page-flags: define PG_locked behavior on compound pages

lock_page() must operate on the whole compound page.  It doesn't make
much sense to lock part of compound page.  Change code to use head
page's PG_locked, if tail page is passed.

This patch also gets rid of custom helper functions --
__set_page_locked() and __clear_page_locked().  They are replaced with
helpers generated by __SETPAGEFLAG/__CLEARPAGEFLAG.  Tail pages to these
helper would trigger VM_BUG_ON().

SLUB uses PG_locked as a bit spin locked.  IIUC, tail pages should never
appear there.  VM_BUG_ON() is added to make sure that this assumption is
correct.

[akpm@linux-foundation.org: fix fs/cifs/file.c]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.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: 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>
Cc: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/cifs/file.c

@@ -3391,13 +3391,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	 * should have access to this page, we're safe to simply set
 	 * PG_locked without checking it first.
 	 */
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	rc = add_to_page_cache_locked(page, mapping,
 				      page->index, gfp);
 
 	/* give up if we can't stick it in the cache */
 	if (rc) {
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 		return rc;
 	}
 
@@ -3418,9 +3418,9 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 		if (*bytes + PAGE_CACHE_SIZE > rsize)
 			break;
 
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
-			__clear_page_locked(page);
+			__ClearPageLocked(page);
 			break;
 		}
 		list_move_tail(&page->lru, tmplist);

include/linux/page-flags.h

@@ -256,7 +256,7 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; }
 #define TESTSCFLAG_FALSE(uname)						\
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
-TESTPAGEFLAG(Locked, locked, PF_ANY)
+__PAGEFLAG(Locked, locked, PF_NO_TAIL)
 PAGEFLAG(Error, error, PF_ANY) TESTCLEARFLAG(Error, error, PF_ANY)
 PAGEFLAG(Referenced, referenced, PF_ANY) TESTCLEARFLAG(Referenced, referenced, PF_ANY)
 	__SETPAGEFLAG(Referenced, referenced, PF_ANY)

include/linux/pagemap.h

@@ -433,18 +433,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
 
-static inline void __set_page_locked(struct page *page)
-{
-	__set_bit(PG_locked, &page->flags);
-}
-
-static inline void __clear_page_locked(struct page *page)
-{
-	__clear_bit(PG_locked, &page->flags);
-}
-
 static inline int trylock_page(struct page *page)
 {
+	page = compound_head(page);
 	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
 }
 
@@ -497,9 +488,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page,
 
 static inline int wait_on_page_locked_killable(struct page *page)
 {
-	if (PageLocked(page))
+	if (!PageLocked(page))
-		return wait_on_page_bit_killable(page, PG_locked);
+		return 0;
-	return 0;
+	return wait_on_page_bit_killable(compound_head(page), PG_locked);
 }
 
 extern wait_queue_head_t *page_waitqueue(struct page *page);
@@ -518,7 +509,7 @@ static inline void wake_up_page(struct page *page, int bit)
 static inline void wait_on_page_locked(struct page *page)
 {
 	if (PageLocked(page))
-		wait_on_page_bit(page, PG_locked);
+		wait_on_page_bit(compound_head(page), PG_locked);
 }
 
 /* 
@@ -664,17 +655,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
- * the page is new, so we can just run __set_page_locked() against it.
+ * the page is new, so we can just run __SetPageLocked() against it.
  */
 static inline int add_to_page_cache(struct page *page,
 		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
 {
 	int error;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
 	if (unlikely(error))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	return error;
 }
 

mm/filemap.c

@@ -682,11 +682,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	void *shadow = NULL;
 	int ret;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	ret = __add_to_page_cache_locked(page, mapping, offset,
 					 gfp_mask, &shadow);
 	if (unlikely(ret))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	else {
 		/*
 		 * The page might have been evicted from cache only
@@ -809,6 +809,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  */
 void unlock_page(struct page *page)
 {
+	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	clear_bit_unlock(PG_locked, &page->flags);
 	smp_mb__after_atomic();
@@ -873,18 +874,20 @@ EXPORT_SYMBOL_GPL(page_endio);
  */
 void __lock_page(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
+	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
 
 int __lock_page_killable(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	return __wait_on_bit_lock(page_waitqueue(page), &wait,
+	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
 					bit_wait_io, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);

mm/ksm.c

@@ -1899,7 +1899,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 	}
 
 	return new_page;

mm/memory-failure.c

@@ -1166,7 +1166,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * We ignore non-LRU pages for good reasons.
 	 * - PG_locked is only well defined for LRU pages and a few others
-	 * - to avoid races with __set_page_locked()
+	 * - to avoid races with __SetPageLocked()
 	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.

mm/migrate.c

@@ -1767,7 +1767,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		flush_tlb_range(vma, mmun_start, mmun_end);
 
 	/* Prepare a page as a migration target */
-	__set_page_locked(new_page);
+	__SetPageLocked(new_page);
 	SetPageSwapBacked(new_page);
 
 	/* anon mapping, we can simply copy page->mapping to the new page: */

mm/shmem.c

@@ -1085,7 +1085,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	copy_highpage(newpage, oldpage);
 	flush_dcache_page(newpage);
 
-	__set_page_locked(newpage);
+	__SetPageLocked(newpage);
 	SetPageUptodate(newpage);
 	SetPageSwapBacked(newpage);
 	set_page_private(newpage, swap_index);
@@ -1277,7 +1277,7 @@ repeat:
 		}
 
 		__SetPageSwapBacked(page);
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 

mm/slub.c

@@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
  */
 static __always_inline void slab_lock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	bit_spin_lock(PG_locked, &page->flags);
 }
 
 static __always_inline void slab_unlock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	__bit_spin_unlock(PG_locked, &page->flags);
 }
 

mm/swap_state.c

@@ -353,7 +353,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 
 		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 		SetPageSwapBacked(new_page);
 		err = __add_to_swap_cache(new_page, entry);
 		if (likely(!err)) {
@@ -367,7 +367,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 		radix_tree_preload_end();
 		ClearPageSwapBacked(new_page);
-		__clear_page_locked(new_page);
+		__ClearPageLocked(new_page);
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.

mm/vmscan.c

@@ -1184,7 +1184,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * we obviously don't have to worry about waking up a process
 		 * waiting on the page lock, because there are no references.
 		 */
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 free_it:
 		nr_reclaimed++;