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
  ...

1 files changed, 25 insertions, 1 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5db7b1379d17..e351da4a934f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -35,6 +35,7 @@
 #include <uapi/linux/fs.h>
 
 struct backing_dev_info;
+struct bdi_writeback;
 struct export_operations;
 struct hd_geometry;
 struct iovec;
@@ -634,6 +635,14 @@ struct inode {
 
 	struct hlist_node	i_hash;
 	struct list_head	i_wb_list;	/* backing dev IO list */
+#ifdef CONFIG_CGROUP_WRITEBACK
+	struct bdi_writeback	*i_wb;		/* the associated cgroup wb */
+
+	/* foreign inode detection, see wbc_detach_inode() */
+	int			i_wb_frn_winner;
+	u16			i_wb_frn_avg_time;
+	u16			i_wb_frn_history;
+#endif
 	struct list_head	i_lru;		/* inode LRU list */
 	struct list_head	i_sb_list;
 	union {
@@ -1232,6 +1241,8 @@ struct mm_struct;
 #define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
 #define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
 
+/* sb->s_iflags */
+#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
 
 /* Possible states of 'frozen' field */
 enum {
@@ -1270,6 +1281,7 @@ struct super_block {
 	const struct quotactl_ops	*s_qcop;
 	const struct export_operations *s_export_op;
 	unsigned long		s_flags;
+	unsigned long		s_iflags;	/* internal SB_I_* flags */
 	unsigned long		s_magic;
 	struct dentry		*s_root;
 	struct rw_semaphore	s_umount;
@@ -1806,6 +1818,11 @@ struct super_operations {
  *
  * I_DIO_WAKEUP		Never set.  Only used as a key for wait_on_bit().
  *
+ * I_WB_SWITCH		Cgroup bdi_writeback switching in progress.  Used to
+ *			synchronize competing switching instances and to tell
+ *			wb stat updates to grab mapping->tree_lock.  See
+ *			inode_switch_wb_work_fn() for details.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -1825,6 +1842,7 @@ struct super_operations {
 #define I_DIRTY_TIME		(1 << 11)
 #define __I_DIRTY_TIME_EXPIRED	12
 #define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
+#define I_WB_SWITCH		(1 << 13)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
@@ -2241,7 +2259,13 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
-extern int sb_is_blkdev_sb(struct super_block *sb);
+
+extern struct super_block *blockdev_superblock;
+
+static inline bool sb_is_blkdev_sb(struct super_block *sb)
+{
+	return sb == blockdev_superblock;
+}
 #else
 static inline void bd_forget(struct inode *inode) {}
 static inline int sync_blockdev(struct block_device *bdev) { return 0; }