1 files changed, 255 insertions, 43 deletions

diff --git a/fs/namei.c b/fs/namei.c
index 8b61d103a8a7..409a441ba2ae 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -508,56 +508,78 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 {
 	struct fs_struct *fs = current->fs;
 	struct dentry *parent = nd->path.dentry;
-	int want_root = 0;
 
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
-		want_root = 1;
-		spin_lock(&fs->lock);
-		if (nd->root.mnt != fs->root.mnt ||
-				nd->root.dentry != fs->root.dentry)
-			goto err_root;
-	}
-	spin_lock(&parent->d_lock);
+
+	/*
+	 * Get a reference to the parent first: we're
+	 * going to make "path_put(nd->path)" valid in
+	 * non-RCU context for "terminate_walk()".
+	 *
+	 * If this doesn't work, return immediately with
+	 * RCU walking still active (and then we will do
+	 * the RCU walk cleanup in terminate_walk()).
+	 */
+	if (!lockref_get_not_dead(&parent->d_lockref))
+		return -ECHILD;
+
+	/*
+	 * After the mntget(), we terminate_walk() will do
+	 * the right thing for non-RCU mode, and all our
+	 * subsequent exit cases should unlock_rcu_walk()
+	 * before returning.
+	 */
+	mntget(nd->path.mnt);
+	nd->flags &= ~LOOKUP_RCU;
+
+	/*
+	 * For a negative lookup, the lookup sequence point is the parents
+	 * sequence point, and it only needs to revalidate the parent dentry.
+	 *
+	 * For a positive lookup, we need to move both the parent and the
+	 * dentry from the RCU domain to be properly refcounted. And the
+	 * sequence number in the dentry validates *both* dentry counters,
+	 * since we checked the sequence number of the parent after we got
+	 * the child sequence number. So we know the parent must still
+	 * be valid if the child sequence number is still valid.
+	 */
 	if (!dentry) {
-		if (!__d_rcu_to_refcount(parent, nd->seq))
-			goto err_parent;
+		if (read_seqcount_retry(&parent->d_seq, nd->seq))
+			goto out;
 		BUG_ON(nd->inode != parent->d_inode);
 	} else {
-		if (dentry->d_parent != parent)
-			goto err_parent;
-		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-		if (!__d_rcu_to_refcount(dentry, nd->seq))
-			goto err_child;
-		/*
-		 * If the sequence check on the child dentry passed, then
-		 * the child has not been removed from its parent. This
-		 * means the parent dentry must be valid and able to take
-		 * a reference at this point.
-		 */
-		BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
-		BUG_ON(!parent->d_count);
-		parent->d_count++;
-		spin_unlock(&dentry->d_lock);
+		if (!lockref_get_not_dead(&dentry->d_lockref))
+			goto out;
+		if (read_seqcount_retry(&dentry->d_seq, nd->seq))
+			goto drop_dentry;
 	}
-	spin_unlock(&parent->d_lock);
-	if (want_root) {
+
+	/*
+	 * Sequence counts matched. Now make sure that the root is
+	 * still valid and get it if required.
+	 */
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		spin_lock(&fs->lock);
+		if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry)
+			goto unlock_and_drop_dentry;
 		path_get(&nd->root);
 		spin_unlock(&fs->lock);
 	}
-	mntget(nd->path.mnt);
 
 	unlock_rcu_walk();
-	nd->flags &= ~LOOKUP_RCU;
 	return 0;
 
-err_child:
-	spin_unlock(&dentry->d_lock);
-err_parent:
-	spin_unlock(&parent->d_lock);
-err_root:
-	if (want_root)
-		spin_unlock(&fs->lock);
+unlock_and_drop_dentry:
+	spin_unlock(&fs->lock);
+drop_dentry:
+	unlock_rcu_walk();
+	dput(dentry);
+	goto drop_root_mnt;
+out:
+	unlock_rcu_walk();
+drop_root_mnt:
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
 	return -ECHILD;
 }
 
@@ -585,14 +607,16 @@ static int complete_walk(struct nameidata *nd)
 		nd->flags &= ~LOOKUP_RCU;
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
-		spin_lock(&dentry->d_lock);
-		if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
-			spin_unlock(&dentry->d_lock);
+
+		if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
 			unlock_rcu_walk();
 			return -ECHILD;
 		}
-		BUG_ON(nd->inode != dentry->d_inode);
-		spin_unlock(&dentry->d_lock);
+		if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
+			unlock_rcu_walk();
+			dput(dentry);
+			return -ECHILD;
+		}
 		mntget(nd->path.mnt);
 		unlock_rcu_walk();
 	}
@@ -2184,6 +2208,194 @@ user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
 	return s;
 }
 
+/**
+ * mountpoint_last - look up last component for umount
+ * @nd:   pathwalk nameidata - currently pointing at parent directory of "last"
+ * @path: pointer to container for result
+ *
+ * This is a special lookup_last function just for umount. In this case, we
+ * need to resolve the path without doing any revalidation.
+ *
+ * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
+ * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
+ * in almost all cases, this lookup will be served out of the dcache. The only
+ * cases where it won't are if nd->last refers to a symlink or the path is
+ * bogus and it doesn't exist.
+ *
+ * Returns:
+ * -error: if there was an error during lookup. This includes -ENOENT if the
+ *         lookup found a negative dentry. The nd->path reference will also be
+ *         put in this case.
+ *
+ * 0:      if we successfully resolved nd->path and found it to not to be a
+ *         symlink that needs to be followed. "path" will also be populated.
+ *         The nd->path reference will also be put.
+ *
+ * 1:      if we successfully resolved nd->last and found it to be a symlink
+ *         that needs to be followed. "path" will be populated with the path
+ *         to the link, and nd->path will *not* be put.
+ */
+static int
+mountpoint_last(struct nameidata *nd, struct path *path)
+{
+	int error = 0;
+	struct dentry *dentry;
+	struct dentry *dir = nd->path.dentry;
+
+	/* If we're in rcuwalk, drop out of it to handle last component */
+	if (nd->flags & LOOKUP_RCU) {
+		if (unlazy_walk(nd, NULL)) {
+			error = -ECHILD;
+			goto out;
+		}
+	}
+
+	nd->flags &= ~LOOKUP_PARENT;
+
+	if (unlikely(nd->last_type != LAST_NORM)) {
+		error = handle_dots(nd, nd->last_type);
+		if (error)
+			goto out;
+		dentry = dget(nd->path.dentry);
+		goto done;
+	}
+
+	mutex_lock(&dir->d_inode->i_mutex);
+	dentry = d_lookup(dir, &nd->last);
+	if (!dentry) {
+		/*
+		 * No cached dentry. Mounted dentries are pinned in the cache,
+		 * so that means that this dentry is probably a symlink or the
+		 * path doesn't actually point to a mounted dentry.
+		 */
+		dentry = d_alloc(dir, &nd->last);
+		if (!dentry) {
+			error = -ENOMEM;
+			goto out;
+		}
+		dentry = lookup_real(dir->d_inode, dentry, nd->flags);
+		error = PTR_ERR(dentry);
+		if (IS_ERR(dentry))
+			goto out;
+	}
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+done:
+	if (!dentry->d_inode) {
+		error = -ENOENT;
+		dput(dentry);
+		goto out;
+	}
+	path->dentry = dentry;
+	path->mnt = mntget(nd->path.mnt);
+	if (should_follow_link(dentry->d_inode, nd->flags & LOOKUP_FOLLOW))
+		return 1;
+	follow_mount(path);
+	error = 0;
+out:
+	terminate_walk(nd);
+	return error;
+}
+
+/**
+ * path_mountpoint - look up a path to be umounted
+ * @dfd:	directory file descriptor to start walk from
+ * @name:	full pathname to walk
+ * @flags:	lookup flags
+ *
+ * Look up the given name, but don't attempt to revalidate the last component.
+ * Returns 0 and "path" will be valid on success; Retuns error otherwise.
+ */
+static int
+path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags)
+{
+	struct file *base = NULL;
+	struct nameidata nd;
+	int err;
+
+	err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
+	if (unlikely(err))
+		return err;
+
+	current->total_link_count = 0;
+	err = link_path_walk(name, &nd);
+	if (err)
+		goto out;
+
+	err = mountpoint_last(&nd, path);
+	while (err > 0) {
+		void *cookie;
+		struct path link = *path;
+		err = may_follow_link(&link, &nd);
+		if (unlikely(err))
+			break;
+		nd.flags |= LOOKUP_PARENT;
+		err = follow_link(&link, &nd, &cookie);
+		if (err)
+			break;
+		err = mountpoint_last(&nd, path);
+		put_link(&nd, &link, cookie);
+	}
+out:
+	if (base)
+		fput(base);
+
+	if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
+		path_put(&nd.root);
+
+	return err;
+}
+
+static int
+filename_mountpoint(int dfd, struct filename *s, struct path *path,
+			unsigned int flags)
+{
+	int error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU);
+	if (unlikely(error == -ECHILD))
+		error = path_mountpoint(dfd, s->name, path, flags);
+	if (unlikely(error == -ESTALE))
+		error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL);
+	if (likely(!error))
+		audit_inode(s, path->dentry, 0);
+	return error;
+}
+
+/**
+ * user_path_mountpoint_at - lookup a path from userland in order to umount it
+ * @dfd:	directory file descriptor
+ * @name:	pathname from userland
+ * @flags:	lookup flags
+ * @path:	pointer to container to hold result
+ *
+ * A umount is a special case for path walking. We're not actually interested
+ * in the inode in this situation, and ESTALE errors can be a problem. We
+ * simply want track down the dentry and vfsmount attached at the mountpoint
+ * and avoid revalidating the last component.
+ *
+ * Returns 0 and populates "path" on success.
+ */
+int
+user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags,
+			struct path *path)
+{
+	struct filename *s = getname(name);
+	int error;
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+	error = filename_mountpoint(dfd, s, path, flags);
+	putname(s);
+	return error;
+}
+
+int
+kern_path_mountpoint(int dfd, const char *name, struct path *path,
+			unsigned int flags)
+{
+	struct filename s = {.name = name};
+	return filename_mountpoint(dfd, &s, path, flags);
+}
+EXPORT_SYMBOL(kern_path_mountpoint);
+
 /*
  * It's inline, so penalty for filesystems that don't use sticky bit is
  * minimal.
@@ -3327,7 +3539,7 @@ void dentry_unhash(struct dentry *dentry)
 {
 	shrink_dcache_parent(dentry);
 	spin_lock(&dentry->d_lock);
-	if (dentry->d_count == 1)
+	if (dentry->d_lockref.count == 1)
 		__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
 }