ext3: Replace lock/unlock_super() with an explicit lock for the orphan list

Use a separate lock to protect the orphan list, so we can stop
overloading the use of lock_super().

Port of ext4 commit 3b9d4ed26680771295d904a6b83e88e620780893
by Theodore Ts'o <tytso@mit.edu>.

CC: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>

diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 81f7348..7b0e44f 100644 (file)
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1920,7 +1920,7 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode)
        struct ext3_iloc iloc;
        int err = 0, rc;
 
-       lock_super(sb);
+       mutex_lock(&EXT3_SB(sb)->s_orphan_lock);
        if (!list_empty(&EXT3_I(inode)->i_orphan))
                goto out_unlock;
 
@@ -1929,9 +1929,13 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode)
 
        /* @@@ FIXME: Observation from aviro:
         * I think I can trigger J_ASSERT in ext3_orphan_add().  We block
-        * here (on lock_super()), so race with ext3_link() which might bump
+        * here (on s_orphan_lock), so race with ext3_link() which might bump
         * ->i_nlink. For, say it, character device. Not a regular file,
         * not a directory, not a symlink and ->i_nlink > 0.
+        *
+        * tytso, 4/25/2009: I'm not sure how that could happen;
+        * shouldn't the fs core protect us from these sort of
+        * unlink()/link() races?
         */
        J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
                S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
@@ -1968,7 +1972,7 @@ int ext3_orphan_add(handle_t *handle, struct inode *inode)
        jbd_debug(4, "orphan inode %lu will point to %d\n",
                        inode->i_ino, NEXT_ORPHAN(inode));
 out_unlock:
-       unlock_super(sb);
+       mutex_unlock(&EXT3_SB(sb)->s_orphan_lock);
        ext3_std_error(inode->i_sb, err);
        return err;
 }
@@ -1986,11 +1990,9 @@ int ext3_orphan_del(handle_t *handle, struct inode *inode)
        struct ext3_iloc iloc;
        int err = 0;
 
-       lock_super(inode->i_sb);
-       if (list_empty(&ei->i_orphan)) {
-               unlock_super(inode->i_sb);
-               return 0;
-       }
+       mutex_lock(&EXT3_SB(inode->i_sb)->s_orphan_lock);
+       if (list_empty(&ei->i_orphan))
+               goto out;
 
        ino_next = NEXT_ORPHAN(inode);
        prev = ei->i_orphan.prev;
@@ -2040,7 +2042,7 @@ int ext3_orphan_del(handle_t *handle, struct inode *inode)
 out_err:
        ext3_std_error(inode->i_sb, err);
 out:
-       unlock_super(inode->i_sb);
+       mutex_unlock(&EXT3_SB(inode->i_sb)->s_orphan_lock);
        return err;
 
 out_brelse:

diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 806b8b7..97dd382 100644 (file)
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1928,6 +1928,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
        sb->dq_op = &ext3_quota_operations;
 #endif
        INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
+       mutex_init(&sbi->s_orphan_lock);
 
        sb->s_root = NULL;
 

diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
index f07f34d..dd61d83 100644 (file)
--- a/include/linux/ext3_fs_sb.h
+++ b/include/linux/ext3_fs_sb.h
@@ -72,6 +72,7 @@ struct ext3_sb_info {
        struct inode * s_journal_inode;
        struct journal_s * s_journal;
        struct list_head s_orphan;
+       struct mutex s_orphan_lock;
        unsigned long s_commit_interval;
        struct block_device *journal_bdev;
 #ifdef CONFIG_JBD_DEBUG