On 10-09-22, 11:17, Manivannan Sadhasivam wrote: > Currently, the dw-edma driver enables the runtime_pm for parent device > (chip->dev) and increments/decrements the refcount during alloc/free > chan resources callbacks. > > This leads to a problem when the eDMA driver has been probed, but the > channels were not used. This scenario can happen when the DW PCIe driver > probes eDMA driver successfully, but the PCI EPF driver decides not to > use eDMA channels and use iATU instead for PCI transfers. > > In this case, the underlying device would be runtime suspended due to > pm_runtime_enable() in dw_edma_probe() and the PCI EPF driver would have > no knowledge of it. > > Ideally, the eDMA driver should not be the one doing the runtime PM of > the parent device. The responsibility should instead belong to the client > drivers like PCI EPF. > > So let's remove the runtime PM support from eDMA driver. Applied, thanks -- ~Vinod
