[Devel] [PATCH vz8 24/42] userfaultfd: wp: add WP pagetable tracking to x86

Andrey Ryabinin aryabinin at virtuozzo.com
Thu Apr 16 13:36:02 MSK 2020


From: Andrea Arcangeli <aarcange at redhat.com>

Accurate userfaultfd WP tracking is possible by tracking exactly which
virtual memory ranges were writeprotected by userland.  We can't relay
only on the RW bit of the mapped pagetable because that information is
destroyed by fork() or KSM or swap.  If we were to relay on that, we'd
need to stay on the safe side and generate false positive wp faults for
every swapped out page.

[peterx at redhat.com: append _PAGE_UFD_WP to _PAGE_CHG_MASK]
Signed-off-by: Andrea Arcangeli <aarcange at redhat.com>
Signed-off-by: Peter Xu <peterx at redhat.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Reviewed-by: Jerome Glisse <jglisse at redhat.com>
Reviewed-by: Mike Rapoport <rppt at linux.vnet.ibm.com>
Cc: Bobby Powers <bobbypowers at gmail.com>
Cc: Brian Geffon <bgeffon at google.com>
Cc: David Hildenbrand <david at redhat.com>
Cc: Denis Plotnikov <dplotnikov at virtuozzo.com>
Cc: "Dr . David Alan Gilbert" <dgilbert at redhat.com>
Cc: Hugh Dickins <hughd at google.com>
Cc: Johannes Weiner <hannes at cmpxchg.org>
Cc: "Kirill A . Shutemov" <kirill at shutemov.name>
Cc: Martin Cracauer <cracauer at cons.org>
Cc: Marty McFadden <mcfadden8 at llnl.gov>
Cc: Maya Gokhale <gokhale2 at llnl.gov>
Cc: Mel Gorman <mgorman at suse.de>
Cc: Mike Kravetz <mike.kravetz at oracle.com>
Cc: Pavel Emelyanov <xemul at openvz.org>
Cc: Rik van Riel <riel at redhat.com>
Cc: Shaohua Li <shli at fb.com>
Link: http://lkml.kernel.org/r/20200220163112.11409-4-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>

https://jira.sw.ru/browse/PSBM-102938
(cherry picked from commit 5a281062af1d43d3f3956a6b429c2d727bc92603)
Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 arch/x86/Kconfig                     |  1 +
 arch/x86/include/asm/pgtable.h       | 52 ++++++++++++++++++++++++++++
 arch/x86/include/asm/pgtable_64.h    |  8 ++++-
 arch/x86/include/asm/pgtable_types.h | 11 +++++-
 include/asm-generic/pgtable.h        |  1 +
 include/asm-generic/pgtable_uffd.h   | 51 +++++++++++++++++++++++++++
 init/Kconfig                         |  5 +++
 7 files changed, 127 insertions(+), 2 deletions(-)
 create mode 100644 include/asm-generic/pgtable_uffd.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c3523eac2cb6..961d472d1e28 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -128,6 +128,7 @@ config X86
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
+	select HAVE_ARCH_USERFAULTFD_WP		if USERFAULTFD
 	select HAVE_ARCH_VMAP_STACK		if X86_64
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 13125aad804c..f01d8e82167b 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -23,6 +23,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/x86_init.h>
+#include <asm-generic/pgtable_uffd.h>
 
 extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
@@ -291,6 +292,23 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
 	return native_make_pte(v & ~clear);
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline int pte_uffd_wp(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_UFFD_WP;
+}
+
+static inline pte_t pte_mkuffd_wp(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_UFFD_WP);
+}
+
+static inline pte_t pte_clear_uffd_wp(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_UFFD_WP);
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
 	return pte_clear_flags(pte, _PAGE_DIRTY);
@@ -370,6 +388,23 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
 	return native_make_pmd(v & ~clear);
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline int pmd_uffd_wp(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_UFFD_WP;
+}
+
+static inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_UFFD_WP);
+}
+
+static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_UFFD_WP);
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
 	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
@@ -1262,6 +1297,23 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
 #endif
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_UFFD_WP);
+}
+
+static inline int pte_swp_uffd_wp(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_UFFD_WP;
+}
+
+static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP);
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 #define PKRU_AD_BIT 0x1
 #define PKRU_WD_BIT 0x2
 #define PKRU_BITS_PER_PKEY 2
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 20127d551ab5..4bc241199087 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -274,7 +274,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|F|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -282,9 +282,15 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  * erratum where they can be incorrectly set by hardware on
  * non-present PTEs.
  *
+ * SD Bits 1-4 are not used in non-present format and available for
+ * special use described below:
+ *
  * SD (1) in swp entry is used to store soft dirty bit, which helps us
  * remember soft dirty over page migration
  *
+ * F (2) in swp entry is used to record when a pagetable is
+ * writeprotected by userfaultfd WP support.
+ *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  *
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index a558381b016b..019a235e5238 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -32,6 +32,7 @@
 
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
+#define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
@@ -99,6 +100,14 @@
 #define _PAGE_SWP_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+#define _PAGE_UFFD_WP		(_AT(pteval_t, 1) << _PAGE_BIT_UFFD_WP)
+#define _PAGE_SWP_UFFD_WP	_PAGE_USER
+#else
+#define _PAGE_UFFD_WP		(_AT(pteval_t, 0))
+#define _PAGE_SWP_UFFD_WP	(_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
@@ -123,7 +132,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_UFFD_WP)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 592b4c0f02c7..631f099e65c1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -10,6 +10,7 @@
 #include <linux/mm_types.h>
 #include <linux/bug.h>
 #include <linux/errno.h>
+#include <asm-generic/pgtable_uffd.h>
 
 #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
 	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
new file mode 100644
index 000000000000..643d1bf559c2
--- /dev/null
+++ b/include/asm-generic/pgtable_uffd.h
@@ -0,0 +1,51 @@
+#ifndef _ASM_GENERIC_PGTABLE_UFFD_H
+#define _ASM_GENERIC_PGTABLE_UFFD_H
+
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static __always_inline int pte_uffd_wp(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline int pmd_uffd_wp(pmd_t pmd)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_mkuffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_clear_uffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_swp_mkuffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline int pte_swp_uffd_wp(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
+{
+	return pte;
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
+#endif /* _ASM_GENERIC_PGTABLE_UFFD_H */
diff --git a/init/Kconfig b/init/Kconfig
index 9560a06d735a..25eae91c2bea 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1357,6 +1357,11 @@ config ADVISE_SYSCALLS
 	  applications use these syscalls, you can disable this option to save
 	  space.
 
+config HAVE_ARCH_USERFAULTFD_WP
+	bool
+	help
+	  Arch has userfaultfd write protection support
+
 config MEMBARRIER
 	bool "Enable membarrier() system call" if EXPERT
 	default y
-- 
2.25.3



More information about the Devel mailing list