diff mbox series

[v15,12/23] mm: pagewalk: Allow walking without vma

Message ID 20191101140942.51554-13-steven.price@arm.com
State New, archived
Headers show
Series Generic page walk and ptdump | expand

Commit Message

Steven Price Nov. 1, 2019, 2:09 p.m. UTC
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.

Signed-off-by: Steven Price <steven.price@arm.com>
---
 include/linux/pagewalk.h |  5 +++++
 mm/pagewalk.c            | 44 ++++++++++++++++++++++++++++++++--------
 2 files changed, 41 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 12004b097eae..ed2bb399fac2 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -53,6 +53,7 @@  struct mm_walk_ops {
  * @ops:	operation to call during the walk
  * @mm:		mm_struct representing the target process of page table walk
  * @vma:	vma currently walked (NULL if walking outside vmas)
+ * @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)
@@ -61,12 +62,16 @@  struct mm_walk {
 	const struct mm_walk_ops *ops;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
+	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);
 
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index fc4d98a3a5a0..626e7fdb0508 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -38,7 +38,7 @@  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)
@@ -61,9 +61,14 @@  static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 		if (!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;
+		} else if (pmd_leaf(*pmd)) {
+			continue;
+		}
+
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
@@ -84,7 +89,7 @@  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)
@@ -98,9 +103,13 @@  static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 				break;
 		}
 
-		split_huge_pud(walk->vma, pud, addr);
-		if (pud_none(*pud))
-			goto again;
+		if (walk->vma) {
+			split_huge_pud(walk->vma, pud, addr);
+			if (pud_none(*pud))
+				goto again;
+		} else if (pud_leaf(*pud)) {
+			continue;
+		}
 
 		if (ops->pmd_entry || ops->pte_entry)
 			err = walk_pmd_range(pud, addr, next, walk);
@@ -358,6 +367,25 @@  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)
 {