On Mon, Dec 08, 2014 at 06:37:27PM +0530, Vinod Koul wrote: > I actually like the split model, you can also prepare txn ahead of time and > submit them when needed. Actually, you can't - that's not permitted. I have email(s) from Dan explicitly stating that it is permitted for a driver to take a spinlock in their prepare callback, and release it when the descriptor is submitted. Several DMA engine drivers (particularly those in for async_tx) do exactly that. The reason that submit is separate from prepare is to allow DMA engine users to set a callback - if it weren't for that, there wouldn't be a submit step, prepare would have done everything. -- FTTC broadband for 0.8mile line: currently at 9.5Mbps down 400kbps up according to speedtest.net. -- To unsubscribe from this list: send the line "unsubscribe dmaengine" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
