Re: [PATCH 7/9] ARM: OMAP2+: Prepare for irqs.h removal

[Tony Lindgren <tony@atomide.com>]

* Mohammed, Afzal <afzal@ti.com> [120904 01:47]:
> Hi Tony,
> 
> On Fri, Aug 31, 2012 at 06:22:37, Tony Lindgren wrote:
> > As the interrupts should only be defined in the platform_data, and
> > eventually coming from device tree, there's no need to define them
> > in header files.
> > 
> > Let's remove the hardcoded references to irqs.h and fix up the includes
> > so we don't rely on headers included in irqs.h. While at it, sort
> > the includes the standard way.
> 
> >  arch/arm/mach-omap2/gpmc.c                         |   11 +++++---
> 
> > diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
> 
> >  /* GPMC register offsets */
> >  #define GPMC_REVISION		0x00
> >  #define GPMC_SYSCONFIG		0x10
> > @@ -846,16 +849,16 @@ static int __init gpmc_init(void)
> >  			l = OMAP2420_GPMC_BASE;
> >  		else
> >  			l = OMAP34XX_GPMC_BASE;
> > -		gpmc_irq = INT_34XX_GPMC_IRQ;
> > +		gpmc_irq = 20;
> >  	} else if (cpu_is_omap34xx()) {
> >  		ck = "gpmc_fck";
> >  		l = OMAP34XX_GPMC_BASE;
> > -		gpmc_irq = INT_34XX_GPMC_IRQ;
> > +		gpmc_irq = 20;
> >  	} else if (cpu_is_omap44xx() || soc_is_omap54xx()) {
> >  		/* Base address and irq number are same for OMAP4/5 */
> >  		ck = "gpmc_ck";
> >  		l = OMAP44XX_GPMC_BASE;
> > -		gpmc_irq = OMAP44XX_IRQ_GPMC;
> > +		gpmc_irq = 20 + OMAP44XX_IRQ_GIC_START;
> 
> I have a suggestion to avoid above hardcoded patching on gpmc.c.
> With driver conversion series it again would have to be patched.
> 
> 
> I have made a basic gpmc driver conversion, which is expected to
> be non-controversial. This was done over your devel-gpmc branch.
> It is working fine, has only 3 patches
> 
> 1. Add hwmod entry
> 2. Adapt to hwmod
> 3. Basic driver conversion
> 
> Here the basic driver gets resources and clk in driver probe
> using con-id "fck", it has no platform data as of now
> 
> It is available
> @git://gitorious.org/x0148406-public/linux-kernel.git gpmc-simple-drv
 
Great, please post that. But let's get this cleanup out of the way
first. It's OK if we have to go back and forth a bit if it means
we can avoid dependencies between the patches as this is already
all over the place.
 
> Originally this was made on top of my series,
> "OMAP-GPMC: generic time calc, prepare for driver"
> It was modified so that it can be applied to your devel-gpmc branch.
> 
> *I am not sending the patches now to avoid confusion by way of having
> too many patch series*
> 
> In case you like this, let me know, I will post.

Yes please post the patches rebased on testing-cleanup branch that I
just pushed. That branch is not immutable yet though as we're waiting
to hear from Arnd regrading the first patch in the branch.
 
> As I am proceeding with Paul's suggestion on hwmod reset,
> I hope Paul can take the first one.

Let's first nail down the cleanup changes though..

Tony