rmap: support file thp

Naive approach: on mapping/unmapping the page as compound we update
->_mapcount on each 4k page.  That's not efficient, but it's not obvious
how we can optimize this.  We can look into optimization later.

PG_double_map optimization doesn't work for file pages since lifecycle
of file pages is different comparing to anon pages: file page can be
mapped again at any time.

Link: http://lkml.kernel.org/r/1466021202-61880-11-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/rmap.h

@@ -165,7 +165,7 @@ void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
 			   unsigned long, int);
 void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long, bool);
-void page_add_file_rmap(struct page *);
+void page_add_file_rmap(struct page *, bool);
 void page_remove_rmap(struct page *, bool);
 
 void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,

mm/huge_memory.c

@@ -3301,18 +3301,22 @@ static void __split_huge_page(struct page *page, struct list_head *list)
 
 int total_mapcount(struct page *page)
 {
-	int i, ret;
+	int i, compound, ret;
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 
 	if (likely(!PageCompound(page)))
 		return atomic_read(&page->_mapcount) + 1;
 
-	ret = compound_mapcount(page);
+	compound = compound_mapcount(page);
 	if (PageHuge(page))
-		return ret;
+		return compound;
+	ret = compound;
 	for (i = 0; i < HPAGE_PMD_NR; i++)
 		ret += atomic_read(&page[i]._mapcount) + 1;
+	/* File pages has compound_mapcount included in _mapcount */
+	if (!PageAnon(page))
+		return ret - compound * HPAGE_PMD_NR;
 	if (PageDoubleMap(page))
 		ret -= HPAGE_PMD_NR;
 	return ret;

mm/memory.c

@@ -1494,7 +1494,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 	/* Ok, finally just insert the thing.. */
 	get_page(page);
 	inc_mm_counter_fast(mm, mm_counter_file(page));
-	page_add_file_rmap(page);
+	page_add_file_rmap(page, false);
 	set_pte_at(mm, addr, pte, mk_pte(page, prot));
 
 	retval = 0;
@@ -2962,7 +2962,7 @@ int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
 		lru_cache_add_active_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
-		page_add_file_rmap(page);
+		page_add_file_rmap(page, false);
 	}
 	set_pte_at(vma->vm_mm, fe->address, fe->pte, entry);
 

mm/migrate.c

@@ -259,7 +259,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	} else if (PageAnon(new))
 		page_add_anon_rmap(new, vma, addr, false);
 	else
-		page_add_file_rmap(new);
+		page_add_file_rmap(new, false);
 
 	if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
 		mlock_vma_page(new);

mm/rmap.c

@@ -1270,18 +1270,34 @@ void page_add_new_anon_rmap(struct page *page,
  *
  * The caller needs to hold the pte lock.
  */
-void page_add_file_rmap(struct page *page)
+void page_add_file_rmap(struct page *page, bool compound)
 {
+	int i, nr = 1;
+
+	VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
 	lock_page_memcg(page);
-	if (atomic_inc_and_test(&page->_mapcount)) {
-		__inc_zone_page_state(page, NR_FILE_MAPPED);
-		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+	if (compound && PageTransHuge(page)) {
+		for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
+			if (atomic_inc_and_test(&page[i]._mapcount))
+				nr++;
+		}
+		if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
+			goto out;
+	} else {
+		if (!atomic_inc_and_test(&page->_mapcount))
+			goto out;
 	}
+	__mod_zone_page_state(page_zone(page), NR_FILE_MAPPED, nr);
+	mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
+out:
 	unlock_page_memcg(page);
 }
 
-static void page_remove_file_rmap(struct page *page)
+static void page_remove_file_rmap(struct page *page, bool compound)
 {
+	int i, nr = 1;
+
+	VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
 	lock_page_memcg(page);
 
 	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
@@ -1292,15 +1308,24 @@ static void page_remove_file_rmap(struct page *page)
 	}
 
 	/* page still mapped by someone else? */
-	if (!atomic_add_negative(-1, &page->_mapcount))
-		goto out;
+	if (compound && PageTransHuge(page)) {
+		for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
+			if (atomic_add_negative(-1, &page[i]._mapcount))
+				nr++;
+		}
+		if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
+			goto out;
+	} else {
+		if (!atomic_add_negative(-1, &page->_mapcount))
+			goto out;
+	}
 
 	/*
 	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
 	 * these counters are not modified in interrupt context, and
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
-	__dec_zone_page_state(page, NR_FILE_MAPPED);
+	__mod_zone_page_state(page_zone(page), NR_FILE_MAPPED, -nr);
 	mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
 
 	if (unlikely(PageMlocked(page)))
@@ -1356,11 +1381,8 @@ static void page_remove_anon_compound_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page, bool compound)
 {
-	if (!PageAnon(page)) {
-		VM_BUG_ON_PAGE(compound && !PageHuge(page), page);
-		page_remove_file_rmap(page);
-		return;
-	}
+	if (!PageAnon(page))
+		return page_remove_file_rmap(page, compound);
 
 	if (compound)
 		return page_remove_anon_compound_rmap(page);

mm/util.c

@@ -412,6 +412,12 @@ int __page_mapcount(struct page *page)
 	int ret;
 
 	ret = atomic_read(&page->_mapcount) + 1;
+	/*
+	 * For file THP page->_mapcount contains total number of mapping
+	 * of the page: no need to look into compound_mapcount.
+	 */
+	if (!PageAnon(page) && !PageHuge(page))
+		return ret;
 	page = compound_head(page);
 	ret += atomic_read(compound_mapcount_ptr(page)) + 1;
 	if (PageDoubleMap(page))