ext3/4 with synchronous writes gets wedged by Postfix

OK, that's probably the easiest way to do that, as much as I don't like it...
Since iget() et.al. will not accept I_FREEING (will wait to go away
and restart), and since we'd better have serialization between new/free
on fs data structures anyway, we can afford simply skipping I_FREEING
et.al. in insert_inode_locked().

We do that from new_inode, so it won't race with free_inode in any interesting
ways and it won't race with iget (of any origin; nfsd or in case of fs
corruption a lookup) since both still will wait for I_LOCK.

Reviewed-by: "Theodore Ts'o" <tytso@mit.edu>
Acked-by: Jan Kara <jack@suse.cz>
Tested-by: David Watson <dbwatson@ukfsn.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/inode.c b/fs/inode.c
index 0571983..a4876e5 100644 (file)
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1053,13 +1053,22 @@ int insert_inode_locked(struct inode *inode)
        struct super_block *sb = inode->i_sb;
        ino_t ino = inode->i_ino;
        struct hlist_head *head = inode_hashtable + hash(sb, ino);
-       struct inode *old;
 
        inode->i_state |= I_LOCK|I_NEW;
        while (1) {
+               struct hlist_node *node;
+               struct inode *old = NULL;
                spin_lock(&inode_lock);
-               old = find_inode_fast(sb, head, ino);
-               if (likely(!old)) {
+               hlist_for_each_entry(old, node, head, i_hash) {
+                       if (old->i_ino != ino)
+                               continue;
+                       if (old->i_sb != sb)
+                               continue;
+                       if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+                               continue;
+                       break;
+               }
+               if (likely(!node)) {
                        hlist_add_head(&inode->i_hash, head);
                        spin_unlock(&inode_lock);
                        return 0;
@@ -1081,14 +1090,24 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 {
        struct super_block *sb = inode->i_sb;
        struct hlist_head *head = inode_hashtable + hash(sb, hashval);
-       struct inode *old;
 
        inode->i_state |= I_LOCK|I_NEW;
 
        while (1) {
+               struct hlist_node *node;
+               struct inode *old = NULL;
+
                spin_lock(&inode_lock);
-               old = find_inode(sb, head, test, data);
-               if (likely(!old)) {
+               hlist_for_each_entry(old, node, head, i_hash) {
+                       if (old->i_sb != sb)
+                               continue;
+                       if (!test(old, data))
+                               continue;
+                       if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
+                               continue;
+                       break;
+               }
+               if (likely(!node)) {
                        hlist_add_head(&inode->i_hash, head);
                        spin_unlock(&inode_lock);
                        return 0;