[PATCH v3] mm: pagewalk: Fix walk for hugepage tables

[Christophe Leroy]

Pagewalk ignores hugepd entries and walk down the tables
as if it was traditionnal entries, leading to crazy result.

Add walk_hugepd_range() and use it to walk hugepage tables.

Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Reviewed-by: Steven Price <steven.price@xxxxxxx>
---
v3:
- Rebased on next-20210624 (no change since v2)
- Added Steven's Reviewed-by
- Sent as standalone for merge via mm

v2:
- Add a guard for NULL ops->pte_entry
- Take mm->page_table_lock when walking hugepage table, as suggested by follow_huge_pd()
---
 mm/pagewalk.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 5 deletions(-)

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index e81640d9f177..9b3db11a4d1d 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -58,6 +58,45 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	return err;
 }
 
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
+			     unsigned long end, struct mm_walk *walk, int pdshift)
+{
+	int err = 0;
+	const struct mm_walk_ops *ops = walk->ops;
+	int shift = hugepd_shift(*phpd);
+	int page_size = 1 << shift;
+
+	if (!ops->pte_entry)
+		return 0;
+
+	if (addr & (page_size - 1))
+		return 0;
+
+	for (;;) {
+		pte_t *pte;
+
+		spin_lock(&walk->mm->page_table_lock);
+		pte = hugepte_offset(*phpd, addr, pdshift);
+		err = ops->pte_entry(pte, addr, addr + page_size, walk);
+		spin_unlock(&walk->mm->page_table_lock);
+
+		if (err)
+			break;
+		if (addr >= end - page_size)
+			break;
+		addr += page_size;
+	}
+	return err;
+}
+#else
+static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr,
+			     unsigned long end, struct mm_walk *walk, int pdshift)
+{
+	return 0;
+}
+#endif
+
 static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
@@ -108,7 +147,10 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 				goto again;
 		}
 
-		err = walk_pte_range(pmd, addr, next, walk);
+		if (is_hugepd(__hugepd(pmd_val(*pmd))))
+			err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT);
+		else
+			err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
 	} while (pmd++, addr = next, addr != end);
@@ -157,7 +199,10 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 		if (pud_none(*pud))
 			goto again;
 
-		err = walk_pmd_range(pud, addr, next, walk);
+		if (is_hugepd(__hugepd(pud_val(*pud))))
+			err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT);
+		else
+			err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
 	} while (pud++, addr = next, addr != end);
@@ -189,7 +234,9 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 			if (err)
 				break;
 		}
-		if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
+		if (is_hugepd(__hugepd(p4d_val(*p4d))))
+			err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT);
+		else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
 			err = walk_pud_range(p4d, addr, next, walk);
 		if (err)
 			break;
@@ -224,8 +271,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 			if (err)
 				break;
 		}
-		if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
-		    ops->pte_entry)
+		if (is_hugepd(__hugepd(pgd_val(*pgd))))
+			err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT);
+		else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry)
 			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;
-- 
2.25.0