mm: pagewalk: allow walking without vma

Since 48684a65b4e3: "mm: pagewalk: fix misbehavior of walk_page_range for
vma(VM_PFNMAP)", page_table_walk() will report any kernel area as a hole,
because it lacks a vma.

This means each arch has re-implemented page table walking when needed,
for example in the per-arch ptdump walker.

Remove the requirement to have a vma in the generic code and add a new
function walk_page_range_novma() which ignores the VMAs and simply walks
the page tables.

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]>

2 files changed, 37 insertions, 8 deletions

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index aa6a0b63964e..d5d07f7a9c14 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -73,6 +73,7 @@ enum page_walk_action {
  * @mm:		mm_struct representing the target process of page table walk
  * @vma:	vma currently walked (NULL if walking outside vmas)
  * @action:	next action to perform (see enum page_walk_action)
+ * @no_vma:	walk ignoring vmas (vma will always be NULL)
  * @private:	private data for callbacks' usage
  *
  * (see the comment on walk_page_range() for more details)
@@ -82,12 +83,16 @@ struct mm_walk {
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	enum page_walk_action action;
+	bool no_vma;
 	void *private;
 };
 
 int walk_page_range(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  void *private);
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private);
 int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 690af44609e2..d5773465f6da 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -39,7 +39,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	do {
 again:
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*pmd) || !walk->vma) {
+		if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, walk);
 			if (err)
@@ -65,13 +65,16 @@ again:
 		 * Check this here so we only break down trans_huge
 		 * pages when we _need_ to
 		 */
-		if (walk->action == ACTION_CONTINUE ||
+		if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) ||
+		    walk->action == ACTION_CONTINUE ||
 		    !(ops->pte_entry))
 			continue;
 
-		split_huge_pmd(walk->vma, pmd, addr);
-		if (pmd_trans_unstable(pmd))
-			goto again;
+		if (walk->vma) {
+			split_huge_pmd(walk->vma, pmd, addr);
+			if (pmd_trans_unstable(pmd))
+				goto again;
+		}
 
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
@@ -93,7 +96,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	do {
  again:
 		next = pud_addr_end(addr, end);
-		if (pud_none(*pud) || !walk->vma) {
+		if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, walk);
 			if (err)
@@ -111,11 +114,13 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 		if (walk->action == ACTION_AGAIN)
 			goto again;
 
-		if (walk->action == ACTION_CONTINUE ||
+		if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) ||
+		    walk->action == ACTION_CONTINUE ||
 		    !(ops->pmd_entry || ops->pte_entry))
 			continue;
 
-		split_huge_pud(walk->vma, pud, addr);
+		if (walk->vma)
+			split_huge_pud(walk->vma, pud, addr);
 		if (pud_none(*pud))
 			goto again;
 
@@ -389,6 +394,25 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  void *private)
+{
+	struct mm_walk walk = {
+		.ops		= ops,
+		.mm		= mm,
+		.private	= private,
+		.no_vma		= true
+	};
+
+	if (start >= end || !walk.mm)
+		return -EINVAL;
+
+	lockdep_assert_held(&walk.mm->mmap_sem);
+
+	return __walk_page_range(start, end, &walk);
+}
+
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private)
 {