In commit
f3ce4d5 ("usb: musb: core: call dma_controller_destroy() in the err path")
I erroneously assumed that the dma controller is not removed in the
error patch. This was wrong because it happens later via musb_free().
That means the original commit can be reverted because it is wrong or we
do this, so it is more obvious.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Felipe Balbi <balbi@ti.com>
free_irq(musb->nIrq, musb);
}
cancel_work_sync(&musb->irq_work);
- if (musb->dma_controller)
- dma_controller_destroy(musb->dma_controller);
musb_host_free(musb);
}
musb_exit_debugfs(musb);
musb_shutdown(pdev);
+ if (musb->dma_controller)
+ dma_controller_destroy(musb->dma_controller);
+
musb_free(musb);
device_init_wakeup(dev, 0);
return 0;