ccw_io_helper neglected to reset vcdev->err after a new channel
program had been successfully started, resulting in stale errors
delivered after one I/O failed. Reset the error after a new
channel program has been successfully started with no old I/O
pending.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
do {
spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags);
ret = ccw_device_start(vcdev->cdev, ccw, intparm, 0, 0);
- if (!ret)
+ if (!ret) {
+ if (!vcdev->curr_io)
+ vcdev->err = 0;
vcdev->curr_io |= flag;
+ }
spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags);
cpu_relax();
} while (ret == -EBUSY);