Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/writeback

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/writeback: (27 commits)
  mm: properly reflect task dirty limits in dirty_exceeded logic
  writeback: don't busy retry writeback on new/freeing inodes
  writeback: scale IO chunk size up to half device bandwidth
  writeback: trace global_dirty_state
  writeback: introduce max-pause and pass-good dirty limits
  writeback: introduce smoothed global dirty limit
  writeback: consolidate variable names in balance_dirty_pages()
  writeback: show bdi write bandwidth in debugfs
  writeback: bdi write bandwidth estimation
  writeback: account per-bdi accumulated written pages
  writeback: make writeback_control.nr_to_write straight
  writeback: skip tmpfs early in balance_dirty_pages_ratelimited_nr()
  writeback: trace event writeback_queue_io
  writeback: trace event writeback_single_inode
  writeback: remove .nonblocking and .encountered_congestion
  writeback: remove writeback_control.more_io
  writeback: skip balance_dirty_pages() for in-memory fs
  writeback: add bdi_dirty_limit() kernel-doc
  writeback: avoid extra sync work at enqueue time
  writeback: elevate queue_io() into wb_writeback()
  ...

Fix up trivial conflicts in fs/fs-writeback.c and mm/filemap.c

fs/block_dev.c

@@ -44,24 +44,28 @@ inline struct block_device *I_BDEV(struct inode *inode)
 {
 	return &BDEV_I(inode)->bdev;
 }
-
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * move the inode from it's current bdi to the a new bdi. if the inode is dirty
- * we need to move it onto the dirty list of @dst so that the inode is always
- * on the right list.
+ * Move the inode from its current bdi to a new bdi. If the inode is dirty we
+ * need to move it onto the dirty list of @dst so that the inode is always on
+ * the right list.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	spin_lock(&inode_wb_list_lock);
+	struct backing_dev_info *old = inode->i_data.backing_dev_info;
+
+	if (unlikely(dst == old))		/* deadlock avoidance */
+		return;
+	bdi_lock_two(&old->wb, &dst->wb);
 	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
 	if (inode->i_state & I_DIRTY)
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
 	spin_unlock(&inode->i_lock);
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&old->wb.list_lock);
+	spin_unlock(&dst->wb.list_lock);
 }
 
 static sector_t max_block(struct block_device *bdev)

fs/btrfs/extent_io.c

@@ -2551,7 +2551,6 @@ int extent_write_full_page(struct extent_io_tree *tree, struct page *page,
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= wbc->sync_mode,
-		.older_than_this = NULL,
 		.nr_to_write	= 64,
 		.range_start	= page_offset(page) + PAGE_CACHE_SIZE,
 		.range_end	= (loff_t)-1,
@@ -2584,7 +2583,6 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= mode,
-		.older_than_this = NULL,
 		.nr_to_write	= nr_pages * 2,
 		.range_start	= start,
 		.range_end	= end + 1,

fs/ext4/inode.c

@@ -2741,7 +2741,7 @@ static int write_cache_pages_da(struct address_space *mapping,
 	index = wbc->range_start >> PAGE_CACHE_SHIFT;
 	end = wbc->range_end >> PAGE_CACHE_SHIFT;
 
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
@@ -2973,7 +2973,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	}
 
 retry:
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 
 	while (!ret && wbc->nr_to_write > 0) {

fs/inode.c

@@ -37,7 +37,7 @@
  *   inode->i_sb->s_inode_lru, inode->i_lru
  * inode_sb_list_lock protects:
  *   sb->s_inodes, inode->i_sb_list
- * inode_wb_list_lock protects:
+ * bdi->wb.list_lock protects:
  *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
  * inode_hash_lock protects:
  *   inode_hashtable, inode->i_hash
@@ -48,7 +48,7 @@
  *   inode->i_lock
  *     inode->i_sb->s_inode_lru_lock
  *
- * inode_wb_list_lock
+ * bdi->wb.list_lock
  *   inode->i_lock
  *
  * inode_hash_lock
@@ -65,7 +65,6 @@ static struct hlist_head *inode_hashtable __read_mostly;
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_wb_list_lock);
 
 /*
  * Empty aops. Can be used for the cases where the user does not

fs/nfs/write.c

@@ -1566,8 +1566,7 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		int status;
 		bool sync = true;
 
-		if (wbc->sync_mode == WB_SYNC_NONE || wbc->nonblocking ||
-		    wbc->for_background)
+		if (wbc->sync_mode == WB_SYNC_NONE)
 			sync = false;
 
 		status = pnfs_layoutcommit_inode(inode, sync);

include/linux/backing-dev.h

@@ -40,6 +40,7 @@ typedef int (congested_fn)(void *, int);
 enum bdi_stat_item {
 	BDI_RECLAIMABLE,
 	BDI_WRITEBACK,
+	BDI_WRITTEN,
 	NR_BDI_STAT_ITEMS
 };
 
@@ -57,6 +58,7 @@ struct bdi_writeback {
 	struct list_head b_dirty;	/* dirty inodes */
 	struct list_head b_io;		/* parked for writeback */
 	struct list_head b_more_io;	/* parked for more writeback */
+	spinlock_t list_lock;		/* protects the b_* lists */
 };
 
 struct backing_dev_info {
@@ -71,6 +73,11 @@ struct backing_dev_info {
 
 	struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
 
+	unsigned long bw_time_stamp;	/* last time write bw is updated */
+	unsigned long written_stamp;	/* pages written at bw_time_stamp */
+	unsigned long write_bandwidth;	/* the estimated write bandwidth */
+	unsigned long avg_write_bandwidth; /* further smoothed write bw */
+
 	struct prop_local_percpu completions;
 	int dirty_exceeded;
 
@@ -106,6 +113,7 @@ int bdi_writeback_thread(void *data);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_arm_supers_timer(void);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;

include/linux/writeback.h

@@ -7,9 +7,39 @@
 #include <linux/sched.h>
 #include <linux/fs.h>
 
-struct backing_dev_info;
+/*
+ * The 1/4 region under the global dirty thresh is for smooth dirty throttling:
+ *
+ *	(thresh - thresh/DIRTY_FULL_SCOPE, thresh)
+ *
+ * The 1/16 region above the global dirty limit will be put to maximum pauses:
+ *
+ *	(limit, limit + limit/DIRTY_MAXPAUSE_AREA)
+ *
+ * The 1/16 region above the max-pause region, dirty exceeded bdi's will be put
+ * to loops:
+ *
+ *	(limit + limit/DIRTY_MAXPAUSE_AREA, limit + limit/DIRTY_PASSGOOD_AREA)
+ *
+ * Further beyond, all dirtier tasks will enter a loop waiting (possibly long
+ * time) for the dirty pages to drop, unless written enough pages.
+ *
+ * The global dirty threshold is normally equal to the global dirty limit,
+ * except when the system suddenly allocates a lot of anonymous memory and
+ * knocks down the global dirty threshold quickly, in which case the global
+ * dirty limit will follow down slowly to prevent livelocking all dirtier tasks.
+ */
+#define DIRTY_SCOPE		8
+#define DIRTY_FULL_SCOPE	(DIRTY_SCOPE / 2)
+#define DIRTY_MAXPAUSE_AREA		16
+#define DIRTY_PASSGOOD_AREA		8
+
+/*
+ * 4MB minimal write chunk size
+ */
+#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
 
-extern spinlock_t inode_wb_list_lock;
+struct backing_dev_info;
 
 /*
  * fs/fs-writeback.c
@@ -26,11 +56,6 @@ enum writeback_sync_modes {
  */
 struct writeback_control {
 	enum writeback_sync_modes sync_mode;
-	unsigned long *older_than_this;	/* If !NULL, only write back inodes
-					   older than this */
-	unsigned long wb_start;         /* Time writeback_inodes_wb was
-					   called. This is needed to avoid
-					   extra jobs and livelock */
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
 	long pages_skipped;		/* Pages which were not written */
@@ -43,13 +68,11 @@ struct writeback_control {
 	loff_t range_start;
 	loff_t range_end;
 
-	unsigned nonblocking:1;		/* Don't get stuck on request queues */
-	unsigned encountered_congestion:1; /* An output: a queue is full */
 	unsigned for_kupdate:1;		/* A kupdate writeback */
 	unsigned for_background:1;	/* A background writeback */
+	unsigned tagged_writepages:1;	/* tag-and-write to avoid livelock */
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
-	unsigned more_io:1;		/* more io to be dispatched */
 };
 
 /*
@@ -62,8 +85,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr);
 int writeback_inodes_sb_if_idle(struct super_block *);
 int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr);
 void sync_inodes_sb(struct super_block *);
-void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc);
+long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages);
 long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
 void wakeup_flusher_threads(long nr_pages);
 
@@ -94,6 +116,8 @@ static inline void laptop_sync_completion(void) { }
 #endif
 void throttle_vm_writeout(gfp_t gfp_mask);
 
+extern unsigned long global_dirty_limit;
+
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;
 extern unsigned long dirty_background_bytes;
@@ -128,6 +152,13 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
 			       unsigned long dirty);
 
+void __bdi_update_bandwidth(struct backing_dev_info *bdi,
+			    unsigned long thresh,
+			    unsigned long dirty,
+			    unsigned long bdi_thresh,
+			    unsigned long bdi_dirty,
+			    unsigned long start_time);
+
 void page_writeback_init(void);
 void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 					unsigned long nr_pages_dirtied);

include/trace/events/btrfs.h

@@ -284,7 +284,6 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__field(	long,   pages_skipped		)
 		__field(	loff_t, range_start		)
 		__field(	loff_t, range_end		)
-		__field(	char,   nonblocking		)
 		__field(	char,   for_kupdate		)
 		__field(	char,   for_reclaim		)
 		__field(	char,   range_cyclic		)
@@ -299,7 +298,6 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->range_start	= wbc->range_start;
 		__entry->range_end	= wbc->range_end;
-		__entry->nonblocking	= wbc->nonblocking;
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
@@ -310,13 +308,13 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 
 	TP_printk("root = %llu(%s), ino = %lu, page_index = %lu, "
 		  "nr_to_write = %ld, pages_skipped = %ld, range_start = %llu, "
-		  "range_end = %llu, nonblocking = %d, for_kupdate = %d, "
+		  "range_end = %llu, for_kupdate = %d, "
 		  "for_reclaim = %d, range_cyclic = %d, writeback_index = %lu",
 		  show_root_type(__entry->root_objectid),
 		  (unsigned long)__entry->ino, __entry->index,
 		  __entry->nr_to_write, __entry->pages_skipped,
 		  __entry->range_start, __entry->range_end,
-		  __entry->nonblocking, __entry->for_kupdate,
+		  __entry->for_kupdate,
 		  __entry->for_reclaim, __entry->range_cyclic,
 		  (unsigned long)__entry->writeback_index)
 );

include/trace/events/ext4.h

@@ -380,7 +380,6 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__field(	int,	pages_written		)
 		__field(	long,	pages_skipped		)
 		__field(	int,	sync_mode		)
-		__field(	char,	more_io			)	
 		__field(       pgoff_t,	writeback_index		)
 	),
 
@@ -391,16 +390,15 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__entry->pages_written	= pages_written;
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->sync_mode	= wbc->sync_mode;
-		__entry->more_io	= wbc->more_io;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
 	TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld "
-		  " more_io %d sync_mode %d writeback_index %lu",
+		  "sync_mode %d writeback_index %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->ret,
 		  __entry->pages_written, __entry->pages_skipped,
-		  __entry->more_io, __entry->sync_mode,
+		  __entry->sync_mode,
 		  (unsigned long) __entry->writeback_index)
 );
 

include/trace/events/writeback.h

@@ -8,6 +8,19 @@
 #include <linux/device.h>
 #include <linux/writeback.h>
 
+#define show_inode_state(state)					\
+	__print_flags(state, "|",				\
+		{I_DIRTY_SYNC,		"I_DIRTY_SYNC"},	\
+		{I_DIRTY_DATASYNC,	"I_DIRTY_DATASYNC"},	\
+		{I_DIRTY_PAGES,		"I_DIRTY_PAGES"},	\
+		{I_NEW,			"I_NEW"},		\
+		{I_WILL_FREE,		"I_WILL_FREE"},		\
+		{I_FREEING,		"I_FREEING"},		\
+		{I_CLEAR,		"I_CLEAR"},		\
+		{I_SYNC,		"I_SYNC"},		\
+		{I_REFERENCED,		"I_REFERENCED"}		\
+	)
+
 struct wb_writeback_work;
 
 DECLARE_EVENT_CLASS(writeback_work_class,
@@ -49,6 +62,9 @@ DEFINE_EVENT(writeback_work_class, name, \
 DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
 DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_start);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_written);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_wait);
 
 TRACE_EVENT(writeback_pages_written,
 	TP_PROTO(long pages_written),
@@ -88,6 +104,30 @@ DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
 DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
 DEFINE_WRITEBACK_EVENT(writeback_thread_start);
 DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
+DEFINE_WRITEBACK_EVENT(balance_dirty_start);
+DEFINE_WRITEBACK_EVENT(balance_dirty_wait);
+
+TRACE_EVENT(balance_dirty_written,
+
+	TP_PROTO(struct backing_dev_info *bdi, int written),
+
+	TP_ARGS(bdi, written),
+
+	TP_STRUCT__entry(
+		__array(char,	name, 32)
+		__field(int,	written)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->written = written;
+	),
+
+	TP_printk("bdi %s written %d",
+		  __entry->name,
+		  __entry->written
+	)
+);
 
 DECLARE_EVENT_CLASS(wbc_class,
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),
@@ -101,8 +141,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, for_background)
 		__field(int, for_reclaim)
 		__field(int, range_cyclic)
-		__field(int, more_io)
-		__field(unsigned long, older_than_this)
 		__field(long, range_start)
 		__field(long, range_end)
 	),
@@ -116,15 +154,12 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background	= wbc->for_background;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
-		__entry->more_io	= wbc->more_io;
-		__entry->older_than_this = wbc->older_than_this ?
-						*wbc->older_than_this : 0;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
-		"bgrd=%d reclm=%d cyclic=%d more=%d older=0x%lx "
+		"bgrd=%d reclm=%d cyclic=%d "
 		"start=0x%lx end=0x%lx",
 		__entry->name,
 		__entry->nr_to_write,
@@ -134,8 +169,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background,
 		__entry->for_reclaim,
 		__entry->range_cyclic,
-		__entry->more_io,
-		__entry->older_than_this,
 		__entry->range_start,
 		__entry->range_end)
 )
@@ -144,14 +177,79 @@ DECLARE_EVENT_CLASS(wbc_class,
 DEFINE_EVENT(wbc_class, name, \
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \
 	TP_ARGS(wbc, bdi))
-DEFINE_WBC_EVENT(wbc_writeback_start);
-DEFINE_WBC_EVENT(wbc_writeback_written);
-DEFINE_WBC_EVENT(wbc_writeback_wait);
-DEFINE_WBC_EVENT(wbc_balance_dirty_start);
-DEFINE_WBC_EVENT(wbc_balance_dirty_written);
-DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+TRACE_EVENT(writeback_queue_io,
+	TP_PROTO(struct bdi_writeback *wb,
+		 unsigned long *older_than_this,
+		 int moved),
+	TP_ARGS(wb, older_than_this, moved),
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned long,	older)
+		__field(long,		age)
+		__field(int,		moved)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+		__entry->older	= older_than_this ?  *older_than_this : 0;
+		__entry->age	= older_than_this ?
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+		__entry->moved	= moved;
+	),
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d",
+		__entry->name,
+		__entry->older,	/* older_than_this in jiffies */
+		__entry->age,	/* older_than_this in relative milliseconds */
+		__entry->moved)
+);
+
+TRACE_EVENT(global_dirty_state,
+
+	TP_PROTO(unsigned long background_thresh,
+		 unsigned long dirty_thresh
+	),
+
+	TP_ARGS(background_thresh,
+		dirty_thresh
+	),
+
+	TP_STRUCT__entry(
+		__field(unsigned long,	nr_dirty)
+		__field(unsigned long,	nr_writeback)
+		__field(unsigned long,	nr_unstable)
+		__field(unsigned long,	background_thresh)
+		__field(unsigned long,	dirty_thresh)
+		__field(unsigned long,	dirty_limit)
+		__field(unsigned long,	nr_dirtied)
+		__field(unsigned long,	nr_written)
+	),
+
+	TP_fast_assign(
+		__entry->nr_dirty	= global_page_state(NR_FILE_DIRTY);
+		__entry->nr_writeback	= global_page_state(NR_WRITEBACK);
+		__entry->nr_unstable	= global_page_state(NR_UNSTABLE_NFS);
+		__entry->nr_dirtied	= global_page_state(NR_DIRTIED);
+		__entry->nr_written	= global_page_state(NR_WRITTEN);
+		__entry->background_thresh = background_thresh;
+		__entry->dirty_thresh	= dirty_thresh;
+		__entry->dirty_limit = global_dirty_limit;
+	),
+
+	TP_printk("dirty=%lu writeback=%lu unstable=%lu "
+		  "bg_thresh=%lu thresh=%lu limit=%lu "
+		  "dirtied=%lu written=%lu",
+		  __entry->nr_dirty,
+		  __entry->nr_writeback,
+		  __entry->nr_unstable,
+		  __entry->background_thresh,
+		  __entry->dirty_thresh,
+		  __entry->dirty_limit,
+		  __entry->nr_dirtied,
+		  __entry->nr_written
+	)
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
@@ -187,6 +285,63 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested,
 	TP_ARGS(usec_timeout, usec_delayed)
 );
 
+DECLARE_EVENT_CLASS(writeback_single_inode_template,
+
+	TP_PROTO(struct inode *inode,
+		 struct writeback_control *wbc,
+		 unsigned long nr_to_write
+	),
+
+	TP_ARGS(inode, wbc, nr_to_write),
+
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(unsigned long, ino)
+		__field(unsigned long, state)
+		__field(unsigned long, age)
+		__field(unsigned long, writeback_index)
+		__field(long, nr_to_write)
+		__field(unsigned long, wrote)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name,
+			dev_name(inode->i_mapping->backing_dev_info->dev), 32);
+		__entry->ino		= inode->i_ino;
+		__entry->state		= inode->i_state;
+		__entry->age		= (jiffies - inode->dirtied_when) *
+								1000 / HZ;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
+		__entry->nr_to_write	= nr_to_write;
+		__entry->wrote		= nr_to_write - wbc->nr_to_write;
+	),
+
+	TP_printk("bdi %s: ino=%lu state=%s age=%lu "
+		  "index=%lu to_write=%ld wrote=%lu",
+		  __entry->name,
+		  __entry->ino,
+		  show_inode_state(__entry->state),
+		  __entry->age,
+		  __entry->writeback_index,
+		  __entry->nr_to_write,
+		  __entry->wrote
+	)
+);
+
+DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_requeue,
+	TP_PROTO(struct inode *inode,
+		 struct writeback_control *wbc,
+		 unsigned long nr_to_write),
+	TP_ARGS(inode, wbc, nr_to_write)
+);
+
+DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode,
+	TP_PROTO(struct inode *inode,
+		 struct writeback_control *wbc,
+		 unsigned long nr_to_write),
+	TP_ARGS(inode, wbc, nr_to_write)
+);
+
 #endif /* _TRACE_WRITEBACK_H */
 
 /* This part must be outside protection */

mm/backing-dev.c

@@ -45,6 +45,17 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+	if (wb1 < wb2) {
+		spin_lock(&wb1->list_lock);
+		spin_lock_nested(&wb2->list_lock, 1);
+	} else {
+		spin_lock(&wb2->list_lock);
+		spin_lock_nested(&wb1->list_lock, 1);
+	}
+}
+
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -67,34 +78,42 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	struct inode *inode;
 
 	nr_dirty = nr_io = nr_more_io = 0;
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
 	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
-		   "BdiWriteback:     %8lu kB\n"
-		   "BdiReclaimable:   %8lu kB\n"
-		   "BdiDirtyThresh:   %8lu kB\n"
-		   "DirtyThresh:      %8lu kB\n"
-		   "BackgroundThresh: %8lu kB\n"
-		   "b_dirty:          %8lu\n"
-		   "b_io:             %8lu\n"
-		   "b_more_io:        %8lu\n"
-		   "bdi_list:         %8u\n"
-		   "state:            %8lx\n",
+		   "BdiWriteback:       %10lu kB\n"
+		   "BdiReclaimable:     %10lu kB\n"
+		   "BdiDirtyThresh:     %10lu kB\n"
+		   "DirtyThresh:        %10lu kB\n"
+		   "BackgroundThresh:   %10lu kB\n"
+		   "BdiWritten:         %10lu kB\n"
+		   "BdiWriteBandwidth:  %10lu kBps\n"
+		   "b_dirty:            %10lu\n"
+		   "b_io:               %10lu\n"
+		   "b_more_io:          %10lu\n"
+		   "bdi_list:           %10u\n"
+		   "state:              %10lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
-		   K(bdi_thresh), K(dirty_thresh),
-		   K(background_thresh), nr_dirty, nr_io, nr_more_io,
+		   K(bdi_thresh),
+		   K(dirty_thresh),
+		   K(background_thresh),
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+		   (unsigned long) K(bdi->write_bandwidth),
+		   nr_dirty,
+		   nr_io,
+		   nr_more_io,
 		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
@@ -249,18 +268,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
 	return wb_has_dirty_io(&bdi->wb);
 }
 
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
-	struct writeback_control wbc = {
-		.sync_mode		= WB_SYNC_NONE,
-		.older_than_this	= NULL,
-		.range_cyclic		= 1,
-		.nr_to_write		= 1024,
-	};
-
-	writeback_inodes_wb(&bdi->wb, &wbc);
-}
-
 /*
  * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
  * or we risk deadlocking on ->s_umount. The longer term solution would be
@@ -446,9 +453,10 @@ static int bdi_forker_thread(void *ptr)
 			if (IS_ERR(task)) {
 				/*
 				 * If thread creation fails, force writeout of
-				 * the bdi from the thread.
+				 * the bdi from the thread. Hopefully 1024 is
+				 * large enough for efficient IO.
 				 */
-				bdi_flush_io(bdi);
+				writeback_inodes_wb(&bdi->wb, 1024);
 			} else {
 				/*
 				 * The spinlock makes sure we do not lose
@@ -629,9 +637,15 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&wb->b_dirty);
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
+	spin_lock_init(&wb->list_lock);
 	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
 }
 
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -654,6 +668,13 @@ int bdi_init(struct backing_dev_info *bdi)
 	}
 
 	bdi->dirty_exceeded = 0;
+
+	bdi->bw_time_stamp = jiffies;
+	bdi->written_stamp = 0;
+
+	bdi->write_bandwidth = INIT_BW;
+	bdi->avg_write_bandwidth = INIT_BW;
+
 	err = prop_local_init_percpu(&bdi->completions);
 
 	if (err) {
@@ -677,11 +698,12 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-		spin_lock(&inode_wb_list_lock);
+		bdi_lock_two(&bdi->wb, dst);
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&inode_wb_list_lock);
+		spin_unlock(&bdi->wb.list_lock);
+		spin_unlock(&dst->list_lock);
 	}
 
 	bdi_unregister(bdi);

mm/filemap.c

@@ -78,7 +78,7 @@
  *  ->i_mutex			(generic_file_buffered_write)
  *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
- *  inode_wb_list_lock
+ *  bdi->wb.list_lock
  *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
@@ -96,9 +96,9 @@
  *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
- *    inode_wb_list_lock	(page_remove_rmap->set_page_dirty)
+ *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
- *    inode_wb_list_lock	(zap_pte_range->set_page_dirty)
+ *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *

mm/rmap.c

@@ -31,11 +31,11 @@
  *               mmlist_lock (in mmput, drain_mmlist and others)
  *               mapping->private_lock (in __set_page_dirty_buffers)
  *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
- *               inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty)
+ *               bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
  *                 sb_lock (within inode_lock in fs/fs-writeback.c)
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,
- *                           within inode_wb_list_lock in __sync_single_inode)
+ *                           within bdi.wb->list_lock in __sync_single_inode)
  *
  * anon_vma->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
  *   ->tasklist_lock