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 <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

2 files changed, 64 insertions, 51 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index b23cf0e..7b1d191 100644
--- a/mm/backing-dev.c
+++ b/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;
 
@@ -427,25 +446,20 @@ 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);
@@ -453,8 +467,8 @@ void bdi_destroy(struct backing_dev_info *bdi)
 		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);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bdeecad..dc673a0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -396,11 +396,11 @@ static unsigned long wp_next_time(unsigned long cur_time)
  * Increment the BDI's writeout completion count and the global writeout
  * completion count. Called from test_clear_page_writeback().
  */
-static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
+static inline void __wb_writeout_inc(struct bdi_writeback *wb)
 {
-	__inc_bdi_stat(bdi, BDI_WRITTEN);
-	__fprop_inc_percpu_max(&writeout_completions, &bdi->completions,
-			       bdi->max_prop_frac);
+	__inc_wb_stat(wb, WB_WRITTEN);
+	__fprop_inc_percpu_max(&writeout_completions, &wb->bdi->completions,
+			       wb->bdi->max_prop_frac);
 	/* First event after period switching was turned off? */
 	if (!unlikely(writeout_period_time)) {
 		/*
@@ -414,15 +414,15 @@ static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
 	}
 }
 
-void bdi_writeout_inc(struct backing_dev_info *bdi)
+void wb_writeout_inc(struct bdi_writeback *wb)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__bdi_writeout_inc(bdi);
+	__wb_writeout_inc(wb);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(bdi_writeout_inc);
+EXPORT_SYMBOL_GPL(wb_writeout_inc);
 
 /*
  * Obtain an accurate fraction of the BDI's portion.
@@ -1130,8 +1130,8 @@ void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 	if (elapsed < BANDWIDTH_INTERVAL)
 		return;
 
-	dirtied = percpu_counter_read(&bdi->bdi_stat[BDI_DIRTIED]);
-	written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]);
+	dirtied = percpu_counter_read(&bdi->wb.stat[WB_DIRTIED]);
+	written = percpu_counter_read(&bdi->wb.stat[WB_WRITTEN]);
 
 	/*
 	 * Skip quiet periods when disk bandwidth is under-utilized.
@@ -1288,7 +1288,8 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
 				    unsigned long *bdi_thresh,
 				    unsigned long *bdi_bg_thresh)
 {
-	unsigned long bdi_reclaimable;
+	struct bdi_writeback *wb = &bdi->wb;
+	unsigned long wb_reclaimable;
 
 	/*
 	 * bdi_thresh is not treated as some limiting factor as
@@ -1320,14 +1321,12 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
 	 * actually dirty; with m+n sitting in the percpu
 	 * deltas.
 	 */
-	if (*bdi_thresh < 2 * bdi_stat_error(bdi)) {
-		bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
-		*bdi_dirty = bdi_reclaimable +
-			bdi_stat_sum(bdi, BDI_WRITEBACK);
+	if (*bdi_thresh < 2 * wb_stat_error(wb)) {
+		wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
+		*bdi_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK);
 	} else {
-		bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
-		*bdi_dirty = bdi_reclaimable +
-			bdi_stat(bdi, BDI_WRITEBACK);
+		wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE);
+		*bdi_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK);
 	}
 }
 
@@ -1514,9 +1513,9 @@ pause:
 		 * In theory 1 page is enough to keep the comsumer-producer
 		 * pipe going: the flusher cleans 1 page => the task dirties 1
 		 * more page. However bdi_dirty has accounting errors.  So use
-		 * the larger and more IO friendly bdi_stat_error.
+		 * the larger and more IO friendly wb_stat_error.
 		 */
-		if (bdi_dirty <= bdi_stat_error(bdi))
+		if (bdi_dirty <= wb_stat_error(&bdi->wb))
 			break;
 
 		if (fatal_signal_pending(current))
@@ -2106,8 +2105,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping,
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_DIRTIED);
-		__inc_bdi_stat(bdi, BDI_RECLAIMABLE);
-		__inc_bdi_stat(bdi, BDI_DIRTIED);
+		__inc_wb_stat(&bdi->wb, WB_RECLAIMABLE);
+		__inc_wb_stat(&bdi->wb, WB_DIRTIED);
 		task_io_account_write(PAGE_CACHE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);
@@ -2126,7 +2125,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 	if (mapping_cap_account_dirty(mapping)) {
 		mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 		dec_zone_page_state(page, NR_FILE_DIRTY);
-		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE);
+		dec_wb_stat(&inode_to_bdi(mapping->host)->wb, WB_RECLAIMABLE);
 		task_io_account_cancelled_write(PAGE_CACHE_SIZE);
 	}
 }
@@ -2190,7 +2189,7 @@ void account_page_redirty(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		current->nr_dirtied--;
 		dec_zone_page_state(page, NR_DIRTIED);
-		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED);
+		dec_wb_stat(&inode_to_bdi(mapping->host)->wb, WB_DIRTIED);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2369,8 +2368,8 @@ int clear_page_dirty_for_io(struct page *page)
 		if (TestClearPageDirty(page)) {
 			mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-			dec_bdi_stat(inode_to_bdi(mapping->host),
-					BDI_RECLAIMABLE);
+			dec_wb_stat(&inode_to_bdi(mapping->host)->wb,
+				    WB_RECLAIMABLE);
 			ret = 1;
 		}
 		mem_cgroup_end_page_stat(memcg);
@@ -2398,8 +2397,8 @@ int test_clear_page_writeback(struct page *page)
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi)) {
-				__dec_bdi_stat(bdi, BDI_WRITEBACK);
-				__bdi_writeout_inc(bdi);
+				__dec_wb_stat(&bdi->wb, WB_WRITEBACK);
+				__wb_writeout_inc(&bdi->wb);
 			}
 		}
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
@@ -2433,7 +2432,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi))
-				__inc_bdi_stat(bdi, BDI_WRITEBACK);
+				__inc_wb_stat(&bdi->wb, WB_WRITEBACK);
 		}
 		if (!PageDirty(page))
 			radix_tree_tag_clear(&mapping->page_tree,