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>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ee12010dd32cb3a90bf0d92d905c2bc1e3aa0648..8b031f40a2f5580fbe5e8c01f419fbec537ec4bd 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6632,8 +6632,7 @@ 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:
@@ -6709,8 +6708,7 @@ 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);
@@ -6855,12 +6853,7 @@ 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:
@@ -10373,8 +10366,7 @@ 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);

diff --git a/fs/dcache.c b/fs/dcache.c
index 8945e6cabd93f7ce42709f93b90db94dceb74273..06463b780e573e37dedd1a488074708b0e82a1f5 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1865,6 +1865,28 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
 }
 EXPORT_SYMBOL(d_instantiate);
 
+/*
+ * 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 847904aa63a9a6554d592dbf0710c7eff7954f49..7bba8f2693b2d5cff40b7b8484f7cf75137d892b 100644 (file)
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -283,8 +283,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
                iget_failed(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 e078075dc66faaa80ce377118c3750246fc64da8..aa6ec191cac08d42c8d83039800f19c46d0844d6 100644 (file)
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -41,8 +41,7 @@ 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);
@@ -269,8 +268,7 @@ 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 b1f21e3a076327df20e5218451ff1feec7e3a13f..4a09063ce1d215492c313a2ce54a10418cf63d8b 100644 (file)
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2411,8 +2411,7 @@ 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);
@@ -2651,8 +2650,7 @@ 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 b68e7b03959f5b7cc67d2b6f9b94715d517fac14..860c9dd4bb4290b798048f28bc91c40cf8859265 100644 (file)
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -218,8 +218,7 @@ 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);
@@ -526,8 +525,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
        err = page_symlink(inode, disk_link.name, disk_link.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
@@ -590,8 +588,7 @@ 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);
@@ -642,8 +639,7 @@ 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 0a754f38462e9623e5608e65f95606abfef453be..e5a6deb38e1e1be47803250b3de5d115ce5c7e88 100644 (file)
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -209,8 +209,7 @@ 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:
@@ -430,8 +429,7 @@ 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:
@@ -575,8 +573,7 @@ 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:
@@ -747,8 +744,7 @@ 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 b41596d71858b4a1fcaf4b3e133ebc7b72d48afd..56c3fcbfe80ed0b69156bcab2f981b4d322b0aba 100644 (file)
--- 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:
@@ -1059,8 +1057,7 @@ 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:
@@ -1447,8 +1444,7 @@ 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 1a2894aa01942597e05dba587d33d42bd2da7c0a..dd52d3f82e8d673bd43dd99dfdfff6658b959357 100644 (file)
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -46,8 +46,7 @@ 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);
@@ -243,8 +242,7 @@ 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/orangefs/namei.c b/fs/orangefs/namei.c
index 6e3134e6d98a51c14a7c170ec6b98fdd7b78ff8e..1b5707c44c3f61dcf54fc6f2bc7901b420d2e322 100644 (file)
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -75,8 +75,7 @@ static int orangefs_create(struct inode *dir,
                     get_khandle_from_ino(inode),
                     dentry);
 
-       d_instantiate(dentry, inode);
-       unlock_new_inode(inode);
+       d_instantiate_new(dentry, inode);
        orangefs_set_timeout(dentry);
        ORANGEFS_I(inode)->getattr_time = jiffies - 1;
        ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -332,8 +331,7 @@ static int orangefs_symlink(struct inode *dir,
                     "Assigned symlink inode new number of %pU\n",
                     get_khandle_from_ino(inode));
 
-       d_instantiate(dentry, inode);
-       unlock_new_inode(inode);
+       d_instantiate_new(dentry, inode);
        orangefs_set_timeout(dentry);
        ORANGEFS_I(inode)->getattr_time = jiffies - 1;
        ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -402,8 +400,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
                     "Assigned dir inode new number of %pU\n",
                     get_khandle_from_ino(inode));
 
-       d_instantiate(dentry, inode);
-       unlock_new_inode(inode);
+       d_instantiate_new(dentry, inode);
        orangefs_set_timeout(dentry);
        ORANGEFS_I(inode)->getattr_time = jiffies - 1;
        ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;

diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index bd39a998843da62db4b634800813c3de29d969c7..5089dac0266020d705e54dcb8f06ca1a998ccec2 100644 (file)
--- 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);
@@ -1187,8 +1184,7 @@ 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 0458dd47e105b0c2724064bd816fd4f7ef24e28a..c586026508db82d0a27a1df1b964bcbf3fcec45c 100644 (file)
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -622,8 +622,7 @@ 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;
 }
@@ -733,8 +732,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
        inc_nlink(dir);
        dir->i_ctime = dir->i_mtime = current_time(dir);
        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 32545cd00cebf0fb50a403a7275efc194ef6bb4f..d5f43ba76c598dea592339f8926327401b181483 100644 (file)
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -39,8 +39,7 @@ 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);
@@ -193,8 +192,7 @@ 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 82a99d366aece7acb77a1ecf5ab9809ada60fbe4..9e9bc9f33c031b8290ebdb84c981c0e6134d6cbb 100644 (file)
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -226,6 +226,7 @@ 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 struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
 extern int d_instantiate_no_diralias(struct dentry *, struct inode *);