Re: [PATCH v4 3/4] drm/pagemap: Split drm_pagemap_migrate_map_pages into device / system

["Thomas Hellström" <thomas.hellstrom@linux.intel.com>]

On Wed, 2026-02-04 at 20:19 -0800, Matthew Brost wrote:
> Split drm_pagemap_migrate_map_pages into device / system helpers
> clearly
> seperating these operations. Will help with upcoming changes to split
> IOVA allocation steps.
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>  drivers/gpu/drm/drm_pagemap.c | 146 ++++++++++++++++++++++----------
> --
>  1 file changed, 96 insertions(+), 50 deletions(-)
> 
> diff --git a/drivers/gpu/drm/drm_pagemap.c
> b/drivers/gpu/drm/drm_pagemap.c
> index fbd69f383457..29677b19bb69 100644
> --- a/drivers/gpu/drm/drm_pagemap.c
> +++ b/drivers/gpu/drm/drm_pagemap.c
> @@ -205,7 +205,7 @@ static void drm_pagemap_get_devmem_page(struct
> page *page,
>  }
>  
>  /**
> - * drm_pagemap_migrate_map_pages() - Map migration pages for GPU SVM
> migration
> + * drm_pagemap_migrate_map_device_pages() - Map device migration
> pages for GPU SVM migration
>   * @dev: The device performing the migration.
>   * @local_dpagemap: The drm_pagemap local to the migrating device.
>   * @pagemap_addr: Array to store DMA information corresponding to
> mapped pages.
> @@ -221,19 +221,22 @@ static void drm_pagemap_get_devmem_page(struct
> page *page,
>   *
>   * Returns: 0 on success, -EFAULT if an error occurs during mapping.
>   */
> -static int drm_pagemap_migrate_map_pages(struct device *dev,
> -					 struct drm_pagemap
> *local_dpagemap,
> -					 struct drm_pagemap_addr
> *pagemap_addr,
> -					 unsigned long *migrate_pfn,
> -					 unsigned long npages,
> -					 enum dma_data_direction
> dir,
> -					 const struct
> drm_pagemap_migrate_details *mdetails)
> +static int
> +drm_pagemap_migrate_map_device_pages(struct device *dev,
> +				     struct drm_pagemap
> *local_dpagemap,
> +				     struct drm_pagemap_addr
> *pagemap_addr,
> +				     unsigned long *migrate_pfn,
> +				     unsigned long npages,
> +				     enum dma_data_direction dir,
> +				     const struct
> drm_pagemap_migrate_details *mdetails)

We might want to call this device_private pages. Device coherent pages
are treated like system pages here, but I figure those are known to the
dma subsystem and can be handled by the map_system_pages callback.

>  {
>  	unsigned long num_peer_pages = 0, num_local_pages = 0, i;
>  
>  	for (i = 0; i < npages;) {
>  		struct page *page =
> migrate_pfn_to_page(migrate_pfn[i]);
> -		dma_addr_t dma_addr;
> +		struct drm_pagemap_zdd *zdd;
> +		struct drm_pagemap *dpagemap;
> +		struct drm_pagemap_addr addr;
>  		struct folio *folio;
>  		unsigned int order = 0;
>  
> @@ -243,36 +246,26 @@ static int drm_pagemap_migrate_map_pages(struct
> device *dev,
>  		folio = page_folio(page);
>  		order = folio_order(folio);
>  
> -		if (is_device_private_page(page)) {
> -			struct drm_pagemap_zdd *zdd =
> drm_pagemap_page_zone_device_data(page);
> -			struct drm_pagemap *dpagemap = zdd-
> >dpagemap;
> -			struct drm_pagemap_addr addr;
> -
> -			if (dpagemap == local_dpagemap) {
> -				if (!mdetails-
> >can_migrate_same_pagemap)
> -					goto next;
> +		WARN_ON_ONCE(!is_device_private_page(page));
>  
> -				num_local_pages += NR_PAGES(order);
> -			} else {
> -				num_peer_pages += NR_PAGES(order);
> -			}
> +		zdd = drm_pagemap_page_zone_device_data(page);
> +		dpagemap = zdd->dpagemap;
>  
> -			addr = dpagemap->ops->device_map(dpagemap,
> dev, page, order, dir);
> -			if (dma_mapping_error(dev, addr.addr))
> -				return -EFAULT;
> +		if (dpagemap == local_dpagemap) {
> +			if (!mdetails->can_migrate_same_pagemap)
> +				goto next;
>  
> -			pagemap_addr[i] = addr;
> +			num_local_pages += NR_PAGES(order);
>  		} else {
> -			dma_addr = dma_map_page(dev, page, 0,
> page_size(page), dir);
> -			if (dma_mapping_error(dev, dma_addr))
> -				return -EFAULT;
> -
> -			pagemap_addr[i] =
> -				drm_pagemap_addr_encode(dma_addr,
> -
> 							DRM_INTERCONNECT_SYSTEM,
> -							order, dir);
> +			num_peer_pages += NR_PAGES(order);
>  		}
>  
> +		addr = dpagemap->ops->device_map(dpagemap, dev,
> page, order, dir);
> +		if (dma_mapping_error(dev, addr.addr))
> +			return -EFAULT;
> +
> +		pagemap_addr[i] = addr;
> +
>  next:
>  		i += NR_PAGES(order);
>  	}
> @@ -287,6 +280,59 @@ static int drm_pagemap_migrate_map_pages(struct
> device *dev,
>  	return 0;
>  }
>  
> +/**
> + * drm_pagemap_migrate_map_system_pages() - Map system migration
> pages for GPU SVM migration
> + * @dev: The device performing the migration.
> + * @pagemap_addr: Array to store DMA information corresponding to
> mapped pages.
> + * @migrate_pfn: Array of page frame numbers of system pages or peer
> pages to map.

system pages or device coherent pages? "Peer" pages would typically be
device-private pages with the same owner.

> + * @npages: Number of system pages or peer pages to map.

Same here.

> + * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
> + *
> + * This function maps pages of memory for migration usage in GPU
> SVM. It
> + * iterates over each page frame number provided in @migrate_pfn,
> maps the
> + * corresponding page, and stores the DMA address in the provided
> @dma_addr
> + * array.
> + *
> + * Returns: 0 on success, -EFAULT if an error occurs during mapping.
> + */
> +static int
> +drm_pagemap_migrate_map_system_pages(struct device *dev,
> +				     struct drm_pagemap_addr
> *pagemap_addr,
> +				     unsigned long *migrate_pfn,
> +				     unsigned long npages,
> +				     enum dma_data_direction dir)
> +{
> +	unsigned long i;
> +
> +	for (i = 0; i < npages;) {
> +		struct page *page =
> migrate_pfn_to_page(migrate_pfn[i]);
> +		dma_addr_t dma_addr;
> +		struct folio *folio;
> +		unsigned int order = 0;
> +
> +		if (!page)
> +			goto next;
> +
> +		WARN_ON_ONCE(is_device_private_page(page));
> +		folio = page_folio(page);
> +		order = folio_order(folio);
> +
> +		dma_addr = dma_map_page(dev, page, 0,
> page_size(page), dir);
> +		if (dma_mapping_error(dev, dma_addr))
> +			return -EFAULT;
> +
> +		pagemap_addr[i] =
> +			drm_pagemap_addr_encode(dma_addr,
> +						DRM_INTERCONNECT_SYS
> TEM,
> +						order, dir);
> +
> +next:
> +		i += NR_PAGES(order);
> +	}
> +
> +	return 0;
> +}
> +
>  /**
>   * drm_pagemap_migrate_unmap_pages() - Unmap pages previously mapped
> for GPU SVM migration
>   * @dev: The device for which the pages were mapped
> @@ -347,9 +393,11 @@ drm_pagemap_migrate_remote_to_local(struct
> drm_pagemap_devmem *devmem,
>  				    const struct
> drm_pagemap_migrate_details *mdetails)
>  
>  {
> -	int err = drm_pagemap_migrate_map_pages(remote_device,
> remote_dpagemap,
> -						pagemap_addr,
> local_pfns,
> -						npages,
> DMA_FROM_DEVICE, mdetails);
> +	int err =
> drm_pagemap_migrate_map_device_pages(remote_device,
> +						      
> remote_dpagemap,
> +						       pagemap_addr,
> local_pfns,
> +						       npages,
> DMA_FROM_DEVICE,
> +						       mdetails);
>  
>  	if (err)
>  		goto out;
> @@ -368,12 +416,11 @@ drm_pagemap_migrate_sys_to_dev(struct
> drm_pagemap_devmem *devmem,
>  			       struct page *local_pages[],
>  			       struct drm_pagemap_addr
> pagemap_addr[],
>  			       unsigned long npages,
> -			       const struct drm_pagemap_devmem_ops
> *ops,
> -			       const struct
> drm_pagemap_migrate_details *mdetails)
> +			       const struct drm_pagemap_devmem_ops
> *ops)
>  {
> -	int err = drm_pagemap_migrate_map_pages(devmem->dev, devmem-
> >dpagemap,
> -						pagemap_addr,
> sys_pfns, npages,
> -						DMA_TO_DEVICE,
> mdetails);
> +	int err = drm_pagemap_migrate_map_system_pages(devmem->dev,
> +						       pagemap_addr,
> sys_pfns,
> +						       npages,
> DMA_TO_DEVICE);


Unfortunately it's a bit more complicated than this. If the destination
gpu migrates, the range to migrate could be a mix of system pages,
device coherent pages and also device private pages, and previously
drm_pagemap_migrate_map_pages() took care of that and did the correct
thing on a per-page basis. 

You can exercise this by setting mdetails::source_peer_migrates to
false on xe. That typically "works" but might generate some errors in
the atomic multi-device tests AFAICT because reading from the BAR does
not flush the L2 caches on BMG. But should be sufficient to exercise
this path.

/Thomas