sys_sync fixes and changes

Index: linux-2.6/fs/fs-writeback.c
===================================================================
@@ -421,9 +421,6 @@ __writeback_single_inode(struct inode *i
  * If we're a pdlfush thread, then implement pdflush collision avoidance
  * against the entire list.
  *
- * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so
- * that it can be located for waiting on in __writeback_single_inode().
- *
  * If `bdi' is non-zero then we're being asked to writeback a specific queue.
  * This function assumes that the blockdev superblock's inodes are backed by
  * a variety of queues, so all inodes are searched.  For other superblocks,

@@ -499,10 +496,6 @@ void generic_sync_sb_inodes(struct super
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		__writeback_single_inode(inode, wbc);
-		if (wbc->sync_mode == WB_SYNC_HOLD) {
-			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &sb->s_dirty);
-		}
 		if (current_is_pdflush())
 			writeback_release(bdi);
 		if (wbc->pages_skipped != pages_skipped) {

@@ -588,8 +581,7 @@ restart:
 
 /*
  * writeback and wait upon the filesystem's dirty inodes.  The caller will
- * do this in two passes - one to write, and one to wait.  WB_SYNC_HOLD is
- * used to park the written inodes on sb->s_dirty for the wait pass.
+ * do this in two passes - one to write, and one to wait.
  *
  * A finite limit is set on the number of pages which will be written.
  * To prevent infinite livelock of sys_sync().

@@ -600,7 +592,7 @@ restart:
 void sync_inodes_sb(struct super_block *sb, int wait)
 {
 	struct writeback_control wbc = {
-		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
+		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_NONE,
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};

Index: linux-2.6/include/linux/writeback.h
===================================================================
@@ -30,7 +30,6 @@ static inline int task_is_pdflush(struct
 enum writeback_sync_modes {
 	WB_SYNC_NONE,	/* Don't wait on anything */
 	WB_SYNC_ALL,	/* Wait on every mapping */
-	WB_SYNC_HOLD,	/* Hold the inode on sb_dirty for sys_sync() */
 };
 
 /*

Index: linux-2.6/fs/fs-writeback.c
===================================================================
@@ -440,6 +440,7 @@ void generic_sync_sb_inodes(struct super
 				struct writeback_control *wbc)
 {
 	const unsigned long start = jiffies;	/* livelock avoidance */
+	int sync = wbc->sync_mode == WB_SYNC_ALL;
 
 	spin_lock(&inode_lock);
 	if (!wbc->for_kupdate || list_empty(&sb->s_io))

@@ -516,7 +517,42 @@ void generic_sync_sb_inodes(struct super
 		if (!list_empty(&sb->s_more_io))
 			wbc->more_io = 1;
 	}
-	spin_unlock(&inode_lock);
+
+	if (unlikely(sync)) {
+		struct inode *inode, *old_inode = NULL;
+
+		/*
+		 * Data integrity sync. Must wait for all pages under writeback,
+		 * because there may have been pages dirtied before our sync
+		 * call, but which had writeout started before we write it out.
+		 * In which case, the inode may not be on the dirty list, but
+		 * we still have to wait for that writeout.
+		 */
+		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+			struct address_space *mapping;
+
+			if (inode->i_state & (I_FREEING|I_WILL_FREE))
+				continue;
+			mapping = inode->i_mapping;
+			if (mapping->nrpages == 0)
+				continue;
+			__iget(inode);
+			spin_unlock(&inode_lock);
+			/* see dquot.c comment */
+			iput(old_inode);
+			old_inode = inode;
+
+			filemap_fdatawait(mapping);
+
+			cond_resched();
+
+			spin_lock(&inode_lock);
+		}
+		spin_unlock(&inode_lock);
+		iput(old_inode);
+	} else
+		spin_unlock(&inode_lock);
+
 	return;		/* Leave any unwritten inodes on s_io */
 }
 EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);

@@ -596,13 +632,16 @@ void sync_inodes_sb(struct super_block *
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};
-	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 
-	wbc.nr_to_write = nr_dirty + nr_unstable +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused) +
-			nr_dirty + nr_unstable;
-	wbc.nr_to_write += wbc.nr_to_write / 2;		/* Bit more for luck */
+	if (!wait) {
+		unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+		unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+
+		wbc.nr_to_write = nr_dirty + nr_unstable +
+			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+	} else
+		wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
+
 	sync_sb_inodes(sb, &wbc);
 }
 

Index: linux-2.6/fs/fs-writeback.c
===================================================================
@@ -645,18 +645,6 @@ void sync_inodes_sb(struct super_block *
 	sync_sb_inodes(sb, &wbc);
 }
 
-/*
- * Rather lame livelock avoidance.
- */
-static void set_sb_syncing(int val)
-{
-	struct super_block *sb;
-	spin_lock(&sb_lock);
-	list_for_each_entry_reverse(sb, &super_blocks, s_list)
-		sb->s_syncing = val;
-	spin_unlock(&sb_lock);
-}
-
 /**
  * sync_inodes - writes all inodes to disk
  * @wait: wait for completion

@@ -683,9 +671,6 @@ static void __sync_inodes(int wait)
 	spin_lock(&sb_lock);
 restart:
 	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_syncing)
-			continue;
-		sb->s_syncing = 1;
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 		down_read(&sb->s_umount);

@@ -703,13 +688,10 @@ restart:
 
 void sync_inodes(int wait)
 {
-	set_sb_syncing(0);
 	__sync_inodes(0);
 
-	if (wait) {
-		set_sb_syncing(0);
+	if (wait)
 		__sync_inodes(1);
-	}
 }
 
 /**

Index: linux-2.6/include/linux/fs.h
===================================================================
@@ -1122,7 +1122,6 @@ struct super_block {
 	struct rw_semaphore	s_umount;
 	struct mutex		s_lock;
 	int			s_count;
-	int			s_syncing;
 	int			s_need_sync_fs;
 	atomic_t		s_active;
 #ifdef CONFIG_SECURITY