do d_instantiate/unlock_new_inode combinations safely

commit 1e2e547a93a00ebc21582c06ca3c6cfea2a309ee upstream.

For anything NFS-exported we do _not_ want to unlock new inode
before it has grown an alias; original set of fixes got the
ordering right, but missed the nasty complication in case of
lockdep being enabled - unlock_new_inode() does
	lockdep_annotate_inode_mutex_key(inode)
which can only be done before anyone gets a chance to touch
->i_mutex.  Unfortunately, flipping the order and doing
unlock_new_inode() before d_instantiate() opens a window when
mkdir can race with open-by-fhandle on a guessed fhandle, leading
to multiple aliases for a directory inode and all the breakage
that follows from that.

	Correct solution: a new primitive (d_instantiate_new())
combining these two in the right order - lockdep annotate, then
d_instantiate(), then the rest of unlock_new_inode().  All
combinations of d_instantiate() with unlock_new_inode() should
be converted to that.

Cc: stable@kernel.org	# 2.6.29 and later
Tested-by: Mike Marshall <hubcap@omnibond.com>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

13 files changed, 54 insertions, 66 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 81b5a461d94e..1f01a8172308 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6413,8 +6413,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto out_unlock_inode;
 	} else {
 		btrfs_update_inode(trans, root, inode);
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 	}
 
 out_unlock:
@@ -6489,8 +6488,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		goto out_unlock_inode;
 
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans, root);
@@ -6633,12 +6631,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (err)
 		goto out_fail_inode;
 
-	d_instantiate(dentry, inode);
-	/*
-	 * mkdir is special.  We're unlocking after we call d_instantiate
-	 * to avoid a race with nfsd calling d_instantiate.
-	 */
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 	drop_on_err = 0;
 
 out_fail:
@@ -9789,8 +9782,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		goto out_unlock_inode;
 	}
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans, root);
diff --git a/fs/dcache.c b/fs/dcache.c
index 751a0d88f049..250c1222e30c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1897,6 +1897,28 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 
 EXPORT_SYMBOL(d_instantiate_unique);
 
+/*
+ * This should be equivalent to d_instantiate() + unlock_new_inode(),
+ * with lockdep-related part of unlock_new_inode() done before
+ * anything else.  Use that instead of open-coding d_instantiate()/
+ * unlock_new_inode() combinations.
+ */
+void d_instantiate_new(struct dentry *entry, struct inode *inode)
+{
+	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+	BUG_ON(!inode);
+	lockdep_annotate_inode_mutex_key(inode);
+	security_d_instantiate(entry, inode);
+	spin_lock(&inode->i_lock);
+	__d_instantiate(entry, inode);
+	WARN_ON(!(inode->i_state & I_NEW));
+	inode->i_state &= ~I_NEW;
+	smp_mb();
+	wake_up_bit(&inode->i_state, __I_NEW);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(d_instantiate_new);
+
 /**
  * d_instantiate_no_diralias - instantiate a non-aliased dentry
  * @entry: dentry to complete
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e2e47ba5d313..844d0c4da84f 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -287,8 +287,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		iput(ecryptfs_inode);
 		goto out;
 	}
-	unlock_new_inode(ecryptfs_inode);
-	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+	d_instantiate_new(ecryptfs_dentry, ecryptfs_inode);
 out:
 	return rc;
 }
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 3267a80dbbe2..da3d40ef1668 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -40,8 +40,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = ext2_add_link(dentry, inode);
 	if (!err) {
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -267,8 +266,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	if (err)
 		goto out_fail;
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 out:
 	return err;
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 32960b3ecd4f..97472088d65a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2429,8 +2429,7 @@ static int ext4_add_nondir(handle_t *handle,
 	int err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {
 		ext4_mark_inode_dirty(handle, inode);
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	drop_nlink(inode);
@@ -2669,8 +2668,7 @@ out_clear_inode:
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (err)
 		goto out_clear_inode;
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 484df6850747..e5553cd8fe4e 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -150,8 +150,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	alloc_nid_done(sbi, ino);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
@@ -399,8 +398,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	err = page_symlink(inode, p_str, p_len);
 
 err_out:
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	/*
 	 * Let's flush symlink data in order to avoid broken symlink as much as
@@ -454,8 +452,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
@@ -499,8 +496,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 30c4c9ebb693..e27317169697 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -207,8 +207,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 		  __func__, inode->i_ino, inode->i_mode, inode->i_nlink,
 		  f->inocache->pino_nlink, inode->i_mapping->nrpages);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
@@ -428,8 +427,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	mutex_unlock(&dir_f->sem);
 	jffs2_complete_reservation(c);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
@@ -573,8 +571,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	mutex_unlock(&dir_f->sem);
 	jffs2_complete_reservation(c);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
@@ -745,8 +742,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	mutex_unlock(&dir_f->sem);
 	jffs2_complete_reservation(c);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
  fail:
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 9d7551f5c32a..f217ae750adb 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -178,8 +178,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out2:
@@ -313,8 +312,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out2:
@@ -1058,8 +1056,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out2:
@@ -1443,8 +1440,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 		unlock_new_inode(ip);
 		iput(ip);
 	} else {
-		unlock_new_inode(ip);
-		d_instantiate(dentry, ip);
+		d_instantiate_new(dentry, ip);
 	}
 
       out1:
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index c9a1a491aa91..cd7f5b0abe84 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -50,8 +50,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = nilfs_add_link(dentry, inode);
 	if (!err) {
-		d_instantiate(dentry, inode);
-		unlock_new_inode(inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -246,8 +245,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out_fail;
 
 	nilfs_mark_inode_dirty(inode);
-	d_instantiate(dentry, inode);
-	unlock_new_inode(inode);
+	d_instantiate_new(dentry, inode);
 out:
 	if (!err)
 		err = nilfs_transaction_commit(dir->i_sb);
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 3ebc70167e41..eb611bdd4725 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -687,8 +687,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
 	reiserfs_update_inode_transaction(inode);
 	reiserfs_update_inode_transaction(dir);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 
 out_failed:
@@ -771,8 +770,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 		goto out_failed;
 	}
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 
 out_failed:
@@ -871,8 +869,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	/* the above add_entry did not update dir's stat data */
 	reiserfs_update_sd(&th, dir);
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 out_failed:
 	reiserfs_write_unlock(dir->i_sb);
@@ -1186,8 +1183,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
 		goto out_failed;
 	}
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	retval = journal_end(&th);
 out_failed:
 	reiserfs_write_unlock(parent_dir->i_sb);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index c97b5a8d1e24..f34c545f4e54 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -611,8 +611,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 	if (fibh.sbh != fibh.ebh)
 		brelse(fibh.ebh);
 	brelse(fibh.sbh);
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 
 	return 0;
 }
@@ -722,8 +721,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inc_nlink(dir);
 	dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb);
 	mark_inode_dirty(dir);
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	if (fibh.sbh != fibh.ebh)
 		brelse(fibh.ebh);
 	brelse(fibh.sbh);
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 47966554317c..2ec7689c25cf 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -38,8 +38,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = ufs_add_link(dentry, inode);
 	if (!err) {
-		unlock_new_inode(inode);
-		d_instantiate(dentry, inode);
+		d_instantiate_new(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -191,8 +190,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	if (err)
 		goto out_fail;
 
-	unlock_new_inode(inode);
-	d_instantiate(dentry, inode);
+	d_instantiate_new(dentry, inode);
 	return 0;
 
 out_fail:
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d516847e0fae..11f4334ab177 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -236,6 +236,7 @@ extern seqlock_t rename_lock;
  * These are the low-level FS interfaces to the dcache..
  */
 extern void d_instantiate(struct dentry *, struct inode *);
+extern void d_instantiate_new(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);