io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT

Add support for getsockopt command (SOCKET_URING_OP_GETSOCKOPT), where
level is SOL_SOCKET. This is leveraging the sockptr_t infrastructure,
where a sockptr_t is either userspace or kernel space, and handled as
such.

Differently from the getsockopt(2), the optlen field is not a userspace
pointers. In getsockopt(2), userspace provides optlen pointer, which is
overwritten by the kernel.  In this implementation, userspace passes a
u32, and the new value is returned in cqe->res. I.e., optlen is not a
pointer.

Important to say that userspace needs to keep the pointer alive until
the CQE is completed.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
Link: https://lore.kernel.org/r/20231016134750.1381153-10-leitao@debian.orgSigned-off-by: Jens Axboe <axboe@kernel.dk>

include/uapi/linux/io_uring.h

@@ -43,6 +43,10 @@ struct io_uring_sqe {
 	union {
 		__u64	addr;	/* pointer to buffer or iovecs */
 		__u64	splice_off_in;
+		struct {
+			__u32	level;
+			__u32	optname;
+		};
 	};
 	__u32	len;		/* buffer size or number of iovecs */
 	union {
@@ -80,6 +84,7 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		__u32	optlen;
 		struct {
 			__u16	addr_len;
 			__u16	__pad3[1];
@@ -90,6 +95,7 @@ struct io_uring_sqe {
 			__u64	addr3;
 			__u64	__pad2[1];
 		};
+		__u64	optval;
 		/*
 		 * If the ring is initialized with IORING_SETUP_SQE128, then
 		 * this field is used for 80 bytes of arbitrary command data
@@ -736,6 +742,7 @@ struct io_uring_recvmsg_out {
 enum {
 	SOCKET_URING_OP_SIOCINQ		= 0,
 	SOCKET_URING_OP_SIOCOUTQ,
+	SOCKET_URING_OP_GETSOCKOPT,
 };
 
 #ifdef __cplusplus

io_uring/uring_cmd.c

@@ -214,6 +214,32 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
 
+static inline int io_uring_cmd_getsockopt(struct socket *sock,
+					  struct io_uring_cmd *cmd,
+					  unsigned int issue_flags)
+{
+	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
+	int optlen, optname, level, err;
+	void __user *optval;
+
+	level = READ_ONCE(cmd->sqe->level);
+	if (level != SOL_SOCKET)
+		return -EOPNOTSUPP;
+
+	optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
+	optname = READ_ONCE(cmd->sqe->optname);
+	optlen = READ_ONCE(cmd->sqe->optlen);
+
+	err = do_sock_getsockopt(sock, compat, level, optname,
+				 USER_SOCKPTR(optval),
+				 KERNEL_SOCKPTR(&optlen));
+	if (err)
+		return err;
+
+	/* On success, return optlen */
+	return optlen;
+}
+
 #if defined(CONFIG_NET)
 int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
@@ -236,6 +262,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 		if (ret)
 			return ret;
 		return arg;
+	case SOCKET_URING_OP_GETSOCKOPT:
+		return io_uring_cmd_getsockopt(sock, cmd, issue_flags);
 	default:
 		return -EOPNOTSUPP;
 	}