[v4,08/10] io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT

Commit Message

Breno Leitao Sept. 4, 2023, 4:25 p.m. UTC

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 <[e-mail]>
---
 include/uapi/linux/io_uring.h |  7 +++++++
 io_uring/uring_cmd.c          | 28 ++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

Comments

Gabriel Krisman Bertazi Sept. 5, 2023, 12:24 p.m. UTC | #1

Breno Leitao <[e-mail]> writes:

> 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 <[e-mail]>

IMO, this looks much cleaner with most of the bpf and socket logic under
net/.

Reviewed-by: Gabriel Krisman Bertazi <[e-mail]>

Thanks!

Patch

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8e61f8b7c2ce..29efa02a4dcb 100644
--- a/include/uapi/linux/io_uring.h
+++ b/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 {
@@ -79,6 +83,7 @@  struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		__u32	optlen;
 		struct {
 			__u16	addr_len;
 			__u16	__pad3[1];
@@ -89,6 +94,7 @@  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
@@ -734,6 +740,7 @@  struct io_uring_recvmsg_out {
 enum {
 	SOCKET_URING_OP_SIOCINQ		= 0,
 	SOCKET_URING_OP_SIOCOUTQ,
+	SOCKET_URING_OP_GETSOCKOPT,
 };
 
 #ifdef __cplusplus
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 6a91e1af7d05..c373e05ba9ce 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -167,6 +167,32 @@  int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
 
+INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level,
+							 int optname));
+static inline int io_uring_cmd_getsockopt(struct socket *sock,
+					  struct io_uring_cmd *cmd,
+					  unsigned int issue_flags)
+{
+	void __user *optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
+	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
+	int optlen = READ_ONCE(cmd->sqe->optlen);
+	int optname = READ_ONCE(cmd->sqe->optname);
+	int level = READ_ONCE(cmd->sqe->level);
+	int err;
+
+	if (level != SOL_SOCKET)
+		return -EOPNOTSUPP;
+
+	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)
 {
@@ -189,6 +215,8 @@  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;
 	}