allow incomplete imports of filenames

There are two filename-related problems in io_uring and its
interplay with audit.

Filenames are imported when request is submitted and used when
it is processed.  Unfortunately, the latter may very well
happen in a different thread.  In that case the reference to
filename is put into the wrong audit_context - that of submitting
thread, not the processing one.  Audit logics is called by
the latter, and it really wants to be able to find the names
in audit_context current (== processing) thread.

Another related problem is the headache with refcounts -
normally all references to given struct filename are visible
only to one thread (the one that uses that struct filename).
io_uring violates that - an extra reference is stashed in
audit_context of submitter.  It gets dropped when submitter
returns to userland, which can happen simultaneously with
processing thread deciding to drop the reference it got.

We paper over that by making refcount atomic, but that means
pointless headache for everyone.

Solution: the notion of partially imported filenames.  Namely,
already copied from userland, but *not* exposed to audit yet.

io_uring can create that in submitter thread, and complete the
import (obtaining the usual reference to struct filename) in
processing thread.

Object: struct delayed_filename.

Primitives for working with it:

delayed_getname(&delayed_filename, user_string) - copies the name from
userland, returning 0 and stashing the address of (still incomplete)
struct filename in delayed_filename on success and returning -E... on
error.

delayed_getname_uflags(&delayed_filename, user_string, atflags) -
similar, in the same relation to delayed_getname() as getname_uflags()
is to getname()

complete_getname(&delayed_filename) - completes the import of filename
stashed in delayed_filename and returns struct filename to caller,
emptying delayed_filename.

CLASS(filename_complete_delayed, name)(&delayed_filename) - variant of
CLASS(filename) with complete_getname() for constructor.

dismiss_delayed_filename(&delayed_filename) - destructor; drops whatever
might be stashed in delayed_filename, emptying it.

putname_to_delayed(&delayed_filename, name) - if name is shared, stashes
its copy into delayed_filename and drops the reference to name, otherwise
stashes the name itself in there.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Author: Al Viro

fs/namei.c

@@ -172,8 +172,8 @@ static int getname_long(struct filename *name, const char __user *filename)
 	return 0;
 }
 
-struct filename *
-getname_flags(const char __user *filename, int flags)
+static struct filename *
+do_getname(const char __user *filename, int flags, bool incomplete)
 {
 	struct filename *result;
 	char *kname;
@@ -214,10 +214,17 @@ getname_flags(const char __user *filename, int flags)
 	}
 
 	initname(result);
-	audit_getname(result);
+	if (likely(!incomplete))
+		audit_getname(result);
 	return result;
 }
 
+struct filename *
+getname_flags(const char __user *filename, int flags)
+{
+	return do_getname(filename, flags, false);
+}
+
 struct filename *getname_uflags(const char __user *filename, int uflags)
 {
 	int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
@@ -242,7 +249,7 @@ struct filename *__getname_maybe_null(const char __user *pathname)
 	return no_free_ptr(name);
 }
 
-struct filename *getname_kernel(const char * filename)
+static struct filename *do_getname_kernel(const char *filename, bool incomplete)
 {
 	struct filename *result;
 	int len = strlen(filename) + 1;
@@ -267,9 +274,15 @@ struct filename *getname_kernel(const char * filename)
 	}
 	result->name = p;
 	initname(result);
-	audit_getname(result);
+	if (likely(!incomplete))
+		audit_getname(result);
 	return result;
 }
+
+struct filename *getname_kernel(const char *filename)
+{
+	return do_getname_kernel(filename, false);
+}
 EXPORT_SYMBOL(getname_kernel);
 
 void putname(struct filename *name)
@@ -294,6 +307,49 @@ void putname(struct filename *name)
 }
 EXPORT_SYMBOL(putname);
 
+static inline int __delayed_getname(struct delayed_filename *v,
+			   const char __user *string, int flags)
+{
+	v->__incomplete_filename = do_getname(string, flags, true);
+	return PTR_ERR_OR_ZERO(v->__incomplete_filename);
+}
+
+int delayed_getname(struct delayed_filename *v, const char __user *string)
+{
+	return __delayed_getname(v, string, 0);
+}
+
+int delayed_getname_uflags(struct delayed_filename *v, const char __user *string,
+			 int uflags)
+{
+	int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+	return __delayed_getname(v, string, flags);
+}
+
+int putname_to_delayed(struct delayed_filename *v, struct filename *name)
+{
+	if (likely(atomic_read(&name->refcnt) == 1)) {
+		v->__incomplete_filename = name;
+		return 0;
+	}
+	v->__incomplete_filename = do_getname_kernel(name->name, true);
+	putname(name);
+	return PTR_ERR_OR_ZERO(v->__incomplete_filename);
+}
+
+void dismiss_delayed_filename(struct delayed_filename *v)
+{
+	putname(no_free_ptr(v->__incomplete_filename));
+}
+
+struct filename *complete_getname(struct delayed_filename *v)
+{
+	struct filename *res = no_free_ptr(v->__incomplete_filename);
+	if (!IS_ERR(res))
+		audit_getname(res);
+	return res;
+}
+
 /**
  * check_acl - perform ACL permission checking
  * @idmap:	idmap of the mount the inode was found from

include/linux/fs.h

@@ -2516,6 +2516,17 @@ static inline struct filename *getname_maybe_null(const char __user *name, int f
 extern void putname(struct filename *name);
 DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T))
 
+struct delayed_filename {
+	struct filename *__incomplete_filename;	// don't touch
+};
+#define INIT_DELAYED_FILENAME(ptr) \
+	((void)(*(ptr) = (struct delayed_filename){}))
+int delayed_getname(struct delayed_filename *, const char __user *);
+int delayed_getname_uflags(struct delayed_filename *v, const char __user *, int);
+void dismiss_delayed_filename(struct delayed_filename *);
+int putname_to_delayed(struct delayed_filename *, struct filename *);
+struct filename *complete_getname(struct delayed_filename *);
+
 static inline struct filename *refname(struct filename *name)
 {
 	atomic_inc(&name->refcnt);
@@ -2527,6 +2538,7 @@ EXTEND_CLASS(filename, _kernel, getname_kernel(p), const char *p)
 EXTEND_CLASS(filename, _flags, getname_flags(p, f), const char __user *p, unsigned int f)
 EXTEND_CLASS(filename, _uflags, getname_uflags(p, f), const char __user *p, unsigned int f)
 EXTEND_CLASS(filename, _maybe_null, getname_maybe_null(p, f), const char __user *p, unsigned int f)
+EXTEND_CLASS(filename, _complete_delayed, complete_getname(p), struct delayed_filename *p)
 
 extern int finish_open(struct file *file, struct dentry *dentry,
 			int (*open)(struct inode *, struct file *));

io_uring/fs.c

@@ -19,38 +19,39 @@ struct io_rename {
 	struct file			*file;
 	int				old_dfd;
 	int				new_dfd;
-	struct filename			*oldpath;
-	struct filename			*newpath;
+	struct delayed_filename		oldpath;
+	struct delayed_filename		newpath;
 	int				flags;
 };
 
 struct io_unlink {
 	struct file			*file;
 	int				dfd;
 	int				flags;
-	struct filename			*filename;
+	struct delayed_filename		filename;
 };
 
 struct io_mkdir {
 	struct file			*file;
 	int				dfd;
 	umode_t				mode;
-	struct filename			*filename;
+	struct delayed_filename		filename;
 };
 
 struct io_link {
 	struct file			*file;
 	int				old_dfd;
 	int				new_dfd;
-	struct filename			*oldpath;
-	struct filename			*newpath;
+	struct delayed_filename		oldpath;
+	struct delayed_filename		newpath;
 	int				flags;
 };
 
 int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename);
 	const char __user *oldf, *newf;
+	int err;
 
 	if (sqe->buf_index || sqe->splice_fd_in)
 		return -EINVAL;
@@ -63,14 +64,14 @@ int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	ren->new_dfd = READ_ONCE(sqe->len);
 	ren->flags = READ_ONCE(sqe->rename_flags);
 
-	ren->oldpath = getname(oldf);
-	if (IS_ERR(ren->oldpath))
-		return PTR_ERR(ren->oldpath);
+	err = delayed_getname(&ren->oldpath, oldf);
+	if (unlikely(err))
+		return err;
 
-	ren->newpath = getname(newf);
-	if (IS_ERR(ren->newpath)) {
-		putname(ren->oldpath);
-		return PTR_ERR(ren->newpath);
+	err = delayed_getname(&ren->newpath, newf);
+	if (unlikely(err)) {
+		dismiss_delayed_filename(&ren->oldpath);
+		return err;
 	}
 
 	req->flags |= REQ_F_NEED_CLEANUP;
@@ -85,8 +86,9 @@ int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd,
-				ren->newpath, ren->flags);
+	ret = do_renameat2(ren->old_dfd, complete_getname(&ren->oldpath),
+			   ren->new_dfd, complete_getname(&ren->newpath),
+			   ren->flags);
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_req_set_res(req, ret, 0);
@@ -97,14 +99,15 @@ void io_renameat_cleanup(struct io_kiocb *req)
 {
 	struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename);
 
-	putname(ren->oldpath);
-	putname(ren->newpath);
+	dismiss_delayed_filename(&ren->oldpath);
+	dismiss_delayed_filename(&ren->newpath);
 }
 
 int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_unlink *un = io_kiocb_to_cmd(req, struct io_unlink);
 	const char __user *fname;
+	int err;
 
 	if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in)
 		return -EINVAL;
@@ -118,9 +121,9 @@ int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 
 	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
-	un->filename = getname(fname);
-	if (IS_ERR(un->filename))
-		return PTR_ERR(un->filename);
+	err = delayed_getname(&un->filename, fname);
+	if (unlikely(err))
+		return err;
 
 	req->flags |= REQ_F_NEED_CLEANUP;
 	req->flags |= REQ_F_FORCE_ASYNC;
@@ -135,9 +138,9 @@ int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
 	if (un->flags & AT_REMOVEDIR)
-		ret = do_rmdir(un->dfd, un->filename);
+		ret = do_rmdir(un->dfd, complete_getname(&un->filename));
 	else
-		ret = do_unlinkat(un->dfd, un->filename);
+		ret = do_unlinkat(un->dfd, complete_getname(&un->filename));
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_req_set_res(req, ret, 0);
@@ -148,13 +151,14 @@ void io_unlinkat_cleanup(struct io_kiocb *req)
 {
 	struct io_unlink *ul = io_kiocb_to_cmd(req, struct io_unlink);
 
-	putname(ul->filename);
+	dismiss_delayed_filename(&ul->filename);
 }
 
 int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_mkdir *mkd = io_kiocb_to_cmd(req, struct io_mkdir);
 	const char __user *fname;
+	int err;
 
 	if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
 		return -EINVAL;
@@ -165,9 +169,9 @@ int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	mkd->mode = READ_ONCE(sqe->len);
 
 	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
-	mkd->filename = getname(fname);
-	if (IS_ERR(mkd->filename))
-		return PTR_ERR(mkd->filename);
+	err = delayed_getname(&mkd->filename, fname);
+	if (unlikely(err))
+		return err;
 
 	req->flags |= REQ_F_NEED_CLEANUP;
 	req->flags |= REQ_F_FORCE_ASYNC;
@@ -181,7 +185,7 @@ int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
+	ret = do_mkdirat(mkd->dfd, complete_getname(&mkd->filename), mkd->mode);
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_req_set_res(req, ret, 0);
@@ -192,13 +196,14 @@ void io_mkdirat_cleanup(struct io_kiocb *req)
 {
 	struct io_mkdir *md = io_kiocb_to_cmd(req, struct io_mkdir);
 
-	putname(md->filename);
+	dismiss_delayed_filename(&md->filename);
 }
 
 int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_link *sl = io_kiocb_to_cmd(req, struct io_link);
 	const char __user *oldpath, *newpath;
+	int err;
 
 	if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
 		return -EINVAL;
@@ -209,14 +214,14 @@ int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 
-	sl->oldpath = getname(oldpath);
-	if (IS_ERR(sl->oldpath))
-		return PTR_ERR(sl->oldpath);
+	err = delayed_getname(&sl->oldpath, oldpath);
+	if (unlikely(err))
+		return err;
 
-	sl->newpath = getname(newpath);
-	if (IS_ERR(sl->newpath)) {
-		putname(sl->oldpath);
-		return PTR_ERR(sl->newpath);
+	err = delayed_getname(&sl->newpath, newpath);
+	if (unlikely(err)) {
+		dismiss_delayed_filename(&sl->oldpath);
+		return err;
 	}
 
 	req->flags |= REQ_F_NEED_CLEANUP;
@@ -231,7 +236,8 @@ int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
+	ret = do_symlinkat(complete_getname(&sl->oldpath), sl->new_dfd,
+			   complete_getname(&sl->newpath));
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_req_set_res(req, ret, 0);
@@ -242,6 +248,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link);
 	const char __user *oldf, *newf;
+	int err;
 
 	if (sqe->buf_index || sqe->splice_fd_in)
 		return -EINVAL;
@@ -254,14 +261,14 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 	lnk->flags = READ_ONCE(sqe->hardlink_flags);
 
-	lnk->oldpath = getname_uflags(oldf, lnk->flags);
-	if (IS_ERR(lnk->oldpath))
-		return PTR_ERR(lnk->oldpath);
+	err = delayed_getname_uflags(&lnk->oldpath, oldf, lnk->flags);
+	if (unlikely(err))
+		return err;
 
-	lnk->newpath = getname(newf);
-	if (IS_ERR(lnk->newpath)) {
-		putname(lnk->oldpath);
-		return PTR_ERR(lnk->newpath);
+	err = delayed_getname(&lnk->newpath, newf);
+	if (unlikely(err)) {
+		dismiss_delayed_filename(&lnk->oldpath);
+		return err;
 	}
 
 	req->flags |= REQ_F_NEED_CLEANUP;
@@ -276,8 +283,8 @@ int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
-				lnk->newpath, lnk->flags);
+	ret = do_linkat(lnk->old_dfd, complete_getname(&lnk->oldpath),
+			lnk->new_dfd, complete_getname(&lnk->newpath), lnk->flags);
 
 	req->flags &= ~REQ_F_NEED_CLEANUP;
 	io_req_set_res(req, ret, 0);
@@ -288,6 +295,6 @@ void io_link_cleanup(struct io_kiocb *req)
 {
 	struct io_link *sl = io_kiocb_to_cmd(req, struct io_link);
 
-	putname(sl->oldpath);
-	putname(sl->newpath);
+	dismiss_delayed_filename(&sl->oldpath);
+	dismiss_delayed_filename(&sl->newpath);
 }