* Ran Shalit <ranshalit@xxxxxxxxx> [150803 07:03]: > > I am using GPMC with smsc911x controller. > If I understand you correctly, I can overcome this, but asking the > hardware not get into inactive state. Correct. Probably the automatic way to block deeper idle states here with GPMC would be to implement DMA transfers for smsc911x. Then the hardware would not enter deeper idle states when a DMA transfer is in progress. Of course there may be still other tuning needed too. > I actully need that the code won't get into inactive state (I don't > think that anyelse is inactive, except the core - this is C3 state). > The problem with this approach is that I'm not sure I can determine > when to decide "turn cpuidle off" and when to decide "turn cpuidle > on". Right, and the hardware can take care of it if implemented. Using pm_runtime_put_autosuspend() in the device driver gives you the timeouts to idle things, but you'd still have to call something to keep the system active when the smsc911x device driver is PM runtime enabled. > I thought that if there is a way to ask the governer (in tickless > kernel, it is menu governer), to wait for a longer time, before > deciding to get into sleep. > I think that if it waits longer time, it will see that there are tasks > to do (small packets in iperf test), and will not enter sleep state. > Is that possible ? Is there any parameter in governer which control this ? Sure I guess you just need to figure out what the official interface to block deeper idle states is. Regards, Tony -- To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
