Commit 0f8975ec authored by Pavel Emelyanov's avatar Pavel Emelyanov Committed by Linus Torvalds
Browse files

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: default avatarPavel 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 2b0a9f01

Documentation/filesystems/proc.txt

+6 −1
Original line number Diff line number Diff line
@@ -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

Documentation/vm/soft-dirty.txt

0 → 100644
+36 −0
Original line number Diff line number Diff line 
                            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

arch/Kconfig

+3 −0
Original line number Diff line number Diff line
@@ -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

arch/x86/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -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

arch/x86/include/asm/pgtable.h

+22 −2
Original line number Diff line number Diff line
@@ -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.

CRA Git | Maintained and supported by SUSTech CRA and CCSE