Re: [PATCH 1/3] i2c: slave: rework the slave API
From: Wolfram Sang
Date: Fri Mar 20 2015 - 04:18:02 EST
On Fri, Mar 20, 2015 at 08:44:47AM +0100, Uwe Kleine-KÃnig wrote:
> On Fri, Mar 20, 2015 at 08:31:35AM +0100, Wolfram Sang wrote:
> > > > > > 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.
> > Do you have a better word at hand? "...to send one event per event"? :)
> Also, the event handling has been simplified to only need a
> single call to the slave callback when an action by the backend
> is required.
Bought. Thank you.
Description: Digital signature