VFS/nfsd/cachefiles/ovl: add start_creating() and end_creating()

start_creating() is similar to simple_start_creating() but is not so
simple.
It takes a qstr for the name, includes permission checking, and does NOT
report an error if the name already exists, returning a positive dentry
instead.

This is currently used by nfsd, cachefiles, and overlayfs.

end_creating() is called after the dentry has been used.
end_creating() drops the reference to the dentry as it is generally no
longer needed.  This is exactly the first section of end_creating_path()
so that function is changed to call the new end_creating()

These calls help encapsulate locking rules so that directory locking can
be changed.

Occasionally this change means that the parent lock is held for a
shorter period of time, for example in cachefiles_commit_tmpfile().
As this function now unlocks after an unlink and before the following
lookup, it is possible that the lookup could again find a positive
dentry, so a while loop is introduced there.

In overlayfs the ovl_lookup_temp() function has ovl_tempname()
split out to be used in ovl_start_creating_temp().  The other use
of ovl_lookup_temp() is preparing for a rename.  When rename handling
is updated, ovl_lookup_temp() will be removed.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://patch.msgid.link/20251113002050.676694-5-neilb@ownmail.net
Tested-by: syzbot@syzkaller.appspotmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 21 insertions, 31 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 9cb20d4aeab1..4efd3688e081 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1521,7 +1521,7 @@ 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, dentry);
 	return err;
 
 out_nfserr:
@@ -1626,28 +1627,26 @@ 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);
+	return err;
+
 out_unlock:
-	inode_unlock(dentry->d_inode);
+	end_creating(dchild, dentry);
 	return err;
 }
 
@@ -1733,11 +1732,9 @@ 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 +1747,11 @@ 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, dentry);
 	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 +1806,31 @@ 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, ddir);
 	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 +1845,6 @@ 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