mm: drop tail page refcounting

Tail page refcounting is utterly complicated and painful to support. It uses ->_mapcount on tail pages to store how many times this page is pinned. get_page() bumps ->_mapcount on tail page in addition to ->_count on head. This information is required by split_huge_page() to be able to distribute pins from head of compound page to tails during the split. We will need ->_mapcount to account PTE mappings of subpages of the compound page. We eliminate need in current meaning of ->_mapcount in tail pages by forbidding split entirely if the page is pinned. The only user of tail page refcounting is THP which is marked BROKEN for now. Let's drop all this mess. It makes get_page() and put_page() much simpler. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh 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: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
torvalds · Jan 16, 2016 · ddc58f2 · ddc58f2
1 parent ad0bed2
commit ddc58f2
Show file tree

Hide file tree

Showing 12 changed files with 40 additions and 466 deletions.
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
@@ -87,8 +87,6 @@ static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end,
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;
@@ -153,8 +151,6 @@ static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end,
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
@@ -999,7 +999,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 {
 	unsigned long mask;
 	unsigned long pte_end;
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	pte_t pte;
 	int refs;
 
@@ -1022,7 +1022,6 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	head = pte_page(pte);
 
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -1044,15 +1043,5 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 		return 0;
 	}
 
-	/*
-	 * Any tail page need their mapcount reference taken before we
-	 * return.
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
@@ -55,7 +55,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	unsigned long mask, result;
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
@@ -67,7 +67,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -88,16 +87,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		return 0;
 	}
 
-	/*
-	 * Any tail page need their mapcount reference taken before we
-	 * return.
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 

diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
@@ -56,8 +56,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			put_page(head);
 			return 0;
 		}
-		if (head != page)
-			get_huge_page_tail(page);
 
 		pages[*nr] = page;
 		(*nr)++;
@@ -70,7 +68,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 			unsigned long end, int write, struct page **pages,
 			int *nr)
 {
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	if (!(pmd_val(pmd) & _PAGE_VALID))
@@ -82,7 +80,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
@@ -103,15 +100,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		return 0;
 	}
 
-	/* Any tail page need their mapcount reference taken before we
-	 * return.
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
@@ -136,8 +136,6 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;
@@ -212,8 +210,6 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
-		if (PageTail(page))
-			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;

diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -466,44 +466,9 @@ static inline int page_count(struct page *page)
 	return atomic_read(&compound_head(page)->_count);
 }
 
-static inline bool __compound_tail_refcounted(struct page *page)
-{
-	return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page);
-}
-
-/*
- * This takes a head page as parameter and tells if the
- * tail page reference counting can be skipped.
- *
- * For this to be safe, PageSlab and PageHeadHuge must remain true on
- * any given page where they return true here, until all tail pins
- * have been released.
- */
-static inline bool compound_tail_refcounted(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	return __compound_tail_refcounted(page);
-}
-
-static inline void get_huge_page_tail(struct page *page)
-{
-	/*
-	 * __split_huge_page_refcount() cannot run from under us.
-	 */
-	VM_BUG_ON_PAGE(!PageTail(page), page);
-	VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
-	if (compound_tail_refcounted(compound_head(page)))
-		atomic_inc(&page->_mapcount);
-}
-
-extern bool __get_page_tail(struct page *page);
-
 static inline void get_page(struct page *page)
 {
-	if (unlikely(PageTail(page)))
-		if (likely(__get_page_tail(page)))
-			return;
+	page = compound_head(page);
 	/*
 	 * Getting a normal page or the head of a compound page
 	 * requires to already have an elevated page->_count.
@@ -528,7 +493,15 @@ static inline void init_page_count(struct page *page)
 	atomic_set(&page->_count, 1);
 }
 
-void put_page(struct page *page);
+void __put_page(struct page *page);
+
+static inline void put_page(struct page *page)
+{
+	page = compound_head(page);
+	if (put_page_testzero(page))
+		__put_page(page);
+}
+
 void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
@@ -81,20 +81,9 @@ struct page {
 
 				union {
 					/*
-					 * Count of ptes mapped in
-					 * mms, to show when page is
-					 * mapped & limit reverse map
-					 * searches.
-					 *
-					 * Used also for tail pages
-					 * refcounting instead of
-					 * _count. Tail pages cannot
-					 * be mapped and keeping the
-					 * tail page _count zero at
-					 * all times guarantees
-					 * get_page_unless_zero() will
-					 * never succeed on tail
-					 * pages.
+					 * Count of ptes mapped in mms, to show
+					 * when page is mapped & limit reverse
+					 * map searches.
 					 */
 					atomic_t _mapcount;
 

diff --git a/mm/gup.c b/mm/gup.c
@@ -130,7 +130,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	}
 
 	if (flags & FOLL_GET)
-		get_page_foll(page);
+		get_page(page);
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
@@ -1153,7 +1153,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	if (write && !pmd_write(orig))
@@ -1162,7 +1162,6 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	refs = 0;
 	head = pmd_page(orig);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
@@ -1183,24 +1182,13 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 	}
 
-	/*
-	 * Any tail pages need their mapcount reference taken before we
-	 * return. (This allows the THP code to bump their ref count when
-	 * they are split into base pages).
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 
 static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 	int refs;
 
 	if (write && !pud_write(orig))
@@ -1209,7 +1197,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	refs = 0;
 	head = pud_page(orig);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
@@ -1230,12 +1217,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }
 
@@ -1244,15 +1225,14 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 			struct page **pages, int *nr)
 {
 	int refs;
-	struct page *head, *page, *tail;
+	struct page *head, *page;
 
 	if (write && !pgd_write(orig))
 		return 0;
 
 	refs = 0;
 	head = pgd_page(orig);
 	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
@@ -1273,12 +1253,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 	}
 
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
 	return 1;
 }