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 eecdb1dafd10b7365ecb49e07b4774dd04961e51..3061a3e127ce397e6c1101f80a57afea023e8807 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5996,8 +5996,7 @@ 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:
@@ -6073,8 +6072,7 @@ 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);
@@ -6217,12 +6215,7 @@ 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:
@@ -9251,8 +9244,7 @@ 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 c064eea24c4a968756fe78f437c1a6b2d94daae2..a34d4019f465cee79ffe789838147bc2fa9ab9b8 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1868,6 +1868,28 @@ static struct dentry * __d_find_any_alias(struct inode *inode)
        return alias;
 }
 
+/*
+ * 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_find_any_alias - find any alias for a given inode
  * @inode: inode to find an alias for

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1686dc2da9fd7627df7fea9035262ca900b5676e..885c6a92c4f1c45b8c506c79ee11ffde6c97cfbf 100644 (file)
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -289,8 +289,7 @@ 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 c268d0af1db93c5c9b3db0dd93dd6819d977b42e..b31b12ddb99b5f3d0ae4fdaa991d1aeb859ef79a 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);
@@ -265,8 +264,7 @@ 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 ebd059aba3433c1458a00763c0987f8cb5cfb972..7c023859ba04be0ccec398c66cbe68cd0bb6dc17 100644 (file)
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2205,8 +2205,7 @@ 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);
@@ -2440,8 +2439,7 @@ 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 0d2526e5aa11401016a985681bff7036bbe54e48..c82f130f57eab8a62cab72e043933ebd27526119 100644 (file)
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -129,8 +129,7 @@ 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);
        return 0;
 out:
        handle_failed_inode(inode);
@@ -259,8 +258,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
        err = page_symlink(inode, symname, symlen);
        alloc_nid_done(sbi, inode->i_ino);
 
-       d_instantiate(dentry, inode);
-       unlock_new_inode(inode);
+       d_instantiate_new(dentry, inode);
        return err;
 out:
        handle_failed_inode(inode);
@@ -293,8 +291,7 @@ 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);
 
        return 0;
 
@@ -338,8 +335,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
        f2fs_unlock_op(sbi);
 
        alloc_nid_done(sbi, inode->i_ino);
-       d_instantiate(dentry, inode);
-       unlock_new_inode(inode);
+       d_instantiate_new(dentry, inode);
        return 0;
 out:
        handle_failed_inode(inode);

diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 938556025d643349b5166e54b5cfc55ea4767dbe..1313e32f66eab954e1192dc6dbb5866a2b06dde4 100644 (file)
--- 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:
@@ -427,8 +426,7 @@ 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:
@@ -572,8 +570,7 @@ 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 d59c7defb1efea8bb46bea33ddffe2c384db390b..d071500a2afa77d43be56ad9fe75221aec02c8c3 100644 (file)
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -176,8 +176,7 @@ 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:
@@ -309,8 +308,7 @@ 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:
@@ -1043,8 +1041,7 @@ 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:
@@ -1424,8 +1421,7 @@ 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 0f84b257932c2351569db8fc87432dfb9bcfebe9..da65882b540713da6f60027e4b45cee49d1a05e9 100644 (file)
--- 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);
@@ -249,8 +248,7 @@ 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 cd11358b10c7a1e427394f78ca8334e67f3c9467..2e9d82f7c35cb588a4e52259f81b8d8f3a1296de 100644 (file)
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -682,8 +682,7 @@ 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:
@@ -763,8 +762,7 @@ 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:
@@ -857,8 +855,7 @@ 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);
@@ -1162,8 +1159,7 @@ 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 6ff19b54b51f285971232e30e9d437fa3966654a..3bff8a2791955c4df1fe66891a66937a4562e1ab 100644 (file)
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -574,8 +574,7 @@ 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;
 }
@@ -684,8 +683,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
        udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL);
        inc_nlink(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 e8ee2985b06886cb803471f821f692ce97ae3b4c..2f446e79de9f75f05e93f42b1ab23d96c162ca26 100644 (file)
--- 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);
@@ -212,8 +211,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
                goto out_fail;
        unlock_ufs(dir->i_sb);
 
-       unlock_new_inode(inode);
-       d_instantiate(dentry, inode);
+       d_instantiate_new(dentry, inode);
 out:
        return err;
 

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 493926ff1717d5d7e1a73a9b36fed2d46c5c0c38..c33793eab131637865221c019f80e2a3390a2ccc 100644 (file)
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -231,6 +231,7 @@ 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_materialise_unique(struct dentry *, struct inode *);
 extern int d_instantiate_no_diralias(struct dentry *, struct inode *);