ksmbd: fix racy issue from using ->d_parent and ->d_name

Al pointed out that ksmbd has racy issue from using ->d_parent and ->d_name
in ksmbd_vfs_unlink and smb2_vfs_rename(). and use new lock_rename_child()
to lock stable parent while underlying rename racy.
Introduce vfs_path_parent_lookup helper to avoid out of share access and
export vfs functions like the following ones to use
vfs_path_parent_lookup().
 - rename __lookup_hash() to lookup_one_qstr_excl().
 - export lookup_one_qstr_excl().
 - export getname_kernel() and putname().

vfs_path_parent_lookup() is used for parent lookup of destination file
using absolute pathname given from FILE_RENAME_INFORMATION request.
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>

fs/ksmbd/smb2pdu.c

@@ -2408,7 +2408,7 @@ static int smb2_creat(struct ksmbd_work *work, struct path *path, char *name,
 			return rc;
 	}
 
-	rc = ksmbd_vfs_kern_path(work, name, 0, path, 0);
+	rc = ksmbd_vfs_kern_path_locked(work, name, 0, path, 0);
 	if (rc) {
 		pr_err("cannot get linux path (%s), err = %d\n",
 		       name, rc);
@@ -2699,8 +2699,10 @@ int smb2_open(struct ksmbd_work *work)
 		goto err_out1;
 	}
 
-	rc = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, 1);
+	rc = ksmbd_vfs_kern_path_locked(work, name, LOOKUP_NO_SYMLINKS, &path, 1);
 	if (!rc) {
+		file_present = true;
+
 		if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) {
 			/*
 			 * If file exists with under flags, return access
@@ -2709,7 +2711,6 @@ int smb2_open(struct ksmbd_work *work)
 			if (req->CreateDisposition == FILE_OVERWRITE_IF_LE ||
 			    req->CreateDisposition == FILE_OPEN_IF_LE) {
 				rc = -EACCES;
-				path_put(&path);
 				goto err_out;
 			}
 
@@ -2717,26 +2718,23 @@ int smb2_open(struct ksmbd_work *work)
 				ksmbd_debug(SMB,
 					    "User does not have write permission\n");
 				rc = -EACCES;
-				path_put(&path);
 				goto err_out;
 			}
 		} else if (d_is_symlink(path.dentry)) {
 			rc = -EACCES;
-			path_put(&path);
 			goto err_out;
 		}
-	}
 
-	if (rc) {
+		file_present = true;
+		idmap = mnt_idmap(path.mnt);
+	} else {
 		if (rc != -ENOENT)
 			goto err_out;
 		ksmbd_debug(SMB, "can not get linux path for %s, rc = %d\n",
 			    name, rc);
 		rc = 0;
-	} else {
-		file_present = true;
-		idmap = mnt_idmap(path.mnt);
 	}
+
 	if (stream_name) {
 		if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) {
 			if (s_type == DATA_STREAM) {
@@ -2864,8 +2862,9 @@ int smb2_open(struct ksmbd_work *work)
 
 			if ((daccess & FILE_DELETE_LE) ||
 			    (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE)) {
-				rc = ksmbd_vfs_may_delete(idmap,
-							  path.dentry);
+				rc = inode_permission(idmap,
+						      d_inode(path.dentry->d_parent),
+						      MAY_EXEC | MAY_WRITE);
 				if (rc)
 					goto err_out;
 			}
@@ -3236,10 +3235,13 @@ int smb2_open(struct ksmbd_work *work)
 	}
 
 err_out:
-	if (file_present || created)
-		path_put(&path);
+	if (file_present || created) {
+		inode_unlock(d_inode(path.dentry->d_parent));
+		dput(path.dentry);
+	}
 	ksmbd_revert_fsids(work);
 err_out1:
+
 	if (rc) {
 		if (rc == -EINVAL)
 			rsp->hdr.Status = STATUS_INVALID_PARAMETER;
@@ -5390,44 +5392,19 @@ int smb2_echo(struct ksmbd_work *work)
 
 static int smb2_rename(struct ksmbd_work *work,
 		       struct ksmbd_file *fp,
-		       struct mnt_idmap *idmap,
 		       struct smb2_file_rename_info *file_info,
 		       struct nls_table *local_nls)
 {
 	struct ksmbd_share_config *share = fp->tcon->share_conf;
-	char *new_name = NULL, *abs_oldname = NULL, *old_name = NULL;
-	char *pathname = NULL;
-	struct path path;
-	bool file_present = true;
-	int rc;
+	char *new_name = NULL;
+	int rc, flags = 0;
 
 	ksmbd_debug(SMB, "setting FILE_RENAME_INFO\n");
-	pathname = kmalloc(PATH_MAX, GFP_KERNEL);
-	if (!pathname)
-		return -ENOMEM;
-
-	abs_oldname = file_path(fp->filp, pathname, PATH_MAX);
-	if (IS_ERR(abs_oldname)) {
-		rc = -EINVAL;
-		goto out;
-	}
-	old_name = strrchr(abs_oldname, '/');
-	if (old_name && old_name[1] != '\0') {
-		old_name++;
-	} else {
-		ksmbd_debug(SMB, "can't get last component in path %s\n",
-			    abs_oldname);
-		rc = -ENOENT;
-		goto out;
-	}
-
 	new_name = smb2_get_name(file_info->FileName,
 				 le32_to_cpu(file_info->FileNameLength),
 				 local_nls);
-	if (IS_ERR(new_name)) {
-		rc = PTR_ERR(new_name);
-		goto out;
-	}
+	if (IS_ERR(new_name))
+		return PTR_ERR(new_name);
 
 	if (strchr(new_name, ':')) {
 		int s_type;
@@ -5453,7 +5430,7 @@ static int smb2_rename(struct ksmbd_work *work,
 		if (rc)
 			goto out;
 
-		rc = ksmbd_vfs_setxattr(idmap,
+		rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp),
 					fp->filp->f_path.dentry,
 					xattr_stream_name,
 					NULL, 0, 0);
@@ -5468,47 +5445,18 @@ static int smb2_rename(struct ksmbd_work *work,
 	}
 
 	ksmbd_debug(SMB, "new name %s\n", new_name);
-	rc = ksmbd_vfs_kern_path(work, new_name, LOOKUP_NO_SYMLINKS, &path, 1);
-	if (rc) {
-		if (rc != -ENOENT)
-			goto out;
-		file_present = false;
-	} else {
-		path_put(&path);
-	}
-
 	if (ksmbd_share_veto_filename(share, new_name)) {
 		rc = -ENOENT;
 		ksmbd_debug(SMB, "Can't rename vetoed file: %s\n", new_name);
 		goto out;
 	}
 
-	if (file_info->ReplaceIfExists) {
-		if (file_present) {
-			rc = ksmbd_vfs_remove_file(work, new_name);
-			if (rc) {
-				if (rc != -ENOTEMPTY)
-					rc = -EINVAL;
-				ksmbd_debug(SMB, "cannot delete %s, rc %d\n",
-					    new_name, rc);
-				goto out;
-			}
-		}
-	} else {
-		if (file_present &&
-		    strncmp(old_name, path.dentry->d_name.name, strlen(old_name))) {
-			rc = -EEXIST;
-			ksmbd_debug(SMB,
-				    "cannot rename already existing file\n");
-			goto out;
-		}
-	}
+	if (!file_info->ReplaceIfExists)
+		flags = RENAME_NOREPLACE;
 
-	rc = ksmbd_vfs_fp_rename(work, fp, new_name);
+	rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags);
 out:
-	kfree(pathname);
-	if (!IS_ERR(new_name))
-		kfree(new_name);
+	kfree(new_name);
 	return rc;
 }
 
@@ -5548,18 +5496,17 @@ static int smb2_create_link(struct ksmbd_work *work,
 	}
 
 	ksmbd_debug(SMB, "target name is %s\n", target_name);
-	rc = ksmbd_vfs_kern_path(work, link_name, LOOKUP_NO_SYMLINKS, &path, 0);
+	rc = ksmbd_vfs_kern_path_locked(work, link_name, LOOKUP_NO_SYMLINKS,
+					&path, 0);
 	if (rc) {
 		if (rc != -ENOENT)
 			goto out;
 		file_present = false;
-	} else {
-		path_put(&path);
 	}
 
 	if (file_info->ReplaceIfExists) {
 		if (file_present) {
-			rc = ksmbd_vfs_remove_file(work, link_name);
+			rc = ksmbd_vfs_remove_file(work, &path);
 			if (rc) {
 				rc = -EINVAL;
 				ksmbd_debug(SMB, "cannot delete %s\n",
@@ -5579,6 +5526,10 @@ static int smb2_create_link(struct ksmbd_work *work,
 	if (rc)
 		rc = -EINVAL;
 out:
+	if (file_present) {
+		inode_unlock(d_inode(path.dentry->d_parent));
+		path_put(&path);
+	}
 	if (!IS_ERR(link_name))
 		kfree(link_name);
 	kfree(pathname);
@@ -5756,12 +5707,6 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp,
 			   struct smb2_file_rename_info *rename_info,
 			   unsigned int buf_len)
 {
-	struct mnt_idmap *idmap;
-	struct ksmbd_file *parent_fp;
-	struct dentry *parent;
-	struct dentry *dentry = fp->filp->f_path.dentry;
-	int ret;
-
 	if (!(fp->daccess & FILE_DELETE_LE)) {
 		pr_err("no right to delete : 0x%x\n", fp->daccess);
 		return -EACCES;
@@ -5771,32 +5716,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp,
 			le32_to_cpu(rename_info->FileNameLength))
 		return -EINVAL;
 
-	idmap = file_mnt_idmap(fp->filp);
-	if (ksmbd_stream_fd(fp))
-		goto next;
-
-	parent = dget_parent(dentry);
-	ret = ksmbd_vfs_lock_parent(idmap, parent, dentry);
-	if (ret) {
-		dput(parent);
-		return ret;
-	}
-
-	parent_fp = ksmbd_lookup_fd_inode(d_inode(parent));
-	inode_unlock(d_inode(parent));
-	dput(parent);
+	if (!le32_to_cpu(rename_info->FileNameLength))
+		return -EINVAL;
 
-	if (parent_fp) {
-		if (parent_fp->daccess & FILE_DELETE_LE) {
-			pr_err("parent dir is opened with delete access\n");
-			ksmbd_fd_put(work, parent_fp);
-			return -ESHARE;
-		}
-		ksmbd_fd_put(work, parent_fp);
-	}
-next:
-	return smb2_rename(work, fp, idmap, rename_info,
-			   work->conn->local_nls);
+	return smb2_rename(work, fp, rename_info, work->conn->local_nls);
 }
 
 static int set_file_disposition_info(struct ksmbd_file *fp,

fs/ksmbd/vfs.h

@@ -71,9 +71,7 @@ struct ksmbd_kstat {
 	__le32			file_attributes;
 };
 
-int ksmbd_vfs_lock_parent(struct mnt_idmap *idmap, struct dentry *parent,
-			  struct dentry *child);
-int ksmbd_vfs_may_delete(struct mnt_idmap *idmap, struct dentry *dentry);
+int ksmbd_vfs_lock_parent(struct dentry *parent, struct dentry *child);
 int ksmbd_vfs_query_maximal_access(struct mnt_idmap *idmap,
 				   struct dentry *dentry, __le32 *daccess);
 int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode);
@@ -84,12 +82,12 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
 		    char *buf, size_t count, loff_t *pos, bool sync,
 		    ssize_t *written);
 int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id);
-int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name);
+int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path);
 int ksmbd_vfs_link(struct ksmbd_work *work,
 		   const char *oldname, const char *newname);
 int ksmbd_vfs_getattr(const struct path *path, struct kstat *stat);
-int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp,
-			char *newname);
+int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path,
+		     char *newname, int flags);
 int ksmbd_vfs_truncate(struct ksmbd_work *work,
 		       struct ksmbd_file *fp, loff_t size);
 struct srv_copychunk;
@@ -116,9 +114,9 @@ int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name,
 				size_t *xattr_stream_name_size, int s_type);
 int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap,
 			   struct dentry *dentry, char *attr_name);
-int ksmbd_vfs_kern_path(struct ksmbd_work *work,
-			char *name, unsigned int flags, struct path *path,
-			bool caseless);
+int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name,
+			       unsigned int flags, struct path *path,
+			       bool caseless);
 struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
 					  const char *name,
 					  unsigned int flags,
@@ -131,8 +129,7 @@ struct file_allocated_range_buffer;
 int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
 			 struct file_allocated_range_buffer *ranges,
 			 unsigned int in_count, unsigned int *out_count);
-int ksmbd_vfs_unlink(struct mnt_idmap *idmap, struct dentry *dir,
-		     struct dentry *dentry);
+int ksmbd_vfs_unlink(struct file *filp);
 void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat);
 int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work,
 				struct mnt_idmap *idmap,

fs/ksmbd/vfs_cache.c

@@ -244,7 +244,6 @@ void ksmbd_release_inode_hash(void)
 
 static void __ksmbd_inode_close(struct ksmbd_file *fp)
 {
-	struct dentry *dir, *dentry;
 	struct ksmbd_inode *ci = fp->f_ci;
 	int err;
 	struct file *filp;
@@ -263,11 +262,9 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp)
 	if (atomic_dec_and_test(&ci->m_count)) {
 		write_lock(&ci->m_lock);
 		if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) {
-			dentry = filp->f_path.dentry;
-			dir = dentry->d_parent;
 			ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING);
 			write_unlock(&ci->m_lock);
-			ksmbd_vfs_unlink(file_mnt_idmap(filp), dir, dentry);
+			ksmbd_vfs_unlink(filp);
 			write_lock(&ci->m_lock);
 		}
 		write_unlock(&ci->m_lock);

fs/namei.c

@@ -254,6 +254,7 @@ getname_kernel(const char * filename)
 
 	return result;
 }
+EXPORT_SYMBOL(getname_kernel);
 
 void putname(struct filename *name)
 {
@@ -271,6 +272,7 @@ void putname(struct filename *name)
 	} else
 		__putname(name);
 }
+EXPORT_SYMBOL(putname);
 
 /**
  * check_acl - perform ACL permission checking
@@ -1581,8 +1583,9 @@ static struct dentry *lookup_dcache(const struct qstr *name,
  * when directory is guaranteed to have no in-lookup children
  * at all.
  */
-static struct dentry *__lookup_hash(const struct qstr *name,
-		struct dentry *base, unsigned int flags)
+struct dentry *lookup_one_qstr_excl(const struct qstr *name,
+				    struct dentry *base,
+				    unsigned int flags)
 {
 	struct dentry *dentry = lookup_dcache(name, base, flags);
 	struct dentry *old;
@@ -1606,6 +1609,7 @@ static struct dentry *__lookup_hash(const struct qstr *name,
 	}
 	return dentry;
 }
+EXPORT_SYMBOL(lookup_one_qstr_excl);
 
 static struct dentry *lookup_fast(struct nameidata *nd)
 {
@@ -2532,16 +2536,17 @@ static int path_parentat(struct nameidata *nd, unsigned flags,
 }
 
 /* Note: this does not consume "name" */
-static int filename_parentat(int dfd, struct filename *name,
-			     unsigned int flags, struct path *parent,
-			     struct qstr *last, int *type)
+static int __filename_parentat(int dfd, struct filename *name,
+			       unsigned int flags, struct path *parent,
+			       struct qstr *last, int *type,
+			       const struct path *root)
 {
 	int retval;
 	struct nameidata nd;
 
 	if (IS_ERR(name))
 		return PTR_ERR(name);
-	set_nameidata(&nd, dfd, name, NULL);
+	set_nameidata(&nd, dfd, name, root);
 	retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
 	if (unlikely(retval == -ECHILD))
 		retval = path_parentat(&nd, flags, parent);
@@ -2556,6 +2561,13 @@ static int filename_parentat(int dfd, struct filename *name,
 	return retval;
 }
 
+static int filename_parentat(int dfd, struct filename *name,
+			     unsigned int flags, struct path *parent,
+			     struct qstr *last, int *type)
+{
+	return __filename_parentat(dfd, name, flags, parent, last, type, NULL);
+}
+
 /* does lookup, returns the object with parent locked */
 static struct dentry *__kern_path_locked(struct filename *name, struct path *path)
 {
@@ -2571,7 +2583,7 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat
 		return ERR_PTR(-EINVAL);
 	}
 	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
-	d = __lookup_hash(&last, path->dentry, 0);
+	d = lookup_one_qstr_excl(&last, path->dentry, 0);
 	if (IS_ERR(d)) {
 		inode_unlock(path->dentry->d_inode);
 		path_put(path);
@@ -2599,6 +2611,24 @@ int kern_path(const char *name, unsigned int flags, struct path *path)
 }
 EXPORT_SYMBOL(kern_path);
 
+/**
+ * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair
+ * @filename: filename structure
+ * @flags: lookup flags
+ * @parent: pointer to struct path to fill
+ * @last: last component
+ * @type: type of the last component
+ * @root: pointer to struct path of the base directory
+ */
+int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
+			   struct path *parent, struct qstr *last, int *type,
+			   const struct path *root)
+{
+	return  __filename_parentat(AT_FDCWD, filename, flags, parent, last,
+				    type, root);
+}
+EXPORT_SYMBOL(vfs_path_parent_lookup);
+
 /**
  * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
  * @dentry:  pointer to dentry of the base directory
@@ -3852,7 +3882,8 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	if (last.name[last.len] && !want_dir)
 		create_flags = 0;
 	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
-	dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags);
+	dentry = lookup_one_qstr_excl(&last, path->dentry,
+				      reval_flag | create_flags);
 	if (IS_ERR(dentry))
 		goto unlock;
 
@@ -4212,7 +4243,7 @@ int do_rmdir(int dfd, struct filename *name)
 		goto exit2;
 
 	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
-	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
+	dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit3;
@@ -4345,7 +4376,7 @@ int do_unlinkat(int dfd, struct filename *name)
 		goto exit2;
 retry_deleg:
 	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
-	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
+	dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
 
@@ -4909,7 +4940,8 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 retry_deleg:
 	trap = lock_rename(new_path.dentry, old_path.dentry);
 
-	old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags);
+	old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry,
+					  lookup_flags);
 	error = PTR_ERR(old_dentry);
 	if (IS_ERR(old_dentry))
 		goto exit3;
@@ -4917,7 +4949,8 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 	error = -ENOENT;
 	if (d_is_negative(old_dentry))
 		goto exit4;
-	new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags);
+	new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry,
+					  lookup_flags | target_flags);
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry))
 		goto exit4;

include/linux/namei.h

@@ -57,12 +57,18 @@ static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
 	return user_path_at_empty(dfd, name, flags, path, NULL);
 }
 
+struct dentry *lookup_one_qstr_excl(const struct qstr *name,
+				    struct dentry *base,
+				    unsigned int flags);
 extern int kern_path(const char *, unsigned, struct path *);
 
 extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int);
 extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
 extern void done_path_create(struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
+int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
+			   struct path *parent, struct qstr *last, int *type,
+			   const struct path *root);
 int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *,
 		    unsigned int, struct path *);