Merge tag 'for-6.11/io_uring-20240714' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "Here are the io_uring updates queued up for 6.11.

  Nothing major this time around, various minor improvements and
  cleanups/fixes. This contains:

   - Add bind/listen opcodes. Main motivation is to support direct
     descriptors, to avoid needing a regular fd just for doing these two
     operations (Gabriel)

   - Probe fixes (Gabriel)

   - Treat io-wq work flags as atomics. Not fixing a real issue, but may
     as well and it silences a KCSAN warning (me)

   - Cleanup of rsrc __set_current_state() usage (me)

   - Add 64-bit for {m,f}advise operations (me)

   - Improve performance of data ring messages (me)

   - Fix for ring message overflow posting (Pavel)

   - Fix for freezer interaction with TWA_NOTIFY_SIGNAL. Not strictly an
     io_uring thing, but since TWA_NOTIFY_SIGNAL was originally added
     for faster task_work signaling for io_uring, bundling it with this
     pull (Pavel)

   - Add Pavel as a co-maintainer

   - Various cleanups (me, Thorsten)"

* tag 'for-6.11/io_uring-20240714' of git://git.kernel.dk/linux: (28 commits)
  io_uring/net: check socket is valid in io_bind()/io_listen()
  kernel: rerun task_work while freezing in get_signal()
  io_uring/io-wq: limit retrying worker initialisation
  io_uring/napi: Remove unnecessary s64 cast
  io_uring/net: cleanup io_recv_finish() bundle handling
  io_uring/msg_ring: fix overflow posting
  MAINTAINERS: change Pavel Begunkov from io_uring reviewer to maintainer
  io_uring/msg_ring: use kmem_cache_free() to free request
  io_uring/msg_ring: check for dead submitter task
  io_uring/msg_ring: add an alloc cache for io_kiocb entries
  io_uring/msg_ring: improve handling of target CQE posting
  io_uring: add io_add_aux_cqe() helper
  io_uring: add remote task_work execution helper
  io_uring/msg_ring: tighten requirement for remote posting
  io_uring: Allocate only necessary memory in io_probe
  io_uring: Fix probe of disabled operations
  io_uring: Introduce IORING_OP_LISTEN
  io_uring: Introduce IORING_OP_BIND
  net: Split a __sys_listen helper for io_uring
  net: Split a __sys_bind helper for io_uring
  ...

1 files changed, 84 insertions, 10 deletions

diff --git a/io_uring/net.c b/io_uring/net.c
index cf742bdd2a93..7b75da2e7826 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -51,6 +51,16 @@ struct io_connect {
 	bool				seen_econnaborted;
 };
 
+struct io_bind {
+	struct file			*file;
+	int				addr_len;
+};
+
+struct io_listen {
+	struct file			*file;
+	int				backlog;
+};
+
 struct io_sr_msg {
 	struct file			*file;
 	union {
@@ -817,20 +827,20 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 				  bool mshot_finished, unsigned issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
-	unsigned int cflags;
-
-	if (sr->flags & IORING_RECVSEND_BUNDLE)
-		cflags = io_put_kbufs(req, io_bundle_nbufs(kmsg, *ret),
-				      issue_flags);
-	else
-		cflags = io_put_kbuf(req, issue_flags);
+	unsigned int cflags = 0;
 
 	if (kmsg->msg.msg_inq > 0)
 		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
 
-	/* bundle with no more immediate buffers, we're done */
-	if (sr->flags & IORING_RECVSEND_BUNDLE && req->flags & REQ_F_BL_EMPTY)
-		goto finish;
+	if (sr->flags & IORING_RECVSEND_BUNDLE) {
+		cflags |= io_put_kbufs(req, io_bundle_nbufs(kmsg, *ret),
+				      issue_flags);
+		/* bundle with no more immediate buffers, we're done */
+		if (req->flags & REQ_F_BL_EMPTY)
+			goto finish;
+	} else {
+		cflags |= io_put_kbuf(req, issue_flags);
+	}
 
 	/*
 	 * Fill CQE for this receive and see if we should keep trying to
@@ -1717,6 +1727,70 @@ out:
 	return IOU_OK;
 }
 
+int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind);
+	struct sockaddr __user *uaddr;
+	struct io_async_msghdr *io;
+
+	if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
+		return -EINVAL;
+
+	uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	bind->addr_len =  READ_ONCE(sqe->addr2);
+
+	io = io_msg_alloc_async(req);
+	if (unlikely(!io))
+		return -ENOMEM;
+	return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr);
+}
+
+int io_bind(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind);
+	struct io_async_msghdr *io = req->async_data;
+	struct socket *sock;
+	int ret;
+
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	ret = __sys_bind_socket(sock, &io->addr, bind->addr_len);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return 0;
+}
+
+int io_listen_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_listen *listen = io_kiocb_to_cmd(req, struct io_listen);
+
+	if (sqe->addr || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in || sqe->addr2)
+		return -EINVAL;
+
+	listen->backlog = READ_ONCE(sqe->len);
+	return 0;
+}
+
+int io_listen(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_listen *listen = io_kiocb_to_cmd(req, struct io_listen);
+	struct socket *sock;
+	int ret;
+
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	ret = __sys_listen_socket(sock, listen->backlog);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return 0;
+}
+
 void io_netmsg_cache_free(const void *entry)
 {
 	struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry;