fs: avoid I_NEW inodes

To be on the safe side, it should be less fragile to exclude I_NEW inodes
from inode list scans by default (unless there is an important reason to
have them).

Normally they will get excluded (eg.  by zero refcount or writecount etc),
however it is a bit fragile for list walkers to know exactly what parts of
the inode state is set up and valid to test when in I_NEW.  So along these
lines, move I_NEW checks upward as well (sometimes taking I_FREEING etc
checks with them too -- this shouldn't be a problem should it?)

Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

4 files changed, 19 insertions, 11 deletions

diff --git a/fs/dquot.c b/fs/dquot.c
index bca3cac..cb1c3bc 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -789,12 +789,12 @@ static void add_dquot_ref(struct super_block *sb, int type)
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+			continue;
 		if (!atomic_read(&inode->i_writecount))
 			continue;
 		if (!dqinit_needed(inode, type))
 			continue;
-		if (inode->i_state & (I_FREEING|I_WILL_FREE))
-			continue;
 
 		__iget(inode);
 		spin_unlock(&inode_lock);
@@ -870,6 +870,12 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+		/*
+		 *  We have to scan also I_NEW inodes because they can already
+		 *  have quota pointer initialized. Luckily, we need to touch
+		 *  only quota pointers and these have separate locking
+		 *  (dqptr_sem).
+		 */
 		if (!IS_NOQUOTA(inode))
 			remove_inode_dquot_ref(inode, type, tofree_head);
 	}
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 3e5637f..44d725f 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb)
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_WILL_FREE))
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
 			continue;
 		if (inode->i_mapping->nrpages == 0)
 			continue;
diff --git a/fs/inode.c b/fs/inode.c
index 826fb0b..06aa5a1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -356,6 +356,8 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
 		if (tmp == head)
 			break;
 		inode = list_entry(tmp, struct inode, i_sb_list);
+		if (inode->i_state & I_NEW)
+			continue;
 		invalidate_inode_buffers(inode);
 		if (!atomic_read(&inode->i_count)) {
 			list_move(&inode->i_list, dispose);
diff --git a/fs/notify/inotify/inotify.c b/fs/notify/inotify/inotify.c
index 331f2e8..220c13f 100644
--- a/fs/notify/inotify/inotify.c
+++ b/fs/notify/inotify/inotify.c
@@ -380,6 +380,14 @@ void inotify_unmount_inodes(struct list_head *list)
 		struct list_head *watches;
 
 		/*
+		 * We cannot __iget() an inode in state I_CLEAR, I_FREEING,
+		 * I_WILL_FREE, or I_NEW which is fine because by that point
+		 * the inode cannot have any associated watches.
+		 */
+		if (inode->i_state & (I_CLEAR|I_FREEING|I_WILL_FREE|I_NEW))
+			continue;
+
+		/*
 		 * If i_count is zero, the inode cannot have any watches and
 		 * doing an __iget/iput with MS_ACTIVE clear would actually
 		 * evict all inodes with zero i_count from icache which is
@@ -388,14 +396,6 @@ void inotify_unmount_inodes(struct list_head *list)
 		if (!atomic_read(&inode->i_count))
 			continue;
 
-		/*
-		 * We cannot __iget() an inode in state I_CLEAR, I_FREEING, or
-		 * I_WILL_FREE which is fine because by that point the inode
-		 * cannot have any associated watches.
-		 */
-		if (inode->i_state & (I_CLEAR | I_FREEING | I_WILL_FREE))
-			continue;
-
 		need_iput_tmp = need_iput;
 		need_iput = NULL;
 		/* In case inotify_remove_watch_locked() drops a reference. */