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()

5 files changed, 87 insertions, 146 deletions

diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 2cb972b5ed99..42adc5461db0 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -281,14 +281,11 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (host_err)
 		return nfserrno(host_err);
 
-	inode_lock_nested(inode, I_MUTEX_PARENT);
-
-	child = lookup_one(&nop_mnt_idmap,
-			   &QSTR_LEN(argp->name, argp->len),
-			   parent);
+	child = start_creating(&nop_mnt_idmap, parent,
+			       &QSTR_LEN(argp->name, argp->len));
 	if (IS_ERR(child)) {
 		status = nfserrno(PTR_ERR(child));
-		goto out;
+		goto out_write;
 	}
 
 	if (d_really_is_negative(child)) {
@@ -367,9 +364,8 @@ set_attr:
 	status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs);
 
 out:
-	inode_unlock(inode);
-	if (child && !IS_ERR(child))
-		dput(child);
+	end_creating(child);
+out_write:
 	fh_drop_write(fhp);
 	return status;
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5cc78f4a81b8..b74800917583 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -264,14 +264,11 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (is_create_with_attrs(open))
 		nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs);
 
-	inode_lock_nested(inode, I_MUTEX_PARENT);
-
-	child = lookup_one(&nop_mnt_idmap,
-			   &QSTR_LEN(open->op_fname, open->op_fnamelen),
-			   parent);
+	child = start_creating(&nop_mnt_idmap, parent,
+			       &QSTR_LEN(open->op_fname, open->op_fnamelen));
 	if (IS_ERR(child)) {
 		status = nfserrno(PTR_ERR(child));
-		goto out;
+		goto out_write;
 	}
 
 	if (d_really_is_negative(child)) {
@@ -379,10 +376,9 @@ set_attr:
 	if (attrs.na_aclerr)
 		open->op_bmval[0] &= ~FATTR4_WORD0_ACL;
 out:
-	inode_unlock(inode);
+	end_creating(child);
 	nfsd_attrs_free(&attrs);
-	if (child && !IS_ERR(child))
-		dput(child);
+out_write:
 	fh_drop_write(fhp);
 	return status;
 }
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 30bae93931d9..b39d4cbdfd35 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -195,13 +195,11 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		goto out_creds;
 
 	dir = nn->rec_file->f_path.dentry;
-	/* lock the parent */
-	inode_lock(d_inode(dir));
 
-	dentry = lookup_one(&nop_mnt_idmap, &QSTR(dname), dir);
+	dentry = start_creating(&nop_mnt_idmap, dir, &QSTR(dname));
 	if (IS_ERR(dentry)) {
 		status = PTR_ERR(dentry);
-		goto out_unlock;
+		goto out;
 	}
 	if (d_really_is_positive(dentry))
 		/*
@@ -212,15 +210,13 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		 * In the 4.0 case, we should never get here; but we may
 		 * as well be forgiving and just succeed silently.
 		 */
-		goto out_put;
+		goto out_end;
 	dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, 0700, NULL);
 	if (IS_ERR(dentry))
 		status = PTR_ERR(dentry);
-out_put:
-	if (!status)
-		dput(dentry);
-out_unlock:
-	inode_unlock(d_inode(dir));
+out_end:
+	end_creating(dentry);
+out:
 	if (status == 0) {
 		if (nn->in_grace)
 			__nfsd4_create_reclaim_record_grace(clp, dname,
@@ -328,20 +324,12 @@ nfsd4_unlink_clid_dir(char *name, struct nfsd_net *nn)
 	dprintk("NFSD: nfsd4_unlink_clid_dir. name %s\n", name);
 
 	dir = nn->rec_file->f_path.dentry;
-	inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
-	dentry = lookup_one(&nop_mnt_idmap, &QSTR(name), dir);
-	if (IS_ERR(dentry)) {
-		status = PTR_ERR(dentry);
-		goto out_unlock;
-	}
-	status = -ENOENT;
-	if (d_really_is_negative(dentry))
-		goto out;
+	dentry = start_removing(&nop_mnt_idmap, dir, &QSTR(name));
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
 	status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry, NULL);
-out:
-	dput(dentry);
-out_unlock:
-	inode_unlock(d_inode(dir));
+	end_removing(dentry);
 	return status;
 }
 
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 8f71f5748c75..481e789a7697 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -306,18 +306,16 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 		goto done;
 	}
 
-	inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT);
-	dchild = lookup_one(&nop_mnt_idmap, &QSTR_LEN(argp->name, argp->len),
-			    dirfhp->fh_dentry);
+	dchild = start_creating(&nop_mnt_idmap, dirfhp->fh_dentry,
+				&QSTR_LEN(argp->name, argp->len));
 	if (IS_ERR(dchild)) {
 		resp->status = nfserrno(PTR_ERR(dchild));
-		goto out_unlock;
+		goto out_write;
 	}
 	fh_init(newfhp, NFS_FHSIZE);
 	resp->status = fh_compose(newfhp, dirfhp->fh_export, dchild, dirfhp);
 	if (!resp->status && d_really_is_negative(dchild))
 		resp->status = nfserr_noent;
-	dput(dchild);
 	if (resp->status) {
 		if (resp->status != nfserr_noent)
 			goto out_unlock;
@@ -409,6 +407,9 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 		/* File doesn't exist. Create it and set attrs */
 		resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type,
 						  rdev, newfhp);
+		/* nfsd_create_locked() unlocked the parent */
+		dput(dchild);
+		goto out_write;
 	} else if (type == S_IFREG) {
 		dprintk("nfsd:   existing %s, valid=%x, size=%ld\n",
 			argp->name, attr->ia_valid, (long) attr->ia_size);
@@ -423,7 +424,8 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 	}
 
 out_unlock:
-	inode_unlock(dirfhp->fh_dentry->d_inode);
+	end_creating(dchild);
+out_write:
 	fh_drop_write(dirfhp);
 done:
 	fh_put(dirfhp);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6642620b6e9e..31cbf46b47b1 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1522,7 +1522,7 @@ nfsd_check_ignore_resizing(struct iattr *iap)
 		iap->ia_valid &= ~ATTR_SIZE;
 }
 
-/* The parent directory should already be locked: */
+/* The parent directory should already be locked - we will unlock */
 __be32
 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		   struct nfsd_attrs *attrs,
@@ -1587,8 +1587,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
 
 out:
-	if (!IS_ERR(dchild))
-		dput(dchild);
+	if (!err)
+		fh_fill_post_attrs(fhp);
+	end_creating(dchild);
 	return err;
 
 out_nfserr:
@@ -1626,28 +1627,24 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (host_err)
 		return nfserrno(host_err);
 
-	inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT);
-	dchild = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry);
+	dchild = start_creating(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen));
 	host_err = PTR_ERR(dchild);
-	if (IS_ERR(dchild)) {
-		err = nfserrno(host_err);
-		goto out_unlock;
-	}
+	if (IS_ERR(dchild))
+		return nfserrno(host_err);
+
 	err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
-	/*
-	 * We unconditionally drop our ref to dchild as fh_compose will have
-	 * already grabbed its own ref for it.
-	 */
-	dput(dchild);
 	if (err)
 		goto out_unlock;
 	err = fh_fill_pre_attrs(fhp);
 	if (err != nfs_ok)
 		goto out_unlock;
 	err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp);
-	fh_fill_post_attrs(fhp);
+	/* nfsd_create_locked() unlocked the parent */
+	dput(dchild);
+	return err;
+
 out_unlock:
-	inode_unlock(dentry->d_inode);
+	end_creating(dchild);
 	return err;
 }
 
@@ -1733,11 +1730,9 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	}
 
 	dentry = fhp->fh_dentry;
-	inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT);
-	dnew = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry);
+	dnew = start_creating(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen));
 	if (IS_ERR(dnew)) {
 		err = nfserrno(PTR_ERR(dnew));
-		inode_unlock(dentry->d_inode);
 		goto out_drop_write;
 	}
 	err = fh_fill_pre_attrs(fhp);
@@ -1750,11 +1745,11 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
 	fh_fill_post_attrs(fhp);
 out_unlock:
-	inode_unlock(dentry->d_inode);
+	end_creating(dnew);
 	if (!err)
 		err = nfserrno(commit_metadata(fhp));
-	dput(dnew);
-	if (err==0) err = cerr;
+	if (!err)
+		err = cerr;
 out_drop_write:
 	fh_drop_write(fhp);
 out:
@@ -1809,32 +1804,31 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 
 	ddir = ffhp->fh_dentry;
 	dirp = d_inode(ddir);
-	inode_lock_nested(dirp, I_MUTEX_PARENT);
+	dnew = start_creating(&nop_mnt_idmap, ddir, &QSTR_LEN(name, len));
 
-	dnew = lookup_one(&nop_mnt_idmap, &QSTR_LEN(name, len), ddir);
 	if (IS_ERR(dnew)) {
 		host_err = PTR_ERR(dnew);
-		goto out_unlock;
+		goto out_drop_write;
 	}
 
 	dold = tfhp->fh_dentry;
 
 	err = nfserr_noent;
 	if (d_really_is_negative(dold))
-		goto out_dput;
+		goto out_unlock;
 	err = fh_fill_pre_attrs(ffhp);
 	if (err != nfs_ok)
-		goto out_dput;
+		goto out_unlock;
 	host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL);
 	fh_fill_post_attrs(ffhp);
-	inode_unlock(dirp);
+out_unlock:
+	end_creating(dnew);
 	if (!host_err) {
 		host_err = commit_metadata(ffhp);
 		if (!host_err)
 			host_err = commit_metadata(tfhp);
 	}
 
-	dput(dnew);
 out_drop_write:
 	fh_drop_write(tfhp);
 	if (host_err == -EBUSY) {
@@ -1849,12 +1843,6 @@ out_drop_write:
 	}
 out:
 	return err != nfs_ok ? err : nfserrno(host_err);
-
-out_dput:
-	dput(dnew);
-out_unlock:
-	inode_unlock(dirp);
-	goto out_drop_write;
 }
 
 static void
@@ -1895,11 +1883,12 @@ __be32
 nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 			    struct svc_fh *tfhp, char *tname, int tlen)
 {
-	struct dentry	*fdentry, *tdentry, *odentry, *ndentry, *trap;
+	struct dentry	*fdentry, *tdentry;
 	int		type = S_IFDIR;
+	struct renamedata rd = {};
 	__be32		err;
 	int		host_err;
-	bool		close_cached = false;
+	struct dentry	*close_cached;
 
 	trace_nfsd_vfs_rename(rqstp, ffhp, tfhp, fname, flen, tname, tlen);
 
@@ -1925,15 +1914,22 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		goto out;
 
 retry:
+	close_cached = NULL;
 	host_err = fh_want_write(ffhp);
 	if (host_err) {
 		err = nfserrno(host_err);
 		goto out;
 	}
 
-	trap = lock_rename(tdentry, fdentry);
-	if (IS_ERR(trap)) {
-		err = nfserr_xdev;
+	rd.mnt_idmap	= &nop_mnt_idmap;
+	rd.old_parent	= fdentry;
+	rd.new_parent	= tdentry;
+
+	host_err = start_renaming(&rd, 0, &QSTR_LEN(fname, flen),
+				  &QSTR_LEN(tname, tlen));
+
+	if (host_err) {
+		err = nfserrno(host_err);
 		goto out_want_write;
 	}
 	err = fh_fill_pre_attrs(ffhp);
@@ -1943,48 +1939,23 @@ retry:
 	if (err != nfs_ok)
 		goto out_unlock;
 
-	odentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), fdentry);
-	host_err = PTR_ERR(odentry);
-	if (IS_ERR(odentry))
-		goto out_nfserr;
+	type = d_inode(rd.old_dentry)->i_mode & S_IFMT;
+
+	if (d_inode(rd.new_dentry))
+		type = d_inode(rd.new_dentry)->i_mode & S_IFMT;
 
-	host_err = -ENOENT;
-	if (d_really_is_negative(odentry))
-		goto out_dput_old;
-	host_err = -EINVAL;
-	if (odentry == trap)
-		goto out_dput_old;
-	type = d_inode(odentry)->i_mode & S_IFMT;
-
-	ndentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(tname, tlen), tdentry);
-	host_err = PTR_ERR(ndentry);
-	if (IS_ERR(ndentry))
-		goto out_dput_old;
-	if (d_inode(ndentry))
-		type = d_inode(ndentry)->i_mode & S_IFMT;
-	host_err = -ENOTEMPTY;
-	if (ndentry == trap)
-		goto out_dput_new;
-
-	if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) &&
-	    nfsd_has_cached_files(ndentry)) {
-		close_cached = true;
-		goto out_dput_old;
+	if ((rd.new_dentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) &&
+	    nfsd_has_cached_files(rd.new_dentry)) {
+		close_cached = dget(rd.new_dentry);
+		goto out_unlock;
 	} else {
-		struct renamedata rd = {
-			.mnt_idmap	= &nop_mnt_idmap,
-			.old_parent	= fdentry,
-			.old_dentry	= odentry,
-			.new_parent	= tdentry,
-			.new_dentry	= ndentry,
-		};
 		int retries;
 
 		for (retries = 1;;) {
 			host_err = vfs_rename(&rd);
 			if (host_err != -EAGAIN || !retries--)
 				break;
-			if (!nfsd_wait_for_delegreturn(rqstp, d_inode(odentry)))
+			if (!nfsd_wait_for_delegreturn(rqstp, d_inode(rd.old_dentry)))
 				break;
 		}
 		if (!host_err) {
@@ -1993,11 +1964,6 @@ retry:
 				host_err = commit_metadata(ffhp);
 		}
 	}
- out_dput_new:
-	dput(ndentry);
- out_dput_old:
-	dput(odentry);
- out_nfserr:
 	if (host_err == -EBUSY) {
 		/*
 		 * See RFC 8881 Section 18.26.4 para 1-3: NFSv4 RENAME
@@ -2016,7 +1982,7 @@ retry:
 		fh_fill_post_attrs(tfhp);
 	}
 out_unlock:
-	unlock_rename(tdentry, fdentry);
+	end_renaming(&rd);
 out_want_write:
 	fh_drop_write(ffhp);
 
@@ -2027,9 +1993,8 @@ out_want_write:
 	 * until this point and then reattempt the whole shebang.
 	 */
 	if (close_cached) {
-		close_cached = false;
-		nfsd_close_cached_files(ndentry);
-		dput(ndentry);
+		nfsd_close_cached_files(close_cached);
+		dput(close_cached);
 		goto retry;
 	}
 out:
@@ -2054,7 +2019,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 {
 	struct dentry	*dentry, *rdentry;
 	struct inode	*dirp;
-	struct inode	*rinode;
+	struct inode	*rinode = NULL;
 	__be32		err;
 	int		host_err;
 
@@ -2073,24 +2038,21 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
-	inode_lock_nested(dirp, I_MUTEX_PARENT);
 
-	rdentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry);
+	rdentry = start_removing(&nop_mnt_idmap, dentry, &QSTR_LEN(fname, flen));
+
 	host_err = PTR_ERR(rdentry);
 	if (IS_ERR(rdentry))
-		goto out_unlock;
+		goto out_drop_write;
 
-	if (d_really_is_negative(rdentry)) {
-		dput(rdentry);
-		host_err = -ENOENT;
-		goto out_unlock;
-	}
-	rinode = d_inode(rdentry);
 	err = fh_fill_pre_attrs(fhp);
 	if (err != nfs_ok)
 		goto out_unlock;
 
+	rinode = d_inode(rdentry);
+	/* Prevent truncation until after locks dropped */
 	ihold(rinode);
+
 	if (!type)
 		type = d_inode(rdentry)->i_mode & S_IFMT;
 
@@ -2112,10 +2074,10 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	}
 	fh_fill_post_attrs(fhp);
 
-	inode_unlock(dirp);
-	if (!host_err)
+out_unlock:
+	end_removing(rdentry);
+	if (!err && !host_err)
 		host_err = commit_metadata(fhp);
-	dput(rdentry);
 	iput(rinode);    /* truncate the inode here */
 
 out_drop_write:
@@ -2133,9 +2095,6 @@ out_nfserr:
 	}
 out:
 	return err != nfs_ok ? err : nfserrno(host_err);
-out_unlock:
-	inode_unlock(dirp);
-	goto out_drop_write;
 }
 
 /*