writeback: move bandwidth related fields from backing_dev_info into bdi_writeback

Currently, a bdi (backing_dev_info) embeds single wb (bdi_writeback)
and the role of the separation is unclear.  For cgroup support for
writeback IOs, a bdi will be updated to host multiple wb's where each
wb serves writeback IOs of a different cgroup on the bdi.  To achieve
that, a wb should carry all states necessary for servicing writeback
IOs for a cgroup independently.

This patch moves bandwidth related fields from backing_dev_info into
bdi_writeback.

* The moved fields are: bw_time_stamp, dirtied_stamp, written_stamp,
  write_bandwidth, avg_write_bandwidth, dirty_ratelimit,
  balanced_dirty_ratelimit, completions and dirty_exceeded.

* writeback_chunk_size() and over_bground_thresh() now take @wb
  instead of @bdi.

* bdi_writeout_fraction(bdi, ...)	-> wb_writeout_fraction(wb, ...)
  bdi_dirty_limit(bdi, ...)		-> wb_dirty_limit(wb, ...)
  bdi_position_ration(bdi, ...)		-> wb_position_ratio(wb, ...)
  bdi_update_writebandwidth(bdi, ...)	-> wb_update_write_bandwidth(wb, ...)
  [__]bdi_update_bandwidth(bdi, ...)	-> [__]wb_update_bandwidth(wb, ...)
  bdi_{max|min}_pause(bdi, ...)		-> wb_{max|min}_pause(wb, ...)
  bdi_dirty_limits(bdi, ...)		-> wb_dirty_limits(wb, ...)

* Init/exits of the relocated fields are moved to bdi_wb_init/exit()
  respectively.  Note that explicit zeroing is dropped in the process
  as wb's are cleared in entirety anyway.

* As there's still only one bdi_writeback per backing_dev_info, all
  uses of bdi->stat[] are mechanically replaced with bdi->wb.stat[]
  introducing no behavior changes.

v2: Typo in description fixed as suggested by Jan.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

fs/f2fs/node.c

@@ -53,7 +53,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 							PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == DIRTY_DENTS) {
-		if (sbi->sb->s_bdi->dirty_exceeded)
+		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
 		mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
@@ -70,7 +70,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 				sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else {
-		if (sbi->sb->s_bdi->dirty_exceeded)
+		if (sbi->sb->s_bdi->wb.dirty_exceeded)
 			return false;
 	}
 	return res;

fs/f2fs/segment.h

@@ -713,7 +713,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {
-	if (sbi->sb->s_bdi->dirty_exceeded)
+	if (sbi->sb->s_bdi->wb.dirty_exceeded)
 		return 0;
 
 	if (type == DATA)

fs/fs-writeback.c

@@ -624,7 +624,7 @@ out:
 	return ret;
 }
 
-static long writeback_chunk_size(struct backing_dev_info *bdi,
+static long writeback_chunk_size(struct bdi_writeback *wb,
 				 struct wb_writeback_work *work)
 {
 	long pages;
@@ -645,7 +645,7 @@ static long writeback_chunk_size(struct backing_dev_info *bdi,
 	if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
 		pages = LONG_MAX;
 	else {
-		pages = min(bdi->avg_write_bandwidth / 2,
+		pages = min(wb->avg_write_bandwidth / 2,
 			    global_dirty_limit / DIRTY_SCOPE);
 		pages = min(pages, work->nr_pages);
 		pages = round_down(pages + MIN_WRITEBACK_PAGES,
@@ -743,7 +743,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		inode->i_state |= I_SYNC;
 		spin_unlock(&inode->i_lock);
 
-		write_chunk = writeback_chunk_size(wb->bdi, work);
+		write_chunk = writeback_chunk_size(wb, work);
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
@@ -830,7 +830,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	return nr_pages - work.nr_pages;
 }
 
-static bool over_bground_thresh(struct backing_dev_info *bdi)
+static bool over_bground_thresh(struct bdi_writeback *wb)
 {
 	unsigned long background_thresh, dirty_thresh;
 
@@ -840,8 +840,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
 	    global_page_state(NR_UNSTABLE_NFS) > background_thresh)
 		return true;
 
-	if (wb_stat(&bdi->wb, WB_RECLAIMABLE) >
-				bdi_dirty_limit(bdi, background_thresh))
+	if (wb_stat(wb, WB_RECLAIMABLE) > wb_dirty_limit(wb, background_thresh))
 		return true;
 
 	return false;
@@ -854,7 +853,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
 static void wb_update_bandwidth(struct bdi_writeback *wb,
 				unsigned long start_time)
 {
-	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time);
+	__wb_update_bandwidth(wb, 0, 0, 0, 0, 0, start_time);
 }
 
 /*
@@ -906,7 +905,7 @@ 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(wb->bdi))
+		if (work->for_background && !over_bground_thresh(wb))
 			break;
 
 		/*
@@ -998,7 +997,7 @@ static unsigned long get_nr_dirty_pages(void)
 
 static long wb_check_background_flush(struct bdi_writeback *wb)
 {
-	if (over_bground_thresh(wb->bdi)) {
+	if (over_bground_thresh(wb)) {
 
 		struct wb_writeback_work work = {
 			.nr_pages	= LONG_MAX,

fs/gfs2/super.c

@@ -748,7 +748,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH);
-	if (bdi->dirty_exceeded)
+	if (bdi->wb.dirty_exceeded)
 		gfs2_ail1_flush(sdp, wbc);
 	else
 		filemap_fdatawrite(metamapping);

include/linux/backing-dev.h

@@ -60,16 +60,6 @@ struct bdi_writeback {
 	spinlock_t list_lock;		/* protects the b_* lists */
 
 	struct percpu_counter stat[NR_WB_STAT_ITEMS];
-};
-
-struct backing_dev_info {
-	struct list_head bdi_list;
-	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
-	unsigned int capabilities; /* Device capabilities */
-	congested_fn *congested_fn; /* Function pointer if device is md/dm */
-	void *congested_data;	/* Pointer to aux data for congested func */
-
-	char *name;
 
 	unsigned long bw_time_stamp;	/* last time write bw is updated */
 	unsigned long dirtied_stamp;
@@ -88,6 +78,16 @@ struct backing_dev_info {
 
 	struct fprop_local_percpu completions;
 	int dirty_exceeded;
+};
+
+struct backing_dev_info {
+	struct list_head bdi_list;
+	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
+	unsigned int capabilities; /* Device capabilities */
+	congested_fn *congested_fn; /* Function pointer if device is md/dm */
+	void *congested_data;	/* Pointer to aux data for congested func */
+
+	char *name;
 
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;

include/linux/writeback.h

@@ -155,16 +155,15 @@ int dirty_writeback_centisecs_handler(struct ctl_table *, int,
 				      void __user *, size_t *, loff_t *);
 
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
-unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
-			       unsigned long dirty);
+unsigned long wb_dirty_limit(struct bdi_writeback *wb, unsigned long dirty);
 
-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,
-			    unsigned long start_time);
+void __wb_update_bandwidth(struct bdi_writeback *wb,
+			   unsigned long thresh,
+			   unsigned long bg_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(struct address_space *mapping);

include/trace/events/writeback.h

@@ -400,13 +400,13 @@ TRACE_EVENT(bdi_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->write_bw	= KBps(bdi->wb.write_bandwidth);
+		__entry->avg_write_bw	= KBps(bdi->wb.avg_write_bandwidth);
 		__entry->dirty_rate	= KBps(dirty_rate);
-		__entry->dirty_ratelimit = KBps(bdi->dirty_ratelimit);
+		__entry->dirty_ratelimit = KBps(bdi->wb.dirty_ratelimit);
 		__entry->task_ratelimit	= KBps(task_ratelimit);
 		__entry->balanced_dirty_ratelimit =
-					  KBps(bdi->balanced_dirty_ratelimit);
+					KBps(bdi->wb.balanced_dirty_ratelimit);
 	),
 
 	TP_printk("bdi %s: "

mm/backing-dev.c

@@ -66,7 +66,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
-	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
+	bdi_thresh = wb_dirty_limit(wb, dirty_thresh);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
@@ -91,7 +91,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   K(background_thresh),
 		   (unsigned long) K(wb_stat(wb, WB_DIRTIED)),
 		   (unsigned long) K(wb_stat(wb, WB_WRITTEN)),
-		   (unsigned long) K(bdi->write_bandwidth),
+		   (unsigned long) K(wb->write_bandwidth),
 		   nr_dirty,
 		   nr_io,
 		   nr_more_io,
@@ -376,6 +376,11 @@ void bdi_unregister(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_unregister);
 
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+
 static int bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -391,11 +396,22 @@ static int bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	spin_lock_init(&wb->list_lock);
 	INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
 
+	wb->bw_time_stamp = jiffies;
+	wb->balanced_dirty_ratelimit = INIT_BW;
+	wb->dirty_ratelimit = INIT_BW;
+	wb->write_bandwidth = INIT_BW;
+	wb->avg_write_bandwidth = INIT_BW;
+
+	err = fprop_local_init_percpu(&wb->completions, GFP_KERNEL);
+	if (err)
+		return err;
+
 	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&wb->stat[i], 0, GFP_KERNEL);
 		if (err) {
 			while (--i)
 				percpu_counter_destroy(&wb->stat[i]);
+			fprop_local_destroy_percpu(&wb->completions);
 			return err;
 		}
 	}
@@ -411,12 +427,9 @@ static void bdi_wb_exit(struct bdi_writeback *wb)
 
 	for (i = 0; i < NR_WB_STAT_ITEMS; i++)
 		percpu_counter_destroy(&wb->stat[i]);
-}
 
-/*
- * Initial write bandwidth: 100 MB/s
- */
-#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+	fprop_local_destroy_percpu(&wb->completions);
+}
 
 int bdi_init(struct backing_dev_info *bdi)
 {
@@ -435,22 +448,6 @@ int bdi_init(struct backing_dev_info *bdi)
 	if (err)
 		return err;
 
-	bdi->dirty_exceeded = 0;
-
-	bdi->bw_time_stamp = jiffies;
-	bdi->written_stamp = 0;
-
-	bdi->balanced_dirty_ratelimit = INIT_BW;
-	bdi->dirty_ratelimit = INIT_BW;
-	bdi->write_bandwidth = INIT_BW;
-	bdi->avg_write_bandwidth = INIT_BW;
-
-	err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL);
-	if (err) {
-		bdi_wb_exit(&bdi->wb);
-		return err;
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL(bdi_init);
@@ -468,8 +465,6 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	}
 
 	bdi_wb_exit(&bdi->wb);
-
-	fprop_local_destroy_percpu(&bdi->completions);
 }
 EXPORT_SYMBOL(bdi_destroy);