writeback: move backing_dev_info->bdi_stat[] 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 bdi->bdi_stat[] into wb.

* enum bdi_stat_item is renamed to wb_stat_item and the prefix of all
  enums is changed from BDI_ to WB_.

* BDI_STAT_BATCH() -> WB_STAT_BATCH()

* [__]{add|inc|dec|sum}_wb_stat(bdi, ...) -> [__]{add|inc}_wb_stat(wb, ...)

* bdi_stat[_error]() -> wb_stat[_error]()

* bdi_writeout_inc() -> wb_writeout_inc()

* stat init is moved to bdi_wb_init() and bdi_wb_exit() is added and
  frees stat.

* 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.

Signed-off-by: Tejun Heo <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Wu Fengguang <[email protected]>
Cc: Miklos Szeredi <[email protected]>
Cc: Trond Myklebust <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

fs/fs-writeback.c

@@ -840,7 +840,7 @@ static bool over_bground_thresh(struct backing_dev_info *bdi)
 	    global_page_state(NR_UNSTABLE_NFS) > background_thresh)
 		return true;
 
-	if (bdi_stat(bdi, BDI_RECLAIMABLE) >
+	if (wb_stat(&bdi->wb, WB_RECLAIMABLE) >
 				bdi_dirty_limit(bdi, background_thresh))
 		return true;
 

fs/fuse/file.c

@@ -1445,9 +1445,9 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 
 	list_del(&req->writepages_entry);
 	for (i = 0; i < req->num_pages; i++) {
-		dec_bdi_stat(bdi, BDI_WRITEBACK);
+		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP);
-		bdi_writeout_inc(bdi);
+		wb_writeout_inc(&bdi->wb);
 	}
 	wake_up(&fi->page_waitq);
 }
@@ -1634,7 +1634,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->end = fuse_writepage_end;
 	req->inode = inode;
 
-	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
@@ -1749,9 +1749,9 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 		copy_highpage(old_req->pages[0], page);
 		spin_unlock(&fc->lock);
 
-		dec_bdi_stat(bdi, BDI_WRITEBACK);
+		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_zone_page_state(page, NR_WRITEBACK_TEMP);
-		bdi_writeout_inc(bdi);
+		wb_writeout_inc(&bdi->wb);
 		fuse_writepage_free(fc, new_req);
 		fuse_request_free(new_req);
 		goto out;
@@ -1848,7 +1848,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].offset = 0;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
-	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;

fs/nfs/internal.h

@@ -607,7 +607,7 @@ void nfs_mark_page_unstable(struct page *page)
 	struct inode *inode = page_file_mapping(page)->host;
 
 	inc_zone_page_state(page, NR_UNSTABLE_NFS);
-	inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE);
+	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
 	 __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 }
 

fs/nfs/write.c

@@ -853,7 +853,8 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
+	dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
+		    WB_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */

include/linux/backing-dev.h

@@ -36,15 +36,15 @@ enum wb_state {
 
 typedef int (congested_fn)(void *, int);
 
-enum bdi_stat_item {
-	BDI_RECLAIMABLE,
-	BDI_WRITEBACK,
-	BDI_DIRTIED,
-	BDI_WRITTEN,
-	NR_BDI_STAT_ITEMS
+enum wb_stat_item {
+	WB_RECLAIMABLE,
+	WB_WRITEBACK,
+	WB_DIRTIED,
+	WB_WRITTEN,
+	NR_WB_STAT_ITEMS
 };
 
-#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
+#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
 struct bdi_writeback {
 	struct backing_dev_info *bdi;	/* our parent bdi */
@@ -58,6 +58,8 @@ struct bdi_writeback {
 	struct list_head b_more_io;	/* parked for more writeback */
 	struct list_head b_dirty_time;	/* time stamps are dirty */
 	spinlock_t list_lock;		/* protects the b_* lists */
+
+	struct percpu_counter stat[NR_WB_STAT_ITEMS];
 };
 
 struct backing_dev_info {
@@ -69,8 +71,6 @@ struct backing_dev_info {
 
 	char *name;
 
-	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 */
@@ -137,78 +137,74 @@ static inline int wb_has_dirty_io(struct bdi_writeback *wb)
 	       !list_empty(&wb->b_more_io);
 }
 
-static inline void __add_bdi_stat(struct backing_dev_info *bdi,
-		enum bdi_stat_item item, s64 amount)
+static inline void __add_wb_stat(struct bdi_writeback *wb,
+				 enum wb_stat_item item, s64 amount)
 {
-	__percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH);
+	__percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH);
 }
 
-static inline void __inc_bdi_stat(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline void __inc_wb_stat(struct bdi_writeback *wb,
+				 enum wb_stat_item item)
 {
-	__add_bdi_stat(bdi, item, 1);
+	__add_wb_stat(wb, item, 1);
 }
 
-static inline void inc_bdi_stat(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__inc_bdi_stat(bdi, item);
+	__inc_wb_stat(wb, item);
 	local_irq_restore(flags);
 }
 
-static inline void __dec_bdi_stat(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline void __dec_wb_stat(struct bdi_writeback *wb,
+				 enum wb_stat_item item)
 {
-	__add_bdi_stat(bdi, item, -1);
+	__add_wb_stat(wb, item, -1);
 }
 
-static inline void dec_bdi_stat(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__dec_bdi_stat(bdi, item);
+	__dec_wb_stat(wb, item);
 	local_irq_restore(flags);
 }
 
-static inline s64 bdi_stat(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	return percpu_counter_read_positive(&bdi->bdi_stat[item]);
+	return percpu_counter_read_positive(&wb->stat[item]);
 }
 
-static inline s64 __bdi_stat_sum(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline s64 __wb_stat_sum(struct bdi_writeback *wb,
+				enum wb_stat_item item)
 {
-	return percpu_counter_sum_positive(&bdi->bdi_stat[item]);
+	return percpu_counter_sum_positive(&wb->stat[item]);
 }
 
-static inline s64 bdi_stat_sum(struct backing_dev_info *bdi,
-		enum bdi_stat_item item)
+static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item)
 {
 	s64 sum;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	sum = __bdi_stat_sum(bdi, item);
+	sum = __wb_stat_sum(wb, item);
 	local_irq_restore(flags);
 
 	return sum;
 }
 
-extern void bdi_writeout_inc(struct backing_dev_info *bdi);
+extern void wb_writeout_inc(struct bdi_writeback *wb);
 
 /*
  * maximal error of a stat counter.
  */
-static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi)
+static inline unsigned long wb_stat_error(struct bdi_writeback *wb)
 {
 #ifdef CONFIG_SMP
-	return nr_cpu_ids * BDI_STAT_BATCH;
+	return nr_cpu_ids * WB_STAT_BATCH;
 #else
 	return 1;
 #endif

mm/backing-dev.c

@@ -84,13 +84,13 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "b_dirty_time:       %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)),
+		   (unsigned long) K(wb_stat(wb, WB_WRITEBACK)),
+		   (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)),
 		   K(bdi_thresh),
 		   K(dirty_thresh),
 		   K(background_thresh),
-		   (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),
-		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+		   (unsigned long) K(wb_stat(wb, WB_DIRTIED)),
+		   (unsigned long) K(wb_stat(wb, WB_WRITTEN)),
 		   (unsigned long) K(bdi->write_bandwidth),
 		   nr_dirty,
 		   nr_io,
@@ -376,8 +376,10 @@ void bdi_unregister(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_unregister);
 
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+static int bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 {
+	int i, err;
+
 	memset(wb, 0, sizeof(*wb));
 
 	wb->bdi = bdi;
@@ -388,6 +390,27 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&wb->b_dirty_time);
 	spin_lock_init(&wb->list_lock);
 	INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
+
+	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]);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void bdi_wb_exit(struct bdi_writeback *wb)
+{
+	int i;
+
+	WARN_ON(delayed_work_pending(&wb->dwork));
+
+	for (i = 0; i < NR_WB_STAT_ITEMS; i++)
+		percpu_counter_destroy(&wb->stat[i]);
 }
 
 /*
@@ -397,7 +420,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 
 int bdi_init(struct backing_dev_info *bdi)
 {
-	int i, err;
+	int err;
 
 	bdi->dev = NULL;
 
@@ -408,13 +431,9 @@ int bdi_init(struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->work_list);
 
-	bdi_wb_init(&bdi->wb, bdi);
-
-	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
-		err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL);
-		if (err)
-			goto err;
-	}
+	err = bdi_wb_init(&bdi->wb, bdi);
+	if (err)
+		return err;
 
 	bdi->dirty_exceeded = 0;
 
@@ -427,34 +446,29 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->avg_write_bandwidth = INIT_BW;
 
 	err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL);
-
 	if (err) {
-err:
-		while (i--)
-			percpu_counter_destroy(&bdi->bdi_stat[i]);
+		bdi_wb_exit(&bdi->wb);
+		return err;
 	}
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL(bdi_init);
 
 void bdi_destroy(struct backing_dev_info *bdi)
 {
-	int i;
-
 	bdi_wb_shutdown(bdi);
 
 	WARN_ON(!list_empty(&bdi->work_list));
-	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 
 	if (bdi->dev) {
 		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
 	}
 
-	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
-		percpu_counter_destroy(&bdi->bdi_stat[i]);
+	bdi_wb_exit(&bdi->wb);
+
 	fprop_local_destroy_percpu(&bdi->completions);
 }
 EXPORT_SYMBOL(bdi_destroy);