mm: page table check

Check user page table entries at the time they are added and removed.

Allows to synchronously catch memory corruption issues related to double
mapping.

When a pte for an anonymous page is added into page table, we verify
that this pte does not already point to a file backed page, and vice
versa if this is a file backed page that is being added we verify that
this page does not have an anonymous mapping

We also enforce that read-only sharing for anonymous pages is allowed
(i.e.  cow after fork).  All other sharing must be for file pages.

Page table check allows to protect and debug cases where "struct page"
metadata became corrupted for some reason.  For example, when refcnt or
mapcount become invalid.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Pasha Tatashin <[email protected]>
Cc: Aneesh Kumar K.V <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Greg Thelen <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jiri Slaby <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Masahiro Yamada <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Muchun Song <[email protected]>
Cc: Paul Turner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Sami Tolvanen <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 147 insertions, 0 deletions

diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h
new file mode 100644
index 000000000000..38cace1da7b6
--- /dev/null
+++ b/include/linux/page_table_check.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2021, Google LLC.
+ * Pasha Tatashin <[email protected]>
+ */
+#ifndef __LINUX_PAGE_TABLE_CHECK_H
+#define __LINUX_PAGE_TABLE_CHECK_H
+
+#ifdef CONFIG_PAGE_TABLE_CHECK
+#include <linux/jump_label.h>
+
+extern struct static_key_true page_table_check_disabled;
+extern struct page_ext_operations page_table_check_ops;
+
+void __page_table_check_zero(struct page *page, unsigned int order);
+void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr,
+				  pte_t pte);
+void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr,
+				  pmd_t pmd);
+void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr,
+				  pud_t pud);
+void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte);
+void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr,
+				pmd_t *pmdp, pmd_t pmd);
+void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
+				pud_t *pudp, pud_t pud);
+
+static inline void page_table_check_alloc(struct page *page, unsigned int order)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_zero(page, order);
+}
+
+static inline void page_table_check_free(struct page *page, unsigned int order)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_zero(page, order);
+}
+
+static inline void page_table_check_pte_clear(struct mm_struct *mm,
+					      unsigned long addr, pte_t pte)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pte_clear(mm, addr, pte);
+}
+
+static inline void page_table_check_pmd_clear(struct mm_struct *mm,
+					      unsigned long addr, pmd_t pmd)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pmd_clear(mm, addr, pmd);
+}
+
+static inline void page_table_check_pud_clear(struct mm_struct *mm,
+					      unsigned long addr, pud_t pud)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pud_clear(mm, addr, pud);
+}
+
+static inline void page_table_check_pte_set(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    pte_t pte)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pte_set(mm, addr, ptep, pte);
+}
+
+static inline void page_table_check_pmd_set(struct mm_struct *mm,
+					    unsigned long addr, pmd_t *pmdp,
+					    pmd_t pmd)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pmd_set(mm, addr, pmdp, pmd);
+}
+
+static inline void page_table_check_pud_set(struct mm_struct *mm,
+					    unsigned long addr, pud_t *pudp,
+					    pud_t pud)
+{
+	if (static_branch_likely(&page_table_check_disabled))
+		return;
+
+	__page_table_check_pud_set(mm, addr, pudp, pud);
+}
+
+#else
+
+static inline void page_table_check_alloc(struct page *page, unsigned int order)
+{
+}
+
+static inline void page_table_check_free(struct page *page, unsigned int order)
+{
+}
+
+static inline void page_table_check_pte_clear(struct mm_struct *mm,
+					      unsigned long addr, pte_t pte)
+{
+}
+
+static inline void page_table_check_pmd_clear(struct mm_struct *mm,
+					      unsigned long addr, pmd_t pmd)
+{
+}
+
+static inline void page_table_check_pud_clear(struct mm_struct *mm,
+					      unsigned long addr, pud_t pud)
+{
+}
+
+static inline void page_table_check_pte_set(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    pte_t pte)
+{
+}
+
+static inline void page_table_check_pmd_set(struct mm_struct *mm,
+					    unsigned long addr, pmd_t *pmdp,
+					    pmd_t pmd)
+{
+}
+
+static inline void page_table_check_pud_set(struct mm_struct *mm,
+					    unsigned long addr, pud_t *pudp,
+					    pud_t pud)
+{
+}
+
+#endif /* CONFIG_PAGE_TABLE_CHECK */
+#endif /* __LINUX_PAGE_TABLE_CHECK_H */