mm: pagewalk: don't lock PTEs for walk_page_range_novma()

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 by splitting out the inner loop to a
separate function and add a comment explaining the difference to
walk_page_range_novma().

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Steven Price <[email protected]>
Cc: Albert Ou <[email protected]>
Cc: Alexandre Ghiti <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: James Hogan <[email protected]>
Cc: James Morse <[email protected]>
Cc: Jerome Glisse <[email protected]>
Cc: "Liang, Kan" <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Paul Burton <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Paul Walmsley <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ralf Baechle <[email protected]>
Cc: Russell King <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vasily Gorbik <[email protected]>
Cc: Vineet Gupta <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Zong Li <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 28 insertions, 7 deletions

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index d5773465f6da..4b5ee92ba079 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -4,15 +4,12 @@
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
 
-static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			  struct mm_walk *walk)
+static int walk_pte_range_inner(pte_t *pte, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
-	pte_t *pte;
-	int err = 0;
 	const struct mm_walk_ops *ops = walk->ops;
-	spinlock_t *ptl;
+	int err = 0;
 
-	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (;;) {
 		err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
@@ -22,8 +19,26 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			break;
 		pte++;
 	}
+	return err;
+}
+
+static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pte_t *pte;
+	int err = 0;
+	spinlock_t *ptl;
+
+	if (walk->no_vma) {
+		pte = pte_offset_map(pmd, addr);
+		err = walk_pte_range_inner(pte, addr, end, walk);
+		pte_unmap(pte);
+	} else {
+		pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		err = walk_pte_range_inner(pte, addr, end, walk);
+		pte_unmap_unlock(pte, ptl);
+	}
 
-	pte_unmap_unlock(pte, ptl);
 	return err;
 }
 
@@ -394,6 +409,12 @@ 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)