRM pagemap set source_peer_migrates to true during
> migration, and it is unclear whether any user would ever want to disable
> this for performance reasons or for features such as compression. It is
> also questionable whether this flag could be made to work with
> high-speed fabric mapping APIs.
> 
> Drop the flag and make DRM pagemap unconditionally assume that
> source_peer_migrates is true.
> 
> Signed-off-by: Matthew Brost <[email protected]>
> ---
>  drivers/gpu/drm/drm_pagemap.c | 10 ++++------
>  drivers/gpu/drm/xe/xe_svm.c   |  1 -
>  include/drm/drm_pagemap.h     |  8 ++------
>  3 files changed, 6 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
> index 01a06d1fd1a0..32535ab01c0f 100644
> --- a/drivers/gpu/drm/drm_pagemap.c
> +++ b/drivers/gpu/drm/drm_pagemap.c
> @@ -602,12 +602,10 @@ int drm_pagemap_migrate_to_devmem(struct 
> drm_pagemap_devmem *devmem_allocation,
>                               own_pages++;
>                               continue;
>                       }
> -                     if (mdetails->source_peer_migrates) {
> -                             cur.dpagemap = src_zdd->dpagemap;
> -                             cur.ops = src_zdd->devmem_allocation->ops;
> -                             cur.device = cur.dpagemap->drm->dev;
> -                             pages[i] = src_page;
> -                     }
> +                     cur.dpagemap = src_zdd->dpagemap;
> +                     cur.ops = src_zdd->devmem_allocation->ops;
> +                     cur.device = cur.dpagemap->drm->dev;
> +                     pages[i] = src_page;
>               }
>               if (!pages[i]) {
>                       cur.dpagemap = NULL;
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> index c96ed760c077..e86e69087c7e 100644
> --- a/drivers/gpu/drm/xe/xe_svm.c
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -1027,7 +1027,6 @@ static int xe_drm_pagemap_populate_mm(struct 
> drm_pagemap *dpagemap,
>       struct xe_pagemap *xpagemap = container_of(dpagemap, typeof(*xpagemap), 
> dpagemap);
>       struct drm_pagemap_migrate_details mdetails = {
>               .timeslice_ms = timeslice_ms,
> -             .source_peer_migrates = 1,
>       };
>       struct xe_vram_region *vr = xe_pagemap_to_vr(xpagemap);
>       struct dma_fence *pre_migrate_fence = NULL;
> diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
> index 72f6828f2604..5c33982141c2 100644
> --- a/include/drm/drm_pagemap.h
> +++ b/include/drm/drm_pagemap.h
> @@ -329,12 +329,8 @@ struct drm_pagemap_devmem {
>   * struct drm_pagemap_migrate_details - Details to govern migration.
>   * @timeslice_ms: The time requested for the migrated pagemap pages to
>   * be present in @mm before being allowed to be migrated back.
> - * @can_migrate_same_pagemap: Whether the copy function as indicated by
> - * the @source_peer_migrates flag, can migrate device pages within a
> - * single drm_pagemap.
> - * @source_peer_migrates: Whether on p2p migration, The source drm_pagemap
> - * should use the copy_to_ram() callback rather than the destination
> - * drm_pagemap should use the copy_to_devmem() callback.
> + * @can_migrate_same_pagemap: Whether the copy function can migrate
> + * device pages within a single drm_pagemap.

I forgot to delete this variable, in effort to save CI cycles, will fix
this in next rev or when merging.

Matt 

>   */
>  struct drm_pagemap_migrate_details {
>       unsigned long timeslice_ms;
> -- 
> 2.34.1
> 

Reply via email to