diff mbox series

[01/11] VFS: introduce vfs_mkdir_return()

Message ID 20241220030830.272429-2-neilb@suse.de
State New
Headers show
Series Allow concurrent changes in a directory | expand

Commit Message

NeilBrown Dec. 20, 2024, 2:54 a.m. UTC
vfs_mkdir() does not guarantee to make the child dentry positive on
success.  It may leave it negative and then the caller needs to perform a
lookup to find the target dentry.

This patch introduced vfs_mkdir_return() which performs the lookup if
needed so that this code is centralised.

This prepares for a new inode operation which will perform mkdir and
returns the correct dentry.

Signed-off-by: NeilBrown <neilb@suse.de>
---
 fs/cachefiles/namei.c    |  7 +----
 fs/namei.c               | 63 ++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/vfs.c            | 21 ++------------
 fs/overlayfs/dir.c       | 33 +--------------------
 fs/overlayfs/overlayfs.h | 10 +++----
 fs/overlayfs/super.c     |  2 +-
 fs/smb/server/vfs.c      | 23 +++------------
 include/linux/fs.h       |  2 ++
 8 files changed, 80 insertions(+), 81 deletions(-)
diff mbox series

Patch

diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 7cf59713f0f7..3c866c3b9534 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -95,7 +95,6 @@  struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 	/* search the current directory for the element name */
 	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
 
-retry:
 	ret = cachefiles_inject_read_error();
 	if (ret == 0)
 		subdir = lookup_one_len(dirname, dir, strlen(dirname));
@@ -130,7 +129,7 @@  struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 			goto mkdir_error;
 		ret = cachefiles_inject_write_error();
 		if (ret == 0)
-			ret = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700);
+			ret = vfs_mkdir_return(&nop_mnt_idmap, d_inode(dir), &subdir, 0700);
 		if (ret < 0) {
 			trace_cachefiles_vfs_error(NULL, d_inode(dir), ret,
 						   cachefiles_trace_mkdir_error);
@@ -138,10 +137,6 @@  struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
 		}
 		trace_cachefiles_mkdir(dir, subdir);
 
-		if (unlikely(d_unhashed(subdir))) {
-			cachefiles_put_directory(subdir);
-			goto retry;
-		}
 		ASSERT(d_backing_inode(subdir));
 
 		_debug("mkdir -> %pd{ino=%lu}",
diff --git a/fs/namei.c b/fs/namei.c
index 9d30c7aa9aa6..cdd1fc9d56a0 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4315,6 +4315,69 @@  int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
+/**
+ * vfs_mkdir_return - create directory returning correct dentry
+ * @idmap:	idmap of the mount the inode was found from
+ * @dir:	inode of the parent directory
+ * @dentryp:	pointer to dentry of the child directory
+ * @mode:	mode of the child directory
+ *
+ * Create a directory.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then take
+ * care to map the inode according to @idmap before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply pass @nop_mnt_idmap.
+ *
+ * The filesystem may not use the dentry that was passed in.  In that case
+ * the passed-in dentry is put and a new one is placed in *@dentryp;
+ * So on successful return *@dentryp will always be positive.
+ */
+int vfs_mkdir_return(struct mnt_idmap *idmap, struct inode *dir,
+		     struct dentry **dentryp, umode_t mode)
+{
+	struct dentry *dentry = *dentryp;
+	int error;
+	unsigned max_links = dir->i_sb->s_max_links;
+
+	error = may_create(idmap, dir, dentry);
+	if (error)
+		return error;
+
+	if (!dir->i_op->mkdir)
+		return -EPERM;
+
+	mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0);
+	error = security_inode_mkdir(dir, dentry, mode);
+	if (error)
+		return error;
+
+	if (max_links && dir->i_nlink >= max_links)
+		return -EMLINK;
+
+	error = dir->i_op->mkdir(idmap, dir, dentry, mode);
+	if (!error) {
+		fsnotify_mkdir(dir, dentry);
+		if (unlikely(d_unhashed(dentry))) {
+			struct dentry *d;
+			d = lookup_dcache((const struct qstr *)&dentry->d_name,
+					  dentry->d_parent, 0);
+			if (IS_ERR(d)) {
+				error = PTR_ERR(d);
+			} else if (unlikely(d_is_negative(d))) {
+				dput(d);
+				error = -ENOENT;
+			} else {
+				dput(dentry);
+				*dentryp = d;
+			}
+		}
+	}
+	return error;
+}
+EXPORT_SYMBOL(vfs_mkdir_return);
+
 int do_mkdirat(int dfd, struct filename *name, umode_t mode)
 {
 	struct dentry *dentry;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 29cb7b812d71..740332413138 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1488,26 +1488,11 @@  nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			nfsd_check_ignore_resizing(iap);
 		break;
 	case S_IFDIR:
-		host_err = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode);
-		if (!host_err && unlikely(d_unhashed(dchild))) {
-			struct dentry *d;
-			d = lookup_one_len(dchild->d_name.name,
-					   dchild->d_parent,
-					   dchild->d_name.len);
-			if (IS_ERR(d)) {
-				host_err = PTR_ERR(d);
-				break;
-			}
-			if (unlikely(d_is_negative(d))) {
-				dput(d);
-				err = nfserr_serverfault;
-				goto out;
-			}
+		host_err = vfs_mkdir_return(&nop_mnt_idmap, dirp, &dchild, iap->ia_mode);
+		if (!host_err && unlikely(dchild != resfhp->fh_dentry)) {
 			dput(resfhp->fh_dentry);
-			resfhp->fh_dentry = dget(d);
+			resfhp->fh_dentry = dget(dchild);
 			err = fh_update(resfhp);
-			dput(dchild);
-			dchild = d;
 			if (err)
 				goto out;
 		}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 08e683917d12..92a277ccc419 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -138,37 +138,6 @@  int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
 	goto out;
 }
 
-int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir,
-		   struct dentry **newdentry, umode_t mode)
-{
-	int err;
-	struct dentry *d, *dentry = *newdentry;
-
-	err = ovl_do_mkdir(ofs, dir, dentry, mode);
-	if (err)
-		return err;
-
-	if (likely(!d_unhashed(dentry)))
-		return 0;
-
-	/*
-	 * vfs_mkdir() may succeed and leave the dentry passed
-	 * to it unhashed and negative. If that happens, try to
-	 * lookup a new hashed and positive dentry.
-	 */
-	d = ovl_lookup_upper(ofs, dentry->d_name.name, dentry->d_parent,
-			     dentry->d_name.len);
-	if (IS_ERR(d)) {
-		pr_warn("failed lookup after mkdir (%pd2, err=%i).\n",
-			dentry, err);
-		return PTR_ERR(d);
-	}
-	dput(dentry);
-	*newdentry = d;
-
-	return 0;
-}
-
 struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir,
 			       struct dentry *newdentry, struct ovl_cattr *attr)
 {
@@ -191,7 +160,7 @@  struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir,
 
 		case S_IFDIR:
 			/* mkdir is special... */
-			err =  ovl_mkdir_real(ofs, dir, &newdentry, attr->mode);
+			err =  ovl_do_mkdir(ofs, dir, &newdentry, attr->mode);
 			break;
 
 		case S_IFCHR:
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b361f35762be..9ff34f84fc50 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -242,11 +242,11 @@  static inline int ovl_do_create(struct ovl_fs *ofs,
 }
 
 static inline int ovl_do_mkdir(struct ovl_fs *ofs,
-			       struct inode *dir, struct dentry *dentry,
+			       struct inode *dir, struct dentry **dentry,
 			       umode_t mode)
 {
-	int err = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
-	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err);
+	int err = vfs_mkdir_return(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
+	pr_debug("mkdir(%pd2, 0%o) = %i\n", *dentry, mode, err);
 	return err;
 }
 
@@ -838,8 +838,8 @@  struct ovl_cattr {
 
 #define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) })
 
-int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir,
-		   struct dentry **newdentry, umode_t mode);
+int ovl_do_mkdir(struct ovl_fs *ofs, struct inode *dir,
+	      struct dentry **newdentry, umode_t mode);
 struct dentry *ovl_create_real(struct ovl_fs *ofs,
 			       struct inode *dir, struct dentry *newdentry,
 			       struct ovl_cattr *attr);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fe511192f83c..24c44f7c1c8b 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -309,7 +309,7 @@  static struct dentry *ovl_workdir_create(struct ovl_fs *ofs,
 			goto retry;
 		}
 
-		err = ovl_mkdir_real(ofs, dir, &work, attr.ia_mode);
+		err = ovl_do_mkdir(ofs, dir, &work, attr.ia_mode);
 		if (err)
 			goto out_dput;
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 88d167a5f8b7..dfb0eee5f5f3 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -211,7 +211,7 @@  int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode)
 {
 	struct mnt_idmap *idmap;
 	struct path path;
-	struct dentry *dentry;
+	struct dentry *dentry, *d;
 	int err;
 
 	dentry = ksmbd_vfs_kern_path_create(work, name,
@@ -227,25 +227,10 @@  int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode)
 
 	idmap = mnt_idmap(path.mnt);
 	mode |= S_IFDIR;
-	err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode);
-	if (!err && d_unhashed(dentry)) {
-		struct dentry *d;
-
-		d = lookup_one(idmap, dentry->d_name.name, dentry->d_parent,
-			       dentry->d_name.len);
-		if (IS_ERR(d)) {
-			err = PTR_ERR(d);
-			goto out_err;
-		}
-		if (unlikely(d_is_negative(d))) {
-			dput(d);
-			err = -ENOENT;
-			goto out_err;
-		}
-
+	d = dentry;
+	err = vfs_mkdir_return(idmap, d_inode(path.dentry), &dentry, mode);
+	if (!err && dentry != d)
 		ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d));
-		dput(d);
-	}
 
 out_err:
 	done_path_create(&path, dentry);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7e29433c5ecc..406887d0394e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1923,6 +1923,8 @@  int vfs_create(struct mnt_idmap *, struct inode *,
 	       struct dentry *, umode_t, bool);
 int vfs_mkdir(struct mnt_idmap *, struct inode *,
 	      struct dentry *, umode_t);
+int vfs_mkdir_return(struct mnt_idmap *, struct inode *,
+		     struct dentry **, umode_t);
 int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
               umode_t, dev_t);
 int vfs_symlink(struct mnt_idmap *, struct inode *,