Merge v6.18.45linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 21 insertions, 15 deletions

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2d19d6a9b034..fdce9ad67aad 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -678,6 +678,8 @@ int walk_kernel_page_table_range_lockless(unsigned long start, unsigned long end
  * will also not lock the PTEs for the pte_entry() callback.
  *
  * This is for debugging purposes ONLY.
+ *
+ * The mmap write lock must be held.
  */
 int walk_page_range_debug(struct mm_struct *mm, unsigned long start,
 			  unsigned long end, const struct mm_walk_ops *ops,
@@ -691,24 +693,28 @@ int walk_page_range_debug(struct mm_struct *mm, unsigned long start,
 		.no_vma		= true
 	};
 
-	/* For convenience, we allow traversal of kernel mappings. */
-	if (mm == &init_mm)
-		return walk_kernel_page_table_range(start, end, ops,
-						    pgd, private);
-	if (start >= end || !walk.mm)
-		return -EINVAL;
-	if (!check_ops_valid(ops))
-		return -EINVAL;
-
 	/*
-	 * The mmap lock protects the page walker from changes to the page
-	 * tables during the walk.  However a read lock is insufficient to
-	 * protect those areas which don't have a VMA as munmap() detaches
-	 * the VMAs before downgrading to a read lock and actually tearing
-	 * down PTEs/page tables. In which case, the mmap write lock should
-	 * be held.
+	 * When walking userland page tables, an mmap write lock must be held to
+	 * account for munmap() downgrading to an mmap read lock when tearing
+	 * down page tables.
+	 *
+	 * When walking kernel page tables, an mmap write lock must also be held
+	 * to account for page table freeing on vmap huge page mapping.
 	 */
 	mmap_assert_write_locked(mm);
+	/*
+	 * x86, arm64 ptdump allow walks of efi mm's and x86 ptdump allows walks
+	 * of arbitrary mm's.
+	 *
+	 * However, they both must also hold the init_mm lock to account for
+	 * concurrent kernel page table freeing.
+	 */
+	mmap_assert_write_locked(&init_mm);
+
+	if (start >= end)
+		return -EINVAL;
+	if (!check_ops_valid(ops))
+		return -EINVAL;
 
 	return walk_pgd_range(start, end, &walk);
 }