io_uring: call req_set_fail_links() on short send[msg]()/recv[msg]() with MSG_WAITALL

[ Upstream commit 0031275d119efe16711cd93519b595e6f9b4b330 ]

Without that it's not safe to use them in a linked combination with
others.

Now combinations like IORING_OP_SENDMSG followed by IORING_OP_SPLICE
should be possible.

We already handle short reads and writes for the following opcodes:

- IORING_OP_READV
- IORING_OP_READ_FIXED
- IORING_OP_READ
- IORING_OP_WRITEV
- IORING_OP_WRITE_FIXED
- IORING_OP_WRITE
- IORING_OP_SPLICE
- IORING_OP_TEE

Now we have it for these as well:

- IORING_OP_SENDMSG
- IORING_OP_SEND
- IORING_OP_RECVMSG
- IORING_OP_RECV

For IORING_OP_RECVMSG we also check for the MSG_TRUNC and MSG_CTRUNC
flags in order to call req_set_fail_links().

There might be applications arround depending on the behavior
that even short send[msg]()/recv[msg]() retuns continue an
IOSQE_IO_LINK chain.

It's very unlikely that such applications pass in MSG_WAITALL,
which is only defined in 'man 2 recvmsg', but not in 'man 2 sendmsg'.

It's expected that the low level sock_sendmsg() call just ignores
MSG_WAITALL, as MSG_ZEROCOPY is also ignored without explicitly set
SO_ZEROCOPY.

We also expect the caller to know about the implicit truncation to
MAX_RW_COUNT, which we don't detect.

cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/c4e1a4cc0d905314f4d5dc567e65a7b09621aab3.1615908477.git.metze@samba.org
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 20 insertions, 4 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index fe2dfdab0acd..4ccf99cb8cdc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4401,6 +4401,7 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock,
 	struct io_async_msghdr iomsg, *kmsg;
 	struct socket *sock;
 	unsigned flags;
+	int min_ret = 0;
 	int ret;
 
 	sock = sock_from_file(req->file, &ret);
@@ -4427,6 +4428,9 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock,
 	else if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
 	ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
 	if (force_nonblock && ret == -EAGAIN)
 		return io_setup_async_msg(req, kmsg);
@@ -4436,7 +4440,7 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock,
 	if (kmsg->iov != kmsg->fast_iov)
 		kfree(kmsg->iov);
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
+	if (ret < min_ret)
 		req_set_fail_links(req);
 	__io_req_complete(req, ret, 0, cs);
 	return 0;
@@ -4450,6 +4454,7 @@ static int io_send(struct io_kiocb *req, bool force_nonblock,
 	struct iovec iov;
 	struct socket *sock;
 	unsigned flags;
+	int min_ret = 0;
 	int ret;
 
 	sock = sock_from_file(req->file, &ret);
@@ -4471,6 +4476,9 @@ static int io_send(struct io_kiocb *req, bool force_nonblock,
 	else if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
 	msg.msg_flags = flags;
 	ret = sock_sendmsg(sock, &msg);
 	if (force_nonblock && ret == -EAGAIN)
@@ -4478,7 +4486,7 @@ static int io_send(struct io_kiocb *req, bool force_nonblock,
 	if (ret == -ERESTARTSYS)
 		ret = -EINTR;
 
-	if (ret < 0)
+	if (ret < min_ret)
 		req_set_fail_links(req);
 	__io_req_complete(req, ret, 0, cs);
 	return 0;
@@ -4630,6 +4638,7 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock,
 	struct socket *sock;
 	struct io_buffer *kbuf;
 	unsigned flags;
+	int min_ret = 0;
 	int ret, cflags = 0;
 
 	sock = sock_from_file(req->file, &ret);
@@ -4665,6 +4674,9 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock,
 	else if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
 	ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
 					kmsg->uaddr, flags);
 	if (force_nonblock && ret == -EAGAIN)
@@ -4677,7 +4689,7 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock,
 	if (kmsg->iov != kmsg->fast_iov)
 		kfree(kmsg->iov);
 	req->flags &= ~REQ_F_NEED_CLEANUP;
-	if (ret < 0)
+	if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
 		req_set_fail_links(req);
 	__io_req_complete(req, ret, cflags, cs);
 	return 0;
@@ -4693,6 +4705,7 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock,
 	struct socket *sock;
 	struct iovec iov;
 	unsigned flags;
+	int min_ret = 0;
 	int ret, cflags = 0;
 
 	sock = sock_from_file(req->file, &ret);
@@ -4723,6 +4736,9 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock,
 	else if (force_nonblock)
 		flags |= MSG_DONTWAIT;
 
+	if (flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
 	ret = sock_recvmsg(sock, &msg, flags);
 	if (force_nonblock && ret == -EAGAIN)
 		return -EAGAIN;
@@ -4731,7 +4747,7 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock,
 out_free:
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		cflags = io_put_recv_kbuf(req);
-	if (ret < 0)
+	if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
 		req_set_fail_links(req);
 	__io_req_complete(req, ret, cflags, cs);
 	return 0;