[PATCH] drm/shmem_helper: Make sure PMD entries get the writeable upgrade

[PATCH] drm/shmem_helper: Make sure PMD entries get the writeable upgrade

[Boris Brezillon]

Unlike PTEs which are automatically upgraded to writeable entries if
.pfn_mkwrite() returns 0, the PMD upgrades go through .huge_fault(),
and we currently pretend to have handled the make-writeable request
even though we only ever map things read-only. Make sure we pass the
proper "write" info to vmf_insert_pfn_pmd() in that case.

This also means we have to record the mkwrite event in the .huge_fault()
path now. Move the dirty tracking logic to a
drm_gem_shmem_record_mkwrite() helper so it can also be called from
drm_gem_shmem_pfn_mkwrite().

Note that this wasn't a problem before commit 28e3918179aa
("drm/gem-shmem: Track folio accessed/dirty status in mmap"), because
the pgprot were not lowered to read-only before this commit (see the
vma_wants_writenotify() in vma_set_page_prot()).

Fixes: 28e3918179aa ("drm/gem-shmem: Track folio accessed/dirty status in mmap")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Biju Das <biju.das.jz@bp.renesas.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
---

This patch is based on drm-tip [2], because that's the only branch
that has both [1] and the dirty tracking changes that live in
drm-misc-next.

Also added the THP maintainers in Cc, so I can hopefully get some
feedback on the fix. For instance, I'm still unsure
drm_gem_shmem_pfn_mkwrite() is race-free (do we need some locking
there? should we call folio_mark_dirty_lock()? should we call the
fault handler directly from there and have all the dirty tracking
in this .[huge_]fault path?).

[1]https://yhbt.net/lore/dri-devel/20260319015224.46896-1-pedrodemargomes@gmail.com/
[2]https://gitlab.freedesktop.org/drm/tip
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 46 ++++++++++++++++++--------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 2062ca607833..545933c7f712 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -554,6 +554,21 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
 }
 EXPORT_SYMBOL_GPL(drm_gem_shmem_dumb_create);
 
+static void drm_gem_shmem_record_mkwrite(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct drm_gem_object *obj = vma->vm_private_data;
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+	loff_t num_pages = obj->size >> PAGE_SHIFT;
+	pgoff_t page_offset = vmf->pgoff - vma->vm_pgoff; /* page offset within VMA */
+
+	if (drm_WARN_ON(obj->dev, !shmem->pages || page_offset >= num_pages))
+		return;
+
+	file_update_time(vma->vm_file);
+	folio_mark_dirty(page_folio(shmem->pages[page_offset]));
+}
+
 static vm_fault_t try_insert_pfn(struct vm_fault *vmf, unsigned int order,
 				 unsigned long pfn)
 {
@@ -566,8 +581,23 @@ static vm_fault_t try_insert_pfn(struct vm_fault *vmf, unsigned int order,
 
 		if (aligned &&
 		    folio_test_pmd_mappable(page_folio(pfn_to_page(pfn)))) {
+			vm_fault_t ret;
+
 			pfn &= PMD_MASK >> PAGE_SHIFT;
-			return vmf_insert_pfn_pmd(vmf, pfn, false);
+
+			/* Unlike PTEs which are automatically upgraded to
+			 * writeable entries, the PMD upgrades go through
+			 * .huge_fault(). Make sure we pass the "write" info
+			 * along in that case.
+			 * This also means we have to record the write fault
+			 * here, instead of in .pfn_mkwrite().
+			 */
+			ret = vmf_insert_pfn_pmd(vmf, pfn,
+						 vmf->flags & FAULT_FLAG_WRITE);
+			if (ret == VM_FAULT_NOPAGE && (vmf->flags & FAULT_FLAG_WRITE))
+				drm_gem_shmem_record_mkwrite(vmf);
+
+			return ret;
 		}
 #endif
 	}
@@ -655,19 +685,7 @@ static void drm_gem_shmem_vm_close(struct vm_area_struct *vma)
 
 static vm_fault_t drm_gem_shmem_pfn_mkwrite(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	struct drm_gem_object *obj = vma->vm_private_data;
-	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-	loff_t num_pages = obj->size >> PAGE_SHIFT;
-	pgoff_t page_offset = vmf->pgoff - vma->vm_pgoff; /* page offset within VMA */
-
-	if (drm_WARN_ON(obj->dev, !shmem->pages || page_offset >= num_pages))
-		return VM_FAULT_SIGBUS;
-
-	file_update_time(vma->vm_file);
-
-	folio_mark_dirty(page_folio(shmem->pages[page_offset]));
-
+	drm_gem_shmem_record_mkwrite(vmf);
 	return 0;
 }
 
-- 
2.53.0

Re: [PATCH] drm/shmem_helper: Make sure PMD entries get the writeable upgrade

[Tommaso Merciai]

Hi Boris,
Thanks for your patch.

On Fri, Mar 20, 2026 at 04:19:13PM +0100, Boris Brezillon wrote:
> Unlike PTEs which are automatically upgraded to writeable entries if
> .pfn_mkwrite() returns 0, the PMD upgrades go through .huge_fault(),
> and we currently pretend to have handled the make-writeable request
> even though we only ever map things read-only. Make sure we pass the
> proper "write" info to vmf_insert_pfn_pmd() in that case.
> 
> This also means we have to record the mkwrite event in the .huge_fault()
> path now. Move the dirty tracking logic to a
> drm_gem_shmem_record_mkwrite() helper so it can also be called from
> drm_gem_shmem_pfn_mkwrite().
> 
> Note that this wasn't a problem before commit 28e3918179aa
> ("drm/gem-shmem: Track folio accessed/dirty status in mmap"), because
> the pgprot were not lowered to read-only before this commit (see the
> vma_wants_writenotify() in vma_set_page_prot()).
> 
> Fixes: 28e3918179aa ("drm/gem-shmem: Track folio accessed/dirty status in mmap")
> Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
> Cc: Biju Das <biju.das.jz@bp.renesas.com>
> Cc: Thomas Zimmermann <tzimmermann@suse.de>
> Cc: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
> ---
> 
> This patch is based on drm-tip [2], because that's the only branch
> that has both [1] and the dirty tracking changes that live in
> drm-misc-next.

Tested on RZ/G3E, this fix the issue on my side.
Thanks for your work.

Tested-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>

Kind Regards,
Tommaso

> 
> Also added the THP maintainers in Cc, so I can hopefully get some
> feedback on the fix. For instance, I'm still unsure
> drm_gem_shmem_pfn_mkwrite() is race-free (do we need some locking
> there? should we call folio_mark_dirty_lock()? should we call the
> fault handler directly from there and have all the dirty tracking
> in this .[huge_]fault path?).
> 
> [1]https://yhbt.net/lore/dri-devel/20260319015224.46896-1-pedrodemargomes@gmail.com/
> [2]https://gitlab.freedesktop.org/drm/tip
> ---
>  drivers/gpu/drm/drm_gem_shmem_helper.c | 46 ++++++++++++++++++--------
>  1 file changed, 32 insertions(+), 14 deletions(-)
> 
> diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
> index 2062ca607833..545933c7f712 100644
> --- a/drivers/gpu/drm/drm_gem_shmem_helper.c
> +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
> @@ -554,6 +554,21 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
>  }
>  EXPORT_SYMBOL_GPL(drm_gem_shmem_dumb_create);
>  
> +static void drm_gem_shmem_record_mkwrite(struct vm_fault *vmf)
> +{
> +	struct vm_area_struct *vma = vmf->vma;
> +	struct drm_gem_object *obj = vma->vm_private_data;
> +	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
> +	loff_t num_pages = obj->size >> PAGE_SHIFT;
> +	pgoff_t page_offset = vmf->pgoff - vma->vm_pgoff; /* page offset within VMA */
> +
> +	if (drm_WARN_ON(obj->dev, !shmem->pages || page_offset >= num_pages))
> +		return;
> +
> +	file_update_time(vma->vm_file);
> +	folio_mark_dirty(page_folio(shmem->pages[page_offset]));
> +}
> +
>  static vm_fault_t try_insert_pfn(struct vm_fault *vmf, unsigned int order,
>  				 unsigned long pfn)
>  {
> @@ -566,8 +581,23 @@ static vm_fault_t try_insert_pfn(struct vm_fault *vmf, unsigned int order,
>  
>  		if (aligned &&
>  		    folio_test_pmd_mappable(page_folio(pfn_to_page(pfn)))) {
> +			vm_fault_t ret;
> +
>  			pfn &= PMD_MASK >> PAGE_SHIFT;
> -			return vmf_insert_pfn_pmd(vmf, pfn, false);
> +
> +			/* Unlike PTEs which are automatically upgraded to
> +			 * writeable entries, the PMD upgrades go through
> +			 * .huge_fault(). Make sure we pass the "write" info
> +			 * along in that case.
> +			 * This also means we have to record the write fault
> +			 * here, instead of in .pfn_mkwrite().
> +			 */
> +			ret = vmf_insert_pfn_pmd(vmf, pfn,
> +						 vmf->flags & FAULT_FLAG_WRITE);
> +			if (ret == VM_FAULT_NOPAGE && (vmf->flags & FAULT_FLAG_WRITE))
> +				drm_gem_shmem_record_mkwrite(vmf);
> +
> +			return ret;
>  		}
>  #endif
>  	}
> @@ -655,19 +685,7 @@ static void drm_gem_shmem_vm_close(struct vm_area_struct *vma)
>  
>  static vm_fault_t drm_gem_shmem_pfn_mkwrite(struct vm_fault *vmf)
>  {
> -	struct vm_area_struct *vma = vmf->vma;
> -	struct drm_gem_object *obj = vma->vm_private_data;
> -	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
> -	loff_t num_pages = obj->size >> PAGE_SHIFT;
> -	pgoff_t page_offset = vmf->pgoff - vma->vm_pgoff; /* page offset within VMA */
> -
> -	if (drm_WARN_ON(obj->dev, !shmem->pages || page_offset >= num_pages))
> -		return VM_FAULT_SIGBUS;
> -
> -	file_update_time(vma->vm_file);
> -
> -	folio_mark_dirty(page_folio(shmem->pages[page_offset]));
> -
> +	drm_gem_shmem_record_mkwrite(vmf);
>  	return 0;
>  }
>  
> -- 
> 2.53.0
>