On 19-08-22, 14:10, Manivannan Sadhasivam wrote: > On Thu, May 12, 2022 at 02:06:12PM +0530, 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. > > > > Cc: Serge Semin <fancer.lancer@xxxxxxxxx> > > Cc: Frank Li <Frank.Li@xxxxxxx> > > Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@xxxxxxxxxx> > > Looks like this one missed 6.0. Vinod, can you please merge this now? This fails for me, can you pls rebase and resend -- ~Vinod
