[PATCH] Preparation work for VFS based union mounts

[PATCH] Preparation work for VFS based union mounts

[Jan Blunck]

Al,
here are some patches that are indenpendant from but necessary for the union
mount patch set. Valerie and I think they are ok to go in separately from the
rest of the patches.

Thanks,
Jan

Jan Blunck (6):
  VFS: BUG() if somebody tries to rehash an already hashed dentry
  VFS: propagate mnt_flags into do_loopback
  VFS: Make lookup_hash() return a struct path
  VFS: Remove unnecessary micro-optimization in cached_lookup()
  VFS: Make real_lookup() return a struct path
  VFS: Introduce dput() variant that maintains a kill-list

 fs/dcache.c    |  116 ++++++++++++++++++++++++++++---
 fs/namei.c     |  209 +++++++++++++++++++++++++++++++-------------------------
 fs/namespace.c |    7 +-
 3 files changed, 225 insertions(+), 107 deletions(-)

[PATCH] VFS: BUG() if somebody tries to rehash an already hashed dentry

[Jan Blunck]

Break early when somebody tries to rehash an already hashed dentry.
Otherwise this leads to interesting corruptions in the dcache hash table
later on.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/dcache.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 75659a6..191c488 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1550,6 +1550,7 @@ void d_rehash(struct dentry * entry)
 {
 	spin_lock(&dcache_lock);
 	spin_lock(&entry->d_lock);
+	BUG_ON(!d_unhashed(entry));
 	_d_rehash(entry);
 	spin_unlock(&entry->d_lock);
 	spin_unlock(&dcache_lock);
-- 
1.6.0.2

[PATCH] VFS: propagate mnt_flags into do_loopback

[Jan Blunck]

The mnt_flags are propagated into do_loopback(), so that they can be checked
when mounting something loopback into a union.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/namespace.c |    7 ++++---
 1 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 134d494..bdff9e4 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1475,8 +1475,8 @@ static int do_change_type(struct path *path, int flag)
 /*
  * do loopback mount.
  */
-static int do_loopback(struct path *path, char *old_name,
-				int recurse)
+static int do_loopback(struct path *path, char *old_name, int recurse,
+		       int mnt_flags)
 {
 	struct path old_path;
 	struct vfsmount *mnt = NULL;
@@ -1971,7 +1971,8 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
 		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
 				    data_page);
 	else if (flags & MS_BIND)
-		retval = do_loopback(&path, dev_name, flags & MS_REC);
+		retval = do_loopback(&path, dev_name, flags & MS_REC,
+				     mnt_flags);
 	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
 		retval = do_change_type(&path, flags);
 	else if (flags & MS_MOVE)
-- 
1.6.0.2

[PATCH] VFS: Make lookup_hash() return a struct path

[Jan Blunck]

This patch changes lookup_hash() into returning a struct path.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/namei.c |  114 +++++++++++++++++++++++++++++++----------------------------
 1 files changed, 60 insertions(+), 54 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 967c3db..c0cd4cb 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1153,7 +1153,7 @@ static int path_lookup_open(int dfd, const char *name,
 }
 
 static struct dentry *__lookup_hash(struct qstr *name,
-		struct dentry *base, struct nameidata *nd)
+				    struct dentry *base, struct nameidata *nd)
 {
 	struct dentry *dentry;
 	struct inode *inode;
@@ -1200,14 +1200,22 @@ out:
  * needs parent already locked. Doesn't follow mounts.
  * SMP-safe.
  */
-static struct dentry *lookup_hash(struct nameidata *nd)
+static int lookup_hash(struct nameidata *nd, struct qstr *name,
+		       struct path *path)
 {
 	int err;
 
 	err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC);
 	if (err)
-		return ERR_PTR(err);
-	return __lookup_hash(&nd->last, nd->path.dentry, nd);
+		return err;
+	path->mnt = nd->path.mnt;
+	path->dentry =  __lookup_hash(name, nd->path.dentry, nd);
+	if (IS_ERR(path->dentry)) {
+		err = PTR_ERR(path->dentry);
+		path->dentry = NULL;
+		path->mnt = NULL;
+	}
+	return err;
 }
 
 static int __lookup_one_len(const char *name, struct qstr *this,
@@ -1700,12 +1708,10 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	if (flag & O_EXCL)
 		nd.flags |= LOOKUP_EXCL;
 	mutex_lock(&dir->d_inode->i_mutex);
-	path.dentry = lookup_hash(&nd);
-	path.mnt = nd.path.mnt;
+	error = lookup_hash(&nd, &nd.last, &path);
 
 do_last:
-	error = PTR_ERR(path.dentry);
-	if (IS_ERR(path.dentry)) {
+	if (error) {
 		mutex_unlock(&dir->d_inode->i_mutex);
 		goto exit;
 	}
@@ -1851,8 +1857,7 @@ do_link:
 	}
 	dir = nd.path.dentry;
 	mutex_lock(&dir->d_inode->i_mutex);
-	path.dentry = lookup_hash(&nd);
-	path.mnt = nd.path.mnt;
+	error = lookup_hash(&nd, &nd.last, &path);
 	__putname(nd.last.name);
 	goto do_last;
 }
@@ -1886,7 +1891,8 @@ EXPORT_SYMBOL(filp_open);
  */
 struct dentry *lookup_create(struct nameidata *nd, int is_dir)
 {
-	struct dentry *dentry = ERR_PTR(-EEXIST);
+	struct path path = { .dentry = ERR_PTR(-EEXIST) } ;
+	int err;
 
 	mutex_lock_nested(&nd->path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	/*
@@ -1902,11 +1908,13 @@ struct dentry *lookup_create(struct nameidata *nd, int is_dir)
 	/*
 	 * Do the final lookup.
 	 */
-	dentry = lookup_hash(nd);
-	if (IS_ERR(dentry))
+	err = lookup_hash(nd, &nd->last, &path);
+	if (err) {
+		path.dentry = ERR_PTR(err);
 		goto fail;
+	}
 
-	if (dentry->d_inode)
+	if (path.dentry->d_inode)
 		goto eexist;
 	/*
 	 * Special case - lookup gave negative, but... we had foo/bar/
@@ -1915,15 +1923,17 @@ struct dentry *lookup_create(struct nameidata *nd, int is_dir)
 	 * been asking for (non-existent) directory. -ENOENT for you.
 	 */
 	if (unlikely(!is_dir && nd->last.name[nd->last.len])) {
-		dput(dentry);
-		dentry = ERR_PTR(-ENOENT);
+		path_put_conditional(&path, nd);
+		path.dentry = ERR_PTR(-ENOENT);
 	}
-	return dentry;
+	if (nd->path.mnt != path.mnt)
+		mntput(path.mnt);
+	return path.dentry;
 eexist:
-	dput(dentry);
-	dentry = ERR_PTR(-EEXIST);
+	path_put_conditional(&path, nd);
+	path.dentry = ERR_PTR(-EEXIST);
 fail:
-	return dentry;
+	return path.dentry;
 }
 EXPORT_SYMBOL_GPL(lookup_create);
 
@@ -2160,7 +2170,7 @@ static long do_rmdir(int dfd, const char __user *pathname)
 {
 	int error = 0;
 	char * name;
-	struct dentry *dentry;
+	struct path path;
 	struct nameidata nd;
 
 	error = user_path_parent(dfd, pathname, &nd, &name);
@@ -2182,21 +2192,20 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	nd.flags &= ~LOOKUP_PARENT;
 
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_hash(&nd);
-	error = PTR_ERR(dentry);
-	if (IS_ERR(dentry))
+	error = lookup_hash(&nd, &nd.last, &path);
+	if (error)
 		goto exit2;
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto exit3;
-	error = security_path_rmdir(&nd.path, dentry);
+	error = security_path_rmdir(&nd.path, path.dentry);
 	if (error)
 		goto exit4;
-	error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
+	error = vfs_rmdir(nd.path.dentry->d_inode, path.dentry);
 exit4:
 	mnt_drop_write(nd.path.mnt);
 exit3:
-	dput(dentry);
+	path_put_conditional(&path, &nd);
 exit2:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 exit1:
@@ -2251,7 +2260,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 {
 	int error;
 	char *name;
-	struct dentry *dentry;
+	struct path path;
 	struct nameidata nd;
 	struct inode *inode = NULL;
 
@@ -2266,26 +2275,25 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	nd.flags &= ~LOOKUP_PARENT;
 
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_hash(&nd);
-	error = PTR_ERR(dentry);
-	if (!IS_ERR(dentry)) {
+	error = lookup_hash(&nd, &nd.last, &path);
+	if (!error) {
 		/* Why not before? Because we want correct error value */
 		if (nd.last.name[nd.last.len])
 			goto slashes;
-		inode = dentry->d_inode;
+		inode = path.dentry->d_inode;
 		if (inode)
 			atomic_inc(&inode->i_count);
 		error = mnt_want_write(nd.path.mnt);
 		if (error)
 			goto exit2;
-		error = security_path_unlink(&nd.path, dentry);
+		error = security_path_unlink(&nd.path, path.dentry);
 		if (error)
 			goto exit3;
-		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+		error = vfs_unlink(nd.path.dentry->d_inode, path.dentry);
 exit3:
 		mnt_drop_write(nd.path.mnt);
 	exit2:
-		dput(dentry);
+		path_put_conditional(&path, &nd);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	if (inode)
@@ -2296,8 +2304,8 @@ exit1:
 	return error;
 
 slashes:
-	error = !dentry->d_inode ? -ENOENT :
-		S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
+	error = !path.dentry->d_inode ? -ENOENT :
+		S_ISDIR(path.dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
 	goto exit2;
 }
 
@@ -2637,7 +2645,7 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 		int, newdfd, const char __user *, newname)
 {
 	struct dentry *old_dir, *new_dir;
-	struct dentry *old_dentry, *new_dentry;
+	struct path old, new;
 	struct dentry *trap;
 	struct nameidata oldnd, newnd;
 	char *from;
@@ -2671,16 +2679,15 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 
 	trap = lock_rename(new_dir, old_dir);
 
-	old_dentry = lookup_hash(&oldnd);
-	error = PTR_ERR(old_dentry);
-	if (IS_ERR(old_dentry))
+	error = lookup_hash(&oldnd, &oldnd.last, &old);
+	if (error)
 		goto exit3;
 	/* source must exist */
 	error = -ENOENT;
-	if (!old_dentry->d_inode)
+	if (!old.dentry->d_inode)
 		goto exit4;
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!S_ISDIR(old_dentry->d_inode->i_mode)) {
+	if (!S_ISDIR(old.dentry->d_inode->i_mode)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit4;
@@ -2689,32 +2696,31 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	}
 	/* source should not be ancestor of target */
 	error = -EINVAL;
-	if (old_dentry == trap)
+	if (old.dentry == trap)
 		goto exit4;
-	new_dentry = lookup_hash(&newnd);
-	error = PTR_ERR(new_dentry);
-	if (IS_ERR(new_dentry))
+	error = lookup_hash(&newnd, &newnd.last, &new);
+	if (error)
 		goto exit4;
 	/* target should not be an ancestor of source */
 	error = -ENOTEMPTY;
-	if (new_dentry == trap)
+	if (new.dentry == trap)
 		goto exit5;
 
 	error = mnt_want_write(oldnd.path.mnt);
 	if (error)
 		goto exit5;
-	error = security_path_rename(&oldnd.path, old_dentry,
-				     &newnd.path, new_dentry);
+	error = security_path_rename(&oldnd.path, old.dentry,
+				     &newnd.path, new.dentry);
 	if (error)
 		goto exit6;
-	error = vfs_rename(old_dir->d_inode, old_dentry,
-				   new_dir->d_inode, new_dentry);
+	error = vfs_rename(old_dir->d_inode, old.dentry,
+				   new_dir->d_inode, new.dentry);
 exit6:
 	mnt_drop_write(oldnd.path.mnt);
 exit5:
-	dput(new_dentry);
+	path_put_conditional(&new, &newnd);
 exit4:
-	dput(old_dentry);
+	path_put_conditional(&old, &oldnd);
 exit3:
 	unlock_rename(new_dir, old_dir);
 exit2:
-- 
1.6.0.2

Re: [PATCH] VFS: Make lookup_hash() return a struct path

[James Morris]

On Wed, 17 Jun 2009, Jan Blunck wrote:

> This patch changes lookup_hash() into returning a struct path.
> 
> Signed-off-by: Jan Blunck <jblunck@suse.de>
> Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>

Reviewed-by: James Morris <jmorris@namei.org>


-- 
James Morris
<jmorris@namei.org>

[PATCH] VFS: Remove unnecessary micro-optimization in cached_lookup()

[Jan Blunck]

d_lookup() takes rename_lock which is a seq_lock.  This is so cheap
it's not worth calling lockless __d_lookup() first from
cache_lookup().  Rename cached_lookup() to cache_lookup() while we're
there.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/namei.c |   13 ++++---------
 1 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c0cd4cb..9b12363 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -404,15 +404,10 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd)
  * Internal lookup() using the new generic dcache.
  * SMP-safe
  */
-static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
+static struct dentry *cache_lookup(struct dentry *parent, struct qstr *name,
+				   struct nameidata *nd)
 {
-	struct dentry * dentry = __d_lookup(parent, name);
-
-	/* lockess __d_lookup may fail due to concurrent d_move() 
-	 * in some unrelated directory, so try with d_lookup
-	 */
-	if (!dentry)
-		dentry = d_lookup(parent, name);
+	struct dentry *dentry = d_lookup(parent, name);
 
 	if (dentry && dentry->d_op && dentry->d_op->d_revalidate)
 		dentry = do_revalidate(dentry, nd);
@@ -1172,7 +1167,7 @@ static struct dentry *__lookup_hash(struct qstr *name,
 			goto out;
 	}
 
-	dentry = cached_lookup(base, name, nd);
+	dentry = cache_lookup(base, name, nd);
 	if (!dentry) {
 		struct dentry *new;
 
-- 
1.6.0.2

[PATCH] VFS: Make real_lookup() return a struct path

[Jan Blunck]

This patch changes real_lookup() into returning a struct path.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/namei.c |   82 +++++++++++++++++++++++++++++++++++++----------------------
 1 files changed, 51 insertions(+), 31 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 9b12363..f40f42c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -462,10 +462,11 @@ ok:
  * make sure that nobody added the entry to the dcache in the meantime..
  * SMP-safe
  */
-static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
+static int real_lookup(struct nameidata *nd, struct qstr *name,
+		       struct path *path)
 {
-	struct dentry * result;
-	struct inode *dir = parent->d_inode;
+	struct inode *dir = nd->path.dentry->d_inode;
+	int res = 0;
 
 	mutex_lock(&dir->i_mutex);
 	/*
@@ -482,27 +483,36 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s
 	 *
 	 * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
 	 */
-	result = d_lookup(parent, name);
-	if (!result) {
+	path->dentry = d_lookup(nd->path.dentry, name);
+	path->mnt = nd->path.mnt;
+	if (!path->dentry) {
 		struct dentry *dentry;
 
 		/* Don't create child dentry for a dead directory. */
-		result = ERR_PTR(-ENOENT);
-		if (IS_DEADDIR(dir))
+		if (IS_DEADDIR(dir)) {
+			res = -ENOENT;
 			goto out_unlock;
+		}
 
-		dentry = d_alloc(parent, name);
-		result = ERR_PTR(-ENOMEM);
+		dentry = d_alloc(nd->path.dentry, name);
 		if (dentry) {
-			result = dir->i_op->lookup(dir, dentry, nd);
-			if (result)
+			path->dentry = dir->i_op->lookup(dir, dentry, nd);
+			if (path->dentry) {
 				dput(dentry);
-			else
-				result = dentry;
+				if (IS_ERR(path->dentry)) {
+					res = PTR_ERR(path->dentry);
+					path->dentry = NULL;
+					path->mnt = NULL;
+				}
+			} else
+				path->dentry = dentry;
+		} else {
+			res = -ENOMEM;
+			path->mnt = NULL;
 		}
 out_unlock:
 		mutex_unlock(&dir->i_mutex);
-		return result;
+		return res;
 	}
 
 	/*
@@ -510,12 +520,20 @@ out_unlock:
 	 * we waited on the semaphore. Need to revalidate.
 	 */
 	mutex_unlock(&dir->i_mutex);
-	if (result->d_op && result->d_op->d_revalidate) {
-		result = do_revalidate(result, nd);
-		if (!result)
-			result = ERR_PTR(-ENOENT);
+	if (path->dentry->d_op && path->dentry->d_op->d_revalidate) {
+		path->dentry = do_revalidate(path->dentry, nd);
+		if (!path->dentry) {
+			res = -ENOENT;
+			path->mnt = NULL;
+		}
+		if (IS_ERR(path->dentry)) {
+			res = PTR_ERR(path->dentry);
+			path->dentry = NULL;
+			path->mnt = NULL;
+		}
 	}
-	return result;
+
+	return res;
 }
 
 /*
@@ -781,35 +799,37 @@ static __always_inline void follow_dotdot(struct nameidata *nd)
 static int do_lookup(struct nameidata *nd, struct qstr *name,
 		     struct path *path)
 {
-	struct vfsmount *mnt = nd->path.mnt;
-	struct dentry *dentry = __d_lookup(nd->path.dentry, name);
+	int err;
 
-	if (!dentry)
+	path->dentry = __d_lookup(nd->path.dentry, name);
+	path->mnt = nd->path.mnt;
+	if (!path->dentry)
 		goto need_lookup;
-	if (dentry->d_op && dentry->d_op->d_revalidate)
+	if (path->dentry->d_op && path->dentry->d_op->d_revalidate)
 		goto need_revalidate;
+
 done:
-	path->mnt = mnt;
-	path->dentry = dentry;
 	__follow_mount(path);
 	return 0;
 
 need_lookup:
-	dentry = real_lookup(nd->path.dentry, name, nd);
-	if (IS_ERR(dentry))
+	err = real_lookup(nd, name, path);
+	if (err)
 		goto fail;
 	goto done;
 
 need_revalidate:
-	dentry = do_revalidate(dentry, nd);
-	if (!dentry)
+	path->dentry = do_revalidate(path->dentry, nd);
+	if (!path->dentry)
 		goto need_lookup;
-	if (IS_ERR(dentry))
+	if (IS_ERR(path->dentry)) {
+		err = PTR_ERR(path->dentry);
 		goto fail;
+	}
 	goto done;
 
 fail:
-	return PTR_ERR(dentry);
+	return err;
 }
 
 /*
-- 
1.6.0.2

Re: [PATCH] VFS: Make real_lookup() return a struct path

[James Morris]

On Wed, 17 Jun 2009, Jan Blunck wrote:

> This patch changes real_lookup() into returning a struct path.
> 
> Signed-off-by: Jan Blunck <jblunck@suse.de>
> Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>

Reviewed-by: James Morris <jmorris@namei.org>

-- 
James Morris
<jmorris@namei.org>

[PATCH] VFS: Introduce dput() variant that maintains a kill-list

[Jan Blunck]

This patch introduces a new variant of dput(). This becomes necessary to
prevent a recursive call to dput() from the union mount code.

  void __dput(struct dentry *dentry, struct list_head *list, int greedy);
  struct dentry *__d_kill(struct dentry *dentry, struct list_head *list,
  	 		  int greedy);

__dput() works mostly like the original dput() did. The main difference is
that if it the greedy argument is zero it will put the parent on a special
list instead of trying to get rid of it directly.

Therefore the union mount code can safely call __dput() when it wants to get
rid of underlying dentry references during a dput(). After calling __dput()
or __d_kill() the caller must make sure that __d_kill_final() is called on all
dentries on the kill list. __d_kill_final() is actually doing the
dentry_iput() and is also dereferencing the parent.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/dcache.c |  115 +++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 105 insertions(+), 10 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 191c488..7ab322e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -157,14 +157,19 @@ static void dentry_lru_del_init(struct dentry *dentry)
 }
 
 /**
- * d_kill - kill dentry and return parent
+ * __d_kill - kill dentry and return parent
  * @dentry: dentry to kill
+ * @list: kill list
+ * @greedy: return parent instead of putting it on the kill list
  *
  * The dentry must already be unhashed and removed from the LRU.
  *
- * If this is the root of the dentry tree, return NULL.
+ * If this is the root of the dentry tree, return NULL. If greedy is zero, we
+ * put the parent of this dentry on the kill list instead. The callers must
+ * make sure that __d_kill_final() is called on all dentries on the kill list.
  */
-static struct dentry *d_kill(struct dentry *dentry)
+static struct dentry *__d_kill(struct dentry *dentry, struct list_head *list,
+			       int greedy)
 	__releases(dentry->d_lock)
 	__releases(dcache_lock)
 {
@@ -172,6 +177,20 @@ static struct dentry *d_kill(struct dentry *dentry)
 
 	list_del(&dentry->d_u.d_child);
 	dentry_stat.nr_dentry--;	/* For d_free, below */
+
+	/*
+	 * If we are not greedy we just put this on a list for later processing
+	 * (follow up to parent, releasing of inode and freeing dentry memory).
+	 */
+	if (!greedy) {
+		list_del_init(&dentry->d_alias);
+		/* at this point nobody can reach this dentry */
+		list_add(&dentry->d_lru, list);
+		spin_unlock(&dentry->d_lock);
+		spin_unlock(&dcache_lock);
+		return NULL;
+	}
+
 	/*drops the locks, at that point nobody can reach this dentry */
 	dentry_iput(dentry);
 	if (IS_ROOT(dentry))
@@ -182,6 +201,54 @@ static struct dentry *d_kill(struct dentry *dentry)
 	return parent;
 }
 
+void __dput(struct dentry *, struct list_head *, int);
+
+static void __d_kill_final(struct dentry *dentry, struct list_head *list)
+{
+	struct dentry *parent;
+	struct inode *inode = dentry->d_inode;
+
+	if (inode) {
+		dentry->d_inode = NULL;
+		if (!inode->i_nlink)
+			fsnotify_inoderemove(inode);
+		if (dentry->d_op && dentry->d_op->d_iput)
+			dentry->d_op->d_iput(dentry, inode);
+		else
+			iput(inode);
+	}
+
+	if (IS_ROOT(dentry))
+		parent = NULL;
+	else
+		parent = dentry->d_parent;
+	d_free(dentry);
+	__dput(parent, list, 1);
+}
+
+/**
+ * d_kill - kill dentry and return parent
+ * @dentry: dentry to kill
+ *
+ * The dentry must already be unhashed and removed from the LRU.
+ *
+ * If this is the root of the dentry tree, return NULL.
+ */
+static struct dentry *d_kill(struct dentry *dentry)
+{
+	LIST_HEAD(mortuary);
+	struct dentry *parent;
+
+	parent = __d_kill(dentry, &mortuary, 1);
+	while (!list_empty(&mortuary)) {
+		dentry = list_entry(mortuary.next, struct dentry, d_lru);
+		list_del(&dentry->d_lru);
+		__d_kill_final(dentry, &mortuary);
+	}
+
+	return parent;
+}
+
 /* 
  * This is dput
  *
@@ -199,19 +266,24 @@ static struct dentry *d_kill(struct dentry *dentry)
  * Real recursion would eat up our stack space.
  */
 
-/*
- * dput - release a dentry
- * @dentry: dentry to release 
+/**
+ * __dput - release a dentry
+ * @dentry: dentry to release
+ * @list: kill list argument for __d_kill()
+ * @greedy: greedy argument for __d_kill()
  *
  * Release a dentry. This will drop the usage count and if appropriate
  * call the dentry unlink method as well as removing it from the queues and
  * releasing its resources. If the parent dentries were scheduled for release
- * they too may now get deleted.
+ * they too may now get deleted if @greedy is not zero. Otherwise parent is
+ * added to the kill list. The callers must make sure that __d_kill_final() is
+ * called on all dentries on the kill list.
+ *
+ * You probably want to use dput() instead.
  *
  * no dcache lock, please.
  */
-
-void dput(struct dentry *dentry)
+void __dput(struct dentry *dentry, struct list_head *list, int greedy)
 {
 	if (!dentry)
 		return;
@@ -252,12 +324,35 @@ unhash_it:
 kill_it:
 	/* if dentry was on the d_lru list delete it from there */
 	dentry_lru_del(dentry);
-	dentry = d_kill(dentry);
+	dentry = __d_kill(dentry, list, greedy);
 	if (dentry)
 		goto repeat;
 }
 
 /**
+ * dput - release a dentry
+ * @dentry: dentry to release
+ *
+ * Release a dentry. This will drop the usage count and if appropriate
+ * call the dentry unlink method as well as removing it from the queues and
+ * releasing its resources. If the parent dentries were scheduled for release
+ * they too may now get deleted.
+ *
+ * no dcache lock, please.
+ */
+void dput(struct dentry *dentry)
+{
+	LIST_HEAD(mortuary);
+
+	__dput(dentry, &mortuary, 1);
+	while (!list_empty(&mortuary)) {
+		dentry = list_entry(mortuary.next, struct dentry, d_lru);
+		list_del(&dentry->d_lru);
+		__d_kill_final(dentry, &mortuary);
+	}
+}
+
+/**
  * d_invalidate - invalidate a dentry
  * @dentry: dentry to invalidate
  *
-- 
1.6.0.2

Re: [PATCH] VFS: Introduce dput() variant that maintains a kill-list

[James Morris]

On Wed, 17 Jun 2009, Jan Blunck wrote:

> This patch introduces a new variant of dput(). This becomes necessary to
> prevent a recursive call to dput() from the union mount code.

Reviewed-by: James Morris <jmorris@namei.org>

-- 
James Morris <jmorris@namei.org>