writeback: fix ntfs with sb_has_dirty_inodes()

@@ -118,7 +118,7 @@ void __mark_inode_dirty(struct inode *in
 			goto out;
 
 		/*
-		 * If the inode was already on s_dirty or s_io, don't
+		 * If the inode was already on s_dirty/s_io/s_more_io, don't
 		 * reposition it (that would break s_dirty time-ordering).
 		 */
 		if (!was_dirty) {

@@ -172,6 +172,33 @@ static void requeue_io(struct inode *ino
 }
 
 /*
+ * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
+ */
+static void move_expired_inodes(struct list_head *delaying_queue,
+			       struct list_head *dispatch_queue,
+				unsigned long *older_than_this)
+{
+	while (!list_empty(delaying_queue)) {
+		struct inode *inode = list_entry(delaying_queue->prev,
+						struct inode, i_list);
+		if (older_than_this &&
+			time_after(inode->dirtied_when, *older_than_this))
+			break;
+		list_move(&inode->i_list, dispatch_queue);
+	}
+}
+
+/*
+ * Queue all expired dirty inodes for io, eldest first.
+ */
+static void queue_io(struct super_block *sb,
+				unsigned long *older_than_this)
+{
+	list_splice_init(&sb->s_more_io, sb->s_io.prev);
+	move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
+}
+
+/*
  * Write a single inode's dirty pages and inode data out to disk.
  * If `wait' is set, wait on the writeout.
  *

@@ -221,7 +248,7 @@ __sync_single_inode(struct inode *inode,
 			/*
 			 * We didn't write back all the pages.  nfs_writepages()
 			 * sometimes bales out without doing anything. Redirty
-			 * the inode.  It is moved from s_io onto s_dirty.
+			 * the inode; Move it from s_io onto s_more_io/s_dirty.
 			 */
 			/*
 			 * akpm: if the caller was the kupdate function we put

@@ -234,10 +261,9 @@ __sync_single_inode(struct inode *inode,
 			 */
 			if (wbc->for_kupdate) {
 				/*
-				 * For the kupdate function we leave the inode
-				 * at the head of sb_dirty so it will get more
-				 * writeout as soon as the queue becomes
-				 * uncongested.
+				 * For the kupdate function we move the inode
+				 * to s_more_io so it will get more writeout as
+				 * soon as the queue becomes uncongested.
 				 */
 				inode->i_state |= I_DIRTY_PAGES;
 				requeue_io(inode);

@@ -295,10 +321,10 @@ __writeback_single_inode(struct inode *i
 
 		/*
 		 * We're skipping this inode because it's locked, and we're not
-		 * doing writeback-for-data-integrity.  Move it to the head of
-		 * s_dirty so that writeback can proceed with the other inodes
-		 * on s_io.  We'll have another go at writing back this inode
-		 * when the s_dirty iodes get moved back onto s_io.
+		 * doing writeback-for-data-integrity.  Move it to s_more_io so
+		 * that writeback can proceed with the other inodes on s_io.
+		 * We'll have another go at writing back this inode when we
+		 * completed a full scan of s_io.
 		 */
 		requeue_io(inode);
 

@@ -365,7 +391,7 @@ sync_sb_inodes(struct super_block *sb, s
 	const unsigned long start = jiffies;	/* livelock avoidance */
 
 	if (!wbc->for_kupdate || list_empty(&sb->s_io))
-		list_splice_init(&sb->s_dirty, &sb->s_io);
+		queue_io(sb, wbc->older_than_this);
 
 	while (!list_empty(&sb->s_io)) {
 		struct inode *inode = list_entry(sb->s_io.prev,

@@ -410,13 +436,6 @@ sync_sb_inodes(struct super_block *sb, s
 		if (time_after(inode->dirtied_when, start))
 			break;
 
-		/* Was this inode dirtied too recently? */
-		if (wbc->older_than_this && time_after(inode->dirtied_when,
-						*wbc->older_than_this)) {
-			list_splice_init(&sb->s_io, sb->s_dirty.prev);
-			break;
-		}
-
 		/* Is another pdflush already flushing this queue? */
 		if (current_is_pdflush() && !writeback_acquire(bdi))
 			break;

@@ -446,9 +465,6 @@ sync_sb_inodes(struct super_block *sb, s
 			break;
 	}
 
-	if (list_empty(&sb->s_io))
-		list_splice_init(&sb->s_more_io, &sb->s_io);
-
 	return;		/* Leave any unwritten inodes on s_io */
 }
 

@@ -458,7 +474,7 @@ sync_sb_inodes(struct super_block *sb, s
  * Note:
  * We don't need to grab a reference to superblock here. If it has non-empty
  * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until both the ->s_dirty and ->s_io lists are
+ * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
  * empty. Since __sync_single_inode() regains inode_lock before it finally moves
  * inode from superblock lists we are OK.
  *

@@ -2381,14 +2381,14 @@ static void ntfs_put_super(struct super_
 	 */
 	ntfs_commit_inode(vol->mft_ino);
 	write_inode_now(vol->mft_ino, 1);
-	if (!list_empty(&sb->s_dirty)) {
+	if (sb_has_dirty_inodes(sb)) {
 		const char *s1, *s2;
 
 		mutex_lock(&vol->mft_ino->i_mutex);
 		truncate_inode_pages(vol->mft_ino->i_mapping, 0);
 		mutex_unlock(&vol->mft_ino->i_mutex);
 		write_inode_now(vol->mft_ino, 1);
-		if (!list_empty(&sb->s_dirty)) {
+		if (sb_has_dirty_inodes(sb)) {
 			static const char *_s1 = "inodes";
 			static const char *_s2 = "";
 			s1 = _s1;

@@ -1712,6 +1712,7 @@ extern int bdev_read_only(struct block_d
 extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
+extern int sb_has_dirty_inodes(struct super_block *);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);

@@ -198,6 +198,14 @@ static void queue_io(struct super_block 
 	move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
 }
 
+int sb_has_dirty_inodes(struct super_block *sb)
+{
+	return !list_empty(&sb->s_dirty) ||
+	       !list_empty(&sb->s_io) ||
+	       !list_empty(&sb->s_more_io);
+}
+EXPORT_SYMBOL(sb_has_dirty_inodes);
+
 /*
  * Write a single inode's dirty pages and inode data out to disk.
  * If `wait' is set, wait on the writeout.

@@ -497,7 +505,7 @@ writeback_inodes(struct writeback_contro
 restart:
 	sb = sb_entry(super_blocks.prev);
 	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
-		if (!list_empty(&sb->s_dirty) || !list_empty(&sb->s_io)) {
+		if (sb_has_dirty_inodes(sb)) {
 			/* we're making our own get_super here */
 			sb->s_count++;
 			spin_unlock(&sb_lock);

@@ -1713,7 +1713,6 @@ done:
 		 * The page and buffer_heads can be released at any time from
 		 * here on.
 		 */
-		wbc->pages_skipped++;	/* We didn't write this page */
 	}
 	return err;
 

@@ -472,6 +472,8 @@ sync_sb_inodes(struct super_block *sb, s
 		if (wbc->nr_to_write <= 0)
 			break;
 	}
+	if (!list_empty(&sb->s_more_io))
+		wbc->more_io = 1;
 
 	return;		/* Leave any unwritten inodes on s_io */
 }

@@ -61,6 +61,7 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
+	unsigned more_io:1;		/* more io to be dispatched */
 
 	void *fs_private;		/* For use by ->writepages() */
 };

@@ -382,6 +382,7 @@ static void background_writeout(unsigned
 			global_page_state(NR_UNSTABLE_NFS) < background_thresh
 				&& min_pages <= 0)
 			break;
+		wbc.more_io = 0;
 		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;

@@ -389,8 +390,9 @@ static void background_writeout(unsigned
 		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
-			congestion_wait(WRITE, HZ/10);
-			if (!wbc.encountered_congestion)
+			if (wbc.encountered_congestion || wbc.more_io)
+				congestion_wait(WRITE, HZ/10);
+			else
 				break;
 		}
 	}

@@ -455,11 +457,12 @@ static void wb_kupdate(unsigned long arg
 			global_page_state(NR_UNSTABLE_NFS) +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
 	while (nr_to_write > 0) {
+		wbc.more_io = 0;
 		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
-			if (wbc.encountered_congestion)
+			if (wbc.encountered_congestion || wbc.more_io)
 				congestion_wait(WRITE, HZ/10);
 			else
 				break;	/* All the old data is written */

@@ -24,6 +24,75 @@
 #include <linux/buffer_head.h>
 #include "internal.h"
 
+int sysctl_inode_debug __read_mostly;
+
+static int __check(struct list_head *head, int print_stuff)
+{
+	struct list_head *cursor = head;
+	unsigned long dirtied_when = 0;
+
+	while ((cursor = cursor->prev) != head) {
+		struct inode *inode = list_entry(cursor, struct inode, i_list);
+		if (print_stuff) {
+			printk("%p:%lu\n", inode, inode->dirtied_when);
+		} else {
+			if (dirtied_when &&
+			    time_before(inode->dirtied_when, dirtied_when))
+				return 1;
+			dirtied_when = inode->dirtied_when;
+		}
+	}
+	return 0;
+}
+
+static void __check_dirty_inode_list(struct super_block *sb,
+			struct inode *inode, const char *file, int line)
+{
+	if (!sysctl_inode_debug)
+		return;
+
+	if (__check(&sb->s_dirty, 0)) {
+		sysctl_inode_debug = 0;
+		if (inode)
+			printk("%s:%d: s_dirty got screwed up.  inode=%p:%lu\n",
+					file, line, inode, inode->dirtied_when);
+		else
+			printk("%s:%d: s_dirty got screwed up\n", file, line);
+		__check(&sb->s_dirty, 1);
+	}
+	if (__check(&sb->s_io, 0)) {
+		sysctl_inode_debug = 0;
+		if (inode)
+			printk("%s:%d: s_io got screwed up.  inode=%p:%lu\n",
+					file, line, inode, inode->dirtied_when);
+		else
+			printk("%s:%d: s_io got screwed up\n", file, line);
+		__check(&sb->s_io, 1);
+	}
+	if (__check(&sb->s_more_io, 0)) {
+		sysctl_inode_debug = 0;
+		if (inode)
+			printk("%s:%d: s_more_io got screwed up.  inode=%p:%lu\n",
+					file, line, inode, inode->dirtied_when);
+		else
+			printk("%s:%d: s_more_io got screwed up\n", file, line);
+		__check(&sb->s_more_io, 1);
+	}
+}
+
+#define check_dirty_inode_list(sb)					\
+	do {								\
+		if (unlikely(sysctl_inode_debug))			\
+		__check_dirty_inode_list(sb, NULL, __FILE__, __LINE__);	\
+	} while (0)
+
+#define check_dirty_inode(inode)					\
+	do {								\
+		if (unlikely(sysctl_inode_debug))			\
+			__check_dirty_inode_list(inode->i_sb, inode,	\
+						__FILE__, __LINE__);	\
+	} while (0)
+
 /**
  *	__mark_inode_dirty -	internal function
  *	@inode: inode to mark

@@ -122,8 +191,10 @@ void __mark_inode_dirty(struct inode *in
 		 * reposition it (that would break s_dirty time-ordering).
 		 */
 		if (!was_dirty) {
+			check_dirty_inode(inode);
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_list, &sb->s_dirty);
+			check_dirty_inode(inode);
 		}
 	}
 out:

@@ -152,6 +223,7 @@ static void redirty_tail(struct inode *i
 {
 	struct super_block *sb = inode->i_sb;
 
+	check_dirty_inode(inode);
 	if (!list_empty(&sb->s_dirty)) {
 		struct inode *tail_inode;
 

@@ -161,6 +233,7 @@ static void redirty_tail(struct inode *i
 			inode->dirtied_when = jiffies;
 	}
 	list_move(&inode->i_list, &sb->s_dirty);
+	check_dirty_inode(inode);
 }
 
 /*

@@ -168,7 +241,9 @@ static void redirty_tail(struct inode *i
  */
 static void requeue_io(struct inode *inode)
 {
+	check_dirty_inode(inode);
 	list_move(&inode->i_list, &inode->i_sb->s_more_io);
+	check_dirty_inode(inode);
 }
 
 static void inode_sync_complete(struct inode *inode)

@@ -463,8 +538,10 @@ int generic_sync_sb_inodes(struct super_
 		if (!ret)
 			ret = err;
 		if (wbc->sync_mode == WB_SYNC_HOLD) {
+			check_dirty_inode(inode);
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_list, &sb->s_dirty);
+			check_dirty_inode(inode);
 		}
 		if (current_is_pdflush())
 			writeback_release(bdi);

@@ -140,5 +140,6 @@ void writeback_set_ratelimit(void);
 extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl
 				   read-only. */
 
+extern int sysctl_inode_debug;
 
 #endif		/* WRITEBACK_H */

@@ -1238,6 +1238,14 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "inode_debug",
+		.data		= &sysctl_inode_debug,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 	{
 		.ctl_name	= CTL_UNNUMBERED,

@@ -224,14 +224,7 @@ static void redirty_tail(struct inode *i
 	struct super_block *sb = inode->i_sb;
 
 	check_dirty_inode(inode);
-	if (!list_empty(&sb->s_dirty)) {
-		struct inode *tail_inode;
-
-		tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
-		if (!time_after_eq(inode->dirtied_when,
-				tail_inode->dirtied_when))
-			inode->dirtied_when = jiffies;
-	}
+	inode->dirtied_when = jiffies;
 	list_move(&inode->i_list, &sb->s_dirty);
 	check_dirty_inode(inode);
 }