diff mbox series

[066/192] mm: pagewalk: fix walk for hugepage tables

Message ID 20210629023643.2S5kiR5Oc%akpm@linux-foundation.org (mailing list archive)
State New
Headers show
Series [001/192] mm/gup: fix try_grab_compound_head() race with split_huge_page() | expand

Commit Message

Andrew Morton June 29, 2021, 2:36 a.m. UTC 
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Subject: mm: pagewalk: fix walk for hugepage tables

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.

Link: https://lkml.kernel.org/r/38d04410700c8d02f28ba37e020b62c55d6f3d2c.1624597695.git.christophe.leroy@csgroup.eu
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Steven Price <steven.price@arm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Daniel Axtens <dja@axtens.net>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/pagewalk.c |   58 +++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 5 deletions(-)
diff mbox series

Patch

--- a/mm/pagewalk.c~mm-pagewalk-fix-walk-for-hugepage-tables
+++ a/mm/pagewalk.c
@@ -58,6 +58,45 @@  static int walk_pte_range(pmd_t *pmd, un
 	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 @@  again:
 				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, un
 		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, un
 			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
 			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;