Merge tag 'for-6.7/io_uring-sockopt-2023-10-30' of git://git.kernel.dk/linux

Pull io_uring {get,set}sockopt support from Jens Axboe:
 "This adds support for using getsockopt and setsockopt via io_uring.

  The main use cases for this is to enable use of direct descriptors,
  rather than first instantiating a normal file descriptor, doing the
  option tweaking needed, then turning it into a direct descriptor. With
  this support, we can avoid needing a regular file descriptor
  completely.

  The net and bpf bits have been signed off on their side"

* tag 'for-6.7/io_uring-sockopt-2023-10-30' of git://git.kernel.dk/linux:
  selftests/bpf/sockopt: Add io_uring support
  io_uring/cmd: Introduce SOCKET_URING_OP_SETSOCKOPT
  io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT
  io_uring/cmd: return -EOPNOTSUPP if net is disabled
  selftests/net: Extract uring helpers to be reusable
  tools headers: Grab copy of io_uring.h
  io_uring/cmd: Pass compat mode in issue_flags
  net/socket: Break down __sys_getsockopt
  net/socket: Break down __sys_setsockopt
  bpf: Add sockptr support for setsockopt
  bpf: Add sockptr support for getsockopt

2 files changed, 67 insertions, 45 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 1d28e3e87970..fef349dd72fa 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2003,14 +2003,6 @@ lenout:
 	return 0;
 }
 
-int sock_getsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, int __user *optlen)
-{
-	return sk_getsockopt(sock->sk, level, optname,
-			     USER_SOCKPTR(optval),
-			     USER_SOCKPTR(optlen));
-}
-
 /*
  * Initialize an sk_lock.
  *
diff --git a/net/socket.c b/net/socket.c
index 5740475e084c..0d1c4e78fc7f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2279,33 +2279,23 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
 	return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags);
 }
 
-/*
- *	Set a socket option. Because we don't know the option lengths we have
- *	to pass the user mode parameter for the protocols to sort out.
- */
-int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
-		int optlen)
+int do_sock_setsockopt(struct socket *sock, bool compat, int level,
+		       int optname, sockptr_t optval, int optlen)
 {
-	sockptr_t optval = USER_SOCKPTR(user_optval);
 	const struct proto_ops *ops;
 	char *kernel_optval = NULL;
-	int err, fput_needed;
-	struct socket *sock;
+	int err;
 
 	if (optlen < 0)
 		return -EINVAL;
 
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
-	if (!sock)
-		return err;
-
 	err = security_socket_setsockopt(sock, level, optname);
 	if (err)
 		goto out_put;
 
-	if (!in_compat_syscall())
+	if (!compat)
 		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname,
-						     user_optval, &optlen,
+						     optval, &optlen,
 						     &kernel_optval);
 	if (err < 0)
 		goto out_put;
@@ -2326,6 +2316,27 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 					    optlen);
 	kfree(kernel_optval);
 out_put:
+	return err;
+}
+EXPORT_SYMBOL(do_sock_setsockopt);
+
+/* Set a socket option. Because we don't know the option lengths we have
+ * to pass the user mode parameter for the protocols to sort out.
+ */
+int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
+		     int optlen)
+{
+	sockptr_t optval = USER_SOCKPTR(user_optval);
+	bool compat = in_compat_syscall();
+	int err, fput_needed;
+	struct socket *sock;
+
+	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	if (!sock)
+		return err;
+
+	err = do_sock_setsockopt(sock, compat, level, optname, optval, optlen);
+
 	fput_light(sock->file, fput_needed);
 	return err;
 }
@@ -2339,43 +2350,62 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
 INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level,
 							 int optname));
 
-/*
- *	Get a socket option. Because we don't know the option lengths we have
- *	to pass a user mode parameter for the protocols to sort out.
- */
-int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
-		int __user *optlen)
+int do_sock_getsockopt(struct socket *sock, bool compat, int level,
+		       int optname, sockptr_t optval, sockptr_t optlen)
 {
 	int max_optlen __maybe_unused;
 	const struct proto_ops *ops;
-	int err, fput_needed;
-	struct socket *sock;
-
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
-	if (!sock)
-		return err;
+	int err;
 
 	err = security_socket_getsockopt(sock, level, optname);
 	if (err)
-		goto out_put;
+		return err;
 
-	if (!in_compat_syscall())
+	if (!compat)
 		max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
 
 	ops = READ_ONCE(sock->ops);
-	if (level == SOL_SOCKET)
-		err = sock_getsockopt(sock, level, optname, optval, optlen);
-	else if (unlikely(!ops->getsockopt))
+	if (level == SOL_SOCKET) {
+		err = sk_getsockopt(sock->sk, level, optname, optval, optlen);
+	} else if (unlikely(!ops->getsockopt)) {
 		err = -EOPNOTSUPP;
-	else
-		err = ops->getsockopt(sock, level, optname, optval,
-					    optlen);
+	} else {
+		if (WARN_ONCE(optval.is_kernel || optlen.is_kernel,
+			      "Invalid argument type"))
+			return -EOPNOTSUPP;
+
+		err = ops->getsockopt(sock, level, optname, optval.user,
+				      optlen.user);
+	}
 
-	if (!in_compat_syscall())
+	if (!compat)
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
 						     optval, optlen, max_optlen,
 						     err);
-out_put:
+
+	return err;
+}
+EXPORT_SYMBOL(do_sock_getsockopt);
+
+/*
+ *	Get a socket option. Because we don't know the option lengths we have
+ *	to pass a user mode parameter for the protocols to sort out.
+ */
+int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
+		int __user *optlen)
+{
+	int err, fput_needed;
+	struct socket *sock;
+	bool compat;
+
+	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	if (!sock)
+		return err;
+
+	compat = in_compat_syscall();
+	err = do_sock_getsockopt(sock, compat, level, optname,
+				 USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
+
 	fput_light(sock->file, fput_needed);
 	return err;
 }