mm: soft-dirty bits for user memory changes tracking

The soft-dirty is a bit on a PTE which helps to track which pages a task
writes to.  In order to do this tracking one should

  1. Clear soft-dirty bits from PTEs ("echo 4 > /proc/PID/clear_refs)
  2. Wait some time.
  3. Read soft-dirty bits (55'th in /proc/PID/pagemap2 entries)

To do this tracking, the writable bit is cleared from PTEs when the
soft-dirty bit is.  Thus, after this, when the task tries to modify a
page at some virtual address the #PF occurs and the kernel sets the
soft-dirty bit on the respective PTE.

Note, that although all the task's address space is marked as r/o after
the soft-dirty bits clear, the #PF-s that occur after that are processed
fast.  This is so, since the pages are still mapped to physical memory,
and thus all the kernel does is finds this fact out and puts back
writable, dirty and soft-dirty bits on the PTE.

Another thing to note, is that when mremap moves PTEs they are marked
with soft-dirty as well, since from the user perspective mremap modifies
the virtual memory at mremap's new address.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 38 insertions, 2 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index a4429bcd609e..8d2ae24b9f4a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -365,6 +365,9 @@ config HAVE_IRQ_TIME_ACCOUNTING
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
         bool
 
+config HAVE_ARCH_SOFT_DIRTY
+        bool
+
 config HAVE_MOD_ARCH_SPECIFIC
         bool
         help
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b094816a7e0f..10764a3d62cc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -102,6 +102,7 @@ config X86
         select HAVE_ARCH_SECCOMP_FILTER
         select BUILDTIME_EXTABLE_SORT
         select GENERIC_CMOS_UPDATE
+        select HAVE_ARCH_SOFT_DIRTY
         select CLOCKSOURCE_WATCHDOG
         select GENERIC_CLOCKEVENTS
         select ARCH_CLOCKSOURCE_DATA if X86_64
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5b0818bc8963..7dc305a46058 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -207,7 +207,7 @@ static inline pte_t pte_mkexec(pte_t pte)
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-        return pte_set_flags(pte, _PAGE_DIRTY);
+        return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
@@ -271,7 +271,7 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
 
 static inline pmd_t pmd_mkdirty(pmd_t pmd)
 {
-        return pmd_set_flags(pmd, _PAGE_DIRTY);
+        return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
 }
 
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
@@ -294,6 +294,26 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
         return pmd_clear_flags(pmd, _PAGE_PRESENT);
 }
 
+static inline int pte_soft_dirty(pte_t pte)
+{
+        return pte_flags(pte) & _PAGE_SOFT_DIRTY;
+}
+
+static inline int pmd_soft_dirty(pmd_t pmd)
+{
+        return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
+}
+
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+        return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
+{
+        return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
+}
+
 /*
  * Mask out unsupported bits in a present pgprot.  Non-present pgprots
  * can use those bits for other purposes, so leave them be.
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index e6423002c10b..c98ac63aae48 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -55,6 +55,18 @@
 #define _PAGE_HIDDEN    (_AT(pteval_t, 0))
 #endif
 
+/*
+ * The same hidden bit is used by kmemcheck, but since kmemcheck
+ * works on kernel pages while soft-dirty engine on user space,
+ * they do not conflict with each other.
+ */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
+#else
+#define _PAGE_SOFT_DIRTY        (_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX        (_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #else