On Mon, Jul 7, 2014 at 1:06 PM, Tejun Heo <tj@xxxxxxxxxx> wrote: > On Mon, Jul 07, 2014 at 11:19:25AM -0700, Dan Williams wrote: >> This change may cause the compiler to do a full divide where >> previously it could optimize to power-of-2 math with the visibility of >> the ATA_MAX_QUEUE constant. How about converting >> ap->host->queue_depth to ap->host->queue_depth_mask? ...then this >> becomes: >> >> tag = (i + ap->last_tag + 1) & max_queue_mask > > Given how inefficient the test_and_set bit is, I don't think a single > moduls matters. Plus, we don't even need modulus there. We can > simply use >= max_depth. True, sounds good. -- To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html