writeback: cgroup writeback support

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->state into wb.

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

* Explicit zeroing of bdi->state is removed without adding zeoring of wb->state as the whole data structure is zeroed on init anyway.

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

Signed-off-by Tejun Heo <[email protected]>

Cc Jens Axboe <[email protected]>

Cc Jan Kara <[email protected]>

Cc Wu Fengguang <[email protected]>

Cc [email protected]

Cc Neil Brown <[email protected]>

Cc Alasdair Kergon <[email protected]>

Cc Mike Snitzer <[email protected]>

---
 block/blk-core.c               |  1 -
 drivers/block/drbd/drbd_main.c | 10 +++++-----
 drivers/md/dm.c                |  2 +-
 drivers/md/raid1.c             |  4 ++--
 drivers/md/raid10.c            |  2 +-
 fs/fs-writeback.c              | 14 +++++++-------
 include/linux/backing-dev.h    | 24 ++++++++++++------------
 mm/backing-dev.c               | 20 ++++++++++----------
 8 files changed, 38 insertions(+), 39 deletions(-)

block/blk-core.c +0 -1

index 56da125..fa1314e 100644
@@ -606,7 +606,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
-	q->backing_dev_info.state = 0;
 	q->backing_dev_info.capabilities = 0;
 	q->backing_dev_info.name = "block";
 	q->node = node_id;

drivers/block/drbd/drbd_main.c +5 -5

index 1fc8342..61b00aa 100644
@@ -2360,7 +2360,7 @@ static void drbd_cleanup(void)
  * @congested_data:	User data
  * @bdi_bits:		Bits the BDI flusher thread is currently interested in
  *
- * Returns 1<<BDI_async_congested and/or 1<<BDI_sync_congested if we are congested.
+ * Returns 1<<WB_async_congested and/or 1<<WB_sync_congested if we are congested.
  */
 static int drbd_congested(void *congested_data, int bdi_bits)
 {

@@ -2377,14 +2377,14 @@ static int drbd_congested(void *congested_data, int bdi_bits)
 	}
 
 	if (test_bit(CALLBACK_PENDING, &first_peer_device(device)->connection->flags)) {
-		r |= (1 << BDI_async_congested);
+		r |= (1 << WB_async_congested);
 		/* Without good local data, we would need to read from remote,
 		 * and that would need the worker thread as well, which is
 		 * currently blocked waiting for that usermode helper to
 		 * finish.
 		 */
 		if (!get_ldev_if_state(device, D_UP_TO_DATE))
-			r |= (1 << BDI_sync_congested);
+			r |= (1 << WB_sync_congested);
 		else
 			put_ldev(device);
 		r &= bdi_bits;

@@ -2400,9 +2400,9 @@ static int drbd_congested(void *congested_data, int bdi_bits)
 			reason = 'b';
 	}
 
-	if (bdi_bits & (1 << BDI_async_congested) &&
+	if (bdi_bits & (1 << WB_async_congested) &&
 	    test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) {
-		r |= (1 << BDI_async_congested);
+		r |= (1 << WB_async_congested);
 		reason = reason == 'b' ? 'a' : 'n';
 	}
 

drivers/md/dm.c +1 -1

index 73f2880..c076982 100644
@@ -2039,7 +2039,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 			 * the query about congestion status of request_queue
 			 */
 			if (dm_request_based(md))
-				r = md->queue->backing_dev_info.state &
+				r = md->queue->backing_dev_info.wb.state &
 				    bdi_bits;
 			else
 				r = dm_table_any_congested(map, bdi_bits);

drivers/md/raid1.c +2 -2

index d34e238..2fca392 100644
@@ -739,7 +739,7 @@ static int raid1_congested(struct mddev *mddev, int bits)
 	struct r1conf *conf = mddev->private;
 	int i, ret = 0;
 
-	if ((bits & (1 << BDI_async_congested)) &&
+	if ((bits & (1 << WB_async_congested)) &&
 	    conf->pending_count >= max_queued_requests)
 		return 1;
 

@@ -754,7 +754,7 @@ static int raid1_congested(struct mddev *mddev, int bits)
 			/* Note the '|| 1' - when read_balance prefers
 			 * non-congested targets, it can be removed
 			 */
-			if ((bits & (1<<BDI_async_congested)) || 1)
+			if ((bits & (1 << WB_async_congested)) || 1)
 				ret |= bdi_congested(&q->backing_dev_info, bits);
 			else
 				ret &= bdi_congested(&q->backing_dev_info, bits);

drivers/md/raid10.c +1 -1

index a7196c4..8d38857 100644
@@ -914,7 +914,7 @@ static int raid10_congested(struct mddev *mddev, int bits)
 	struct r10conf *conf = mddev->private;
 	int i, ret = 0;
 
-	if ((bits & (1 << BDI_async_congested)) &&
+	if ((bits & (1 << WB_async_congested)) &&
 	    conf->pending_count >= max_queued_requests)
 		return 1;
 

fs/fs-writeback.c +7 -7

index e907052..fea13fe 100644
@@ -62,7 +62,7 @@ struct wb_writeback_work {
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
-	return test_bit(BDI_writeback_running, &bdi->state);
+	return test_bit(WB_writeback_running, &bdi->wb.state);
 }
 EXPORT_SYMBOL(writeback_in_progress);
 

@@ -100,7 +100,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
 static void bdi_wakeup_thread(struct backing_dev_info *bdi)
 {
 	spin_lock_bh(&bdi->wb_lock);
-	if (test_bit(BDI_registered, &bdi->state))
+	if (test_bit(WB_registered, &bdi->wb.state))
 		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 	spin_unlock_bh(&bdi->wb_lock);
 }

@@ -111,7 +111,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
-	if (!test_bit(BDI_registered, &bdi->state)) {
+	if (!test_bit(WB_registered, &bdi->wb.state)) {
 		if (work->done)
 			complete(work->done);
 		goto out_unlock;

@@ -1039,7 +1039,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
-	set_bit(BDI_writeback_running, &wb->bdi->state);
+	set_bit(WB_writeback_running, &wb->state);
 	while ((work = get_next_work_item(bdi)) != NULL) {
 
 		trace_writeback_exec(bdi, work);

@@ -1061,7 +1061,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	 */
 	wrote += wb_check_old_data_flush(wb);
 	wrote += wb_check_background_flush(wb);
-	clear_bit(BDI_writeback_running, &wb->bdi->state);
+	clear_bit(WB_writeback_running, &wb->state);
 
 	return wrote;
 }

@@ -1081,7 +1081,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   !test_bit(BDI_registered, &bdi->state))) {
+		   !test_bit(WB_registered, &wb->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken

@@ -1255,7 +1255,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			spin_unlock(&inode->i_lock);
 			spin_lock(&bdi->wb.list_lock);
 			if (bdi_cap_writeback_dirty(bdi)) {
-				WARN(!test_bit(BDI_registered, &bdi->state),
+				WARN(!test_bit(WB_registered, &bdi->wb.state),
 				     "bdi-%s not registered\n", bdi->name);
 
 				/*

include/linux/backing-dev.h +12 -12

index aff923a..eb14f98 100644
@@ -25,13 +25,13 @@ struct device;
 struct dentry;
 
 /*
- * Bits in backing_dev_info.state
+ * Bits in bdi_writeback.state
  */
-enum bdi_state {
-	BDI_async_congested,	/* The async (write) queue is getting full */
-	BDI_sync_congested,	/* The sync queue is getting full */
-	BDI_registered,		/* bdi_register() was done */
-	BDI_writeback_running,	/* Writeback is in progress */
+enum wb_state {
+	WB_async_congested,	/* The async (write) queue is getting full */
+	WB_sync_congested,	/* The sync queue is getting full */
+	WB_registered,		/* bdi_register() was done */
+	WB_writeback_running,	/* Writeback is in progress */
 };
 
 typedef int (congested_fn)(void *, int);

@@ -49,6 +49,7 @@ enum bdi_stat_item {
 struct bdi_writeback {
 	struct backing_dev_info *bdi;	/* our parent bdi */
 
+	unsigned long state;		/* Always use atomic bitops on this */
 	unsigned long last_old_flush;	/* last old data flush */
 
 	struct delayed_work dwork;	/* work item used for writeback */

@@ -62,7 +63,6 @@ struct bdi_writeback {
 struct backing_dev_info {
 	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
-	unsigned long state;	/* Always use atomic bitops on this */
 	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 */

@@ -250,23 +250,23 @@ static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 {
 	if (bdi->congested_fn)
 		return bdi->congested_fn(bdi->congested_data, bdi_bits);
-	return (bdi->state & bdi_bits);
+	return (bdi->wb.state & bdi_bits);
 }
 
 static inline int bdi_read_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_sync_congested);
+	return bdi_congested(bdi, 1 << WB_sync_congested);
 }
 
 static inline int bdi_write_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_async_congested);
+	return bdi_congested(bdi, 1 << WB_async_congested);
 }
 
 static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, (1 << BDI_sync_congested) |
-				  (1 << BDI_async_congested));
+	return bdi_congested(bdi, (1 << WB_sync_congested) |
+				  (1 << WB_async_congested));
 }
 
 enum {

mm/backing-dev.c +10 -10

index 6dc4580..b23cf0e 100644
@@ -96,7 +96,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   nr_io,
 		   nr_more_io,
 		   nr_dirty_time,
-		   !list_empty(&bdi->bdi_list), bdi->state);
+		   !list_empty(&bdi->bdi_list), bdi->wb.state);
 #undef K
 
 	return 0;

@@ -280,7 +280,7 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
 	spin_lock_bh(&bdi->wb_lock);
-	if (test_bit(BDI_registered, &bdi->state))
+	if (test_bit(WB_registered, &bdi->wb.state))
 		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
 	spin_unlock_bh(&bdi->wb_lock);
 }

@@ -315,7 +315,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 	bdi->dev = dev;
 
 	bdi_debug_register(bdi, dev_name(dev));
-	set_bit(BDI_registered, &bdi->state);
+	set_bit(WB_registered, &bdi->wb.state);
 
 	spin_lock_bh(&bdi_lock);
 	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);

@@ -339,7 +339,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
 	/* Make sure nobody queues further work */
 	spin_lock_bh(&bdi->wb_lock);
-	if (!test_and_clear_bit(BDI_registered, &bdi->state)) {
+	if (!test_and_clear_bit(WB_registered, &bdi->wb.state)) {
 		spin_unlock_bh(&bdi->wb_lock);
 		return;
 	}

@@ -492,11 +492,11 @@ static atomic_t nr_bdi_congested[2];
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
-	enum bdi_state bit;
+	enum wb_state bit;
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
-	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	if (test_and_clear_bit(bit, &bdi->state))
+	bit = sync ? WB_sync_congested : WB_async_congested;
+	if (test_and_clear_bit(bit, &bdi->wb.state))
 		atomic_dec(&nr_bdi_congested[sync]);
 	smp_mb__after_atomic();
 	if (waitqueue_active(wqh))

@@ -506,10 +506,10 @@ EXPORT_SYMBOL(clear_bdi_congested);
 
 void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
-	enum bdi_state bit;
+	enum wb_state bit;
 
-	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	if (!test_and_set_bit(bit, &bdi->state))
+	bit = sync ? WB_sync_congested : WB_async_congested;
+	if (!test_and_set_bit(bit, &bdi->wb.state))
 		atomic_inc(&nr_bdi_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);

Signature · 1 line

2.1.0

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]>

Cc Jens Axboe <[email protected]>

Cc Jan Kara <[email protected]>

Cc Wu Fengguang <[email protected]>

Cc Miklos Szeredi <[email protected]>

Cc Trond Myklebust <[email protected]>

---
 fs/fs-writeback.c           |  2 +-
 fs/fuse/file.c              | 12 ++++----
 fs/nfs/internal.h           |  2 +-
 fs/nfs/write.c              |  3 +-
 include/linux/backing-dev.h | 68 +++++++++++++++++++++------------------------
 mm/backing-dev.c            | 60 ++++++++++++++++++++++++---------------
 mm/filemap.c                |  2 +-
 mm/page-writeback.c         | 53 +++++++++++++++++------------------
 mm/truncate.c               |  4 +--
 9 files changed, 108 insertions(+), 98 deletions(-)

fs/fs-writeback.c +1 -1

index fea13fe..992a065 100644
@@ -822,7 +822,7 @@ 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 +6 -6

index c01ec3b..997c88a 100644
@@ -1469,9 +1469,9 @@ 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);
 }

@@ -1658,7 +1658,7 @@ 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);

@@ -1773,9 +1773,9 @@ 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;

@@ -1872,7 +1872,7 @@ 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 +1 -1

index 9e6475b..7e3c460 100644
@@ -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 +2 -1

index 849ed78..8bbeafe 100644
@@ -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 +32 -36

index eb14f98..fe7a907 100644
@@ -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 +37 -23

index b23cf0e..7b1d191 100644
@@ -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);

mm/filemap.c +1 -1

index 21cebb6..a2b098b 100644
@@ -215,7 +215,7 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 	if (PageDirty(page) && 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);
 	}
 }
 

mm/page-writeback.c +26 -27

index 9b6277a..af3edb6 100644
@@ -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);

@@ -2174,7 +2173,7 @@ 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);

@@ -2320,8 +2319,8 @@ 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);

@@ -2349,8 +2348,8 @@ 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);

@@ -2384,7 +2383,7 @@ 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,

mm/truncate.c +2 -2

index 059cac7..df16f8c 100644
@@ -116,8 +116,8 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
 		if (mapping && 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);
 			if (account_size)
 				task_io_account_cancelled_write(account_size);
 		}

Signature · 1 line

2.1.0

Maybe bdi_wb_destroy() would be somewhat more descriptive than
bdi_wb_exit()? Otherwise the patch looks good to me. You can add:

Reviewed-by Jan Kara <[email protected]>

Quoted 3 lines · Jan Kara

Maybe bdi_wb_destroy() would be somewhat more descriptive than
bdi_wb_exit()? Otherwise the patch looks good to me. You can add:

Reviewed-by Jan Kara <[email protected]>

Hmmm... maybe, I don't know. I feel weird matching up destroy with init instead of create. Why is exit weird?

I can easily understand what "initializing writeback structure" means but
"exiting writeback structure" doesn't really make sense to me. OTOH "destroying writeback structure" does make sense to me. That's the only reason.

Quoted 4 lines · Jan Kara

I can easily understand what "initializing writeback structure" means but
"exiting writeback structure" doesn't really make sense to me. OTOH "destroying writeback structure" does make sense to me. That's the only reason.

We have enough cases where "exit" is used that way starting with module_exit() and all the accompanying __exit annotations and there are quite a few others. I think it's enough to establish "exit" as the counterpart of "init" but I do agree that it felt a bit alien to me at the beginning too.

In general, I've been sticking with create/destroy if the object itself is being created or destroyed and init/exit if the object itself stays put across init/exit which is the case here. This isn't quite universal but I think there exists enough of a pattern to make it worthwhile to stick to it. As such, I'd like to stick to the current names if it isn't a big deal.

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_bgroup_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.

Signed-off-by Tejun Heo <[email protected]>

Cc Jens Axboe <[email protected]>

Cc Jan Kara <[email protected]>

Cc Wu Fengguang <[email protected]>

Cc Jaegeuk Kim <[email protected]>

Cc Steven Whitehouse <[email protected]>

---
 fs/f2fs/node.c                   |   4 +-
 fs/f2fs/segment.h                |   2 +-
 fs/fs-writeback.c                |  17 ++-
 fs/gfs2/super.c                  |   2 +-
 include/linux/backing-dev.h      |  20 +--
 include/linux/writeback.h        |  19 ++-
 include/trace/events/writeback.h |   8 +-
 mm/backing-dev.c                 |  45 +++----
 mm/page-writeback.c              | 262 ++++++++++++++++++++-------------------
 9 files changed, 187 insertions(+), 192 deletions(-)

fs/f2fs/node.c +2 -2

index 97bd9d3..a97da4e 100644
@@ -51,7 +51,7 @@ 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);

@@ -63,7 +63,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 				sizeof(struct ino_entry)) >> 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 +1 -1

index 7fd3511..3a5bfcf 100644
@@ -712,7 +712,7 @@ 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 +8 -9

index 992a065..4fcf2385 100644
@@ -606,7 +606,7 @@ 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;

@@ -627,7 +627,7 @@ 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,

@@ -725,7 +725,7 @@ 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;
 

@@ -812,7 +812,7 @@ 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;
 

@@ -822,8 +822,7 @@ 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;

@@ -836,7 +835,7 @@ 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);
 }
 
 /*

@@ -888,7 +887,7 @@ 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;
 
 		/*

@@ -980,7 +979,7 @@ 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 +1 -1

index 1666382..5b4c4d35 100644
@@ -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 +10 -10

index fe7a907..2ab0604 100644
@@ -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 +9 -10

index 0004833..8e4485f 100644
@@ -152,16 +152,15 @@ 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);
-
-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);
+unsigned long wb_dirty_limit(struct bdi_writeback *wb, unsigned long dirty);
+
+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 +4 -4

index 5a14ead..5c9a68c 100644
@@ -383,13 +383,13 @@ 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 +20 -25

index 7b1d191..9a6c472 100644
@@ -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);
 

mm/page-writeback.c +132 -130

index af3edb6..29fb4f3 100644
@@ -399,7 +399,7 @@ static unsigned long wp_next_time(unsigned long cur_time)
 static inline void __wb_writeout_inc(struct bdi_writeback *wb)
 {
 	__inc_wb_stat(wb, WB_WRITTEN);
-	__fprop_inc_percpu_max(&writeout_completions, &wb->bdi->completions,
+	__fprop_inc_percpu_max(&writeout_completions, &wb->completions,
 			       wb->bdi->max_prop_frac);
 	/* First event after period switching was turned off? */
 	if (!unlikely(writeout_period_time)) {

@@ -427,10 +427,10 @@ EXPORT_SYMBOL_GPL(wb_writeout_inc);
 /*
  * Obtain an accurate fraction of the BDI's portion.
  */
-static void bdi_writeout_fraction(struct backing_dev_info *bdi,
-		long *numerator, long *denominator)
+static void wb_writeout_fraction(struct bdi_writeback *wb,
+				 long *numerator, long *denominator)
 {
-	fprop_fraction_percpu(&writeout_completions, &bdi->completions,
+	fprop_fraction_percpu(&writeout_completions, &wb->completions,
 				numerator, denominator);
 }
 

@@ -516,11 +516,11 @@ static unsigned long hard_dirty_limit(unsigned long thresh)
 }
 
 /**
- * bdi_dirty_limit - @bdi's share of dirty throttling threshold
- * @bdi: the backing_dev_info to query
+ * wb_dirty_limit - @wb's share of dirty throttling threshold
+ * @wb: bdi_writeback to query
  * @dirty: global dirty limit in pages
  *
- * Returns @bdi's dirty limit in pages. The term "dirty" in the context of
+ * Returns @wb's dirty limit in pages. The term "dirty" in the context of
  * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
  *
  * Note that balance_dirty_pages() will only seriously take it as a hard limit

@@ -528,34 +528,35 @@ static unsigned long hard_dirty_limit(unsigned long thresh)
  * control. For example, when the device is completely stalled due to some error
  * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
  * In the other normal situations, it acts more gently by throttling the tasks
- * more (rather than completely block them) when the bdi dirty pages go high.
+ * more (rather than completely block them) when the wb dirty pages go high.
  *
  * It allocates high/low dirty limits to fast/slow devices, in order to prevent
  * - starving fast devices
  * - piling up dirty pages (that will take long time to sync) on slow devices
  *
- * The bdi's share of dirty limit will be adapting to its throughput and
+ * The wb's share of dirty limit will be adapting to its throughput and
  * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
  */
-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)
 {
-	u64 bdi_dirty;
+	struct backing_dev_info *bdi = wb->bdi;
+	u64 wb_dirty;
 	long numerator, denominator;
 
 	/*
 	 * Calculate this BDI's share of the dirty ratio.
 	 */
-	bdi_writeout_fraction(bdi, &numerator, &denominator);
+	wb_writeout_fraction(wb, &numerator, &denominator);
 
-	bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
-	bdi_dirty *= numerator;
-	do_div(bdi_dirty, denominator);
+	wb_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
+	wb_dirty *= numerator;
+	do_div(wb_dirty, denominator);
 
-	bdi_dirty += (dirty * bdi->min_ratio) / 100;
-	if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
-		bdi_dirty = dirty * bdi->max_ratio / 100;
+	wb_dirty += (dirty * bdi->min_ratio) / 100;
+	if (wb_dirty > (dirty * bdi->max_ratio) / 100)
+		wb_dirty = dirty * bdi->max_ratio / 100;
 
-	return bdi_dirty;
+	return wb_dirty;
 }
 
 /*

@@ -664,14 +665,14 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *   card's bdi_dirty may rush to many times higher than bdi_setpoint.
  * - the bdi dirty thresh drops quickly due to change of JBOD workload
  */
-static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
-					unsigned long thresh,
-					unsigned long bg_thresh,
-					unsigned long dirty,
-					unsigned long bdi_thresh,
-					unsigned long bdi_dirty)
+static unsigned long wb_position_ratio(struct bdi_writeback *wb,
+				       unsigned long thresh,
+				       unsigned long bg_thresh,
+				       unsigned long dirty,
+				       unsigned long bdi_thresh,
+				       unsigned long bdi_dirty)
 {
-	unsigned long write_bw = bdi->avg_write_bandwidth;
+	unsigned long write_bw = wb->avg_write_bandwidth;
 	unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
 	unsigned long limit = hard_dirty_limit(thresh);
 	unsigned long x_intercept;

@@ -702,12 +703,12 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	 * consume arbitrary amount of RAM because it is accounted in
 	 * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty".
 	 *
-	 * Here, in bdi_position_ratio(), we calculate pos_ratio based on
+	 * Here, in wb_position_ratio(), we calculate pos_ratio based on
 	 * two values: bdi_dirty and bdi_thresh. Let's consider an example:
 	 * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global
 	 * limits are set by default to 10% and 20% (background and throttle).
 	 * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages.
-	 * bdi_dirty_limit(bdi, bg_thresh) is about ~4K pages. bdi_setpoint is
+	 * wb_dirty_limit(wb, bg_thresh) is about ~4K pages. bdi_setpoint is
 	 * about ~6K pages (as the average of background and throttle bdi
 	 * limits). The 3rd order polynomial will provide positive feedback if
 	 * bdi_dirty is under bdi_setpoint and vice versa.

@@ -717,7 +718,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	 * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB
 	 * in the example above).
 	 */
-	if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
+	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		long long bdi_pos_ratio;
 		unsigned long bdi_bg_thresh;
 

@@ -842,13 +843,13 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	return pos_ratio;
 }
 
-static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
-				       unsigned long elapsed,
-				       unsigned long written)
+static void wb_update_write_bandwidth(struct bdi_writeback *wb,
+				      unsigned long elapsed,
+				      unsigned long written)
 {
 	const unsigned long period = roundup_pow_of_two(3 * HZ);
-	unsigned long avg = bdi->avg_write_bandwidth;
-	unsigned long old = bdi->write_bandwidth;
+	unsigned long avg = wb->avg_write_bandwidth;
+	unsigned long old = wb->write_bandwidth;
 	u64 bw;
 
 	/*

@@ -861,14 +862,14 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
 	 * @written may have decreased due to account_page_redirty().
 	 * Avoid underflowing @bw calculation.
 	 */
-	bw = written - min(written, bdi->written_stamp);
+	bw = written - min(written, wb->written_stamp);
 	bw *= HZ;
 	if (unlikely(elapsed > period)) {
 		do_div(bw, elapsed);
 		avg = bw;
 		goto out;
 	}
-	bw += (u64)bdi->write_bandwidth * (period - elapsed);
+	bw += (u64)wb->write_bandwidth * (period - elapsed);
 	bw >>= ilog2(period);
 
 	/*

@@ -881,8 +882,8 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
 		avg += (old - avg) >> 3;
 
 out:
-	bdi->write_bandwidth = bw;
-	bdi->avg_write_bandwidth = avg;
+	wb->write_bandwidth = bw;
+	wb->avg_write_bandwidth = avg;
 }
 
 /*

@@ -947,20 +948,20 @@ static void global_update_bandwidth(unsigned long thresh,
  * Normal bdi tasks will be curbed at or below it in long term.
  * Obviously it should be around (write_bw / N) when there are N dd tasks.
  */
-static void bdi_update_dirty_ratelimit(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 dirtied,
-				       unsigned long elapsed)
+static void wb_update_dirty_ratelimit(struct bdi_writeback *wb,
+				      unsigned long thresh,
+				      unsigned long bg_thresh,
+				      unsigned long dirty,
+				      unsigned long bdi_thresh,
+				      unsigned long bdi_dirty,
+				      unsigned long dirtied,
+				      unsigned long elapsed)
 {
 	unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
 	unsigned long limit = hard_dirty_limit(thresh);
 	unsigned long setpoint = (freerun + limit) / 2;
-	unsigned long write_bw = bdi->avg_write_bandwidth;
-	unsigned long dirty_ratelimit = bdi->dirty_ratelimit;
+	unsigned long write_bw = wb->avg_write_bandwidth;
+	unsigned long dirty_ratelimit = wb->dirty_ratelimit;
 	unsigned long dirty_rate;
 	unsigned long task_ratelimit;
 	unsigned long balanced_dirty_ratelimit;

@@ -972,10 +973,10 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
 	 * The dirty rate will match the writeout rate in long term, except
 	 * when dirty pages are truncated by userspace or re-dirtied by FS.
 	 */
-	dirty_rate = (dirtied - bdi->dirtied_stamp) * HZ / elapsed;
+	dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed;
 
-	pos_ratio = bdi_position_ratio(bdi, thresh, bg_thresh, dirty,
-				       bdi_thresh, bdi_dirty);
+	pos_ratio = wb_position_ratio(wb, thresh, bg_thresh, dirty,
+				      bdi_thresh, bdi_dirty);
 	/*
 	 * task_ratelimit reflects each dd's dirty rate for the past 200ms.
 	 */

@@ -1059,31 +1060,31 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
 
 	/*
 	 * For strictlimit case, calculations above were based on bdi counters
-	 * and limits (starting from pos_ratio = bdi_position_ratio() and up to
+	 * and limits (starting from pos_ratio = wb_position_ratio() and up to
 	 * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
 	 * Hence, to calculate "step" properly, we have to use bdi_dirty as
 	 * "dirty" and bdi_setpoint as "setpoint".
 	 *
 	 * We rampup dirty_ratelimit forcibly if bdi_dirty is low because
 	 * it's possible that bdi_thresh is close to zero due to inactivity
-	 * of backing device (see the implementation of bdi_dirty_limit()).
+	 * of backing device (see the implementation of wb_dirty_limit()).
 	 */
-	if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
+	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		dirty = bdi_dirty;
 		if (bdi_dirty < 8)
 			setpoint = bdi_dirty + 1;
 		else
 			setpoint = (bdi_thresh +
-				    bdi_dirty_limit(bdi, bg_thresh)) / 2;
+				    wb_dirty_limit(wb, bg_thresh)) / 2;
 	}
 
 	if (dirty < setpoint) {
-		x = min3(bdi->balanced_dirty_ratelimit,
+		x = min3(wb->balanced_dirty_ratelimit,
 			 balanced_dirty_ratelimit, task_ratelimit);
 		if (dirty_ratelimit < x)
 			step = x - dirty_ratelimit;
 	} else {
-		x = max3(bdi->balanced_dirty_ratelimit,
+		x = max3(wb->balanced_dirty_ratelimit,
 			 balanced_dirty_ratelimit, task_ratelimit);
 		if (dirty_ratelimit > x)
 			step = dirty_ratelimit - x;

@@ -1105,22 +1106,22 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
 	else
 		dirty_ratelimit -= step;
 
-	bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL);
-	bdi->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
+	wb->dirty_ratelimit = max(dirty_ratelimit, 1UL);
+	wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
 
-	trace_bdi_dirty_ratelimit(bdi, dirty_rate, task_ratelimit);
+	trace_bdi_dirty_ratelimit(wb->bdi, dirty_rate, task_ratelimit);
 }
 
-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)
 {
 	unsigned long now = jiffies;
-	unsigned long elapsed = now - bdi->bw_time_stamp;
+	unsigned long elapsed = now - wb->bw_time_stamp;
 	unsigned long dirtied;
 	unsigned long written;
 

@@ -1130,44 +1131,44 @@ void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 	if (elapsed < BANDWIDTH_INTERVAL)
 		return;
 
-	dirtied = percpu_counter_read(&bdi->wb.stat[WB_DIRTIED]);
-	written = percpu_counter_read(&bdi->wb.stat[WB_WRITTEN]);
+	dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]);
+	written = percpu_counter_read(&wb->stat[WB_WRITTEN]);
 
 	/*
 	 * Skip quiet periods when disk bandwidth is under-utilized.
 	 * (at least 1s idle time between two flusher runs)
 	 */
-	if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time))
+	if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time))
 		goto snapshot;
 
 	if (thresh) {
 		global_update_bandwidth(thresh, dirty, now);
-		bdi_update_dirty_ratelimit(bdi, thresh, bg_thresh, dirty,
-					   bdi_thresh, bdi_dirty,
-					   dirtied, elapsed);
+		wb_update_dirty_ratelimit(wb, thresh, bg_thresh, dirty,
+					  bdi_thresh, bdi_dirty,
+					  dirtied, elapsed);
 	}
-	bdi_update_write_bandwidth(bdi, elapsed, written);
+	wb_update_write_bandwidth(wb, elapsed, written);
 
 snapshot:
-	bdi->dirtied_stamp = dirtied;
-	bdi->written_stamp = written;
-	bdi->bw_time_stamp = now;
+	wb->dirtied_stamp = dirtied;
+	wb->written_stamp = written;
+	wb->bw_time_stamp = now;
 }
 
-static 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)
+static 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)
 {
-	if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL))
+	if (time_is_after_eq_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL))
 		return;
-	spin_lock(&bdi->wb.list_lock);
-	__bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty,
-			       bdi_thresh, bdi_dirty, start_time);
-	spin_unlock(&bdi->wb.list_lock);
+	spin_lock(&wb->list_lock);
+	__wb_update_bandwidth(wb, thresh, bg_thresh, dirty,
+			      bdi_thresh, bdi_dirty, start_time);
+	spin_unlock(&wb->list_lock);
 }
 
 /*

@@ -1187,10 +1188,10 @@ static unsigned long dirty_poll_interval(unsigned long dirty,
 	return 1;
 }
 
-static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
-				   unsigned long bdi_dirty)
+static unsigned long wb_max_pause(struct bdi_writeback *wb,
+				      unsigned long bdi_dirty)
 {
-	unsigned long bw = bdi->avg_write_bandwidth;
+	unsigned long bw = wb->avg_write_bandwidth;
 	unsigned long t;
 
 	/*

@@ -1206,14 +1207,14 @@ static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
 	return min_t(unsigned long, t, MAX_PAUSE);
 }
 
-static long bdi_min_pause(struct backing_dev_info *bdi,
-			  long max_pause,
-			  unsigned long task_ratelimit,
-			  unsigned long dirty_ratelimit,
-			  int *nr_dirtied_pause)
+static long wb_min_pause(struct bdi_writeback *wb,
+			 long max_pause,
+			 unsigned long task_ratelimit,
+			 unsigned long dirty_ratelimit,
+			 int *nr_dirtied_pause)
 {
-	long hi = ilog2(bdi->avg_write_bandwidth);
-	long lo = ilog2(bdi->dirty_ratelimit);
+	long hi = ilog2(wb->avg_write_bandwidth);
+	long lo = ilog2(wb->dirty_ratelimit);
 	long t;		/* target pause */
 	long pause;	/* estimated next pause */
 	int pages;	/* target nr_dirtied_pause */

@@ -1281,14 +1282,13 @@ static long bdi_min_pause(struct backing_dev_info *bdi,
 	return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t;
 }
 
-static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
-				    unsigned long dirty_thresh,
-				    unsigned long background_thresh,
-				    unsigned long *bdi_dirty,
-				    unsigned long *bdi_thresh,
-				    unsigned long *bdi_bg_thresh)
+static inline void wb_dirty_limits(struct bdi_writeback *wb,
+				   unsigned long dirty_thresh,
+				   unsigned long background_thresh,
+				   unsigned long *bdi_dirty,
+				   unsigned long *bdi_thresh,
+				   unsigned long *bdi_bg_thresh)
 {
-	struct bdi_writeback *wb = &bdi->wb;
 	unsigned long wb_reclaimable;
 
 	/*

@@ -1301,10 +1301,10 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
 	 *   In this case we don't want to hard throttle the USB key
 	 *   dirtiers for 100 seconds until bdi_dirty drops under
 	 *   bdi_thresh. Instead the auxiliary bdi control line in
-	 *   bdi_position_ratio() will let the dirtier task progress
+	 *   wb_position_ratio() will let the dirtier task progress
 	 *   at some rate <= (write_bw / 2) for bringing down bdi_dirty.
 	 */
-	*bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
+	*bdi_thresh = wb_dirty_limit(wb, dirty_thresh);
 
 	if (bdi_bg_thresh)
 		*bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh *

@@ -1354,6 +1354,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 	unsigned long dirty_ratelimit;
 	unsigned long pos_ratio;
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+	struct bdi_writeback *wb = &bdi->wb;
 	bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
 	unsigned long start_time = jiffies;
 

@@ -1378,8 +1379,8 @@ static void balance_dirty_pages(struct address_space *mapping,
 		global_dirty_limits(&background_thresh, &dirty_thresh);
 
 		if (unlikely(strictlimit)) {
-			bdi_dirty_limits(bdi, dirty_thresh, background_thresh,
-					 &bdi_dirty, &bdi_thresh, &bg_thresh);
+			wb_dirty_limits(wb, dirty_thresh, background_thresh,
+					&bdi_dirty, &bdi_thresh, &bg_thresh);
 
 			dirty = bdi_dirty;
 			thresh = bdi_thresh;

@@ -1410,28 +1411,28 @@ static void balance_dirty_pages(struct address_space *mapping,
 			bdi_start_background_writeback(bdi);
 
 		if (!strictlimit)
-			bdi_dirty_limits(bdi, dirty_thresh, background_thresh,
-					 &bdi_dirty, &bdi_thresh, NULL);
+			wb_dirty_limits(wb, dirty_thresh, background_thresh,
+					&bdi_dirty, &bdi_thresh, NULL);
 
 		dirty_exceeded = (bdi_dirty > bdi_thresh) &&
 				 ((nr_dirty > dirty_thresh) || strictlimit);
-		if (dirty_exceeded && !bdi->dirty_exceeded)
-			bdi->dirty_exceeded = 1;
+		if (dirty_exceeded && !wb->dirty_exceeded)
+			wb->dirty_exceeded = 1;
 
-		bdi_update_bandwidth(bdi, dirty_thresh, background_thresh,
-				     nr_dirty, bdi_thresh, bdi_dirty,
-				     start_time);
+		wb_update_bandwidth(wb, dirty_thresh, background_thresh,
+				    nr_dirty, bdi_thresh, bdi_dirty,
+				    start_time);
 
-		dirty_ratelimit = bdi->dirty_ratelimit;
-		pos_ratio = bdi_position_ratio(bdi, dirty_thresh,
-					       background_thresh, nr_dirty,
-					       bdi_thresh, bdi_dirty);
+		dirty_ratelimit = wb->dirty_ratelimit;
+		pos_ratio = wb_position_ratio(wb, dirty_thresh,
+					      background_thresh, nr_dirty,
+					      bdi_thresh, bdi_dirty);
 		task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >>
 							RATELIMIT_CALC_SHIFT;
-		max_pause = bdi_max_pause(bdi, bdi_dirty);
-		min_pause = bdi_min_pause(bdi, max_pause,
-					  task_ratelimit, dirty_ratelimit,
-					  &nr_dirtied_pause);
+		max_pause = wb_max_pause(wb, bdi_dirty);
+		min_pause = wb_min_pause(wb, max_pause,
+					 task_ratelimit, dirty_ratelimit,
+					 &nr_dirtied_pause);
 
 		if (unlikely(task_ratelimit == 0)) {
 			period = max_pause;

@@ -1515,15 +1516,15 @@ pause:
 		 * more page. However bdi_dirty has accounting errors.  So use
 		 * the larger and more IO friendly wb_stat_error.
 		 */
-		if (bdi_dirty <= wb_stat_error(&bdi->wb))
+		if (bdi_dirty <= wb_stat_error(wb))
 			break;
 
 		if (fatal_signal_pending(current))
 			break;
 	}
 
-	if (!dirty_exceeded && bdi->dirty_exceeded)
-		bdi->dirty_exceeded = 0;
+	if (!dirty_exceeded && wb->dirty_exceeded)
+		wb->dirty_exceeded = 0;
 
 	if (writeback_in_progress(bdi))
 		return;

@@ -1577,6 +1578,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
 void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+	struct bdi_writeback *wb = &bdi->wb;
 	int ratelimit;
 	int *p;
 

@@ -1584,7 +1586,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
 		return;
 
 	ratelimit = current->nr_dirtied_pause;
-	if (bdi->dirty_exceeded)
+	if (wb->dirty_exceeded)
 		ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
 
 	preempt_disable();

Signature · 1 line

2.1.0