Merge branch 'for-2.6.39/core' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.39/core' of git://git.kernel.dk/linux-2.6-block: (65 commits)
  Documentation/iostats.txt: bit-size reference etc.
  cfq-iosched: removing unnecessary think time checking
  cfq-iosched: Don't clear queue stats when preempt.
  blk-throttle: Reset group slice when limits are changed
  blk-cgroup: Only give unaccounted_time under debug
  cfq-iosched: Don't set active queue in preempt
  block: fix non-atomic access to genhd inflight structures
  block: attempt to merge with existing requests on plug flush
  block: NULL dereference on error path in __blkdev_get()
  cfq-iosched: Don't update group weights when on service tree
  fs: assign sb->s_bdi to default_backing_dev_info if the bdi is going away
  block: Require subsystems to explicitly allocate bio_set integrity mempool
  jbd2: finish conversion from WRITE_SYNC_PLUG to WRITE_SYNC and explicit plugging
  jbd: finish conversion from WRITE_SYNC_PLUG to WRITE_SYNC and explicit plugging
  fs: make fsync_buffers_list() plug
  mm: make generic_writepages() use plugging
  blk-cgroup: Add unaccounted time to timeslice_used.
  block: fixup plugging stubs for !CONFIG_BLOCK
  block: remove obsolete comments for blkdev_issue_zeroout.
  blktrace: Use rq->cmd_flags directly in blk_add_trace_rq.
  ...

Fix up conflicts in fs/{aio.c,super.c}

mm/backing-dev.c

@@ -14,17 +14,11 @@
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
-
 struct backing_dev_info default_backing_dev_info = {
 	.name		= "default",
 	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
 	.state		= 0,
 	.capabilities	= BDI_CAP_MAP_COPY,
-	.unplug_io_fn	= default_unplug_io_fn,
 };
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
@@ -604,7 +598,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 	spin_lock(&sb_lock);
 	list_for_each_entry(sb, &super_blocks, s_list) {
 		if (sb->s_bdi == bdi)
-			sb->s_bdi = NULL;
+			sb->s_bdi = &default_backing_dev_info;
 	}
 	spin_unlock(&sb_lock);
 }

mm/filemap.c

@@ -164,45 +164,15 @@ void delete_from_page_cache(struct page *page)
 }
 EXPORT_SYMBOL(delete_from_page_cache);
 
-static int sync_page(void *word)
+static int sleep_on_page(void *word)
 {
-	struct address_space *mapping;
-	struct page *page;
-
-	page = container_of((unsigned long *)word, struct page, flags);
-
-	/*
-	 * page_mapping() is being called without PG_locked held.
-	 * Some knowledge of the state and use of the page is used to
-	 * reduce the requirements down to a memory barrier.
-	 * The danger here is of a stale page_mapping() return value
-	 * indicating a struct address_space different from the one it's
-	 * associated with when it is associated with one.
-	 * After smp_mb(), it's either the correct page_mapping() for
-	 * the page, or an old page_mapping() and the page's own
-	 * page_mapping() has gone NULL.
-	 * The ->sync_page() address_space operation must tolerate
-	 * page_mapping() going NULL. By an amazing coincidence,
-	 * this comes about because none of the users of the page
-	 * in the ->sync_page() methods make essential use of the
-	 * page_mapping(), merely passing the page down to the backing
-	 * device's unplug functions when it's non-NULL, which in turn
-	 * ignore it for all cases but swap, where only page_private(page) is
-	 * of interest. When page_mapping() does go NULL, the entire
-	 * call stack gracefully ignores the page and returns.
-	 * -- wli
-	 */
-	smp_mb();
-	mapping = page_mapping(page);
-	if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
-		mapping->a_ops->sync_page(page);
 	io_schedule();
 	return 0;
 }
 
-static int sync_page_killable(void *word)
+static int sleep_on_page_killable(void *word)
 {
-	sync_page(word);
+	sleep_on_page(word);
 	return fatal_signal_pending(current) ? -EINTR : 0;
 }
 
@@ -558,12 +528,6 @@ struct page *__page_cache_alloc(gfp_t gfp)
 EXPORT_SYMBOL(__page_cache_alloc);
 #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
@@ -591,7 +555,7 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
 
 	if (test_bit(bit_nr, &page->flags))
-		__wait_on_bit(page_waitqueue(page), &wait, sync_page,
+		__wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
@@ -655,17 +619,12 @@ EXPORT_SYMBOL(end_page_writeback);
 /**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
- *
- * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
- * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
- * chances are that on the second loop, the block layer's plug list is empty,
- * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
  */
 void __lock_page(struct page *page)
 {
 	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
+	__wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
@@ -675,24 +634,10 @@ int __lock_page_killable(struct page *page)
 	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
 	return __wait_on_bit_lock(page_waitqueue(page), &wait,
-					sync_page_killable, TASK_KILLABLE);
+					sleep_on_page_killable, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
-/**
- * __lock_page_nosync - get a lock on the page, without calling sync_page()
- * @page: the page to lock
- *
- * Variant of lock_page that does not require the caller to hold a reference
- * on the page's mapping.
- */
-void __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);
-}
-
 int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 			 unsigned int flags)
 {
@@ -1407,12 +1352,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
+	struct blk_plug plug;
 
 	count = 0;
 	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
 	if (retval)
 		return retval;
 
+	blk_start_plug(&plug);
+
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
 		loff_t size;
@@ -1485,6 +1433,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 			break;
 	}
 out:
+	blk_finish_plug(&plug);
 	return retval;
 }
 EXPORT_SYMBOL(generic_file_aio_read);
@@ -2596,11 +2545,13 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct blk_plug plug;
 	ssize_t ret;
 
 	BUG_ON(iocb->ki_pos != pos);
 
 	mutex_lock(&inode->i_mutex);
+	blk_start_plug(&plug);
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
@@ -2611,6 +2562,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err < 0 && ret > 0)
 			ret = err;
 	}
+	blk_finish_plug(&plug);
 	return ret;
 }
 EXPORT_SYMBOL(generic_file_aio_write);

mm/memory-failure.c

@@ -945,7 +945,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 		collect_procs(ppage, &tokill);
 
 	if (hpage != ppage)
-		lock_page_nosync(ppage);
+		lock_page(ppage);
 
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
@@ -1038,7 +1038,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 			 * Check "just unpoisoned", "filter hit", and
 			 * "race with other subpage."
 			 */
-			lock_page_nosync(hpage);
+			lock_page(hpage);
 			if (!PageHWPoison(hpage)
 			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
 			    || (p != hpage && TestSetPageHWPoison(hpage))) {
@@ -1088,7 +1088,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * It's very difficult to mess with pages currently under IO
 	 * and in many cases impossible, so we just avoid it here.
 	 */
-	lock_page_nosync(hpage);
+	lock_page(hpage);
 
 	/*
 	 * unpoison always clear PG_hwpoison inside page lock
@@ -1231,7 +1231,7 @@ int unpoison_memory(unsigned long pfn)
 		return 0;
 	}
 
-	lock_page_nosync(page);
+	lock_page(page);
 	/*
 	 * This test is racy because PG_hwpoison is set outside of page lock.
 	 * That's acceptable because that won't trigger kernel panic. Instead,

mm/nommu.c

@@ -1842,10 +1842,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
-void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-
 unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long pgoff, unsigned long flags)
 {

mm/page-writeback.c

@@ -1040,11 +1040,17 @@ static int __writepage(struct page *page, struct writeback_control *wbc,
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc)
 {
+	struct blk_plug plug;
+	int ret;
+
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
 		return 0;
 
-	return write_cache_pages(mapping, wbc, __writepage, mapping);
+	blk_start_plug(&plug);
+	ret = write_cache_pages(mapping, wbc, __writepage, mapping);
+	blk_finish_plug(&plug);
+	return ret;
 }
 
 EXPORT_SYMBOL(generic_writepages);
@@ -1251,7 +1257,7 @@ int set_page_dirty_lock(struct page *page)
 {
 	int ret;
 
-	lock_page_nosync(page);
+	lock_page(page);
 	ret = set_page_dirty(page);
 	unlock_page(page);
 	return ret;

mm/page_io.c

@@ -106,7 +106,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		goto out;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		rw |= REQ_SYNC | REQ_UNPLUG;
+		rw |= REQ_SYNC;
 	count_vm_event(PSWPOUT);
 	set_page_writeback(page);
 	unlock_page(page);

mm/readahead.c

@@ -109,9 +109,12 @@ EXPORT_SYMBOL(read_cache_pages);
 static int read_pages(struct address_space *mapping, struct file *filp,
 		struct list_head *pages, unsigned nr_pages)
 {
+	struct blk_plug plug;
 	unsigned page_idx;
 	int ret;
 
+	blk_start_plug(&plug);
+
 	if (mapping->a_ops->readpages) {
 		ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
 		/* Clean up the remaining pages */
@@ -129,7 +132,10 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 		page_cache_release(page);
 	}
 	ret = 0;
+
 out:
+	blk_finish_plug(&plug);
+
 	return ret;
 }
 
@@ -554,17 +560,5 @@ page_cache_async_readahead(struct address_space *mapping,
 
 	/* do read-ahead */
 	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
-
-#ifdef CONFIG_BLOCK
-	/*
-	 * Normally the current page is !uptodate and lock_page() will be
-	 * immediately called to implicitly unplug the device. However this
-	 * is not always true for RAID conifgurations, where data arrives
-	 * not strictly in their submission order. In this case we need to
-	 * explicitly kick off the IO.
-	 */
-	if (PageUptodate(page))
-		blk_run_backing_dev(mapping->backing_dev_info, NULL);
-#endif
 }
 EXPORT_SYMBOL_GPL(page_cache_async_readahead);

mm/shmem.c

@@ -224,7 +224,6 @@ static const struct vm_operations_struct shmem_vm_ops;
 static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
 	.ra_pages	= 0,	/* No readahead */
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-	.unplug_io_fn	= default_unplug_io_fn,
 };
 
 static LIST_HEAD(shmem_swaplist);

mm/swap_state.c

@@ -24,12 +24,10 @@
 
 /*
  * swapper_space is a fiction, retained to simplify the path through
- * vmscan's shrink_page_list, to make sync_page look nicer, and to allow
- * future use of radix_tree tags in the swap cache.
+ * vmscan's shrink_page_list.
  */
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.sync_page	= block_sync_page,
 	.set_page_dirty	= __set_page_dirty_nobuffers,
 	.migratepage	= migrate_page,
 };
@@ -37,7 +35,6 @@ static const struct address_space_operations swap_aops = {
 static struct backing_dev_info swap_backing_dev_info = {
 	.name		= "swap",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-	.unplug_io_fn	= swap_unplug_io_fn,
 };
 
 struct address_space swapper_space = {

mm/swapfile.c

@@ -94,39 +94,6 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
 	return ret;
 }
 
-/*
- * We need this because the bdev->unplug_fn can sleep and we cannot
- * hold swap_lock while calling the unplug_fn. And swap_lock
- * cannot be turned into a mutex.
- */
-static DECLARE_RWSEM(swap_unplug_sem);
-
-void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
-{
-	swp_entry_t entry;
-
-	down_read(&swap_unplug_sem);
-	entry.val = page_private(page);
-	if (PageSwapCache(page)) {
-		struct block_device *bdev = swap_info[swp_type(entry)]->bdev;
-		struct backing_dev_info *bdi;
-
-		/*
-		 * If the page is removed from swapcache from under us (with a
-		 * racy try_to_unuse/swapoff) we need an additional reference
-		 * count to avoid reading garbage from page_private(page) above.
-		 * If the WARN_ON triggers during a swapoff it maybe the race
-		 * condition and it's harmless. However if it triggers without
-		 * swapoff it signals a problem.
-		 */
-		WARN_ON(page_count(page) <= 1);
-
-		bdi = bdev->bd_inode->i_mapping->backing_dev_info;
-		blk_run_backing_dev(bdi, page);
-	}
-	up_read(&swap_unplug_sem);
-}
-
 /*
  * swapon tell device that all the old swap contents can be discarded,
  * to allow the swap device to optimize its wear-levelling.
@@ -1662,10 +1629,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		goto out_dput;
 	}
 
-	/* wait for any unplug function to finish */
-	down_write(&swap_unplug_sem);
-	up_write(&swap_unplug_sem);
-
 	destroy_swap_extents(p);
 	if (p->flags & SWP_CONTINUED)
 		free_swap_count_continuations(p);

mm/vmscan.c

@@ -358,7 +358,7 @@ static int may_write_to_queue(struct backing_dev_info *bdi,
 static void handle_write_error(struct address_space *mapping,
 				struct page *page, int error)
 {
-	lock_page_nosync(page);
+	lock_page(page);
 	if (page_mapping(page) == mapping)
 		mapping_set_error(mapping, error);
 	unlock_page(page);