[PATCH 0/5] mm: Ability to monitor task memory changes (v4)

[PATCH 0/5] mm: Ability to monitor task memory changes (v4)

[Pavel Emelyanov]

This is the resend and (while the iron is hot) the request for merge of
the implementation of the soft-dirty bit concept that should help to track
changes in user memory.

This set differs from what Andrew has sent recently in a single point --
the way pagemap entries' bits are reused (patch #5, and one hunk about
Documantation/ file in patch #4). Other places hasn't changed at all.

Thanks,
Pavel

[PATCH 1/5] clear_refs: sanitize accepted commands declaration

[Pavel Emelyanov]

This is the implementation of the soft-dirty bit concept that should help
keep track of changes in user memory, which in turn is very-very required
by the checkpoint-restore project (http://criu.org).

To create a dump of an application(s) we save all the information about it
to files, and the biggest part of such dump is the contents of tasks' memory.
However, there are usage scenarios where it's not required to get _all_ the
task memory while creating a dump. For example, when doing periodical dumps,
it's only required to take full memory dump only at the first step and then
take incremental changes of memory. Another example is live migration. We
copy all the memory to the destination node without stopping all tasks, then
stop them, check for what pages has changed, dump it and the rest of the state,
then copy it to the destination node. This decreases freeze time significantly.

That said, some help from kernel to watch how processes modify the contents
of their memory is required.

The proposal is to track changes with the help of new soft-dirty bit this way:

1. First do "echo 4 > /proc/$pid/clear_refs".
   At that point kernel clears the soft dirty _and_ the writable bits from all
   ptes of process $pid. From now on every write to any page will result in #pf
   and the subsequent call to pte_mkdirty/pmd_mkdirty, which in turn will set
   the soft dirty flag.

2. Then read the /proc/$pid/pagemap and check the soft-dirty bit reported there
   (the 55'th one). If set, the respective pte was written to since last call
   to clear refs.

The soft-dirty bit is the _PAGE_BIT_HIDDEN one. Although it's used by kmemcheck,
the latter one marks kernel pages with it, while the former bit is put on user
pages so they do not conflict to each other.

This patch:

A new clear-refs type will be added in the next patch, so prepare
code for that.

[akpm@linux-foundation.org: don't assume that sizeof(enum clear_refs_types) == sizeof(int)]
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
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>
---
 fs/proc/task_mmu.c |   19 ++++++++++++-------
 1 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3e636d8..dad0809 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -688,6 +688,13 @@ const struct file_operations proc_tid_smaps_operations = {
 	.release	= seq_release_private,
 };
 
+enum clear_refs_types {
+	CLEAR_REFS_ALL = 1,
+	CLEAR_REFS_ANON,
+	CLEAR_REFS_MAPPED,
+	CLEAR_REFS_LAST,
+};
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
@@ -719,10 +726,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
-#define CLEAR_REFS_ALL 1
-#define CLEAR_REFS_ANON 2
-#define CLEAR_REFS_MAPPED 3
-
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -730,7 +733,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	char buffer[PROC_NUMBUF];
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	int type;
+	enum clear_refs_types type;
+	int itype;
 	int rv;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -738,10 +742,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		count = sizeof(buffer) - 1;
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
-	rv = kstrtoint(strstrip(buffer), 10, &type);
+	rv = kstrtoint(strstrip(buffer), 10, &itype);
 	if (rv < 0)
 		return rv;
-	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+	type = (enum clear_refs_types)itype;
+	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
 		return -EINVAL;
 	task = get_proc_task(file_inode(file));
 	if (!task)
-- 
1.7.6.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/5] clear_refs: introduce private struct for mm_walk

[Pavel Emelyanov]

In the next patch the clear-refs-type will be required in
clear_refs_pte_range funciton, so prepare the walk->private to carry this
info.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
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>
---
 fs/proc/task_mmu.c |   12 ++++++++++--
 1 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dad0809..ef6f6c6 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -695,10 +695,15 @@ enum clear_refs_types {
 	CLEAR_REFS_LAST,
 };
 
+struct clear_refs_private {
+	struct vm_area_struct *vma;
+};
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = walk->private;
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = cp->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
@@ -753,13 +758,16 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		return -ESRCH;
 	mm = get_task_mm(task);
 	if (mm) {
+		struct clear_refs_private cp = {
+		};
 		struct mm_walk clear_refs_walk = {
 			.pmd_entry = clear_refs_pte_range,
 			.mm = mm,
+			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			clear_refs_walk.private = vma;
+			cp.vma = vma;
 			if (is_vm_hugetlb_page(vma))
 				continue;
 			/*
-- 
1.7.6.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 3/5] pagemap: introduce pagemap_entry_t without pmshift bits

[Pavel Emelyanov]

These bits are always constant (== PAGE_SHIFT) and just occupy space in
the entry.  Moreover, in next patch we will need to report one more bit in
the pagemap, but all bits are already busy on it.

That said, describe the pagemap entry that has 6 more free zero bits.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
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>
---
 fs/proc/task_mmu.c |   40 ++++++++++++++++++++++------------------
 1 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ef6f6c6..39d6412 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -807,6 +807,7 @@ typedef struct {
 struct pagemapread {
 	int pos, len;
 	pagemap_entry_t *buffer;
+	bool v2;
 };
 
 #define PAGEMAP_WALK_SIZE	(PMD_SIZE)
@@ -820,14 +821,16 @@ struct pagemapread {
 #define PM_PSHIFT_BITS      6
 #define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
 #define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define __PM_PSHIFT(x)      (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
 #define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
 #define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+/* in "new" pagemap pshift bits are occupied with more status bits */
+#define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
 
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
 #define PM_FILE             PM_STATUS(1LL)
-#define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
+#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
 #define PM_END_OF_BUFFER    1
 
 static inline pagemap_entry_t make_pme(u64 val)
@@ -850,7 +853,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		err = add_to_pagemap(addr, &pme, pm);
@@ -860,7 +863,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	return err;
 }
 
-static void pte_to_pagemap_entry(pagemap_entry_t *pme,
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
 	u64 frame, flags;
@@ -879,18 +882,18 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme,
 		if (is_migration_entry(entry))
 			page = migration_entry_to_page(entry);
 	} else {
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 		return;
 	}
 
 	if (page && !PageAnon(page))
 		flags |= PM_FILE;
 
-	*pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags);
+	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, 0) | flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 					pmd_t pmd, int offset)
 {
 	/*
@@ -900,12 +903,12 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
 	 */
 	if (pmd_present(pmd))
 		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+				| PM_STATUS2(pm->v2, 0) | PM_PRESENT);
 	else
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 }
 #else
-static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 						pmd_t pmd, int offset)
 {
 }
@@ -918,7 +921,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
@@ -928,7 +931,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 			offset = (addr & ~PAGEMAP_WALK_MASK) >>
 					PAGE_SHIFT;
-			thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset);
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
 				break;
@@ -945,7 +948,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		 * and need a new, higher one */
 		if (vma && (addr >= vma->vm_end)) {
 			vma = find_vma(walk->mm, addr);
-			pme = make_pme(PM_NOT_PRESENT);
+			pme = make_pme(PM_NOT_PRESENT(pm->v2));
 		}
 
 		/* check that 'vma' actually covers this address,
@@ -953,7 +956,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, vma, addr, *pte);
+			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
@@ -968,14 +971,14 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 					pte_t pte, int offset)
 {
 	if (pte_present(pte))
 		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+				| PM_STATUS2(pm->v2, 0) | PM_PRESENT);
 	else
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -989,7 +992,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		huge_pte_to_pagemap_entry(&pme, *pte, offset);
+		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset);
 		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
@@ -1051,6 +1054,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
+	pm.v2 = false;
 	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
 	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;
-- 
1.7.6.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 4/5] mm: soft-dirty bits for user memory changes tracking

[Pavel Emelyanov]

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/pagemap 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: Andrew Morton <akpm@linux-foundation.org>
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>
---
 Documentation/filesystems/proc.txt   |    7 +++++-
 Documentation/vm/soft-dirty.txt      |   36 +++++++++++++++++++++++++++++
 arch/Kconfig                         |    3 ++
 arch/x86/Kconfig                     |    1 +
 arch/x86/include/asm/pgtable.h       |   24 +++++++++++++++++-
 arch/x86/include/asm/pgtable_types.h |   12 +++++++++
 fs/proc/task_mmu.c                   |   42 +++++++++++++++++++++++++++++----
 include/asm-generic/pgtable.h        |   22 +++++++++++++++++
 mm/Kconfig                           |   12 +++++++++
 mm/huge_memory.c                     |    2 +-
 mm/mremap.c                          |    2 +-
 11 files changed, 153 insertions(+), 10 deletions(-)
 create mode 100644 Documentation/vm/soft-dirty.txt

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index fd8d0d5..fcc22c9 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -473,7 +473,8 @@ This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
 
 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
-bits on both physical and virtual pages associated with a process.
+bits on both physical and virtual pages associated with a process, and the
+soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
 To clear the bits for all the pages associated with the process
     > echo 1 > /proc/PID/clear_refs
 
@@ -482,6 +483,10 @@ To clear the bits for the anonymous pages associated with the process
 
 To clear the bits for the file mapped pages associated with the process
     > echo 3 > /proc/PID/clear_refs
+
+To clear the soft-dirty bit
+    > echo 4 > /proc/PID/clear_refs
+
 Any other value written to /proc/PID/clear_refs will have no effect.
 
 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
diff --git a/Documentation/vm/soft-dirty.txt b/Documentation/vm/soft-dirty.txt
new file mode 100644
index 0000000..9a12a59
--- /dev/null
+++ b/Documentation/vm/soft-dirty.txt
@@ -0,0 +1,36 @@
+                            SOFT-DIRTY PTEs
+
+  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 the task's PTEs.
+
+     This is done by writing "4" into the /proc/PID/clear_refs file of the
+     task in question.
+
+  2. Wait some time.
+
+  3. Read soft-dirty bits from the PTEs.
+
+     This is done by reading from the /proc/PID/pagemap. The bit 55 of the
+     64-bit qword is the soft-dirty one. If set, the respective PTE was
+     written to since step 1.
+
+
+  Internally, to do this tracking, the writable bit is cleared from PTEs
+when the soft-dirty bit is cleared. So, 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 both writable and soft-dirty
+bits on the PTE.
+
+
+  This feature is actively used by the checkpoint-restore project. You
+can find more details about it on http://criu.org
+
+
+-- Pavel Emelyanov, Apr 9, 2013
diff --git a/arch/Kconfig b/arch/Kconfig
index 1455579..71c06ab 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 05b057d..b30ae26 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -101,6 +101,7 @@ 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 1e67223..ebf9373 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 e642300..c98ac63 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
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 39d6412..9238acb 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -692,13 +692,32 @@ enum clear_refs_types {
 	CLEAR_REFS_ALL = 1,
 	CLEAR_REFS_ANON,
 	CLEAR_REFS_MAPPED,
+	CLEAR_REFS_SOFT_DIRTY,
 	CLEAR_REFS_LAST,
 };
 
 struct clear_refs_private {
 	struct vm_area_struct *vma;
+	enum clear_refs_types type;
 };
 
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	/*
+	 * The soft-dirty tracker uses #PF-s to catch writes
+	 * to pages, so write-protect the pte as well. See the
+	 * Documentation/vm/soft-dirty.txt for full description
+	 * of how soft-dirty works.
+	 */
+	pte_t ptent = *pte;
+	ptent = pte_wrprotect(ptent);
+	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+	set_pte_at(vma->vm_mm, addr, pte, ptent);
+#endif
+}
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
@@ -718,6 +737,11 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		if (!pte_present(ptent))
 			continue;
 
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty(vma, addr, pte);
+			continue;
+		}
+
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
@@ -759,6 +783,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	mm = get_task_mm(task);
 	if (mm) {
 		struct clear_refs_private cp = {
+			.type = type,
 		};
 		struct mm_walk clear_refs_walk = {
 			.pmd_entry = clear_refs_pte_range,
@@ -827,6 +852,7 @@ struct pagemapread {
 /* in "new" pagemap pshift bits are occupied with more status bits */
 #define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
 
+#define __PM_SOFT_DIRTY      (1LL)
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
 #define PM_FILE             PM_STATUS(1LL)
@@ -868,6 +894,7 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 {
 	u64 frame, flags;
 	struct page *page = NULL;
+	int flags2 = 0;
 
 	if (pte_present(pte)) {
 		frame = pte_pfn(pte);
@@ -888,13 +915,15 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 
 	if (page && !PageAnon(page))
 		flags |= PM_FILE;
+	if (pte_soft_dirty(pte))
+		flags2 |= __PM_SOFT_DIRTY;
 
-	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, 0) | flags);
+	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-					pmd_t pmd, int offset)
+		pmd_t pmd, int offset, int pmd_flags2)
 {
 	/*
 	 * Currently pmd for thp is always present because thp can not be
@@ -903,13 +932,13 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *p
 	 */
 	if (pmd_present(pmd))
 		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
-				| PM_STATUS2(pm->v2, 0) | PM_PRESENT);
+				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
 	else
 		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 }
 #else
 static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-						pmd_t pmd, int offset)
+		pmd_t pmd, int offset, int pmd_flags2)
 {
 }
 #endif
@@ -926,12 +955,15 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
 	if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+		int pmd_flags2;
+
+		pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0);
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
 
 			offset = (addr & ~PAGEMAP_WALK_MASK) >>
 					PAGE_SHIFT;
-			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset);
+			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
 				break;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a59ff51..347fb7b 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -396,6 +396,28 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #define arch_start_context_switch(prev)	do {} while (0)
 #endif
 
+#ifndef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline int pte_soft_dirty(pte_t pte)
+{
+	return 0;
+}
+
+static inline int pmd_soft_dirty(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
+{
+	return pmd;
+}
+#endif
+
 #ifndef __HAVE_PFNMAP_TRACKING
 /*
  * Interfaces that can be used by architecture code to keep track of
diff --git a/mm/Kconfig b/mm/Kconfig
index e742d06..b0a7dad 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -477,3 +477,15 @@ config FRONTSWAP
 	  and swap data is stored as normal on the matching swap device.
 
 	  If unsure, say Y to enable frontswap.
+
+config MEM_SOFT_DIRTY
+	bool "Track memory changes"
+	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+	select PROC_PAGE_MONITOR
+	help
+	  This option enables memory changes tracking by introducing a
+	  soft-dirty bit on pte-s. This bit it set when someone writes
+	  into a page just as regular dirty bit, but unlike the latter
+	  it can be cleared by hands.
+
+	  See Documentation/vm/soft-dirty.txt for more details.
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 03a89a2..d252c6e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1429,7 +1429,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 	if (ret == 1) {
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
-		set_pmd_at(mm, new_addr, new_pmd, pmd);
+		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
 		spin_unlock(&mm->page_table_lock);
 	}
 out:
diff --git a/mm/mremap.c b/mm/mremap.c
index 463a257..3708655 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -126,7 +126,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 			continue;
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
-		set_pte_at(mm, new_addr, new_pte, pte);
+		set_pte_at(mm, new_addr, new_pte, pte_mksoft_dirty(pte));
 	}
 
 	arch_leave_lazy_mmu_mode();
-- 
1.7.6.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 4/5] mm: soft-dirty bits for user memory changes tracking

[Xiao Guangrong]

On 05/01/2013 12:12 AM, Pavel Emelyanov wrote:

> +static inline void clear_soft_dirty(struct vm_area_struct *vma,
> +		unsigned long addr, pte_t *pte)
> +{
> +#ifdef CONFIG_MEM_SOFT_DIRTY
> +	/*
> +	 * The soft-dirty tracker uses #PF-s to catch writes
> +	 * to pages, so write-protect the pte as well. See the
> +	 * Documentation/vm/soft-dirty.txt for full description
> +	 * of how soft-dirty works.
> +	 */
> +	pte_t ptent = *pte;
> +	ptent = pte_wrprotect(ptent);
> +	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
> +	set_pte_at(vma->vm_mm, addr, pte, ptent);
> +#endif

It seems that TLBs are not flushed and mmu-notification is not called?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 4/5] mm: soft-dirty bits for user memory changes tracking

[Pavel Emelyanov]

On 05/03/2013 03:36 PM, Xiao Guangrong wrote:
> On 05/01/2013 12:12 AM, Pavel Emelyanov wrote:
> 
>> +static inline void clear_soft_dirty(struct vm_area_struct *vma,
>> +		unsigned long addr, pte_t *pte)
>> +{
>> +#ifdef CONFIG_MEM_SOFT_DIRTY
>> +	/*
>> +	 * The soft-dirty tracker uses #PF-s to catch writes
>> +	 * to pages, so write-protect the pte as well. See the
>> +	 * Documentation/vm/soft-dirty.txt for full description
>> +	 * of how soft-dirty works.
>> +	 */
>> +	pte_t ptent = *pte;
>> +	ptent = pte_wrprotect(ptent);
>> +	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
>> +	set_pte_at(vma->vm_mm, addr, pte, ptent);
>> +#endif
> 
> It seems that TLBs are not flushed and mmu-notification is not called?

TLBs are flushed by clear_refs_write()->flush_tlb_mm().

As far as MMU notification is concerned -- yes, you're right! I will
prepare the patch for this soon.

> .
> 


Thanks,
Pavel

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 4/5] mm: soft-dirty bits for user memory changes tracking

[Andy Lutomirski]

On 04/30/2013 09:12 AM, Pavel Emelyanov wrote:
> 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/pagemap 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.
> 
> 

Sorry I'm late to the party -- I didn't notice this until the lwn
article this week.

How does this get munmap + mmap right?  mremap marks things soft-dirty,
but unmapping and remapping seems like it will result in the soft-dirty
bit being cleared.  For that matter, won't this sequence also end up wrong:

 - clear_refs
 - Write to mapping
 - Page and pte evicted due to memory pressure
 - Read from mapping -- clean page faulted back in
 - pte soft-dirty is now clear ?!?

--Andy

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 4/5] mm: soft-dirty bits for user memory changes tracking

[Pavel Emelyanov]

On 07/11/2013 10:46 PM, Andy Lutomirski wrote:
> 
> Sorry I'm late to the party -- I didn't notice this until the lwn
> article this week.
> 
> How does this get munmap + mmap right?  mremap marks things soft-dirty,
> but unmapping and remapping seems like it will result in the soft-dirty
> bit being cleared.  For that matter, won't this sequence also end up wrong:
> 
>  - clear_refs
>  - Write to mapping
>  - Page and pte evicted due to memory pressure
>  - Read from mapping -- clean page faulted back in
>  - pte soft-dirty is now clear ?!?

Yes, it looks like this problem exists. I'll look what can be done about
it, thank you.

> --Andy

Pavel

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 5/5] pagemap: Prepare to reuse constant bits with page-shitf

[Pavel Emelyanov]

In order to reuse bits from pagemap entries gracefully, we leave the entries as
is but on pagemap open emit a warning in dmesg, that bits 55-60 are about to change
in a couple of releases. Next, if a user issues soft-dirty clear command via the
clear_refs file (it was disabled before v3.9) we assume that he's aware of the new
pagemap format, note that fact and report the bits in pagemap in the new manner.

The "migration strategy" looks like this then:

1. existing users are not affected -- they don't touch soft-dirty feature, thus
   see old bits in pagemap, but are warned and have time to fix themselves
2. those who use soft-dirty know about new pagemap format
3. some time soon we get rid of any signs of page-shift in pagemap as well as
   this trick with clear-soft-dirty affecting pagemap format.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
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>
---
 Documentation/vm/pagemap.txt |    3 ++-
 fs/proc/task_mmu.c           |   35 ++++++++++++++++++++++++++++++++++-
 2 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 7587493..fd7c3cf 100644
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/vm/pagemap.txt
@@ -15,7 +15,8 @@ There are three components to pagemap:
     * Bits 0-54  page frame number (PFN) if present
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
-    * Bits 55-60 page shift (page size = 1<<page shift)
+    * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
+    * Bits 56-60 zero
     * Bit  61    page is file-page or shared-anon
     * Bit  62    page swapped
     * Bit  63    page present
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9238acb..27453c0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -688,6 +688,23 @@ const struct file_operations proc_tid_smaps_operations = {
 	.release	= seq_release_private,
 };
 
+/*
+ * We do not want to have constant page-shift bits sitting in
+ * pagemap entries and are about to reuse them some time soon.
+ *
+ * Here's the "migration strategy":
+ * 1. when the system boots these bits remain what they are,
+ *    but a warning about future change is printed in log;
+ * 2. once anyone clears soft-dirty bits via clear_refs file,
+ *    these flag is set to denote, that user is aware of the
+ *    new API and those page-shift bits change their meaning.
+ *    The respective warning is printed in dmesg;
+ * 3. In a couple of releases we will remove all the mentions
+ *    of page-shift in pagemap entries.
+ */
+
+static bool soft_dirty_cleared __read_mostly;
+
 enum clear_refs_types {
 	CLEAR_REFS_ALL = 1,
 	CLEAR_REFS_ANON,
@@ -777,6 +794,13 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	type = (enum clear_refs_types)itype;
 	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
 		return -EINVAL;
+
+	if (type == CLEAR_REFS_SOFT_DIRTY) {
+		soft_dirty_cleared = true;
+		pr_warn_once("The pagemap bits 55-60 has changed their meaning! "
+				"See the linux/Documentation/vm/pagemap.txt for details.\n");
+	}
+
 	task = get_proc_task(file_inode(file));
 	if (!task)
 		return -ESRCH;
@@ -1086,7 +1110,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
-	pm.v2 = false;
+	pm.v2 = soft_dirty_cleared;
 	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
 	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;
@@ -1159,9 +1183,18 @@ out:
 	return ret;
 }
 
+static int pagemap_open(struct inode *inode, struct file *file)
+{
+	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
+			"to stop being page-shift some time soon. See the "
+			"linux/Documentation/vm/pagemap.txt for details.\n");
+	return 0;
+}
+
 const struct file_operations proc_pagemap_operations = {
 	.llseek		= mem_lseek, /* borrow this */
 	.read		= pagemap_read,
+	.open		= pagemap_open,
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
-- 
1.7.6.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>