drm/pagemap, drm/xe: Manage drm_pagemap provider lifetimes

If a device holds a reference on a foregin device's drm_pagemap,
and a device unbind is executed on the foreign device,
Typically that foreign device would evict its device-private
pages and then continue its device-managed cleanup eventually
releasing its drm device and possibly allow for module unload.
However, since we're still holding a reference on a drm_pagemap,
when that reference is released and the provider module is
unloaded we'd execute out of undefined memory.

Therefore keep a reference on the provider device and module until
the last drm_pagemap reference is gone.

Note that in theory, the drm_gpusvm_helper module may be unloaded
as soon as the final module_put() of the provider driver module is
executed, so we need to add a module_exit() function that waits
for the work item executing the module_put() has completed.

v2:
- Better commit message (Matt Brost)

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> # For merging through drm-xe.
Link: https://patch.msgid.link/20251219113320.183860-7-thomas.hellstrom@linux.intel.com

1 files changed, 7 insertions, 3 deletions

diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
index 093e7199c44b..b3edcdde4454 100644
--- a/include/drm/drm_pagemap.h
+++ b/include/drm/drm_pagemap.h
@@ -10,6 +10,7 @@
 
 struct dma_fence;
 struct drm_pagemap;
+struct drm_pagemap_dev_hold;
 struct drm_pagemap_zdd;
 struct device;
 
@@ -131,14 +132,17 @@ struct drm_pagemap_ops {
  * used for device p2p handshaking.
  * @ops: The struct drm_pagemap_ops.
  * @ref: Reference count.
- * @dev: The struct drevice owning the device-private memory.
+ * @drm: The struct drm device owning the device-private memory.
  * @pagemap: Pointer to the underlying dev_pagemap.
+ * @dev_hold: Pointer to a struct drm_pagemap_dev_hold for
+ * device referencing.
  */
 struct drm_pagemap {
 	const struct drm_pagemap_ops *ops;
 	struct kref ref;
-	struct device *dev;
+	struct drm_device *drm;
 	struct dev_pagemap *pagemap;
+	struct drm_pagemap_dev_hold *dev_hold;
 };
 
 struct drm_pagemap_devmem;
@@ -213,7 +217,7 @@ struct drm_pagemap_devmem_ops {
 			   struct dma_fence *pre_migrate_fence);
 };
 
-struct drm_pagemap *drm_pagemap_create(struct device *dev,
+struct drm_pagemap *drm_pagemap_create(struct drm_device *drm,
 				       struct dev_pagemap *pagemap,
 				       const struct drm_pagemap_ops *ops);