thp: alter compound get_page/put_page

Alter compound get_page/put_page to keep references on subpages too, in
order to allow __split_huge_page_refcount to split an hugepage even while
subpages have been pinned by one of the get_user_pages() variants.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/powerpc/mm/gup.c

@@ -16,6 +16,16 @@
 
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 
+static inline void get_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < 0);
+	atomic_inc(&page->_count);
+}
+
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -47,6 +57,8 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			put_page(page);
 			return 0;
 		}
+		if (PageTail(page))
+			get_huge_page_tail(page);
 		pages[*nr] = page;
 		(*nr)++;
 

arch/x86/mm/gup.c

@@ -105,6 +105,16 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 	atomic_add(nr, &page->_count);
 }
 
+static inline void get_huge_page_tail(struct page *page)
+{
+	/*
+	 * __split_huge_page_refcount() cannot run
+	 * from under us.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < 0);
+	atomic_inc(&page->_count);
+}
+
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -128,6 +138,8 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
+		if (PageTail(page))
+			get_huge_page_tail(page);
 		(*nr)++;
 		page++;
 		refs++;

include/linux/mm.h

@@ -353,9 +353,29 @@ static inline int page_count(struct page *page)
 
 static inline void get_page(struct page *page)
 {
-	page = compound_head(page);
-	VM_BUG_ON(atomic_read(&page->_count) == 0);
+	/*
+	 * Getting a normal page or the head of a compound page
+	 * requires to already have an elevated page->_count. Only if
+	 * we're getting a tail page, the elevated page->_count is
+	 * required only in the head page, so for tail pages the
+	 * bugcheck only verifies that the page->_count isn't
+	 * negative.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
 	atomic_inc(&page->_count);
+	/*
+	 * Getting a tail page will elevate both the head and tail
+	 * page->_count(s).
+	 */
+	if (unlikely(PageTail(page))) {
+		/*
+		 * This is safe only because
+		 * __split_huge_page_refcount can't run under
+		 * get_page().
+		 */
+		VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
+		atomic_inc(&page->first_page->_count);
+	}
 }
 
 static inline struct page *virt_to_head_page(const void *x)

mm/swap.c

@@ -56,17 +56,93 @@ static void __page_cache_release(struct page *page)
 		del_page_from_lru(zone, page);
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 	}
+}
+
+static void __put_single_page(struct page *page)
+{
+	__page_cache_release(page);
 	free_hot_cold_page(page, 0);
 }
 
-static void put_compound_page(struct page *page)
+static void __put_compound_page(struct page *page)
 {
-	page = compound_head(page);
-	if (put_page_testzero(page)) {
-		compound_page_dtor *dtor;
+	compound_page_dtor *dtor;
+
+	__page_cache_release(page);
+	dtor = get_compound_page_dtor(page);
+	(*dtor)(page);
+}
 
-		dtor = get_compound_page_dtor(page);
-		(*dtor)(page);
+static void put_compound_page(struct page *page)
+{
+	if (unlikely(PageTail(page))) {
+		/* __split_huge_page_refcount can run under us */
+		struct page *page_head = page->first_page;
+		smp_rmb();
+		/*
+		 * If PageTail is still set after smp_rmb() we can be sure
+		 * that the page->first_page we read wasn't a dangling pointer.
+		 * See __split_huge_page_refcount() smp_wmb().
+		 */
+		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+			unsigned long flags;
+			/*
+			 * Verify that our page_head wasn't converted
+			 * to a a regular page before we got a
+			 * reference on it.
+			 */
+			if (unlikely(!PageHead(page_head))) {
+				/* PageHead is cleared after PageTail */
+				smp_rmb();
+				VM_BUG_ON(PageTail(page));
+				goto out_put_head;
+			}
+			/*
+			 * Only run compound_lock on a valid PageHead,
+			 * after having it pinned with
+			 * get_page_unless_zero() above.
+			 */
+			smp_mb();
+			/* page_head wasn't a dangling pointer */
+			flags = compound_lock_irqsave(page_head);
+			if (unlikely(!PageTail(page))) {
+				/* __split_huge_page_refcount run before us */
+				compound_unlock_irqrestore(page_head, flags);
+				VM_BUG_ON(PageHead(page_head));
+			out_put_head:
+				if (put_page_testzero(page_head))
+					__put_single_page(page_head);
+			out_put_single:
+				if (put_page_testzero(page))
+					__put_single_page(page);
+				return;
+			}
+			VM_BUG_ON(page_head != page->first_page);
+			/*
+			 * We can release the refcount taken by
+			 * get_page_unless_zero now that
+			 * split_huge_page_refcount is blocked on the
+			 * compound_lock.
+			 */
+			if (put_page_testzero(page_head))
+				VM_BUG_ON(1);
+			/* __split_huge_page_refcount will wait now */
+			VM_BUG_ON(atomic_read(&page->_count) <= 0);
+			atomic_dec(&page->_count);
+			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+			compound_unlock_irqrestore(page_head, flags);
+			if (put_page_testzero(page_head))
+				__put_compound_page(page_head);
+		} else {
+			/* page_head is a dangling pointer */
+			VM_BUG_ON(PageTail(page));
+			goto out_put_single;
+		}
+	} else if (put_page_testzero(page)) {
+		if (PageHead(page))
+			__put_compound_page(page);
+		else
+			__put_single_page(page);
 	}
 }
 
@@ -75,7 +151,7 @@ void put_page(struct page *page)
 	if (unlikely(PageCompound(page)))
 		put_compound_page(page);
 	else if (put_page_testzero(page))
-		__page_cache_release(page);
+		__put_single_page(page);
 }
 EXPORT_SYMBOL(put_page);