Merge branch 'for-4.2/writeback' of git://git.kernel.dk/linux-block

Pull cgroup writeback support from Jens Axboe:
 "This is the big pull request for adding cgroup writeback support.

  This code has been in development for a long time, and it has been
  simmering in for-next for a good chunk of this cycle too.  This is one
  of those problems that has been talked about for at least half a
  decade, finally there's a solution and code to go with it.

  Also see last weeks writeup on LWN:

        http://lwn.net/Articles/648292/"

* 'for-4.2/writeback' of git://git.kernel.dk/linux-block: (85 commits)
  writeback, blkio: add documentation for cgroup writeback support
  vfs, writeback: replace FS_CGROUP_WRITEBACK with SB_I_CGROUPWB
  writeback: do foreign inode detection iff cgroup writeback is enabled
  v9fs: fix error handling in v9fs_session_init()
  bdi: fix wrong error return value in cgwb_create()
  buffer: remove unusued 'ret' variable
  writeback: disassociate inodes from dying bdi_writebacks
  writeback: implement foreign cgroup inode bdi_writeback switching
  writeback: add lockdep annotation to inode_to_wb()
  writeback: use unlocked_inode_to_wb transaction in inode_congested()
  writeback: implement unlocked_inode_to_wb transaction and use it for stat updates
  writeback: implement [locked_]inode_to_wb_and_lock_list()
  writeback: implement foreign cgroup inode detection
  writeback: make writeback_control track the inode being written back
  writeback: relocate wb[_try]_get(), wb_put(), inode_{attach|detach}_wb()
  mm: vmscan: disable memcg direct reclaim stalling if cgroup writeback support is in use
  writeback: implement memcg writeback domain based throttling
  writeback: reset wb_domain->dirty_limit[_tstmp] when memcg domain size changes
  writeback: implement memcg wb_domain
  writeback: update wb_over_bg_thresh() to use wb_domain aware operations
  ...

27 files changed, 1079 insertions, 274 deletions

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 620d93489539..8aa56bb6e861 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -320,31 +320,21 @@ fail_option_alloc:
 struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		  const char *dev_name, char *data)
 {
-	int retval = -EINVAL;
 	struct p9_fid *fid;
-	int rc;
+	int rc = -ENOMEM;
 
 	v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
 	if (!v9ses->uname)
-		return ERR_PTR(-ENOMEM);
+		goto err_names;
 
 	v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
-	if (!v9ses->aname) {
-		kfree(v9ses->uname);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!v9ses->aname)
+		goto err_names;
 	init_rwsem(&v9ses->rename_sem);
 
 	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
-	if (rc) {
-		kfree(v9ses->aname);
-		kfree(v9ses->uname);
-		return ERR_PTR(rc);
-	}
-
-	spin_lock(&v9fs_sessionlist_lock);
-	list_add(&v9ses->slist, &v9fs_sessionlist);
-	spin_unlock(&v9fs_sessionlist_lock);
+	if (rc)
+		goto err_names;
 
 	v9ses->uid = INVALID_UID;
 	v9ses->dfltuid = V9FS_DEFUID;
@@ -352,10 +342,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 
 	v9ses->clnt = p9_client_create(dev_name, data);
 	if (IS_ERR(v9ses->clnt)) {
-		retval = PTR_ERR(v9ses->clnt);
-		v9ses->clnt = NULL;
+		rc = PTR_ERR(v9ses->clnt);
 		p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
-		goto error;
+		goto err_bdi;
 	}
 
 	v9ses->flags = V9FS_ACCESS_USER;
@@ -368,10 +357,8 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	}
 
 	rc = v9fs_parse_options(v9ses, data);
-	if (rc < 0) {
-		retval = rc;
-		goto error;
-	}
+	if (rc < 0)
+		goto err_clnt;
 
 	v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
 
@@ -405,10 +392,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID,
 							v9ses->aname);
 	if (IS_ERR(fid)) {
-		retval = PTR_ERR(fid);
-		fid = NULL;
+		rc = PTR_ERR(fid);
 		p9_debug(P9_DEBUG_ERROR, "cannot attach\n");
-		goto error;
+		goto err_clnt;
 	}
 
 	if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE)
@@ -420,12 +406,20 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	/* register the session for caching */
 	v9fs_cache_session_get_cookie(v9ses);
 #endif
+	spin_lock(&v9fs_sessionlist_lock);
+	list_add(&v9ses->slist, &v9fs_sessionlist);
+	spin_unlock(&v9fs_sessionlist_lock);
 
 	return fid;
 
-error:
+err_clnt:
+	p9_client_destroy(v9ses->clnt);
+err_bdi:
 	bdi_destroy(&v9ses->bdi);
-	return ERR_PTR(retval);
+err_names:
+	kfree(v9ses->uname);
+	kfree(v9ses->aname);
+	return ERR_PTR(rc);
 }
 
 /**
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index e99a338a4638..bf495cedec26 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -130,11 +130,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	fid = v9fs_session_init(v9ses, dev_name, data);
 	if (IS_ERR(fid)) {
 		retval = PTR_ERR(fid);
-		/*
-		 * we need to call session_close to tear down some
-		 * of the data structure setup by session_init
-		 */
-		goto close_session;
+		goto free_session;
 	}
 
 	sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
@@ -195,8 +191,8 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 
 clunk_fid:
 	p9_client_clunk(fid);
-close_session:
 	v9fs_session_close(v9ses);
+free_session:
 	kfree(v9ses);
 	return ERR_PTR(retval);
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c7e4163ede87..f04c873a7365 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -14,6 +14,7 @@
 #include <linux/device_cgroup.h>
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/module.h>
 #include <linux/blkpg.h>
 #include <linux/magic.h>
@@ -546,7 +547,8 @@ static struct file_system_type bd_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-static struct super_block *blockdev_superblock __read_mostly;
+struct super_block *blockdev_superblock __read_mostly;
+EXPORT_SYMBOL_GPL(blockdev_superblock);
 
 void __init bdev_cache_init(void)
 {
@@ -687,11 +689,6 @@ static struct block_device *bd_acquire(struct inode *inode)
 	return bdev;
 }
 
-int sb_is_blkdev_sb(struct super_block *sb)
-{
-	return sb == blockdev_superblock;
-}
-
 /* Call when you free inode */
 
 void bd_forget(struct inode *inode)
diff --git a/fs/buffer.c b/fs/buffer.c
index f96173ad62d9..1cf7a53a0277 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -30,6 +30,7 @@
 #include <linux/quotaops.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
+#include <linux/backing-dev.h>
 #include <linux/writeback.h>
 #include <linux/hash.h>
 #include <linux/suspend.h>
@@ -44,6 +45,9 @@
 #include <trace/events/block.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
+static int submit_bh_wbc(int rw, struct buffer_head *bh,
+			 unsigned long bio_flags,
+			 struct writeback_control *wbc);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
@@ -623,21 +627,22 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  *
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
+ *
+ * The caller must hold mem_cgroup_begin_page_stat() lock.
  */
-static void __set_page_dirty(struct page *page,
-		struct address_space *mapping, int warn)
+static void __set_page_dirty(struct page *page, struct address_space *mapping,
+			     struct mem_cgroup *memcg, int warn)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping);
+		account_page_dirtied(page, mapping, memcg);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 
 /*
@@ -668,6 +673,7 @@ static void __set_page_dirty(struct page *page,
 int __set_page_dirty_buffers(struct page *page)
 {
 	int newly_dirty;
+	struct mem_cgroup *memcg;
 	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
@@ -683,11 +689,22 @@ int __set_page_dirty_buffers(struct page *page)
 			bh = bh->b_this_page;
 		} while (bh != head);
 	}
+	/*
+	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
+	 * per-memcg dirty page counters.
+	 */
+	memcg = mem_cgroup_begin_page_stat(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
 	if (newly_dirty)
-		__set_page_dirty(page, mapping, 1);
+		__set_page_dirty(page, mapping, memcg, 1);
+
+	mem_cgroup_end_page_stat(memcg);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
 	return newly_dirty;
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);
@@ -1158,11 +1175,18 @@ void mark_buffer_dirty(struct buffer_head *bh)
 
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
+		struct address_space *mapping = NULL;
+		struct mem_cgroup *memcg;
+
+		memcg = mem_cgroup_begin_page_stat(page);
 		if (!TestSetPageDirty(page)) {
-			struct address_space *mapping = page_mapping(page);
+			mapping = page_mapping(page);
 			if (mapping)
-				__set_page_dirty(page, mapping, 0);
+				__set_page_dirty(page, mapping, memcg, 0);
 		}
+		mem_cgroup_end_page_stat(memcg);
+		if (mapping)
+			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
 }
 EXPORT_SYMBOL(mark_buffer_dirty);
@@ -1684,8 +1708,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	struct buffer_head *bh, *head;
 	unsigned int blocksize, bbits;
 	int nr_underway = 0;
-	int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
-			WRITE_SYNC : WRITE);
+	int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
 
 	head = create_page_buffers(page, inode,
 					(1 << BH_Dirty)|(1 << BH_Uptodate));
@@ -1774,7 +1797,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(write_op, bh);
+			submit_bh_wbc(write_op, bh, 0, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -1828,7 +1851,7 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh(write_op, bh);
+			submit_bh_wbc(write_op, bh, 0, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -2993,7 +3016,8 @@ void guard_bio_eod(int rw, struct bio *bio)
 	}
 }
 
-int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
+static int submit_bh_wbc(int rw, struct buffer_head *bh,
+			 unsigned long bio_flags, struct writeback_control *wbc)
 {
 	struct bio *bio;
 
@@ -3015,6 +3039,11 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	 */
 	bio = bio_alloc(GFP_NOIO, 1);
 
+	if (wbc) {
+		wbc_init_bio(wbc, bio);
+		wbc_account_io(wbc, bh->b_page, bh->b_size);
+	}
+
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
 	bio->bi_io_vec[0].bv_page = bh->b_page;
@@ -3039,11 +3068,16 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	submit_bio(rw, bio);
 	return 0;
 }
+
+int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
+{
+	return submit_bh_wbc(rw, bh, bio_flags, NULL);
+}
 EXPORT_SYMBOL_GPL(_submit_bh);
 
 int submit_bh(int rw, struct buffer_head *bh)
 {
-	return _submit_bh(rw, bh, 0);
+	return submit_bh_wbc(rw, bh, 0, NULL);
 }
 EXPORT_SYMBOL(submit_bh);
 
@@ -3232,8 +3266,8 @@ int try_to_free_buffers(struct page *page)
 	 * to synchronise against __set_page_dirty_buffers and prevent the
 	 * dirty bit from being lost.
 	 */
-	if (ret && TestClearPageDirty(page))
-		account_page_cleaned(page, mapping);
+	if (ret)
+		cancel_dirty_page(page);
 	spin_unlock(&mapping->private_lock);
 out:
 	if (buffers_to_free) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index d0e746e96511..900e19cf9ef6 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -882,6 +882,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
 		 MS_POSIXACL : 0);
+	sb->s_iflags |= SB_I_CGROUPWB;
 
 	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
 	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index d86d2622f826..aadb72828834 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/fiemap.h>
+#include <linux/backing-dev.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 #include "xattr.h"
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 1c535fa67640..f6aedf88da43 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -26,6 +26,7 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/backing-dev.h>
 #include <trace/events/ext4.h>
 
 #ifdef CONFIG_EXT4_DEBUG
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 90ec13fe8ac7..a7b4b6e10269 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/parser.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index d9c52424bac2..7dd63b794bfb 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -53,7 +53,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 							PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == DIRTY_DENTS) {
-		if (sbi->sb->s_bdi->dirty_exceeded)
+		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
 		mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
@@ -70,7 +70,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 				sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else {
-		if (sbi->sb->s_bdi->dirty_exceeded)
+		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
 	}
 	return res;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 849635778118..79e7b879a753 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -9,6 +9,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 
 /* constant macro */
 #define NULL_SEGNO			((unsigned int)(~0))
@@ -714,7 +715,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {
-	if (sbi->sb->s_bdi->dirty_exceeded)
+	if (sbi->sb->s_bdi->wb.dirty_exceeded)
 		return 0;
 
 	if (type == DATA)
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 442d50a0e33e..a08f1039909a 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -11,6 +11,7 @@
 #include <linux/compat.h>
 #include <linux/mount.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include "fat.h"
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index c06774658345..509411dd3698 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -18,6 +18,7 @@
 #include <linux/parser.h>
 #include <linux/uio.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <asm/unaligned.h>
 #include "fat.h"
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 32a8bbd7a9ad..f0520bcf2094 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/tracepoint.h>
 #include <linux/device.h>
+#include <linux/memcontrol.h>
 #include "internal.h"
 
 /*
@@ -34,6 +35,10 @@
  */
 #define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
 
+struct wb_completion {
+	atomic_t		cnt;
+};
+
 /*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
@@ -47,13 +52,29 @@ struct wb_writeback_work {
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
+	unsigned int auto_free:1;	/* free on completion */
+	unsigned int single_wait:1;
+	unsigned int single_done:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
-	struct completion *done;	/* set if the caller waits */
+	struct wb_completion *done;	/* set if the caller waits */
 };
 
 /*
+ * If one wants to wait for one or more wb_writeback_works, each work's
+ * ->done should be set to a wb_completion defined using the following
+ * macro.  Once all work items are issued with wb_queue_work(), the caller
+ * can wait for the completion of all using wb_wait_for_completion().  Work
+ * items which are waited upon aren't freed automatically on completion.
+ */
+#define DEFINE_WB_COMPLETION_ONSTACK(cmpl)				\
+	struct wb_completion cmpl = {					\
+		.cnt		= ATOMIC_INIT(1),			\
+	}
+
+
+/*
  * If an inode is constantly having its pages dirtied, but then the
  * updates stop dirtytime_expire_interval seconds in the past, it's
  * possible for the worst case time between when an inode has its
@@ -65,35 +86,6 @@ struct wb_writeback_work {
  */
 unsigned int dirtytime_expire_interval = 12 * 60 * 60;
 
-/**
- * writeback_in_progress - determine whether there is writeback in progress
- * @bdi: the device's backing_dev_info structure.
- *
- * Determine whether there is writeback waiting to be handled against a
- * backing device.
- */
-int writeback_in_progress(struct backing_dev_info *bdi)
-{
-	return test_bit(BDI_writeback_running, &bdi->state);
-}
-EXPORT_SYMBOL(writeback_in_progress);
-
-struct backing_dev_info *inode_to_bdi(struct inode *inode)
-{
-	struct super_block *sb;
-
-	if (!inode)
-		return &noop_backing_dev_info;
-
-	sb = inode->i_sb;
-#ifdef CONFIG_BLOCK
-	if (sb_is_blkdev_sb(sb))
-		return blk_get_backing_dev_info(I_BDEV(inode));
-#endif
-	return sb->s_bdi;
-}
-EXPORT_SYMBOL_GPL(inode_to_bdi);
-
 static inline struct inode *wb_inode(struct list_head *head)
 {
 	return list_entry(head, struct inode, i_wb_list);
@@ -109,45 +101,830 @@ static inline struct inode *wb_inode(struct list_head *head)
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
 
-static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+static bool wb_io_lists_populated(struct bdi_writeback *wb)
+{
+	if (wb_has_dirty_io(wb)) {
+		return false;
+	} else {
+		set_bit(WB_has_dirty_io, &wb->state);
+		WARN_ON_ONCE(!wb->avg_write_bandwidth);
+		atomic_long_add(wb->avg_write_bandwidth,
+				&wb->bdi->tot_write_bandwidth);
+		return true;
+	}
+}
+
+static void wb_io_lists_depopulated(struct bdi_writeback *wb)
 {
-	spin_lock_bh(&bdi->wb_lock);
-	if (test_bit(BDI_registered, &bdi->state))
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
-	spin_unlock_bh(&bdi->wb_lock);
+	if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
+	    list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) {
+		clear_bit(WB_has_dirty_io, &wb->state);
+		WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth,
+					&wb->bdi->tot_write_bandwidth) < 0);
+	}
 }
 
-static void bdi_queue_work(struct backing_dev_info *bdi,
-			   struct wb_writeback_work *work)
+/**
+ * inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
+ * @inode: inode to be moved
+ * @wb: target bdi_writeback
+ * @head: one of @wb->b_{dirty|io|more_io}
+ *
+ * Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
+ * Returns %true if @inode is the first occupant of the !dirty_time IO
+ * lists; otherwise, %false.
+ */
+static bool inode_wb_list_move_locked(struct inode *inode,
+				      struct bdi_writeback *wb,
+				      struct list_head *head)
 {
-	trace_writeback_queue(bdi, work);
+	assert_spin_locked(&wb->list_lock);
+
+	list_move(&inode->i_wb_list, head);
 
-	spin_lock_bh(&bdi->wb_lock);
-	if (!test_bit(BDI_registered, &bdi->state)) {
-		if (work->done)
-			complete(work->done);
+	/* dirty_time doesn't count as dirty_io until expiration */
+	if (head != &wb->b_dirty_time)
+		return wb_io_lists_populated(wb);
+
+	wb_io_lists_depopulated(wb);
+	return false;
+}
+
+/**
+ * inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
+ * @inode: inode to be removed
+ * @wb: bdi_writeback @inode is being removed from
+ *
+ * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
+ * clear %WB_has_dirty_io if all are empty afterwards.
+ */
+static void inode_wb_list_del_locked(struct inode *inode,
+				     struct bdi_writeback *wb)
+{
+	assert_spin_locked(&wb->list_lock);
+
+	list_del_init(&inode->i_wb_list);
+	wb_io_lists_depopulated(wb);
+}
+
+static void wb_wakeup(struct bdi_writeback *wb)
+{
+	spin_lock_bh(&wb->work_lock);
+	if (test_bit(WB_registered, &wb->state))
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	spin_unlock_bh(&wb->work_lock);
+}
+
+static void wb_queue_work(struct bdi_writeback *wb,
+			  struct wb_writeback_work *work)
+{
+	trace_writeback_queue(wb->bdi, work);
+
+	spin_lock_bh(&wb->work_lock);
+	if (!test_bit(WB_registered, &wb->state)) {
+		if (work->single_wait)
+			work->single_done = 1;
 		goto out_unlock;
 	}
-	list_add_tail(&work->list, &bdi->work_list);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	if (work->done)
+		atomic_inc(&work->done->cnt);
+	list_add_tail(&work->list, &wb->work_list);
+	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 out_unlock:
-	spin_unlock_bh(&bdi->wb_lock);
+	spin_unlock_bh(&wb->work_lock);
+}
+
+/**
+ * wb_wait_for_completion - wait for completion of bdi_writeback_works
+ * @bdi: bdi work items were issued to
+ * @done: target wb_completion
+ *
+ * Wait for one or more work items issued to @bdi with their ->done field
+ * set to @done, which should have been defined with
+ * DEFINE_WB_COMPLETION_ONSTACK().  This function returns after all such
+ * work items are completed.  Work items which are waited upon aren't freed
+ * automatically on completion.
+ */
+static void wb_wait_for_completion(struct backing_dev_info *bdi,
+				   struct wb_completion *done)
+{
+	atomic_dec(&done->cnt);		/* put down the initial count */
+	wait_event(bdi->wb_waitq, !atomic_read(&done->cnt));
+}
+
+#ifdef CONFIG_CGROUP_WRITEBACK
+
+/* parameters for foreign inode detection, see wb_detach_inode() */
+#define WB_FRN_TIME_SHIFT	13	/* 1s = 2^13, upto 8 secs w/ 16bit */
+#define WB_FRN_TIME_AVG_SHIFT	3	/* avg = avg * 7/8 + new * 1/8 */
+#define WB_FRN_TIME_CUT_DIV	2	/* ignore rounds < avg / 2 */
+#define WB_FRN_TIME_PERIOD	(2 * (1 << WB_FRN_TIME_SHIFT))	/* 2s */
+
+#define WB_FRN_HIST_SLOTS	16	/* inode->i_wb_frn_history is 16bit */
+#define WB_FRN_HIST_UNIT	(WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS)
+					/* each slot's duration is 2s / 16 */
+#define WB_FRN_HIST_THR_SLOTS	(WB_FRN_HIST_SLOTS / 2)
+					/* if foreign slots >= 8, switch */
+#define WB_FRN_HIST_MAX_SLOTS	(WB_FRN_HIST_THR_SLOTS / 2 + 1)
+					/* one round can affect upto 5 slots */
+
+void __inode_attach_wb(struct inode *inode, struct page *page)
+{
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
+	struct bdi_writeback *wb = NULL;
+
+	if (inode_cgwb_enabled(inode)) {
+		struct cgroup_subsys_state *memcg_css;
+
+		if (page) {
+			memcg_css = mem_cgroup_css_from_page(page);
+			wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+		} else {
+			/* must pin memcg_css, see wb_get_create() */
+			memcg_css = task_get_css(current, memory_cgrp_id);
+			wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+			css_put(memcg_css);
+		}
+	}
+
+	if (!wb)
+		wb = &bdi->wb;
+
+	/*
+	 * There may be multiple instances of this function racing to
+	 * update the same inode.  Use cmpxchg() to tell the winner.
+	 */
+	if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
+		wb_put(wb);
+}
+
+/**
+ * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it
+ * @inode: inode of interest with i_lock held
+ *
+ * Returns @inode's wb with its list_lock held.  @inode->i_lock must be
+ * held on entry and is released on return.  The returned wb is guaranteed
+ * to stay @inode's associated wb until its list_lock is released.
+ */
+static struct bdi_writeback *
+locked_inode_to_wb_and_lock_list(struct inode *inode)
+	__releases(&inode->i_lock)
+	__acquires(&wb->list_lock)
+{
+	while (true) {
+		struct bdi_writeback *wb = inode_to_wb(inode);
+
+		/*
+		 * inode_to_wb() association is protected by both
+		 * @inode->i_lock and @wb->list_lock but list_lock nests
+		 * outside i_lock.  Drop i_lock and verify that the
+		 * association hasn't changed after acquiring list_lock.
+		 */
+		wb_get(wb);
+		spin_unlock(&inode->i_lock);
+		spin_lock(&wb->list_lock);
+		wb_put(wb);		/* not gonna deref it anymore */
+
+		/* i_wb may have changed inbetween, can't use inode_to_wb() */
+		if (likely(wb == inode->i_wb))
+			return wb;	/* @inode already has ref */
+
+		spin_unlock(&wb->list_lock);
+		cpu_relax();
+		spin_lock(&inode->i_lock);
+	}
+}
+
+/**
+ * inode_to_wb_and_lock_list - determine an inode's wb and lock it
+ * @inode: inode of interest
+ *
+ * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held
+ * on entry.
+ */
+static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode)
+	__acquires(&wb->list_lock)
+{
+	spin_lock(&inode->i_lock);
+	return locked_inode_to_wb_and_lock_list(inode);
+}
+
+struct inode_switch_wbs_context {
+	struct inode		*inode;
+	struct bdi_writeback	*new_wb;
+
+	struct rcu_head		rcu_head;
+	struct work_struct	work;
+};
+
+static void inode_switch_wbs_work_fn(struct work_struct *work)
+{
+	struct inode_switch_wbs_context *isw =
+		container_of(work, struct inode_switch_wbs_context, work);
+	struct inode *inode = isw->inode;
+	struct address_space *mapping = inode->i_mapping;
+	struct bdi_writeback *old_wb = inode->i_wb;
+	struct bdi_writeback *new_wb = isw->new_wb;
+	struct radix_tree_iter iter;
+	bool switched = false;
+	void **slot;
+
+	/*
+	 * By the time control reaches here, RCU grace period has passed
+	 * since I_WB_SWITCH assertion and all wb stat update transactions
+	 * between unlocked_inode_to_wb_begin/end() are guaranteed to be
+	 * synchronizing against mapping->tree_lock.
+	 *
+	 * Grabbing old_wb->list_lock, inode->i_lock and mapping->tree_lock
+	 * gives us exclusion against all wb related operations on @inode
+	 * including IO list manipulations and stat updates.
+	 */
+	if (old_wb < new_wb) {
+		spin_lock(&old_wb->list_lock);
+		spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock(&new_wb->list_lock);
+		spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING);
+	}
+	spin_lock(&inode->i_lock);
+	spin_lock_irq(&mapping->tree_lock);
+
+	/*
+	 * Once I_FREEING is visible under i_lock, the eviction path owns
+	 * the inode and we shouldn't modify ->i_wb_list.
+	 */
+	if (unlikely(inode->i_state & I_FREEING))
+		goto skip_switch;
+
+	/*
+	 * Count and transfer stats.  Note that PAGECACHE_TAG_DIRTY points
+	 * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to
+	 * pages actually under underwriteback.
+	 */
+	radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, 0,
+				   PAGECACHE_TAG_DIRTY) {
+		struct page *page = radix_tree_deref_slot_protected(slot,
+							&mapping->tree_lock);
+		if (likely(page) && PageDirty(page)) {
+			__dec_wb_stat(old_wb, WB_RECLAIMABLE);
+			__inc_wb_stat(new_wb, WB_RECLAIMABLE);
+		}
+	}
+
+	radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, 0,
+				   PAGECACHE_TAG_WRITEBACK) {
+		struct page *page = radix_tree_deref_slot_protected(slot,
+							&mapping->tree_lock);
+		if (likely(page)) {
+			WARN_ON_ONCE(!PageWriteback(page));
+			__dec_wb_stat(old_wb, WB_WRITEBACK);
+			__inc_wb_stat(new_wb, WB_WRITEBACK);
+		}
+	}
+
+	wb_get(new_wb);
+
+	/*
+	 * Transfer to @new_wb's IO list if necessary.  The specific list
+	 * @inode was on is ignored and the inode is put on ->b_dirty which
+	 * is always correct including from ->b_dirty_time.  The transfer
+	 * preserves @inode->dirtied_when ordering.
+	 */
+	if (!list_empty(&inode->i_wb_list)) {
+		struct inode *pos;
+
+		inode_wb_list_del_locked(inode, old_wb);
+		inode->i_wb = new_wb;
+		list_for_each_entry(pos, &new_wb->b_dirty, i_wb_list)
+			if (time_after_eq(inode->dirtied_when,
+					  pos->dirtied_when))
+				break;
+		inode_wb_list_move_locked(inode, new_wb, pos->i_wb_list.prev);
+	} else {
+		inode->i_wb = new_wb;
+	}
+
+	/* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */
+	inode->i_wb_frn_winner = 0;
+	inode->i_wb_frn_avg_time = 0;
+	inode->i_wb_frn_history = 0;
+	switched = true;
+skip_switch:
+	/*
+	 * Paired with load_acquire in unlocked_inode_to_wb_begin() and
+	 * ensures that the new wb is visible if they see !I_WB_SWITCH.
+	 */
+	smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH);
+
+	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&new_wb->list_lock);
+	spin_unlock(&old_wb->list_lock);
+
+	if (switched) {
+		wb_wakeup(new_wb);
+		wb_put(old_wb);
+	}
+	wb_put(new_wb);
+
+	iput(inode);
+	kfree(isw);
+}
+
+static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
+{
+	struct inode_switch_wbs_context *isw = container_of(rcu_head,
+				struct inode_switch_wbs_context, rcu_head);
+
+	/* needs to grab bh-unsafe locks, bounce to work item */
+	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
+	schedule_work(&isw->work);
+}
+
+/**
+ * inode_switch_wbs - change the wb association of an inode
+ * @inode: target inode
+ * @new_wb_id: ID of the new wb
+ *
+ * Switch @inode's wb association to the wb identified by @new_wb_id.  The
+ * switching is performed asynchronously and may fail silently.
+ */
+static void inode_switch_wbs(struct inode *inode, int new_wb_id)
+{
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
+	struct cgroup_subsys_state *memcg_css;
+	struct inode_switch_wbs_context *isw;
+
+	/* noop if seems to be already in progress */
+	if (inode->i_state & I_WB_SWITCH)
+		return;
+
+	isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
+	if (!isw)
+		return;
+
+	/* find and pin the new wb */
+	rcu_read_lock();
+	memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys);
+	if (memcg_css)
+		isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+	rcu_read_unlock();
+	if (!isw->new_wb)
+		goto out_free;
+
+	/* while holding I_WB_SWITCH, no one else can update the association */
+	spin_lock(&inode->i_lock);
+	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	    inode_to_wb(inode) == isw->new_wb) {
+		spin_unlock(&inode->i_lock);
+		goto out_free;
+	}
+	inode->i_state |= I_WB_SWITCH;
+	spin_unlock(&inode->i_lock);
+
+	ihold(inode);
+	isw->inode = inode;
+
+	/*
+	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
+	 * the RCU protected stat update paths to grab the mapping's
+	 * tree_lock so that stat transfer can synchronize against them.
+	 * Let's continue after I_WB_SWITCH is guaranteed to be visible.
+	 */
+	call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
+	return;
+
+out_free:
+	if (isw->new_wb)
+		wb_put(isw->new_wb);
+	kfree(isw);
+}
+
+/**
+ * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it
+ * @wbc: writeback_control of interest
+ * @inode: target inode
+ *
+ * @inode is locked and about to be written back under the control of @wbc.
+ * Record @inode's writeback context into @wbc and unlock the i_lock.  On
+ * writeback completion, wbc_detach_inode() should be called.  This is used
+ * to track the cgroup writeback context.
+ */
+void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+				 struct inode *inode)
+{
+	if (!inode_cgwb_enabled(inode)) {
+		spin_unlock(&inode->i_lock);
+		return;
+	}
+
+	wbc->wb = inode_to_wb(inode);
+	wbc->inode = inode;
+
+	wbc->wb_id = wbc->wb->memcg_css->id;
+	wbc->wb_lcand_id = inode->i_wb_frn_winner;
+	wbc->wb_tcand_id = 0;
+	wbc->wb_bytes = 0;
+	wbc->wb_lcand_bytes = 0;
+	wbc->wb_tcand_bytes = 0;
+
+	wb_get(wbc->wb);
+	spin_unlock(&inode->i_lock);
+
+	/*
+	 * A dying wb indicates that the memcg-blkcg mapping has changed
+	 * and a new wb is already serving the memcg.  Switch immediately.
+	 */
+	if (unlikely(wb_dying(wbc->wb)))
+		inode_switch_wbs(inode, wbc->wb_id);
+}
+
+/**
+ * wbc_detach_inode - disassociate wbc from inode and perform foreign detection
+ * @wbc: writeback_control of the just finished writeback
+ *
+ * To be called after a writeback attempt of an inode finishes and undoes
+ * wbc_attach_and_unlock_inode().  Can be called under any context.
+ *
+ * As concurrent write sharing of an inode is expected to be very rare and
+ * memcg only tracks page ownership on first-use basis severely confining
+ * the usefulness of such sharing, cgroup writeback tracks ownership
+ * per-inode.  While the support for concurrent write sharing of an inode
+ * is deemed unnecessary, an inode being written to by different cgroups at
+ * different points in time is a lot more common, and, more importantly,
+ * charging only by first-use can too readily lead to grossly incorrect
+ * behaviors (single foreign page can lead to gigabytes of writeback to be
+ * incorrectly attributed).
+ *
+ * To resolve this issue, cgroup writeback detects the majority dirtier of
+ * an inode and transfers the ownership to it.  To avoid unnnecessary
+ * oscillation, the detection mechanism keeps track of history and gives
+ * out the switch verdict only if the foreign usage pattern is stable over
+ * a certain amount of time and/or writeback attempts.
+ *
+ * On each writeback attempt, @wbc tries to detect the majority writer
+ * using Boyer-Moore majority vote algorithm.  In addition to the byte
+ * count from the majority voting, it also counts the bytes written for the
+ * current wb and the last round's winner wb (max of last round's current
+ * wb, the winner from two rounds ago, and the last round's majority
+ * candidate).  Keeping track of the historical winner helps the algorithm
+ * to semi-reliably detect the most active writer even when it's not the
+ * absolute majority.
+ *
+ * Once the winner of the round is determined, whether the winner is
+ * foreign or not and how much IO time the round consumed is recorded in
+ * inode->i_wb_frn_history.  If the amount of recorded foreign IO time is
+ * over a certain threshold, the switch verdict is given.
+ */
+void wbc_detach_inode(struct writeback_control *wbc)
+{
+	struct bdi_writeback *wb = wbc->wb;
+	struct inode *inode = wbc->inode;
+	unsigned long avg_time, max_bytes, max_time;
+	u16 history;
+	int max_id;
+
+	if (!wb)
+		return;
+
+	history = inode->i_wb_frn_history;
+	avg_time = inode->i_wb_frn_avg_time;
+
+	/* pick the winner of this round */
+	if (wbc->wb_bytes >= wbc->wb_lcand_bytes &&
+	    wbc->wb_bytes >= wbc->wb_tcand_bytes) {
+		max_id = wbc->wb_id;
+		max_bytes = wbc->wb_bytes;
+	} else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) {
+		max_id = wbc->wb_lcand_id;
+		max_bytes = wbc->wb_lcand_bytes;
+	} else {
+		max_id = wbc->wb_tcand_id;
+		max_bytes = wbc->wb_tcand_bytes;
+	}
+
+	/*
+	 * Calculate the amount of IO time the winner consumed and fold it
+	 * into the running average kept per inode.  If the consumed IO
+	 * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for
+	 * deciding whether to switch or not.  This is to prevent one-off
+	 * small dirtiers from skewing the verdict.
+	 */
+	max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT,
+				wb->avg_write_bandwidth);
+	if (avg_time)
+		avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) -
+			    (avg_time >> WB_FRN_TIME_AVG_SHIFT);
+	else
+		avg_time = max_time;	/* immediate catch up on first run */
+
+	if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) {
+		int slots;
+
+		/*
+		 * The switch verdict is reached if foreign wb's consume
+		 * more than a certain proportion of IO time in a
+		 * WB_FRN_TIME_PERIOD.  This is loosely tracked by 16 slot
+		 * history mask where each bit represents one sixteenth of
+		 * the period.  Determine the number of slots to shift into
+		 * history from @max_time.
+		 */
+		slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT),
+			    (unsigned long)WB_FRN_HIST_MAX_SLOTS);
+		history <<= slots;
+		if (wbc->wb_id != max_id)
+			history |= (1U << slots) - 1;
+
+		/*
+		 * Switch if the current wb isn't the consistent winner.
+		 * If there are multiple closely competing dirtiers, the
+		 * inode may switch across them repeatedly over time, which
+		 * is okay.  The main goal is avoiding keeping an inode on
+		 * the wrong wb for an extended period of time.
+		 */
+		if (hweight32(history) > WB_FRN_HIST_THR_SLOTS)
+			inode_switch_wbs(inode, max_id);
+	}
+
+	/*
+	 * Multiple instances of this function may race to update the
+	 * following fields but we don't mind occassional inaccuracies.
+	 */
+	inode->i_wb_frn_winner = max_id;
+	inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX);
+	inode->i_wb_frn_history = history;
+
+	wb_put(wbc->wb);
+	wbc->wb = NULL;
+}
+
+/**
+ * wbc_account_io - account IO issued during writeback
+ * @wbc: writeback_control of the writeback in progress
+ * @page: page being written out
+ * @bytes: number of bytes being written out
+ *
+ * @bytes from @page are about to written out during the writeback
+ * controlled by @wbc.  Keep the book for foreign inode detection.  See
+ * wbc_detach_inode().
+ */
+void wbc_account_io(struct writeback_control *wbc, struct page *page,
+		    size_t bytes)
+{
+	int id;
+
+	/*
+	 * pageout() path doesn't attach @wbc to the inode being written
+	 * out.  This is intentional as we don't want the function to block
+	 * behind a slow cgroup.  Ultimately, we want pageout() to kick off
+	 * regular writeback instead of writing things out itself.
+	 */
+	if (!wbc->wb)
+		return;
+
+	rcu_read_lock();
+	id = mem_cgroup_css_from_page(page)->id;
+	rcu_read_unlock();
+
+	if (id == wbc->wb_id) {
+		wbc->wb_bytes += bytes;
+		return;
+	}
+
+	if (id == wbc->wb_lcand_id)
+		wbc->wb_lcand_bytes += bytes;
+
+	/* Boyer-Moore majority vote algorithm */
+	if (!wbc->wb_tcand_bytes)
+		wbc->wb_tcand_id = id;
+	if (id == wbc->wb_tcand_id)
+		wbc->wb_tcand_bytes += bytes;
+	else
+		wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes);
 }
 
-static void
-__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-		      bool range_cyclic, enum wb_reason reason)
+/**
+ * inode_congested - test whether an inode is congested
+ * @inode: inode to test for congestion
+ * @cong_bits: mask of WB_[a]sync_congested bits to test
+ *
+ * Tests whether @inode is congested.  @cong_bits is the mask of congestion
+ * bits to test and the return value is the mask of set bits.
+ *
+ * If cgroup writeback is enabled for @inode, the congestion state is
+ * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg
+ * associated with @inode is congested; otherwise, the root wb's congestion
+ * state is used.
+ */
+int inode_congested(struct inode *inode, int cong_bits)
+{
+	/*
+	 * Once set, ->i_wb never becomes NULL while the inode is alive.
+	 * Start transaction iff ->i_wb is visible.
+	 */
+	if (inode && inode_to_wb_is_valid(inode)) {
+		struct bdi_writeback *wb;
+		bool locked, congested;
+
+		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		congested = wb_congested(wb, cong_bits);
+		unlocked_inode_to_wb_end(inode, locked);
+		return congested;
+	}
+
+	return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
+}
+EXPORT_SYMBOL_GPL(inode_congested);
+
+/**
+ * wb_wait_for_single_work - wait for completion of a single bdi_writeback_work
+ * @bdi: bdi the work item was issued to
+ * @work: work item to wait for
+ *
+ * Wait for the completion of @work which was issued to one of @bdi's
+ * bdi_writeback's.  The caller must have set @work->single_wait before
+ * issuing it.  This wait operates independently fo
+ * wb_wait_for_completion() and also disables automatic freeing of @work.
+ */
+static void wb_wait_for_single_work(struct backing_dev_info *bdi,
+				    struct wb_writeback_work *work)
+{
+	if (WARN_ON_ONCE(!work->single_wait))
+		return;
+
+	wait_event(bdi->wb_waitq, work->single_done);
+
+	/*
+	 * Paired with smp_wmb() in wb_do_writeback() and ensures that all
+	 * modifications to @work prior to assertion of ->single_done is
+	 * visible to the caller once this function returns.
+	 */
+	smp_rmb();
+}
+
+/**
+ * wb_split_bdi_pages - split nr_pages to write according to bandwidth
+ * @wb: target bdi_writeback to split @nr_pages to
+ * @nr_pages: number of pages to write for the whole bdi
+ *
+ * Split @wb's portion of @nr_pages according to @wb's write bandwidth in
+ * relation to the total write bandwidth of all wb's w/ dirty inodes on
+ * @wb->bdi.
+ */
+static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
+{
+	unsigned long this_bw = wb->avg_write_bandwidth;
+	unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);
+
+	if (nr_pages == LONG_MAX)
+		return LONG_MAX;
+
+	/*
+	 * This may be called on clean wb's and proportional distribution
+	 * may not make sense, just use the original @nr_pages in those
+	 * cases.  In general, we wanna err on the side of writing more.
+	 */
+	if (!tot_bw || this_bw >= tot_bw)
+		return nr_pages;
+	else
+		return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw);
+}
+
+/**
+ * wb_clone_and_queue_work - clone a wb_writeback_work and issue it to a wb
+ * @wb: target bdi_writeback
+ * @base_work: source wb_writeback_work
+ *
+ * Try to make a clone of @base_work and issue it to @wb.  If cloning
+ * succeeds, %true is returned; otherwise, @base_work is issued directly
+ * and %false is returned.  In the latter case, the caller is required to
+ * wait for @base_work's completion using wb_wait_for_single_work().
+ *
+ * A clone is auto-freed on completion.  @base_work never is.
+ */
+static bool wb_clone_and_queue_work(struct bdi_writeback *wb,
+				    struct wb_writeback_work *base_work)
 {
 	struct wb_writeback_work *work;
 
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work) {
+		*work = *base_work;
+		work->auto_free = 1;
+		work->single_wait = 0;
+	} else {
+		work = base_work;
+		work->auto_free = 0;
+		work->single_wait = 1;
+	}
+	work->single_done = 0;
+	wb_queue_work(wb, work);
+	return work != base_work;
+}
+
+/**
+ * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi
+ * @bdi: target backing_dev_info
+ * @base_work: wb_writeback_work to issue
+ * @skip_if_busy: skip wb's which already have writeback in progress
+ *
+ * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which
+ * have dirty inodes.  If @base_work->nr_page isn't %LONG_MAX, it's
+ * distributed to the busy wbs according to each wb's proportion in the
+ * total active write bandwidth of @bdi.
+ */
+static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
+				  struct wb_writeback_work *base_work,
+				  bool skip_if_busy)
+{
+	long nr_pages = base_work->nr_pages;
+	int next_blkcg_id = 0;
+	struct bdi_writeback *wb;
+	struct wb_iter iter;
+
+	might_sleep();
+
+	if (!bdi_has_dirty_io(bdi))
+		return;
+restart:
+	rcu_read_lock();
+	bdi_for_each_wb(wb, bdi, &iter, next_blkcg_id) {
+		if (!wb_has_dirty_io(wb) ||
+		    (skip_if_busy && writeback_in_progress(wb)))
+			continue;
+
+		base_work->nr_pages = wb_split_bdi_pages(wb, nr_pages);
+		if (!wb_clone_and_queue_work(wb, base_work)) {
+			next_blkcg_id = wb->blkcg_css->id + 1;
+			rcu_read_unlock();
+			wb_wait_for_single_work(bdi, base_work);
+			goto restart;
+		}
+	}
+	rcu_read_unlock();
+}
+
+#else	/* CONFIG_CGROUP_WRITEBACK */
+
+static struct bdi_writeback *
+locked_inode_to_wb_and_lock_list(struct inode *inode)
+	__releases(&inode->i_lock)
+	__acquires(&wb->list_lock)
+{
+	struct bdi_writeback *wb = inode_to_wb(inode);
+
+	spin_unlock(&inode->i_lock);
+	spin_lock(&wb->list_lock);
+	return wb;
+}
+
+static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode)
+	__acquires(&wb->list_lock)
+{
+	struct bdi_writeback *wb = inode_to_wb(inode);
+
+	spin_lock(&wb->list_lock);
+	return wb;
+}
+
+static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
+{
+	return nr_pages;
+}
+
+static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
+				  struct wb_writeback_work *base_work,
+				  bool skip_if_busy)
+{
+	might_sleep();
+
+	if (bdi_has_dirty_io(bdi) &&
+	    (!skip_if_busy || !writeback_in_progress(&bdi->wb))) {
+		base_work->auto_free = 0;
+		base_work->single_wait = 0;
+		base_work->single_done = 0;
+		wb_queue_work(&bdi->wb, base_work);
+	}
+}
+
+#endif	/* CONFIG_CGROUP_WRITEBACK */
+
+void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
+			bool range_cyclic, enum wb_reason reason)
+{
+	struct wb_writeback_work *work;
+
+	if (!wb_has_dirty_io(wb))
+		return;
+
 	/*
 	 * This is WB_SYNC_NONE writeback, so if allocation fails just
 	 * wakeup the thread for old dirty data writeback
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		trace_writeback_nowork(bdi);
-		bdi_wakeup_thread(bdi);
+		trace_writeback_nowork(wb->bdi);
+		wb_wakeup(wb);
 		return;
 	}
 
@@ -155,46 +932,29 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work->nr_pages	= nr_pages;
 	work->range_cyclic = range_cyclic;
 	work->reason	= reason;
+	work->auto_free	= 1;
 
-	bdi_queue_work(bdi, work);
+	wb_queue_work(wb, work);
 }
 
 /**
- * bdi_start_writeback - start writeback
- * @bdi: the backing device to write from
- * @nr_pages: the number of pages to write
- * @reason: reason why some writeback work was initiated
- *
- * Description:
- *   This does WB_SYNC_NONE opportunistic writeback. The IO is only
- *   started when this function returns, we make no guarantees on
- *   completion. Caller need not hold sb s_umount semaphore.
- *
- */
-void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-			enum wb_reason reason)
-{
-	__bdi_start_writeback(bdi, nr_pages, true, reason);
-}
-
-/**
- * bdi_start_background_writeback - start background writeback
- * @bdi: the backing device to write from
+ * wb_start_background_writeback - start background writeback
+ * @wb: bdi_writback to write from
  *
  * Description:
  *   This makes sure WB_SYNC_NONE background writeback happens. When
- *   this function returns, it is only guaranteed that for given BDI
+ *   this function returns, it is only guaranteed that for given wb
  *   some IO is happening if we are over background dirty threshold.
  *   Caller need not hold sb s_umount semaphore.
  */
-void bdi_start_background_writeback(struct backing_dev_info *bdi)
+void wb_start_background_writeback(struct bdi_writeback *wb)
 {
 	/*
 	 * We just wake up the flusher thread. It will perform background
 	 * writeback as soon as there is no other work to do.
 	 */
-	trace_writeback_wake_background(bdi);
-	bdi_wakeup_thread(bdi);
+	trace_writeback_wake_background(wb->bdi);
+	wb_wakeup(wb);
 }
 
 /*
@@ -202,11 +962,11 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
  */
 void inode_wb_list_del(struct inode *inode)
 {
-	struct backing_dev_info *bdi = inode_to_bdi(inode);
+	struct bdi_writeback *wb;
 
-	spin_lock(&bdi->wb.list_lock);
-	list_del_init(&inode->i_wb_list);
-	spin_unlock(&bdi->wb.list_lock);
+	wb = inode_to_wb_and_lock_list(inode);
+	inode_wb_list_del_locked(inode, wb);
+	spin_unlock(&wb->list_lock);
 }
 
 /*
@@ -220,7 +980,6 @@ void inode_wb_list_del(struct inode *inode)
  */
 static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 {
-	assert_spin_locked(&wb->list_lock);
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
@@ -228,7 +987,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 		if (time_before(inode->dirtied_when, tail->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
-	list_move(&inode->i_wb_list, &wb->b_dirty);
+	inode_wb_list_move_locked(inode, wb, &wb->b_dirty);
 }
 
 /*
@@ -236,8 +995,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
  */
 static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 {
-	assert_spin_locked(&wb->list_lock);
-	list_move(&inode->i_wb_list, &wb->b_more_io);
+	inode_wb_list_move_locked(inode, wb, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
@@ -346,6 +1104,8 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
 	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
 	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
 				     EXPIRE_DIRTY_ATIME, work);
+	if (moved)
+		wb_io_lists_populated(wb);
 	trace_writeback_queue_io(wb, work, moved);
 }
 
@@ -471,10 +1231,10 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		redirty_tail(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
 		inode->dirtied_when = jiffies;
-		list_move(&inode->i_wb_list, &wb->b_dirty_time);
+		inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
-		list_del_init(&inode->i_wb_list);
+		inode_wb_list_del_locked(inode, wb);
 	}
 }
 
@@ -605,10 +1365,11 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
 	inode->i_state |= I_SYNC;
-	spin_unlock(&inode->i_lock);
+	wbc_attach_and_unlock_inode(wbc, inode);
 
 	ret = __writeback_single_inode(inode, wbc);
 
+	wbc_detach_inode(wbc);
 	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
 	/*
@@ -616,7 +1377,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * touch it. See comment above for explanation.
 	 */
 	if (!(inode->i_state & I_DIRTY_ALL))
-		list_del_init(&inode->i_wb_list);
+		inode_wb_list_del_locked(inode, wb);
 	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
 out:
@@ -624,7 +1385,7 @@ out:
 	return ret;
 }
 
-static long writeback_chunk_size(struct backing_dev_info *bdi,
+static long writeback_chunk_size(struct bdi_writeback *wb,
 				 struct wb_writeback_work *work)
 {
 	long pages;
@@ -645,8 +1406,8 @@ static long writeback_chunk_size(struct backing_dev_info *bdi,
 	if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
 		pages = LONG_MAX;
 	else {
-		pages = min(bdi->avg_write_bandwidth / 2,
-			    global_dirty_limit / DIRTY_SCOPE);
+		pages = min(wb->avg_write_bandwidth / 2,
+			    global_wb_domain.dirty_limit / DIRTY_SCOPE);
 		pages = min(pages, work->nr_pages);
 		pages = round_down(pages + MIN_WRITEBACK_PAGES,
 				   MIN_WRITEBACK_PAGES);
@@ -741,9 +1502,9 @@ static long writeback_sb_inodes(struct super_block *sb,
 			continue;
 		}
 		inode->i_state |= I_SYNC;
-		spin_unlock(&inode->i_lock);
+		wbc_attach_and_unlock_inode(&wbc, inode);
 
-		write_chunk = writeback_chunk_size(wb->bdi, work);
+		write_chunk = writeback_chunk_size(wb, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
@@ -753,6 +1514,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		 */
 		__writeback_single_inode(inode, &wbc);
 
+		wbc_detach_inode(&wbc);
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote += write_chunk - wbc.nr_to_write;
 		spin_lock(&wb->list_lock);
@@ -830,33 +1592,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	return nr_pages - work.nr_pages;
 }
 
-static bool over_bground_thresh(struct backing_dev_info *bdi)
-{
-	unsigned long background_thresh, dirty_thresh;
-
-	global_dirty_limits(&background_thresh, &dirty_thresh);
-
-	if (global_page_state(NR_FILE_DIRTY) +
-	    global_page_state(NR_UNSTABLE_NFS) > background_thresh)
-		return true;
-
-	if (bdi_stat(bdi, BDI_RECLAIMABLE) >
-				bdi_dirty_limit(bdi, background_thresh))
-		return true;
-
-	return false;
-}
-
-/*
- * Called under wb->list_lock. If there are multiple wb per bdi,
- * only the flusher working on the first wb should do it.
- */
-static void wb_update_bandwidth(struct bdi_writeback *wb,
-				unsigned long start_time)
-{
-	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time);
-}
-
 /*
  * Explicit flushing or periodic writeback of "old" data.
  *
@@ -899,14 +1634,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * after the other works are all done.
 		 */
 		if ((work->for_background || work->for_kupdate) &&
-		    !list_empty(&wb->bdi->work_list))
+		    !list_empty(&wb->work_list))
 			break;
 
 		/*
 		 * For background writeout, stop when we are below the
 		 * background dirty threshold
 		 */
-		if (work->for_background && !over_bground_thresh(wb->bdi))
+		if (work->for_background && !wb_over_bg_thresh(wb))
 			break;
 
 		/*
@@ -970,18 +1705,17 @@ static long wb_writeback(struct bdi_writeback *wb,
 /*
  * Return the next wb_writeback_work struct that hasn't been processed yet.
  */
-static struct wb_writeback_work *
-get_next_work_item(struct backing_dev_info *bdi)
+static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock_bh(&bdi->wb_lock);
-	if (!list_empty(&bdi->work_list)) {
-		work = list_entry(bdi->work_list.next,
+	spin_lock_bh(&wb->work_lock);
+	if (!list_empty(&wb->work_list)) {
+		work = list_entry(wb->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_bh(&bdi->wb_lock);
+	spin_unlock_bh(&wb->work_lock);
 	return work;
 }
 
@@ -998,7 +1732,7 @@ static unsigned long get_nr_dirty_pages(void)
 
 static long wb_check_background_flush(struct bdi_writeback *wb)
 {
-	if (over_bground_thresh(wb->bdi)) {
+	if (wb_over_bg_thresh(wb)) {
 
 		struct wb_writeback_work work = {
 			.nr_pages	= LONG_MAX,
@@ -1053,25 +1787,33 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
  */
 static long wb_do_writeback(struct bdi_writeback *wb)
 {
-	struct backing_dev_info *bdi = wb->bdi;
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
-	set_bit(BDI_writeback_running, &wb->bdi->state);
-	while ((work = get_next_work_item(bdi)) != NULL) {
+	set_bit(WB_writeback_running, &wb->state);
+	while ((work = get_next_work_item(wb)) != NULL) {
+		struct wb_completion *done = work->done;
+		bool need_wake_up = false;
 
-		trace_writeback_exec(bdi, work);
+		trace_writeback_exec(wb->bdi, work);
 
 		wrote += wb_writeback(wb, work);
 
-		/*
-		 * Notify the caller of completion if this is a synchronous
-		 * work item, otherwise just free it.
-		 */
-		if (work->done)
-			complete(work->done);
-		else
+		if (work->single_wait) {
+			WARN_ON_ONCE(work->auto_free);
+			/* paired w/ rmb in wb_wait_for_single_work() */
+			smp_wmb();
+			work->single_done = 1;
+			need_wake_up = true;
+		} else if (work->auto_free) {
 			kfree(work);
+		}
+
+		if (done && atomic_dec_and_test(&done->cnt))
+			need_wake_up = true;
+
+		if (need_wake_up)
+			wake_up_all(&wb->bdi->wb_waitq);
 	}
 
 	/*
@@ -1079,7 +1821,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	 */
 	wrote += wb_check_old_data_flush(wb);
 	wrote += wb_check_background_flush(wb);
-	clear_bit(BDI_writeback_running, &wb->bdi->state);
+	clear_bit(WB_writeback_running, &wb->state);
 
 	return wrote;
 }
@@ -1088,43 +1830,42 @@ static long wb_do_writeback(struct bdi_writeback *wb)
  * Handle writeback of dirty data for the device backed by this bdi. Also
  * reschedules periodically and does kupdated style flushing.
  */
-void bdi_writeback_workfn(struct work_struct *work)
+void wb_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(to_delayed_work(work),
 						struct bdi_writeback, dwork);
-	struct backing_dev_info *bdi = wb->bdi;
 	long pages_written;
 
-	set_worker_desc("flush-%s", dev_name(bdi->dev));
+	set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   !test_bit(BDI_registered, &bdi->state))) {
+		   !test_bit(WB_registered, &wb->state))) {
 		/*
-		 * The normal path.  Keep writing back @bdi until its
+		 * The normal path.  Keep writing back @wb until its
 		 * work_list is empty.  Note that this path is also taken
-		 * if @bdi is shutting down even when we're running off the
+		 * if @wb is shutting down even when we're running off the
 		 * rescuer as work_list needs to be drained.
 		 */
 		do {
 			pages_written = wb_do_writeback(wb);
 			trace_writeback_pages_written(pages_written);
-		} while (!list_empty(&bdi->work_list));
+		} while (!list_empty(&wb->work_list));
 	} else {
 		/*
 		 * bdi_wq can't get enough workers and we're running off
 		 * the emergency worker.  Don't hog it.  Hopefully, 1024 is
 		 * enough for efficient IO.
 		 */
-		pages_written = writeback_inodes_wb(&bdi->wb, 1024,
+		pages_written = writeback_inodes_wb(wb, 1024,
 						    WB_REASON_FORKER_THREAD);
 		trace_writeback_pages_written(pages_written);
 	}
 
-	if (!list_empty(&bdi->work_list))
+	if (!list_empty(&wb->work_list))
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
-		bdi_wakeup_thread_delayed(bdi);
+		wb_wakeup_delayed(wb);
 
 	current->flags &= ~PF_SWAPWRITE;
 }
@@ -1142,9 +1883,15 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
+		struct bdi_writeback *wb;
+		struct wb_iter iter;
+
 		if (!bdi_has_dirty_io(bdi))
 			continue;
-		__bdi_start_writeback(bdi, nr_pages, false, reason);
+
+		bdi_for_each_wb(wb, bdi, &iter, 0)
+			wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages),
+					   false, reason);
 	}
 	rcu_read_unlock();
 }
@@ -1173,9 +1920,12 @@ static void wakeup_dirtytime_writeback(struct work_struct *w)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
-		if (list_empty(&bdi->wb.b_dirty_time))
-			continue;
-		bdi_wakeup_thread(bdi);
+		struct bdi_writeback *wb;
+		struct wb_iter iter;
+
+		bdi_for_each_wb(wb, bdi, &iter, 0)
+			if (!list_empty(&bdi->wb.b_dirty_time))
+				wb_wakeup(&bdi->wb);
 	}
 	rcu_read_unlock();
 	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
@@ -1249,7 +1999,6 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
-	struct backing_dev_info *bdi = NULL;
 	int dirtytime;
 
 	trace_writeback_mark_inode_dirty(inode, flags);
@@ -1289,6 +2038,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 
+		inode_attach_wb(inode, NULL);
+
 		if (flags & I_DIRTY_INODE)
 			inode->i_state &= ~I_DIRTY_TIME;
 		inode->i_state |= flags;
@@ -1317,38 +2068,39 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * reposition it (that would break b_dirty time-ordering).
 		 */
 		if (!was_dirty) {
+			struct bdi_writeback *wb;
+			struct list_head *dirty_list;
 			bool wakeup_bdi = false;
-			bdi = inode_to_bdi(inode);
 
-			spin_unlock(&inode->i_lock);
-			spin_lock(&bdi->wb.list_lock);
-			if (bdi_cap_writeback_dirty(bdi)) {
-				WARN(!test_bit(BDI_registered, &bdi->state),
-				     "bdi-%s not registered\n", bdi->name);
+			wb = locked_inode_to_wb_and_lock_list(inode);
 
-				/*
-				 * If this is the first dirty inode for this
-				 * bdi, we have to wake-up the corresponding
-				 * bdi thread to make sure background
-				 * write-back happens later.
-				 */
-				if (!wb_has_dirty_io(&bdi->wb))
-					wakeup_bdi = true;
-			}
+			WARN(bdi_cap_writeback_dirty(wb->bdi) &&
+			     !test_bit(WB_registered, &wb->state),
+			     "bdi-%s not registered\n", wb->bdi->name);
 
 			inode->dirtied_when = jiffies;
 			if (dirtytime)
 				inode->dirtied_time_when = jiffies;
+
 			if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES))
-				list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
+				dirty_list = &wb->b_dirty;
 			else
-				list_move(&inode->i_wb_list,
-					  &bdi->wb.b_dirty_time);
-			spin_unlock(&bdi->wb.list_lock);
+				dirty_list = &wb->b_dirty_time;
+
+			wakeup_bdi = inode_wb_list_move_locked(inode, wb,
+							       dirty_list);
+
+			spin_unlock(&wb->list_lock);
 			trace_writeback_dirty_inode_enqueue(inode);
 
-			if (wakeup_bdi)
-				bdi_wakeup_thread_delayed(bdi);
+			/*
+			 * If this is the first dirty inode for this bdi,
+			 * we have to wake-up the corresponding bdi thread
+			 * to make sure background write-back happens
+			 * later.
+			 */
+			if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi)
+				wb_wakeup_delayed(wb);
 			return;
 		}
 	}
@@ -1411,6 +2163,28 @@ static void wait_sb_inodes(struct super_block *sb)
 	iput(old_inode);
 }
 
+static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
+				     enum wb_reason reason, bool skip_if_busy)
+{
+	DEFINE_WB_COMPLETION_ONSTACK(done);
+	struct wb_writeback_work work = {
+		.sb			= sb,
+		.sync_mode		= WB_SYNC_NONE,
+		.tagged_writepages	= 1,
+		.done			= &done,
+		.nr_pages		= nr,
+		.reason			= reason,
+	};
+	struct backing_dev_info *bdi = sb->s_bdi;
+
+	if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info)
+		return;
+	WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+	bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy);
+	wb_wait_for_completion(bdi, &done);
+}
+
 /**
  * writeback_inodes_sb_nr -	writeback dirty inodes from given super_block
  * @sb: the superblock
@@ -1425,21 +2199,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
 			    unsigned long nr,
 			    enum wb_reason reason)
 {
-	DECLARE_COMPLETION_ONSTACK(done);
-	struct wb_writeback_work work = {
-		.sb			= sb,
-		.sync_mode		= WB_SYNC_NONE,
-		.tagged_writepages	= 1,
-		.done			= &done,
-		.nr_pages		= nr,
-		.reason			= reason,
-	};
-
-	if (sb->s_bdi == &noop_backing_dev_info)
-		return;
-	WARN_ON(!rwsem_is_locked(&sb->s_umount));
-	bdi_queue_work(sb->s_bdi, &work);
-	wait_for_completion(&done);
+	__writeback_inodes_sb_nr(sb, nr, reason, false);
 }
 EXPORT_SYMBOL(writeback_inodes_sb_nr);
 
@@ -1467,19 +2227,15 @@ EXPORT_SYMBOL(writeback_inodes_sb);
  * Invoke writeback_inodes_sb_nr if no writeback is currently underway.
  * Returns 1 if writeback was started, 0 if not.
  */
-int try_to_writeback_inodes_sb_nr(struct super_block *sb,
-				  unsigned long nr,
-				  enum wb_reason reason)
+bool try_to_writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
+				   enum wb_reason reason)
 {
-	if (writeback_in_progress(sb->s_bdi))
-		return 1;
-
 	if (!down_read_trylock(&sb->s_umount))
-		return 0;
+		return false;
 
-	writeback_inodes_sb_nr(sb, nr, reason);
+	__writeback_inodes_sb_nr(sb, nr, reason, true);
 	up_read(&sb->s_umount);
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);
 
@@ -1491,7 +2247,7 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);
  * Implement by try_to_writeback_inodes_sb_nr()
  * Returns 1 if writeback was started, 0 if not.
  */
-int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
+bool try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 {
 	return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
 }
@@ -1506,7 +2262,7 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
  */
 void sync_inodes_sb(struct super_block *sb)
 {
-	DECLARE_COMPLETION_ONSTACK(done);
+	DEFINE_WB_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
@@ -1516,14 +2272,15 @@ void sync_inodes_sb(struct super_block *sb)
 		.reason		= WB_REASON_SYNC,
 		.for_sync	= 1,
 	};
+	struct backing_dev_info *bdi = sb->s_bdi;
 
 	/* Nothing to do? */
-	if (sb->s_bdi == &noop_backing_dev_info)
+	if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info)
 		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	bdi_queue_work(sb->s_bdi, &work);
-	wait_for_completion(&done);
+	bdi_split_work_to_wbs(bdi, &work, false);
+	wb_wait_for_completion(bdi, &done);
 
 	wait_sb_inodes(sb);
 }
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5ef05b5c4cff..8c5e2fa68835 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1445,9 +1445,9 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 
 	list_del(&req->writepages_entry);
 	for (i = 0; i < req->num_pages; i++) {
-		dec_bdi_stat(bdi, BDI_WRITEBACK);
+		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP);
-		bdi_writeout_inc(bdi);
+		wb_writeout_inc(&bdi->wb);
 	}
 	wake_up(&fi->page_waitq);
 }
@@ -1634,7 +1634,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->end = fuse_writepage_end;
 	req->inode = inode;
 
-	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
@@ -1749,9 +1749,9 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 		copy_highpage(old_req->pages[0], page);
 		spin_unlock(&fc->lock);
 
-		dec_bdi_stat(bdi, BDI_WRITEBACK);
+		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_zone_page_state(page, NR_WRITEBACK_TEMP);
-		bdi_writeout_inc(bdi);
+		wb_writeout_inc(&bdi->wb);
 		fuse_writepage_free(fc, new_req);
 		fuse_request_free(new_req);
 		goto out;
@@ -1848,7 +1848,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].offset = 0;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
-	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 859c6edbf81a..2982445947e1 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -748,7 +748,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH);
-	if (bdi->dirty_exceeded)
+	if (bdi->wb.dirty_exceeded)
 		gfs2_ail1_flush(sdp, wbc);
 	else
 		filemap_fdatawrite(metamapping);
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index eee7206c38d1..55c03b9e9070 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -14,6 +14,7 @@
 
 #include <linux/module.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/mount.h>
 #include <linux/init.h>
 #include <linux/nls.h>
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 593af2fdcc2d..7302d96ae8bf 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/pagemap.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/vfs.h>
diff --git a/fs/inode.c b/fs/inode.c
index e8d62688ed91..069721f0cc0e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -224,6 +224,7 @@ EXPORT_SYMBOL(free_inode_nonrcu);
 void __destroy_inode(struct inode *inode)
 {
 	BUG_ON(inode_has_buffers(inode));
+	inode_detach_wb(inode);
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
 	locks_free_lock_context(inode->i_flctx);
diff --git a/fs/mpage.c b/fs/mpage.c
index 3e79220babac..ca0244b69de8 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -605,6 +605,8 @@ alloc_new:
 				bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
 		if (bio == NULL)
 			goto confused;
+
+		wbc_init_bio(wbc, bio);
 	}
 
 	/*
@@ -612,6 +614,7 @@ alloc_new:
 	 * the confused fail path above (OOM) will be very confused when
 	 * it finds all bh marked clean (i.e. it will not write anything)
 	 */
+	wbc_account_io(wbc, page, PAGE_SIZE);
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
 		bio = mpage_bio_submit(WRITE, bio);
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index a46bf6de9ce4..b34f2e228601 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -32,6 +32,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 
 #include <linux/sunrpc/metrics.h>
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9e6475bc5ba2..7e3c4604bea8 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -607,7 +607,7 @@ void nfs_mark_page_unstable(struct page *page)
 	struct inode *inode = page_file_mapping(page)->host;
 
 	inc_zone_page_state(page, NR_UNSTABLE_NFS);
-	inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
 	 __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index dfc19f1575a1..e6c262555e08 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -853,7 +853,8 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
+	dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
+		    WB_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index fbfadb289e62..719f7f4c7a37 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -37,6 +37,7 @@
 #include <linux/falloc.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 
 #include <cluster/masklog.h>
 
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 0111ad0466ed..3e0af317fcc3 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -21,6 +21,7 @@
 #include "xattr.h"
 #include <linux/init.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/quotaops.h>
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index b3bc3e7ae79d..098508a93c7b 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -80,6 +80,7 @@
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <linux/blkdev.h>
+#include <linux/backing-dev.h>
 #include <linux/init.h>
 #include <linux/parser.h>
 #include <linux/buffer_head.h>
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 095f94c2d8b5..e5099f268032 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1873,6 +1873,7 @@ xfs_vm_set_page_dirty(
 	loff_t			end_offset;
 	loff_t			offset;
 	int			newly_dirty;
+	struct mem_cgroup	*memcg;
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
@@ -1892,6 +1893,11 @@ xfs_vm_set_page_dirty(
 			offset += 1 << inode->i_blkbits;
 		} while (bh != head);
 	}
+	/*
+	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
+	 * per-memcg dirty page counters.
+	 */
+	memcg = mem_cgroup_begin_page_stat(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
@@ -1902,13 +1908,15 @@ xfs_vm_set_page_dirty(
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		if (page->mapping) {	/* Race with truncate? */
 			WARN_ON_ONCE(!PageUptodate(page));
-			account_page_dirtied(page, mapping);
+			account_page_dirtied(page, mapping, memcg);
 			radix_tree_tag_set(&mapping->page_tree,
 					page_index(page), PAGECACHE_TAG_DIRTY);
 		}
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
+	mem_cgroup_end_page_stat(memcg);
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	return newly_dirty;
 }
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 3b7591224f4a..7c62fca53e2f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -41,6 +41,7 @@
 #include <linux/dcache.h>
 #include <linux/falloc.h>
 #include <linux/pagevec.h>
+#include <linux/backing-dev.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;