Re: [PATCH 1/3] i2c: slave: rework the slave API

["Uwe Kleine-König" <u.kleine-koenig@pengutronix.de>]

Moin Wolfram,

On Fri, Mar 20, 2015 at 08:15:04AM +0100, Wolfram Sang wrote:
> On Thu, Mar 19, 2015 at 09:17:51PM +0100, Uwe Kleine-König wrote:
> > Hello Wolfram,
> > 
> > On Thu, Mar 12, 2015 at 01:42:01PM +0100, Wolfram Sang wrote:
> > > From: Wolfram Sang <wsa+renesas@sang-engineering.com>
> > > 
> > > After more discussion, brave users, and additional datasheet evaluation,
> > > some API updates for the new I2C slave framework became imminent. The
> > > slave events now get some easier to understand naming. Also, the event
> > > handling has been simplified to only send one event per interrupt.
> > what is an interrupt here? An event where the bus driver needs feedback
> > from the backend?
> 
> More the other way around: when the bus driver needs to notify the
> backend. I wasn't 100% sure about the word 'interrupt', but then decided
> a HW slave support without interrupts would be so rare and adventurous
> that it is okay to use the term :)
Yeah, I agree on HW slave support without interrupts is hardly possible.
But I imagine that controllers differ in which situations they can issue
an interrupt so talking about them for generic code feels strange to me
because $flexiblecontrolerwithvariousirqs doesn't need to send more
events than $bareminimumcontroler.

Best regards
Uwe


-- 
Pengutronix e.K.                           | Uwe Kleine-König            |
Industrial Linux Solutions                 | http://www.pengutronix.de/  |