Re: [patch] fs: avoid I_NEW inodes

[Nick Piggin]

How about this?

--
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@xxxxxxx>

---
 fs/dquot.c                  |   10 ++++++++--
 fs/drop_caches.c            |    2 +-
 fs/inode.c                  |    2 ++
 fs/notify/inotify/inotify.c |   16 ++++++++--------
 4 files changed, 19 insertions(+), 11 deletions(-)

Index: linux-2.6/fs/dquot.c
===================================================================
--- linux-2.6.orig/fs/dquot.c
+++ linux-2.6/fs/dquot.c
@@ -789,12 +789,12 @@ static void add_dquot_ref(struct super_b
 
 	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 supe
 
 	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);
 	}
Index: linux-2.6/fs/drop_caches.c
===================================================================
--- linux-2.6.orig/fs/drop_caches.c
+++ linux-2.6/fs/drop_caches.c
@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct sup
 
 	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;
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c
+++ linux-2.6/fs/inode.c
@@ -356,6 +356,8 @@ static int invalidate_list(struct list_h
 		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);
Index: linux-2.6/fs/notify/inotify/inotify.c
===================================================================
--- linux-2.6.orig/fs/notify/inotify/inotify.c
+++ linux-2.6/fs/notify/inotify/inotify.c
@@ -380,6 +380,14 @@ void inotify_unmount_inodes(struct 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_
 		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. */
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/