userfaultfd: wp: add WP pagetable tracking to x86

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

arch/x86/Kconfig

@@ -149,6 +149,7 @@ 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_ASM_MODVERSIONS

arch/x86/include/asm/pgtable.h

@@ -25,6 +25,7 @@
 #include <asm/x86_init.h>
 #include <asm/fpu/xstate.h>
 #include <asm/fpu/api.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);
@@ -313,6 +314,23 @@ 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);
@@ -392,6 +410,23 @@ 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);
@@ -1374,6 +1409,23 @@ 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

arch/x86/include/asm/pgtable_64.h

@@ -189,7 +189,7 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
  *
  * |     ...            | 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
@@ -197,9 +197,15 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
  * 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.
  *

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
 
@@ -100,6 +101,14 @@
 #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)
@@ -118,7 +127,8 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC |  \
+			 _PAGE_UFFD_WP)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*

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

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 */

init/Kconfig

@@ -1556,6 +1556,11 @@ 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