leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

mm, thp: Do not make page table dirty unconditionally in touch_p[mu]d()

Browse Source 
Currently, we unconditionally make page table dirty in touch_pmd().
It may result in false-positive can_follow_write_pmd().

We may avoid the situation, if we would only make the page table entry
dirty if caller asks for write access -- FOLL_WRITE.

The patch also changes touch_pud() in the same way.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Kirill A. Shutemov 2017-11-27 06:21:25 +03:00 committed by Linus Torvalds
parent 4fbd8d194f
commit a8f9736645
1 changed files with 13 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
mm/huge_memory.c
View File

@ -842,20 +842,15 @@ EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd) pmd_t *pmd, int flags)
{ {
pmd_t _pmd; pmd_t _pmd;
/* _pmd = pmd_mkyoung(*pmd);
* We should set the dirty bit only for FOLL_WRITE but for now if (flags & FOLL_WRITE)
* the dirty bit in the pmd is meaningless. And if the dirty _pmd = pmd_mkdirty(_pmd);
* bit will become meaningful and we'll only set it with
* FOLL_WRITE, an atomic set_bit will be required on the pmd to
* set the young bit, instead of the current set_pmd_at.
*/
_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
pmd, _pmd, 1)) pmd, _pmd, flags & FOLL_WRITE))
update_mmu_cache_pmd(vma, addr, pmd); update_mmu_cache_pmd(vma, addr, pmd);
} }
@ -884,7 +879,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
return NULL; return NULL;
if (flags & FOLL_TOUCH) if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd); touch_pmd(vma, addr, pmd, flags);
/* /*
* device mapped pages can only be returned if the * device mapped pages can only be returned if the
@ -995,20 +990,15 @@ out:
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void touch_pud(struct vm_area_struct *vma, unsigned long addr, static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud) pud_t *pud, int flags)
{ {
pud_t _pud; pud_t _pud;
/* _pud = pud_mkyoung(*pud);
* We should set the dirty bit only for FOLL_WRITE but for now if (flags & FOLL_WRITE)
* the dirty bit in the pud is meaningless. And if the dirty _pud = pud_mkdirty(_pud);
* bit will become meaningful and we'll only set it with
* FOLL_WRITE, an atomic set_bit will be required on the pud to
* set the young bit, instead of the current set_pud_at.
*/
_pud = pud_mkyoung(pud_mkdirty(*pud));
if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
pud, _pud, 1)) pud, _pud, flags & FOLL_WRITE))
update_mmu_cache_pud(vma, addr, pud); update_mmu_cache_pud(vma, addr, pud);
} }
@ -1031,7 +1021,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
return NULL; return NULL;
if (flags & FOLL_TOUCH) if (flags & FOLL_TOUCH)
touch_pud(vma, addr, pud); touch_pud(vma, addr, pud, flags);
/* /*
* device mapped pages can only be returned if the * device mapped pages can only be returned if the
@ -1424,7 +1414,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
page = pmd_page(*pmd); page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH) if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd); touch_pmd(vma, addr, pmd, flags);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/* /*
* We don't mlock() pte-mapped THPs. This way we can avoid * We don't mlock() pte-mapped THPs. This way we can avoid