Re: [PATCH 0/2] nand: Remove BUG abuse

[Boris Brezillon <boris.brezillon@free-electrons.com>]

On Sat, 2 Apr 2016 12:37:06 -0300
Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> wrote:

> On 4 April 2016 at 12:20, Boris Brezillon
> <boris.brezillon@free-electrons.com> wrote:
> > On Sat, 2 Apr 2016 15:55:24 +0200
> > Boris Brezillon <boris.brezillon@free-electrons.com> wrote:
> >
> >> On Fri,  1 Apr 2016 18:29:24 -0300
> >> Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> wrote:
> >>
> >> > There's no reason to BUG() when parameters are being
> >> > validated. Drivers can get things wrong, and it's much nicer
> >> > to just throw a noisy warn and fail gracefully, than calling
> >> > BUG() and throwing the whole system down the drain.
> >>
> >> I'm fine with this change as long as all callers are checking
> >> nand_scan_tail() return value.
> >
> > Actually, the s3c2410 driver is not checking nand_scan_tail() return
> > value. Could you send a v2 addressing that?
> >
> 
> Hmm, I don't see how that relates to this patch.
> As far as I can see, it's two completely independent issues.
> 
> Or am I missing something here?

Well, you're removing BUG() calls and are returning an error instead, so
if existing nand_scan_tail() callers don't check the return status you
may hide an existing bug...

I know it's unlikely to happen, but I'd still prefer to have all
nand_scan_tail() callers to check the return value before removing
those calls to BUG().

-- 
Boris Brezillon, Free Electrons
Embedded Linux and Kernel engineering
http://free-electrons.com