Merge tag 'vfs-6.19-rc1.directory.locking' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull directory locking updates from Christian Brauner:
 "This contains the work to add centralized APIs for directory locking
  operations.

  This series is part of a larger effort to change directory operation
  locking to allow multiple concurrent operations in a directory. The
  ultimate goal is to lock the target dentry(s) rather than the whole
  parent directory.

  To help with changing the locking protocol, this series centralizes
  locking and lookup in new helper functions. The helpers establish a
  pattern where it is the dentry that is being locked and unlocked
  (currently the lock is held on dentry->d_parent->d_inode, but that can
  change in the future).

  This also changes vfs_mkdir() to unlock the parent on failure, as well
  as dput()ing the dentry. This allows end_creating() to only require
  the target dentry (which may be IS_ERR() after vfs_mkdir()), not the
  parent"

* tag 'vfs-6.19-rc1.directory.locking' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  nfsd: fix end_creating() conversion
  VFS: introduce end_creating_keep()
  VFS: change vfs_mkdir() to unlock on failure.
  ecryptfs: use new start_creating/start_removing APIs
  Add start_renaming_two_dentries()
  VFS/ovl/smb: introduce start_renaming_dentry()
  VFS/nfsd/ovl: introduce start_renaming() and end_renaming()
  VFS: add start_creating_killable() and start_removing_killable()
  VFS: introduce start_removing_dentry()
  smb/server: use end_removing_noperm for for target of smb2_create_link()
  VFS: introduce start_creating_noperm() and start_removing_noperm()
  VFS/nfsd/cachefiles/ovl: introduce start_removing() and end_removing()
  VFS/nfsd/cachefiles/ovl: add start_creating() and end_creating()
  VFS: tidy up do_unlinkat()
  VFS: introduce start_dirop() and end_dirop()
  debugfs: rename end_creating() to debugfs_end_creating()

1 files changed, 118 insertions, 123 deletions

diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 83b955a1d55c..d21f81a524f6 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -47,79 +47,70 @@ static int ovl_cleanup_locked(struct ovl_fs *ofs, struct inode *wdir,
 int ovl_cleanup(struct ovl_fs *ofs, struct dentry *workdir,
 		struct dentry *wdentry)
 {
-	int err;
-
-	err = ovl_parent_lock(workdir, wdentry);
-	if (err)
-		return err;
+	wdentry = start_removing_dentry(workdir, wdentry);
+	if (IS_ERR(wdentry))
+		return PTR_ERR(wdentry);
 
 	ovl_cleanup_locked(ofs, workdir->d_inode, wdentry);
-	ovl_parent_unlock(workdir);
+	end_removing(wdentry);
 
 	return 0;
 }
 
-struct dentry *ovl_lookup_temp(struct ovl_fs *ofs, struct dentry *workdir)
+void ovl_tempname(char name[OVL_TEMPNAME_SIZE])
 {
-	struct dentry *temp;
-	char name[20];
 	static atomic_t temp_id = ATOMIC_INIT(0);
 
 	/* counter is allowed to wrap, since temp dentries are ephemeral */
-	snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
+	snprintf(name, OVL_TEMPNAME_SIZE, "#%x", atomic_inc_return(&temp_id));
+}
 
-	temp = ovl_lookup_upper(ofs, name, workdir, strlen(name));
-	if (!IS_ERR(temp) && temp->d_inode) {
-		pr_err("workdir/%s already exists\n", name);
-		dput(temp);
-		temp = ERR_PTR(-EIO);
-	}
+static struct dentry *ovl_start_creating_temp(struct ovl_fs *ofs,
+					      struct dentry *workdir)
+{
+	char name[OVL_TEMPNAME_SIZE];
 
-	return temp;
+	ovl_tempname(name);
+	return start_creating(ovl_upper_mnt_idmap(ofs), workdir,
+			      &QSTR(name));
 }
 
 static struct dentry *ovl_whiteout(struct ovl_fs *ofs)
 {
 	int err;
-	struct dentry *whiteout;
+	struct dentry *whiteout, *link;
 	struct dentry *workdir = ofs->workdir;
 	struct inode *wdir = workdir->d_inode;
 
 	guard(mutex)(&ofs->whiteout_lock);
 
 	if (!ofs->whiteout) {
-		inode_lock_nested(wdir, I_MUTEX_PARENT);
-		whiteout = ovl_lookup_temp(ofs, workdir);
-		if (!IS_ERR(whiteout)) {
-			err = ovl_do_whiteout(ofs, wdir, whiteout);
-			if (err) {
-				dput(whiteout);
-				whiteout = ERR_PTR(err);
-			}
-		}
-		inode_unlock(wdir);
+		whiteout = ovl_start_creating_temp(ofs, workdir);
 		if (IS_ERR(whiteout))
 			return whiteout;
-		ofs->whiteout = whiteout;
+		err = ovl_do_whiteout(ofs, wdir, whiteout);
+		if (!err)
+			ofs->whiteout = dget(whiteout);
+		end_creating(whiteout);
+		if (err)
+			return ERR_PTR(err);
 	}
 
 	if (!ofs->no_shared_whiteout) {
-		inode_lock_nested(wdir, I_MUTEX_PARENT);
-		whiteout = ovl_lookup_temp(ofs, workdir);
-		if (!IS_ERR(whiteout)) {
-			err = ovl_do_link(ofs, ofs->whiteout, wdir, whiteout);
-			if (err) {
-				dput(whiteout);
-				whiteout = ERR_PTR(err);
-			}
-		}
-		inode_unlock(wdir);
-		if (!IS_ERR(whiteout))
-			return whiteout;
-		if (PTR_ERR(whiteout) != -EMLINK) {
-			pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%lu)\n",
+		link = ovl_start_creating_temp(ofs, workdir);
+		if (IS_ERR(link))
+			return link;
+		err = ovl_do_link(ofs, ofs->whiteout, wdir, link);
+		if (!err)
+			whiteout = dget(link);
+		end_creating(link);
+		if (!err)
+			return whiteout;;
+
+		if (err != -EMLINK) {
+			pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%u)\n",
 				ofs->whiteout->d_inode->i_nlink,
-				PTR_ERR(whiteout));
+				err);
 			ofs->no_shared_whiteout = true;
 		}
 	}
@@ -132,6 +123,7 @@ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
 			     struct dentry *dentry)
 {
 	struct dentry *whiteout;
+	struct renamedata rd = {};
 	int err;
 	int flags = 0;
 
@@ -143,10 +135,14 @@ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
 	if (d_is_dir(dentry))
 		flags = RENAME_EXCHANGE;
 
-	err = ovl_lock_rename_workdir(ofs->workdir, whiteout, dir, dentry);
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = ofs->workdir;
+	rd.new_parent = dir;
+	rd.flags = flags;
+	err = start_renaming_two_dentries(&rd, whiteout, dentry);
 	if (!err) {
-		err = ovl_do_rename(ofs, ofs->workdir, whiteout, dir, dentry, flags);
-		unlock_rename(ofs->workdir, dir);
+		err = ovl_do_rename_rd(&rd);
+		end_renaming(&rd);
 	}
 	if (err)
 		goto kill_whiteout;
@@ -191,7 +187,7 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent,
 			if (!err && ofs->casefold != ovl_dentry_casefolded(newdentry)) {
 				pr_warn_ratelimited("wrong inherited casefold (%pd2)\n",
 						    newdentry);
-				dput(newdentry);
+				end_creating(newdentry);
 				err = -EINVAL;
 			}
 			break;
@@ -241,8 +237,7 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent,
 	}
 out:
 	if (err) {
-		if (!IS_ERR(newdentry))
-			dput(newdentry);
+		end_creating(newdentry);
 		return ERR_PTR(err);
 	}
 	return newdentry;
@@ -252,11 +247,11 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
 			       struct ovl_cattr *attr)
 {
 	struct dentry *ret;
-	inode_lock_nested(workdir->d_inode, I_MUTEX_PARENT);
-	ret = ovl_create_real(ofs, workdir,
-			      ovl_lookup_temp(ofs, workdir), attr);
-	inode_unlock(workdir->d_inode);
-	return ret;
+	ret = ovl_start_creating_temp(ofs, workdir);
+	if (IS_ERR(ret))
+		return ret;
+	ret = ovl_create_real(ofs, workdir, ret, attr);
+	return end_creating_keep(ret);
 }
 
 static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
@@ -354,19 +349,20 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 {
 	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
-	struct inode *udir = upperdir->d_inode;
 	struct dentry *newdentry;
 	int err;
 
-	inode_lock_nested(udir, I_MUTEX_PARENT);
-	newdentry = ovl_create_real(ofs, upperdir,
-				    ovl_lookup_upper(ofs, dentry->d_name.name,
-						     upperdir, dentry->d_name.len),
-				    attr);
-	inode_unlock(udir);
+	newdentry = ovl_start_creating_upper(ofs, upperdir,
+					     &QSTR_LEN(dentry->d_name.name,
+						       dentry->d_name.len));
+	if (IS_ERR(newdentry))
+		return PTR_ERR(newdentry);
+	newdentry = ovl_create_real(ofs, upperdir, newdentry, attr);
 	if (IS_ERR(newdentry))
 		return PTR_ERR(newdentry);
 
+	end_creating_keep(newdentry);
+
 	if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry) &&
 	    !ovl_allow_offline_changes(ofs)) {
 		/* Setting opaque here is just an optimization, allow to fail */
@@ -391,6 +387,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	struct dentry *workdir = ovl_workdir(dentry);
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+	struct renamedata rd = {};
 	struct path upperpath;
 	struct dentry *upper;
 	struct dentry *opaquedir;
@@ -416,7 +413,11 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (IS_ERR(opaquedir))
 		goto out;
 
-	err = ovl_lock_rename_workdir(workdir, opaquedir, upperdir, upper);
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = workdir;
+	rd.new_parent = upperdir;
+	rd.flags = RENAME_EXCHANGE;
+	err = start_renaming_two_dentries(&rd, opaquedir, upper);
 	if (err)
 		goto out_cleanup_unlocked;
 
@@ -434,8 +435,8 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(ofs, workdir, opaquedir, upperdir, upper, RENAME_EXCHANGE);
-	unlock_rename(workdir, upperdir);
+	err = ovl_do_rename_rd(&rd);
+	end_renaming(&rd);
 	if (err)
 		goto out_cleanup_unlocked;
 
@@ -448,7 +449,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	return opaquedir;
 
 out_cleanup:
-	unlock_rename(workdir, upperdir);
+	end_renaming(&rd);
 out_cleanup_unlocked:
 	ovl_cleanup(ofs, workdir, opaquedir);
 	dput(opaquedir);
@@ -471,6 +472,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
 	struct dentry *workdir = ovl_workdir(dentry);
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+	struct renamedata rd = {};
 	struct dentry *upper;
 	struct dentry *newdentry;
 	int err;
@@ -502,7 +504,11 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 	if (IS_ERR(newdentry))
 		goto out_dput;
 
-	err = ovl_lock_rename_workdir(workdir, newdentry, upperdir, upper);
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = workdir;
+	rd.new_parent = upperdir;
+	rd.flags = 0;
+	err = start_renaming_two_dentries(&rd, newdentry, upper);
 	if (err)
 		goto out_cleanup_unlocked;
 
@@ -539,16 +545,16 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 		if (err)
 			goto out_cleanup;
 
-		err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper,
-				    RENAME_EXCHANGE);
-		unlock_rename(workdir, upperdir);
+		rd.flags = RENAME_EXCHANGE;
+		err = ovl_do_rename_rd(&rd);
+		end_renaming(&rd);
 		if (err)
 			goto out_cleanup_unlocked;
 
 		ovl_cleanup(ofs, workdir, upper);
 	} else {
-		err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper, 0);
-		unlock_rename(workdir, upperdir);
+		err = ovl_do_rename_rd(&rd);
+		end_renaming(&rd);
 		if (err)
 			goto out_cleanup_unlocked;
 	}
@@ -568,7 +574,7 @@ out:
 	return err;
 
 out_cleanup:
-	unlock_rename(workdir, upperdir);
+	end_renaming(&rd);
 out_cleanup_unlocked:
 	ovl_cleanup(ofs, workdir, newdentry);
 	dput(newdentry);
@@ -850,17 +856,17 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir,
 			goto out;
 	}
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
-	upper = ovl_lookup_upper(ofs, dentry->d_name.name, upperdir,
-				 dentry->d_name.len);
+	upper = ovl_start_removing_upper(ofs, upperdir,
+					 &QSTR_LEN(dentry->d_name.name,
+						   dentry->d_name.len));
 	err = PTR_ERR(upper);
 	if (IS_ERR(upper))
-		goto out_unlock;
+		goto out_dput;
 
 	err = -ESTALE;
 	if ((opaquedir && upper != opaquedir) ||
 	    (!opaquedir && !ovl_matches_upper(dentry, upper)))
-		goto out_dput_upper;
+		goto out_unlock;
 
 	if (is_dir)
 		err = ovl_do_rmdir(ofs, dir, upper);
@@ -876,10 +882,9 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir,
 	 */
 	if (!err)
 		d_drop(dentry);
-out_dput_upper:
-	dput(upper);
 out_unlock:
-	inode_unlock(dir);
+	end_removing(upper);
+out_dput:
 	dput(opaquedir);
 out:
 	return err;
@@ -1111,9 +1116,7 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 	int err;
 	struct dentry *old_upperdir;
 	struct dentry *new_upperdir;
-	struct dentry *olddentry = NULL;
-	struct dentry *newdentry = NULL;
-	struct dentry *trap, *de;
+	struct renamedata rd = {};
 	bool old_opaque;
 	bool new_opaque;
 	bool cleanup_whiteout = false;
@@ -1123,6 +1126,7 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 	bool new_is_dir = d_is_dir(new);
 	bool samedir = olddir == newdir;
 	struct dentry *opaquedir = NULL;
+	struct dentry *whiteout = NULL;
 	const struct cred *old_cred = NULL;
 	struct ovl_fs *ofs = OVL_FS(old->d_sb);
 	LIST_HEAD(list);
@@ -1220,29 +1224,21 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 		}
 	}
 
-	trap = lock_rename(new_upperdir, old_upperdir);
-	if (IS_ERR(trap)) {
-		err = PTR_ERR(trap);
-		goto out_revert_creds;
-	}
+	rd.mnt_idmap = ovl_upper_mnt_idmap(ofs);
+	rd.old_parent = old_upperdir;
+	rd.new_parent = new_upperdir;
+	rd.flags = flags;
 
-	de = ovl_lookup_upper(ofs, old->d_name.name, old_upperdir,
-			      old->d_name.len);
-	err = PTR_ERR(de);
-	if (IS_ERR(de))
-		goto out_unlock;
-	olddentry = de;
+	err = start_renaming(&rd, 0,
+			     &QSTR_LEN(old->d_name.name, old->d_name.len),
+			     &QSTR_LEN(new->d_name.name, new->d_name.len));
 
-	err = -ESTALE;
-	if (!ovl_matches_upper(old, olddentry))
-		goto out_unlock;
+	if (err)
+		goto out_revert_creds;
 
-	de = ovl_lookup_upper(ofs, new->d_name.name, new_upperdir,
-			      new->d_name.len);
-	err = PTR_ERR(de);
-	if (IS_ERR(de))
+	err = -ESTALE;
+	if (!ovl_matches_upper(old, rd.old_dentry))
 		goto out_unlock;
-	newdentry = de;
 
 	old_opaque = ovl_dentry_is_opaque(old);
 	new_opaque = ovl_dentry_is_opaque(new);
@@ -1250,15 +1246,15 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 	err = -ESTALE;
 	if (d_inode(new) && ovl_dentry_upper(new)) {
 		if (opaquedir) {
-			if (newdentry != opaquedir)
+			if (rd.new_dentry != opaquedir)
 				goto out_unlock;
 		} else {
-			if (!ovl_matches_upper(new, newdentry))
+			if (!ovl_matches_upper(new, rd.new_dentry))
 				goto out_unlock;
 		}
 	} else {
-		if (!d_is_negative(newdentry)) {
-			if (!new_opaque || !ovl_upper_is_whiteout(ofs, newdentry))
+		if (!d_is_negative(rd.new_dentry)) {
+			if (!new_opaque || !ovl_upper_is_whiteout(ofs, rd.new_dentry))
 				goto out_unlock;
 		} else {
 			if (flags & RENAME_EXCHANGE)
@@ -1266,19 +1262,14 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 		}
 	}
 
-	if (olddentry == trap)
-		goto out_unlock;
-	if (newdentry == trap)
-		goto out_unlock;
-
-	if (olddentry->d_inode == newdentry->d_inode)
+	if (rd.old_dentry->d_inode == rd.new_dentry->d_inode)
 		goto out_unlock;
 
 	err = 0;
 	if (ovl_type_merge_or_lower(old))
 		err = ovl_set_redirect(old, samedir);
 	else if (is_dir && !old_opaque && ovl_type_merge(new->d_parent))
-		err = ovl_set_opaque_xerr(old, olddentry, -EXDEV);
+		err = ovl_set_opaque_xerr(old, rd.old_dentry, -EXDEV);
 	if (err)
 		goto out_unlock;
 
@@ -1286,18 +1277,24 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 		err = ovl_set_redirect(new, samedir);
 	else if (!overwrite && new_is_dir && !new_opaque &&
 		 ovl_type_merge(old->d_parent))
-		err = ovl_set_opaque_xerr(new, newdentry, -EXDEV);
+		err = ovl_set_opaque_xerr(new, rd.new_dentry, -EXDEV);
 	if (err)
 		goto out_unlock;
 
-	err = ovl_do_rename(ofs, old_upperdir, olddentry,
-			    new_upperdir, newdentry, flags);
-	unlock_rename(new_upperdir, old_upperdir);
+	err = ovl_do_rename_rd(&rd);
+
+	if (!err && cleanup_whiteout)
+		whiteout = dget(rd.new_dentry);
+
+	end_renaming(&rd);
+
 	if (err)
 		goto out_revert_creds;
 
-	if (cleanup_whiteout)
-		ovl_cleanup(ofs, old_upperdir, newdentry);
+	if (whiteout) {
+		ovl_cleanup(ofs, old_upperdir, whiteout);
+		dput(whiteout);
+	}
 
 	if (overwrite && d_inode(new)) {
 		if (new_is_dir)
@@ -1323,14 +1320,12 @@ out_revert_creds:
 	else
 		ovl_drop_write(old);
 out:
-	dput(newdentry);
-	dput(olddentry);
 	dput(opaquedir);
 	ovl_cache_free(&list);
 	return err;
 
 out_unlock:
-	unlock_rename(new_upperdir, old_upperdir);
+	end_renaming(&rd);
 	goto out_revert_creds;
 }