There is one race case in vduse_dev_msg_sync and vduse_dev_read_iter:

vduse_dev_read_iter():
    lock(msg_lock);
    dequeue_msg(send_list);
    unlock(msg_lock);
vduse_dev_msg_sync():
    wait_timeout() finish
    lock(msg_lock);
    check msg->complete is false
        list_del(msg);   <- double list_del() crash!

To fix this case, we shall ensure vduse_msg is on send_list or recv_list
outside the msg_lock critical section.

Fixes: c8a6153b6c59 ("vduse: Introduce VDUSE - vDPA Device in Userspace")
Cc: [email protected]
Signed-off-by: Zhang Tianci <[email protected]>
Reviewed-by: Xie Yongji <[email protected]>
---
 drivers/vdpa/vdpa_user/vduse_dev.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c 
b/drivers/vdpa/vdpa_user/vduse_dev.c
index b37f18a0ce6fd..1e274688bba32 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -331,6 +331,7 @@ static ssize_t vduse_dev_read_iter(struct kiocb *iocb, 
struct iov_iter *to)
        struct file *file = iocb->ki_filp;
        struct vduse_dev *dev = file->private_data;
        struct vduse_dev_msg *msg;
+       struct vduse_dev_request req;
        int size = sizeof(struct vduse_dev_request);
        ssize_t ret;
 
@@ -345,7 +346,7 @@ static ssize_t vduse_dev_read_iter(struct kiocb *iocb, 
struct iov_iter *to)
 
                ret = -EAGAIN;
                if (file->f_flags & O_NONBLOCK)
-                       goto unlock;
+                       break;
 
                spin_unlock(&dev->msg_lock);
                ret = wait_event_interruptible_exclusive(dev->waitq,
@@ -355,17 +356,30 @@ static ssize_t vduse_dev_read_iter(struct kiocb *iocb, 
struct iov_iter *to)
 
                spin_lock(&dev->msg_lock);
        }
+       if (!msg) {
+               spin_unlock(&dev->msg_lock);
+               return ret;
+       }
+
+       memcpy(&req, &msg->req, sizeof(req));
+       /*
+        * We must ensure vduse_msg is on send_list or recv_list before unlock
+        * dev->msg_lock. Because vduse_dev_msg_sync() may be timeout when we
+        * copy data to userspace, and will call list_del() for this msg.
+        */
+       vduse_enqueue_msg(&dev->recv_list, msg);
        spin_unlock(&dev->msg_lock);
-       ret = copy_to_iter(&msg->req, size, to);
-       spin_lock(&dev->msg_lock);
+
+       ret = copy_to_iter(&req, size, to);
        if (ret != size) {
+               spin_lock(&dev->msg_lock);
+               /* Roll back: move msg back to send_list if still pending. */
+               msg = vduse_find_msg(&dev->recv_list, req.request_id);
+               if (msg)
+                       vduse_enqueue_msg_head(&dev->send_list, msg);
+               spin_unlock(&dev->msg_lock);
                ret = -EFAULT;
-               vduse_enqueue_msg_head(&dev->send_list, msg);
-               goto unlock;
        }
-       vduse_enqueue_msg(&dev->recv_list, msg);
-unlock:
-       spin_unlock(&dev->msg_lock);
 
        return ret;
 }
-- 
2.39.5


Reply via email to