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

* 'writeback-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux:
  writeback: Add a 'reason' to wb_writeback_work
  writeback: send work item to queue_io, move_expired_inodes
  writeback: trace event balance_dirty_pages
  writeback: trace event bdi_dirty_ratelimit
  writeback: fix ppc compile warnings on do_div(long long, unsigned long)
  writeback: per-bdi background threshold
  writeback: dirty position control - bdi reserve area
  writeback: control dirty pause time
  writeback: limit max dirty pause time
  writeback: IO-less balance_dirty_pages()
  writeback: per task dirty rate limit
  writeback: stabilize bdi->dirty_ratelimit
  writeback: dirty rate control
  writeback: add bg_threshold parameter to __bdi_update_bandwidth()
  writeback: dirty position control
  writeback: account per-bdi accumulated dirtied pages

4 files changed, 178 insertions, 37 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 3b2f9cb8298..b1038bd686a 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_DIRTIED,
 	BDI_WRITTEN,
 	NR_BDI_STAT_ITEMS
 };
@@ -74,10 +75,20 @@ 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 dirtied_stamp;
 	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 */
 
+	/*
+	 * The base dirty throttle rate, re-calculated on every 200ms.
+	 * All the bdi tasks' dirty rate will be curbed under it.
+	 * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit
+	 * in small steps and is much more smooth/stable than the latter.
+	 */
+	unsigned long dirty_ratelimit;
+	unsigned long balanced_dirty_ratelimit;
+
 	struct prop_local_percpu completions;
 	int dirty_exceeded;
 
@@ -107,7 +118,8 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
 int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
-void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages);
+void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
+			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
 int bdi_writeback_thread(void *data);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e8acce717d2..68daf4f27e2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1522,6 +1522,13 @@ struct task_struct {
 	int make_it_fail;
 #endif
 	struct prop_local_single dirties;
+	/*
+	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
+	 * balance_dirty_pages() for some dirty throttling pause
+	 */
+	int nr_dirtied;
+	int nr_dirtied_pause;
+
 #ifdef CONFIG_LATENCYTOP
 	int latency_record_count;
 	struct latency_record latency_record[LT_SAVECOUNT];
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 2b8963ff0f3..a378c295851 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -39,6 +39,23 @@ enum writeback_sync_modes {
 };
 
 /*
+ * why some writeback work was initiated
+ */
+enum wb_reason {
+	WB_REASON_BACKGROUND,
+	WB_REASON_TRY_TO_FREE_PAGES,
+	WB_REASON_SYNC,
+	WB_REASON_PERIODIC,
+	WB_REASON_LAPTOP_TIMER,
+	WB_REASON_FREE_MORE_MEM,
+	WB_REASON_FS_FREE_SPACE,
+	WB_REASON_FORKER_THREAD,
+
+	WB_REASON_MAX,
+};
+extern const char *wb_reason_name[];
+
+/*
  * A control structure which tells the writeback code what to do.  These are
  * always on the stack, and hence need no locking.  They are always initialised
  * in a manner such that unspecified fields are set to zero.
@@ -69,14 +86,17 @@ struct writeback_control {
  */	
 struct bdi_writeback;
 int inode_wait(void *);
-void writeback_inodes_sb(struct super_block *);
-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 writeback_inodes_sb(struct super_block *, enum wb_reason reason);
+void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
+							enum wb_reason reason);
+int writeback_inodes_sb_if_idle(struct super_block *, enum wb_reason reason);
+int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr,
+							enum wb_reason reason);
 void sync_inodes_sb(struct super_block *);
-long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages);
+long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
+				enum wb_reason reason);
 long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
-void wakeup_flusher_threads(long nr_pages);
+void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
@@ -143,6 +163,7 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
 
 void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 			    unsigned long thresh,
+			    unsigned long bg_thresh,
 			    unsigned long dirty,
 			    unsigned long bdi_thresh,
 			    unsigned long bdi_dirty,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 5f172703eb4..b99caa8b780 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -34,6 +34,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, for_kupdate)
 		__field(int, range_cyclic)
 		__field(int, for_background)
+		__field(int, reason)
 	),
 	TP_fast_assign(
 		strncpy(__entry->name, dev_name(bdi->dev), 32);
@@ -43,16 +44,18 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__entry->for_kupdate = work->for_kupdate;
 		__entry->range_cyclic = work->range_cyclic;
 		__entry->for_background	= work->for_background;
+		__entry->reason = work->reason;
 	),
 	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
-		  "kupdate=%d range_cyclic=%d background=%d",
+		  "kupdate=%d range_cyclic=%d background=%d reason=%s",
 		  __entry->name,
 		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
 		  __entry->nr_pages,
 		  __entry->sync_mode,
 		  __entry->for_kupdate,
 		  __entry->range_cyclic,
-		  __entry->for_background
+		  __entry->for_background,
+		  wb_reason_name[__entry->reason]
 	)
 );
 #define DEFINE_WRITEBACK_WORK_EVENT(name) \
@@ -104,30 +107,6 @@ 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),
@@ -181,27 +160,31 @@ DEFINE_WBC_EVENT(wbc_writepage);
 
 TRACE_EVENT(writeback_queue_io,
 	TP_PROTO(struct bdi_writeback *wb,
-		 unsigned long *older_than_this,
+		 struct wb_writeback_work *work,
 		 int moved),
-	TP_ARGS(wb, older_than_this, moved),
+	TP_ARGS(wb, work, moved),
 	TP_STRUCT__entry(
 		__array(char,		name, 32)
 		__field(unsigned long,	older)
 		__field(long,		age)
 		__field(int,		moved)
+		__field(int,		reason)
 	),
 	TP_fast_assign(
+		unsigned long *older_than_this = work->older_than_this;
 		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;
+		__entry->reason	= work->reason;
 	),
-	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d",
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s",
 		__entry->name,
 		__entry->older,	/* older_than_this in jiffies */
 		__entry->age,	/* older_than_this in relative milliseconds */
-		__entry->moved)
+		__entry->moved,
+		wb_reason_name[__entry->reason])
 );
 
 TRACE_EVENT(global_dirty_state,
@@ -250,6 +233,124 @@ TRACE_EVENT(global_dirty_state,
 	)
 );
 
+#define KBps(x)			((x) << (PAGE_SHIFT - 10))
+
+TRACE_EVENT(bdi_dirty_ratelimit,
+
+	TP_PROTO(struct backing_dev_info *bdi,
+		 unsigned long dirty_rate,
+		 unsigned long task_ratelimit),
+
+	TP_ARGS(bdi, dirty_rate, task_ratelimit),
+
+	TP_STRUCT__entry(
+		__array(char,		bdi, 32)
+		__field(unsigned long,	write_bw)
+		__field(unsigned long,	avg_write_bw)
+		__field(unsigned long,	dirty_rate)
+		__field(unsigned long,	dirty_ratelimit)
+		__field(unsigned long,	task_ratelimit)
+		__field(unsigned long,	balanced_dirty_ratelimit)
+	),
+
+	TP_fast_assign(
+		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
+		__entry->write_bw	= KBps(bdi->write_bandwidth);
+		__entry->avg_write_bw	= KBps(bdi->avg_write_bandwidth);
+		__entry->dirty_rate	= KBps(dirty_rate);
+		__entry->dirty_ratelimit = KBps(bdi->dirty_ratelimit);
+		__entry->task_ratelimit	= KBps(task_ratelimit);
+		__entry->balanced_dirty_ratelimit =
+					  KBps(bdi->balanced_dirty_ratelimit);
+	),
+
+	TP_printk("bdi %s: "
+		  "write_bw=%lu awrite_bw=%lu dirty_rate=%lu "
+		  "dirty_ratelimit=%lu task_ratelimit=%lu "
+		  "balanced_dirty_ratelimit=%lu",
+		  __entry->bdi,
+		  __entry->write_bw,		/* write bandwidth */
+		  __entry->avg_write_bw,	/* avg write bandwidth */
+		  __entry->dirty_rate,		/* bdi dirty rate */
+		  __entry->dirty_ratelimit,	/* base ratelimit */
+		  __entry->task_ratelimit, /* ratelimit with position control */
+		  __entry->balanced_dirty_ratelimit /* the balanced ratelimit */
+	)
+);
+
+TRACE_EVENT(balance_dirty_pages,
+
+	TP_PROTO(struct backing_dev_info *bdi,
+		 unsigned long thresh,
+		 unsigned long bg_thresh,
+		 unsigned long dirty,
+		 unsigned long bdi_thresh,
+		 unsigned long bdi_dirty,
+		 unsigned long dirty_ratelimit,
+		 unsigned long task_ratelimit,
+		 unsigned long dirtied,
+		 long pause,
+		 unsigned long start_time),
+
+	TP_ARGS(bdi, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty,
+		dirty_ratelimit, task_ratelimit,
+		dirtied, pause, start_time),
+
+	TP_STRUCT__entry(
+		__array(	 char,	bdi, 32)
+		__field(unsigned long,	limit)
+		__field(unsigned long,	setpoint)
+		__field(unsigned long,	dirty)
+		__field(unsigned long,	bdi_setpoint)
+		__field(unsigned long,	bdi_dirty)
+		__field(unsigned long,	dirty_ratelimit)
+		__field(unsigned long,	task_ratelimit)
+		__field(unsigned int,	dirtied)
+		__field(unsigned int,	dirtied_pause)
+		__field(unsigned long,	paused)
+		__field(	 long,	pause)
+	),
+
+	TP_fast_assign(
+		unsigned long freerun = (thresh + bg_thresh) / 2;
+		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
+
+		__entry->limit		= global_dirty_limit;
+		__entry->setpoint	= (global_dirty_limit + freerun) / 2;
+		__entry->dirty		= dirty;
+		__entry->bdi_setpoint	= __entry->setpoint *
+						bdi_thresh / (thresh + 1);
+		__entry->bdi_dirty	= bdi_dirty;
+		__entry->dirty_ratelimit = KBps(dirty_ratelimit);
+		__entry->task_ratelimit	= KBps(task_ratelimit);
+		__entry->dirtied	= dirtied;
+		__entry->dirtied_pause	= current->nr_dirtied_pause;
+		__entry->pause		= pause * 1000 / HZ;
+		__entry->paused		= (jiffies - start_time) * 1000 / HZ;
+	),
+
+
+	TP_printk("bdi %s: "
+		  "limit=%lu setpoint=%lu dirty=%lu "
+		  "bdi_setpoint=%lu bdi_dirty=%lu "
+		  "dirty_ratelimit=%lu task_ratelimit=%lu "
+		  "dirtied=%u dirtied_pause=%u "
+		  "paused=%lu pause=%ld",
+		  __entry->bdi,
+		  __entry->limit,
+		  __entry->setpoint,
+		  __entry->dirty,
+		  __entry->bdi_setpoint,
+		  __entry->bdi_dirty,
+		  __entry->dirty_ratelimit,
+		  __entry->task_ratelimit,
+		  __entry->dirtied,
+		  __entry->dirtied_pause,
+		  __entry->paused,	/* ms */
+		  __entry->pause	/* ms */
+	  )
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),