Commit 179ef71c authored by Cyrill Gorcunov's avatar Cyrill Gorcunov Committed by Linus Torvalds
Browse files

mm: save soft-dirty bits on swapped pages 



Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set
get swapped out, the bit is getting lost and no longer available when
pte read back.

To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in
pte entry for the page being swapped out.  When such page is to be read
back from a swap cache we check for bit presence and if it's there we
clear it and restore the former _PAGE_SOFT_DIRTY bit back.

One of the problem was to find a place in pte entry where we can save
the _PTE_SWP_SOFT_DIRTY bit while page is in swap.  The _PAGE_PSE was
chosen for that, it doesn't intersect with swap entry format stored in
pte.

Reported-by: default avatarAndy Lutomirski <luto@amacapital.net>
Signed-off-by: default avatarCyrill Gorcunov <gorcunov@openvz.org>
Acked-by: default avatarPavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: default avatarMinchan Kim <minchan@kernel.org>
Reviewed-by: default avatarWanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 3e6b11df

arch/x86/include/asm/pgtable.h

+15 −0
Original line number Diff line number Diff line
@@ -314,6 +314,21 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) 
	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);

}



static inline pte_t pte_swp_mksoft_dirty(pte_t pte)

{

	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);

}



static inline int pte_swp_soft_dirty(pte_t pte)

{

	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;

}



static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)

{

	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);

}



/*

 * Mask out unsupported bits in a present pgprot.  Non-present pgprots

 * can use those bits for other purposes, so leave them be.

arch/x86/include/asm/pgtable_types.h

+13 −0
Original line number Diff line number Diff line
@@ -67,6 +67,19 @@ 
#define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 0))

#endif



/*

 * Tracking soft dirty bit when a page goes to a swap is tricky.

 * We need a bit which can be stored in pte _and_ not conflict

 * with swap entry format. On x86 bits 6 and 7 are *not* involved

 * into swap entry computation, but bit 6 is used for nonlinear

 * file mapping, so we borrow bit 7 for soft dirty tracking.

 */

#ifdef CONFIG_MEM_SOFT_DIRTY

#define _PAGE_SWP_SOFT_DIRTY	_PAGE_PSE

#else

#define _PAGE_SWP_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

fs/proc/task_mmu.c

+15 −6
Original line number Diff line number Diff line
@@ -730,8 +730,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, 
	 * of how soft-dirty works.

	 */

	pte_t ptent = *pte;



	if (pte_present(ptent)) {

		ptent = pte_wrprotect(ptent);

		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);

	} else if (is_swap_pte(ptent)) {

		ptent = pte_swp_clear_soft_dirty(ptent);

	}



	set_pte_at(vma->vm_mm, addr, pte, ptent);

#endif

}
@@ -752,14 +758,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, 
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);

	for (; addr != end; pte++, addr += PAGE_SIZE) {

		ptent = *pte;

		if (!pte_present(ptent))

			continue;



		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {

			clear_soft_dirty(vma, addr, pte);

			continue;

		}



		if (!pte_present(ptent))

			continue;



		page = vm_normal_page(vma, addr, ptent);

		if (!page)

			continue;
@@ -930,8 +937,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, 
		flags = PM_PRESENT;

		page = vm_normal_page(vma, addr, pte);

	} else if (is_swap_pte(pte)) {

		swp_entry_t entry = pte_to_swp_entry(pte);



		swp_entry_t entry;

		if (pte_swp_soft_dirty(pte))

			flags2 |= __PM_SOFT_DIRTY;

		entry = pte_to_swp_entry(pte);

		frame = swp_type(entry) |

			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);

		flags = PM_SWAP;

include/asm-generic/pgtable.h

+15 −0
Original line number Diff line number Diff line
@@ -417,6 +417,21 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) 
{

	return pmd;

}



static inline pte_t pte_swp_mksoft_dirty(pte_t pte)

{

	return pte;

}



static inline int pte_swp_soft_dirty(pte_t pte)

{

	return 0;

}



static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)

{

	return pte;

}

#endif



#ifndef __HAVE_PFNMAP_TRACKING

include/linux/swapops.h

+2 −0
Original line number Diff line number Diff line
@@ -67,6 +67,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) 
	swp_entry_t arch_entry;



	BUG_ON(pte_file(pte));

	if (pte_swp_soft_dirty(pte))

		pte = pte_swp_clear_soft_dirty(pte);

	arch_entry = __pte_to_swp_entry(pte);

	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE