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

5 files changed, 224 insertions, 34 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 96f4094b706d..a008982e7c08 100644
--- a/include/linux/backing-dev.h
+++ b/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;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 17e7ccc322a5..f1bfa12ea246 100644
--- a/include/linux/writeback.h
+++ b/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
 
-extern spinlock_t inode_wb_list_lock;
+/*
+ * 4MB minimal write chunk size
+ */
+#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
+
+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);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 4114129f0794..b31702ac15be 100644
--- a/include/trace/events/btrfs.h
+++ b/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)
 );
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 5ce2b2f5f524..6363193a3418 100644
--- a/include/trace/events/ext4.h
+++ b/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)
 );
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 4e249b927eaa..6bca4cc0063c 100644
--- a/include/trace/events/writeback.h
+++ b/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 */