[PATCH v16 13/25] mm: pagewalk: Don't lock PTEs for walk_page_range_novma()

[Steven Price]

walk_page_range_novma() can be used to walk page tables or the kernel or
for firmware. These page tables may contain entries that are not backed
by a struct page and so it isn't (in general) possible to take the PTE
lock for the pte_entry() callback. So update walk_pte_range() to only
take the lock when no_vma==false and add a comment explaining the
difference to walk_page_range_novma().

Signed-off-by: Steven Price <steven.price@xxxxxxx>
---
 mm/pagewalk.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index efa464cf079b..1b9a3ba24c51 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -10,9 +10,10 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	int err = 0;
 	const struct mm_walk_ops *ops = walk->ops;
-	spinlock_t *ptl;
+	spinlock_t *uninitialized_var(ptl);
 
-	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	pte = walk->no_vma ? pte_offset_map(pmd, addr) :
+			     pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (;;) {
 		err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
@@ -23,7 +24,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		pte++;
 	}
 
-	pte_unmap_unlock(pte, ptl);
+	if (!walk->no_vma)
+		spin_unlock(ptl);
+	pte_unmap(pte);
 	return err;
 }
 
@@ -383,6 +386,12 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
+/*
+ * Similar to walk_page_range() but can walk any page tables even if they are
+ * not backed by VMAs. Because 'unusual' entries may be walked this function
+ * will also not lock the PTEs for the pte_entry() callback. This is useful for
+ * walking the kernel pages tables or page tables for firmware.
+ */
 int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 			  unsigned long end, const struct mm_walk_ops *ops,
 			  void *private)
-- 
2.20.1