[PATCH v16 15/25] mm: pagewalk: Add test_p?d callbacks

[Steven Price <steven.price@xxxxxxx>]

It is useful to be able to skip parts of the page table tree even when
walking without VMAs. Add test_p?d callbacks similar to test_walk but
which are called just before a table at that level is walked. If the
callback returns non-zero then the entire table is skipped.

Tested-by: Zong Li <zong.li@xxxxxxxxxx>
Signed-off-by: Steven Price <steven.price@xxxxxxx>
---
 include/linux/pagewalk.h | 11 +++++++++++
 mm/pagewalk.c            | 24 ++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 2c9725bdcf1f..84ac77620bfc 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -24,6 +24,11 @@ struct mm_walk;
  *			"do page table walk over the current vma", returning
  *			a negative value means "abort current page table walk
  *			right now" and returning 1 means "skip the current vma"
+ * @test_pmd:		similar to test_walk(), but called for every pmd.
+ * @test_pud:		similar to test_walk(), but called for every pud.
+ * @test_p4d:		similar to test_walk(), but called for every p4d.
+ *			Returning 0 means walk this part of the page tables,
+ *			returning 1 means to skip this range.
  * @pre_vma:            if set, called before starting walk on a non-null vma.
  * @post_vma:           if set, called after a walk on a non-null vma, provided
  *                      that @pre_vma and the vma walk succeeded.
@@ -49,6 +54,12 @@ struct mm_walk_ops {
 			     struct mm_walk *walk);
 	int (*test_walk)(unsigned long addr, unsigned long next,
 			struct mm_walk *walk);
+	int (*test_pmd)(unsigned long addr, unsigned long next,
+			pmd_t *pmd_start, struct mm_walk *walk);
+	int (*test_pud)(unsigned long addr, unsigned long next,
+			pud_t *pud_start, struct mm_walk *walk);
+	int (*test_p4d)(unsigned long addr, unsigned long next,
+			p4d_t *p4d_start, struct mm_walk *walk);
 	int (*pre_vma)(unsigned long start, unsigned long end,
 		       struct mm_walk *walk);
 	void (*post_vma)(struct mm_walk *walk);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 88104ab00a97..83ab6c1ebf9b 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -38,6 +38,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
+	if (ops->test_pmd) {
+		err = ops->test_pmd(addr, end, pmd_offset(pud, 0UL), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	pmd = pmd_offset(pud, addr);
 	do {
 again:
@@ -89,6 +97,14 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
+	if (ops->test_pud) {
+		err = ops->test_pud(addr, end, pud_offset(p4d, 0UL), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	pud = pud_offset(p4d, addr);
 	do {
  again:
@@ -132,6 +148,14 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
+	if (ops->test_p4d) {
+		err = ops->test_p4d(addr, end, p4d_offset(pgd, 0UL), walk);
+		if (err < 0)
+			return err;
+		if (err > 0)
+			return 0;
+	}
+
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);
-- 
2.20.1