On Tue, Feb 5, 2013 at 5:47 PM, Mark Brown <broonie@xxxxxxxxxxxxxxxxxxxxxxxxxxx> wrote: > On Tue, Feb 05, 2013 at 05:21:48PM +0100, Linus Walleij wrote: > >> For IRQ mode, use the completion callback to push each cookie >> to NAPI, and thus let the IRQ drive the traffic. > > The whole purpose of NAPI is to avoid taking interrupts for completion > of transfers. Anything that generates interrupts when NAPI is in > polling mode is defeating the point. So what I was trying to get across is that when you're in polling mode you do not set DMA_PREP_INTERRUPT on your transfers, just throw the obtained struct dma_async_tx_descriptor on some list and then when polling use dma_async_is_tx_complete() on the channel and the cookie inside the descriptor. I was trying to describe that you can move from IRQ mode to polling mode and back again by selectively choosing to set/not set the DMA_PREP_INTERRUPT flag. If polling is all you want you never set it. Then there is the fact that the transfer needs to have been flagged complete and it is indeed something that needs to be set in some bytes somewhere. By something. But it doesn't have to be an interrupt from the DMA controller. In such cases we use dma_async_is_tx_complete() with channel and cookies as parameter. This will call down into the driver chan->device->device_tx_status() and there we can actually poll the hardware to see if the transfer happens to be complete, and if it is flag it complete. Which is likely what we want. No interrupts, only function calls as far as I can see. (I bet Russell will poke a hole in my reasoning, but it's worth a try.) Yours, Linus Walleij -- To unsubscribe from this list: send the line "unsubscribe linux-doc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html