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

Author: torvalds

fs/btrfs/extent-tree.c

@@ -3340,7 +3340,8 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 		smp_mb();
 		nr_pages = min_t(unsigned long, nr_pages,
 		       root->fs_info->delalloc_bytes >> PAGE_CACHE_SHIFT);
-		writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
+		writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages,
+						WB_REASON_FS_FREE_SPACE);
 
 		spin_lock(&space_info->lock);
 		if (reserved > space_info->bytes_reserved)

fs/buffer.c

@@ -288,7 +288,7 @@ static void free_more_memory(void)
 	struct zone *zone;
 	int nid;
 
-	wakeup_flusher_threads(1024);
+	wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM);
 	yield();
 
 	for_each_online_node(nid) {

fs/ext4/inode.c

@@ -2372,7 +2372,7 @@ static int ext4_nonda_switch(struct super_block *sb)
 	 * start pushing delalloc when 1/2 of free blocks are dirty.
 	 */
 	if (free_blocks < 2 * dirty_blocks)
-		writeback_inodes_sb_if_idle(sb);
+		writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE);
 
 	return 0;
 }

fs/fs-writeback.c

@@ -41,11 +41,23 @@ struct wb_writeback_work {
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
+	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
 	struct completion *done;	/* set if the caller waits */
 };
 
+const char *wb_reason_name[] = {
+	[WB_REASON_BACKGROUND]		= "background",
+	[WB_REASON_TRY_TO_FREE_PAGES]	= "try_to_free_pages",
+	[WB_REASON_SYNC]		= "sync",
+	[WB_REASON_PERIODIC]		= "periodic",
+	[WB_REASON_LAPTOP_TIMER]	= "laptop_timer",
+	[WB_REASON_FREE_MORE_MEM]	= "free_more_memory",
+	[WB_REASON_FS_FREE_SPACE]	= "fs_free_space",
+	[WB_REASON_FORKER_THREAD]	= "forker_thread"
+};
+
 /*
  * Include the creation of the trace points after defining the
  * wb_writeback_work structure so that the definition remains local to this
@@ -115,7 +127,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 
 static void
 __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-		      bool range_cyclic)
+		      bool range_cyclic, enum wb_reason reason)
 {
 	struct wb_writeback_work *work;
 
@@ -135,6 +147,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work->sync_mode	= WB_SYNC_NONE;
 	work->nr_pages	= nr_pages;
 	work->range_cyclic = range_cyclic;
+	work->reason	= reason;
 
 	bdi_queue_work(bdi, work);
 }
@@ -150,9 +163,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
  *   completion. Caller need not hold sb s_umount semaphore.
  *
  */
-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)
 {
-	__bdi_start_writeback(bdi, nr_pages, true);
+	__bdi_start_writeback(bdi, nr_pages, true, reason);
 }
 
 /**
@@ -251,7 +265,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-			       unsigned long *older_than_this)
+			       struct wb_writeback_work *work)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
@@ -262,8 +276,8 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (older_than_this &&
-		    inode_dirtied_after(inode, *older_than_this))
+		if (work->older_than_this &&
+		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
 		if (sb && sb != inode->i_sb)
 			do_sb_sort = 1;
@@ -302,13 +316,13 @@ static int move_expired_inodes(struct list_head *delaying_queue,
  *                                           |
  *                                           +--> dequeue for IO
  */
-static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
 {
 	int moved;
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
-	trace_writeback_queue_io(wb, older_than_this, moved);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work);
+	trace_writeback_queue_io(wb, work, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -641,31 +655,40 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb,
 	return wrote;
 }
 
-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)
 {
 	struct wb_writeback_work work = {
 		.nr_pages	= nr_pages,
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
+		.reason		= reason,
 	};
 
 	spin_lock(&wb->list_lock);
 	if (list_empty(&wb->b_io))
-		queue_io(wb, NULL);
+		queue_io(wb, &work);
 	__writeback_inodes_wb(wb, &work);
 	spin_unlock(&wb->list_lock);
 
 	return nr_pages - work.nr_pages;
 }
 
-static inline bool over_bground_thresh(void)
+static bool over_bground_thresh(struct backing_dev_info *bdi)
 {
 	unsigned long background_thresh, dirty_thresh;
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 
-	return (global_page_state(NR_FILE_DIRTY) +
-		global_page_state(NR_UNSTABLE_NFS) > background_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;
 }
 
 /*
@@ -675,7 +698,7 @@ static inline bool over_bground_thresh(void)
 static void wb_update_bandwidth(struct bdi_writeback *wb,
 				unsigned long start_time)
 {
-	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time);
+	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time);
 }
 
 /*
@@ -727,7 +750,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * For background writeout, stop when we are below the
 		 * background dirty threshold
 		 */
-		if (work->for_background && !over_bground_thresh())
+		if (work->for_background && !over_bground_thresh(wb->bdi))
 			break;
 
 		if (work->for_kupdate) {
@@ -738,7 +761,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
-			queue_io(wb, work->older_than_this);
+			queue_io(wb, work);
 		if (work->sb)
 			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
@@ -811,13 +834,14 @@ static unsigned long get_nr_dirty_pages(void)
 
 static long wb_check_background_flush(struct bdi_writeback *wb)
 {
-	if (over_bground_thresh()) {
+	if (over_bground_thresh(wb->bdi)) {
 
 		struct wb_writeback_work work = {
 			.nr_pages	= LONG_MAX,
 			.sync_mode	= WB_SYNC_NONE,
 			.for_background	= 1,
 			.range_cyclic	= 1,
+			.reason		= WB_REASON_BACKGROUND,
 		};
 
 		return wb_writeback(wb, &work);
@@ -851,6 +875,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 			.sync_mode	= WB_SYNC_NONE,
 			.for_kupdate	= 1,
 			.range_cyclic	= 1,
+			.reason		= WB_REASON_PERIODIC,
 		};
 
 		return wb_writeback(wb, &work);
@@ -969,7 +994,7 @@ int bdi_writeback_thread(void *data)
  * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
  * the whole world.
  */
-void wakeup_flusher_threads(long nr_pages)
+void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 {
 	struct backing_dev_info *bdi;
 
@@ -982,7 +1007,7 @@ void wakeup_flusher_threads(long nr_pages)
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		if (!bdi_has_dirty_io(bdi))
 			continue;
-		__bdi_start_writeback(bdi, nr_pages, false);
+		__bdi_start_writeback(bdi, nr_pages, false, reason);
 	}
 	rcu_read_unlock();
 }
@@ -1203,7 +1228,9 @@ static void wait_sb_inodes(struct super_block *sb)
  * on how many (if any) will be written, and this function does not wait
  * for IO completion of submitted IO.
  */
-void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr)
+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 = {
@@ -1212,6 +1239,7 @@ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr)
 		.tagged_writepages	= 1,
 		.done			= &done,
 		.nr_pages		= nr,
+		.reason			= reason,
 	};
 
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
@@ -1228,9 +1256,9 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr);
  * on how many (if any) will be written, and this function does not wait
  * for IO completion of submitted IO.
  */
-void writeback_inodes_sb(struct super_block *sb)
+void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 {
-	return writeback_inodes_sb_nr(sb, get_nr_dirty_pages());
+	return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
 }
 EXPORT_SYMBOL(writeback_inodes_sb);
 
@@ -1241,11 +1269,11 @@ EXPORT_SYMBOL(writeback_inodes_sb);
  * Invoke writeback_inodes_sb if no writeback is currently underway.
  * Returns 1 if writeback was started, 0 if not.
  */
-int writeback_inodes_sb_if_idle(struct super_block *sb)
+int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason)
 {
 	if (!writeback_in_progress(sb->s_bdi)) {
 		down_read(&sb->s_umount);
-		writeback_inodes_sb(sb);
+		writeback_inodes_sb(sb, reason);
 		up_read(&sb->s_umount);
 		return 1;
 	} else
@@ -1262,11 +1290,12 @@ EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
  * Returns 1 if writeback was started, 0 if not.
  */
 int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
-				   unsigned long nr)
+				   unsigned long nr,
+				   enum wb_reason reason)
 {
 	if (!writeback_in_progress(sb->s_bdi)) {
 		down_read(&sb->s_umount);
-		writeback_inodes_sb_nr(sb, nr);
+		writeback_inodes_sb_nr(sb, nr, reason);
 		up_read(&sb->s_umount);
 		return 1;
 	} else
@@ -1290,6 +1319,7 @@ void sync_inodes_sb(struct super_block *sb)
 		.nr_pages	= LONG_MAX,
 		.range_cyclic	= 0,
 		.done		= &done,
+		.reason		= WB_REASON_SYNC,
 	};
 
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));

fs/quota/quota.c

@@ -286,7 +286,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		/* caller already holds s_umount */
 		if (sb->s_flags & MS_RDONLY)
 			return -EROFS;
-		writeback_inodes_sb(sb);
+		writeback_inodes_sb(sb, WB_REASON_SYNC);
 		return 0;
 	default:
 		return -EINVAL;

fs/sync.c

@@ -43,7 +43,7 @@ static int __sync_filesystem(struct super_block *sb, int wait)
 	if (wait)
 		sync_inodes_sb(sb);
 	else
-		writeback_inodes_sb(sb);
+		writeback_inodes_sb(sb, WB_REASON_SYNC);
 
 	if (sb->s_op->sync_fs)
 		sb->s_op->sync_fs(sb, wait);
@@ -98,7 +98,7 @@ static void sync_filesystems(int wait)
  */
 SYSCALL_DEFINE0(sync)
 {
-	wakeup_flusher_threads(0);
+	wakeup_flusher_threads(0, WB_REASON_SYNC);
 	sync_filesystems(0);
 	sync_filesystems(1);
 	if (unlikely(laptop_mode))

fs/ubifs/budget.c

@@ -63,7 +63,7 @@
 static void shrink_liability(struct ubifs_info *c, int nr_to_write)
 {
 	down_read(&c->vfs_sb->s_umount);
-	writeback_inodes_sb(c->vfs_sb);
+	writeback_inodes_sb(c->vfs_sb, WB_REASON_FS_FREE_SPACE);
 	up_read(&c->vfs_sb->s_umount);
 }
 

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);

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];