Commit 7da4d641 authored by Peter Zijlstra's avatar Peter Zijlstra Committed by Mel Gorman

mm: Count the number of pages affected in change_protection()

This will be used for three kinds of purposes:

 - to optimize mprotect()

 - to speed up working set scanning for working set areas that
   have not been touched

 - to more accurately scan per real working set

No change in functionality from this patch.
Suggested-by: default avatarIngo Molnar <mingo@kernel.org>
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 4fd01770
...@@ -87,7 +87,7 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, ...@@ -87,7 +87,7 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int write); pud_t *pud, int write);
int pmd_huge(pmd_t pmd); int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pmd); int pud_huge(pud_t pmd);
void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot); unsigned long address, unsigned long end, pgprot_t newprot);
#else /* !CONFIG_HUGETLB_PAGE */ #else /* !CONFIG_HUGETLB_PAGE */
...@@ -132,7 +132,11 @@ static inline void copy_huge_page(struct page *dst, struct page *src) ...@@ -132,7 +132,11 @@ static inline void copy_huge_page(struct page *dst, struct page *src)
{ {
} }
#define hugetlb_change_protection(vma, address, end, newprot) static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot)
{
return 0;
}
static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start, struct vm_area_struct *vma, unsigned long start,
......
...@@ -1078,6 +1078,9 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, ...@@ -1078,6 +1078,9 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
extern unsigned long do_mremap(unsigned long addr, extern unsigned long do_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len, unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr); unsigned long flags, unsigned long new_addr);
extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
int dirty_accountable);
extern int mprotect_fixup(struct vm_area_struct *vma, extern int mprotect_fixup(struct vm_area_struct *vma,
struct vm_area_struct **pprev, unsigned long start, struct vm_area_struct **pprev, unsigned long start,
unsigned long end, unsigned long newflags); unsigned long end, unsigned long newflags);
......
...@@ -3014,7 +3014,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, ...@@ -3014,7 +3014,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
return i ? i : -EFAULT; return i ? i : -EFAULT;
} }
void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot) unsigned long address, unsigned long end, pgprot_t newprot)
{ {
struct mm_struct *mm = vma->vm_mm; struct mm_struct *mm = vma->vm_mm;
...@@ -3022,6 +3022,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma, ...@@ -3022,6 +3022,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
pte_t *ptep; pte_t *ptep;
pte_t pte; pte_t pte;
struct hstate *h = hstate_vma(vma); struct hstate *h = hstate_vma(vma);
unsigned long pages = 0;
BUG_ON(address >= end); BUG_ON(address >= end);
flush_cache_range(vma, address, end); flush_cache_range(vma, address, end);
...@@ -3032,12 +3033,15 @@ void hugetlb_change_protection(struct vm_area_struct *vma, ...@@ -3032,12 +3033,15 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
ptep = huge_pte_offset(mm, address); ptep = huge_pte_offset(mm, address);
if (!ptep) if (!ptep)
continue; continue;
if (huge_pmd_unshare(mm, &address, ptep)) if (huge_pmd_unshare(mm, &address, ptep)) {
pages++;
continue; continue;
}
if (!huge_pte_none(huge_ptep_get(ptep))) { if (!huge_pte_none(huge_ptep_get(ptep))) {
pte = huge_ptep_get_and_clear(mm, address, ptep); pte = huge_ptep_get_and_clear(mm, address, ptep);
pte = pte_mkhuge(pte_modify(pte, newprot)); pte = pte_mkhuge(pte_modify(pte, newprot));
set_huge_pte_at(mm, address, ptep, pte); set_huge_pte_at(mm, address, ptep, pte);
pages++;
} }
} }
spin_unlock(&mm->page_table_lock); spin_unlock(&mm->page_table_lock);
...@@ -3049,6 +3053,8 @@ void hugetlb_change_protection(struct vm_area_struct *vma, ...@@ -3049,6 +3053,8 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
*/ */
flush_tlb_range(vma, start, end); flush_tlb_range(vma, start, end);
mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
return pages << h->order;
} }
int hugetlb_reserve_pages(struct inode *inode, int hugetlb_reserve_pages(struct inode *inode,
......
...@@ -35,12 +35,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) ...@@ -35,12 +35,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
} }
#endif #endif
static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, static unsigned long change_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable) int dirty_accountable)
{ {
pte_t *pte, oldpte; pte_t *pte, oldpte;
spinlock_t *ptl; spinlock_t *ptl;
unsigned long pages = 0;
pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode(); arch_enter_lazy_mmu_mode();
...@@ -60,6 +61,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, ...@@ -60,6 +61,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
ptent = pte_mkwrite(ptent); ptent = pte_mkwrite(ptent);
ptep_modify_prot_commit(mm, addr, pte, ptent); ptep_modify_prot_commit(mm, addr, pte, ptent);
pages++;
} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte); swp_entry_t entry = pte_to_swp_entry(oldpte);
...@@ -72,18 +74,22 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, ...@@ -72,18 +74,22 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
set_pte_at(mm, addr, pte, set_pte_at(mm, addr, pte,
swp_entry_to_pte(entry)); swp_entry_to_pte(entry));
} }
pages++;
} }
} while (pte++, addr += PAGE_SIZE, addr != end); } while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode(); arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl); pte_unmap_unlock(pte - 1, ptl);
return pages;
} }
static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud, static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable) int dirty_accountable)
{ {
pmd_t *pmd; pmd_t *pmd;
unsigned long next; unsigned long next;
unsigned long pages = 0;
pmd = pmd_offset(pud, addr); pmd = pmd_offset(pud, addr);
do { do {
...@@ -91,35 +97,42 @@ static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud, ...@@ -91,35 +97,42 @@ static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
if (pmd_trans_huge(*pmd)) { if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) if (next - addr != HPAGE_PMD_SIZE)
split_huge_page_pmd(vma->vm_mm, pmd); split_huge_page_pmd(vma->vm_mm, pmd);
else if (change_huge_pmd(vma, pmd, addr, newprot)) else if (change_huge_pmd(vma, pmd, addr, newprot)) {
pages += HPAGE_PMD_NR;
continue; continue;
}
/* fall through */ /* fall through */
} }
if (pmd_none_or_clear_bad(pmd)) if (pmd_none_or_clear_bad(pmd))
continue; continue;
change_pte_range(vma->vm_mm, pmd, addr, next, newprot, pages += change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
dirty_accountable); dirty_accountable);
} while (pmd++, addr = next, addr != end); } while (pmd++, addr = next, addr != end);
return pages;
} }
static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd, static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable) int dirty_accountable)
{ {
pud_t *pud; pud_t *pud;
unsigned long next; unsigned long next;
unsigned long pages = 0;
pud = pud_offset(pgd, addr); pud = pud_offset(pgd, addr);
do { do {
next = pud_addr_end(addr, end); next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud)) if (pud_none_or_clear_bad(pud))
continue; continue;
change_pmd_range(vma, pud, addr, next, newprot, pages += change_pmd_range(vma, pud, addr, next, newprot,
dirty_accountable); dirty_accountable);
} while (pud++, addr = next, addr != end); } while (pud++, addr = next, addr != end);
return pages;
} }
static void change_protection(struct vm_area_struct *vma, static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable) int dirty_accountable)
{ {
...@@ -127,6 +140,7 @@ static void change_protection(struct vm_area_struct *vma, ...@@ -127,6 +140,7 @@ static void change_protection(struct vm_area_struct *vma,
pgd_t *pgd; pgd_t *pgd;
unsigned long next; unsigned long next;
unsigned long start = addr; unsigned long start = addr;
unsigned long pages = 0;
BUG_ON(addr >= end); BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr); pgd = pgd_offset(mm, addr);
...@@ -135,10 +149,30 @@ static void change_protection(struct vm_area_struct *vma, ...@@ -135,10 +149,30 @@ static void change_protection(struct vm_area_struct *vma,
next = pgd_addr_end(addr, end); next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd)) if (pgd_none_or_clear_bad(pgd))
continue; continue;
change_pud_range(vma, pgd, addr, next, newprot, pages += change_pud_range(vma, pgd, addr, next, newprot,
dirty_accountable); dirty_accountable);
} while (pgd++, addr = next, addr != end); } while (pgd++, addr = next, addr != end);
flush_tlb_range(vma, start, end); flush_tlb_range(vma, start, end);
return pages;
}
unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
int dirty_accountable)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long pages;
mmu_notifier_invalidate_range_start(mm, start, end);
if (is_vm_hugetlb_page(vma))
pages = hugetlb_change_protection(vma, start, end, newprot);
else
pages = change_protection_range(vma, start, end, newprot, dirty_accountable);
mmu_notifier_invalidate_range_end(mm, start, end);
return pages;
} }
int int
...@@ -213,12 +247,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, ...@@ -213,12 +247,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
dirty_accountable = 1; dirty_accountable = 1;
} }
mmu_notifier_invalidate_range_start(mm, start, end); change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
if (is_vm_hugetlb_page(vma))
hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
else
change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
mmu_notifier_invalidate_range_end(mm, start, end);
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
vm_stat_account(mm, newflags, vma->vm_file, nrpages); vm_stat_account(mm, newflags, vma->vm_file, nrpages);
perf_event_mmap(vma); perf_event_mmap(vma);
......
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