Add support for name_to_handle_at(2) to io_uring.

Like openat*(), this tries to do a non-blocking lookup first and resorts
to async lookup when that fails.

This uses sqe->addr for the path, ->addr2 for the file handle which is
filled in by the kernel, and ->addr3 for the mouint_id which is filled
in by the kernel.

Signed-off-by: Thomas Bertschinger <tahbertschinger@gmail.com>
---
 include/uapi/linux/io_uring.h |  2 ++
 io_uring/opdef.c              | 11 +++++++++
 io_uring/openclose.c          | 45 +++++++++++++++++++++++++++++++++++
 io_uring/openclose.h          |  5 ++++
 4 files changed, 63 insertions(+)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 6957dc539d83..a4aa83ad9527 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -74,6 +74,7 @@ struct io_uring_sqe {
 		__u32		install_fd_flags;
 		__u32		nop_flags;
 		__u32		pipe_flags;
+		__u32		name_to_handle_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -289,6 +290,7 @@ enum io_uring_op {
 	IORING_OP_READV_FIXED,
 	IORING_OP_WRITEV_FIXED,
 	IORING_OP_PIPE,
+	IORING_OP_NAME_TO_HANDLE_AT,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 9568785810d9..76306c9e0ecd 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -574,6 +574,14 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_pipe_prep,
 		.issue			= io_pipe,
 	},
+	[IORING_OP_NAME_TO_HANDLE_AT] = {
+#if defined(CONFIG_FHANDLE)
+		.prep			= io_name_to_handle_at_prep,
+		.issue			= io_name_to_handle_at,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -824,6 +832,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_PIPE] = {
 		.name			= "PIPE",
 	},
+	[IORING_OP_NAME_TO_HANDLE_AT] = {
+		.name			= "NAME_TO_HANDLE_AT",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index d70700e5cef8..884a66e56643 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -27,6 +27,15 @@ struct io_open {
 	unsigned long			nofile;
 };
 
+struct io_name_to_handle {
+	struct file			*file;
+	int				dfd;
+	int				flags;
+	struct file_handle __user	*ufh;
+	char __user			*path;
+	void __user			*mount_id;
+};
+
 struct io_close {
 	struct file			*file;
 	int				fd;
@@ -187,6 +196,42 @@ void io_open_cleanup(struct io_kiocb *req)
 		putname(open->filename);
 }
 
+#if defined(CONFIG_FHANDLE)
+int io_name_to_handle_at_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_name_to_handle *nh = io_kiocb_to_cmd(req, struct io_name_to_handle);
+
+	nh->dfd = READ_ONCE(sqe->fd);
+	nh->flags = READ_ONCE(sqe->name_to_handle_flags);
+	nh->path = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	nh->ufh = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	nh->mount_id = u64_to_user_ptr(READ_ONCE(sqe->addr3));
+
+	return 0;
+}
+
+int io_name_to_handle_at(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_name_to_handle *nh = io_kiocb_to_cmd(req, struct io_name_to_handle);
+	int lookup_flags = 0;
+	long ret;
+
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		lookup_flags = LOOKUP_CACHED;
+
+	ret = do_sys_name_to_handle_at(nh->dfd, nh->path, nh->ufh, nh->mount_id,
+				       nh->flags, lookup_flags);
+
+	if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
+		return -EAGAIN;
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+#endif /* CONFIG_FHANDLE */
+
 int __io_close_fixed(struct io_ring_ctx *ctx, unsigned int issue_flags,
 		     unsigned int offset)
 {
diff --git a/io_uring/openclose.h b/io_uring/openclose.h
index 4ca2a9935abc..2fc1c8d35d0b 100644
--- a/io_uring/openclose.h
+++ b/io_uring/openclose.h
@@ -10,6 +10,11 @@ void io_open_cleanup(struct io_kiocb *req);
 int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_openat2(struct io_kiocb *req, unsigned int issue_flags);
 
+#if defined(CONFIG_FHANDLE)
+int io_name_to_handle_at_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_name_to_handle_at(struct io_kiocb *req, unsigned int issue_flags);
+#endif /* CONFIG_FHANDLE */
+
 int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_close(struct io_kiocb *req, unsigned int issue_flags);
 
-- 
2.51.0