Commit 7207f436 authored by Laurent Dufour's avatar Laurent Dufour Committed by Michael Ellerman

powerpc/mm: Add page soft dirty tracking

User space checkpoint and restart tool (CRIU) needs the page's change
to be soft tracked. This allows to do a pre checkpoint and then dump
only touched pages.

This is done by using a newly assigned PTE bit (_PAGE_SOFT_DIRTY) when
the page is backed in memory, and a new _PAGE_SWP_SOFT_DIRTY bit when
the page is swapped out.

To introduce a new PTE _PAGE_SOFT_DIRTY bit value common to hash 4k
and hash 64k pte, the bits already defined in hash-*4k.h should be
shifted left by one.

The _PAGE_SWP_SOFT_DIRTY bit is dynamically put after the swap type in
the swap pte. A check is added to ensure that the bit is not
overwritten by _PAGE_HPTEFLAGS.
Signed-off-by: default avatarLaurent Dufour <ldufour@linux.vnet.ibm.com>
CC: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent 2613265c
...@@ -559,6 +559,7 @@ choice ...@@ -559,6 +559,7 @@ choice
config PPC_4K_PAGES config PPC_4K_PAGES
bool "4k page size" bool "4k page size"
select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
config PPC_16K_PAGES config PPC_16K_PAGES
bool "16k page size" bool "16k page size"
...@@ -567,6 +568,7 @@ config PPC_16K_PAGES ...@@ -567,6 +568,7 @@ config PPC_16K_PAGES
config PPC_64K_PAGES config PPC_64K_PAGES
bool "64k page size" bool "64k page size"
depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64) depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64)
select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
config PPC_256K_PAGES config PPC_256K_PAGES
bool "256k page size" bool "256k page size"
......
...@@ -52,7 +52,7 @@ ...@@ -52,7 +52,7 @@
_PAGE_F_SECOND | _PAGE_F_GIX) _PAGE_F_SECOND | _PAGE_F_GIX)
/* shift to put page number into pte */ /* shift to put page number into pte */
#define PTE_RPN_SHIFT (17) #define PTE_RPN_SHIFT (18)
#define _PAGE_4K_PFN 0 #define _PAGE_4K_PFN 0
#ifndef __ASSEMBLY__ #ifndef __ASSEMBLY__
......
...@@ -25,8 +25,8 @@ ...@@ -25,8 +25,8 @@
#define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1)) #define PGDIR_MASK (~(PGDIR_SIZE-1))
#define _PAGE_COMBO 0x00020000 /* this is a combo 4k page */ #define _PAGE_COMBO 0x00040000 /* this is a combo 4k page */
#define _PAGE_4K_PFN 0x00040000 /* PFN is for a single 4k page */ #define _PAGE_4K_PFN 0x00080000 /* PFN is for a single 4k page */
/* /*
* Used to track subpage group valid if _PAGE_COMBO is set * Used to track subpage group valid if _PAGE_COMBO is set
* This overloads _PAGE_F_GIX and _PAGE_F_SECOND * This overloads _PAGE_F_GIX and _PAGE_F_SECOND
......
...@@ -33,6 +33,7 @@ ...@@ -33,6 +33,7 @@
#define _PAGE_F_GIX_SHIFT 12 #define _PAGE_F_GIX_SHIFT 12
#define _PAGE_F_SECOND 0x08000 /* Whether to use secondary hash or not */ #define _PAGE_F_SECOND 0x08000 /* Whether to use secondary hash or not */
#define _PAGE_SPECIAL 0x10000 /* software: special page */ #define _PAGE_SPECIAL 0x10000 /* software: special page */
#define _PAGE_SOFT_DIRTY 0x20000 /* software: software dirty tracking */
/* /*
* THP pages can't be special. So use the _PAGE_SPECIAL * THP pages can't be special. So use the _PAGE_SPECIAL
...@@ -50,7 +51,7 @@ ...@@ -50,7 +51,7 @@
*/ */
#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \ #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \
_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \ _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
_PAGE_THP_HUGE | _PAGE_PTE) _PAGE_THP_HUGE | _PAGE_PTE | _PAGE_SOFT_DIRTY)
#ifdef CONFIG_PPC_64K_PAGES #ifdef CONFIG_PPC_64K_PAGES
#include <asm/book3s/64/hash-64k.h> #include <asm/book3s/64/hash-64k.h>
...@@ -136,14 +137,16 @@ ...@@ -136,14 +137,16 @@
* pgprot changes * pgprot changes
*/ */
#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ #define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
_PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE) _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \
_PAGE_SOFT_DIRTY)
/* /*
* Mask of bits returned by pte_pgprot() * Mask of bits returned by pte_pgprot()
*/ */
#define PAGE_PROT_BITS (_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \ #define PAGE_PROT_BITS (_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
_PAGE_WRITETHRU | _PAGE_4K_PFN | \ _PAGE_WRITETHRU | _PAGE_4K_PFN | \
_PAGE_USER | _PAGE_ACCESSED | \ _PAGE_USER | _PAGE_ACCESSED | \
_PAGE_RW | _PAGE_DIRTY | _PAGE_EXEC) _PAGE_RW | _PAGE_DIRTY | _PAGE_EXEC | \
_PAGE_SOFT_DIRTY)
/* /*
* We define 2 sets of base prot bits, one for basic pages (ie, * We define 2 sets of base prot bits, one for basic pages (ie,
* cacheable kernel and user pages) and one for non cacheable * cacheable kernel and user pages) and one for non cacheable
...@@ -339,7 +342,8 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, ...@@ -339,7 +342,8 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry) static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
{ {
unsigned long bits = pte_val(entry) & unsigned long bits = pte_val(entry) &
(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC |
_PAGE_SOFT_DIRTY);
unsigned long old, tmp; unsigned long old, tmp;
...@@ -366,6 +370,22 @@ static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIA ...@@ -366,6 +370,22 @@ static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIA
static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline bool pte_soft_dirty(pte_t pte)
{
return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
}
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
}
static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY);
}
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
#ifdef CONFIG_NUMA_BALANCING #ifdef CONFIG_NUMA_BALANCING
/* /*
* These work without NUMA balancing but the kernel does not care. See the * These work without NUMA balancing but the kernel does not care. See the
...@@ -424,7 +444,7 @@ static inline pte_t pte_mkwrite(pte_t pte) ...@@ -424,7 +444,7 @@ static inline pte_t pte_mkwrite(pte_t pte)
static inline pte_t pte_mkdirty(pte_t pte) static inline pte_t pte_mkdirty(pte_t pte)
{ {
return __pte(pte_val(pte) | _PAGE_DIRTY); return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
} }
static inline pte_t pte_mkyoung(pte_t pte) static inline pte_t pte_mkyoung(pte_t pte)
......
...@@ -146,6 +146,7 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val) ...@@ -146,6 +146,7 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
* We filter HPTEFLAGS on set_pte. \ * We filter HPTEFLAGS on set_pte. \
*/ \ */ \
BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \
} while (0) } while (0)
/* /*
* on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
...@@ -161,6 +162,24 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val) ...@@ -161,6 +162,24 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
#define __swp_entry_to_pte(x) __pte((x).val) #define __swp_entry_to_pte(x) __pte((x).val)
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
}
static inline bool pte_swp_soft_dirty(pte_t pte)
{
return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
}
static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
}
#else
#define _PAGE_SWP_SOFT_DIRTY 0
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
void pgtable_cache_init(void); void pgtable_cache_init(void);
...@@ -201,6 +220,13 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) ...@@ -201,6 +220,13 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd)))
#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
#define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd))
#define pmd_mksoft_dirty(pmd) pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))
#define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)))
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
#ifdef CONFIG_NUMA_BALANCING #ifdef CONFIG_NUMA_BALANCING
static inline int pmd_protnone(pmd_t pmd) static inline int pmd_protnone(pmd_t pmd)
{ {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment