Re: [PATCH] dmaengine: dw-edma: Remove runtime PM support

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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



[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [Linux for Sparc]     [IETF Annouce]     [Security]     [Bugtraq]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux