On 6/8/2020 4:28 AM, Mark Brown wrote: > On Mon, Jun 08, 2020 at 12:11:11PM +0100, Robin Murphy wrote: > >> Again, 2 cycles. The overhead of a static key alone is at least 50% of that. >> And that's not even considering whether the change in code layout caused by >> doubling up the IRQ handler might affect I-cache or branch predictor >> behaviour, where a single miss stands to more than wipe out any perceived >> saving. And all in code that has at least one obvious inefficiency left on >> the table either way. > >> This thread truly epitomises Knuth's "premature optimisation" quote... ;) > > In fairness the main reason this driver is so heavily tuned already (and > has lead to some really nice improvements in the core) is that there are > a number of users hitting 100% CPU utilization driving SPI devices on > some of the older RPi hardware, IIRC around IIO type applications > mostly. I do tend to agree that this particular optimization is a bit > marginal but there has been a lot of effort put into this. OK, so this has been dropped for spi/for-next right? How do we move from there? -- Florian
