[v2,5/5] mm/mmu_notifier: use MMU_NOTIFY_CLEAR in remove_device_exclusive_entry()

Commit Message

David Hildenbrand Feb. 26, 2025, 1:22 p.m. UTC

Let's limit the use of MMU_NOTIFY_EXCLUSIVE to the case where we convert
a present PTE to device-exclusive. For the other case, we can simply
use MMU_NOTIFY_CLEAR, because it really is clearing the
device-exclusive entry first, to then install the present entry.

Update the documentation of MMU_NOTIFY_EXCLUSIVE, to document the single
use case more thoroughly.

If ever required, we could add a separate MMU_NOTIFY_CLEAR_EXCLUSIVE;
for now using MMU_NOTIFY_CLEAR seems to be sufficient.

Signed-off-by: David Hildenbrand <[e-mail]>
---
 include/linux/mmu_notifier.h | 8 ++++----
 mm/memory.c                  | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

Patch

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index d4e7146618262..bc2402a45741d 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -43,10 +43,10 @@  struct mmu_interval_notifier;
  * a device driver to possibly ignore the invalidation if the
  * owner field matches the driver's device private pgmap owner.
  *
- * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no
- * longer have exclusive access to the page. When sent during creation of an
- * exclusive range the owner will be initialised to the value provided by the
- * caller of make_device_exclusive(), otherwise the owner will be NULL.
+ * @MMU_NOTIFY_EXCLUSIVE: conversion of a page table entry to device-exclusive.
+ * The owner is initialized to the value provided by the caller of
+ * make_device_exclusive(), such that this caller can filter out these
+ * events.
  */
 enum mmu_notifier_event {
 	MMU_NOTIFY_UNMAP = 0,
diff --git a/mm/memory.c b/mm/memory.c
index 50a305d7efcb9..79acd2d95dcff 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4046,7 +4046,7 @@  static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
 		folio_put(folio);
 		return ret;
 	}
-	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
+	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_CLEAR, 0,
 				vma->vm_mm, vmf->address & PAGE_MASK,
 				(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
 	mmu_notifier_invalidate_range_start(&range);