[PATCH] mm: non syncing lock_page()

lock_page needs the caller to have a reference on the page->mapping inode
due to sync_page, ergo set_page_dirty_lock is obviously buggy according to
its comments.

Solve it by introducing a new lock_page_nosync which does not do a sync_page.

akpm: unpleasant solution to an unpleasant problem.  If it goes wrong it could
cause great slowdowns while the lock_page() caller waits for kblockd to
perform the unplug.  And if a filesystem has special sync_page() requirements
(none presently do), permanent hangs are possible.

otoh, set_page_dirty_lock() is usually (always?) called against userspace
pages.  They are always up-to-date, so there shouldn't be any pending read I/O
against these pages.

Signed-off-by: Nick Piggin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Nick Piggin

include/linux/pagemap.h

@@ -130,14 +130,29 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 }
 
 extern void FASTCALL(__lock_page(struct page *page));
+extern void FASTCALL(__lock_page_nosync(struct page *page));
 extern void FASTCALL(unlock_page(struct page *page));
 
+/*
+ * lock_page may only be called if we have the page's inode pinned.
+ */
 static inline void lock_page(struct page *page)
 {
 	might_sleep();
 	if (TestSetPageLocked(page))
 		__lock_page(page);
 }
+
+/*
+ * lock_page_nosync should only be used if we can't pin the page's inode.
+ * Doesn't play quite so well with block device plugging.
+ */
+static inline void lock_page_nosync(struct page *page)
+{
+	might_sleep();
+	if (TestSetPageLocked(page))
+		__lock_page_nosync(page);
+}
 
 /*
  * This is exported only for wait_on_page_locked/wait_on_page_writeback.

mm/filemap.c

@@ -488,6 +488,12 @@ struct page *page_cache_alloc_cold(struct address_space *x)
 EXPORT_SYMBOL(page_cache_alloc_cold);
 #endif
 
+static int __sleep_on_page_lock(void *word)
+{
+	io_schedule();
+	return 0;
+}
+
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
@@ -577,6 +583,17 @@ void fastcall __lock_page(struct page *page)
 }
 EXPORT_SYMBOL(__lock_page);
 
+/*
+ * Variant of lock_page that does not require the caller to hold a reference
+ * on the page's mapping.
+ */
+void fastcall __lock_page_nosync(struct page *page)
+{
+	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	__wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
+							TASK_UNINTERRUPTIBLE);
+}
+
 /**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search

mm/page-writeback.c

@@ -701,7 +701,7 @@ int set_page_dirty_lock(struct page *page)
 {
 	int ret;
 
-	lock_page(page);
+	lock_page_nosync(page);
 	ret = set_page_dirty(page);
 	unlock_page(page);
 	return ret;