a0188eb6e7
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@gmail.com> Cc: Frank Li <Frank.Li@nxp.com> Reviewed-by: Serge Semin <fancer.lancer@gmail.com> Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> Link: https://lore.kernel.org/r/20220910054700.12205-1-manivannan.sadhasivam@linaro.org Signed-off-by: Vinod Koul <vkoul@kernel.org> |
||
|---|---|---|
| .. | ||
| dw-edma-core.c | ||
| dw-edma-core.h | ||
| dw-edma-pcie.c | ||
| dw-edma-v0-core.c | ||
| dw-edma-v0-core.h | ||
| dw-edma-v0-debugfs.c | ||
| dw-edma-v0-debugfs.h | ||
| dw-edma-v0-regs.h | ||
| Kconfig | ||
| Makefile | ||