[RFC][PATCH 10/16] writeback: simplify bdi code a little

[Artem Bityutskiy <dedekind1@gmail.com>]

From: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>

This patch simplifies bdi code a little by removing the 'pending_list'
which is redundant. Indeed, currently the forker thread
('bdi_forker_thread()') is working like this:

1. In a loop, fetch  all bdi's which have works but have no writeback
   thread and move them to the 'pending_list'.
2. If the list is empty, sleep for 5 s.
3. Otherwise, take one BDI from the list, fork the writeback thread for
   this bdi, and repeat the loop again.

IOW, it first moves everything to the 'pending_list', then process only
one element, and so on. With this patch the algorithm is:

1. Find the first bdi which has work and remove it from the global
   list of bdi's (bdi_list).
2. If there were not such bdi, sleep 5 s.
3. Fork the writeback thread for this bdi and repeat the loop again.

IOW, now we find the first bdi to process, process it, and so on. This
is simpler and involves less lists.

This patch also removes unneeded and unused complications which involve
'rcu_call()' and 'bdi->rcu_head' - now we use simple 'synchronize_rcu()'
and remove the 'rcu_head' field from 'struct backing_dev_info'.

Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
---
 include/linux/backing-dev.h |    1 -
 mm/backing-dev.c            |   75 ++++++++++--------------------------------
 2 files changed, 18 insertions(+), 58 deletions(-)

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f0936f5..95ecb2b 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -58,7 +58,6 @@ struct bdi_writeback {
 
 struct backing_dev_info {
 	struct list_head bdi_list;
-	struct rcu_head rcu_head;
 	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 */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index ab783b9..a42e5ef 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -50,8 +50,6 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
-static void bdi_add_default_flusher_thread(struct backing_dev_info *bdi);
-
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -332,6 +330,7 @@ static int bdi_forker_thread(void *ptr)
 	set_user_nice(current, 0);
 
 	for (;;) {
+		bool fork = false;
 		struct backing_dev_info *bdi, *tmp;
 		struct task_struct *task;
 
@@ -346,22 +345,29 @@ static int bdi_forker_thread(void *ptr)
 		 * a thread registered. If so, set that up.
 		 */
 		list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
+			if (!bdi_cap_writeback_dirty(bdi))
+				continue;
 			if (bdi->wb.task)
 				continue;
 			if (!bdi_has_dirty_io(bdi))
 				continue;
 
-			bdi_add_default_flusher_thread(bdi);
+			WARN(!test_bit(BDI_registered, &bdi->state),
+			     "bdi %p/%s is not registered!\n", bdi, bdi->name);
+
+			list_del_rcu(&bdi->bdi_list);
+			fork = true;
+			break;
 		}
+		spin_unlock_bh(&bdi_lock);
 
 		/* Keep working if default bdi still has some works */
 		if (!list_empty(&me->bdi->work_list))
 			__set_current_state(TASK_RUNNING);
 
-		if (list_empty(&bdi_pending_list)) {
+		if (!fork) {
 			unsigned long wait;
 
-			spin_unlock_bh(&bdi_lock);
 			wait = msecs_to_jiffies(dirty_writeback_interval * 10);
 			if (wait)
 				schedule_timeout(wait);
@@ -374,13 +380,13 @@ static int bdi_forker_thread(void *ptr)
 		__set_current_state(TASK_RUNNING);
 
 		/*
-		 * This is our real job - check for pending entries in
-		 * bdi_pending_list, and create the threads that got added
+		 * Set the pending bit - if someone will try to unregister this
+		 * bdi - it'll wait on this bit.
 		 */
-		bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
-				 bdi_list);
-		list_del_init(&bdi->bdi_list);
-		spin_unlock_bh(&bdi_lock);
+		set_bit(BDI_pending, &bdi->state);
+
+		/* Make sure no one uses the picked bdi */
+		synchronize_rcu();
 
 		task = kthread_run(bdi_writeback_thread, &bdi->wb, "flush-%s",
  					dev_name(bdi->dev));
@@ -393,7 +399,7 @@ static int bdi_forker_thread(void *ptr)
 			 * flush other bdi's to free memory.
 			 */
 			spin_lock_bh(&bdi_lock);
-			list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+			list_add_tail(&bdi->bdi_list, &bdi_list);
 			spin_unlock_bh(&bdi_lock);
 
 			bdi_flush_io(bdi);
@@ -404,50 +410,6 @@ static int bdi_forker_thread(void *ptr)
 	return 0;
 }
 
-static void bdi_add_to_pending(struct rcu_head *head)
-{
-	struct backing_dev_info *bdi;
-
-	bdi = container_of(head, struct backing_dev_info, rcu_head);
-
-	spin_lock(&bdi_lock);
-	list_add_tail(&bdi->bdi_list, &bdi_pending_list);
-	spin_unlock(&bdi_lock);
-}
-
-/*
- * Add the default flusher thread that gets created for any bdi
- * that has dirty data pending writeout
- */
-void static bdi_add_default_flusher_thread(struct backing_dev_info *bdi)
-{
-	if (!bdi_cap_writeback_dirty(bdi))
-		return;
-
-	if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
-		printk(KERN_ERR "bdi %p/%s is not registered!\n",
-							bdi, bdi->name);
-		return;
-	}
-
-	/*
-	 * Check with the helper whether to proceed adding a thread. Will only
-	 * abort if we two or more simultanous calls to
-	 * bdi_add_default_flusher_thread() occured, further additions will
-	 * block waiting for previous additions to finish.
-	 */
-	if (!test_and_set_bit(BDI_pending, &bdi->state)) {
-		list_del_rcu(&bdi->bdi_list);
-
-		/*
-		 * We must wait for the current RCU period to end before
-		 * moving to the pending list. So schedule that operation
-		 * from an RCU callback.
-		 */
-		call_rcu(&bdi->rcu_head, bdi_add_to_pending);
-	}
-}
-
 /*
  * Look up for bdi in the bdi_list. If found, remove it, ensure that it is
  * no longer visible, and return 0. If not found, return 1.
@@ -603,7 +565,6 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = PROP_FRAC_BASE;
 	spin_lock_init(&bdi->wb_lock);
-	INIT_RCU_HEAD(&bdi->rcu_head);
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->work_list);
 
-- 
1.7.1.1