[PATCHSET 0/2] io_uring: add sendmsg/recvmsg support

[PATCHSET 0/2] io_uring: add sendmsg/recvmsg support

[Jens Axboe]

This adds basic support for sendmsg(2) and recvmsg(2) through io_uring.
Similarly to how we handle file IO, we first attempt a non-blocking
call, and if that fails with -EAGAIN/-ENONBLOCK, we punt to an async
worker.

Pretty straightforward, and a test case can be found in the liburing
repository.

-- 
Jens Axboe

[PATCH 1/2] io_uring: add support for sendmsg()

[Jens Axboe]

This is done through IORING_OP_SENDMSG. There's a new sqe->msg_flags
for the flags argument, and the msghdr struct is passed in the
sqe->addr field.

We use MSG_DONTWAIT to force an inline fast path if sendmsg() doesn't
block, and punt to async execution if it would have.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 40 +++++++++++++++++++++++++++++++++++
 include/linux/socket.h        |  4 ++++
 include/uapi/linux/io_uring.h |  2 ++
 net/socket.c                  |  7 ++++++
 4 files changed, 53 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 9f0ef4956f87..5d4cd8c4132d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1390,6 +1390,43 @@ static int io_sync_file_range(struct io_kiocb *req,
 	return 0;
 }
 
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	struct socket *sock;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
+	sock = sock_from_file(req->file, &ret);
+	if (sock) {
+		struct user_msghdr __user *msg;
+		unsigned flags;
+
+		flags = READ_ONCE(sqe->msg_flags);
+		if (flags & MSG_DONTWAIT)
+			req->flags |= REQ_F_NOWAIT;
+		else if (force_nonblock)
+			flags |= MSG_DONTWAIT;
+
+		msg = (struct user_msghdr __user *) (unsigned long)
+			READ_ONCE(sqe->addr);
+
+		ret = __sys_sendmsg_sock(sock, msg, flags);
+		if (force_nonblock && ret == -EAGAIN)
+			return ret;
+	}
+
+	io_cqring_add_event(req->ctx, sqe->user_data, ret);
+	io_put_req(req);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
 static void io_poll_remove_one(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = &req->poll;
@@ -1675,6 +1712,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_SYNC_FILE_RANGE:
 		ret = io_sync_file_range(req, s->sqe, force_nonblock);
 		break;
+	case IORING_OP_SENDMSG:
+		ret = io_sendmsg(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b57cd8bf96e2..9d770ef3ced5 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -12,6 +12,7 @@
 
 struct pid;
 struct cred;
+struct socket;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -374,6 +375,9 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg,
 extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
 			  unsigned int vlen, unsigned int flags,
 			  bool forbid_cmsg_compat);
+extern long __sys_sendmsg_sock(struct socket *sock,
+			       struct user_msghdr __user *msg,
+			       unsigned int flags);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 10b7c45f6d57..d74742d6269f 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -27,6 +27,7 @@ struct io_uring_sqe {
 		__u32		fsync_flags;
 		__u16		poll_events;
 		__u32		sync_range_flags;
+		__u32		msg_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
@@ -58,6 +59,7 @@ struct io_uring_sqe {
 #define IORING_OP_POLL_ADD	6
 #define IORING_OP_POLL_REMOVE	7
 #define IORING_OP_SYNC_FILE_RANGE	8
+#define IORING_OP_SENDMSG	9
 
 /*
  * sqe->fsync_flags
diff --git a/net/socket.c b/net/socket.c
index bffec466b4f1..b9536940255e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2313,6 +2313,13 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 /*
  *	BSD sendmsg interface
  */
+long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0);
+}
 
 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
-- 
2.17.1

[PATCH 2/2] io_uring: add support for recvmsg()

[Jens Axboe]

This is done through IORING_OP_RECVMSG. This opcode uses the same
sqe->msg_flags that IORING_OP_SENDMSG added, and we pass in the
msghdr struct in the sqe->addr field as well.

We use MSG_DONTWAIT to force an inline fast path if recvmsg() doesn't
block, and punt to async execution if it would have.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 31 +++++++++++++++++++++++++++----
 include/linux/socket.h        |  3 +++
 include/uapi/linux/io_uring.h |  1 +
 net/socket.c                  |  8 ++++++++
 4 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5d4cd8c4132d..8d86e31b0762 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1390,10 +1390,12 @@ static int io_sync_file_range(struct io_kiocb *req,
 	return 0;
 }
 
-static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-		      bool force_nonblock)
-{
 #if defined(CONFIG_NET)
+static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+			   bool force_nonblock,
+		   long (*fn)(struct socket *, struct user_msghdr __user *,
+				unsigned int))
+{
 	struct socket *sock;
 	int ret;
 
@@ -1414,7 +1416,7 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		msg = (struct user_msghdr __user *) (unsigned long)
 			READ_ONCE(sqe->addr);
 
-		ret = __sys_sendmsg_sock(sock, msg, flags);
+		ret = fn(sock, msg, flags);
 		if (force_nonblock && ret == -EAGAIN)
 			return ret;
 	}
@@ -1422,6 +1424,24 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	io_cqring_add_event(req->ctx, sqe->user_data, ret);
 	io_put_req(req);
 	return 0;
+}
+#endif
+
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock);
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock);
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -1715,6 +1735,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_SENDMSG:
 		ret = io_sendmsg(req, s->sqe, force_nonblock);
 		break;
+	case IORING_OP_RECVMSG:
+		ret = io_recvmsg(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 9d770ef3ced5..97523818cb14 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -378,6 +378,9 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
 extern long __sys_sendmsg_sock(struct socket *sock,
 			       struct user_msghdr __user *msg,
 			       unsigned int flags);
+extern long __sys_recvmsg_sock(struct socket *sock,
+			       struct user_msghdr __user *msg,
+			       unsigned int flags);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index d74742d6269f..1e1652f25cc1 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -60,6 +60,7 @@ struct io_uring_sqe {
 #define IORING_OP_POLL_REMOVE	7
 #define IORING_OP_SYNC_FILE_RANGE	8
 #define IORING_OP_SENDMSG	9
+#define IORING_OP_RECVMSG	10
 
 /*
  * sqe->fsync_flags
diff --git a/net/socket.c b/net/socket.c
index b9536940255e..98354cc18840 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2494,6 +2494,14 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
  *	BSD recvmsg interface
  */
 
+long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0);
+}
+
 long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
 {
-- 
2.17.1