[PATCH] io_uring: fix sporadic -EFAULT from IORING_OP_RECMSG

[Jens Axboe <axboe@xxxxxxxxx>]

If we have to punt the recvmsg to async context, we copy all the
context.  But since the iovec used can be either on-stack (if small) or
dynamically allocated, if it's on-stack, then we need to ensure we reset
the iov pointer. If we don't, then we're reusing old stack data, and
that can lead to -EFAULTs if things get overwritten.

Ensure we retain the right pointers for the iov, and free it as well if
we end up having to go beyond UIO_FASTIOV number of vectors.

Fixes: 03b1230ca12a ("io_uring: ensure async punted sendmsg/recvmsg requests copy data")
Reported-by: 李通洲 <carter.li@xxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>

---


diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2fff83a3878f..4424c5d7a3a1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2041,6 +2041,7 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		      struct io_kiocb **nxt, bool force_nonblock)
 {
 #if defined(CONFIG_NET)
+	struct io_async_msghdr *kmsg = NULL;
 	struct socket *sock;
 	int ret;
 
@@ -2051,7 +2052,6 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (sock) {
 		struct io_async_ctx io, *copy;
 		struct sockaddr_storage addr;
-		struct msghdr *kmsg;
 		unsigned flags;
 
 		flags = READ_ONCE(sqe->msg_flags);
@@ -2061,17 +2061,21 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			flags |= MSG_DONTWAIT;
 
 		if (req->io) {
-			kmsg = &req->io->msg.msg;
-			kmsg->msg_name = &addr;
+			kmsg = &req->io->msg;
+			kmsg->msg.msg_name = &addr;
+			/* if iov is set, it's allocated already */
+			if (!req->io->msg.iov)
+				req->io->msg.iov = req->io->msg.fast_iov;
+			kmsg->msg.msg_iter.iov = req->io->msg.iov;
 		} else {
-			kmsg = &io.msg.msg;
-			kmsg->msg_name = &addr;
+			kmsg = &io.msg;
+			kmsg->msg.msg_name = &addr;
 			ret = io_sendmsg_prep(req, &io);
 			if (ret)
 				goto out;
 		}
 
-		ret = __sys_sendmsg_sock(sock, kmsg, flags);
+		ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
 		if (force_nonblock && ret == -EAGAIN) {
 			copy = kmalloc(sizeof(*copy), GFP_KERNEL);
 			if (!copy) {
@@ -2089,6 +2093,8 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	}
 
 out:
+	if (kmsg && kmsg->iov != kmsg->fast_iov)
+		kfree(kmsg->iov);
 	io_cqring_add_event(req, ret);
 	if (ret < 0)
 		req_set_fail_links(req);
@@ -2120,6 +2126,7 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		      struct io_kiocb **nxt, bool force_nonblock)
 {
 #if defined(CONFIG_NET)
+	struct io_async_msghdr *kmsg = NULL;
 	struct socket *sock;
 	int ret;
 
@@ -2131,7 +2138,6 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		struct user_msghdr __user *msg;
 		struct io_async_ctx io, *copy;
 		struct sockaddr_storage addr;
-		struct msghdr *kmsg;
 		unsigned flags;
 
 		flags = READ_ONCE(sqe->msg_flags);
@@ -2143,17 +2149,21 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		msg = (struct user_msghdr __user *) (unsigned long)
 			READ_ONCE(sqe->addr);
 		if (req->io) {
-			kmsg = &req->io->msg.msg;
-			kmsg->msg_name = &addr;
+			kmsg = &req->io->msg;
+			kmsg->msg.msg_name = &addr;
+			/* if iov is set, it's allocated already */
+			if (!req->io->msg.iov)
+				req->io->msg.iov = req->io->msg.fast_iov;
+			kmsg->msg.msg_iter.iov = req->io->msg.iov;
 		} else {
-			kmsg = &io.msg.msg;
-			kmsg->msg_name = &addr;
+			kmsg = &io.msg;
+			kmsg->msg.msg_name = &addr;
 			ret = io_recvmsg_prep(req, &io);
 			if (ret)
 				goto out;
 		}
 
-		ret = __sys_recvmsg_sock(sock, kmsg, msg, io.msg.uaddr, flags);
+		ret = __sys_recvmsg_sock(sock, &kmsg->msg, msg, kmsg->uaddr, flags);
 		if (force_nonblock && ret == -EAGAIN) {
 			copy = kmalloc(sizeof(*copy), GFP_KERNEL);
 			if (!copy) {
@@ -2171,6 +2181,8 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	}
 
 out:
+	if (kmsg && kmsg->iov != kmsg->fast_iov)
+		kfree(kmsg->iov);
 	io_cqring_add_event(req, ret);
 	if (ret < 0)
 		req_set_fail_links(req);

-- 
Jens Axboe