Commit e8c6158f authored by Kirill A. Shutemov's avatar Kirill A. Shutemov Committed by Linus Torvalds
Browse files

mm: consolidate all page-flags helpers in <linux/page-flags.h> 



Currently we take a naive approach to page flags on compound pages - we
set the flag on the page without consideration if the flag makes sense
for tail page or for compound page in general.  This patchset try to
sort this out by defining per-flag policy on what need to be done if
page-flag helper operate on compound page.

The last patch in the patchset also sanitizes usege of page->mapping for
tail pages.  We don't define the meaning of page->mapping for tail
pages.  Currently it's always NULL, which can be inconsistent with head
page and potentially lead to problems.

For now I caught one case of illegal usage of page flags or ->mapping:
sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
It leads to setting dirty bit on tail pages and access to tail_page's
->mapping.  I don't see any bad behaviour caused by this, but worth
fixing anyway.

This patchset makes more sense if you take my THP refcounting into
account: we will see more compound pages mapped with PTEs and we need to
define behaviour of flags on compound pages to avoid bugs.

This patch (of 16):

We have page-flags helper function declarations/definitions spread over
several header files.  Let's consolidate them in <linux/page-flags.h>.

Signed-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: default avatarHugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 64d37a2b

include/linux/hugetlb.h

+0 −7
Original line number Diff line number Diff line
@@ -41,8 +41,6 @@ extern int hugetlb_max_hstate __read_mostly; 
struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);

void hugepage_put_subpool(struct hugepage_subpool *spool);



int PageHuge(struct page *page);



void reset_vma_resv_huge_pages(struct vm_area_struct *vma);

int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);

int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -109,11 +107,6 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, 


#else /* !CONFIG_HUGETLB_PAGE */



static inline int PageHuge(struct page *page)

{

	return 0;

}



static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)

{

}

include/linux/ksm.h

+0 −17
Original line number Diff line number Diff line
@@ -35,18 +35,6 @@ static inline void ksm_exit(struct mm_struct *mm) 
		__ksm_exit(mm);

}



/*

 * A KSM page is one of those write-protected "shared pages" or "merged pages"

 * which KSM maps into multiple mms, wherever identical anonymous page content

 * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any

 * anon_vma, but to that page's node of the stable tree.

 */

static inline int PageKsm(struct page *page)

{

	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==

				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);

}



static inline struct stable_node *page_stable_node(struct page *page)

{

	return PageKsm(page) ? page_rmapping(page) : NULL;
@@ -87,11 +75,6 @@ static inline void ksm_exit(struct mm_struct *mm) 
{

}



static inline int PageKsm(struct page *page)

{

	return 0;

}



#ifdef CONFIG_MMU

static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,

		unsigned long end, int advice, unsigned long *vm_flags)

include/linux/mm.h

+0 −81
Original line number Diff line number Diff line
@@ -494,15 +494,6 @@ static inline int page_count(struct page *page) 
	return atomic_read(&compound_head(page)->_count);

}



#ifdef CONFIG_HUGETLB_PAGE

extern int PageHeadHuge(struct page *page_head);

#else /* CONFIG_HUGETLB_PAGE */

static inline int PageHeadHuge(struct page *page_head)

{

	return 0;

}

#endif /* CONFIG_HUGETLB_PAGE */



static inline bool __compound_tail_refcounted(struct page *page)

{

	return !PageSlab(page) && !PageHeadHuge(page);
@@ -571,53 +562,6 @@ static inline void init_page_count(struct page *page) 
	atomic_set(&page->_count, 1);

}



/*

 * PageBuddy() indicate that the page is free and in the buddy system

 * (see mm/page_alloc.c).

 *

 * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to

 * -2 so that an underflow of the page_mapcount() won't be mistaken

 * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very

 * efficiently by most CPU architectures.

 */

#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)



static inline int PageBuddy(struct page *page)

{

	return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;

}



static inline void __SetPageBuddy(struct page *page)

{

	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);

	atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);

}



static inline void __ClearPageBuddy(struct page *page)

{

	VM_BUG_ON_PAGE(!PageBuddy(page), page);

	atomic_set(&page->_mapcount, -1);

}



#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)



static inline int PageBalloon(struct page *page)

{

	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;

}



static inline void __SetPageBalloon(struct page *page)

{

	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);

	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);

}



static inline void __ClearPageBalloon(struct page *page)

{

	VM_BUG_ON_PAGE(!PageBalloon(page), page);

	atomic_set(&page->_mapcount, -1);

}



void put_page(struct page *page);

void put_pages_list(struct list_head *pages);
@@ -1006,26 +950,6 @@ void page_address_init(void); 
#define page_address_init()  do { } while(0)

#endif



/*

 * On an anonymous page mapped into a user virtual memory area,

 * page->mapping points to its anon_vma, not to a struct address_space;

 * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.

 *

 * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,

 * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;

 * and then page->mapping points, not to an anon_vma, but to a private

 * structure which KSM associates with that merged page.  See ksm.h.

 *

 * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.

 *

 * Please note that, confusingly, "page_mapping" refers to the inode

 * address_space which maps the page from disk; whereas "page_mapped"

 * refers to user virtual address space into which the page is mapped.

 */

#define PAGE_MAPPING_ANON	1

#define PAGE_MAPPING_KSM	2

#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)



extern struct address_space *page_mapping(struct page *page);



/* Neutral page->mapping pointer to address_space or anon_vma or other */
@@ -1045,11 +969,6 @@ struct address_space *page_file_mapping(struct page *page) 
	return page->mapping;

}



static inline int PageAnon(struct page *page)

{

	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;

}



/*

 * Return the pagecache index of the passed page.  Regular pagecache pages

 * use ->index whereas swapcache pages use ->private

include/linux/page-flags.h

+96 −0
Original line number Diff line number Diff line
@@ -289,6 +289,47 @@ PAGEFLAG_FALSE(HWPoison) 
#define __PG_HWPOISON 0

#endif



/*

 * On an anonymous page mapped into a user virtual memory area,

 * page->mapping points to its anon_vma, not to a struct address_space;

 * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.

 *

 * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,

 * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;

 * and then page->mapping points, not to an anon_vma, but to a private

 * structure which KSM associates with that merged page.  See ksm.h.

 *

 * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.

 *

 * Please note that, confusingly, "page_mapping" refers to the inode

 * address_space which maps the page from disk; whereas "page_mapped"

 * refers to user virtual address space into which the page is mapped.

 */

#define PAGE_MAPPING_ANON	1

#define PAGE_MAPPING_KSM	2

#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)



static inline int PageAnon(struct page *page)

{

	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;

}



#ifdef CONFIG_KSM

/*

 * A KSM page is one of those write-protected "shared pages" or "merged pages"

 * which KSM maps into multiple mms, wherever identical anonymous page content

 * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any

 * anon_vma, but to that page's node of the stable tree.

 */

static inline int PageKsm(struct page *page)

{

	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==

				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);

}

#else

TESTPAGEFLAG_FALSE(Ksm)

#endif



u64 stable_page_flags(struct page *page);



static inline int PageUptodate(struct page *page)
@@ -426,6 +467,14 @@ static inline void ClearPageCompound(struct page *page) 


#endif /* !PAGEFLAGS_EXTENDED */



#ifdef CONFIG_HUGETLB_PAGE

int PageHuge(struct page *page);

int PageHeadHuge(struct page *page);

#else

TESTPAGEFLAG_FALSE(Huge)

TESTPAGEFLAG_FALSE(HeadHuge)

#endif



#ifdef CONFIG_TRANSPARENT_HUGEPAGE

/*

 * PageHuge() only returns true for hugetlbfs pages, but not for
@@ -479,6 +528,53 @@ static inline int PageTransTail(struct page *page) 
}

#endif



/*

 * PageBuddy() indicate that the page is free and in the buddy system

 * (see mm/page_alloc.c).

 *

 * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to

 * -2 so that an underflow of the page_mapcount() won't be mistaken

 * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very

 * efficiently by most CPU architectures.

 */

#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)



static inline int PageBuddy(struct page *page)

{

	return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;

}



static inline void __SetPageBuddy(struct page *page)

{

	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);

	atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);

}



static inline void __ClearPageBuddy(struct page *page)

{

	VM_BUG_ON_PAGE(!PageBuddy(page), page);

	atomic_set(&page->_mapcount, -1);

}



#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)



static inline int PageBalloon(struct page *page)

{

	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;

}



static inline void __SetPageBalloon(struct page *page)

{

	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);

	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);

}



static inline void __ClearPageBalloon(struct page *page)

{

	VM_BUG_ON_PAGE(!PageBalloon(page), page);

	atomic_set(&page->_mapcount, -1);

}



/*

 * If network-based swap is enabled, sl*b must keep track of whether pages

 * were allocated from pfmemalloc reserves.

CRA Git | Maintained and supported by SUSTech CRA and CCSE