io_uring/msg_ring: add support for sending a sync message

Normally MSG_RING requires both a source and a destination ring. But
some users don't always have a ring avilable to send a message from, yet
they still need to notify a target ring.

Add support for using io_uring_register(2) without having a source ring,
using a file descriptor of -1 for that. Internally those are called
blind registration opcodes. Implement IORING_REGISTER_SEND_MSG_RING as a
blind opcode, which simply takes an sqe that the application can put on
the stack and use the normal liburing helpers to initialize it. Then the
app can call:

io_uring_register(-1, IORING_REGISTER_SEND_MSG_RING, &sqe, 1);

and get the same behavior in terms of the target, where a CQE is posted
with the details given in the sqe.

For now this takes a single sqe pointer argument, and hence arg must
be set to that, and nr_args must be 1. Could easily be extended to take
an array of sqes, but for now let's keep it simple.

Link: https://lore.kernel.org/r/20240924115932.116167-3-axboe@kernel.dk
Signed-off-by: Jens Axboe <axboe@kernel.dk>

include/uapi/linux/io_uring.h

@@ -612,6 +612,9 @@ enum io_uring_register_op {
 	/* clone registered buffers from source ring to current ring */
 	IORING_REGISTER_CLONE_BUFFERS		= 30,
 
+	/* send MSG_RING without having a ring */
+	IORING_REGISTER_SEND_MSG_RING		= 31,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 

io_uring/msg_ring.c

@@ -331,6 +331,35 @@ done:
 	return IOU_OK;
 }
 
+int io_uring_sync_msg_ring(struct io_uring_sqe *sqe)
+{
+	struct io_msg io_msg = { };
+	struct fd f;
+	int ret;
+
+	ret = __io_msg_ring_prep(&io_msg, sqe);
+	if (unlikely(ret))
+		return ret;
+
+	/*
+	 * Only data sending supported, not IORING_MSG_SEND_FD as that one
+	 * doesn't make sense without a source ring to send files from.
+	 */
+	if (io_msg.cmd != IORING_MSG_DATA)
+		return -EINVAL;
+
+	ret = -EBADF;
+	f = fdget(sqe->fd);
+	if (fd_file(f)) {
+		ret = -EBADFD;
+		if (io_is_uring_fops(fd_file(f)))
+			ret = __io_msg_ring_data(fd_file(f)->private_data,
+						 &io_msg, IO_URING_F_UNLOCKED);
+		fdput(f);
+	}
+	return ret;
+}
+
 void io_msg_cache_free(const void *entry)
 {
 	struct io_kiocb *req = (struct io_kiocb *) entry;

io_uring/msg_ring.h

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+int io_uring_sync_msg_ring(struct io_uring_sqe *sqe);
 int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags);
 void io_msg_ring_cleanup(struct io_kiocb *req);

io_uring/register.c

@@ -28,6 +28,7 @@
 #include "kbuf.h"
 #include "napi.h"
 #include "eventfd.h"
+#include "msg_ring.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -588,6 +589,32 @@ struct file *io_uring_register_get_file(unsigned int fd, bool registered)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+/*
+ * "blind" registration opcodes are ones where there's no ring given, and
+ * hence the source fd must be -1.
+ */
+static int io_uring_register_blind(unsigned int opcode, void __user *arg,
+				   unsigned int nr_args)
+{
+	switch (opcode) {
+	case IORING_REGISTER_SEND_MSG_RING: {
+		struct io_uring_sqe sqe;
+
+		if (!arg || nr_args != 1)
+			return -EINVAL;
+		if (copy_from_user(&sqe, arg, sizeof(sqe)))
+			return -EFAULT;
+		/* no flags supported */
+		if (sqe.flags)
+			return -EINVAL;
+		if (sqe.opcode == IORING_OP_MSG_RING)
+			return io_uring_sync_msg_ring(&sqe);
+		}
+	}
+
+	return -EINVAL;
+}
+
 SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 		void __user *, arg, unsigned int, nr_args)
 {
@@ -602,6 +629,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 	if (opcode >= IORING_REGISTER_LAST)
 		return -EINVAL;
 
+	if (fd == -1)
+		return io_uring_register_blind(opcode, arg, nr_args);
+
 	file = io_uring_register_get_file(fd, use_registered_ring);
 	if (IS_ERR(file))
 		return PTR_ERR(file);